/src/aom/aom_dsp/variance.c
Line | Count | Source (jump to first uncovered line) |
1 | | /* |
2 | | * Copyright (c) 2016, Alliance for Open Media. All rights reserved |
3 | | * |
4 | | * This source code is subject to the terms of the BSD 2 Clause License and |
5 | | * the Alliance for Open Media Patent License 1.0. If the BSD 2 Clause License |
6 | | * was not distributed with this source code in the LICENSE file, you can |
7 | | * obtain it at www.aomedia.org/license/software. If the Alliance for Open |
8 | | * Media Patent License 1.0 was not distributed with this source code in the |
9 | | * PATENTS file, you can obtain it at www.aomedia.org/license/patent. |
10 | | */ |
11 | | #include <assert.h> |
12 | | #include <stdlib.h> |
13 | | #include <string.h> |
14 | | |
15 | | #include "config/aom_config.h" |
16 | | #include "config/aom_dsp_rtcd.h" |
17 | | |
18 | | #include "aom/aom_integer.h" |
19 | | #include "aom_ports/mem.h" |
20 | | |
21 | | #include "aom_dsp/aom_filter.h" |
22 | | #include "aom_dsp/blend.h" |
23 | | #include "aom_dsp/variance.h" |
24 | | |
25 | | #include "av1/common/filter.h" |
26 | | #include "av1/common/reconinter.h" |
27 | | |
28 | | uint32_t aom_get4x4sse_cs_c(const uint8_t *a, int a_stride, const uint8_t *b, |
29 | 0 | int b_stride) { |
30 | 0 | int distortion = 0; |
31 | 0 | int r, c; |
32 | |
|
33 | 0 | for (r = 0; r < 4; ++r) { |
34 | 0 | for (c = 0; c < 4; ++c) { |
35 | 0 | int diff = a[c] - b[c]; |
36 | 0 | distortion += diff * diff; |
37 | 0 | } |
38 | |
|
39 | 0 | a += a_stride; |
40 | 0 | b += b_stride; |
41 | 0 | } |
42 | |
|
43 | 0 | return distortion; |
44 | 0 | } |
45 | | |
46 | 0 | uint32_t aom_get_mb_ss_c(const int16_t *a) { |
47 | 0 | unsigned int i, sum = 0; |
48 | |
|
49 | 0 | for (i = 0; i < 256; ++i) { |
50 | 0 | sum += a[i] * a[i]; |
51 | 0 | } |
52 | |
|
53 | 0 | return sum; |
54 | 0 | } |
55 | | |
56 | | static void variance(const uint8_t *a, int a_stride, const uint8_t *b, |
57 | 4.23M | int b_stride, int w, int h, uint32_t *sse, int *sum) { |
58 | 4.23M | int i, j; |
59 | | |
60 | 4.23M | *sum = 0; |
61 | 4.23M | *sse = 0; |
62 | | |
63 | 34.5M | for (i = 0; i < h; ++i) { |
64 | 466M | for (j = 0; j < w; ++j) { |
65 | 435M | const int diff = a[j] - b[j]; |
66 | 435M | *sum += diff; |
67 | 435M | *sse += diff * diff; |
68 | 435M | } |
69 | | |
70 | 30.3M | a += a_stride; |
71 | 30.3M | b += b_stride; |
72 | 30.3M | } |
73 | 4.23M | } |
74 | | |
75 | | uint32_t aom_sse_odd_size(const uint8_t *a, int a_stride, const uint8_t *b, |
76 | 18.6k | int b_stride, int w, int h) { |
77 | 18.6k | uint32_t sse; |
78 | 18.6k | int sum; |
79 | 18.6k | variance(a, a_stride, b, b_stride, w, h, &sse, &sum); |
80 | 18.6k | return sse; |
81 | 18.6k | } |
82 | | |
83 | | // Applies a 1-D 2-tap bilinear filter to the source block in either horizontal |
84 | | // or vertical direction to produce the filtered output block. Used to implement |
85 | | // the first-pass of 2-D separable filter. |
86 | | // |
87 | | // Produces int16_t output to retain precision for the next pass. Two filter |
88 | | // taps should sum to FILTER_WEIGHT. pixel_step defines whether the filter is |
89 | | // applied horizontally (pixel_step = 1) or vertically (pixel_step = stride). |
90 | | // It defines the offset required to move from one input to the next. |
91 | | void aom_var_filter_block2d_bil_first_pass_c(const uint8_t *a, uint16_t *b, |
92 | | unsigned int src_pixels_per_line, |
93 | | unsigned int pixel_step, |
94 | | unsigned int output_height, |
95 | | unsigned int output_width, |
96 | 0 | const uint8_t *filter) { |
97 | 0 | unsigned int i, j; |
98 | |
|
99 | 0 | for (i = 0; i < output_height; ++i) { |
100 | 0 | for (j = 0; j < output_width; ++j) { |
101 | 0 | b[j] = ROUND_POWER_OF_TWO( |
102 | 0 | (int)a[0] * filter[0] + (int)a[pixel_step] * filter[1], FILTER_BITS); |
103 | |
|
104 | 0 | ++a; |
105 | 0 | } |
106 | |
|
107 | 0 | a += src_pixels_per_line - output_width; |
108 | 0 | b += output_width; |
109 | 0 | } |
110 | 0 | } |
111 | | |
112 | | // Applies a 1-D 2-tap bilinear filter to the source block in either horizontal |
113 | | // or vertical direction to produce the filtered output block. Used to implement |
114 | | // the second-pass of 2-D separable filter. |
115 | | // |
116 | | // Requires 16-bit input as produced by filter_block2d_bil_first_pass. Two |
117 | | // filter taps should sum to FILTER_WEIGHT. pixel_step defines whether the |
118 | | // filter is applied horizontally (pixel_step = 1) or vertically |
119 | | // (pixel_step = stride). It defines the offset required to move from one input |
120 | | // to the next. Output is 8-bit. |
121 | | void aom_var_filter_block2d_bil_second_pass_c(const uint16_t *a, uint8_t *b, |
122 | | unsigned int src_pixels_per_line, |
123 | | unsigned int pixel_step, |
124 | | unsigned int output_height, |
125 | | unsigned int output_width, |
126 | 0 | const uint8_t *filter) { |
127 | 0 | unsigned int i, j; |
128 | |
|
129 | 0 | for (i = 0; i < output_height; ++i) { |
130 | 0 | for (j = 0; j < output_width; ++j) { |
131 | 0 | b[j] = ROUND_POWER_OF_TWO( |
132 | 0 | (int)a[0] * filter[0] + (int)a[pixel_step] * filter[1], FILTER_BITS); |
133 | 0 | ++a; |
134 | 0 | } |
135 | |
|
136 | 0 | a += src_pixels_per_line - output_width; |
137 | 0 | b += output_width; |
138 | 0 | } |
139 | 0 | } |
140 | | |
141 | | #define VAR(W, H) \ |
142 | | uint32_t aom_variance##W##x##H##_c(const uint8_t *a, int a_stride, \ |
143 | | const uint8_t *b, int b_stride, \ |
144 | 3.71M | uint32_t *sse) { \ |
145 | 3.71M | int sum; \ |
146 | 3.71M | variance(a, a_stride, b, b_stride, W, H, sse, &sum); \ |
147 | 3.71M | return *sse - (uint32_t)(((int64_t)sum * sum) / (W * H)); \ |
148 | 3.71M | } Unexecuted instantiation: aom_variance128x128_c Unexecuted instantiation: aom_variance128x64_c Unexecuted instantiation: aom_variance64x128_c Line | Count | Source | 144 | 32.8k | uint32_t *sse) { \ | 145 | 32.8k | int sum; \ | 146 | 32.8k | variance(a, a_stride, b, b_stride, W, H, sse, &sum); \ | 147 | 32.8k | return *sse - (uint32_t)(((int64_t)sum * sum) / (W * H)); \ | 148 | 32.8k | } |
Line | Count | Source | 144 | 3.16k | uint32_t *sse) { \ | 145 | 3.16k | int sum; \ | 146 | 3.16k | variance(a, a_stride, b, b_stride, W, H, sse, &sum); \ | 147 | 3.16k | return *sse - (uint32_t)(((int64_t)sum * sum) / (W * H)); \ | 148 | 3.16k | } |
Line | Count | Source | 144 | 2.78k | uint32_t *sse) { \ | 145 | 2.78k | int sum; \ | 146 | 2.78k | variance(a, a_stride, b, b_stride, W, H, sse, &sum); \ | 147 | 2.78k | return *sse - (uint32_t)(((int64_t)sum * sum) / (W * H)); \ | 148 | 2.78k | } |
Line | Count | Source | 144 | 24.7k | uint32_t *sse) { \ | 145 | 24.7k | int sum; \ | 146 | 24.7k | variance(a, a_stride, b, b_stride, W, H, sse, &sum); \ | 147 | 24.7k | return *sse - (uint32_t)(((int64_t)sum * sum) / (W * H)); \ | 148 | 24.7k | } |
Line | Count | Source | 144 | 7.91k | uint32_t *sse) { \ | 145 | 7.91k | int sum; \ | 146 | 7.91k | variance(a, a_stride, b, b_stride, W, H, sse, &sum); \ | 147 | 7.91k | return *sse - (uint32_t)(((int64_t)sum * sum) / (W * H)); \ | 148 | 7.91k | } |
Line | Count | Source | 144 | 7.52k | uint32_t *sse) { \ | 145 | 7.52k | int sum; \ | 146 | 7.52k | variance(a, a_stride, b, b_stride, W, H, sse, &sum); \ | 147 | 7.52k | return *sse - (uint32_t)(((int64_t)sum * sum) / (W * H)); \ | 148 | 7.52k | } |
Line | Count | Source | 144 | 38.4k | uint32_t *sse) { \ | 145 | 38.4k | int sum; \ | 146 | 38.4k | variance(a, a_stride, b, b_stride, W, H, sse, &sum); \ | 147 | 38.4k | return *sse - (uint32_t)(((int64_t)sum * sum) / (W * H)); \ | 148 | 38.4k | } |
Line | Count | Source | 144 | 18.8k | uint32_t *sse) { \ | 145 | 18.8k | int sum; \ | 146 | 18.8k | variance(a, a_stride, b, b_stride, W, H, sse, &sum); \ | 147 | 18.8k | return *sse - (uint32_t)(((int64_t)sum * sum) / (W * H)); \ | 148 | 18.8k | } |
Line | Count | Source | 144 | 18.3k | uint32_t *sse) { \ | 145 | 18.3k | int sum; \ | 146 | 18.3k | variance(a, a_stride, b, b_stride, W, H, sse, &sum); \ | 147 | 18.3k | return *sse - (uint32_t)(((int64_t)sum * sum) / (W * H)); \ | 148 | 18.3k | } |
Line | Count | Source | 144 | 533k | uint32_t *sse) { \ | 145 | 533k | int sum; \ | 146 | 533k | variance(a, a_stride, b, b_stride, W, H, sse, &sum); \ | 147 | 533k | return *sse - (uint32_t)(((int64_t)sum * sum) / (W * H)); \ | 148 | 533k | } |
Line | Count | Source | 144 | 13.6k | uint32_t *sse) { \ | 145 | 13.6k | int sum; \ | 146 | 13.6k | variance(a, a_stride, b, b_stride, W, H, sse, &sum); \ | 147 | 13.6k | return *sse - (uint32_t)(((int64_t)sum * sum) / (W * H)); \ | 148 | 13.6k | } |
Line | Count | Source | 144 | 11.3k | uint32_t *sse) { \ | 145 | 11.3k | int sum; \ | 146 | 11.3k | variance(a, a_stride, b, b_stride, W, H, sse, &sum); \ | 147 | 11.3k | return *sse - (uint32_t)(((int64_t)sum * sum) / (W * H)); \ | 148 | 11.3k | } |
Line | Count | Source | 144 | 2.95M | uint32_t *sse) { \ | 145 | 2.95M | int sum; \ | 146 | 2.95M | variance(a, a_stride, b, b_stride, W, H, sse, &sum); \ | 147 | 2.95M | return *sse - (uint32_t)(((int64_t)sum * sum) / (W * H)); \ | 148 | 2.95M | } |
Unexecuted instantiation: aom_variance4x2_c Unexecuted instantiation: aom_variance2x4_c Unexecuted instantiation: aom_variance2x2_c Line | Count | Source | 144 | 494 | uint32_t *sse) { \ | 145 | 494 | int sum; \ | 146 | 494 | variance(a, a_stride, b, b_stride, W, H, sse, &sum); \ | 147 | 494 | return *sse - (uint32_t)(((int64_t)sum * sum) / (W * H)); \ | 148 | 494 | } |
Unexecuted instantiation: aom_variance16x4_c Line | Count | Source | 144 | 21.7k | uint32_t *sse) { \ | 145 | 21.7k | int sum; \ | 146 | 21.7k | variance(a, a_stride, b, b_stride, W, H, sse, &sum); \ | 147 | 21.7k | return *sse - (uint32_t)(((int64_t)sum * sum) / (W * H)); \ | 148 | 21.7k | } |
Line | Count | Source | 144 | 21.6k | uint32_t *sse) { \ | 145 | 21.6k | int sum; \ | 146 | 21.6k | variance(a, a_stride, b, b_stride, W, H, sse, &sum); \ | 147 | 21.6k | return *sse - (uint32_t)(((int64_t)sum * sum) / (W * H)); \ | 148 | 21.6k | } |
Unexecuted instantiation: aom_variance16x64_c Unexecuted instantiation: aom_variance64x16_c |
149 | | |
150 | | #define SUBPIX_VAR(W, H) \ |
151 | | uint32_t aom_sub_pixel_variance##W##x##H##_c( \ |
152 | | const uint8_t *a, int a_stride, int xoffset, int yoffset, \ |
153 | 0 | const uint8_t *b, int b_stride, uint32_t *sse) { \ |
154 | 0 | uint16_t fdata3[(H + 1) * W]; \ |
155 | 0 | uint8_t temp2[H * W]; \ |
156 | 0 | \ |
157 | 0 | aom_var_filter_block2d_bil_first_pass_c(a, fdata3, a_stride, 1, H + 1, W, \ |
158 | 0 | bilinear_filters_2t[xoffset]); \ |
159 | 0 | aom_var_filter_block2d_bil_second_pass_c(fdata3, temp2, W, W, H, W, \ |
160 | 0 | bilinear_filters_2t[yoffset]); \ |
161 | 0 | \ |
162 | 0 | return aom_variance##W##x##H##_c(temp2, W, b, b_stride, sse); \ |
163 | 0 | } Unexecuted instantiation: aom_sub_pixel_variance128x128_c Unexecuted instantiation: aom_sub_pixel_variance128x64_c Unexecuted instantiation: aom_sub_pixel_variance64x128_c Unexecuted instantiation: aom_sub_pixel_variance64x64_c Unexecuted instantiation: aom_sub_pixel_variance64x32_c Unexecuted instantiation: aom_sub_pixel_variance32x64_c Unexecuted instantiation: aom_sub_pixel_variance32x32_c Unexecuted instantiation: aom_sub_pixel_variance32x16_c Unexecuted instantiation: aom_sub_pixel_variance16x32_c Unexecuted instantiation: aom_sub_pixel_variance16x16_c Unexecuted instantiation: aom_sub_pixel_variance16x8_c Unexecuted instantiation: aom_sub_pixel_variance8x16_c Unexecuted instantiation: aom_sub_pixel_variance8x8_c Unexecuted instantiation: aom_sub_pixel_variance8x4_c Unexecuted instantiation: aom_sub_pixel_variance4x8_c Unexecuted instantiation: aom_sub_pixel_variance4x4_c Unexecuted instantiation: aom_sub_pixel_variance4x2_c Unexecuted instantiation: aom_sub_pixel_variance2x4_c Unexecuted instantiation: aom_sub_pixel_variance2x2_c Unexecuted instantiation: aom_sub_pixel_variance4x16_c Unexecuted instantiation: aom_sub_pixel_variance16x4_c Unexecuted instantiation: aom_sub_pixel_variance8x32_c Unexecuted instantiation: aom_sub_pixel_variance32x8_c Unexecuted instantiation: aom_sub_pixel_variance16x64_c Unexecuted instantiation: aom_sub_pixel_variance64x16_c |
164 | | |
165 | | #define SUBPIX_AVG_VAR(W, H) \ |
166 | | uint32_t aom_sub_pixel_avg_variance##W##x##H##_c( \ |
167 | | const uint8_t *a, int a_stride, int xoffset, int yoffset, \ |
168 | | const uint8_t *b, int b_stride, uint32_t *sse, \ |
169 | 0 | const uint8_t *second_pred) { \ |
170 | 0 | uint16_t fdata3[(H + 1) * W]; \ |
171 | 0 | uint8_t temp2[H * W]; \ |
172 | 0 | DECLARE_ALIGNED(16, uint8_t, temp3[H * W]); \ |
173 | 0 | \ |
174 | 0 | aom_var_filter_block2d_bil_first_pass_c(a, fdata3, a_stride, 1, H + 1, W, \ |
175 | 0 | bilinear_filters_2t[xoffset]); \ |
176 | 0 | aom_var_filter_block2d_bil_second_pass_c(fdata3, temp2, W, W, H, W, \ |
177 | 0 | bilinear_filters_2t[yoffset]); \ |
178 | 0 | \ |
179 | 0 | aom_comp_avg_pred(temp3, second_pred, W, H, temp2, W); \ |
180 | 0 | \ |
181 | 0 | return aom_variance##W##x##H##_c(temp3, W, b, b_stride, sse); \ |
182 | 0 | } \ Unexecuted instantiation: aom_sub_pixel_avg_variance128x128_c Unexecuted instantiation: aom_sub_pixel_avg_variance128x64_c Unexecuted instantiation: aom_sub_pixel_avg_variance64x128_c Unexecuted instantiation: aom_sub_pixel_avg_variance64x64_c Unexecuted instantiation: aom_sub_pixel_avg_variance64x32_c Unexecuted instantiation: aom_sub_pixel_avg_variance32x64_c Unexecuted instantiation: aom_sub_pixel_avg_variance32x32_c Unexecuted instantiation: aom_sub_pixel_avg_variance32x16_c Unexecuted instantiation: aom_sub_pixel_avg_variance16x32_c Unexecuted instantiation: aom_sub_pixel_avg_variance16x16_c Unexecuted instantiation: aom_sub_pixel_avg_variance16x8_c Unexecuted instantiation: aom_sub_pixel_avg_variance8x16_c Unexecuted instantiation: aom_sub_pixel_avg_variance8x8_c Unexecuted instantiation: aom_sub_pixel_avg_variance8x4_c Unexecuted instantiation: aom_sub_pixel_avg_variance4x8_c Unexecuted instantiation: aom_sub_pixel_avg_variance4x4_c Unexecuted instantiation: aom_sub_pixel_avg_variance4x2_c Unexecuted instantiation: aom_sub_pixel_avg_variance2x4_c Unexecuted instantiation: aom_sub_pixel_avg_variance2x2_c Unexecuted instantiation: aom_sub_pixel_avg_variance4x16_c Unexecuted instantiation: aom_sub_pixel_avg_variance16x4_c Unexecuted instantiation: aom_sub_pixel_avg_variance8x32_c Unexecuted instantiation: aom_sub_pixel_avg_variance32x8_c Unexecuted instantiation: aom_sub_pixel_avg_variance16x64_c Unexecuted instantiation: aom_sub_pixel_avg_variance64x16_c |
183 | | uint32_t aom_dist_wtd_sub_pixel_avg_variance##W##x##H##_c( \ |
184 | | const uint8_t *a, int a_stride, int xoffset, int yoffset, \ |
185 | | const uint8_t *b, int b_stride, uint32_t *sse, \ |
186 | 0 | const uint8_t *second_pred, const DIST_WTD_COMP_PARAMS *jcp_param) { \ |
187 | 0 | uint16_t fdata3[(H + 1) * W]; \ |
188 | 0 | uint8_t temp2[H * W]; \ |
189 | 0 | DECLARE_ALIGNED(16, uint8_t, temp3[H * W]); \ |
190 | 0 | \ |
191 | 0 | aom_var_filter_block2d_bil_first_pass_c(a, fdata3, a_stride, 1, H + 1, W, \ |
192 | 0 | bilinear_filters_2t[xoffset]); \ |
193 | 0 | aom_var_filter_block2d_bil_second_pass_c(fdata3, temp2, W, W, H, W, \ |
194 | 0 | bilinear_filters_2t[yoffset]); \ |
195 | 0 | \ |
196 | 0 | aom_dist_wtd_comp_avg_pred(temp3, second_pred, W, H, temp2, W, jcp_param); \ |
197 | 0 | \ |
198 | 0 | return aom_variance##W##x##H(temp3, W, b, b_stride, sse); \ |
199 | 0 | } Unexecuted instantiation: aom_dist_wtd_sub_pixel_avg_variance128x128_c Unexecuted instantiation: aom_dist_wtd_sub_pixel_avg_variance128x64_c Unexecuted instantiation: aom_dist_wtd_sub_pixel_avg_variance64x128_c Unexecuted instantiation: aom_dist_wtd_sub_pixel_avg_variance64x64_c Unexecuted instantiation: aom_dist_wtd_sub_pixel_avg_variance64x32_c Unexecuted instantiation: aom_dist_wtd_sub_pixel_avg_variance32x64_c Unexecuted instantiation: aom_dist_wtd_sub_pixel_avg_variance32x32_c Unexecuted instantiation: aom_dist_wtd_sub_pixel_avg_variance32x16_c Unexecuted instantiation: aom_dist_wtd_sub_pixel_avg_variance16x32_c Unexecuted instantiation: aom_dist_wtd_sub_pixel_avg_variance16x16_c Unexecuted instantiation: aom_dist_wtd_sub_pixel_avg_variance16x8_c Unexecuted instantiation: aom_dist_wtd_sub_pixel_avg_variance8x16_c Unexecuted instantiation: aom_dist_wtd_sub_pixel_avg_variance8x8_c Unexecuted instantiation: aom_dist_wtd_sub_pixel_avg_variance8x4_c Unexecuted instantiation: aom_dist_wtd_sub_pixel_avg_variance4x8_c Unexecuted instantiation: aom_dist_wtd_sub_pixel_avg_variance4x4_c Unexecuted instantiation: aom_dist_wtd_sub_pixel_avg_variance4x2_c Unexecuted instantiation: aom_dist_wtd_sub_pixel_avg_variance2x4_c Unexecuted instantiation: aom_dist_wtd_sub_pixel_avg_variance2x2_c Unexecuted instantiation: aom_dist_wtd_sub_pixel_avg_variance4x16_c Unexecuted instantiation: aom_dist_wtd_sub_pixel_avg_variance16x4_c Unexecuted instantiation: aom_dist_wtd_sub_pixel_avg_variance8x32_c Unexecuted instantiation: aom_dist_wtd_sub_pixel_avg_variance32x8_c Unexecuted instantiation: aom_dist_wtd_sub_pixel_avg_variance16x64_c Unexecuted instantiation: aom_dist_wtd_sub_pixel_avg_variance64x16_c |
200 | | |
201 | | /* Identical to the variance call except it takes an additional parameter, sum, |
202 | | * and returns that value using pass-by-reference instead of returning |
203 | | * sse - sum^2 / w*h |
204 | | */ |
205 | | #define GET_VAR(W, H) \ |
206 | | void aom_get##W##x##H##var_c(const uint8_t *a, int a_stride, \ |
207 | | const uint8_t *b, int b_stride, uint32_t *sse, \ |
208 | 0 | int *sum) { \ |
209 | 0 | variance(a, a_stride, b, b_stride, W, H, sse, sum); \ |
210 | 0 | } Unexecuted instantiation: aom_get16x16var_c Unexecuted instantiation: aom_get8x8var_c |
211 | | |
212 | | /* Identical to the variance call except it does not calculate the |
213 | | * sse - sum^2 / w*h and returns sse in addtion to modifying the passed in |
214 | | * variable. |
215 | | */ |
216 | | #define MSE(W, H) \ |
217 | | uint32_t aom_mse##W##x##H##_c(const uint8_t *a, int a_stride, \ |
218 | | const uint8_t *b, int b_stride, \ |
219 | 498k | uint32_t *sse) { \ |
220 | 498k | int sum; \ |
221 | 498k | variance(a, a_stride, b, b_stride, W, H, sse, &sum); \ |
222 | 498k | return *sse; \ |
223 | 498k | } Line | Count | Source | 219 | 498k | uint32_t *sse) { \ | 220 | 498k | int sum; \ | 221 | 498k | variance(a, a_stride, b, b_stride, W, H, sse, &sum); \ | 222 | 498k | return *sse; \ | 223 | 498k | } |
Unexecuted instantiation: aom_mse16x8_c Unexecuted instantiation: aom_mse8x16_c Unexecuted instantiation: aom_mse8x8_c |
224 | | |
225 | | /* All three forms of the variance are available in the same sizes. */ |
226 | | #define VARIANCES(W, H) \ |
227 | | VAR(W, H) \ |
228 | | SUBPIX_VAR(W, H) \ |
229 | | SUBPIX_AVG_VAR(W, H) |
230 | | |
231 | | VARIANCES(128, 128) |
232 | | VARIANCES(128, 64) |
233 | | VARIANCES(64, 128) |
234 | | VARIANCES(64, 64) |
235 | | VARIANCES(64, 32) |
236 | | VARIANCES(32, 64) |
237 | | VARIANCES(32, 32) |
238 | | VARIANCES(32, 16) |
239 | | VARIANCES(16, 32) |
240 | | VARIANCES(16, 16) |
241 | | VARIANCES(16, 8) |
242 | | VARIANCES(8, 16) |
243 | | VARIANCES(8, 8) |
244 | | VARIANCES(8, 4) |
245 | | VARIANCES(4, 8) |
246 | | VARIANCES(4, 4) |
247 | | VARIANCES(4, 2) |
248 | | VARIANCES(2, 4) |
249 | | VARIANCES(2, 2) |
250 | | |
251 | | // Realtime mode doesn't use rectangular blocks. |
252 | | #if !CONFIG_REALTIME_ONLY |
253 | | VARIANCES(4, 16) |
254 | | VARIANCES(16, 4) |
255 | | VARIANCES(8, 32) |
256 | | VARIANCES(32, 8) |
257 | | VARIANCES(16, 64) |
258 | | VARIANCES(64, 16) |
259 | | #endif |
260 | | |
261 | | GET_VAR(16, 16) |
262 | | GET_VAR(8, 8) |
263 | | |
264 | | MSE(16, 16) |
265 | | MSE(16, 8) |
266 | | MSE(8, 16) |
267 | | MSE(8, 8) |
268 | | |
269 | | void aom_comp_avg_pred_c(uint8_t *comp_pred, const uint8_t *pred, int width, |
270 | 0 | int height, const uint8_t *ref, int ref_stride) { |
271 | 0 | int i, j; |
272 | |
|
273 | 0 | for (i = 0; i < height; ++i) { |
274 | 0 | for (j = 0; j < width; ++j) { |
275 | 0 | const int tmp = pred[j] + ref[j]; |
276 | 0 | comp_pred[j] = ROUND_POWER_OF_TWO(tmp, 1); |
277 | 0 | } |
278 | 0 | comp_pred += width; |
279 | 0 | pred += width; |
280 | 0 | ref += ref_stride; |
281 | 0 | } |
282 | 0 | } |
283 | | |
284 | | void aom_dist_wtd_comp_avg_pred_c(uint8_t *comp_pred, const uint8_t *pred, |
285 | | int width, int height, const uint8_t *ref, |
286 | | int ref_stride, |
287 | 0 | const DIST_WTD_COMP_PARAMS *jcp_param) { |
288 | 0 | int i, j; |
289 | 0 | const int fwd_offset = jcp_param->fwd_offset; |
290 | 0 | const int bck_offset = jcp_param->bck_offset; |
291 | |
|
292 | 0 | for (i = 0; i < height; ++i) { |
293 | 0 | for (j = 0; j < width; ++j) { |
294 | 0 | int tmp = pred[j] * bck_offset + ref[j] * fwd_offset; |
295 | 0 | tmp = ROUND_POWER_OF_TWO(tmp, DIST_PRECISION_BITS); |
296 | 0 | comp_pred[j] = (uint8_t)tmp; |
297 | 0 | } |
298 | 0 | comp_pred += width; |
299 | 0 | pred += width; |
300 | 0 | ref += ref_stride; |
301 | 0 | } |
302 | 0 | } |
303 | | |
304 | | #if CONFIG_AV1_HIGHBITDEPTH |
305 | | static void highbd_variance64(const uint8_t *a8, int a_stride, |
306 | | const uint8_t *b8, int b_stride, int w, int h, |
307 | 0 | uint64_t *sse, int64_t *sum) { |
308 | 0 | const uint16_t *a = CONVERT_TO_SHORTPTR(a8); |
309 | 0 | const uint16_t *b = CONVERT_TO_SHORTPTR(b8); |
310 | 0 | int64_t tsum = 0; |
311 | 0 | uint64_t tsse = 0; |
312 | 0 | for (int i = 0; i < h; ++i) { |
313 | 0 | int32_t lsum = 0; |
314 | 0 | for (int j = 0; j < w; ++j) { |
315 | 0 | const int diff = a[j] - b[j]; |
316 | 0 | lsum += diff; |
317 | 0 | tsse += (uint32_t)(diff * diff); |
318 | 0 | } |
319 | 0 | tsum += lsum; |
320 | 0 | a += a_stride; |
321 | 0 | b += b_stride; |
322 | 0 | } |
323 | 0 | *sum = tsum; |
324 | 0 | *sse = tsse; |
325 | 0 | } |
326 | | |
327 | | uint64_t aom_highbd_sse_odd_size(const uint8_t *a, int a_stride, |
328 | 0 | const uint8_t *b, int b_stride, int w, int h) { |
329 | 0 | uint64_t sse; |
330 | 0 | int64_t sum; |
331 | 0 | highbd_variance64(a, a_stride, b, b_stride, w, h, &sse, &sum); |
332 | 0 | return sse; |
333 | 0 | } |
334 | | |
335 | | static void highbd_8_variance(const uint8_t *a8, int a_stride, |
336 | | const uint8_t *b8, int b_stride, int w, int h, |
337 | 0 | uint32_t *sse, int *sum) { |
338 | 0 | uint64_t sse_long = 0; |
339 | 0 | int64_t sum_long = 0; |
340 | 0 | highbd_variance64(a8, a_stride, b8, b_stride, w, h, &sse_long, &sum_long); |
341 | 0 | *sse = (uint32_t)sse_long; |
342 | 0 | *sum = (int)sum_long; |
343 | 0 | } |
344 | | |
345 | | static void highbd_10_variance(const uint8_t *a8, int a_stride, |
346 | | const uint8_t *b8, int b_stride, int w, int h, |
347 | 0 | uint32_t *sse, int *sum) { |
348 | 0 | uint64_t sse_long = 0; |
349 | 0 | int64_t sum_long = 0; |
350 | 0 | highbd_variance64(a8, a_stride, b8, b_stride, w, h, &sse_long, &sum_long); |
351 | 0 | *sse = (uint32_t)ROUND_POWER_OF_TWO(sse_long, 4); |
352 | 0 | *sum = (int)ROUND_POWER_OF_TWO(sum_long, 2); |
353 | 0 | } |
354 | | |
355 | | static void highbd_12_variance(const uint8_t *a8, int a_stride, |
356 | | const uint8_t *b8, int b_stride, int w, int h, |
357 | 0 | uint32_t *sse, int *sum) { |
358 | 0 | uint64_t sse_long = 0; |
359 | 0 | int64_t sum_long = 0; |
360 | 0 | highbd_variance64(a8, a_stride, b8, b_stride, w, h, &sse_long, &sum_long); |
361 | 0 | *sse = (uint32_t)ROUND_POWER_OF_TWO(sse_long, 8); |
362 | 0 | *sum = (int)ROUND_POWER_OF_TWO(sum_long, 4); |
363 | 0 | } |
364 | | |
365 | | #define HIGHBD_VAR(W, H) \ |
366 | | uint32_t aom_highbd_8_variance##W##x##H##_c(const uint8_t *a, int a_stride, \ |
367 | | const uint8_t *b, int b_stride, \ |
368 | 0 | uint32_t *sse) { \ |
369 | 0 | int sum; \ |
370 | 0 | highbd_8_variance(a, a_stride, b, b_stride, W, H, sse, &sum); \ |
371 | 0 | return *sse - (uint32_t)(((int64_t)sum * sum) / (W * H)); \ |
372 | 0 | } \ Unexecuted instantiation: aom_highbd_8_variance128x128_c Unexecuted instantiation: aom_highbd_8_variance128x64_c Unexecuted instantiation: aom_highbd_8_variance64x128_c Unexecuted instantiation: aom_highbd_8_variance64x64_c Unexecuted instantiation: aom_highbd_8_variance64x32_c Unexecuted instantiation: aom_highbd_8_variance32x64_c Unexecuted instantiation: aom_highbd_8_variance32x32_c Unexecuted instantiation: aom_highbd_8_variance32x16_c Unexecuted instantiation: aom_highbd_8_variance16x32_c Unexecuted instantiation: aom_highbd_8_variance16x16_c Unexecuted instantiation: aom_highbd_8_variance16x8_c Unexecuted instantiation: aom_highbd_8_variance8x16_c Unexecuted instantiation: aom_highbd_8_variance8x8_c Unexecuted instantiation: aom_highbd_8_variance8x4_c Unexecuted instantiation: aom_highbd_8_variance4x8_c Unexecuted instantiation: aom_highbd_8_variance4x4_c Unexecuted instantiation: aom_highbd_8_variance4x2_c Unexecuted instantiation: aom_highbd_8_variance2x4_c Unexecuted instantiation: aom_highbd_8_variance2x2_c Unexecuted instantiation: aom_highbd_8_variance4x16_c Unexecuted instantiation: aom_highbd_8_variance16x4_c Unexecuted instantiation: aom_highbd_8_variance8x32_c Unexecuted instantiation: aom_highbd_8_variance32x8_c Unexecuted instantiation: aom_highbd_8_variance16x64_c Unexecuted instantiation: aom_highbd_8_variance64x16_c |
373 | | \ |
374 | | uint32_t aom_highbd_10_variance##W##x##H##_c(const uint8_t *a, int a_stride, \ |
375 | | const uint8_t *b, int b_stride, \ |
376 | 0 | uint32_t *sse) { \ |
377 | 0 | int sum; \ |
378 | 0 | int64_t var; \ |
379 | 0 | highbd_10_variance(a, a_stride, b, b_stride, W, H, sse, &sum); \ |
380 | 0 | var = (int64_t)(*sse) - (((int64_t)sum * sum) / (W * H)); \ |
381 | 0 | return (var >= 0) ? (uint32_t)var : 0; \ |
382 | 0 | } \ Unexecuted instantiation: aom_highbd_10_variance128x128_c Unexecuted instantiation: aom_highbd_10_variance128x64_c Unexecuted instantiation: aom_highbd_10_variance64x128_c Unexecuted instantiation: aom_highbd_10_variance64x64_c Unexecuted instantiation: aom_highbd_10_variance64x32_c Unexecuted instantiation: aom_highbd_10_variance32x64_c Unexecuted instantiation: aom_highbd_10_variance32x32_c Unexecuted instantiation: aom_highbd_10_variance32x16_c Unexecuted instantiation: aom_highbd_10_variance16x32_c Unexecuted instantiation: aom_highbd_10_variance16x16_c Unexecuted instantiation: aom_highbd_10_variance16x8_c Unexecuted instantiation: aom_highbd_10_variance8x16_c Unexecuted instantiation: aom_highbd_10_variance8x8_c Unexecuted instantiation: aom_highbd_10_variance8x4_c Unexecuted instantiation: aom_highbd_10_variance4x8_c Unexecuted instantiation: aom_highbd_10_variance4x4_c Unexecuted instantiation: aom_highbd_10_variance4x2_c Unexecuted instantiation: aom_highbd_10_variance2x4_c Unexecuted instantiation: aom_highbd_10_variance2x2_c Unexecuted instantiation: aom_highbd_10_variance4x16_c Unexecuted instantiation: aom_highbd_10_variance16x4_c Unexecuted instantiation: aom_highbd_10_variance8x32_c Unexecuted instantiation: aom_highbd_10_variance32x8_c Unexecuted instantiation: aom_highbd_10_variance16x64_c Unexecuted instantiation: aom_highbd_10_variance64x16_c |
383 | | \ |
384 | | uint32_t aom_highbd_12_variance##W##x##H##_c(const uint8_t *a, int a_stride, \ |
385 | | const uint8_t *b, int b_stride, \ |
386 | 0 | uint32_t *sse) { \ |
387 | 0 | int sum; \ |
388 | 0 | int64_t var; \ |
389 | 0 | highbd_12_variance(a, a_stride, b, b_stride, W, H, sse, &sum); \ |
390 | 0 | var = (int64_t)(*sse) - (((int64_t)sum * sum) / (W * H)); \ |
391 | 0 | return (var >= 0) ? (uint32_t)var : 0; \ |
392 | 0 | } Unexecuted instantiation: aom_highbd_12_variance128x128_c Unexecuted instantiation: aom_highbd_12_variance128x64_c Unexecuted instantiation: aom_highbd_12_variance64x128_c Unexecuted instantiation: aom_highbd_12_variance64x64_c Unexecuted instantiation: aom_highbd_12_variance64x32_c Unexecuted instantiation: aom_highbd_12_variance32x64_c Unexecuted instantiation: aom_highbd_12_variance32x32_c Unexecuted instantiation: aom_highbd_12_variance32x16_c Unexecuted instantiation: aom_highbd_12_variance16x32_c Unexecuted instantiation: aom_highbd_12_variance16x16_c Unexecuted instantiation: aom_highbd_12_variance16x8_c Unexecuted instantiation: aom_highbd_12_variance8x16_c Unexecuted instantiation: aom_highbd_12_variance8x8_c Unexecuted instantiation: aom_highbd_12_variance8x4_c Unexecuted instantiation: aom_highbd_12_variance4x8_c Unexecuted instantiation: aom_highbd_12_variance4x4_c Unexecuted instantiation: aom_highbd_12_variance4x2_c Unexecuted instantiation: aom_highbd_12_variance2x4_c Unexecuted instantiation: aom_highbd_12_variance2x2_c Unexecuted instantiation: aom_highbd_12_variance4x16_c Unexecuted instantiation: aom_highbd_12_variance16x4_c Unexecuted instantiation: aom_highbd_12_variance8x32_c Unexecuted instantiation: aom_highbd_12_variance32x8_c Unexecuted instantiation: aom_highbd_12_variance16x64_c Unexecuted instantiation: aom_highbd_12_variance64x16_c |
393 | | |
394 | | #define HIGHBD_GET_VAR(S) \ |
395 | | void aom_highbd_8_get##S##x##S##var_c(const uint8_t *src, int src_stride, \ |
396 | | const uint8_t *ref, int ref_stride, \ |
397 | 0 | uint32_t *sse, int *sum) { \ |
398 | 0 | highbd_8_variance(src, src_stride, ref, ref_stride, S, S, sse, sum); \ |
399 | 0 | } \ Unexecuted instantiation: aom_highbd_8_get8x8var_c Unexecuted instantiation: aom_highbd_8_get16x16var_c |
400 | | \ |
401 | | void aom_highbd_10_get##S##x##S##var_c(const uint8_t *src, int src_stride, \ |
402 | | const uint8_t *ref, int ref_stride, \ |
403 | 0 | uint32_t *sse, int *sum) { \ |
404 | 0 | highbd_10_variance(src, src_stride, ref, ref_stride, S, S, sse, sum); \ |
405 | 0 | } \ Unexecuted instantiation: aom_highbd_10_get8x8var_c Unexecuted instantiation: aom_highbd_10_get16x16var_c |
406 | | \ |
407 | | void aom_highbd_12_get##S##x##S##var_c(const uint8_t *src, int src_stride, \ |
408 | | const uint8_t *ref, int ref_stride, \ |
409 | 0 | uint32_t *sse, int *sum) { \ |
410 | 0 | highbd_12_variance(src, src_stride, ref, ref_stride, S, S, sse, sum); \ |
411 | 0 | } Unexecuted instantiation: aom_highbd_12_get8x8var_c Unexecuted instantiation: aom_highbd_12_get16x16var_c |
412 | | |
413 | | #define HIGHBD_MSE(W, H) \ |
414 | | uint32_t aom_highbd_8_mse##W##x##H##_c(const uint8_t *src, int src_stride, \ |
415 | | const uint8_t *ref, int ref_stride, \ |
416 | 0 | uint32_t *sse) { \ |
417 | 0 | int sum; \ |
418 | 0 | highbd_8_variance(src, src_stride, ref, ref_stride, W, H, sse, &sum); \ |
419 | 0 | return *sse; \ |
420 | 0 | } \ Unexecuted instantiation: aom_highbd_8_mse16x16_c Unexecuted instantiation: aom_highbd_8_mse16x8_c Unexecuted instantiation: aom_highbd_8_mse8x16_c Unexecuted instantiation: aom_highbd_8_mse8x8_c |
421 | | \ |
422 | | uint32_t aom_highbd_10_mse##W##x##H##_c(const uint8_t *src, int src_stride, \ |
423 | | const uint8_t *ref, int ref_stride, \ |
424 | 0 | uint32_t *sse) { \ |
425 | 0 | int sum; \ |
426 | 0 | highbd_10_variance(src, src_stride, ref, ref_stride, W, H, sse, &sum); \ |
427 | 0 | return *sse; \ |
428 | 0 | } \ Unexecuted instantiation: aom_highbd_10_mse16x16_c Unexecuted instantiation: aom_highbd_10_mse16x8_c Unexecuted instantiation: aom_highbd_10_mse8x16_c Unexecuted instantiation: aom_highbd_10_mse8x8_c |
429 | | \ |
430 | | uint32_t aom_highbd_12_mse##W##x##H##_c(const uint8_t *src, int src_stride, \ |
431 | | const uint8_t *ref, int ref_stride, \ |
432 | 0 | uint32_t *sse) { \ |
433 | 0 | int sum; \ |
434 | 0 | highbd_12_variance(src, src_stride, ref, ref_stride, W, H, sse, &sum); \ |
435 | 0 | return *sse; \ |
436 | 0 | } Unexecuted instantiation: aom_highbd_12_mse16x16_c Unexecuted instantiation: aom_highbd_12_mse16x8_c Unexecuted instantiation: aom_highbd_12_mse8x16_c Unexecuted instantiation: aom_highbd_12_mse8x8_c |
437 | | |
438 | | void aom_highbd_var_filter_block2d_bil_first_pass( |
439 | | const uint8_t *src_ptr8, uint16_t *output_ptr, |
440 | | unsigned int src_pixels_per_line, int pixel_step, |
441 | | unsigned int output_height, unsigned int output_width, |
442 | 0 | const uint8_t *filter) { |
443 | 0 | unsigned int i, j; |
444 | 0 | uint16_t *src_ptr = CONVERT_TO_SHORTPTR(src_ptr8); |
445 | 0 | for (i = 0; i < output_height; ++i) { |
446 | 0 | for (j = 0; j < output_width; ++j) { |
447 | 0 | output_ptr[j] = ROUND_POWER_OF_TWO( |
448 | 0 | (int)src_ptr[0] * filter[0] + (int)src_ptr[pixel_step] * filter[1], |
449 | 0 | FILTER_BITS); |
450 | |
|
451 | 0 | ++src_ptr; |
452 | 0 | } |
453 | | |
454 | | // Next row... |
455 | 0 | src_ptr += src_pixels_per_line - output_width; |
456 | 0 | output_ptr += output_width; |
457 | 0 | } |
458 | 0 | } |
459 | | |
460 | | void aom_highbd_var_filter_block2d_bil_second_pass( |
461 | | const uint16_t *src_ptr, uint16_t *output_ptr, |
462 | | unsigned int src_pixels_per_line, unsigned int pixel_step, |
463 | | unsigned int output_height, unsigned int output_width, |
464 | 0 | const uint8_t *filter) { |
465 | 0 | unsigned int i, j; |
466 | |
|
467 | 0 | for (i = 0; i < output_height; ++i) { |
468 | 0 | for (j = 0; j < output_width; ++j) { |
469 | 0 | output_ptr[j] = ROUND_POWER_OF_TWO( |
470 | 0 | (int)src_ptr[0] * filter[0] + (int)src_ptr[pixel_step] * filter[1], |
471 | 0 | FILTER_BITS); |
472 | 0 | ++src_ptr; |
473 | 0 | } |
474 | |
|
475 | 0 | src_ptr += src_pixels_per_line - output_width; |
476 | 0 | output_ptr += output_width; |
477 | 0 | } |
478 | 0 | } |
479 | | |
480 | | #define HIGHBD_SUBPIX_VAR(W, H) \ |
481 | | uint32_t aom_highbd_8_sub_pixel_variance##W##x##H##_c( \ |
482 | | const uint8_t *src, int src_stride, int xoffset, int yoffset, \ |
483 | 0 | const uint8_t *dst, int dst_stride, uint32_t *sse) { \ |
484 | 0 | uint16_t fdata3[(H + 1) * W]; \ |
485 | 0 | uint16_t temp2[H * W]; \ |
486 | 0 | \ |
487 | 0 | aom_highbd_var_filter_block2d_bil_first_pass( \ |
488 | 0 | src, fdata3, src_stride, 1, H + 1, W, bilinear_filters_2t[xoffset]); \ |
489 | 0 | aom_highbd_var_filter_block2d_bil_second_pass( \ |
490 | 0 | fdata3, temp2, W, W, H, W, bilinear_filters_2t[yoffset]); \ |
491 | 0 | \ |
492 | 0 | return aom_highbd_8_variance##W##x##H##_c(CONVERT_TO_BYTEPTR(temp2), W, \ |
493 | 0 | dst, dst_stride, sse); \ |
494 | 0 | } \ Unexecuted instantiation: aom_highbd_8_sub_pixel_variance128x128_c Unexecuted instantiation: aom_highbd_8_sub_pixel_variance128x64_c Unexecuted instantiation: aom_highbd_8_sub_pixel_variance64x128_c Unexecuted instantiation: aom_highbd_8_sub_pixel_variance64x64_c Unexecuted instantiation: aom_highbd_8_sub_pixel_variance64x32_c Unexecuted instantiation: aom_highbd_8_sub_pixel_variance32x64_c Unexecuted instantiation: aom_highbd_8_sub_pixel_variance32x32_c Unexecuted instantiation: aom_highbd_8_sub_pixel_variance32x16_c Unexecuted instantiation: aom_highbd_8_sub_pixel_variance16x32_c Unexecuted instantiation: aom_highbd_8_sub_pixel_variance16x16_c Unexecuted instantiation: aom_highbd_8_sub_pixel_variance16x8_c Unexecuted instantiation: aom_highbd_8_sub_pixel_variance8x16_c Unexecuted instantiation: aom_highbd_8_sub_pixel_variance8x8_c Unexecuted instantiation: aom_highbd_8_sub_pixel_variance8x4_c Unexecuted instantiation: aom_highbd_8_sub_pixel_variance4x8_c Unexecuted instantiation: aom_highbd_8_sub_pixel_variance4x4_c Unexecuted instantiation: aom_highbd_8_sub_pixel_variance4x2_c Unexecuted instantiation: aom_highbd_8_sub_pixel_variance2x4_c Unexecuted instantiation: aom_highbd_8_sub_pixel_variance2x2_c Unexecuted instantiation: aom_highbd_8_sub_pixel_variance4x16_c Unexecuted instantiation: aom_highbd_8_sub_pixel_variance16x4_c Unexecuted instantiation: aom_highbd_8_sub_pixel_variance8x32_c Unexecuted instantiation: aom_highbd_8_sub_pixel_variance32x8_c Unexecuted instantiation: aom_highbd_8_sub_pixel_variance16x64_c Unexecuted instantiation: aom_highbd_8_sub_pixel_variance64x16_c |
495 | | \ |
496 | | uint32_t aom_highbd_10_sub_pixel_variance##W##x##H##_c( \ |
497 | | const uint8_t *src, int src_stride, int xoffset, int yoffset, \ |
498 | 0 | const uint8_t *dst, int dst_stride, uint32_t *sse) { \ |
499 | 0 | uint16_t fdata3[(H + 1) * W]; \ |
500 | 0 | uint16_t temp2[H * W]; \ |
501 | 0 | \ |
502 | 0 | aom_highbd_var_filter_block2d_bil_first_pass( \ |
503 | 0 | src, fdata3, src_stride, 1, H + 1, W, bilinear_filters_2t[xoffset]); \ |
504 | 0 | aom_highbd_var_filter_block2d_bil_second_pass( \ |
505 | 0 | fdata3, temp2, W, W, H, W, bilinear_filters_2t[yoffset]); \ |
506 | 0 | \ |
507 | 0 | return aom_highbd_10_variance##W##x##H##_c(CONVERT_TO_BYTEPTR(temp2), W, \ |
508 | 0 | dst, dst_stride, sse); \ |
509 | 0 | } \ Unexecuted instantiation: aom_highbd_10_sub_pixel_variance128x128_c Unexecuted instantiation: aom_highbd_10_sub_pixel_variance128x64_c Unexecuted instantiation: aom_highbd_10_sub_pixel_variance64x128_c Unexecuted instantiation: aom_highbd_10_sub_pixel_variance64x64_c Unexecuted instantiation: aom_highbd_10_sub_pixel_variance64x32_c Unexecuted instantiation: aom_highbd_10_sub_pixel_variance32x64_c Unexecuted instantiation: aom_highbd_10_sub_pixel_variance32x32_c Unexecuted instantiation: aom_highbd_10_sub_pixel_variance32x16_c Unexecuted instantiation: aom_highbd_10_sub_pixel_variance16x32_c Unexecuted instantiation: aom_highbd_10_sub_pixel_variance16x16_c Unexecuted instantiation: aom_highbd_10_sub_pixel_variance16x8_c Unexecuted instantiation: aom_highbd_10_sub_pixel_variance8x16_c Unexecuted instantiation: aom_highbd_10_sub_pixel_variance8x8_c Unexecuted instantiation: aom_highbd_10_sub_pixel_variance8x4_c Unexecuted instantiation: aom_highbd_10_sub_pixel_variance4x8_c Unexecuted instantiation: aom_highbd_10_sub_pixel_variance4x4_c Unexecuted instantiation: aom_highbd_10_sub_pixel_variance4x2_c Unexecuted instantiation: aom_highbd_10_sub_pixel_variance2x4_c Unexecuted instantiation: aom_highbd_10_sub_pixel_variance2x2_c Unexecuted instantiation: aom_highbd_10_sub_pixel_variance4x16_c Unexecuted instantiation: aom_highbd_10_sub_pixel_variance16x4_c Unexecuted instantiation: aom_highbd_10_sub_pixel_variance8x32_c Unexecuted instantiation: aom_highbd_10_sub_pixel_variance32x8_c Unexecuted instantiation: aom_highbd_10_sub_pixel_variance16x64_c Unexecuted instantiation: aom_highbd_10_sub_pixel_variance64x16_c |
510 | | \ |
511 | | uint32_t aom_highbd_12_sub_pixel_variance##W##x##H##_c( \ |
512 | | const uint8_t *src, int src_stride, int xoffset, int yoffset, \ |
513 | 0 | const uint8_t *dst, int dst_stride, uint32_t *sse) { \ |
514 | 0 | uint16_t fdata3[(H + 1) * W]; \ |
515 | 0 | uint16_t temp2[H * W]; \ |
516 | 0 | \ |
517 | 0 | aom_highbd_var_filter_block2d_bil_first_pass( \ |
518 | 0 | src, fdata3, src_stride, 1, H + 1, W, bilinear_filters_2t[xoffset]); \ |
519 | 0 | aom_highbd_var_filter_block2d_bil_second_pass( \ |
520 | 0 | fdata3, temp2, W, W, H, W, bilinear_filters_2t[yoffset]); \ |
521 | 0 | \ |
522 | 0 | return aom_highbd_12_variance##W##x##H##_c(CONVERT_TO_BYTEPTR(temp2), W, \ |
523 | 0 | dst, dst_stride, sse); \ |
524 | 0 | } Unexecuted instantiation: aom_highbd_12_sub_pixel_variance128x128_c Unexecuted instantiation: aom_highbd_12_sub_pixel_variance128x64_c Unexecuted instantiation: aom_highbd_12_sub_pixel_variance64x128_c Unexecuted instantiation: aom_highbd_12_sub_pixel_variance64x64_c Unexecuted instantiation: aom_highbd_12_sub_pixel_variance64x32_c Unexecuted instantiation: aom_highbd_12_sub_pixel_variance32x64_c Unexecuted instantiation: aom_highbd_12_sub_pixel_variance32x32_c Unexecuted instantiation: aom_highbd_12_sub_pixel_variance32x16_c Unexecuted instantiation: aom_highbd_12_sub_pixel_variance16x32_c Unexecuted instantiation: aom_highbd_12_sub_pixel_variance16x16_c Unexecuted instantiation: aom_highbd_12_sub_pixel_variance16x8_c Unexecuted instantiation: aom_highbd_12_sub_pixel_variance8x16_c Unexecuted instantiation: aom_highbd_12_sub_pixel_variance8x8_c Unexecuted instantiation: aom_highbd_12_sub_pixel_variance8x4_c Unexecuted instantiation: aom_highbd_12_sub_pixel_variance4x8_c Unexecuted instantiation: aom_highbd_12_sub_pixel_variance4x4_c Unexecuted instantiation: aom_highbd_12_sub_pixel_variance4x2_c Unexecuted instantiation: aom_highbd_12_sub_pixel_variance2x4_c Unexecuted instantiation: aom_highbd_12_sub_pixel_variance2x2_c Unexecuted instantiation: aom_highbd_12_sub_pixel_variance4x16_c Unexecuted instantiation: aom_highbd_12_sub_pixel_variance16x4_c Unexecuted instantiation: aom_highbd_12_sub_pixel_variance8x32_c Unexecuted instantiation: aom_highbd_12_sub_pixel_variance32x8_c Unexecuted instantiation: aom_highbd_12_sub_pixel_variance16x64_c Unexecuted instantiation: aom_highbd_12_sub_pixel_variance64x16_c |
525 | | |
526 | | #define HIGHBD_SUBPIX_AVG_VAR(W, H) \ |
527 | | uint32_t aom_highbd_8_sub_pixel_avg_variance##W##x##H##_c( \ |
528 | | const uint8_t *src, int src_stride, int xoffset, int yoffset, \ |
529 | | const uint8_t *dst, int dst_stride, uint32_t *sse, \ |
530 | 0 | const uint8_t *second_pred) { \ |
531 | 0 | uint16_t fdata3[(H + 1) * W]; \ |
532 | 0 | uint16_t temp2[H * W]; \ |
533 | 0 | DECLARE_ALIGNED(16, uint16_t, temp3[H * W]); \ |
534 | 0 | \ |
535 | 0 | aom_highbd_var_filter_block2d_bil_first_pass( \ |
536 | 0 | src, fdata3, src_stride, 1, H + 1, W, bilinear_filters_2t[xoffset]); \ |
537 | 0 | aom_highbd_var_filter_block2d_bil_second_pass( \ |
538 | 0 | fdata3, temp2, W, W, H, W, bilinear_filters_2t[yoffset]); \ |
539 | 0 | \ |
540 | 0 | aom_highbd_comp_avg_pred_c(CONVERT_TO_BYTEPTR(temp3), second_pred, W, H, \ |
541 | 0 | CONVERT_TO_BYTEPTR(temp2), W); \ |
542 | 0 | \ |
543 | 0 | return aom_highbd_8_variance##W##x##H##_c(CONVERT_TO_BYTEPTR(temp3), W, \ |
544 | 0 | dst, dst_stride, sse); \ |
545 | 0 | } \ Unexecuted instantiation: aom_highbd_8_sub_pixel_avg_variance128x128_c Unexecuted instantiation: aom_highbd_8_sub_pixel_avg_variance128x64_c Unexecuted instantiation: aom_highbd_8_sub_pixel_avg_variance64x128_c Unexecuted instantiation: aom_highbd_8_sub_pixel_avg_variance64x64_c Unexecuted instantiation: aom_highbd_8_sub_pixel_avg_variance64x32_c Unexecuted instantiation: aom_highbd_8_sub_pixel_avg_variance32x64_c Unexecuted instantiation: aom_highbd_8_sub_pixel_avg_variance32x32_c Unexecuted instantiation: aom_highbd_8_sub_pixel_avg_variance32x16_c Unexecuted instantiation: aom_highbd_8_sub_pixel_avg_variance16x32_c Unexecuted instantiation: aom_highbd_8_sub_pixel_avg_variance16x16_c Unexecuted instantiation: aom_highbd_8_sub_pixel_avg_variance16x8_c Unexecuted instantiation: aom_highbd_8_sub_pixel_avg_variance8x16_c Unexecuted instantiation: aom_highbd_8_sub_pixel_avg_variance8x8_c Unexecuted instantiation: aom_highbd_8_sub_pixel_avg_variance8x4_c Unexecuted instantiation: aom_highbd_8_sub_pixel_avg_variance4x8_c Unexecuted instantiation: aom_highbd_8_sub_pixel_avg_variance4x4_c Unexecuted instantiation: aom_highbd_8_sub_pixel_avg_variance4x2_c Unexecuted instantiation: aom_highbd_8_sub_pixel_avg_variance2x4_c Unexecuted instantiation: aom_highbd_8_sub_pixel_avg_variance2x2_c Unexecuted instantiation: aom_highbd_8_sub_pixel_avg_variance4x16_c Unexecuted instantiation: aom_highbd_8_sub_pixel_avg_variance16x4_c Unexecuted instantiation: aom_highbd_8_sub_pixel_avg_variance8x32_c Unexecuted instantiation: aom_highbd_8_sub_pixel_avg_variance32x8_c Unexecuted instantiation: aom_highbd_8_sub_pixel_avg_variance16x64_c Unexecuted instantiation: aom_highbd_8_sub_pixel_avg_variance64x16_c |
546 | | \ |
547 | | uint32_t aom_highbd_10_sub_pixel_avg_variance##W##x##H##_c( \ |
548 | | const uint8_t *src, int src_stride, int xoffset, int yoffset, \ |
549 | | const uint8_t *dst, int dst_stride, uint32_t *sse, \ |
550 | 0 | const uint8_t *second_pred) { \ |
551 | 0 | uint16_t fdata3[(H + 1) * W]; \ |
552 | 0 | uint16_t temp2[H * W]; \ |
553 | 0 | DECLARE_ALIGNED(16, uint16_t, temp3[H * W]); \ |
554 | 0 | \ |
555 | 0 | aom_highbd_var_filter_block2d_bil_first_pass( \ |
556 | 0 | src, fdata3, src_stride, 1, H + 1, W, bilinear_filters_2t[xoffset]); \ |
557 | 0 | aom_highbd_var_filter_block2d_bil_second_pass( \ |
558 | 0 | fdata3, temp2, W, W, H, W, bilinear_filters_2t[yoffset]); \ |
559 | 0 | \ |
560 | 0 | aom_highbd_comp_avg_pred_c(CONVERT_TO_BYTEPTR(temp3), second_pred, W, H, \ |
561 | 0 | CONVERT_TO_BYTEPTR(temp2), W); \ |
562 | 0 | \ |
563 | 0 | return aom_highbd_10_variance##W##x##H##_c(CONVERT_TO_BYTEPTR(temp3), W, \ |
564 | 0 | dst, dst_stride, sse); \ |
565 | 0 | } \ Unexecuted instantiation: aom_highbd_10_sub_pixel_avg_variance128x128_c Unexecuted instantiation: aom_highbd_10_sub_pixel_avg_variance128x64_c Unexecuted instantiation: aom_highbd_10_sub_pixel_avg_variance64x128_c Unexecuted instantiation: aom_highbd_10_sub_pixel_avg_variance64x64_c Unexecuted instantiation: aom_highbd_10_sub_pixel_avg_variance64x32_c Unexecuted instantiation: aom_highbd_10_sub_pixel_avg_variance32x64_c Unexecuted instantiation: aom_highbd_10_sub_pixel_avg_variance32x32_c Unexecuted instantiation: aom_highbd_10_sub_pixel_avg_variance32x16_c Unexecuted instantiation: aom_highbd_10_sub_pixel_avg_variance16x32_c Unexecuted instantiation: aom_highbd_10_sub_pixel_avg_variance16x16_c Unexecuted instantiation: aom_highbd_10_sub_pixel_avg_variance16x8_c Unexecuted instantiation: aom_highbd_10_sub_pixel_avg_variance8x16_c Unexecuted instantiation: aom_highbd_10_sub_pixel_avg_variance8x8_c Unexecuted instantiation: aom_highbd_10_sub_pixel_avg_variance8x4_c Unexecuted instantiation: aom_highbd_10_sub_pixel_avg_variance4x8_c Unexecuted instantiation: aom_highbd_10_sub_pixel_avg_variance4x4_c Unexecuted instantiation: aom_highbd_10_sub_pixel_avg_variance4x2_c Unexecuted instantiation: aom_highbd_10_sub_pixel_avg_variance2x4_c Unexecuted instantiation: aom_highbd_10_sub_pixel_avg_variance2x2_c Unexecuted instantiation: aom_highbd_10_sub_pixel_avg_variance4x16_c Unexecuted instantiation: aom_highbd_10_sub_pixel_avg_variance16x4_c Unexecuted instantiation: aom_highbd_10_sub_pixel_avg_variance8x32_c Unexecuted instantiation: aom_highbd_10_sub_pixel_avg_variance32x8_c Unexecuted instantiation: aom_highbd_10_sub_pixel_avg_variance16x64_c Unexecuted instantiation: aom_highbd_10_sub_pixel_avg_variance64x16_c |
566 | | \ |
567 | | uint32_t aom_highbd_12_sub_pixel_avg_variance##W##x##H##_c( \ |
568 | | const uint8_t *src, int src_stride, int xoffset, int yoffset, \ |
569 | | const uint8_t *dst, int dst_stride, uint32_t *sse, \ |
570 | 0 | const uint8_t *second_pred) { \ |
571 | 0 | uint16_t fdata3[(H + 1) * W]; \ |
572 | 0 | uint16_t temp2[H * W]; \ |
573 | 0 | DECLARE_ALIGNED(16, uint16_t, temp3[H * W]); \ |
574 | 0 | \ |
575 | 0 | aom_highbd_var_filter_block2d_bil_first_pass( \ |
576 | 0 | src, fdata3, src_stride, 1, H + 1, W, bilinear_filters_2t[xoffset]); \ |
577 | 0 | aom_highbd_var_filter_block2d_bil_second_pass( \ |
578 | 0 | fdata3, temp2, W, W, H, W, bilinear_filters_2t[yoffset]); \ |
579 | 0 | \ |
580 | 0 | aom_highbd_comp_avg_pred_c(CONVERT_TO_BYTEPTR(temp3), second_pred, W, H, \ |
581 | 0 | CONVERT_TO_BYTEPTR(temp2), W); \ |
582 | 0 | \ |
583 | 0 | return aom_highbd_12_variance##W##x##H##_c(CONVERT_TO_BYTEPTR(temp3), W, \ |
584 | 0 | dst, dst_stride, sse); \ |
585 | 0 | } \ Unexecuted instantiation: aom_highbd_12_sub_pixel_avg_variance128x128_c Unexecuted instantiation: aom_highbd_12_sub_pixel_avg_variance128x64_c Unexecuted instantiation: aom_highbd_12_sub_pixel_avg_variance64x128_c Unexecuted instantiation: aom_highbd_12_sub_pixel_avg_variance64x64_c Unexecuted instantiation: aom_highbd_12_sub_pixel_avg_variance64x32_c Unexecuted instantiation: aom_highbd_12_sub_pixel_avg_variance32x64_c Unexecuted instantiation: aom_highbd_12_sub_pixel_avg_variance32x32_c Unexecuted instantiation: aom_highbd_12_sub_pixel_avg_variance32x16_c Unexecuted instantiation: aom_highbd_12_sub_pixel_avg_variance16x32_c Unexecuted instantiation: aom_highbd_12_sub_pixel_avg_variance16x16_c Unexecuted instantiation: aom_highbd_12_sub_pixel_avg_variance16x8_c Unexecuted instantiation: aom_highbd_12_sub_pixel_avg_variance8x16_c Unexecuted instantiation: aom_highbd_12_sub_pixel_avg_variance8x8_c Unexecuted instantiation: aom_highbd_12_sub_pixel_avg_variance8x4_c Unexecuted instantiation: aom_highbd_12_sub_pixel_avg_variance4x8_c Unexecuted instantiation: aom_highbd_12_sub_pixel_avg_variance4x4_c Unexecuted instantiation: aom_highbd_12_sub_pixel_avg_variance4x2_c Unexecuted instantiation: aom_highbd_12_sub_pixel_avg_variance2x4_c Unexecuted instantiation: aom_highbd_12_sub_pixel_avg_variance2x2_c Unexecuted instantiation: aom_highbd_12_sub_pixel_avg_variance4x16_c Unexecuted instantiation: aom_highbd_12_sub_pixel_avg_variance16x4_c Unexecuted instantiation: aom_highbd_12_sub_pixel_avg_variance8x32_c Unexecuted instantiation: aom_highbd_12_sub_pixel_avg_variance32x8_c Unexecuted instantiation: aom_highbd_12_sub_pixel_avg_variance16x64_c Unexecuted instantiation: aom_highbd_12_sub_pixel_avg_variance64x16_c |
586 | | \ |
587 | | uint32_t aom_highbd_8_dist_wtd_sub_pixel_avg_variance##W##x##H##_c( \ |
588 | | const uint8_t *src, int src_stride, int xoffset, int yoffset, \ |
589 | | const uint8_t *dst, int dst_stride, uint32_t *sse, \ |
590 | 0 | const uint8_t *second_pred, const DIST_WTD_COMP_PARAMS *jcp_param) { \ |
591 | 0 | uint16_t fdata3[(H + 1) * W]; \ |
592 | 0 | uint16_t temp2[H * W]; \ |
593 | 0 | DECLARE_ALIGNED(16, uint16_t, temp3[H * W]); \ |
594 | 0 | \ |
595 | 0 | aom_highbd_var_filter_block2d_bil_first_pass( \ |
596 | 0 | src, fdata3, src_stride, 1, H + 1, W, bilinear_filters_2t[xoffset]); \ |
597 | 0 | aom_highbd_var_filter_block2d_bil_second_pass( \ |
598 | 0 | fdata3, temp2, W, W, H, W, bilinear_filters_2t[yoffset]); \ |
599 | 0 | \ |
600 | 0 | aom_highbd_dist_wtd_comp_avg_pred(CONVERT_TO_BYTEPTR(temp3), second_pred, \ |
601 | 0 | W, H, CONVERT_TO_BYTEPTR(temp2), W, \ |
602 | 0 | jcp_param); \ |
603 | 0 | \ |
604 | 0 | return aom_highbd_8_variance##W##x##H(CONVERT_TO_BYTEPTR(temp3), W, dst, \ |
605 | 0 | dst_stride, sse); \ |
606 | 0 | } \ Unexecuted instantiation: aom_highbd_8_dist_wtd_sub_pixel_avg_variance128x128_c Unexecuted instantiation: aom_highbd_8_dist_wtd_sub_pixel_avg_variance128x64_c Unexecuted instantiation: aom_highbd_8_dist_wtd_sub_pixel_avg_variance64x128_c Unexecuted instantiation: aom_highbd_8_dist_wtd_sub_pixel_avg_variance64x64_c Unexecuted instantiation: aom_highbd_8_dist_wtd_sub_pixel_avg_variance64x32_c Unexecuted instantiation: aom_highbd_8_dist_wtd_sub_pixel_avg_variance32x64_c Unexecuted instantiation: aom_highbd_8_dist_wtd_sub_pixel_avg_variance32x32_c Unexecuted instantiation: aom_highbd_8_dist_wtd_sub_pixel_avg_variance32x16_c Unexecuted instantiation: aom_highbd_8_dist_wtd_sub_pixel_avg_variance16x32_c Unexecuted instantiation: aom_highbd_8_dist_wtd_sub_pixel_avg_variance16x16_c Unexecuted instantiation: aom_highbd_8_dist_wtd_sub_pixel_avg_variance16x8_c Unexecuted instantiation: aom_highbd_8_dist_wtd_sub_pixel_avg_variance8x16_c Unexecuted instantiation: aom_highbd_8_dist_wtd_sub_pixel_avg_variance8x8_c Unexecuted instantiation: aom_highbd_8_dist_wtd_sub_pixel_avg_variance8x4_c Unexecuted instantiation: aom_highbd_8_dist_wtd_sub_pixel_avg_variance4x8_c Unexecuted instantiation: aom_highbd_8_dist_wtd_sub_pixel_avg_variance4x4_c Unexecuted instantiation: aom_highbd_8_dist_wtd_sub_pixel_avg_variance4x2_c Unexecuted instantiation: aom_highbd_8_dist_wtd_sub_pixel_avg_variance2x4_c Unexecuted instantiation: aom_highbd_8_dist_wtd_sub_pixel_avg_variance2x2_c Unexecuted instantiation: aom_highbd_8_dist_wtd_sub_pixel_avg_variance4x16_c Unexecuted instantiation: aom_highbd_8_dist_wtd_sub_pixel_avg_variance16x4_c Unexecuted instantiation: aom_highbd_8_dist_wtd_sub_pixel_avg_variance8x32_c Unexecuted instantiation: aom_highbd_8_dist_wtd_sub_pixel_avg_variance32x8_c Unexecuted instantiation: aom_highbd_8_dist_wtd_sub_pixel_avg_variance16x64_c Unexecuted instantiation: aom_highbd_8_dist_wtd_sub_pixel_avg_variance64x16_c |
607 | | \ |
608 | | uint32_t aom_highbd_10_dist_wtd_sub_pixel_avg_variance##W##x##H##_c( \ |
609 | | const uint8_t *src, int src_stride, int xoffset, int yoffset, \ |
610 | | const uint8_t *dst, int dst_stride, uint32_t *sse, \ |
611 | 0 | const uint8_t *second_pred, const DIST_WTD_COMP_PARAMS *jcp_param) { \ |
612 | 0 | uint16_t fdata3[(H + 1) * W]; \ |
613 | 0 | uint16_t temp2[H * W]; \ |
614 | 0 | DECLARE_ALIGNED(16, uint16_t, temp3[H * W]); \ |
615 | 0 | \ |
616 | 0 | aom_highbd_var_filter_block2d_bil_first_pass( \ |
617 | 0 | src, fdata3, src_stride, 1, H + 1, W, bilinear_filters_2t[xoffset]); \ |
618 | 0 | aom_highbd_var_filter_block2d_bil_second_pass( \ |
619 | 0 | fdata3, temp2, W, W, H, W, bilinear_filters_2t[yoffset]); \ |
620 | 0 | \ |
621 | 0 | aom_highbd_dist_wtd_comp_avg_pred(CONVERT_TO_BYTEPTR(temp3), second_pred, \ |
622 | 0 | W, H, CONVERT_TO_BYTEPTR(temp2), W, \ |
623 | 0 | jcp_param); \ |
624 | 0 | \ |
625 | 0 | return aom_highbd_10_variance##W##x##H(CONVERT_TO_BYTEPTR(temp3), W, dst, \ |
626 | 0 | dst_stride, sse); \ |
627 | 0 | } \ Unexecuted instantiation: aom_highbd_10_dist_wtd_sub_pixel_avg_variance128x128_c Unexecuted instantiation: aom_highbd_10_dist_wtd_sub_pixel_avg_variance128x64_c Unexecuted instantiation: aom_highbd_10_dist_wtd_sub_pixel_avg_variance64x128_c Unexecuted instantiation: aom_highbd_10_dist_wtd_sub_pixel_avg_variance64x64_c Unexecuted instantiation: aom_highbd_10_dist_wtd_sub_pixel_avg_variance64x32_c Unexecuted instantiation: aom_highbd_10_dist_wtd_sub_pixel_avg_variance32x64_c Unexecuted instantiation: aom_highbd_10_dist_wtd_sub_pixel_avg_variance32x32_c Unexecuted instantiation: aom_highbd_10_dist_wtd_sub_pixel_avg_variance32x16_c Unexecuted instantiation: aom_highbd_10_dist_wtd_sub_pixel_avg_variance16x32_c Unexecuted instantiation: aom_highbd_10_dist_wtd_sub_pixel_avg_variance16x16_c Unexecuted instantiation: aom_highbd_10_dist_wtd_sub_pixel_avg_variance16x8_c Unexecuted instantiation: aom_highbd_10_dist_wtd_sub_pixel_avg_variance8x16_c Unexecuted instantiation: aom_highbd_10_dist_wtd_sub_pixel_avg_variance8x8_c Unexecuted instantiation: aom_highbd_10_dist_wtd_sub_pixel_avg_variance8x4_c Unexecuted instantiation: aom_highbd_10_dist_wtd_sub_pixel_avg_variance4x8_c Unexecuted instantiation: aom_highbd_10_dist_wtd_sub_pixel_avg_variance4x4_c Unexecuted instantiation: aom_highbd_10_dist_wtd_sub_pixel_avg_variance4x2_c Unexecuted instantiation: aom_highbd_10_dist_wtd_sub_pixel_avg_variance2x4_c Unexecuted instantiation: aom_highbd_10_dist_wtd_sub_pixel_avg_variance2x2_c Unexecuted instantiation: aom_highbd_10_dist_wtd_sub_pixel_avg_variance4x16_c Unexecuted instantiation: aom_highbd_10_dist_wtd_sub_pixel_avg_variance16x4_c Unexecuted instantiation: aom_highbd_10_dist_wtd_sub_pixel_avg_variance8x32_c Unexecuted instantiation: aom_highbd_10_dist_wtd_sub_pixel_avg_variance32x8_c Unexecuted instantiation: aom_highbd_10_dist_wtd_sub_pixel_avg_variance16x64_c Unexecuted instantiation: aom_highbd_10_dist_wtd_sub_pixel_avg_variance64x16_c |
628 | | \ |
629 | | uint32_t aom_highbd_12_dist_wtd_sub_pixel_avg_variance##W##x##H##_c( \ |
630 | | const uint8_t *src, int src_stride, int xoffset, int yoffset, \ |
631 | | const uint8_t *dst, int dst_stride, uint32_t *sse, \ |
632 | 0 | const uint8_t *second_pred, const DIST_WTD_COMP_PARAMS *jcp_param) { \ |
633 | 0 | uint16_t fdata3[(H + 1) * W]; \ |
634 | 0 | uint16_t temp2[H * W]; \ |
635 | 0 | DECLARE_ALIGNED(16, uint16_t, temp3[H * W]); \ |
636 | 0 | \ |
637 | 0 | aom_highbd_var_filter_block2d_bil_first_pass( \ |
638 | 0 | src, fdata3, src_stride, 1, H + 1, W, bilinear_filters_2t[xoffset]); \ |
639 | 0 | aom_highbd_var_filter_block2d_bil_second_pass( \ |
640 | 0 | fdata3, temp2, W, W, H, W, bilinear_filters_2t[yoffset]); \ |
641 | 0 | \ |
642 | 0 | aom_highbd_dist_wtd_comp_avg_pred(CONVERT_TO_BYTEPTR(temp3), second_pred, \ |
643 | 0 | W, H, CONVERT_TO_BYTEPTR(temp2), W, \ |
644 | 0 | jcp_param); \ |
645 | 0 | \ |
646 | 0 | return aom_highbd_12_variance##W##x##H(CONVERT_TO_BYTEPTR(temp3), W, dst, \ |
647 | 0 | dst_stride, sse); \ |
648 | 0 | } Unexecuted instantiation: aom_highbd_12_dist_wtd_sub_pixel_avg_variance128x128_c Unexecuted instantiation: aom_highbd_12_dist_wtd_sub_pixel_avg_variance128x64_c Unexecuted instantiation: aom_highbd_12_dist_wtd_sub_pixel_avg_variance64x128_c Unexecuted instantiation: aom_highbd_12_dist_wtd_sub_pixel_avg_variance64x64_c Unexecuted instantiation: aom_highbd_12_dist_wtd_sub_pixel_avg_variance64x32_c Unexecuted instantiation: aom_highbd_12_dist_wtd_sub_pixel_avg_variance32x64_c Unexecuted instantiation: aom_highbd_12_dist_wtd_sub_pixel_avg_variance32x32_c Unexecuted instantiation: aom_highbd_12_dist_wtd_sub_pixel_avg_variance32x16_c Unexecuted instantiation: aom_highbd_12_dist_wtd_sub_pixel_avg_variance16x32_c Unexecuted instantiation: aom_highbd_12_dist_wtd_sub_pixel_avg_variance16x16_c Unexecuted instantiation: aom_highbd_12_dist_wtd_sub_pixel_avg_variance16x8_c Unexecuted instantiation: aom_highbd_12_dist_wtd_sub_pixel_avg_variance8x16_c Unexecuted instantiation: aom_highbd_12_dist_wtd_sub_pixel_avg_variance8x8_c Unexecuted instantiation: aom_highbd_12_dist_wtd_sub_pixel_avg_variance8x4_c Unexecuted instantiation: aom_highbd_12_dist_wtd_sub_pixel_avg_variance4x8_c Unexecuted instantiation: aom_highbd_12_dist_wtd_sub_pixel_avg_variance4x4_c Unexecuted instantiation: aom_highbd_12_dist_wtd_sub_pixel_avg_variance4x2_c Unexecuted instantiation: aom_highbd_12_dist_wtd_sub_pixel_avg_variance2x4_c Unexecuted instantiation: aom_highbd_12_dist_wtd_sub_pixel_avg_variance2x2_c Unexecuted instantiation: aom_highbd_12_dist_wtd_sub_pixel_avg_variance4x16_c Unexecuted instantiation: aom_highbd_12_dist_wtd_sub_pixel_avg_variance16x4_c Unexecuted instantiation: aom_highbd_12_dist_wtd_sub_pixel_avg_variance8x32_c Unexecuted instantiation: aom_highbd_12_dist_wtd_sub_pixel_avg_variance32x8_c Unexecuted instantiation: aom_highbd_12_dist_wtd_sub_pixel_avg_variance16x64_c Unexecuted instantiation: aom_highbd_12_dist_wtd_sub_pixel_avg_variance64x16_c |
649 | | |
650 | | /* All three forms of the variance are available in the same sizes. */ |
651 | | #define HIGHBD_VARIANCES(W, H) \ |
652 | | HIGHBD_VAR(W, H) \ |
653 | | HIGHBD_SUBPIX_VAR(W, H) \ |
654 | | HIGHBD_SUBPIX_AVG_VAR(W, H) |
655 | | |
656 | | HIGHBD_VARIANCES(128, 128) |
657 | | HIGHBD_VARIANCES(128, 64) |
658 | | HIGHBD_VARIANCES(64, 128) |
659 | | HIGHBD_VARIANCES(64, 64) |
660 | | HIGHBD_VARIANCES(64, 32) |
661 | | HIGHBD_VARIANCES(32, 64) |
662 | | HIGHBD_VARIANCES(32, 32) |
663 | | HIGHBD_VARIANCES(32, 16) |
664 | | HIGHBD_VARIANCES(16, 32) |
665 | | HIGHBD_VARIANCES(16, 16) |
666 | | HIGHBD_VARIANCES(16, 8) |
667 | | HIGHBD_VARIANCES(8, 16) |
668 | | HIGHBD_VARIANCES(8, 8) |
669 | | HIGHBD_VARIANCES(8, 4) |
670 | | HIGHBD_VARIANCES(4, 8) |
671 | | HIGHBD_VARIANCES(4, 4) |
672 | | HIGHBD_VARIANCES(4, 2) |
673 | | HIGHBD_VARIANCES(2, 4) |
674 | | HIGHBD_VARIANCES(2, 2) |
675 | | |
676 | | // Realtime mode doesn't use 4x rectangular blocks. |
677 | | #if !CONFIG_REALTIME_ONLY |
678 | | HIGHBD_VARIANCES(4, 16) |
679 | | HIGHBD_VARIANCES(16, 4) |
680 | | HIGHBD_VARIANCES(8, 32) |
681 | | HIGHBD_VARIANCES(32, 8) |
682 | | HIGHBD_VARIANCES(16, 64) |
683 | | HIGHBD_VARIANCES(64, 16) |
684 | | #endif |
685 | | |
686 | | HIGHBD_GET_VAR(8) |
687 | | HIGHBD_GET_VAR(16) |
688 | | |
689 | | HIGHBD_MSE(16, 16) |
690 | | HIGHBD_MSE(16, 8) |
691 | | HIGHBD_MSE(8, 16) |
692 | | HIGHBD_MSE(8, 8) |
693 | | |
694 | | void aom_highbd_comp_avg_pred_c(uint8_t *comp_pred8, const uint8_t *pred8, |
695 | | int width, int height, const uint8_t *ref8, |
696 | 0 | int ref_stride) { |
697 | 0 | int i, j; |
698 | 0 | uint16_t *pred = CONVERT_TO_SHORTPTR(pred8); |
699 | 0 | uint16_t *ref = CONVERT_TO_SHORTPTR(ref8); |
700 | 0 | uint16_t *comp_pred = CONVERT_TO_SHORTPTR(comp_pred8); |
701 | 0 | for (i = 0; i < height; ++i) { |
702 | 0 | for (j = 0; j < width; ++j) { |
703 | 0 | const int tmp = pred[j] + ref[j]; |
704 | 0 | comp_pred[j] = ROUND_POWER_OF_TWO(tmp, 1); |
705 | 0 | } |
706 | 0 | comp_pred += width; |
707 | 0 | pred += width; |
708 | 0 | ref += ref_stride; |
709 | 0 | } |
710 | 0 | } |
711 | | |
712 | | void aom_highbd_dist_wtd_comp_avg_pred_c( |
713 | | uint8_t *comp_pred8, const uint8_t *pred8, int width, int height, |
714 | | const uint8_t *ref8, int ref_stride, |
715 | 0 | const DIST_WTD_COMP_PARAMS *jcp_param) { |
716 | 0 | int i, j; |
717 | 0 | const int fwd_offset = jcp_param->fwd_offset; |
718 | 0 | const int bck_offset = jcp_param->bck_offset; |
719 | 0 | uint16_t *pred = CONVERT_TO_SHORTPTR(pred8); |
720 | 0 | uint16_t *ref = CONVERT_TO_SHORTPTR(ref8); |
721 | 0 | uint16_t *comp_pred = CONVERT_TO_SHORTPTR(comp_pred8); |
722 | |
|
723 | 0 | for (i = 0; i < height; ++i) { |
724 | 0 | for (j = 0; j < width; ++j) { |
725 | 0 | int tmp = pred[j] * bck_offset + ref[j] * fwd_offset; |
726 | 0 | tmp = ROUND_POWER_OF_TWO(tmp, DIST_PRECISION_BITS); |
727 | 0 | comp_pred[j] = (uint16_t)tmp; |
728 | 0 | } |
729 | 0 | comp_pred += width; |
730 | 0 | pred += width; |
731 | 0 | ref += ref_stride; |
732 | 0 | } |
733 | 0 | } |
734 | | #endif // CONFIG_AV1_HIGHBITDEPTH |
735 | | |
736 | | void aom_comp_mask_pred_c(uint8_t *comp_pred, const uint8_t *pred, int width, |
737 | | int height, const uint8_t *ref, int ref_stride, |
738 | | const uint8_t *mask, int mask_stride, |
739 | 0 | int invert_mask) { |
740 | 0 | int i, j; |
741 | 0 | const uint8_t *src0 = invert_mask ? pred : ref; |
742 | 0 | const uint8_t *src1 = invert_mask ? ref : pred; |
743 | 0 | const int stride0 = invert_mask ? width : ref_stride; |
744 | 0 | const int stride1 = invert_mask ? ref_stride : width; |
745 | 0 | for (i = 0; i < height; ++i) { |
746 | 0 | for (j = 0; j < width; ++j) { |
747 | 0 | comp_pred[j] = AOM_BLEND_A64(mask[j], src0[j], src1[j]); |
748 | 0 | } |
749 | 0 | comp_pred += width; |
750 | 0 | src0 += stride0; |
751 | 0 | src1 += stride1; |
752 | 0 | mask += mask_stride; |
753 | 0 | } |
754 | 0 | } |
755 | | |
756 | | #define MASK_SUBPIX_VAR(W, H) \ |
757 | | unsigned int aom_masked_sub_pixel_variance##W##x##H##_c( \ |
758 | | const uint8_t *src, int src_stride, int xoffset, int yoffset, \ |
759 | | const uint8_t *ref, int ref_stride, const uint8_t *second_pred, \ |
760 | | const uint8_t *msk, int msk_stride, int invert_mask, \ |
761 | 0 | unsigned int *sse) { \ |
762 | 0 | uint16_t fdata3[(H + 1) * W]; \ |
763 | 0 | uint8_t temp2[H * W]; \ |
764 | 0 | DECLARE_ALIGNED(16, uint8_t, temp3[H * W]); \ |
765 | 0 | \ |
766 | 0 | aom_var_filter_block2d_bil_first_pass_c(src, fdata3, src_stride, 1, H + 1, \ |
767 | 0 | W, bilinear_filters_2t[xoffset]); \ |
768 | 0 | aom_var_filter_block2d_bil_second_pass_c(fdata3, temp2, W, W, H, W, \ |
769 | 0 | bilinear_filters_2t[yoffset]); \ |
770 | 0 | \ |
771 | 0 | aom_comp_mask_pred_c(temp3, second_pred, W, H, temp2, W, msk, msk_stride, \ |
772 | 0 | invert_mask); \ |
773 | 0 | return aom_variance##W##x##H##_c(temp3, W, ref, ref_stride, sse); \ |
774 | 0 | } Unexecuted instantiation: aom_masked_sub_pixel_variance4x4_c Unexecuted instantiation: aom_masked_sub_pixel_variance4x8_c Unexecuted instantiation: aom_masked_sub_pixel_variance8x4_c Unexecuted instantiation: aom_masked_sub_pixel_variance8x8_c Unexecuted instantiation: aom_masked_sub_pixel_variance8x16_c Unexecuted instantiation: aom_masked_sub_pixel_variance16x8_c Unexecuted instantiation: aom_masked_sub_pixel_variance16x16_c Unexecuted instantiation: aom_masked_sub_pixel_variance16x32_c Unexecuted instantiation: aom_masked_sub_pixel_variance32x16_c Unexecuted instantiation: aom_masked_sub_pixel_variance32x32_c Unexecuted instantiation: aom_masked_sub_pixel_variance32x64_c Unexecuted instantiation: aom_masked_sub_pixel_variance64x32_c Unexecuted instantiation: aom_masked_sub_pixel_variance64x64_c Unexecuted instantiation: aom_masked_sub_pixel_variance64x128_c Unexecuted instantiation: aom_masked_sub_pixel_variance128x64_c Unexecuted instantiation: aom_masked_sub_pixel_variance128x128_c Unexecuted instantiation: aom_masked_sub_pixel_variance4x16_c Unexecuted instantiation: aom_masked_sub_pixel_variance16x4_c Unexecuted instantiation: aom_masked_sub_pixel_variance8x32_c Unexecuted instantiation: aom_masked_sub_pixel_variance32x8_c Unexecuted instantiation: aom_masked_sub_pixel_variance16x64_c Unexecuted instantiation: aom_masked_sub_pixel_variance64x16_c |
775 | | |
776 | | MASK_SUBPIX_VAR(4, 4) |
777 | | MASK_SUBPIX_VAR(4, 8) |
778 | | MASK_SUBPIX_VAR(8, 4) |
779 | | MASK_SUBPIX_VAR(8, 8) |
780 | | MASK_SUBPIX_VAR(8, 16) |
781 | | MASK_SUBPIX_VAR(16, 8) |
782 | | MASK_SUBPIX_VAR(16, 16) |
783 | | MASK_SUBPIX_VAR(16, 32) |
784 | | MASK_SUBPIX_VAR(32, 16) |
785 | | MASK_SUBPIX_VAR(32, 32) |
786 | | MASK_SUBPIX_VAR(32, 64) |
787 | | MASK_SUBPIX_VAR(64, 32) |
788 | | MASK_SUBPIX_VAR(64, 64) |
789 | | MASK_SUBPIX_VAR(64, 128) |
790 | | MASK_SUBPIX_VAR(128, 64) |
791 | | MASK_SUBPIX_VAR(128, 128) |
792 | | |
793 | | // Realtime mode doesn't use 4x rectangular blocks. |
794 | | #if !CONFIG_REALTIME_ONLY |
795 | | MASK_SUBPIX_VAR(4, 16) |
796 | | MASK_SUBPIX_VAR(16, 4) |
797 | | MASK_SUBPIX_VAR(8, 32) |
798 | | MASK_SUBPIX_VAR(32, 8) |
799 | | MASK_SUBPIX_VAR(16, 64) |
800 | | MASK_SUBPIX_VAR(64, 16) |
801 | | #endif |
802 | | |
803 | | #if CONFIG_AV1_HIGHBITDEPTH |
804 | | void aom_highbd_comp_mask_pred_c(uint8_t *comp_pred8, const uint8_t *pred8, |
805 | | int width, int height, const uint8_t *ref8, |
806 | | int ref_stride, const uint8_t *mask, |
807 | 0 | int mask_stride, int invert_mask) { |
808 | 0 | int i, j; |
809 | 0 | uint16_t *pred = CONVERT_TO_SHORTPTR(pred8); |
810 | 0 | uint16_t *ref = CONVERT_TO_SHORTPTR(ref8); |
811 | 0 | uint16_t *comp_pred = CONVERT_TO_SHORTPTR(comp_pred8); |
812 | 0 | for (i = 0; i < height; ++i) { |
813 | 0 | for (j = 0; j < width; ++j) { |
814 | 0 | if (!invert_mask) |
815 | 0 | comp_pred[j] = AOM_BLEND_A64(mask[j], ref[j], pred[j]); |
816 | 0 | else |
817 | 0 | comp_pred[j] = AOM_BLEND_A64(mask[j], pred[j], ref[j]); |
818 | 0 | } |
819 | 0 | comp_pred += width; |
820 | 0 | pred += width; |
821 | 0 | ref += ref_stride; |
822 | 0 | mask += mask_stride; |
823 | 0 | } |
824 | 0 | } |
825 | | |
826 | | #define HIGHBD_MASK_SUBPIX_VAR(W, H) \ |
827 | | unsigned int aom_highbd_8_masked_sub_pixel_variance##W##x##H##_c( \ |
828 | | const uint8_t *src, int src_stride, int xoffset, int yoffset, \ |
829 | | const uint8_t *ref, int ref_stride, const uint8_t *second_pred, \ |
830 | | const uint8_t *msk, int msk_stride, int invert_mask, \ |
831 | 0 | unsigned int *sse) { \ |
832 | 0 | uint16_t fdata3[(H + 1) * W]; \ |
833 | 0 | uint16_t temp2[H * W]; \ |
834 | 0 | DECLARE_ALIGNED(16, uint16_t, temp3[H * W]); \ |
835 | 0 | \ |
836 | 0 | aom_highbd_var_filter_block2d_bil_first_pass( \ |
837 | 0 | src, fdata3, src_stride, 1, H + 1, W, bilinear_filters_2t[xoffset]); \ |
838 | 0 | aom_highbd_var_filter_block2d_bil_second_pass( \ |
839 | 0 | fdata3, temp2, W, W, H, W, bilinear_filters_2t[yoffset]); \ |
840 | 0 | \ |
841 | 0 | aom_highbd_comp_mask_pred_c(CONVERT_TO_BYTEPTR(temp3), second_pred, W, H, \ |
842 | 0 | CONVERT_TO_BYTEPTR(temp2), W, msk, msk_stride, \ |
843 | 0 | invert_mask); \ |
844 | 0 | \ |
845 | 0 | return aom_highbd_8_variance##W##x##H##_c(CONVERT_TO_BYTEPTR(temp3), W, \ |
846 | 0 | ref, ref_stride, sse); \ |
847 | 0 | } \ Unexecuted instantiation: aom_highbd_8_masked_sub_pixel_variance4x4_c Unexecuted instantiation: aom_highbd_8_masked_sub_pixel_variance4x8_c Unexecuted instantiation: aom_highbd_8_masked_sub_pixel_variance8x4_c Unexecuted instantiation: aom_highbd_8_masked_sub_pixel_variance8x8_c Unexecuted instantiation: aom_highbd_8_masked_sub_pixel_variance8x16_c Unexecuted instantiation: aom_highbd_8_masked_sub_pixel_variance16x8_c Unexecuted instantiation: aom_highbd_8_masked_sub_pixel_variance16x16_c Unexecuted instantiation: aom_highbd_8_masked_sub_pixel_variance16x32_c Unexecuted instantiation: aom_highbd_8_masked_sub_pixel_variance32x16_c Unexecuted instantiation: aom_highbd_8_masked_sub_pixel_variance32x32_c Unexecuted instantiation: aom_highbd_8_masked_sub_pixel_variance32x64_c Unexecuted instantiation: aom_highbd_8_masked_sub_pixel_variance64x32_c Unexecuted instantiation: aom_highbd_8_masked_sub_pixel_variance64x64_c Unexecuted instantiation: aom_highbd_8_masked_sub_pixel_variance64x128_c Unexecuted instantiation: aom_highbd_8_masked_sub_pixel_variance128x64_c Unexecuted instantiation: aom_highbd_8_masked_sub_pixel_variance128x128_c Unexecuted instantiation: aom_highbd_8_masked_sub_pixel_variance4x16_c Unexecuted instantiation: aom_highbd_8_masked_sub_pixel_variance16x4_c Unexecuted instantiation: aom_highbd_8_masked_sub_pixel_variance8x32_c Unexecuted instantiation: aom_highbd_8_masked_sub_pixel_variance32x8_c Unexecuted instantiation: aom_highbd_8_masked_sub_pixel_variance16x64_c Unexecuted instantiation: aom_highbd_8_masked_sub_pixel_variance64x16_c |
848 | | \ |
849 | | unsigned int aom_highbd_10_masked_sub_pixel_variance##W##x##H##_c( \ |
850 | | const uint8_t *src, int src_stride, int xoffset, int yoffset, \ |
851 | | const uint8_t *ref, int ref_stride, const uint8_t *second_pred, \ |
852 | | const uint8_t *msk, int msk_stride, int invert_mask, \ |
853 | 0 | unsigned int *sse) { \ |
854 | 0 | uint16_t fdata3[(H + 1) * W]; \ |
855 | 0 | uint16_t temp2[H * W]; \ |
856 | 0 | DECLARE_ALIGNED(16, uint16_t, temp3[H * W]); \ |
857 | 0 | \ |
858 | 0 | aom_highbd_var_filter_block2d_bil_first_pass( \ |
859 | 0 | src, fdata3, src_stride, 1, H + 1, W, bilinear_filters_2t[xoffset]); \ |
860 | 0 | aom_highbd_var_filter_block2d_bil_second_pass( \ |
861 | 0 | fdata3, temp2, W, W, H, W, bilinear_filters_2t[yoffset]); \ |
862 | 0 | \ |
863 | 0 | aom_highbd_comp_mask_pred_c(CONVERT_TO_BYTEPTR(temp3), second_pred, W, H, \ |
864 | 0 | CONVERT_TO_BYTEPTR(temp2), W, msk, msk_stride, \ |
865 | 0 | invert_mask); \ |
866 | 0 | \ |
867 | 0 | return aom_highbd_10_variance##W##x##H##_c(CONVERT_TO_BYTEPTR(temp3), W, \ |
868 | 0 | ref, ref_stride, sse); \ |
869 | 0 | } \ Unexecuted instantiation: aom_highbd_10_masked_sub_pixel_variance4x4_c Unexecuted instantiation: aom_highbd_10_masked_sub_pixel_variance4x8_c Unexecuted instantiation: aom_highbd_10_masked_sub_pixel_variance8x4_c Unexecuted instantiation: aom_highbd_10_masked_sub_pixel_variance8x8_c Unexecuted instantiation: aom_highbd_10_masked_sub_pixel_variance8x16_c Unexecuted instantiation: aom_highbd_10_masked_sub_pixel_variance16x8_c Unexecuted instantiation: aom_highbd_10_masked_sub_pixel_variance16x16_c Unexecuted instantiation: aom_highbd_10_masked_sub_pixel_variance16x32_c Unexecuted instantiation: aom_highbd_10_masked_sub_pixel_variance32x16_c Unexecuted instantiation: aom_highbd_10_masked_sub_pixel_variance32x32_c Unexecuted instantiation: aom_highbd_10_masked_sub_pixel_variance32x64_c Unexecuted instantiation: aom_highbd_10_masked_sub_pixel_variance64x32_c Unexecuted instantiation: aom_highbd_10_masked_sub_pixel_variance64x64_c Unexecuted instantiation: aom_highbd_10_masked_sub_pixel_variance64x128_c Unexecuted instantiation: aom_highbd_10_masked_sub_pixel_variance128x64_c Unexecuted instantiation: aom_highbd_10_masked_sub_pixel_variance128x128_c Unexecuted instantiation: aom_highbd_10_masked_sub_pixel_variance4x16_c Unexecuted instantiation: aom_highbd_10_masked_sub_pixel_variance16x4_c Unexecuted instantiation: aom_highbd_10_masked_sub_pixel_variance8x32_c Unexecuted instantiation: aom_highbd_10_masked_sub_pixel_variance32x8_c Unexecuted instantiation: aom_highbd_10_masked_sub_pixel_variance16x64_c Unexecuted instantiation: aom_highbd_10_masked_sub_pixel_variance64x16_c |
870 | | \ |
871 | | unsigned int aom_highbd_12_masked_sub_pixel_variance##W##x##H##_c( \ |
872 | | const uint8_t *src, int src_stride, int xoffset, int yoffset, \ |
873 | | const uint8_t *ref, int ref_stride, const uint8_t *second_pred, \ |
874 | | const uint8_t *msk, int msk_stride, int invert_mask, \ |
875 | 0 | unsigned int *sse) { \ |
876 | 0 | uint16_t fdata3[(H + 1) * W]; \ |
877 | 0 | uint16_t temp2[H * W]; \ |
878 | 0 | DECLARE_ALIGNED(16, uint16_t, temp3[H * W]); \ |
879 | 0 | \ |
880 | 0 | aom_highbd_var_filter_block2d_bil_first_pass( \ |
881 | 0 | src, fdata3, src_stride, 1, H + 1, W, bilinear_filters_2t[xoffset]); \ |
882 | 0 | aom_highbd_var_filter_block2d_bil_second_pass( \ |
883 | 0 | fdata3, temp2, W, W, H, W, bilinear_filters_2t[yoffset]); \ |
884 | 0 | \ |
885 | 0 | aom_highbd_comp_mask_pred_c(CONVERT_TO_BYTEPTR(temp3), second_pred, W, H, \ |
886 | 0 | CONVERT_TO_BYTEPTR(temp2), W, msk, msk_stride, \ |
887 | 0 | invert_mask); \ |
888 | 0 | \ |
889 | 0 | return aom_highbd_12_variance##W##x##H##_c(CONVERT_TO_BYTEPTR(temp3), W, \ |
890 | 0 | ref, ref_stride, sse); \ |
891 | 0 | } Unexecuted instantiation: aom_highbd_12_masked_sub_pixel_variance4x4_c Unexecuted instantiation: aom_highbd_12_masked_sub_pixel_variance4x8_c Unexecuted instantiation: aom_highbd_12_masked_sub_pixel_variance8x4_c Unexecuted instantiation: aom_highbd_12_masked_sub_pixel_variance8x8_c Unexecuted instantiation: aom_highbd_12_masked_sub_pixel_variance8x16_c Unexecuted instantiation: aom_highbd_12_masked_sub_pixel_variance16x8_c Unexecuted instantiation: aom_highbd_12_masked_sub_pixel_variance16x16_c Unexecuted instantiation: aom_highbd_12_masked_sub_pixel_variance16x32_c Unexecuted instantiation: aom_highbd_12_masked_sub_pixel_variance32x16_c Unexecuted instantiation: aom_highbd_12_masked_sub_pixel_variance32x32_c Unexecuted instantiation: aom_highbd_12_masked_sub_pixel_variance32x64_c Unexecuted instantiation: aom_highbd_12_masked_sub_pixel_variance64x32_c Unexecuted instantiation: aom_highbd_12_masked_sub_pixel_variance64x64_c Unexecuted instantiation: aom_highbd_12_masked_sub_pixel_variance64x128_c Unexecuted instantiation: aom_highbd_12_masked_sub_pixel_variance128x64_c Unexecuted instantiation: aom_highbd_12_masked_sub_pixel_variance128x128_c Unexecuted instantiation: aom_highbd_12_masked_sub_pixel_variance4x16_c Unexecuted instantiation: aom_highbd_12_masked_sub_pixel_variance16x4_c Unexecuted instantiation: aom_highbd_12_masked_sub_pixel_variance8x32_c Unexecuted instantiation: aom_highbd_12_masked_sub_pixel_variance32x8_c Unexecuted instantiation: aom_highbd_12_masked_sub_pixel_variance16x64_c Unexecuted instantiation: aom_highbd_12_masked_sub_pixel_variance64x16_c |
892 | | |
893 | | HIGHBD_MASK_SUBPIX_VAR(4, 4) |
894 | | HIGHBD_MASK_SUBPIX_VAR(4, 8) |
895 | | HIGHBD_MASK_SUBPIX_VAR(8, 4) |
896 | | HIGHBD_MASK_SUBPIX_VAR(8, 8) |
897 | | HIGHBD_MASK_SUBPIX_VAR(8, 16) |
898 | | HIGHBD_MASK_SUBPIX_VAR(16, 8) |
899 | | HIGHBD_MASK_SUBPIX_VAR(16, 16) |
900 | | HIGHBD_MASK_SUBPIX_VAR(16, 32) |
901 | | HIGHBD_MASK_SUBPIX_VAR(32, 16) |
902 | | HIGHBD_MASK_SUBPIX_VAR(32, 32) |
903 | | HIGHBD_MASK_SUBPIX_VAR(32, 64) |
904 | | HIGHBD_MASK_SUBPIX_VAR(64, 32) |
905 | | HIGHBD_MASK_SUBPIX_VAR(64, 64) |
906 | | HIGHBD_MASK_SUBPIX_VAR(64, 128) |
907 | | HIGHBD_MASK_SUBPIX_VAR(128, 64) |
908 | | HIGHBD_MASK_SUBPIX_VAR(128, 128) |
909 | | #if !CONFIG_REALTIME_ONLY |
910 | | HIGHBD_MASK_SUBPIX_VAR(4, 16) |
911 | | HIGHBD_MASK_SUBPIX_VAR(16, 4) |
912 | | HIGHBD_MASK_SUBPIX_VAR(8, 32) |
913 | | HIGHBD_MASK_SUBPIX_VAR(32, 8) |
914 | | HIGHBD_MASK_SUBPIX_VAR(16, 64) |
915 | | HIGHBD_MASK_SUBPIX_VAR(64, 16) |
916 | | #endif |
917 | | #endif // CONFIG_AV1_HIGHBITDEPTH |
918 | | |
919 | | #if !CONFIG_REALTIME_ONLY |
920 | | static INLINE void obmc_variance(const uint8_t *pre, int pre_stride, |
921 | | const int32_t *wsrc, const int32_t *mask, |
922 | 0 | int w, int h, unsigned int *sse, int *sum) { |
923 | 0 | int i, j; |
924 | |
|
925 | 0 | *sse = 0; |
926 | 0 | *sum = 0; |
927 | |
|
928 | 0 | for (i = 0; i < h; i++) { |
929 | 0 | for (j = 0; j < w; j++) { |
930 | 0 | int diff = ROUND_POWER_OF_TWO_SIGNED(wsrc[j] - pre[j] * mask[j], 12); |
931 | 0 | *sum += diff; |
932 | 0 | *sse += diff * diff; |
933 | 0 | } |
934 | |
|
935 | 0 | pre += pre_stride; |
936 | 0 | wsrc += w; |
937 | 0 | mask += w; |
938 | 0 | } |
939 | 0 | } |
940 | | |
941 | | #define OBMC_VAR(W, H) \ |
942 | | unsigned int aom_obmc_variance##W##x##H##_c( \ |
943 | | const uint8_t *pre, int pre_stride, const int32_t *wsrc, \ |
944 | 0 | const int32_t *mask, unsigned int *sse) { \ |
945 | 0 | int sum; \ |
946 | 0 | obmc_variance(pre, pre_stride, wsrc, mask, W, H, sse, &sum); \ |
947 | 0 | return *sse - (unsigned int)(((int64_t)sum * sum) / (W * H)); \ |
948 | 0 | } Unexecuted instantiation: aom_obmc_variance4x4_c Unexecuted instantiation: aom_obmc_variance4x8_c Unexecuted instantiation: aom_obmc_variance8x4_c Unexecuted instantiation: aom_obmc_variance8x8_c Unexecuted instantiation: aom_obmc_variance8x16_c Unexecuted instantiation: aom_obmc_variance16x8_c Unexecuted instantiation: aom_obmc_variance16x16_c Unexecuted instantiation: aom_obmc_variance16x32_c Unexecuted instantiation: aom_obmc_variance32x16_c Unexecuted instantiation: aom_obmc_variance32x32_c Unexecuted instantiation: aom_obmc_variance32x64_c Unexecuted instantiation: aom_obmc_variance64x32_c Unexecuted instantiation: aom_obmc_variance64x64_c Unexecuted instantiation: aom_obmc_variance64x128_c Unexecuted instantiation: aom_obmc_variance128x64_c Unexecuted instantiation: aom_obmc_variance128x128_c Unexecuted instantiation: aom_obmc_variance4x16_c Unexecuted instantiation: aom_obmc_variance16x4_c Unexecuted instantiation: aom_obmc_variance8x32_c Unexecuted instantiation: aom_obmc_variance32x8_c Unexecuted instantiation: aom_obmc_variance16x64_c Unexecuted instantiation: aom_obmc_variance64x16_c |
949 | | |
950 | | #define OBMC_SUBPIX_VAR(W, H) \ |
951 | | unsigned int aom_obmc_sub_pixel_variance##W##x##H##_c( \ |
952 | | const uint8_t *pre, int pre_stride, int xoffset, int yoffset, \ |
953 | 0 | const int32_t *wsrc, const int32_t *mask, unsigned int *sse) { \ |
954 | 0 | uint16_t fdata3[(H + 1) * W]; \ |
955 | 0 | uint8_t temp2[H * W]; \ |
956 | 0 | \ |
957 | 0 | aom_var_filter_block2d_bil_first_pass_c(pre, fdata3, pre_stride, 1, H + 1, \ |
958 | 0 | W, bilinear_filters_2t[xoffset]); \ |
959 | 0 | aom_var_filter_block2d_bil_second_pass_c(fdata3, temp2, W, W, H, W, \ |
960 | 0 | bilinear_filters_2t[yoffset]); \ |
961 | 0 | \ |
962 | 0 | return aom_obmc_variance##W##x##H##_c(temp2, W, wsrc, mask, sse); \ |
963 | 0 | } Unexecuted instantiation: aom_obmc_sub_pixel_variance4x4_c Unexecuted instantiation: aom_obmc_sub_pixel_variance4x8_c Unexecuted instantiation: aom_obmc_sub_pixel_variance8x4_c Unexecuted instantiation: aom_obmc_sub_pixel_variance8x8_c Unexecuted instantiation: aom_obmc_sub_pixel_variance8x16_c Unexecuted instantiation: aom_obmc_sub_pixel_variance16x8_c Unexecuted instantiation: aom_obmc_sub_pixel_variance16x16_c Unexecuted instantiation: aom_obmc_sub_pixel_variance16x32_c Unexecuted instantiation: aom_obmc_sub_pixel_variance32x16_c Unexecuted instantiation: aom_obmc_sub_pixel_variance32x32_c Unexecuted instantiation: aom_obmc_sub_pixel_variance32x64_c Unexecuted instantiation: aom_obmc_sub_pixel_variance64x32_c Unexecuted instantiation: aom_obmc_sub_pixel_variance64x64_c Unexecuted instantiation: aom_obmc_sub_pixel_variance64x128_c Unexecuted instantiation: aom_obmc_sub_pixel_variance128x64_c Unexecuted instantiation: aom_obmc_sub_pixel_variance128x128_c Unexecuted instantiation: aom_obmc_sub_pixel_variance4x16_c Unexecuted instantiation: aom_obmc_sub_pixel_variance16x4_c Unexecuted instantiation: aom_obmc_sub_pixel_variance8x32_c Unexecuted instantiation: aom_obmc_sub_pixel_variance32x8_c Unexecuted instantiation: aom_obmc_sub_pixel_variance16x64_c Unexecuted instantiation: aom_obmc_sub_pixel_variance64x16_c |
964 | | |
965 | | OBMC_VAR(4, 4) |
966 | | OBMC_SUBPIX_VAR(4, 4) |
967 | | |
968 | | OBMC_VAR(4, 8) |
969 | | OBMC_SUBPIX_VAR(4, 8) |
970 | | |
971 | | OBMC_VAR(8, 4) |
972 | | OBMC_SUBPIX_VAR(8, 4) |
973 | | |
974 | | OBMC_VAR(8, 8) |
975 | | OBMC_SUBPIX_VAR(8, 8) |
976 | | |
977 | | OBMC_VAR(8, 16) |
978 | | OBMC_SUBPIX_VAR(8, 16) |
979 | | |
980 | | OBMC_VAR(16, 8) |
981 | | OBMC_SUBPIX_VAR(16, 8) |
982 | | |
983 | | OBMC_VAR(16, 16) |
984 | | OBMC_SUBPIX_VAR(16, 16) |
985 | | |
986 | | OBMC_VAR(16, 32) |
987 | | OBMC_SUBPIX_VAR(16, 32) |
988 | | |
989 | | OBMC_VAR(32, 16) |
990 | | OBMC_SUBPIX_VAR(32, 16) |
991 | | |
992 | | OBMC_VAR(32, 32) |
993 | | OBMC_SUBPIX_VAR(32, 32) |
994 | | |
995 | | OBMC_VAR(32, 64) |
996 | | OBMC_SUBPIX_VAR(32, 64) |
997 | | |
998 | | OBMC_VAR(64, 32) |
999 | | OBMC_SUBPIX_VAR(64, 32) |
1000 | | |
1001 | | OBMC_VAR(64, 64) |
1002 | | OBMC_SUBPIX_VAR(64, 64) |
1003 | | |
1004 | | OBMC_VAR(64, 128) |
1005 | | OBMC_SUBPIX_VAR(64, 128) |
1006 | | |
1007 | | OBMC_VAR(128, 64) |
1008 | | OBMC_SUBPIX_VAR(128, 64) |
1009 | | |
1010 | | OBMC_VAR(128, 128) |
1011 | | OBMC_SUBPIX_VAR(128, 128) |
1012 | | |
1013 | | OBMC_VAR(4, 16) |
1014 | | OBMC_SUBPIX_VAR(4, 16) |
1015 | | OBMC_VAR(16, 4) |
1016 | | OBMC_SUBPIX_VAR(16, 4) |
1017 | | OBMC_VAR(8, 32) |
1018 | | OBMC_SUBPIX_VAR(8, 32) |
1019 | | OBMC_VAR(32, 8) |
1020 | | OBMC_SUBPIX_VAR(32, 8) |
1021 | | OBMC_VAR(16, 64) |
1022 | | OBMC_SUBPIX_VAR(16, 64) |
1023 | | OBMC_VAR(64, 16) |
1024 | | OBMC_SUBPIX_VAR(64, 16) |
1025 | | |
1026 | | #if CONFIG_AV1_HIGHBITDEPTH |
1027 | | static INLINE void highbd_obmc_variance64(const uint8_t *pre8, int pre_stride, |
1028 | | const int32_t *wsrc, |
1029 | | const int32_t *mask, int w, int h, |
1030 | 0 | uint64_t *sse, int64_t *sum) { |
1031 | 0 | int i, j; |
1032 | 0 | uint16_t *pre = CONVERT_TO_SHORTPTR(pre8); |
1033 | |
|
1034 | 0 | *sse = 0; |
1035 | 0 | *sum = 0; |
1036 | |
|
1037 | 0 | for (i = 0; i < h; i++) { |
1038 | 0 | for (j = 0; j < w; j++) { |
1039 | 0 | int diff = ROUND_POWER_OF_TWO_SIGNED(wsrc[j] - pre[j] * mask[j], 12); |
1040 | 0 | *sum += diff; |
1041 | 0 | *sse += diff * diff; |
1042 | 0 | } |
1043 | |
|
1044 | 0 | pre += pre_stride; |
1045 | 0 | wsrc += w; |
1046 | 0 | mask += w; |
1047 | 0 | } |
1048 | 0 | } |
1049 | | |
1050 | | static INLINE void highbd_obmc_variance(const uint8_t *pre8, int pre_stride, |
1051 | | const int32_t *wsrc, |
1052 | | const int32_t *mask, int w, int h, |
1053 | 0 | unsigned int *sse, int *sum) { |
1054 | 0 | int64_t sum64; |
1055 | 0 | uint64_t sse64; |
1056 | 0 | highbd_obmc_variance64(pre8, pre_stride, wsrc, mask, w, h, &sse64, &sum64); |
1057 | 0 | *sum = (int)sum64; |
1058 | 0 | *sse = (unsigned int)sse64; |
1059 | 0 | } |
1060 | | |
1061 | | static INLINE void highbd_10_obmc_variance(const uint8_t *pre8, int pre_stride, |
1062 | | const int32_t *wsrc, |
1063 | | const int32_t *mask, int w, int h, |
1064 | 0 | unsigned int *sse, int *sum) { |
1065 | 0 | int64_t sum64; |
1066 | 0 | uint64_t sse64; |
1067 | 0 | highbd_obmc_variance64(pre8, pre_stride, wsrc, mask, w, h, &sse64, &sum64); |
1068 | 0 | *sum = (int)ROUND_POWER_OF_TWO(sum64, 2); |
1069 | 0 | *sse = (unsigned int)ROUND_POWER_OF_TWO(sse64, 4); |
1070 | 0 | } |
1071 | | |
1072 | | static INLINE void highbd_12_obmc_variance(const uint8_t *pre8, int pre_stride, |
1073 | | const int32_t *wsrc, |
1074 | | const int32_t *mask, int w, int h, |
1075 | 0 | unsigned int *sse, int *sum) { |
1076 | 0 | int64_t sum64; |
1077 | 0 | uint64_t sse64; |
1078 | 0 | highbd_obmc_variance64(pre8, pre_stride, wsrc, mask, w, h, &sse64, &sum64); |
1079 | 0 | *sum = (int)ROUND_POWER_OF_TWO(sum64, 4); |
1080 | 0 | *sse = (unsigned int)ROUND_POWER_OF_TWO(sse64, 8); |
1081 | 0 | } |
1082 | | |
1083 | | #define HIGHBD_OBMC_VAR(W, H) \ |
1084 | | unsigned int aom_highbd_obmc_variance##W##x##H##_c( \ |
1085 | | const uint8_t *pre, int pre_stride, const int32_t *wsrc, \ |
1086 | 0 | const int32_t *mask, unsigned int *sse) { \ |
1087 | 0 | int sum; \ |
1088 | 0 | highbd_obmc_variance(pre, pre_stride, wsrc, mask, W, H, sse, &sum); \ |
1089 | 0 | return *sse - (unsigned int)(((int64_t)sum * sum) / (W * H)); \ |
1090 | 0 | } \ Unexecuted instantiation: aom_highbd_obmc_variance4x4_c Unexecuted instantiation: aom_highbd_obmc_variance4x8_c Unexecuted instantiation: aom_highbd_obmc_variance8x4_c Unexecuted instantiation: aom_highbd_obmc_variance8x8_c Unexecuted instantiation: aom_highbd_obmc_variance8x16_c Unexecuted instantiation: aom_highbd_obmc_variance16x8_c Unexecuted instantiation: aom_highbd_obmc_variance16x16_c Unexecuted instantiation: aom_highbd_obmc_variance16x32_c Unexecuted instantiation: aom_highbd_obmc_variance32x16_c Unexecuted instantiation: aom_highbd_obmc_variance32x32_c Unexecuted instantiation: aom_highbd_obmc_variance32x64_c Unexecuted instantiation: aom_highbd_obmc_variance64x32_c Unexecuted instantiation: aom_highbd_obmc_variance64x64_c Unexecuted instantiation: aom_highbd_obmc_variance64x128_c Unexecuted instantiation: aom_highbd_obmc_variance128x64_c Unexecuted instantiation: aom_highbd_obmc_variance128x128_c Unexecuted instantiation: aom_highbd_obmc_variance4x16_c Unexecuted instantiation: aom_highbd_obmc_variance16x4_c Unexecuted instantiation: aom_highbd_obmc_variance8x32_c Unexecuted instantiation: aom_highbd_obmc_variance32x8_c Unexecuted instantiation: aom_highbd_obmc_variance16x64_c Unexecuted instantiation: aom_highbd_obmc_variance64x16_c |
1091 | | \ |
1092 | | unsigned int aom_highbd_10_obmc_variance##W##x##H##_c( \ |
1093 | | const uint8_t *pre, int pre_stride, const int32_t *wsrc, \ |
1094 | 0 | const int32_t *mask, unsigned int *sse) { \ |
1095 | 0 | int sum; \ |
1096 | 0 | int64_t var; \ |
1097 | 0 | highbd_10_obmc_variance(pre, pre_stride, wsrc, mask, W, H, sse, &sum); \ |
1098 | 0 | var = (int64_t)(*sse) - (((int64_t)sum * sum) / (W * H)); \ |
1099 | 0 | return (var >= 0) ? (uint32_t)var : 0; \ |
1100 | 0 | } \ Unexecuted instantiation: aom_highbd_10_obmc_variance4x4_c Unexecuted instantiation: aom_highbd_10_obmc_variance4x8_c Unexecuted instantiation: aom_highbd_10_obmc_variance8x4_c Unexecuted instantiation: aom_highbd_10_obmc_variance8x8_c Unexecuted instantiation: aom_highbd_10_obmc_variance8x16_c Unexecuted instantiation: aom_highbd_10_obmc_variance16x8_c Unexecuted instantiation: aom_highbd_10_obmc_variance16x16_c Unexecuted instantiation: aom_highbd_10_obmc_variance16x32_c Unexecuted instantiation: aom_highbd_10_obmc_variance32x16_c Unexecuted instantiation: aom_highbd_10_obmc_variance32x32_c Unexecuted instantiation: aom_highbd_10_obmc_variance32x64_c Unexecuted instantiation: aom_highbd_10_obmc_variance64x32_c Unexecuted instantiation: aom_highbd_10_obmc_variance64x64_c Unexecuted instantiation: aom_highbd_10_obmc_variance64x128_c Unexecuted instantiation: aom_highbd_10_obmc_variance128x64_c Unexecuted instantiation: aom_highbd_10_obmc_variance128x128_c Unexecuted instantiation: aom_highbd_10_obmc_variance4x16_c Unexecuted instantiation: aom_highbd_10_obmc_variance16x4_c Unexecuted instantiation: aom_highbd_10_obmc_variance8x32_c Unexecuted instantiation: aom_highbd_10_obmc_variance32x8_c Unexecuted instantiation: aom_highbd_10_obmc_variance16x64_c Unexecuted instantiation: aom_highbd_10_obmc_variance64x16_c |
1101 | | \ |
1102 | | unsigned int aom_highbd_12_obmc_variance##W##x##H##_c( \ |
1103 | | const uint8_t *pre, int pre_stride, const int32_t *wsrc, \ |
1104 | 0 | const int32_t *mask, unsigned int *sse) { \ |
1105 | 0 | int sum; \ |
1106 | 0 | int64_t var; \ |
1107 | 0 | highbd_12_obmc_variance(pre, pre_stride, wsrc, mask, W, H, sse, &sum); \ |
1108 | 0 | var = (int64_t)(*sse) - (((int64_t)sum * sum) / (W * H)); \ |
1109 | 0 | return (var >= 0) ? (uint32_t)var : 0; \ |
1110 | 0 | } Unexecuted instantiation: aom_highbd_12_obmc_variance4x4_c Unexecuted instantiation: aom_highbd_12_obmc_variance4x8_c Unexecuted instantiation: aom_highbd_12_obmc_variance8x4_c Unexecuted instantiation: aom_highbd_12_obmc_variance8x8_c Unexecuted instantiation: aom_highbd_12_obmc_variance8x16_c Unexecuted instantiation: aom_highbd_12_obmc_variance16x8_c Unexecuted instantiation: aom_highbd_12_obmc_variance16x16_c Unexecuted instantiation: aom_highbd_12_obmc_variance16x32_c Unexecuted instantiation: aom_highbd_12_obmc_variance32x16_c Unexecuted instantiation: aom_highbd_12_obmc_variance32x32_c Unexecuted instantiation: aom_highbd_12_obmc_variance32x64_c Unexecuted instantiation: aom_highbd_12_obmc_variance64x32_c Unexecuted instantiation: aom_highbd_12_obmc_variance64x64_c Unexecuted instantiation: aom_highbd_12_obmc_variance64x128_c Unexecuted instantiation: aom_highbd_12_obmc_variance128x64_c Unexecuted instantiation: aom_highbd_12_obmc_variance128x128_c Unexecuted instantiation: aom_highbd_12_obmc_variance4x16_c Unexecuted instantiation: aom_highbd_12_obmc_variance16x4_c Unexecuted instantiation: aom_highbd_12_obmc_variance8x32_c Unexecuted instantiation: aom_highbd_12_obmc_variance32x8_c Unexecuted instantiation: aom_highbd_12_obmc_variance16x64_c Unexecuted instantiation: aom_highbd_12_obmc_variance64x16_c |
1111 | | |
1112 | | #define HIGHBD_OBMC_SUBPIX_VAR(W, H) \ |
1113 | | unsigned int aom_highbd_obmc_sub_pixel_variance##W##x##H##_c( \ |
1114 | | const uint8_t *pre, int pre_stride, int xoffset, int yoffset, \ |
1115 | 0 | const int32_t *wsrc, const int32_t *mask, unsigned int *sse) { \ |
1116 | 0 | uint16_t fdata3[(H + 1) * W]; \ |
1117 | 0 | uint16_t temp2[H * W]; \ |
1118 | 0 | \ |
1119 | 0 | aom_highbd_var_filter_block2d_bil_first_pass( \ |
1120 | 0 | pre, fdata3, pre_stride, 1, H + 1, W, bilinear_filters_2t[xoffset]); \ |
1121 | 0 | aom_highbd_var_filter_block2d_bil_second_pass( \ |
1122 | 0 | fdata3, temp2, W, W, H, W, bilinear_filters_2t[yoffset]); \ |
1123 | 0 | \ |
1124 | 0 | return aom_highbd_obmc_variance##W##x##H##_c(CONVERT_TO_BYTEPTR(temp2), W, \ |
1125 | 0 | wsrc, mask, sse); \ |
1126 | 0 | } \ Unexecuted instantiation: aom_highbd_obmc_sub_pixel_variance4x4_c Unexecuted instantiation: aom_highbd_obmc_sub_pixel_variance4x8_c Unexecuted instantiation: aom_highbd_obmc_sub_pixel_variance8x4_c Unexecuted instantiation: aom_highbd_obmc_sub_pixel_variance8x8_c Unexecuted instantiation: aom_highbd_obmc_sub_pixel_variance8x16_c Unexecuted instantiation: aom_highbd_obmc_sub_pixel_variance16x8_c Unexecuted instantiation: aom_highbd_obmc_sub_pixel_variance16x16_c Unexecuted instantiation: aom_highbd_obmc_sub_pixel_variance16x32_c Unexecuted instantiation: aom_highbd_obmc_sub_pixel_variance32x16_c Unexecuted instantiation: aom_highbd_obmc_sub_pixel_variance32x32_c Unexecuted instantiation: aom_highbd_obmc_sub_pixel_variance32x64_c Unexecuted instantiation: aom_highbd_obmc_sub_pixel_variance64x32_c Unexecuted instantiation: aom_highbd_obmc_sub_pixel_variance64x64_c Unexecuted instantiation: aom_highbd_obmc_sub_pixel_variance64x128_c Unexecuted instantiation: aom_highbd_obmc_sub_pixel_variance128x64_c Unexecuted instantiation: aom_highbd_obmc_sub_pixel_variance128x128_c Unexecuted instantiation: aom_highbd_obmc_sub_pixel_variance4x16_c Unexecuted instantiation: aom_highbd_obmc_sub_pixel_variance16x4_c Unexecuted instantiation: aom_highbd_obmc_sub_pixel_variance8x32_c Unexecuted instantiation: aom_highbd_obmc_sub_pixel_variance32x8_c Unexecuted instantiation: aom_highbd_obmc_sub_pixel_variance16x64_c Unexecuted instantiation: aom_highbd_obmc_sub_pixel_variance64x16_c |
1127 | | \ |
1128 | | unsigned int aom_highbd_10_obmc_sub_pixel_variance##W##x##H##_c( \ |
1129 | | const uint8_t *pre, int pre_stride, int xoffset, int yoffset, \ |
1130 | 0 | const int32_t *wsrc, const int32_t *mask, unsigned int *sse) { \ |
1131 | 0 | uint16_t fdata3[(H + 1) * W]; \ |
1132 | 0 | uint16_t temp2[H * W]; \ |
1133 | 0 | \ |
1134 | 0 | aom_highbd_var_filter_block2d_bil_first_pass( \ |
1135 | 0 | pre, fdata3, pre_stride, 1, H + 1, W, bilinear_filters_2t[xoffset]); \ |
1136 | 0 | aom_highbd_var_filter_block2d_bil_second_pass( \ |
1137 | 0 | fdata3, temp2, W, W, H, W, bilinear_filters_2t[yoffset]); \ |
1138 | 0 | \ |
1139 | 0 | return aom_highbd_10_obmc_variance##W##x##H##_c(CONVERT_TO_BYTEPTR(temp2), \ |
1140 | 0 | W, wsrc, mask, sse); \ |
1141 | 0 | } \ Unexecuted instantiation: aom_highbd_10_obmc_sub_pixel_variance4x4_c Unexecuted instantiation: aom_highbd_10_obmc_sub_pixel_variance4x8_c Unexecuted instantiation: aom_highbd_10_obmc_sub_pixel_variance8x4_c Unexecuted instantiation: aom_highbd_10_obmc_sub_pixel_variance8x8_c Unexecuted instantiation: aom_highbd_10_obmc_sub_pixel_variance8x16_c Unexecuted instantiation: aom_highbd_10_obmc_sub_pixel_variance16x8_c Unexecuted instantiation: aom_highbd_10_obmc_sub_pixel_variance16x16_c Unexecuted instantiation: aom_highbd_10_obmc_sub_pixel_variance16x32_c Unexecuted instantiation: aom_highbd_10_obmc_sub_pixel_variance32x16_c Unexecuted instantiation: aom_highbd_10_obmc_sub_pixel_variance32x32_c Unexecuted instantiation: aom_highbd_10_obmc_sub_pixel_variance32x64_c Unexecuted instantiation: aom_highbd_10_obmc_sub_pixel_variance64x32_c Unexecuted instantiation: aom_highbd_10_obmc_sub_pixel_variance64x64_c Unexecuted instantiation: aom_highbd_10_obmc_sub_pixel_variance64x128_c Unexecuted instantiation: aom_highbd_10_obmc_sub_pixel_variance128x64_c Unexecuted instantiation: aom_highbd_10_obmc_sub_pixel_variance128x128_c Unexecuted instantiation: aom_highbd_10_obmc_sub_pixel_variance4x16_c Unexecuted instantiation: aom_highbd_10_obmc_sub_pixel_variance16x4_c Unexecuted instantiation: aom_highbd_10_obmc_sub_pixel_variance8x32_c Unexecuted instantiation: aom_highbd_10_obmc_sub_pixel_variance32x8_c Unexecuted instantiation: aom_highbd_10_obmc_sub_pixel_variance16x64_c Unexecuted instantiation: aom_highbd_10_obmc_sub_pixel_variance64x16_c |
1142 | | \ |
1143 | | unsigned int aom_highbd_12_obmc_sub_pixel_variance##W##x##H##_c( \ |
1144 | | const uint8_t *pre, int pre_stride, int xoffset, int yoffset, \ |
1145 | 0 | const int32_t *wsrc, const int32_t *mask, unsigned int *sse) { \ |
1146 | 0 | uint16_t fdata3[(H + 1) * W]; \ |
1147 | 0 | uint16_t temp2[H * W]; \ |
1148 | 0 | \ |
1149 | 0 | aom_highbd_var_filter_block2d_bil_first_pass( \ |
1150 | 0 | pre, fdata3, pre_stride, 1, H + 1, W, bilinear_filters_2t[xoffset]); \ |
1151 | 0 | aom_highbd_var_filter_block2d_bil_second_pass( \ |
1152 | 0 | fdata3, temp2, W, W, H, W, bilinear_filters_2t[yoffset]); \ |
1153 | 0 | \ |
1154 | 0 | return aom_highbd_12_obmc_variance##W##x##H##_c(CONVERT_TO_BYTEPTR(temp2), \ |
1155 | 0 | W, wsrc, mask, sse); \ |
1156 | 0 | } Unexecuted instantiation: aom_highbd_12_obmc_sub_pixel_variance4x4_c Unexecuted instantiation: aom_highbd_12_obmc_sub_pixel_variance4x8_c Unexecuted instantiation: aom_highbd_12_obmc_sub_pixel_variance8x4_c Unexecuted instantiation: aom_highbd_12_obmc_sub_pixel_variance8x8_c Unexecuted instantiation: aom_highbd_12_obmc_sub_pixel_variance8x16_c Unexecuted instantiation: aom_highbd_12_obmc_sub_pixel_variance16x8_c Unexecuted instantiation: aom_highbd_12_obmc_sub_pixel_variance16x16_c Unexecuted instantiation: aom_highbd_12_obmc_sub_pixel_variance16x32_c Unexecuted instantiation: aom_highbd_12_obmc_sub_pixel_variance32x16_c Unexecuted instantiation: aom_highbd_12_obmc_sub_pixel_variance32x32_c Unexecuted instantiation: aom_highbd_12_obmc_sub_pixel_variance32x64_c Unexecuted instantiation: aom_highbd_12_obmc_sub_pixel_variance64x32_c Unexecuted instantiation: aom_highbd_12_obmc_sub_pixel_variance64x64_c Unexecuted instantiation: aom_highbd_12_obmc_sub_pixel_variance64x128_c Unexecuted instantiation: aom_highbd_12_obmc_sub_pixel_variance128x64_c Unexecuted instantiation: aom_highbd_12_obmc_sub_pixel_variance128x128_c Unexecuted instantiation: aom_highbd_12_obmc_sub_pixel_variance4x16_c Unexecuted instantiation: aom_highbd_12_obmc_sub_pixel_variance16x4_c Unexecuted instantiation: aom_highbd_12_obmc_sub_pixel_variance8x32_c Unexecuted instantiation: aom_highbd_12_obmc_sub_pixel_variance32x8_c Unexecuted instantiation: aom_highbd_12_obmc_sub_pixel_variance16x64_c Unexecuted instantiation: aom_highbd_12_obmc_sub_pixel_variance64x16_c |
1157 | | |
1158 | | HIGHBD_OBMC_VAR(4, 4) |
1159 | | HIGHBD_OBMC_SUBPIX_VAR(4, 4) |
1160 | | |
1161 | | HIGHBD_OBMC_VAR(4, 8) |
1162 | | HIGHBD_OBMC_SUBPIX_VAR(4, 8) |
1163 | | |
1164 | | HIGHBD_OBMC_VAR(8, 4) |
1165 | | HIGHBD_OBMC_SUBPIX_VAR(8, 4) |
1166 | | |
1167 | | HIGHBD_OBMC_VAR(8, 8) |
1168 | | HIGHBD_OBMC_SUBPIX_VAR(8, 8) |
1169 | | |
1170 | | HIGHBD_OBMC_VAR(8, 16) |
1171 | | HIGHBD_OBMC_SUBPIX_VAR(8, 16) |
1172 | | |
1173 | | HIGHBD_OBMC_VAR(16, 8) |
1174 | | HIGHBD_OBMC_SUBPIX_VAR(16, 8) |
1175 | | |
1176 | | HIGHBD_OBMC_VAR(16, 16) |
1177 | | HIGHBD_OBMC_SUBPIX_VAR(16, 16) |
1178 | | |
1179 | | HIGHBD_OBMC_VAR(16, 32) |
1180 | | HIGHBD_OBMC_SUBPIX_VAR(16, 32) |
1181 | | |
1182 | | HIGHBD_OBMC_VAR(32, 16) |
1183 | | HIGHBD_OBMC_SUBPIX_VAR(32, 16) |
1184 | | |
1185 | | HIGHBD_OBMC_VAR(32, 32) |
1186 | | HIGHBD_OBMC_SUBPIX_VAR(32, 32) |
1187 | | |
1188 | | HIGHBD_OBMC_VAR(32, 64) |
1189 | | HIGHBD_OBMC_SUBPIX_VAR(32, 64) |
1190 | | |
1191 | | HIGHBD_OBMC_VAR(64, 32) |
1192 | | HIGHBD_OBMC_SUBPIX_VAR(64, 32) |
1193 | | |
1194 | | HIGHBD_OBMC_VAR(64, 64) |
1195 | | HIGHBD_OBMC_SUBPIX_VAR(64, 64) |
1196 | | |
1197 | | HIGHBD_OBMC_VAR(64, 128) |
1198 | | HIGHBD_OBMC_SUBPIX_VAR(64, 128) |
1199 | | |
1200 | | HIGHBD_OBMC_VAR(128, 64) |
1201 | | HIGHBD_OBMC_SUBPIX_VAR(128, 64) |
1202 | | |
1203 | | HIGHBD_OBMC_VAR(128, 128) |
1204 | | HIGHBD_OBMC_SUBPIX_VAR(128, 128) |
1205 | | |
1206 | | HIGHBD_OBMC_VAR(4, 16) |
1207 | | HIGHBD_OBMC_SUBPIX_VAR(4, 16) |
1208 | | HIGHBD_OBMC_VAR(16, 4) |
1209 | | HIGHBD_OBMC_SUBPIX_VAR(16, 4) |
1210 | | HIGHBD_OBMC_VAR(8, 32) |
1211 | | HIGHBD_OBMC_SUBPIX_VAR(8, 32) |
1212 | | HIGHBD_OBMC_VAR(32, 8) |
1213 | | HIGHBD_OBMC_SUBPIX_VAR(32, 8) |
1214 | | HIGHBD_OBMC_VAR(16, 64) |
1215 | | HIGHBD_OBMC_SUBPIX_VAR(16, 64) |
1216 | | HIGHBD_OBMC_VAR(64, 16) |
1217 | | HIGHBD_OBMC_SUBPIX_VAR(64, 16) |
1218 | | #endif // CONFIG_AV1_HIGHBITDEPTH |
1219 | | #endif // !CONFIG_REALTIME_ONLY |
1220 | | |
1221 | | uint64_t aom_mse_wxh_16bit_c(uint8_t *dst, int dstride, uint16_t *src, |
1222 | 0 | int sstride, int w, int h) { |
1223 | 0 | uint64_t sum = 0; |
1224 | 0 | for (int i = 0; i < h; i++) { |
1225 | 0 | for (int j = 0; j < w; j++) { |
1226 | 0 | int e = (uint16_t)dst[i * dstride + j] - src[i * sstride + j]; |
1227 | 0 | sum += e * e; |
1228 | 0 | } |
1229 | 0 | } |
1230 | 0 | return sum; |
1231 | 0 | } |
1232 | | |
1233 | | uint64_t aom_mse_wxh_16bit_highbd_c(uint16_t *dst, int dstride, uint16_t *src, |
1234 | 0 | int sstride, int w, int h) { |
1235 | 0 | uint64_t sum = 0; |
1236 | 0 | for (int i = 0; i < h; i++) { |
1237 | 0 | for (int j = 0; j < w; j++) { |
1238 | 0 | int e = dst[i * dstride + j] - src[i * sstride + j]; |
1239 | 0 | sum += e * e; |
1240 | 0 | } |
1241 | 0 | } |
1242 | 0 | return sum; |
1243 | 0 | } |