[Webkit-unassigned] [Bug 68316] DFG JIT does not have full block-local CSE
bugzilla-daemon at webkit.org
bugzilla-daemon at webkit.org
Sat Sep 17 14:08:42 PDT 2011
https://bugs.webkit.org/show_bug.cgi?id=68316
--- Comment #1 from Filip Pizlo <fpizlo at apple.com> 2011-09-17 14:08:42 PST ---
Created an attachment (id=107773)
--> (https://bugs.webkit.org/attachment.cgi?id=107773&action=review)
work in progress
Still working on this, but it's pretty awesome for Kraken.
Benchmark report for Kraken.
VMs tested:
"TipOfTree" at /Volumes/Data/pizlo/quinary/OpenSource/WebKitBuild/Release/jsc
"PhantomCSE" at /Volumes/Data/pizlo/OpenSource/WebKitBuild/Release/jsc
Collected 12 samples per benchmark/VM, with 4 VM invocations per benchmark. Used 1 benchmark iteration per VM
invocation for warm-up. Used the jsc-specific preciseTime() function to get microsecond-level timing.
Reporting benchmark execution times with 95% confidence intervals in milliseconds.
TipOfTree PhantomCSE
ai-astar 634.8768+-5.2150 632.3351+-4.7085
audio-beat-detection 467.5151+-1.2716 465.7044+-1.3745
audio-dft 423.1598+-2.3857 421.5126+-2.3649
audio-fft 364.7906+-1.2717 ? 365.5174+-1.0969 ?
audio-oscillator 312.1471+-1.5005 ? 331.5295+-21.8849 ? might be 1.0621x slower
imaging-darkroom 412.6474+-1.6945 411.6372+-1.1734
imaging-desaturate 207.4252+-0.7089 ! 221.9861+-0.8245 ! definitely 1.0702x slower
imaging-gaussian-blur 1082.7893+-2.2880 ^ 591.5093+-0.8721 ^ definitely 1.8306x faster
json-parse-financial 49.5232+-0.2997 ? 50.3901+-1.3708 ? might be 1.0175x slower
json-stringify-tinderbox 68.0220+-0.2688 67.8016+-0.6565
stanford-crypto-aes 144.5714+-0.6423 143.6752+-1.0772
stanford-crypto-ccm 110.8207+-0.2111 110.1401+-0.5823
stanford-crypto-pbkdf2 396.3371+-1.5674 394.0494+-5.6482
stanford-crypto-sha256-iterative 148.7113+-0.6486 ? 149.4918+-0.3482 ?
<arithmetic> 344.5241+-0.4476 ^ 311.2343+-1.5880 ^ definitely 1.1070x faster
<geometric> 252.2160+-0.3048 ^ 243.4866+-0.8714 ^ definitely 1.0359x faster
<harmonic> 174.4002+-0.3305 174.1282+-0.7948
--
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