lib/glibc
1
0
Fork 0
mirror of https://sourceware.org/git/glibc.git synced 2025-07-29 11:41:21 +03:00
Code Activity

Maintain runtime of each benchmark at ~10 seconds

Browse Source 
The idea to run benchmarks for a constant number of iterations is
problematic.  While the benchmarks may run for 10 seconds on x86_64,
they could run for about 30 seconds on powerpc and worse, over 3
minutes on arm.  Besides that, adding a new benchmark is cumbersome
since one needs to find out the number of iterations needed for a
sufficient runtime.

A better idea would be to run each benchmark for a specific amount of
time.  This patch does just that.  The run time defaults to 10 seconds
and it is configurable at command line:

  make BENCH_DURATION=5 bench
This commit is contained in:
Siddhesh Poyarekar
2013-04-30 14:10:20 +05:30
parent a6a242fe7c
commit d569c6eeb4
5 changed files with 54 additions and 36 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
scripts/bench.pl
View File

@ -22,23 +22,22 @@ use warnings;
# Generate a benchmark source file for a given input.
if (@ARGV < 2) {
die "Usage: bench.pl <function> <iterations> [parameter types] [return type]"
die "Usage: bench.pl <function> [parameter types] [return type]"
}
my $arg;
my $func = $ARGV[0];
my $iters = $ARGV[1];
my @args;
my $ret = "void";
my $getret = "";
my $retval = "";
if (@ARGV >= 3) {
@args = split(':', $ARGV[2]);
if (@ARGV >= 2) {
@args = split(':', $ARGV[1]);
}
if (@ARGV == 4) {
$ret = $ARGV[3];
if (@ARGV == 3) {
$ret = $ARGV[2];
}
my $decl = "extern $ret $func (";
@ -88,6 +87,5 @@ if ($ret ne "void") {
print "#define BENCH_FUNC(j) ({$getret CALL_BENCH_FUNC (j);})\n";
print "#define ITER $iters\n";
print "#define FUNCNAME \"$func\"\n";
print "#include \"bench-skeleton.c\"\n";