Changeset bd72f517 for doc/theses/mike_brooks_MMath/plots/string-peq-cppemu.py

Timestamp:

May 13, 2025, 1:17:50 PM (4 months ago)

Author:

Mike Brooks <mlbrooks@…>

Branches:

master

Children:

0528d79

Parents:

7d02d35 (diff), 2410424 (diff)
Note: this is a merge changeset, the changes displayed below correspond to the merge itself.
Use the (diff) links above to see all the changes relative to each parent.

Message:

Merge branch 'master' of plg.uwaterloo.ca:software/cfa/cfa-cc

File:

• doc/theses/mike_brooks_MMath/plots/string-peq-cppemu.py (modified) (2 diffs)

doc/theses/mike_brooks_MMath/plots/string-peq-cppemu.py

@@ -12 +12 @@
 import pandas as pd
 import numpy as np
+import sys
 import os
 
-infile = os.path.dirname(os.path.abspath(__file__)) + '/../benchmarks/string/result-append-pbv.csv'
+sys.path.insert(0, os.path.dirname(__file__))
+from common import *
 
 prettyFieldNames = {
@@ -23 +25 @@
 }
 
-timings = pd.read_csv(
-    infile,
-    names=['test', 'corpus', 'concatsPerReset', 'corpusItemCount', 'corpusMeanLenChars', 'concatDoneActualCount', 'execTimeActualSec'],
-    dtype={'test':                  str,
-           'corpus':                str,
-           'concatsPerReset':       'Int64', # allows missing; https://stackoverflow.com/a/70626154
-           'corpusItemCount':       np.int64,
-           'corpusMeanLenChars':    np.float64,
-           'concatDoneActualCount': np.int64,
-           'execTimeActualSec':     np.float64},
-    na_values=['xxx'],
-)
-# print(timings.head())
+timings = loadParseTimingData('result-append-pbv.csv')
 
+# Filter operation=peq, corpus=100-*-1
 
-# project: parse executable and corpus names
-
-timings[['test-slug',
-     'sut-platform',
-     'operation',
-     'sut-cfa-level',
-     'sut-cfa-sharing',
-     'op-alloc']] = timings['test'].str.strip().str.split('-', expand=True)
-timings['sut'] = timings[['sut-platform',
-                    'sut-cfa-level',
-                    'sut-cfa-sharing',
-                    'op-alloc']].agg('-'.join, axis=1)
-
-timings[['corpus-basename',
-     'corpus-ext']] = timings['corpus'].str.strip().str.split('.', expand=True)
-timings[['corpus-slug',
-     'corpus-nstrs',
-     'corpus-meanlen',
-     'corpus-runid']] = timings['corpus-basename'].str.strip().str.split('-', expand=True)
-timings["corpus-nstrs"] = pd.to_numeric(timings["corpus-nstrs"])
-timings["corpus-meanlen"] = pd.to_numeric(timings["corpus-meanlen"])
-timings["corpus-runid"] = pd.to_numeric(timings["corpus-runid"])
-
-
-# project: calculate fact
-
-timings['op-duration-s'] = timings['execTimeActualSec'] / timings['concatDoneActualCount']
-timings['op-duration-ns'] = timings['op-duration-s'] * 1000 * 1000 * 1000
-
-
-# Filter operation=peq
-
-groupedOp = timings.groupby('operation')
-tgtOpTimings = groupedOp.get_group('peq')
-
+timings = timings.groupby('operation').get_group('peq')
+timings = timings.groupby('corpus-nstrs').get_group(100)
+timings = timings.groupby('corpus-runid').get_group(1)
 
 # Emit in groups
 
-groupedSut = tgtOpTimings.groupby('sut')
+groupedSut = timings.groupby('sut')
 
 for sut, sgroup in groupedSut: