From 764ce559f812b72e8b932b585a6c407ff55f50f1 Mon Sep 17 00:00:00 2001
From: John Cupitt <jcupitt@gmail.com>
Date: Wed, 3 Aug 2011 11:25:31 +0100
Subject: [PATCH] better benchmark prog

the benchmark program (benchmark/benchmarkn.sh) runs each test three
times and just reports the fastest run

it also detects the number of CPUs you have and automatically loops the
right number of times

additionally, tiles now default to 512x512, so it explicitly sets tiles
back to 64x64 to make comparisons with earlier versions easier
---
 ChangeLog               |  2 ++
 benchmark/benchmarkn.sh | 50 ++++++++++++++++++++++++++++-------------
 2 files changed, 36 insertions(+), 16 deletions(-)

diff --git a/ChangeLog b/ChangeLog
index f7a4c9e9..4869fdfd 100644
--- a/ChangeLog
+++ b/ChangeLog
@@ -3,6 +3,8 @@
 - oops, ==0 missing from a strcmp() in vips7compat
 - fixed a race in im_XYZ2Lab() table build
 - added im_concurrency_get() to operation db
+- better benchmarkn.sh runs for the correct number of CPUs automatically, runs
+  three times for each one, and just reports the fastest
 
 26/7/11 started 7.26.0
 - version bunp for 7.26
diff --git a/benchmark/benchmarkn.sh b/benchmark/benchmarkn.sh
index 16a40b63..9527cda4 100755
--- a/benchmark/benchmarkn.sh
+++ b/benchmark/benchmarkn.sh
@@ -1,4 +1,4 @@
-#!/bin/sh
+#!/bin/bash
 
 uname -a
 gcc --version
@@ -7,7 +7,7 @@ vips --version
 # how large an image do you want to process? 
 # sample2.v is 290x442 pixels ... replicate this many times horizontally and 
 # vertically to get a highres image for the benchmark
-tile=2
+tile=13
 
 # how complex an operation do you want to run?
 # this sets the number of copies of the benchmark we chain together:
@@ -21,26 +21,44 @@ if [ $? != 0 ]; then
   echo "build of test image failed -- out of disc space?"
   exit 1
 fi
-echo -n "test image is" `header -f Xsize temp.v` 
-echo " by" `header -f Ysize temp.v` "pixels"
+echo -n "test image is" `header -f width temp.v` 
+echo " by" `header -f height temp.v` "pixels"
+max_cpus=`vips im_concurrency_get`
 
+echo "max cpus = $max_cpus"
 echo "starting benchmark ..."
-echo "chain=$chain"
-
-for cpus in 1 2 3 4 ; do
-  export IM_CONCURRENCY=$cpus
-
-  echo IM_CONCURRENCY=$IM_CONCURRENCY
-  echo time -p vips im_benchmarkn temp.v temp2.v $chain
-  time -p vips im_benchmarkn temp.v temp2-$cpus.v $chain
+echo /usr/bin/time -f %e vips \
+  --vips-concurrency=xx \
+  --vips-tile-width=64 --vips-tile-height=64 \
+  im_benchmarkn temp.v temp2.v $chain
+echo reported real-time is best of three runs
+echo cpus real-time
 
+for((cpus = 1; cpus <= max_cpus; cpus++)); do
+  t1=`/usr/bin/time -f %e vips \
+	  --vips-concurrency=$cpus \
+	  --vips-tile-width=64 --vips-tile-height=64 \
+	  im_benchmarkn temp.v temp2.v $chain 2>&1`
   if [ $? != 0 ]; then
     echo "benchmark failed -- install problem?"
     exit 1
   fi
+  t2=`/usr/bin/time -f %e vips \
+	  --vips-concurrency=$cpus \
+	  --vips-tile-width=64 --vips-tile-height=64 \
+	  im_benchmarkn temp.v temp2.v $chain 2>&1`
+  t3=`/usr/bin/time -f %e vips \
+	  --vips-concurrency=$cpus \
+	  --vips-tile-width=64 --vips-tile-height=64 \
+	  im_benchmarkn temp.v temp2.v $chain 2>&1`
 
-  # find pixel average ... should be the same for all IM_CONCURRENCY settings
-  # or we have some kind of terrible bug
-  echo vips im_avg temp2-$cpus.v
-  vips im_avg temp2-$cpus.v
+  # echo $t1 $t2 $t3
+
+  if [[ $t2 < $t1 ]]; then
+	  t1=$t2
+  fi
+  if [[ $t3 < $t1 ]]; then
+	  t1=$t3
+  fi
+  echo $cpus $t1
 done