Chromium Code Reviews
chromiumcodereview-hr@appspot.gserviceaccount.com (chromiumcodereview-hr) | Please choose your nickname with Settings | Help | Chromium Project | Gerrit Changes | Sign out
(20)

Issue 315743002: DM: go back to memcmp for BitmapsEqual (Closed)

Created:
6 years, 6 months ago by mtklein_C
Modified:
6 years, 6 months ago
Reviewers:
hal.canary, mtklein
CC:
skia-review_googlegroups.com
Base URL:
https://skia.googlesource.com/skia.git@master
Visibility:
Public.

Description

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: Committed: https://skia.googlesource.com/skia/+/9c4ff80d9b76e1bda532fb9182f66f67cfc95324

Patch Set 1 #

Unified diffs Side-by-side diffs Delta from patch set Stats (+5 lines, -1 line) Patch
M dm/DMUtil.cpp View 1 chunk +5 lines, -1 line 0 comments Download

Messages

Total messages: 6 (0 generated)
mtklein
6 years, 6 months ago (2014-06-03 20:11:05 UTC) #1
hal.canary
lgtm, as long as you are sure that a.rowBytes()==b.rowBytes()==a.info()->minRowBytes()
6 years, 6 months ago (2014-06-03 20:20:24 UTC) #2
mtklein
On 2014/06/03 20:20:24, Hal Canary wrote: > lgtm, as long as you are sure that ...
6 years, 6 months ago (2014-06-03 20:27:03 UTC) #3
mtklein
The CQ bit was checked by mtklein@google.com
6 years, 6 months ago (2014-06-03 20:27:10 UTC) #4
commit-bot: I haz the power
CQ is trying da patch. Follow status at https://skia-tree-status.appspot.com/cq/mtklein@chromium.org/315743002/1
6 years, 6 months ago (2014-06-03 20:27:35 UTC) #5
commit-bot: I haz the power
6 years, 6 months ago (2014-06-03 20:56:58 UTC) #6
Message was sent while issue was closed.
Change committed as 9c4ff80d9b76e1bda532fb9182f66f67cfc95324

Powered by Google App Engine
This is Rietveld 408576698