1/* 2 * VC-1 and WMV3 - DSP functions MMX-optimized 3 * Copyright (c) 2007 Christophe GISQUET <christophe.gisquet@free.fr> 4 * 5 * Permission is hereby granted, free of charge, to any person 6 * obtaining a copy of this software and associated documentation 7 * files (the "Software"), to deal in the Software without 8 * restriction, including without limitation the rights to use, 9 * copy, modify, merge, publish, distribute, sublicense, and/or sell 10 * copies of the Software, and to permit persons to whom the 11 * Software is furnished to do so, subject to the following 12 * conditions: 13 * 14 * The above copyright notice and this permission notice shall be 15 * included in all copies or substantial portions of the Software. 16 * 17 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, 18 * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES 19 * OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND 20 * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT 21 * HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, 22 * WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 23 * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR 24 * OTHER DEALINGS IN THE SOFTWARE. 25 */ 26 27#include "libavutil/attributes.h" 28#include "libavutil/cpu.h" 29#include "libavutil/x86/cpu.h" 30#include "libavutil/x86/asm.h" 31#include "libavcodec/vc1dsp.h" 32#include "fpel.h" 33#include "vc1dsp.h" 34#include "config.h" 35 36#define LOOP_FILTER4(EXT) \ 37void ff_vc1_v_loop_filter4_ ## EXT(uint8_t *src, ptrdiff_t stride, int pq); \ 38void ff_vc1_h_loop_filter4_ ## EXT(uint8_t *src, ptrdiff_t stride, int pq); 39#define LOOP_FILTER816(EXT) \ 40void ff_vc1_v_loop_filter8_ ## EXT(uint8_t *src, ptrdiff_t stride, int pq); \ 41void ff_vc1_h_loop_filter8_ ## EXT(uint8_t *src, ptrdiff_t stride, int pq); \ 42\ 43static void vc1_v_loop_filter16_ ## EXT(uint8_t *src, ptrdiff_t stride, int pq) \ 44{ \ 45 ff_vc1_v_loop_filter8_ ## EXT(src, stride, pq); \ 46 ff_vc1_v_loop_filter8_ ## EXT(src+8, stride, pq); \ 47} \ 48\ 49static void vc1_h_loop_filter16_ ## EXT(uint8_t *src, ptrdiff_t stride, int pq) \ 50{ \ 51 ff_vc1_h_loop_filter8_ ## EXT(src, stride, pq); \ 52 ff_vc1_h_loop_filter8_ ## EXT(src+8*stride, stride, pq); \ 53} 54 55#if HAVE_X86ASM 56LOOP_FILTER4(mmxext) 57LOOP_FILTER816(sse2) 58LOOP_FILTER4(ssse3) 59LOOP_FILTER816(ssse3) 60 61void ff_vc1_h_loop_filter8_sse4(uint8_t *src, ptrdiff_t stride, int pq); 62 63static void vc1_h_loop_filter16_sse4(uint8_t *src, ptrdiff_t stride, int pq) 64{ 65 ff_vc1_h_loop_filter8_sse4(src, stride, pq); 66 ff_vc1_h_loop_filter8_sse4(src+8*stride, stride, pq); 67} 68 69#define DECLARE_FUNCTION(OP, DEPTH, INSN) \ 70 static void OP##vc1_mspel_mc00_##DEPTH##INSN(uint8_t *dst, \ 71 const uint8_t *src, ptrdiff_t stride, int rnd) \ 72 { \ 73 ff_ ## OP ## pixels ## DEPTH ## INSN(dst, src, stride, DEPTH); \ 74 } 75 76DECLARE_FUNCTION(put_, 8, _mmx) 77DECLARE_FUNCTION(avg_, 8, _mmxext) 78DECLARE_FUNCTION(put_, 16, _sse2) 79DECLARE_FUNCTION(avg_, 16, _sse2) 80 81#endif /* HAVE_X86ASM */ 82 83void ff_put_vc1_chroma_mc8_nornd_mmx (uint8_t *dst, uint8_t *src, 84 ptrdiff_t stride, int h, int x, int y); 85void ff_avg_vc1_chroma_mc8_nornd_mmxext(uint8_t *dst, uint8_t *src, 86 ptrdiff_t stride, int h, int x, int y); 87void ff_put_vc1_chroma_mc8_nornd_ssse3(uint8_t *dst, uint8_t *src, 88 ptrdiff_t stride, int h, int x, int y); 89void ff_avg_vc1_chroma_mc8_nornd_ssse3(uint8_t *dst, uint8_t *src, 90 ptrdiff_t stride, int h, int x, int y); 91void ff_vc1_inv_trans_4x4_dc_mmxext(uint8_t *dest, ptrdiff_t linesize, 92 int16_t *block); 93void ff_vc1_inv_trans_4x8_dc_mmxext(uint8_t *dest, ptrdiff_t linesize, 94 int16_t *block); 95void ff_vc1_inv_trans_8x4_dc_mmxext(uint8_t *dest, ptrdiff_t linesize, 96 int16_t *block); 97void ff_vc1_inv_trans_8x8_dc_mmxext(uint8_t *dest, ptrdiff_t linesize, 98 int16_t *block); 99 100 101av_cold void ff_vc1dsp_init_x86(VC1DSPContext *dsp) 102{ 103 int cpu_flags = av_get_cpu_flags(); 104 105 if (HAVE_6REGS && INLINE_MMX(cpu_flags)) 106 if (EXTERNAL_MMX(cpu_flags)) 107 ff_vc1dsp_init_mmx(dsp); 108 109 if (HAVE_6REGS && INLINE_MMXEXT(cpu_flags)) 110 if (EXTERNAL_MMXEXT(cpu_flags)) 111 ff_vc1dsp_init_mmxext(dsp); 112 113#define ASSIGN_LF4(EXT) \ 114 dsp->vc1_v_loop_filter4 = ff_vc1_v_loop_filter4_ ## EXT; \ 115 dsp->vc1_h_loop_filter4 = ff_vc1_h_loop_filter4_ ## EXT 116#define ASSIGN_LF816(EXT) \ 117 dsp->vc1_v_loop_filter8 = ff_vc1_v_loop_filter8_ ## EXT; \ 118 dsp->vc1_h_loop_filter8 = ff_vc1_h_loop_filter8_ ## EXT; \ 119 dsp->vc1_v_loop_filter16 = vc1_v_loop_filter16_ ## EXT; \ 120 dsp->vc1_h_loop_filter16 = vc1_h_loop_filter16_ ## EXT 121 122#if HAVE_X86ASM 123 if (EXTERNAL_MMX(cpu_flags)) { 124 dsp->put_no_rnd_vc1_chroma_pixels_tab[0] = ff_put_vc1_chroma_mc8_nornd_mmx; 125 126 dsp->put_vc1_mspel_pixels_tab[1][0] = put_vc1_mspel_mc00_8_mmx; 127 } 128 if (EXTERNAL_MMXEXT(cpu_flags)) { 129 ASSIGN_LF4(mmxext); 130 dsp->avg_no_rnd_vc1_chroma_pixels_tab[0] = ff_avg_vc1_chroma_mc8_nornd_mmxext; 131 132 dsp->avg_vc1_mspel_pixels_tab[1][0] = avg_vc1_mspel_mc00_8_mmxext; 133 134 dsp->vc1_inv_trans_8x8_dc = ff_vc1_inv_trans_8x8_dc_mmxext; 135 dsp->vc1_inv_trans_4x8_dc = ff_vc1_inv_trans_4x8_dc_mmxext; 136 dsp->vc1_inv_trans_8x4_dc = ff_vc1_inv_trans_8x4_dc_mmxext; 137 dsp->vc1_inv_trans_4x4_dc = ff_vc1_inv_trans_4x4_dc_mmxext; 138 } 139 if (EXTERNAL_SSE2(cpu_flags)) { 140 ASSIGN_LF816(sse2); 141 142 dsp->put_vc1_mspel_pixels_tab[0][0] = put_vc1_mspel_mc00_16_sse2; 143 dsp->avg_vc1_mspel_pixels_tab[0][0] = avg_vc1_mspel_mc00_16_sse2; 144 } 145 if (EXTERNAL_SSSE3(cpu_flags)) { 146 ASSIGN_LF4(ssse3); 147 ASSIGN_LF816(ssse3); 148 dsp->put_no_rnd_vc1_chroma_pixels_tab[0] = ff_put_vc1_chroma_mc8_nornd_ssse3; 149 dsp->avg_no_rnd_vc1_chroma_pixels_tab[0] = ff_avg_vc1_chroma_mc8_nornd_ssse3; 150 } 151 if (EXTERNAL_SSE4(cpu_flags)) { 152 dsp->vc1_h_loop_filter8 = ff_vc1_h_loop_filter8_sse4; 153 dsp->vc1_h_loop_filter16 = vc1_h_loop_filter16_sse4; 154 } 155#endif /* HAVE_X86ASM */ 156} 157