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
|
/*
* Copyright (c) 2014 The WebM project authors. All Rights Reserved.
*
* Use of this source code is governed by a BSD-style license
* that can be found in the LICENSE file in the root of the source
* tree. An additional intellectual property rights grant can be found
* in the file PATENTS. All contributing project authors may
* be found in the AUTHORS file in the root of the source tree.
*/
#include "./vpx_config.h"
#include "./vpx_dsp_rtcd.h"
#include "vpx_dsp/x86/convolve.h"
#if HAVE_SSE2
filter8_1dfunction vpx_filter_block1d16_v8_sse2;
filter8_1dfunction vpx_filter_block1d16_h8_sse2;
filter8_1dfunction vpx_filter_block1d8_v8_sse2;
filter8_1dfunction vpx_filter_block1d8_h8_sse2;
filter8_1dfunction vpx_filter_block1d4_v8_sse2;
filter8_1dfunction vpx_filter_block1d4_h8_sse2;
filter8_1dfunction vpx_filter_block1d16_v8_avg_sse2;
filter8_1dfunction vpx_filter_block1d16_h8_avg_sse2;
filter8_1dfunction vpx_filter_block1d8_v8_avg_sse2;
filter8_1dfunction vpx_filter_block1d8_h8_avg_sse2;
filter8_1dfunction vpx_filter_block1d4_v8_avg_sse2;
filter8_1dfunction vpx_filter_block1d4_h8_avg_sse2;
filter8_1dfunction vpx_filter_block1d16_v2_sse2;
filter8_1dfunction vpx_filter_block1d16_h2_sse2;
filter8_1dfunction vpx_filter_block1d8_v2_sse2;
filter8_1dfunction vpx_filter_block1d8_h2_sse2;
filter8_1dfunction vpx_filter_block1d4_v2_sse2;
filter8_1dfunction vpx_filter_block1d4_h2_sse2;
filter8_1dfunction vpx_filter_block1d16_v2_avg_sse2;
filter8_1dfunction vpx_filter_block1d16_h2_avg_sse2;
filter8_1dfunction vpx_filter_block1d8_v2_avg_sse2;
filter8_1dfunction vpx_filter_block1d8_h2_avg_sse2;
filter8_1dfunction vpx_filter_block1d4_v2_avg_sse2;
filter8_1dfunction vpx_filter_block1d4_h2_avg_sse2;
// void vpx_convolve8_horiz_sse2(const uint8_t *src, ptrdiff_t src_stride,
// uint8_t *dst, ptrdiff_t dst_stride,
// const int16_t *filter_x, int x_step_q4,
// const int16_t *filter_y, int y_step_q4,
// int w, int h);
// void vpx_convolve8_vert_sse2(const uint8_t *src, ptrdiff_t src_stride,
// uint8_t *dst, ptrdiff_t dst_stride,
// const int16_t *filter_x, int x_step_q4,
// const int16_t *filter_y, int y_step_q4,
// int w, int h);
// void vpx_convolve8_avg_horiz_sse2(const uint8_t *src, ptrdiff_t src_stride,
// uint8_t *dst, ptrdiff_t dst_stride,
// const int16_t *filter_x, int x_step_q4,
// const int16_t *filter_y, int y_step_q4,
// int w, int h);
// void vpx_convolve8_avg_vert_sse2(const uint8_t *src, ptrdiff_t src_stride,
// uint8_t *dst, ptrdiff_t dst_stride,
// const int16_t *filter_x, int x_step_q4,
// const int16_t *filter_y, int y_step_q4,
// int w, int h);
FUN_CONV_1D(horiz, x_step_q4, filter_x, h, src, , sse2);
FUN_CONV_1D(vert, y_step_q4, filter_y, v, src - src_stride * 3, , sse2);
FUN_CONV_1D(avg_horiz, x_step_q4, filter_x, h, src, avg_, sse2);
FUN_CONV_1D(avg_vert, y_step_q4, filter_y, v, src - src_stride * 3, avg_, sse2);
// void vpx_convolve8_sse2(const uint8_t *src, ptrdiff_t src_stride,
// uint8_t *dst, ptrdiff_t dst_stride,
// const int16_t *filter_x, int x_step_q4,
// const int16_t *filter_y, int y_step_q4,
// int w, int h);
// void vpx_convolve8_avg_sse2(const uint8_t *src, ptrdiff_t src_stride,
// uint8_t *dst, ptrdiff_t dst_stride,
// const int16_t *filter_x, int x_step_q4,
// const int16_t *filter_y, int y_step_q4,
// int w, int h);
FUN_CONV_2D(, sse2);
FUN_CONV_2D(avg_ , sse2);
#if CONFIG_VP9_HIGHBITDEPTH && ARCH_X86_64
highbd_filter8_1dfunction vpx_highbd_filter_block1d16_v8_sse2;
highbd_filter8_1dfunction vpx_highbd_filter_block1d16_h8_sse2;
highbd_filter8_1dfunction vpx_highbd_filter_block1d8_v8_sse2;
highbd_filter8_1dfunction vpx_highbd_filter_block1d8_h8_sse2;
highbd_filter8_1dfunction vpx_highbd_filter_block1d4_v8_sse2;
highbd_filter8_1dfunction vpx_highbd_filter_block1d4_h8_sse2;
highbd_filter8_1dfunction vpx_highbd_filter_block1d16_v8_avg_sse2;
highbd_filter8_1dfunction vpx_highbd_filter_block1d16_h8_avg_sse2;
highbd_filter8_1dfunction vpx_highbd_filter_block1d8_v8_avg_sse2;
highbd_filter8_1dfunction vpx_highbd_filter_block1d8_h8_avg_sse2;
highbd_filter8_1dfunction vpx_highbd_filter_block1d4_v8_avg_sse2;
highbd_filter8_1dfunction vpx_highbd_filter_block1d4_h8_avg_sse2;
highbd_filter8_1dfunction vpx_highbd_filter_block1d16_v2_sse2;
highbd_filter8_1dfunction vpx_highbd_filter_block1d16_h2_sse2;
highbd_filter8_1dfunction vpx_highbd_filter_block1d8_v2_sse2;
highbd_filter8_1dfunction vpx_highbd_filter_block1d8_h2_sse2;
highbd_filter8_1dfunction vpx_highbd_filter_block1d4_v2_sse2;
highbd_filter8_1dfunction vpx_highbd_filter_block1d4_h2_sse2;
highbd_filter8_1dfunction vpx_highbd_filter_block1d16_v2_avg_sse2;
highbd_filter8_1dfunction vpx_highbd_filter_block1d16_h2_avg_sse2;
highbd_filter8_1dfunction vpx_highbd_filter_block1d8_v2_avg_sse2;
highbd_filter8_1dfunction vpx_highbd_filter_block1d8_h2_avg_sse2;
highbd_filter8_1dfunction vpx_highbd_filter_block1d4_v2_avg_sse2;
highbd_filter8_1dfunction vpx_highbd_filter_block1d4_h2_avg_sse2;
// void vpx_highbd_convolve8_horiz_sse2(const uint8_t *src,
// ptrdiff_t src_stride,
// uint8_t *dst,
// ptrdiff_t dst_stride,
// const int16_t *filter_x,
// int x_step_q4,
// const int16_t *filter_y,
// int y_step_q4,
// int w, int h, int bd);
// void vpx_highbd_convolve8_vert_sse2(const uint8_t *src,
// ptrdiff_t src_stride,
// uint8_t *dst,
// ptrdiff_t dst_stride,
// const int16_t *filter_x,
// int x_step_q4,
// const int16_t *filter_y,
// int y_step_q4,
// int w, int h, int bd);
// void vpx_highbd_convolve8_avg_horiz_sse2(const uint8_t *src,
// ptrdiff_t src_stride,
// uint8_t *dst,
// ptrdiff_t dst_stride,
// const int16_t *filter_x,
// int x_step_q4,
// const int16_t *filter_y,
// int y_step_q4,
// int w, int h, int bd);
// void vpx_highbd_convolve8_avg_vert_sse2(const uint8_t *src,
// ptrdiff_t src_stride,
// uint8_t *dst,
// ptrdiff_t dst_stride,
// const int16_t *filter_x,
// int x_step_q4,
// const int16_t *filter_y,
// int y_step_q4,
// int w, int h, int bd);
HIGH_FUN_CONV_1D(horiz, x_step_q4, filter_x, h, src, , sse2);
HIGH_FUN_CONV_1D(vert, y_step_q4, filter_y, v, src - src_stride * 3, , sse2);
HIGH_FUN_CONV_1D(avg_horiz, x_step_q4, filter_x, h, src, avg_, sse2);
HIGH_FUN_CONV_1D(avg_vert, y_step_q4, filter_y, v, src - src_stride * 3, avg_,
sse2);
// void vpx_highbd_convolve8_sse2(const uint8_t *src, ptrdiff_t src_stride,
// uint8_t *dst, ptrdiff_t dst_stride,
// const int16_t *filter_x, int x_step_q4,
// const int16_t *filter_y, int y_step_q4,
// int w, int h, int bd);
// void vpx_highbd_convolve8_avg_sse2(const uint8_t *src, ptrdiff_t src_stride,
// uint8_t *dst, ptrdiff_t dst_stride,
// const int16_t *filter_x, int x_step_q4,
// const int16_t *filter_y, int y_step_q4,
// int w, int h, int bd);
HIGH_FUN_CONV_2D(, sse2);
HIGH_FUN_CONV_2D(avg_ , sse2);
#endif // CONFIG_VP9_HIGHBITDEPTH && ARCH_X86_64
#endif // HAVE_SSE2
|