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