[Webkit-unassigned] [Bug 41606] New: Refactored string parsing in the lexer
bugzilla-daemon at webkit.org
bugzilla-daemon at webkit.org
Mon Jul 5 04:55:13 PDT 2010
https://bugs.webkit.org/show_bug.cgi?id=41606
Summary: Refactored string parsing in the lexer
Product: WebKit
Version: 528+ (Nightly build)
Platform: All
OS/Version: All
Status: NEW
Severity: Enhancement
Priority: P2
Component: JavaScriptCore
AssignedTo: webkit-unassigned at lists.webkit.org
ReportedBy: zherczeg at webkit.org
CC: oliver at apple.com
The current sunspider parse-only results are the following:
=============================================================================
** TOTAL **: 1.044x as fast 33.1ms +/- 1.9% 31.7ms +/- 1.1% significant
=============================================================================
jquery: - 5.1ms +/- 4.4% 5.1ms +/- 4.4%
1.3.2: - 5.1ms +/- 4.4% 5.1ms +/- 4.4%
mootools: 1.080x as fast 5.4ms +/- 6.8% 5.0ms +/- 0.0% significant
1.2.2-core-nc: 1.080x as fast 5.4ms +/- 6.8% 5.0ms +/- 0.0% significant
prototype: - 6.1ms +/- 3.7% 6.0ms +/- 0.0%
1.6.0.3: - 6.1ms +/- 3.7% 6.0ms +/- 0.0%
concat: 1.058x as fast 16.5ms +/- 2.3% 15.6ms +/- 2.4% significant
jquery-mootools-prototype: 1.058x as fast 16.5ms +/- 2.3% 15.6ms +/- 2.4% significant
But it was not before, actually it was a 5% slowdown. This patch was actually completed a week ago, and I didn't really changed it. I planned to submit a patch with a gcov output and ask for help. (I usually run sunspider 10-15 times before choose the best measurement, to lessen the effect of deviation caused by the OS. So this patch was really slower before, and faster now, albeit I think it is not the effect of the patch, more likely the changed binary structure) Anyway, the gcov output is also attached.
--
Configure bugmail: https://bugs.webkit.org/userprefs.cgi?tab=email
------- You are receiving this mail because: -------
You are the assignee for the bug.
More information about the webkit-unassigned
mailing list