glibc/benchtests/scripts/import_bench.py

140 lines
4.1 KiB
Python
Raw Normal View History

#!/usr/bin/python
# Copyright (C) 2015-2022 Free Software Foundation, Inc.
# This file is part of the GNU C Library.
#
# The GNU C Library is free software; you can redistribute it and/or
# modify it under the terms of the GNU Lesser General Public
# License as published by the Free Software Foundation; either
# version 2.1 of the License, or (at your option) any later version.
#
# The GNU C Library is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
# Lesser General Public License for more details.
#
# You should have received a copy of the GNU Lesser General Public
# License along with the GNU C Library; if not, see
Prefer https to http for gnu.org and fsf.org URLs Also, change sources.redhat.com to sourceware.org. This patch was automatically generated by running the following shell script, which uses GNU sed, and which avoids modifying files imported from upstream: sed -ri ' s,(http|ftp)(://(.*\.)?(gnu|fsf|sourceware)\.org($|[^.]|\.[^a-z])),https\2,g s,(http|ftp)(://(.*\.)?)sources\.redhat\.com($|[^.]|\.[^a-z]),https\2sourceware.org\4,g ' \ $(find $(git ls-files) -prune -type f \ ! -name '*.po' \ ! -name 'ChangeLog*' \ ! -path COPYING ! -path COPYING.LIB \ ! -path manual/fdl-1.3.texi ! -path manual/lgpl-2.1.texi \ ! -path manual/texinfo.tex ! -path scripts/config.guess \ ! -path scripts/config.sub ! -path scripts/install-sh \ ! -path scripts/mkinstalldirs ! -path scripts/move-if-change \ ! -path INSTALL ! -path locale/programs/charmap-kw.h \ ! -path po/libc.pot ! -path sysdeps/gnu/errlist.c \ ! '(' -name configure \ -execdir test -f configure.ac -o -f configure.in ';' ')' \ ! '(' -name preconfigure \ -execdir test -f preconfigure.ac ';' ')' \ -print) and then by running 'make dist-prepare' to regenerate files built from the altered files, and then executing the following to cleanup: chmod a+x sysdeps/unix/sysv/linux/riscv/configure # Omit irrelevant whitespace and comment-only changes, # perhaps from a slightly-different Autoconf version. git checkout -f \ sysdeps/csky/configure \ sysdeps/hppa/configure \ sysdeps/riscv/configure \ sysdeps/unix/sysv/linux/csky/configure # Omit changes that caused a pre-commit check to fail like this: # remote: *** error: sysdeps/powerpc/powerpc64/ppc-mcount.S: trailing lines git checkout -f \ sysdeps/powerpc/powerpc64/ppc-mcount.S \ sysdeps/unix/sysv/linux/s390/s390-64/syscall.S # Omit change that caused a pre-commit check to fail like this: # remote: *** error: sysdeps/sparc/sparc64/multiarch/memcpy-ultra3.S: last line does not end in newline git checkout -f sysdeps/sparc/sparc64/multiarch/memcpy-ultra3.S
2019-09-07 13:40:42 +08:00
# <https://www.gnu.org/licenses/>.
"""Functions to import benchmark data and process it"""
import json
try:
import jsonschema as validator
except ImportError:
print('Could not find jsonschema module.')
raise
2015-06-02 01:44:11 +08:00
def mean(lst):
"""Compute and return mean of numbers in a list
The numpy average function has horrible performance, so implement our
own mean function.
Args:
lst: The list of numbers to average.
Return:
The mean of members in the list.
"""
return sum(lst) / len(lst)
def split_list(bench, func, var):
""" Split the list into a smaller set of more distinct points
Group together points such that the difference between the smallest
point and the mean is less than 1/3rd of the mean. This means that
the mean is at most 1.5x the smallest member of that group.
mean - xmin < mean / 3
i.e. 2 * mean / 3 < xmin
i.e. mean < 3 * xmin / 2
For an evenly distributed group, the largest member will be less than
twice the smallest member of the group.
Derivation:
An evenly distributed series would be xmin, xmin + d, xmin + 2d...
mean = (2 * n * xmin + n * (n - 1) * d) / 2 * n
and max element is xmin + (n - 1) * d
Now, mean < 3 * xmin / 2
3 * xmin > 2 * mean
3 * xmin > (2 * n * xmin + n * (n - 1) * d) / n
3 * n * xmin > 2 * n * xmin + n * (n - 1) * d
n * xmin > n * (n - 1) * d
xmin > (n - 1) * d
2 * xmin > xmin + (n-1) * d
2 * xmin > xmax
Hence, proved.
Similarly, it is trivial to prove that for a similar aggregation by using
the maximum element, the maximum element in the group must be at most 4/3
times the mean.
Args:
bench: The benchmark object
func: The function name
var: The function variant name
"""
means = []
lst = bench['functions'][func][var]['timings']
last = len(lst) - 1
while lst:
for i in range(last + 1):
avg = mean(lst[i:])
if avg > 0.75 * lst[last]:
means.insert(0, avg)
lst = lst[:i]
last = i - 1
break
bench['functions'][func][var]['timings'] = means
def do_for_all_timings(bench, callback):
"""Call a function for all timing objects for each function and its
variants.
Args:
bench: The benchmark object
callback: The callback function
"""
for func in bench['functions'].keys():
for k in bench['functions'][func].keys():
if 'timings' not in bench['functions'][func][k].keys():
continue
callback(bench, func, k)
def compress_timings(points):
"""Club points with close enough values into a single mean value
See split_list for details on how the clubbing is done.
Args:
points: The set of points.
"""
do_for_all_timings(points, split_list)
def parse_bench(filename, schema_filename):
"""Parse the input file
Parse and validate the json file containing the benchmark outputs. Return
the resulting object.
Args:
filename: Name of the benchmark output file.
Return:
The bench dictionary.
"""
with open(schema_filename, 'r') as schemafile:
schema = json.load(schemafile)
with open(filename, 'r') as benchfile:
bench = json.load(benchfile)
validator.validate(bench, schema)
return bench