[Webkit-unassigned] [Bug 67670] DFG JIT does not optimize booleans

bugzilla-daemon at webkit.org bugzilla-daemon at webkit.org
Tue Sep 6 15:04:14 PDT 2011


https://bugs.webkit.org/show_bug.cgi?id=67670





--- Comment #3 from Filip Pizlo <fpizlo at apple.com>  2011-09-06 15:04:14 PST ---
Here's the current performance of this patch relative to just dynamic optimization alone:



Benchmark report for V8.

VMs tested:
"TipOfTree" at /Volumes/Data/pizlo/quinary/OpenSource/WebKitBuild/Release/jsc
"DynamicOpt" at /Volumes/Data/pizlo/quartary/OpenSource/WebKitBuild/Release/jsc
"DynamicBoolOpt" at /Volumes/Data/pizlo/octonary/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               DynamicOpt            DynamicBoolOpt       DynamicBoolOpt v. TipOfTree

crypto            92.9087+-1.0076    ^    82.0337+-0.5620    ?    82.9391+-1.3857       ^ definitely 1.1202x faster
deltablue        273.9975+-5.3832    ^   261.2656+-1.0780    ?   261.7145+-2.2611       ^ definitely 1.0469x faster
earley-boyer     101.8557+-1.8443    !   108.5937+-2.2791    ^   102.9614+-0.9825       ? might be 1.0109x slower
raytrace          81.4509+-1.0405    ?    83.5420+-1.2135    ^    81.4757+-0.7785       ?
regexp           111.8391+-1.3009        110.3129+-1.7970    ?   111.0009+-1.0489       
richards         245.8331+-1.3454    ^   236.6249+-1.3738    ^   220.2786+-2.1472       ^ definitely 1.1160x faster
splay            104.5783+-1.5713    ?   105.3847+-0.8156    ?   105.7928+-2.3796       ? might be 1.0116x slower

<arithmetic>     144.6376+-1.0918    ^   141.1082+-0.3229    ^   138.0233+-0.5582       ^ definitely 1.0479x faster
<geometric>      129.3673+-0.6707    ^   127.0473+-0.3857    ^   124.7610+-0.6602       ^ definitely 1.0369x faster
<harmonic>       118.4370+-0.4619    ^   116.6713+-0.4381    ^   114.9704+-0.7147       ^ definitely 1.0302x faster

-- 
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