New issue
Advanced search Search tips
Note: Color blocks (like █ or █) mean that a user may not be available. Tooltip shows the reason.

Issue 877201 link

Starred by 1 user
Status: WontFix
Owner:
enne@chromium.org
Closed: Sep 17
Cc:
█ bsalomon@chromium.org
majidvp@google.com
enne@chromium.org
█ ethannicholas@chromium.org
Components:
EstimatedDays: ----
NextAction: ----
OS: ----
Pri: 2
Type: Bug-Regression



Sign in to add a comment

2.5% regression in memory.desktop at 585258:585302

Project Member Reported by majidvp@chromium.org, Aug 23 
See the link to graphs below.
Project Member

Comment 1 by 42576172...@developer.gserviceaccount.com, Aug 23 

All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=877201

(For debugging:) Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?sid=84d11b6db5c862790a248a6d530068668f3d2628679e2f08afc6dd2f0ce0b8e0


Bot(s) for this bug's original alert(s):

mac-10_13_laptop_high_end-perf
Project Member

Comment 3 by 42576172...@developer.gserviceaccount.com, Aug 23

Cc: enne@chromium.org
Owner: enne@chromium.org
Status: Assigned (was: Untriaged)
📍 Found a significant difference after 1 commit.
https://pinpoint-dot-chromeperf.appspot.com/job/10664a61640000

Add unfold_short_circuit_as_ternary workaround by enne@chromium.org
https://skia.googlesource.com/skia/+/c02165fae11402933e23ad2bb080862220b5a1a8
1.394e+08 → 1.422e+08 (+2.816e+06)

Understanding performance regressions:
  http://g.co/ChromePerformanceRegressions

Comment 4 by enne@chromium.org, Aug 28

Cc: ethannicholas@chromium.org bsalomon@chromium.org
Components: Internals>Compositing>OOP-Raster
bsalomon, ethannicholas: I think this bug is WontFix, because this is a correctness change.  However, I'm a little surprised that this shader change resulted in a 3.4mb shader regression.  Do either of you have a sense of why this might be?

Comment 5 by enne@chromium.org, Sep 17

Status: WontFix (was: Assigned)
I'm still curious to hear from Skia folks if they have any ideas here, but I will WontFix this for now.

Comment 6 by bsalo...@google.com, Sep 18 

I really can't imagine how it'd cause a memory regression like this.
►

Sign in to add a comment