71ecb5d7d9
Use mpsadbw, and calculate 8 sad at once. Function list: vp8_sad16x16x8_sse4 vp8_sad16x8x8_sse4 vp8_sad8x16x8_sse4 vp8_sad8x8x8_sse4 vp8_sad4x4x8_sse4 (test clip: tulip) For best quality mode, this gave encoder a 5% performance boost. For good quality mode with speed=1, this gave encoder a 3% performance boost. Change-Id: I083b5a39d39144f88dcbccbef95da6498e490134
38 lines
850 B
C
38 lines
850 B
C
/*
|
|
* Copyright (c) 2010 The WebM project authors. All Rights Reserved.
|
|
*
|
|
* Use of this source code is governed by a BSD-style license
|
|
* that can be found in the LICENSE file in the root of the source
|
|
* tree. An additional intellectual property rights grant can be found
|
|
* in the file PATENTS. All contributing project authors may
|
|
* be found in the AUTHORS file in the root of the source tree.
|
|
*/
|
|
|
|
|
|
#ifndef MCOMP_X86_H
|
|
#define MCOMP_X86_H
|
|
|
|
#if HAVE_SSE3
|
|
#if !CONFIG_RUNTIME_CPU_DETECT
|
|
|
|
#undef vp8_search_full_search
|
|
#define vp8_search_full_search vp8_full_search_sadx3
|
|
|
|
#undef vp8_search_diamond_search
|
|
#define vp8_search_diamond_search vp8_diamond_search_sadx4
|
|
|
|
#endif
|
|
#endif
|
|
|
|
#if HAVE_SSE4_1
|
|
#if !CONFIG_RUNTIME_CPU_DETECT
|
|
|
|
#undef vp8_search_full_search
|
|
#define vp8_search_full_search vp8_full_search_sadx8
|
|
|
|
#endif
|
|
#endif
|
|
|
|
#endif
|
|
|