Changeset 2410424 for doc/theses/mike_brooks_MMath/plots

Timestamp:

May 13, 2025, 12:54:03 PM (5 months ago)

Author:

Michael Brooks <mlbrooks@…>

Branches:

master

Children:

bd72f517

Parents:

edd11bd

Message:

Pushing work in progress on data for string plots.

All in-thesis plots source from baselined result data, with no manual massaging. Removing older placeholder graph images and temp data.

Allocation plot, especially the last attribution stacked bar, is showing untrustrworthy data.

Location:

doc/theses/mike_brooks_MMath/plots

Files:

• common.py (added)
• string-allocn-attrib.py (added)
• string-allocn.d (added)
• string-allocn.gp (added)
• string-allocn.py (added)
• string-pbv-fixcorp.py (added)
• string-pbv-varcorp.py (added)
• string-pbv.d (added)
• string-pbv.gp (moved) (moved from doc/theses/mike_brooks_MMath/plot-pbv.gp ) (2 diffs)
• string-peq-cppemu.py (modified) (2 diffs)
• string-peq-sharing.d (added)
• string-peq-sharing.gp (moved) (moved from doc/theses/mike_brooks_MMath/plot-peq-sharing.gp ) (2 diffs)
• string-peq-sharing.py (added)
• string-pta-sharing.d (added)
• string-pta-sharing.gp (moved) (moved from doc/theses/mike_brooks_MMath/plot-pta-sharing.gp ) (2 diffs)
• string-pta-sharing.py (added)

doc/theses/mike_brooks_MMath/plots/string-pbv.gp

@@ -3 +3 @@
 #set terminal wxt size 950,1250
 
-DIR="pictures"
+INDIR="build"
+OUTDIR="build"
 
 set macros
-set output "build/string-graph-pbv.pdf"
+set output OUTDIR."/plot-string-pbv.pdf"
+
+set multiplot layout 1, 2 ;
+
+
 #set pointsize 2.0
 set grid
@@ -14 +19 @@
 set logscale x
 set logscale y 2
-set xlabel "String Length being passed (interp. varies)" offset 2,0
-set ylabel "Time per append (ns, mean), log_{2} scale"
+set xlabel "String length passed, varying (mean)"
+set ylabel "Time per pass (ns, mean), log_{2} scale"
+set yrange [4:64]
 set linetype 3 dashtype 2
 set linetype 4 dashtype 2
-plot DIR."/string-graph-pbv.dat" \
-           i 0 using 1:2 title columnheader(1) with linespoints lt rgb "blue"   pt  2  ps 1 lw 1, \
-        '' i 1 using 1:2 title columnheader(1) with linespoints lt rgb "red"    pt  3  ps 1 lw 1, \
-        '' i 2 using 1:2 title columnheader(1) with linespoints lt rgb "blue"   pt  6  ps 1 lw 1
+plot INDIR."/plot-string-pbv-varcorp.dat" \
+           i 0 using 1:2 title columnheader(1) with linespoints lt rgb "red"    pt  3  ps 1 lw 1, \
+        '' i 1 using 1:2 title columnheader(1) with linespoints lt rgb "blue"   pt  6  ps 1 lw 1
+
+set xlabel "String length passed, fixed"
+set ylabel
+plot INDIR."/plot-string-pbv-fixcorp.dat"  \
+           i 0 using 1:2 title columnheader(1) with linespoints lt rgb "red"    pt  3  ps 1 lw 1, \
+        '' i 1 using 1:2 title columnheader(1) with linespoints lt rgb "blue"   pt  6  ps 1 lw 1
+
+unset multiplot

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:

doc/theses/mike_brooks_MMath/plots/string-peq-sharing.gp

@@ -3 +3 @@
 #set terminal wxt size 950,1250
 
-DIR="pictures"
+INDIR="build"
+OUTDIR="build"
 
 set macros
-set output "build/string-graph-peq-sharing.pdf"
+set output OUTDIR."/plot-string-peq-sharing.pdf"
 #set pointsize 2.0
 set grid
@@ -12 +13 @@
 set xtics (1,2,5,10,20,50,100,200,500)
 set logscale x
-#set logscale y 2
-set yrange [0:115]
+#set logscale y
+set yrange [10:115]
 set xlabel "String Length being appended (mean, geo. dist.), log scale" offset 2,0
 set ylabel "Time per append (ns, mean)"
 set linetype 2 dashtype 2
 set linetype 4 dashtype 2
-plot DIR."/string-graph-peq-sharing.dat" \
+plot INDIR."/plot-string-peq-sharing.dat" \
            i 0 using 1:2 title columnheader(1) with linespoints lt rgb "red"    pt  2  ps 1 lw 1, \
         '' i 1 using 1:2 title columnheader(1) with linespoints lt rgb "red"    pt  3  ps 1 lw 1, \

doc/theses/mike_brooks_MMath/plots/string-pta-sharing.gp

@@ -3 +3 @@
 #set terminal wxt size 950,1250
 
-DIR="pictures"
+INDIR="build"
+OUTDIR="build"
 
 set macros
-set output "build/string-graph-pta-sharing.pdf"
+set output OUTDIR."/plot-string-pta-sharing.pdf"
 #set pointsize 2.0
 set grid
@@ -16 +17 @@
 set xlabel "String Length being appended (mean, geo. dist.), log scale" offset 2,0
 set ylabel "Time per append (ns, mean), log_{2} scale"
-set linetype 2 dashtype 2
-set linetype 6 dashtype 2
 #show colornames
-plot DIR."/string-graph-pta-sharing.dat" \
+plot INDIR."/plot-string-pta-sharing.dat" \
            i 0 using 1:2 title columnheader(1) with linespoints lt rgb "red"    pt  2  ps 1 lw 1, \
-        '' i 1 using 1:2 title columnheader(1) with linespoints lt rgb "red"    pt  3  ps 1 lw 1, \
-        '' i 2 using 1:2 title columnheader(1) with linespoints lt rgb "dark-green" pt  4  ps 1 lw 1, \
-        '' i 3 using 1:2 title columnheader(1) with linespoints lt rgb "blue"   pt  6  ps 1 lw 1, \
-        '' i 4  using 1:2 title columnheader(1) with linespoints lt rgb "dark-green" pt  12  ps 1 lw 1, \
-        '' i 5  using 1:2 title columnheader(1) with linespoints lt rgb "blue"  pt  8  ps 1 lw 1
+        '' i 1 using 1:2 title columnheader(1) with linespoints lt rgb "dark-green" pt  4  ps 1 lw 1, \
+        '' i 2 using 1:2 title columnheader(1) with linespoints lt rgb "blue"   pt  6  ps 1 lw 1, \
+        '' i 3  using 1:2 title columnheader(1) with linespoints lt rgb "dark-green" pt  12  ps 1 lw 1