diff options
| author | H.J. Lu <hjl.tools@gmail.com> | 2017-09-12 07:46:11 -0700 |
|---|---|---|
| committer | H.J. Lu <hjl.tools@gmail.com> | 2017-09-12 07:54:47 -0700 |
| commit | ef8adeb0416309082c41a1518caee6961b5c42e8 (patch) | |
| tree | 1907bd459f82a962252cc5852bbee9025b3a99ad /sysdeps/x86 | |
| parent | a166531fdf601560a0005479427f60d3173f8257 (diff) | |
| download | glibc-ef8adeb0416309082c41a1518caee6961b5c42e8.tar glibc-ef8adeb0416309082c41a1518caee6961b5c42e8.tar.gz glibc-ef8adeb0416309082c41a1518caee6961b5c42e8.tar.bz2 glibc-ef8adeb0416309082c41a1518caee6961b5c42e8.zip | |
x86: Add MathVec_Prefer_No_AVX512 to cpu-features [BZ #21967]
AVX512 functions in mathvec are used on machines with AVX512. An AVX2
wrapper is also provided and it can be used when the AVX512 version
isn't profitable. MathVec_Prefer_No_AVX512 is addded to cpu-features.
If glibc.tune.hwcaps=MathVec_Prefer_No_AVX512 is set in GLIBC_TUNABLES
environment variable, the AVX2 wrapper will be used.
Tested on x86-64 machines with and without AVX512. Also verified
glibc.tune.hwcaps=MathVec_Prefer_No_AVX512 on AVX512 machine.
[BZ #21967]
* sysdeps/x86/cpu-features.h (bit_arch_MathVec_Prefer_No_AVX512):
New.
(index_arch_MathVec_Prefer_No_AVX512): Likewise.
* sysdeps/x86/cpu-tunables.c (TUNABLE_CALLBACK (set_hwcaps)):
Handle MathVec_Prefer_No_AVX512.
* sysdeps/x86_64/fpu/multiarch/ifunc-mathvec-avx512.h
(IFUNC_SELECTOR): Return AVX2 version if MathVec_Prefer_No_AVX512
is set.
Diffstat (limited to 'sysdeps/x86')
| -rw-r--r-- | sysdeps/x86/cpu-features.h | 2 | ||||
| -rw-r--r-- | sysdeps/x86/cpu-tunables.c | 7 |
2 files changed, 9 insertions, 0 deletions
diff --git a/sysdeps/x86/cpu-features.h b/sysdeps/x86/cpu-features.h index 9e01781424..a032a2e168 100644 --- a/sysdeps/x86/cpu-features.h +++ b/sysdeps/x86/cpu-features.h @@ -40,6 +40,7 @@ #define bit_arch_Use_dl_runtime_resolve_opt (1 << 20) #define bit_arch_Use_dl_runtime_resolve_slow (1 << 21) #define bit_arch_Prefer_No_AVX512 (1 << 22) +#define bit_arch_MathVec_Prefer_No_AVX512 (1 << 23) /* CPUID Feature flags. */ @@ -239,6 +240,7 @@ extern const struct cpu_features *__get_cpu_features (void) # define index_arch_Use_dl_runtime_resolve_opt FEATURE_INDEX_1 # define index_arch_Use_dl_runtime_resolve_slow FEATURE_INDEX_1 # define index_arch_Prefer_No_AVX512 FEATURE_INDEX_1 +# define index_arch_MathVec_Prefer_No_AVX512 FEATURE_INDEX_1 #endif /* !__ASSEMBLER__ */ diff --git a/sysdeps/x86/cpu-tunables.c b/sysdeps/x86/cpu-tunables.c index 0ab708cca8..ec72d86f08 100644 --- a/sysdeps/x86/cpu-tunables.c +++ b/sysdeps/x86/cpu-tunables.c @@ -303,6 +303,13 @@ TUNABLE_CALLBACK (set_hwcaps) (tunable_val_t *valp) disable, 23); } break; + case 24: + { + CHECK_GLIBC_IFUNC_ARCH_NEED_ARCH_BOTH + (n, cpu_features, MathVec_Prefer_No_AVX512, + AVX512F_Usable, disable, 24); + } + break; case 26: { CHECK_GLIBC_IFUNC_ARCH_NEED_CPU_BOTH |