1/*
2 * Copyright (c) 2015 Henrik Gramner
3 *
4 * This file is part of FFmpeg.
5 *
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.
10 *
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.
15 *
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.
19 */
20
21#include <string.h>
22#include "checkasm.h"
23#include "libavcodec/h264qpel.h"
24#include "libavutil/common.h"
25#include "libavutil/internal.h"
26#include "libavutil/intreadwrite.h"
27#include "libavutil/mem_internal.h"
28
29static const uint32_t pixel_mask[3] = { 0xffffffff, 0x01ff01ff, 0x03ff03ff };
30
31#define SIZEOF_PIXEL ((bit_depth + 7) / 8)
32#define BUF_SIZE (2 * 16 * (16 + 3 + 4))
33
34#define randomize_buffers()                        \
35    do {                                           \
36        uint32_t mask = pixel_mask[bit_depth - 8]; \
37        int k;                                     \
38        for (k = 0; k < BUF_SIZE; k += 4) {        \
39            uint32_t r = rnd() & mask;             \
40            AV_WN32A(buf0 + k, r);                 \
41            AV_WN32A(buf1 + k, r);                 \
42            r = rnd();                             \
43            AV_WN32A(dst0 + k, r);                 \
44            AV_WN32A(dst1 + k, r);                 \
45        }                                          \
46    } while (0)
47
48#define src0 (buf0 + 3 * 2 * 16) /* h264qpel functions read data from negative src pointer offsets */
49#define src1 (buf1 + 3 * 2 * 16)
50
51void checkasm_check_h264qpel(void)
52{
53    LOCAL_ALIGNED_16(uint8_t, buf0, [BUF_SIZE]);
54    LOCAL_ALIGNED_16(uint8_t, buf1, [BUF_SIZE]);
55    LOCAL_ALIGNED_16(uint8_t, dst0, [BUF_SIZE]);
56    LOCAL_ALIGNED_16(uint8_t, dst1, [BUF_SIZE]);
57    H264QpelContext h;
58    int op, bit_depth, i, j;
59    declare_func_emms(AV_CPU_FLAG_MMX | AV_CPU_FLAG_MMXEXT, void, uint8_t *dst, const uint8_t *src, ptrdiff_t stride);
60
61    for (op = 0; op < 2; op++) {
62        qpel_mc_func (*tab)[16] = op ? h.avg_h264_qpel_pixels_tab : h.put_h264_qpel_pixels_tab;
63        const char *op_name = op ? "avg" : "put";
64
65        for (bit_depth = 8; bit_depth <= 10; bit_depth++) {
66            ff_h264qpel_init(&h, bit_depth);
67            for (i = 0; i < (op ? 3 : 4); i++) {
68                int size = 16 >> i;
69                for (j = 0; j < 16; j++)
70                    if (check_func(tab[i][j], "%s_h264_qpel_%d_mc%d%d_%d", op_name, size, j & 3, j >> 2, bit_depth)) {
71                        randomize_buffers();
72                        call_ref(dst0, src0, size * SIZEOF_PIXEL);
73                        call_new(dst1, src1, size * SIZEOF_PIXEL);
74                        if (memcmp(buf0, buf1, BUF_SIZE) || memcmp(dst0, dst1, BUF_SIZE))
75                            fail();
76                        bench_new(dst1, src1, size * SIZEOF_PIXEL);
77                    }
78            }
79        }
80        report("%s", op_name);
81    }
82}
83