summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorAurelien Jarno <aurelien@aurel32.net>2022-10-03 23:46:11 +0200
committerAurelien Jarno <aurelien@aurel32.net>2022-10-03 23:47:49 +0200
commit7afbd1e56acb721031bffd876f275dcb1af7e530 (patch)
treede64a345e917480dd7a733a1c1f1e28b5f90fc10
parent46479e5d10ed87825aa277da158d6a687974518b (diff)
downloadglibc-7afbd1e56acb721031bffd876f275dcb1af7e530.tar.gz
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.c4
-rw-r--r--sysdeps/x86_64/multiarch/strcmp.c4
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 d208fae4bf..a42b0a4620 100644
--- a/sysdeps/x86_64/multiarch/ifunc-impl-list.c
+++ b/sysdeps/x86_64/multiarch/ifunc-impl-list.c
@@ -591,10 +591,12 @@ __libc_ifunc_impl_list (const char *name, struct libc_ifunc_impl *array,
&& CPU_FEATURE_USABLE (BMI2)),
__strcmp_evex)
X86_IFUNC_IMPL_ADD_V3 (array, i, strcmp,
- CPU_FEATURE_USABLE (AVX2),
+ (CPU_FEATURE_USABLE (AVX2)
+ && CPU_FEATURE_USABLE (BMI2)),
__strcmp_avx2)
X86_IFUNC_IMPL_ADD_V3 (array, i, strcmp,
(CPU_FEATURE_USABLE (AVX2)
+ && CPU_FEATURE_USABLE (BMI2)
&& CPU_FEATURE_USABLE (RTM)),
__strcmp_avx2_rtm)
X86_IFUNC_IMPL_ADD_V2 (array, i, strcmp,
diff --git a/sysdeps/x86_64/multiarch/strcmp.c b/sysdeps/x86_64/multiarch/strcmp.c
index fdd5afe3af..9d6c9f66ba 100644
--- a/sysdeps/x86_64/multiarch/strcmp.c
+++ b/sysdeps/x86_64/multiarch/strcmp.c
@@ -45,12 +45,12 @@ IFUNC_SELECTOR (void)
const struct cpu_features *cpu_features = __get_cpu_features ();
if (X86_ISA_CPU_FEATURE_USABLE_P (cpu_features, AVX2)
+ && X86_ISA_CPU_FEATURE_USABLE_P (cpu_features, BMI2)
&& X86_ISA_CPU_FEATURES_ARCH_P (cpu_features,
AVX_Fast_Unaligned_Load, ))
{
if (X86_ISA_CPU_FEATURE_USABLE_P (cpu_features, AVX512VL)
- && X86_ISA_CPU_FEATURE_USABLE_P (cpu_features, AVX512BW)
- && X86_ISA_CPU_FEATURE_USABLE_P (cpu_features, BMI2))
+ && X86_ISA_CPU_FEATURE_USABLE_P (cpu_features, AVX512BW))
return OPTIMIZE (evex);
if (CPU_FEATURE_USABLE_P (cpu_features, RTM))