1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
|
/*
* Copyright (c) 2015 Tiancheng "Timothy" Gu
*
* This file is part of FFmpeg.
*
* FFmpeg is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* FFmpeg is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License along
* with FFmpeg; if not, write to the Free Software Foundation, Inc.,
* 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
*/
#include <string.h>
#include "checkasm.h"
#include "libavcodec/pixblockdsp.h"
#include "libavutil/common.h"
#include "libavutil/internal.h"
#include "libavutil/intreadwrite.h"
#define BUF_UNITS 8
#define BUF_SIZE (BUF_UNITS * 128 + 8 * BUF_UNITS)
#define randomize_buffers() \
do { \
int i; \
for (i = 0; i < BUF_SIZE; i += 4) { \
uint32_t r = rnd(); \
AV_WN32A(src10 + i, r); \
AV_WN32A(src11 + i, r); \
r = rnd(); \
AV_WN32A(src20 + i, r); \
AV_WN32A(src21 + i, r); \
r = rnd(); \
AV_WN32A(dst0_ + i, r); \
AV_WN32A(dst1_ + i, r); \
} \
} while (0)
#define check_get_pixels(type) \
do { \
int i; \
declare_func_emms(AV_CPU_FLAG_MMX, void, int16_t *block, const uint8_t *pixels, ptrdiff_t line_size); \
\
for (i = 0; i < BUF_UNITS; i++) { \
int src_offset = i * 64 * sizeof(type) + 8 * i; /* Test various alignments */ \
int dst_offset = i * 64; /* dst must be aligned */ \
randomize_buffers(); \
call_ref(dst0 + dst_offset, src10 + src_offset, 8); \
call_new(dst1 + dst_offset, src11 + src_offset, 8); \
if (memcmp(src10, src11, BUF_SIZE)|| memcmp(dst0, dst1, BUF_SIZE)) \
fail(); \
bench_new(dst1 + dst_offset, src11 + src_offset, 8); \
} \
} while (0)
#define check_diff_pixels(type) \
do { \
int i; \
declare_func_emms(AV_CPU_FLAG_MMX, void, int16_t *av_restrict block, const uint8_t *s1, const uint8_t *s2, int stride); \
\
for (i = 0; i < BUF_UNITS; i++) { \
int src_offset = i * 64 * sizeof(type) + 8 * i; /* Test various alignments */ \
int dst_offset = i * 64; /* dst must be aligned */ \
randomize_buffers(); \
call_ref(dst0 + dst_offset, src10 + src_offset, src20 + src_offset, 8); \
call_new(dst1 + dst_offset, src11 + src_offset, src21 + src_offset, 8); \
if (memcmp(src10, src11, BUF_SIZE) || memcmp(src20, src21, BUF_SIZE) || memcmp(dst0, dst1, BUF_SIZE)) \
fail(); \
bench_new(dst1 + dst_offset, src11 + src_offset, src21 + src_offset, 8); \
} \
} while (0)
void checkasm_check_pixblockdsp(void)
{
LOCAL_ALIGNED_16(uint8_t, src10, [BUF_SIZE]);
LOCAL_ALIGNED_16(uint8_t, src11, [BUF_SIZE]);
LOCAL_ALIGNED_16(uint8_t, src20, [BUF_SIZE]);
LOCAL_ALIGNED_16(uint8_t, src21, [BUF_SIZE]);
LOCAL_ALIGNED_16(uint8_t, dst0_, [BUF_SIZE]);
LOCAL_ALIGNED_16(uint8_t, dst1_, [BUF_SIZE]);
uint16_t *dst0 = (uint16_t *)dst0_;
uint16_t *dst1 = (uint16_t *)dst1_;
PixblockDSPContext h;
AVCodecContext avctx = {
.bits_per_raw_sample = 8,
};
ff_pixblockdsp_init(&h, &avctx);
if (check_func(h.get_pixels, "get_pixels"))
check_get_pixels(uint8_t);
report("get_pixels");
if (check_func(h.diff_pixels, "diff_pixels"))
check_diff_pixels(uint8_t);
report("diff_pixels");
}
|
