From 658efd2fc986bca88336569b2e6fa8b537a660d8 Mon Sep 17 00:00:00 2001 From: Ray Kinsella Date: Fri, 21 Apr 2017 11:08:43 +0100 Subject: vppinfra: clib_memcpy improvement In the case where n is a constant 16 bytes, the second load/store is ignored by the load/store unit - it has neglible/zero cost. In the case where n is variable and greater than 512 bytes, the extra if (n == 16) branch has a very small performance impact. Change-Id: I04b313cf022c18fee31b1d9bcf6a128414659a99 Signed-off-by: Ray Kinsella --- src/vppinfra/memcpy_sse3.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'src/vppinfra/memcpy_sse3.h') diff --git a/src/vppinfra/memcpy_sse3.h b/src/vppinfra/memcpy_sse3.h index 49baf5e5d31..4fc48c86c8b 100644 --- a/src/vppinfra/memcpy_sse3.h +++ b/src/vppinfra/memcpy_sse3.h @@ -224,11 +224,6 @@ clib_memcpy (void *dst, const void *src, size_t n) /** * Fast way when copy size doesn't exceed 512 bytes */ - if (n == 16) - { - clib_mov16 ((u8 *) dst, (const u8 *) src); - return ret; - } if (n <= 32) { clib_mov16 ((u8 *) dst, (const u8 *) src); -- cgit 1.2.3-korg