Bug 121660 - DoYouEvenBench: Add tests WebKit is slow on so WebKit is not fastest when we start optimizing
Summary: DoYouEvenBench: Add tests WebKit is slow on so WebKit is not fastest when we ...
Status: RESOLVED INVALID
Alias: None
Product: WebKit
Classification: Unclassified
Component: Tools / Tests (show other bugs)
Version: 528+ (Nightly build)
Hardware: Unspecified Unspecified
: P2 Normal
Assignee: Nobody
URL:
Keywords:
Depends on:
Blocks:
 
Reported: 2013-09-19 23:26 PDT by Ryosuke Niwa
Modified: 2013-09-24 16:45 PDT (History)
9 users (show)

See Also:

Attachments
Add an attachment (proposed patch, testcase, etc.)

Note You need to log in before you can comment on or make changes to this bug.
Description Ryosuke Niwa 2013-09-19 23:26:11 PDT 
On the current DoYouEvenBench, WebKit turns out to be the fastest engine on the average:

Nightly build of WebKit: 6682 ms
Firefox 23.0.1: 7158 ms
Chrome 29.0.1547.76:  8290 ms

This defeats the whole point of creating a DOM benchmark to optimize for.  We need to find & add more demo apps to mitigate the fact WebKit is so damn fast.
Comment 1 Benjamin Poulain 2013-09-20 00:35:17 PDT 
God damnit, we should stop doing such a good job optimizing WebKit :)

Maybe you could consider:
-Gaming frameworks? (https://github.com/mrdoob/three.js/, Box2D, LimeJS) 
-Mobile frameworks? (http://jquerymobile.com/)
-Charting frameworks? (http://raphaeljs.com/, http://livedocs.dojotoolkit.org/dojox/charting).
-Various Polyfills (Mozilla Brick?). The interesting part is, it would show if a native implementation bring much benefits to the browsers implementing it.

All of them have demos. Maybe the demos can be made into something useful for performance tracking?
Comment 2 Ryosuke Niwa 2013-09-20 18:32:28 PDT 
Firefox 24 beats us!

Firefox 24: 5991.2 ms
Comment 3 Ryosuke Niwa 2013-09-24 16:45:47 PDT 
Firefox 24 is faster than Nightly build of WebKit. The problem solved!