diff options
| author | Aurelien Jarno <aurelien@aurel32.net> | 2022-10-03 23:16:46 +0200 |
|---|---|---|
| committer | Aurelien Jarno <aurelien@aurel32.net> | 2022-10-04 00:03:19 +0200 |
| commit | 26d4359b448a39054e627ad072a7480dd24f0313 (patch) | |
| tree | 2b79853908b9dbda7880f1de3464437ef53c9438 | |
| parent | 007581a1cc79f51bc02debf04fc3e4ad62fad1df (diff) | |
| download | glibc-26d4359b448a39054e627ad072a7480dd24f0313.tar.gz glibc-26d4359b448a39054e627ad072a7480dd24f0313.tar.xz glibc-26d4359b448a39054e627ad072a7480dd24f0313.zip | |
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)
| -rw-r--r-- | sysdeps/x86_64/multiarch/ifunc-impl-list.c | 4 | ||||
| -rw-r--r-- | sysdeps/x86_64/multiarch/strcmp.c | 4 |
2 files changed, 5 insertions, 3 deletions
diff --git a/sysdeps/x86_64/multiarch/ifunc-impl-list.c b/sysdeps/x86_64/multiarch/ifunc-impl-list.c index ca64b34c14..70931f1598 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 b457fb4c15..0c0cd20a03 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)) |