projects / platform / upstream / libSkiaSharp.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: 182a631) | patch
DM: go back to memcmp for BitmapsEqual
authormtklein <mtklein@chromium.org>
Tue, 3 Jun 2014 20:56:54 +0000 (13:56 -0700)
committerCommit bot <commit-bot@chromium.org>
Tue, 3 Jun 2014 20:56:54 +0000 (13:56 -0700)
commit9c4ff80d9b76e1bda532fb9182f66f67cfc95324
treef14cf81529b67be5961ecb5317a0262c3ad010fetree | snapshot
parent182a631e989b9b6c58e4342c9f661682361446edcommit | diff
DM: go back to memcmp for BitmapsEqual

Even when autovectorized, using MaxComponentDifference is slower than memcmp.
And debug builds (most runs of DM) will never even be autovectorized.

DM::MaxComponentDifference is the top function on DM profile, and memcmp moves
to ~20th.

BUG=skia:
R=halcanary@google.com, mtklein@google.com

Author: mtklein@chromium.org

Review URL: https://codereview.chromium.org/315743002
dm/DMUtil.cpp diff | blob | history
Domain: Dotnet / API;