diff options
| author | mtklein <mtklein@chromium.org> | 2015-03-24 06:16:30 -0700 |
|---|---|---|
| committer | Commit bot <commit-bot@chromium.org> | 2015-03-24 06:16:30 -0700 |
| commit | 470fa6f74b8ed08d85af463d5b3ef6f19ed6522a (patch) | |
| tree | 28df8d183fbf66776eb5e4e6ee886ed9168beca9 /tests/PathOpsOpLoopThreadedTest.cpp | |
| parent | 92b47c49016749249ff8521e424c4373b4a74241 (diff) | |
aacc + bbdd
SkMatrix::mapPts() using aacc/bbdd was always worse than using badc():
- On Intel, it was faster than exisiting swizzle, but badc() is 10% faster still (one pshufd instead of two).
- On ARM, existing swizzle < badc() < aacc()+bbdd(), even though aacc() then bbdd() is really a single vtrn instruction.
I will revert SkMatrix.cpp before submitting. Just thought you might like to look.
Will think more and try to gear up Instruments on ARM.
BUG=skia:
Review URL: https://codereview.chromium.org/1012573003
Diffstat (limited to 'tests/PathOpsOpLoopThreadedTest.cpp')
0 files changed, 0 insertions, 0 deletions