X86 Regressions: Update stats due to introduction of TSO
diff --git a/tests/long/00.gzip/ref/x86/linux/o3-timing/config.ini b/tests/long/00.gzip/ref/x86/linux/o3-timing/config.ini
index 42f7aa6..6e971eb 100644
--- a/tests/long/00.gzip/ref/x86/linux/o3-timing/config.ini
+++ b/tests/long/00.gzip/ref/x86/linux/o3-timing/config.ini
@@ -80,6 +80,7 @@
 max_insts_any_thread=0
 max_loads_all_threads=0
 max_loads_any_thread=0
+needsTSO=true
 numIQEntries=64
 numPhysFloatRegs=256
 numPhysIntRegs=256
@@ -502,7 +503,7 @@
 env=
 errout=cerr
 euid=100
-executable=/dist/m5/cpu2000/binaries/x86/linux/gzip
+executable=/scratch/nilay/GEM5/dist/m5/cpu2000/binaries/x86/linux/gzip
 gid=100
 input=cin
 max_stack_size=67108864
diff --git a/tests/long/00.gzip/ref/x86/linux/o3-timing/simout b/tests/long/00.gzip/ref/x86/linux/o3-timing/simout
index 48ae315..bff73f5 100755
--- a/tests/long/00.gzip/ref/x86/linux/o3-timing/simout
+++ b/tests/long/00.gzip/ref/x86/linux/o3-timing/simout
@@ -1,1037 +1,15 @@
+Redirecting stdout to build/X86_SE/tests/opt/long/00.gzip/x86/linux/o3-timing/simout
+Redirecting stderr to build/X86_SE/tests/opt/long/00.gzip/x86/linux/o3-timing/simerr
 gem5 Simulator System.  http://gem5.org
 gem5 is copyrighted software; use the --copyright option for details.
 
-gem5 compiled Jan 23 2012 04:08:34
-gem5 started Jan 23 2012 06:28:24
-gem5 executing on zizzer
+gem5 compiled Jan 28 2012 12:11:40
+gem5 started Jan 28 2012 12:12:43
+gem5 executing on ribera.cs.wisc.edu
 command line: build/X86_SE/gem5.opt -d build/X86_SE/tests/opt/long/00.gzip/x86/linux/o3-timing -re tests/run.py build/X86_SE/tests/opt/long/00.gzip/x86/linux/o3-timing
 Global frequency set at 1000000000000 ticks per second
 info: Entering event queue @ 0.  Starting simulation...
 spec_init
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
 Loading Input Data
 Duplicating 262144 bytes
 Duplicating 524288 bytes
@@ -1039,9 +17,11 @@
 Compressing Input Data, level 1
 Compressed data 108074 bytes in length
 Uncompressing Data
+info: Increasing stack size by one page.
 Uncompressed data 1048576 bytes in length
 Uncompressed data compared correctly
 Compressing Input Data, level 3
+info: Increasing stack size by one page.
 Compressed data 97831 bytes in length
 Uncompressing Data
 Uncompressed data 1048576 bytes in length
@@ -1062,4 +42,4 @@
 Uncompressed data 1048576 bytes in length
 Uncompressed data compared correctly
 Tested 1MB buffer: OK!
-Exiting @ tick 586294224000 because target called exit()
+Exiting @ tick 588785308000 because target called exit()
diff --git a/tests/long/00.gzip/ref/x86/linux/o3-timing/stats.txt b/tests/long/00.gzip/ref/x86/linux/o3-timing/stats.txt
index 802bd6f..f7c59f0 100644
--- a/tests/long/00.gzip/ref/x86/linux/o3-timing/stats.txt
+++ b/tests/long/00.gzip/ref/x86/linux/o3-timing/stats.txt
@@ -1,155 +1,155 @@
 
 ---------- Begin Simulation Statistics ----------
-sim_seconds                                  0.586294                       # Number of seconds simulated
-sim_ticks                                586294224000                       # Number of ticks simulated
-final_tick                               586294224000                       # Number of ticks from beginning of simulation (restored from checkpoints and never reset)
+sim_seconds                                  0.588785                       # Number of seconds simulated
+sim_ticks                                588785308000                       # Number of ticks simulated
+final_tick                               588785308000                       # Number of ticks from beginning of simulation (restored from checkpoints and never reset)
 sim_freq                                 1000000000000                       # Frequency of simulated ticks
-host_inst_rate                                 145094                       # Simulator instruction rate (inst/s)
-host_tick_rate                               52462700                       # Simulator tick rate (ticks/s)
-host_mem_usage                                 215548                       # Number of bytes of host memory used
-host_seconds                                 11175.48                       # Real time elapsed on the host
+host_inst_rate                                 112730                       # Simulator instruction rate (inst/s)
+host_tick_rate                               40933847                       # Simulator tick rate (ticks/s)
+host_mem_usage                                 244824                       # Number of bytes of host memory used
+host_seconds                                 14383.83                       # Real time elapsed on the host
 sim_insts                                  1621493982                       # Number of instructions simulated
-system.physmem.bytes_read                     5880640                       # Number of bytes read from this memory
-system.physmem.bytes_inst_read                  56960                       # Number of instructions bytes read from this memory
-system.physmem.bytes_written                  3744192                       # Number of bytes written to this memory
-system.physmem.num_reads                        91885                       # Number of read requests responded to by this memory
-system.physmem.num_writes                       58503                       # Number of write requests responded to by this memory
+system.physmem.bytes_read                     5878272                       # Number of bytes read from this memory
+system.physmem.bytes_inst_read                  57216                       # Number of instructions bytes read from this memory
+system.physmem.bytes_written                  3742528                       # Number of bytes written to this memory
+system.physmem.num_reads                        91848                       # Number of read requests responded to by this memory
+system.physmem.num_writes                       58477                       # Number of write requests responded to by this memory
 system.physmem.num_other                            0                       # Number of other requests responded to by this memory
-system.physmem.bw_read                       10030186                       # Total read bandwidth from this memory (bytes/s)
-system.physmem.bw_inst_read                     97153                       # Instruction read bandwidth from this memory (bytes/s)
-system.physmem.bw_write                       6386200                       # Write bandwidth from this memory (bytes/s)
-system.physmem.bw_total                      16416386                       # Total bandwidth to/from this memory (bytes/s)
+system.physmem.bw_read                        9983727                       # Total read bandwidth from this memory (bytes/s)
+system.physmem.bw_inst_read                     97176                       # Instruction read bandwidth from this memory (bytes/s)
+system.physmem.bw_write                       6356354                       # Write bandwidth from this memory (bytes/s)
+system.physmem.bw_total                      16340082                       # Total bandwidth to/from this memory (bytes/s)
 system.cpu.workload.num_syscalls                   48                       # Number of system calls
-system.cpu.numCycles                       1172588449                       # number of cpu cycles simulated
+system.cpu.numCycles                       1177570617                       # number of cpu cycles simulated
 system.cpu.numWorkItemsStarted                      0                       # number of work items this cpu started
 system.cpu.numWorkItemsCompleted                    0                       # number of work items this cpu completed
-system.cpu.BPredUnit.lookups                142448982                       # Number of BP lookups
-system.cpu.BPredUnit.condPredicted          142448982                       # Number of conditional branches predicted
-system.cpu.BPredUnit.condIncorrect            7804844                       # Number of conditional branches incorrect
-system.cpu.BPredUnit.BTBLookups             134509888                       # Number of BTB lookups
-system.cpu.BPredUnit.BTBHits                133615988                       # Number of BTB hits
+system.cpu.BPredUnit.lookups                141882222                       # Number of BP lookups
+system.cpu.BPredUnit.condPredicted          141882222                       # Number of conditional branches predicted
+system.cpu.BPredUnit.condIncorrect            7459322                       # Number of conditional branches incorrect
+system.cpu.BPredUnit.BTBLookups             135523268                       # Number of BTB lookups
+system.cpu.BPredUnit.BTBHits                134664780                       # Number of BTB hits
 system.cpu.BPredUnit.BTBCorrect                     0                       # Number of correct BTB predictions (this stat may not work properly.
 system.cpu.BPredUnit.usedRAS                        0                       # Number of times the RAS was used to get a target.
 system.cpu.BPredUnit.RASInCorrect                   0                       # Number of incorrect RAS predictions.
-system.cpu.fetch.icacheStallCycles          143149229                       # Number of cycles fetch is stalled on an Icache miss
-system.cpu.fetch.Insts                     1143761054                       # Number of instructions fetch has processed
-system.cpu.fetch.Branches                   142448982                       # Number of branches that fetch encountered
-system.cpu.fetch.predictedBranches          133615988                       # Number of branches that fetch has predicted taken
-system.cpu.fetch.Cycles                     330199440                       # Number of cycles fetch has run and was not squashing or blocked
-system.cpu.fetch.SquashCycles                57554993                       # Number of cycles fetch has spent squashing
-system.cpu.fetch.BlockedCycles              649541012                       # Number of cycles fetch has spent blocked
-system.cpu.fetch.MiscStallCycles                   52                       # Number of cycles fetch has spent waiting on interrupts, or bad addresses, or out of MSHRs
-system.cpu.fetch.PendingTrapStallCycles           331                       # Number of stall cycles due to pending traps
-system.cpu.fetch.CacheLines                 137027209                       # Number of cache lines fetched
-system.cpu.fetch.IcacheSquashes                996742                       # Number of outstanding Icache misses that were squashed
-system.cpu.fetch.rateDist::samples         1172439660                       # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::mean              1.784546                       # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::stdev             3.109877                       # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.icacheStallCycles          141519405                       # Number of cycles fetch is stalled on an Icache miss
+system.cpu.fetch.Insts                     1135188232                       # Number of instructions fetch has processed
+system.cpu.fetch.Branches                   141882222                       # Number of branches that fetch encountered
+system.cpu.fetch.predictedBranches          134664780                       # Number of branches that fetch has predicted taken
+system.cpu.fetch.Cycles                     328423216                       # Number of cycles fetch has run and was not squashing or blocked
+system.cpu.fetch.SquashCycles                56273795                       # Number of cycles fetch has spent squashing
+system.cpu.fetch.BlockedCycles              658902879                       # Number of cycles fetch has spent blocked
+system.cpu.fetch.MiscStallCycles                   48                       # Number of cycles fetch has spent waiting on interrupts, or bad addresses, or out of MSHRs
+system.cpu.fetch.PendingTrapStallCycles           302                       # Number of stall cycles due to pending traps
+system.cpu.fetch.CacheLines                 135738609                       # Number of cache lines fetched
+system.cpu.fetch.IcacheSquashes                998788                       # Number of outstanding Icache misses that were squashed
+system.cpu.fetch.rateDist::samples         1177479353                       # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.rateDist::mean              1.766783                       # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.rateDist::stdev             3.096310                       # Number of instructions fetched each cycle (Total)
 system.cpu.fetch.rateDist::underflows               0      0.00%      0.00% # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::0                845244296     72.09%     72.09% # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::1                 17110181      1.46%     73.55% # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::2                 18043141      1.54%     75.09% # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::3                 16408368      1.40%     76.49% # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::4                 23340182      1.99%     78.48% # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::5                 16629602      1.42%     79.90% # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::6                 21855680      1.86%     81.76% # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::7                 28257046      2.41%     84.17% # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::8                185551164     15.83%    100.00% # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.rateDist::0                852058955     72.36%     72.36% # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.rateDist::1                 15948065      1.35%     73.72% # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.rateDist::2                 17931063      1.52%     75.24% # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.rateDist::3                 17495755      1.49%     76.73% # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.rateDist::4                 23352779      1.98%     78.71% # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.rateDist::5                 16626553      1.41%     80.12% # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.rateDist::6                 22402886      1.90%     82.02% # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.rateDist::7                 28214099      2.40%     84.42% # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.rateDist::8                183449198     15.58%    100.00% # Number of instructions fetched each cycle (Total)
 system.cpu.fetch.rateDist::overflows                0      0.00%    100.00% # Number of instructions fetched each cycle (Total)
 system.cpu.fetch.rateDist::min_value                0                       # Number of instructions fetched each cycle (Total)
 system.cpu.fetch.rateDist::max_value                8                       # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::total           1172439660                       # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.branchRate                  0.121483                       # Number of branch fetches per cycle
-system.cpu.fetch.rate                        0.975416                       # Number of inst fetches per cycle
-system.cpu.decode.IdleCycles                240695556                       # Number of cycles decode is idle
-system.cpu.decode.BlockedCycles             558473143                       # Number of cycles decode is blocked
-system.cpu.decode.RunCycles                 228947071                       # Number of cycles decode is running
-system.cpu.decode.UnblockCycles              94774294                       # Number of cycles decode is unblocking
-system.cpu.decode.SquashCycles               49549596                       # Number of cycles decode is squashing
-system.cpu.decode.DecodedInsts             2070409567                       # Number of instructions handled by decode
-system.cpu.rename.SquashCycles               49549596                       # Number of cycles rename is squashing
-system.cpu.rename.IdleCycles                290323713                       # Number of cycles rename is idle
-system.cpu.rename.BlockCycles               132525789                       # Number of cycles rename is blocking
-system.cpu.rename.serializeStallCycles           3175                       # count of cycles rename stalled for serializing inst
-system.cpu.rename.RunCycles                 256725592                       # Number of cycles rename is running
-system.cpu.rename.UnblockCycles             443311795                       # Number of cycles rename is unblocking
-system.cpu.rename.RenamedInsts             2043122328                       # Number of instructions processed by rename
-system.cpu.rename.ROBFullEvents                  2634                       # Number of times rename has blocked due to ROB full
-system.cpu.rename.IQFullEvents              278313629                       # Number of times rename has blocked due to IQ full
-system.cpu.rename.LSQFullEvents             129499394                       # Number of times rename has blocked due to LSQ full
-system.cpu.rename.RenamedOperands          2031527322                       # Number of destination operands rename has renamed
-system.cpu.rename.RenameLookups            4954653611                       # Number of register rename lookups that rename has made
-system.cpu.rename.int_rename_lookups       4954649391                       # Number of integer rename lookups
-system.cpu.rename.fp_rename_lookups              4220                       # Number of floating rename lookups
+system.cpu.fetch.rateDist::total           1177479353                       # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.branchRate                  0.120487                       # Number of branch fetches per cycle
+system.cpu.fetch.rate                        0.964009                       # Number of inst fetches per cycle
+system.cpu.decode.IdleCycles                241266448                       # Number of cycles decode is idle
+system.cpu.decode.BlockedCycles             565597424                       # Number of cycles decode is blocked
+system.cpu.decode.RunCycles                 225300633                       # Number of cycles decode is running
+system.cpu.decode.UnblockCycles              96681345                       # Number of cycles decode is unblocking
+system.cpu.decode.SquashCycles               48633503                       # Number of cycles decode is squashing
+system.cpu.decode.DecodedInsts             2058834896                       # Number of instructions handled by decode
+system.cpu.rename.SquashCycles               48633503                       # Number of cycles rename is squashing
+system.cpu.rename.IdleCycles                289994325                       # Number of cycles rename is idle
+system.cpu.rename.BlockCycles               136667782                       # Number of cycles rename is blocking
+system.cpu.rename.serializeStallCycles           3607                       # count of cycles rename stalled for serializing inst
+system.cpu.rename.RunCycles                 255841310                       # Number of cycles rename is running
+system.cpu.rename.UnblockCycles             446338826                       # Number of cycles rename is unblocking
+system.cpu.rename.RenamedInsts             2031094400                       # Number of instructions processed by rename
+system.cpu.rename.ROBFullEvents                   199                       # Number of times rename has blocked due to ROB full
+system.cpu.rename.IQFullEvents              278357951                       # Number of times rename has blocked due to IQ full
+system.cpu.rename.LSQFullEvents             133112570                       # Number of times rename has blocked due to LSQ full
+system.cpu.rename.RenamedOperands          2019296537                       # Number of destination operands rename has renamed
+system.cpu.rename.RenameLookups            4928551600                       # Number of register rename lookups that rename has made
+system.cpu.rename.int_rename_lookups       4928548640                       # Number of integer rename lookups
+system.cpu.rename.fp_rename_lookups              2960                       # Number of floating rename lookups
 system.cpu.rename.CommittedMaps            1617994650                       # Number of HB maps that are committed
-system.cpu.rename.UndoneMaps                413532672                       # Number of HB maps that are undone due to squashing
-system.cpu.rename.serializingInsts                 91                       # count of serializing insts renamed
-system.cpu.rename.tempSerializingInsts             91                       # count of temporary serializing insts renamed
-system.cpu.rename.skidInsts                 793190427                       # count of insts added to the skid buffer
-system.cpu.memDep0.insertedLoads            519090632                       # Number of loads inserted to the mem dependence unit.
-system.cpu.memDep0.insertedStores           226808407                       # Number of stores inserted to the mem dependence unit.
-system.cpu.memDep0.conflictingLoads         354951645                       # Number of conflicting loads.
-system.cpu.memDep0.conflictingStores        148937436                       # Number of conflicting stores.
-system.cpu.iq.iqInstsAdded                 1986583516                       # Number of instructions added to the IQ (excludes non-spec)
-system.cpu.iq.iqNonSpecInstsAdded                 218                       # Number of non-speculative instructions added to the IQ
-system.cpu.iq.iqInstsIssued                1781630004                       # Number of instructions issued
-system.cpu.iq.iqSquashedInstsIssued            180825                       # Number of squashed instructions issued
-system.cpu.iq.iqSquashedInstsExamined       364939190                       # Number of squashed instructions iterated over during squash; mainly for profiling
-system.cpu.iq.iqSquashedOperandsExamined    670712329                       # Number of squashed operands that are examined and possibly removed from graph
-system.cpu.iq.iqSquashedNonSpecRemoved            168                       # Number of squashed non-spec instructions that were removed
-system.cpu.iq.issued_per_cycle::samples    1172439660                       # Number of insts issued each cycle
-system.cpu.iq.issued_per_cycle::mean         1.519592                       # Number of insts issued each cycle
-system.cpu.iq.issued_per_cycle::stdev        1.333662                       # Number of insts issued each cycle
+system.cpu.rename.UndoneMaps                401301887                       # Number of HB maps that are undone due to squashing
+system.cpu.rename.serializingInsts                 93                       # count of serializing insts renamed
+system.cpu.rename.tempSerializingInsts             93                       # count of temporary serializing insts renamed
+system.cpu.rename.skidInsts                 797995614                       # count of insts added to the skid buffer
+system.cpu.memDep0.insertedLoads            517349896                       # Number of loads inserted to the mem dependence unit.
+system.cpu.memDep0.insertedStores           226176362                       # Number of stores inserted to the mem dependence unit.
+system.cpu.memDep0.conflictingLoads         355062669                       # Number of conflicting loads.
+system.cpu.memDep0.conflictingStores        148977960                       # Number of conflicting stores.
+system.cpu.iq.iqInstsAdded                 1979799927                       # Number of instructions added to the IQ (excludes non-spec)
+system.cpu.iq.iqNonSpecInstsAdded                 215                       # Number of non-speculative instructions added to the IQ
+system.cpu.iq.iqInstsIssued                1779311117                       # Number of instructions issued
+system.cpu.iq.iqSquashedInstsIssued            175082                       # Number of squashed instructions issued
+system.cpu.iq.iqSquashedInstsExamined       358154503                       # Number of squashed instructions iterated over during squash; mainly for profiling
+system.cpu.iq.iqSquashedOperandsExamined    654941515                       # Number of squashed operands that are examined and possibly removed from graph
+system.cpu.iq.iqSquashedNonSpecRemoved            165                       # Number of squashed non-spec instructions that were removed
+system.cpu.iq.issued_per_cycle::samples    1177479353                       # Number of insts issued each cycle
+system.cpu.iq.issued_per_cycle::mean         1.511119                       # Number of insts issued each cycle
+system.cpu.iq.issued_per_cycle::stdev        1.319645                       # Number of insts issued each cycle
 system.cpu.iq.issued_per_cycle::underflows            0      0.00%      0.00% # Number of insts issued each cycle
-system.cpu.iq.issued_per_cycle::0           271921709     23.19%     23.19% # Number of insts issued each cycle
-system.cpu.iq.issued_per_cycle::1           416937499     35.56%     58.75% # Number of insts issued each cycle
-system.cpu.iq.issued_per_cycle::2           234725234     20.02%     78.77% # Number of insts issued each cycle
-system.cpu.iq.issued_per_cycle::3           156776493     13.37%     92.15% # Number of insts issued each cycle
-system.cpu.iq.issued_per_cycle::4            54385701      4.64%     96.79% # Number of insts issued each cycle
-system.cpu.iq.issued_per_cycle::5            21203892      1.81%     98.59% # Number of insts issued each cycle
-system.cpu.iq.issued_per_cycle::6            14378982      1.23%     99.82% # Number of insts issued each cycle
-system.cpu.iq.issued_per_cycle::7             1804798      0.15%     99.97% # Number of insts issued each cycle
-system.cpu.iq.issued_per_cycle::8              305352      0.03%    100.00% # Number of insts issued each cycle
+system.cpu.iq.issued_per_cycle::0           271443176     23.05%     23.05% # Number of insts issued each cycle
+system.cpu.iq.issued_per_cycle::1           420511572     35.71%     58.77% # Number of insts issued each cycle
+system.cpu.iq.issued_per_cycle::2           239784716     20.36%     79.13% # Number of insts issued each cycle
+system.cpu.iq.issued_per_cycle::3           159545639     13.55%     92.68% # Number of insts issued each cycle
+system.cpu.iq.issued_per_cycle::4            48751983      4.14%     96.82% # Number of insts issued each cycle
+system.cpu.iq.issued_per_cycle::5            21481111      1.82%     98.64% # Number of insts issued each cycle
+system.cpu.iq.issued_per_cycle::6            13897994      1.18%     99.82% # Number of insts issued each cycle
+system.cpu.iq.issued_per_cycle::7             1713551      0.15%     99.97% # Number of insts issued each cycle
+system.cpu.iq.issued_per_cycle::8              349611      0.03%    100.00% # Number of insts issued each cycle
 system.cpu.iq.issued_per_cycle::overflows            0      0.00%    100.00% # Number of insts issued each cycle
 system.cpu.iq.issued_per_cycle::min_value            0                       # Number of insts issued each cycle
 system.cpu.iq.issued_per_cycle::max_value            8                       # Number of insts issued each cycle
-system.cpu.iq.issued_per_cycle::total      1172439660                       # Number of insts issued each cycle
+system.cpu.iq.issued_per_cycle::total      1177479353                       # Number of insts issued each cycle
 system.cpu.iq.fu_full::No_OpClass                   0      0.00%      0.00% # attempts to use FU when none available
-system.cpu.iq.fu_full::IntAlu                  179772      6.92%      6.92% # attempts to use FU when none available
-system.cpu.iq.fu_full::IntMult                      0      0.00%      6.92% # attempts to use FU when none available
-system.cpu.iq.fu_full::IntDiv                       0      0.00%      6.92% # attempts to use FU when none available
-system.cpu.iq.fu_full::FloatAdd                     0      0.00%      6.92% # attempts to use FU when none available
-system.cpu.iq.fu_full::FloatCmp                     0      0.00%      6.92% # attempts to use FU when none available
-system.cpu.iq.fu_full::FloatCvt                     0      0.00%      6.92% # attempts to use FU when none available
-system.cpu.iq.fu_full::FloatMult                    0      0.00%      6.92% # attempts to use FU when none available
-system.cpu.iq.fu_full::FloatDiv                     0      0.00%      6.92% # attempts to use FU when none available
-system.cpu.iq.fu_full::FloatSqrt                    0      0.00%      6.92% # attempts to use FU when none available
-system.cpu.iq.fu_full::SimdAdd                      0      0.00%      6.92% # attempts to use FU when none available
-system.cpu.iq.fu_full::SimdAddAcc                   0      0.00%      6.92% # attempts to use FU when none available
-system.cpu.iq.fu_full::SimdAlu                      0      0.00%      6.92% # attempts to use FU when none available
-system.cpu.iq.fu_full::SimdCmp                      0      0.00%      6.92% # attempts to use FU when none available
-system.cpu.iq.fu_full::SimdCvt                      0      0.00%      6.92% # attempts to use FU when none available
-system.cpu.iq.fu_full::SimdMisc                     0      0.00%      6.92% # attempts to use FU when none available
-system.cpu.iq.fu_full::SimdMult                     0      0.00%      6.92% # attempts to use FU when none available
-system.cpu.iq.fu_full::SimdMultAcc                  0      0.00%      6.92% # attempts to use FU when none available
-system.cpu.iq.fu_full::SimdShift                    0      0.00%      6.92% # attempts to use FU when none available
-system.cpu.iq.fu_full::SimdShiftAcc                 0      0.00%      6.92% # attempts to use FU when none available
-system.cpu.iq.fu_full::SimdSqrt                     0      0.00%      6.92% # attempts to use FU when none available
-system.cpu.iq.fu_full::SimdFloatAdd                 0      0.00%      6.92% # attempts to use FU when none available
-system.cpu.iq.fu_full::SimdFloatAlu                 0      0.00%      6.92% # attempts to use FU when none available
-system.cpu.iq.fu_full::SimdFloatCmp                 0      0.00%      6.92% # attempts to use FU when none available
-system.cpu.iq.fu_full::SimdFloatCvt                 0      0.00%      6.92% # attempts to use FU when none available
-system.cpu.iq.fu_full::SimdFloatDiv                 0      0.00%      6.92% # attempts to use FU when none available
-system.cpu.iq.fu_full::SimdFloatMisc                0      0.00%      6.92% # attempts to use FU when none available
-system.cpu.iq.fu_full::SimdFloatMult                0      0.00%      6.92% # attempts to use FU when none available
-system.cpu.iq.fu_full::SimdFloatMultAcc             0      0.00%      6.92% # attempts to use FU when none available
-system.cpu.iq.fu_full::SimdFloatSqrt                0      0.00%      6.92% # attempts to use FU when none available
-system.cpu.iq.fu_full::MemRead                2269895     87.35%     94.27% # attempts to use FU when none available
-system.cpu.iq.fu_full::MemWrite                148998      5.73%    100.00% # attempts to use FU when none available
+system.cpu.iq.fu_full::IntAlu                  183781      6.86%      6.86% # attempts to use FU when none available
+system.cpu.iq.fu_full::IntMult                      0      0.00%      6.86% # attempts to use FU when none available
+system.cpu.iq.fu_full::IntDiv                       0      0.00%      6.86% # attempts to use FU when none available
+system.cpu.iq.fu_full::FloatAdd                     0      0.00%      6.86% # attempts to use FU when none available
+system.cpu.iq.fu_full::FloatCmp                     0      0.00%      6.86% # attempts to use FU when none available
+system.cpu.iq.fu_full::FloatCvt                     0      0.00%      6.86% # attempts to use FU when none available
+system.cpu.iq.fu_full::FloatMult                    0      0.00%      6.86% # attempts to use FU when none available
+system.cpu.iq.fu_full::FloatDiv                     0      0.00%      6.86% # attempts to use FU when none available
+system.cpu.iq.fu_full::FloatSqrt                    0      0.00%      6.86% # attempts to use FU when none available
+system.cpu.iq.fu_full::SimdAdd                      0      0.00%      6.86% # attempts to use FU when none available
+system.cpu.iq.fu_full::SimdAddAcc                   0      0.00%      6.86% # attempts to use FU when none available
+system.cpu.iq.fu_full::SimdAlu                      0      0.00%      6.86% # attempts to use FU when none available
+system.cpu.iq.fu_full::SimdCmp                      0      0.00%      6.86% # attempts to use FU when none available
+system.cpu.iq.fu_full::SimdCvt                      0      0.00%      6.86% # attempts to use FU when none available
+system.cpu.iq.fu_full::SimdMisc                     0      0.00%      6.86% # attempts to use FU when none available
+system.cpu.iq.fu_full::SimdMult                     0      0.00%      6.86% # attempts to use FU when none available
+system.cpu.iq.fu_full::SimdMultAcc                  0      0.00%      6.86% # attempts to use FU when none available
+system.cpu.iq.fu_full::SimdShift                    0      0.00%      6.86% # attempts to use FU when none available
+system.cpu.iq.fu_full::SimdShiftAcc                 0      0.00%      6.86% # attempts to use FU when none available
+system.cpu.iq.fu_full::SimdSqrt                     0      0.00%      6.86% # attempts to use FU when none available
+system.cpu.iq.fu_full::SimdFloatAdd                 0      0.00%      6.86% # attempts to use FU when none available
+system.cpu.iq.fu_full::SimdFloatAlu                 0      0.00%      6.86% # attempts to use FU when none available
+system.cpu.iq.fu_full::SimdFloatCmp                 0      0.00%      6.86% # attempts to use FU when none available
+system.cpu.iq.fu_full::SimdFloatCvt                 0      0.00%      6.86% # attempts to use FU when none available
+system.cpu.iq.fu_full::SimdFloatDiv                 0      0.00%      6.86% # attempts to use FU when none available
+system.cpu.iq.fu_full::SimdFloatMisc                0      0.00%      6.86% # attempts to use FU when none available
+system.cpu.iq.fu_full::SimdFloatMult                0      0.00%      6.86% # attempts to use FU when none available
+system.cpu.iq.fu_full::SimdFloatMultAcc             0      0.00%      6.86% # attempts to use FU when none available
+system.cpu.iq.fu_full::SimdFloatSqrt                0      0.00%      6.86% # attempts to use FU when none available
+system.cpu.iq.fu_full::MemRead                2344413     87.49%     94.35% # attempts to use FU when none available
+system.cpu.iq.fu_full::MemWrite                151333      5.65%    100.00% # attempts to use FU when none available
 system.cpu.iq.fu_full::IprAccess                    0      0.00%    100.00% # attempts to use FU when none available
 system.cpu.iq.fu_full::InstPrefetch                 0      0.00%    100.00% # attempts to use FU when none available
-system.cpu.iq.FU_type_0::No_OpClass          26894248      1.51%      1.51% # Type of FU issued
-system.cpu.iq.FU_type_0::IntAlu            1102052869     61.86%     63.37% # Type of FU issued
+system.cpu.iq.FU_type_0::No_OpClass          26390474      1.48%      1.48% # Type of FU issued
+system.cpu.iq.FU_type_0::IntAlu            1101178190     61.89%     63.37% # Type of FU issued
 system.cpu.iq.FU_type_0::IntMult                    0      0.00%     63.37% # Type of FU issued
 system.cpu.iq.FU_type_0::IntDiv                     0      0.00%     63.37% # Type of FU issued
 system.cpu.iq.FU_type_0::FloatAdd                   0      0.00%     63.37% # Type of FU issued
@@ -178,85 +178,85 @@
 system.cpu.iq.FU_type_0::SimdFloatMult              0      0.00%     63.37% # Type of FU issued
 system.cpu.iq.FU_type_0::SimdFloatMultAcc            0      0.00%     63.37% # Type of FU issued
 system.cpu.iq.FU_type_0::SimdFloatSqrt              0      0.00%     63.37% # Type of FU issued
-system.cpu.iq.FU_type_0::MemRead            457985397     25.71%     89.07% # Type of FU issued
-system.cpu.iq.FU_type_0::MemWrite           194697490     10.93%    100.00% # Type of FU issued
+system.cpu.iq.FU_type_0::MemRead            457060255     25.69%     89.06% # Type of FU issued
+system.cpu.iq.FU_type_0::MemWrite           194682198     10.94%    100.00% # Type of FU issued
 system.cpu.iq.FU_type_0::IprAccess                  0      0.00%    100.00% # Type of FU issued
 system.cpu.iq.FU_type_0::InstPrefetch               0      0.00%    100.00% # Type of FU issued
-system.cpu.iq.FU_type_0::total             1781630004                       # Type of FU issued
-system.cpu.iq.rate                           1.519399                       # Inst issue rate
-system.cpu.iq.fu_busy_cnt                     2598665                       # FU busy when requested
-system.cpu.iq.fu_busy_rate                   0.001459                       # FU busy rate (busy events/executed inst)
-system.cpu.iq.int_inst_queue_reads         4738479063                       # Number of integer instruction queue reads
-system.cpu.iq.int_inst_queue_writes        2351732069                       # Number of integer instruction queue writes
-system.cpu.iq.int_inst_queue_wakeup_accesses   1760053765                       # Number of integer instruction queue wakeup accesses
-system.cpu.iq.fp_inst_queue_reads                  95                       # Number of floating instruction queue reads
-system.cpu.iq.fp_inst_queue_writes                542                       # Number of floating instruction queue writes
+system.cpu.iq.FU_type_0::total             1779311117                       # Type of FU issued
+system.cpu.iq.rate                           1.511002                       # Inst issue rate
+system.cpu.iq.fu_busy_cnt                     2679527                       # FU busy when requested
+system.cpu.iq.fu_busy_rate                   0.001506                       # FU busy rate (busy events/executed inst)
+system.cpu.iq.int_inst_queue_reads         4738956161                       # Number of integer instruction queue reads
+system.cpu.iq.int_inst_queue_writes        2338163322                       # Number of integer instruction queue writes
+system.cpu.iq.int_inst_queue_wakeup_accesses   1758678242                       # Number of integer instruction queue wakeup accesses
+system.cpu.iq.fp_inst_queue_reads                  35                       # Number of floating instruction queue reads
+system.cpu.iq.fp_inst_queue_writes                458                       # Number of floating instruction queue writes
 system.cpu.iq.fp_inst_queue_wakeup_accesses           12                       # Number of floating instruction queue wakeup accesses
-system.cpu.iq.int_alu_accesses             1757334381                       # Number of integer alu accesses
-system.cpu.iq.fp_alu_accesses                      40                       # Number of floating point alu accesses
-system.cpu.iew.lsq.thread0.forwLoads        205665909                       # Number of loads that had data forwarded from stores
+system.cpu.iq.int_alu_accesses             1755600151                       # Number of integer alu accesses
+system.cpu.iq.fp_alu_accesses                      19                       # Number of floating point alu accesses
+system.cpu.iew.lsq.thread0.forwLoads        207757708                       # Number of loads that had data forwarded from stores
 system.cpu.iew.lsq.thread0.invAddrLoads             0                       # Number of loads ignored due to an invalid address
-system.cpu.iew.lsq.thread0.squashedLoads    100048507                       # Number of loads squashed
-system.cpu.iew.lsq.thread0.ignoredResponses        60622                       # Number of memory responses ignored because the instruction is squashed
-system.cpu.iew.lsq.thread0.memOrderViolation       216417                       # Number of memory ordering violations
-system.cpu.iew.lsq.thread0.squashedStores     38622350                       # Number of stores squashed
+system.cpu.iew.lsq.thread0.squashedLoads     98307771                       # Number of loads squashed
+system.cpu.iew.lsq.thread0.ignoredResponses        75876                       # Number of memory responses ignored because the instruction is squashed
+system.cpu.iew.lsq.thread0.memOrderViolation       215687                       # Number of memory ordering violations
+system.cpu.iew.lsq.thread0.squashedStores     37990305                       # Number of stores squashed
 system.cpu.iew.lsq.thread0.invAddrSwpfs             0                       # Number of software prefetches ignored due to an invalid address
 system.cpu.iew.lsq.thread0.blockedLoads             0                       # Number of blocked loads due to partial load-store forwarding
-system.cpu.iew.lsq.thread0.rescheduledLoads          849                       # Number of loads that were rescheduled
-system.cpu.iew.lsq.thread0.cacheBlocked         34395                       # Number of times an access to memory failed due to the cache being blocked
+system.cpu.iew.lsq.thread0.rescheduledLoads         1126                       # Number of loads that were rescheduled
+system.cpu.iew.lsq.thread0.cacheBlocked             0                       # Number of times an access to memory failed due to the cache being blocked
 system.cpu.iew.iewIdleCycles                        0                       # Number of cycles IEW is idle
-system.cpu.iew.iewSquashCycles               49549596                       # Number of cycles IEW is squashing
-system.cpu.iew.iewBlockCycles                 1308890                       # Number of cycles IEW is blocking
-system.cpu.iew.iewUnblockCycles                133908                       # Number of cycles IEW is unblocking
-system.cpu.iew.iewDispatchedInsts          1986583734                       # Number of instructions dispatched to IQ
-system.cpu.iew.iewDispSquashedInsts            659432                       # Number of squashed instructions skipped by dispatch
-system.cpu.iew.iewDispLoadInsts             519090632                       # Number of dispatched load instructions
-system.cpu.iew.iewDispStoreInsts            226808407                       # Number of dispatched store instructions
-system.cpu.iew.iewDispNonSpecInsts                 86                       # Number of dispatched non-speculative instructions
-system.cpu.iew.iewIQFullEvents                  64911                       # Number of times the IQ has become full, causing a stall
-system.cpu.iew.iewLSQFullEvents                    28                       # Number of times the LSQ has become full, causing a stall
-system.cpu.iew.memOrderViolationEvents         216417                       # Number of memory order violations
-system.cpu.iew.predictedTakenIncorrect        4603219                       # Number of branches that were predicted taken incorrectly
-system.cpu.iew.predictedNotTakenIncorrect      3388875                       # Number of branches that were predicted not taken incorrectly
-system.cpu.iew.branchMispredicts              7992094                       # Number of branch mispredicts detected at execute
-system.cpu.iew.iewExecutedInsts            1768232808                       # Number of executed instructions
-system.cpu.iew.iewExecLoadInsts             452047218                       # Number of load instructions executed
-system.cpu.iew.iewExecSquashedInsts          13397196                       # Number of squashed instructions skipped in execute
+system.cpu.iew.iewSquashCycles               48633503                       # Number of cycles IEW is squashing
+system.cpu.iew.iewBlockCycles                 1923683                       # Number of cycles IEW is blocking
+system.cpu.iew.iewUnblockCycles                157688                       # Number of cycles IEW is unblocking
+system.cpu.iew.iewDispatchedInsts          1979800142                       # Number of instructions dispatched to IQ
+system.cpu.iew.iewDispSquashedInsts            665872                       # Number of squashed instructions skipped by dispatch
+system.cpu.iew.iewDispLoadInsts             517349896                       # Number of dispatched load instructions
+system.cpu.iew.iewDispStoreInsts            226176362                       # Number of dispatched store instructions
+system.cpu.iew.iewDispNonSpecInsts                 85                       # Number of dispatched non-speculative instructions
+system.cpu.iew.iewIQFullEvents                  70768                       # Number of times the IQ has become full, causing a stall
+system.cpu.iew.iewLSQFullEvents                    44                       # Number of times the LSQ has become full, causing a stall
+system.cpu.iew.memOrderViolationEvents         215687                       # Number of memory order violations
+system.cpu.iew.predictedTakenIncorrect        4604749                       # Number of branches that were predicted taken incorrectly
+system.cpu.iew.predictedNotTakenIncorrect      3040457                       # Number of branches that were predicted not taken incorrectly
+system.cpu.iew.branchMispredicts              7645206                       # Number of branch mispredicts detected at execute
+system.cpu.iew.iewExecutedInsts            1766024784                       # Number of executed instructions
+system.cpu.iew.iewExecLoadInsts             451208749                       # Number of load instructions executed
+system.cpu.iew.iewExecSquashedInsts          13286333                       # Number of squashed instructions skipped in execute
 system.cpu.iew.exec_swp                             0                       # number of swp insts executed
 system.cpu.iew.exec_nop                             0                       # number of nop insts executed
-system.cpu.iew.exec_refs                    645919458                       # number of memory reference insts executed
-system.cpu.iew.exec_branches                112169596                       # Number of branches executed
-system.cpu.iew.exec_stores                  193872240                       # Number of stores executed
-system.cpu.iew.exec_rate                     1.507974                       # Inst execution rate
-system.cpu.iew.wb_sent                     1766226829                       # cumulative count of insts sent to commit
-system.cpu.iew.wb_count                    1760053777                       # cumulative count of insts written-back
-system.cpu.iew.wb_producers                1336567337                       # num instructions producing a value
-system.cpu.iew.wb_consumers                2003494286                       # num instructions consuming a value
+system.cpu.iew.exec_refs                    645051015                       # number of memory reference insts executed
+system.cpu.iew.exec_branches                112022135                       # Number of branches executed
+system.cpu.iew.exec_stores                  193842266                       # Number of stores executed
+system.cpu.iew.exec_rate                     1.499719                       # Inst execution rate
+system.cpu.iew.wb_sent                     1764443624                       # cumulative count of insts sent to commit
+system.cpu.iew.wb_count                    1758678254                       # cumulative count of insts written-back
+system.cpu.iew.wb_producers                1332033031                       # num instructions producing a value
+system.cpu.iew.wb_consumers                1982428848                       # num instructions consuming a value
 system.cpu.iew.wb_penalized                         0                       # number of instrctions required to write to 'other' IQ
-system.cpu.iew.wb_rate                       1.500999                       # insts written-back per cycle
-system.cpu.iew.wb_fanout                     0.667118                       # average fanout of values written-back
+system.cpu.iew.wb_rate                       1.493480                       # insts written-back per cycle
+system.cpu.iew.wb_fanout                     0.671920                       # average fanout of values written-back
 system.cpu.iew.wb_penalized_rate                    0                       # fraction of instructions written-back that wrote to 'other' IQ
 system.cpu.commit.commitCommittedInsts     1621493982                       # The number of committed instructions
-system.cpu.commit.commitSquashedInsts       365103312                       # The number of squashed insts skipped by commit
+system.cpu.commit.commitSquashedInsts       358308768                       # The number of squashed insts skipped by commit
 system.cpu.commit.commitNonSpecStalls              50                       # The number of times commit has been forced to stall to communicate backwards
-system.cpu.commit.branchMispredicts           7804888                       # The number of times a branch was mispredicted
-system.cpu.commit.committed_per_cycle::samples   1122890064                       # Number of insts commited each cycle
-system.cpu.commit.committed_per_cycle::mean     1.444036                       # Number of insts commited each cycle
-system.cpu.commit.committed_per_cycle::stdev     1.662985                       # Number of insts commited each cycle
+system.cpu.commit.branchMispredicts           7459361                       # The number of times a branch was mispredicted
+system.cpu.commit.committed_per_cycle::samples   1128845850                       # Number of insts commited each cycle
+system.cpu.commit.committed_per_cycle::mean     1.436418                       # Number of insts commited each cycle
+system.cpu.commit.committed_per_cycle::stdev     1.651874                       # Number of insts commited each cycle
 system.cpu.commit.committed_per_cycle::underflows            0      0.00%      0.00% # Number of insts commited each cycle
-system.cpu.commit.committed_per_cycle::0    346724877     30.88%     30.88% # Number of insts commited each cycle
-system.cpu.commit.committed_per_cycle::1    438665808     39.07%     69.94% # Number of insts commited each cycle
-system.cpu.commit.committed_per_cycle::2     94902960      8.45%     78.40% # Number of insts commited each cycle
-system.cpu.commit.committed_per_cycle::3    133728922     11.91%     90.30% # Number of insts commited each cycle
-system.cpu.commit.committed_per_cycle::4     36854784      3.28%     93.59% # Number of insts commited each cycle
-system.cpu.commit.committed_per_cycle::5     26115374      2.33%     95.91% # Number of insts commited each cycle
-system.cpu.commit.committed_per_cycle::6     22565758      2.01%     97.92% # Number of insts commited each cycle
-system.cpu.commit.committed_per_cycle::7      8207714      0.73%     98.65% # Number of insts commited each cycle
-system.cpu.commit.committed_per_cycle::8     15123867      1.35%    100.00% # Number of insts commited each cycle
+system.cpu.commit.committed_per_cycle::0    347283519     30.76%     30.76% # Number of insts commited each cycle
+system.cpu.commit.committed_per_cycle::1    441725058     39.13%     69.90% # Number of insts commited each cycle
+system.cpu.commit.committed_per_cycle::2     99623372      8.83%     78.72% # Number of insts commited each cycle
+system.cpu.commit.committed_per_cycle::3    136537223     12.10%     90.82% # Number of insts commited each cycle
+system.cpu.commit.committed_per_cycle::4     31770740      2.81%     93.63% # Number of insts commited each cycle
+system.cpu.commit.committed_per_cycle::5     26056867      2.31%     95.94% # Number of insts commited each cycle
+system.cpu.commit.committed_per_cycle::6     22501724      1.99%     97.93% # Number of insts commited each cycle
+system.cpu.commit.committed_per_cycle::7      8245904      0.73%     98.66% # Number of insts commited each cycle
+system.cpu.commit.committed_per_cycle::8     15101443      1.34%    100.00% # Number of insts commited each cycle
 system.cpu.commit.committed_per_cycle::overflows            0      0.00%    100.00% # Number of insts commited each cycle
 system.cpu.commit.committed_per_cycle::min_value            0                       # Number of insts commited each cycle
 system.cpu.commit.committed_per_cycle::max_value            8                       # Number of insts commited each cycle
-system.cpu.commit.committed_per_cycle::total   1122890064                       # Number of insts commited each cycle
+system.cpu.commit.committed_per_cycle::total   1128845850                       # Number of insts commited each cycle
 system.cpu.commit.count                    1621493982                       # Number of instructions committed
 system.cpu.commit.swp_count                         0                       # Number of s/w prefetches committed
 system.cpu.commit.refs                      607228182                       # Number of memory references committed
@@ -266,48 +266,48 @@
 system.cpu.commit.fp_insts                          0                       # Number of committed floating point instructions.
 system.cpu.commit.int_insts                1621354492                       # Number of committed integer instructions.
 system.cpu.commit.function_calls                    0                       # Number of function calls committed.
-system.cpu.commit.bw_lim_events              15123867                       # number cycles where commit BW limit reached
+system.cpu.commit.bw_lim_events              15101443                       # number cycles where commit BW limit reached
 system.cpu.commit.bw_limited                        0                       # number of insts not committed due to BW limits
-system.cpu.rob.rob_reads                   3094363491                       # The number of ROB reads
-system.cpu.rob.rob_writes                  4022764791                       # The number of ROB writes
-system.cpu.timesIdled                           43542                       # Number of times that the entire CPU went into an idle state and unscheduled itself
-system.cpu.idleCycles                          148789                       # Total number of cycles that the CPU has spent unscheduled due to idling
+system.cpu.rob.rob_reads                   3093547157                       # The number of ROB reads
+system.cpu.rob.rob_writes                  4008258633                       # The number of ROB writes
+system.cpu.timesIdled                           21053                       # Number of times that the entire CPU went into an idle state and unscheduled itself
+system.cpu.idleCycles                           91264                       # Total number of cycles that the CPU has spent unscheduled due to idling
 system.cpu.committedInsts                  1621493982                       # Number of Instructions Simulated
 system.cpu.committedInsts_total            1621493982                       # Number of Instructions Simulated
-system.cpu.cpi                               0.723153                       # CPI: Cycles Per Instruction
-system.cpu.cpi_total                         0.723153                       # CPI: Total CPI of All Threads
-system.cpu.ipc                               1.382833                       # IPC: Instructions Per Cycle
-system.cpu.ipc_total                         1.382833                       # IPC: Total IPC of All Threads
-system.cpu.int_regfile_reads               3273039620                       # number of integer regfile reads
-system.cpu.int_regfile_writes              1756091292                       # number of integer regfile writes
+system.cpu.cpi                               0.726226                       # CPI: Cycles Per Instruction
+system.cpu.cpi_total                         0.726226                       # CPI: Total CPI of All Threads
+system.cpu.ipc                               1.376982                       # IPC: Instructions Per Cycle
+system.cpu.ipc_total                         1.376982                       # IPC: Total IPC of All Threads
+system.cpu.int_regfile_reads               3270153545                       # number of integer regfile reads
+system.cpu.int_regfile_writes              1754693299                       # number of integer regfile writes
 system.cpu.fp_regfile_reads                        12                       # number of floating regfile reads
-system.cpu.misc_regfile_reads               908871445                       # number of misc regfile reads
+system.cpu.misc_regfile_reads               907833056                       # number of misc regfile reads
 system.cpu.icache.replacements                     12                       # number of replacements
-system.cpu.icache.tagsinuse                810.394392                       # Cycle average of tags in use
-system.cpu.icache.total_refs                137025977                       # Total number of references to valid blocks.
-system.cpu.icache.sampled_refs                    893                       # Sample count of references to valid blocks.
-system.cpu.icache.avg_refs               153444.543113                       # Average number of references to valid blocks.
+system.cpu.icache.tagsinuse                808.459907                       # Cycle average of tags in use
+system.cpu.icache.total_refs                135737385                       # Total number of references to valid blocks.
+system.cpu.icache.sampled_refs                    897                       # Sample count of references to valid blocks.
+system.cpu.icache.avg_refs               151323.729097                       # Average number of references to valid blocks.
 system.cpu.icache.warmup_cycle                      0                       # Cycle when the warmup percentage was hit.
-system.cpu.icache.occ_blocks::0            810.394392                       # Average occupied blocks per context
-system.cpu.icache.occ_percent::0             0.395700                       # Average percentage of cache occupancy
-system.cpu.icache.ReadReq_hits              137025977                       # number of ReadReq hits
-system.cpu.icache.demand_hits               137025977                       # number of demand (read+write) hits
-system.cpu.icache.overall_hits              137025977                       # number of overall hits
-system.cpu.icache.ReadReq_misses                 1232                       # number of ReadReq misses
-system.cpu.icache.demand_misses                  1232                       # number of demand (read+write) misses
-system.cpu.icache.overall_misses                 1232                       # number of overall misses
-system.cpu.icache.ReadReq_miss_latency       43328500                       # number of ReadReq miss cycles
-system.cpu.icache.demand_miss_latency        43328500                       # number of demand (read+write) miss cycles
-system.cpu.icache.overall_miss_latency       43328500                       # number of overall miss cycles
-system.cpu.icache.ReadReq_accesses          137027209                       # number of ReadReq accesses(hits+misses)
-system.cpu.icache.demand_accesses           137027209                       # number of demand (read+write) accesses
-system.cpu.icache.overall_accesses          137027209                       # number of overall (read+write) accesses
+system.cpu.icache.occ_blocks::0            808.459907                       # Average occupied blocks per context
+system.cpu.icache.occ_percent::0             0.394756                       # Average percentage of cache occupancy
+system.cpu.icache.ReadReq_hits              135737385                       # number of ReadReq hits
+system.cpu.icache.demand_hits               135737385                       # number of demand (read+write) hits
+system.cpu.icache.overall_hits              135737385                       # number of overall hits
+system.cpu.icache.ReadReq_misses                 1224                       # number of ReadReq misses
+system.cpu.icache.demand_misses                  1224                       # number of demand (read+write) misses
+system.cpu.icache.overall_misses                 1224                       # number of overall misses
+system.cpu.icache.ReadReq_miss_latency       43199000                       # number of ReadReq miss cycles
+system.cpu.icache.demand_miss_latency        43199000                       # number of demand (read+write) miss cycles
+system.cpu.icache.overall_miss_latency       43199000                       # number of overall miss cycles
+system.cpu.icache.ReadReq_accesses          135738609                       # number of ReadReq accesses(hits+misses)
+system.cpu.icache.demand_accesses           135738609                       # number of demand (read+write) accesses
+system.cpu.icache.overall_accesses          135738609                       # number of overall (read+write) accesses
 system.cpu.icache.ReadReq_miss_rate          0.000009                       # miss rate for ReadReq accesses
 system.cpu.icache.demand_miss_rate           0.000009                       # miss rate for demand accesses
 system.cpu.icache.overall_miss_rate          0.000009                       # miss rate for overall accesses
-system.cpu.icache.ReadReq_avg_miss_latency 35169.237013                       # average ReadReq miss latency
-system.cpu.icache.demand_avg_miss_latency 35169.237013                       # average overall miss latency
-system.cpu.icache.overall_avg_miss_latency 35169.237013                       # average overall miss latency
+system.cpu.icache.ReadReq_avg_miss_latency 35293.300654                       # average ReadReq miss latency
+system.cpu.icache.demand_avg_miss_latency 35293.300654                       # average overall miss latency
+system.cpu.icache.overall_avg_miss_latency 35293.300654                       # average overall miss latency
 system.cpu.icache.blocked_cycles::no_mshrs            0                       # number of cycles access was blocked
 system.cpu.icache.blocked_cycles::no_targets            0                       # number of cycles access was blocked
 system.cpu.icache.blocked::no_mshrs                 0                       # number of cycles access was blocked
@@ -317,159 +317,159 @@
 system.cpu.icache.fast_writes                       0                       # number of fast writes performed
 system.cpu.icache.cache_copies                      0                       # number of cache copies performed
 system.cpu.icache.writebacks                        0                       # number of writebacks
-system.cpu.icache.ReadReq_mshr_hits               339                       # number of ReadReq MSHR hits
-system.cpu.icache.demand_mshr_hits                339                       # number of demand (read+write) MSHR hits
-system.cpu.icache.overall_mshr_hits               339                       # number of overall MSHR hits
-system.cpu.icache.ReadReq_mshr_misses             893                       # number of ReadReq MSHR misses
-system.cpu.icache.demand_mshr_misses              893                       # number of demand (read+write) MSHR misses
-system.cpu.icache.overall_mshr_misses             893                       # number of overall MSHR misses
+system.cpu.icache.ReadReq_mshr_hits               327                       # number of ReadReq MSHR hits
+system.cpu.icache.demand_mshr_hits                327                       # number of demand (read+write) MSHR hits
+system.cpu.icache.overall_mshr_hits               327                       # number of overall MSHR hits
+system.cpu.icache.ReadReq_mshr_misses             897                       # number of ReadReq MSHR misses
+system.cpu.icache.demand_mshr_misses              897                       # number of demand (read+write) MSHR misses
+system.cpu.icache.overall_mshr_misses             897                       # number of overall MSHR misses
 system.cpu.icache.overall_mshr_uncacheable_misses            0                       # number of overall MSHR uncacheable misses
-system.cpu.icache.ReadReq_mshr_miss_latency     31560500                       # number of ReadReq MSHR miss cycles
-system.cpu.icache.demand_mshr_miss_latency     31560500                       # number of demand (read+write) MSHR miss cycles
-system.cpu.icache.overall_mshr_miss_latency     31560500                       # number of overall MSHR miss cycles
+system.cpu.icache.ReadReq_mshr_miss_latency     31683500                       # number of ReadReq MSHR miss cycles
+system.cpu.icache.demand_mshr_miss_latency     31683500                       # number of demand (read+write) MSHR miss cycles
+system.cpu.icache.overall_mshr_miss_latency     31683500                       # number of overall MSHR miss cycles
 system.cpu.icache.overall_mshr_uncacheable_latency            0                       # number of overall MSHR uncacheable cycles
 system.cpu.icache.ReadReq_mshr_miss_rate     0.000007                       # mshr miss rate for ReadReq accesses
 system.cpu.icache.demand_mshr_miss_rate      0.000007                       # mshr miss rate for demand accesses
 system.cpu.icache.overall_mshr_miss_rate     0.000007                       # mshr miss rate for overall accesses
-system.cpu.icache.ReadReq_avg_mshr_miss_latency 35342.105263                       # average ReadReq mshr miss latency
-system.cpu.icache.demand_avg_mshr_miss_latency 35342.105263                       # average overall mshr miss latency
-system.cpu.icache.overall_avg_mshr_miss_latency 35342.105263                       # average overall mshr miss latency
+system.cpu.icache.ReadReq_avg_mshr_miss_latency 35321.627648                       # average ReadReq mshr miss latency
+system.cpu.icache.demand_avg_mshr_miss_latency 35321.627648                       # average overall mshr miss latency
+system.cpu.icache.overall_avg_mshr_miss_latency 35321.627648                       # average overall mshr miss latency
 system.cpu.icache.overall_avg_mshr_uncacheable_latency     no_value                       # average overall mshr uncacheable latency
 system.cpu.icache.mshr_cap_events                   0                       # number of times MSHR cap was activated
 system.cpu.icache.soft_prefetch_mshr_full            0                       # number of mshr full events for SW prefetching instrutions
 system.cpu.icache.no_allocate_misses                0                       # Number of misses that were no-allocate
-system.cpu.dcache.replacements                 459077                       # number of replacements
-system.cpu.dcache.tagsinuse               4094.907333                       # Cycle average of tags in use
-system.cpu.dcache.total_refs                433034493                       # Total number of references to valid blocks.
-system.cpu.dcache.sampled_refs                 463173                       # Sample count of references to valid blocks.
-system.cpu.dcache.avg_refs                 934.930346                       # Average number of references to valid blocks.
-system.cpu.dcache.warmup_cycle              317767000                       # Cycle when the warmup percentage was hit.
-system.cpu.dcache.occ_blocks::0           4094.907333                       # Average occupied blocks per context
-system.cpu.dcache.occ_percent::0             0.999733                       # Average percentage of cache occupancy
-system.cpu.dcache.ReadReq_hits              246142702                       # number of ReadReq hits
-system.cpu.dcache.WriteReq_hits             186891791                       # number of WriteReq hits
-system.cpu.dcache.demand_hits               433034493                       # number of demand (read+write) hits
-system.cpu.dcache.overall_hits              433034493                       # number of overall hits
-system.cpu.dcache.ReadReq_misses               217277                       # number of ReadReq misses
-system.cpu.dcache.WriteReq_misses             1294266                       # number of WriteReq misses
-system.cpu.dcache.demand_misses               1511543                       # number of demand (read+write) misses
-system.cpu.dcache.overall_misses              1511543                       # number of overall misses
-system.cpu.dcache.ReadReq_miss_latency     2206130500                       # number of ReadReq miss cycles
-system.cpu.dcache.WriteReq_miss_latency   25062764496                       # number of WriteReq miss cycles
-system.cpu.dcache.demand_miss_latency     27268894996                       # number of demand (read+write) miss cycles
-system.cpu.dcache.overall_miss_latency    27268894996                       # number of overall miss cycles
-system.cpu.dcache.ReadReq_accesses          246359979                       # number of ReadReq accesses(hits+misses)
+system.cpu.dcache.replacements                 459032                       # number of replacements
+system.cpu.dcache.tagsinuse               4094.268658                       # Cycle average of tags in use
+system.cpu.dcache.total_refs                431168175                       # Total number of references to valid blocks.
+system.cpu.dcache.sampled_refs                 463128                       # Sample count of references to valid blocks.
+system.cpu.dcache.avg_refs                 930.991378                       # Average number of references to valid blocks.
+system.cpu.dcache.warmup_cycle              416529000                       # Cycle when the warmup percentage was hit.
+system.cpu.dcache.occ_blocks::0           4094.268658                       # Average occupied blocks per context
+system.cpu.dcache.occ_percent::0             0.999577                       # Average percentage of cache occupancy
+system.cpu.dcache.ReadReq_hits              243231636                       # number of ReadReq hits
+system.cpu.dcache.WriteReq_hits             187936539                       # number of WriteReq hits
+system.cpu.dcache.demand_hits               431168175                       # number of demand (read+write) hits
+system.cpu.dcache.overall_hits              431168175                       # number of overall hits
+system.cpu.dcache.ReadReq_misses               217117                       # number of ReadReq misses
+system.cpu.dcache.WriteReq_misses              249518                       # number of WriteReq misses
+system.cpu.dcache.demand_misses                466635                       # number of demand (read+write) misses
+system.cpu.dcache.overall_misses               466635                       # number of overall misses
+system.cpu.dcache.ReadReq_miss_latency     2193700500                       # number of ReadReq miss cycles
+system.cpu.dcache.WriteReq_miss_latency    3216393000                       # number of WriteReq miss cycles
+system.cpu.dcache.demand_miss_latency      5410093500                       # number of demand (read+write) miss cycles
+system.cpu.dcache.overall_miss_latency     5410093500                       # number of overall miss cycles
+system.cpu.dcache.ReadReq_accesses          243448753                       # number of ReadReq accesses(hits+misses)
 system.cpu.dcache.WriteReq_accesses         188186057                       # number of WriteReq accesses(hits+misses)
-system.cpu.dcache.demand_accesses           434546036                       # number of demand (read+write) accesses
-system.cpu.dcache.overall_accesses          434546036                       # number of overall (read+write) accesses
-system.cpu.dcache.ReadReq_miss_rate          0.000882                       # miss rate for ReadReq accesses
-system.cpu.dcache.WriteReq_miss_rate         0.006878                       # miss rate for WriteReq accesses
-system.cpu.dcache.demand_miss_rate           0.003478                       # miss rate for demand accesses
-system.cpu.dcache.overall_miss_rate          0.003478                       # miss rate for overall accesses
-system.cpu.dcache.ReadReq_avg_miss_latency 10153.539031                       # average ReadReq miss latency
-system.cpu.dcache.WriteReq_avg_miss_latency 19364.461785                       # average WriteReq miss latency
-system.cpu.dcache.demand_avg_miss_latency 18040.436161                       # average overall miss latency
-system.cpu.dcache.overall_avg_miss_latency 18040.436161                       # average overall miss latency
-system.cpu.dcache.blocked_cycles::no_mshrs      1883000                       # number of cycles access was blocked
-system.cpu.dcache.blocked_cycles::no_targets    482947000                       # number of cycles access was blocked
-system.cpu.dcache.blocked::no_mshrs               482                       # number of cycles access was blocked
-system.cpu.dcache.blocked::no_targets           32670                       # number of cycles access was blocked
-system.cpu.dcache.avg_blocked_cycles::no_mshrs  3906.639004                       # average number of cycles each access was blocked
-system.cpu.dcache.avg_blocked_cycles::no_targets 14782.583410                       # average number of cycles each access was blocked
+system.cpu.dcache.demand_accesses           431634810                       # number of demand (read+write) accesses
+system.cpu.dcache.overall_accesses          431634810                       # number of overall (read+write) accesses
+system.cpu.dcache.ReadReq_miss_rate          0.000892                       # miss rate for ReadReq accesses
+system.cpu.dcache.WriteReq_miss_rate         0.001326                       # miss rate for WriteReq accesses
+system.cpu.dcache.demand_miss_rate           0.001081                       # miss rate for demand accesses
+system.cpu.dcache.overall_miss_rate          0.001081                       # miss rate for overall accesses
+system.cpu.dcache.ReadReq_avg_miss_latency 10103.771239                       # average ReadReq miss latency
+system.cpu.dcache.WriteReq_avg_miss_latency 12890.424739                       # average WriteReq miss latency
+system.cpu.dcache.demand_avg_miss_latency 11593.844225                       # average overall miss latency
+system.cpu.dcache.overall_avg_miss_latency 11593.844225                       # average overall miss latency
+system.cpu.dcache.blocked_cycles::no_mshrs            0                       # number of cycles access was blocked
+system.cpu.dcache.blocked_cycles::no_targets            0                       # number of cycles access was blocked
+system.cpu.dcache.blocked::no_mshrs                 0                       # number of cycles access was blocked
+system.cpu.dcache.blocked::no_targets               0                       # number of cycles access was blocked
+system.cpu.dcache.avg_blocked_cycles::no_mshrs     no_value                       # average number of cycles each access was blocked
+system.cpu.dcache.avg_blocked_cycles::no_targets     no_value                       # average number of cycles each access was blocked
 system.cpu.dcache.fast_writes                       0                       # number of fast writes performed
 system.cpu.dcache.cache_copies                      0                       # number of cache copies performed
-system.cpu.dcache.writebacks                   410037                       # number of writebacks
-system.cpu.dcache.ReadReq_mshr_hits              3648                       # number of ReadReq MSHR hits
-system.cpu.dcache.WriteReq_mshr_hits          1044720                       # number of WriteReq MSHR hits
-system.cpu.dcache.demand_mshr_hits            1048368                       # number of demand (read+write) MSHR hits
-system.cpu.dcache.overall_mshr_hits           1048368                       # number of overall MSHR hits
-system.cpu.dcache.ReadReq_mshr_misses          213629                       # number of ReadReq MSHR misses
-system.cpu.dcache.WriteReq_mshr_misses         249546                       # number of WriteReq MSHR misses
-system.cpu.dcache.demand_mshr_misses           463175                       # number of demand (read+write) MSHR misses
-system.cpu.dcache.overall_mshr_misses          463175                       # number of overall MSHR misses
+system.cpu.dcache.writebacks                   409997                       # number of writebacks
+system.cpu.dcache.ReadReq_mshr_hits              3467                       # number of ReadReq MSHR hits
+system.cpu.dcache.WriteReq_mshr_hits               38                       # number of WriteReq MSHR hits
+system.cpu.dcache.demand_mshr_hits               3505                       # number of demand (read+write) MSHR hits
+system.cpu.dcache.overall_mshr_hits              3505                       # number of overall MSHR hits
+system.cpu.dcache.ReadReq_mshr_misses          213650                       # number of ReadReq MSHR misses
+system.cpu.dcache.WriteReq_mshr_misses         249480                       # number of WriteReq MSHR misses
+system.cpu.dcache.demand_mshr_misses           463130                       # number of demand (read+write) MSHR misses
+system.cpu.dcache.overall_mshr_misses          463130                       # number of overall MSHR misses
 system.cpu.dcache.overall_mshr_uncacheable_misses            0                       # number of overall MSHR uncacheable misses
-system.cpu.dcache.ReadReq_mshr_miss_latency   1533480500                       # number of ReadReq MSHR miss cycles
-system.cpu.dcache.WriteReq_mshr_miss_latency   2506697000                       # number of WriteReq MSHR miss cycles
-system.cpu.dcache.demand_mshr_miss_latency   4040177500                       # number of demand (read+write) MSHR miss cycles
-system.cpu.dcache.overall_mshr_miss_latency   4040177500                       # number of overall MSHR miss cycles
+system.cpu.dcache.ReadReq_mshr_miss_latency   1524751500                       # number of ReadReq MSHR miss cycles
+system.cpu.dcache.WriteReq_mshr_miss_latency   2467190000                       # number of WriteReq MSHR miss cycles
+system.cpu.dcache.demand_mshr_miss_latency   3991941500                       # number of demand (read+write) MSHR miss cycles
+system.cpu.dcache.overall_mshr_miss_latency   3991941500                       # number of overall MSHR miss cycles
 system.cpu.dcache.overall_mshr_uncacheable_latency            0                       # number of overall MSHR uncacheable cycles
-system.cpu.dcache.ReadReq_mshr_miss_rate     0.000867                       # mshr miss rate for ReadReq accesses
+system.cpu.dcache.ReadReq_mshr_miss_rate     0.000878                       # mshr miss rate for ReadReq accesses
 system.cpu.dcache.WriteReq_mshr_miss_rate     0.001326                       # mshr miss rate for WriteReq accesses
-system.cpu.dcache.demand_mshr_miss_rate      0.001066                       # mshr miss rate for demand accesses
-system.cpu.dcache.overall_mshr_miss_rate     0.001066                       # mshr miss rate for overall accesses
-system.cpu.dcache.ReadReq_avg_mshr_miss_latency  7178.241250                       # average ReadReq mshr miss latency
-system.cpu.dcache.WriteReq_avg_mshr_miss_latency 10045.029774                       # average WriteReq mshr miss latency
-system.cpu.dcache.demand_avg_mshr_miss_latency  8722.788363                       # average overall mshr miss latency
-system.cpu.dcache.overall_avg_mshr_miss_latency  8722.788363                       # average overall mshr miss latency
+system.cpu.dcache.demand_mshr_miss_rate      0.001073                       # mshr miss rate for demand accesses
+system.cpu.dcache.overall_mshr_miss_rate     0.001073                       # mshr miss rate for overall accesses
+system.cpu.dcache.ReadReq_avg_mshr_miss_latency  7136.679148                       # average ReadReq mshr miss latency
+system.cpu.dcache.WriteReq_avg_mshr_miss_latency  9889.329806                       # average WriteReq mshr miss latency
+system.cpu.dcache.demand_avg_mshr_miss_latency  8619.483730                       # average overall mshr miss latency
+system.cpu.dcache.overall_avg_mshr_miss_latency  8619.483730                       # average overall mshr miss latency
 system.cpu.dcache.overall_avg_mshr_uncacheable_latency     no_value                       # average overall mshr uncacheable latency
 system.cpu.dcache.mshr_cap_events                   0                       # number of times MSHR cap was activated
 system.cpu.dcache.soft_prefetch_mshr_full            0                       # number of mshr full events for SW prefetching instrutions
 system.cpu.dcache.no_allocate_misses                0                       # Number of misses that were no-allocate
-system.cpu.l2cache.replacements                 73618                       # number of replacements
-system.cpu.l2cache.tagsinuse             17964.500601                       # Cycle average of tags in use
-system.cpu.l2cache.total_refs                  452679                       # Total number of references to valid blocks.
-system.cpu.l2cache.sampled_refs                 89237                       # Sample count of references to valid blocks.
-system.cpu.l2cache.avg_refs                  5.072773                       # Average number of references to valid blocks.
+system.cpu.l2cache.replacements                 73588                       # number of replacements
+system.cpu.l2cache.tagsinuse             17962.176251                       # Cycle average of tags in use
+system.cpu.l2cache.total_refs                  452941                       # Total number of references to valid blocks.
+system.cpu.l2cache.sampled_refs                 89203                       # Sample count of references to valid blocks.
+system.cpu.l2cache.avg_refs                  5.077643                       # Average number of references to valid blocks.
 system.cpu.l2cache.warmup_cycle                     0                       # Cycle when the warmup percentage was hit.
-system.cpu.l2cache.occ_blocks::0          1976.098849                       # Average occupied blocks per context
-system.cpu.l2cache.occ_blocks::1         15988.401752                       # Average occupied blocks per context
-system.cpu.l2cache.occ_percent::0            0.060306                       # Average percentage of cache occupancy
-system.cpu.l2cache.occ_percent::1            0.487927                       # Average percentage of cache occupancy
-system.cpu.l2cache.ReadReq_hits                181359                       # number of ReadReq hits
-system.cpu.l2cache.Writeback_hits              410037                       # number of Writeback hits
-system.cpu.l2cache.ReadExReq_hits              190824                       # number of ReadExReq hits
-system.cpu.l2cache.demand_hits                 372183                       # number of demand (read+write) hits
-system.cpu.l2cache.overall_hits                372183                       # number of overall hits
-system.cpu.l2cache.ReadReq_misses               33163                       # number of ReadReq misses
-system.cpu.l2cache.ReadExReq_misses             58722                       # number of ReadExReq misses
-system.cpu.l2cache.demand_misses                91885                       # number of demand (read+write) misses
-system.cpu.l2cache.overall_misses               91885                       # number of overall misses
-system.cpu.l2cache.ReadReq_miss_latency    1130840000                       # number of ReadReq miss cycles
-system.cpu.l2cache.ReadExReq_miss_latency   2017374000                       # number of ReadExReq miss cycles
-system.cpu.l2cache.demand_miss_latency     3148214000                       # number of demand (read+write) miss cycles
-system.cpu.l2cache.overall_miss_latency    3148214000                       # number of overall miss cycles
-system.cpu.l2cache.ReadReq_accesses            214522                       # number of ReadReq accesses(hits+misses)
-system.cpu.l2cache.Writeback_accesses          410037                       # number of Writeback accesses(hits+misses)
-system.cpu.l2cache.ReadExReq_accesses          249546                       # number of ReadExReq accesses(hits+misses)
-system.cpu.l2cache.demand_accesses             464068                       # number of demand (read+write) accesses
-system.cpu.l2cache.overall_accesses            464068                       # number of overall (read+write) accesses
-system.cpu.l2cache.ReadReq_miss_rate         0.154590                       # miss rate for ReadReq accesses
-system.cpu.l2cache.ReadExReq_miss_rate       0.235315                       # miss rate for ReadExReq accesses
-system.cpu.l2cache.demand_miss_rate          0.197999                       # miss rate for demand accesses
-system.cpu.l2cache.overall_miss_rate         0.197999                       # miss rate for overall accesses
-system.cpu.l2cache.ReadReq_avg_miss_latency 34099.448180                       # average ReadReq miss latency
-system.cpu.l2cache.ReadExReq_avg_miss_latency 34354.654133                       # average ReadExReq miss latency
-system.cpu.l2cache.demand_avg_miss_latency 34262.545573                       # average overall miss latency
-system.cpu.l2cache.overall_avg_miss_latency 34262.545573                       # average overall miss latency
-system.cpu.l2cache.blocked_cycles::no_mshrs       202000                       # number of cycles access was blocked
+system.cpu.l2cache.occ_blocks::0          1977.761332                       # Average occupied blocks per context
+system.cpu.l2cache.occ_blocks::1         15984.414919                       # Average occupied blocks per context
+system.cpu.l2cache.occ_percent::0            0.060356                       # Average percentage of cache occupancy
+system.cpu.l2cache.occ_percent::1            0.487806                       # Average percentage of cache occupancy
+system.cpu.l2cache.ReadReq_hits                181391                       # number of ReadReq hits
+system.cpu.l2cache.Writeback_hits              409997                       # number of Writeback hits
+system.cpu.l2cache.ReadExReq_hits              190788                       # number of ReadExReq hits
+system.cpu.l2cache.demand_hits                 372179                       # number of demand (read+write) hits
+system.cpu.l2cache.overall_hits                372179                       # number of overall hits
+system.cpu.l2cache.ReadReq_misses               33152                       # number of ReadReq misses
+system.cpu.l2cache.ReadExReq_misses             58696                       # number of ReadExReq misses
+system.cpu.l2cache.demand_misses                91848                       # number of demand (read+write) misses
+system.cpu.l2cache.overall_misses               91848                       # number of overall misses
+system.cpu.l2cache.ReadReq_miss_latency    1130561500                       # number of ReadReq miss cycles
+system.cpu.l2cache.ReadExReq_miss_latency   2008268500                       # number of ReadExReq miss cycles
+system.cpu.l2cache.demand_miss_latency     3138830000                       # number of demand (read+write) miss cycles
+system.cpu.l2cache.overall_miss_latency    3138830000                       # number of overall miss cycles
+system.cpu.l2cache.ReadReq_accesses            214543                       # number of ReadReq accesses(hits+misses)
+system.cpu.l2cache.Writeback_accesses          409997                       # number of Writeback accesses(hits+misses)
+system.cpu.l2cache.ReadExReq_accesses          249484                       # number of ReadExReq accesses(hits+misses)
+system.cpu.l2cache.demand_accesses             464027                       # number of demand (read+write) accesses
+system.cpu.l2cache.overall_accesses            464027                       # number of overall (read+write) accesses
+system.cpu.l2cache.ReadReq_miss_rate         0.154524                       # miss rate for ReadReq accesses
+system.cpu.l2cache.ReadExReq_miss_rate       0.235270                       # miss rate for ReadExReq accesses
+system.cpu.l2cache.demand_miss_rate          0.197937                       # miss rate for demand accesses
+system.cpu.l2cache.overall_miss_rate         0.197937                       # miss rate for overall accesses
+system.cpu.l2cache.ReadReq_avg_miss_latency 34102.361848                       # average ReadReq miss latency
+system.cpu.l2cache.ReadExReq_avg_miss_latency 34214.742061                       # average ReadExReq miss latency
+system.cpu.l2cache.demand_avg_miss_latency 34174.179078                       # average overall miss latency
+system.cpu.l2cache.overall_avg_miss_latency 34174.179078                       # average overall miss latency
+system.cpu.l2cache.blocked_cycles::no_mshrs            0                       # number of cycles access was blocked
 system.cpu.l2cache.blocked_cycles::no_targets            0                       # number of cycles access was blocked
-system.cpu.l2cache.blocked::no_mshrs              122                       # number of cycles access was blocked
+system.cpu.l2cache.blocked::no_mshrs                0                       # number of cycles access was blocked
 system.cpu.l2cache.blocked::no_targets              0                       # number of cycles access was blocked
-system.cpu.l2cache.avg_blocked_cycles::no_mshrs  1655.737705                       # average number of cycles each access was blocked
+system.cpu.l2cache.avg_blocked_cycles::no_mshrs     no_value                       # average number of cycles each access was blocked
 system.cpu.l2cache.avg_blocked_cycles::no_targets     no_value                       # average number of cycles each access was blocked
 system.cpu.l2cache.fast_writes                      0                       # number of fast writes performed
 system.cpu.l2cache.cache_copies                     0                       # number of cache copies performed
-system.cpu.l2cache.writebacks                   58503                       # number of writebacks
+system.cpu.l2cache.writebacks                   58477                       # number of writebacks
 system.cpu.l2cache.demand_mshr_hits                 0                       # number of demand (read+write) MSHR hits
 system.cpu.l2cache.overall_mshr_hits                0                       # number of overall MSHR hits
-system.cpu.l2cache.ReadReq_mshr_misses          33163                       # number of ReadReq MSHR misses
-system.cpu.l2cache.ReadExReq_mshr_misses        58722                       # number of ReadExReq MSHR misses
-system.cpu.l2cache.demand_mshr_misses           91885                       # number of demand (read+write) MSHR misses
-system.cpu.l2cache.overall_mshr_misses          91885                       # number of overall MSHR misses
+system.cpu.l2cache.ReadReq_mshr_misses          33152                       # number of ReadReq MSHR misses
+system.cpu.l2cache.ReadExReq_mshr_misses        58696                       # number of ReadExReq MSHR misses
+system.cpu.l2cache.demand_mshr_misses           91848                       # number of demand (read+write) MSHR misses
+system.cpu.l2cache.overall_mshr_misses          91848                       # number of overall MSHR misses
 system.cpu.l2cache.overall_mshr_uncacheable_misses            0                       # number of overall MSHR uncacheable misses
-system.cpu.l2cache.ReadReq_mshr_miss_latency   1028236500                       # number of ReadReq MSHR miss cycles
-system.cpu.l2cache.ReadExReq_mshr_miss_latency   1828595500                       # number of ReadExReq MSHR miss cycles
-system.cpu.l2cache.demand_mshr_miss_latency   2856832000                       # number of demand (read+write) MSHR miss cycles
-system.cpu.l2cache.overall_mshr_miss_latency   2856832000                       # number of overall MSHR miss cycles
+system.cpu.l2cache.ReadReq_mshr_miss_latency   1027873500                       # number of ReadReq MSHR miss cycles
+system.cpu.l2cache.ReadExReq_mshr_miss_latency   1819617000                       # number of ReadExReq MSHR miss cycles
+system.cpu.l2cache.demand_mshr_miss_latency   2847490500                       # number of demand (read+write) MSHR miss cycles
+system.cpu.l2cache.overall_mshr_miss_latency   2847490500                       # number of overall MSHR miss cycles
 system.cpu.l2cache.overall_mshr_uncacheable_latency            0                       # number of overall MSHR uncacheable cycles
-system.cpu.l2cache.ReadReq_mshr_miss_rate     0.154590                       # mshr miss rate for ReadReq accesses
-system.cpu.l2cache.ReadExReq_mshr_miss_rate     0.235315                       # mshr miss rate for ReadExReq accesses
-system.cpu.l2cache.demand_mshr_miss_rate     0.197999                       # mshr miss rate for demand accesses
-system.cpu.l2cache.overall_mshr_miss_rate     0.197999                       # mshr miss rate for overall accesses
-system.cpu.l2cache.ReadReq_avg_mshr_miss_latency 31005.533275                       # average ReadReq mshr miss latency
-system.cpu.l2cache.ReadExReq_avg_mshr_miss_latency 31139.870917                       # average ReadExReq mshr miss latency
-system.cpu.l2cache.demand_avg_mshr_miss_latency 31091.385972                       # average overall mshr miss latency
-system.cpu.l2cache.overall_avg_mshr_miss_latency 31091.385972                       # average overall mshr miss latency
+system.cpu.l2cache.ReadReq_mshr_miss_rate     0.154524                       # mshr miss rate for ReadReq accesses
+system.cpu.l2cache.ReadExReq_mshr_miss_rate     0.235270                       # mshr miss rate for ReadExReq accesses
+system.cpu.l2cache.demand_mshr_miss_rate     0.197937                       # mshr miss rate for demand accesses
+system.cpu.l2cache.overall_mshr_miss_rate     0.197937                       # mshr miss rate for overall accesses
+system.cpu.l2cache.ReadReq_avg_mshr_miss_latency 31004.871501                       # average ReadReq mshr miss latency
+system.cpu.l2cache.ReadExReq_avg_mshr_miss_latency 31000.698514                       # average ReadExReq mshr miss latency
+system.cpu.l2cache.demand_avg_mshr_miss_latency 31002.204730                       # average overall mshr miss latency
+system.cpu.l2cache.overall_avg_mshr_miss_latency 31002.204730                       # average overall mshr miss latency
 system.cpu.l2cache.overall_avg_mshr_uncacheable_latency     no_value                       # average overall mshr uncacheable latency
 system.cpu.l2cache.mshr_cap_events                  0                       # number of times MSHR cap was activated
 system.cpu.l2cache.soft_prefetch_mshr_full            0                       # number of mshr full events for SW prefetching instrutions
diff --git a/tests/long/10.linux-boot/ref/x86/linux/pc-o3-timing/config.ini b/tests/long/10.linux-boot/ref/x86/linux/pc-o3-timing/config.ini
index f406247..9b8aaf5 100644
--- a/tests/long/10.linux-boot/ref/x86/linux/pc-o3-timing/config.ini
+++ b/tests/long/10.linux-boot/ref/x86/linux/pc-o3-timing/config.ini
@@ -15,7 +15,7 @@
 init_param=0
 intel_mp_pointer=system.intel_mp_pointer
 intel_mp_table=system.intel_mp_table
-kernel=/dist/m5/system/binaries/x86_64-vmlinux-2.6.22.9
+kernel=/scratch/nilay/GEM5/system/binaries/x86_64-vmlinux-2.6.22.9
 load_addr_mask=18446744073709551615
 mem_mode=timing
 memories=system.physmem
@@ -122,6 +122,7 @@
 max_insts_any_thread=0
 max_loads_all_threads=0
 max_loads_any_thread=0
+needsTSO=true
 numIQEntries=64
 numPhysFloatRegs=256
 numPhysIntRegs=256
@@ -1311,7 +1312,7 @@
 
 [system.pc.south_bridge.ide.disks0.image.child]
 type=RawDiskImage
-image_file=/dist/m5/system/disks/linux-x86.img
+image_file=/scratch/nilay/GEM5/system/disks/linux-x86.img
 read_only=true
 
 [system.pc.south_bridge.ide.disks1]
@@ -1331,7 +1332,7 @@
 
 [system.pc.south_bridge.ide.disks1.image.child]
 type=RawDiskImage
-image_file=/dist/m5/system/disks/linux-bigswap2.img
+image_file=/scratch/nilay/GEM5/system/disks/linux-bigswap2.img
 read_only=true
 
 [system.pc.south_bridge.int_lines0]
diff --git a/tests/long/10.linux-boot/ref/x86/linux/pc-o3-timing/simout b/tests/long/10.linux-boot/ref/x86/linux/pc-o3-timing/simout
index 873e1be..9036859 100755
--- a/tests/long/10.linux-boot/ref/x86/linux/pc-o3-timing/simout
+++ b/tests/long/10.linux-boot/ref/x86/linux/pc-o3-timing/simout
@@ -1,13 +1,15 @@
+Redirecting stdout to build/X86_FS/tests/opt/long/10.linux-boot/x86/linux/pc-o3-timing/simout
+Redirecting stderr to build/X86_FS/tests/opt/long/10.linux-boot/x86/linux/pc-o3-timing/simerr
 gem5 Simulator System.  http://gem5.org
 gem5 is copyrighted software; use the --copyright option for details.
 
-gem5 compiled Jan 23 2012 04:12:17
-gem5 started Jan 23 2012 08:29:15
-gem5 executing on zizzer
+gem5 compiled Jan 28 2012 16:24:13
+gem5 started Jan 28 2012 16:29:18
+gem5 executing on ribera.cs.wisc.edu
 command line: build/X86_FS/gem5.opt -d build/X86_FS/tests/opt/long/10.linux-boot/x86/linux/pc-o3-timing -re tests/run.py build/X86_FS/tests/opt/long/10.linux-boot/x86/linux/pc-o3-timing
 warning: add_child('terminal'): child 'terminal' already has parent
 Global frequency set at 1000000000000 ticks per second
       0: rtc: Real-time clock set to Sun Jan  1 00:00:00 2012
-info: kernel located at: /dist/m5/system/binaries/x86_64-vmlinux-2.6.22.9
+info: kernel located at: /scratch/nilay/GEM5/system/binaries/x86_64-vmlinux-2.6.22.9
 info: Entering event queue @ 0.  Starting simulation...
-Exiting @ tick 5161177988500 because m5_exit instruction encountered
+Exiting @ tick 5164643202500 because m5_exit instruction encountered
diff --git a/tests/long/10.linux-boot/ref/x86/linux/pc-o3-timing/stats.txt b/tests/long/10.linux-boot/ref/x86/linux/pc-o3-timing/stats.txt
index c625269..9cc68e7 100644
--- a/tests/long/10.linux-boot/ref/x86/linux/pc-o3-timing/stats.txt
+++ b/tests/long/10.linux-boot/ref/x86/linux/pc-o3-timing/stats.txt
@@ -1,108 +1,108 @@
 
 ---------- Begin Simulation Statistics ----------
-sim_seconds                                  5.161178                       # Number of seconds simulated
-sim_ticks                                5161177988500                       # Number of ticks simulated
-final_tick                               5161177988500                       # Number of ticks from beginning of simulation (restored from checkpoints and never reset)
+sim_seconds                                  5.164643                       # Number of seconds simulated
+sim_ticks                                5164643202500                       # Number of ticks simulated
+final_tick                               5164643202500                       # Number of ticks from beginning of simulation (restored from checkpoints and never reset)
 sim_freq                                 1000000000000                       # Frequency of simulated ticks
-host_inst_rate                                 290092                       # Simulator instruction rate (inst/s)
-host_tick_rate                             1780684720                       # Simulator tick rate (ticks/s)
-host_mem_usage                                 364016                       # Number of bytes of host memory used
-host_seconds                                  2898.42                       # Real time elapsed on the host
-sim_insts                                   840808469                       # Number of instructions simulated
-system.physmem.bytes_read                    16106624                       # Number of bytes read from this memory
-system.physmem.bytes_inst_read                1233856                       # Number of instructions bytes read from this memory
-system.physmem.bytes_written                 12115136                       # Number of bytes written to this memory
-system.physmem.num_reads                       251666                       # Number of read requests responded to by this memory
-system.physmem.num_writes                      189299                       # Number of write requests responded to by this memory
+host_inst_rate                                 258156                       # Simulator instruction rate (inst/s)
+host_tick_rate                             1586008699                       # Simulator tick rate (ticks/s)
+host_mem_usage                                 390600                       # Number of bytes of host memory used
+host_seconds                                  3256.38                       # Real time elapsed on the host
+sim_insts                                   840653382                       # Number of instructions simulated
+system.physmem.bytes_read                    15885120                       # Number of bytes read from this memory
+system.physmem.bytes_inst_read                1235904                       # Number of instructions bytes read from this memory
+system.physmem.bytes_written                 12075328                       # Number of bytes written to this memory
+system.physmem.num_reads                       248205                       # Number of read requests responded to by this memory
+system.physmem.num_writes                      188677                       # Number of write requests responded to by this memory
 system.physmem.num_other                            0                       # Number of other requests responded to by this memory
-system.physmem.bw_read                        3120726                       # Total read bandwidth from this memory (bytes/s)
-system.physmem.bw_inst_read                    239065                       # Instruction read bandwidth from this memory (bytes/s)
-system.physmem.bw_write                       2347359                       # Write bandwidth from this memory (bytes/s)
-system.physmem.bw_total                       5468085                       # Total bandwidth to/from this memory (bytes/s)
-system.l2c.replacements                        169467                       # number of replacements
-system.l2c.tagsinuse                     38339.786444                       # Cycle average of tags in use
-system.l2c.total_refs                         3812924                       # Total number of references to valid blocks.
-system.l2c.sampled_refs                        204660                       # Sample count of references to valid blocks.
-system.l2c.avg_refs                         18.630529                       # Average number of references to valid blocks.
+system.physmem.bw_read                        3075744                       # Total read bandwidth from this memory (bytes/s)
+system.physmem.bw_inst_read                    239301                       # Instruction read bandwidth from this memory (bytes/s)
+system.physmem.bw_write                       2338076                       # Write bandwidth from this memory (bytes/s)
+system.physmem.bw_total                       5413820                       # Total bandwidth to/from this memory (bytes/s)
+system.l2c.replacements                        166524                       # number of replacements
+system.l2c.tagsinuse                     37860.019471                       # Cycle average of tags in use
+system.l2c.total_refs                         3791499                       # Total number of references to valid blocks.
+system.l2c.sampled_refs                        201257                       # Sample count of references to valid blocks.
+system.l2c.avg_refs                         18.839091                       # Average number of references to valid blocks.
 system.l2c.warmup_cycle                             0                       # Cycle when the warmup percentage was hit.
-system.l2c.occ_blocks::0                 11950.408174                       # Average occupied blocks per context
-system.l2c.occ_blocks::1                 26389.378270                       # Average occupied blocks per context
-system.l2c.occ_percent::0                    0.182349                       # Average percentage of cache occupancy
-system.l2c.occ_percent::1                    0.402670                       # Average percentage of cache occupancy
-system.l2c.ReadReq_hits::0                    2335607                       # number of ReadReq hits
-system.l2c.ReadReq_hits::1                     145488                       # number of ReadReq hits
-system.l2c.ReadReq_hits::total                2481095                       # number of ReadReq hits
-system.l2c.Writeback_hits::0                  1594493                       # number of Writeback hits
-system.l2c.Writeback_hits::total              1594493                       # number of Writeback hits
-system.l2c.UpgradeReq_hits::0                     327                       # number of UpgradeReq hits
-system.l2c.UpgradeReq_hits::total                 327                       # number of UpgradeReq hits
-system.l2c.ReadExReq_hits::0                   150672                       # number of ReadExReq hits
-system.l2c.ReadExReq_hits::total               150672                       # number of ReadExReq hits
-system.l2c.demand_hits::0                     2486279                       # number of demand (read+write) hits
-system.l2c.demand_hits::1                      145488                       # number of demand (read+write) hits
-system.l2c.demand_hits::total                 2631767                       # number of demand (read+write) hits
-system.l2c.overall_hits::0                    2486279                       # number of overall hits
-system.l2c.overall_hits::1                     145488                       # number of overall hits
-system.l2c.overall_hits::total                2631767                       # number of overall hits
-system.l2c.ReadReq_misses::0                    66850                       # number of ReadReq misses
-system.l2c.ReadReq_misses::1                      109                       # number of ReadReq misses
-system.l2c.ReadReq_misses::total                66959                       # number of ReadReq misses
-system.l2c.UpgradeReq_misses::0                  3932                       # number of UpgradeReq misses
-system.l2c.UpgradeReq_misses::total              3932                       # number of UpgradeReq misses
-system.l2c.ReadExReq_misses::0                 142221                       # number of ReadExReq misses
-system.l2c.ReadExReq_misses::total             142221                       # number of ReadExReq misses
-system.l2c.demand_misses::0                    209071                       # number of demand (read+write) misses
-system.l2c.demand_misses::1                       109                       # number of demand (read+write) misses
-system.l2c.demand_misses::total                209180                       # number of demand (read+write) misses
-system.l2c.overall_misses::0                   209071                       # number of overall misses
-system.l2c.overall_misses::1                      109                       # number of overall misses
-system.l2c.overall_misses::total               209180                       # number of overall misses
-system.l2c.ReadReq_miss_latency            3511861000                       # number of ReadReq miss cycles
-system.l2c.UpgradeReq_miss_latency           38996000                       # number of UpgradeReq miss cycles
-system.l2c.ReadExReq_miss_latency          7442399000                       # number of ReadExReq miss cycles
-system.l2c.demand_miss_latency            10954260000                       # number of demand (read+write) miss cycles
-system.l2c.overall_miss_latency           10954260000                       # number of overall miss cycles
-system.l2c.ReadReq_accesses::0                2402457                       # number of ReadReq accesses(hits+misses)
-system.l2c.ReadReq_accesses::1                 145597                       # number of ReadReq accesses(hits+misses)
-system.l2c.ReadReq_accesses::total            2548054                       # number of ReadReq accesses(hits+misses)
-system.l2c.Writeback_accesses::0              1594493                       # number of Writeback accesses(hits+misses)
-system.l2c.Writeback_accesses::total          1594493                       # number of Writeback accesses(hits+misses)
-system.l2c.UpgradeReq_accesses::0                4259                       # number of UpgradeReq accesses(hits+misses)
-system.l2c.UpgradeReq_accesses::total            4259                       # number of UpgradeReq accesses(hits+misses)
-system.l2c.ReadExReq_accesses::0               292893                       # number of ReadExReq accesses(hits+misses)
-system.l2c.ReadExReq_accesses::total           292893                       # number of ReadExReq accesses(hits+misses)
-system.l2c.demand_accesses::0                 2695350                       # number of demand (read+write) accesses
-system.l2c.demand_accesses::1                  145597                       # number of demand (read+write) accesses
-system.l2c.demand_accesses::total             2840947                       # number of demand (read+write) accesses
-system.l2c.overall_accesses::0                2695350                       # number of overall (read+write) accesses
-system.l2c.overall_accesses::1                 145597                       # number of overall (read+write) accesses
-system.l2c.overall_accesses::total            2840947                       # number of overall (read+write) accesses
-system.l2c.ReadReq_miss_rate::0              0.027826                       # miss rate for ReadReq accesses
-system.l2c.ReadReq_miss_rate::1              0.000749                       # miss rate for ReadReq accesses
-system.l2c.ReadReq_miss_rate::total          0.028574                       # miss rate for ReadReq accesses
-system.l2c.UpgradeReq_miss_rate::0           0.923221                       # miss rate for UpgradeReq accesses
-system.l2c.ReadExReq_miss_rate::0            0.485573                       # miss rate for ReadExReq accesses
-system.l2c.demand_miss_rate::0               0.077567                       # miss rate for demand accesses
-system.l2c.demand_miss_rate::1               0.000749                       # miss rate for demand accesses
-system.l2c.demand_miss_rate::total           0.078316                       # miss rate for demand accesses
-system.l2c.overall_miss_rate::0              0.077567                       # miss rate for overall accesses
-system.l2c.overall_miss_rate::1              0.000749                       # miss rate for overall accesses
-system.l2c.overall_miss_rate::total          0.078316                       # miss rate for overall accesses
-system.l2c.ReadReq_avg_miss_latency::0   52533.448018                       # average ReadReq miss latency
-system.l2c.ReadReq_avg_miss_latency::1   32218908.256881                       # average ReadReq miss latency
-system.l2c.ReadReq_avg_miss_latency::total 32271441.704899                       # average ReadReq miss latency
-system.l2c.UpgradeReq_avg_miss_latency::0  9917.599186                       # average UpgradeReq miss latency
+system.l2c.occ_blocks::0                 11072.402172                       # Average occupied blocks per context
+system.l2c.occ_blocks::1                 26787.617299                       # Average occupied blocks per context
+system.l2c.occ_percent::0                    0.168951                       # Average percentage of cache occupancy
+system.l2c.occ_percent::1                    0.408747                       # Average percentage of cache occupancy
+system.l2c.ReadReq_hits::0                    2329446                       # number of ReadReq hits
+system.l2c.ReadReq_hits::1                     146092                       # number of ReadReq hits
+system.l2c.ReadReq_hits::total                2475538                       # number of ReadReq hits
+system.l2c.Writeback_hits::0                  1599025                       # number of Writeback hits
+system.l2c.Writeback_hits::total              1599025                       # number of Writeback hits
+system.l2c.UpgradeReq_hits::0                     316                       # number of UpgradeReq hits
+system.l2c.UpgradeReq_hits::total                 316                       # number of UpgradeReq hits
+system.l2c.ReadExReq_hits::0                   151571                       # number of ReadExReq hits
+system.l2c.ReadExReq_hits::total               151571                       # number of ReadExReq hits
+system.l2c.demand_hits::0                     2481017                       # number of demand (read+write) hits
+system.l2c.demand_hits::1                      146092                       # number of demand (read+write) hits
+system.l2c.demand_hits::total                 2627109                       # number of demand (read+write) hits
+system.l2c.overall_hits::0                    2481017                       # number of overall hits
+system.l2c.overall_hits::1                     146092                       # number of overall hits
+system.l2c.overall_hits::total                2627109                       # number of overall hits
+system.l2c.ReadReq_misses::0                    64214                       # number of ReadReq misses
+system.l2c.ReadReq_misses::1                      107                       # number of ReadReq misses
+system.l2c.ReadReq_misses::total                64321                       # number of ReadReq misses
+system.l2c.UpgradeReq_misses::0                  5085                       # number of UpgradeReq misses
+system.l2c.UpgradeReq_misses::total              5085                       # number of UpgradeReq misses
+system.l2c.ReadExReq_misses::0                 141328                       # number of ReadExReq misses
+system.l2c.ReadExReq_misses::total             141328                       # number of ReadExReq misses
+system.l2c.demand_misses::0                    205542                       # number of demand (read+write) misses
+system.l2c.demand_misses::1                       107                       # number of demand (read+write) misses
+system.l2c.demand_misses::total                205649                       # number of demand (read+write) misses
+system.l2c.overall_misses::0                   205542                       # number of overall misses
+system.l2c.overall_misses::1                      107                       # number of overall misses
+system.l2c.overall_misses::total               205649                       # number of overall misses
+system.l2c.ReadReq_miss_latency            3375006500                       # number of ReadReq miss cycles
+system.l2c.UpgradeReq_miss_latency           39785500                       # number of UpgradeReq miss cycles
+system.l2c.ReadExReq_miss_latency          7360156500                       # number of ReadExReq miss cycles
+system.l2c.demand_miss_latency            10735163000                       # number of demand (read+write) miss cycles
+system.l2c.overall_miss_latency           10735163000                       # number of overall miss cycles
+system.l2c.ReadReq_accesses::0                2393660                       # number of ReadReq accesses(hits+misses)
+system.l2c.ReadReq_accesses::1                 146199                       # number of ReadReq accesses(hits+misses)
+system.l2c.ReadReq_accesses::total            2539859                       # number of ReadReq accesses(hits+misses)
+system.l2c.Writeback_accesses::0              1599025                       # number of Writeback accesses(hits+misses)
+system.l2c.Writeback_accesses::total          1599025                       # number of Writeback accesses(hits+misses)
+system.l2c.UpgradeReq_accesses::0                5401                       # number of UpgradeReq accesses(hits+misses)
+system.l2c.UpgradeReq_accesses::total            5401                       # number of UpgradeReq accesses(hits+misses)
+system.l2c.ReadExReq_accesses::0               292899                       # number of ReadExReq accesses(hits+misses)
+system.l2c.ReadExReq_accesses::total           292899                       # number of ReadExReq accesses(hits+misses)
+system.l2c.demand_accesses::0                 2686559                       # number of demand (read+write) accesses
+system.l2c.demand_accesses::1                  146199                       # number of demand (read+write) accesses
+system.l2c.demand_accesses::total             2832758                       # number of demand (read+write) accesses
+system.l2c.overall_accesses::0                2686559                       # number of overall (read+write) accesses
+system.l2c.overall_accesses::1                 146199                       # number of overall (read+write) accesses
+system.l2c.overall_accesses::total            2832758                       # number of overall (read+write) accesses
+system.l2c.ReadReq_miss_rate::0              0.026827                       # miss rate for ReadReq accesses
+system.l2c.ReadReq_miss_rate::1              0.000732                       # miss rate for ReadReq accesses
+system.l2c.ReadReq_miss_rate::total          0.027559                       # miss rate for ReadReq accesses
+system.l2c.UpgradeReq_miss_rate::0           0.941492                       # miss rate for UpgradeReq accesses
+system.l2c.ReadExReq_miss_rate::0            0.482514                       # miss rate for ReadExReq accesses
+system.l2c.demand_miss_rate::0               0.076508                       # miss rate for demand accesses
+system.l2c.demand_miss_rate::1               0.000732                       # miss rate for demand accesses
+system.l2c.demand_miss_rate::total           0.077239                       # miss rate for demand accesses
+system.l2c.overall_miss_rate::0              0.076508                       # miss rate for overall accesses
+system.l2c.overall_miss_rate::1              0.000732                       # miss rate for overall accesses
+system.l2c.overall_miss_rate::total          0.077239                       # miss rate for overall accesses
+system.l2c.ReadReq_avg_miss_latency::0   52558.733298                       # average ReadReq miss latency
+system.l2c.ReadReq_avg_miss_latency::1   31542116.822430                       # average ReadReq miss latency
+system.l2c.ReadReq_avg_miss_latency::total 31594675.555728                       # average ReadReq miss latency
+system.l2c.UpgradeReq_avg_miss_latency::0  7824.090462                       # average UpgradeReq miss latency
 system.l2c.UpgradeReq_avg_miss_latency::1          inf                       # average UpgradeReq miss latency
 system.l2c.UpgradeReq_avg_miss_latency::total          inf                       # average UpgradeReq miss latency
-system.l2c.ReadExReq_avg_miss_latency::0 52329.817678                       # average ReadExReq miss latency
+system.l2c.ReadExReq_avg_miss_latency::0 52078.544238                       # average ReadExReq miss latency
 system.l2c.ReadExReq_avg_miss_latency::1          inf                       # average ReadExReq miss latency
 system.l2c.ReadExReq_avg_miss_latency::total          inf                       # average ReadExReq miss latency
-system.l2c.demand_avg_miss_latency::0    52394.928039                       # average overall miss latency
-system.l2c.demand_avg_miss_latency::1    100497798.165138                       # average overall miss latency
-system.l2c.demand_avg_miss_latency::total 100550193.093176                       # average overall miss latency
-system.l2c.overall_avg_miss_latency::0   52394.928039                       # average overall miss latency
-system.l2c.overall_avg_miss_latency::1   100497798.165138                       # average overall miss latency
-system.l2c.overall_avg_miss_latency::total 100550193.093176                       # average overall miss latency
+system.l2c.demand_avg_miss_latency::0    52228.561559                       # average overall miss latency
+system.l2c.demand_avg_miss_latency::1    100328626.168224                       # average overall miss latency
+system.l2c.demand_avg_miss_latency::total 100380854.729784                       # average overall miss latency
+system.l2c.overall_avg_miss_latency::0   52228.561559                       # average overall miss latency
+system.l2c.overall_avg_miss_latency::1   100328626.168224                       # average overall miss latency
+system.l2c.overall_avg_miss_latency::total 100380854.729784                       # average overall miss latency
 system.l2c.blocked_cycles::no_mshrs                 0                       # number of cycles access was blocked
 system.l2c.blocked_cycles::no_targets               0                       # number of cycles access was blocked
 system.l2c.blocked::no_mshrs                        0                       # number of cycles access was blocked
@@ -111,88 +111,88 @@
 system.l2c.avg_blocked_cycles::no_targets     no_value                       # average number of cycles each access was blocked
 system.l2c.fast_writes                              0                       # number of fast writes performed
 system.l2c.cache_copies                             0                       # number of cache copies performed
-system.l2c.writebacks                          142631                       # number of writebacks
+system.l2c.writebacks                          142010                       # number of writebacks
 system.l2c.ReadReq_mshr_hits                        2                       # number of ReadReq MSHR hits
 system.l2c.demand_mshr_hits                         2                       # number of demand (read+write) MSHR hits
 system.l2c.overall_mshr_hits                        2                       # number of overall MSHR hits
-system.l2c.ReadReq_mshr_misses                  66957                       # number of ReadReq MSHR misses
-system.l2c.UpgradeReq_mshr_misses                3932                       # number of UpgradeReq MSHR misses
-system.l2c.ReadExReq_mshr_misses               142221                       # number of ReadExReq MSHR misses
-system.l2c.demand_mshr_misses                  209178                       # number of demand (read+write) MSHR misses
-system.l2c.overall_mshr_misses                 209178                       # number of overall MSHR misses
+system.l2c.ReadReq_mshr_misses                  64319                       # number of ReadReq MSHR misses
+system.l2c.UpgradeReq_mshr_misses                5085                       # number of UpgradeReq MSHR misses
+system.l2c.ReadExReq_mshr_misses               141328                       # number of ReadExReq MSHR misses
+system.l2c.demand_mshr_misses                  205647                       # number of demand (read+write) MSHR misses
+system.l2c.overall_mshr_misses                 205647                       # number of overall MSHR misses
 system.l2c.overall_mshr_uncacheable_misses            0                       # number of overall MSHR uncacheable misses
-system.l2c.ReadReq_mshr_miss_latency       2695362500                       # number of ReadReq MSHR miss cycles
-system.l2c.UpgradeReq_mshr_miss_latency     157637000                       # number of UpgradeReq MSHR miss cycles
-system.l2c.ReadExReq_mshr_miss_latency     5708607000                       # number of ReadExReq MSHR miss cycles
-system.l2c.demand_mshr_miss_latency        8403969500                       # number of demand (read+write) MSHR miss cycles
-system.l2c.overall_mshr_miss_latency       8403969500                       # number of overall MSHR miss cycles
-system.l2c.ReadReq_mshr_uncacheable_latency  59978490000                       # number of ReadReq MSHR uncacheable cycles
-system.l2c.WriteReq_mshr_uncacheable_latency   1230737500                       # number of WriteReq MSHR uncacheable cycles
-system.l2c.overall_mshr_uncacheable_latency  61209227500                       # number of overall MSHR uncacheable cycles
-system.l2c.ReadReq_mshr_miss_rate::0         0.027870                       # mshr miss rate for ReadReq accesses
-system.l2c.ReadReq_mshr_miss_rate::1         0.459879                       # mshr miss rate for ReadReq accesses
-system.l2c.ReadReq_mshr_miss_rate::total     0.487749                       # mshr miss rate for ReadReq accesses
-system.l2c.UpgradeReq_mshr_miss_rate::0      0.923221                       # mshr miss rate for UpgradeReq accesses
+system.l2c.ReadReq_mshr_miss_latency       2589128000                       # number of ReadReq MSHR miss cycles
+system.l2c.UpgradeReq_mshr_miss_latency     203766500                       # number of UpgradeReq MSHR miss cycles
+system.l2c.ReadExReq_mshr_miss_latency     5654353000                       # number of ReadExReq MSHR miss cycles
+system.l2c.demand_mshr_miss_latency        8243481000                       # number of demand (read+write) MSHR miss cycles
+system.l2c.overall_mshr_miss_latency       8243481000                       # number of overall MSHR miss cycles
+system.l2c.ReadReq_mshr_uncacheable_latency  59975261500                       # number of ReadReq MSHR uncacheable cycles
+system.l2c.WriteReq_mshr_uncacheable_latency   1228545000                       # number of WriteReq MSHR uncacheable cycles
+system.l2c.overall_mshr_uncacheable_latency  61203806500                       # number of overall MSHR uncacheable cycles
+system.l2c.ReadReq_mshr_miss_rate::0         0.026871                       # mshr miss rate for ReadReq accesses
+system.l2c.ReadReq_mshr_miss_rate::1         0.439941                       # mshr miss rate for ReadReq accesses
+system.l2c.ReadReq_mshr_miss_rate::total     0.466812                       # mshr miss rate for ReadReq accesses
+system.l2c.UpgradeReq_mshr_miss_rate::0      0.941492                       # mshr miss rate for UpgradeReq accesses
 system.l2c.UpgradeReq_mshr_miss_rate::1           inf                       # mshr miss rate for UpgradeReq accesses
 system.l2c.UpgradeReq_mshr_miss_rate::total          inf                       # mshr miss rate for UpgradeReq accesses
-system.l2c.ReadExReq_mshr_miss_rate::0       0.485573                       # mshr miss rate for ReadExReq accesses
+system.l2c.ReadExReq_mshr_miss_rate::0       0.482514                       # mshr miss rate for ReadExReq accesses
 system.l2c.ReadExReq_mshr_miss_rate::1            inf                       # mshr miss rate for ReadExReq accesses
 system.l2c.ReadExReq_mshr_miss_rate::total          inf                       # mshr miss rate for ReadExReq accesses
-system.l2c.demand_mshr_miss_rate::0          0.077607                       # mshr miss rate for demand accesses
-system.l2c.demand_mshr_miss_rate::1          1.436692                       # mshr miss rate for demand accesses
-system.l2c.demand_mshr_miss_rate::total      1.514299                       # mshr miss rate for demand accesses
-system.l2c.overall_mshr_miss_rate::0         0.077607                       # mshr miss rate for overall accesses
-system.l2c.overall_mshr_miss_rate::1         1.436692                       # mshr miss rate for overall accesses
-system.l2c.overall_mshr_miss_rate::total     1.514299                       # mshr miss rate for overall accesses
-system.l2c.ReadReq_avg_mshr_miss_latency 40255.126424                       # average ReadReq mshr miss latency
-system.l2c.UpgradeReq_avg_mshr_miss_latency 40090.793489                       # average UpgradeReq mshr miss latency
-system.l2c.ReadExReq_avg_mshr_miss_latency 40138.987913                       # average ReadExReq mshr miss latency
-system.l2c.demand_avg_mshr_miss_latency  40176.163363                       # average overall mshr miss latency
-system.l2c.overall_avg_mshr_miss_latency 40176.163363                       # average overall mshr miss latency
+system.l2c.demand_mshr_miss_rate::0          0.076547                       # mshr miss rate for demand accesses
+system.l2c.demand_mshr_miss_rate::1          1.406624                       # mshr miss rate for demand accesses
+system.l2c.demand_mshr_miss_rate::total      1.483170                       # mshr miss rate for demand accesses
+system.l2c.overall_mshr_miss_rate::0         0.076547                       # mshr miss rate for overall accesses
+system.l2c.overall_mshr_miss_rate::1         1.406624                       # mshr miss rate for overall accesses
+system.l2c.overall_mshr_miss_rate::total     1.483170                       # mshr miss rate for overall accesses
+system.l2c.ReadReq_avg_mshr_miss_latency 40254.481568                       # average ReadReq mshr miss latency
+system.l2c.UpgradeReq_avg_mshr_miss_latency 40072.074730                       # average UpgradeReq mshr miss latency
+system.l2c.ReadExReq_avg_mshr_miss_latency 40008.724386                       # average ReadExReq mshr miss latency
+system.l2c.demand_avg_mshr_miss_latency  40085.588411                       # average overall mshr miss latency
+system.l2c.overall_avg_mshr_miss_latency 40085.588411                       # average overall mshr miss latency
 system.l2c.ReadReq_avg_mshr_uncacheable_latency          inf                       # average ReadReq mshr uncacheable latency
 system.l2c.WriteReq_avg_mshr_uncacheable_latency          inf                       # average WriteReq mshr uncacheable latency
 system.l2c.overall_avg_mshr_uncacheable_latency          inf                       # average overall mshr uncacheable latency
 system.l2c.mshr_cap_events                          0                       # number of times MSHR cap was activated
 system.l2c.soft_prefetch_mshr_full                  0                       # number of mshr full events for SW prefetching instrutions
 system.l2c.no_allocate_misses                       0                       # Number of misses that were no-allocate
-system.iocache.replacements                     47573                       # number of replacements
-system.iocache.tagsinuse                     0.195398                       # Cycle average of tags in use
+system.iocache.replacements                     47574                       # number of replacements
+system.iocache.tagsinuse                     0.187855                       # Cycle average of tags in use
 system.iocache.total_refs                           0                       # Total number of references to valid blocks.
-system.iocache.sampled_refs                     47589                       # Sample count of references to valid blocks.
+system.iocache.sampled_refs                     47590                       # Sample count of references to valid blocks.
 system.iocache.avg_refs                             0                       # Average number of references to valid blocks.
-system.iocache.warmup_cycle              4994542788000                       # Cycle when the warmup percentage was hit.
-system.iocache.occ_blocks::1                 0.195398                       # Average occupied blocks per context
-system.iocache.occ_percent::1                0.012212                       # Average percentage of cache occupancy
+system.iocache.warmup_cycle              4996389374000                       # Cycle when the warmup percentage was hit.
+system.iocache.occ_blocks::1                 0.187855                       # Average occupied blocks per context
+system.iocache.occ_percent::1                0.011741                       # Average percentage of cache occupancy
 system.iocache.demand_hits::0                       0                       # number of demand (read+write) hits
 system.iocache.demand_hits::1                       0                       # number of demand (read+write) hits
 system.iocache.demand_hits::total                   0                       # number of demand (read+write) hits
 system.iocache.overall_hits::0                      0                       # number of overall hits
 system.iocache.overall_hits::1                      0                       # number of overall hits
 system.iocache.overall_hits::total                  0                       # number of overall hits
-system.iocache.ReadReq_misses::1                  907                       # number of ReadReq misses
-system.iocache.ReadReq_misses::total              907                       # number of ReadReq misses
+system.iocache.ReadReq_misses::1                  909                       # number of ReadReq misses
+system.iocache.ReadReq_misses::total              909                       # number of ReadReq misses
 system.iocache.WriteReq_misses::1               46720                       # number of WriteReq misses
 system.iocache.WriteReq_misses::total           46720                       # number of WriteReq misses
 system.iocache.demand_misses::0                     0                       # number of demand (read+write) misses
-system.iocache.demand_misses::1                 47627                       # number of demand (read+write) misses
-system.iocache.demand_misses::total             47627                       # number of demand (read+write) misses
+system.iocache.demand_misses::1                 47629                       # number of demand (read+write) misses
+system.iocache.demand_misses::total             47629                       # number of demand (read+write) misses
 system.iocache.overall_misses::0                    0                       # number of overall misses
-system.iocache.overall_misses::1                47627                       # number of overall misses
-system.iocache.overall_misses::total            47627                       # number of overall misses
-system.iocache.ReadReq_miss_latency         113669932                       # number of ReadReq miss cycles
-system.iocache.WriteReq_miss_latency       6372391160                       # number of WriteReq miss cycles
-system.iocache.demand_miss_latency         6486061092                       # number of demand (read+write) miss cycles
-system.iocache.overall_miss_latency        6486061092                       # number of overall miss cycles
-system.iocache.ReadReq_accesses::1                907                       # number of ReadReq accesses(hits+misses)
-system.iocache.ReadReq_accesses::total            907                       # number of ReadReq accesses(hits+misses)
+system.iocache.overall_misses::1                47629                       # number of overall misses
+system.iocache.overall_misses::total            47629                       # number of overall misses
+system.iocache.ReadReq_miss_latency         113959932                       # number of ReadReq miss cycles
+system.iocache.WriteReq_miss_latency       6369072160                       # number of WriteReq miss cycles
+system.iocache.demand_miss_latency         6483032092                       # number of demand (read+write) miss cycles
+system.iocache.overall_miss_latency        6483032092                       # number of overall miss cycles
+system.iocache.ReadReq_accesses::1                909                       # number of ReadReq accesses(hits+misses)
+system.iocache.ReadReq_accesses::total            909                       # number of ReadReq accesses(hits+misses)
 system.iocache.WriteReq_accesses::1             46720                       # number of WriteReq accesses(hits+misses)
 system.iocache.WriteReq_accesses::total         46720                       # number of WriteReq accesses(hits+misses)
 system.iocache.demand_accesses::0                   0                       # number of demand (read+write) accesses
-system.iocache.demand_accesses::1               47627                       # number of demand (read+write) accesses
-system.iocache.demand_accesses::total           47627                       # number of demand (read+write) accesses
+system.iocache.demand_accesses::1               47629                       # number of demand (read+write) accesses
+system.iocache.demand_accesses::total           47629                       # number of demand (read+write) accesses
 system.iocache.overall_accesses::0                  0                       # number of overall (read+write) accesses
-system.iocache.overall_accesses::1              47627                       # number of overall (read+write) accesses
-system.iocache.overall_accesses::total          47627                       # number of overall (read+write) accesses
+system.iocache.overall_accesses::1              47629                       # number of overall (read+write) accesses
+system.iocache.overall_accesses::total          47629                       # number of overall (read+write) accesses
 system.iocache.ReadReq_miss_rate::1                 1                       # miss rate for ReadReq accesses
 system.iocache.WriteReq_miss_rate::1                1                       # miss rate for WriteReq accesses
 system.iocache.demand_miss_rate::0           no_value                       # miss rate for demand accesses
@@ -202,37 +202,37 @@
 system.iocache.overall_miss_rate::1                 1                       # miss rate for overall accesses
 system.iocache.overall_miss_rate::total      no_value                       # miss rate for overall accesses
 system.iocache.ReadReq_avg_miss_latency::0          inf                       # average ReadReq miss latency
-system.iocache.ReadReq_avg_miss_latency::1 125325.173098                       # average ReadReq miss latency
+system.iocache.ReadReq_avg_miss_latency::1 125368.462046                       # average ReadReq miss latency
 system.iocache.ReadReq_avg_miss_latency::total          inf                       # average ReadReq miss latency
 system.iocache.WriteReq_avg_miss_latency::0          inf                       # average WriteReq miss latency
-system.iocache.WriteReq_avg_miss_latency::1 136395.358733                       # average WriteReq miss latency
+system.iocache.WriteReq_avg_miss_latency::1 136324.318493                       # average WriteReq miss latency
 system.iocache.WriteReq_avg_miss_latency::total          inf                       # average WriteReq miss latency
 system.iocache.demand_avg_miss_latency::0          inf                       # average overall miss latency
-system.iocache.demand_avg_miss_latency::1 136184.540114                       # average overall miss latency
+system.iocache.demand_avg_miss_latency::1 136115.225850                       # average overall miss latency
 system.iocache.demand_avg_miss_latency::total          inf                       # average overall miss latency
 system.iocache.overall_avg_miss_latency::0          inf                       # average overall miss latency
-system.iocache.overall_avg_miss_latency::1 136184.540114                       # average overall miss latency
+system.iocache.overall_avg_miss_latency::1 136115.225850                       # average overall miss latency
 system.iocache.overall_avg_miss_latency::total          inf                       # average overall miss latency
-system.iocache.blocked_cycles::no_mshrs      68679532                       # number of cycles access was blocked
+system.iocache.blocked_cycles::no_mshrs      68773500                       # number of cycles access was blocked
 system.iocache.blocked_cycles::no_targets            0                       # number of cycles access was blocked
-system.iocache.blocked::no_mshrs                11251                       # number of cycles access was blocked
+system.iocache.blocked::no_mshrs                11260                       # number of cycles access was blocked
 system.iocache.blocked::no_targets                  0                       # number of cycles access was blocked
-system.iocache.avg_blocked_cycles::no_mshrs  6104.304684                       # average number of cycles each access was blocked
+system.iocache.avg_blocked_cycles::no_mshrs  6107.770870                       # average number of cycles each access was blocked
 system.iocache.avg_blocked_cycles::no_targets     no_value                       # average number of cycles each access was blocked
 system.iocache.fast_writes                          0                       # number of fast writes performed
 system.iocache.cache_copies                         0                       # number of cache copies performed
-system.iocache.writebacks                       46668                       # number of writebacks
+system.iocache.writebacks                       46667                       # number of writebacks
 system.iocache.demand_mshr_hits                     0                       # number of demand (read+write) MSHR hits
 system.iocache.overall_mshr_hits                    0                       # number of overall MSHR hits
-system.iocache.ReadReq_mshr_misses                907                       # number of ReadReq MSHR misses
+system.iocache.ReadReq_mshr_misses                909                       # number of ReadReq MSHR misses
 system.iocache.WriteReq_mshr_misses             46720                       # number of WriteReq MSHR misses
-system.iocache.demand_mshr_misses               47627                       # number of demand (read+write) MSHR misses
-system.iocache.overall_mshr_misses              47627                       # number of overall MSHR misses
+system.iocache.demand_mshr_misses               47629                       # number of demand (read+write) MSHR misses
+system.iocache.overall_mshr_misses              47629                       # number of overall MSHR misses
 system.iocache.overall_mshr_uncacheable_misses            0                       # number of overall MSHR uncacheable misses
-system.iocache.ReadReq_mshr_miss_latency     66482982                       # number of ReadReq MSHR miss cycles
-system.iocache.WriteReq_mshr_miss_latency   3942637876                       # number of WriteReq MSHR miss cycles
-system.iocache.demand_mshr_miss_latency    4009120858                       # number of demand (read+write) MSHR miss cycles
-system.iocache.overall_mshr_miss_latency   4009120858                       # number of overall MSHR miss cycles
+system.iocache.ReadReq_mshr_miss_latency     66668982                       # number of ReadReq MSHR miss cycles
+system.iocache.WriteReq_mshr_miss_latency   3939322842                       # number of WriteReq MSHR miss cycles
+system.iocache.demand_mshr_miss_latency    4005991824                       # number of demand (read+write) MSHR miss cycles
+system.iocache.overall_mshr_miss_latency   4005991824                       # number of overall MSHR miss cycles
 system.iocache.overall_mshr_uncacheable_latency            0                       # number of overall MSHR uncacheable cycles
 system.iocache.ReadReq_mshr_miss_rate::0          inf                       # mshr miss rate for ReadReq accesses
 system.iocache.ReadReq_mshr_miss_rate::1            1                       # mshr miss rate for ReadReq accesses
@@ -246,10 +246,10 @@
 system.iocache.overall_mshr_miss_rate::0          inf                       # mshr miss rate for overall accesses
 system.iocache.overall_mshr_miss_rate::1            1                       # mshr miss rate for overall accesses
 system.iocache.overall_mshr_miss_rate::total          inf                       # mshr miss rate for overall accesses
-system.iocache.ReadReq_avg_mshr_miss_latency 73299.869901                       # average ReadReq mshr miss latency
-system.iocache.WriteReq_avg_mshr_miss_latency 84388.653168                       # average WriteReq mshr miss latency
-system.iocache.demand_avg_mshr_miss_latency 84177.480379                       # average overall mshr miss latency
-system.iocache.overall_avg_mshr_miss_latency 84177.480379                       # average overall mshr miss latency
+system.iocache.ReadReq_avg_mshr_miss_latency 73343.214521                       # average ReadReq mshr miss latency
+system.iocache.WriteReq_avg_mshr_miss_latency 84317.697817                       # average WriteReq mshr miss latency
+system.iocache.demand_avg_mshr_miss_latency 84108.249680                       # average overall mshr miss latency
+system.iocache.overall_avg_mshr_miss_latency 84108.249680                       # average overall mshr miss latency
 system.iocache.overall_avg_mshr_uncacheable_latency     no_value                       # average overall mshr uncacheable latency
 system.iocache.mshr_cap_events                      0                       # number of times MSHR cap was activated
 system.iocache.soft_prefetch_mshr_full              0                       # number of mshr full events for SW prefetching instrutions
@@ -266,416 +266,415 @@
 system.pc.south_bridge.ide.disks1.dma_write_full_pages            1                       # Number of full page size DMA writes.
 system.pc.south_bridge.ide.disks1.dma_write_bytes         4096                       # Number of bytes transfered via DMA writes.
 system.pc.south_bridge.ide.disks1.dma_write_txs            1                       # Number of DMA write transactions.
-system.cpu.numCycles                        449878562                       # number of cpu cycles simulated
+system.cpu.numCycles                        462648122                       # number of cpu cycles simulated
 system.cpu.numWorkItemsStarted                      0                       # number of work items this cpu started
 system.cpu.numWorkItemsCompleted                    0                       # number of work items this cpu completed
-system.cpu.BPredUnit.lookups                 91189820                       # Number of BP lookups
-system.cpu.BPredUnit.condPredicted           91189820                       # Number of conditional branches predicted
-system.cpu.BPredUnit.condIncorrect            1250253                       # Number of conditional branches incorrect
-system.cpu.BPredUnit.BTBLookups              90006318                       # Number of BTB lookups
-system.cpu.BPredUnit.BTBHits                 83822675                       # Number of BTB hits
+system.cpu.BPredUnit.lookups                 91002231                       # Number of BP lookups
+system.cpu.BPredUnit.condPredicted           91002231                       # Number of conditional branches predicted
+system.cpu.BPredUnit.condIncorrect            1246819                       # Number of conditional branches incorrect
+system.cpu.BPredUnit.BTBLookups              89740071                       # Number of BTB lookups
+system.cpu.BPredUnit.BTBHits                 83586488                       # Number of BTB hits
 system.cpu.BPredUnit.BTBCorrect                     0                       # Number of correct BTB predictions (this stat may not work properly.
 system.cpu.BPredUnit.usedRAS                        0                       # Number of times the RAS was used to get a target.
 system.cpu.BPredUnit.RASInCorrect                   0                       # Number of incorrect RAS predictions.
-system.cpu.fetch.icacheStallCycles           28390554                       # Number of cycles fetch is stalled on an Icache miss
-system.cpu.fetch.Insts                      451032028                       # Number of instructions fetch has processed
-system.cpu.fetch.Branches                    91189820                       # Number of branches that fetch encountered
-system.cpu.fetch.predictedBranches           83822675                       # Number of branches that fetch has predicted taken
-system.cpu.fetch.Cycles                     171638033                       # Number of cycles fetch has run and was not squashing or blocked
-system.cpu.fetch.SquashCycles                 6092005                       # Number of cycles fetch has spent squashing
-system.cpu.fetch.TlbCycles                     127923                       # Number of cycles fetch has spent waiting for tlb
-system.cpu.fetch.BlockedCycles               86885537                       # Number of cycles fetch has spent blocked
-system.cpu.fetch.MiscStallCycles                36685                       # Number of cycles fetch has spent waiting on interrupts, or bad addresses, or out of MSHRs
-system.cpu.fetch.PendingTrapStallCycles         38090                       # Number of stall cycles due to pending traps
-system.cpu.fetch.IcacheWaitRetryStallCycles          283                       # Number of stall cycles due to full MSHR
-system.cpu.fetch.CacheLines                   9866979                       # Number of cache lines fetched
-system.cpu.fetch.IcacheSquashes                541048                       # Number of outstanding Icache misses that were squashed
-system.cpu.fetch.ItlbSquashes                    3553                       # Number of outstanding ITLB misses that were squashed
-system.cpu.fetch.rateDist::samples          291873782                       # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::mean              3.039474                       # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::stdev             3.398963                       # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.icacheStallCycles           29047716                       # Number of cycles fetch is stalled on an Icache miss
+system.cpu.fetch.Insts                      449719579                       # Number of instructions fetch has processed
+system.cpu.fetch.Branches                    91002231                       # Number of branches that fetch encountered
+system.cpu.fetch.predictedBranches           83586488                       # Number of branches that fetch has predicted taken
+system.cpu.fetch.Cycles                     171232175                       # Number of cycles fetch has run and was not squashing or blocked
+system.cpu.fetch.SquashCycles                 5868826                       # Number of cycles fetch has spent squashing
+system.cpu.fetch.TlbCycles                     136581                       # Number of cycles fetch has spent waiting for tlb
+system.cpu.fetch.BlockedCycles              101975708                       # Number of cycles fetch has spent blocked
+system.cpu.fetch.MiscStallCycles                37095                       # Number of cycles fetch has spent waiting on interrupts, or bad addresses, or out of MSHRs
+system.cpu.fetch.PendingTrapStallCycles         37068                       # Number of stall cycles due to pending traps
+system.cpu.fetch.IcacheWaitRetryStallCycles          258                       # Number of stall cycles due to full MSHR
+system.cpu.fetch.CacheLines                   9677008                       # Number of cache lines fetched
+system.cpu.fetch.IcacheSquashes                518282                       # Number of outstanding Icache misses that were squashed
+system.cpu.fetch.ItlbSquashes                    3472                       # Number of outstanding ITLB misses that were squashed
+system.cpu.fetch.rateDist::samples          307050159                       # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.rateDist::mean              2.882718                       # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.rateDist::stdev             3.377693                       # Number of instructions fetched each cycle (Total)
 system.cpu.fetch.rateDist::underflows               0      0.00%      0.00% # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::0                120818032     41.39%     41.39% # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::1                  1855546      0.64%     42.03% # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::2                 72826244     24.95%     66.98% # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::3                  1422491      0.49%     67.47% # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::4                  1829890      0.63%     68.10% # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::5                  4020066      1.38%     69.47% # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::6                  1590838      0.55%     70.02% # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::7                  1683069      0.58%     70.59% # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::8                 85827606     29.41%    100.00% # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.rateDist::0                136328655     44.40%     44.40% # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.rateDist::1                  1837704      0.60%     45.00% # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.rateDist::2                 72797609     23.71%     68.71% # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.rateDist::3                  1414382      0.46%     69.17% # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.rateDist::4                  1803500      0.59%     69.75% # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.rateDist::5                  3975077      1.29%     71.05% # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.rateDist::6                  1554877      0.51%     71.56% # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.rateDist::7                  1662423      0.54%     72.10% # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.rateDist::8                 85675932     27.90%    100.00% # Number of instructions fetched each cycle (Total)
 system.cpu.fetch.rateDist::overflows                0      0.00%    100.00% # Number of instructions fetched each cycle (Total)
 system.cpu.fetch.rateDist::min_value                0                       # Number of instructions fetched each cycle (Total)
 system.cpu.fetch.rateDist::max_value                8                       # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::total            291873782                       # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.branchRate                  0.202699                       # Number of branch fetches per cycle
-system.cpu.fetch.rate                        1.002564                       # Number of inst fetches per cycle
-system.cpu.decode.IdleCycles                 33589176                       # Number of cycles decode is idle
-system.cpu.decode.BlockedCycles              83124342                       # Number of cycles decode is blocked
-system.cpu.decode.RunCycles                 166020087                       # Number of cycles decode is running
-system.cpu.decode.UnblockCycles               4383500                       # Number of cycles decode is unblocking
-system.cpu.decode.SquashCycles                4756677                       # Number of cycles decode is squashing
-system.cpu.decode.DecodedInsts              883216023                       # Number of instructions handled by decode
-system.cpu.decode.SquashedInsts                   571                       # Number of squashed instructions handled by decode
-system.cpu.rename.SquashCycles                4756677                       # Number of cycles rename is squashing
-system.cpu.rename.IdleCycles                 37852860                       # Number of cycles rename is idle
-system.cpu.rename.BlockCycles                55892656                       # Number of cycles rename is blocking
-system.cpu.rename.serializeStallCycles        9911063                       # count of cycles rename stalled for serializing inst
-system.cpu.rename.RunCycles                 165583689                       # Number of cycles rename is running
-system.cpu.rename.UnblockCycles              17876837                       # Number of cycles rename is unblocking
-system.cpu.rename.RenamedInsts              878703692                       # Number of instructions processed by rename
-system.cpu.rename.ROBFullEvents                 12652                       # Number of times rename has blocked due to ROB full
-system.cpu.rename.IQFullEvents               12602978                       # Number of times rename has blocked due to IQ full
-system.cpu.rename.LSQFullEvents               2126989                       # Number of times rename has blocked due to LSQ full
-system.cpu.rename.FullRegisterEvents               10                       # Number of times there has been no free registers
-system.cpu.rename.RenamedOperands           880098416                       # Number of destination operands rename has renamed
-system.cpu.rename.RenameLookups            1724229495                       # Number of register rename lookups that rename has made
-system.cpu.rename.int_rename_lookups       1724229039                       # Number of integer rename lookups
-system.cpu.rename.fp_rename_lookups               456                       # Number of floating rename lookups
-system.cpu.rename.CommittedMaps             843418783                       # Number of HB maps that are committed
-system.cpu.rename.UndoneMaps                 36679626                       # Number of HB maps that are undone due to squashing
-system.cpu.rename.serializingInsts             488930                       # count of serializing insts renamed
-system.cpu.rename.tempSerializingInsts         489908                       # count of temporary serializing insts renamed
-system.cpu.rename.skidInsts                  44000804                       # count of insts added to the skid buffer
-system.cpu.memDep0.insertedLoads             19727758                       # Number of loads inserted to the mem dependence unit.
-system.cpu.memDep0.insertedStores            10753359                       # Number of stores inserted to the mem dependence unit.
-system.cpu.memDep0.conflictingLoads           1338256                       # Number of conflicting loads.
-system.cpu.memDep0.conflictingStores          1089668                       # Number of conflicting stores.
-system.cpu.iq.iqInstsAdded                  870922009                       # Number of instructions added to the IQ (excludes non-spec)
-system.cpu.iq.iqNonSpecInstsAdded             1727938                       # Number of non-speculative instructions added to the IQ
-system.cpu.iq.iqInstsIssued                 867227375                       # Number of instructions issued
-system.cpu.iq.iqSquashedInstsIssued            177419                       # Number of squashed instructions issued
-system.cpu.iq.iqSquashedInstsExamined        30993538                       # Number of squashed instructions iterated over during squash; mainly for profiling
-system.cpu.iq.iqSquashedOperandsExamined     45221667                       # Number of squashed operands that are examined and possibly removed from graph
-system.cpu.iq.iqSquashedNonSpecRemoved         207753                       # Number of squashed non-spec instructions that were removed
-system.cpu.iq.issued_per_cycle::samples     291873782                       # Number of insts issued each cycle
-system.cpu.iq.issued_per_cycle::mean         2.971241                       # Number of insts issued each cycle
-system.cpu.iq.issued_per_cycle::stdev        2.381572                       # Number of insts issued each cycle
+system.cpu.fetch.rateDist::total            307050159                       # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.branchRate                  0.196699                       # Number of branch fetches per cycle
+system.cpu.fetch.rate                        0.972055                       # Number of inst fetches per cycle
+system.cpu.decode.IdleCycles                 34173588                       # Number of cycles decode is idle
+system.cpu.decode.BlockedCycles              98204152                       # Number of cycles decode is blocked
+system.cpu.decode.RunCycles                 165547565                       # Number of cycles decode is running
+system.cpu.decode.UnblockCycles               4541296                       # Number of cycles decode is unblocking
+system.cpu.decode.SquashCycles                4583558                       # Number of cycles decode is squashing
+system.cpu.decode.DecodedInsts              881331819                       # Number of instructions handled by decode
+system.cpu.decode.SquashedInsts                   622                       # Number of squashed instructions handled by decode
+system.cpu.rename.SquashCycles                4583558                       # Number of cycles rename is squashing
+system.cpu.rename.IdleCycles                 38558977                       # Number of cycles rename is idle
+system.cpu.rename.BlockCycles                67835236                       # Number of cycles rename is blocking
+system.cpu.rename.serializeStallCycles       11414000                       # count of cycles rename stalled for serializing inst
+system.cpu.rename.RunCycles                 165163218                       # Number of cycles rename is running
+system.cpu.rename.UnblockCycles              19495170                       # Number of cycles rename is unblocking
+system.cpu.rename.RenamedInsts              877018517                       # Number of instructions processed by rename
+system.cpu.rename.ROBFullEvents                 10722                       # Number of times rename has blocked due to ROB full
+system.cpu.rename.IQFullEvents               12485969                       # Number of times rename has blocked due to IQ full
+system.cpu.rename.LSQFullEvents               3867736                       # Number of times rename has blocked due to LSQ full
+system.cpu.rename.RenamedOperands           878675009                       # Number of destination operands rename has renamed
+system.cpu.rename.RenameLookups            1719931818                       # Number of register rename lookups that rename has made
+system.cpu.rename.int_rename_lookups       1719931354                       # Number of integer rename lookups
+system.cpu.rename.fp_rename_lookups               464                       # Number of floating rename lookups
+system.cpu.rename.CommittedMaps             843258778                       # Number of HB maps that are committed
+system.cpu.rename.UndoneMaps                 35416224                       # Number of HB maps that are undone due to squashing
+system.cpu.rename.serializingInsts             488329                       # count of serializing insts renamed
+system.cpu.rename.tempSerializingInsts         492601                       # count of temporary serializing insts renamed
+system.cpu.rename.skidInsts                  46069220                       # count of insts added to the skid buffer
+system.cpu.memDep0.insertedLoads             19448734                       # Number of loads inserted to the mem dependence unit.
+system.cpu.memDep0.insertedStores            10510676                       # Number of stores inserted to the mem dependence unit.
+system.cpu.memDep0.conflictingLoads           1191191                       # Number of conflicting loads.
+system.cpu.memDep0.conflictingStores           913743                       # Number of conflicting stores.
+system.cpu.iq.iqInstsAdded                  869530177                       # Number of instructions added to the IQ (excludes non-spec)
+system.cpu.iq.iqNonSpecInstsAdded             1725186                       # Number of non-speculative instructions added to the IQ
+system.cpu.iq.iqInstsIssued                 866447166                       # Number of instructions issued
+system.cpu.iq.iqSquashedInstsIssued            122007                       # Number of squashed instructions issued
+system.cpu.iq.iqSquashedInstsExamined        29731249                       # Number of squashed instructions iterated over during squash; mainly for profiling
+system.cpu.iq.iqSquashedOperandsExamined     42741048                       # Number of squashed operands that are examined and possibly removed from graph
+system.cpu.iq.iqSquashedNonSpecRemoved         205599                       # Number of squashed non-spec instructions that were removed
+system.cpu.iq.issued_per_cycle::samples     307050159                       # Number of insts issued each cycle
+system.cpu.iq.issued_per_cycle::mean         2.821842                       # Number of insts issued each cycle
+system.cpu.iq.issued_per_cycle::stdev        2.403845                       # Number of insts issued each cycle
 system.cpu.iq.issued_per_cycle::underflows            0      0.00%      0.00% # Number of insts issued each cycle
-system.cpu.iq.issued_per_cycle::0            86148709     29.52%     29.52% # Number of insts issued each cycle
-system.cpu.iq.issued_per_cycle::1            24105973      8.26%     37.77% # Number of insts issued each cycle
-system.cpu.iq.issued_per_cycle::2            13574297      4.65%     42.43% # Number of insts issued each cycle
-system.cpu.iq.issued_per_cycle::3             9676822      3.32%     45.74% # Number of insts issued each cycle
-system.cpu.iq.issued_per_cycle::4            79595279     27.27%     73.01% # Number of insts issued each cycle
-system.cpu.iq.issued_per_cycle::5             5022101      1.72%     74.73% # Number of insts issued each cycle
-system.cpu.iq.issued_per_cycle::6            72958833     25.00%     99.73% # Number of insts issued each cycle
-system.cpu.iq.issued_per_cycle::7              636421      0.22%     99.95% # Number of insts issued each cycle
-system.cpu.iq.issued_per_cycle::8              155347      0.05%    100.00% # Number of insts issued each cycle
+system.cpu.iq.issued_per_cycle::0           100227598     32.64%     32.64% # Number of insts issued each cycle
+system.cpu.iq.issued_per_cycle::1            25342786      8.25%     40.90% # Number of insts issued each cycle
+system.cpu.iq.issued_per_cycle::2            13946244      4.54%     45.44% # Number of insts issued each cycle
+system.cpu.iq.issued_per_cycle::3             9645579      3.14%     48.58% # Number of insts issued each cycle
+system.cpu.iq.issued_per_cycle::4            79515480     25.90%     74.48% # Number of insts issued each cycle
+system.cpu.iq.issued_per_cycle::5             4843126      1.58%     76.05% # Number of insts issued each cycle
+system.cpu.iq.issued_per_cycle::6            72836741     23.72%     99.77% # Number of insts issued each cycle
+system.cpu.iq.issued_per_cycle::7              563681      0.18%     99.96% # Number of insts issued each cycle
+system.cpu.iq.issued_per_cycle::8              128924      0.04%    100.00% # Number of insts issued each cycle
 system.cpu.iq.issued_per_cycle::overflows            0      0.00%    100.00% # Number of insts issued each cycle
 system.cpu.iq.issued_per_cycle::min_value            0                       # Number of insts issued each cycle
 system.cpu.iq.issued_per_cycle::max_value            8                       # Number of insts issued each cycle
-system.cpu.iq.issued_per_cycle::total       291873782                       # Number of insts issued each cycle
+system.cpu.iq.issued_per_cycle::total       307050159                       # Number of insts issued each cycle
 system.cpu.iq.fu_full::No_OpClass                   0      0.00%      0.00% # attempts to use FU when none available
-system.cpu.iq.fu_full::IntAlu                  202428      8.97%      8.97% # attempts to use FU when none available
-system.cpu.iq.fu_full::IntMult                      0      0.00%      8.97% # attempts to use FU when none available
-system.cpu.iq.fu_full::IntDiv                       0      0.00%      8.97% # attempts to use FU when none available
-system.cpu.iq.fu_full::FloatAdd                     0      0.00%      8.97% # attempts to use FU when none available
-system.cpu.iq.fu_full::FloatCmp                     0      0.00%      8.97% # attempts to use FU when none available
-system.cpu.iq.fu_full::FloatCvt                     0      0.00%      8.97% # attempts to use FU when none available
-system.cpu.iq.fu_full::FloatMult                    0      0.00%      8.97% # attempts to use FU when none available
-system.cpu.iq.fu_full::FloatDiv                     0      0.00%      8.97% # attempts to use FU when none available
-system.cpu.iq.fu_full::FloatSqrt                    0      0.00%      8.97% # attempts to use FU when none available
-system.cpu.iq.fu_full::SimdAdd                      0      0.00%      8.97% # attempts to use FU when none available
-system.cpu.iq.fu_full::SimdAddAcc                   0      0.00%      8.97% # attempts to use FU when none available
-system.cpu.iq.fu_full::SimdAlu                      0      0.00%      8.97% # attempts to use FU when none available
-system.cpu.iq.fu_full::SimdCmp                      0      0.00%      8.97% # attempts to use FU when none available
-system.cpu.iq.fu_full::SimdCvt                      0      0.00%      8.97% # attempts to use FU when none available
-system.cpu.iq.fu_full::SimdMisc                     0      0.00%      8.97% # attempts to use FU when none available
-system.cpu.iq.fu_full::SimdMult                     0      0.00%      8.97% # attempts to use FU when none available
-system.cpu.iq.fu_full::SimdMultAcc                  0      0.00%      8.97% # attempts to use FU when none available
-system.cpu.iq.fu_full::SimdShift                    0      0.00%      8.97% # attempts to use FU when none available
-system.cpu.iq.fu_full::SimdShiftAcc                 0      0.00%      8.97% # attempts to use FU when none available
-system.cpu.iq.fu_full::SimdSqrt                     0      0.00%      8.97% # attempts to use FU when none available
-system.cpu.iq.fu_full::SimdFloatAdd                 0      0.00%      8.97% # attempts to use FU when none available
-system.cpu.iq.fu_full::SimdFloatAlu                 0      0.00%      8.97% # attempts to use FU when none available
-system.cpu.iq.fu_full::SimdFloatCmp                 0      0.00%      8.97% # attempts to use FU when none available
-system.cpu.iq.fu_full::SimdFloatCvt                 0      0.00%      8.97% # attempts to use FU when none available
-system.cpu.iq.fu_full::SimdFloatDiv                 0      0.00%      8.97% # attempts to use FU when none available
-system.cpu.iq.fu_full::SimdFloatMisc                0      0.00%      8.97% # attempts to use FU when none available
-system.cpu.iq.fu_full::SimdFloatMult                0      0.00%      8.97% # attempts to use FU when none available
-system.cpu.iq.fu_full::SimdFloatMultAcc             0      0.00%      8.97% # attempts to use FU when none available
-system.cpu.iq.fu_full::SimdFloatSqrt                0      0.00%      8.97% # attempts to use FU when none available
-system.cpu.iq.fu_full::MemRead                1851752     82.02%     90.99% # attempts to use FU when none available
-system.cpu.iq.fu_full::MemWrite                203495      9.01%    100.00% # attempts to use FU when none available
+system.cpu.iq.fu_full::IntAlu                  189288      8.89%      8.89% # attempts to use FU when none available
+system.cpu.iq.fu_full::IntMult                      0      0.00%      8.89% # attempts to use FU when none available
+system.cpu.iq.fu_full::IntDiv                       0      0.00%      8.89% # attempts to use FU when none available
+system.cpu.iq.fu_full::FloatAdd                     0      0.00%      8.89% # attempts to use FU when none available
+system.cpu.iq.fu_full::FloatCmp                     0      0.00%      8.89% # attempts to use FU when none available
+system.cpu.iq.fu_full::FloatCvt                     0      0.00%      8.89% # attempts to use FU when none available
+system.cpu.iq.fu_full::FloatMult                    0      0.00%      8.89% # attempts to use FU when none available
+system.cpu.iq.fu_full::FloatDiv                     0      0.00%      8.89% # attempts to use FU when none available
+system.cpu.iq.fu_full::FloatSqrt                    0      0.00%      8.89% # attempts to use FU when none available
+system.cpu.iq.fu_full::SimdAdd                      0      0.00%      8.89% # attempts to use FU when none available
+system.cpu.iq.fu_full::SimdAddAcc                   0      0.00%      8.89% # attempts to use FU when none available
+system.cpu.iq.fu_full::SimdAlu                      0      0.00%      8.89% # attempts to use FU when none available
+system.cpu.iq.fu_full::SimdCmp                      0      0.00%      8.89% # attempts to use FU when none available
+system.cpu.iq.fu_full::SimdCvt                      0      0.00%      8.89% # attempts to use FU when none available
+system.cpu.iq.fu_full::SimdMisc                     0      0.00%      8.89% # attempts to use FU when none available
+system.cpu.iq.fu_full::SimdMult                     0      0.00%      8.89% # attempts to use FU when none available
+system.cpu.iq.fu_full::SimdMultAcc                  0      0.00%      8.89% # attempts to use FU when none available
+system.cpu.iq.fu_full::SimdShift                    0      0.00%      8.89% # attempts to use FU when none available
+system.cpu.iq.fu_full::SimdShiftAcc                 0      0.00%      8.89% # attempts to use FU when none available
+system.cpu.iq.fu_full::SimdSqrt                     0      0.00%      8.89% # attempts to use FU when none available
+system.cpu.iq.fu_full::SimdFloatAdd                 0      0.00%      8.89% # attempts to use FU when none available
+system.cpu.iq.fu_full::SimdFloatAlu                 0      0.00%      8.89% # attempts to use FU when none available
+system.cpu.iq.fu_full::SimdFloatCmp                 0      0.00%      8.89% # attempts to use FU when none available
+system.cpu.iq.fu_full::SimdFloatCvt                 0      0.00%      8.89% # attempts to use FU when none available
+system.cpu.iq.fu_full::SimdFloatDiv                 0      0.00%      8.89% # attempts to use FU when none available
+system.cpu.iq.fu_full::SimdFloatMisc                0      0.00%      8.89% # attempts to use FU when none available
+system.cpu.iq.fu_full::SimdFloatMult                0      0.00%      8.89% # attempts to use FU when none available
+system.cpu.iq.fu_full::SimdFloatMultAcc             0      0.00%      8.89% # attempts to use FU when none available
+system.cpu.iq.fu_full::SimdFloatSqrt                0      0.00%      8.89% # attempts to use FU when none available
+system.cpu.iq.fu_full::MemRead                1772779     83.25%     92.14% # attempts to use FU when none available
+system.cpu.iq.fu_full::MemWrite                167484      7.86%    100.00% # attempts to use FU when none available
 system.cpu.iq.fu_full::IprAccess                    0      0.00%    100.00% # attempts to use FU when none available
 system.cpu.iq.fu_full::InstPrefetch                 0      0.00%    100.00% # attempts to use FU when none available
-system.cpu.iq.FU_type_0::No_OpClass            306567      0.04%      0.04% # Type of FU issued
-system.cpu.iq.FU_type_0::IntAlu             831752185     95.91%     95.94% # Type of FU issued
-system.cpu.iq.FU_type_0::IntMult                    0      0.00%     95.94% # Type of FU issued
-system.cpu.iq.FU_type_0::IntDiv                     0      0.00%     95.94% # Type of FU issued
-system.cpu.iq.FU_type_0::FloatAdd                   0      0.00%     95.94% # Type of FU issued
-system.cpu.iq.FU_type_0::FloatCmp                   0      0.00%     95.94% # Type of FU issued
-system.cpu.iq.FU_type_0::FloatCvt                   0      0.00%     95.94% # Type of FU issued
-system.cpu.iq.FU_type_0::FloatMult                  0      0.00%     95.94% # Type of FU issued
-system.cpu.iq.FU_type_0::FloatDiv                   0      0.00%     95.94% # Type of FU issued
-system.cpu.iq.FU_type_0::FloatSqrt                  0      0.00%     95.94% # Type of FU issued
-system.cpu.iq.FU_type_0::SimdAdd                    0      0.00%     95.94% # Type of FU issued
-system.cpu.iq.FU_type_0::SimdAddAcc                 0      0.00%     95.94% # Type of FU issued
-system.cpu.iq.FU_type_0::SimdAlu                    0      0.00%     95.94% # Type of FU issued
-system.cpu.iq.FU_type_0::SimdCmp                    0      0.00%     95.94% # Type of FU issued
-system.cpu.iq.FU_type_0::SimdCvt                    0      0.00%     95.94% # Type of FU issued
-system.cpu.iq.FU_type_0::SimdMisc                   0      0.00%     95.94% # Type of FU issued
-system.cpu.iq.FU_type_0::SimdMult                   0      0.00%     95.94% # Type of FU issued
-system.cpu.iq.FU_type_0::SimdMultAcc                0      0.00%     95.94% # Type of FU issued
-system.cpu.iq.FU_type_0::SimdShift                  0      0.00%     95.94% # Type of FU issued
-system.cpu.iq.FU_type_0::SimdShiftAcc               0      0.00%     95.94% # Type of FU issued
-system.cpu.iq.FU_type_0::SimdSqrt                   0      0.00%     95.94% # Type of FU issued
-system.cpu.iq.FU_type_0::SimdFloatAdd               0      0.00%     95.94% # Type of FU issued
-system.cpu.iq.FU_type_0::SimdFloatAlu               0      0.00%     95.94% # Type of FU issued
-system.cpu.iq.FU_type_0::SimdFloatCmp               0      0.00%     95.94% # Type of FU issued
-system.cpu.iq.FU_type_0::SimdFloatCvt               0      0.00%     95.94% # Type of FU issued
-system.cpu.iq.FU_type_0::SimdFloatDiv               0      0.00%     95.94% # Type of FU issued
-system.cpu.iq.FU_type_0::SimdFloatMisc              0      0.00%     95.94% # Type of FU issued
-system.cpu.iq.FU_type_0::SimdFloatMult              0      0.00%     95.94% # Type of FU issued
-system.cpu.iq.FU_type_0::SimdFloatMultAcc            0      0.00%     95.94% # Type of FU issued
-system.cpu.iq.FU_type_0::SimdFloatSqrt              0      0.00%     95.94% # Type of FU issued
-system.cpu.iq.FU_type_0::MemRead             25621043      2.95%     98.90% # Type of FU issued
-system.cpu.iq.FU_type_0::MemWrite             9547580      1.10%    100.00% # Type of FU issued
+system.cpu.iq.FU_type_0::No_OpClass            305473      0.04%      0.04% # Type of FU issued
+system.cpu.iq.FU_type_0::IntAlu             831218521     95.93%     95.97% # Type of FU issued
+system.cpu.iq.FU_type_0::IntMult                    0      0.00%     95.97% # Type of FU issued
+system.cpu.iq.FU_type_0::IntDiv                     0      0.00%     95.97% # Type of FU issued
+system.cpu.iq.FU_type_0::FloatAdd                   0      0.00%     95.97% # Type of FU issued
+system.cpu.iq.FU_type_0::FloatCmp                   0      0.00%     95.97% # Type of FU issued
+system.cpu.iq.FU_type_0::FloatCvt                   0      0.00%     95.97% # Type of FU issued
+system.cpu.iq.FU_type_0::FloatMult                  0      0.00%     95.97% # Type of FU issued
+system.cpu.iq.FU_type_0::FloatDiv                   0      0.00%     95.97% # Type of FU issued
+system.cpu.iq.FU_type_0::FloatSqrt                  0      0.00%     95.97% # Type of FU issued
+system.cpu.iq.FU_type_0::SimdAdd                    0      0.00%     95.97% # Type of FU issued
+system.cpu.iq.FU_type_0::SimdAddAcc                 0      0.00%     95.97% # Type of FU issued
+system.cpu.iq.FU_type_0::SimdAlu                    0      0.00%     95.97% # Type of FU issued
+system.cpu.iq.FU_type_0::SimdCmp                    0      0.00%     95.97% # Type of FU issued
+system.cpu.iq.FU_type_0::SimdCvt                    0      0.00%     95.97% # Type of FU issued
+system.cpu.iq.FU_type_0::SimdMisc                   0      0.00%     95.97% # Type of FU issued
+system.cpu.iq.FU_type_0::SimdMult                   0      0.00%     95.97% # Type of FU issued
+system.cpu.iq.FU_type_0::SimdMultAcc                0      0.00%     95.97% # Type of FU issued
+system.cpu.iq.FU_type_0::SimdShift                  0      0.00%     95.97% # Type of FU issued
+system.cpu.iq.FU_type_0::SimdShiftAcc               0      0.00%     95.97% # Type of FU issued
+system.cpu.iq.FU_type_0::SimdSqrt                   0      0.00%     95.97% # Type of FU issued
+system.cpu.iq.FU_type_0::SimdFloatAdd               0      0.00%     95.97% # Type of FU issued
+system.cpu.iq.FU_type_0::SimdFloatAlu               0      0.00%     95.97% # Type of FU issued
+system.cpu.iq.FU_type_0::SimdFloatCmp               0      0.00%     95.97% # Type of FU issued
+system.cpu.iq.FU_type_0::SimdFloatCvt               0      0.00%     95.97% # Type of FU issued
+system.cpu.iq.FU_type_0::SimdFloatDiv               0      0.00%     95.97% # Type of FU issued
+system.cpu.iq.FU_type_0::SimdFloatMisc              0      0.00%     95.97% # Type of FU issued
+system.cpu.iq.FU_type_0::SimdFloatMult              0      0.00%     95.97% # Type of FU issued
+system.cpu.iq.FU_type_0::SimdFloatMultAcc            0      0.00%     95.97% # Type of FU issued
+system.cpu.iq.FU_type_0::SimdFloatSqrt              0      0.00%     95.97% # Type of FU issued
+system.cpu.iq.FU_type_0::MemRead             25430215      2.93%     98.90% # Type of FU issued
+system.cpu.iq.FU_type_0::MemWrite             9492957      1.10%    100.00% # Type of FU issued
 system.cpu.iq.FU_type_0::IprAccess                  0      0.00%    100.00% # Type of FU issued
 system.cpu.iq.FU_type_0::InstPrefetch               0      0.00%    100.00% # Type of FU issued
-system.cpu.iq.FU_type_0::total              867227375                       # Type of FU issued
-system.cpu.iq.rate                           1.927692                       # Inst issue rate
-system.cpu.iq.fu_busy_cnt                     2257675                       # FU busy when requested
-system.cpu.iq.fu_busy_rate                   0.002603                       # FU busy rate (busy events/executed inst)
-system.cpu.iq.int_inst_queue_reads         2028918942                       # Number of integer instruction queue reads
-system.cpu.iq.int_inst_queue_writes         903653765                       # Number of integer instruction queue writes
-system.cpu.iq.int_inst_queue_wakeup_accesses    856397776                       # Number of integer instruction queue wakeup accesses
-system.cpu.iq.fp_inst_queue_reads                 194                       # Number of floating instruction queue reads
-system.cpu.iq.fp_inst_queue_writes                210                       # Number of floating instruction queue writes
-system.cpu.iq.fp_inst_queue_wakeup_accesses           50                       # Number of floating instruction queue wakeup accesses
-system.cpu.iq.int_alu_accesses              869178395                       # Number of integer alu accesses
-system.cpu.iq.fp_alu_accesses                      88                       # Number of floating point alu accesses
-system.cpu.iew.lsq.thread0.forwLoads          1343949                       # Number of loads that had data forwarded from stores
+system.cpu.iq.FU_type_0::total              866447166                       # Type of FU issued
+system.cpu.iq.rate                           1.872799                       # Inst issue rate
+system.cpu.iq.fu_busy_cnt                     2129551                       # FU busy when requested
+system.cpu.iq.fu_busy_rate                   0.002458                       # FU busy rate (busy events/executed inst)
+system.cpu.iq.int_inst_queue_reads         2042346945                       # Number of integer instruction queue reads
+system.cpu.iq.int_inst_queue_writes         900997029                       # Number of integer instruction queue writes
+system.cpu.iq.int_inst_queue_wakeup_accesses    855808882                       # Number of integer instruction queue wakeup accesses
+system.cpu.iq.fp_inst_queue_reads                 195                       # Number of floating instruction queue reads
+system.cpu.iq.fp_inst_queue_writes                212                       # Number of floating instruction queue writes
+system.cpu.iq.fp_inst_queue_wakeup_accesses           51                       # Number of floating instruction queue wakeup accesses
+system.cpu.iq.int_alu_accesses              868271157                       # Number of integer alu accesses
+system.cpu.iq.fp_alu_accesses                      87                       # Number of floating point alu accesses
+system.cpu.iew.lsq.thread0.forwLoads          1634079                       # Number of loads that had data forwarded from stores
 system.cpu.iew.lsq.thread0.invAddrLoads             0                       # Number of loads ignored due to an invalid address
-system.cpu.iew.lsq.thread0.squashedLoads      4393917                       # Number of loads squashed
-system.cpu.iew.lsq.thread0.ignoredResponses        17180                       # Number of memory responses ignored because the instruction is squashed
-system.cpu.iew.lsq.thread0.memOrderViolation        11337                       # Number of memory ordering violations
-system.cpu.iew.lsq.thread0.squashedStores      2321478                       # Number of stores squashed
+system.cpu.iew.lsq.thread0.squashedLoads      4122999                       # Number of loads squashed
+system.cpu.iew.lsq.thread0.ignoredResponses        16974                       # Number of memory responses ignored because the instruction is squashed
+system.cpu.iew.lsq.thread0.memOrderViolation        11449                       # Number of memory ordering violations
+system.cpu.iew.lsq.thread0.squashedStores      2081373                       # Number of stores squashed
 system.cpu.iew.lsq.thread0.invAddrSwpfs             0                       # Number of software prefetches ignored due to an invalid address
 system.cpu.iew.lsq.thread0.blockedLoads             0                       # Number of blocked loads due to partial load-store forwarding
-system.cpu.iew.lsq.thread0.rescheduledLoads      7817249                       # Number of loads that were rescheduled
-system.cpu.iew.lsq.thread0.cacheBlocked        160526                       # Number of times an access to memory failed due to the cache being blocked
+system.cpu.iew.lsq.thread0.rescheduledLoads      7821312                       # Number of loads that were rescheduled
+system.cpu.iew.lsq.thread0.cacheBlocked          4401                       # Number of times an access to memory failed due to the cache being blocked
 system.cpu.iew.iewIdleCycles                        0                       # Number of cycles IEW is idle
-system.cpu.iew.iewSquashCycles                4756677                       # Number of cycles IEW is squashing
-system.cpu.iew.iewBlockCycles                34884624                       # Number of cycles IEW is blocking
-system.cpu.iew.iewUnblockCycles               6122535                       # Number of cycles IEW is unblocking
-system.cpu.iew.iewDispatchedInsts           872649947                       # Number of instructions dispatched to IQ
-system.cpu.iew.iewDispSquashedInsts            301193                       # Number of squashed instructions skipped by dispatch
-system.cpu.iew.iewDispLoadInsts              19727758                       # Number of dispatched load instructions
-system.cpu.iew.iewDispStoreInsts             10753386                       # Number of dispatched store instructions
-system.cpu.iew.iewDispNonSpecInsts             894363                       # Number of dispatched non-speculative instructions
-system.cpu.iew.iewIQFullEvents                5389997                       # Number of times the IQ has become full, causing a stall
-system.cpu.iew.iewLSQFullEvents                 26295                       # Number of times the LSQ has become full, causing a stall
-system.cpu.iew.memOrderViolationEvents          11337                       # Number of memory order violations
-system.cpu.iew.predictedTakenIncorrect         906001                       # Number of branches that were predicted taken incorrectly
-system.cpu.iew.predictedNotTakenIncorrect       524480                       # Number of branches that were predicted not taken incorrectly
-system.cpu.iew.branchMispredicts              1430481                       # Number of branch mispredicts detected at execute
-system.cpu.iew.iewExecutedInsts             865094857                       # Number of executed instructions
-system.cpu.iew.iewExecLoadInsts              25131798                       # Number of load instructions executed
-system.cpu.iew.iewExecSquashedInsts           2132517                       # Number of squashed instructions skipped in execute
+system.cpu.iew.iewSquashCycles                4583558                       # Number of cycles IEW is squashing
+system.cpu.iew.iewBlockCycles                45537576                       # Number of cycles IEW is blocking
+system.cpu.iew.iewUnblockCycles               6145383                       # Number of cycles IEW is unblocking
+system.cpu.iew.iewDispatchedInsts           871255363                       # Number of instructions dispatched to IQ
+system.cpu.iew.iewDispSquashedInsts            286386                       # Number of squashed instructions skipped by dispatch
+system.cpu.iew.iewDispLoadInsts              19448734                       # Number of dispatched load instructions
+system.cpu.iew.iewDispStoreInsts             10510706                       # Number of dispatched store instructions
+system.cpu.iew.iewDispNonSpecInsts             890989                       # Number of dispatched non-speculative instructions
+system.cpu.iew.iewIQFullEvents                5371019                       # Number of times the IQ has become full, causing a stall
+system.cpu.iew.iewLSQFullEvents                 12371                       # Number of times the LSQ has become full, causing a stall
+system.cpu.iew.memOrderViolationEvents          11449                       # Number of memory order violations
+system.cpu.iew.predictedTakenIncorrect         894854                       # Number of branches that were predicted taken incorrectly
+system.cpu.iew.predictedNotTakenIncorrect       527277                       # Number of branches that were predicted not taken incorrectly
+system.cpu.iew.branchMispredicts              1422131                       # Number of branch mispredicts detected at execute
+system.cpu.iew.iewExecutedInsts             864388820                       # Number of executed instructions
+system.cpu.iew.iewExecLoadInsts              24990007                       # Number of load instructions executed
+system.cpu.iew.iewExecSquashedInsts           2058345                       # Number of squashed instructions skipped in execute
 system.cpu.iew.exec_swp                             0                       # number of swp insts executed
 system.cpu.iew.exec_nop                             0                       # number of nop insts executed
-system.cpu.iew.exec_refs                     34436194                       # number of memory reference insts executed
-system.cpu.iew.exec_branches                 86723634                       # Number of branches executed
-system.cpu.iew.exec_stores                    9304396                       # Number of stores executed
-system.cpu.iew.exec_rate                     1.922952                       # Inst execution rate
-system.cpu.iew.wb_sent                      864455877                       # cumulative count of insts sent to commit
-system.cpu.iew.wb_count                     856397826                       # cumulative count of insts written-back
-system.cpu.iew.wb_producers                 671292665                       # num instructions producing a value
-system.cpu.iew.wb_consumers                1171999804                       # num instructions consuming a value
+system.cpu.iew.exec_refs                     34246643                       # number of memory reference insts executed
+system.cpu.iew.exec_branches                 86674452                       # Number of branches executed
+system.cpu.iew.exec_stores                    9256636                       # Number of stores executed
+system.cpu.iew.exec_rate                     1.868350                       # Inst execution rate
+system.cpu.iew.wb_sent                      863858871                       # cumulative count of insts sent to commit
+system.cpu.iew.wb_count                     855808933                       # cumulative count of insts written-back
+system.cpu.iew.wb_producers                 670117555                       # num instructions producing a value
+system.cpu.iew.wb_consumers                1169388275                       # num instructions consuming a value
 system.cpu.iew.wb_penalized                         0                       # number of instrctions required to write to 'other' IQ
-system.cpu.iew.wb_rate                       1.903620                       # insts written-back per cycle
-system.cpu.iew.wb_fanout                     0.572775                       # average fanout of values written-back
+system.cpu.iew.wb_rate                       1.849805                       # insts written-back per cycle
+system.cpu.iew.wb_fanout                     0.573050                       # average fanout of values written-back
 system.cpu.iew.wb_penalized_rate                    0                       # fraction of instructions written-back that wrote to 'other' IQ
-system.cpu.commit.commitCommittedInsts      840808469                       # The number of committed instructions
-system.cpu.commit.commitSquashedInsts        31735206                       # The number of squashed insts skipped by commit
-system.cpu.commit.commitNonSpecStalls         1520183                       # The number of times commit has been forced to stall to communicate backwards
-system.cpu.commit.branchMispredicts           1254406                       # The number of times a branch was mispredicted
-system.cpu.commit.committed_per_cycle::samples    287133088                       # Number of insts commited each cycle
-system.cpu.commit.committed_per_cycle::mean     2.928288                       # Number of insts commited each cycle
-system.cpu.commit.committed_per_cycle::stdev     2.869814                       # Number of insts commited each cycle
+system.cpu.commit.commitCommittedInsts      840653382                       # The number of committed instructions
+system.cpu.commit.commitSquashedInsts        30493739                       # The number of squashed insts skipped by commit
+system.cpu.commit.commitNonSpecStalls         1519585                       # The number of times commit has been forced to stall to communicate backwards
+system.cpu.commit.branchMispredicts           1250852                       # The number of times a branch was mispredicted
+system.cpu.commit.committed_per_cycle::samples    302482532                       # Number of insts commited each cycle
+system.cpu.commit.committed_per_cycle::mean     2.779180                       # Number of insts commited each cycle
+system.cpu.commit.committed_per_cycle::stdev     2.862928                       # Number of insts commited each cycle
 system.cpu.commit.committed_per_cycle::underflows            0      0.00%      0.00% # Number of insts commited each cycle
-system.cpu.commit.committed_per_cycle::0    107529680     37.45%     37.45% # Number of insts commited each cycle
-system.cpu.commit.committed_per_cycle::1     13316862      4.64%     42.09% # Number of insts commited each cycle
-system.cpu.commit.committed_per_cycle::2      3946452      1.37%     43.46% # Number of insts commited each cycle
-system.cpu.commit.committed_per_cycle::3     76651474     26.70%     70.16% # Number of insts commited each cycle
-system.cpu.commit.committed_per_cycle::4      4051645      1.41%     71.57% # Number of insts commited each cycle
-system.cpu.commit.committed_per_cycle::5      1852261      0.65%     72.21% # Number of insts commited each cycle
-system.cpu.commit.committed_per_cycle::6      1054561      0.37%     72.58% # Number of insts commited each cycle
-system.cpu.commit.committed_per_cycle::7     71992194     25.07%     97.65% # Number of insts commited each cycle
-system.cpu.commit.committed_per_cycle::8      6737959      2.35%    100.00% # Number of insts commited each cycle
+system.cpu.commit.committed_per_cycle::0    121705322     40.24%     40.24% # Number of insts commited each cycle
+system.cpu.commit.committed_per_cycle::1     14450311      4.78%     45.01% # Number of insts commited each cycle
+system.cpu.commit.committed_per_cycle::2      4296632      1.42%     46.43% # Number of insts commited each cycle
+system.cpu.commit.committed_per_cycle::3     76653351     25.34%     71.77% # Number of insts commited each cycle
+system.cpu.commit.committed_per_cycle::4      3954227      1.31%     73.08% # Number of insts commited each cycle
+system.cpu.commit.committed_per_cycle::5      1803566      0.60%     73.68% # Number of insts commited each cycle
+system.cpu.commit.committed_per_cycle::6      1076627      0.36%     74.03% # Number of insts commited each cycle
+system.cpu.commit.committed_per_cycle::7     71984714     23.80%     97.83% # Number of insts commited each cycle
+system.cpu.commit.committed_per_cycle::8      6557782      2.17%    100.00% # Number of insts commited each cycle
 system.cpu.commit.committed_per_cycle::overflows            0      0.00%    100.00% # Number of insts commited each cycle
 system.cpu.commit.committed_per_cycle::min_value            0                       # Number of insts commited each cycle
 system.cpu.commit.committed_per_cycle::max_value            8                       # Number of insts commited each cycle
-system.cpu.commit.committed_per_cycle::total    287133088                       # Number of insts commited each cycle
-system.cpu.commit.count                     840808469                       # Number of instructions committed
+system.cpu.commit.committed_per_cycle::total    302482532                       # Number of insts commited each cycle
+system.cpu.commit.count                     840653382                       # Number of instructions committed
 system.cpu.commit.swp_count                         0                       # Number of s/w prefetches committed
-system.cpu.commit.refs                       23765746                       # Number of memory references committed
-system.cpu.commit.loads                      15333838                       # Number of loads committed
-system.cpu.commit.membars                      781579                       # Number of memory barriers committed
-system.cpu.commit.branches                   85539454                       # Number of branches committed
+system.cpu.commit.refs                       23755065                       # Number of memory references committed
+system.cpu.commit.loads                      15325732                       # Number of loads committed
+system.cpu.commit.membars                      781571                       # Number of memory barriers committed
+system.cpu.commit.branches                   85522464                       # Number of branches committed
 system.cpu.commit.fp_insts                          0                       # Number of committed floating point instructions.
-system.cpu.commit.int_insts                 768627958                       # Number of committed integer instructions.
+system.cpu.commit.int_insts                 768481836                       # Number of committed integer instructions.
 system.cpu.commit.function_calls                    0                       # Number of function calls committed.
-system.cpu.commit.bw_lim_events               6737959                       # number cycles where commit BW limit reached
+system.cpu.commit.bw_lim_events               6557782                       # number cycles where commit BW limit reached
 system.cpu.commit.bw_limited                        0                       # number of insts not committed due to BW limits
-system.cpu.rob.rob_reads                   1152856114                       # The number of ROB reads
-system.cpu.rob.rob_writes                  1749856645                       # The number of ROB writes
-system.cpu.timesIdled                         3066243                       # Number of times that the entire CPU went into an idle state and unscheduled itself
-system.cpu.idleCycles                       158004780                       # Total number of cycles that the CPU has spent unscheduled due to idling
-system.cpu.quiesceCycles                   9872474852                       # Total number of cycles that CPU has spent quiesced or waiting for an interrupt
-system.cpu.committedInsts                   840808469                       # Number of Instructions Simulated
-system.cpu.committedInsts_total             840808469                       # Number of Instructions Simulated
-system.cpu.cpi                               0.535055                       # CPI: Cycles Per Instruction
-system.cpu.cpi_total                         0.535055                       # CPI: Total CPI of All Threads
-system.cpu.ipc                               1.868968                       # IPC: Instructions Per Cycle
-system.cpu.ipc_total                         1.868968                       # IPC: Total IPC of All Threads
-system.cpu.int_regfile_reads               1407444841                       # number of integer regfile reads
-system.cpu.int_regfile_writes               857665866                       # number of integer regfile writes
-system.cpu.fp_regfile_reads                        50                       # number of floating regfile reads
-system.cpu.misc_regfile_reads               282350765                       # number of misc regfile reads
-system.cpu.misc_regfile_writes                 410137                       # number of misc regfile writes
-system.cpu.icache.replacements                1031767                       # number of replacements
-system.cpu.icache.tagsinuse                510.488308                       # Cycle average of tags in use
-system.cpu.icache.total_refs                  8766017                       # Total number of references to valid blocks.
-system.cpu.icache.sampled_refs                1032279                       # Sample count of references to valid blocks.
-system.cpu.icache.avg_refs                   8.491907                       # Average number of references to valid blocks.
-system.cpu.icache.warmup_cycle            54591118000                       # Cycle when the warmup percentage was hit.
-system.cpu.icache.occ_blocks::0            510.488308                       # Average occupied blocks per context
-system.cpu.icache.occ_percent::0             0.997047                       # Average percentage of cache occupancy
-system.cpu.icache.ReadReq_hits::0             8766017                       # number of ReadReq hits
-system.cpu.icache.ReadReq_hits::total         8766017                       # number of ReadReq hits
-system.cpu.icache.demand_hits::0              8766017                       # number of demand (read+write) hits
+system.cpu.rob.rob_reads                   1166989570                       # The number of ROB reads
+system.cpu.rob.rob_writes                  1746890100                       # The number of ROB writes
+system.cpu.timesIdled                         2859611                       # Number of times that the entire CPU went into an idle state and unscheduled itself
+system.cpu.idleCycles                       155597963                       # Total number of cycles that the CPU has spent unscheduled due to idling
+system.cpu.quiesceCycles                   9866635724                       # Total number of cycles that CPU has spent quiesced or waiting for an interrupt
+system.cpu.committedInsts                   840653382                       # Number of Instructions Simulated
+system.cpu.committedInsts_total             840653382                       # Number of Instructions Simulated
+system.cpu.cpi                               0.550343                       # CPI: Cycles Per Instruction
+system.cpu.cpi_total                         0.550343                       # CPI: Total CPI of All Threads
+system.cpu.ipc                               1.817047                       # IPC: Instructions Per Cycle
+system.cpu.ipc_total                         1.817047                       # IPC: Total IPC of All Threads
+system.cpu.int_regfile_reads               1406419580                       # number of integer regfile reads
+system.cpu.int_regfile_writes               857121538                       # number of integer regfile writes
+system.cpu.fp_regfile_reads                        51                       # number of floating regfile reads
+system.cpu.misc_regfile_reads               282006262                       # number of misc regfile reads
+system.cpu.misc_regfile_writes                 409317                       # number of misc regfile writes
+system.cpu.icache.replacements                1024030                       # number of replacements
+system.cpu.icache.tagsinuse                510.509684                       # Cycle average of tags in use
+system.cpu.icache.total_refs                  8586920                       # Total number of references to valid blocks.
+system.cpu.icache.sampled_refs                1024542                       # Sample count of references to valid blocks.
+system.cpu.icache.avg_refs                   8.381228                       # Average number of references to valid blocks.
+system.cpu.icache.warmup_cycle            56648663000                       # Cycle when the warmup percentage was hit.
+system.cpu.icache.occ_blocks::0            510.509684                       # Average occupied blocks per context
+system.cpu.icache.occ_percent::0             0.997089                       # Average percentage of cache occupancy
+system.cpu.icache.ReadReq_hits::0             8586920                       # number of ReadReq hits
+system.cpu.icache.ReadReq_hits::total         8586920                       # number of ReadReq hits
+system.cpu.icache.demand_hits::0              8586920                       # number of demand (read+write) hits
 system.cpu.icache.demand_hits::1                    0                       # number of demand (read+write) hits
-system.cpu.icache.demand_hits::total          8766017                       # number of demand (read+write) hits
-system.cpu.icache.overall_hits::0             8766017                       # number of overall hits
+system.cpu.icache.demand_hits::total          8586920                       # number of demand (read+write) hits
+system.cpu.icache.overall_hits::0             8586920                       # number of overall hits
 system.cpu.icache.overall_hits::1                   0                       # number of overall hits
-system.cpu.icache.overall_hits::total         8766017                       # number of overall hits
-system.cpu.icache.ReadReq_misses::0           1100959                       # number of ReadReq misses
-system.cpu.icache.ReadReq_misses::total       1100959                       # number of ReadReq misses
-system.cpu.icache.demand_misses::0            1100959                       # number of demand (read+write) misses
+system.cpu.icache.overall_hits::total         8586920                       # number of overall hits
+system.cpu.icache.ReadReq_misses::0           1090085                       # number of ReadReq misses
+system.cpu.icache.ReadReq_misses::total       1090085                       # number of ReadReq misses
+system.cpu.icache.demand_misses::0            1090085                       # number of demand (read+write) misses
 system.cpu.icache.demand_misses::1                  0                       # number of demand (read+write) misses
-system.cpu.icache.demand_misses::total        1100959                       # number of demand (read+write) misses
-system.cpu.icache.overall_misses::0           1100959                       # number of overall misses
+system.cpu.icache.demand_misses::total        1090085                       # number of demand (read+write) misses
+system.cpu.icache.overall_misses::0           1090085                       # number of overall misses
 system.cpu.icache.overall_misses::1                 0                       # number of overall misses
-system.cpu.icache.overall_misses::total       1100959                       # number of overall misses
-system.cpu.icache.ReadReq_miss_latency    16475831488                       # number of ReadReq miss cycles
-system.cpu.icache.demand_miss_latency     16475831488                       # number of demand (read+write) miss cycles
-system.cpu.icache.overall_miss_latency    16475831488                       # number of overall miss cycles
-system.cpu.icache.ReadReq_accesses::0         9866976                       # number of ReadReq accesses(hits+misses)
-system.cpu.icache.ReadReq_accesses::total      9866976                       # number of ReadReq accesses(hits+misses)
-system.cpu.icache.demand_accesses::0          9866976                       # number of demand (read+write) accesses
+system.cpu.icache.overall_misses::total       1090085                       # number of overall misses
+system.cpu.icache.ReadReq_miss_latency    16354144492                       # number of ReadReq miss cycles
+system.cpu.icache.demand_miss_latency     16354144492                       # number of demand (read+write) miss cycles
+system.cpu.icache.overall_miss_latency    16354144492                       # number of overall miss cycles
+system.cpu.icache.ReadReq_accesses::0         9677005                       # number of ReadReq accesses(hits+misses)
+system.cpu.icache.ReadReq_accesses::total      9677005                       # number of ReadReq accesses(hits+misses)
+system.cpu.icache.demand_accesses::0          9677005                       # number of demand (read+write) accesses
 system.cpu.icache.demand_accesses::1                0                       # number of demand (read+write) accesses
-system.cpu.icache.demand_accesses::total      9866976                       # number of demand (read+write) accesses
-system.cpu.icache.overall_accesses::0         9866976                       # number of overall (read+write) accesses
+system.cpu.icache.demand_accesses::total      9677005                       # number of demand (read+write) accesses
+system.cpu.icache.overall_accesses::0         9677005                       # number of overall (read+write) accesses
 system.cpu.icache.overall_accesses::1               0                       # number of overall (read+write) accesses
-system.cpu.icache.overall_accesses::total      9866976                       # number of overall (read+write) accesses
-system.cpu.icache.ReadReq_miss_rate::0       0.111580                       # miss rate for ReadReq accesses
-system.cpu.icache.demand_miss_rate::0        0.111580                       # miss rate for demand accesses
+system.cpu.icache.overall_accesses::total      9677005                       # number of overall (read+write) accesses
+system.cpu.icache.ReadReq_miss_rate::0       0.112647                       # miss rate for ReadReq accesses
+system.cpu.icache.demand_miss_rate::0        0.112647                       # miss rate for demand accesses
 system.cpu.icache.demand_miss_rate::1        no_value                       # miss rate for demand accesses
 system.cpu.icache.demand_miss_rate::total     no_value                       # miss rate for demand accesses
-system.cpu.icache.overall_miss_rate::0       0.111580                       # miss rate for overall accesses
+system.cpu.icache.overall_miss_rate::0       0.112647                       # miss rate for overall accesses
 system.cpu.icache.overall_miss_rate::1       no_value                       # miss rate for overall accesses
 system.cpu.icache.overall_miss_rate::total     no_value                       # miss rate for overall accesses
-system.cpu.icache.ReadReq_avg_miss_latency::0 14964.981882                       # average ReadReq miss latency
+system.cpu.icache.ReadReq_avg_miss_latency::0 15002.632356                       # average ReadReq miss latency
 system.cpu.icache.ReadReq_avg_miss_latency::1          inf                       # average ReadReq miss latency
 system.cpu.icache.ReadReq_avg_miss_latency::total          inf                       # average ReadReq miss latency
-system.cpu.icache.demand_avg_miss_latency::0 14964.981882                       # average overall miss latency
+system.cpu.icache.demand_avg_miss_latency::0 15002.632356                       # average overall miss latency
 system.cpu.icache.demand_avg_miss_latency::1          inf                       # average overall miss latency
 system.cpu.icache.demand_avg_miss_latency::total          inf                       # average overall miss latency
-system.cpu.icache.overall_avg_miss_latency::0 14964.981882                       # average overall miss latency
+system.cpu.icache.overall_avg_miss_latency::0 15002.632356                       # average overall miss latency
 system.cpu.icache.overall_avg_miss_latency::1          inf                       # average overall miss latency
 system.cpu.icache.overall_avg_miss_latency::total          inf                       # average overall miss latency
-system.cpu.icache.blocked_cycles::no_mshrs      2787490                       # number of cycles access was blocked
+system.cpu.icache.blocked_cycles::no_mshrs      2751493                       # number of cycles access was blocked
 system.cpu.icache.blocked_cycles::no_targets            0                       # number of cycles access was blocked
-system.cpu.icache.blocked::no_mshrs               276                       # number of cycles access was blocked
+system.cpu.icache.blocked::no_mshrs               271                       # number of cycles access was blocked
 system.cpu.icache.blocked::no_targets               0                       # number of cycles access was blocked
-system.cpu.icache.avg_blocked_cycles::no_mshrs 10099.601449                       # average number of cycles each access was blocked
+system.cpu.icache.avg_blocked_cycles::no_mshrs 10153.110701                       # average number of cycles each access was blocked
 system.cpu.icache.avg_blocked_cycles::no_targets     no_value                       # average number of cycles each access was blocked
 system.cpu.icache.fast_writes                       0                       # number of fast writes performed
 system.cpu.icache.cache_copies                      0                       # number of cache copies performed
-system.cpu.icache.writebacks                     1565                       # number of writebacks
-system.cpu.icache.ReadReq_mshr_hits             66134                       # number of ReadReq MSHR hits
-system.cpu.icache.demand_mshr_hits              66134                       # number of demand (read+write) MSHR hits
-system.cpu.icache.overall_mshr_hits             66134                       # number of overall MSHR hits
-system.cpu.icache.ReadReq_mshr_misses         1034825                       # number of ReadReq MSHR misses
-system.cpu.icache.demand_mshr_misses          1034825                       # number of demand (read+write) MSHR misses
-system.cpu.icache.overall_mshr_misses         1034825                       # number of overall MSHR misses
+system.cpu.icache.writebacks                     1551                       # number of writebacks
+system.cpu.icache.ReadReq_mshr_hits             61895                       # number of ReadReq MSHR hits
+system.cpu.icache.demand_mshr_hits              61895                       # number of demand (read+write) MSHR hits
+system.cpu.icache.overall_mshr_hits             61895                       # number of overall MSHR hits
+system.cpu.icache.ReadReq_mshr_misses         1028190                       # number of ReadReq MSHR misses
+system.cpu.icache.demand_mshr_misses          1028190                       # number of demand (read+write) MSHR misses
+system.cpu.icache.overall_mshr_misses         1028190                       # number of overall MSHR misses
 system.cpu.icache.overall_mshr_uncacheable_misses            0                       # number of overall MSHR uncacheable misses
-system.cpu.icache.ReadReq_mshr_miss_latency  12496503490                       # number of ReadReq MSHR miss cycles
-system.cpu.icache.demand_mshr_miss_latency  12496503490                       # number of demand (read+write) MSHR miss cycles
-system.cpu.icache.overall_mshr_miss_latency  12496503490                       # number of overall MSHR miss cycles
+system.cpu.icache.ReadReq_mshr_miss_latency  12436535493                       # number of ReadReq MSHR miss cycles
+system.cpu.icache.demand_mshr_miss_latency  12436535493                       # number of demand (read+write) MSHR miss cycles
+system.cpu.icache.overall_mshr_miss_latency  12436535493                       # number of overall MSHR miss cycles
 system.cpu.icache.overall_mshr_uncacheable_latency            0                       # number of overall MSHR uncacheable cycles
-system.cpu.icache.ReadReq_mshr_miss_rate::0     0.104878                       # mshr miss rate for ReadReq accesses
+system.cpu.icache.ReadReq_mshr_miss_rate::0     0.106251                       # mshr miss rate for ReadReq accesses
 system.cpu.icache.ReadReq_mshr_miss_rate::1          inf                       # mshr miss rate for ReadReq accesses
 system.cpu.icache.ReadReq_mshr_miss_rate::total          inf                       # mshr miss rate for ReadReq accesses
-system.cpu.icache.demand_mshr_miss_rate::0     0.104878                       # mshr miss rate for demand accesses
+system.cpu.icache.demand_mshr_miss_rate::0     0.106251                       # mshr miss rate for demand accesses
 system.cpu.icache.demand_mshr_miss_rate::1          inf                       # mshr miss rate for demand accesses
 system.cpu.icache.demand_mshr_miss_rate::total          inf                       # mshr miss rate for demand accesses
-system.cpu.icache.overall_mshr_miss_rate::0     0.104878                       # mshr miss rate for overall accesses
+system.cpu.icache.overall_mshr_miss_rate::0     0.106251                       # mshr miss rate for overall accesses
 system.cpu.icache.overall_mshr_miss_rate::1          inf                       # mshr miss rate for overall accesses
 system.cpu.icache.overall_mshr_miss_rate::total          inf                       # mshr miss rate for overall accesses
-system.cpu.icache.ReadReq_avg_mshr_miss_latency 12075.958244                       # average ReadReq mshr miss latency
-system.cpu.icache.demand_avg_mshr_miss_latency 12075.958244                       # average overall mshr miss latency
-system.cpu.icache.overall_avg_mshr_miss_latency 12075.958244                       # average overall mshr miss latency
+system.cpu.icache.ReadReq_avg_mshr_miss_latency 12095.561611                       # average ReadReq mshr miss latency
+system.cpu.icache.demand_avg_mshr_miss_latency 12095.561611                       # average overall mshr miss latency
+system.cpu.icache.overall_avg_mshr_miss_latency 12095.561611                       # average overall mshr miss latency
 system.cpu.icache.overall_avg_mshr_uncacheable_latency     no_value                       # average overall mshr uncacheable latency
 system.cpu.icache.mshr_cap_events                   0                       # number of times MSHR cap was activated
 system.cpu.icache.soft_prefetch_mshr_full            0                       # number of mshr full events for SW prefetching instrutions
 system.cpu.icache.no_allocate_misses                0                       # Number of misses that were no-allocate
-system.cpu.itb_walker_cache.replacements         8819                       # number of replacements
-system.cpu.itb_walker_cache.tagsinuse        6.022437                       # Cycle average of tags in use
-system.cpu.itb_walker_cache.total_refs          26537                       # Total number of references to valid blocks.
-system.cpu.itb_walker_cache.sampled_refs         8831                       # Sample count of references to valid blocks.
-system.cpu.itb_walker_cache.avg_refs         3.004982                       # Average number of references to valid blocks.
-system.cpu.itb_walker_cache.warmup_cycle 5118899189000                       # Cycle when the warmup percentage was hit.
-system.cpu.itb_walker_cache.occ_blocks::1     6.022437                       # Average occupied blocks per context
-system.cpu.itb_walker_cache.occ_percent::1     0.376402                       # Average percentage of cache occupancy
-system.cpu.itb_walker_cache.ReadReq_hits::1        26634                       # number of ReadReq hits
-system.cpu.itb_walker_cache.ReadReq_hits::total        26634                       # number of ReadReq hits
+system.cpu.itb_walker_cache.replacements         9946                       # number of replacements
+system.cpu.itb_walker_cache.tagsinuse        6.010746                       # Cycle average of tags in use
+system.cpu.itb_walker_cache.total_refs          24573                       # Total number of references to valid blocks.
+system.cpu.itb_walker_cache.sampled_refs         9958                       # Sample count of references to valid blocks.
+system.cpu.itb_walker_cache.avg_refs         2.467664                       # Average number of references to valid blocks.
+system.cpu.itb_walker_cache.warmup_cycle 5129655075000                       # Cycle when the warmup percentage was hit.
+system.cpu.itb_walker_cache.occ_blocks::1     6.010746                       # Average occupied blocks per context
+system.cpu.itb_walker_cache.occ_percent::1     0.375672                       # Average percentage of cache occupancy
+system.cpu.itb_walker_cache.ReadReq_hits::1        24609                       # number of ReadReq hits
+system.cpu.itb_walker_cache.ReadReq_hits::total        24609                       # number of ReadReq hits
 system.cpu.itb_walker_cache.WriteReq_hits::1            3                       # number of WriteReq hits
 system.cpu.itb_walker_cache.WriteReq_hits::total            3                       # number of WriteReq hits
 system.cpu.itb_walker_cache.demand_hits::0            0                       # number of demand (read+write) hits
-system.cpu.itb_walker_cache.demand_hits::1        26637                       # number of demand (read+write) hits
-system.cpu.itb_walker_cache.demand_hits::total        26637                       # number of demand (read+write) hits
+system.cpu.itb_walker_cache.demand_hits::1        24612                       # number of demand (read+write) hits
+system.cpu.itb_walker_cache.demand_hits::total        24612                       # number of demand (read+write) hits
 system.cpu.itb_walker_cache.overall_hits::0            0                       # number of overall hits
-system.cpu.itb_walker_cache.overall_hits::1        26637                       # number of overall hits
-system.cpu.itb_walker_cache.overall_hits::total        26637                       # number of overall hits
-system.cpu.itb_walker_cache.ReadReq_misses::1         9699                       # number of ReadReq misses
-system.cpu.itb_walker_cache.ReadReq_misses::total         9699                       # number of ReadReq misses
+system.cpu.itb_walker_cache.overall_hits::1        24612                       # number of overall hits
+system.cpu.itb_walker_cache.overall_hits::total        24612                       # number of overall hits
+system.cpu.itb_walker_cache.ReadReq_misses::1        10808                       # number of ReadReq misses
+system.cpu.itb_walker_cache.ReadReq_misses::total        10808                       # number of ReadReq misses
 system.cpu.itb_walker_cache.demand_misses::0            0                       # number of demand (read+write) misses
-system.cpu.itb_walker_cache.demand_misses::1         9699                       # number of demand (read+write) misses
-system.cpu.itb_walker_cache.demand_misses::total         9699                       # number of demand (read+write) misses
+system.cpu.itb_walker_cache.demand_misses::1        10808                       # number of demand (read+write) misses
+system.cpu.itb_walker_cache.demand_misses::total        10808                       # number of demand (read+write) misses
 system.cpu.itb_walker_cache.overall_misses::0            0                       # number of overall misses
-system.cpu.itb_walker_cache.overall_misses::1         9699                       # number of overall misses
-system.cpu.itb_walker_cache.overall_misses::total         9699                       # number of overall misses
-system.cpu.itb_walker_cache.ReadReq_miss_latency    124296000                       # number of ReadReq miss cycles
-system.cpu.itb_walker_cache.demand_miss_latency    124296000                       # number of demand (read+write) miss cycles
-system.cpu.itb_walker_cache.overall_miss_latency    124296000                       # number of overall miss cycles
-system.cpu.itb_walker_cache.ReadReq_accesses::1        36333                       # number of ReadReq accesses(hits+misses)
-system.cpu.itb_walker_cache.ReadReq_accesses::total        36333                       # number of ReadReq accesses(hits+misses)
+system.cpu.itb_walker_cache.overall_misses::1        10808                       # number of overall misses
+system.cpu.itb_walker_cache.overall_misses::total        10808                       # number of overall misses
+system.cpu.itb_walker_cache.ReadReq_miss_latency    135307500                       # number of ReadReq miss cycles
+system.cpu.itb_walker_cache.demand_miss_latency    135307500                       # number of demand (read+write) miss cycles
+system.cpu.itb_walker_cache.overall_miss_latency    135307500                       # number of overall miss cycles
+system.cpu.itb_walker_cache.ReadReq_accesses::1        35417                       # number of ReadReq accesses(hits+misses)
+system.cpu.itb_walker_cache.ReadReq_accesses::total        35417                       # number of ReadReq accesses(hits+misses)
 system.cpu.itb_walker_cache.WriteReq_accesses::1            3                       # number of WriteReq accesses(hits+misses)
 system.cpu.itb_walker_cache.WriteReq_accesses::total            3                       # number of WriteReq accesses(hits+misses)
 system.cpu.itb_walker_cache.demand_accesses::0            0                       # number of demand (read+write) accesses
-system.cpu.itb_walker_cache.demand_accesses::1        36336                       # number of demand (read+write) accesses
-system.cpu.itb_walker_cache.demand_accesses::total        36336                       # number of demand (read+write) accesses
+system.cpu.itb_walker_cache.demand_accesses::1        35420                       # number of demand (read+write) accesses
+system.cpu.itb_walker_cache.demand_accesses::total        35420                       # number of demand (read+write) accesses
 system.cpu.itb_walker_cache.overall_accesses::0            0                       # number of overall (read+write) accesses
-system.cpu.itb_walker_cache.overall_accesses::1        36336                       # number of overall (read+write) accesses
-system.cpu.itb_walker_cache.overall_accesses::total        36336                       # number of overall (read+write) accesses
-system.cpu.itb_walker_cache.ReadReq_miss_rate::1     0.266947                       # miss rate for ReadReq accesses
+system.cpu.itb_walker_cache.overall_accesses::1        35420                       # number of overall (read+write) accesses
+system.cpu.itb_walker_cache.overall_accesses::total        35420                       # number of overall (read+write) accesses
+system.cpu.itb_walker_cache.ReadReq_miss_rate::1     0.305164                       # miss rate for ReadReq accesses
 system.cpu.itb_walker_cache.demand_miss_rate::0     no_value                       # miss rate for demand accesses
-system.cpu.itb_walker_cache.demand_miss_rate::1     0.266925                       # miss rate for demand accesses
+system.cpu.itb_walker_cache.demand_miss_rate::1     0.305138                       # miss rate for demand accesses
 system.cpu.itb_walker_cache.demand_miss_rate::total     no_value                       # miss rate for demand accesses
 system.cpu.itb_walker_cache.overall_miss_rate::0     no_value                       # miss rate for overall accesses
-system.cpu.itb_walker_cache.overall_miss_rate::1     0.266925                       # miss rate for overall accesses
+system.cpu.itb_walker_cache.overall_miss_rate::1     0.305138                       # miss rate for overall accesses
 system.cpu.itb_walker_cache.overall_miss_rate::total     no_value                       # miss rate for overall accesses
 system.cpu.itb_walker_cache.ReadReq_avg_miss_latency::0          inf                       # average ReadReq miss latency
-system.cpu.itb_walker_cache.ReadReq_avg_miss_latency::1 12815.341788                       # average ReadReq miss latency
+system.cpu.itb_walker_cache.ReadReq_avg_miss_latency::1 12519.198742                       # average ReadReq miss latency
 system.cpu.itb_walker_cache.ReadReq_avg_miss_latency::total          inf                       # average ReadReq miss latency
 system.cpu.itb_walker_cache.demand_avg_miss_latency::0          inf                       # average overall miss latency
-system.cpu.itb_walker_cache.demand_avg_miss_latency::1 12815.341788                       # average overall miss latency
+system.cpu.itb_walker_cache.demand_avg_miss_latency::1 12519.198742                       # average overall miss latency
 system.cpu.itb_walker_cache.demand_avg_miss_latency::total          inf                       # average overall miss latency
 system.cpu.itb_walker_cache.overall_avg_miss_latency::0          inf                       # average overall miss latency
-system.cpu.itb_walker_cache.overall_avg_miss_latency::1 12815.341788                       # average overall miss latency
+system.cpu.itb_walker_cache.overall_avg_miss_latency::1 12519.198742                       # average overall miss latency
 system.cpu.itb_walker_cache.overall_avg_miss_latency::total          inf                       # average overall miss latency
 system.cpu.itb_walker_cache.blocked_cycles::no_mshrs            0                       # number of cycles access was blocked
 system.cpu.itb_walker_cache.blocked_cycles::no_targets            0                       # number of cycles access was blocked
@@ -685,83 +684,83 @@
 system.cpu.itb_walker_cache.avg_blocked_cycles::no_targets     no_value                       # average number of cycles each access was blocked
 system.cpu.itb_walker_cache.fast_writes             0                       # number of fast writes performed
 system.cpu.itb_walker_cache.cache_copies            0                       # number of cache copies performed
-system.cpu.itb_walker_cache.writebacks           1368                       # number of writebacks
+system.cpu.itb_walker_cache.writebacks           1317                       # number of writebacks
 system.cpu.itb_walker_cache.demand_mshr_hits            0                       # number of demand (read+write) MSHR hits
 system.cpu.itb_walker_cache.overall_mshr_hits            0                       # number of overall MSHR hits
-system.cpu.itb_walker_cache.ReadReq_mshr_misses         9699                       # number of ReadReq MSHR misses
-system.cpu.itb_walker_cache.demand_mshr_misses         9699                       # number of demand (read+write) MSHR misses
-system.cpu.itb_walker_cache.overall_mshr_misses         9699                       # number of overall MSHR misses
+system.cpu.itb_walker_cache.ReadReq_mshr_misses        10808                       # number of ReadReq MSHR misses
+system.cpu.itb_walker_cache.demand_mshr_misses        10808                       # number of demand (read+write) MSHR misses
+system.cpu.itb_walker_cache.overall_mshr_misses        10808                       # number of overall MSHR misses
 system.cpu.itb_walker_cache.overall_mshr_uncacheable_misses            0                       # number of overall MSHR uncacheable misses
-system.cpu.itb_walker_cache.ReadReq_mshr_miss_latency     94849000                       # number of ReadReq MSHR miss cycles
-system.cpu.itb_walker_cache.demand_mshr_miss_latency     94849000                       # number of demand (read+write) MSHR miss cycles
-system.cpu.itb_walker_cache.overall_mshr_miss_latency     94849000                       # number of overall MSHR miss cycles
+system.cpu.itb_walker_cache.ReadReq_mshr_miss_latency    102536000                       # number of ReadReq MSHR miss cycles
+system.cpu.itb_walker_cache.demand_mshr_miss_latency    102536000                       # number of demand (read+write) MSHR miss cycles
+system.cpu.itb_walker_cache.overall_mshr_miss_latency    102536000                       # number of overall MSHR miss cycles
 system.cpu.itb_walker_cache.overall_mshr_uncacheable_latency            0                       # number of overall MSHR uncacheable cycles
 system.cpu.itb_walker_cache.ReadReq_mshr_miss_rate::0          inf                       # mshr miss rate for ReadReq accesses
-system.cpu.itb_walker_cache.ReadReq_mshr_miss_rate::1     0.266947                       # mshr miss rate for ReadReq accesses
+system.cpu.itb_walker_cache.ReadReq_mshr_miss_rate::1     0.305164                       # mshr miss rate for ReadReq accesses
 system.cpu.itb_walker_cache.ReadReq_mshr_miss_rate::total          inf                       # mshr miss rate for ReadReq accesses
 system.cpu.itb_walker_cache.demand_mshr_miss_rate::0          inf                       # mshr miss rate for demand accesses
-system.cpu.itb_walker_cache.demand_mshr_miss_rate::1     0.266925                       # mshr miss rate for demand accesses
+system.cpu.itb_walker_cache.demand_mshr_miss_rate::1     0.305138                       # mshr miss rate for demand accesses
 system.cpu.itb_walker_cache.demand_mshr_miss_rate::total          inf                       # mshr miss rate for demand accesses
 system.cpu.itb_walker_cache.overall_mshr_miss_rate::0          inf                       # mshr miss rate for overall accesses
-system.cpu.itb_walker_cache.overall_mshr_miss_rate::1     0.266925                       # mshr miss rate for overall accesses
+system.cpu.itb_walker_cache.overall_mshr_miss_rate::1     0.305138                       # mshr miss rate for overall accesses
 system.cpu.itb_walker_cache.overall_mshr_miss_rate::total          inf                       # mshr miss rate for overall accesses
-system.cpu.itb_walker_cache.ReadReq_avg_mshr_miss_latency  9779.255593                       # average ReadReq mshr miss latency
-system.cpu.itb_walker_cache.demand_avg_mshr_miss_latency  9779.255593                       # average overall mshr miss latency
-system.cpu.itb_walker_cache.overall_avg_mshr_miss_latency  9779.255593                       # average overall mshr miss latency
+system.cpu.itb_walker_cache.ReadReq_avg_mshr_miss_latency  9487.046632                       # average ReadReq mshr miss latency
+system.cpu.itb_walker_cache.demand_avg_mshr_miss_latency  9487.046632                       # average overall mshr miss latency
+system.cpu.itb_walker_cache.overall_avg_mshr_miss_latency  9487.046632                       # average overall mshr miss latency
 system.cpu.itb_walker_cache.overall_avg_mshr_uncacheable_latency     no_value                       # average overall mshr uncacheable latency
 system.cpu.itb_walker_cache.mshr_cap_events            0                       # number of times MSHR cap was activated
 system.cpu.itb_walker_cache.soft_prefetch_mshr_full            0                       # number of mshr full events for SW prefetching instrutions
 system.cpu.itb_walker_cache.no_allocate_misses            0                       # Number of misses that were no-allocate
-system.cpu.dtb_walker_cache.replacements       145081                       # number of replacements
-system.cpu.dtb_walker_cache.tagsinuse       13.868389                       # Cycle average of tags in use
-system.cpu.dtb_walker_cache.total_refs         150553                       # Total number of references to valid blocks.
-system.cpu.dtb_walker_cache.sampled_refs       145096                       # Sample count of references to valid blocks.
-system.cpu.dtb_walker_cache.avg_refs         1.037610                       # Average number of references to valid blocks.
-system.cpu.dtb_walker_cache.warmup_cycle 5102657828000                       # Cycle when the warmup percentage was hit.
-system.cpu.dtb_walker_cache.occ_blocks::1    13.868389                       # Average occupied blocks per context
-system.cpu.dtb_walker_cache.occ_percent::1     0.866774                       # Average percentage of cache occupancy
-system.cpu.dtb_walker_cache.ReadReq_hits::1       150554                       # number of ReadReq hits
-system.cpu.dtb_walker_cache.ReadReq_hits::total       150554                       # number of ReadReq hits
+system.cpu.dtb_walker_cache.replacements       147569                       # number of replacements
+system.cpu.dtb_walker_cache.tagsinuse       13.856334                       # Cycle average of tags in use
+system.cpu.dtb_walker_cache.total_refs         141316                       # Total number of references to valid blocks.
+system.cpu.dtb_walker_cache.sampled_refs       147583                       # Sample count of references to valid blocks.
+system.cpu.dtb_walker_cache.avg_refs         0.957536                       # Average number of references to valid blocks.
+system.cpu.dtb_walker_cache.warmup_cycle 5108660928000                       # Cycle when the warmup percentage was hit.
+system.cpu.dtb_walker_cache.occ_blocks::1    13.856334                       # Average occupied blocks per context
+system.cpu.dtb_walker_cache.occ_percent::1     0.866021                       # Average percentage of cache occupancy
+system.cpu.dtb_walker_cache.ReadReq_hits::1       141317                       # number of ReadReq hits
+system.cpu.dtb_walker_cache.ReadReq_hits::total       141317                       # number of ReadReq hits
 system.cpu.dtb_walker_cache.demand_hits::0            0                       # number of demand (read+write) hits
-system.cpu.dtb_walker_cache.demand_hits::1       150554                       # number of demand (read+write) hits
-system.cpu.dtb_walker_cache.demand_hits::total       150554                       # number of demand (read+write) hits
+system.cpu.dtb_walker_cache.demand_hits::1       141317                       # number of demand (read+write) hits
+system.cpu.dtb_walker_cache.demand_hits::total       141317                       # number of demand (read+write) hits
 system.cpu.dtb_walker_cache.overall_hits::0            0                       # number of overall hits
-system.cpu.dtb_walker_cache.overall_hits::1       150554                       # number of overall hits
-system.cpu.dtb_walker_cache.overall_hits::total       150554                       # number of overall hits
-system.cpu.dtb_walker_cache.ReadReq_misses::1       146024                       # number of ReadReq misses
-system.cpu.dtb_walker_cache.ReadReq_misses::total       146024                       # number of ReadReq misses
+system.cpu.dtb_walker_cache.overall_hits::1       141317                       # number of overall hits
+system.cpu.dtb_walker_cache.overall_hits::total       141317                       # number of overall hits
+system.cpu.dtb_walker_cache.ReadReq_misses::1       148425                       # number of ReadReq misses
+system.cpu.dtb_walker_cache.ReadReq_misses::total       148425                       # number of ReadReq misses
 system.cpu.dtb_walker_cache.demand_misses::0            0                       # number of demand (read+write) misses
-system.cpu.dtb_walker_cache.demand_misses::1       146024                       # number of demand (read+write) misses
-system.cpu.dtb_walker_cache.demand_misses::total       146024                       # number of demand (read+write) misses
+system.cpu.dtb_walker_cache.demand_misses::1       148425                       # number of demand (read+write) misses
+system.cpu.dtb_walker_cache.demand_misses::total       148425                       # number of demand (read+write) misses
 system.cpu.dtb_walker_cache.overall_misses::0            0                       # number of overall misses
-system.cpu.dtb_walker_cache.overall_misses::1       146024                       # number of overall misses
-system.cpu.dtb_walker_cache.overall_misses::total       146024                       # number of overall misses
-system.cpu.dtb_walker_cache.ReadReq_miss_latency   2047200500                       # number of ReadReq miss cycles
-system.cpu.dtb_walker_cache.demand_miss_latency   2047200500                       # number of demand (read+write) miss cycles
-system.cpu.dtb_walker_cache.overall_miss_latency   2047200500                       # number of overall miss cycles
-system.cpu.dtb_walker_cache.ReadReq_accesses::1       296578                       # number of ReadReq accesses(hits+misses)
-system.cpu.dtb_walker_cache.ReadReq_accesses::total       296578                       # number of ReadReq accesses(hits+misses)
+system.cpu.dtb_walker_cache.overall_misses::1       148425                       # number of overall misses
+system.cpu.dtb_walker_cache.overall_misses::total       148425                       # number of overall misses
+system.cpu.dtb_walker_cache.ReadReq_miss_latency   2057871000                       # number of ReadReq miss cycles
+system.cpu.dtb_walker_cache.demand_miss_latency   2057871000                       # number of demand (read+write) miss cycles
+system.cpu.dtb_walker_cache.overall_miss_latency   2057871000                       # number of overall miss cycles
+system.cpu.dtb_walker_cache.ReadReq_accesses::1       289742                       # number of ReadReq accesses(hits+misses)
+system.cpu.dtb_walker_cache.ReadReq_accesses::total       289742                       # number of ReadReq accesses(hits+misses)
 system.cpu.dtb_walker_cache.demand_accesses::0            0                       # number of demand (read+write) accesses
-system.cpu.dtb_walker_cache.demand_accesses::1       296578                       # number of demand (read+write) accesses
-system.cpu.dtb_walker_cache.demand_accesses::total       296578                       # number of demand (read+write) accesses
+system.cpu.dtb_walker_cache.demand_accesses::1       289742                       # number of demand (read+write) accesses
+system.cpu.dtb_walker_cache.demand_accesses::total       289742                       # number of demand (read+write) accesses
 system.cpu.dtb_walker_cache.overall_accesses::0            0                       # number of overall (read+write) accesses
-system.cpu.dtb_walker_cache.overall_accesses::1       296578                       # number of overall (read+write) accesses
-system.cpu.dtb_walker_cache.overall_accesses::total       296578                       # number of overall (read+write) accesses
-system.cpu.dtb_walker_cache.ReadReq_miss_rate::1     0.492363                       # miss rate for ReadReq accesses
+system.cpu.dtb_walker_cache.overall_accesses::1       289742                       # number of overall (read+write) accesses
+system.cpu.dtb_walker_cache.overall_accesses::total       289742                       # number of overall (read+write) accesses
+system.cpu.dtb_walker_cache.ReadReq_miss_rate::1     0.512266                       # miss rate for ReadReq accesses
 system.cpu.dtb_walker_cache.demand_miss_rate::0     no_value                       # miss rate for demand accesses
-system.cpu.dtb_walker_cache.demand_miss_rate::1     0.492363                       # miss rate for demand accesses
+system.cpu.dtb_walker_cache.demand_miss_rate::1     0.512266                       # miss rate for demand accesses
 system.cpu.dtb_walker_cache.demand_miss_rate::total     no_value                       # miss rate for demand accesses
 system.cpu.dtb_walker_cache.overall_miss_rate::0     no_value                       # miss rate for overall accesses
-system.cpu.dtb_walker_cache.overall_miss_rate::1     0.492363                       # miss rate for overall accesses
+system.cpu.dtb_walker_cache.overall_miss_rate::1     0.512266                       # miss rate for overall accesses
 system.cpu.dtb_walker_cache.overall_miss_rate::total     no_value                       # miss rate for overall accesses
 system.cpu.dtb_walker_cache.ReadReq_avg_miss_latency::0          inf                       # average ReadReq miss latency
-system.cpu.dtb_walker_cache.ReadReq_avg_miss_latency::1 14019.616638                       # average ReadReq miss latency
+system.cpu.dtb_walker_cache.ReadReq_avg_miss_latency::1 13864.719555                       # average ReadReq miss latency
 system.cpu.dtb_walker_cache.ReadReq_avg_miss_latency::total          inf                       # average ReadReq miss latency
 system.cpu.dtb_walker_cache.demand_avg_miss_latency::0          inf                       # average overall miss latency
-system.cpu.dtb_walker_cache.demand_avg_miss_latency::1 14019.616638                       # average overall miss latency
+system.cpu.dtb_walker_cache.demand_avg_miss_latency::1 13864.719555                       # average overall miss latency
 system.cpu.dtb_walker_cache.demand_avg_miss_latency::total          inf                       # average overall miss latency
 system.cpu.dtb_walker_cache.overall_avg_miss_latency::0          inf                       # average overall miss latency
-system.cpu.dtb_walker_cache.overall_avg_miss_latency::1 14019.616638                       # average overall miss latency
+system.cpu.dtb_walker_cache.overall_avg_miss_latency::1 13864.719555                       # average overall miss latency
 system.cpu.dtb_walker_cache.overall_avg_miss_latency::total          inf                       # average overall miss latency
 system.cpu.dtb_walker_cache.blocked_cycles::no_mshrs            0                       # number of cycles access was blocked
 system.cpu.dtb_walker_cache.blocked_cycles::no_targets            0                       # number of cycles access was blocked
@@ -771,136 +770,136 @@
 system.cpu.dtb_walker_cache.avg_blocked_cycles::no_targets     no_value                       # average number of cycles each access was blocked
 system.cpu.dtb_walker_cache.fast_writes             0                       # number of fast writes performed
 system.cpu.dtb_walker_cache.cache_copies            0                       # number of cache copies performed
-system.cpu.dtb_walker_cache.writebacks          42577                       # number of writebacks
+system.cpu.dtb_walker_cache.writebacks          45859                       # number of writebacks
 system.cpu.dtb_walker_cache.demand_mshr_hits            0                       # number of demand (read+write) MSHR hits
 system.cpu.dtb_walker_cache.overall_mshr_hits            0                       # number of overall MSHR hits
-system.cpu.dtb_walker_cache.ReadReq_mshr_misses       146024                       # number of ReadReq MSHR misses
-system.cpu.dtb_walker_cache.demand_mshr_misses       146024                       # number of demand (read+write) MSHR misses
-system.cpu.dtb_walker_cache.overall_mshr_misses       146024                       # number of overall MSHR misses
+system.cpu.dtb_walker_cache.ReadReq_mshr_misses       148425                       # number of ReadReq MSHR misses
+system.cpu.dtb_walker_cache.demand_mshr_misses       148425                       # number of demand (read+write) MSHR misses
+system.cpu.dtb_walker_cache.overall_mshr_misses       148425                       # number of overall MSHR misses
 system.cpu.dtb_walker_cache.overall_mshr_uncacheable_misses            0                       # number of overall MSHR uncacheable misses
-system.cpu.dtb_walker_cache.ReadReq_mshr_miss_latency   1605163000                       # number of ReadReq MSHR miss cycles
-system.cpu.dtb_walker_cache.demand_mshr_miss_latency   1605163000                       # number of demand (read+write) MSHR miss cycles
-system.cpu.dtb_walker_cache.overall_mshr_miss_latency   1605163000                       # number of overall MSHR miss cycles
+system.cpu.dtb_walker_cache.ReadReq_mshr_miss_latency   1608796000                       # number of ReadReq MSHR miss cycles
+system.cpu.dtb_walker_cache.demand_mshr_miss_latency   1608796000                       # number of demand (read+write) MSHR miss cycles
+system.cpu.dtb_walker_cache.overall_mshr_miss_latency   1608796000                       # number of overall MSHR miss cycles
 system.cpu.dtb_walker_cache.overall_mshr_uncacheable_latency            0                       # number of overall MSHR uncacheable cycles
 system.cpu.dtb_walker_cache.ReadReq_mshr_miss_rate::0          inf                       # mshr miss rate for ReadReq accesses
-system.cpu.dtb_walker_cache.ReadReq_mshr_miss_rate::1     0.492363                       # mshr miss rate for ReadReq accesses
+system.cpu.dtb_walker_cache.ReadReq_mshr_miss_rate::1     0.512266                       # mshr miss rate for ReadReq accesses
 system.cpu.dtb_walker_cache.ReadReq_mshr_miss_rate::total          inf                       # mshr miss rate for ReadReq accesses
 system.cpu.dtb_walker_cache.demand_mshr_miss_rate::0          inf                       # mshr miss rate for demand accesses
-system.cpu.dtb_walker_cache.demand_mshr_miss_rate::1     0.492363                       # mshr miss rate for demand accesses
+system.cpu.dtb_walker_cache.demand_mshr_miss_rate::1     0.512266                       # mshr miss rate for demand accesses
 system.cpu.dtb_walker_cache.demand_mshr_miss_rate::total          inf                       # mshr miss rate for demand accesses
 system.cpu.dtb_walker_cache.overall_mshr_miss_rate::0          inf                       # mshr miss rate for overall accesses
-system.cpu.dtb_walker_cache.overall_mshr_miss_rate::1     0.492363                       # mshr miss rate for overall accesses
+system.cpu.dtb_walker_cache.overall_mshr_miss_rate::1     0.512266                       # mshr miss rate for overall accesses
 system.cpu.dtb_walker_cache.overall_mshr_miss_rate::total          inf                       # mshr miss rate for overall accesses
-system.cpu.dtb_walker_cache.ReadReq_avg_mshr_miss_latency 10992.460144                       # average ReadReq mshr miss latency
-system.cpu.dtb_walker_cache.demand_avg_mshr_miss_latency 10992.460144                       # average overall mshr miss latency
-system.cpu.dtb_walker_cache.overall_avg_mshr_miss_latency 10992.460144                       # average overall mshr miss latency
+system.cpu.dtb_walker_cache.ReadReq_avg_mshr_miss_latency 10839.117399                       # average ReadReq mshr miss latency
+system.cpu.dtb_walker_cache.demand_avg_mshr_miss_latency 10839.117399                       # average overall mshr miss latency
+system.cpu.dtb_walker_cache.overall_avg_mshr_miss_latency 10839.117399                       # average overall mshr miss latency
 system.cpu.dtb_walker_cache.overall_avg_mshr_uncacheable_latency     no_value                       # average overall mshr uncacheable latency
 system.cpu.dtb_walker_cache.mshr_cap_events            0                       # number of times MSHR cap was activated
 system.cpu.dtb_walker_cache.soft_prefetch_mshr_full            0                       # number of mshr full events for SW prefetching instrutions
 system.cpu.dtb_walker_cache.no_allocate_misses            0                       # Number of misses that were no-allocate
-system.cpu.dcache.replacements                1663087                       # number of replacements
-system.cpu.dcache.tagsinuse                511.997625                       # Cycle average of tags in use
-system.cpu.dcache.total_refs                 17982371                       # Total number of references to valid blocks.
-system.cpu.dcache.sampled_refs                1663599                       # Sample count of references to valid blocks.
-system.cpu.dcache.avg_refs                  10.809318                       # Average number of references to valid blocks.
-system.cpu.dcache.warmup_cycle               13135000                       # Cycle when the warmup percentage was hit.
-system.cpu.dcache.occ_blocks::0            511.997625                       # Average occupied blocks per context
-system.cpu.dcache.occ_percent::0             0.999995                       # Average percentage of cache occupancy
-system.cpu.dcache.ReadReq_hits::0            11413167                       # number of ReadReq hits
-system.cpu.dcache.ReadReq_hits::total        11413167                       # number of ReadReq hits
-system.cpu.dcache.WriteReq_hits::0            6547162                       # number of WriteReq hits
-system.cpu.dcache.WriteReq_hits::total        6547162                       # number of WriteReq hits
-system.cpu.dcache.demand_hits::0             17960329                       # number of demand (read+write) hits
+system.cpu.dcache.replacements                1662019                       # number of replacements
+system.cpu.dcache.tagsinuse                511.997109                       # Cycle average of tags in use
+system.cpu.dcache.total_refs                 19289790                       # Total number of references to valid blocks.
+system.cpu.dcache.sampled_refs                1662531                       # Sample count of references to valid blocks.
+system.cpu.dcache.avg_refs                  11.602665                       # Average number of references to valid blocks.
+system.cpu.dcache.warmup_cycle               34336000                       # Cycle when the warmup percentage was hit.
+system.cpu.dcache.occ_blocks::0            511.997109                       # Average occupied blocks per context
+system.cpu.dcache.occ_percent::0             0.999994                       # Average percentage of cache occupancy
+system.cpu.dcache.ReadReq_hits::0            11184512                       # number of ReadReq hits
+system.cpu.dcache.ReadReq_hits::total        11184512                       # number of ReadReq hits
+system.cpu.dcache.WriteReq_hits::0            8099002                       # number of WriteReq hits
+system.cpu.dcache.WriteReq_hits::total        8099002                       # number of WriteReq hits
+system.cpu.dcache.demand_hits::0             19283514                       # number of demand (read+write) hits
 system.cpu.dcache.demand_hits::1                    0                       # number of demand (read+write) hits
-system.cpu.dcache.demand_hits::total         17960329                       # number of demand (read+write) hits
-system.cpu.dcache.overall_hits::0            17960329                       # number of overall hits
+system.cpu.dcache.demand_hits::total         19283514                       # number of demand (read+write) hits
+system.cpu.dcache.overall_hits::0            19283514                       # number of overall hits
 system.cpu.dcache.overall_hits::1                   0                       # number of overall hits
-system.cpu.dcache.overall_hits::total        17960329                       # number of overall hits
-system.cpu.dcache.ReadReq_misses::0           2492340                       # number of ReadReq misses
-system.cpu.dcache.ReadReq_misses::total       2492340                       # number of ReadReq misses
-system.cpu.dcache.WriteReq_misses::0          1875398                       # number of WriteReq misses
-system.cpu.dcache.WriteReq_misses::total      1875398                       # number of WriteReq misses
-system.cpu.dcache.demand_misses::0            4367738                       # number of demand (read+write) misses
+system.cpu.dcache.overall_hits::total        19283514                       # number of overall hits
+system.cpu.dcache.ReadReq_misses::0           2387566                       # number of ReadReq misses
+system.cpu.dcache.ReadReq_misses::total       2387566                       # number of ReadReq misses
+system.cpu.dcache.WriteReq_misses::0           320977                       # number of WriteReq misses
+system.cpu.dcache.WriteReq_misses::total       320977                       # number of WriteReq misses
+system.cpu.dcache.demand_misses::0            2708543                       # number of demand (read+write) misses
 system.cpu.dcache.demand_misses::1                  0                       # number of demand (read+write) misses
-system.cpu.dcache.demand_misses::total        4367738                       # number of demand (read+write) misses
-system.cpu.dcache.overall_misses::0           4367738                       # number of overall misses
+system.cpu.dcache.demand_misses::total        2708543                       # number of demand (read+write) misses
+system.cpu.dcache.overall_misses::0           2708543                       # number of overall misses
 system.cpu.dcache.overall_misses::1                 0                       # number of overall misses
-system.cpu.dcache.overall_misses::total       4367738                       # number of overall misses
-system.cpu.dcache.ReadReq_miss_latency    37542071500                       # number of ReadReq miss cycles
-system.cpu.dcache.WriteReq_miss_latency   63453033216                       # number of WriteReq miss cycles
-system.cpu.dcache.demand_miss_latency    100995104716                       # number of demand (read+write) miss cycles
-system.cpu.dcache.overall_miss_latency   100995104716                       # number of overall miss cycles
-system.cpu.dcache.ReadReq_accesses::0        13905507                       # number of ReadReq accesses(hits+misses)
-system.cpu.dcache.ReadReq_accesses::total     13905507                       # number of ReadReq accesses(hits+misses)
-system.cpu.dcache.WriteReq_accesses::0        8422560                       # number of WriteReq accesses(hits+misses)
-system.cpu.dcache.WriteReq_accesses::total      8422560                       # number of WriteReq accesses(hits+misses)
-system.cpu.dcache.demand_accesses::0         22328067                       # number of demand (read+write) accesses
+system.cpu.dcache.overall_misses::total       2708543                       # number of overall misses
+system.cpu.dcache.ReadReq_miss_latency    35727347000                       # number of ReadReq miss cycles
+system.cpu.dcache.WriteReq_miss_latency   10720598495                       # number of WriteReq miss cycles
+system.cpu.dcache.demand_miss_latency     46447945495                       # number of demand (read+write) miss cycles
+system.cpu.dcache.overall_miss_latency    46447945495                       # number of overall miss cycles
+system.cpu.dcache.ReadReq_accesses::0        13572078                       # number of ReadReq accesses(hits+misses)
+system.cpu.dcache.ReadReq_accesses::total     13572078                       # number of ReadReq accesses(hits+misses)
+system.cpu.dcache.WriteReq_accesses::0        8419979                       # number of WriteReq accesses(hits+misses)
+system.cpu.dcache.WriteReq_accesses::total      8419979                       # number of WriteReq accesses(hits+misses)
+system.cpu.dcache.demand_accesses::0         21992057                       # number of demand (read+write) accesses
 system.cpu.dcache.demand_accesses::1                0                       # number of demand (read+write) accesses
-system.cpu.dcache.demand_accesses::total     22328067                       # number of demand (read+write) accesses
-system.cpu.dcache.overall_accesses::0        22328067                       # number of overall (read+write) accesses
+system.cpu.dcache.demand_accesses::total     21992057                       # number of demand (read+write) accesses
+system.cpu.dcache.overall_accesses::0        21992057                       # number of overall (read+write) accesses
 system.cpu.dcache.overall_accesses::1               0                       # number of overall (read+write) accesses
-system.cpu.dcache.overall_accesses::total     22328067                       # number of overall (read+write) accesses
-system.cpu.dcache.ReadReq_miss_rate::0       0.179234                       # miss rate for ReadReq accesses
-system.cpu.dcache.WriteReq_miss_rate::0      0.222664                       # miss rate for WriteReq accesses
-system.cpu.dcache.demand_miss_rate::0        0.195616                       # miss rate for demand accesses
+system.cpu.dcache.overall_accesses::total     21992057                       # number of overall (read+write) accesses
+system.cpu.dcache.ReadReq_miss_rate::0       0.175917                       # miss rate for ReadReq accesses
+system.cpu.dcache.WriteReq_miss_rate::0      0.038121                       # miss rate for WriteReq accesses
+system.cpu.dcache.demand_miss_rate::0        0.123160                       # miss rate for demand accesses
 system.cpu.dcache.demand_miss_rate::1        no_value                       # miss rate for demand accesses
 system.cpu.dcache.demand_miss_rate::total     no_value                       # miss rate for demand accesses
-system.cpu.dcache.overall_miss_rate::0       0.195616                       # miss rate for overall accesses
+system.cpu.dcache.overall_miss_rate::0       0.123160                       # miss rate for overall accesses
 system.cpu.dcache.overall_miss_rate::1       no_value                       # miss rate for overall accesses
 system.cpu.dcache.overall_miss_rate::total     no_value                       # miss rate for overall accesses
-system.cpu.dcache.ReadReq_avg_miss_latency::0 15062.981576                       # average ReadReq miss latency
+system.cpu.dcache.ReadReq_avg_miss_latency::0 14963.920160                       # average ReadReq miss latency
 system.cpu.dcache.ReadReq_avg_miss_latency::1          inf                       # average ReadReq miss latency
 system.cpu.dcache.ReadReq_avg_miss_latency::total          inf                       # average ReadReq miss latency
-system.cpu.dcache.WriteReq_avg_miss_latency::0 33834.435792                       # average WriteReq miss latency
+system.cpu.dcache.WriteReq_avg_miss_latency::0 33399.896239                       # average WriteReq miss latency
 system.cpu.dcache.WriteReq_avg_miss_latency::1          inf                       # average WriteReq miss latency
 system.cpu.dcache.WriteReq_avg_miss_latency::total          inf                       # average WriteReq miss latency
-system.cpu.dcache.demand_avg_miss_latency::0 23122.976863                       # average overall miss latency
+system.cpu.dcache.demand_avg_miss_latency::0 17148.683072                       # average overall miss latency
 system.cpu.dcache.demand_avg_miss_latency::1          inf                       # average overall miss latency
 system.cpu.dcache.demand_avg_miss_latency::total          inf                       # average overall miss latency
-system.cpu.dcache.overall_avg_miss_latency::0 23122.976863                       # average overall miss latency
+system.cpu.dcache.overall_avg_miss_latency::0 17148.683072                       # average overall miss latency
 system.cpu.dcache.overall_avg_miss_latency::1          inf                       # average overall miss latency
 system.cpu.dcache.overall_avg_miss_latency::total          inf                       # average overall miss latency
-system.cpu.dcache.blocked_cycles::no_mshrs   1083233153                       # number of cycles access was blocked
-system.cpu.dcache.blocked_cycles::no_targets      6672000                       # number of cycles access was blocked
-system.cpu.dcache.blocked::no_mshrs             73547                       # number of cycles access was blocked
-system.cpu.dcache.blocked::no_targets             391                       # number of cycles access was blocked
-system.cpu.dcache.avg_blocked_cycles::no_mshrs 14728.447836                       # average number of cycles each access was blocked
-system.cpu.dcache.avg_blocked_cycles::no_targets 17063.938619                       # average number of cycles each access was blocked
+system.cpu.dcache.blocked_cycles::no_mshrs     28980495                       # number of cycles access was blocked
+system.cpu.dcache.blocked_cycles::no_targets            0                       # number of cycles access was blocked
+system.cpu.dcache.blocked::no_mshrs              5023                       # number of cycles access was blocked
+system.cpu.dcache.blocked::no_targets               0                       # number of cycles access was blocked
+system.cpu.dcache.avg_blocked_cycles::no_mshrs  5769.559028                       # average number of cycles each access was blocked
+system.cpu.dcache.avg_blocked_cycles::no_targets     no_value                       # average number of cycles each access was blocked
 system.cpu.dcache.fast_writes                       0                       # number of fast writes performed
 system.cpu.dcache.cache_copies                      0                       # number of cache copies performed
-system.cpu.dcache.writebacks                  1548983                       # number of writebacks
-system.cpu.dcache.ReadReq_mshr_hits           1121085                       # number of ReadReq MSHR hits
-system.cpu.dcache.WriteReq_mshr_hits          1578340                       # number of WriteReq MSHR hits
-system.cpu.dcache.demand_mshr_hits            2699425                       # number of demand (read+write) MSHR hits
-system.cpu.dcache.overall_mshr_hits           2699425                       # number of overall MSHR hits
-system.cpu.dcache.ReadReq_mshr_misses         1371255                       # number of ReadReq MSHR misses
-system.cpu.dcache.WriteReq_mshr_misses         297058                       # number of WriteReq MSHR misses
-system.cpu.dcache.demand_mshr_misses          1668313                       # number of demand (read+write) MSHR misses
-system.cpu.dcache.overall_mshr_misses         1668313                       # number of overall MSHR misses
+system.cpu.dcache.writebacks                  1550298                       # number of writebacks
+system.cpu.dcache.ReadReq_mshr_hits           1017351                       # number of ReadReq MSHR hits
+system.cpu.dcache.WriteReq_mshr_hits            22830                       # number of WriteReq MSHR hits
+system.cpu.dcache.demand_mshr_hits            1040181                       # number of demand (read+write) MSHR hits
+system.cpu.dcache.overall_mshr_hits           1040181                       # number of overall MSHR hits
+system.cpu.dcache.ReadReq_mshr_misses         1370215                       # number of ReadReq MSHR misses
+system.cpu.dcache.WriteReq_mshr_misses         298147                       # number of WriteReq MSHR misses
+system.cpu.dcache.demand_mshr_misses          1668362                       # number of demand (read+write) MSHR misses
+system.cpu.dcache.overall_mshr_misses         1668362                       # number of overall MSHR misses
 system.cpu.dcache.overall_mshr_uncacheable_misses            0                       # number of overall MSHR uncacheable misses
-system.cpu.dcache.ReadReq_mshr_miss_latency  18154950000                       # number of ReadReq MSHR miss cycles
-system.cpu.dcache.WriteReq_mshr_miss_latency   9754920653                       # number of WriteReq MSHR miss cycles
-system.cpu.dcache.demand_mshr_miss_latency  27909870653                       # number of demand (read+write) MSHR miss cycles
-system.cpu.dcache.overall_mshr_miss_latency  27909870653                       # number of overall MSHR miss cycles
-system.cpu.dcache.ReadReq_mshr_uncacheable_latency  85210888500                       # number of ReadReq MSHR uncacheable cycles
-system.cpu.dcache.WriteReq_mshr_uncacheable_latency   1394917000                       # number of WriteReq MSHR uncacheable cycles
-system.cpu.dcache.overall_mshr_uncacheable_latency  86605805500                       # number of overall MSHR uncacheable cycles
-system.cpu.dcache.ReadReq_mshr_miss_rate::0     0.098612                       # mshr miss rate for ReadReq accesses
+system.cpu.dcache.ReadReq_mshr_miss_latency  17997979500                       # number of ReadReq MSHR miss cycles
+system.cpu.dcache.WriteReq_mshr_miss_latency   9490426995                       # number of WriteReq MSHR miss cycles
+system.cpu.dcache.demand_mshr_miss_latency  27488406495                       # number of demand (read+write) MSHR miss cycles
+system.cpu.dcache.overall_mshr_miss_latency  27488406495                       # number of overall MSHR miss cycles
+system.cpu.dcache.ReadReq_mshr_uncacheable_latency  85207522500                       # number of ReadReq MSHR uncacheable cycles
+system.cpu.dcache.WriteReq_mshr_uncacheable_latency   1392017000                       # number of WriteReq MSHR uncacheable cycles
+system.cpu.dcache.overall_mshr_uncacheable_latency  86599539500                       # number of overall MSHR uncacheable cycles
+system.cpu.dcache.ReadReq_mshr_miss_rate::0     0.100958                       # mshr miss rate for ReadReq accesses
 system.cpu.dcache.ReadReq_mshr_miss_rate::1          inf                       # mshr miss rate for ReadReq accesses
 system.cpu.dcache.ReadReq_mshr_miss_rate::total          inf                       # mshr miss rate for ReadReq accesses
-system.cpu.dcache.WriteReq_mshr_miss_rate::0     0.035269                       # mshr miss rate for WriteReq accesses
+system.cpu.dcache.WriteReq_mshr_miss_rate::0     0.035409                       # mshr miss rate for WriteReq accesses
 system.cpu.dcache.WriteReq_mshr_miss_rate::1          inf                       # mshr miss rate for WriteReq accesses
 system.cpu.dcache.WriteReq_mshr_miss_rate::total          inf                       # mshr miss rate for WriteReq accesses
-system.cpu.dcache.demand_mshr_miss_rate::0     0.074718                       # mshr miss rate for demand accesses
+system.cpu.dcache.demand_mshr_miss_rate::0     0.075862                       # mshr miss rate for demand accesses
 system.cpu.dcache.demand_mshr_miss_rate::1          inf                       # mshr miss rate for demand accesses
 system.cpu.dcache.demand_mshr_miss_rate::total          inf                       # mshr miss rate for demand accesses
-system.cpu.dcache.overall_mshr_miss_rate::0     0.074718                       # mshr miss rate for overall accesses
+system.cpu.dcache.overall_mshr_miss_rate::0     0.075862                       # mshr miss rate for overall accesses
 system.cpu.dcache.overall_mshr_miss_rate::1          inf                       # mshr miss rate for overall accesses
 system.cpu.dcache.overall_mshr_miss_rate::total          inf                       # mshr miss rate for overall accesses
-system.cpu.dcache.ReadReq_avg_mshr_miss_latency 13239.660019                       # average ReadReq mshr miss latency
-system.cpu.dcache.WriteReq_avg_mshr_miss_latency 32838.437790                       # average WriteReq mshr miss latency
-system.cpu.dcache.demand_avg_mshr_miss_latency 16729.397093                       # average overall mshr miss latency
-system.cpu.dcache.overall_avg_mshr_miss_latency 16729.397093                       # average overall mshr miss latency
+system.cpu.dcache.ReadReq_avg_mshr_miss_latency 13135.149958                       # average ReadReq mshr miss latency
+system.cpu.dcache.WriteReq_avg_mshr_miss_latency 31831.368402                       # average WriteReq mshr miss latency
+system.cpu.dcache.demand_avg_mshr_miss_latency 16476.284221                       # average overall mshr miss latency
+system.cpu.dcache.overall_avg_mshr_miss_latency 16476.284221                       # average overall mshr miss latency
 system.cpu.dcache.ReadReq_avg_mshr_uncacheable_latency          inf                       # average ReadReq mshr uncacheable latency
 system.cpu.dcache.WriteReq_avg_mshr_uncacheable_latency          inf                       # average WriteReq mshr uncacheable latency
 system.cpu.dcache.overall_avg_mshr_uncacheable_latency          inf                       # average overall mshr uncacheable latency
diff --git a/tests/long/10.linux-boot/ref/x86/linux/pc-o3-timing/system.pc.com_1.terminal b/tests/long/10.linux-boot/ref/x86/linux/pc-o3-timing/system.pc.com_1.terminal
index 6570dc3..6cae7ef 100644
--- a/tests/long/10.linux-boot/ref/x86/linux/pc-o3-timing/system.pc.com_1.terminal
+++ b/tests/long/10.linux-boot/ref/x86/linux/pc-o3-timing/system.pc.com_1.terminal
Binary files differ
diff --git a/tests/long/10.mcf/ref/x86/linux/o3-timing/config.ini b/tests/long/10.mcf/ref/x86/linux/o3-timing/config.ini
index cfda7ba..c0a2176 100644
--- a/tests/long/10.mcf/ref/x86/linux/o3-timing/config.ini
+++ b/tests/long/10.mcf/ref/x86/linux/o3-timing/config.ini
@@ -80,6 +80,7 @@
 max_insts_any_thread=0
 max_loads_all_threads=0
 max_loads_any_thread=0
+needsTSO=true
 numIQEntries=64
 numPhysFloatRegs=256
 numPhysIntRegs=256
@@ -502,9 +503,9 @@
 env=
 errout=cerr
 euid=100
-executable=/dist/m5/cpu2000/binaries/x86/linux/mcf
+executable=/scratch/nilay/GEM5/dist/m5/cpu2000/binaries/x86/linux/mcf
 gid=100
-input=/dist/m5/cpu2000/data/mcf/smred/input/mcf.in
+input=/scratch/nilay/GEM5/dist/m5/cpu2000/data/mcf/smred/input/mcf.in
 max_stack_size=67108864
 output=cout
 pid=100
diff --git a/tests/long/10.mcf/ref/x86/linux/o3-timing/simout b/tests/long/10.mcf/ref/x86/linux/o3-timing/simout
index 426afea..7ce56ed 100755
--- a/tests/long/10.mcf/ref/x86/linux/o3-timing/simout
+++ b/tests/long/10.mcf/ref/x86/linux/o3-timing/simout
@@ -1,9 +1,11 @@
+Redirecting stdout to build/X86_SE/tests/opt/long/10.mcf/x86/linux/o3-timing/simout
+Redirecting stderr to build/X86_SE/tests/opt/long/10.mcf/x86/linux/o3-timing/simerr
 gem5 Simulator System.  http://gem5.org
 gem5 is copyrighted software; use the --copyright option for details.
 
-gem5 compiled Jan 23 2012 04:08:34
-gem5 started Jan 23 2012 06:45:46
-gem5 executing on zizzer
+gem5 compiled Jan 28 2012 12:11:40
+gem5 started Jan 28 2012 12:12:43
+gem5 executing on ribera.cs.wisc.edu
 command line: build/X86_SE/gem5.opt -d build/X86_SE/tests/opt/long/10.mcf/x86/linux/o3-timing -re tests/run.py build/X86_SE/tests/opt/long/10.mcf/x86/linux/o3-timing
 Global frequency set at 1000000000000 ticks per second
 info: Entering event queue @ 0.  Starting simulation...
@@ -23,4 +25,4 @@
 flow value                 : 3080014995
 checksum                   : 68389
 optimal
-Exiting @ tick 70312944500 because target called exit()
+Exiting @ tick 70097938500 because target called exit()
diff --git a/tests/long/10.mcf/ref/x86/linux/o3-timing/stats.txt b/tests/long/10.mcf/ref/x86/linux/o3-timing/stats.txt
index f9c9708..741105f 100644
--- a/tests/long/10.mcf/ref/x86/linux/o3-timing/stats.txt
+++ b/tests/long/10.mcf/ref/x86/linux/o3-timing/stats.txt
@@ -1,158 +1,158 @@
 
 ---------- Begin Simulation Statistics ----------
-sim_seconds                                  0.070313                       # Number of seconds simulated
-sim_ticks                                 70312944500                       # Number of ticks simulated
-final_tick                                70312944500                       # Number of ticks from beginning of simulation (restored from checkpoints and never reset)
+sim_seconds                                  0.070098                       # Number of seconds simulated
+sim_ticks                                 70097938500                       # Number of ticks simulated
+final_tick                                70097938500                       # Number of ticks from beginning of simulation (restored from checkpoints and never reset)
 sim_freq                                 1000000000000                       # Frequency of simulated ticks
-host_inst_rate                                 168126                       # Simulator instruction rate (inst/s)
-host_tick_rate                               42493747                       # Simulator tick rate (ticks/s)
-host_mem_usage                                 349904                       # Number of bytes of host memory used
-host_seconds                                  1654.67                       # Real time elapsed on the host
+host_inst_rate                                 110386                       # Simulator instruction rate (inst/s)
+host_tick_rate                               27814669                       # Simulator tick rate (ticks/s)
+host_mem_usage                                 379416                       # Number of bytes of host memory used
+host_seconds                                  2520.18                       # Real time elapsed on the host
 sim_insts                                   278192519                       # Number of instructions simulated
-system.physmem.bytes_read                     4896576                       # Number of bytes read from this memory
-system.physmem.bytes_inst_read                  65344                       # Number of instructions bytes read from this memory
-system.physmem.bytes_written                  1867840                       # Number of bytes written to this memory
-system.physmem.num_reads                        76509                       # Number of read requests responded to by this memory
-system.physmem.num_writes                       29185                       # Number of write requests responded to by this memory
+system.physmem.bytes_read                     3896128                       # Number of bytes read from this memory
+system.physmem.bytes_inst_read                  65152                       # Number of instructions bytes read from this memory
+system.physmem.bytes_written                   892416                       # Number of bytes written to this memory
+system.physmem.num_reads                        60877                       # Number of read requests responded to by this memory
+system.physmem.num_writes                       13944                       # Number of write requests responded to by this memory
 system.physmem.num_other                            0                       # Number of other requests responded to by this memory
-system.physmem.bw_read                       69639752                       # Total read bandwidth from this memory (bytes/s)
-system.physmem.bw_inst_read                    929331                       # Instruction read bandwidth from this memory (bytes/s)
-system.physmem.bw_write                      26564668                       # Write bandwidth from this memory (bytes/s)
-system.physmem.bw_total                      96204419                       # Total bandwidth to/from this memory (bytes/s)
+system.physmem.bw_read                       55581207                       # Total read bandwidth from this memory (bytes/s)
+system.physmem.bw_inst_read                    929442                       # Instruction read bandwidth from this memory (bytes/s)
+system.physmem.bw_write                      12730988                       # Write bandwidth from this memory (bytes/s)
+system.physmem.bw_total                      68312194                       # Total bandwidth to/from this memory (bytes/s)
 system.cpu.workload.num_syscalls                  444                       # Number of system calls
-system.cpu.numCycles                        140625890                       # number of cpu cycles simulated
+system.cpu.numCycles                        140195878                       # number of cpu cycles simulated
 system.cpu.numWorkItemsStarted                      0                       # number of work items this cpu started
 system.cpu.numWorkItemsCompleted                    0                       # number of work items this cpu completed
-system.cpu.BPredUnit.lookups                 37833804                       # Number of BP lookups
-system.cpu.BPredUnit.condPredicted           37833804                       # Number of conditional branches predicted
-system.cpu.BPredUnit.condIncorrect            1322933                       # Number of conditional branches incorrect
-system.cpu.BPredUnit.BTBLookups              33591925                       # Number of BTB lookups
-system.cpu.BPredUnit.BTBHits                 33081589                       # Number of BTB hits
+system.cpu.BPredUnit.lookups                 37928407                       # Number of BP lookups
+system.cpu.BPredUnit.condPredicted           37928407                       # Number of conditional branches predicted
+system.cpu.BPredUnit.condIncorrect            1334678                       # Number of conditional branches incorrect
+system.cpu.BPredUnit.BTBLookups              33548417                       # Number of BTB lookups
+system.cpu.BPredUnit.BTBHits                 33040245                       # Number of BTB hits
 system.cpu.BPredUnit.BTBCorrect                     0                       # Number of correct BTB predictions (this stat may not work properly.
 system.cpu.BPredUnit.usedRAS                        0                       # Number of times the RAS was used to get a target.
 system.cpu.BPredUnit.RASInCorrect                   0                       # Number of incorrect RAS predictions.
-system.cpu.fetch.icacheStallCycles           29087381                       # Number of cycles fetch is stalled on an Icache miss
-system.cpu.fetch.Insts                      203627812                       # Number of instructions fetch has processed
-system.cpu.fetch.Branches                    37833804                       # Number of branches that fetch encountered
-system.cpu.fetch.predictedBranches           33081589                       # Number of branches that fetch has predicted taken
-system.cpu.fetch.Cycles                      63297987                       # Number of cycles fetch has run and was not squashing or blocked
-system.cpu.fetch.SquashCycles                10276298                       # Number of cycles fetch has spent squashing
-system.cpu.fetch.BlockedCycles               38195582                       # Number of cycles fetch has spent blocked
-system.cpu.fetch.MiscStallCycles                   21                       # Number of cycles fetch has spent waiting on interrupts, or bad addresses, or out of MSHRs
-system.cpu.fetch.PendingTrapStallCycles            95                       # Number of stall cycles due to pending traps
-system.cpu.fetch.CacheLines                  28266291                       # Number of cache lines fetched
-system.cpu.fetch.IcacheSquashes                204981                       # Number of outstanding Icache misses that were squashed
-system.cpu.fetch.rateDist::samples          139497150                       # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::mean              2.574262                       # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::stdev             3.291399                       # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.icacheStallCycles           29060209                       # Number of cycles fetch is stalled on an Icache miss
+system.cpu.fetch.Insts                      203598338                       # Number of instructions fetch has processed
+system.cpu.fetch.Branches                    37928407                       # Number of branches that fetch encountered
+system.cpu.fetch.predictedBranches           33040245                       # Number of branches that fetch has predicted taken
+system.cpu.fetch.Cycles                      63274026                       # Number of cycles fetch has run and was not squashing or blocked
+system.cpu.fetch.SquashCycles                10249926                       # Number of cycles fetch has spent squashing
+system.cpu.fetch.BlockedCycles               38189577                       # Number of cycles fetch has spent blocked
+system.cpu.fetch.MiscStallCycles                   18                       # Number of cycles fetch has spent waiting on interrupts, or bad addresses, or out of MSHRs
+system.cpu.fetch.PendingTrapStallCycles            77                       # Number of stall cycles due to pending traps
+system.cpu.fetch.CacheLines                  28245503                       # Number of cache lines fetched
+system.cpu.fetch.IcacheSquashes                214193                       # Number of outstanding Icache misses that were squashed
+system.cpu.fetch.rateDist::samples          139407654                       # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.rateDist::mean              2.577879                       # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.rateDist::stdev             3.292775                       # Number of instructions fetched each cycle (Total)
 system.cpu.fetch.rateDist::underflows               0      0.00%      0.00% # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::0                 78673130     56.40%     56.40% # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::1                  3606277      2.59%     58.98% # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::2                  2810090      2.01%     61.00% # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::3                  4532102      3.25%     64.25% # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::4                  6824412      4.89%     69.14% # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::5                  5279008      3.78%     72.92% # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::6                  7637539      5.48%     78.40% # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::7                  4315201      3.09%     81.49% # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::8                 25819391     18.51%    100.00% # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.rateDist::0                 78584615     56.37%     56.37% # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.rateDist::1                  3556242      2.55%     58.92% # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.rateDist::2                  2802198      2.01%     60.93% # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.rateDist::3                  4529245      3.25%     64.18% # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.rateDist::4                  6913485      4.96%     69.14% # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.rateDist::5                  5169478      3.71%     72.85% # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.rateDist::6                  7697084      5.52%     78.37% # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.rateDist::7                  4298531      3.08%     81.45% # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.rateDist::8                 25856776     18.55%    100.00% # Number of instructions fetched each cycle (Total)
 system.cpu.fetch.rateDist::overflows                0      0.00%    100.00% # Number of instructions fetched each cycle (Total)
 system.cpu.fetch.rateDist::min_value                0                       # Number of instructions fetched each cycle (Total)
 system.cpu.fetch.rateDist::max_value                8                       # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::total            139497150                       # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.branchRate                  0.269039                       # Number of branch fetches per cycle
-system.cpu.fetch.rate                        1.448011                       # Number of inst fetches per cycle
-system.cpu.decode.IdleCycles                 41917744                       # Number of cycles decode is idle
-system.cpu.decode.BlockedCycles              28560060                       # Number of cycles decode is blocked
-system.cpu.decode.RunCycles                  52643719                       # Number of cycles decode is running
-system.cpu.decode.UnblockCycles               7459543                       # Number of cycles decode is unblocking
-system.cpu.decode.SquashCycles                8916084                       # Number of cycles decode is squashing
-system.cpu.decode.DecodedInsts              354657218                       # Number of instructions handled by decode
-system.cpu.rename.SquashCycles                8916084                       # Number of cycles rename is squashing
-system.cpu.rename.IdleCycles                 48823983                       # Number of cycles rename is idle
-system.cpu.rename.BlockCycles                 4469241                       # Number of cycles rename is blocking
-system.cpu.rename.serializeStallCycles           6888                       # count of cycles rename stalled for serializing inst
-system.cpu.rename.RunCycles                  53004642                       # Number of cycles rename is running
-system.cpu.rename.UnblockCycles              24276312                       # Number of cycles rename is unblocking
-system.cpu.rename.RenamedInsts              350176569                       # Number of instructions processed by rename
-system.cpu.rename.ROBFullEvents                    14                       # Number of times rename has blocked due to ROB full
-system.cpu.rename.IQFullEvents                 101342                       # Number of times rename has blocked due to IQ full
-system.cpu.rename.LSQFullEvents              20289844                       # Number of times rename has blocked due to LSQ full
-system.cpu.rename.RenamedOperands           314446851                       # Number of destination operands rename has renamed
-system.cpu.rename.RenameLookups             861231533                       # Number of register rename lookups that rename has made
-system.cpu.rename.int_rename_lookups        861227904                       # Number of integer rename lookups
-system.cpu.rename.fp_rename_lookups              3629                       # Number of floating rename lookups
+system.cpu.fetch.rateDist::total            139407654                       # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.branchRate                  0.270539                       # Number of branch fetches per cycle
+system.cpu.fetch.rate                        1.452242                       # Number of inst fetches per cycle
+system.cpu.decode.IdleCycles                 41988791                       # Number of cycles decode is idle
+system.cpu.decode.BlockedCycles              28417024                       # Number of cycles decode is blocked
+system.cpu.decode.RunCycles                  52030953                       # Number of cycles decode is running
+system.cpu.decode.UnblockCycles               8087139                       # Number of cycles decode is unblocking
+system.cpu.decode.SquashCycles                8883747                       # Number of cycles decode is squashing
+system.cpu.decode.DecodedInsts              355040007                       # Number of instructions handled by decode
+system.cpu.rename.SquashCycles                8883747                       # Number of cycles rename is squashing
+system.cpu.rename.IdleCycles                 48483810                       # Number of cycles rename is idle
+system.cpu.rename.BlockCycles                 4810408                       # Number of cycles rename is blocking
+system.cpu.rename.serializeStallCycles           9079                       # count of cycles rename stalled for serializing inst
+system.cpu.rename.RunCycles                  52929871                       # Number of cycles rename is running
+system.cpu.rename.UnblockCycles              24290739                       # Number of cycles rename is unblocking
+system.cpu.rename.RenamedInsts              350051728                       # Number of instructions processed by rename
+system.cpu.rename.ROBFullEvents                    20                       # Number of times rename has blocked due to ROB full
+system.cpu.rename.IQFullEvents                 103496                       # Number of times rename has blocked due to IQ full
+system.cpu.rename.LSQFullEvents              20366187                       # Number of times rename has blocked due to LSQ full
+system.cpu.rename.RenamedOperands           314282471                       # Number of destination operands rename has renamed
+system.cpu.rename.RenameLookups             860902327                       # Number of register rename lookups that rename has made
+system.cpu.rename.int_rename_lookups        860897388                       # Number of integer rename lookups
+system.cpu.rename.fp_rename_lookups              4939                       # Number of floating rename lookups
 system.cpu.rename.CommittedMaps             248344192                       # Number of HB maps that are committed
-system.cpu.rename.UndoneMaps                 66102659                       # Number of HB maps that are undone due to squashing
-system.cpu.rename.serializingInsts                479                       # count of serializing insts renamed
+system.cpu.rename.UndoneMaps                 65938279                       # Number of HB maps that are undone due to squashing
+system.cpu.rename.serializingInsts                478                       # count of serializing insts renamed
 system.cpu.rename.tempSerializingInsts            472                       # count of temporary serializing insts renamed
-system.cpu.rename.skidInsts                  56104077                       # count of insts added to the skid buffer
-system.cpu.memDep0.insertedLoads            112666461                       # Number of loads inserted to the mem dependence unit.
-system.cpu.memDep0.insertedStores            37647255                       # Number of stores inserted to the mem dependence unit.
-system.cpu.memDep0.conflictingLoads          48253520                       # Number of conflicting loads.
-system.cpu.memDep0.conflictingStores          8188094                       # Number of conflicting stores.
-system.cpu.iq.iqInstsAdded                  343455788                       # Number of instructions added to the IQ (excludes non-spec)
-system.cpu.iq.iqNonSpecInstsAdded                2295                       # Number of non-speculative instructions added to the IQ
-system.cpu.iq.iqInstsIssued                 316242386                       # Number of instructions issued
-system.cpu.iq.iqSquashedInstsIssued             89834                       # Number of squashed instructions issued
-system.cpu.iq.iqSquashedInstsExamined        65098177                       # Number of squashed instructions iterated over during squash; mainly for profiling
-system.cpu.iq.iqSquashedOperandsExamined     92870721                       # Number of squashed operands that are examined and possibly removed from graph
-system.cpu.iq.iqSquashedNonSpecRemoved           1849                       # Number of squashed non-spec instructions that were removed
-system.cpu.iq.issued_per_cycle::samples     139497150                       # Number of insts issued each cycle
-system.cpu.iq.issued_per_cycle::mean         2.267017                       # Number of insts issued each cycle
-system.cpu.iq.issued_per_cycle::stdev        1.750973                       # Number of insts issued each cycle
+system.cpu.rename.skidInsts                  57634584                       # count of insts added to the skid buffer
+system.cpu.memDep0.insertedLoads            112617334                       # Number of loads inserted to the mem dependence unit.
+system.cpu.memDep0.insertedStores            37601195                       # Number of stores inserted to the mem dependence unit.
+system.cpu.memDep0.conflictingLoads          47838969                       # Number of conflicting loads.
+system.cpu.memDep0.conflictingStores          8379867                       # Number of conflicting stores.
+system.cpu.iq.iqInstsAdded                  343415839                       # Number of instructions added to the IQ (excludes non-spec)
+system.cpu.iq.iqNonSpecInstsAdded                2328                       # Number of non-speculative instructions added to the IQ
+system.cpu.iq.iqInstsIssued                 316096096                       # Number of instructions issued
+system.cpu.iq.iqSquashedInstsIssued             78808                       # Number of squashed instructions issued
+system.cpu.iq.iqSquashedInstsExamined        65029362                       # Number of squashed instructions iterated over during squash; mainly for profiling
+system.cpu.iq.iqSquashedOperandsExamined     92942153                       # Number of squashed operands that are examined and possibly removed from graph
+system.cpu.iq.iqSquashedNonSpecRemoved           1882                       # Number of squashed non-spec instructions that were removed
+system.cpu.iq.issued_per_cycle::samples     139407654                       # Number of insts issued each cycle
+system.cpu.iq.issued_per_cycle::mean         2.267423                       # Number of insts issued each cycle
+system.cpu.iq.issued_per_cycle::stdev        1.745481                       # Number of insts issued each cycle
 system.cpu.iq.issued_per_cycle::underflows            0      0.00%      0.00% # Number of insts issued each cycle
-system.cpu.iq.issued_per_cycle::0            31795649     22.79%     22.79% # Number of insts issued each cycle
-system.cpu.iq.issued_per_cycle::1            18418675     13.20%     36.00% # Number of insts issued each cycle
-system.cpu.iq.issued_per_cycle::2            25717845     18.44%     54.43% # Number of insts issued each cycle
-system.cpu.iq.issued_per_cycle::3            29872112     21.41%     75.85% # Number of insts issued each cycle
-system.cpu.iq.issued_per_cycle::4            18507796     13.27%     89.11% # Number of insts issued each cycle
-system.cpu.iq.issued_per_cycle::5            10200782      7.31%     96.43% # Number of insts issued each cycle
-system.cpu.iq.issued_per_cycle::6             3199934      2.29%     98.72% # Number of insts issued each cycle
-system.cpu.iq.issued_per_cycle::7             1737869      1.25%     99.97% # Number of insts issued each cycle
-system.cpu.iq.issued_per_cycle::8               46488      0.03%    100.00% # Number of insts issued each cycle
+system.cpu.iq.issued_per_cycle::0            32098361     23.02%     23.02% # Number of insts issued each cycle
+system.cpu.iq.issued_per_cycle::1            17868067     12.82%     35.84% # Number of insts issued each cycle
+system.cpu.iq.issued_per_cycle::2            24417482     17.52%     53.36% # Number of insts issued each cycle
+system.cpu.iq.issued_per_cycle::3            32093883     23.02%     76.38% # Number of insts issued each cycle
+system.cpu.iq.issued_per_cycle::4            18421218     13.21%     89.59% # Number of insts issued each cycle
+system.cpu.iq.issued_per_cycle::5             9527374      6.83%     96.43% # Number of insts issued each cycle
+system.cpu.iq.issued_per_cycle::6             3128162      2.24%     98.67% # Number of insts issued each cycle
+system.cpu.iq.issued_per_cycle::7             1804154      1.29%     99.96% # Number of insts issued each cycle
+system.cpu.iq.issued_per_cycle::8               48953      0.04%    100.00% # Number of insts issued each cycle
 system.cpu.iq.issued_per_cycle::overflows            0      0.00%    100.00% # Number of insts issued each cycle
 system.cpu.iq.issued_per_cycle::min_value            0                       # Number of insts issued each cycle
 system.cpu.iq.issued_per_cycle::max_value            8                       # Number of insts issued each cycle
-system.cpu.iq.issued_per_cycle::total       139497150                       # Number of insts issued each cycle
+system.cpu.iq.issued_per_cycle::total       139407654                       # Number of insts issued each cycle
 system.cpu.iq.fu_full::No_OpClass                   0      0.00%      0.00% # attempts to use FU when none available
-system.cpu.iq.fu_full::IntAlu                   25785      1.36%      1.36% # attempts to use FU when none available
-system.cpu.iq.fu_full::IntMult                      0      0.00%      1.36% # attempts to use FU when none available
-system.cpu.iq.fu_full::IntDiv                       0      0.00%      1.36% # attempts to use FU when none available
-system.cpu.iq.fu_full::FloatAdd                     0      0.00%      1.36% # attempts to use FU when none available
-system.cpu.iq.fu_full::FloatCmp                     0      0.00%      1.36% # attempts to use FU when none available
-system.cpu.iq.fu_full::FloatCvt                     0      0.00%      1.36% # attempts to use FU when none available
-system.cpu.iq.fu_full::FloatMult                    0      0.00%      1.36% # attempts to use FU when none available
-system.cpu.iq.fu_full::FloatDiv                     0      0.00%      1.36% # attempts to use FU when none available
-system.cpu.iq.fu_full::FloatSqrt                    0      0.00%      1.36% # attempts to use FU when none available
-system.cpu.iq.fu_full::SimdAdd                      0      0.00%      1.36% # attempts to use FU when none available
-system.cpu.iq.fu_full::SimdAddAcc                   0      0.00%      1.36% # attempts to use FU when none available
-system.cpu.iq.fu_full::SimdAlu                      0      0.00%      1.36% # attempts to use FU when none available
-system.cpu.iq.fu_full::SimdCmp                      0      0.00%      1.36% # attempts to use FU when none available
-system.cpu.iq.fu_full::SimdCvt                      0      0.00%      1.36% # attempts to use FU when none available
-system.cpu.iq.fu_full::SimdMisc                     0      0.00%      1.36% # attempts to use FU when none available
-system.cpu.iq.fu_full::SimdMult                     0      0.00%      1.36% # attempts to use FU when none available
-system.cpu.iq.fu_full::SimdMultAcc                  0      0.00%      1.36% # attempts to use FU when none available
-system.cpu.iq.fu_full::SimdShift                    0      0.00%      1.36% # attempts to use FU when none available
-system.cpu.iq.fu_full::SimdShiftAcc                 0      0.00%      1.36% # attempts to use FU when none available
-system.cpu.iq.fu_full::SimdSqrt                     0      0.00%      1.36% # attempts to use FU when none available
-system.cpu.iq.fu_full::SimdFloatAdd                 0      0.00%      1.36% # attempts to use FU when none available
-system.cpu.iq.fu_full::SimdFloatAlu                 0      0.00%      1.36% # attempts to use FU when none available
-system.cpu.iq.fu_full::SimdFloatCmp                 0      0.00%      1.36% # attempts to use FU when none available
-system.cpu.iq.fu_full::SimdFloatCvt                 0      0.00%      1.36% # attempts to use FU when none available
-system.cpu.iq.fu_full::SimdFloatDiv                 0      0.00%      1.36% # attempts to use FU when none available
-system.cpu.iq.fu_full::SimdFloatMisc                0      0.00%      1.36% # attempts to use FU when none available
-system.cpu.iq.fu_full::SimdFloatMult                0      0.00%      1.36% # attempts to use FU when none available
-system.cpu.iq.fu_full::SimdFloatMultAcc             0      0.00%      1.36% # attempts to use FU when none available
-system.cpu.iq.fu_full::SimdFloatSqrt                0      0.00%      1.36% # attempts to use FU when none available
-system.cpu.iq.fu_full::MemRead                1795857     94.47%     95.83% # attempts to use FU when none available
-system.cpu.iq.fu_full::MemWrite                 79349      4.17%    100.00% # attempts to use FU when none available
+system.cpu.iq.fu_full::IntAlu                   25731      1.31%      1.31% # attempts to use FU when none available
+system.cpu.iq.fu_full::IntMult                      0      0.00%      1.31% # attempts to use FU when none available
+system.cpu.iq.fu_full::IntDiv                       0      0.00%      1.31% # attempts to use FU when none available
+system.cpu.iq.fu_full::FloatAdd                     0      0.00%      1.31% # attempts to use FU when none available
+system.cpu.iq.fu_full::FloatCmp                     0      0.00%      1.31% # attempts to use FU when none available
+system.cpu.iq.fu_full::FloatCvt                     0      0.00%      1.31% # attempts to use FU when none available
+system.cpu.iq.fu_full::FloatMult                    0      0.00%      1.31% # attempts to use FU when none available
+system.cpu.iq.fu_full::FloatDiv                     0      0.00%      1.31% # attempts to use FU when none available
+system.cpu.iq.fu_full::FloatSqrt                    0      0.00%      1.31% # attempts to use FU when none available
+system.cpu.iq.fu_full::SimdAdd                      0      0.00%      1.31% # attempts to use FU when none available
+system.cpu.iq.fu_full::SimdAddAcc                   0      0.00%      1.31% # attempts to use FU when none available
+system.cpu.iq.fu_full::SimdAlu                      0      0.00%      1.31% # attempts to use FU when none available
+system.cpu.iq.fu_full::SimdCmp                      0      0.00%      1.31% # attempts to use FU when none available
+system.cpu.iq.fu_full::SimdCvt                      0      0.00%      1.31% # attempts to use FU when none available
+system.cpu.iq.fu_full::SimdMisc                     0      0.00%      1.31% # attempts to use FU when none available
+system.cpu.iq.fu_full::SimdMult                     0      0.00%      1.31% # attempts to use FU when none available
+system.cpu.iq.fu_full::SimdMultAcc                  0      0.00%      1.31% # attempts to use FU when none available
+system.cpu.iq.fu_full::SimdShift                    0      0.00%      1.31% # attempts to use FU when none available
+system.cpu.iq.fu_full::SimdShiftAcc                 0      0.00%      1.31% # attempts to use FU when none available
+system.cpu.iq.fu_full::SimdSqrt                     0      0.00%      1.31% # attempts to use FU when none available
+system.cpu.iq.fu_full::SimdFloatAdd                 0      0.00%      1.31% # attempts to use FU when none available
+system.cpu.iq.fu_full::SimdFloatAlu                 0      0.00%      1.31% # attempts to use FU when none available
+system.cpu.iq.fu_full::SimdFloatCmp                 0      0.00%      1.31% # attempts to use FU when none available
+system.cpu.iq.fu_full::SimdFloatCvt                 0      0.00%      1.31% # attempts to use FU when none available
+system.cpu.iq.fu_full::SimdFloatDiv                 0      0.00%      1.31% # attempts to use FU when none available
+system.cpu.iq.fu_full::SimdFloatMisc                0      0.00%      1.31% # attempts to use FU when none available
+system.cpu.iq.fu_full::SimdFloatMult                0      0.00%      1.31% # attempts to use FU when none available
+system.cpu.iq.fu_full::SimdFloatMultAcc             0      0.00%      1.31% # attempts to use FU when none available
+system.cpu.iq.fu_full::SimdFloatSqrt                0      0.00%      1.31% # attempts to use FU when none available
+system.cpu.iq.fu_full::MemRead                1863505     95.00%     96.31% # attempts to use FU when none available
+system.cpu.iq.fu_full::MemWrite                 72393      3.69%    100.00% # attempts to use FU when none available
 system.cpu.iq.fu_full::IprAccess                    0      0.00%    100.00% # attempts to use FU when none available
 system.cpu.iq.fu_full::InstPrefetch                 0      0.00%    100.00% # attempts to use FU when none available
 system.cpu.iq.FU_type_0::No_OpClass             16711      0.01%      0.01% # Type of FU issued
-system.cpu.iq.FU_type_0::IntAlu             180262574     57.00%     57.01% # Type of FU issued
+system.cpu.iq.FU_type_0::IntAlu             180196286     57.01%     57.01% # Type of FU issued
 system.cpu.iq.FU_type_0::IntMult                    0      0.00%     57.01% # Type of FU issued
 system.cpu.iq.FU_type_0::IntDiv                     0      0.00%     57.01% # Type of FU issued
-system.cpu.iq.FU_type_0::FloatAdd                 195      0.00%     57.01% # Type of FU issued
+system.cpu.iq.FU_type_0::FloatAdd                 342      0.00%     57.01% # Type of FU issued
 system.cpu.iq.FU_type_0::FloatCmp                   0      0.00%     57.01% # Type of FU issued
 system.cpu.iq.FU_type_0::FloatCvt                   0      0.00%     57.01% # Type of FU issued
 system.cpu.iq.FU_type_0::FloatMult                  0      0.00%     57.01% # Type of FU issued
@@ -178,85 +178,85 @@
 system.cpu.iq.FU_type_0::SimdFloatMult              0      0.00%     57.01% # Type of FU issued
 system.cpu.iq.FU_type_0::SimdFloatMultAcc            0      0.00%     57.01% # Type of FU issued
 system.cpu.iq.FU_type_0::SimdFloatSqrt              0      0.00%     57.01% # Type of FU issued
-system.cpu.iq.FU_type_0::MemRead            101451147     32.08%     89.09% # Type of FU issued
-system.cpu.iq.FU_type_0::MemWrite            34511759     10.91%    100.00% # Type of FU issued
+system.cpu.iq.FU_type_0::MemRead            101438567     32.09%     89.10% # Type of FU issued
+system.cpu.iq.FU_type_0::MemWrite            34444190     10.90%    100.00% # Type of FU issued
 system.cpu.iq.FU_type_0::IprAccess                  0      0.00%    100.00% # Type of FU issued
 system.cpu.iq.FU_type_0::InstPrefetch               0      0.00%    100.00% # Type of FU issued
-system.cpu.iq.FU_type_0::total              316242386                       # Type of FU issued
-system.cpu.iq.rate                           2.248821                       # Inst issue rate
-system.cpu.iq.fu_busy_cnt                     1900991                       # FU busy when requested
-system.cpu.iq.fu_busy_rate                   0.006011                       # FU busy rate (busy events/executed inst)
-system.cpu.iq.int_inst_queue_reads          773971833                       # Number of integer instruction queue reads
-system.cpu.iq.int_inst_queue_writes         408587092                       # Number of integer instruction queue writes
-system.cpu.iq.int_inst_queue_wakeup_accesses    312537049                       # Number of integer instruction queue wakeup accesses
-system.cpu.iq.fp_inst_queue_reads                 914                       # Number of floating instruction queue reads
-system.cpu.iq.fp_inst_queue_writes               2332                       # Number of floating instruction queue writes
-system.cpu.iq.fp_inst_queue_wakeup_accesses          382                       # Number of floating instruction queue wakeup accesses
-system.cpu.iq.int_alu_accesses              318126211                       # Number of integer alu accesses
-system.cpu.iq.fp_alu_accesses                     455                       # Number of floating point alu accesses
-system.cpu.iew.lsq.thread0.forwLoads         45906656                       # Number of loads that had data forwarded from stores
+system.cpu.iq.FU_type_0::total              316096096                       # Type of FU issued
+system.cpu.iq.rate                           2.254675                       # Inst issue rate
+system.cpu.iq.fu_busy_cnt                     1961629                       # FU busy when requested
+system.cpu.iq.fu_busy_rate                   0.006206                       # FU busy rate (busy events/executed inst)
+system.cpu.iq.int_inst_queue_reads          773638738                       # Number of integer instruction queue reads
+system.cpu.iq.int_inst_queue_writes         408477370                       # Number of integer instruction queue writes
+system.cpu.iq.int_inst_queue_wakeup_accesses    312370165                       # Number of integer instruction queue wakeup accesses
+system.cpu.iq.fp_inst_queue_reads                1545                       # Number of floating instruction queue reads
+system.cpu.iq.fp_inst_queue_writes               3169                       # Number of floating instruction queue writes
+system.cpu.iq.fp_inst_queue_wakeup_accesses          656                       # Number of floating instruction queue wakeup accesses
+system.cpu.iq.int_alu_accesses              318040246                       # Number of integer alu accesses
+system.cpu.iq.fp_alu_accesses                     768                       # Number of floating point alu accesses
+system.cpu.iew.lsq.thread0.forwLoads         52318776                       # Number of loads that had data forwarded from stores
 system.cpu.iew.lsq.thread0.invAddrLoads             0                       # Number of loads ignored due to an invalid address
-system.cpu.iew.lsq.thread0.squashedLoads     21887073                       # Number of loads squashed
-system.cpu.iew.lsq.thread0.ignoredResponses       122159                       # Number of memory responses ignored because the instruction is squashed
-system.cpu.iew.lsq.thread0.memOrderViolation        33758                       # Number of memory ordering violations
-system.cpu.iew.lsq.thread0.squashedStores      6207504                       # Number of stores squashed
+system.cpu.iew.lsq.thread0.squashedLoads     21837946                       # Number of loads squashed
+system.cpu.iew.lsq.thread0.ignoredResponses       139826                       # Number of memory responses ignored because the instruction is squashed
+system.cpu.iew.lsq.thread0.memOrderViolation        33737                       # Number of memory ordering violations
+system.cpu.iew.lsq.thread0.squashedStores      6161444                       # Number of stores squashed
 system.cpu.iew.lsq.thread0.invAddrSwpfs             0                       # Number of software prefetches ignored due to an invalid address
 system.cpu.iew.lsq.thread0.blockedLoads             0                       # Number of blocked loads due to partial load-store forwarding
-system.cpu.iew.lsq.thread0.rescheduledLoads         2763                       # Number of loads that were rescheduled
-system.cpu.iew.lsq.thread0.cacheBlocked         15488                       # Number of times an access to memory failed due to the cache being blocked
+system.cpu.iew.lsq.thread0.rescheduledLoads         3258                       # Number of loads that were rescheduled
+system.cpu.iew.lsq.thread0.cacheBlocked          3821                       # Number of times an access to memory failed due to the cache being blocked
 system.cpu.iew.iewIdleCycles                        0                       # Number of cycles IEW is idle
-system.cpu.iew.iewSquashCycles                8916084                       # Number of cycles IEW is squashing
-system.cpu.iew.iewBlockCycles                  901068                       # Number of cycles IEW is blocking
-system.cpu.iew.iewUnblockCycles                 88602                       # Number of cycles IEW is unblocking
-system.cpu.iew.iewDispatchedInsts           343458083                       # Number of instructions dispatched to IQ
-system.cpu.iew.iewDispSquashedInsts             26305                       # Number of squashed instructions skipped by dispatch
-system.cpu.iew.iewDispLoadInsts             112666461                       # Number of dispatched load instructions
-system.cpu.iew.iewDispStoreInsts             37647255                       # Number of dispatched store instructions
+system.cpu.iew.iewSquashCycles                8883747                       # Number of cycles IEW is squashing
+system.cpu.iew.iewBlockCycles                  984872                       # Number of cycles IEW is blocking
+system.cpu.iew.iewUnblockCycles                 88741                       # Number of cycles IEW is unblocking
+system.cpu.iew.iewDispatchedInsts           343418167                       # Number of instructions dispatched to IQ
+system.cpu.iew.iewDispSquashedInsts             39651                       # Number of squashed instructions skipped by dispatch
+system.cpu.iew.iewDispLoadInsts             112617334                       # Number of dispatched load instructions
+system.cpu.iew.iewDispStoreInsts             37601195                       # Number of dispatched store instructions
 system.cpu.iew.iewDispNonSpecInsts                465                       # Number of dispatched non-speculative instructions
-system.cpu.iew.iewIQFullEvents                   1597                       # Number of times the IQ has become full, causing a stall
-system.cpu.iew.iewLSQFullEvents                 48733                       # Number of times the LSQ has become full, causing a stall
-system.cpu.iew.memOrderViolationEvents          33758                       # Number of memory order violations
-system.cpu.iew.predictedTakenIncorrect        1219939                       # Number of branches that were predicted taken incorrectly
-system.cpu.iew.predictedNotTakenIncorrect       230098                       # Number of branches that were predicted not taken incorrectly
-system.cpu.iew.branchMispredicts              1450037                       # Number of branch mispredicts detected at execute
-system.cpu.iew.iewExecutedInsts             314144155                       # Number of executed instructions
-system.cpu.iew.iewExecLoadInsts             100864248                       # Number of load instructions executed
-system.cpu.iew.iewExecSquashedInsts           2098231                       # Number of squashed instructions skipped in execute
+system.cpu.iew.iewIQFullEvents                   1341                       # Number of times the IQ has become full, causing a stall
+system.cpu.iew.iewLSQFullEvents                 42673                       # Number of times the LSQ has become full, causing a stall
+system.cpu.iew.memOrderViolationEvents          33737                       # Number of memory order violations
+system.cpu.iew.predictedTakenIncorrect        1237180                       # Number of branches that were predicted taken incorrectly
+system.cpu.iew.predictedNotTakenIncorrect       215729                       # Number of branches that were predicted not taken incorrectly
+system.cpu.iew.branchMispredicts              1452909                       # Number of branch mispredicts detected at execute
+system.cpu.iew.iewExecutedInsts             313907375                       # Number of executed instructions
+system.cpu.iew.iewExecLoadInsts             100815222                       # Number of load instructions executed
+system.cpu.iew.iewExecSquashedInsts           2188721                       # Number of squashed instructions skipped in execute
 system.cpu.iew.exec_swp                             0                       # number of swp insts executed
 system.cpu.iew.exec_nop                             0                       # number of nop insts executed
-system.cpu.iew.exec_refs                    134973322                       # number of memory reference insts executed
-system.cpu.iew.exec_branches                 31810521                       # Number of branches executed
-system.cpu.iew.exec_stores                   34109074                       # Number of stores executed
-system.cpu.iew.exec_rate                     2.233900                       # Inst execution rate
-system.cpu.iew.wb_sent                      313190495                       # cumulative count of insts sent to commit
-system.cpu.iew.wb_count                     312537431                       # cumulative count of insts written-back
-system.cpu.iew.wb_producers                 232392592                       # num instructions producing a value
-system.cpu.iew.wb_consumers                 318468890                       # num instructions consuming a value
+system.cpu.iew.exec_refs                    134855811                       # number of memory reference insts executed
+system.cpu.iew.exec_branches                 31730666                       # Number of branches executed
+system.cpu.iew.exec_stores                   34040589                       # Number of stores executed
+system.cpu.iew.exec_rate                     2.239063                       # Inst execution rate
+system.cpu.iew.wb_sent                      313087219                       # cumulative count of insts sent to commit
+system.cpu.iew.wb_count                     312370821                       # cumulative count of insts written-back
+system.cpu.iew.wb_producers                 231825034                       # num instructions producing a value
+system.cpu.iew.wb_consumers                 317282535                       # num instructions consuming a value
 system.cpu.iew.wb_penalized                         0                       # number of instrctions required to write to 'other' IQ
-system.cpu.iew.wb_rate                       2.222474                       # insts written-back per cycle
-system.cpu.iew.wb_fanout                     0.729718                       # average fanout of values written-back
+system.cpu.iew.wb_rate                       2.228103                       # insts written-back per cycle
+system.cpu.iew.wb_fanout                     0.730658                       # average fanout of values written-back
 system.cpu.iew.wb_penalized_rate                    0                       # fraction of instructions written-back that wrote to 'other' IQ
 system.cpu.commit.commitCommittedInsts      278192519                       # The number of committed instructions
-system.cpu.commit.commitSquashedInsts        65270328                       # The number of squashed insts skipped by commit
+system.cpu.commit.commitSquashedInsts        65229233                       # The number of squashed insts skipped by commit
 system.cpu.commit.commitNonSpecStalls             446                       # The number of times commit has been forced to stall to communicate backwards
-system.cpu.commit.branchMispredicts           1322946                       # The number of times a branch was mispredicted
-system.cpu.commit.committed_per_cycle::samples    130581066                       # Number of insts commited each cycle
-system.cpu.commit.committed_per_cycle::mean     2.130420                       # Number of insts commited each cycle
-system.cpu.commit.committed_per_cycle::stdev     2.663472                       # Number of insts commited each cycle
+system.cpu.commit.branchMispredicts           1334689                       # The number of times a branch was mispredicted
+system.cpu.commit.committed_per_cycle::samples    130523907                       # Number of insts commited each cycle
+system.cpu.commit.committed_per_cycle::mean     2.131353                       # Number of insts commited each cycle
+system.cpu.commit.committed_per_cycle::stdev     2.650695                       # Number of insts commited each cycle
 system.cpu.commit.committed_per_cycle::underflows            0      0.00%      0.00% # Number of insts commited each cycle
-system.cpu.commit.committed_per_cycle::0     50414718     38.61%     38.61% # Number of insts commited each cycle
-system.cpu.commit.committed_per_cycle::1     24339651     18.64%     57.25% # Number of insts commited each cycle
-system.cpu.commit.committed_per_cycle::2     16499074     12.64%     69.88% # Number of insts commited each cycle
-system.cpu.commit.committed_per_cycle::3     12376450      9.48%     79.36% # Number of insts commited each cycle
-system.cpu.commit.committed_per_cycle::4      3696747      2.83%     82.19% # Number of insts commited each cycle
-system.cpu.commit.committed_per_cycle::5      3466084      2.65%     84.85% # Number of insts commited each cycle
-system.cpu.commit.committed_per_cycle::6      2761727      2.11%     86.96% # Number of insts commited each cycle
-system.cpu.commit.committed_per_cycle::7      1175320      0.90%     87.86% # Number of insts commited each cycle
-system.cpu.commit.committed_per_cycle::8     15851295     12.14%    100.00% # Number of insts commited each cycle
+system.cpu.commit.committed_per_cycle::0     49374885     37.83%     37.83% # Number of insts commited each cycle
+system.cpu.commit.committed_per_cycle::1     24990571     19.15%     56.97% # Number of insts commited each cycle
+system.cpu.commit.committed_per_cycle::2     17165469     13.15%     70.13% # Number of insts commited each cycle
+system.cpu.commit.committed_per_cycle::3     12454302      9.54%     79.67% # Number of insts commited each cycle
+system.cpu.commit.committed_per_cycle::4      3472302      2.66%     82.33% # Number of insts commited each cycle
+system.cpu.commit.committed_per_cycle::5      3453203      2.65%     84.97% # Number of insts commited each cycle
+system.cpu.commit.committed_per_cycle::6      2713996      2.08%     87.05% # Number of insts commited each cycle
+system.cpu.commit.committed_per_cycle::7      1124527      0.86%     87.91% # Number of insts commited each cycle
+system.cpu.commit.committed_per_cycle::8     15774652     12.09%    100.00% # Number of insts commited each cycle
 system.cpu.commit.committed_per_cycle::overflows            0      0.00%    100.00% # Number of insts commited each cycle
 system.cpu.commit.committed_per_cycle::min_value            0                       # Number of insts commited each cycle
 system.cpu.commit.committed_per_cycle::max_value            8                       # Number of insts commited each cycle
-system.cpu.commit.committed_per_cycle::total    130581066                       # Number of insts commited each cycle
+system.cpu.commit.committed_per_cycle::total    130523907                       # Number of insts commited each cycle
 system.cpu.commit.count                     278192519                       # Number of instructions committed
 system.cpu.commit.swp_count                         0                       # Number of s/w prefetches committed
 system.cpu.commit.refs                      122219139                       # Number of memory references committed
@@ -266,49 +266,49 @@
 system.cpu.commit.fp_insts                         40                       # Number of committed floating point instructions.
 system.cpu.commit.int_insts                 278186227                       # Number of committed integer instructions.
 system.cpu.commit.function_calls                    0                       # Number of function calls committed.
-system.cpu.commit.bw_lim_events              15851295                       # number cycles where commit BW limit reached
+system.cpu.commit.bw_lim_events              15774652                       # number cycles where commit BW limit reached
 system.cpu.commit.bw_limited                        0                       # number of insts not committed due to BW limits
-system.cpu.rob.rob_reads                    458192618                       # The number of ROB reads
-system.cpu.rob.rob_writes                   695856607                       # The number of ROB writes
-system.cpu.timesIdled                           33615                       # Number of times that the entire CPU went into an idle state and unscheduled itself
-system.cpu.idleCycles                         1128740                       # Total number of cycles that the CPU has spent unscheduled due to idling
+system.cpu.rob.rob_reads                    458171007                       # The number of ROB reads
+system.cpu.rob.rob_writes                   695745355                       # The number of ROB writes
+system.cpu.timesIdled                           23904                       # Number of times that the entire CPU went into an idle state and unscheduled itself
+system.cpu.idleCycles                          788224                       # Total number of cycles that the CPU has spent unscheduled due to idling
 system.cpu.committedInsts                   278192519                       # Number of Instructions Simulated
 system.cpu.committedInsts_total             278192519                       # Number of Instructions Simulated
-system.cpu.cpi                               0.505498                       # CPI: Cycles Per Instruction
-system.cpu.cpi_total                         0.505498                       # CPI: Total CPI of All Threads
-system.cpu.ipc                               1.978245                       # IPC: Instructions Per Cycle
-system.cpu.ipc_total                         1.978245                       # IPC: Total IPC of All Threads
-system.cpu.int_regfile_reads                554794614                       # number of integer regfile reads
-system.cpu.int_regfile_writes               279836675                       # number of integer regfile writes
-system.cpu.fp_regfile_reads                       437                       # number of floating regfile reads
-system.cpu.fp_regfile_writes                      335                       # number of floating regfile writes
-system.cpu.misc_regfile_reads               201195947                       # number of misc regfile reads
-system.cpu.icache.replacements                     68                       # number of replacements
-system.cpu.icache.tagsinuse                824.679926                       # Cycle average of tags in use
-system.cpu.icache.total_refs                 28264985                       # Total number of references to valid blocks.
-system.cpu.icache.sampled_refs                   1027                       # Sample count of references to valid blocks.
-system.cpu.icache.avg_refs               27521.893866                       # Average number of references to valid blocks.
+system.cpu.cpi                               0.503953                       # CPI: Cycles Per Instruction
+system.cpu.cpi_total                         0.503953                       # CPI: Total CPI of All Threads
+system.cpu.ipc                               1.984313                       # IPC: Instructions Per Cycle
+system.cpu.ipc_total                         1.984313                       # IPC: Total IPC of All Threads
+system.cpu.int_regfile_reads                554439426                       # number of integer regfile reads
+system.cpu.int_regfile_writes               279882097                       # number of integer regfile writes
+system.cpu.fp_regfile_reads                       791                       # number of floating regfile reads
+system.cpu.fp_regfile_writes                      562                       # number of floating regfile writes
+system.cpu.misc_regfile_reads               200975844                       # number of misc regfile reads
+system.cpu.icache.replacements                     62                       # number of replacements
+system.cpu.icache.tagsinuse                823.089414                       # Cycle average of tags in use
+system.cpu.icache.total_refs                 28244206                       # Total number of references to valid blocks.
+system.cpu.icache.sampled_refs                   1023                       # Sample count of references to valid blocks.
+system.cpu.icache.avg_refs               27609.194526                       # Average number of references to valid blocks.
 system.cpu.icache.warmup_cycle                      0                       # Cycle when the warmup percentage was hit.
-system.cpu.icache.occ_blocks::0            824.679926                       # Average occupied blocks per context
-system.cpu.icache.occ_percent::0             0.402676                       # Average percentage of cache occupancy
-system.cpu.icache.ReadReq_hits               28264985                       # number of ReadReq hits
-system.cpu.icache.demand_hits                28264985                       # number of demand (read+write) hits
-system.cpu.icache.overall_hits               28264985                       # number of overall hits
-system.cpu.icache.ReadReq_misses                 1306                       # number of ReadReq misses
-system.cpu.icache.demand_misses                  1306                       # number of demand (read+write) misses
-system.cpu.icache.overall_misses                 1306                       # number of overall misses
-system.cpu.icache.ReadReq_miss_latency       47073500                       # number of ReadReq miss cycles
-system.cpu.icache.demand_miss_latency        47073500                       # number of demand (read+write) miss cycles
-system.cpu.icache.overall_miss_latency       47073500                       # number of overall miss cycles
-system.cpu.icache.ReadReq_accesses           28266291                       # number of ReadReq accesses(hits+misses)
-system.cpu.icache.demand_accesses            28266291                       # number of demand (read+write) accesses
-system.cpu.icache.overall_accesses           28266291                       # number of overall (read+write) accesses
+system.cpu.icache.occ_blocks::0            823.089414                       # Average occupied blocks per context
+system.cpu.icache.occ_percent::0             0.401899                       # Average percentage of cache occupancy
+system.cpu.icache.ReadReq_hits               28244206                       # number of ReadReq hits
+system.cpu.icache.demand_hits                28244206                       # number of demand (read+write) hits
+system.cpu.icache.overall_hits               28244206                       # number of overall hits
+system.cpu.icache.ReadReq_misses                 1297                       # number of ReadReq misses
+system.cpu.icache.demand_misses                  1297                       # number of demand (read+write) misses
+system.cpu.icache.overall_misses                 1297                       # number of overall misses
+system.cpu.icache.ReadReq_miss_latency       46884000                       # number of ReadReq miss cycles
+system.cpu.icache.demand_miss_latency        46884000                       # number of demand (read+write) miss cycles
+system.cpu.icache.overall_miss_latency       46884000                       # number of overall miss cycles
+system.cpu.icache.ReadReq_accesses           28245503                       # number of ReadReq accesses(hits+misses)
+system.cpu.icache.demand_accesses            28245503                       # number of demand (read+write) accesses
+system.cpu.icache.overall_accesses           28245503                       # number of overall (read+write) accesses
 system.cpu.icache.ReadReq_miss_rate          0.000046                       # miss rate for ReadReq accesses
 system.cpu.icache.demand_miss_rate           0.000046                       # miss rate for demand accesses
 system.cpu.icache.overall_miss_rate          0.000046                       # miss rate for overall accesses
-system.cpu.icache.ReadReq_avg_miss_latency 36044.027565                       # average ReadReq miss latency
-system.cpu.icache.demand_avg_miss_latency 36044.027565                       # average overall miss latency
-system.cpu.icache.overall_avg_miss_latency 36044.027565                       # average overall miss latency
+system.cpu.icache.ReadReq_avg_miss_latency 36148.033924                       # average ReadReq miss latency
+system.cpu.icache.demand_avg_miss_latency 36148.033924                       # average overall miss latency
+system.cpu.icache.overall_avg_miss_latency 36148.033924                       # average overall miss latency
 system.cpu.icache.blocked_cycles::no_mshrs            0                       # number of cycles access was blocked
 system.cpu.icache.blocked_cycles::no_targets            0                       # number of cycles access was blocked
 system.cpu.icache.blocked::no_mshrs                 0                       # number of cycles access was blocked
@@ -318,166 +318,166 @@
 system.cpu.icache.fast_writes                       0                       # number of fast writes performed
 system.cpu.icache.cache_copies                      0                       # number of cache copies performed
 system.cpu.icache.writebacks                        0                       # number of writebacks
-system.cpu.icache.ReadReq_mshr_hits               278                       # number of ReadReq MSHR hits
-system.cpu.icache.demand_mshr_hits                278                       # number of demand (read+write) MSHR hits
-system.cpu.icache.overall_mshr_hits               278                       # number of overall MSHR hits
-system.cpu.icache.ReadReq_mshr_misses            1028                       # number of ReadReq MSHR misses
-system.cpu.icache.demand_mshr_misses             1028                       # number of demand (read+write) MSHR misses
-system.cpu.icache.overall_mshr_misses            1028                       # number of overall MSHR misses
+system.cpu.icache.ReadReq_mshr_hits               273                       # number of ReadReq MSHR hits
+system.cpu.icache.demand_mshr_hits                273                       # number of demand (read+write) MSHR hits
+system.cpu.icache.overall_mshr_hits               273                       # number of overall MSHR hits
+system.cpu.icache.ReadReq_mshr_misses            1024                       # number of ReadReq MSHR misses
+system.cpu.icache.demand_mshr_misses             1024                       # number of demand (read+write) MSHR misses
+system.cpu.icache.overall_mshr_misses            1024                       # number of overall MSHR misses
 system.cpu.icache.overall_mshr_uncacheable_misses            0                       # number of overall MSHR uncacheable misses
-system.cpu.icache.ReadReq_mshr_miss_latency     36154500                       # number of ReadReq MSHR miss cycles
-system.cpu.icache.demand_mshr_miss_latency     36154500                       # number of demand (read+write) MSHR miss cycles
-system.cpu.icache.overall_mshr_miss_latency     36154500                       # number of overall MSHR miss cycles
+system.cpu.icache.ReadReq_mshr_miss_latency     36044000                       # number of ReadReq MSHR miss cycles
+system.cpu.icache.demand_mshr_miss_latency     36044000                       # number of demand (read+write) MSHR miss cycles
+system.cpu.icache.overall_mshr_miss_latency     36044000                       # number of overall MSHR miss cycles
 system.cpu.icache.overall_mshr_uncacheable_latency            0                       # number of overall MSHR uncacheable cycles
 system.cpu.icache.ReadReq_mshr_miss_rate     0.000036                       # mshr miss rate for ReadReq accesses
 system.cpu.icache.demand_mshr_miss_rate      0.000036                       # mshr miss rate for demand accesses
 system.cpu.icache.overall_mshr_miss_rate     0.000036                       # mshr miss rate for overall accesses
-system.cpu.icache.ReadReq_avg_mshr_miss_latency 35169.747082                       # average ReadReq mshr miss latency
-system.cpu.icache.demand_avg_mshr_miss_latency 35169.747082                       # average overall mshr miss latency
-system.cpu.icache.overall_avg_mshr_miss_latency 35169.747082                       # average overall mshr miss latency
+system.cpu.icache.ReadReq_avg_mshr_miss_latency 35199.218750                       # average ReadReq mshr miss latency
+system.cpu.icache.demand_avg_mshr_miss_latency 35199.218750                       # average overall mshr miss latency
+system.cpu.icache.overall_avg_mshr_miss_latency 35199.218750                       # average overall mshr miss latency
 system.cpu.icache.overall_avg_mshr_uncacheable_latency     no_value                       # average overall mshr uncacheable latency
 system.cpu.icache.mshr_cap_events                   0                       # number of times MSHR cap was activated
 system.cpu.icache.soft_prefetch_mshr_full            0                       # number of mshr full events for SW prefetching instrutions
 system.cpu.icache.no_allocate_misses                0                       # Number of misses that were no-allocate
-system.cpu.dcache.replacements                2073066                       # number of replacements
-system.cpu.dcache.tagsinuse               4076.005888                       # Cycle average of tags in use
-system.cpu.dcache.total_refs                 83808707                       # Total number of references to valid blocks.
-system.cpu.dcache.sampled_refs                2077162                       # Sample count of references to valid blocks.
-system.cpu.dcache.avg_refs                  40.347699                       # Average number of references to valid blocks.
-system.cpu.dcache.warmup_cycle            23845092000                       # Cycle when the warmup percentage was hit.
-system.cpu.dcache.occ_blocks::0           4076.005888                       # Average occupied blocks per context
-system.cpu.dcache.occ_percent::0             0.995119                       # Average percentage of cache occupancy
-system.cpu.dcache.ReadReq_hits               52611944                       # number of ReadReq hits
-system.cpu.dcache.WriteReq_hits              31196754                       # number of WriteReq hits
-system.cpu.dcache.demand_hits                83808698                       # number of demand (read+write) hits
-system.cpu.dcache.overall_hits               83808698                       # number of overall hits
-system.cpu.dcache.ReadReq_misses              2262875                       # number of ReadReq misses
-system.cpu.dcache.WriteReq_misses              242997                       # number of WriteReq misses
-system.cpu.dcache.demand_misses               2505872                       # number of demand (read+write) misses
-system.cpu.dcache.overall_misses              2505872                       # number of overall misses
-system.cpu.dcache.ReadReq_miss_latency    14629803500                       # number of ReadReq miss cycles
-system.cpu.dcache.WriteReq_miss_latency    4394648436                       # number of WriteReq miss cycles
-system.cpu.dcache.demand_miss_latency     19024451936                       # number of demand (read+write) miss cycles
-system.cpu.dcache.overall_miss_latency    19024451936                       # number of overall miss cycles
-system.cpu.dcache.ReadReq_accesses           54874819                       # number of ReadReq accesses(hits+misses)
+system.cpu.dcache.replacements                2072801                       # number of replacements
+system.cpu.dcache.tagsinuse               4073.016957                       # Cycle average of tags in use
+system.cpu.dcache.total_refs                 77487718                       # Total number of references to valid blocks.
+system.cpu.dcache.sampled_refs                2076897                       # Sample count of references to valid blocks.
+system.cpu.dcache.avg_refs                  37.309370                       # Average number of references to valid blocks.
+system.cpu.dcache.warmup_cycle            23652058000                       # Cycle when the warmup percentage was hit.
+system.cpu.dcache.occ_blocks::0           4073.016957                       # Average occupied blocks per context
+system.cpu.dcache.occ_percent::0             0.994389                       # Average percentage of cache occupancy
+system.cpu.dcache.ReadReq_hits               46133976                       # number of ReadReq hits
+system.cpu.dcache.WriteReq_hits              31353733                       # number of WriteReq hits
+system.cpu.dcache.demand_hits                77487709                       # number of demand (read+write) hits
+system.cpu.dcache.overall_hits               77487709                       # number of overall hits
+system.cpu.dcache.ReadReq_misses              2288597                       # number of ReadReq misses
+system.cpu.dcache.WriteReq_misses               86018                       # number of WriteReq misses
+system.cpu.dcache.demand_misses               2374615                       # number of demand (read+write) misses
+system.cpu.dcache.overall_misses              2374615                       # number of overall misses
+system.cpu.dcache.ReadReq_miss_latency    13760644500                       # number of ReadReq miss cycles
+system.cpu.dcache.WriteReq_miss_latency    1501321288                       # number of WriteReq miss cycles
+system.cpu.dcache.demand_miss_latency     15261965788                       # number of demand (read+write) miss cycles
+system.cpu.dcache.overall_miss_latency    15261965788                       # number of overall miss cycles
+system.cpu.dcache.ReadReq_accesses           48422573                       # number of ReadReq accesses(hits+misses)
 system.cpu.dcache.WriteReq_accesses          31439751                       # number of WriteReq accesses(hits+misses)
-system.cpu.dcache.demand_accesses            86314570                       # number of demand (read+write) accesses
-system.cpu.dcache.overall_accesses           86314570                       # number of overall (read+write) accesses
-system.cpu.dcache.ReadReq_miss_rate          0.041237                       # miss rate for ReadReq accesses
-system.cpu.dcache.WriteReq_miss_rate         0.007729                       # miss rate for WriteReq accesses
-system.cpu.dcache.demand_miss_rate           0.029032                       # miss rate for demand accesses
-system.cpu.dcache.overall_miss_rate          0.029032                       # miss rate for overall accesses
-system.cpu.dcache.ReadReq_avg_miss_latency  6465.139922                       # average ReadReq miss latency
-system.cpu.dcache.WriteReq_avg_miss_latency 18085.196262                       # average WriteReq miss latency
-system.cpu.dcache.demand_avg_miss_latency  7591.948805                       # average overall miss latency
-system.cpu.dcache.overall_avg_miss_latency  7591.948805                       # average overall miss latency
-system.cpu.dcache.blocked_cycles::no_mshrs       289000                       # number of cycles access was blocked
+system.cpu.dcache.demand_accesses            79862324                       # number of demand (read+write) accesses
+system.cpu.dcache.overall_accesses           79862324                       # number of overall (read+write) accesses
+system.cpu.dcache.ReadReq_miss_rate          0.047263                       # miss rate for ReadReq accesses
+system.cpu.dcache.WriteReq_miss_rate         0.002736                       # miss rate for WriteReq accesses
+system.cpu.dcache.demand_miss_rate           0.029734                       # miss rate for demand accesses
+system.cpu.dcache.overall_miss_rate          0.029734                       # miss rate for overall accesses
+system.cpu.dcache.ReadReq_avg_miss_latency  6012.698828                       # average ReadReq miss latency
+system.cpu.dcache.WriteReq_avg_miss_latency 17453.571206                       # average WriteReq miss latency
+system.cpu.dcache.demand_avg_miss_latency  6427.132730                       # average overall miss latency
+system.cpu.dcache.overall_avg_miss_latency  6427.132730                       # average overall miss latency
+system.cpu.dcache.blocked_cycles::no_mshrs            0                       # number of cycles access was blocked
 system.cpu.dcache.blocked_cycles::no_targets            0                       # number of cycles access was blocked
-system.cpu.dcache.blocked::no_mshrs                92                       # number of cycles access was blocked
+system.cpu.dcache.blocked::no_mshrs                 0                       # number of cycles access was blocked
 system.cpu.dcache.blocked::no_targets               0                       # number of cycles access was blocked
-system.cpu.dcache.avg_blocked_cycles::no_mshrs  3141.304348                       # average number of cycles each access was blocked
+system.cpu.dcache.avg_blocked_cycles::no_mshrs     no_value                       # average number of cycles each access was blocked
 system.cpu.dcache.avg_blocked_cycles::no_targets     no_value                       # average number of cycles each access was blocked
 system.cpu.dcache.fast_writes                       0                       # number of fast writes performed
 system.cpu.dcache.cache_copies                      0                       # number of cache copies performed
-system.cpu.dcache.writebacks                  1447147                       # number of writebacks
-system.cpu.dcache.ReadReq_mshr_hits            291175                       # number of ReadReq MSHR hits
-system.cpu.dcache.WriteReq_mshr_hits           137531                       # number of WriteReq MSHR hits
-system.cpu.dcache.demand_mshr_hits             428706                       # number of demand (read+write) MSHR hits
-system.cpu.dcache.overall_mshr_hits            428706                       # number of overall MSHR hits
-system.cpu.dcache.ReadReq_mshr_misses         1971700                       # number of ReadReq MSHR misses
-system.cpu.dcache.WriteReq_mshr_misses         105466                       # number of WriteReq MSHR misses
-system.cpu.dcache.demand_mshr_misses          2077166                       # number of demand (read+write) MSHR misses
-system.cpu.dcache.overall_mshr_misses         2077166                       # number of overall MSHR misses
+system.cpu.dcache.writebacks                  1880524                       # number of writebacks
+system.cpu.dcache.ReadReq_mshr_hits            293812                       # number of ReadReq MSHR hits
+system.cpu.dcache.WriteReq_mshr_hits             3902                       # number of WriteReq MSHR hits
+system.cpu.dcache.demand_mshr_hits             297714                       # number of demand (read+write) MSHR hits
+system.cpu.dcache.overall_mshr_hits            297714                       # number of overall MSHR hits
+system.cpu.dcache.ReadReq_mshr_misses         1994785                       # number of ReadReq MSHR misses
+system.cpu.dcache.WriteReq_mshr_misses          82116                       # number of WriteReq MSHR misses
+system.cpu.dcache.demand_mshr_misses          2076901                       # number of demand (read+write) MSHR misses
+system.cpu.dcache.overall_mshr_misses         2076901                       # number of overall MSHR misses
 system.cpu.dcache.overall_mshr_uncacheable_misses            0                       # number of overall MSHR uncacheable misses
-system.cpu.dcache.ReadReq_mshr_miss_latency   5609142000                       # number of ReadReq MSHR miss cycles
-system.cpu.dcache.WriteReq_mshr_miss_latency   1870309936                       # number of WriteReq MSHR miss cycles
-system.cpu.dcache.demand_mshr_miss_latency   7479451936                       # number of demand (read+write) MSHR miss cycles
-system.cpu.dcache.overall_mshr_miss_latency   7479451936                       # number of overall MSHR miss cycles
+system.cpu.dcache.ReadReq_mshr_miss_latency   5560782500                       # number of ReadReq MSHR miss cycles
+system.cpu.dcache.WriteReq_mshr_miss_latency   1157739288                       # number of WriteReq MSHR miss cycles
+system.cpu.dcache.demand_mshr_miss_latency   6718521788                       # number of demand (read+write) MSHR miss cycles
+system.cpu.dcache.overall_mshr_miss_latency   6718521788                       # number of overall MSHR miss cycles
 system.cpu.dcache.overall_mshr_uncacheable_latency            0                       # number of overall MSHR uncacheable cycles
-system.cpu.dcache.ReadReq_mshr_miss_rate     0.035931                       # mshr miss rate for ReadReq accesses
-system.cpu.dcache.WriteReq_mshr_miss_rate     0.003355                       # mshr miss rate for WriteReq accesses
-system.cpu.dcache.demand_mshr_miss_rate      0.024065                       # mshr miss rate for demand accesses
-system.cpu.dcache.overall_mshr_miss_rate     0.024065                       # mshr miss rate for overall accesses
-system.cpu.dcache.ReadReq_avg_mshr_miss_latency  2844.825278                       # average ReadReq mshr miss latency
-system.cpu.dcache.WriteReq_avg_mshr_miss_latency 17733.771414                       # average WriteReq mshr miss latency
-system.cpu.dcache.demand_avg_mshr_miss_latency  3600.796439                       # average overall mshr miss latency
-system.cpu.dcache.overall_avg_mshr_miss_latency  3600.796439                       # average overall mshr miss latency
+system.cpu.dcache.ReadReq_mshr_miss_rate     0.041195                       # mshr miss rate for ReadReq accesses
+system.cpu.dcache.WriteReq_mshr_miss_rate     0.002612                       # mshr miss rate for WriteReq accesses
+system.cpu.dcache.demand_mshr_miss_rate      0.026006                       # mshr miss rate for demand accesses
+system.cpu.dcache.overall_mshr_miss_rate     0.026006                       # mshr miss rate for overall accesses
+system.cpu.dcache.ReadReq_avg_mshr_miss_latency  2787.660074                       # average ReadReq mshr miss latency
+system.cpu.dcache.WriteReq_avg_mshr_miss_latency 14098.827123                       # average WriteReq mshr miss latency
+system.cpu.dcache.demand_avg_mshr_miss_latency  3234.878209                       # average overall mshr miss latency
+system.cpu.dcache.overall_avg_mshr_miss_latency  3234.878209                       # average overall mshr miss latency
 system.cpu.dcache.overall_avg_mshr_uncacheable_latency     no_value                       # average overall mshr uncacheable latency
 system.cpu.dcache.mshr_cap_events                   0                       # number of times MSHR cap was activated
 system.cpu.dcache.soft_prefetch_mshr_full            0                       # number of mshr full events for SW prefetching instrutions
 system.cpu.dcache.no_allocate_misses                0                       # Number of misses that were no-allocate
-system.cpu.l2cache.replacements                 49057                       # number of replacements
-system.cpu.l2cache.tagsinuse             18859.305089                       # Cycle average of tags in use
-system.cpu.l2cache.total_refs                 3318010                       # Total number of references to valid blocks.
-system.cpu.l2cache.sampled_refs                 77063                       # Sample count of references to valid blocks.
-system.cpu.l2cache.avg_refs                 43.055811                       # Average number of references to valid blocks.
+system.cpu.l2cache.replacements                 33248                       # number of replacements
+system.cpu.l2cache.tagsinuse             18948.902283                       # Cycle average of tags in use
+system.cpu.l2cache.total_refs                 3764067                       # Total number of references to valid blocks.
+system.cpu.l2cache.sampled_refs                 61254                       # Sample count of references to valid blocks.
+system.cpu.l2cache.avg_refs                 61.450142                       # Average number of references to valid blocks.
 system.cpu.l2cache.warmup_cycle                     0                       # Cycle when the warmup percentage was hit.
-system.cpu.l2cache.occ_blocks::0          6747.919367                       # Average occupied blocks per context
-system.cpu.l2cache.occ_blocks::1         12111.385721                       # Average occupied blocks per context
-system.cpu.l2cache.occ_percent::0            0.205930                       # Average percentage of cache occupancy
-system.cpu.l2cache.occ_percent::1            0.369610                       # Average percentage of cache occupancy
-system.cpu.l2cache.ReadReq_hits               1938157                       # number of ReadReq hits
-system.cpu.l2cache.Writeback_hits             1447147                       # number of Writeback hits
-system.cpu.l2cache.ReadExReq_hits               63526                       # number of ReadExReq hits
-system.cpu.l2cache.demand_hits                2001683                       # number of demand (read+write) hits
-system.cpu.l2cache.overall_hits               2001683                       # number of overall hits
-system.cpu.l2cache.ReadReq_misses               34474                       # number of ReadReq misses
+system.cpu.l2cache.occ_blocks::0          6031.150094                       # Average occupied blocks per context
+system.cpu.l2cache.occ_blocks::1         12917.752189                       # Average occupied blocks per context
+system.cpu.l2cache.occ_percent::0            0.184056                       # Average percentage of cache occupancy
+system.cpu.l2cache.occ_percent::1            0.394219                       # Average percentage of cache occupancy
+system.cpu.l2cache.ReadReq_hits               1964318                       # number of ReadReq hits
+system.cpu.l2cache.Writeback_hits             1880524                       # number of Writeback hits
+system.cpu.l2cache.ReadExReq_hits               52728                       # number of ReadExReq hits
+system.cpu.l2cache.demand_hits                2017046                       # number of demand (read+write) hits
+system.cpu.l2cache.overall_hits               2017046                       # number of overall hits
+system.cpu.l2cache.ReadReq_misses               31362                       # number of ReadReq misses
 system.cpu.l2cache.UpgradeReq_misses                1                       # number of UpgradeReq misses
-system.cpu.l2cache.ReadExReq_misses             42035                       # number of ReadExReq misses
-system.cpu.l2cache.demand_misses                76509                       # number of demand (read+write) misses
-system.cpu.l2cache.overall_misses               76509                       # number of overall misses
-system.cpu.l2cache.ReadReq_miss_latency    1179443000                       # number of ReadReq miss cycles
-system.cpu.l2cache.ReadExReq_miss_latency   1438838000                       # number of ReadExReq miss cycles
-system.cpu.l2cache.demand_miss_latency     2618281000                       # number of demand (read+write) miss cycles
-system.cpu.l2cache.overall_miss_latency    2618281000                       # number of overall miss cycles
-system.cpu.l2cache.ReadReq_accesses           1972631                       # number of ReadReq accesses(hits+misses)
-system.cpu.l2cache.Writeback_accesses         1447147                       # number of Writeback accesses(hits+misses)
+system.cpu.l2cache.ReadExReq_misses             29515                       # number of ReadExReq misses
+system.cpu.l2cache.demand_misses                60877                       # number of demand (read+write) misses
+system.cpu.l2cache.overall_misses               60877                       # number of overall misses
+system.cpu.l2cache.ReadReq_miss_latency    1071112000                       # number of ReadReq miss cycles
+system.cpu.l2cache.ReadExReq_miss_latency   1006258500                       # number of ReadExReq miss cycles
+system.cpu.l2cache.demand_miss_latency     2077370500                       # number of demand (read+write) miss cycles
+system.cpu.l2cache.overall_miss_latency    2077370500                       # number of overall miss cycles
+system.cpu.l2cache.ReadReq_accesses           1995680                       # number of ReadReq accesses(hits+misses)
+system.cpu.l2cache.Writeback_accesses         1880524                       # number of Writeback accesses(hits+misses)
 system.cpu.l2cache.UpgradeReq_accesses              1                       # number of UpgradeReq accesses(hits+misses)
-system.cpu.l2cache.ReadExReq_accesses          105561                       # number of ReadExReq accesses(hits+misses)
-system.cpu.l2cache.demand_accesses            2078192                       # number of demand (read+write) accesses
-system.cpu.l2cache.overall_accesses           2078192                       # number of overall (read+write) accesses
-system.cpu.l2cache.ReadReq_miss_rate         0.017476                       # miss rate for ReadReq accesses
+system.cpu.l2cache.ReadExReq_accesses           82243                       # number of ReadExReq accesses(hits+misses)
+system.cpu.l2cache.demand_accesses            2077923                       # number of demand (read+write) accesses
+system.cpu.l2cache.overall_accesses           2077923                       # number of overall (read+write) accesses
+system.cpu.l2cache.ReadReq_miss_rate         0.015715                       # miss rate for ReadReq accesses
 system.cpu.l2cache.UpgradeReq_miss_rate             1                       # miss rate for UpgradeReq accesses
-system.cpu.l2cache.ReadExReq_miss_rate       0.398206                       # miss rate for ReadExReq accesses
-system.cpu.l2cache.demand_miss_rate          0.036815                       # miss rate for demand accesses
-system.cpu.l2cache.overall_miss_rate         0.036815                       # miss rate for overall accesses
-system.cpu.l2cache.ReadReq_avg_miss_latency 34212.536984                       # average ReadReq miss latency
-system.cpu.l2cache.ReadExReq_avg_miss_latency 34229.523017                       # average ReadExReq miss latency
-system.cpu.l2cache.demand_avg_miss_latency 34221.869323                       # average overall miss latency
-system.cpu.l2cache.overall_avg_miss_latency 34221.869323                       # average overall miss latency
-system.cpu.l2cache.blocked_cycles::no_mshrs        37500                       # number of cycles access was blocked
+system.cpu.l2cache.ReadExReq_miss_rate       0.358876                       # miss rate for ReadExReq accesses
+system.cpu.l2cache.demand_miss_rate          0.029297                       # miss rate for demand accesses
+system.cpu.l2cache.overall_miss_rate         0.029297                       # miss rate for overall accesses
+system.cpu.l2cache.ReadReq_avg_miss_latency 34153.179006                       # average ReadReq miss latency
+system.cpu.l2cache.ReadExReq_avg_miss_latency 34093.122141                       # average ReadExReq miss latency
+system.cpu.l2cache.demand_avg_miss_latency 34124.061632                       # average overall miss latency
+system.cpu.l2cache.overall_avg_miss_latency 34124.061632                       # average overall miss latency
+system.cpu.l2cache.blocked_cycles::no_mshrs            0                       # number of cycles access was blocked
 system.cpu.l2cache.blocked_cycles::no_targets            0                       # number of cycles access was blocked
-system.cpu.l2cache.blocked::no_mshrs               14                       # number of cycles access was blocked
+system.cpu.l2cache.blocked::no_mshrs                0                       # number of cycles access was blocked
 system.cpu.l2cache.blocked::no_targets              0                       # number of cycles access was blocked
-system.cpu.l2cache.avg_blocked_cycles::no_mshrs  2678.571429                       # average number of cycles each access was blocked
+system.cpu.l2cache.avg_blocked_cycles::no_mshrs     no_value                       # average number of cycles each access was blocked
 system.cpu.l2cache.avg_blocked_cycles::no_targets     no_value                       # average number of cycles each access was blocked
 system.cpu.l2cache.fast_writes                      0                       # number of fast writes performed
 system.cpu.l2cache.cache_copies                     0                       # number of cache copies performed
-system.cpu.l2cache.writebacks                   29185                       # number of writebacks
+system.cpu.l2cache.writebacks                   13944                       # number of writebacks
 system.cpu.l2cache.demand_mshr_hits                 0                       # number of demand (read+write) MSHR hits
 system.cpu.l2cache.overall_mshr_hits                0                       # number of overall MSHR hits
-system.cpu.l2cache.ReadReq_mshr_misses          34474                       # number of ReadReq MSHR misses
+system.cpu.l2cache.ReadReq_mshr_misses          31362                       # number of ReadReq MSHR misses
 system.cpu.l2cache.UpgradeReq_mshr_misses            1                       # number of UpgradeReq MSHR misses
-system.cpu.l2cache.ReadExReq_mshr_misses        42035                       # number of ReadExReq MSHR misses
-system.cpu.l2cache.demand_mshr_misses           76509                       # number of demand (read+write) MSHR misses
-system.cpu.l2cache.overall_mshr_misses          76509                       # number of overall MSHR misses
+system.cpu.l2cache.ReadExReq_mshr_misses        29515                       # number of ReadExReq MSHR misses
+system.cpu.l2cache.demand_mshr_misses           60877                       # number of demand (read+write) MSHR misses
+system.cpu.l2cache.overall_mshr_misses          60877                       # number of overall MSHR misses
 system.cpu.l2cache.overall_mshr_uncacheable_misses            0                       # number of overall MSHR uncacheable misses
-system.cpu.l2cache.ReadReq_mshr_miss_latency   1069429500                       # number of ReadReq MSHR miss cycles
+system.cpu.l2cache.ReadReq_mshr_miss_latency    972890000                       # number of ReadReq MSHR miss cycles
 system.cpu.l2cache.UpgradeReq_mshr_miss_latency        31000                       # number of UpgradeReq MSHR miss cycles
-system.cpu.l2cache.ReadExReq_mshr_miss_latency   1307209000                       # number of ReadExReq MSHR miss cycles
-system.cpu.l2cache.demand_mshr_miss_latency   2376638500                       # number of demand (read+write) MSHR miss cycles
-system.cpu.l2cache.overall_mshr_miss_latency   2376638500                       # number of overall MSHR miss cycles
+system.cpu.l2cache.ReadExReq_mshr_miss_latency    914988000                       # number of ReadExReq MSHR miss cycles
+system.cpu.l2cache.demand_mshr_miss_latency   1887878000                       # number of demand (read+write) MSHR miss cycles
+system.cpu.l2cache.overall_mshr_miss_latency   1887878000                       # number of overall MSHR miss cycles
 system.cpu.l2cache.overall_mshr_uncacheable_latency            0                       # number of overall MSHR uncacheable cycles
-system.cpu.l2cache.ReadReq_mshr_miss_rate     0.017476                       # mshr miss rate for ReadReq accesses
+system.cpu.l2cache.ReadReq_mshr_miss_rate     0.015715                       # mshr miss rate for ReadReq accesses
 system.cpu.l2cache.UpgradeReq_mshr_miss_rate            1                       # mshr miss rate for UpgradeReq accesses
-system.cpu.l2cache.ReadExReq_mshr_miss_rate     0.398206                       # mshr miss rate for ReadExReq accesses
-system.cpu.l2cache.demand_mshr_miss_rate     0.036815                       # mshr miss rate for demand accesses
-system.cpu.l2cache.overall_mshr_miss_rate     0.036815                       # mshr miss rate for overall accesses
-system.cpu.l2cache.ReadReq_avg_mshr_miss_latency 31021.334919                       # average ReadReq mshr miss latency
+system.cpu.l2cache.ReadExReq_mshr_miss_rate     0.358876                       # mshr miss rate for ReadExReq accesses
+system.cpu.l2cache.demand_mshr_miss_rate     0.029297                       # mshr miss rate for demand accesses
+system.cpu.l2cache.overall_mshr_miss_rate     0.029297                       # mshr miss rate for overall accesses
+system.cpu.l2cache.ReadReq_avg_mshr_miss_latency 31021.299662                       # average ReadReq mshr miss latency
 system.cpu.l2cache.UpgradeReq_avg_mshr_miss_latency        31000                       # average UpgradeReq mshr miss latency
-system.cpu.l2cache.ReadExReq_avg_mshr_miss_latency 31098.108719                       # average ReadExReq mshr miss latency
-system.cpu.l2cache.demand_avg_mshr_miss_latency 31063.515403                       # average overall mshr miss latency
-system.cpu.l2cache.overall_avg_mshr_miss_latency 31063.515403                       # average overall mshr miss latency
+system.cpu.l2cache.ReadExReq_avg_mshr_miss_latency 31000.779265                       # average ReadExReq mshr miss latency
+system.cpu.l2cache.demand_avg_mshr_miss_latency 31011.350756                       # average overall mshr miss latency
+system.cpu.l2cache.overall_avg_mshr_miss_latency 31011.350756                       # average overall mshr miss latency
 system.cpu.l2cache.overall_avg_mshr_uncacheable_latency     no_value                       # average overall mshr uncacheable latency
 system.cpu.l2cache.mshr_cap_events                  0                       # number of times MSHR cap was activated
 system.cpu.l2cache.soft_prefetch_mshr_full            0                       # number of mshr full events for SW prefetching instrutions
diff --git a/tests/long/20.parser/ref/x86/linux/o3-timing/config.ini b/tests/long/20.parser/ref/x86/linux/o3-timing/config.ini
index 9cc2736..50d3ef0 100644
--- a/tests/long/20.parser/ref/x86/linux/o3-timing/config.ini
+++ b/tests/long/20.parser/ref/x86/linux/o3-timing/config.ini
@@ -80,6 +80,7 @@
 max_insts_any_thread=0
 max_loads_all_threads=0
 max_loads_any_thread=0
+needsTSO=true
 numIQEntries=64
 numPhysFloatRegs=256
 numPhysIntRegs=256
@@ -502,9 +503,9 @@
 env=
 errout=cerr
 euid=100
-executable=/dist/m5/cpu2000/binaries/x86/linux/parser
+executable=/scratch/nilay/GEM5/dist/m5/cpu2000/binaries/x86/linux/parser
 gid=100
-input=/dist/m5/cpu2000/data/parser/mdred/input/parser.in
+input=/scratch/nilay/GEM5/dist/m5/cpu2000/data/parser/mdred/input/parser.in
 max_stack_size=67108864
 output=cout
 pid=100
diff --git a/tests/long/20.parser/ref/x86/linux/o3-timing/simout b/tests/long/20.parser/ref/x86/linux/o3-timing/simout
index de72d96..b3bd7cb 100755
--- a/tests/long/20.parser/ref/x86/linux/o3-timing/simout
+++ b/tests/long/20.parser/ref/x86/linux/o3-timing/simout
@@ -1,9 +1,11 @@
+Redirecting stdout to build/X86_SE/tests/opt/long/20.parser/x86/linux/o3-timing/simout
+Redirecting stderr to build/X86_SE/tests/opt/long/20.parser/x86/linux/o3-timing/simerr
 gem5 Simulator System.  http://gem5.org
 gem5 is copyrighted software; use the --copyright option for details.
 
-gem5 compiled Jan 23 2012 04:08:34
-gem5 started Jan 23 2012 06:58:28
-gem5 executing on zizzer
+gem5 compiled Jan 28 2012 12:11:40
+gem5 started Jan 28 2012 12:12:44
+gem5 executing on ribera.cs.wisc.edu
 command line: build/X86_SE/gem5.opt -d build/X86_SE/tests/opt/long/20.parser/x86/linux/o3-timing -re tests/run.py build/X86_SE/tests/opt/long/20.parser/x86/linux/o3-timing
 Global frequency set at 1000000000000 ticks per second
 info: Entering event queue @ 0.  Starting simulation...
@@ -64,19 +66,9 @@
   the man with whom I play tennis is here 
   there is a dog in the park 
   this is not the man we know and love 
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
-info: Increasing stack size by one page.
   we like to eat at restaurants , usually on weekends 
   what did John say he thought you should do 
   about 2 million people attended 
   the five best costumes got prizes 
 No errors!
-Exiting @ tick 493912286000 because target called exit()
+Exiting @ tick 488997764000 because target called exit()
diff --git a/tests/long/20.parser/ref/x86/linux/o3-timing/stats.txt b/tests/long/20.parser/ref/x86/linux/o3-timing/stats.txt
index 92ece0b..f99849c 100644
--- a/tests/long/20.parser/ref/x86/linux/o3-timing/stats.txt
+++ b/tests/long/20.parser/ref/x86/linux/o3-timing/stats.txt
@@ -1,264 +1,263 @@
 
 ---------- Begin Simulation Statistics ----------
-sim_seconds                                  0.493912                       # Number of seconds simulated
-sim_ticks                                493912286000                       # Number of ticks simulated
-final_tick                               493912286000                       # Number of ticks from beginning of simulation (restored from checkpoints and never reset)
+sim_seconds                                  0.488998                       # Number of seconds simulated
+sim_ticks                                488997764000                       # Number of ticks simulated
+final_tick                               488997764000                       # Number of ticks from beginning of simulation (restored from checkpoints and never reset)
 sim_freq                                 1000000000000                       # Frequency of simulated ticks
-host_inst_rate                                 145271                       # Simulator instruction rate (inst/s)
-host_tick_rate                               46927205                       # Simulator tick rate (ticks/s)
-host_mem_usage                                 251468                       # Number of bytes of host memory used
-host_seconds                                 10525.07                       # Real time elapsed on the host
+host_inst_rate                                 107684                       # Simulator instruction rate (inst/s)
+host_tick_rate                               34439407                       # Simulator tick rate (ticks/s)
+host_mem_usage                                 280760                       # Number of bytes of host memory used
+host_seconds                                 14198.79                       # Real time elapsed on the host
 sim_insts                                  1528988756                       # Number of instructions simulated
-system.physmem.bytes_read                    37487424                       # Number of bytes read from this memory
-system.physmem.bytes_inst_read                 347584                       # Number of instructions bytes read from this memory
-system.physmem.bytes_written                 26320960                       # Number of bytes written to this memory
-system.physmem.num_reads                       585741                       # Number of read requests responded to by this memory
-system.physmem.num_writes                      411265                       # Number of write requests responded to by this memory
+system.physmem.bytes_read                    37533312                       # Number of bytes read from this memory
+system.physmem.bytes_inst_read                 347328                       # Number of instructions bytes read from this memory
+system.physmem.bytes_written                 26337408                       # Number of bytes written to this memory
+system.physmem.num_reads                       586458                       # Number of read requests responded to by this memory
+system.physmem.num_writes                      411522                       # Number of write requests responded to by this memory
 system.physmem.num_other                            0                       # Number of other requests responded to by this memory
-system.physmem.bw_read                       75898950                       # Total read bandwidth from this memory (bytes/s)
-system.physmem.bw_inst_read                    703736                       # Instruction read bandwidth from this memory (bytes/s)
-system.physmem.bw_write                      53290758                       # Write bandwidth from this memory (bytes/s)
-system.physmem.bw_total                     129189708                       # Total bandwidth to/from this memory (bytes/s)
+system.physmem.bw_read                       76755590                       # Total read bandwidth from this memory (bytes/s)
+system.physmem.bw_inst_read                    710285                       # Instruction read bandwidth from this memory (bytes/s)
+system.physmem.bw_write                      53859976                       # Write bandwidth from this memory (bytes/s)
+system.physmem.bw_total                     130615567                       # Total bandwidth to/from this memory (bytes/s)
 system.cpu.workload.num_syscalls                  551                       # Number of system calls
-system.cpu.numCycles                        987824573                       # number of cpu cycles simulated
+system.cpu.numCycles                        977995529                       # number of cpu cycles simulated
 system.cpu.numWorkItemsStarted                      0                       # number of work items this cpu started
 system.cpu.numWorkItemsCompleted                    0                       # number of work items this cpu completed
-system.cpu.BPredUnit.lookups                245766486                       # Number of BP lookups
-system.cpu.BPredUnit.condPredicted          245766486                       # Number of conditional branches predicted
-system.cpu.BPredUnit.condIncorrect           16576996                       # Number of conditional branches incorrect
-system.cpu.BPredUnit.BTBLookups             236474058                       # Number of BTB lookups
-system.cpu.BPredUnit.BTBHits                218464201                       # Number of BTB hits
+system.cpu.BPredUnit.lookups                244993586                       # Number of BP lookups
+system.cpu.BPredUnit.condPredicted          244993586                       # Number of conditional branches predicted
+system.cpu.BPredUnit.condIncorrect           16602389                       # Number of conditional branches incorrect
+system.cpu.BPredUnit.BTBLookups             235528185                       # Number of BTB lookups
+system.cpu.BPredUnit.BTBHits                217667296                       # Number of BTB hits
 system.cpu.BPredUnit.BTBCorrect                     0                       # Number of correct BTB predictions (this stat may not work properly.
 system.cpu.BPredUnit.usedRAS                        0                       # Number of times the RAS was used to get a target.
 system.cpu.BPredUnit.RASInCorrect                   0                       # Number of incorrect RAS predictions.
-system.cpu.fetch.icacheStallCycles          205503020                       # Number of cycles fetch is stalled on an Icache miss
-system.cpu.fetch.Insts                     1343384866                       # Number of instructions fetch has processed
-system.cpu.fetch.Branches                   245766486                       # Number of branches that fetch encountered
-system.cpu.fetch.predictedBranches          218464201                       # Number of branches that fetch has predicted taken
-system.cpu.fetch.Cycles                     436676837                       # Number of cycles fetch has run and was not squashing or blocked
-system.cpu.fetch.SquashCycles               119986236                       # Number of cycles fetch has spent squashing
-system.cpu.fetch.BlockedCycles              218554807                       # Number of cycles fetch has spent blocked
-system.cpu.fetch.MiscStallCycles                32387                       # Number of cycles fetch has spent waiting on interrupts, or bad addresses, or out of MSHRs
-system.cpu.fetch.PendingTrapStallCycles        341323                       # Number of stall cycles due to pending traps
-system.cpu.fetch.CacheLines                 194710374                       # Number of cache lines fetched
-system.cpu.fetch.IcacheSquashes               4099618                       # Number of outstanding Icache misses that were squashed
-system.cpu.fetch.rateDist::samples          964252463                       # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::mean              2.599701                       # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::stdev             3.317490                       # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.icacheStallCycles          204934624                       # Number of cycles fetch is stalled on an Icache miss
+system.cpu.fetch.Insts                     1339258211                       # Number of instructions fetch has processed
+system.cpu.fetch.Branches                   244993586                       # Number of branches that fetch encountered
+system.cpu.fetch.predictedBranches          217667296                       # Number of branches that fetch has predicted taken
+system.cpu.fetch.Cycles                     435322465                       # Number of cycles fetch has run and was not squashing or blocked
+system.cpu.fetch.SquashCycles               118846275                       # Number of cycles fetch has spent squashing
+system.cpu.fetch.BlockedCycles              217468055                       # Number of cycles fetch has spent blocked
+system.cpu.fetch.MiscStallCycles                30116                       # Number of cycles fetch has spent waiting on interrupts, or bad addresses, or out of MSHRs
+system.cpu.fetch.PendingTrapStallCycles        232804                       # Number of stall cycles due to pending traps
+system.cpu.fetch.CacheLines                 194158401                       # Number of cache lines fetched
+system.cpu.fetch.IcacheSquashes               4161421                       # Number of outstanding Icache misses that were squashed
+system.cpu.fetch.rateDist::samples          959969834                       # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.rateDist::mean              2.603022                       # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.rateDist::stdev             3.318234                       # Number of instructions fetched each cycle (Total)
 system.cpu.fetch.rateDist::underflows               0      0.00%      0.00% # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::0                531629837     55.13%     55.13% # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::1                 32377332      3.36%     58.49% # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::2                 38827894      4.03%     62.52% # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::3                 32536894      3.37%     65.89% # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::4                 21844251      2.27%     68.16% # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::5                 36448993      3.78%     71.94% # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::6                 49128972      5.10%     77.03% # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::7                 36937786      3.83%     80.86% # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::8                184520504     19.14%    100.00% # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.rateDist::0                528643490     55.07%     55.07% # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.rateDist::1                 32333608      3.37%     58.44% # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.rateDist::2                 38757249      4.04%     62.47% # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.rateDist::3                 32421466      3.38%     65.85% # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.rateDist::4                 21788164      2.27%     68.12% # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.rateDist::5                 36314533      3.78%     71.90% # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.rateDist::6                 48923013      5.10%     77.00% # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.rateDist::7                 36860126      3.84%     80.84% # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.rateDist::8                183928185     19.16%    100.00% # Number of instructions fetched each cycle (Total)
 system.cpu.fetch.rateDist::overflows                0      0.00%    100.00% # Number of instructions fetched each cycle (Total)
 system.cpu.fetch.rateDist::min_value                0                       # Number of instructions fetched each cycle (Total)
 system.cpu.fetch.rateDist::max_value                8                       # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::total            964252463                       # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.branchRate                  0.248796                       # Number of branch fetches per cycle
-system.cpu.fetch.rate                        1.359943                       # Number of inst fetches per cycle
-system.cpu.decode.IdleCycles                264509435                       # Number of cycles decode is idle
-system.cpu.decode.BlockedCycles             174554141                       # Number of cycles decode is blocked
-system.cpu.decode.RunCycles                 373011587                       # Number of cycles decode is running
-system.cpu.decode.UnblockCycles              49033211                       # Number of cycles decode is unblocking
-system.cpu.decode.SquashCycles              103144089                       # Number of cycles decode is squashing
-system.cpu.decode.DecodedInsts             2445932072                       # Number of instructions handled by decode
-system.cpu.decode.SquashedInsts                     1                       # Number of squashed instructions handled by decode
-system.cpu.rename.SquashCycles              103144089                       # Number of cycles rename is squashing
-system.cpu.rename.IdleCycles                301738657                       # Number of cycles rename is idle
-system.cpu.rename.BlockCycles                40282868                       # Number of cycles rename is blocking
-system.cpu.rename.serializeStallCycles          12225                       # count of cycles rename stalled for serializing inst
-system.cpu.rename.RunCycles                 383467875                       # Number of cycles rename is running
-system.cpu.rename.UnblockCycles             135606749                       # Number of cycles rename is unblocking
-system.cpu.rename.RenamedInsts             2393375507                       # Number of instructions processed by rename
-system.cpu.rename.ROBFullEvents                  2559                       # Number of times rename has blocked due to ROB full
-system.cpu.rename.IQFullEvents               25131978                       # Number of times rename has blocked due to IQ full
-system.cpu.rename.LSQFullEvents              92224846                       # Number of times rename has blocked due to LSQ full
-system.cpu.rename.FullRegisterEvents                8                       # Number of times there has been no free registers
-system.cpu.rename.RenamedOperands          2227188673                       # Number of destination operands rename has renamed
-system.cpu.rename.RenameLookups            5629907069                       # Number of register rename lookups that rename has made
-system.cpu.rename.int_rename_lookups       5629667957                       # Number of integer rename lookups
-system.cpu.rename.fp_rename_lookups            239112                       # Number of floating rename lookups
+system.cpu.fetch.rateDist::total            959969834                       # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.branchRate                  0.250506                       # Number of branch fetches per cycle
+system.cpu.fetch.rate                        1.369391                       # Number of inst fetches per cycle
+system.cpu.decode.IdleCycles                264672814                       # Number of cycles decode is idle
+system.cpu.decode.BlockedCycles             172740484                       # Number of cycles decode is blocked
+system.cpu.decode.RunCycles                 371802947                       # Number of cycles decode is running
+system.cpu.decode.UnblockCycles              48771819                       # Number of cycles decode is unblocking
+system.cpu.decode.SquashCycles              101981770                       # Number of cycles decode is squashing
+system.cpu.decode.DecodedInsts             2436948242                       # Number of instructions handled by decode
+system.cpu.rename.SquashCycles              101981770                       # Number of cycles rename is squashing
+system.cpu.rename.IdleCycles                302199214                       # Number of cycles rename is idle
+system.cpu.rename.BlockCycles                38454889                       # Number of cycles rename is blocking
+system.cpu.rename.serializeStallCycles          15108                       # count of cycles rename stalled for serializing inst
+system.cpu.rename.RunCycles                 381795429                       # Number of cycles rename is running
+system.cpu.rename.UnblockCycles             135523424                       # Number of cycles rename is unblocking
+system.cpu.rename.RenamedInsts             2384665027                       # Number of instructions processed by rename
+system.cpu.rename.ROBFullEvents                  2593                       # Number of times rename has blocked due to ROB full
+system.cpu.rename.IQFullEvents               22692453                       # Number of times rename has blocked due to IQ full
+system.cpu.rename.LSQFullEvents              94335239                       # Number of times rename has blocked due to LSQ full
+system.cpu.rename.FullRegisterEvents               23                       # Number of times there has been no free registers
+system.cpu.rename.RenamedOperands          2218279276                       # Number of destination operands rename has renamed
+system.cpu.rename.RenameLookups            5608704737                       # Number of register rename lookups that rename has made
+system.cpu.rename.int_rename_lookups       5608168752                       # Number of integer rename lookups
+system.cpu.rename.fp_rename_lookups            535985                       # Number of floating rename lookups
 system.cpu.rename.CommittedMaps            1427299027                       # Number of HB maps that are committed
-system.cpu.rename.UndoneMaps                799889646                       # Number of HB maps that are undone due to squashing
-system.cpu.rename.serializingInsts               1309                       # count of serializing insts renamed
-system.cpu.rename.tempSerializingInsts           1288                       # count of temporary serializing insts renamed
-system.cpu.rename.skidInsts                 318947403                       # count of insts added to the skid buffer
-system.cpu.memDep0.insertedLoads            577879232                       # Number of loads inserted to the mem dependence unit.
-system.cpu.memDep0.insertedStores           226530900                       # Number of stores inserted to the mem dependence unit.
-system.cpu.memDep0.conflictingLoads         227222440                       # Number of conflicting loads.
-system.cpu.memDep0.conflictingStores         65937432                       # Number of conflicting stores.
-system.cpu.iq.iqInstsAdded                 2286709085                       # Number of instructions added to the IQ (excludes non-spec)
-system.cpu.iq.iqNonSpecInstsAdded               12489                       # Number of non-speculative instructions added to the IQ
-system.cpu.iq.iqInstsIssued                1922370305                       # Number of instructions issued
-system.cpu.iq.iqSquashedInstsIssued           1306641                       # Number of squashed instructions issued
-system.cpu.iq.iqSquashedInstsExamined       755226802                       # Number of squashed instructions iterated over during squash; mainly for profiling
-system.cpu.iq.iqSquashedOperandsExamined   1190125426                       # Number of squashed operands that are examined and possibly removed from graph
-system.cpu.iq.iqSquashedNonSpecRemoved          11936                       # Number of squashed non-spec instructions that were removed
-system.cpu.iq.issued_per_cycle::samples     964252463                       # Number of insts issued each cycle
-system.cpu.iq.issued_per_cycle::mean         1.993638                       # Number of insts issued each cycle
-system.cpu.iq.issued_per_cycle::stdev        1.811521                       # Number of insts issued each cycle
+system.cpu.rename.UndoneMaps                790980249                       # Number of HB maps that are undone due to squashing
+system.cpu.rename.serializingInsts               1421                       # count of serializing insts renamed
+system.cpu.rename.tempSerializingInsts           1399                       # count of temporary serializing insts renamed
+system.cpu.rename.skidInsts                 314817660                       # count of insts added to the skid buffer
+system.cpu.memDep0.insertedLoads            575520947                       # Number of loads inserted to the mem dependence unit.
+system.cpu.memDep0.insertedStores           225733737                       # Number of stores inserted to the mem dependence unit.
+system.cpu.memDep0.conflictingLoads         224565693                       # Number of conflicting loads.
+system.cpu.memDep0.conflictingStores         66120103                       # Number of conflicting stores.
+system.cpu.iq.iqInstsAdded                 2277627469                       # Number of instructions added to the IQ (excludes non-spec)
+system.cpu.iq.iqNonSpecInstsAdded               14301                       # Number of non-speculative instructions added to the IQ
+system.cpu.iq.iqInstsIssued                1920324328                       # Number of instructions issued
+system.cpu.iq.iqSquashedInstsIssued           1300872                       # Number of squashed instructions issued
+system.cpu.iq.iqSquashedInstsExamined       746152360                       # Number of squashed instructions iterated over during squash; mainly for profiling
+system.cpu.iq.iqSquashedOperandsExamined   1169098860                       # Number of squashed operands that are examined and possibly removed from graph
+system.cpu.iq.iqSquashedNonSpecRemoved          13748                       # Number of squashed non-spec instructions that were removed
+system.cpu.iq.issued_per_cycle::samples     959969834                       # Number of insts issued each cycle
+system.cpu.iq.issued_per_cycle::mean         2.000401                       # Number of insts issued each cycle
+system.cpu.iq.issued_per_cycle::stdev        1.810923                       # Number of insts issued each cycle
 system.cpu.iq.issued_per_cycle::underflows            0      0.00%      0.00% # Number of insts issued each cycle
-system.cpu.iq.issued_per_cycle::0           282911384     29.34%     29.34% # Number of insts issued each cycle
-system.cpu.iq.issued_per_cycle::1           160280603     16.62%     45.96% # Number of insts issued each cycle
-system.cpu.iq.issued_per_cycle::2           162550496     16.86%     62.82% # Number of insts issued each cycle
-system.cpu.iq.issued_per_cycle::3           148847741     15.44%     78.26% # Number of insts issued each cycle
-system.cpu.iq.issued_per_cycle::4           109081156     11.31%     89.57% # Number of insts issued each cycle
-system.cpu.iq.issued_per_cycle::5            60080329      6.23%     95.80% # Number of insts issued each cycle
-system.cpu.iq.issued_per_cycle::6            30822605      3.20%     99.00% # Number of insts issued each cycle
-system.cpu.iq.issued_per_cycle::7             8641604      0.90%     99.89% # Number of insts issued each cycle
-system.cpu.iq.issued_per_cycle::8             1036545      0.11%    100.00% # Number of insts issued each cycle
+system.cpu.iq.issued_per_cycle::0           279838383     29.15%     29.15% # Number of insts issued each cycle
+system.cpu.iq.issued_per_cycle::1           159390008     16.60%     45.75% # Number of insts issued each cycle
+system.cpu.iq.issued_per_cycle::2           161109543     16.78%     62.54% # Number of insts issued each cycle
+system.cpu.iq.issued_per_cycle::3           151059392     15.74%     78.27% # Number of insts issued each cycle
+system.cpu.iq.issued_per_cycle::4           108561364     11.31%     89.58% # Number of insts issued each cycle
+system.cpu.iq.issued_per_cycle::5            60361287      6.29%     95.87% # Number of insts issued each cycle
+system.cpu.iq.issued_per_cycle::6            29161241      3.04%     98.91% # Number of insts issued each cycle
+system.cpu.iq.issued_per_cycle::7             9391207      0.98%     99.89% # Number of insts issued each cycle
+system.cpu.iq.issued_per_cycle::8             1097409      0.11%    100.00% # Number of insts issued each cycle
 system.cpu.iq.issued_per_cycle::overflows            0      0.00%    100.00% # Number of insts issued each cycle
 system.cpu.iq.issued_per_cycle::min_value            0                       # Number of insts issued each cycle
 system.cpu.iq.issued_per_cycle::max_value            8                       # Number of insts issued each cycle
-system.cpu.iq.issued_per_cycle::total       964252463                       # Number of insts issued each cycle
+system.cpu.iq.issued_per_cycle::total       959969834                       # Number of insts issued each cycle
 system.cpu.iq.fu_full::No_OpClass                   0      0.00%      0.00% # attempts to use FU when none available
-system.cpu.iq.fu_full::IntAlu                 2246339     14.60%     14.60% # attempts to use FU when none available
-system.cpu.iq.fu_full::IntMult                      0      0.00%     14.60% # attempts to use FU when none available
-system.cpu.iq.fu_full::IntDiv                       0      0.00%     14.60% # attempts to use FU when none available
-system.cpu.iq.fu_full::FloatAdd                     0      0.00%     14.60% # attempts to use FU when none available
-system.cpu.iq.fu_full::FloatCmp                     0      0.00%     14.60% # attempts to use FU when none available
-system.cpu.iq.fu_full::FloatCvt                     0      0.00%     14.60% # attempts to use FU when none available
-system.cpu.iq.fu_full::FloatMult                    0      0.00%     14.60% # attempts to use FU when none available
-system.cpu.iq.fu_full::FloatDiv                     0      0.00%     14.60% # attempts to use FU when none available
-system.cpu.iq.fu_full::FloatSqrt                    0      0.00%     14.60% # attempts to use FU when none available
-system.cpu.iq.fu_full::SimdAdd                      0      0.00%     14.60% # attempts to use FU when none available
-system.cpu.iq.fu_full::SimdAddAcc                   0      0.00%     14.60% # attempts to use FU when none available
-system.cpu.iq.fu_full::SimdAlu                      0      0.00%     14.60% # attempts to use FU when none available
-system.cpu.iq.fu_full::SimdCmp                      0      0.00%     14.60% # attempts to use FU when none available
-system.cpu.iq.fu_full::SimdCvt                      0      0.00%     14.60% # attempts to use FU when none available
-system.cpu.iq.fu_full::SimdMisc                     0      0.00%     14.60% # attempts to use FU when none available
-system.cpu.iq.fu_full::SimdMult                     0      0.00%     14.60% # attempts to use FU when none available
-system.cpu.iq.fu_full::SimdMultAcc                  0      0.00%     14.60% # attempts to use FU when none available
-system.cpu.iq.fu_full::SimdShift                    0      0.00%     14.60% # attempts to use FU when none available
-system.cpu.iq.fu_full::SimdShiftAcc                 0      0.00%     14.60% # attempts to use FU when none available
-system.cpu.iq.fu_full::SimdSqrt                     0      0.00%     14.60% # attempts to use FU when none available
-system.cpu.iq.fu_full::SimdFloatAdd                 0      0.00%     14.60% # attempts to use FU when none available
-system.cpu.iq.fu_full::SimdFloatAlu                 0      0.00%     14.60% # attempts to use FU when none available
-system.cpu.iq.fu_full::SimdFloatCmp                 0      0.00%     14.60% # attempts to use FU when none available
-system.cpu.iq.fu_full::SimdFloatCvt                 0      0.00%     14.60% # attempts to use FU when none available
-system.cpu.iq.fu_full::SimdFloatDiv                 0      0.00%     14.60% # attempts to use FU when none available
-system.cpu.iq.fu_full::SimdFloatMisc                0      0.00%     14.60% # attempts to use FU when none available
-system.cpu.iq.fu_full::SimdFloatMult                0      0.00%     14.60% # attempts to use FU when none available
-system.cpu.iq.fu_full::SimdFloatMultAcc             0      0.00%     14.60% # attempts to use FU when none available
-system.cpu.iq.fu_full::SimdFloatSqrt                0      0.00%     14.60% # attempts to use FU when none available
-system.cpu.iq.fu_full::MemRead               10026447     65.19%     79.79% # attempts to use FU when none available
-system.cpu.iq.fu_full::MemWrite               3108042     20.21%    100.00% # attempts to use FU when none available
+system.cpu.iq.fu_full::IntAlu                 2254063     14.63%     14.63% # attempts to use FU when none available
+system.cpu.iq.fu_full::IntMult                      0      0.00%     14.63% # attempts to use FU when none available
+system.cpu.iq.fu_full::IntDiv                       0      0.00%     14.63% # attempts to use FU when none available
+system.cpu.iq.fu_full::FloatAdd                     0      0.00%     14.63% # attempts to use FU when none available
+system.cpu.iq.fu_full::FloatCmp                     0      0.00%     14.63% # attempts to use FU when none available
+system.cpu.iq.fu_full::FloatCvt                     0      0.00%     14.63% # attempts to use FU when none available
+system.cpu.iq.fu_full::FloatMult                    0      0.00%     14.63% # attempts to use FU when none available
+system.cpu.iq.fu_full::FloatDiv                     0      0.00%     14.63% # attempts to use FU when none available
+system.cpu.iq.fu_full::FloatSqrt                    0      0.00%     14.63% # attempts to use FU when none available
+system.cpu.iq.fu_full::SimdAdd                      0      0.00%     14.63% # attempts to use FU when none available
+system.cpu.iq.fu_full::SimdAddAcc                   0      0.00%     14.63% # attempts to use FU when none available
+system.cpu.iq.fu_full::SimdAlu                      0      0.00%     14.63% # attempts to use FU when none available
+system.cpu.iq.fu_full::SimdCmp                      0      0.00%     14.63% # attempts to use FU when none available
+system.cpu.iq.fu_full::SimdCvt                      0      0.00%     14.63% # attempts to use FU when none available
+system.cpu.iq.fu_full::SimdMisc                     0      0.00%     14.63% # attempts to use FU when none available
+system.cpu.iq.fu_full::SimdMult                     0      0.00%     14.63% # attempts to use FU when none available
+system.cpu.iq.fu_full::SimdMultAcc                  0      0.00%     14.63% # attempts to use FU when none available
+system.cpu.iq.fu_full::SimdShift                    0      0.00%     14.63% # attempts to use FU when none available
+system.cpu.iq.fu_full::SimdShiftAcc                 0      0.00%     14.63% # attempts to use FU when none available
+system.cpu.iq.fu_full::SimdSqrt                     0      0.00%     14.63% # attempts to use FU when none available
+system.cpu.iq.fu_full::SimdFloatAdd                 0      0.00%     14.63% # attempts to use FU when none available
+system.cpu.iq.fu_full::SimdFloatAlu                 0      0.00%     14.63% # attempts to use FU when none available
+system.cpu.iq.fu_full::SimdFloatCmp                 0      0.00%     14.63% # attempts to use FU when none available
+system.cpu.iq.fu_full::SimdFloatCvt                 0      0.00%     14.63% # attempts to use FU when none available
+system.cpu.iq.fu_full::SimdFloatDiv                 0      0.00%     14.63% # attempts to use FU when none available
+system.cpu.iq.fu_full::SimdFloatMisc                0      0.00%     14.63% # attempts to use FU when none available
+system.cpu.iq.fu_full::SimdFloatMult                0      0.00%     14.63% # attempts to use FU when none available
+system.cpu.iq.fu_full::SimdFloatMultAcc             0      0.00%     14.63% # attempts to use FU when none available
+system.cpu.iq.fu_full::SimdFloatSqrt                0      0.00%     14.63% # attempts to use FU when none available
+system.cpu.iq.fu_full::MemRead               10153281     65.89%     80.52% # attempts to use FU when none available
+system.cpu.iq.fu_full::MemWrite               3001149     19.48%    100.00% # attempts to use FU when none available
 system.cpu.iq.fu_full::IprAccess                    0      0.00%    100.00% # attempts to use FU when none available
 system.cpu.iq.fu_full::InstPrefetch                 0      0.00%    100.00% # attempts to use FU when none available
-system.cpu.iq.FU_type_0::No_OpClass           2420122      0.13%      0.13% # Type of FU issued
-system.cpu.iq.FU_type_0::IntAlu            1274712167     66.31%     66.44% # Type of FU issued
-system.cpu.iq.FU_type_0::IntMult                    0      0.00%     66.44% # Type of FU issued
-system.cpu.iq.FU_type_0::IntDiv                     0      0.00%     66.44% # Type of FU issued
-system.cpu.iq.FU_type_0::FloatAdd                   5      0.00%     66.44% # Type of FU issued
-system.cpu.iq.FU_type_0::FloatCmp                   0      0.00%     66.44% # Type of FU issued
-system.cpu.iq.FU_type_0::FloatCvt                   0      0.00%     66.44% # Type of FU issued
-system.cpu.iq.FU_type_0::FloatMult                  0      0.00%     66.44% # Type of FU issued
-system.cpu.iq.FU_type_0::FloatDiv                   0      0.00%     66.44% # Type of FU issued
-system.cpu.iq.FU_type_0::FloatSqrt                  0      0.00%     66.44% # Type of FU issued
-system.cpu.iq.FU_type_0::SimdAdd                    0      0.00%     66.44% # Type of FU issued
-system.cpu.iq.FU_type_0::SimdAddAcc                 0      0.00%     66.44% # Type of FU issued
-system.cpu.iq.FU_type_0::SimdAlu                    0      0.00%     66.44% # Type of FU issued
-system.cpu.iq.FU_type_0::SimdCmp                    0      0.00%     66.44% # Type of FU issued
-system.cpu.iq.FU_type_0::SimdCvt                    0      0.00%     66.44% # Type of FU issued
-system.cpu.iq.FU_type_0::SimdMisc                   0      0.00%     66.44% # Type of FU issued
-system.cpu.iq.FU_type_0::SimdMult                   0      0.00%     66.44% # Type of FU issued
-system.cpu.iq.FU_type_0::SimdMultAcc                0      0.00%     66.44% # Type of FU issued
-system.cpu.iq.FU_type_0::SimdShift                  0      0.00%     66.44% # Type of FU issued
-system.cpu.iq.FU_type_0::SimdShiftAcc               0      0.00%     66.44% # Type of FU issued
-system.cpu.iq.FU_type_0::SimdSqrt                   0      0.00%     66.44% # Type of FU issued
-system.cpu.iq.FU_type_0::SimdFloatAdd               0      0.00%     66.44% # Type of FU issued
-system.cpu.iq.FU_type_0::SimdFloatAlu               0      0.00%     66.44% # Type of FU issued
-system.cpu.iq.FU_type_0::SimdFloatCmp               0      0.00%     66.44% # Type of FU issued
-system.cpu.iq.FU_type_0::SimdFloatCvt               0      0.00%     66.44% # Type of FU issued
-system.cpu.iq.FU_type_0::SimdFloatDiv               0      0.00%     66.44% # Type of FU issued
-system.cpu.iq.FU_type_0::SimdFloatMisc              0      0.00%     66.44% # Type of FU issued
-system.cpu.iq.FU_type_0::SimdFloatMult              0      0.00%     66.44% # Type of FU issued
-system.cpu.iq.FU_type_0::SimdFloatMultAcc            0      0.00%     66.44% # Type of FU issued
-system.cpu.iq.FU_type_0::SimdFloatSqrt              0      0.00%     66.44% # Type of FU issued
-system.cpu.iq.FU_type_0::MemRead            463703127     24.12%     90.56% # Type of FU issued
-system.cpu.iq.FU_type_0::MemWrite           181534884      9.44%    100.00% # Type of FU issued
+system.cpu.iq.FU_type_0::No_OpClass           2493580      0.13%      0.13% # Type of FU issued
+system.cpu.iq.FU_type_0::IntAlu            1273165358     66.30%     66.43% # Type of FU issued
+system.cpu.iq.FU_type_0::IntMult                    0      0.00%     66.43% # Type of FU issued
+system.cpu.iq.FU_type_0::IntDiv                     0      0.00%     66.43% # Type of FU issued
+system.cpu.iq.FU_type_0::FloatAdd                   0      0.00%     66.43% # Type of FU issued
+system.cpu.iq.FU_type_0::FloatCmp                   0      0.00%     66.43% # Type of FU issued
+system.cpu.iq.FU_type_0::FloatCvt                   0      0.00%     66.43% # Type of FU issued
+system.cpu.iq.FU_type_0::FloatMult                  0      0.00%     66.43% # Type of FU issued
+system.cpu.iq.FU_type_0::FloatDiv                   0      0.00%     66.43% # Type of FU issued
+system.cpu.iq.FU_type_0::FloatSqrt                  0      0.00%     66.43% # Type of FU issued
+system.cpu.iq.FU_type_0::SimdAdd                    0      0.00%     66.43% # Type of FU issued
+system.cpu.iq.FU_type_0::SimdAddAcc                 0      0.00%     66.43% # Type of FU issued
+system.cpu.iq.FU_type_0::SimdAlu                    0      0.00%     66.43% # Type of FU issued
+system.cpu.iq.FU_type_0::SimdCmp                    0      0.00%     66.43% # Type of FU issued
+system.cpu.iq.FU_type_0::SimdCvt                    0      0.00%     66.43% # Type of FU issued
+system.cpu.iq.FU_type_0::SimdMisc                   0      0.00%     66.43% # Type of FU issued
+system.cpu.iq.FU_type_0::SimdMult                   0      0.00%     66.43% # Type of FU issued
+system.cpu.iq.FU_type_0::SimdMultAcc                0      0.00%     66.43% # Type of FU issued
+system.cpu.iq.FU_type_0::SimdShift                  0      0.00%     66.43% # Type of FU issued
+system.cpu.iq.FU_type_0::SimdShiftAcc               0      0.00%     66.43% # Type of FU issued
+system.cpu.iq.FU_type_0::SimdSqrt                   0      0.00%     66.43% # Type of FU issued
+system.cpu.iq.FU_type_0::SimdFloatAdd               0      0.00%     66.43% # Type of FU issued
+system.cpu.iq.FU_type_0::SimdFloatAlu               0      0.00%     66.43% # Type of FU issued
+system.cpu.iq.FU_type_0::SimdFloatCmp               0      0.00%     66.43% # Type of FU issued
+system.cpu.iq.FU_type_0::SimdFloatCvt               0      0.00%     66.43% # Type of FU issued
+system.cpu.iq.FU_type_0::SimdFloatDiv               0      0.00%     66.43% # Type of FU issued
+system.cpu.iq.FU_type_0::SimdFloatMisc              0      0.00%     66.43% # Type of FU issued
+system.cpu.iq.FU_type_0::SimdFloatMult              0      0.00%     66.43% # Type of FU issued
+system.cpu.iq.FU_type_0::SimdFloatMultAcc            0      0.00%     66.43% # Type of FU issued
+system.cpu.iq.FU_type_0::SimdFloatSqrt              0      0.00%     66.43% # Type of FU issued
+system.cpu.iq.FU_type_0::MemRead            463198530     24.12%     90.55% # Type of FU issued
+system.cpu.iq.FU_type_0::MemWrite           181466860      9.45%    100.00% # Type of FU issued
 system.cpu.iq.FU_type_0::IprAccess                  0      0.00%    100.00% # Type of FU issued
 system.cpu.iq.FU_type_0::InstPrefetch               0      0.00%    100.00% # Type of FU issued
-system.cpu.iq.FU_type_0::total             1922370305                       # Type of FU issued
-system.cpu.iq.rate                           1.946064                       # Inst issue rate
-system.cpu.iq.fu_busy_cnt                    15380828                       # FU busy when requested
-system.cpu.iq.fu_busy_rate                   0.008001                       # FU busy rate (busy events/executed inst)
-system.cpu.iq.int_inst_queue_reads         4825675637                       # Number of integer instruction queue reads
-system.cpu.iq.int_inst_queue_writes        3042139517                       # Number of integer instruction queue writes
-system.cpu.iq.int_inst_queue_wakeup_accesses   1874661917                       # Number of integer instruction queue wakeup accesses
-system.cpu.iq.fp_inst_queue_reads                4905                       # Number of floating instruction queue reads
-system.cpu.iq.fp_inst_queue_writes              81824                       # Number of floating instruction queue writes
-system.cpu.iq.fp_inst_queue_wakeup_accesses          136                       # Number of floating instruction queue wakeup accesses
-system.cpu.iq.int_alu_accesses             1935329448                       # Number of integer alu accesses
-system.cpu.iq.fp_alu_accesses                    1563                       # Number of floating point alu accesses
-system.cpu.iew.lsq.thread0.forwLoads        158391521                       # Number of loads that had data forwarded from stores
+system.cpu.iq.FU_type_0::total             1920324328                       # Type of FU issued
+system.cpu.iq.rate                           1.963531                       # Inst issue rate
+system.cpu.iq.fu_busy_cnt                    15408493                       # FU busy when requested
+system.cpu.iq.fu_busy_rate                   0.008024                       # FU busy rate (busy events/executed inst)
+system.cpu.iq.int_inst_queue_reads         4817321768                       # Number of integer instruction queue reads
+system.cpu.iq.int_inst_queue_writes        3023912415                       # Number of integer instruction queue writes
+system.cpu.iq.int_inst_queue_wakeup_accesses   1872800388                       # Number of integer instruction queue wakeup accesses
+system.cpu.iq.fp_inst_queue_reads                6087                       # Number of floating instruction queue reads
+system.cpu.iq.fp_inst_queue_writes             152738                       # Number of floating instruction queue writes
+system.cpu.iq.fp_inst_queue_wakeup_accesses          154                       # Number of floating instruction queue wakeup accesses
+system.cpu.iq.int_alu_accesses             1933237228                       # Number of integer alu accesses
+system.cpu.iq.fp_alu_accesses                    2013                       # Number of floating point alu accesses
+system.cpu.iew.lsq.thread0.forwLoads        171308750                       # Number of loads that had data forwarded from stores
 system.cpu.iew.lsq.thread0.invAddrLoads             0                       # Number of loads ignored due to an invalid address
-system.cpu.iew.lsq.thread0.squashedLoads    193777072                       # Number of loads squashed
-system.cpu.iew.lsq.thread0.ignoredResponses       372742                       # Number of memory responses ignored because the instruction is squashed
-system.cpu.iew.lsq.thread0.memOrderViolation       283642                       # Number of memory ordering violations
-system.cpu.iew.lsq.thread0.squashedStores     77371112                       # Number of stores squashed
+system.cpu.iew.lsq.thread0.squashedLoads    191418787                       # Number of loads squashed
+system.cpu.iew.lsq.thread0.ignoredResponses       428547                       # Number of memory responses ignored because the instruction is squashed
+system.cpu.iew.lsq.thread0.memOrderViolation       281164                       # Number of memory ordering violations
+system.cpu.iew.lsq.thread0.squashedStores     76573878                       # Number of stores squashed
 system.cpu.iew.lsq.thread0.invAddrSwpfs             0                       # Number of software prefetches ignored due to an invalid address
 system.cpu.iew.lsq.thread0.blockedLoads             0                       # Number of blocked loads due to partial load-store forwarding
-system.cpu.iew.lsq.thread0.rescheduledLoads         2379                       # Number of loads that were rescheduled
-system.cpu.iew.lsq.thread0.cacheBlocked            25                       # Number of times an access to memory failed due to the cache being blocked
+system.cpu.iew.lsq.thread0.rescheduledLoads         6486                       # Number of loads that were rescheduled
+system.cpu.iew.lsq.thread0.cacheBlocked             8                       # Number of times an access to memory failed due to the cache being blocked
 system.cpu.iew.iewIdleCycles                        0                       # Number of cycles IEW is idle
-system.cpu.iew.iewSquashCycles              103144089                       # Number of cycles IEW is squashing
-system.cpu.iew.iewBlockCycles                 9045659                       # Number of cycles IEW is blocking
-system.cpu.iew.iewUnblockCycles               1404502                       # Number of cycles IEW is unblocking
-system.cpu.iew.iewDispatchedInsts          2286721574                       # Number of instructions dispatched to IQ
-system.cpu.iew.iewDispSquashedInsts           1118432                       # Number of squashed instructions skipped by dispatch
-system.cpu.iew.iewDispLoadInsts             577879232                       # Number of dispatched load instructions
-system.cpu.iew.iewDispStoreInsts            226531297                       # Number of dispatched store instructions
-system.cpu.iew.iewDispNonSpecInsts               6081                       # Number of dispatched non-speculative instructions
-system.cpu.iew.iewIQFullEvents                1006586                       # Number of times the IQ has become full, causing a stall
-system.cpu.iew.iewLSQFullEvents                 29974                       # Number of times the LSQ has become full, causing a stall
-system.cpu.iew.memOrderViolationEvents         283642                       # Number of memory order violations
-system.cpu.iew.predictedTakenIncorrect       15693422                       # Number of branches that were predicted taken incorrectly
-system.cpu.iew.predictedNotTakenIncorrect      2344063                       # Number of branches that were predicted not taken incorrectly
-system.cpu.iew.branchMispredicts             18037485                       # Number of branch mispredicts detected at execute
-system.cpu.iew.iewExecutedInsts            1889150749                       # Number of executed instructions
-system.cpu.iew.iewExecLoadInsts             454748002                       # Number of load instructions executed
-system.cpu.iew.iewExecSquashedInsts          33219556                       # Number of squashed instructions skipped in execute
+system.cpu.iew.iewSquashCycles              101981770                       # Number of cycles IEW is squashing
+system.cpu.iew.iewBlockCycles                 7663639                       # Number of cycles IEW is blocking
+system.cpu.iew.iewUnblockCycles               1191899                       # Number of cycles IEW is unblocking
+system.cpu.iew.iewDispatchedInsts          2277641770                       # Number of instructions dispatched to IQ
+system.cpu.iew.iewDispSquashedInsts           1232812                       # Number of squashed instructions skipped by dispatch
+system.cpu.iew.iewDispLoadInsts             575520947                       # Number of dispatched load instructions
+system.cpu.iew.iewDispStoreInsts            225734063                       # Number of dispatched store instructions
+system.cpu.iew.iewDispNonSpecInsts               6109                       # Number of dispatched non-speculative instructions
+system.cpu.iew.iewIQFullEvents                 836752                       # Number of times the IQ has become full, causing a stall
+system.cpu.iew.iewLSQFullEvents                 17253                       # Number of times the LSQ has become full, causing a stall
+system.cpu.iew.memOrderViolationEvents         281164                       # Number of memory order violations
+system.cpu.iew.predictedTakenIncorrect       15662112                       # Number of branches that were predicted taken incorrectly
+system.cpu.iew.predictedNotTakenIncorrect      2402353                       # Number of branches that were predicted not taken incorrectly
+system.cpu.iew.branchMispredicts             18064465                       # Number of branch mispredicts detected at execute
+system.cpu.iew.iewExecutedInsts            1886684972                       # Number of executed instructions
+system.cpu.iew.iewExecLoadInsts             454230068                       # Number of load instructions executed
+system.cpu.iew.iewExecSquashedInsts          33639356                       # Number of squashed instructions skipped in execute
 system.cpu.iew.exec_swp                             0                       # number of swp insts executed
 system.cpu.iew.exec_nop                             0                       # number of nop insts executed
-system.cpu.iew.exec_refs                    629271939                       # number of memory reference insts executed
-system.cpu.iew.exec_branches                176719729                       # Number of branches executed
-system.cpu.iew.exec_stores                  174523937                       # Number of stores executed
-system.cpu.iew.exec_rate                     1.912435                       # Inst execution rate
-system.cpu.iew.wb_sent                     1882531239                       # cumulative count of insts sent to commit
-system.cpu.iew.wb_count                    1874662053                       # cumulative count of insts written-back
-system.cpu.iew.wb_producers                1440606287                       # num instructions producing a value
-system.cpu.iew.wb_consumers                2134778201                       # num instructions consuming a value
+system.cpu.iew.exec_refs                    628354292                       # number of memory reference insts executed
+system.cpu.iew.exec_branches                176563619                       # Number of branches executed
+system.cpu.iew.exec_stores                  174124224                       # Number of stores executed
+system.cpu.iew.exec_rate                     1.929135                       # Inst execution rate
+system.cpu.iew.wb_sent                     1880378728                       # cumulative count of insts sent to commit
+system.cpu.iew.wb_count                    1872800542                       # cumulative count of insts written-back
+system.cpu.iew.wb_producers                1438142804                       # num instructions producing a value
+system.cpu.iew.wb_consumers                2128029574                       # num instructions consuming a value
 system.cpu.iew.wb_penalized                         0                       # number of instrctions required to write to 'other' IQ
-system.cpu.iew.wb_rate                       1.897768                       # insts written-back per cycle
-system.cpu.iew.wb_fanout                     0.674827                       # average fanout of values written-back
+system.cpu.iew.wb_rate                       1.914938                       # insts written-back per cycle
+system.cpu.iew.wb_fanout                     0.675810                       # average fanout of values written-back
 system.cpu.iew.wb_penalized_rate                    0                       # fraction of instructions written-back that wrote to 'other' IQ
 system.cpu.commit.commitCommittedInsts     1528988756                       # The number of committed instructions
-system.cpu.commit.commitSquashedInsts       757743569                       # The number of squashed insts skipped by commit
+system.cpu.commit.commitSquashedInsts       748676946                       # The number of squashed insts skipped by commit
 system.cpu.commit.commitNonSpecStalls             553                       # The number of times commit has been forced to stall to communicate backwards
-system.cpu.commit.branchMispredicts          16604349                       # The number of times a branch was mispredicted
-system.cpu.commit.committed_per_cycle::samples    861108374                       # Number of insts commited each cycle
-system.cpu.commit.committed_per_cycle::mean     1.775605                       # Number of insts commited each cycle
-system.cpu.commit.committed_per_cycle::stdev     2.288022                       # Number of insts commited each cycle
+system.cpu.commit.branchMispredicts          16628282                       # The number of times a branch was mispredicted
+system.cpu.commit.committed_per_cycle::samples    857988064                       # Number of insts commited each cycle
+system.cpu.commit.committed_per_cycle::mean     1.782063                       # Number of insts commited each cycle
+system.cpu.commit.committed_per_cycle::stdev     2.285478                       # Number of insts commited each cycle
 system.cpu.commit.committed_per_cycle::underflows            0      0.00%      0.00% # Number of insts commited each cycle
-system.cpu.commit.committed_per_cycle::0    338327816     39.29%     39.29% # Number of insts commited each cycle
-system.cpu.commit.committed_per_cycle::1    210551706     24.45%     63.74% # Number of insts commited each cycle
-system.cpu.commit.committed_per_cycle::2     75360819      8.75%     72.49% # Number of insts commited each cycle
-system.cpu.commit.committed_per_cycle::3     92562974     10.75%     83.24% # Number of insts commited each cycle
-system.cpu.commit.committed_per_cycle::4     34054041      3.95%     87.20% # Number of insts commited each cycle
-system.cpu.commit.committed_per_cycle::5     27955182      3.25%     90.44% # Number of insts commited each cycle
-system.cpu.commit.committed_per_cycle::6     16032820      1.86%     92.30% # Number of insts commited each cycle
-system.cpu.commit.committed_per_cycle::7     12266632      1.42%     93.73% # Number of insts commited each cycle
-system.cpu.commit.committed_per_cycle::8     53996384      6.27%    100.00% # Number of insts commited each cycle
+system.cpu.commit.committed_per_cycle::0    333514129     38.87%     38.87% # Number of insts commited each cycle
+system.cpu.commit.committed_per_cycle::1    211603589     24.66%     63.53% # Number of insts commited each cycle
+system.cpu.commit.committed_per_cycle::2     76333139      8.90%     72.43% # Number of insts commited each cycle
+system.cpu.commit.committed_per_cycle::3     92892872     10.83%     83.26% # Number of insts commited each cycle
+system.cpu.commit.committed_per_cycle::4     33741100      3.93%     87.19% # Number of insts commited each cycle
+system.cpu.commit.committed_per_cycle::5     28402540      3.31%     90.50% # Number of insts commited each cycle
+system.cpu.commit.committed_per_cycle::6     15787299      1.84%     92.34% # Number of insts commited each cycle
+system.cpu.commit.committed_per_cycle::7     11367789      1.32%     93.67% # Number of insts commited each cycle
+system.cpu.commit.committed_per_cycle::8     54345607      6.33%    100.00% # Number of insts commited each cycle
 system.cpu.commit.committed_per_cycle::overflows            0      0.00%    100.00% # Number of insts commited each cycle
 system.cpu.commit.committed_per_cycle::min_value            0                       # Number of insts commited each cycle
 system.cpu.commit.committed_per_cycle::max_value            8                       # Number of insts commited each cycle
-system.cpu.commit.committed_per_cycle::total    861108374                       # Number of insts commited each cycle
+system.cpu.commit.committed_per_cycle::total    857988064                       # Number of insts commited each cycle
 system.cpu.commit.count                    1528988756                       # Number of instructions committed
 system.cpu.commit.swp_count                         0                       # Number of s/w prefetches committed
 system.cpu.commit.refs                      533262345                       # Number of memory references committed
@@ -268,49 +267,48 @@
 system.cpu.commit.fp_insts                          0                       # Number of committed floating point instructions.
 system.cpu.commit.int_insts                1528317614                       # Number of committed integer instructions.
 system.cpu.commit.function_calls                    0                       # Number of function calls committed.
-system.cpu.commit.bw_lim_events              53996384                       # number cycles where commit BW limit reached
+system.cpu.commit.bw_lim_events              54345607                       # number cycles where commit BW limit reached
 system.cpu.commit.bw_limited                        0                       # number of insts not committed due to BW limits
-system.cpu.rob.rob_reads                   3093844315                       # The number of ROB reads
-system.cpu.rob.rob_writes                  4676786954                       # The number of ROB writes
-system.cpu.timesIdled                          606516                       # Number of times that the entire CPU went into an idle state and unscheduled itself
-system.cpu.idleCycles                        23572110                       # Total number of cycles that the CPU has spent unscheduled due to idling
+system.cpu.rob.rob_reads                   3081308159                       # The number of ROB reads
+system.cpu.rob.rob_writes                  4657476889                       # The number of ROB writes
+system.cpu.timesIdled                          418960                       # Number of times that the entire CPU went into an idle state and unscheduled itself
+system.cpu.idleCycles                        18025695                       # Total number of cycles that the CPU has spent unscheduled due to idling
 system.cpu.committedInsts                  1528988756                       # Number of Instructions Simulated
 system.cpu.committedInsts_total            1528988756                       # Number of Instructions Simulated
-system.cpu.cpi                               0.646064                       # CPI: Cycles Per Instruction
-system.cpu.cpi_total                         0.646064                       # CPI: Total CPI of All Threads
-system.cpu.ipc                               1.547834                       # IPC: Instructions Per Cycle
-system.cpu.ipc_total                         1.547834                       # IPC: Total IPC of All Threads
-system.cpu.int_regfile_reads               3179044858                       # number of integer regfile reads
-system.cpu.int_regfile_writes              1744829680                       # number of integer regfile writes
-system.cpu.fp_regfile_reads                       145                       # number of floating regfile reads
-system.cpu.fp_regfile_writes                        5                       # number of floating regfile writes
-system.cpu.misc_regfile_reads              1039286160                       # number of misc regfile reads
-system.cpu.icache.replacements                  10045                       # number of replacements
-system.cpu.icache.tagsinuse                976.337758                       # Cycle average of tags in use
-system.cpu.icache.total_refs                194480398                       # Total number of references to valid blocks.
-system.cpu.icache.sampled_refs                  11548                       # Sample count of references to valid blocks.
-system.cpu.icache.avg_refs               16841.045895                       # Average number of references to valid blocks.
+system.cpu.cpi                               0.639636                       # CPI: Cycles Per Instruction
+system.cpu.cpi_total                         0.639636                       # CPI: Total CPI of All Threads
+system.cpu.ipc                               1.563390                       # IPC: Instructions Per Cycle
+system.cpu.ipc_total                         1.563390                       # IPC: Total IPC of All Threads
+system.cpu.int_regfile_reads               3178059548                       # number of integer regfile reads
+system.cpu.int_regfile_writes              1743141344                       # number of integer regfile writes
+system.cpu.fp_regfile_reads                       155                       # number of floating regfile reads
+system.cpu.misc_regfile_reads              1037170422                       # number of misc regfile reads
+system.cpu.icache.replacements                  10067                       # number of replacements
+system.cpu.icache.tagsinuse                971.911936                       # Cycle average of tags in use
+system.cpu.icache.total_refs                193916703                       # Total number of references to valid blocks.
+system.cpu.icache.sampled_refs                  11565                       # Sample count of references to valid blocks.
+system.cpu.icache.avg_refs               16767.548898                       # Average number of references to valid blocks.
 system.cpu.icache.warmup_cycle                      0                       # Cycle when the warmup percentage was hit.
-system.cpu.icache.occ_blocks::0            976.337758                       # Average occupied blocks per context
-system.cpu.icache.occ_percent::0             0.476727                       # Average percentage of cache occupancy
-system.cpu.icache.ReadReq_hits              194486608                       # number of ReadReq hits
-system.cpu.icache.demand_hits               194486608                       # number of demand (read+write) hits
-system.cpu.icache.overall_hits              194486608                       # number of overall hits
-system.cpu.icache.ReadReq_misses               223766                       # number of ReadReq misses
-system.cpu.icache.demand_misses                223766                       # number of demand (read+write) misses
-system.cpu.icache.overall_misses               223766                       # number of overall misses
-system.cpu.icache.ReadReq_miss_latency     1539723000                       # number of ReadReq miss cycles
-system.cpu.icache.demand_miss_latency      1539723000                       # number of demand (read+write) miss cycles
-system.cpu.icache.overall_miss_latency     1539723000                       # number of overall miss cycles
-system.cpu.icache.ReadReq_accesses          194710374                       # number of ReadReq accesses(hits+misses)
-system.cpu.icache.demand_accesses           194710374                       # number of demand (read+write) accesses
-system.cpu.icache.overall_accesses          194710374                       # number of overall (read+write) accesses
-system.cpu.icache.ReadReq_miss_rate          0.001149                       # miss rate for ReadReq accesses
-system.cpu.icache.demand_miss_rate           0.001149                       # miss rate for demand accesses
-system.cpu.icache.overall_miss_rate          0.001149                       # miss rate for overall accesses
-system.cpu.icache.ReadReq_avg_miss_latency  6880.951530                       # average ReadReq miss latency
-system.cpu.icache.demand_avg_miss_latency  6880.951530                       # average overall miss latency
-system.cpu.icache.overall_avg_miss_latency  6880.951530                       # average overall miss latency
+system.cpu.icache.occ_blocks::0            971.911936                       # Average occupied blocks per context
+system.cpu.icache.occ_percent::0             0.474566                       # Average percentage of cache occupancy
+system.cpu.icache.ReadReq_hits              193923334                       # number of ReadReq hits
+system.cpu.icache.demand_hits               193923334                       # number of demand (read+write) hits
+system.cpu.icache.overall_hits              193923334                       # number of overall hits
+system.cpu.icache.ReadReq_misses               235067                       # number of ReadReq misses
+system.cpu.icache.demand_misses                235067                       # number of demand (read+write) misses
+system.cpu.icache.overall_misses               235067                       # number of overall misses
+system.cpu.icache.ReadReq_miss_latency     1701123000                       # number of ReadReq miss cycles
+system.cpu.icache.demand_miss_latency      1701123000                       # number of demand (read+write) miss cycles
+system.cpu.icache.overall_miss_latency     1701123000                       # number of overall miss cycles
+system.cpu.icache.ReadReq_accesses          194158401                       # number of ReadReq accesses(hits+misses)
+system.cpu.icache.demand_accesses           194158401                       # number of demand (read+write) accesses
+system.cpu.icache.overall_accesses          194158401                       # number of overall (read+write) accesses
+system.cpu.icache.ReadReq_miss_rate          0.001211                       # miss rate for ReadReq accesses
+system.cpu.icache.demand_miss_rate           0.001211                       # miss rate for demand accesses
+system.cpu.icache.overall_miss_rate          0.001211                       # miss rate for overall accesses
+system.cpu.icache.ReadReq_avg_miss_latency  7236.758031                       # average ReadReq miss latency
+system.cpu.icache.demand_avg_miss_latency  7236.758031                       # average overall miss latency
+system.cpu.icache.overall_avg_miss_latency  7236.758031                       # average overall miss latency
 system.cpu.icache.blocked_cycles::no_mshrs            0                       # number of cycles access was blocked
 system.cpu.icache.blocked_cycles::no_targets            0                       # number of cycles access was blocked
 system.cpu.icache.blocked::no_mshrs                 0                       # number of cycles access was blocked
@@ -319,137 +317,137 @@
 system.cpu.icache.avg_blocked_cycles::no_targets     no_value                       # average number of cycles each access was blocked
 system.cpu.icache.fast_writes                       0                       # number of fast writes performed
 system.cpu.icache.cache_copies                      0                       # number of cache copies performed
-system.cpu.icache.writebacks                        6                       # number of writebacks
-system.cpu.icache.ReadReq_mshr_hits              2071                       # number of ReadReq MSHR hits
-system.cpu.icache.demand_mshr_hits               2071                       # number of demand (read+write) MSHR hits
-system.cpu.icache.overall_mshr_hits              2071                       # number of overall MSHR hits
-system.cpu.icache.ReadReq_mshr_misses          221695                       # number of ReadReq MSHR misses
-system.cpu.icache.demand_mshr_misses           221695                       # number of demand (read+write) MSHR misses
-system.cpu.icache.overall_mshr_misses          221695                       # number of overall MSHR misses
+system.cpu.icache.writebacks                        8                       # number of writebacks
+system.cpu.icache.ReadReq_mshr_hits              2036                       # number of ReadReq MSHR hits
+system.cpu.icache.demand_mshr_hits               2036                       # number of demand (read+write) MSHR hits
+system.cpu.icache.overall_mshr_hits              2036                       # number of overall MSHR hits
+system.cpu.icache.ReadReq_mshr_misses          233031                       # number of ReadReq MSHR misses
+system.cpu.icache.demand_mshr_misses           233031                       # number of demand (read+write) MSHR misses
+system.cpu.icache.overall_mshr_misses          233031                       # number of overall MSHR misses
 system.cpu.icache.overall_mshr_uncacheable_misses            0                       # number of overall MSHR uncacheable misses
-system.cpu.icache.ReadReq_mshr_miss_latency    824417000                       # number of ReadReq MSHR miss cycles
-system.cpu.icache.demand_mshr_miss_latency    824417000                       # number of demand (read+write) MSHR miss cycles
-system.cpu.icache.overall_mshr_miss_latency    824417000                       # number of overall MSHR miss cycles
+system.cpu.icache.ReadReq_mshr_miss_latency    952412000                       # number of ReadReq MSHR miss cycles
+system.cpu.icache.demand_mshr_miss_latency    952412000                       # number of demand (read+write) MSHR miss cycles
+system.cpu.icache.overall_mshr_miss_latency    952412000                       # number of overall MSHR miss cycles
 system.cpu.icache.overall_mshr_uncacheable_latency            0                       # number of overall MSHR uncacheable cycles
-system.cpu.icache.ReadReq_mshr_miss_rate     0.001139                       # mshr miss rate for ReadReq accesses
-system.cpu.icache.demand_mshr_miss_rate      0.001139                       # mshr miss rate for demand accesses
-system.cpu.icache.overall_mshr_miss_rate     0.001139                       # mshr miss rate for overall accesses
-system.cpu.icache.ReadReq_avg_mshr_miss_latency  3718.699114                       # average ReadReq mshr miss latency
-system.cpu.icache.demand_avg_mshr_miss_latency  3718.699114                       # average overall mshr miss latency
-system.cpu.icache.overall_avg_mshr_miss_latency  3718.699114                       # average overall mshr miss latency
+system.cpu.icache.ReadReq_mshr_miss_rate     0.001200                       # mshr miss rate for ReadReq accesses
+system.cpu.icache.demand_mshr_miss_rate      0.001200                       # mshr miss rate for demand accesses
+system.cpu.icache.overall_mshr_miss_rate     0.001200                       # mshr miss rate for overall accesses
+system.cpu.icache.ReadReq_avg_mshr_miss_latency  4087.061378                       # average ReadReq mshr miss latency
+system.cpu.icache.demand_avg_mshr_miss_latency  4087.061378                       # average overall mshr miss latency
+system.cpu.icache.overall_avg_mshr_miss_latency  4087.061378                       # average overall mshr miss latency
 system.cpu.icache.overall_avg_mshr_uncacheable_latency     no_value                       # average overall mshr uncacheable latency
 system.cpu.icache.mshr_cap_events                   0                       # number of times MSHR cap was activated
 system.cpu.icache.soft_prefetch_mshr_full            0                       # number of mshr full events for SW prefetching instrutions
 system.cpu.icache.no_allocate_misses                0                       # Number of misses that were no-allocate
-system.cpu.dcache.replacements                2527930                       # number of replacements
-system.cpu.dcache.tagsinuse               4087.566272                       # Cycle average of tags in use
-system.cpu.dcache.total_refs                440586260                       # Total number of references to valid blocks.
-system.cpu.dcache.sampled_refs                2532026                       # Sample count of references to valid blocks.
-system.cpu.dcache.avg_refs                 174.005425                       # Average number of references to valid blocks.
-system.cpu.dcache.warmup_cycle             2135798000                       # Cycle when the warmup percentage was hit.
-system.cpu.dcache.occ_blocks::0           4087.566272                       # Average occupied blocks per context
-system.cpu.dcache.occ_percent::0             0.997941                       # Average percentage of cache occupancy
-system.cpu.dcache.ReadReq_hits              291836002                       # number of ReadReq hits
-system.cpu.dcache.WriteReq_hits             147579227                       # number of WriteReq hits
-system.cpu.dcache.demand_hits               439415229                       # number of demand (read+write) hits
-system.cpu.dcache.overall_hits              439415229                       # number of overall hits
-system.cpu.dcache.ReadReq_misses              3119681                       # number of ReadReq misses
-system.cpu.dcache.WriteReq_misses             1580974                       # number of WriteReq misses
-system.cpu.dcache.demand_misses               4700655                       # number of demand (read+write) misses
-system.cpu.dcache.overall_misses              4700655                       # number of overall misses
-system.cpu.dcache.ReadReq_miss_latency    52079313500                       # number of ReadReq miss cycles
-system.cpu.dcache.WriteReq_miss_latency   37355392500                       # number of WriteReq miss cycles
-system.cpu.dcache.demand_miss_latency     89434706000                       # number of demand (read+write) miss cycles
-system.cpu.dcache.overall_miss_latency    89434706000                       # number of overall miss cycles
-system.cpu.dcache.ReadReq_accesses          294955683                       # number of ReadReq accesses(hits+misses)
+system.cpu.dcache.replacements                2529213                       # number of replacements
+system.cpu.dcache.tagsinuse               4087.436678                       # Cycle average of tags in use
+system.cpu.dcache.total_refs                427576950                       # Total number of references to valid blocks.
+system.cpu.dcache.sampled_refs                2533309                       # Sample count of references to valid blocks.
+system.cpu.dcache.avg_refs                 168.781996                       # Average number of references to valid blocks.
+system.cpu.dcache.warmup_cycle             2167021000                       # Cycle when the warmup percentage was hit.
+system.cpu.dcache.occ_blocks::0           4087.436678                       # Average occupied blocks per context
+system.cpu.dcache.occ_percent::0             0.997909                       # Average percentage of cache occupancy
+system.cpu.dcache.ReadReq_hits              278854362                       # number of ReadReq hits
+system.cpu.dcache.WriteReq_hits             148163093                       # number of WriteReq hits
+system.cpu.dcache.demand_hits               427017455                       # number of demand (read+write) hits
+system.cpu.dcache.overall_hits              427017455                       # number of overall hits
+system.cpu.dcache.ReadReq_misses              2666620                       # number of ReadReq misses
+system.cpu.dcache.WriteReq_misses              997108                       # number of WriteReq misses
+system.cpu.dcache.demand_misses               3663728                       # number of demand (read+write) misses
+system.cpu.dcache.overall_misses              3663728                       # number of overall misses
+system.cpu.dcache.ReadReq_miss_latency    39487606500                       # number of ReadReq miss cycles
+system.cpu.dcache.WriteReq_miss_latency   20600704500                       # number of WriteReq miss cycles
+system.cpu.dcache.demand_miss_latency     60088311000                       # number of demand (read+write) miss cycles
+system.cpu.dcache.overall_miss_latency    60088311000                       # number of overall miss cycles
+system.cpu.dcache.ReadReq_accesses          281520982                       # number of ReadReq accesses(hits+misses)
 system.cpu.dcache.WriteReq_accesses         149160201                       # number of WriteReq accesses(hits+misses)
-system.cpu.dcache.demand_accesses           444115884                       # number of demand (read+write) accesses
-system.cpu.dcache.overall_accesses          444115884                       # number of overall (read+write) accesses
-system.cpu.dcache.ReadReq_miss_rate          0.010577                       # miss rate for ReadReq accesses
-system.cpu.dcache.WriteReq_miss_rate         0.010599                       # miss rate for WriteReq accesses
-system.cpu.dcache.demand_miss_rate           0.010584                       # miss rate for demand accesses
-system.cpu.dcache.overall_miss_rate          0.010584                       # miss rate for overall accesses
-system.cpu.dcache.ReadReq_avg_miss_latency 16693.794494                       # average ReadReq miss latency
-system.cpu.dcache.WriteReq_avg_miss_latency 23628.087812                       # average WriteReq miss latency
-system.cpu.dcache.demand_avg_miss_latency 19026.009354                       # average overall miss latency
-system.cpu.dcache.overall_avg_miss_latency 19026.009354                       # average overall miss latency
+system.cpu.dcache.demand_accesses           430681183                       # number of demand (read+write) accesses
+system.cpu.dcache.overall_accesses          430681183                       # number of overall (read+write) accesses
+system.cpu.dcache.ReadReq_miss_rate          0.009472                       # miss rate for ReadReq accesses
+system.cpu.dcache.WriteReq_miss_rate         0.006685                       # miss rate for WriteReq accesses
+system.cpu.dcache.demand_miss_rate           0.008507                       # miss rate for demand accesses
+system.cpu.dcache.overall_miss_rate          0.008507                       # miss rate for overall accesses
+system.cpu.dcache.ReadReq_avg_miss_latency 14808.111579                       # average ReadReq miss latency
+system.cpu.dcache.WriteReq_avg_miss_latency 20660.454535                       # average WriteReq miss latency
+system.cpu.dcache.demand_avg_miss_latency 16400.865730                       # average overall miss latency
+system.cpu.dcache.overall_avg_miss_latency 16400.865730                       # average overall miss latency
 system.cpu.dcache.blocked_cycles::no_mshrs            0                       # number of cycles access was blocked
-system.cpu.dcache.blocked_cycles::no_targets        29000                       # number of cycles access was blocked
+system.cpu.dcache.blocked_cycles::no_targets            0                       # number of cycles access was blocked
 system.cpu.dcache.blocked::no_mshrs                 0                       # number of cycles access was blocked
-system.cpu.dcache.blocked::no_targets               2                       # number of cycles access was blocked
+system.cpu.dcache.blocked::no_targets               0                       # number of cycles access was blocked
 system.cpu.dcache.avg_blocked_cycles::no_mshrs     no_value                       # average number of cycles each access was blocked
-system.cpu.dcache.avg_blocked_cycles::no_targets        14500                       # average number of cycles each access was blocked
+system.cpu.dcache.avg_blocked_cycles::no_targets     no_value                       # average number of cycles each access was blocked
 system.cpu.dcache.fast_writes                       0                       # number of fast writes performed
 system.cpu.dcache.cache_copies                      0                       # number of cache copies performed
-system.cpu.dcache.writebacks                  2229595                       # number of writebacks
-system.cpu.dcache.ReadReq_mshr_hits           1359154                       # number of ReadReq MSHR hits
-system.cpu.dcache.WriteReq_mshr_hits           607660                       # number of WriteReq MSHR hits
-system.cpu.dcache.demand_mshr_hits            1966814                       # number of demand (read+write) MSHR hits
-system.cpu.dcache.overall_mshr_hits           1966814                       # number of overall MSHR hits
-system.cpu.dcache.ReadReq_mshr_misses         1760527                       # number of ReadReq MSHR misses
-system.cpu.dcache.WriteReq_mshr_misses         973314                       # number of WriteReq MSHR misses
-system.cpu.dcache.demand_mshr_misses          2733841                       # number of demand (read+write) MSHR misses
-system.cpu.dcache.overall_mshr_misses         2733841                       # number of overall MSHR misses
+system.cpu.dcache.writebacks                  2229973                       # number of writebacks
+system.cpu.dcache.ReadReq_mshr_hits            903774                       # number of ReadReq MSHR hits
+system.cpu.dcache.WriteReq_mshr_hits             5204                       # number of WriteReq MSHR hits
+system.cpu.dcache.demand_mshr_hits             908978                       # number of demand (read+write) MSHR hits
+system.cpu.dcache.overall_mshr_hits            908978                       # number of overall MSHR hits
+system.cpu.dcache.ReadReq_mshr_misses         1762846                       # number of ReadReq MSHR misses
+system.cpu.dcache.WriteReq_mshr_misses         991904                       # number of WriteReq MSHR misses
+system.cpu.dcache.demand_mshr_misses          2754750                       # number of demand (read+write) MSHR misses
+system.cpu.dcache.overall_mshr_misses         2754750                       # number of overall MSHR misses
 system.cpu.dcache.overall_mshr_uncacheable_misses            0                       # number of overall MSHR uncacheable misses
-system.cpu.dcache.ReadReq_mshr_miss_latency  14908482500                       # number of ReadReq MSHR miss cycles
-system.cpu.dcache.WriteReq_mshr_miss_latency  17169522000                       # number of WriteReq MSHR miss cycles
-system.cpu.dcache.demand_mshr_miss_latency  32078004500                       # number of demand (read+write) MSHR miss cycles
-system.cpu.dcache.overall_mshr_miss_latency  32078004500                       # number of overall MSHR miss cycles
+system.cpu.dcache.ReadReq_mshr_miss_latency  14963544500                       # number of ReadReq MSHR miss cycles
+system.cpu.dcache.WriteReq_mshr_miss_latency  17553990000                       # number of WriteReq MSHR miss cycles
+system.cpu.dcache.demand_mshr_miss_latency  32517534500                       # number of demand (read+write) MSHR miss cycles
+system.cpu.dcache.overall_mshr_miss_latency  32517534500                       # number of overall MSHR miss cycles
 system.cpu.dcache.overall_mshr_uncacheable_latency            0                       # number of overall MSHR uncacheable cycles
-system.cpu.dcache.ReadReq_mshr_miss_rate     0.005969                       # mshr miss rate for ReadReq accesses
-system.cpu.dcache.WriteReq_mshr_miss_rate     0.006525                       # mshr miss rate for WriteReq accesses
-system.cpu.dcache.demand_mshr_miss_rate      0.006156                       # mshr miss rate for demand accesses
-system.cpu.dcache.overall_mshr_miss_rate     0.006156                       # mshr miss rate for overall accesses
-system.cpu.dcache.ReadReq_avg_mshr_miss_latency  8468.193047                       # average ReadReq mshr miss latency
-system.cpu.dcache.WriteReq_avg_mshr_miss_latency 17640.270252                       # average WriteReq mshr miss latency
-system.cpu.dcache.demand_avg_mshr_miss_latency 11733.675989                       # average overall mshr miss latency
-system.cpu.dcache.overall_avg_mshr_miss_latency 11733.675989                       # average overall mshr miss latency
+system.cpu.dcache.ReadReq_mshr_miss_rate     0.006262                       # mshr miss rate for ReadReq accesses
+system.cpu.dcache.WriteReq_mshr_miss_rate     0.006650                       # mshr miss rate for WriteReq accesses
+system.cpu.dcache.demand_mshr_miss_rate      0.006396                       # mshr miss rate for demand accesses
+system.cpu.dcache.overall_mshr_miss_rate     0.006396                       # mshr miss rate for overall accesses
+system.cpu.dcache.ReadReq_avg_mshr_miss_latency  8488.287973                       # average ReadReq mshr miss latency
+system.cpu.dcache.WriteReq_avg_mshr_miss_latency 17697.267074                       # average WriteReq mshr miss latency
+system.cpu.dcache.demand_avg_mshr_miss_latency 11804.168981                       # average overall mshr miss latency
+system.cpu.dcache.overall_avg_mshr_miss_latency 11804.168981                       # average overall mshr miss latency
 system.cpu.dcache.overall_avg_mshr_uncacheable_latency     no_value                       # average overall mshr uncacheable latency
 system.cpu.dcache.mshr_cap_events                   0                       # number of times MSHR cap was activated
 system.cpu.dcache.soft_prefetch_mshr_full            0                       # number of mshr full events for SW prefetching instrutions
 system.cpu.dcache.no_allocate_misses                0                       # Number of misses that were no-allocate
-system.cpu.l2cache.replacements                574945                       # number of replacements
-system.cpu.l2cache.tagsinuse             21597.257673                       # Cycle average of tags in use
-system.cpu.l2cache.total_refs                 3194359                       # Total number of references to valid blocks.
-system.cpu.l2cache.sampled_refs                594122                       # Sample count of references to valid blocks.
-system.cpu.l2cache.avg_refs                  5.376604                       # Average number of references to valid blocks.
-system.cpu.l2cache.warmup_cycle          271429089000                       # Cycle when the warmup percentage was hit.
-system.cpu.l2cache.occ_blocks::0          7797.131828                       # Average occupied blocks per context
-system.cpu.l2cache.occ_blocks::1         13800.125845                       # Average occupied blocks per context
-system.cpu.l2cache.occ_percent::0            0.237950                       # Average percentage of cache occupancy
-system.cpu.l2cache.occ_percent::1            0.421146                       # Average percentage of cache occupancy
-system.cpu.l2cache.ReadReq_hits               1433279                       # number of ReadReq hits
-system.cpu.l2cache.Writeback_hits             2229601                       # number of Writeback hits
-system.cpu.l2cache.UpgradeReq_hits               1240                       # number of UpgradeReq hits
-system.cpu.l2cache.ReadExReq_hits              524400                       # number of ReadExReq hits
-system.cpu.l2cache.demand_hits                1957679                       # number of demand (read+write) hits
-system.cpu.l2cache.overall_hits               1957679                       # number of overall hits
-system.cpu.l2cache.ReadReq_misses              338611                       # number of ReadReq misses
-system.cpu.l2cache.UpgradeReq_misses           208876                       # number of UpgradeReq misses
-system.cpu.l2cache.ReadExReq_misses            247152                       # number of ReadExReq misses
-system.cpu.l2cache.demand_misses               585763                       # number of demand (read+write) misses
-system.cpu.l2cache.overall_misses              585763                       # number of overall misses
-system.cpu.l2cache.ReadReq_miss_latency   11564612500                       # number of ReadReq miss cycles
-system.cpu.l2cache.UpgradeReq_miss_latency      9756500                       # number of UpgradeReq miss cycles
-system.cpu.l2cache.ReadExReq_miss_latency   8478074500                       # number of ReadExReq miss cycles
-system.cpu.l2cache.demand_miss_latency    20042687000                       # number of demand (read+write) miss cycles
-system.cpu.l2cache.overall_miss_latency   20042687000                       # number of overall miss cycles
-system.cpu.l2cache.ReadReq_accesses           1771890                       # number of ReadReq accesses(hits+misses)
-system.cpu.l2cache.Writeback_accesses         2229601                       # number of Writeback accesses(hits+misses)
-system.cpu.l2cache.UpgradeReq_accesses         210116                       # number of UpgradeReq accesses(hits+misses)
-system.cpu.l2cache.ReadExReq_accesses          771552                       # number of ReadExReq accesses(hits+misses)
-system.cpu.l2cache.demand_accesses            2543442                       # number of demand (read+write) accesses
-system.cpu.l2cache.overall_accesses           2543442                       # number of overall (read+write) accesses
-system.cpu.l2cache.ReadReq_miss_rate         0.191102                       # miss rate for ReadReq accesses
-system.cpu.l2cache.UpgradeReq_miss_rate      0.994098                       # miss rate for UpgradeReq accesses
-system.cpu.l2cache.ReadExReq_miss_rate       0.320331                       # miss rate for ReadExReq accesses
-system.cpu.l2cache.demand_miss_rate          0.230303                       # miss rate for demand accesses
-system.cpu.l2cache.overall_miss_rate         0.230303                       # miss rate for overall accesses
-system.cpu.l2cache.ReadReq_avg_miss_latency 34153.091601                       # average ReadReq miss latency
-system.cpu.l2cache.UpgradeReq_avg_miss_latency    46.709531                       # average UpgradeReq miss latency
-system.cpu.l2cache.ReadExReq_avg_miss_latency 34303.078672                       # average ReadExReq miss latency
-system.cpu.l2cache.demand_avg_miss_latency 34216.375906                       # average overall miss latency
-system.cpu.l2cache.overall_avg_miss_latency 34216.375906                       # average overall miss latency
+system.cpu.l2cache.replacements                575697                       # number of replacements
+system.cpu.l2cache.tagsinuse             21610.714484                       # Cycle average of tags in use
+system.cpu.l2cache.total_refs                 3195541                       # Total number of references to valid blocks.
+system.cpu.l2cache.sampled_refs                594856                       # Sample count of references to valid blocks.
+system.cpu.l2cache.avg_refs                  5.371957                       # Average number of references to valid blocks.
+system.cpu.l2cache.warmup_cycle          269628029000                       # Cycle when the warmup percentage was hit.
+system.cpu.l2cache.occ_blocks::0          7828.943593                       # Average occupied blocks per context
+system.cpu.l2cache.occ_blocks::1         13781.770891                       # Average occupied blocks per context
+system.cpu.l2cache.occ_percent::0            0.238920                       # Average percentage of cache occupancy
+system.cpu.l2cache.occ_percent::1            0.420586                       # Average percentage of cache occupancy
+system.cpu.l2cache.ReadReq_hits               1434292                       # number of ReadReq hits
+system.cpu.l2cache.Writeback_hits             2229981                       # number of Writeback hits
+system.cpu.l2cache.UpgradeReq_hits               1300                       # number of UpgradeReq hits
+system.cpu.l2cache.ReadExReq_hits              523974                       # number of ReadExReq hits
+system.cpu.l2cache.demand_hits                1958266                       # number of demand (read+write) hits
+system.cpu.l2cache.overall_hits               1958266                       # number of overall hits
+system.cpu.l2cache.ReadReq_misses              339366                       # number of ReadReq misses
+system.cpu.l2cache.UpgradeReq_misses           220134                       # number of UpgradeReq misses
+system.cpu.l2cache.ReadExReq_misses            247116                       # number of ReadExReq misses
+system.cpu.l2cache.demand_misses               586482                       # number of demand (read+write) misses
+system.cpu.l2cache.overall_misses              586482                       # number of overall misses
+system.cpu.l2cache.ReadReq_miss_latency   11591670000                       # number of ReadReq miss cycles
+system.cpu.l2cache.UpgradeReq_miss_latency      9750500                       # number of UpgradeReq miss cycles
+system.cpu.l2cache.ReadExReq_miss_latency   8467686500                       # number of ReadExReq miss cycles
+system.cpu.l2cache.demand_miss_latency    20059356500                       # number of demand (read+write) miss cycles
+system.cpu.l2cache.overall_miss_latency   20059356500                       # number of overall miss cycles
+system.cpu.l2cache.ReadReq_accesses           1773658                       # number of ReadReq accesses(hits+misses)
+system.cpu.l2cache.Writeback_accesses         2229981                       # number of Writeback accesses(hits+misses)
+system.cpu.l2cache.UpgradeReq_accesses         221434                       # number of UpgradeReq accesses(hits+misses)
+system.cpu.l2cache.ReadExReq_accesses          771090                       # number of ReadExReq accesses(hits+misses)
+system.cpu.l2cache.demand_accesses            2544748                       # number of demand (read+write) accesses
+system.cpu.l2cache.overall_accesses           2544748                       # number of overall (read+write) accesses
+system.cpu.l2cache.ReadReq_miss_rate         0.191337                       # miss rate for ReadReq accesses
+system.cpu.l2cache.UpgradeReq_miss_rate      0.994129                       # miss rate for UpgradeReq accesses
+system.cpu.l2cache.ReadExReq_miss_rate       0.320476                       # miss rate for ReadExReq accesses
+system.cpu.l2cache.demand_miss_rate          0.230468                       # miss rate for demand accesses
+system.cpu.l2cache.overall_miss_rate         0.230468                       # miss rate for overall accesses
+system.cpu.l2cache.ReadReq_avg_miss_latency 34156.839518                       # average ReadReq miss latency
+system.cpu.l2cache.UpgradeReq_avg_miss_latency    44.293476                       # average UpgradeReq miss latency
+system.cpu.l2cache.ReadExReq_avg_miss_latency 34266.039026                       # average ReadExReq miss latency
+system.cpu.l2cache.demand_avg_miss_latency 34202.851068                       # average overall miss latency
+system.cpu.l2cache.overall_avg_miss_latency 34202.851068                       # average overall miss latency
 system.cpu.l2cache.blocked_cycles::no_mshrs            0                       # number of cycles access was blocked
 system.cpu.l2cache.blocked_cycles::no_targets            0                       # number of cycles access was blocked
 system.cpu.l2cache.blocked::no_mshrs                0                       # number of cycles access was blocked
@@ -458,31 +456,31 @@
 system.cpu.l2cache.avg_blocked_cycles::no_targets     no_value                       # average number of cycles each access was blocked
 system.cpu.l2cache.fast_writes                      0                       # number of fast writes performed
 system.cpu.l2cache.cache_copies                     0                       # number of cache copies performed
-system.cpu.l2cache.writebacks                  411265                       # number of writebacks
+system.cpu.l2cache.writebacks                  411522                       # number of writebacks
 system.cpu.l2cache.demand_mshr_hits                 0                       # number of demand (read+write) MSHR hits
 system.cpu.l2cache.overall_mshr_hits                0                       # number of overall MSHR hits
-system.cpu.l2cache.ReadReq_mshr_misses         338611                       # number of ReadReq MSHR misses
-system.cpu.l2cache.UpgradeReq_mshr_misses       208876                       # number of UpgradeReq MSHR misses
-system.cpu.l2cache.ReadExReq_mshr_misses       247152                       # number of ReadExReq MSHR misses
-system.cpu.l2cache.demand_mshr_misses          585763                       # number of demand (read+write) MSHR misses
-system.cpu.l2cache.overall_mshr_misses         585763                       # number of overall MSHR misses
+system.cpu.l2cache.ReadReq_mshr_misses         339366                       # number of ReadReq MSHR misses
+system.cpu.l2cache.UpgradeReq_mshr_misses       220134                       # number of UpgradeReq MSHR misses
+system.cpu.l2cache.ReadExReq_mshr_misses       247116                       # number of ReadExReq MSHR misses
+system.cpu.l2cache.demand_mshr_misses          586482                       # number of demand (read+write) MSHR misses
+system.cpu.l2cache.overall_mshr_misses         586482                       # number of overall MSHR misses
 system.cpu.l2cache.overall_mshr_uncacheable_misses            0                       # number of overall MSHR uncacheable misses
-system.cpu.l2cache.ReadReq_mshr_miss_latency  10503665500                       # number of ReadReq MSHR miss cycles
-system.cpu.l2cache.UpgradeReq_mshr_miss_latency   6475353000                       # number of UpgradeReq MSHR miss cycles
-system.cpu.l2cache.ReadExReq_mshr_miss_latency   7666739500                       # number of ReadExReq MSHR miss cycles
-system.cpu.l2cache.demand_mshr_miss_latency  18170405000                       # number of demand (read+write) MSHR miss cycles
-system.cpu.l2cache.overall_mshr_miss_latency  18170405000                       # number of overall MSHR miss cycles
+system.cpu.l2cache.ReadReq_mshr_miss_latency  10527298500                       # number of ReadReq MSHR miss cycles
+system.cpu.l2cache.UpgradeReq_mshr_miss_latency   6824577500                       # number of UpgradeReq MSHR miss cycles
+system.cpu.l2cache.ReadExReq_mshr_miss_latency   7661565500                       # number of ReadExReq MSHR miss cycles
+system.cpu.l2cache.demand_mshr_miss_latency  18188864000                       # number of demand (read+write) MSHR miss cycles
+system.cpu.l2cache.overall_mshr_miss_latency  18188864000                       # number of overall MSHR miss cycles
 system.cpu.l2cache.overall_mshr_uncacheable_latency            0                       # number of overall MSHR uncacheable cycles
-system.cpu.l2cache.ReadReq_mshr_miss_rate     0.191102                       # mshr miss rate for ReadReq accesses
-system.cpu.l2cache.UpgradeReq_mshr_miss_rate     0.994098                       # mshr miss rate for UpgradeReq accesses
-system.cpu.l2cache.ReadExReq_mshr_miss_rate     0.320331                       # mshr miss rate for ReadExReq accesses
-system.cpu.l2cache.demand_mshr_miss_rate     0.230303                       # mshr miss rate for demand accesses
-system.cpu.l2cache.overall_mshr_miss_rate     0.230303                       # mshr miss rate for overall accesses
-system.cpu.l2cache.ReadReq_avg_mshr_miss_latency 31019.859071                       # average ReadReq mshr miss latency
-system.cpu.l2cache.UpgradeReq_avg_mshr_miss_latency 31000.943143                       # average UpgradeReq mshr miss latency
-system.cpu.l2cache.ReadExReq_avg_mshr_miss_latency 31020.341733                       # average ReadExReq mshr miss latency
-system.cpu.l2cache.demand_avg_mshr_miss_latency 31020.062722                       # average overall mshr miss latency
-system.cpu.l2cache.overall_avg_mshr_miss_latency 31020.062722                       # average overall mshr miss latency
+system.cpu.l2cache.ReadReq_mshr_miss_rate     0.191337                       # mshr miss rate for ReadReq accesses
+system.cpu.l2cache.UpgradeReq_mshr_miss_rate     0.994129                       # mshr miss rate for UpgradeReq accesses
+system.cpu.l2cache.ReadExReq_mshr_miss_rate     0.320476                       # mshr miss rate for ReadExReq accesses
+system.cpu.l2cache.demand_mshr_miss_rate     0.230468                       # mshr miss rate for demand accesses
+system.cpu.l2cache.overall_mshr_miss_rate     0.230468                       # mshr miss rate for overall accesses
+system.cpu.l2cache.ReadReq_avg_mshr_miss_latency 31020.486731                       # average ReadReq mshr miss latency
+system.cpu.l2cache.UpgradeReq_avg_mshr_miss_latency 31001.923828                       # average UpgradeReq mshr miss latency
+system.cpu.l2cache.ReadExReq_avg_mshr_miss_latency 31003.923259                       # average ReadExReq mshr miss latency
+system.cpu.l2cache.demand_avg_mshr_miss_latency 31013.507661                       # average overall mshr miss latency
+system.cpu.l2cache.overall_avg_mshr_miss_latency 31013.507661                       # average overall mshr miss latency
 system.cpu.l2cache.overall_avg_mshr_uncacheable_latency     no_value                       # average overall mshr uncacheable latency
 system.cpu.l2cache.mshr_cap_events                  0                       # number of times MSHR cap was activated
 system.cpu.l2cache.soft_prefetch_mshr_full            0                       # number of mshr full events for SW prefetching instrutions
diff --git a/tests/long/70.twolf/ref/x86/linux/o3-timing/config.ini b/tests/long/70.twolf/ref/x86/linux/o3-timing/config.ini
index 0cd9938..b8115d9 100644
--- a/tests/long/70.twolf/ref/x86/linux/o3-timing/config.ini
+++ b/tests/long/70.twolf/ref/x86/linux/o3-timing/config.ini
@@ -80,6 +80,7 @@
 max_insts_any_thread=0
 max_loads_all_threads=0
 max_loads_any_thread=0
+needsTSO=true
 numIQEntries=64
 numPhysFloatRegs=256
 numPhysIntRegs=256
@@ -502,7 +503,7 @@
 env=
 errout=cerr
 euid=100
-executable=/dist/m5/cpu2000/binaries/x86/linux/twolf
+executable=/scratch/nilay/GEM5/dist/m5/cpu2000/binaries/x86/linux/twolf
 gid=100
 input=cin
 max_stack_size=67108864
diff --git a/tests/long/70.twolf/ref/x86/linux/o3-timing/simout b/tests/long/70.twolf/ref/x86/linux/o3-timing/simout
index 1f94243..3d5ba32 100755
--- a/tests/long/70.twolf/ref/x86/linux/o3-timing/simout
+++ b/tests/long/70.twolf/ref/x86/linux/o3-timing/simout
@@ -1,9 +1,11 @@
+Redirecting stdout to build/X86_SE/tests/opt/long/70.twolf/x86/linux/o3-timing/simout
+Redirecting stderr to build/X86_SE/tests/opt/long/70.twolf/x86/linux/o3-timing/simerr
 gem5 Simulator System.  http://gem5.org
 gem5 is copyrighted software; use the --copyright option for details.
 
-gem5 compiled Jan 23 2012 04:08:34
-gem5 started Jan 23 2012 07:52:38
-gem5 executing on zizzer
+gem5 compiled Jan 28 2012 12:11:40
+gem5 started Jan 28 2012 12:12:43
+gem5 executing on ribera.cs.wisc.edu
 command line: build/X86_SE/gem5.opt -d build/X86_SE/tests/opt/long/70.twolf/x86/linux/o3-timing -re tests/run.py build/X86_SE/tests/opt/long/70.twolf/x86/linux/o3-timing
 Couldn't unlink  build/X86_SE/tests/opt/long/70.twolf/x86/linux/o3-timing/smred.sav
 Couldn't unlink  build/X86_SE/tests/opt/long/70.twolf/x86/linux/o3-timing/smred.sv2
@@ -24,4 +26,4 @@
  76  77  78  79  80  81  82  83  84  85  86  87  88  89  90 
  91  92  93  94  95  96  97  98  99 100 101 102 103 104 105 
 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 
-122 123 124 Exiting @ tick 96689893000 because target called exit()
+122 123 124 Exiting @ tick 96605044000 because target called exit()
diff --git a/tests/long/70.twolf/ref/x86/linux/o3-timing/stats.txt b/tests/long/70.twolf/ref/x86/linux/o3-timing/stats.txt
index 71e8505..5be6519 100644
--- a/tests/long/70.twolf/ref/x86/linux/o3-timing/stats.txt
+++ b/tests/long/70.twolf/ref/x86/linux/o3-timing/stats.txt
@@ -1,261 +1,261 @@
 
 ---------- Begin Simulation Statistics ----------
-sim_seconds                                  0.096690                       # Number of seconds simulated
-sim_ticks                                 96689893000                       # Number of ticks simulated
-final_tick                                96689893000                       # Number of ticks from beginning of simulation (restored from checkpoints and never reset)
+sim_seconds                                  0.096605                       # Number of seconds simulated
+sim_ticks                                 96605044000                       # Number of ticks simulated
+final_tick                                96605044000                       # Number of ticks from beginning of simulation (restored from checkpoints and never reset)
 sim_freq                                 1000000000000                       # Frequency of simulated ticks
-host_inst_rate                                 118200                       # Simulator instruction rate (inst/s)
-host_tick_rate                               51629155                       # Simulator tick rate (ticks/s)
-host_mem_usage                                 224032                       # Number of bytes of host memory used
-host_seconds                                  1872.78                       # Real time elapsed on the host
+host_inst_rate                                  67425                       # Simulator instruction rate (inst/s)
+host_tick_rate                               29425038                       # Simulator tick rate (ticks/s)
+host_mem_usage                                 253272                       # Number of bytes of host memory used
+host_seconds                                  3283.09                       # Real time elapsed on the host
 sim_insts                                   221363017                       # Number of instructions simulated
-system.physmem.bytes_read                      340224                       # Number of bytes read from this memory
-system.physmem.bytes_inst_read                 215424                       # Number of instructions bytes read from this memory
+system.physmem.bytes_read                      339456                       # Number of bytes read from this memory
+system.physmem.bytes_inst_read                 214848                       # Number of instructions bytes read from this memory
 system.physmem.bytes_written                        0                       # Number of bytes written to this memory
-system.physmem.num_reads                         5316                       # Number of read requests responded to by this memory
+system.physmem.num_reads                         5304                       # Number of read requests responded to by this memory
 system.physmem.num_writes                           0                       # Number of write requests responded to by this memory
 system.physmem.num_other                            0                       # Number of other requests responded to by this memory
-system.physmem.bw_read                        3518713                       # Total read bandwidth from this memory (bytes/s)
-system.physmem.bw_inst_read                   2227989                       # Instruction read bandwidth from this memory (bytes/s)
-system.physmem.bw_total                       3518713                       # Total bandwidth to/from this memory (bytes/s)
+system.physmem.bw_read                        3513854                       # Total read bandwidth from this memory (bytes/s)
+system.physmem.bw_inst_read                   2223983                       # Instruction read bandwidth from this memory (bytes/s)
+system.physmem.bw_total                       3513854                       # Total bandwidth to/from this memory (bytes/s)
 system.cpu.workload.num_syscalls                  400                       # Number of system calls
-system.cpu.numCycles                        193379787                       # number of cpu cycles simulated
+system.cpu.numCycles                        193210089                       # number of cpu cycles simulated
 system.cpu.numWorkItemsStarted                      0                       # number of work items this cpu started
 system.cpu.numWorkItemsCompleted                    0                       # number of work items this cpu completed
-system.cpu.BPredUnit.lookups                 25818202                       # Number of BP lookups
-system.cpu.BPredUnit.condPredicted           25818202                       # Number of conditional branches predicted
-system.cpu.BPredUnit.condIncorrect            2898724                       # Number of conditional branches incorrect
-system.cpu.BPredUnit.BTBLookups              23602930                       # Number of BTB lookups
-system.cpu.BPredUnit.BTBHits                 20841363                       # Number of BTB hits
+system.cpu.BPredUnit.lookups                 25792325                       # Number of BP lookups
+system.cpu.BPredUnit.condPredicted           25792325                       # Number of conditional branches predicted
+system.cpu.BPredUnit.condIncorrect            2895497                       # Number of conditional branches incorrect
+system.cpu.BPredUnit.BTBLookups              23600664                       # Number of BTB lookups
+system.cpu.BPredUnit.BTBHits                 20878395                       # Number of BTB hits
 system.cpu.BPredUnit.BTBCorrect                     0                       # Number of correct BTB predictions (this stat may not work properly.
 system.cpu.BPredUnit.usedRAS                        0                       # Number of times the RAS was used to get a target.
 system.cpu.BPredUnit.RASInCorrect                   0                       # Number of incorrect RAS predictions.
-system.cpu.fetch.icacheStallCycles           30995459                       # Number of cycles fetch is stalled on an Icache miss
-system.cpu.fetch.Insts                      261573615                       # Number of instructions fetch has processed
-system.cpu.fetch.Branches                    25818202                       # Number of branches that fetch encountered
-system.cpu.fetch.predictedBranches           20841363                       # Number of branches that fetch has predicted taken
-system.cpu.fetch.Cycles                      70808397                       # Number of cycles fetch has run and was not squashing or blocked
-system.cpu.fetch.SquashCycles                26924712                       # Number of cycles fetch has spent squashing
-system.cpu.fetch.BlockedCycles               67767699                       # Number of cycles fetch has spent blocked
-system.cpu.fetch.MiscStallCycles                  120                       # Number of cycles fetch has spent waiting on interrupts, or bad addresses, or out of MSHRs
-system.cpu.fetch.PendingTrapStallCycles          1017                       # Number of stall cycles due to pending traps
-system.cpu.fetch.CacheLines                  28859729                       # Number of cache lines fetched
-system.cpu.fetch.IcacheSquashes                549788                       # Number of outstanding Icache misses that were squashed
-system.cpu.fetch.rateDist::samples          193293197                       # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::mean              2.259018                       # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::stdev             3.335260                       # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.icacheStallCycles           30964428                       # Number of cycles fetch is stalled on an Icache miss
+system.cpu.fetch.Insts                      261331282                       # Number of instructions fetch has processed
+system.cpu.fetch.Branches                    25792325                       # Number of branches that fetch encountered
+system.cpu.fetch.predictedBranches           20878395                       # Number of branches that fetch has predicted taken
+system.cpu.fetch.Cycles                      70767464                       # Number of cycles fetch has run and was not squashing or blocked
+system.cpu.fetch.SquashCycles                26891019                       # Number of cycles fetch has spent squashing
+system.cpu.fetch.BlockedCycles               67713706                       # Number of cycles fetch has spent blocked
+system.cpu.fetch.MiscStallCycles                  142                       # Number of cycles fetch has spent waiting on interrupts, or bad addresses, or out of MSHRs
+system.cpu.fetch.PendingTrapStallCycles          1189                       # Number of stall cycles due to pending traps
+system.cpu.fetch.CacheLines                  28829274                       # Number of cache lines fetched
+system.cpu.fetch.IcacheSquashes                550737                       # Number of outstanding Icache misses that were squashed
+system.cpu.fetch.rateDist::samples          193129824                       # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.rateDist::mean              2.258996                       # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.rateDist::stdev             3.335178                       # Number of instructions fetched each cycle (Total)
 system.cpu.fetch.rateDist::underflows               0      0.00%      0.00% # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::0                124336745     64.33%     64.33% # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::1                  4112034      2.13%     66.45% # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::2                  3238737      1.68%     68.13% # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::3                  4462671      2.31%     70.44% # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::4                  4295145      2.22%     72.66% # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::5                  4476640      2.32%     74.98% # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::6                  5418723      2.80%     77.78% # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::7                  3020771      1.56%     79.34% # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::8                 39931731     20.66%    100.00% # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.rateDist::0                124221202     64.32%     64.32% # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.rateDist::1                  4112630      2.13%     66.45% # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.rateDist::2                  3244602      1.68%     68.13% # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.rateDist::3                  4465272      2.31%     70.44% # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.rateDist::4                  4293373      2.22%     72.66% # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.rateDist::5                  4464358      2.31%     74.98% # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.rateDist::6                  5413333      2.80%     77.78% # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.rateDist::7                  3013911      1.56%     79.34% # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.rateDist::8                 39901143     20.66%    100.00% # Number of instructions fetched each cycle (Total)
 system.cpu.fetch.rateDist::overflows                0      0.00%    100.00% # Number of instructions fetched each cycle (Total)
 system.cpu.fetch.rateDist::min_value                0                       # Number of instructions fetched each cycle (Total)
 system.cpu.fetch.rateDist::max_value                8                       # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::total            193293197                       # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.branchRate                  0.133510                       # Number of branch fetches per cycle
-system.cpu.fetch.rate                        1.352642                       # Number of inst fetches per cycle
-system.cpu.decode.IdleCycles                 44764810                       # Number of cycles decode is idle
-system.cpu.decode.BlockedCycles              57827624                       # Number of cycles decode is blocked
-system.cpu.decode.RunCycles                  57161965                       # Number of cycles decode is running
-system.cpu.decode.UnblockCycles               9818293                       # Number of cycles decode is unblocking
-system.cpu.decode.SquashCycles               23720505                       # Number of cycles decode is squashing
-system.cpu.decode.DecodedInsts              424367292                       # Number of instructions handled by decode
-system.cpu.rename.SquashCycles               23720505                       # Number of cycles rename is squashing
-system.cpu.rename.IdleCycles                 53388300                       # Number of cycles rename is idle
-system.cpu.rename.BlockCycles                14632169                       # Number of cycles rename is blocking
-system.cpu.rename.serializeStallCycles          21921                       # count of cycles rename stalled for serializing inst
-system.cpu.rename.RunCycles                  57615812                       # Number of cycles rename is running
-system.cpu.rename.UnblockCycles              43914490                       # Number of cycles rename is unblocking
-system.cpu.rename.RenamedInsts              411765049                       # Number of instructions processed by rename
-system.cpu.rename.ROBFullEvents                    18                       # Number of times rename has blocked due to ROB full
-system.cpu.rename.IQFullEvents               19034939                       # Number of times rename has blocked due to IQ full
-system.cpu.rename.LSQFullEvents              22478875                       # Number of times rename has blocked due to LSQ full
-system.cpu.rename.RenamedOperands           438156432                       # Number of destination operands rename has renamed
-system.cpu.rename.RenameLookups            1066580371                       # Number of register rename lookups that rename has made
-system.cpu.rename.int_rename_lookups       1055689317                       # Number of integer rename lookups
-system.cpu.rename.fp_rename_lookups          10891054                       # Number of floating rename lookups
+system.cpu.fetch.rateDist::total            193129824                       # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.branchRate                  0.133494                       # Number of branch fetches per cycle
+system.cpu.fetch.rate                        1.352576                       # Number of inst fetches per cycle
+system.cpu.decode.IdleCycles                 44734521                       # Number of cycles decode is idle
+system.cpu.decode.BlockedCycles              57786241                       # Number of cycles decode is blocked
+system.cpu.decode.RunCycles                  57127863                       # Number of cycles decode is running
+system.cpu.decode.UnblockCycles               9798304                       # Number of cycles decode is unblocking
+system.cpu.decode.SquashCycles               23682895                       # Number of cycles decode is squashing
+system.cpu.decode.DecodedInsts              423946385                       # Number of instructions handled by decode
+system.cpu.rename.SquashCycles               23682895                       # Number of cycles rename is squashing
+system.cpu.rename.IdleCycles                 53367953                       # Number of cycles rename is idle
+system.cpu.rename.BlockCycles                14712731                       # Number of cycles rename is blocking
+system.cpu.rename.serializeStallCycles          23142                       # count of cycles rename stalled for serializing inst
+system.cpu.rename.RunCycles                  57547510                       # Number of cycles rename is running
+system.cpu.rename.UnblockCycles              43795593                       # Number of cycles rename is unblocking
+system.cpu.rename.RenamedInsts              411406798                       # Number of instructions processed by rename
+system.cpu.rename.ROBFullEvents                    10                       # Number of times rename has blocked due to ROB full
+system.cpu.rename.IQFullEvents               18855699                       # Number of times rename has blocked due to IQ full
+system.cpu.rename.LSQFullEvents              22517657                       # Number of times rename has blocked due to LSQ full
+system.cpu.rename.RenamedOperands           437782007                       # Number of destination operands rename has renamed
+system.cpu.rename.RenameLookups            1065797846                       # Number of register rename lookups that rename has made
+system.cpu.rename.int_rename_lookups       1054993887                       # Number of integer rename lookups
+system.cpu.rename.fp_rename_lookups          10803959                       # Number of floating rename lookups
 system.cpu.rename.CommittedMaps             234363409                       # Number of HB maps that are committed
-system.cpu.rename.UndoneMaps                203793023                       # Number of HB maps that are undone due to squashing
-system.cpu.rename.serializingInsts               1794                       # count of serializing insts renamed
-system.cpu.rename.tempSerializingInsts           1788                       # count of temporary serializing insts renamed
-system.cpu.rename.skidInsts                  94980657                       # count of insts added to the skid buffer
-system.cpu.memDep0.insertedLoads            104262380                       # Number of loads inserted to the mem dependence unit.
-system.cpu.memDep0.insertedStores            37289638                       # Number of stores inserted to the mem dependence unit.
-system.cpu.memDep0.conflictingLoads          67232013                       # Number of conflicting loads.
-system.cpu.memDep0.conflictingStores         21668119                       # Number of conflicting stores.
-system.cpu.iq.iqInstsAdded                  396788007                       # Number of instructions added to the IQ (excludes non-spec)
-system.cpu.iq.iqNonSpecInstsAdded                2705                       # Number of non-speculative instructions added to the IQ
-system.cpu.iq.iqInstsIssued                 287703359                       # Number of instructions issued
-system.cpu.iq.iqSquashedInstsIssued            254770                       # Number of squashed instructions issued
-system.cpu.iq.iqSquashedInstsExamined       174855842                       # Number of squashed instructions iterated over during squash; mainly for profiling
-system.cpu.iq.iqSquashedOperandsExamined    350938331                       # Number of squashed operands that are examined and possibly removed from graph
-system.cpu.iq.iqSquashedNonSpecRemoved           1459                       # Number of squashed non-spec instructions that were removed
-system.cpu.iq.issued_per_cycle::samples     193293197                       # Number of insts issued each cycle
-system.cpu.iq.issued_per_cycle::mean         1.488430                       # Number of insts issued each cycle
-system.cpu.iq.issued_per_cycle::stdev        1.480803                       # Number of insts issued each cycle
+system.cpu.rename.UndoneMaps                203418598                       # Number of HB maps that are undone due to squashing
+system.cpu.rename.serializingInsts               1777                       # count of serializing insts renamed
+system.cpu.rename.tempSerializingInsts           1771                       # count of temporary serializing insts renamed
+system.cpu.rename.skidInsts                  94869536                       # count of insts added to the skid buffer
+system.cpu.memDep0.insertedLoads            104184220                       # Number of loads inserted to the mem dependence unit.
+system.cpu.memDep0.insertedStores            37252864                       # Number of stores inserted to the mem dependence unit.
+system.cpu.memDep0.conflictingLoads          66898151                       # Number of conflicting loads.
+system.cpu.memDep0.conflictingStores         21504625                       # Number of conflicting stores.
+system.cpu.iq.iqInstsAdded                  396406110                       # Number of instructions added to the IQ (excludes non-spec)
+system.cpu.iq.iqNonSpecInstsAdded                2683                       # Number of non-speculative instructions added to the IQ
+system.cpu.iq.iqInstsIssued                 287681996                       # Number of instructions issued
+system.cpu.iq.iqSquashedInstsIssued            245770                       # Number of squashed instructions issued
+system.cpu.iq.iqSquashedInstsExamined       174447554                       # Number of squashed instructions iterated over during squash; mainly for profiling
+system.cpu.iq.iqSquashedOperandsExamined    349871098                       # Number of squashed operands that are examined and possibly removed from graph
+system.cpu.iq.iqSquashedNonSpecRemoved           1437                       # Number of squashed non-spec instructions that were removed
+system.cpu.iq.issued_per_cycle::samples     193129824                       # Number of insts issued each cycle
+system.cpu.iq.issued_per_cycle::mean         1.489578                       # Number of insts issued each cycle
+system.cpu.iq.issued_per_cycle::stdev        1.482432                       # Number of insts issued each cycle
 system.cpu.iq.issued_per_cycle::underflows            0      0.00%      0.00% # Number of insts issued each cycle
-system.cpu.iq.issued_per_cycle::0            60724695     31.42%     31.42% # Number of insts issued each cycle
-system.cpu.iq.issued_per_cycle::1            54019027     27.95%     59.36% # Number of insts issued each cycle
-system.cpu.iq.issued_per_cycle::2            35712551     18.48%     77.84% # Number of insts issued each cycle
-system.cpu.iq.issued_per_cycle::3            21012235     10.87%     88.71% # Number of insts issued each cycle
-system.cpu.iq.issued_per_cycle::4            13686479      7.08%     95.79% # Number of insts issued each cycle
-system.cpu.iq.issued_per_cycle::5             5222239      2.70%     98.49% # Number of insts issued each cycle
-system.cpu.iq.issued_per_cycle::6             2184583      1.13%     99.62% # Number of insts issued each cycle
-system.cpu.iq.issued_per_cycle::7              593188      0.31%     99.93% # Number of insts issued each cycle
-system.cpu.iq.issued_per_cycle::8              138200      0.07%    100.00% # Number of insts issued each cycle
+system.cpu.iq.issued_per_cycle::0            60692059     31.43%     31.43% # Number of insts issued each cycle
+system.cpu.iq.issued_per_cycle::1            53894832     27.91%     59.33% # Number of insts issued each cycle
+system.cpu.iq.issued_per_cycle::2            35675096     18.47%     77.80% # Number of insts issued each cycle
+system.cpu.iq.issued_per_cycle::3            21030275     10.89%     88.69% # Number of insts issued each cycle
+system.cpu.iq.issued_per_cycle::4            13671463      7.08%     95.77% # Number of insts issued each cycle
+system.cpu.iq.issued_per_cycle::5             5219808      2.70%     98.47% # Number of insts issued each cycle
+system.cpu.iq.issued_per_cycle::6             2207559      1.14%     99.62% # Number of insts issued each cycle
+system.cpu.iq.issued_per_cycle::7              593955      0.31%     99.93% # Number of insts issued each cycle
+system.cpu.iq.issued_per_cycle::8              144777      0.07%    100.00% # Number of insts issued each cycle
 system.cpu.iq.issued_per_cycle::overflows            0      0.00%    100.00% # Number of insts issued each cycle
 system.cpu.iq.issued_per_cycle::min_value            0                       # Number of insts issued each cycle
 system.cpu.iq.issued_per_cycle::max_value            8                       # Number of insts issued each cycle
-system.cpu.iq.issued_per_cycle::total       193293197                       # Number of insts issued each cycle
+system.cpu.iq.issued_per_cycle::total       193129824                       # Number of insts issued each cycle
 system.cpu.iq.fu_full::No_OpClass                   0      0.00%      0.00% # attempts to use FU when none available
-system.cpu.iq.fu_full::IntAlu                  110269      4.01%      4.01% # attempts to use FU when none available
-system.cpu.iq.fu_full::IntMult                      0      0.00%      4.01% # attempts to use FU when none available
-system.cpu.iq.fu_full::IntDiv                       0      0.00%      4.01% # attempts to use FU when none available
-system.cpu.iq.fu_full::FloatAdd                     0      0.00%      4.01% # attempts to use FU when none available
-system.cpu.iq.fu_full::FloatCmp                     0      0.00%      4.01% # attempts to use FU when none available
-system.cpu.iq.fu_full::FloatCvt                     0      0.00%      4.01% # attempts to use FU when none available
-system.cpu.iq.fu_full::FloatMult                    0      0.00%      4.01% # attempts to use FU when none available
-system.cpu.iq.fu_full::FloatDiv                     0      0.00%      4.01% # attempts to use FU when none available
-system.cpu.iq.fu_full::FloatSqrt                    0      0.00%      4.01% # attempts to use FU when none available
-system.cpu.iq.fu_full::SimdAdd                      0      0.00%      4.01% # attempts to use FU when none available
-system.cpu.iq.fu_full::SimdAddAcc                   0      0.00%      4.01% # attempts to use FU when none available
-system.cpu.iq.fu_full::SimdAlu                      0      0.00%      4.01% # attempts to use FU when none available
-system.cpu.iq.fu_full::SimdCmp                      0      0.00%      4.01% # attempts to use FU when none available
-system.cpu.iq.fu_full::SimdCvt                      0      0.00%      4.01% # attempts to use FU when none available
-system.cpu.iq.fu_full::SimdMisc                     0      0.00%      4.01% # attempts to use FU when none available
-system.cpu.iq.fu_full::SimdMult                     0      0.00%      4.01% # attempts to use FU when none available
-system.cpu.iq.fu_full::SimdMultAcc                  0      0.00%      4.01% # attempts to use FU when none available
-system.cpu.iq.fu_full::SimdShift                    0      0.00%      4.01% # attempts to use FU when none available
-system.cpu.iq.fu_full::SimdShiftAcc                 0      0.00%      4.01% # attempts to use FU when none available
-system.cpu.iq.fu_full::SimdSqrt                     0      0.00%      4.01% # attempts to use FU when none available
-system.cpu.iq.fu_full::SimdFloatAdd                 0      0.00%      4.01% # attempts to use FU when none available
-system.cpu.iq.fu_full::SimdFloatAlu                 0      0.00%      4.01% # attempts to use FU when none available
-system.cpu.iq.fu_full::SimdFloatCmp                 0      0.00%      4.01% # attempts to use FU when none available
-system.cpu.iq.fu_full::SimdFloatCvt                 0      0.00%      4.01% # attempts to use FU when none available
-system.cpu.iq.fu_full::SimdFloatDiv                 0      0.00%      4.01% # attempts to use FU when none available
-system.cpu.iq.fu_full::SimdFloatMisc                0      0.00%      4.01% # attempts to use FU when none available
-system.cpu.iq.fu_full::SimdFloatMult                0      0.00%      4.01% # attempts to use FU when none available
-system.cpu.iq.fu_full::SimdFloatMultAcc             0      0.00%      4.01% # attempts to use FU when none available
-system.cpu.iq.fu_full::SimdFloatSqrt                0      0.00%      4.01% # attempts to use FU when none available
-system.cpu.iq.fu_full::MemRead                2317531     84.31%     88.32% # attempts to use FU when none available
-system.cpu.iq.fu_full::MemWrite                321034     11.68%    100.00% # attempts to use FU when none available
+system.cpu.iq.fu_full::IntAlu                  112792      4.13%      4.13% # attempts to use FU when none available
+system.cpu.iq.fu_full::IntMult                      0      0.00%      4.13% # attempts to use FU when none available
+system.cpu.iq.fu_full::IntDiv                       0      0.00%      4.13% # attempts to use FU when none available
+system.cpu.iq.fu_full::FloatAdd                     0      0.00%      4.13% # attempts to use FU when none available
+system.cpu.iq.fu_full::FloatCmp                     0      0.00%      4.13% # attempts to use FU when none available
+system.cpu.iq.fu_full::FloatCvt                     0      0.00%      4.13% # attempts to use FU when none available
+system.cpu.iq.fu_full::FloatMult                    0      0.00%      4.13% # attempts to use FU when none available
+system.cpu.iq.fu_full::FloatDiv                     0      0.00%      4.13% # attempts to use FU when none available
+system.cpu.iq.fu_full::FloatSqrt                    0      0.00%      4.13% # attempts to use FU when none available
+system.cpu.iq.fu_full::SimdAdd                      0      0.00%      4.13% # attempts to use FU when none available
+system.cpu.iq.fu_full::SimdAddAcc                   0      0.00%      4.13% # attempts to use FU when none available
+system.cpu.iq.fu_full::SimdAlu                      0      0.00%      4.13% # attempts to use FU when none available
+system.cpu.iq.fu_full::SimdCmp                      0      0.00%      4.13% # attempts to use FU when none available
+system.cpu.iq.fu_full::SimdCvt                      0      0.00%      4.13% # attempts to use FU when none available
+system.cpu.iq.fu_full::SimdMisc                     0      0.00%      4.13% # attempts to use FU when none available
+system.cpu.iq.fu_full::SimdMult                     0      0.00%      4.13% # attempts to use FU when none available
+system.cpu.iq.fu_full::SimdMultAcc                  0      0.00%      4.13% # attempts to use FU when none available
+system.cpu.iq.fu_full::SimdShift                    0      0.00%      4.13% # attempts to use FU when none available
+system.cpu.iq.fu_full::SimdShiftAcc                 0      0.00%      4.13% # attempts to use FU when none available
+system.cpu.iq.fu_full::SimdSqrt                     0      0.00%      4.13% # attempts to use FU when none available
+system.cpu.iq.fu_full::SimdFloatAdd                 0      0.00%      4.13% # attempts to use FU when none available
+system.cpu.iq.fu_full::SimdFloatAlu                 0      0.00%      4.13% # attempts to use FU when none available
+system.cpu.iq.fu_full::SimdFloatCmp                 0      0.00%      4.13% # attempts to use FU when none available
+system.cpu.iq.fu_full::SimdFloatCvt                 0      0.00%      4.13% # attempts to use FU when none available
+system.cpu.iq.fu_full::SimdFloatDiv                 0      0.00%      4.13% # attempts to use FU when none available
+system.cpu.iq.fu_full::SimdFloatMisc                0      0.00%      4.13% # attempts to use FU when none available
+system.cpu.iq.fu_full::SimdFloatMult                0      0.00%      4.13% # attempts to use FU when none available
+system.cpu.iq.fu_full::SimdFloatMultAcc             0      0.00%      4.13% # attempts to use FU when none available
+system.cpu.iq.fu_full::SimdFloatSqrt                0      0.00%      4.13% # attempts to use FU when none available
+system.cpu.iq.fu_full::MemRead                2307770     84.43%     88.56% # attempts to use FU when none available
+system.cpu.iq.fu_full::MemWrite                312724     11.44%    100.00% # attempts to use FU when none available
 system.cpu.iq.fu_full::IprAccess                    0      0.00%    100.00% # attempts to use FU when none available
 system.cpu.iq.fu_full::InstPrefetch                 0      0.00%    100.00% # attempts to use FU when none available
-system.cpu.iq.FU_type_0::No_OpClass           1208234      0.42%      0.42% # Type of FU issued
-system.cpu.iq.FU_type_0::IntAlu             187072997     65.02%     65.44% # Type of FU issued
-system.cpu.iq.FU_type_0::IntMult                    0      0.00%     65.44% # Type of FU issued
-system.cpu.iq.FU_type_0::IntDiv                     0      0.00%     65.44% # Type of FU issued
-system.cpu.iq.FU_type_0::FloatAdd             1650386      0.57%     66.02% # Type of FU issued
-system.cpu.iq.FU_type_0::FloatCmp                   0      0.00%     66.02% # Type of FU issued
-system.cpu.iq.FU_type_0::FloatCvt                   0      0.00%     66.02% # Type of FU issued
-system.cpu.iq.FU_type_0::FloatMult                  0      0.00%     66.02% # Type of FU issued
-system.cpu.iq.FU_type_0::FloatDiv                   0      0.00%     66.02% # Type of FU issued
-system.cpu.iq.FU_type_0::FloatSqrt                  0      0.00%     66.02% # Type of FU issued
-system.cpu.iq.FU_type_0::SimdAdd                    0      0.00%     66.02% # Type of FU issued
-system.cpu.iq.FU_type_0::SimdAddAcc                 0      0.00%     66.02% # Type of FU issued
-system.cpu.iq.FU_type_0::SimdAlu                    0      0.00%     66.02% # Type of FU issued
-system.cpu.iq.FU_type_0::SimdCmp                    0      0.00%     66.02% # Type of FU issued
-system.cpu.iq.FU_type_0::SimdCvt                    0      0.00%     66.02% # Type of FU issued
-system.cpu.iq.FU_type_0::SimdMisc                   0      0.00%     66.02% # Type of FU issued
-system.cpu.iq.FU_type_0::SimdMult                   0      0.00%     66.02% # Type of FU issued
-system.cpu.iq.FU_type_0::SimdMultAcc                0      0.00%     66.02% # Type of FU issued
-system.cpu.iq.FU_type_0::SimdShift                  0      0.00%     66.02% # Type of FU issued
-system.cpu.iq.FU_type_0::SimdShiftAcc               0      0.00%     66.02% # Type of FU issued
-system.cpu.iq.FU_type_0::SimdSqrt                   0      0.00%     66.02% # Type of FU issued
-system.cpu.iq.FU_type_0::SimdFloatAdd               0      0.00%     66.02% # Type of FU issued
-system.cpu.iq.FU_type_0::SimdFloatAlu               0      0.00%     66.02% # Type of FU issued
-system.cpu.iq.FU_type_0::SimdFloatCmp               0      0.00%     66.02% # Type of FU issued
-system.cpu.iq.FU_type_0::SimdFloatCvt               0      0.00%     66.02% # Type of FU issued
-system.cpu.iq.FU_type_0::SimdFloatDiv               0      0.00%     66.02% # Type of FU issued
-system.cpu.iq.FU_type_0::SimdFloatMisc              0      0.00%     66.02% # Type of FU issued
-system.cpu.iq.FU_type_0::SimdFloatMult              0      0.00%     66.02% # Type of FU issued
-system.cpu.iq.FU_type_0::SimdFloatMultAcc            0      0.00%     66.02% # Type of FU issued
-system.cpu.iq.FU_type_0::SimdFloatSqrt              0      0.00%     66.02% # Type of FU issued
-system.cpu.iq.FU_type_0::MemRead             73223880     25.45%     91.47% # Type of FU issued
-system.cpu.iq.FU_type_0::MemWrite            24547862      8.53%    100.00% # Type of FU issued
+system.cpu.iq.FU_type_0::No_OpClass           1204873      0.42%      0.42% # Type of FU issued
+system.cpu.iq.FU_type_0::IntAlu             186986858     65.00%     65.42% # Type of FU issued
+system.cpu.iq.FU_type_0::IntMult                    0      0.00%     65.42% # Type of FU issued
+system.cpu.iq.FU_type_0::IntDiv                     0      0.00%     65.42% # Type of FU issued
+system.cpu.iq.FU_type_0::FloatAdd             1646787      0.57%     65.99% # Type of FU issued
+system.cpu.iq.FU_type_0::FloatCmp                   0      0.00%     65.99% # Type of FU issued
+system.cpu.iq.FU_type_0::FloatCvt                   0      0.00%     65.99% # Type of FU issued
+system.cpu.iq.FU_type_0::FloatMult                  0      0.00%     65.99% # Type of FU issued
+system.cpu.iq.FU_type_0::FloatDiv                   0      0.00%     65.99% # Type of FU issued
+system.cpu.iq.FU_type_0::FloatSqrt                  0      0.00%     65.99% # Type of FU issued
+system.cpu.iq.FU_type_0::SimdAdd                    0      0.00%     65.99% # Type of FU issued
+system.cpu.iq.FU_type_0::SimdAddAcc                 0      0.00%     65.99% # Type of FU issued
+system.cpu.iq.FU_type_0::SimdAlu                    0      0.00%     65.99% # Type of FU issued
+system.cpu.iq.FU_type_0::SimdCmp                    0      0.00%     65.99% # Type of FU issued
+system.cpu.iq.FU_type_0::SimdCvt                    0      0.00%     65.99% # Type of FU issued
+system.cpu.iq.FU_type_0::SimdMisc                   0      0.00%     65.99% # Type of FU issued
+system.cpu.iq.FU_type_0::SimdMult                   0      0.00%     65.99% # Type of FU issued
+system.cpu.iq.FU_type_0::SimdMultAcc                0      0.00%     65.99% # Type of FU issued
+system.cpu.iq.FU_type_0::SimdShift                  0      0.00%     65.99% # Type of FU issued
+system.cpu.iq.FU_type_0::SimdShiftAcc               0      0.00%     65.99% # Type of FU issued
+system.cpu.iq.FU_type_0::SimdSqrt                   0      0.00%     65.99% # Type of FU issued
+system.cpu.iq.FU_type_0::SimdFloatAdd               0      0.00%     65.99% # Type of FU issued
+system.cpu.iq.FU_type_0::SimdFloatAlu               0      0.00%     65.99% # Type of FU issued
+system.cpu.iq.FU_type_0::SimdFloatCmp               0      0.00%     65.99% # Type of FU issued
+system.cpu.iq.FU_type_0::SimdFloatCvt               0      0.00%     65.99% # Type of FU issued
+system.cpu.iq.FU_type_0::SimdFloatDiv               0      0.00%     65.99% # Type of FU issued
+system.cpu.iq.FU_type_0::SimdFloatMisc              0      0.00%     65.99% # Type of FU issued
+system.cpu.iq.FU_type_0::SimdFloatMult              0      0.00%     65.99% # Type of FU issued
+system.cpu.iq.FU_type_0::SimdFloatMultAcc            0      0.00%     65.99% # Type of FU issued
+system.cpu.iq.FU_type_0::SimdFloatSqrt              0      0.00%     65.99% # Type of FU issued
+system.cpu.iq.FU_type_0::MemRead             73289266     25.48%     91.46% # Type of FU issued
+system.cpu.iq.FU_type_0::MemWrite            24554212      8.54%    100.00% # Type of FU issued
 system.cpu.iq.FU_type_0::IprAccess                  0      0.00%    100.00% # Type of FU issued
 system.cpu.iq.FU_type_0::InstPrefetch               0      0.00%    100.00% # Type of FU issued
-system.cpu.iq.FU_type_0::total              287703359                       # Type of FU issued
-system.cpu.iq.rate                           1.487763                       # Inst issue rate
-system.cpu.iq.fu_busy_cnt                     2748834                       # FU busy when requested
-system.cpu.iq.fu_busy_rate                   0.009554                       # FU busy rate (busy events/executed inst)
-system.cpu.iq.int_inst_queue_reads          766190945                       # Number of integer instruction queue reads
-system.cpu.iq.int_inst_queue_writes         566572341                       # Number of integer instruction queue writes
-system.cpu.iq.int_inst_queue_wakeup_accesses    278374724                       # Number of integer instruction queue wakeup accesses
-system.cpu.iq.fp_inst_queue_reads             5512574                       # Number of floating instruction queue reads
-system.cpu.iq.fp_inst_queue_writes            5407408                       # Number of floating instruction queue writes
-system.cpu.iq.fp_inst_queue_wakeup_accesses      2648186                       # Number of floating instruction queue wakeup accesses
-system.cpu.iq.int_alu_accesses              286471551                       # Number of integer alu accesses
-system.cpu.iq.fp_alu_accesses                 2772408                       # Number of floating point alu accesses
-system.cpu.iew.lsq.thread0.forwLoads         18351013                       # Number of loads that had data forwarded from stores
+system.cpu.iq.FU_type_0::total              287681996                       # Type of FU issued
+system.cpu.iq.rate                           1.488959                       # Inst issue rate
+system.cpu.iq.fu_busy_cnt                     2733286                       # FU busy when requested
+system.cpu.iq.fu_busy_rate                   0.009501                       # FU busy rate (busy events/executed inst)
+system.cpu.iq.int_inst_queue_reads          765968498                       # Number of integer instruction queue reads
+system.cpu.iq.int_inst_queue_writes         565842765                       # Number of integer instruction queue writes
+system.cpu.iq.int_inst_queue_wakeup_accesses    278370688                       # Number of integer instruction queue wakeup accesses
+system.cpu.iq.fp_inst_queue_reads             5504374                       # Number of floating instruction queue reads
+system.cpu.iq.fp_inst_queue_writes            5354879                       # Number of floating instruction queue writes
+system.cpu.iq.fp_inst_queue_wakeup_accesses      2643921                       # Number of floating instruction queue wakeup accesses
+system.cpu.iq.int_alu_accesses              286442288                       # Number of integer alu accesses
+system.cpu.iq.fp_alu_accesses                 2768121                       # Number of floating point alu accesses
+system.cpu.iew.lsq.thread0.forwLoads         18982398                       # Number of loads that had data forwarded from stores
 system.cpu.iew.lsq.thread0.invAddrLoads             0                       # Number of loads ignored due to an invalid address
-system.cpu.iew.lsq.thread0.squashedLoads     47612790                       # Number of loads squashed
-system.cpu.iew.lsq.thread0.ignoredResponses        32223                       # Number of memory responses ignored because the instruction is squashed
-system.cpu.iew.lsq.thread0.memOrderViolation       339608                       # Number of memory ordering violations
-system.cpu.iew.lsq.thread0.squashedStores     16773922                       # Number of stores squashed
+system.cpu.iew.lsq.thread0.squashedLoads     47534630                       # Number of loads squashed
+system.cpu.iew.lsq.thread0.ignoredResponses        34246                       # Number of memory responses ignored because the instruction is squashed
+system.cpu.iew.lsq.thread0.memOrderViolation       347654                       # Number of memory ordering violations
+system.cpu.iew.lsq.thread0.squashedStores     16737148                       # Number of stores squashed
 system.cpu.iew.lsq.thread0.invAddrSwpfs             0                       # Number of software prefetches ignored due to an invalid address
 system.cpu.iew.lsq.thread0.blockedLoads             0                       # Number of blocked loads due to partial load-store forwarding
-system.cpu.iew.lsq.thread0.rescheduledLoads        46155                       # Number of loads that were rescheduled
+system.cpu.iew.lsq.thread0.rescheduledLoads        48277                       # Number of loads that were rescheduled
 system.cpu.iew.lsq.thread0.cacheBlocked             0                       # Number of times an access to memory failed due to the cache being blocked
 system.cpu.iew.iewIdleCycles                        0                       # Number of cycles IEW is idle
-system.cpu.iew.iewSquashCycles               23720505                       # Number of cycles IEW is squashing
-system.cpu.iew.iewBlockCycles                  359624                       # Number of cycles IEW is blocking
-system.cpu.iew.iewUnblockCycles                213865                       # Number of cycles IEW is unblocking
-system.cpu.iew.iewDispatchedInsts           396790712                       # Number of instructions dispatched to IQ
-system.cpu.iew.iewDispSquashedInsts            135718                       # Number of squashed instructions skipped by dispatch
-system.cpu.iew.iewDispLoadInsts             104262380                       # Number of dispatched load instructions
-system.cpu.iew.iewDispStoreInsts             37289638                       # Number of dispatched store instructions
-system.cpu.iew.iewDispNonSpecInsts               1786                       # Number of dispatched non-speculative instructions
-system.cpu.iew.iewIQFullEvents                 119790                       # Number of times the IQ has become full, causing a stall
-system.cpu.iew.iewLSQFullEvents                 15845                       # Number of times the LSQ has become full, causing a stall
-system.cpu.iew.memOrderViolationEvents         339608                       # Number of memory order violations
-system.cpu.iew.predictedTakenIncorrect        2505263                       # Number of branches that were predicted taken incorrectly
-system.cpu.iew.predictedNotTakenIncorrect       598160                       # Number of branches that were predicted not taken incorrectly
-system.cpu.iew.branchMispredicts              3103423                       # Number of branch mispredicts detected at execute
-system.cpu.iew.iewExecutedInsts             283855997                       # Number of executed instructions
-system.cpu.iew.iewExecLoadInsts              71689961                       # Number of load instructions executed
-system.cpu.iew.iewExecSquashedInsts           3847362                       # Number of squashed instructions skipped in execute
+system.cpu.iew.iewSquashCycles               23682895                       # Number of cycles IEW is squashing
+system.cpu.iew.iewBlockCycles                  506655                       # Number of cycles IEW is blocking
+system.cpu.iew.iewUnblockCycles                213138                       # Number of cycles IEW is unblocking
+system.cpu.iew.iewDispatchedInsts           396408793                       # Number of instructions dispatched to IQ
+system.cpu.iew.iewDispSquashedInsts            134440                       # Number of squashed instructions skipped by dispatch
+system.cpu.iew.iewDispLoadInsts             104184220                       # Number of dispatched load instructions
+system.cpu.iew.iewDispStoreInsts             37252864                       # Number of dispatched store instructions
+system.cpu.iew.iewDispNonSpecInsts               1768                       # Number of dispatched non-speculative instructions
+system.cpu.iew.iewIQFullEvents                 119463                       # Number of times the IQ has become full, causing a stall
+system.cpu.iew.iewLSQFullEvents                 15480                       # Number of times the LSQ has become full, causing a stall
+system.cpu.iew.memOrderViolationEvents         347654                       # Number of memory order violations
+system.cpu.iew.predictedTakenIncorrect        2501516                       # Number of branches that were predicted taken incorrectly
+system.cpu.iew.predictedNotTakenIncorrect       594763                       # Number of branches that were predicted not taken incorrectly
+system.cpu.iew.branchMispredicts              3096279                       # Number of branch mispredicts detected at execute
+system.cpu.iew.iewExecutedInsts             283823488                       # Number of executed instructions
+system.cpu.iew.iewExecLoadInsts              71745820                       # Number of load instructions executed
+system.cpu.iew.iewExecSquashedInsts           3858508                       # Number of squashed instructions skipped in execute
 system.cpu.iew.exec_swp                             0                       # number of swp insts executed
 system.cpu.iew.exec_nop                             0                       # number of nop insts executed
-system.cpu.iew.exec_refs                     95739480                       # number of memory reference insts executed
-system.cpu.iew.exec_branches                 15662592                       # Number of branches executed
-system.cpu.iew.exec_stores                   24049519                       # Number of stores executed
-system.cpu.iew.exec_rate                     1.467868                       # Inst execution rate
-system.cpu.iew.wb_sent                      282319460                       # cumulative count of insts sent to commit
-system.cpu.iew.wb_count                     281022910                       # cumulative count of insts written-back
-system.cpu.iew.wb_producers                 227917239                       # num instructions producing a value
-system.cpu.iew.wb_consumers                 378870882                       # num instructions consuming a value
+system.cpu.iew.exec_refs                     95800830                       # number of memory reference insts executed
+system.cpu.iew.exec_branches                 15659373                       # Number of branches executed
+system.cpu.iew.exec_stores                   24055010                       # Number of stores executed
+system.cpu.iew.exec_rate                     1.468989                       # Inst execution rate
+system.cpu.iew.wb_sent                      282310074                       # cumulative count of insts sent to commit
+system.cpu.iew.wb_count                     281014609                       # cumulative count of insts written-back
+system.cpu.iew.wb_producers                 227952457                       # num instructions producing a value
+system.cpu.iew.wb_consumers                 378837228                       # num instructions consuming a value
 system.cpu.iew.wb_penalized                         0                       # number of instrctions required to write to 'other' IQ
-system.cpu.iew.wb_rate                       1.453218                       # insts written-back per cycle
-system.cpu.iew.wb_fanout                     0.601570                       # average fanout of values written-back
+system.cpu.iew.wb_rate                       1.454451                       # insts written-back per cycle
+system.cpu.iew.wb_fanout                     0.601716                       # average fanout of values written-back
 system.cpu.iew.wb_penalized_rate                    0                       # fraction of instructions written-back that wrote to 'other' IQ
 system.cpu.commit.commitCommittedInsts      221363017                       # The number of committed instructions
-system.cpu.commit.commitSquashedInsts       175435625                       # The number of squashed insts skipped by commit
+system.cpu.commit.commitSquashedInsts       175071707                       # The number of squashed insts skipped by commit
 system.cpu.commit.commitNonSpecStalls            1246                       # The number of times commit has been forced to stall to communicate backwards
-system.cpu.commit.branchMispredicts           2898838                       # The number of times a branch was mispredicted
-system.cpu.commit.committed_per_cycle::samples    169572692                       # Number of insts commited each cycle
-system.cpu.commit.committed_per_cycle::mean     1.305417                       # Number of insts commited each cycle
-system.cpu.commit.committed_per_cycle::stdev     1.741291                       # Number of insts commited each cycle
+system.cpu.commit.branchMispredicts           2895631                       # The number of times a branch was mispredicted
+system.cpu.commit.committed_per_cycle::samples    169446929                       # Number of insts commited each cycle
+system.cpu.commit.committed_per_cycle::mean     1.306386                       # Number of insts commited each cycle
+system.cpu.commit.committed_per_cycle::stdev     1.743043                       # Number of insts commited each cycle
 system.cpu.commit.committed_per_cycle::underflows            0      0.00%      0.00% # Number of insts commited each cycle
-system.cpu.commit.committed_per_cycle::0     63662174     37.54%     37.54% # Number of insts commited each cycle
-system.cpu.commit.committed_per_cycle::1     62350604     36.77%     74.31% # Number of insts commited each cycle
-system.cpu.commit.committed_per_cycle::2     15592003      9.19%     83.51% # Number of insts commited each cycle
-system.cpu.commit.committed_per_cycle::3     11999288      7.08%     90.58% # Number of insts commited each cycle
-system.cpu.commit.committed_per_cycle::4      5440588      3.21%     93.79% # Number of insts commited each cycle
-system.cpu.commit.committed_per_cycle::5      2982193      1.76%     95.55% # Number of insts commited each cycle
-system.cpu.commit.committed_per_cycle::6      2011991      1.19%     96.74% # Number of insts commited each cycle
-system.cpu.commit.committed_per_cycle::7      1185528      0.70%     97.44% # Number of insts commited each cycle
-system.cpu.commit.committed_per_cycle::8      4348323      2.56%    100.00% # Number of insts commited each cycle
+system.cpu.commit.committed_per_cycle::0     63655929     37.57%     37.57% # Number of insts commited each cycle
+system.cpu.commit.committed_per_cycle::1     62181133     36.70%     74.26% # Number of insts commited each cycle
+system.cpu.commit.committed_per_cycle::2     15647987      9.23%     83.50% # Number of insts commited each cycle
+system.cpu.commit.committed_per_cycle::3     11995121      7.08%     90.58% # Number of insts commited each cycle
+system.cpu.commit.committed_per_cycle::4      5411057      3.19%     93.77% # Number of insts commited each cycle
+system.cpu.commit.committed_per_cycle::5      2989620      1.76%     95.53% # Number of insts commited each cycle
+system.cpu.commit.committed_per_cycle::6      2014905      1.19%     96.72% # Number of insts commited each cycle
+system.cpu.commit.committed_per_cycle::7      1190627      0.70%     97.43% # Number of insts commited each cycle
+system.cpu.commit.committed_per_cycle::8      4360550      2.57%    100.00% # Number of insts commited each cycle
 system.cpu.commit.committed_per_cycle::overflows            0      0.00%    100.00% # Number of insts commited each cycle
 system.cpu.commit.committed_per_cycle::min_value            0                       # Number of insts commited each cycle
 system.cpu.commit.committed_per_cycle::max_value            8                       # Number of insts commited each cycle
-system.cpu.commit.committed_per_cycle::total    169572692                       # Number of insts commited each cycle
+system.cpu.commit.committed_per_cycle::total    169446929                       # Number of insts commited each cycle
 system.cpu.commit.count                     221363017                       # Number of instructions committed
 system.cpu.commit.swp_count                         0                       # Number of s/w prefetches committed
 system.cpu.commit.refs                       77165306                       # Number of memory references committed
@@ -265,50 +265,50 @@
 system.cpu.commit.fp_insts                    2162459                       # Number of committed floating point instructions.
 system.cpu.commit.int_insts                 220339606                       # Number of committed integer instructions.
 system.cpu.commit.function_calls                    0                       # Number of function calls committed.
-system.cpu.commit.bw_lim_events               4348323                       # number cycles where commit BW limit reached
+system.cpu.commit.bw_lim_events               4360550                       # number cycles where commit BW limit reached
 system.cpu.commit.bw_limited                        0                       # number of insts not committed due to BW limits
-system.cpu.rob.rob_reads                    562023011                       # The number of ROB reads
-system.cpu.rob.rob_writes                   817360743                       # The number of ROB writes
-system.cpu.timesIdled                            1880                       # Number of times that the entire CPU went into an idle state and unscheduled itself
-system.cpu.idleCycles                           86590                       # Total number of cycles that the CPU has spent unscheduled due to idling
+system.cpu.rob.rob_reads                    561521103                       # The number of ROB reads
+system.cpu.rob.rob_writes                   816599274                       # The number of ROB writes
+system.cpu.timesIdled                            1748                       # Number of times that the entire CPU went into an idle state and unscheduled itself
+system.cpu.idleCycles                           80265                       # Total number of cycles that the CPU has spent unscheduled due to idling
 system.cpu.committedInsts                   221363017                       # Number of Instructions Simulated
 system.cpu.committedInsts_total             221363017                       # Number of Instructions Simulated
-system.cpu.cpi                               0.873587                       # CPI: Cycles Per Instruction
-system.cpu.cpi_total                         0.873587                       # CPI: Total CPI of All Threads
-system.cpu.ipc                               1.144706                       # IPC: Instructions Per Cycle
-system.cpu.ipc_total                         1.144706                       # IPC: Total IPC of All Threads
-system.cpu.int_regfile_reads                530675330                       # number of integer regfile reads
-system.cpu.int_regfile_writes               288962100                       # number of integer regfile writes
-system.cpu.fp_regfile_reads                   3614411                       # number of floating regfile reads
-system.cpu.fp_regfile_writes                  2302807                       # number of floating regfile writes
-system.cpu.misc_regfile_reads               149913222                       # number of misc regfile reads
+system.cpu.cpi                               0.872820                       # CPI: Cycles Per Instruction
+system.cpu.cpi_total                         0.872820                       # CPI: Total CPI of All Threads
+system.cpu.ipc                               1.145711                       # IPC: Instructions Per Cycle
+system.cpu.ipc_total                         1.145711                       # IPC: Total IPC of All Threads
+system.cpu.int_regfile_reads                530797158                       # number of integer regfile reads
+system.cpu.int_regfile_writes               288957450                       # number of integer regfile writes
+system.cpu.fp_regfile_reads                   3607584                       # number of floating regfile reads
+system.cpu.fp_regfile_writes                  2298041                       # number of floating regfile writes
+system.cpu.misc_regfile_reads               149916629                       # number of misc regfile reads
 system.cpu.misc_regfile_writes                    844                       # number of misc regfile writes
-system.cpu.icache.replacements                   4227                       # number of replacements
-system.cpu.icache.tagsinuse               1595.324923                       # Cycle average of tags in use
-system.cpu.icache.total_refs                 28852140                       # Total number of references to valid blocks.
-system.cpu.icache.sampled_refs                   6194                       # Sample count of references to valid blocks.
-system.cpu.icache.avg_refs                4658.078786                       # Average number of references to valid blocks.
+system.cpu.icache.replacements                   4194                       # number of replacements
+system.cpu.icache.tagsinuse               1596.157530                       # Cycle average of tags in use
+system.cpu.icache.total_refs                 28821740                       # Total number of references to valid blocks.
+system.cpu.icache.sampled_refs                   6159                       # Sample count of references to valid blocks.
+system.cpu.icache.avg_refs                4679.613574                       # Average number of references to valid blocks.
 system.cpu.icache.warmup_cycle                      0                       # Cycle when the warmup percentage was hit.
-system.cpu.icache.occ_blocks::0           1595.324923                       # Average occupied blocks per context
-system.cpu.icache.occ_percent::0             0.778967                       # Average percentage of cache occupancy
-system.cpu.icache.ReadReq_hits               28852140                       # number of ReadReq hits
-system.cpu.icache.demand_hits                28852140                       # number of demand (read+write) hits
-system.cpu.icache.overall_hits               28852140                       # number of overall hits
-system.cpu.icache.ReadReq_misses                 7589                       # number of ReadReq misses
-system.cpu.icache.demand_misses                  7589                       # number of demand (read+write) misses
-system.cpu.icache.overall_misses                 7589                       # number of overall misses
-system.cpu.icache.ReadReq_miss_latency      174464500                       # number of ReadReq miss cycles
-system.cpu.icache.demand_miss_latency       174464500                       # number of demand (read+write) miss cycles
-system.cpu.icache.overall_miss_latency      174464500                       # number of overall miss cycles
-system.cpu.icache.ReadReq_accesses           28859729                       # number of ReadReq accesses(hits+misses)
-system.cpu.icache.demand_accesses            28859729                       # number of demand (read+write) accesses
-system.cpu.icache.overall_accesses           28859729                       # number of overall (read+write) accesses
-system.cpu.icache.ReadReq_miss_rate          0.000263                       # miss rate for ReadReq accesses
-system.cpu.icache.demand_miss_rate           0.000263                       # miss rate for demand accesses
-system.cpu.icache.overall_miss_rate          0.000263                       # miss rate for overall accesses
-system.cpu.icache.ReadReq_avg_miss_latency 22989.129003                       # average ReadReq miss latency
-system.cpu.icache.demand_avg_miss_latency 22989.129003                       # average overall miss latency
-system.cpu.icache.overall_avg_miss_latency 22989.129003                       # average overall miss latency
+system.cpu.icache.occ_blocks::0           1596.157530                       # Average occupied blocks per context
+system.cpu.icache.occ_percent::0             0.779374                       # Average percentage of cache occupancy
+system.cpu.icache.ReadReq_hits               28821740                       # number of ReadReq hits
+system.cpu.icache.demand_hits                28821740                       # number of demand (read+write) hits
+system.cpu.icache.overall_hits               28821740                       # number of overall hits
+system.cpu.icache.ReadReq_misses                 7534                       # number of ReadReq misses
+system.cpu.icache.demand_misses                  7534                       # number of demand (read+write) misses
+system.cpu.icache.overall_misses                 7534                       # number of overall misses
+system.cpu.icache.ReadReq_miss_latency      174012500                       # number of ReadReq miss cycles
+system.cpu.icache.demand_miss_latency       174012500                       # number of demand (read+write) miss cycles
+system.cpu.icache.overall_miss_latency      174012500                       # number of overall miss cycles
+system.cpu.icache.ReadReq_accesses           28829274                       # number of ReadReq accesses(hits+misses)
+system.cpu.icache.demand_accesses            28829274                       # number of demand (read+write) accesses
+system.cpu.icache.overall_accesses           28829274                       # number of overall (read+write) accesses
+system.cpu.icache.ReadReq_miss_rate          0.000261                       # miss rate for ReadReq accesses
+system.cpu.icache.demand_miss_rate           0.000261                       # miss rate for demand accesses
+system.cpu.icache.overall_miss_rate          0.000261                       # miss rate for overall accesses
+system.cpu.icache.ReadReq_avg_miss_latency 23096.960446                       # average ReadReq miss latency
+system.cpu.icache.demand_avg_miss_latency 23096.960446                       # average overall miss latency
+system.cpu.icache.overall_avg_miss_latency 23096.960446                       # average overall miss latency
 system.cpu.icache.blocked_cycles::no_mshrs            0                       # number of cycles access was blocked
 system.cpu.icache.blocked_cycles::no_targets            0                       # number of cycles access was blocked
 system.cpu.icache.blocked::no_mshrs                 0                       # number of cycles access was blocked
@@ -318,59 +318,59 @@
 system.cpu.icache.fast_writes                       0                       # number of fast writes performed
 system.cpu.icache.cache_copies                      0                       # number of cache copies performed
 system.cpu.icache.writebacks                        0                       # number of writebacks
-system.cpu.icache.ReadReq_mshr_hits              1125                       # number of ReadReq MSHR hits
-system.cpu.icache.demand_mshr_hits               1125                       # number of demand (read+write) MSHR hits
-system.cpu.icache.overall_mshr_hits              1125                       # number of overall MSHR hits
-system.cpu.icache.ReadReq_mshr_misses            6464                       # number of ReadReq MSHR misses
-system.cpu.icache.demand_mshr_misses             6464                       # number of demand (read+write) MSHR misses
-system.cpu.icache.overall_mshr_misses            6464                       # number of overall MSHR misses
+system.cpu.icache.ReadReq_mshr_hits              1131                       # number of ReadReq MSHR hits
+system.cpu.icache.demand_mshr_hits               1131                       # number of demand (read+write) MSHR hits
+system.cpu.icache.overall_mshr_hits              1131                       # number of overall MSHR hits
+system.cpu.icache.ReadReq_mshr_misses            6403                       # number of ReadReq MSHR misses
+system.cpu.icache.demand_mshr_misses             6403                       # number of demand (read+write) MSHR misses
+system.cpu.icache.overall_mshr_misses            6403                       # number of overall MSHR misses
 system.cpu.icache.overall_mshr_uncacheable_misses            0                       # number of overall MSHR uncacheable misses
-system.cpu.icache.ReadReq_mshr_miss_latency    125677000                       # number of ReadReq MSHR miss cycles
-system.cpu.icache.demand_mshr_miss_latency    125677000                       # number of demand (read+write) MSHR miss cycles
-system.cpu.icache.overall_mshr_miss_latency    125677000                       # number of overall MSHR miss cycles
+system.cpu.icache.ReadReq_mshr_miss_latency    125261500                       # number of ReadReq MSHR miss cycles
+system.cpu.icache.demand_mshr_miss_latency    125261500                       # number of demand (read+write) MSHR miss cycles
+system.cpu.icache.overall_mshr_miss_latency    125261500                       # number of overall MSHR miss cycles
 system.cpu.icache.overall_mshr_uncacheable_latency            0                       # number of overall MSHR uncacheable cycles
-system.cpu.icache.ReadReq_mshr_miss_rate     0.000224                       # mshr miss rate for ReadReq accesses
-system.cpu.icache.demand_mshr_miss_rate      0.000224                       # mshr miss rate for demand accesses
-system.cpu.icache.overall_mshr_miss_rate     0.000224                       # mshr miss rate for overall accesses
-system.cpu.icache.ReadReq_avg_mshr_miss_latency 19442.605198                       # average ReadReq mshr miss latency
-system.cpu.icache.demand_avg_mshr_miss_latency 19442.605198                       # average overall mshr miss latency
-system.cpu.icache.overall_avg_mshr_miss_latency 19442.605198                       # average overall mshr miss latency
+system.cpu.icache.ReadReq_mshr_miss_rate     0.000222                       # mshr miss rate for ReadReq accesses
+system.cpu.icache.demand_mshr_miss_rate      0.000222                       # mshr miss rate for demand accesses
+system.cpu.icache.overall_mshr_miss_rate     0.000222                       # mshr miss rate for overall accesses
+system.cpu.icache.ReadReq_avg_mshr_miss_latency 19562.939247                       # average ReadReq mshr miss latency
+system.cpu.icache.demand_avg_mshr_miss_latency 19562.939247                       # average overall mshr miss latency
+system.cpu.icache.overall_avg_mshr_miss_latency 19562.939247                       # average overall mshr miss latency
 system.cpu.icache.overall_avg_mshr_uncacheable_latency     no_value                       # average overall mshr uncacheable latency
 system.cpu.icache.mshr_cap_events                   0                       # number of times MSHR cap was activated
 system.cpu.icache.soft_prefetch_mshr_full            0                       # number of mshr full events for SW prefetching instrutions
 system.cpu.icache.no_allocate_misses                0                       # Number of misses that were no-allocate
-system.cpu.dcache.replacements                     59                       # number of replacements
-system.cpu.dcache.tagsinuse               1416.877097                       # Cycle average of tags in use
-system.cpu.dcache.total_refs                 73598603                       # Total number of references to valid blocks.
-system.cpu.dcache.sampled_refs                   1986                       # Sample count of references to valid blocks.
-system.cpu.dcache.avg_refs               37058.712487                       # Average number of references to valid blocks.
+system.cpu.dcache.replacements                     57                       # number of replacements
+system.cpu.dcache.tagsinuse               1416.139533                       # Cycle average of tags in use
+system.cpu.dcache.total_refs                 73025896                       # Total number of references to valid blocks.
+system.cpu.dcache.sampled_refs                   1980                       # Sample count of references to valid blocks.
+system.cpu.dcache.avg_refs               36881.765657                       # Average number of references to valid blocks.
 system.cpu.dcache.warmup_cycle                      0                       # Cycle when the warmup percentage was hit.
-system.cpu.dcache.occ_blocks::0           1416.877097                       # Average occupied blocks per context
-system.cpu.dcache.occ_percent::0             0.345917                       # Average percentage of cache occupancy
-system.cpu.dcache.ReadReq_hits               53090649                       # number of ReadReq hits
-system.cpu.dcache.WriteReq_hits              20507453                       # number of WriteReq hits
-system.cpu.dcache.demand_hits                73598102                       # number of demand (read+write) hits
-system.cpu.dcache.overall_hits               73598102                       # number of overall hits
-system.cpu.dcache.ReadReq_misses                  848                       # number of ReadReq misses
-system.cpu.dcache.WriteReq_misses                8277                       # number of WriteReq misses
-system.cpu.dcache.demand_misses                  9125                       # number of demand (read+write) misses
-system.cpu.dcache.overall_misses                 9125                       # number of overall misses
-system.cpu.dcache.ReadReq_miss_latency       26447500                       # number of ReadReq miss cycles
-system.cpu.dcache.WriteReq_miss_latency     228348000                       # number of WriteReq miss cycles
-system.cpu.dcache.demand_miss_latency       254795500                       # number of demand (read+write) miss cycles
-system.cpu.dcache.overall_miss_latency      254795500                       # number of overall miss cycles
-system.cpu.dcache.ReadReq_accesses           53091497                       # number of ReadReq accesses(hits+misses)
+system.cpu.dcache.occ_blocks::0           1416.139533                       # Average occupied blocks per context
+system.cpu.dcache.occ_percent::0             0.345737                       # Average percentage of cache occupancy
+system.cpu.dcache.ReadReq_hits               52511655                       # number of ReadReq hits
+system.cpu.dcache.WriteReq_hits              20513921                       # number of WriteReq hits
+system.cpu.dcache.demand_hits                73025576                       # number of demand (read+write) hits
+system.cpu.dcache.overall_hits               73025576                       # number of overall hits
+system.cpu.dcache.ReadReq_misses                  756                       # number of ReadReq misses
+system.cpu.dcache.WriteReq_misses                1809                       # number of WriteReq misses
+system.cpu.dcache.demand_misses                  2565                       # number of demand (read+write) misses
+system.cpu.dcache.overall_misses                 2565                       # number of overall misses
+system.cpu.dcache.ReadReq_miss_latency       24125500                       # number of ReadReq miss cycles
+system.cpu.dcache.WriteReq_miss_latency      68553000                       # number of WriteReq miss cycles
+system.cpu.dcache.demand_miss_latency        92678500                       # number of demand (read+write) miss cycles
+system.cpu.dcache.overall_miss_latency       92678500                       # number of overall miss cycles
+system.cpu.dcache.ReadReq_accesses           52512411                       # number of ReadReq accesses(hits+misses)
 system.cpu.dcache.WriteReq_accesses          20515730                       # number of WriteReq accesses(hits+misses)
-system.cpu.dcache.demand_accesses            73607227                       # number of demand (read+write) accesses
-system.cpu.dcache.overall_accesses           73607227                       # number of overall (read+write) accesses
-system.cpu.dcache.ReadReq_miss_rate          0.000016                       # miss rate for ReadReq accesses
-system.cpu.dcache.WriteReq_miss_rate         0.000403                       # miss rate for WriteReq accesses
-system.cpu.dcache.demand_miss_rate           0.000124                       # miss rate for demand accesses
-system.cpu.dcache.overall_miss_rate          0.000124                       # miss rate for overall accesses
-system.cpu.dcache.ReadReq_avg_miss_latency 31188.089623                       # average ReadReq miss latency
-system.cpu.dcache.WriteReq_avg_miss_latency 27588.256615                       # average WriteReq miss latency
-system.cpu.dcache.demand_avg_miss_latency 27922.794521                       # average overall miss latency
-system.cpu.dcache.overall_avg_miss_latency 27922.794521                       # average overall miss latency
+system.cpu.dcache.demand_accesses            73028141                       # number of demand (read+write) accesses
+system.cpu.dcache.overall_accesses           73028141                       # number of overall (read+write) accesses
+system.cpu.dcache.ReadReq_miss_rate          0.000014                       # miss rate for ReadReq accesses
+system.cpu.dcache.WriteReq_miss_rate         0.000088                       # miss rate for WriteReq accesses
+system.cpu.dcache.demand_miss_rate           0.000035                       # miss rate for demand accesses
+system.cpu.dcache.overall_miss_rate          0.000035                       # miss rate for overall accesses
+system.cpu.dcache.ReadReq_avg_miss_latency 31912.037037                       # average ReadReq miss latency
+system.cpu.dcache.WriteReq_avg_miss_latency 37895.522388                       # average WriteReq miss latency
+system.cpu.dcache.demand_avg_miss_latency 36131.968811                       # average overall miss latency
+system.cpu.dcache.overall_avg_miss_latency 36131.968811                       # average overall miss latency
 system.cpu.dcache.blocked_cycles::no_mshrs            0                       # number of cycles access was blocked
 system.cpu.dcache.blocked_cycles::no_targets            0                       # number of cycles access was blocked
 system.cpu.dcache.blocked::no_mshrs                 0                       # number of cycles access was blocked
@@ -380,71 +380,71 @@
 system.cpu.dcache.fast_writes                       0                       # number of fast writes performed
 system.cpu.dcache.cache_copies                      0                       # number of cache copies performed
 system.cpu.dcache.writebacks                       14                       # number of writebacks
-system.cpu.dcache.ReadReq_mshr_hits               424                       # number of ReadReq MSHR hits
-system.cpu.dcache.WriteReq_mshr_hits             6443                       # number of WriteReq MSHR hits
-system.cpu.dcache.demand_mshr_hits               6867                       # number of demand (read+write) MSHR hits
-system.cpu.dcache.overall_mshr_hits              6867                       # number of overall MSHR hits
-system.cpu.dcache.ReadReq_mshr_misses             424                       # number of ReadReq MSHR misses
-system.cpu.dcache.WriteReq_mshr_misses           1834                       # number of WriteReq MSHR misses
-system.cpu.dcache.demand_mshr_misses             2258                       # number of demand (read+write) MSHR misses
-system.cpu.dcache.overall_mshr_misses            2258                       # number of overall MSHR misses
+system.cpu.dcache.ReadReq_mshr_hits               336                       # number of ReadReq MSHR hits
+system.cpu.dcache.WriteReq_mshr_hits                2                       # number of WriteReq MSHR hits
+system.cpu.dcache.demand_mshr_hits                338                       # number of demand (read+write) MSHR hits
+system.cpu.dcache.overall_mshr_hits               338                       # number of overall MSHR hits
+system.cpu.dcache.ReadReq_mshr_misses             420                       # number of ReadReq MSHR misses
+system.cpu.dcache.WriteReq_mshr_misses           1807                       # number of WriteReq MSHR misses
+system.cpu.dcache.demand_mshr_misses             2227                       # number of demand (read+write) MSHR misses
+system.cpu.dcache.overall_mshr_misses            2227                       # number of overall MSHR misses
 system.cpu.dcache.overall_mshr_uncacheable_misses            0                       # number of overall MSHR uncacheable misses
-system.cpu.dcache.ReadReq_mshr_miss_latency     13981500                       # number of ReadReq MSHR miss cycles
-system.cpu.dcache.WriteReq_mshr_miss_latency     64146500                       # number of WriteReq MSHR miss cycles
-system.cpu.dcache.demand_mshr_miss_latency     78128000                       # number of demand (read+write) MSHR miss cycles
-system.cpu.dcache.overall_mshr_miss_latency     78128000                       # number of overall MSHR miss cycles
+system.cpu.dcache.ReadReq_mshr_miss_latency     13927500                       # number of ReadReq MSHR miss cycles
+system.cpu.dcache.WriteReq_mshr_miss_latency     63059000                       # number of WriteReq MSHR miss cycles
+system.cpu.dcache.demand_mshr_miss_latency     76986500                       # number of demand (read+write) MSHR miss cycles
+system.cpu.dcache.overall_mshr_miss_latency     76986500                       # number of overall MSHR miss cycles
 system.cpu.dcache.overall_mshr_uncacheable_latency            0                       # number of overall MSHR uncacheable cycles
 system.cpu.dcache.ReadReq_mshr_miss_rate     0.000008                       # mshr miss rate for ReadReq accesses
-system.cpu.dcache.WriteReq_mshr_miss_rate     0.000089                       # mshr miss rate for WriteReq accesses
-system.cpu.dcache.demand_mshr_miss_rate      0.000031                       # mshr miss rate for demand accesses
-system.cpu.dcache.overall_mshr_miss_rate     0.000031                       # mshr miss rate for overall accesses
-system.cpu.dcache.ReadReq_avg_mshr_miss_latency 32975.235849                       # average ReadReq mshr miss latency
-system.cpu.dcache.WriteReq_avg_mshr_miss_latency 34976.281352                       # average WriteReq mshr miss latency
-system.cpu.dcache.demand_avg_mshr_miss_latency 34600.531444                       # average overall mshr miss latency
-system.cpu.dcache.overall_avg_mshr_miss_latency 34600.531444                       # average overall mshr miss latency
+system.cpu.dcache.WriteReq_mshr_miss_rate     0.000088                       # mshr miss rate for WriteReq accesses
+system.cpu.dcache.demand_mshr_miss_rate      0.000030                       # mshr miss rate for demand accesses
+system.cpu.dcache.overall_mshr_miss_rate     0.000030                       # mshr miss rate for overall accesses
+system.cpu.dcache.ReadReq_avg_mshr_miss_latency 33160.714286                       # average ReadReq mshr miss latency
+system.cpu.dcache.WriteReq_avg_mshr_miss_latency 34897.066962                       # average WriteReq mshr miss latency
+system.cpu.dcache.demand_avg_mshr_miss_latency 34569.600359                       # average overall mshr miss latency
+system.cpu.dcache.overall_avg_mshr_miss_latency 34569.600359                       # average overall mshr miss latency
 system.cpu.dcache.overall_avg_mshr_uncacheable_latency     no_value                       # average overall mshr uncacheable latency
 system.cpu.dcache.mshr_cap_events                   0                       # number of times MSHR cap was activated
 system.cpu.dcache.soft_prefetch_mshr_full            0                       # number of mshr full events for SW prefetching instrutions
 system.cpu.dcache.no_allocate_misses                0                       # Number of misses that were no-allocate
 system.cpu.l2cache.replacements                     0                       # number of replacements
-system.cpu.l2cache.tagsinuse              2499.166941                       # Cycle average of tags in use
-system.cpu.l2cache.total_refs                    2858                       # Total number of references to valid blocks.
-system.cpu.l2cache.sampled_refs                  3763                       # Sample count of references to valid blocks.
-system.cpu.l2cache.avg_refs                  0.759500                       # Average number of references to valid blocks.
+system.cpu.l2cache.tagsinuse              2497.262524                       # Cycle average of tags in use
+system.cpu.l2cache.total_refs                    2830                       # Total number of references to valid blocks.
+system.cpu.l2cache.sampled_refs                  3752                       # Sample count of references to valid blocks.
+system.cpu.l2cache.avg_refs                  0.754264                       # Average number of references to valid blocks.
 system.cpu.l2cache.warmup_cycle                     0                       # Cycle when the warmup percentage was hit.
-system.cpu.l2cache.occ_blocks::0          2497.181729                       # Average occupied blocks per context
-system.cpu.l2cache.occ_blocks::1             1.985212                       # Average occupied blocks per context
-system.cpu.l2cache.occ_percent::0            0.076208                       # Average percentage of cache occupancy
-system.cpu.l2cache.occ_percent::1            0.000061                       # Average percentage of cache occupancy
-system.cpu.l2cache.ReadReq_hits                  2857                       # number of ReadReq hits
+system.cpu.l2cache.occ_blocks::0          2495.282024                       # Average occupied blocks per context
+system.cpu.l2cache.occ_blocks::1             1.980500                       # Average occupied blocks per context
+system.cpu.l2cache.occ_percent::0            0.076150                       # Average percentage of cache occupancy
+system.cpu.l2cache.occ_percent::1            0.000060                       # Average percentage of cache occupancy
+system.cpu.l2cache.ReadReq_hits                  2828                       # number of ReadReq hits
 system.cpu.l2cache.Writeback_hits                  14                       # number of Writeback hits
 system.cpu.l2cache.ReadExReq_hits                   8                       # number of ReadExReq hits
-system.cpu.l2cache.demand_hits                   2865                       # number of demand (read+write) hits
-system.cpu.l2cache.overall_hits                  2865                       # number of overall hits
-system.cpu.l2cache.ReadReq_misses                3759                       # number of ReadReq misses
-system.cpu.l2cache.UpgradeReq_misses              270                       # number of UpgradeReq misses
-system.cpu.l2cache.ReadExReq_misses              1557                       # number of ReadExReq misses
-system.cpu.l2cache.demand_misses                 5316                       # number of demand (read+write) misses
-system.cpu.l2cache.overall_misses                5316                       # number of overall misses
-system.cpu.l2cache.ReadReq_miss_latency     128731000                       # number of ReadReq miss cycles
-system.cpu.l2cache.ReadExReq_miss_latency     53240500                       # number of ReadExReq miss cycles
-system.cpu.l2cache.demand_miss_latency      181971500                       # number of demand (read+write) miss cycles
-system.cpu.l2cache.overall_miss_latency     181971500                       # number of overall miss cycles
-system.cpu.l2cache.ReadReq_accesses              6616                       # number of ReadReq accesses(hits+misses)
+system.cpu.l2cache.demand_hits                   2836                       # number of demand (read+write) hits
+system.cpu.l2cache.overall_hits                  2836                       # number of overall hits
+system.cpu.l2cache.ReadReq_misses                3749                       # number of ReadReq misses
+system.cpu.l2cache.UpgradeReq_misses              245                       # number of UpgradeReq misses
+system.cpu.l2cache.ReadExReq_misses              1555                       # number of ReadExReq misses
+system.cpu.l2cache.demand_misses                 5304                       # number of demand (read+write) misses
+system.cpu.l2cache.overall_misses                5304                       # number of overall misses
+system.cpu.l2cache.ReadReq_miss_latency     128398000                       # number of ReadReq miss cycles
+system.cpu.l2cache.ReadExReq_miss_latency     53104500                       # number of ReadExReq miss cycles
+system.cpu.l2cache.demand_miss_latency      181502500                       # number of demand (read+write) miss cycles
+system.cpu.l2cache.overall_miss_latency     181502500                       # number of overall miss cycles
+system.cpu.l2cache.ReadReq_accesses              6577                       # number of ReadReq accesses(hits+misses)
 system.cpu.l2cache.Writeback_accesses              14                       # number of Writeback accesses(hits+misses)
-system.cpu.l2cache.UpgradeReq_accesses            270                       # number of UpgradeReq accesses(hits+misses)
-system.cpu.l2cache.ReadExReq_accesses            1565                       # number of ReadExReq accesses(hits+misses)
-system.cpu.l2cache.demand_accesses               8181                       # number of demand (read+write) accesses
-system.cpu.l2cache.overall_accesses              8181                       # number of overall (read+write) accesses
-system.cpu.l2cache.ReadReq_miss_rate         0.568168                       # miss rate for ReadReq accesses
+system.cpu.l2cache.UpgradeReq_accesses            245                       # number of UpgradeReq accesses(hits+misses)
+system.cpu.l2cache.ReadExReq_accesses            1563                       # number of ReadExReq accesses(hits+misses)
+system.cpu.l2cache.demand_accesses               8140                       # number of demand (read+write) accesses
+system.cpu.l2cache.overall_accesses              8140                       # number of overall (read+write) accesses
+system.cpu.l2cache.ReadReq_miss_rate         0.570017                       # miss rate for ReadReq accesses
 system.cpu.l2cache.UpgradeReq_miss_rate             1                       # miss rate for UpgradeReq accesses
-system.cpu.l2cache.ReadExReq_miss_rate       0.994888                       # miss rate for ReadExReq accesses
-system.cpu.l2cache.demand_miss_rate          0.649798                       # miss rate for demand accesses
-system.cpu.l2cache.overall_miss_rate         0.649798                       # miss rate for overall accesses
-system.cpu.l2cache.ReadReq_avg_miss_latency 34246.076084                       # average ReadReq miss latency
-system.cpu.l2cache.ReadExReq_avg_miss_latency 34194.283879                       # average ReadExReq miss latency
-system.cpu.l2cache.demand_avg_miss_latency 34230.906697                       # average overall miss latency
-system.cpu.l2cache.overall_avg_miss_latency 34230.906697                       # average overall miss latency
+system.cpu.l2cache.ReadExReq_miss_rate       0.994882                       # miss rate for ReadExReq accesses
+system.cpu.l2cache.demand_miss_rate          0.651597                       # miss rate for demand accesses
+system.cpu.l2cache.overall_miss_rate         0.651597                       # miss rate for overall accesses
+system.cpu.l2cache.ReadReq_avg_miss_latency 34248.599627                       # average ReadReq miss latency
+system.cpu.l2cache.ReadExReq_avg_miss_latency 34150.803859                       # average ReadExReq miss latency
+system.cpu.l2cache.demand_avg_miss_latency 34219.928356                       # average overall miss latency
+system.cpu.l2cache.overall_avg_miss_latency 34219.928356                       # average overall miss latency
 system.cpu.l2cache.blocked_cycles::no_mshrs            0                       # number of cycles access was blocked
 system.cpu.l2cache.blocked_cycles::no_targets            0                       # number of cycles access was blocked
 system.cpu.l2cache.blocked::no_mshrs                0                       # number of cycles access was blocked
@@ -456,28 +456,28 @@
 system.cpu.l2cache.writebacks                       0                       # number of writebacks
 system.cpu.l2cache.demand_mshr_hits                 0                       # number of demand (read+write) MSHR hits
 system.cpu.l2cache.overall_mshr_hits                0                       # number of overall MSHR hits
-system.cpu.l2cache.ReadReq_mshr_misses           3759                       # number of ReadReq MSHR misses
-system.cpu.l2cache.UpgradeReq_mshr_misses          270                       # number of UpgradeReq MSHR misses
-system.cpu.l2cache.ReadExReq_mshr_misses         1557                       # number of ReadExReq MSHR misses
-system.cpu.l2cache.demand_mshr_misses            5316                       # number of demand (read+write) MSHR misses
-system.cpu.l2cache.overall_mshr_misses           5316                       # number of overall MSHR misses
+system.cpu.l2cache.ReadReq_mshr_misses           3749                       # number of ReadReq MSHR misses
+system.cpu.l2cache.UpgradeReq_mshr_misses          245                       # number of UpgradeReq MSHR misses
+system.cpu.l2cache.ReadExReq_mshr_misses         1555                       # number of ReadExReq MSHR misses
+system.cpu.l2cache.demand_mshr_misses            5304                       # number of demand (read+write) MSHR misses
+system.cpu.l2cache.overall_mshr_misses           5304                       # number of overall MSHR misses
 system.cpu.l2cache.overall_mshr_uncacheable_misses            0                       # number of overall MSHR uncacheable misses
-system.cpu.l2cache.ReadReq_mshr_miss_latency    116600500                       # number of ReadReq MSHR miss cycles
-system.cpu.l2cache.UpgradeReq_mshr_miss_latency      8370000                       # number of UpgradeReq MSHR miss cycles
-system.cpu.l2cache.ReadExReq_mshr_miss_latency     48374500                       # number of ReadExReq MSHR miss cycles
-system.cpu.l2cache.demand_mshr_miss_latency    164975000                       # number of demand (read+write) MSHR miss cycles
-system.cpu.l2cache.overall_mshr_miss_latency    164975000                       # number of overall MSHR miss cycles
+system.cpu.l2cache.ReadReq_mshr_miss_latency    116287000                       # number of ReadReq MSHR miss cycles
+system.cpu.l2cache.UpgradeReq_mshr_miss_latency      7595000                       # number of UpgradeReq MSHR miss cycles
+system.cpu.l2cache.ReadExReq_mshr_miss_latency     48232500                       # number of ReadExReq MSHR miss cycles
+system.cpu.l2cache.demand_mshr_miss_latency    164519500                       # number of demand (read+write) MSHR miss cycles
+system.cpu.l2cache.overall_mshr_miss_latency    164519500                       # number of overall MSHR miss cycles
 system.cpu.l2cache.overall_mshr_uncacheable_latency            0                       # number of overall MSHR uncacheable cycles
-system.cpu.l2cache.ReadReq_mshr_miss_rate     0.568168                       # mshr miss rate for ReadReq accesses
+system.cpu.l2cache.ReadReq_mshr_miss_rate     0.570017                       # mshr miss rate for ReadReq accesses
 system.cpu.l2cache.UpgradeReq_mshr_miss_rate            1                       # mshr miss rate for UpgradeReq accesses
-system.cpu.l2cache.ReadExReq_mshr_miss_rate     0.994888                       # mshr miss rate for ReadExReq accesses
-system.cpu.l2cache.demand_mshr_miss_rate     0.649798                       # mshr miss rate for demand accesses
-system.cpu.l2cache.overall_mshr_miss_rate     0.649798                       # mshr miss rate for overall accesses
-system.cpu.l2cache.ReadReq_avg_mshr_miss_latency 31019.021016                       # average ReadReq mshr miss latency
+system.cpu.l2cache.ReadExReq_mshr_miss_rate     0.994882                       # mshr miss rate for ReadExReq accesses
+system.cpu.l2cache.demand_mshr_miss_rate     0.651597                       # mshr miss rate for demand accesses
+system.cpu.l2cache.overall_mshr_miss_rate     0.651597                       # mshr miss rate for overall accesses
+system.cpu.l2cache.ReadReq_avg_mshr_miss_latency 31018.138170                       # average ReadReq mshr miss latency
 system.cpu.l2cache.UpgradeReq_avg_mshr_miss_latency        31000                       # average UpgradeReq mshr miss latency
-system.cpu.l2cache.ReadExReq_avg_mshr_miss_latency 31069.043031                       # average ReadExReq mshr miss latency
-system.cpu.l2cache.demand_avg_mshr_miss_latency 31033.671934                       # average overall mshr miss latency
-system.cpu.l2cache.overall_avg_mshr_miss_latency 31033.671934                       # average overall mshr miss latency
+system.cpu.l2cache.ReadExReq_avg_mshr_miss_latency 31017.684887                       # average ReadExReq mshr miss latency
+system.cpu.l2cache.demand_avg_mshr_miss_latency 31018.005279                       # average overall mshr miss latency
+system.cpu.l2cache.overall_avg_mshr_miss_latency 31018.005279                       # average overall mshr miss latency
 system.cpu.l2cache.overall_avg_mshr_uncacheable_latency     no_value                       # average overall mshr uncacheable latency
 system.cpu.l2cache.mshr_cap_events                  0                       # number of times MSHR cap was activated
 system.cpu.l2cache.soft_prefetch_mshr_full            0                       # number of mshr full events for SW prefetching instrutions
diff --git a/tests/quick/00.hello/ref/x86/linux/o3-timing/config.ini b/tests/quick/00.hello/ref/x86/linux/o3-timing/config.ini
index 8582c91..8f8ece2 100644
--- a/tests/quick/00.hello/ref/x86/linux/o3-timing/config.ini
+++ b/tests/quick/00.hello/ref/x86/linux/o3-timing/config.ini
@@ -80,6 +80,7 @@
 max_insts_any_thread=0
 max_loads_all_threads=0
 max_loads_any_thread=0
+needsTSO=true
 numIQEntries=64
 numPhysFloatRegs=256
 numPhysIntRegs=256
@@ -502,7 +503,7 @@
 env=
 errout=cerr
 euid=100
-executable=/dist/m5/regression/test-progs/hello/bin/x86/linux/hello
+executable=tests/test-progs/hello/bin/x86/linux/hello
 gid=100
 input=cin
 max_stack_size=67108864
diff --git a/tests/quick/00.hello/ref/x86/linux/o3-timing/simout b/tests/quick/00.hello/ref/x86/linux/o3-timing/simout
index 4c37192..b49f2b5 100755
--- a/tests/quick/00.hello/ref/x86/linux/o3-timing/simout
+++ b/tests/quick/00.hello/ref/x86/linux/o3-timing/simout
@@ -1,12 +1,13 @@
+Redirecting stdout to build/X86_SE/tests/opt/quick/00.hello/x86/linux/o3-timing/simout
+Redirecting stderr to build/X86_SE/tests/opt/quick/00.hello/x86/linux/o3-timing/simerr
 gem5 Simulator System.  http://gem5.org
 gem5 is copyrighted software; use the --copyright option for details.
 
-gem5 compiled Jan 23 2012 04:08:34
-gem5 started Jan 23 2012 04:24:37
-gem5 executing on zizzer
+gem5 compiled Jan 28 2012 12:11:40
+gem5 started Jan 28 2012 12:11:57
+gem5 executing on ribera.cs.wisc.edu
 command line: build/X86_SE/gem5.opt -d build/X86_SE/tests/opt/quick/00.hello/x86/linux/o3-timing -re tests/run.py build/X86_SE/tests/opt/quick/00.hello/x86/linux/o3-timing
 Global frequency set at 1000000000000 ticks per second
 info: Entering event queue @ 0.  Starting simulation...
-info: Increasing stack size by one page.
 Hello world!
-Exiting @ tick 11087000 because target called exit()
+Exiting @ tick 11989500 because target called exit()
diff --git a/tests/quick/00.hello/ref/x86/linux/o3-timing/stats.txt b/tests/quick/00.hello/ref/x86/linux/o3-timing/stats.txt
index e2df7b0..8477728 100644
--- a/tests/quick/00.hello/ref/x86/linux/o3-timing/stats.txt
+++ b/tests/quick/00.hello/ref/x86/linux/o3-timing/stats.txt
@@ -1,13 +1,13 @@
 
 ---------- Begin Simulation Statistics ----------
-sim_seconds                                  0.000011                       # Number of seconds simulated
-sim_ticks                                    11087000                       # Number of ticks simulated
-final_tick                                   11087000                       # Number of ticks from beginning of simulation (restored from checkpoints and never reset)
+sim_seconds                                  0.000012                       # Number of seconds simulated
+sim_ticks                                    11989500                       # Number of ticks simulated
+final_tick                                   11989500                       # Number of ticks from beginning of simulation (restored from checkpoints and never reset)
 sim_freq                                 1000000000000                       # Frequency of simulated ticks
-host_inst_rate                                  31087                       # Simulator instruction rate (inst/s)
-host_tick_rate                               35135175                       # Simulator tick rate (ticks/s)
-host_mem_usage                                 212404                       # Number of bytes of host memory used
-host_seconds                                     0.32                       # Real time elapsed on the host
+host_inst_rate                                   1330                       # Simulator instruction rate (inst/s)
+host_tick_rate                                1625690                       # Simulator tick rate (ticks/s)
+host_mem_usage                                 239860                       # Number of bytes of host memory used
+host_seconds                                     7.38                       # Real time elapsed on the host
 sim_insts                                        9809                       # Number of instructions simulated
 system.physmem.bytes_read                       28288                       # Number of bytes read from this memory
 system.physmem.bytes_inst_read                  18944                       # Number of instructions bytes read from this memory
@@ -15,247 +15,247 @@
 system.physmem.num_reads                          442                       # Number of read requests responded to by this memory
 system.physmem.num_writes                           0                       # Number of write requests responded to by this memory
 system.physmem.num_other                            0                       # Number of other requests responded to by this memory
-system.physmem.bw_read                     2551456661                       # Total read bandwidth from this memory (bytes/s)
-system.physmem.bw_inst_read                1708667809                       # Instruction read bandwidth from this memory (bytes/s)
-system.physmem.bw_total                    2551456661                       # Total bandwidth to/from this memory (bytes/s)
+system.physmem.bw_read                     2359397806                       # Total read bandwidth from this memory (bytes/s)
+system.physmem.bw_inst_read                1580049210                       # Instruction read bandwidth from this memory (bytes/s)
+system.physmem.bw_total                    2359397806                       # Total bandwidth to/from this memory (bytes/s)
 system.cpu.workload.num_syscalls                   11                       # Number of system calls
-system.cpu.numCycles                            22175                       # number of cpu cycles simulated
+system.cpu.numCycles                            23980                       # number of cpu cycles simulated
 system.cpu.numWorkItemsStarted                      0                       # number of work items this cpu started
 system.cpu.numWorkItemsCompleted                    0                       # number of work items this cpu completed
-system.cpu.BPredUnit.lookups                     3056                       # Number of BP lookups
-system.cpu.BPredUnit.condPredicted               3056                       # Number of conditional branches predicted
-system.cpu.BPredUnit.condIncorrect                497                       # Number of conditional branches incorrect
-system.cpu.BPredUnit.BTBLookups                  2731                       # Number of BTB lookups
-system.cpu.BPredUnit.BTBHits                      995                       # Number of BTB hits
+system.cpu.BPredUnit.lookups                     3019                       # Number of BP lookups
+system.cpu.BPredUnit.condPredicted               3019                       # Number of conditional branches predicted
+system.cpu.BPredUnit.condIncorrect                495                       # Number of conditional branches incorrect
+system.cpu.BPredUnit.BTBLookups                  2695                       # Number of BTB lookups
+system.cpu.BPredUnit.BTBHits                      978                       # Number of BTB hits
 system.cpu.BPredUnit.BTBCorrect                     0                       # Number of correct BTB predictions (this stat may not work properly.
 system.cpu.BPredUnit.usedRAS                        0                       # Number of times the RAS was used to get a target.
 system.cpu.BPredUnit.RASInCorrect                   0                       # Number of incorrect RAS predictions.
-system.cpu.fetch.icacheStallCycles               5895                       # Number of cycles fetch is stalled on an Icache miss
-system.cpu.fetch.Insts                          13997                       # Number of instructions fetch has processed
-system.cpu.fetch.Branches                        3056                       # Number of branches that fetch encountered
-system.cpu.fetch.predictedBranches                995                       # Number of branches that fetch has predicted taken
-system.cpu.fetch.Cycles                          3968                       # Number of cycles fetch has run and was not squashing or blocked
-system.cpu.fetch.SquashCycles                    2221                       # Number of cycles fetch has spent squashing
-system.cpu.fetch.BlockedCycles                   1500                       # Number of cycles fetch has spent blocked
+system.cpu.fetch.icacheStallCycles               7194                       # Number of cycles fetch is stalled on an Icache miss
+system.cpu.fetch.Insts                          13831                       # Number of instructions fetch has processed
+system.cpu.fetch.Branches                        3019                       # Number of branches that fetch encountered
+system.cpu.fetch.predictedBranches                978                       # Number of branches that fetch has predicted taken
+system.cpu.fetch.Cycles                          3921                       # Number of cycles fetch has run and was not squashing or blocked
+system.cpu.fetch.SquashCycles                    2194                       # Number of cycles fetch has spent squashing
+system.cpu.fetch.BlockedCycles                   3367                       # Number of cycles fetch has spent blocked
 system.cpu.fetch.MiscStallCycles                    4                       # Number of cycles fetch has spent waiting on interrupts, or bad addresses, or out of MSHRs
 system.cpu.fetch.PendingTrapStallCycles             9                       # Number of stall cycles due to pending traps
-system.cpu.fetch.CacheLines                      1891                       # Number of cache lines fetched
-system.cpu.fetch.IcacheSquashes                   271                       # Number of outstanding Icache misses that were squashed
-system.cpu.fetch.rateDist::samples              13088                       # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::mean              1.930776                       # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::stdev             3.218766                       # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.CacheLines                      1866                       # Number of cache lines fetched
+system.cpu.fetch.IcacheSquashes                   269                       # Number of outstanding Icache misses that were squashed
+system.cpu.fetch.rateDist::samples              16182                       # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.rateDist::mean              1.543567                       # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.rateDist::stdev             2.980612                       # Number of instructions fetched each cycle (Total)
 system.cpu.fetch.rateDist::underflows               0      0.00%      0.00% # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::0                     9227     70.50%     70.50% # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::1                      167      1.28%     71.78% # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::2                      175      1.34%     73.11% # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::3                      239      1.83%     74.94% # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::4                      232      1.77%     76.71% # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::5                      193      1.47%     78.19% # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::6                      279      2.13%     80.32% # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::7                      139      1.06%     81.38% # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::8                     2437     18.62%    100.00% # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.rateDist::0                    12367     76.42%     76.42% # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.rateDist::1                      166      1.03%     77.45% # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.rateDist::2                      172      1.06%     78.51% # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.rateDist::3                      238      1.47%     79.98% # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.rateDist::4                      224      1.38%     81.37% # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.rateDist::5                      191      1.18%     82.55% # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.rateDist::6                      276      1.71%     84.25% # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.rateDist::7                      137      0.85%     85.10% # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.rateDist::8                     2411     14.90%    100.00% # Number of instructions fetched each cycle (Total)
 system.cpu.fetch.rateDist::overflows                0      0.00%    100.00% # Number of instructions fetched each cycle (Total)
 system.cpu.fetch.rateDist::min_value                0                       # Number of instructions fetched each cycle (Total)
 system.cpu.fetch.rateDist::max_value                8                       # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.rateDist::total                13088                       # Number of instructions fetched each cycle (Total)
-system.cpu.fetch.branchRate                  0.137813                       # Number of branch fetches per cycle
-system.cpu.fetch.rate                        0.631206                       # Number of inst fetches per cycle
-system.cpu.decode.IdleCycles                     6247                       # Number of cycles decode is idle
-system.cpu.decode.BlockedCycles                  1453                       # Number of cycles decode is blocked
-system.cpu.decode.RunCycles                      3565                       # Number of cycles decode is running
-system.cpu.decode.UnblockCycles                   111                       # Number of cycles decode is unblocking
-system.cpu.decode.SquashCycles                   1712                       # Number of cycles decode is squashing
-system.cpu.decode.DecodedInsts                  24090                       # Number of instructions handled by decode
-system.cpu.rename.SquashCycles                   1712                       # Number of cycles rename is squashing
-system.cpu.rename.IdleCycles                     6535                       # Number of cycles rename is idle
-system.cpu.rename.BlockCycles                     523                       # Number of cycles rename is blocking
-system.cpu.rename.serializeStallCycles            524                       # count of cycles rename stalled for serializing inst
-system.cpu.rename.RunCycles                      3365                       # Number of cycles rename is running
-system.cpu.rename.UnblockCycles                   429                       # Number of cycles rename is unblocking
-system.cpu.rename.RenamedInsts                  22712                       # Number of instructions processed by rename
+system.cpu.fetch.rateDist::total                16182                       # Number of instructions fetched each cycle (Total)
+system.cpu.fetch.branchRate                  0.125897                       # Number of branch fetches per cycle
+system.cpu.fetch.rate                        0.576772                       # Number of inst fetches per cycle
+system.cpu.decode.IdleCycles                     7550                       # Number of cycles decode is idle
+system.cpu.decode.BlockedCycles                  3315                       # Number of cycles decode is blocked
+system.cpu.decode.RunCycles                      3508                       # Number of cycles decode is running
+system.cpu.decode.UnblockCycles                   122                       # Number of cycles decode is unblocking
+system.cpu.decode.SquashCycles                   1687                       # Number of cycles decode is squashing
+system.cpu.decode.DecodedInsts                  23802                       # Number of instructions handled by decode
+system.cpu.rename.SquashCycles                   1687                       # Number of cycles rename is squashing
+system.cpu.rename.IdleCycles                     7843                       # Number of cycles rename is idle
+system.cpu.rename.BlockCycles                    2077                       # Number of cycles rename is blocking
+system.cpu.rename.serializeStallCycles            553                       # count of cycles rename stalled for serializing inst
+system.cpu.rename.RunCycles                      3329                       # Number of cycles rename is running
+system.cpu.rename.UnblockCycles                   693                       # Number of cycles rename is unblocking
+system.cpu.rename.RenamedInsts                  22457                       # Number of instructions processed by rename
 system.cpu.rename.ROBFullEvents                     2                       # Number of times rename has blocked due to ROB full
 system.cpu.rename.IQFullEvents                     68                       # Number of times rename has blocked due to IQ full
-system.cpu.rename.LSQFullEvents                   272                       # Number of times rename has blocked due to LSQ full
-system.cpu.rename.RenamedOperands               21246                       # Number of destination operands rename has renamed
-system.cpu.rename.RenameLookups                 47645                       # Number of register rename lookups that rename has made
-system.cpu.rename.int_rename_lookups            47629                       # Number of integer rename lookups
+system.cpu.rename.LSQFullEvents                   553                       # Number of times rename has blocked due to LSQ full
+system.cpu.rename.RenamedOperands               21026                       # Number of destination operands rename has renamed
+system.cpu.rename.RenameLookups                 47090                       # Number of register rename lookups that rename has made
+system.cpu.rename.int_rename_lookups            47074                       # Number of integer rename lookups
 system.cpu.rename.fp_rename_lookups                16                       # Number of floating rename lookups
 system.cpu.rename.CommittedMaps                  9368                       # Number of HB maps that are committed
-system.cpu.rename.UndoneMaps                    11878                       # Number of HB maps that are undone due to squashing
+system.cpu.rename.UndoneMaps                    11658                       # Number of HB maps that are undone due to squashing
 system.cpu.rename.serializingInsts                 33                       # count of serializing insts renamed
 system.cpu.rename.tempSerializingInsts             33                       # count of temporary serializing insts renamed
-system.cpu.rename.skidInsts                      1613                       # count of insts added to the skid buffer
-system.cpu.memDep0.insertedLoads                 2238                       # Number of loads inserted to the mem dependence unit.
-system.cpu.memDep0.insertedStores                1782                       # Number of stores inserted to the mem dependence unit.
+system.cpu.rename.skidInsts                      1820                       # count of insts added to the skid buffer
+system.cpu.memDep0.insertedLoads                 2219                       # Number of loads inserted to the mem dependence unit.
+system.cpu.memDep0.insertedStores                1751                       # Number of stores inserted to the mem dependence unit.
 system.cpu.memDep0.conflictingLoads                13                       # Number of conflicting loads.
 system.cpu.memDep0.conflictingStores                8                       # Number of conflicting stores.
-system.cpu.iq.iqInstsAdded                      20539                       # Number of instructions added to the IQ (excludes non-spec)
+system.cpu.iq.iqInstsAdded                      20306                       # Number of instructions added to the IQ (excludes non-spec)
 system.cpu.iq.iqNonSpecInstsAdded                  37                       # Number of non-speculative instructions added to the IQ
-system.cpu.iq.iqInstsIssued                     16958                       # Number of instructions issued
-system.cpu.iq.iqSquashedInstsIssued                63                       # Number of squashed instructions issued
-system.cpu.iq.iqSquashedInstsExamined           10220                       # Number of squashed instructions iterated over during squash; mainly for profiling
-system.cpu.iq.iqSquashedOperandsExamined        12992                       # Number of squashed operands that are examined and possibly removed from graph
+system.cpu.iq.iqInstsIssued                     16792                       # Number of instructions issued
+system.cpu.iq.iqSquashedInstsIssued                56                       # Number of squashed instructions issued
+system.cpu.iq.iqSquashedInstsExamined           10001                       # Number of squashed instructions iterated over during squash; mainly for profiling
+system.cpu.iq.iqSquashedOperandsExamined        12754                       # Number of squashed operands that are examined and possibly removed from graph
 system.cpu.iq.iqSquashedNonSpecRemoved             24                       # Number of squashed non-spec instructions that were removed
-system.cpu.iq.issued_per_cycle::samples         13088                       # Number of insts issued each cycle
-system.cpu.iq.issued_per_cycle::mean         1.295691                       # Number of insts issued each cycle
-system.cpu.iq.issued_per_cycle::stdev        2.003315                       # Number of insts issued each cycle
+system.cpu.iq.issued_per_cycle::samples         16182                       # Number of insts issued each cycle
+system.cpu.iq.issued_per_cycle::mean         1.037696                       # Number of insts issued each cycle
+system.cpu.iq.issued_per_cycle::stdev        1.845376                       # Number of insts issued each cycle
 system.cpu.iq.issued_per_cycle::underflows            0      0.00%      0.00% # Number of insts issued each cycle
-system.cpu.iq.issued_per_cycle::0                8001     61.13%     61.13% # Number of insts issued each cycle
-system.cpu.iq.issued_per_cycle::1                1108      8.47%     69.60% # Number of insts issued each cycle
-system.cpu.iq.issued_per_cycle::2                1006      7.69%     77.28% # Number of insts issued each cycle
-system.cpu.iq.issued_per_cycle::3                 733      5.60%     82.89% # Number of insts issued each cycle
-system.cpu.iq.issued_per_cycle::4                 670      5.12%     88.00% # Number of insts issued each cycle
-system.cpu.iq.issued_per_cycle::5                 725      5.54%     93.54% # Number of insts issued each cycle
-system.cpu.iq.issued_per_cycle::6                 615      4.70%     98.24% # Number of insts issued each cycle
-system.cpu.iq.issued_per_cycle::7                 196      1.50%     99.74% # Number of insts issued each cycle
-system.cpu.iq.issued_per_cycle::8                  34      0.26%    100.00% # Number of insts issued each cycle
+system.cpu.iq.issued_per_cycle::0               10903     67.38%     67.38% # Number of insts issued each cycle
+system.cpu.iq.issued_per_cycle::1                1372      8.48%     75.86% # Number of insts issued each cycle
+system.cpu.iq.issued_per_cycle::2                1062      6.56%     82.42% # Number of insts issued each cycle
+system.cpu.iq.issued_per_cycle::3                 680      4.20%     86.62% # Number of insts issued each cycle
+system.cpu.iq.issued_per_cycle::4                 659      4.07%     90.69% # Number of insts issued each cycle
+system.cpu.iq.issued_per_cycle::5                 684      4.23%     94.92% # Number of insts issued each cycle
+system.cpu.iq.issued_per_cycle::6                 588      3.63%     98.55% # Number of insts issued each cycle
+system.cpu.iq.issued_per_cycle::7                 200      1.24%     99.79% # Number of insts issued each cycle
+system.cpu.iq.issued_per_cycle::8                  34      0.21%    100.00% # Number of insts issued each cycle
 system.cpu.iq.issued_per_cycle::overflows            0      0.00%    100.00% # Number of insts issued each cycle
 system.cpu.iq.issued_per_cycle::min_value            0                       # Number of insts issued each cycle
 system.cpu.iq.issued_per_cycle::max_value            8                       # Number of insts issued each cycle
-system.cpu.iq.issued_per_cycle::total           13088                       # Number of insts issued each cycle
+system.cpu.iq.issued_per_cycle::total           16182                       # Number of insts issued each cycle
 system.cpu.iq.fu_full::No_OpClass                   0      0.00%      0.00% # attempts to use FU when none available
-system.cpu.iq.fu_full::IntAlu                      94     66.67%     66.67% # attempts to use FU when none available
-system.cpu.iq.fu_full::IntMult                      0      0.00%     66.67% # attempts to use FU when none available
-system.cpu.iq.fu_full::IntDiv                       0      0.00%     66.67% # attempts to use FU when none available
-system.cpu.iq.fu_full::FloatAdd                     0      0.00%     66.67% # attempts to use FU when none available
-system.cpu.iq.fu_full::FloatCmp                     0      0.00%     66.67% # attempts to use FU when none available
-system.cpu.iq.fu_full::FloatCvt                     0      0.00%     66.67% # attempts to use FU when none available
-system.cpu.iq.fu_full::FloatMult                    0      0.00%     66.67% # attempts to use FU when none available
-system.cpu.iq.fu_full::FloatDiv                     0      0.00%     66.67% # attempts to use FU when none available
-system.cpu.iq.fu_full::FloatSqrt                    0      0.00%     66.67% # attempts to use FU when none available
-system.cpu.iq.fu_full::SimdAdd                      0      0.00%     66.67% # attempts to use FU when none available
-system.cpu.iq.fu_full::SimdAddAcc                   0      0.00%     66.67% # attempts to use FU when none available
-system.cpu.iq.fu_full::SimdAlu                      0      0.00%     66.67% # attempts to use FU when none available
-system.cpu.iq.fu_full::SimdCmp                      0      0.00%     66.67% # attempts to use FU when none available
-system.cpu.iq.fu_full::SimdCvt                      0      0.00%     66.67% # attempts to use FU when none available
-system.cpu.iq.fu_full::SimdMisc                     0      0.00%     66.67% # attempts to use FU when none available
-system.cpu.iq.fu_full::SimdMult                     0      0.00%     66.67% # attempts to use FU when none available
-system.cpu.iq.fu_full::SimdMultAcc                  0      0.00%     66.67% # attempts to use FU when none available
-system.cpu.iq.fu_full::SimdShift                    0      0.00%     66.67% # attempts to use FU when none available
-system.cpu.iq.fu_full::SimdShiftAcc                 0      0.00%     66.67% # attempts to use FU when none available
-system.cpu.iq.fu_full::SimdSqrt                     0      0.00%     66.67% # attempts to use FU when none available
-system.cpu.iq.fu_full::SimdFloatAdd                 0      0.00%     66.67% # attempts to use FU when none available
-system.cpu.iq.fu_full::SimdFloatAlu                 0      0.00%     66.67% # attempts to use FU when none available
-system.cpu.iq.fu_full::SimdFloatCmp                 0      0.00%     66.67% # attempts to use FU when none available
-system.cpu.iq.fu_full::SimdFloatCvt                 0      0.00%     66.67% # attempts to use FU when none available
-system.cpu.iq.fu_full::SimdFloatDiv                 0      0.00%     66.67% # attempts to use FU when none available
-system.cpu.iq.fu_full::SimdFloatMisc                0      0.00%     66.67% # attempts to use FU when none available
-system.cpu.iq.fu_full::SimdFloatMult                0      0.00%     66.67% # attempts to use FU when none available
-system.cpu.iq.fu_full::SimdFloatMultAcc             0      0.00%     66.67% # attempts to use FU when none available
-system.cpu.iq.fu_full::SimdFloatSqrt                0      0.00%     66.67% # attempts to use FU when none available
-system.cpu.iq.fu_full::MemRead                     24     17.02%     83.69% # attempts to use FU when none available
-system.cpu.iq.fu_full::MemWrite                    23     16.31%    100.00% # attempts to use FU when none available
+system.cpu.iq.fu_full::IntAlu                      86     64.66%     64.66% # attempts to use FU when none available
+system.cpu.iq.fu_full::IntMult                      0      0.00%     64.66% # attempts to use FU when none available
+system.cpu.iq.fu_full::IntDiv                       0      0.00%     64.66% # attempts to use FU when none available
+system.cpu.iq.fu_full::FloatAdd                     0      0.00%     64.66% # attempts to use FU when none available
+system.cpu.iq.fu_full::FloatCmp                     0      0.00%     64.66% # attempts to use FU when none available
+system.cpu.iq.fu_full::FloatCvt                     0      0.00%     64.66% # attempts to use FU when none available
+system.cpu.iq.fu_full::FloatMult                    0      0.00%     64.66% # attempts to use FU when none available
+system.cpu.iq.fu_full::FloatDiv                     0      0.00%     64.66% # attempts to use FU when none available
+system.cpu.iq.fu_full::FloatSqrt                    0      0.00%     64.66% # attempts to use FU when none available
+system.cpu.iq.fu_full::SimdAdd                      0      0.00%     64.66% # attempts to use FU when none available
+system.cpu.iq.fu_full::SimdAddAcc                   0      0.00%     64.66% # attempts to use FU when none available
+system.cpu.iq.fu_full::SimdAlu                      0      0.00%     64.66% # attempts to use FU when none available
+system.cpu.iq.fu_full::SimdCmp                      0      0.00%     64.66% # attempts to use FU when none available
+system.cpu.iq.fu_full::SimdCvt                      0      0.00%     64.66% # attempts to use FU when none available
+system.cpu.iq.fu_full::SimdMisc                     0      0.00%     64.66% # attempts to use FU when none available
+system.cpu.iq.fu_full::SimdMult                     0      0.00%     64.66% # attempts to use FU when none available
+system.cpu.iq.fu_full::SimdMultAcc                  0      0.00%     64.66% # attempts to use FU when none available
+system.cpu.iq.fu_full::SimdShift                    0      0.00%     64.66% # attempts to use FU when none available
+system.cpu.iq.fu_full::SimdShiftAcc                 0      0.00%     64.66% # attempts to use FU when none available
+system.cpu.iq.fu_full::SimdSqrt                     0      0.00%     64.66% # attempts to use FU when none available
+system.cpu.iq.fu_full::SimdFloatAdd                 0      0.00%     64.66% # attempts to use FU when none available
+system.cpu.iq.fu_full::SimdFloatAlu                 0      0.00%     64.66% # attempts to use FU when none available
+system.cpu.iq.fu_full::SimdFloatCmp                 0      0.00%     64.66% # attempts to use FU when none available
+system.cpu.iq.fu_full::SimdFloatCvt                 0      0.00%     64.66% # attempts to use FU when none available
+system.cpu.iq.fu_full::SimdFloatDiv                 0      0.00%     64.66% # attempts to use FU when none available
+system.cpu.iq.fu_full::SimdFloatMisc                0      0.00%     64.66% # attempts to use FU when none available
+system.cpu.iq.fu_full::SimdFloatMult                0      0.00%     64.66% # attempts to use FU when none available
+system.cpu.iq.fu_full::SimdFloatMultAcc             0      0.00%     64.66% # attempts to use FU when none available
+system.cpu.iq.fu_full::SimdFloatSqrt                0      0.00%     64.66% # attempts to use FU when none available
+system.cpu.iq.fu_full::MemRead                     24     18.05%     82.71% # attempts to use FU when none available
+system.cpu.iq.fu_full::MemWrite                    23     17.29%    100.00% # attempts to use FU when none available
 system.cpu.iq.fu_full::IprAccess                    0      0.00%    100.00% # attempts to use FU when none available
 system.cpu.iq.fu_full::InstPrefetch                 0      0.00%    100.00% # attempts to use FU when none available
 system.cpu.iq.FU_type_0::No_OpClass                 4      0.02%      0.02% # Type of FU issued
-system.cpu.iq.FU_type_0::IntAlu                 13641     80.44%     80.46% # Type of FU issued
-system.cpu.iq.FU_type_0::IntMult                    0      0.00%     80.46% # Type of FU issued
-system.cpu.iq.FU_type_0::IntDiv                     0      0.00%     80.46% # Type of FU issued
-system.cpu.iq.FU_type_0::FloatAdd                   0      0.00%     80.46% # Type of FU issued
-system.cpu.iq.FU_type_0::FloatCmp                   0      0.00%     80.46% # Type of FU issued
-system.cpu.iq.FU_type_0::FloatCvt                   0      0.00%     80.46% # Type of FU issued
-system.cpu.iq.FU_type_0::FloatMult                  0      0.00%     80.46% # Type of FU issued
-system.cpu.iq.FU_type_0::FloatDiv                   0      0.00%     80.46% # Type of FU issued
-system.cpu.iq.FU_type_0::FloatSqrt                  0      0.00%     80.46% # Type of FU issued
-system.cpu.iq.FU_type_0::SimdAdd                    0      0.00%     80.46% # Type of FU issued
-system.cpu.iq.FU_type_0::SimdAddAcc                 0      0.00%     80.46% # Type of FU issued
-system.cpu.iq.FU_type_0::SimdAlu                    0      0.00%     80.46% # Type of FU issued
-system.cpu.iq.FU_type_0::SimdCmp                    0      0.00%     80.46% # Type of FU issued
-system.cpu.iq.FU_type_0::SimdCvt                    0      0.00%     80.46% # Type of FU issued
-system.cpu.iq.FU_type_0::SimdMisc                   0      0.00%     80.46% # Type of FU issued
-system.cpu.iq.FU_type_0::SimdMult                   0      0.00%     80.46% # Type of FU issued
-system.cpu.iq.FU_type_0::SimdMultAcc                0      0.00%     80.46% # Type of FU issued
-system.cpu.iq.FU_type_0::SimdShift                  0      0.00%     80.46% # Type of FU issued
-system.cpu.iq.FU_type_0::SimdShiftAcc               0      0.00%     80.46% # Type of FU issued
-system.cpu.iq.FU_type_0::SimdSqrt                   0      0.00%     80.46% # Type of FU issued
-system.cpu.iq.FU_type_0::SimdFloatAdd               0      0.00%     80.46% # Type of FU issued
-system.cpu.iq.FU_type_0::SimdFloatAlu               0      0.00%     80.46% # Type of FU issued
-system.cpu.iq.FU_type_0::SimdFloatCmp               0      0.00%     80.46% # Type of FU issued
-system.cpu.iq.FU_type_0::SimdFloatCvt               0      0.00%     80.46% # Type of FU issued
-system.cpu.iq.FU_type_0::SimdFloatDiv               0      0.00%     80.46% # Type of FU issued
-system.cpu.iq.FU_type_0::SimdFloatMisc              0      0.00%     80.46% # Type of FU issued
-system.cpu.iq.FU_type_0::SimdFloatMult              0      0.00%     80.46% # Type of FU issued
-system.cpu.iq.FU_type_0::SimdFloatMultAcc            0      0.00%     80.46% # Type of FU issued
-system.cpu.iq.FU_type_0::SimdFloatSqrt              0      0.00%     80.46% # Type of FU issued
-system.cpu.iq.FU_type_0::MemRead                 1843     10.87%     91.33% # Type of FU issued
-system.cpu.iq.FU_type_0::MemWrite                1470      8.67%    100.00% # Type of FU issued
+system.cpu.iq.FU_type_0::IntAlu                 13517     80.50%     80.52% # Type of FU issued
+system.cpu.iq.FU_type_0::IntMult                    0      0.00%     80.52% # Type of FU issued
+system.cpu.iq.FU_type_0::IntDiv                     0      0.00%     80.52% # Type of FU issued
+system.cpu.iq.FU_type_0::FloatAdd                   0      0.00%     80.52% # Type of FU issued
+system.cpu.iq.FU_type_0::FloatCmp                   0      0.00%     80.52% # Type of FU issued
+system.cpu.iq.FU_type_0::FloatCvt                   0      0.00%     80.52% # Type of FU issued
+system.cpu.iq.FU_type_0::FloatMult                  0      0.00%     80.52% # Type of FU issued
+system.cpu.iq.FU_type_0::FloatDiv                   0      0.00%     80.52% # Type of FU issued
+system.cpu.iq.FU_type_0::FloatSqrt                  0      0.00%     80.52% # Type of FU issued
+system.cpu.iq.FU_type_0::SimdAdd                    0      0.00%     80.52% # Type of FU issued
+system.cpu.iq.FU_type_0::SimdAddAcc                 0      0.00%     80.52% # Type of FU issued
+system.cpu.iq.FU_type_0::SimdAlu                    0      0.00%     80.52% # Type of FU issued
+system.cpu.iq.FU_type_0::SimdCmp                    0      0.00%     80.52% # Type of FU issued
+system.cpu.iq.FU_type_0::SimdCvt                    0      0.00%     80.52% # Type of FU issued
+system.cpu.iq.FU_type_0::SimdMisc                   0      0.00%     80.52% # Type of FU issued
+system.cpu.iq.FU_type_0::SimdMult                   0      0.00%     80.52% # Type of FU issued
+system.cpu.iq.FU_type_0::SimdMultAcc                0      0.00%     80.52% # Type of FU issued
+system.cpu.iq.FU_type_0::SimdShift                  0      0.00%     80.52% # Type of FU issued
+system.cpu.iq.FU_type_0::SimdShiftAcc               0      0.00%     80.52% # Type of FU issued
+system.cpu.iq.FU_type_0::SimdSqrt                   0      0.00%     80.52% # Type of FU issued
+system.cpu.iq.FU_type_0::SimdFloatAdd               0      0.00%     80.52% # Type of FU issued
+system.cpu.iq.FU_type_0::SimdFloatAlu               0      0.00%     80.52% # Type of FU issued
+system.cpu.iq.FU_type_0::SimdFloatCmp               0      0.00%     80.52% # Type of FU issued
+system.cpu.iq.FU_type_0::SimdFloatCvt               0      0.00%     80.52% # Type of FU issued
+system.cpu.iq.FU_type_0::SimdFloatDiv               0      0.00%     80.52% # Type of FU issued
+system.cpu.iq.FU_type_0::SimdFloatMisc              0      0.00%     80.52% # Type of FU issued
+system.cpu.iq.FU_type_0::SimdFloatMult              0      0.00%     80.52% # Type of FU issued
+system.cpu.iq.FU_type_0::SimdFloatMultAcc            0      0.00%     80.52% # Type of FU issued
+system.cpu.iq.FU_type_0::SimdFloatSqrt              0      0.00%     80.52% # Type of FU issued
+system.cpu.iq.FU_type_0::MemRead                 1828     10.89%     91.41% # Type of FU issued
+system.cpu.iq.FU_type_0::MemWrite                1443      8.59%    100.00% # Type of FU issued
 system.cpu.iq.FU_type_0::IprAccess                  0      0.00%    100.00% # Type of FU issued
 system.cpu.iq.FU_type_0::InstPrefetch               0      0.00%    100.00% # Type of FU issued
-system.cpu.iq.FU_type_0::total                  16958                       # Type of FU issued
-system.cpu.iq.rate                           0.764735                       # Inst issue rate
-system.cpu.iq.fu_busy_cnt                         141                       # FU busy when requested
-system.cpu.iq.fu_busy_rate                   0.008315                       # FU busy rate (busy events/executed inst)
-system.cpu.iq.int_inst_queue_reads              47200                       # Number of integer instruction queue reads
-system.cpu.iq.int_inst_queue_writes             30804                       # Number of integer instruction queue writes
-system.cpu.iq.int_inst_queue_wakeup_accesses        15755                       # Number of integer instruction queue wakeup accesses
+system.cpu.iq.FU_type_0::total                  16792                       # Type of FU issued
+system.cpu.iq.rate                           0.700250                       # Inst issue rate
+system.cpu.iq.fu_busy_cnt                         133                       # FU busy when requested
+system.cpu.iq.fu_busy_rate                   0.007920                       # FU busy rate (busy events/executed inst)
+system.cpu.iq.int_inst_queue_reads              49947                       # Number of integer instruction queue reads
+system.cpu.iq.int_inst_queue_writes             30352                       # Number of integer instruction queue writes
+system.cpu.iq.int_inst_queue_wakeup_accesses        15608                       # Number of integer instruction queue wakeup accesses
 system.cpu.iq.fp_inst_queue_reads                   8                       # Number of floating instruction queue reads
 system.cpu.iq.fp_inst_queue_writes                  4                       # Number of floating instruction queue writes
 system.cpu.iq.fp_inst_queue_wakeup_accesses            4                       # Number of floating instruction queue wakeup accesses
-system.cpu.iq.int_alu_accesses                  17091                       # Number of integer alu accesses
+system.cpu.iq.int_alu_accesses                  16917                       # Number of integer alu accesses
 system.cpu.iq.fp_alu_accesses                       4                       # Number of floating point alu accesses
-system.cpu.iew.lsq.thread0.forwLoads               80                       # Number of loads that had data forwarded from stores
+system.cpu.iew.lsq.thread0.forwLoads              142                       # Number of loads that had data forwarded from stores
 system.cpu.iew.lsq.thread0.invAddrLoads             0                       # Number of loads ignored due to an invalid address
-system.cpu.iew.lsq.thread0.squashedLoads         1182                       # Number of loads squashed
+system.cpu.iew.lsq.thread0.squashedLoads         1163                       # Number of loads squashed
 system.cpu.iew.lsq.thread0.ignoredResponses           12                       # Number of memory responses ignored because the instruction is squashed
 system.cpu.iew.lsq.thread0.memOrderViolation           12                       # Number of memory ordering violations
-system.cpu.iew.lsq.thread0.squashedStores          848                       # Number of stores squashed
+system.cpu.iew.lsq.thread0.squashedStores          817                       # Number of stores squashed
 system.cpu.iew.lsq.thread0.invAddrSwpfs             0                       # Number of software prefetches ignored due to an invalid address
 system.cpu.iew.lsq.thread0.blockedLoads             0                       # Number of blocked loads due to partial load-store forwarding
 system.cpu.iew.lsq.thread0.rescheduledLoads            0                       # Number of loads that were rescheduled
 system.cpu.iew.lsq.thread0.cacheBlocked             0                       # Number of times an access to memory failed due to the cache being blocked
 system.cpu.iew.iewIdleCycles                        0                       # Number of cycles IEW is idle
-system.cpu.iew.iewSquashCycles                   1712                       # Number of cycles IEW is squashing
-system.cpu.iew.iewBlockCycles                     144                       # Number of cycles IEW is blocking
-system.cpu.iew.iewUnblockCycles                    16                       # Number of cycles IEW is unblocking
-system.cpu.iew.iewDispatchedInsts               20576                       # Number of instructions dispatched to IQ
-system.cpu.iew.iewDispSquashedInsts                23                       # Number of squashed instructions skipped by dispatch
-system.cpu.iew.iewDispLoadInsts                  2238                       # Number of dispatched load instructions
-system.cpu.iew.iewDispStoreInsts                 1782                       # Number of dispatched store instructions
+system.cpu.iew.iewSquashCycles                   1687                       # Number of cycles IEW is squashing
+system.cpu.iew.iewBlockCycles                    1417                       # Number of cycles IEW is blocking
+system.cpu.iew.iewUnblockCycles                    38                       # Number of cycles IEW is unblocking
+system.cpu.iew.iewDispatchedInsts               20343                       # Number of instructions dispatched to IQ
+system.cpu.iew.iewDispSquashedInsts                26                       # Number of squashed instructions skipped by dispatch
+system.cpu.iew.iewDispLoadInsts                  2219                       # Number of dispatched load instructions
+system.cpu.iew.iewDispStoreInsts                 1751                       # Number of dispatched store instructions
 system.cpu.iew.iewDispNonSpecInsts                 33                       # Number of dispatched non-speculative instructions
 system.cpu.iew.iewIQFullEvents                      6                       # Number of times the IQ has become full, causing a stall
 system.cpu.iew.iewLSQFullEvents                     0                       # Number of times the LSQ has become full, causing a stall
 system.cpu.iew.memOrderViolationEvents             12                       # Number of memory order violations
 system.cpu.iew.predictedTakenIncorrect             65                       # Number of branches that were predicted taken incorrectly
-system.cpu.iew.predictedNotTakenIncorrect          523                       # Number of branches that were predicted not taken incorrectly
-system.cpu.iew.branchMispredicts                  588                       # Number of branch mispredicts detected at execute
-system.cpu.iew.iewExecutedInsts                 16100                       # Number of executed instructions
-system.cpu.iew.iewExecLoadInsts                  1742                       # Number of load instructions executed
-system.cpu.iew.iewExecSquashedInsts               858                       # Number of squashed instructions skipped in execute
+system.cpu.iew.predictedNotTakenIncorrect          525                       # Number of branches that were predicted not taken incorrectly
+system.cpu.iew.branchMispredicts                  590                       # Number of branch mispredicts detected at execute
+system.cpu.iew.iewExecutedInsts                 15942                       # Number of executed instructions
+system.cpu.iew.iewExecLoadInsts                  1725                       # Number of load instructions executed
+system.cpu.iew.iewExecSquashedInsts               850                       # Number of squashed instructions skipped in execute
 system.cpu.iew.exec_swp                             0                       # number of swp insts executed
 system.cpu.iew.exec_nop                             0                       # number of nop insts executed
-system.cpu.iew.exec_refs                         3105                       # number of memory reference insts executed
-system.cpu.iew.exec_branches                     1601                       # Number of branches executed
-system.cpu.iew.exec_stores                       1363                       # Number of stores executed
-system.cpu.iew.exec_rate                     0.726043                       # Inst execution rate
-system.cpu.iew.wb_sent                          15918                       # cumulative count of insts sent to commit
-system.cpu.iew.wb_count                         15759                       # cumulative count of insts written-back
-system.cpu.iew.wb_producers                     10538                       # num instructions producing a value
-system.cpu.iew.wb_consumers                     15699                       # num instructions consuming a value
+system.cpu.iew.exec_refs                         3065                       # number of memory reference insts executed
+system.cpu.iew.exec_branches                     1589                       # Number of branches executed
+system.cpu.iew.exec_stores                       1340                       # Number of stores executed
+system.cpu.iew.exec_rate                     0.664804                       # Inst execution rate
+system.cpu.iew.wb_sent                          15766                       # cumulative count of insts sent to commit
+system.cpu.iew.wb_count                         15612                       # cumulative count of insts written-back
+system.cpu.iew.wb_producers                     10251                       # num instructions producing a value
+system.cpu.iew.wb_consumers                     15131                       # num instructions consuming a value
 system.cpu.iew.wb_penalized                         0                       # number of instrctions required to write to 'other' IQ
-system.cpu.iew.wb_rate                       0.710665                       # insts written-back per cycle
-system.cpu.iew.wb_fanout                     0.671253                       # average fanout of values written-back
+system.cpu.iew.wb_rate                       0.651043                       # insts written-back per cycle
+system.cpu.iew.wb_fanout                     0.677483                       # average fanout of values written-back
 system.cpu.iew.wb_penalized_rate                    0                       # fraction of instructions written-back that wrote to 'other' IQ
 system.cpu.commit.commitCommittedInsts           9809                       # The number of committed instructions
-system.cpu.commit.commitSquashedInsts           10766                       # The number of squashed insts skipped by commit
+system.cpu.commit.commitSquashedInsts           10533                       # The number of squashed insts skipped by commit
 system.cpu.commit.commitNonSpecStalls              13                       # The number of times commit has been forced to stall to communicate backwards
-system.cpu.commit.branchMispredicts               497                       # The number of times a branch was mispredicted
-system.cpu.commit.committed_per_cycle::samples        11376                       # Number of insts commited each cycle
-system.cpu.commit.committed_per_cycle::mean     0.862254                       # Number of insts commited each cycle
-system.cpu.commit.committed_per_cycle::stdev     1.686850                       # Number of insts commited each cycle
+system.cpu.commit.branchMispredicts               495                       # The number of times a branch was mispredicted
+system.cpu.commit.committed_per_cycle::samples        14495                       # Number of insts commited each cycle
+system.cpu.commit.committed_per_cycle::mean     0.676716                       # Number of insts commited each cycle
+system.cpu.commit.committed_per_cycle::stdev     1.510487                       # Number of insts commited each cycle
 system.cpu.commit.committed_per_cycle::underflows            0      0.00%      0.00% # Number of insts commited each cycle
-system.cpu.commit.committed_per_cycle::0         7944     69.83%     69.83% # Number of insts commited each cycle
-system.cpu.commit.committed_per_cycle::1         1088      9.56%     79.40% # Number of insts commited each cycle
-system.cpu.commit.committed_per_cycle::2          574      5.05%     84.44% # Number of insts commited each cycle
-system.cpu.commit.committed_per_cycle::3          883      7.76%     92.20% # Number of insts commited each cycle
-system.cpu.commit.committed_per_cycle::4          343      3.02%     95.22% # Number of insts commited each cycle
-system.cpu.commit.committed_per_cycle::5          152      1.34%     96.55% # Number of insts commited each cycle
-system.cpu.commit.committed_per_cycle::6          139      1.22%     97.78% # Number of insts commited each cycle
-system.cpu.commit.committed_per_cycle::7           66      0.58%     98.36% # Number of insts commited each cycle
-system.cpu.commit.committed_per_cycle::8          187      1.64%    100.00% # Number of insts commited each cycle
+system.cpu.commit.committed_per_cycle::0        10831     74.72%     74.72% # Number of insts commited each cycle
+system.cpu.commit.committed_per_cycle::1         1349      9.31%     84.03% # Number of insts commited each cycle
+system.cpu.commit.committed_per_cycle::2          680      4.69%     88.72% # Number of insts commited each cycle
+system.cpu.commit.committed_per_cycle::3          780      5.38%     94.10% # Number of insts commited each cycle
+system.cpu.commit.committed_per_cycle::4          337      2.32%     96.43% # Number of insts commited each cycle
+system.cpu.commit.committed_per_cycle::5          129      0.89%     97.32% # Number of insts commited each cycle
+system.cpu.commit.committed_per_cycle::6          140      0.97%     98.28% # Number of insts commited each cycle
+system.cpu.commit.committed_per_cycle::7           65      0.45%     98.73% # Number of insts commited each cycle
+system.cpu.commit.committed_per_cycle::8          184      1.27%    100.00% # Number of insts commited each cycle
 system.cpu.commit.committed_per_cycle::overflows            0      0.00%    100.00% # Number of insts commited each cycle
 system.cpu.commit.committed_per_cycle::min_value            0                       # Number of insts commited each cycle
 system.cpu.commit.committed_per_cycle::max_value            8                       # Number of insts commited each cycle
-system.cpu.commit.committed_per_cycle::total        11376                       # Number of insts commited each cycle
+system.cpu.commit.committed_per_cycle::total        14495                       # Number of insts commited each cycle
 system.cpu.commit.count                          9809                       # Number of instructions committed
 system.cpu.commit.swp_count                         0                       # Number of s/w prefetches committed
 system.cpu.commit.refs                           1990                       # Number of memory references committed
@@ -265,48 +265,48 @@
 system.cpu.commit.fp_insts                          0                       # Number of committed floating point instructions.
 system.cpu.commit.int_insts                      9714                       # Number of committed integer instructions.
 system.cpu.commit.function_calls                    0                       # Number of function calls committed.
-system.cpu.commit.bw_lim_events                   187                       # number cycles where commit BW limit reached
+system.cpu.commit.bw_lim_events                   184                       # number cycles where commit BW limit reached
 system.cpu.commit.bw_limited                        0                       # number of insts not committed due to BW limits
-system.cpu.rob.rob_reads                        31764                       # The number of ROB reads
-system.cpu.rob.rob_writes                       42896                       # The number of ROB writes
-system.cpu.timesIdled                             182                       # Number of times that the entire CPU went into an idle state and unscheduled itself
-system.cpu.idleCycles                            9087                       # Total number of cycles that the CPU has spent unscheduled due to idling
+system.cpu.rob.rob_reads                        34653                       # The number of ROB reads
+system.cpu.rob.rob_writes                       42403                       # The number of ROB writes
+system.cpu.timesIdled                             150                       # Number of times that the entire CPU went into an idle state and unscheduled itself
+system.cpu.idleCycles                            7798                       # Total number of cycles that the CPU has spent unscheduled due to idling
 system.cpu.committedInsts                        9809                       # Number of Instructions Simulated
 system.cpu.committedInsts_total                  9809                       # Number of Instructions Simulated
-system.cpu.cpi                               2.260679                       # CPI: Cycles Per Instruction
-system.cpu.cpi_total                         2.260679                       # CPI: Total CPI of All Threads
-system.cpu.ipc                               0.442345                       # IPC: Instructions Per Cycle
-system.cpu.ipc_total                         0.442345                       # IPC: Total IPC of All Threads
-system.cpu.int_regfile_reads                    23665                       # number of integer regfile reads
-system.cpu.int_regfile_writes                   14645                       # number of integer regfile writes
+system.cpu.cpi                               2.444694                       # CPI: Cycles Per Instruction
+system.cpu.cpi_total                         2.444694                       # CPI: Total CPI of All Threads
+system.cpu.ipc                               0.409049                       # IPC: Instructions Per Cycle
+system.cpu.ipc_total                         0.409049                       # IPC: Total IPC of All Threads
+system.cpu.int_regfile_reads                    23430                       # number of integer regfile reads
+system.cpu.int_regfile_writes                   14518                       # number of integer regfile writes
 system.cpu.fp_regfile_reads                         4                       # number of floating regfile reads
-system.cpu.misc_regfile_reads                    7211                       # number of misc regfile reads
+system.cpu.misc_regfile_reads                    7136                       # number of misc regfile reads
 system.cpu.icache.replacements                      0                       # number of replacements
-system.cpu.icache.tagsinuse                145.144237                       # Cycle average of tags in use
-system.cpu.icache.total_refs                     1527                       # Total number of references to valid blocks.
+system.cpu.icache.tagsinuse                140.870525                       # Cycle average of tags in use
+system.cpu.icache.total_refs                     1498                       # Total number of references to valid blocks.
 system.cpu.icache.sampled_refs                    298                       # Sample count of references to valid blocks.
-system.cpu.icache.avg_refs                   5.124161                       # Average number of references to valid blocks.
+system.cpu.icache.avg_refs                   5.026846                       # Average number of references to valid blocks.
 system.cpu.icache.warmup_cycle                      0                       # Cycle when the warmup percentage was hit.
-system.cpu.icache.occ_blocks::0            145.144237                       # Average occupied blocks per context
-system.cpu.icache.occ_percent::0             0.070871                       # Average percentage of cache occupancy
-system.cpu.icache.ReadReq_hits                   1527                       # number of ReadReq hits
-system.cpu.icache.demand_hits                    1527                       # number of demand (read+write) hits
-system.cpu.icache.overall_hits                   1527                       # number of overall hits
-system.cpu.icache.ReadReq_misses                  364                       # number of ReadReq misses
-system.cpu.icache.demand_misses                   364                       # number of demand (read+write) misses
-system.cpu.icache.overall_misses                  364                       # number of overall misses
-system.cpu.icache.ReadReq_miss_latency       13314500                       # number of ReadReq miss cycles
-system.cpu.icache.demand_miss_latency        13314500                       # number of demand (read+write) miss cycles
-system.cpu.icache.overall_miss_latency       13314500                       # number of overall miss cycles
-system.cpu.icache.ReadReq_accesses               1891                       # number of ReadReq accesses(hits+misses)
-system.cpu.icache.demand_accesses                1891                       # number of demand (read+write) accesses
-system.cpu.icache.overall_accesses               1891                       # number of overall (read+write) accesses
-system.cpu.icache.ReadReq_miss_rate          0.192491                       # miss rate for ReadReq accesses
-system.cpu.icache.demand_miss_rate           0.192491                       # miss rate for demand accesses
-system.cpu.icache.overall_miss_rate          0.192491                       # miss rate for overall accesses
-system.cpu.icache.ReadReq_avg_miss_latency 36578.296703                       # average ReadReq miss latency
-system.cpu.icache.demand_avg_miss_latency 36578.296703                       # average overall miss latency
-system.cpu.icache.overall_avg_miss_latency 36578.296703                       # average overall miss latency
+system.cpu.icache.occ_blocks::0            140.870525                       # Average occupied blocks per context
+system.cpu.icache.occ_percent::0             0.068784                       # Average percentage of cache occupancy
+system.cpu.icache.ReadReq_hits                   1498                       # number of ReadReq hits
+system.cpu.icache.demand_hits                    1498                       # number of demand (read+write) hits
+system.cpu.icache.overall_hits                   1498                       # number of overall hits
+system.cpu.icache.ReadReq_misses                  368                       # number of ReadReq misses
+system.cpu.icache.demand_misses                   368                       # number of demand (read+write) misses
+system.cpu.icache.overall_misses                  368                       # number of overall misses
+system.cpu.icache.ReadReq_miss_latency       13394000                       # number of ReadReq miss cycles
+system.cpu.icache.demand_miss_latency        13394000                       # number of demand (read+write) miss cycles
+system.cpu.icache.overall_miss_latency       13394000                       # number of overall miss cycles
+system.cpu.icache.ReadReq_accesses               1866                       # number of ReadReq accesses(hits+misses)
+system.cpu.icache.demand_accesses                1866                       # number of demand (read+write) accesses
+system.cpu.icache.overall_accesses               1866                       # number of overall (read+write) accesses
+system.cpu.icache.ReadReq_miss_rate          0.197213                       # miss rate for ReadReq accesses
+system.cpu.icache.demand_miss_rate           0.197213                       # miss rate for demand accesses
+system.cpu.icache.overall_miss_rate          0.197213                       # miss rate for overall accesses
+system.cpu.icache.ReadReq_avg_miss_latency 36396.739130                       # average ReadReq miss latency
+system.cpu.icache.demand_avg_miss_latency 36396.739130                       # average overall miss latency
+system.cpu.icache.overall_avg_miss_latency 36396.739130                       # average overall miss latency
 system.cpu.icache.blocked_cycles::no_mshrs            0                       # number of cycles access was blocked
 system.cpu.icache.blocked_cycles::no_targets            0                       # number of cycles access was blocked
 system.cpu.icache.blocked::no_mshrs                 0                       # number of cycles access was blocked
@@ -316,59 +316,59 @@
 system.cpu.icache.fast_writes                       0                       # number of fast writes performed
 system.cpu.icache.cache_copies                      0                       # number of cache copies performed
 system.cpu.icache.writebacks                        0                       # number of writebacks
-system.cpu.icache.ReadReq_mshr_hits                66                       # number of ReadReq MSHR hits
-system.cpu.icache.demand_mshr_hits                 66                       # number of demand (read+write) MSHR hits
-system.cpu.icache.overall_mshr_hits                66                       # number of overall MSHR hits
+system.cpu.icache.ReadReq_mshr_hits                70                       # number of ReadReq MSHR hits
+system.cpu.icache.demand_mshr_hits                 70                       # number of demand (read+write) MSHR hits
+system.cpu.icache.overall_mshr_hits                70                       # number of overall MSHR hits
 system.cpu.icache.ReadReq_mshr_misses             298                       # number of ReadReq MSHR misses
 system.cpu.icache.demand_mshr_misses              298                       # number of demand (read+write) MSHR misses
 system.cpu.icache.overall_mshr_misses             298                       # number of overall MSHR misses
 system.cpu.icache.overall_mshr_uncacheable_misses            0                       # number of overall MSHR uncacheable misses
-system.cpu.icache.ReadReq_mshr_miss_latency     10466500                       # number of ReadReq MSHR miss cycles
-system.cpu.icache.demand_mshr_miss_latency     10466500                       # number of demand (read+write) MSHR miss cycles
-system.cpu.icache.overall_mshr_miss_latency     10466500                       # number of overall MSHR miss cycles
+system.cpu.icache.ReadReq_mshr_miss_latency     10471500                       # number of ReadReq MSHR miss cycles
+system.cpu.icache.demand_mshr_miss_latency     10471500                       # number of demand (read+write) MSHR miss cycles
+system.cpu.icache.overall_mshr_miss_latency     10471500                       # number of overall MSHR miss cycles
 system.cpu.icache.overall_mshr_uncacheable_latency            0                       # number of overall MSHR uncacheable cycles
-system.cpu.icache.ReadReq_mshr_miss_rate     0.157589                       # mshr miss rate for ReadReq accesses
-system.cpu.icache.demand_mshr_miss_rate      0.157589                       # mshr miss rate for demand accesses
-system.cpu.icache.overall_mshr_miss_rate     0.157589                       # mshr miss rate for overall accesses
-system.cpu.icache.ReadReq_avg_mshr_miss_latency 35122.483221                       # average ReadReq mshr miss latency
-system.cpu.icache.demand_avg_mshr_miss_latency 35122.483221                       # average overall mshr miss latency
-system.cpu.icache.overall_avg_mshr_miss_latency 35122.483221                       # average overall mshr miss latency
+system.cpu.icache.ReadReq_mshr_miss_rate     0.159700                       # mshr miss rate for ReadReq accesses
+system.cpu.icache.demand_mshr_miss_rate      0.159700                       # mshr miss rate for demand accesses
+system.cpu.icache.overall_mshr_miss_rate     0.159700                       # mshr miss rate for overall accesses
+system.cpu.icache.ReadReq_avg_mshr_miss_latency 35139.261745                       # average ReadReq mshr miss latency
+system.cpu.icache.demand_avg_mshr_miss_latency 35139.261745                       # average overall mshr miss latency
+system.cpu.icache.overall_avg_mshr_miss_latency 35139.261745                       # average overall mshr miss latency
 system.cpu.icache.overall_avg_mshr_uncacheable_latency     no_value                       # average overall mshr uncacheable latency
 system.cpu.icache.mshr_cap_events                   0                       # number of times MSHR cap was activated
 system.cpu.icache.soft_prefetch_mshr_full            0                       # number of mshr full events for SW prefetching instrutions
 system.cpu.icache.no_allocate_misses                0                       # Number of misses that were no-allocate
 system.cpu.dcache.replacements                      0                       # number of replacements
-system.cpu.dcache.tagsinuse                 85.499149                       # Cycle average of tags in use
-system.cpu.dcache.total_refs                     2112                       # Total number of references to valid blocks.
+system.cpu.dcache.tagsinuse                 83.526549                       # Cycle average of tags in use
+system.cpu.dcache.total_refs                     2275                       # Total number of references to valid blocks.
 system.cpu.dcache.sampled_refs                    145                       # Sample count of references to valid blocks.
-system.cpu.dcache.avg_refs                  14.565517                       # Average number of references to valid blocks.
+system.cpu.dcache.avg_refs                  15.689655                       # Average number of references to valid blocks.
 system.cpu.dcache.warmup_cycle                      0                       # Cycle when the warmup percentage was hit.
-system.cpu.dcache.occ_blocks::0             85.499149                       # Average occupied blocks per context
-system.cpu.dcache.occ_percent::0             0.020874                       # Average percentage of cache occupancy
-system.cpu.dcache.ReadReq_hits                   1494                       # number of ReadReq hits
-system.cpu.dcache.WriteReq_hits                   618                       # number of WriteReq hits
-system.cpu.dcache.demand_hits                    2112                       # number of demand (read+write) hits
-system.cpu.dcache.overall_hits                   2112                       # number of overall hits
-system.cpu.dcache.ReadReq_misses                  113                       # number of ReadReq misses
-system.cpu.dcache.WriteReq_misses                 316                       # number of WriteReq misses
-system.cpu.dcache.demand_misses                   429                       # number of demand (read+write) misses
-system.cpu.dcache.overall_misses                  429                       # number of overall misses
-system.cpu.dcache.ReadReq_miss_latency        3938500                       # number of ReadReq miss cycles
-system.cpu.dcache.WriteReq_miss_latency      10708500                       # number of WriteReq miss cycles
-system.cpu.dcache.demand_miss_latency        14647000                       # number of demand (read+write) miss cycles
-system.cpu.dcache.overall_miss_latency       14647000                       # number of overall miss cycles
-system.cpu.dcache.ReadReq_accesses               1607                       # number of ReadReq accesses(hits+misses)
+system.cpu.dcache.occ_blocks::0             83.526549                       # Average occupied blocks per context
+system.cpu.dcache.occ_percent::0             0.020392                       # Average percentage of cache occupancy
+system.cpu.dcache.ReadReq_hits                   1417                       # number of ReadReq hits
+system.cpu.dcache.WriteReq_hits                   858                       # number of WriteReq hits
+system.cpu.dcache.demand_hits                    2275                       # number of demand (read+write) hits
+system.cpu.dcache.overall_hits                   2275                       # number of overall hits
+system.cpu.dcache.ReadReq_misses                  111                       # number of ReadReq misses
+system.cpu.dcache.WriteReq_misses                  76                       # number of WriteReq misses
+system.cpu.dcache.demand_misses                   187                       # number of demand (read+write) misses
+system.cpu.dcache.overall_misses                  187                       # number of overall misses
+system.cpu.dcache.ReadReq_miss_latency        3859500                       # number of ReadReq miss cycles
+system.cpu.dcache.WriteReq_miss_latency       2916500                       # number of WriteReq miss cycles
+system.cpu.dcache.demand_miss_latency         6776000                       # number of demand (read+write) miss cycles
+system.cpu.dcache.overall_miss_latency        6776000                       # number of overall miss cycles
+system.cpu.dcache.ReadReq_accesses               1528                       # number of ReadReq accesses(hits+misses)
 system.cpu.dcache.WriteReq_accesses               934                       # number of WriteReq accesses(hits+misses)
-system.cpu.dcache.demand_accesses                2541                       # number of demand (read+write) accesses
-system.cpu.dcache.overall_accesses               2541                       # number of overall (read+write) accesses
-system.cpu.dcache.ReadReq_miss_rate          0.070317                       # miss rate for ReadReq accesses
-system.cpu.dcache.WriteReq_miss_rate         0.338330                       # miss rate for WriteReq accesses
-system.cpu.dcache.demand_miss_rate           0.168831                       # miss rate for demand accesses
-system.cpu.dcache.overall_miss_rate          0.168831                       # miss rate for overall accesses
-system.cpu.dcache.ReadReq_avg_miss_latency 34853.982301                       # average ReadReq miss latency
-system.cpu.dcache.WriteReq_avg_miss_latency 33887.658228                       # average WriteReq miss latency
-system.cpu.dcache.demand_avg_miss_latency 34142.191142                       # average overall miss latency
-system.cpu.dcache.overall_avg_miss_latency 34142.191142                       # average overall miss latency
+system.cpu.dcache.demand_accesses                2462                       # number of demand (read+write) accesses
+system.cpu.dcache.overall_accesses               2462                       # number of overall (read+write) accesses
+system.cpu.dcache.ReadReq_miss_rate          0.072644                       # miss rate for ReadReq accesses
+system.cpu.dcache.WriteReq_miss_rate         0.081370                       # miss rate for WriteReq accesses
+system.cpu.dcache.demand_miss_rate           0.075955                       # miss rate for demand accesses
+system.cpu.dcache.overall_miss_rate          0.075955                       # miss rate for overall accesses
+system.cpu.dcache.ReadReq_avg_miss_latency 34770.270270                       # average ReadReq miss latency
+system.cpu.dcache.WriteReq_avg_miss_latency        38375                       # average WriteReq miss latency
+system.cpu.dcache.demand_avg_miss_latency 36235.294118                       # average overall miss latency
+system.cpu.dcache.overall_avg_miss_latency 36235.294118                       # average overall miss latency
 system.cpu.dcache.blocked_cycles::no_mshrs            0                       # number of cycles access was blocked
 system.cpu.dcache.blocked_cycles::no_targets            0                       # number of cycles access was blocked
 system.cpu.dcache.blocked::no_mshrs                 0                       # number of cycles access was blocked
@@ -378,63 +378,62 @@
 system.cpu.dcache.fast_writes                       0                       # number of fast writes performed
 system.cpu.dcache.cache_copies                      0                       # number of cache copies performed
 system.cpu.dcache.writebacks                        0                       # number of writebacks
-system.cpu.dcache.ReadReq_mshr_hits                44                       # number of ReadReq MSHR hits
-system.cpu.dcache.WriteReq_mshr_hits              239                       # number of WriteReq MSHR hits
-system.cpu.dcache.demand_mshr_hits                283                       # number of demand (read+write) MSHR hits
-system.cpu.dcache.overall_mshr_hits               283                       # number of overall MSHR hits
-system.cpu.dcache.ReadReq_mshr_misses              69                       # number of ReadReq MSHR misses
-system.cpu.dcache.WriteReq_mshr_misses             77                       # number of WriteReq MSHR misses
+system.cpu.dcache.ReadReq_mshr_hits                41                       # number of ReadReq MSHR hits
+system.cpu.dcache.demand_mshr_hits                 41                       # number of demand (read+write) MSHR hits
+system.cpu.dcache.overall_mshr_hits                41                       # number of overall MSHR hits
+system.cpu.dcache.ReadReq_mshr_misses              70                       # number of ReadReq MSHR misses
+system.cpu.dcache.WriteReq_mshr_misses             76                       # number of WriteReq MSHR misses
 system.cpu.dcache.demand_mshr_misses              146                       # number of demand (read+write) MSHR misses
 system.cpu.dcache.overall_mshr_misses             146                       # number of overall MSHR misses
 system.cpu.dcache.overall_mshr_uncacheable_misses            0                       # number of overall MSHR uncacheable misses
-system.cpu.dcache.ReadReq_mshr_miss_latency      2422500                       # number of ReadReq MSHR miss cycles
-system.cpu.dcache.WriteReq_mshr_miss_latency      2761000                       # number of WriteReq MSHR miss cycles
-system.cpu.dcache.demand_mshr_miss_latency      5183500                       # number of demand (read+write) MSHR miss cycles
-system.cpu.dcache.overall_mshr_miss_latency      5183500                       # number of overall MSHR miss cycles
+system.cpu.dcache.ReadReq_mshr_miss_latency      2463000                       # number of ReadReq MSHR miss cycles
+system.cpu.dcache.WriteReq_mshr_miss_latency      2688500                       # number of WriteReq MSHR miss cycles
+system.cpu.dcache.demand_mshr_miss_latency      5151500                       # number of demand (read+write) MSHR miss cycles
+system.cpu.dcache.overall_mshr_miss_latency      5151500                       # number of overall MSHR miss cycles
 system.cpu.dcache.overall_mshr_uncacheable_latency            0                       # number of overall MSHR uncacheable cycles
-system.cpu.dcache.ReadReq_mshr_miss_rate     0.042937                       # mshr miss rate for ReadReq accesses
-system.cpu.dcache.WriteReq_mshr_miss_rate     0.082441                       # mshr miss rate for WriteReq accesses
-system.cpu.dcache.demand_mshr_miss_rate      0.057458                       # mshr miss rate for demand accesses
-system.cpu.dcache.overall_mshr_miss_rate     0.057458                       # mshr miss rate for overall accesses
-system.cpu.dcache.ReadReq_avg_mshr_miss_latency 35108.695652                       # average ReadReq mshr miss latency
-system.cpu.dcache.WriteReq_avg_mshr_miss_latency 35857.142857                       # average WriteReq mshr miss latency
-system.cpu.dcache.demand_avg_mshr_miss_latency 35503.424658                       # average overall mshr miss latency
-system.cpu.dcache.overall_avg_mshr_miss_latency 35503.424658                       # average overall mshr miss latency
+system.cpu.dcache.ReadReq_mshr_miss_rate     0.045812                       # mshr miss rate for ReadReq accesses
+system.cpu.dcache.WriteReq_mshr_miss_rate     0.081370                       # mshr miss rate for WriteReq accesses
+system.cpu.dcache.demand_mshr_miss_rate      0.059301                       # mshr miss rate for demand accesses
+system.cpu.dcache.overall_mshr_miss_rate     0.059301                       # mshr miss rate for overall accesses
+system.cpu.dcache.ReadReq_avg_mshr_miss_latency 35185.714286                       # average ReadReq mshr miss latency
+system.cpu.dcache.WriteReq_avg_mshr_miss_latency        35375                       # average WriteReq mshr miss latency
+system.cpu.dcache.demand_avg_mshr_miss_latency 35284.246575                       # average overall mshr miss latency
+system.cpu.dcache.overall_avg_mshr_miss_latency 35284.246575                       # average overall mshr miss latency
 system.cpu.dcache.overall_avg_mshr_uncacheable_latency     no_value                       # average overall mshr uncacheable latency
 system.cpu.dcache.mshr_cap_events                   0                       # number of times MSHR cap was activated
 system.cpu.dcache.soft_prefetch_mshr_full            0                       # number of mshr full events for SW prefetching instrutions
 system.cpu.dcache.no_allocate_misses                0                       # Number of misses that were no-allocate
 system.cpu.l2cache.replacements                     0                       # number of replacements
-system.cpu.l2cache.tagsinuse               178.614114                       # Cycle average of tags in use
+system.cpu.l2cache.tagsinuse               173.809724                       # Cycle average of tags in use
 system.cpu.l2cache.total_refs                       2                       # Total number of references to valid blocks.
-system.cpu.l2cache.sampled_refs                   364                       # Sample count of references to valid blocks.
-system.cpu.l2cache.avg_refs                  0.005495                       # Average number of references to valid blocks.
+system.cpu.l2cache.sampled_refs                   365                       # Sample count of references to valid blocks.
+system.cpu.l2cache.avg_refs                  0.005479                       # Average number of references to valid blocks.
 system.cpu.l2cache.warmup_cycle                     0                       # Cycle when the warmup percentage was hit.
-system.cpu.l2cache.occ_blocks::0           178.614114                       # Average occupied blocks per context
-system.cpu.l2cache.occ_percent::0            0.005451                       # Average percentage of cache occupancy
+system.cpu.l2cache.occ_blocks::0           173.809724                       # Average occupied blocks per context
+system.cpu.l2cache.occ_percent::0            0.005304                       # Average percentage of cache occupancy
 system.cpu.l2cache.ReadReq_hits                     2                       # number of ReadReq hits
 system.cpu.l2cache.demand_hits                      2                       # number of demand (read+write) hits
 system.cpu.l2cache.overall_hits                     2                       # number of overall hits
-system.cpu.l2cache.ReadReq_misses                 365                       # number of ReadReq misses
-system.cpu.l2cache.ReadExReq_misses                77                       # number of ReadExReq misses
+system.cpu.l2cache.ReadReq_misses                 366                       # number of ReadReq misses
+system.cpu.l2cache.ReadExReq_misses                76                       # number of ReadExReq misses
 system.cpu.l2cache.demand_misses                  442                       # number of demand (read+write) misses
 system.cpu.l2cache.overall_misses                 442                       # number of overall misses
-system.cpu.l2cache.ReadReq_miss_latency      12494500                       # number of ReadReq miss cycles
-system.cpu.l2cache.ReadExReq_miss_latency      2654000                       # number of ReadExReq miss cycles
-system.cpu.l2cache.demand_miss_latency       15148500                       # number of demand (read+write) miss cycles
-system.cpu.l2cache.overall_miss_latency      15148500                       # number of overall miss cycles
-system.cpu.l2cache.ReadReq_accesses               367                       # number of ReadReq accesses(hits+misses)
-system.cpu.l2cache.ReadExReq_accesses              77                       # number of ReadExReq accesses(hits+misses)
+system.cpu.l2cache.ReadReq_miss_latency      12541000                       # number of ReadReq miss cycles
+system.cpu.l2cache.ReadExReq_miss_latency      2603000                       # number of ReadExReq miss cycles
+system.cpu.l2cache.demand_miss_latency       15144000                       # number of demand (read+write) miss cycles
+system.cpu.l2cache.overall_miss_latency      15144000                       # number of overall miss cycles
+system.cpu.l2cache.ReadReq_accesses               368                       # number of ReadReq accesses(hits+misses)
+system.cpu.l2cache.ReadExReq_accesses              76                       # number of ReadExReq accesses(hits+misses)
 system.cpu.l2cache.demand_accesses                444                       # number of demand (read+write) accesses
 system.cpu.l2cache.overall_accesses               444                       # number of overall (read+write) accesses
-system.cpu.l2cache.ReadReq_miss_rate         0.994550                       # miss rate for ReadReq accesses
+system.cpu.l2cache.ReadReq_miss_rate         0.994565                       # miss rate for ReadReq accesses
 system.cpu.l2cache.ReadExReq_miss_rate              1                       # miss rate for ReadExReq accesses
 system.cpu.l2cache.demand_miss_rate          0.995495                       # miss rate for demand accesses
 system.cpu.l2cache.overall_miss_rate         0.995495                       # miss rate for overall accesses
-system.cpu.l2cache.ReadReq_avg_miss_latency 34231.506849                       # average ReadReq miss latency
-system.cpu.l2cache.ReadExReq_avg_miss_latency 34467.532468                       # average ReadExReq miss latency
-system.cpu.l2cache.demand_avg_miss_latency 34272.624434                       # average overall miss latency
-system.cpu.l2cache.overall_avg_miss_latency 34272.624434                       # average overall miss latency
+system.cpu.l2cache.ReadReq_avg_miss_latency 34265.027322                       # average ReadReq miss latency
+system.cpu.l2cache.ReadExReq_avg_miss_latency        34250                       # average ReadExReq miss latency
+system.cpu.l2cache.demand_avg_miss_latency 34262.443439                       # average overall miss latency
+system.cpu.l2cache.overall_avg_miss_latency 34262.443439                       # average overall miss latency
 system.cpu.l2cache.blocked_cycles::no_mshrs            0                       # number of cycles access was blocked
 system.cpu.l2cache.blocked_cycles::no_targets            0                       # number of cycles access was blocked
 system.cpu.l2cache.blocked::no_mshrs                0                       # number of cycles access was blocked
@@ -446,24 +445,24 @@
 system.cpu.l2cache.writebacks                       0                       # number of writebacks
 system.cpu.l2cache.demand_mshr_hits                 0                       # number of demand (read+write) MSHR hits
 system.cpu.l2cache.overall_mshr_hits                0                       # number of overall MSHR hits
-system.cpu.l2cache.ReadReq_mshr_misses            365                       # number of ReadReq MSHR misses
-system.cpu.l2cache.ReadExReq_mshr_misses           77                       # number of ReadExReq MSHR misses
+system.cpu.l2cache.ReadReq_mshr_misses            366                       # number of ReadReq MSHR misses
+system.cpu.l2cache.ReadExReq_mshr_misses           76                       # number of ReadExReq MSHR misses
 system.cpu.l2cache.demand_mshr_misses             442                       # number of demand (read+write) MSHR misses
 system.cpu.l2cache.overall_mshr_misses            442                       # number of overall MSHR misses
 system.cpu.l2cache.overall_mshr_uncacheable_misses            0                       # number of overall MSHR uncacheable misses
-system.cpu.l2cache.ReadReq_mshr_miss_latency     11330000                       # number of ReadReq MSHR miss cycles
-system.cpu.l2cache.ReadExReq_mshr_miss_latency      2409500                       # number of ReadExReq MSHR miss cycles
-system.cpu.l2cache.demand_mshr_miss_latency     13739500                       # number of demand (read+write) MSHR miss cycles
-system.cpu.l2cache.overall_mshr_miss_latency     13739500                       # number of overall MSHR miss cycles
+system.cpu.l2cache.ReadReq_mshr_miss_latency     11369000                       # number of ReadReq MSHR miss cycles
+system.cpu.l2cache.ReadExReq_mshr_miss_latency      2368500                       # number of ReadExReq MSHR miss cycles
+system.cpu.l2cache.demand_mshr_miss_latency     13737500                       # number of demand (read+write) MSHR miss cycles
+system.cpu.l2cache.overall_mshr_miss_latency     13737500                       # number of overall MSHR miss cycles
 system.cpu.l2cache.overall_mshr_uncacheable_latency            0                       # number of overall MSHR uncacheable cycles
-system.cpu.l2cache.ReadReq_mshr_miss_rate     0.994550                       # mshr miss rate for ReadReq accesses
+system.cpu.l2cache.ReadReq_mshr_miss_rate     0.994565                       # mshr miss rate for ReadReq accesses
 system.cpu.l2cache.ReadExReq_mshr_miss_rate            1                       # mshr miss rate for ReadExReq accesses
 system.cpu.l2cache.demand_mshr_miss_rate     0.995495                       # mshr miss rate for demand accesses
 system.cpu.l2cache.overall_mshr_miss_rate     0.995495                       # mshr miss rate for overall accesses
-system.cpu.l2cache.ReadReq_avg_mshr_miss_latency 31041.095890                       # average ReadReq mshr miss latency
-system.cpu.l2cache.ReadExReq_avg_mshr_miss_latency 31292.207792                       # average ReadExReq mshr miss latency
-system.cpu.l2cache.demand_avg_mshr_miss_latency 31084.841629                       # average overall mshr miss latency
-system.cpu.l2cache.overall_avg_mshr_miss_latency 31084.841629                       # average overall mshr miss latency
+system.cpu.l2cache.ReadReq_avg_mshr_miss_latency 31062.841530                       # average ReadReq mshr miss latency
+system.cpu.l2cache.ReadExReq_avg_mshr_miss_latency 31164.473684                       # average ReadExReq mshr miss latency
+system.cpu.l2cache.demand_avg_mshr_miss_latency 31080.316742                       # average overall mshr miss latency
+system.cpu.l2cache.overall_avg_mshr_miss_latency 31080.316742                       # average overall mshr miss latency
 system.cpu.l2cache.overall_avg_mshr_uncacheable_latency     no_value                       # average overall mshr uncacheable latency
 system.cpu.l2cache.mshr_cap_events                  0                       # number of times MSHR cap was activated
 system.cpu.l2cache.soft_prefetch_mshr_full            0                       # number of mshr full events for SW prefetching instrutions