public inbox for libc-alpha@sourceware.org
 help / color / mirror / Atom feed
From: "H.J. Lu" <hjl.tools@gmail.com>
To: Noah Goldstein <goldstein.w.n@gmail.com>
Cc: libc-alpha@sourceware.org, carlos@systemhalted.org
Subject: Re: [PATCH v1 2/5] benchtests: Add additional cases to bench-memcpy.c and bench-memmove.c
Date: Fri, 5 Nov 2021 19:27:52 -0700	[thread overview]
Message-ID: <YYXoKH3KFDKOPWz+@gmail.com> (raw)
In-Reply-To: <20211101054952.2349590-2-goldstein.w.n@gmail.com>

On Mon, Nov 01, 2021 at 12:49:49AM -0500, Noah Goldstein wrote:
> This commit adds more benchmarks for the common memcpy/memmove
> benchmarks. The most signifcant cases are the half page offsets. The
> current versions leaves dst and src near page aligned which leads to
> false 4k aliasing on x86_64. This can add noise due to false
> dependencies from one run to the next. As well, this seems like more
> of an edge case that common case so it shouldn't be the only thing
> ---
>  benchtests/bench-memcpy.c  | 49 +++++++++++++++++++++++++++++++++-----
>  benchtests/bench-memmove.c | 26 +++++++++++++++++---
>  2 files changed, 66 insertions(+), 9 deletions(-)
> 
> diff --git a/benchtests/bench-memcpy.c b/benchtests/bench-memcpy.c
> index d9236a2282..744bea26d3 100644
> --- a/benchtests/bench-memcpy.c
> +++ b/benchtests/bench-memcpy.c
> @@ -40,7 +40,10 @@ do_one_test (json_ctx_t *json_ctx, impl_t *impl, char *dst, const char *src,
>  {
>    size_t i, iters = INNER_LOOP_ITERS;
>    timing_t start, stop, cur;
> -
> +  for (i = 0; i < iters / 64; ++i)
> +    {
> +      CALL (impl, dst, src, len);
> +    }
>    TIMING_NOW (start);
>    for (i = 0; i < iters; ++i)
>      {
> @@ -60,11 +63,11 @@ do_test (json_ctx_t *json_ctx, size_t align1, size_t align2, size_t len,
>    size_t i, j;
>    char *s1, *s2;
>    size_t repeats;
> -  align1 &= 63;
> +  align1 &= (getpagesize () - 1);
>    if (align1 + len >= page_size)
>      return;
>  
> -  align2 &= 63;
> +  align2 &= (getpagesize () - 1);
>    if (align2 + len >= page_size)
>      return;
>  
> @@ -99,7 +102,7 @@ test_main (void)
>  {
>    json_ctx_t json_ctx;
>    size_t i;
> -
> +  size_t half_page = getpagesize () / 2;
>    test_init ();
>  
>    json_init (&json_ctx, 0, stdout);
> @@ -121,8 +124,15 @@ test_main (void)
>      {
>        do_test (&json_ctx, 0, 0, 1 << i, 1);
>        do_test (&json_ctx, i, 0, 1 << i, 1);
> +      do_test (&json_ctx, i + 32, 0, 1 << i, 1);
>        do_test (&json_ctx, 0, i, 1 << i, 1);
> +      do_test (&json_ctx, 0, i + 32, 1 << i, 1);
>        do_test (&json_ctx, i, i, 1 << i, 1);
> +      do_test (&json_ctx, i + 32, i + 32, 1 << i, 1);
> +      do_test (&json_ctx, half_page, 0, 1 << i, 1);
> +      do_test (&json_ctx, half_page + i, 0, 1 << i, 1);
> +      do_test (&json_ctx, half_page, i, 1 << i, 1);
> +      do_test (&json_ctx, half_page + i, i, 1 << i, 1);
>      }
>  
>    for (i = 0; i < 32; ++i)
> @@ -131,16 +141,26 @@ test_main (void)
>        do_test (&json_ctx, i, 0, i, 0);
>        do_test (&json_ctx, 0, i, i, 0);
>        do_test (&json_ctx, i, i, i, 0);
> +      do_test (&json_ctx, half_page, 0, i, 0);
> +      do_test (&json_ctx, half_page + i, 0, i, 0);
> +      do_test (&json_ctx, half_page, i, i, 0);
> +      do_test (&json_ctx, half_page + i, i, i, 0);
> +      do_test (&json_ctx, getpagesize () - 1, 0, i, 0);
> +      do_test (&json_ctx, 0, getpagesize () - 1, i, 0);
>      }
>  
>    for (i = 3; i < 32; ++i)
>      {
>        if ((i & (i - 1)) == 0)
> -	continue;
> +        continue;
>        do_test (&json_ctx, 0, 0, 16 * i, 1);
>        do_test (&json_ctx, i, 0, 16 * i, 1);
>        do_test (&json_ctx, 0, i, 16 * i, 1);
>        do_test (&json_ctx, i, i, 16 * i, 1);
> +      do_test (&json_ctx, half_page, 0, 16 * i, 1);
> +      do_test (&json_ctx, half_page + i, 0, 16 * i, 1);
> +      do_test (&json_ctx, half_page, i, 16 * i, 1);
> +      do_test (&json_ctx, half_page + i, i, 16 * i, 1);
>      }
>  
>    for (i = 32; i < 64; ++i)
> @@ -149,16 +169,33 @@ test_main (void)
>        do_test (&json_ctx, i, 0, 32 * i, 1);
>        do_test (&json_ctx, 0, i, 32 * i, 1);
>        do_test (&json_ctx, i, i, 32 * i, 1);
> +      do_test (&json_ctx, half_page, 0, 32 * i, 1);
> +      do_test (&json_ctx, half_page + i, 0, 32 * i, 1);
> +      do_test (&json_ctx, half_page, i, 32 * i, 1);
> +      do_test (&json_ctx, half_page + i, i, 32 * i, 1);
>      }
>  
>    do_test (&json_ctx, 0, 0, getpagesize (), 1);
>  
> -  for (i = 0; i <= 32; ++i)
> +  for (i = 0; i <= 48; ++i)
>      {
>        do_test (&json_ctx, 0, 0, 2048 + 64 * i, 1);
>        do_test (&json_ctx, i, 0, 2048 + 64 * i, 1);
> +      do_test (&json_ctx, i + 32, 0, 2048 + 64 * i, 1);
>        do_test (&json_ctx, 0, i, 2048 + 64 * i, 1);
> +      do_test (&json_ctx, 0, i + 32, 2048 + 64 * i, 1);
>        do_test (&json_ctx, i, i, 2048 + 64 * i, 1);
> +      do_test (&json_ctx, i + 32, i + 32, 2048 + 64 * i, 1);
> +      do_test (&json_ctx, half_page, 0, 2048 + 64 * i, 1);
> +      do_test (&json_ctx, half_page + i, 0, 2048 + 64 * i, 1);
> +      do_test (&json_ctx, half_page, i, 2048 + 64 * i, 1);
> +      do_test (&json_ctx, half_page + i, i, 2048 + 64 * i, 1);
> +      do_test (&json_ctx, i, 1, 2048 + 64 * i, 1);
> +      do_test (&json_ctx, 1, i, 2048 + 64 * i, 1);
> +      do_test (&json_ctx, i + 32, 1, 2048 + 64 * i, 1);
> +      do_test (&json_ctx, 1, i + 32, 2048 + 64 * i, 1);
> +      do_test (&json_ctx, half_page + i, 1, 2048 + 64 * i, 1);
> +      do_test (&json_ctx, half_page + 1, i, 2048 + 64 * i, 1);
>      }
>  
>    json_array_end (&json_ctx);
> diff --git a/benchtests/bench-memmove.c b/benchtests/bench-memmove.c
> index 6becbf4782..855f4d0649 100644
> --- a/benchtests/bench-memmove.c
> +++ b/benchtests/bench-memmove.c
> @@ -34,7 +34,10 @@ do_one_test (json_ctx_t *json_ctx, impl_t *impl, char *dst, char *src,
>  {
>    size_t i, iters = INNER_LOOP_ITERS;
>    timing_t start, stop, cur;
> -
> +  for (i = 0; i < iters / 64; ++i)
> +    {
> +      CALL (impl, dst, src, len);
> +    }
>    TIMING_NOW (start);
>    for (i = 0; i < iters; ++i)
>      {
> @@ -53,11 +56,11 @@ do_test (json_ctx_t *json_ctx, size_t align1, size_t align2, size_t len)
>    size_t i, j;
>    char *s1, *s2;
>  
> -  align1 &= 63;
> +  align1 &= (getpagesize () - 1);
>    if (align1 + len >= page_size)
>      return;
>  
> -  align2 &= 63;
> +  align2 &= (getpagesize () - 1);
>    if (align2 + len >= page_size)
>      return;
>  
> @@ -85,6 +88,7 @@ test_main (void)
>  {
>    json_ctx_t json_ctx;
>    size_t i;
> +  size_t half_page = getpagesize () / 2;
>  
>    test_init ();
>  
> @@ -138,6 +142,22 @@ test_main (void)
>        do_test (&json_ctx, i, i, 32 * i);
>      }
>  
> +  for (i = 0; i <= 48; ++i)
> +    {
> +      do_test (&json_ctx, 0, 0, 2048 + 64 * i);
> +      do_test (&json_ctx, i, 0, 2048 + 64 * i);
> +      do_test (&json_ctx, 0, i, 2048 + 64 * i);
> +      do_test (&json_ctx, i, i, 2048 + 64 * i);
> +      do_test (&json_ctx, half_page, 0, 2048 + 64 * i);
> +      do_test (&json_ctx, 0, half_page, 2048 + 64 * i);
> +      do_test (&json_ctx, half_page + i, 0, 2048 + 64 * i);
> +      do_test (&json_ctx, i, half_page, 2048 + 64 * i);
> +      do_test (&json_ctx, half_page, i, 2048 + 64 * i);
> +      do_test (&json_ctx, 0, half_page + i, 2048 + 64 * i);
> +      do_test (&json_ctx, half_page + i, i, 2048 + 64 * i);
> +      do_test (&json_ctx, i, half_page + i, 2048 + 64 * i);
> +    }
> +
>    json_array_end (&json_ctx);
>    json_attr_object_end (&json_ctx);
>    json_attr_object_end (&json_ctx);
> -- 
> 2.25.1
>

LGTM.

Reviewed-by: H.J. Lu <hjl.tools@gmail.com>

Thanks.

H.J.

  reply	other threads:[~2021-11-06  2:27 UTC|newest]

Thread overview: 46+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-11-01  5:49 [PATCH v1 1/5] string: Make tests birdirectional test-memcpy.c Noah Goldstein
2021-11-01  5:49 ` [PATCH v1 2/5] benchtests: Add additional cases to bench-memcpy.c and bench-memmove.c Noah Goldstein
2021-11-06  2:27   ` H.J. Lu [this message]
2021-11-01  5:49 ` [PATCH v1 3/5] benchtests: Add partial overlap case in bench-memmove-walk.c Noah Goldstein
2021-11-06  2:28   ` H.J. Lu
2021-11-01  5:49 ` [PATCH v1 4/5] x86: Optimize memmove-vec-unaligned-erms.S Noah Goldstein
2021-11-01  5:52   ` Noah Goldstein
2021-11-06  2:29   ` H.J. Lu
2021-11-01  5:49 ` [PATCH v1 5/5] x86: Double size of ERMS rep_movsb_threshold in dl-cacheinfo.h Noah Goldstein
2021-11-06  2:31   ` H.J. Lu
2021-11-06  4:39     ` Noah Goldstein
2021-11-06 12:04       ` H.J. Lu
2021-11-06 17:38         ` Noah Goldstein
2021-11-06  2:27 ` [PATCH v1 1/5] string: Make tests birdirectional test-memcpy.c H.J. Lu
2021-11-06  4:39 ` [PATCH v2 " Noah Goldstein
2021-11-06  4:39   ` [PATCH v2 2/5] benchtests: Add additional cases to bench-memcpy.c and bench-memmove.c Noah Goldstein
2021-11-06  4:39   ` [PATCH v2 3/5] benchtests: Add partial overlap case in bench-memmove-walk.c Noah Goldstein
2021-11-06  4:39   ` [PATCH v2 4/5] x86: Optimize memmove-vec-unaligned-erms.S Noah Goldstein
2021-11-06  4:39   ` [PATCH v2 5/5] x86: Double size of ERMS rep_movsb_threshold in dl-cacheinfo.h Noah Goldstein
2021-11-06 17:37 ` [PATCH v3 1/5] string: Make tests birdirectional test-memcpy.c Noah Goldstein
2021-11-06 17:37   ` [PATCH v3 2/5] benchtests: Add additional cases to bench-memcpy.c and bench-memmove.c Noah Goldstein
2021-11-06 17:37   ` [PATCH v3 3/5] benchtests: Add partial overlap case in bench-memmove-walk.c Noah Goldstein
2021-11-06 17:37   ` [PATCH v3 4/5] x86: Optimize memmove-vec-unaligned-erms.S Noah Goldstein
2021-11-06 17:37   ` [PATCH v3 5/5] x86: Double size of ERMS rep_movsb_threshold in dl-cacheinfo.h Noah Goldstein
2021-11-06 17:56     ` H.J. Lu
2021-11-06 18:11       ` Noah Goldstein
2021-11-06 18:21         ` H.J. Lu
2021-11-06 18:34           ` Noah Goldstein
2021-11-06 18:33 ` [PATCH v4 1/5] string: Make tests birdirectional test-memcpy.c Noah Goldstein
2021-11-06 18:33   ` [PATCH v4 2/5] benchtests: Add additional cases to bench-memcpy.c and bench-memmove.c Noah Goldstein
2021-11-06 19:12     ` H.J. Lu
2021-11-06 18:33   ` [PATCH v4 3/5] benchtests: Add partial overlap case in bench-memmove-walk.c Noah Goldstein
2021-11-06 19:11     ` H.J. Lu
2021-11-06 18:33   ` [PATCH v4 4/5] x86: Optimize memmove-vec-unaligned-erms.S Noah Goldstein
2021-11-06 19:11     ` H.J. Lu
2022-04-23  1:41       ` Sunil Pandey
2021-11-06 18:33   ` [PATCH v4 5/5] x86: Double size of ERMS rep_movsb_threshold in dl-cacheinfo.h Noah Goldstein
2021-11-06 19:10     ` H.J. Lu
2022-04-23  1:42       ` Sunil Pandey
2021-11-06 19:12   ` [PATCH v4 1/5] string: Make tests birdirectional test-memcpy.c H.J. Lu
2021-11-06 21:20     ` Noah Goldstein
2021-11-07 13:53       ` H.J. Lu
2021-12-07 21:10   ` Stafford Horne
2021-12-07 21:36     ` Noah Goldstein
2021-12-07 22:07       ` Stafford Horne
2021-12-07 22:13         ` Noah Goldstein

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=YYXoKH3KFDKOPWz+@gmail.com \
    --to=hjl.tools@gmail.com \
    --cc=carlos@systemhalted.org \
    --cc=goldstein.w.n@gmail.com \
    --cc=libc-alpha@sourceware.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
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).