| @@ -849,6 +849,6 @@ av_cold void ff_vc1dsp_init(VC1DSPContext* dsp) { | |||||
| if (HAVE_ALTIVEC) | if (HAVE_ALTIVEC) | ||||
| ff_vc1dsp_init_altivec(dsp); | ff_vc1dsp_init_altivec(dsp); | ||||
| if (HAVE_MMX) | |||||
| ff_vc1dsp_init_mmx(dsp); | |||||
| if (ARCH_X86) | |||||
| ff_vc1dsp_init_x86(dsp); | |||||
| } | } | ||||
| @@ -74,6 +74,6 @@ typedef struct VC1DSPContext { | |||||
| void ff_vc1dsp_init(VC1DSPContext* c); | void ff_vc1dsp_init(VC1DSPContext* c); | ||||
| void ff_vc1dsp_init_altivec(VC1DSPContext* c); | void ff_vc1dsp_init_altivec(VC1DSPContext* c); | ||||
| void ff_vc1dsp_init_mmx(VC1DSPContext* dsp); | |||||
| void ff_vc1dsp_init_x86(VC1DSPContext* dsp); | |||||
| #endif /* AVCODEC_VC1DSP_H */ | #endif /* AVCODEC_VC1DSP_H */ | ||||
| @@ -18,6 +18,7 @@ OBJS-$(CONFIG_RV30_DECODER) += x86/rv34dsp_init.o | |||||
| OBJS-$(CONFIG_RV40_DECODER) += x86/rv34dsp_init.o \ | OBJS-$(CONFIG_RV40_DECODER) += x86/rv34dsp_init.o \ | ||||
| x86/rv40dsp_init.o | x86/rv40dsp_init.o | ||||
| OBJS-$(CONFIG_TRUEHD_DECODER) += x86/mlpdsp.o | OBJS-$(CONFIG_TRUEHD_DECODER) += x86/mlpdsp.o | ||||
| OBJS-$(CONFIG_VC1_DECODER) += x86/vc1dsp_init.o | |||||
| OBJS-$(CONFIG_VP3DSP) += x86/vp3dsp_init.o | OBJS-$(CONFIG_VP3DSP) += x86/vp3dsp_init.o | ||||
| OBJS-$(CONFIG_VP5_DECODER) += x86/vp56dsp_init.o | OBJS-$(CONFIG_VP5_DECODER) += x86/vp56dsp_init.o | ||||
| OBJS-$(CONFIG_VP6_DECODER) += x86/vp56dsp_init.o | OBJS-$(CONFIG_VP6_DECODER) += x86/vp56dsp_init.o | ||||
| @@ -0,0 +1,29 @@ | |||||
| /* | |||||
| * VC-1 and WMV3 decoder - X86 DSP init functions | |||||
| * | |||||
| * This file is part of Libav. | |||||
| * | |||||
| * Libav is free software; you can redistribute it and/or | |||||
| * modify it under the terms of the GNU Lesser General Public | |||||
| * License as published by the Free Software Foundation; either | |||||
| * version 2.1 of the License, or (at your option) any later version. | |||||
| * | |||||
| * Libav is distributed in the hope that it will be useful, | |||||
| * but WITHOUT ANY WARRANTY; without even the implied warranty of | |||||
| * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU | |||||
| * Lesser General Public License for more details. | |||||
| * | |||||
| * You should have received a copy of the GNU Lesser General Public | |||||
| * License along with Libav; if not, write to the Free Software | |||||
| * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA | |||||
| */ | |||||
| #ifndef AVCODEC_X86_VC1DSP_H | |||||
| #define AVCODEC_X86_VC1DSP_H | |||||
| #include "libavcodec/vc1dsp.h" | |||||
| void ff_vc1dsp_init_mmx(VC1DSPContext *dsp); | |||||
| void ff_vc1dsp_init_mmxext(VC1DSPContext *dsp); | |||||
| #endif /* AVCODEC_X86_VC1DSP_H */ | |||||
| @@ -0,0 +1,123 @@ | |||||
| /* | |||||
| * VC-1 and WMV3 - DSP functions MMX-optimized | |||||
| * Copyright (c) 2007 Christophe GISQUET <christophe.gisquet@free.fr> | |||||
| * | |||||
| * Permission is hereby granted, free of charge, to any person | |||||
| * obtaining a copy of this software and associated documentation | |||||
| * files (the "Software"), to deal in the Software without | |||||
| * restriction, including without limitation the rights to use, | |||||
| * copy, modify, merge, publish, distribute, sublicense, and/or sell | |||||
| * copies of the Software, and to permit persons to whom the | |||||
| * Software is furnished to do so, subject to the following | |||||
| * conditions: | |||||
| * | |||||
| * The above copyright notice and this permission notice shall be | |||||
| * included in all copies or substantial portions of the Software. | |||||
| * | |||||
| * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, | |||||
| * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES | |||||
| * OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND | |||||
| * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT | |||||
| * HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, | |||||
| * WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING | |||||
| * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR | |||||
| * OTHER DEALINGS IN THE SOFTWARE. | |||||
| */ | |||||
| #include "libavutil/cpu.h" | |||||
| #include "libavutil/x86/cpu.h" | |||||
| #include "libavcodec/vc1dsp.h" | |||||
| #include "vc1dsp.h" | |||||
| #include "config.h" | |||||
| #define LOOP_FILTER(EXT) \ | |||||
| void ff_vc1_v_loop_filter4_ ## EXT(uint8_t *src, int stride, int pq); \ | |||||
| void ff_vc1_h_loop_filter4_ ## EXT(uint8_t *src, int stride, int pq); \ | |||||
| void ff_vc1_v_loop_filter8_ ## EXT(uint8_t *src, int stride, int pq); \ | |||||
| void ff_vc1_h_loop_filter8_ ## EXT(uint8_t *src, int stride, int pq); \ | |||||
| \ | |||||
| static void vc1_v_loop_filter16_ ## EXT(uint8_t *src, int stride, int pq) \ | |||||
| { \ | |||||
| ff_vc1_v_loop_filter8_ ## EXT(src, stride, pq); \ | |||||
| ff_vc1_v_loop_filter8_ ## EXT(src+8, stride, pq); \ | |||||
| } \ | |||||
| \ | |||||
| static void vc1_h_loop_filter16_ ## EXT(uint8_t *src, int stride, int pq) \ | |||||
| { \ | |||||
| ff_vc1_h_loop_filter8_ ## EXT(src, stride, pq); \ | |||||
| ff_vc1_h_loop_filter8_ ## EXT(src+8*stride, stride, pq); \ | |||||
| } | |||||
| #if HAVE_YASM | |||||
| LOOP_FILTER(mmx2) | |||||
| LOOP_FILTER(sse2) | |||||
| LOOP_FILTER(ssse3) | |||||
| void ff_vc1_h_loop_filter8_sse4(uint8_t *src, int stride, int pq); | |||||
| static void vc1_h_loop_filter16_sse4(uint8_t *src, int stride, int pq) | |||||
| { | |||||
| ff_vc1_h_loop_filter8_sse4(src, stride, pq); | |||||
| ff_vc1_h_loop_filter8_sse4(src+8*stride, stride, pq); | |||||
| } | |||||
| #endif /* HAVE_YASM */ | |||||
| void ff_put_vc1_chroma_mc8_mmx_nornd (uint8_t *dst, uint8_t *src, | |||||
| int stride, int h, int x, int y); | |||||
| void ff_avg_vc1_chroma_mc8_mmx2_nornd (uint8_t *dst, uint8_t *src, | |||||
| int stride, int h, int x, int y); | |||||
| void ff_avg_vc1_chroma_mc8_3dnow_nornd(uint8_t *dst, uint8_t *src, | |||||
| int stride, int h, int x, int y); | |||||
| void ff_put_vc1_chroma_mc8_ssse3_nornd(uint8_t *dst, uint8_t *src, | |||||
| int stride, int h, int x, int y); | |||||
| void ff_avg_vc1_chroma_mc8_ssse3_nornd(uint8_t *dst, uint8_t *src, | |||||
| int stride, int h, int x, int y); | |||||
| av_cold void ff_vc1dsp_init_x86(VC1DSPContext *dsp) | |||||
| { | |||||
| int mm_flags = av_get_cpu_flags(); | |||||
| if (INLINE_MMX(mm_flags)) | |||||
| ff_vc1dsp_init_mmx(dsp); | |||||
| if (INLINE_MMXEXT(mm_flags)) | |||||
| ff_vc1dsp_init_mmxext(dsp); | |||||
| #define ASSIGN_LF(EXT) \ | |||||
| dsp->vc1_v_loop_filter4 = ff_vc1_v_loop_filter4_ ## EXT; \ | |||||
| dsp->vc1_h_loop_filter4 = ff_vc1_h_loop_filter4_ ## EXT; \ | |||||
| dsp->vc1_v_loop_filter8 = ff_vc1_v_loop_filter8_ ## EXT; \ | |||||
| dsp->vc1_h_loop_filter8 = ff_vc1_h_loop_filter8_ ## EXT; \ | |||||
| dsp->vc1_v_loop_filter16 = vc1_v_loop_filter16_ ## EXT; \ | |||||
| dsp->vc1_h_loop_filter16 = vc1_h_loop_filter16_ ## EXT | |||||
| #if HAVE_YASM | |||||
| if (mm_flags & AV_CPU_FLAG_MMX) { | |||||
| dsp->put_no_rnd_vc1_chroma_pixels_tab[0]= ff_put_vc1_chroma_mc8_mmx_nornd; | |||||
| } | |||||
| if (mm_flags & AV_CPU_FLAG_MMXEXT) { | |||||
| ASSIGN_LF(mmx2); | |||||
| dsp->avg_no_rnd_vc1_chroma_pixels_tab[0]= ff_avg_vc1_chroma_mc8_mmx2_nornd; | |||||
| } else if (mm_flags & AV_CPU_FLAG_3DNOW) { | |||||
| dsp->avg_no_rnd_vc1_chroma_pixels_tab[0]= ff_avg_vc1_chroma_mc8_3dnow_nornd; | |||||
| } | |||||
| if (mm_flags & AV_CPU_FLAG_SSE2) { | |||||
| dsp->vc1_v_loop_filter8 = ff_vc1_v_loop_filter8_sse2; | |||||
| dsp->vc1_h_loop_filter8 = ff_vc1_h_loop_filter8_sse2; | |||||
| dsp->vc1_v_loop_filter16 = vc1_v_loop_filter16_sse2; | |||||
| dsp->vc1_h_loop_filter16 = vc1_h_loop_filter16_sse2; | |||||
| } | |||||
| if (mm_flags & AV_CPU_FLAG_SSSE3) { | |||||
| ASSIGN_LF(ssse3); | |||||
| dsp->put_no_rnd_vc1_chroma_pixels_tab[0]= ff_put_vc1_chroma_mc8_ssse3_nornd; | |||||
| dsp->avg_no_rnd_vc1_chroma_pixels_tab[0]= ff_avg_vc1_chroma_mc8_ssse3_nornd; | |||||
| } | |||||
| if (mm_flags & AV_CPU_FLAG_SSE4) { | |||||
| dsp->vc1_h_loop_filter8 = ff_vc1_h_loop_filter8_sse4; | |||||
| dsp->vc1_h_loop_filter16 = vc1_h_loop_filter16_sse4; | |||||
| } | |||||
| #endif /* HAVE_YASM */ | |||||
| } | |||||
| @@ -28,9 +28,11 @@ | |||||
| #include "libavutil/internal.h" | #include "libavutil/internal.h" | ||||
| #include "libavutil/mem.h" | #include "libavutil/mem.h" | ||||
| #include "libavutil/x86/asm.h" | #include "libavutil/x86/asm.h" | ||||
| #include "libavutil/x86/cpu.h" | |||||
| #include "libavcodec/dsputil.h" | #include "libavcodec/dsputil.h" | ||||
| #include "dsputil_mmx.h" | #include "dsputil_mmx.h" | ||||
| #include "libavcodec/vc1dsp.h" | #include "libavcodec/vc1dsp.h" | ||||
| #include "vc1dsp.h" | |||||
| #if HAVE_INLINE_ASM | #if HAVE_INLINE_ASM | ||||
| @@ -686,57 +688,8 @@ static void vc1_inv_trans_8x8_dc_mmx2(uint8_t *dest, int linesize, DCTELEM *bloc | |||||
| ); | ); | ||||
| } | } | ||||
| #endif /* HAVE_INLINE_ASM */ | |||||
| #define LOOP_FILTER(EXT) \ | |||||
| void ff_vc1_v_loop_filter4_ ## EXT(uint8_t *src, int stride, int pq); \ | |||||
| void ff_vc1_h_loop_filter4_ ## EXT(uint8_t *src, int stride, int pq); \ | |||||
| void ff_vc1_v_loop_filter8_ ## EXT(uint8_t *src, int stride, int pq); \ | |||||
| void ff_vc1_h_loop_filter8_ ## EXT(uint8_t *src, int stride, int pq); \ | |||||
| \ | |||||
| static void vc1_v_loop_filter16_ ## EXT(uint8_t *src, int stride, int pq) \ | |||||
| { \ | |||||
| ff_vc1_v_loop_filter8_ ## EXT(src, stride, pq); \ | |||||
| ff_vc1_v_loop_filter8_ ## EXT(src+8, stride, pq); \ | |||||
| } \ | |||||
| \ | |||||
| static void vc1_h_loop_filter16_ ## EXT(uint8_t *src, int stride, int pq) \ | |||||
| { \ | |||||
| ff_vc1_h_loop_filter8_ ## EXT(src, stride, pq); \ | |||||
| ff_vc1_h_loop_filter8_ ## EXT(src+8*stride, stride, pq); \ | |||||
| } | |||||
| #if HAVE_YASM | |||||
| LOOP_FILTER(mmx2) | |||||
| LOOP_FILTER(sse2) | |||||
| LOOP_FILTER(ssse3) | |||||
| void ff_vc1_h_loop_filter8_sse4(uint8_t *src, int stride, int pq); | |||||
| static void vc1_h_loop_filter16_sse4(uint8_t *src, int stride, int pq) | |||||
| av_cold void ff_vc1dsp_init_mmx(VC1DSPContext *dsp) | |||||
| { | { | ||||
| ff_vc1_h_loop_filter8_sse4(src, stride, pq); | |||||
| ff_vc1_h_loop_filter8_sse4(src+8*stride, stride, pq); | |||||
| } | |||||
| #endif /* HAVE_YASM */ | |||||
| void ff_put_vc1_chroma_mc8_mmx_nornd (uint8_t *dst, uint8_t *src, | |||||
| int stride, int h, int x, int y); | |||||
| void ff_avg_vc1_chroma_mc8_mmx2_nornd (uint8_t *dst, uint8_t *src, | |||||
| int stride, int h, int x, int y); | |||||
| void ff_avg_vc1_chroma_mc8_3dnow_nornd(uint8_t *dst, uint8_t *src, | |||||
| int stride, int h, int x, int y); | |||||
| void ff_put_vc1_chroma_mc8_ssse3_nornd(uint8_t *dst, uint8_t *src, | |||||
| int stride, int h, int x, int y); | |||||
| void ff_avg_vc1_chroma_mc8_ssse3_nornd(uint8_t *dst, uint8_t *src, | |||||
| int stride, int h, int x, int y); | |||||
| void ff_vc1dsp_init_mmx(VC1DSPContext *dsp) | |||||
| { | |||||
| int mm_flags = av_get_cpu_flags(); | |||||
| #if HAVE_INLINE_ASM | |||||
| if (mm_flags & AV_CPU_FLAG_MMX) { | |||||
| dsp->put_vc1_mspel_pixels_tab[ 0] = ff_put_vc1_mspel_mc00_mmx; | dsp->put_vc1_mspel_pixels_tab[ 0] = ff_put_vc1_mspel_mc00_mmx; | ||||
| dsp->put_vc1_mspel_pixels_tab[ 4] = put_vc1_mspel_mc01_mmx; | dsp->put_vc1_mspel_pixels_tab[ 4] = put_vc1_mspel_mc01_mmx; | ||||
| dsp->put_vc1_mspel_pixels_tab[ 8] = put_vc1_mspel_mc02_mmx; | dsp->put_vc1_mspel_pixels_tab[ 8] = put_vc1_mspel_mc02_mmx; | ||||
| @@ -756,9 +709,10 @@ void ff_vc1dsp_init_mmx(VC1DSPContext *dsp) | |||||
| dsp->put_vc1_mspel_pixels_tab[ 7] = put_vc1_mspel_mc31_mmx; | dsp->put_vc1_mspel_pixels_tab[ 7] = put_vc1_mspel_mc31_mmx; | ||||
| dsp->put_vc1_mspel_pixels_tab[11] = put_vc1_mspel_mc32_mmx; | dsp->put_vc1_mspel_pixels_tab[11] = put_vc1_mspel_mc32_mmx; | ||||
| dsp->put_vc1_mspel_pixels_tab[15] = put_vc1_mspel_mc33_mmx; | dsp->put_vc1_mspel_pixels_tab[15] = put_vc1_mspel_mc33_mmx; | ||||
| } | |||||
| } | |||||
| if (mm_flags & AV_CPU_FLAG_MMXEXT) { | |||||
| av_cold void ff_vc1dsp_init_mmxext(VC1DSPContext *dsp) | |||||
| { | |||||
| dsp->avg_vc1_mspel_pixels_tab[ 0] = ff_avg_vc1_mspel_mc00_mmx2; | dsp->avg_vc1_mspel_pixels_tab[ 0] = ff_avg_vc1_mspel_mc00_mmx2; | ||||
| dsp->avg_vc1_mspel_pixels_tab[ 4] = avg_vc1_mspel_mc01_mmx2; | dsp->avg_vc1_mspel_pixels_tab[ 4] = avg_vc1_mspel_mc01_mmx2; | ||||
| dsp->avg_vc1_mspel_pixels_tab[ 8] = avg_vc1_mspel_mc02_mmx2; | dsp->avg_vc1_mspel_pixels_tab[ 8] = avg_vc1_mspel_mc02_mmx2; | ||||
| @@ -783,43 +737,5 @@ void ff_vc1dsp_init_mmx(VC1DSPContext *dsp) | |||||
| dsp->vc1_inv_trans_4x8_dc = vc1_inv_trans_4x8_dc_mmx2; | dsp->vc1_inv_trans_4x8_dc = vc1_inv_trans_4x8_dc_mmx2; | ||||
| dsp->vc1_inv_trans_8x4_dc = vc1_inv_trans_8x4_dc_mmx2; | dsp->vc1_inv_trans_8x4_dc = vc1_inv_trans_8x4_dc_mmx2; | ||||
| dsp->vc1_inv_trans_4x4_dc = vc1_inv_trans_4x4_dc_mmx2; | dsp->vc1_inv_trans_4x4_dc = vc1_inv_trans_4x4_dc_mmx2; | ||||
| } | |||||
| #endif /* HAVE_INLINE_ASM */ | |||||
| #define ASSIGN_LF(EXT) \ | |||||
| dsp->vc1_v_loop_filter4 = ff_vc1_v_loop_filter4_ ## EXT; \ | |||||
| dsp->vc1_h_loop_filter4 = ff_vc1_h_loop_filter4_ ## EXT; \ | |||||
| dsp->vc1_v_loop_filter8 = ff_vc1_v_loop_filter8_ ## EXT; \ | |||||
| dsp->vc1_h_loop_filter8 = ff_vc1_h_loop_filter8_ ## EXT; \ | |||||
| dsp->vc1_v_loop_filter16 = vc1_v_loop_filter16_ ## EXT; \ | |||||
| dsp->vc1_h_loop_filter16 = vc1_h_loop_filter16_ ## EXT | |||||
| #if HAVE_YASM | |||||
| if (mm_flags & AV_CPU_FLAG_MMX) { | |||||
| dsp->put_no_rnd_vc1_chroma_pixels_tab[0]= ff_put_vc1_chroma_mc8_mmx_nornd; | |||||
| } | |||||
| if (mm_flags & AV_CPU_FLAG_MMXEXT) { | |||||
| ASSIGN_LF(mmx2); | |||||
| dsp->avg_no_rnd_vc1_chroma_pixels_tab[0]= ff_avg_vc1_chroma_mc8_mmx2_nornd; | |||||
| } else if (mm_flags & AV_CPU_FLAG_3DNOW) { | |||||
| dsp->avg_no_rnd_vc1_chroma_pixels_tab[0]= ff_avg_vc1_chroma_mc8_3dnow_nornd; | |||||
| } | |||||
| if (mm_flags & AV_CPU_FLAG_SSE2) { | |||||
| dsp->vc1_v_loop_filter8 = ff_vc1_v_loop_filter8_sse2; | |||||
| dsp->vc1_h_loop_filter8 = ff_vc1_h_loop_filter8_sse2; | |||||
| dsp->vc1_v_loop_filter16 = vc1_v_loop_filter16_sse2; | |||||
| dsp->vc1_h_loop_filter16 = vc1_h_loop_filter16_sse2; | |||||
| } | |||||
| if (mm_flags & AV_CPU_FLAG_SSSE3) { | |||||
| ASSIGN_LF(ssse3); | |||||
| dsp->put_no_rnd_vc1_chroma_pixels_tab[0]= ff_put_vc1_chroma_mc8_ssse3_nornd; | |||||
| dsp->avg_no_rnd_vc1_chroma_pixels_tab[0]= ff_avg_vc1_chroma_mc8_ssse3_nornd; | |||||
| } | |||||
| if (mm_flags & AV_CPU_FLAG_SSE4) { | |||||
| dsp->vc1_h_loop_filter8 = ff_vc1_h_loop_filter8_sse4; | |||||
| dsp->vc1_h_loop_filter16 = vc1_h_loop_filter16_sse4; | |||||
| } | |||||
| #endif /* HAVE_YASM */ | |||||
| } | } | ||||
| #endif /* HAVE_INLINE_ASM */ | |||||