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
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
|
/*
* Copyright (C) 2011 Hendrik Leppkes
* http://www.1f0.de
*
* This Program 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, or (at your option)
* any later version.
*
* This Program 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 this program; see the file COPYING. If not, write to
* the Free Software Foundation, 675 Mass Ave, Cambridge, MA 02139, USA.
* http://www.gnu.org/copyleft/gpl.html
*/
#include "stdafx.h"
#include <emmintrin.h>
#include "pixconv_internal.h"
#include "pixconv_sse2_templates.h"
#define PIXCONV_INTERLEAVE_AYUV(regY, regU, regV, regA, regOut1, regOut2) \
regY = _mm_unpacklo_epi8(regY, regA); /* YAYAYAYA */ \
regV = _mm_unpacklo_epi8(regV, regU); /* VUVUVUVU */ \
regOut1 = _mm_unpacklo_epi16(regV, regY); /* VUYAVUYA */ \
regOut2 = _mm_unpackhi_epi16(regV, regY); /* VUYAVUYA */
#define YUV444_PACK_AYUV(dst) *idst++ = v[i] | (u[i] << 8) | (y[i] << 16) | (0xff << 24);
DECLARE_CONV_FUNC_IMPL(convert_yuv444_ayuv)
{
const uint8_t *y = (const uint8_t *)src[0];
const uint8_t *u = (const uint8_t *)src[1];
const uint8_t *v = (const uint8_t *)src[2];
const int inStride = srcStride[0];
const int outStride = dstStride << 2;
int line, i;
__m128i xmm0,xmm1,xmm2,xmm3,xmm4,xmm5,xmm6;
xmm6 = _mm_set1_epi32(-1);
for (line = 0; line < height; ++line) {
__m128i *dst128 = (__m128i *)(dst + line * outStride);
for (i = 0; i < width; i+=16) {
// Load pixels into registers
PIXCONV_LOAD_PIXEL8_ALIGNED(xmm0, (y+i)); /* YYYYYYYY */
PIXCONV_LOAD_PIXEL8_ALIGNED(xmm1, (u+i)); /* UUUUUUUU */
PIXCONV_LOAD_PIXEL8_ALIGNED(xmm2, (v+i)); /* VVVVVVVV */
// Interlave into AYUV
xmm4 = xmm0;
xmm0 = _mm_unpacklo_epi8(xmm0, xmm6); /* YAYAYAYA */
xmm4 = _mm_unpackhi_epi8(xmm4, xmm6); /* YAYAYAYA */
xmm5 = xmm2;
xmm2 = _mm_unpacklo_epi8(xmm2, xmm1); /* VUVUVUVU */
xmm5 = _mm_unpackhi_epi8(xmm5, xmm1); /* VUVUVUVU */
xmm1 = _mm_unpacklo_epi16(xmm2, xmm0); /* VUYAVUYA */
xmm2 = _mm_unpackhi_epi16(xmm2, xmm0); /* VUYAVUYA */
xmm0 = _mm_unpacklo_epi16(xmm5, xmm4); /* VUYAVUYA */
xmm3 = _mm_unpackhi_epi16(xmm5, xmm4); /* VUYAVUYA */
// Write data back
_mm_stream_si128(dst128++, xmm1);
_mm_stream_si128(dst128++, xmm2);
_mm_stream_si128(dst128++, xmm0);
_mm_stream_si128(dst128++, xmm3);
}
y += inStride;
u += inStride;
v += inStride;
}
return S_OK;
}
DECLARE_CONV_FUNC_IMPL(convert_yuv444_ayuv_dither_le)
{
const uint16_t *y = (const uint16_t *)src[0];
const uint16_t *u = (const uint16_t *)src[1];
const uint16_t *v = (const uint16_t *)src[2];
const int inStride = srcStride[0] >> 1;
const int outStride = dstStride << 2;
// Number of bits to shift to reach 8
int shift = bpp - 8;
int line, i;
__m128i xmm0,xmm1,xmm2,xmm3,xmm4,xmm5,xmm6,xmm7;
xmm5 = _mm_setzero_si128();
xmm6 = _mm_set1_epi16(-256); /* 0xFF00 - 0A0A0A0A */
for (line = 0; line < height; ++line) {
// Load dithering coefficients for this line
PIXCONV_LOAD_DITHER_COEFFS(xmm7,line,shift,dithers);
__m128i *dst128 = (__m128i *)(dst + line * outStride);
for (i = 0; i < width; i+=8) {
// Load pixels into registers, and apply dithering
PIXCONV_LOAD_PIXEL16_DITHER(xmm0, xmm7, (y+i), shift); /* Y0Y0Y0Y0 */
PIXCONV_LOAD_PIXEL16_DITHER(xmm1, xmm7, (u+i), shift); /* U0U0U0U0 */
PIXCONV_LOAD_PIXEL16_DITHER(xmm2, xmm7, (v+i), shift); /* V0V0V0V0 */
// Interlave into AYUV
xmm0 = _mm_or_si128(xmm0, xmm6); /* YAYAYAYA */
xmm1 = _mm_slli_epi16(xmm1, 8); /* 0U0U0U0U */
xmm2 = _mm_or_si128(xmm2, xmm1); /* VUVUVUVU */
xmm3 = _mm_unpacklo_epi16(xmm2, xmm0); /* VUYAVUYA */
xmm4 = _mm_unpackhi_epi16(xmm2, xmm0); /* VUYAVUYA */
// Write data back
_mm_stream_si128(dst128++, xmm3);
_mm_stream_si128(dst128++, xmm4);
}
y += inStride;
u += inStride;
v += inStride;
}
return S_OK;
}
|
