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
|
/*
* SIMD-optimized lossless video encoding functions
* Copyright (c) 2000, 2001 Fabrice Bellard
* Copyright (c) 2002-2004 Michael Niedermayer <michaelni@gmx.at>
*
* MMX optimization by Nick Kurshev <nickols_k@mail.ru>
*
* This file is part of FFmpeg.
*
* FFmpeg is free software; you can redistribute it and/or
* modify it under the terms of the GNU Lesser General Public
* License as published by the Free Software Foundation; either
* version 2.1 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
* Lesser General Public License for more details.
*
* You should have received a copy of the GNU Lesser 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 "libavutil/attributes.h"
#include "libavutil/cpu.h"
#include "libavutil/x86/asm.h"
#include "libavutil/x86/cpu.h"
#include "libavcodec/lossless_videoencdsp.h"
#include "libavcodec/mathops.h"
void ff_diff_bytes_sse2(uint8_t *dst, const uint8_t *src1, const uint8_t *src2,
intptr_t w);
void ff_diff_bytes_avx2(uint8_t *dst, const uint8_t *src1, const uint8_t *src2,
intptr_t w);
void ff_sub_left_predict_avx(uint8_t *dst, const uint8_t *src,
ptrdiff_t stride, ptrdiff_t width, int height);
#if HAVE_INLINE_ASM
static void sub_median_pred_mmxext(uint8_t *dst, const uint8_t *src1,
const uint8_t *src2, intptr_t w,
int *left, int *left_top)
{
x86_reg i = 0;
uint8_t l, lt;
__asm__ volatile (
"movq (%1, %0), %%mm0 \n\t" // LT
"psllq $8, %%mm0 \n\t"
"1: \n\t"
"movq (%1, %0), %%mm1 \n\t" // T
"movq -1(%2, %0), %%mm2 \n\t" // L
"movq (%2, %0), %%mm3 \n\t" // X
"movq %%mm2, %%mm4 \n\t" // L
"psubb %%mm0, %%mm2 \n\t"
"paddb %%mm1, %%mm2 \n\t" // L + T - LT
"movq %%mm4, %%mm5 \n\t" // L
"pmaxub %%mm1, %%mm4 \n\t" // max(T, L)
"pminub %%mm5, %%mm1 \n\t" // min(T, L)
"pminub %%mm2, %%mm4 \n\t"
"pmaxub %%mm1, %%mm4 \n\t"
"psubb %%mm4, %%mm3 \n\t" // dst - pred
"movq %%mm3, (%3, %0) \n\t"
"add $8, %0 \n\t"
"movq -1(%1, %0), %%mm0 \n\t" // LT
"cmp %4, %0 \n\t"
" jb 1b \n\t"
: "+r" (i)
: "r" (src1), "r" (src2), "r" (dst), "r" ((x86_reg) w));
l = *left;
lt = *left_top;
dst[0] = src2[0] - mid_pred(l, src1[0], (l + src1[0] - lt) & 0xFF);
*left_top = src1[w - 1];
*left = src2[w - 1];
}
#endif /* HAVE_INLINE_ASM */
av_cold void ff_llvidencdsp_init_x86(LLVidEncDSPContext *c)
{
av_unused int cpu_flags = av_get_cpu_flags();
#if HAVE_INLINE_ASM
if (INLINE_MMXEXT(cpu_flags)) {
c->sub_median_pred = sub_median_pred_mmxext;
}
#endif /* HAVE_INLINE_ASM */
if (EXTERNAL_SSE2(cpu_flags)) {
c->diff_bytes = ff_diff_bytes_sse2;
}
if (EXTERNAL_AVX(cpu_flags)) {
c->sub_left_predict = ff_sub_left_predict_avx;
}
if (EXTERNAL_AVX2_FAST(cpu_flags)) {
c->diff_bytes = ff_diff_bytes_avx2;
}
}
|
