Add AVX2 autovectorized versions of premultiply

Following up on using GCC's autovectorizing for faster SSE4.1
premultiply, this patch adds specialized autovectorized versions
of premultiply for AVX2, giving another almost doubling in speed.
To make the speed up for AVX2 and also SSE4_1 available to non-GCC
compilers, the target-specific methods have been moved to separate
files.

Change-Id: I97ce05be67f4adeeb9a096eef80fd5fb662099f3
Reviewed-by: Gunnar Sletta <gunnar@sletta.org>

1 files changed, 79 insertions, 0 deletions

diff --git a/src/gui/painting/qdrawhelper_sse4.cpp b/src/gui/painting/qdrawhelper_sse4.cpp
new file mode 100644
index 0000000000..43a3958997
--- /dev/null
+++ b/src/gui/painting/qdrawhelper_sse4.cpp
@@ -0,0 +1,79 @@
+/****************************************************************************
+**
+** Copyright (C) 2015 The Qt Company Ltd.
+** Contact: http://www.qt.io/licensing/
+**
+** This file is part of the QtGui module 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 <private/qdrawhelper_p.h>
+#include <private/qdrawingprimitive_sse2_p.h>
+
+#if defined(QT_COMPILER_SUPPORTS_SSE4_1)
+
+QT_BEGIN_NAMESPACE
+
+const uint *QT_FASTCALL convertARGB32ToARGB32PM_sse4(uint *buffer, const uint *src, int count,
+                                                     const QPixelLayout *, const QRgb *)
+{
+    return qt_convertARGB32ToARGB32PM(buffer, src, count);
+}
+
+const uint *QT_FASTCALL convertRGBA8888ToARGB32PM_sse4(uint *buffer, const uint *src, int count,
+                                                       const QPixelLayout *, const QRgb *)
+{
+    return qt_convertRGBA8888ToARGB32PM(buffer, src, count);
+}
+
+const uint *QT_FASTCALL convertARGB32FromARGB32PM_sse4(uint *buffer, const uint *src, int count,
+                                                       const QPixelLayout *, const QRgb *)
+{
+    for (int i = 0; i < count; ++i)
+        buffer[i] = qUnpremultiply_sse4(src[i]);
+    return buffer;
+}
+
+const uint *QT_FASTCALL convertRGBA8888FromARGB32PM_sse4(uint *buffer, const uint *src, int count,
+                                                         const QPixelLayout *, const QRgb *)
+{
+    for (int i = 0; i < count; ++i)
+        buffer[i] = ARGB2RGBA(qUnpremultiply_sse4(src[i]));
+    return buffer;
+}
+
+const uint *QT_FASTCALL convertRGBXFromARGB32PM_sse4(uint *buffer, const uint *src, int count,
+                                                     const QPixelLayout *, const QRgb *)
+{
+    for (int i = 0; i < count; ++i)
+        buffer[i] = ARGB2RGBA(0xff000000 | qUnpremultiply_sse4(src[i]));
+    return buffer;
+}
+
+QT_END_NAMESPACE
+
+#endif