tree 1141961fe3fcaed60f76ee319cab400c96936667
parent 12b1831ea49f3d88e93b7d2793d94852d03813e8
author jmuizelaar <jmuizelaar@mozilla.com> 1412880182 -0700
committer Commit bot <commit-bot@chromium.org> 1412880182 -0700

Improve SkARGB32_A8_BlitMask_SSE2

With clang this:

-       movzbl  -3(%rbx), %edx
-       pxor    %xmm5, %xmm5
-       pinsrw  $0, %edx, %xmm5
-       pinsrw  $1, %edx, %xmm5
-       movzbl  -2(%rbx), %edx
-       pinsrw  $2, %edx, %xmm5
-       pinsrw  $3, %edx, %xmm5
-       movzbl  -1(%rbx), %edx
-       pinsrw  $4, %edx, %xmm5
-       pinsrw  $5, %edx, %xmm5
-       movzbl  (%rbx), %edx
-       pinsrw  $6, %edx, %xmm5
-       pinsrw  $7, %edx, %xmm5

becomes:

+       movd    (%rbx), %xmm4
+       punpcklbw       %xmm9, %xmm4
+       punpcklwd       %xmm4, %xmm4

And clang already does better codegen than msvc 2013 on this.

BUG=skia:

Review URL: https://codereview.chromium.org/609823003