You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
56 lines
2.3 KiB
56 lines
2.3 KiB
commit e1561d8cf005a23bcaf514802854b493829a25b1
|
|
Author: Aurelien Jarno <aurelien@aurel32.net>
|
|
Date: Mon Oct 3 23:16:46 2022 +0200
|
|
|
|
x86-64: Require BMI2 for AVX2 strcmp implementation
|
|
|
|
The AVX2 strcmp implementation uses 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 4d64c6445735e9b34e2ac8e369312cbfc2f88e17)
|
|
|
|
diff --git a/sysdeps/x86_64/multiarch/ifunc-impl-list.c b/sysdeps/x86_64/multiarch/ifunc-impl-list.c
|
|
index ca64b34c146a76f9..70931f15985334af 100644
|
|
--- a/sysdeps/x86_64/multiarch/ifunc-impl-list.c
|
|
+++ b/sysdeps/x86_64/multiarch/ifunc-impl-list.c
|
|
@@ -503,10 +503,12 @@ __libc_ifunc_impl_list (const char *name, struct libc_ifunc_impl *array,
|
|
/* Support sysdeps/x86_64/multiarch/strcmp.c. */
|
|
IFUNC_IMPL (i, name, strcmp,
|
|
IFUNC_IMPL_ADD (array, i, strcmp,
|
|
- CPU_FEATURE_USABLE (AVX2),
|
|
+ (CPU_FEATURE_USABLE (AVX2)
|
|
+ && CPU_FEATURE_USABLE (BMI2)),
|
|
__strcmp_avx2)
|
|
IFUNC_IMPL_ADD (array, i, strcmp,
|
|
(CPU_FEATURE_USABLE (AVX2)
|
|
+ && CPU_FEATURE_USABLE (BMI2)
|
|
&& CPU_FEATURE_USABLE (RTM)),
|
|
__strcmp_avx2_rtm)
|
|
IFUNC_IMPL_ADD (array, i, strcmp,
|
|
diff --git a/sysdeps/x86_64/multiarch/strcmp.c b/sysdeps/x86_64/multiarch/strcmp.c
|
|
index b457fb4c150e4407..0c0cd20a03278a2b 100644
|
|
--- a/sysdeps/x86_64/multiarch/strcmp.c
|
|
+++ b/sysdeps/x86_64/multiarch/strcmp.c
|
|
@@ -40,11 +40,11 @@ IFUNC_SELECTOR (void)
|
|
const struct cpu_features* cpu_features = __get_cpu_features ();
|
|
|
|
if (CPU_FEATURE_USABLE_P (cpu_features, AVX2)
|
|
+ && CPU_FEATURE_USABLE_P (cpu_features, BMI2)
|
|
&& CPU_FEATURES_ARCH_P (cpu_features, AVX_Fast_Unaligned_Load))
|
|
{
|
|
if (CPU_FEATURE_USABLE_P (cpu_features, AVX512VL)
|
|
- && CPU_FEATURE_USABLE_P (cpu_features, AVX512BW)
|
|
- && CPU_FEATURE_USABLE_P (cpu_features, BMI2))
|
|
+ && CPU_FEATURE_USABLE_P (cpu_features, AVX512BW))
|
|
return OPTIMIZE (evex);
|
|
|
|
if (CPU_FEATURE_USABLE_P (cpu_features, RTM))
|