diff options
| author | H.J. Lu <hjl.tools@gmail.com> | 2017-06-09 05:18:03 -0700 |
|---|---|---|
| committer | H.J. Lu <hjl.tools@gmail.com> | 2017-06-09 05:18:18 -0700 |
| commit | dc485ceb2ac596d27294cc1942adf3181f15e8bf (patch) | |
| tree | 54a2e09bd5996b759565efbc216f6b05e2b77d1a /sysdeps/x86_64/multiarch/wcsnlen.c | |
| parent | 2f5d20ac99b9434a634629282cbb46e2a8d56a1c (diff) | |
| download | glibc-dc485ceb2ac596d27294cc1942adf3181f15e8bf.tar.gz glibc-dc485ceb2ac596d27294cc1942adf3181f15e8bf.tar.xz glibc-dc485ceb2ac596d27294cc1942adf3181f15e8bf.zip | |
x86-64: Optimize strlen/strnlen/wcslen/wcsnlen with AVX2
Optimize strlen/strnlen/wcslen/wcsnlen with AVX2 to check 32 bytes with a single vector compare instruction. It is as fast as SSE2 versions for size <= 16 bytes and up to 1X faster for or size > 16 bytes on Haswell. Select AVX2 version on AVX2 machines where vzeroupper is preferred and AVX unaligned load is fast. NB: It uses TZCNT instead of BSF since TZCNT produces the same result as BSF for non-zero input. TZCNT is faster than BSF and is executed as BSF if machine doesn't support TZCNT. * sysdeps/x86_64/multiarch/Makefile (sysdep_routines): Add strlen-sse2, strnlen-sse2, strlen-avx2, strnlen-avx2, wcslen-sse2, wcslen-avx2 and wcsnlen-avx2. * sysdeps/x86_64/multiarch/ifunc-impl-list.c (__libc_ifunc_impl_list): Add tests for __strlen_avx2, __strlen_sse2, __strnlen_avx2, __strnlen_sse2, __wcslen_avx2, __wcslen_sse2 and __wcsnlen_avx2. * sysdeps/x86_64/multiarch/strlen-avx2.S: New file. * sysdeps/x86_64/multiarch/strlen-sse2.S: Likewise. * sysdeps/x86_64/multiarch/strlen.c: Likewise. * sysdeps/x86_64/multiarch/strnlen-avx2.S: Likewise. * sysdeps/x86_64/multiarch/strnlen-sse2.S: Likewise. * sysdeps/x86_64/multiarch/strnlen.c: Likewise. * sysdeps/x86_64/multiarch/wcslen-avx2.S: Likewise. * sysdeps/x86_64/multiarch/wcslen-sse2.S: Likewise. * sysdeps/x86_64/multiarch/wcslen.c: Likewise. * sysdeps/x86_64/multiarch/wcsnlen-avx2.S: Likewise. * sysdeps/x86_64/multiarch/wcsnlen.c (OPTIMIZE (avx2)): New. (IFUNC_SELECTOR): Return OPTIMIZE (avx2) on AVX2 machines where vzeroupper is preferred and AVX unaligned load is fast.
Diffstat (limited to 'sysdeps/x86_64/multiarch/wcsnlen.c')
| -rw-r--r-- | sysdeps/x86_64/multiarch/wcsnlen.c | 6 |
1 files changed, 6 insertions, 0 deletions
diff --git a/sysdeps/x86_64/multiarch/wcsnlen.c b/sysdeps/x86_64/multiarch/wcsnlen.c index 304f62eec3..1e3f3c5104 100644 --- a/sysdeps/x86_64/multiarch/wcsnlen.c +++ b/sysdeps/x86_64/multiarch/wcsnlen.c @@ -28,12 +28,18 @@ extern __typeof (REDIRECT_NAME) OPTIMIZE (sse2) attribute_hidden; extern __typeof (REDIRECT_NAME) OPTIMIZE (sse4_1) attribute_hidden; +extern __typeof (REDIRECT_NAME) OPTIMIZE (avx2) attribute_hidden; static inline void * IFUNC_SELECTOR (void) { const struct cpu_features* cpu_features = __get_cpu_features (); + if (!CPU_FEATURES_ARCH_P (cpu_features, Prefer_No_VZEROUPPER) + && CPU_FEATURES_ARCH_P (cpu_features, AVX2_Usable) + && CPU_FEATURES_ARCH_P (cpu_features, AVX_Fast_Unaligned_Load)) + return OPTIMIZE (avx2); + if (CPU_FEATURES_CPU_P (cpu_features, SSE4_1)) return OPTIMIZE (sse4_1); |