aboutsummaryrefslogtreecommitdiff
path: root/benchtests/bench-memcpy.c
diff options
context:
space:
mode:
authorNoah Goldstein <goldstein.w.n@gmail.com>2021-11-01 00:49:49 -0500
committerNoah Goldstein <goldstein.w.n@gmail.com>2021-11-06 16:17:51 -0500
commit5e6cce9b34e1609dc5183312a9efaf0d420a547a (patch)
tree0bd200d8d31be312a936a31c2c683b91950a85af /benchtests/bench-memcpy.c
parentd585ba47fcda99fdf228e3e45a01b11a15efbc5a (diff)
downloadglibc-5e6cce9b34e1609dc5183312a9efaf0d420a547a.tar
glibc-5e6cce9b34e1609dc5183312a9efaf0d420a547a.tar.gz
glibc-5e6cce9b34e1609dc5183312a9efaf0d420a547a.tar.bz2
glibc-5e6cce9b34e1609dc5183312a9efaf0d420a547a.zip
benchtests: Add additional cases to bench-memcpy.c and bench-memmove.c
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 Signed-off-by: Noah Goldstein <goldstein.w.n@gmail.com> Reviewed-by: H.J. Lu <hjl.tools@gmail.com>
Diffstat (limited to 'benchtests/bench-memcpy.c')
-rw-r--r--benchtests/bench-memcpy.c49
1 files changed, 43 insertions, 6 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);