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
|
/****************************************************************************
**
** Copyright (C) 2015 The Qt Company Ltd.
** Contact: http://www.qt.io/licensing/
**
** This file is part of the Qt Toolkit.
**
** $QT_BEGIN_LICENSE:LGPL21$
** Commercial License Usage
** Licensees holding valid commercial Qt licenses may use this file in
** accordance with the commercial license agreement provided with the
** Software or, alternatively, in accordance with the terms contained in
** a written agreement between you and The Qt Company. For licensing terms
** and conditions see http://www.qt.io/terms-conditions. For further
** information use the contact form at http://www.qt.io/contact-us.
**
** GNU Lesser General Public License Usage
** Alternatively, this file may be used under the terms of the GNU Lesser
** General Public License version 2.1 or version 3 as published by the Free
** Software Foundation and appearing in the file LICENSE.LGPLv21 and
** LICENSE.LGPLv3 included in the packaging of this file. Please review the
** following information to ensure the GNU Lesser General Public License
** requirements will be met: https://www.gnu.org/licenses/lgpl.html and
** http://www.gnu.org/licenses/old-licenses/lgpl-2.1.html.
**
** As a special exception, The Qt Company gives you certain additional
** rights. These rights are described in The Qt Company LGPL Exception
** version 1.1, included in the file LGPL_EXCEPTION.txt in this package.
**
** $QT_END_LICENSE$
**
****************************************************************************/
#include "qvideoframeconversionhelper_p.h"
#ifdef QT_COMPILER_SUPPORTS_AVX2
QT_BEGIN_NAMESPACE
void QT_FASTCALL qt_convert_BGRA32_to_ARGB32_avx2(const QVideoFrame &frame, uchar *output)
{
FETCH_INFO_PACKED(frame)
MERGE_LOOPS(width, height, stride, 4)
quint32 *argb = reinterpret_cast<quint32*>(output);
const __m256i shuffleMask = _mm256_set_epi8(12, 13, 14, 15, 8, 9, 10, 11, 4, 5, 6, 7, 0, 1, 2, 3,
12, 13, 14, 15, 8, 9, 10, 11, 4, 5, 6, 7, 0, 1, 2, 3);
for (int y = 0; y < height; ++y) {
const quint32 *bgra = reinterpret_cast<const quint32*>(src);
int x = 0;
ALIGN(32, argb, x, width) {
*argb = qConvertBGRA32ToARGB32(*bgra);
++bgra;
++argb;
}
for (; x < width - 15; x += 16) {
__m256i pixelData = _mm256_loadu_si256(reinterpret_cast<const __m256i*>(bgra));
__m256i pixelData2 = _mm256_loadu_si256(reinterpret_cast<const __m256i*>(bgra + 8));
bgra += 16;
pixelData = _mm256_shuffle_epi8(pixelData, shuffleMask);
pixelData2 = _mm256_shuffle_epi8(pixelData2, shuffleMask);
_mm256_store_si256(reinterpret_cast<__m256i*>(argb), pixelData);
_mm256_store_si256(reinterpret_cast<__m256i*>(argb + 8), pixelData2);
argb += 16;
}
// leftovers
for (; x < width; ++x) {
*argb = qConvertBGRA32ToARGB32(*bgra);
++bgra;
++argb;
}
src += stride;
}
}
QT_END_NAMESPACE
#endif
|