aboutsummaryrefslogtreecommitdiffstats
path: root/libavcodec/x86/vc1dsp_init.c
blob: c8943fa2f7a414c3374d9ddb2a7c90e460f9779a (plain) (blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
/*
 * 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/attributes.h"
#include "libavutil/cpu.h"
#include "libavutil/x86/cpu.h"
#include "libavutil/x86/asm.h"
#include "libavcodec/vc1dsp.h"
#include "fpel.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(mmxext)
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);
}

#define DECLARE_FUNCTION(OP, DEPTH, INSN)                       \
    static void OP##vc1_mspel_mc00_##DEPTH##INSN(uint8_t *dst,          \
                             const uint8_t *src, ptrdiff_t stride, int rnd) \
    {                                                                       \
        ff_ ## OP ## pixels ## DEPTH ## INSN(dst, src, stride, DEPTH);     \
    }

DECLARE_FUNCTION(put_,  8, _mmx)
DECLARE_FUNCTION(put_, 16, _mmx)
DECLARE_FUNCTION(avg_,  8, _mmx)
DECLARE_FUNCTION(avg_, 16, _mmx)
DECLARE_FUNCTION(avg_,  8, _mmxext)
DECLARE_FUNCTION(avg_, 16, _mmxext)
DECLARE_FUNCTION(put_, 16, _sse2)
DECLARE_FUNCTION(avg_, 16, _sse2)

#endif /* HAVE_YASM */

void ff_put_vc1_chroma_mc8_nornd_mmx  (uint8_t *dst, uint8_t *src,
                                       int stride, int h, int x, int y);
void ff_avg_vc1_chroma_mc8_nornd_mmxext(uint8_t *dst, uint8_t *src,
                                        int stride, int h, int x, int y);
void ff_avg_vc1_chroma_mc8_nornd_3dnow(uint8_t *dst, uint8_t *src,
                                       int stride, int h, int x, int y);
void ff_put_vc1_chroma_mc8_nornd_ssse3(uint8_t *dst, uint8_t *src,
                                       int stride, int h, int x, int y);
void ff_avg_vc1_chroma_mc8_nornd_ssse3(uint8_t *dst, uint8_t *src,
                                       int stride, int h, int x, int y);
void ff_vc1_inv_trans_4x4_dc_mmxext(uint8_t *dest, int linesize,
                                    int16_t *block);
void ff_vc1_inv_trans_4x8_dc_mmxext(uint8_t *dest, int linesize,
                                    int16_t *block);
void ff_vc1_inv_trans_8x4_dc_mmxext(uint8_t *dest, int linesize,
                                    int16_t *block);
void ff_vc1_inv_trans_8x8_dc_mmxext(uint8_t *dest, int linesize,
                                    int16_t *block);


av_cold void ff_vc1dsp_init_x86(VC1DSPContext *dsp)
{
    int cpu_flags = av_get_cpu_flags();

    if (HAVE_6REGS && INLINE_MMX(cpu_flags) && EXTERNAL_MMX(cpu_flags))
        ff_vc1dsp_init_mmx(dsp);

    if (HAVE_6REGS && INLINE_MMXEXT(cpu_flags) && EXTERNAL_MMXEXT(cpu_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 (EXTERNAL_MMX(cpu_flags)) {
        dsp->put_no_rnd_vc1_chroma_pixels_tab[0] = ff_put_vc1_chroma_mc8_nornd_mmx;

        dsp->put_vc1_mspel_pixels_tab[1][0]      = put_vc1_mspel_mc00_8_mmx;
        dsp->put_vc1_mspel_pixels_tab[0][0]      = put_vc1_mspel_mc00_16_mmx;
        dsp->avg_vc1_mspel_pixels_tab[1][0]      = avg_vc1_mspel_mc00_8_mmx;
        dsp->avg_vc1_mspel_pixels_tab[0][0]      = avg_vc1_mspel_mc00_16_mmx;
    }
    if (EXTERNAL_AMD3DNOW(cpu_flags)) {
        dsp->avg_no_rnd_vc1_chroma_pixels_tab[0] = ff_avg_vc1_chroma_mc8_nornd_3dnow;
    }
    if (EXTERNAL_MMXEXT(cpu_flags)) {
        ASSIGN_LF(mmxext);
        dsp->avg_no_rnd_vc1_chroma_pixels_tab[0] = ff_avg_vc1_chroma_mc8_nornd_mmxext;

        dsp->avg_vc1_mspel_pixels_tab[1][0]      = avg_vc1_mspel_mc00_8_mmxext;
        dsp->avg_vc1_mspel_pixels_tab[0][0]      = avg_vc1_mspel_mc00_16_mmxext;

        dsp->vc1_inv_trans_8x8_dc                = ff_vc1_inv_trans_8x8_dc_mmxext;
        dsp->vc1_inv_trans_4x8_dc                = ff_vc1_inv_trans_4x8_dc_mmxext;
        dsp->vc1_inv_trans_8x4_dc                = ff_vc1_inv_trans_8x4_dc_mmxext;
        dsp->vc1_inv_trans_4x4_dc                = ff_vc1_inv_trans_4x4_dc_mmxext;
    }
    if (EXTERNAL_SSE2(cpu_flags)) {
        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;

        dsp->put_vc1_mspel_pixels_tab[0][0]      = put_vc1_mspel_mc00_16_sse2;
        dsp->avg_vc1_mspel_pixels_tab[0][0]      = avg_vc1_mspel_mc00_16_sse2;
    }
    if (EXTERNAL_SSSE3(cpu_flags)) {
        ASSIGN_LF(ssse3);
        dsp->put_no_rnd_vc1_chroma_pixels_tab[0] = ff_put_vc1_chroma_mc8_nornd_ssse3;
        dsp->avg_no_rnd_vc1_chroma_pixels_tab[0] = ff_avg_vc1_chroma_mc8_nornd_ssse3;
    }
    if (EXTERNAL_SSE4(cpu_flags)) {
        dsp->vc1_h_loop_filter8  = ff_vc1_h_loop_filter8_sse4;
        dsp->vc1_h_loop_filter16 = vc1_h_loop_filter16_sse4;
    }
#endif /* HAVE_YASM */
}