diff options
author | Noah Goldstein <goldstein.w.n@gmail.com> | 2021-05-17 13:56:52 -0400 |
---|---|---|
committer | Noah Goldstein <goldstein.w.n@gmail.com> | 2021-05-18 22:57:44 -0400 |
commit | 16d12015c57701b08d7bbed6ec536641bcafb428 (patch) | |
tree | ade2bfb8b7361e3a29c71d086bb6c4b683311d0b /sysdeps/x86_64/multiarch/ifunc-impl-list.c | |
parent | e68d6fcccae10f325799b965875744470adc7281 (diff) | |
download | glibc-16d12015c57701b08d7bbed6ec536641bcafb428.tar.gz glibc-16d12015c57701b08d7bbed6ec536641bcafb428.tar.xz glibc-16d12015c57701b08d7bbed6ec536641bcafb428.zip |
x86: Optimize memcmp-avx2-movbe.S
No bug. This commit optimizes memcmp-avx2.S. The optimizations include adding a new vec compare path for small sizes, reorganizing the entry control flow, and removing some unnecissary ALU instructions from the main loop. test-memcmp and test-wmemcmp are both passing. Signed-off-by: Noah Goldstein <goldstein.w.n@gmail.com> Reviewed-by: H.J. Lu <hjl.tools@gmail.com>
Diffstat (limited to 'sysdeps/x86_64/multiarch/ifunc-impl-list.c')
-rw-r--r-- | sysdeps/x86_64/multiarch/ifunc-impl-list.c | 6 |
1 files changed, 6 insertions, 0 deletions
diff --git a/sysdeps/x86_64/multiarch/ifunc-impl-list.c b/sysdeps/x86_64/multiarch/ifunc-impl-list.c index 2d811a550b..15eda47667 100644 --- a/sysdeps/x86_64/multiarch/ifunc-impl-list.c +++ b/sysdeps/x86_64/multiarch/ifunc-impl-list.c @@ -63,16 +63,19 @@ __libc_ifunc_impl_list (const char *name, struct libc_ifunc_impl *array, IFUNC_IMPL (i, name, memcmp, IFUNC_IMPL_ADD (array, i, memcmp, (CPU_FEATURE_USABLE (AVX2) + && CPU_FEATURE_USABLE (BMI2) && CPU_FEATURE_USABLE (MOVBE)), __memcmp_avx2_movbe) IFUNC_IMPL_ADD (array, i, memcmp, (CPU_FEATURE_USABLE (AVX2) + && CPU_FEATURE_USABLE (BMI2) && CPU_FEATURE_USABLE (MOVBE) && CPU_FEATURE_USABLE (RTM)), __memcmp_avx2_movbe_rtm) IFUNC_IMPL_ADD (array, i, memcmp, (CPU_FEATURE_USABLE (AVX512VL) && CPU_FEATURE_USABLE (AVX512BW) + && CPU_FEATURE_USABLE (BMI2) && CPU_FEATURE_USABLE (MOVBE)), __memcmp_evex_movbe) IFUNC_IMPL_ADD (array, i, memcmp, CPU_FEATURE_USABLE (SSE4_1), @@ -729,16 +732,19 @@ __libc_ifunc_impl_list (const char *name, struct libc_ifunc_impl *array, IFUNC_IMPL (i, name, wmemcmp, IFUNC_IMPL_ADD (array, i, wmemcmp, (CPU_FEATURE_USABLE (AVX2) + && CPU_FEATURE_USABLE (BMI2) && CPU_FEATURE_USABLE (MOVBE)), __wmemcmp_avx2_movbe) IFUNC_IMPL_ADD (array, i, wmemcmp, (CPU_FEATURE_USABLE (AVX2) + && CPU_FEATURE_USABLE (BMI2) && CPU_FEATURE_USABLE (MOVBE) && CPU_FEATURE_USABLE (RTM)), __wmemcmp_avx2_movbe_rtm) IFUNC_IMPL_ADD (array, i, wmemcmp, (CPU_FEATURE_USABLE (AVX512VL) && CPU_FEATURE_USABLE (AVX512BW) + && CPU_FEATURE_USABLE (BMI2) && CPU_FEATURE_USABLE (MOVBE)), __wmemcmp_evex_movbe) IFUNC_IMPL_ADD (array, i, wmemcmp, CPU_FEATURE_USABLE (SSE4_1), |