1/****************************************************************************
2**
3** Copyright (C) 2016 The Qt Company Ltd.
4** Contact: https://www.qt.io/licensing/
5**
6** This file is part of the Qt Toolkit.
7**
8** $QT_BEGIN_LICENSE:LGPL$
9** Commercial License Usage
10** Licensees holding valid commercial Qt licenses may use this file in
11** accordance with the commercial license agreement provided with the
12** Software or, alternatively, in accordance with the terms contained in
13** a written agreement between you and The Qt Company. For licensing terms
14** and conditions see https://www.qt.io/terms-conditions. For further
15** information use the contact form at https://www.qt.io/contact-us.
16**
17** GNU Lesser General Public License Usage
18** Alternatively, this file may be used under the terms of the GNU Lesser
19** General Public License version 3 as published by the Free Software
20** Foundation and appearing in the file LICENSE.LGPL3 included in the
21** packaging of this file. Please review the following information to
22** ensure the GNU Lesser General Public License version 3 requirements
23** will be met: https://www.gnu.org/licenses/lgpl-3.0.html.
24**
25** GNU General Public License Usage
26** Alternatively, this file may be used under the terms of the GNU
27** General Public License version 2.0 or (at your option) the GNU General
28** Public license version 3 or any later version approved by the KDE Free
29** Qt Foundation. The licenses are as published by the Free Software
30** Foundation and appearing in the file LICENSE.GPL2 and LICENSE.GPL3
31** included in the packaging of this file. Please review the following
32** information to ensure the GNU General Public License requirements will
33** be met: https://www.gnu.org/licenses/gpl-2.0.html and
34** https://www.gnu.org/licenses/gpl-3.0.html.
35**
36** $QT_END_LICENSE$
37**
38****************************************************************************/
39
40#include "qvideoframeconversionhelper_p.h"
41
42#ifdef QT_COMPILER_SUPPORTS_AVX2
43
44QT_BEGIN_NAMESPACE
45
46void QT_FASTCALL qt_convert_BGRA32_to_ARGB32_avx2(const QVideoFrame &frame, uchar *output)
47{
48 FETCH_INFO_PACKED(frame)
49 MERGE_LOOPS(width, height, stride, 4)
50 quint32 *argb = reinterpret_cast<quint32*>(output);
51
52 const __m256i shuffleMask = _mm256_set_epi8(12, 13, 14, 15, 8, 9, 10, 11, 4, 5, 6, 7, 0, 1, 2, 3,
53 12, 13, 14, 15, 8, 9, 10, 11, 4, 5, 6, 7, 0, 1, 2, 3);
54
55 for (int y = 0; y < height; ++y) {
56 const quint32 *bgra = reinterpret_cast<const quint32*>(src);
57
58 int x = 0;
59 ALIGN(32, argb, x, width) {
60 *argb = qConvertBGRA32ToARGB32(*bgra);
61 ++bgra;
62 ++argb;
63 }
64
65 for (; x < width - 15; x += 16) {
66 __m256i pixelData = _mm256_loadu_si256(reinterpret_cast<const __m256i*>(bgra));
67 __m256i pixelData2 = _mm256_loadu_si256(reinterpret_cast<const __m256i*>(bgra + 8));
68 bgra += 16;
69 pixelData = _mm256_shuffle_epi8(pixelData, shuffleMask);
70 pixelData2 = _mm256_shuffle_epi8(pixelData2, shuffleMask);
71 _mm256_store_si256(reinterpret_cast<__m256i*>(argb), pixelData);
72 _mm256_store_si256(reinterpret_cast<__m256i*>(argb + 8), pixelData2);
73 argb += 16;
74 }
75
76 // leftovers
77 for (; x < width; ++x) {
78 *argb = qConvertBGRA32ToARGB32(*bgra);
79 ++bgra;
80 ++argb;
81 }
82
83 src += stride;
84 }
85}
86
87QT_END_NAMESPACE
88
89#endif
90