2 * Copyright (c) 2016 Alexandra Hájková
4 * This file is part of FFmpeg.
6 * FFmpeg is free software; you can redistribute it and/or modify
7 * it under the terms of the GNU General Public License as published by
8 * the Free Software Foundation; either version 2 of the License, or
9 * (at your option) any later version.
11 * FFmpeg is distributed in the hope that it will be useful,
12 * but WITHOUT ANY WARRANTY; without even the implied warranty of
13 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
14 * GNU General Public License for more details.
16 * You should have received a copy of the GNU General Public License along
17 * with FFmpeg; if not, write to the Free Software Foundation, Inc.,
18 * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
23 #include "libavutil/intreadwrite.h"
24 #include "libavutil/mem_internal.h"
26 #include "libavcodec/hevcdsp.h"
30 #define randomize_buffers(buf, size) \
33 for (j = 0; j < size; j++) { \
35 AV_WN16A(buf + j, r >> 3); \
39 #define randomize_buffers2(buf, size) \
42 for (j = 0; j < size; j++) \
43 AV_WN16A(buf + j * 2, rnd() & 0x3FF); \
46 static void compare_add_res(int size, ptrdiff_t stride, int overflow_test)
48 LOCAL_ALIGNED_32(int16_t, res0, [32 * 32]);
49 LOCAL_ALIGNED_32(int16_t, res1, [32 * 32]);
50 LOCAL_ALIGNED_32(uint8_t, dst0, [32 * 32 * 2]);
51 LOCAL_ALIGNED_32(uint8_t, dst1, [32 * 32 * 2]);
53 declare_func_emms(AV_CPU_FLAG_MMX, void, uint8_t *dst, int16_t *res, ptrdiff_t stride);
55 randomize_buffers(res0, size);
56 randomize_buffers2(dst0, size);
59 memcpy(res1, res0, sizeof(*res0) * size);
60 memcpy(dst1, dst0, sizeof(int16_t) * size);
62 call_ref(dst0, res0, stride);
63 call_new(dst1, res1, stride);
64 if (memcmp(dst0, dst1, size))
66 bench_new(dst1, res1, stride);
69 static void check_add_res(HEVCDSPContext h, int bit_depth)
73 for (i = 2; i <= 5; i++) {
74 int block_size = 1 << i;
75 int size = block_size * block_size;
76 ptrdiff_t stride = block_size << (bit_depth > 8);
78 if (check_func(h.add_residual[i - 2], "hevc_add_res_%dx%d_%d", block_size, block_size, bit_depth)) {
79 compare_add_res(size, stride, 0);
80 // overflow test for res = -32768
81 compare_add_res(size, stride, 1);
86 void checkasm_check_hevc_add_res(void)
90 for (bit_depth = 8; bit_depth <= 10; bit_depth++) {
93 ff_hevc_dsp_init(&h, bit_depth);
94 check_add_res(h, bit_depth);
96 report("add_residual");