52 lines
2.1 KiB
Diff
52 lines
2.1 KiB
Diff
commit 67e863742d98c990b3d3b814b80042c0fa0d50a5
|
|
Author: Aurelien Jarno <aurelien@aurel32.net>
|
|
Date: Mon Oct 3 23:16:46 2022 +0200
|
|
|
|
x86-64: Require BMI2 for AVX2 wcs(n)cmp implementations
|
|
|
|
The AVX2 wcs(n)cmp implementations use the 'bzhi' instruction, which
|
|
belongs to the BMI2 CPU feature.
|
|
|
|
NB: It also uses the 'tzcnt' BMI1 instruction, but it is executed as BSF
|
|
as BSF if the CPU doesn't support TZCNT, and produces the same result
|
|
for non-zero input.
|
|
|
|
Partially fixes: b77b06e0e296 ("x86: Optimize strcmp-avx2.S")
|
|
Partially resolves: BZ #29611
|
|
|
|
Reviewed-by: Noah Goldstein <goldstein.w.n@gmail.com>
|
|
(cherry picked from commit f31a5a884ed84bd37032729d4d1eb9d06c9f3c29)
|
|
|
|
diff --git a/sysdeps/x86_64/multiarch/ifunc-impl-list.c b/sysdeps/x86_64/multiarch/ifunc-impl-list.c
|
|
index 34d5f6efe5421014..e76a991dc671c1a9 100644
|
|
--- a/sysdeps/x86_64/multiarch/ifunc-impl-list.c
|
|
+++ b/sysdeps/x86_64/multiarch/ifunc-impl-list.c
|
|
@@ -693,10 +693,12 @@ __libc_ifunc_impl_list (const char *name, struct libc_ifunc_impl *array,
|
|
/* Support sysdeps/x86_64/multiarch/wcscmp.c. */
|
|
IFUNC_IMPL (i, name, wcscmp,
|
|
IFUNC_IMPL_ADD (array, i, wcscmp,
|
|
- CPU_FEATURE_USABLE (AVX2),
|
|
+ (CPU_FEATURE_USABLE (AVX2)
|
|
+ && CPU_FEATURE_USABLE (BMI2)),
|
|
__wcscmp_avx2)
|
|
IFUNC_IMPL_ADD (array, i, wcscmp,
|
|
(CPU_FEATURE_USABLE (AVX2)
|
|
+ && CPU_FEATURE_USABLE (BMI2)
|
|
&& CPU_FEATURE_USABLE (RTM)),
|
|
__wcscmp_avx2_rtm)
|
|
IFUNC_IMPL_ADD (array, i, wcscmp,
|
|
@@ -709,10 +711,12 @@ __libc_ifunc_impl_list (const char *name, struct libc_ifunc_impl *array,
|
|
/* Support sysdeps/x86_64/multiarch/wcsncmp.c. */
|
|
IFUNC_IMPL (i, name, wcsncmp,
|
|
IFUNC_IMPL_ADD (array, i, wcsncmp,
|
|
- CPU_FEATURE_USABLE (AVX2),
|
|
+ (CPU_FEATURE_USABLE (AVX2)
|
|
+ && CPU_FEATURE_USABLE (BMI2)),
|
|
__wcsncmp_avx2)
|
|
IFUNC_IMPL_ADD (array, i, wcsncmp,
|
|
(CPU_FEATURE_USABLE (AVX2)
|
|
+ && CPU_FEATURE_USABLE (BMI2)
|
|
&& CPU_FEATURE_USABLE (RTM)),
|
|
__wcsncmp_avx2_rtm)
|
|
IFUNC_IMPL_ADD (array, i, wcsncmp,
|