From 28b90d9c19d368645f475e36297ca21c53c38799 Mon Sep 17 00:00:00 2001 From: Liang Li Date: Tue, 8 Mar 2016 13:53:17 +0800 Subject: cutils: add avx2 instruction optimization buffer_find_nonzero_offset() is a hot function during live migration. Now it use SSE2 instructions for optimization. For platform supports AVX2 instructions, use AVX2 instructions for optimization can help to improve the performance of buffer_find_nonzero_offset() about 30% comparing to SSE2. Live migration can be faster with this optimization, the test result shows that for an 8GiB RAM idle guest just boots, this patch can help to shorten the total live migration time about 6%. This patch use the ifunc mechanism to select the proper function when running, for platform supports AVX2, execute the AVX2 instructions, else, execute the original instructions. Signed-off-by: Liang Li Suggested-by: Paolo Bonzini Suggested-by: Richard Henderson Reviewed-by: Paolo Bonzini Message-Id: <1457416397-26671-3-git-send-email-liang.z.li@intel.com> Signed-off-by: Amit Shah --- include/qemu-common.h | 8 +------- 1 file changed, 1 insertion(+), 7 deletions(-) (limited to 'include') diff --git a/include/qemu-common.h b/include/qemu-common.h index ced2994..887ca71 100644 --- a/include/qemu-common.h +++ b/include/qemu-common.h @@ -476,13 +476,7 @@ void qemu_hexdump(const char *buf, FILE *fp, const char *prefix, size_t size); #endif #define BUFFER_FIND_NONZERO_OFFSET_UNROLL_FACTOR 8 -static inline bool -can_use_buffer_find_nonzero_offset(const void *buf, size_t len) -{ - return (len % (BUFFER_FIND_NONZERO_OFFSET_UNROLL_FACTOR - * sizeof(VECTYPE)) == 0 - && ((uintptr_t) buf) % sizeof(VECTYPE) == 0); -} +bool can_use_buffer_find_nonzero_offset(const void *buf, size_t len); size_t buffer_find_nonzero_offset(const void *buf, size_t len); /* -- cgit v1.1