diff options
Diffstat (limited to 'src/multimedia/video/qvideoframeconversionhelper_avx2.cpp')
-rw-r--r-- | src/multimedia/video/qvideoframeconversionhelper_avx2.cpp | 87 |
1 files changed, 44 insertions, 43 deletions
diff --git a/src/multimedia/video/qvideoframeconversionhelper_avx2.cpp b/src/multimedia/video/qvideoframeconversionhelper_avx2.cpp index c17f8a6a4..6802cca74 100644 --- a/src/multimedia/video/qvideoframeconversionhelper_avx2.cpp +++ b/src/multimedia/video/qvideoframeconversionhelper_avx2.cpp @@ -1,41 +1,5 @@ -/**************************************************************************** -** -** Copyright (C) 2016 The Qt Company Ltd. -** Contact: https://www.qt.io/licensing/ -** -** This file is part of the Qt Toolkit. -** -** $QT_BEGIN_LICENSE:LGPL$ -** 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 https://www.qt.io/terms-conditions. For further -** information use the contact form at https://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 3 as published by the Free Software -** Foundation and appearing in the file LICENSE.LGPL3 included in the -** packaging of this file. Please review the following information to -** ensure the GNU Lesser General Public License version 3 requirements -** will be met: https://www.gnu.org/licenses/lgpl-3.0.html. -** -** GNU General Public License Usage -** Alternatively, this file may be used under the terms of the GNU -** General Public License version 2.0 or (at your option) the GNU General -** Public license version 3 or any later version approved by the KDE Free -** Qt Foundation. The licenses are as published by the Free Software -** Foundation and appearing in the file LICENSE.GPL2 and LICENSE.GPL3 -** included in the packaging of this file. Please review the following -** information to ensure the GNU General Public License requirements will -** be met: https://www.gnu.org/licenses/gpl-2.0.html and -** https://www.gnu.org/licenses/gpl-3.0.html. -** -** $QT_END_LICENSE$ -** -****************************************************************************/ +// Copyright (C) 2016 The Qt Company Ltd. +// SPDX-License-Identifier: LicenseRef-Qt-Commercial OR LGPL-3.0-only OR GPL-2.0-only OR GPL-3.0-only #include "qvideoframeconversionhelper_p.h" @@ -72,13 +36,13 @@ void convert_to_ARGB32_avx2(const QVideoFrame &frame, uchar *output) 3 - a, 3 - r, 3 - g, 3 - b); #endif - using Pixel = const RgbPixel<a, r, g, b>; + using Pixel = const ArgbPixel<a, r, g, b>; for (int y = 0; y < height; ++y) { auto *pixel = reinterpret_cast<const Pixel *>(src); int x = 0; - ALIGN(32, argb, x, width) { + QT_MEDIA_ALIGN(32, argb, x, width) { *argb = pixel->convert(); ++pixel; ++argb; @@ -114,21 +78,58 @@ void QT_FASTCALL qt_convert_ARGB8888_to_ARGB32_avx2(const QVideoFrame &frame, uc convert_to_ARGB32_avx2<0, 1, 2, 3>(frame, output); } -void qt_convert_ABGR8888_to_ARGB32_avx2(const QVideoFrame &frame, uchar *output) +void QT_FASTCALL qt_convert_ABGR8888_to_ARGB32_avx2(const QVideoFrame &frame, uchar *output) { convert_to_ARGB32_avx2<0, 3, 2, 1>(frame, output); } -void qt_convert_RGBA8888_to_ARGB32_avx2(const QVideoFrame &frame, uchar *output) +void QT_FASTCALL qt_convert_RGBA8888_to_ARGB32_avx2(const QVideoFrame &frame, uchar *output) { convert_to_ARGB32_avx2<3, 0, 1, 2>(frame, output); } -void qt_convert_BGRA8888_to_ARGB32_avx2(const QVideoFrame &frame, uchar *output) +void QT_FASTCALL qt_convert_BGRA8888_to_ARGB32_avx2(const QVideoFrame &frame, uchar *output) { convert_to_ARGB32_avx2<3, 2, 1, 0>(frame, output); } +void QT_FASTCALL qt_copy_pixels_with_mask_avx2(uint32_t *dst, const uint32_t *src, size_t size, uint32_t mask) +{ + const auto mask256 = _mm256_set_epi32(mask, mask, mask, mask, mask, mask, mask, mask); + + size_t x = 0; + + QT_MEDIA_ALIGN(32, dst, x, size) + *(dst++) = *(src++) | mask; + + for (; x < size - (8 * 4 + 1); x += 8 * 4) { + const auto srcData1 = _mm256_loadu_si256(reinterpret_cast<const __m256i *>(src)); + const auto srcData2 = _mm256_loadu_si256(reinterpret_cast<const __m256i *>(src += 8)); + const auto srcData3 = _mm256_loadu_si256(reinterpret_cast<const __m256i *>(src += 8)); + const auto srcData4 = _mm256_loadu_si256(reinterpret_cast<const __m256i *>(src += 8)); + + _mm256_store_si256(reinterpret_cast<__m256i *>(dst), _mm256_or_si256(srcData1, mask256)); + _mm256_store_si256(reinterpret_cast<__m256i *>(dst += 8), _mm256_or_si256(srcData2, mask256)); + _mm256_store_si256(reinterpret_cast<__m256i *>(dst += 8), _mm256_or_si256(srcData3, mask256)); + _mm256_store_si256(reinterpret_cast<__m256i *>(dst += 8), _mm256_or_si256(srcData4, mask256)); + + src += 8; + dst += 8; + } + + // leftovers + for (; x < size - 7; x += 8) { + const auto srcData = _mm256_loadu_si256(reinterpret_cast<const __m256i *>(src)); + _mm256_store_si256(reinterpret_cast<__m256i *>(dst), _mm256_or_si256(srcData, mask256)); + + src += 8; + dst += 8; + } + + for (; x < size; ++x) + *(dst++) = *(src++) | mask; +} + QT_END_NAMESPACE #endif |