From 5ac7aa1d7cce8580f8225c33c819991abca102b9 Mon Sep 17 00:00:00 2001 From: "H.J. Lu" Date: Fri, 9 Jun 2017 05:44:30 -0700 Subject: x86-64: Optimize memrchr with AVX2 Optimize memrchr with AVX2 to search 32 bytes with a single vector compare instruction. It is as fast as SSE2 memrchr for small data sizes and up to 1X faster for large data sizes on Haswell. Select AVX2 memrchr on AVX2 machines where vzeroupper is preferred and AVX unaligned load is fast. * sysdeps/x86_64/multiarch/Makefile (sysdep_routines): Add memrchr-sse2 and memrchr-avx2. * sysdeps/x86_64/multiarch/ifunc-impl-list.c (__libc_ifunc_impl_list): Add tests for __memrchr_avx2 and __memrchr_sse2. * sysdeps/x86_64/multiarch/memrchr-avx2.S: New file. * sysdeps/x86_64/multiarch/memrchr-sse2.S: Likewise. * sysdeps/x86_64/multiarch/memrchr.c: Likewise. --- sysdeps/x86_64/multiarch/ifunc-impl-list.c | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'sysdeps/x86_64/multiarch/ifunc-impl-list.c') diff --git a/sysdeps/x86_64/multiarch/ifunc-impl-list.c b/sysdeps/x86_64/multiarch/ifunc-impl-list.c index 8dda1b040a..5670eb7e9e 100644 --- a/sysdeps/x86_64/multiarch/ifunc-impl-list.c +++ b/sysdeps/x86_64/multiarch/ifunc-impl-list.c @@ -112,6 +112,13 @@ __libc_ifunc_impl_list (const char *name, struct libc_ifunc_impl *array, IFUNC_IMPL_ADD (array, i, memmove, 1, __memmove_sse2_unaligned_erms)) + /* Support sysdeps/x86_64/multiarch/memrchr.S. */ + IFUNC_IMPL (i, name, memrchr, + IFUNC_IMPL_ADD (array, i, memrchr, + HAS_ARCH_FEATURE (AVX2_Usable), + __memrchr_avx2) + IFUNC_IMPL_ADD (array, i, memrchr, 1, __memrchr_sse2)) + /* Support sysdeps/x86_64/multiarch/memset_chk.S. */ IFUNC_IMPL (i, name, __memset_chk, IFUNC_IMPL_ADD (array, i, __memset_chk, 1, -- cgit 1.4.1