python: Add search functions to pystats groups
This change adds three functions, a `children` function which will
iterate through all of the children of group based (optionally) on some
predicate. Then, it implements a `find` function and a `find_re`
function using the `children` function.
The `find` function allows users to match statistics or groups
within a group. For instance, you might want to find all of the groups
within the system which have the name "cpu{i}". This is useful for
aggregate statistic values across multiple components.
Example:
total_instruuctions = sum([cpu.exec_context.thread_0.numInsts.value
for cpu in simstat.system.find('cpu')])
The find function matches based on substring. If the name given the find
function is a substring of the stat name or the group name the
stat/group will be returned.
The `find_re` function is the same as find, but matches a regular
expression instead of a simple substring match.
Note: this was originally reviewed on
https://gem5-review.googlesource.com/c/public/gem5/+/41603 was rebased
incorrectly before merging. This change fixes the rebase and adds back
the children() and re_find() functions.
Change-Id: Idaa1e9efc56fd26de3285d3fa505087ddd78ac8a
Signed-off-by: Jason Lowe-Power <jason@lowepower.com>
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/42014
Maintainer: Jason Lowe-Power <power.jg@gmail.com>
Tested-by: kokoro <noreply+kokoro@google.com>
Reviewed-by: Andreas Sandberg <andreas.sandberg@arm.com>
diff --git a/src/python/m5/ext/pystats/group.py b/src/python/m5/ext/pystats/group.py
index 10887e2..bde1c40 100644
--- a/src/python/m5/ext/pystats/group.py
+++ b/src/python/m5/ext/pystats/group.py
@@ -24,7 +24,8 @@
# (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
# OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
-from typing import Dict, Iterator, List, Optional, Union
+import re
+from typing import Callable, Dict, Iterator, List, Optional, Union
from .jsonserializable import JsonSerializable
from .statistic import Scalar, Statistic
@@ -53,25 +54,72 @@
for key,value in kwargs.items():
setattr(self, key, value)
+ def children(self, predicate: Optional[Callable[[str], bool]] = None
+ ) -> Iterator[Union["Group", Statistic]]:
+ """ Iterate through all of the children, optionally with a predicate
+
+ ```
+ >>> system.children(lambda _name: 'cpu' in name)
+ [cpu0, cpu1, cpu2]
+ ```
+
+ :param: predicate(str) -> bool: Optional. Each child's name is passed
+ to this function. If it returns true, then the child is
+ yielded. Otherwise, the child is skipped.
+ If not provided then all children are returned.
+ """
+ for attr in self.__dict__:
+ # Check the provided predicate. If not a match, skip this child
+ if predicate and not predicate(attr): continue
+ obj = getattr(self, attr)
+ if isinstance(obj, Group) or isinstance(obj, Statistic):
+ yield obj
+
def find(self, name: str) -> Iterator[Union["Group", Statistic]]:
""" Find all stats that match the name
+
This function searches all of the "children" in this group. It yields
the set of attributes (children) that have the `name` as a substring.
The order of the objects returned by the generator is arbitrary.
+
```
- system.find('cpu') -> [cpu0, cpu1, cpu2, cpu3, other_cpu, ...]
+ >>> system.find('cpu')
+ [cpu0, cpu1, cpu2, cpu3, other_cpu, ...]
```
+
This is useful for performing aggregates over substats. For instance:
+
```
- total_instruuctions = sum([cpu.exec_context.thread_0.numInsts.value
- for cpu in simstat.system.find('cpu')])
+ >>> total_instructions = sum([cpu.exec_context.thread_0.numInsts.value
+ for cpu in simstat.system.find('cpu')])
+ 100000
```
+
+ :param: name: The name to search for
"""
- for attr in self.__dict__:
- if name in attr:
- obj = getattr(self, attr)
- if isinstance(obj, Group) or isinstance(obj, Statistic):
- yield obj
+ yield from self.children(lambda _name: _name in name)
+
+ def find_re(self, regex: Union[str, re.Pattern]
+ ) -> Iterator[Union["Group", Statistic]]:
+ """ Find all stats that match the name
+
+ This function searches all of the "children" in this group. It yields
+ the set of attributes (children) that have the `name` mathing the
+ regex provided. The order of the objects returned by the generator is
+ arbitrary.
+
+ ```
+ >>> system.find_re('cpu[0-9]')
+ [cpu0, cpu1, cpu2]
+ ```
+ Note: The above will not match `cpu_other`.
+
+ :param: regex: The regular expression used to search. Can be a
+ precompiled regex or a string in regex format
+ """
+ if isinstance(regex, str):
+ regex = re.compile(regex)
+ yield from self.children(lambda _name: regex.search(_name))
class Vector(Group):
"""
@@ -86,4 +134,4 @@
type="Vector",
time_conversion=None,
**scalar_map,
- )
\ No newline at end of file
+ )
