| Message ID | 20230403141105.551198-1-nisha.s.menon@gmail.com |
|---|---|
| State | New |
| Headers | show |
| Series | compare_strings.py : Add --gmean flag | expand |
On Mon, Apr 3, 2023 at 9:11 AM Nisha Poyarekar via Libc-alpha <libc-alpha@sourceware.org> wrote: > > To calculate geometric mean for string benchmark results. > > Signed-off-by: Nisha Poyarekar <nisha.s.menon@gmail.com> > --- > benchtests/scripts/compare_strings.py | 20 ++++++++++++++++++-- > 1 file changed, 18 insertions(+), 2 deletions(-) > > diff --git a/benchtests/scripts/compare_strings.py b/benchtests/scripts/compare_strings.py > index 1195a6c741..a4ab3e42c2 100755 > --- a/benchtests/scripts/compare_strings.py > +++ b/benchtests/scripts/compare_strings.py > @@ -21,6 +21,7 @@ Given a string benchmark result file, print a table with comparisons with a > baseline. The baseline is the first function, which typically is the builtin > function. > """ > +import math > import matplotlib as mpl > mpl.use('Agg') > > @@ -83,7 +84,8 @@ def draw_graph(f, v, ifuncs, results): > pylab.savefig('%s-%s.png' % (f, v), bbox_inches='tight') > > > -def process_results(results, attrs, funcs, base_func, graph, no_diff, no_header): > +def process_results(results, attrs, funcs, base_func, graph, no_diff, > + no_header, gmean): > """ Process results and print them > > Args: > @@ -132,6 +134,8 @@ def process_results(results, attrs, funcs, base_func, graph, no_diff, no_header) > print("%36s%s" % (' ', '\t'.join(ifuncs))) > print("=" * 120) > > + mean_row = [0 for i in range(len(ifuncs))] > + total=0 > graph_res = {} > for res in results['functions'][f]['results']: > try: > @@ -144,8 +148,11 @@ def process_results(results, attrs, funcs, base_func, graph, no_diff, no_header) > key = ', '.join(attr_list) > sys.stdout.write('%36s: ' % key) > graph_res[key] = res['timings'] > + > for t in res['timings']: > if selected[i]: > + if gmean: > + mean_row[i] = mean_row[i]+math.log(t) Is there an issue using statistics package and just doing: `statistics.geometric_mean` ? Otherwise LGTM. > sys.stdout.write ('%12.2f' % t) > if not no_diff: > if i != base_index: > @@ -159,6 +166,12 @@ def process_results(results, attrs, funcs, base_func, graph, no_diff, no_header) > if graph: > draw_graph(f, v, results['functions'][f]['ifuncs'], graph_res) > > + if gmean: > + print("=" * 120) > + total = len(results['functions'][f]['results']) > + sys.stdout.write ('Geo-mean (for %s inputs)'%total) > + for m in mean_row: > + sys.stdout.write ('%12.2f' % (math.exp(m/total))) > > def main(args): > """Program Entry Point > @@ -180,7 +193,8 @@ def main(args): > funcs = None > > results = parse_file(args.input, args.schema) > - process_results(results, attrs, funcs, base_func, args.graph, args.no_diff, args.no_header) > + process_results(results, attrs, funcs, base_func, args.graph, args.no_diff, > + args.no_header, args.gmean) > return os.EX_OK > > > @@ -207,6 +221,8 @@ if __name__ == '__main__': > help='Do not print the difference from baseline.') > parser.add_argument('--no-header', action='store_true', > help='Do not print the header.') > + parser.add_argument('--gmean', action='store_true', > + help='Print the geometric mean at the end of the output.') > > args = parser.parse_args() > sys.exit(main(args)) > -- > 2.37.2 >
* Noah Goldstein via Libc-alpha: > Is there an issue using statistics package and just doing: > `statistics.geometric_mean` > ? According to <https://docs.python.org/3/library/statistics.html#statistics.geometric_mean> it was added in Python 3.8, which is newer than what we aim for in general (INSTALL currently mentions Python 3.4). Thanks, Florian
On Mon, Apr 3, 2023 at 5:37 PM Florian Weimer <fweimer@redhat.com> wrote: > > * Noah Goldstein via Libc-alpha: > > > Is there an issue using statistics package and just doing: > > `statistics.geometric_mean` > > ? > > According to > > <https://docs.python.org/3/library/statistics.html#statistics.geometric_mean> > > it was added in Python 3.8, which is newer than what we aim for in > general (INSTALL currently mentions Python 3.4). > So is the fix okay as it is? Thanks, Nisha
On Mon, Apr 3, 2023 at 5:58 PM Nisha Menon <nisha.s.menon@gmail.com> wrote: > > On Mon, Apr 3, 2023 at 5:37 PM Florian Weimer <fweimer@redhat.com> wrote: > > > > * Noah Goldstein via Libc-alpha: > > > > > Is there an issue using statistics package and just doing: > > > `statistics.geometric_mean` > > > ? > > > > According to > > > > <https://docs.python.org/3/library/statistics.html#statistics.geometric_mean> > > > > it was added in Python 3.8, which is newer than what we aim for in > > general (INSTALL currently mentions Python 3.4). > > > > So is the fix okay as it is? > > Thanks, > Nisha Yeah LGTM.
On Mon, Apr 3, 2023 at 7:35 PM Noah Goldstein <goldstein.w.n@gmail.com> wrote: > > So is the fix okay as it is? > > > > Thanks, > > Nisha > > Yeah LGTM. Thanks. Can you please push the patch for me. I don't have commit access. Thanks, Nisha
diff --git a/benchtests/scripts/compare_strings.py b/benchtests/scripts/compare_strings.py index 1195a6c741..a4ab3e42c2 100755 --- a/benchtests/scripts/compare_strings.py +++ b/benchtests/scripts/compare_strings.py @@ -21,6 +21,7 @@ Given a string benchmark result file, print a table with comparisons with a baseline. The baseline is the first function, which typically is the builtin function. """ +import math import matplotlib as mpl mpl.use('Agg') @@ -83,7 +84,8 @@ def draw_graph(f, v, ifuncs, results): pylab.savefig('%s-%s.png' % (f, v), bbox_inches='tight') -def process_results(results, attrs, funcs, base_func, graph, no_diff, no_header): +def process_results(results, attrs, funcs, base_func, graph, no_diff, + no_header, gmean): """ Process results and print them Args: @@ -132,6 +134,8 @@ def process_results(results, attrs, funcs, base_func, graph, no_diff, no_header) print("%36s%s" % (' ', '\t'.join(ifuncs))) print("=" * 120) + mean_row = [0 for i in range(len(ifuncs))] + total=0 graph_res = {} for res in results['functions'][f]['results']: try: @@ -144,8 +148,11 @@ def process_results(results, attrs, funcs, base_func, graph, no_diff, no_header) key = ', '.join(attr_list) sys.stdout.write('%36s: ' % key) graph_res[key] = res['timings'] + for t in res['timings']: if selected[i]: + if gmean: + mean_row[i] = mean_row[i]+math.log(t) sys.stdout.write ('%12.2f' % t) if not no_diff: if i != base_index: @@ -159,6 +166,12 @@ def process_results(results, attrs, funcs, base_func, graph, no_diff, no_header) if graph: draw_graph(f, v, results['functions'][f]['ifuncs'], graph_res) + if gmean: + print("=" * 120) + total = len(results['functions'][f]['results']) + sys.stdout.write ('Geo-mean (for %s inputs)'%total) + for m in mean_row: + sys.stdout.write ('%12.2f' % (math.exp(m/total))) def main(args): """Program Entry Point @@ -180,7 +193,8 @@ def main(args): funcs = None results = parse_file(args.input, args.schema) - process_results(results, attrs, funcs, base_func, args.graph, args.no_diff, args.no_header) + process_results(results, attrs, funcs, base_func, args.graph, args.no_diff, + args.no_header, args.gmean) return os.EX_OK @@ -207,6 +221,8 @@ if __name__ == '__main__': help='Do not print the difference from baseline.') parser.add_argument('--no-header', action='store_true', help='Do not print the header.') + parser.add_argument('--gmean', action='store_true', + help='Print the geometric mean at the end of the output.') args = parser.parse_args() sys.exit(main(args))
To calculate geometric mean for string benchmark results. Signed-off-by: Nisha Poyarekar <nisha.s.menon@gmail.com> --- benchtests/scripts/compare_strings.py | 20 ++++++++++++++++++-- 1 file changed, 18 insertions(+), 2 deletions(-)