generic-library/vpx
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity
22c05c0575
vpx/vp8/encoder/x86/quantize_x86.h

68 lines
1.6 KiB
C
Raw Normal View History

sse2 version of vp8_regular_quantize_b Added sse2 version of vp8_regular_quantize_b which improved encode performance(for the clip used) by ~10% for 32 bit builds and ~3% for 64 bit builds. Also updated SHADOW_ARGS_TO_STACK to allow for more than 9 arguments. Change-Id: I62f78eabc8040b39f3ffdf21be175811e96b39af
2010-06-14 20:07:56 +02:00
/*
Use WebM in copyright notice for consistency Changes 'The VP8 project' to 'The WebM project', for consistency with other webmproject.org repositories. Fixes issue #97. Change-Id: I37c13ed5fbdb9d334ceef71c6350e9febed9bbba
2010-09-09 14:16:39 +02:00
* Copyright (c) 2010 The WebM project authors. All Rights Reserved.
sse2 version of vp8_regular_quantize_b Added sse2 version of vp8_regular_quantize_b which improved encode performance(for the clip used) by ~10% for 32 bit builds and ~3% for 64 bit builds. Also updated SHADOW_ARGS_TO_STACK to allow for more than 9 arguments. Change-Id: I62f78eabc8040b39f3ffdf21be175811e96b39af
2010-06-14 20:07:56 +02:00
*
* Use of this source code is governed by a BSD-style license and patent
* grant that can be found in the LICENSE file in the root of the source
* tree. All contributing project authors may be found in the AUTHORS
* file in the root of the source tree.
*/
#ifndef QUANTIZE_X86_H
#define QUANTIZE_X86_H
/* Note:
*
* This platform is commonly built for runtime CPU detection. If you modify
* any of the function mappings present in this file, be sure to also update
* them in the function pointer initialization code
*/
#if HAVE_MMX
use asm_offsets with vp8_fast_quantize_b_sse3 on the same order as the sse2 fast quantize change: ~2% except for 32bit. only a slight improvment there. Change-Id: Iff80e5f1ce7e646eebfdc8871405458ff911986b
2011-04-07 22:40:05 +02:00
#endif /* HAVE_MMX */
sse2 version of vp8_regular_quantize_b Added sse2 version of vp8_regular_quantize_b which improved encode performance(for the clip used) by ~10% for 32 bit builds and ~3% for 64 bit builds. Also updated SHADOW_ARGS_TO_STACK to allow for more than 9 arguments. Change-Id: I62f78eabc8040b39f3ffdf21be175811e96b39af
2010-06-14 20:07:56 +02:00
#if HAVE_SSE2
extern prototype_quantize_block(vp8_regular_quantize_b_sse2);
use asm_offsets with vp8_fast_quantize_b_sse2 on the same order as the regular quantize change: ~2% Change-Id: I5c9eec18e89ae7345dd96945cb740e6f349cee86
2011-03-24 18:31:10 +01:00
extern prototype_quantize_block(vp8_fast_quantize_b_sse2);
sse2 version of vp8_regular_quantize_b Added sse2 version of vp8_regular_quantize_b which improved encode performance(for the clip used) by ~10% for 32 bit builds and ~3% for 64 bit builds. Also updated SHADOW_ARGS_TO_STACK to allow for more than 9 arguments. Change-Id: I62f78eabc8040b39f3ffdf21be175811e96b39af
2010-06-14 20:07:56 +02:00
#if !CONFIG_RUNTIME_CPU_DETECT
update sse2 regular quantizer about ~5% gain on 32bit. disabled for 64bit unset executable bit on ssse3 version (cosmetic) Change-Id: I1a5860839eb294ce4261f819caea2dcfa78e57ca
2011-01-11 15:41:57 +01:00
#undef vp8_quantize_quantb
#define vp8_quantize_quantb vp8_regular_quantize_b_sse2
sse2 version of vp8_regular_quantize_b Added sse2 version of vp8_regular_quantize_b which improved encode performance(for the clip used) by ~10% for 32 bit builds and ~3% for 64 bit builds. Also updated SHADOW_ARGS_TO_STACK to allow for more than 9 arguments. Change-Id: I62f78eabc8040b39f3ffdf21be175811e96b39af
2010-06-14 20:07:56 +02:00
use asm_offsets with vp8_fast_quantize_b_sse2 on the same order as the regular quantize change: ~2% Change-Id: I5c9eec18e89ae7345dd96945cb740e6f349cee86
2011-03-24 18:31:10 +01:00
#undef vp8_quantize_fastquantb
#define vp8_quantize_fastquantb vp8_fast_quantize_b_sse2
use asm_offsets with vp8_fast_quantize_b_sse3 on the same order as the sse2 fast quantize change: ~2% except for 32bit. only a slight improvment there. Change-Id: Iff80e5f1ce7e646eebfdc8871405458ff911986b
2011-04-07 22:40:05 +02:00
#endif /* !CONFIG_RUNTIME_CPU_DETECT */
sse2 version of vp8_regular_quantize_b Added sse2 version of vp8_regular_quantize_b which improved encode performance(for the clip used) by ~10% for 32 bit builds and ~3% for 64 bit builds. Also updated SHADOW_ARGS_TO_STACK to allow for more than 9 arguments. Change-Id: I62f78eabc8040b39f3ffdf21be175811e96b39af
2010-06-14 20:07:56 +02:00
use asm_offsets with vp8_fast_quantize_b_sse3 on the same order as the sse2 fast quantize change: ~2% except for 32bit. only a slight improvment there. Change-Id: Iff80e5f1ce7e646eebfdc8871405458ff911986b
2011-04-07 22:40:05 +02:00
#endif /* HAVE_SSE2 */
sse2 version of vp8_regular_quantize_b Added sse2 version of vp8_regular_quantize_b which improved encode performance(for the clip used) by ~10% for 32 bit builds and ~3% for 64 bit builds. Also updated SHADOW_ARGS_TO_STACK to allow for more than 9 arguments. Change-Id: I62f78eabc8040b39f3ffdf21be175811e96b39af
2010-06-14 20:07:56 +02:00
use asm_offsets with vp8_fast_quantize_b_sse3 on the same order as the sse2 fast quantize change: ~2% except for 32bit. only a slight improvment there. Change-Id: Iff80e5f1ce7e646eebfdc8871405458ff911986b
2011-04-07 22:40:05 +02:00
#if HAVE_SSSE3
extern prototype_quantize_block(vp8_fast_quantize_b_ssse3);
#if !CONFIG_RUNTIME_CPU_DETECT
#undef vp8_quantize_fastquantb
#define vp8_quantize_fastquantb vp8_fast_quantize_b_ssse3
#endif /* !CONFIG_RUNTIME_CPU_DETECT */
#endif /* HAVE_SSSE3 */
keep values in registers during quantization add an sse4 quantizer so we can use pinsrw/pextrw and keep values in xmm registers instead of proxying through the stack. and as long as we're bumping up, use some ssse3 instructions in the EOB detection (see ssse3 fast quantizer) pick up about a percent on 32bit and about two on 64bit. Change-Id: If15abba0e8b037a1d231c0edf33501545c9d9363
2011-04-13 22:38:02 +02:00
#if HAVE_SSE4_1
extern prototype_quantize_block(vp8_regular_quantize_b_sse4);
#if !CONFIG_RUNTIME_CPU_DETECT
#undef vp8_quantize_quantb
#define vp8_quantize_quantb vp8_regular_quantize_b_sse4
#endif /* !CONFIG_RUNTIME_CPU_DETECT */
#endif /* HAVE_SSE4_1 */
use asm_offsets with vp8_fast_quantize_b_sse3 on the same order as the sse2 fast quantize change: ~2% except for 32bit. only a slight improvment there. Change-Id: Iff80e5f1ce7e646eebfdc8871405458ff911986b
2011-04-07 22:40:05 +02:00
#endif /* QUANTIZE_X86_H */
Reference in New Issue Copy Permalink