mirror of git://sourceware.org/git/glibc.git
On Skylake server, AVX512 load/store instructions in memcpy/memset may lead to lower CPU turbo frequency in certain situations. Use of AVX2 in memcpy/memset has been observed to have improved overall performance in many workloads due to the higher frequency. Since AVX512ER is unique to Xeon Phi, this patch sets Prefer_No_AVX512 if AVX512ER isn't available so that AVX2 versions of memcpy/memset are used on Skylake server. [BZ #21396] * sysdeps/x86/cpu-features.c (init_cpu_features): Set Prefer_No_AVX512 if AVX512ER isn't available. * sysdeps/x86/cpu-features.h (bit_arch_Prefer_No_AVX512): New. (index_arch_Prefer_No_AVX512): Likewise. * sysdeps/x86_64/multiarch/memcpy.S (__new_memcpy): Don't use AVX512 version if Prefer_No_AVX512 is set. * sysdeps/x86_64/multiarch/memcpy_chk.S (__memcpy_chk): Likewise. * sysdeps/x86_64/multiarch/memmove.S (__libc_memmove): Likewise. * sysdeps/x86_64/multiarch/memmove_chk.S (__memmove_chk): Likewise. * sysdeps/x86_64/multiarch/mempcpy.S (__mempcpy): Likewise. * sysdeps/x86_64/multiarch/mempcpy_chk.S (__mempcpy_chk): Likewise. * sysdeps/x86_64/multiarch/memset.S (memset): Likewise. * sysdeps/x86_64/multiarch/memset_chk.S (__memset_chk): Likewise. |
||
|---|---|---|
| .. | ||
| Makefile | ||
| bcopy.S | ||
| ifunc-impl-list.c | ||
| memcmp-sse4.S | ||
| memcmp-ssse3.S | ||
| memcmp.S | ||
| memcpy-ssse3-back.S | ||
| memcpy-ssse3.S | ||
| memcpy.S | ||
| memcpy_chk.S | ||
| memmove-avx-unaligned-erms.S | ||
| memmove-avx512-no-vzeroupper.S | ||
| memmove-avx512-unaligned-erms.S | ||
| memmove-ssse3-back.S | ||
| memmove-ssse3.S | ||
| memmove-vec-unaligned-erms.S | ||
| memmove.S | ||
| memmove_chk.S | ||
| mempcpy.S | ||
| mempcpy_chk.S | ||
| memset-avx2-unaligned-erms.S | ||
| memset-avx512-no-vzeroupper.S | ||
| memset-avx512-unaligned-erms.S | ||
| memset-vec-unaligned-erms.S | ||
| memset.S | ||
| memset_chk.S | ||
| sched_cpucount.c | ||
| stpcpy-sse2-unaligned.S | ||
| stpcpy-ssse3.S | ||
| stpcpy.S | ||
| stpncpy-c.c | ||
| stpncpy-sse2-unaligned.S | ||
| stpncpy-ssse3.S | ||
| stpncpy.S | ||
| strcasecmp_l-ssse3.S | ||
| strcasecmp_l.S | ||
| strcat-sse2-unaligned.S | ||
| strcat-ssse3.S | ||
| strcat.S | ||
| strchr-sse2-no-bsf.S | ||
| strchr.S | ||
| strcmp-sse2-unaligned.S | ||
| strcmp-sse42.S | ||
| strcmp-ssse3.S | ||
| strcmp.S | ||
| strcpy-sse2-unaligned.S | ||
| strcpy-ssse3.S | ||
| strcpy.S | ||
| strcspn-c.c | ||
| strcspn.S | ||
| strncase_l-ssse3.S | ||
| strncase_l.S | ||
| strncat-c.c | ||
| strncat-sse2-unaligned.S | ||
| strncat-ssse3.S | ||
| strncat.S | ||
| strncmp-ssse3.S | ||
| strncmp.S | ||
| strncpy-c.c | ||
| strncpy-sse2-unaligned.S | ||
| strncpy-ssse3.S | ||
| strncpy.S | ||
| strpbrk-c.c | ||
| strpbrk.S | ||
| strspn-c.c | ||
| strspn.S | ||
| strstr-sse2-unaligned.S | ||
| strstr.c | ||
| test-multiarch.c | ||
| varshift.c | ||
| varshift.h | ||
| wcscpy-c.c | ||
| wcscpy-ssse3.S | ||
| wcscpy.S | ||
| wmemcmp-c.c | ||
| wmemcmp-sse4.S | ||
| wmemcmp-ssse3.S | ||
| wmemcmp.S | ||