diff options
| author | H.J. Lu <hjl.tools@gmail.com> | 2021-03-05 06:46:08 -0800 |
|---|---|---|
| committer | H.J. Lu <hjl.tools@gmail.com> | 2022-01-27 12:47:19 -0800 |
| commit | 5141ddbe3aace5c713d6e2c4260cd1646e54489b (patch) | |
| tree | 704d4bbbd732c08513535ac6364ec27d8edbf39a /sysdeps/x86_64/multiarch/ifunc-memmove.h | |
| parent | a3a8109999f86bd7f968aa99c3fa7e2d3a7c6de8 (diff) | |
| download | glibc-5141ddbe3aace5c713d6e2c4260cd1646e54489b.tar.gz glibc-5141ddbe3aace5c713d6e2c4260cd1646e54489b.tar.xz glibc-5141ddbe3aace5c713d6e2c4260cd1646e54489b.zip | |
x86-64: Add memmove family functions with 256-bit EVEX
Update ifunc-memmove.h to select the function optimized with 256-bit EVEX instructions using YMM16-YMM31 registers to avoid RTM abort with usable AVX512VL since VZEROUPPER isn't needed at function exit. (cherry picked from commit 63ad43566f7a25d140dc723598aeb441ad657eed)
Diffstat (limited to 'sysdeps/x86_64/multiarch/ifunc-memmove.h')
| -rw-r--r-- | sysdeps/x86_64/multiarch/ifunc-memmove.h | 21 |
1 files changed, 18 insertions, 3 deletions
diff --git a/sysdeps/x86_64/multiarch/ifunc-memmove.h b/sysdeps/x86_64/multiarch/ifunc-memmove.h index 5b1eb1c92c..83db955826 100644 --- a/sysdeps/x86_64/multiarch/ifunc-memmove.h +++ b/sysdeps/x86_64/multiarch/ifunc-memmove.h @@ -29,6 +29,10 @@ extern __typeof (REDIRECT_NAME) OPTIMIZE (ssse3_back) attribute_hidden; extern __typeof (REDIRECT_NAME) OPTIMIZE (avx_unaligned) attribute_hidden; extern __typeof (REDIRECT_NAME) OPTIMIZE (avx_unaligned_erms) attribute_hidden; +extern __typeof (REDIRECT_NAME) OPTIMIZE (evex_unaligned) + attribute_hidden; +extern __typeof (REDIRECT_NAME) OPTIMIZE (evex_unaligned_erms) + attribute_hidden; extern __typeof (REDIRECT_NAME) OPTIMIZE (avx512_unaligned) attribute_hidden; extern __typeof (REDIRECT_NAME) OPTIMIZE (avx512_unaligned_erms) @@ -59,10 +63,21 @@ IFUNC_SELECTOR (void) if (CPU_FEATURES_ARCH_P (cpu_features, AVX_Fast_Unaligned_Load)) { - if (CPU_FEATURES_CPU_P (cpu_features, ERMS)) - return OPTIMIZE (avx_unaligned_erms); + if (CPU_FEATURES_ARCH_P (cpu_features, AVX512VL_Usable)) + { + if (CPU_FEATURES_CPU_P (cpu_features, ERMS)) + return OPTIMIZE (evex_unaligned_erms); + + return OPTIMIZE (evex_unaligned); + } + + if (!CPU_FEATURES_ARCH_P (cpu_features, Prefer_No_VZEROUPPER)) + { + if (CPU_FEATURES_CPU_P (cpu_features, ERMS)) + return OPTIMIZE (avx_unaligned_erms); - return OPTIMIZE (avx_unaligned); + return OPTIMIZE (avx_unaligned); + } } if (!CPU_FEATURES_CPU_P (cpu_features, SSSE3) |