* [PATCH] Benchtests: Increase benchmark iterations
@ 2024-01-03 14:13 Wilco Dijkstra
2024-01-03 18:39 ` Adhemerval Zanella Netto
0 siblings, 1 reply; 2+ messages in thread
From: Wilco Dijkstra @ 2024-01-03 14:13 UTC (permalink / raw)
To: 'GNU C Library'
Increase benchmark iterations for math and vector math functions to improve timing accuracy.
Vector math benchmarks now take 1-3 seconds on a modern CPU.
OK for commit?
---
diff --git a/benchtests/bench-libmvec-skeleton.c b/benchtests/bench-libmvec-skeleton.c
index 7fa96cabb7e7a302394b140ea095afa4afe5e6a5..e31458f02384a1ca61574681e8307a0d5023048a 100644
--- a/benchtests/bench-libmvec-skeleton.c
+++ b/benchtests/bench-libmvec-skeleton.c
@@ -29,7 +29,7 @@
#include <bench-libmvec-arch.h>
#include <bench-util.c>
-#define D_ITERS 10000
+#define D_ITERS 200000
int
main (int argc, char **argv)
diff --git a/benchtests/bench-skeleton.c b/benchtests/bench-skeleton.c
index fc9cf001fdc6ce4aae1a22c3ae21b2ae4424776b..824ea38b222a992de85e9a0acef2c73452c07ee7 100644
--- a/benchtests/bench-skeleton.c
+++ b/benchtests/bench-skeleton.c
@@ -48,7 +48,7 @@ main (int argc, char **argv)
memset (&runtime, 0, sizeof (runtime));
- unsigned long iters = 1000;
+ unsigned long iters = 2000;
#ifdef BENCH_INIT
BENCH_INIT ();
^ permalink raw reply [flat|nested] 2+ messages in thread
* Re: [PATCH] Benchtests: Increase benchmark iterations
2024-01-03 14:13 [PATCH] Benchtests: Increase benchmark iterations Wilco Dijkstra
@ 2024-01-03 18:39 ` Adhemerval Zanella Netto
0 siblings, 0 replies; 2+ messages in thread
From: Adhemerval Zanella Netto @ 2024-01-03 18:39 UTC (permalink / raw)
To: Wilco Dijkstra, 'GNU C Library'
On 03/01/24 11:13, Wilco Dijkstra wrote:
> Increase benchmark iterations for math and vector math functions to improve timing accuracy.
> Vector math benchmarks now take 1-3 seconds on a modern CPU.
>
> OK for commit?
>
LGTM, thanks.
Reviewed-bt: Adhemerval Zanella <adhemerval.zanella@linaro.org>
> ---
>
> diff --git a/benchtests/bench-libmvec-skeleton.c b/benchtests/bench-libmvec-skeleton.c
> index 7fa96cabb7e7a302394b140ea095afa4afe5e6a5..e31458f02384a1ca61574681e8307a0d5023048a 100644
> --- a/benchtests/bench-libmvec-skeleton.c
> +++ b/benchtests/bench-libmvec-skeleton.c
> @@ -29,7 +29,7 @@
> #include <bench-libmvec-arch.h>
>
> #include <bench-util.c>
> -#define D_ITERS 10000
> +#define D_ITERS 200000
>
> int
> main (int argc, char **argv)
> diff --git a/benchtests/bench-skeleton.c b/benchtests/bench-skeleton.c
> index fc9cf001fdc6ce4aae1a22c3ae21b2ae4424776b..824ea38b222a992de85e9a0acef2c73452c07ee7 100644
> --- a/benchtests/bench-skeleton.c
> +++ b/benchtests/bench-skeleton.c
> @@ -48,7 +48,7 @@ main (int argc, char **argv)
>
> memset (&runtime, 0, sizeof (runtime));
>
> - unsigned long iters = 1000;
> + unsigned long iters = 2000;
>
> #ifdef BENCH_INIT
> BENCH_INIT ();
>
^ permalink raw reply [flat|nested] 2+ messages in thread
end of thread, other threads:[~2024-01-03 18:39 UTC | newest]
Thread overview: 2+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2024-01-03 14:13 [PATCH] Benchtests: Increase benchmark iterations Wilco Dijkstra
2024-01-03 18:39 ` Adhemerval Zanella Netto
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).