Implement the general blending of ARGB32_pm with SSSE3

SSSE3 provides two tools to improve the blending speed over SSE2:
-palignr
-byte permutation

The alignement is enforced on src and dst with palignr to always make
aligned access.
The extraction of the alpha mask is done with a byte permutation in
order to save two instructions per cycle.

On Atom, this patch gives between 0% (aligned src) to 10% of
improvement (unaligned 4 and 12 bytes).

On Core 2, this patch gives consistently 8% to 10% of improvement
for every miss-alignment.

Reviewed-by: Samuel Rødal

1 files changed, 11 insertions, 0 deletions

diff --git a/src/gui/painting/qdrawhelper.cpp b/src/gui/painting/qdrawhelper.cpp
index 1ff3d7b..276da93 100644
--- a/src/gui/painting/qdrawhelper.cpp
+++ b/src/gui/painting/qdrawhelper.cpp
@@ -7840,6 +7840,17 @@ void qInitDrawhelperAsm()
             qBlendFunctions[QImage::Format_ARGB32_Premultiplied][QImage::Format_RGB32] = qt_blend_rgb32_on_rgb32_sse2;
             qBlendFunctions[QImage::Format_RGB32][QImage::Format_ARGB32_Premultiplied] = qt_blend_argb32_on_argb32_sse2;
             qBlendFunctions[QImage::Format_ARGB32_Premultiplied][QImage::Format_ARGB32_Premultiplied] = qt_blend_argb32_on_argb32_sse2;
+
+#if defined(QT_HAVE_SSSE3)
+            if (features & SSSE3) {
+                extern void qt_blend_argb32_on_argb32_ssse3(uchar *destPixels, int dbpl,
+                                                            const uchar *srcPixels, int sbpl,
+                                                            int w, int h,
+                                                            int const_alpha);
+                qBlendFunctions[QImage::Format_RGB32][QImage::Format_ARGB32_Premultiplied] = qt_blend_argb32_on_argb32_ssse3;
+                qBlendFunctions[QImage::Format_ARGB32_Premultiplied][QImage::Format_ARGB32_Premultiplied] = qt_blend_argb32_on_argb32_ssse3;
+            }
+#endif // QT_HAVE_SSSE3
         } else
 #endif
         {