[webkit-reviews] review requested: [Bug 117906] fourthTier: DFG shouldn't exit just because a String GetByVal went out-of-bounds : [Attachment 205237] the ptach

[bugzilla-daemon at webkit.org]

Filip Pizlo <fpizlo at apple.com> has asked  for review:
Bug 117906: fourthTier: DFG shouldn't exit just because a String GetByVal went
out-of-bounds
https://bugs.webkit.org/show_bug.cgi?id=117906

Attachment 205237: the ptach
https://bugs.webkit.org/attachment.cgi?id=205237&action=review

------- Additional Comments from Filip Pizlo <fpizlo at apple.com>
Benchmark report for JSRegress on dethklok (MacBookPro9,1).

VMs tested:
"TipOfTree" at
/Volumes/Data/pizlo/fourthTier/secondary/OpenSource/WebKitBuild/Release/jsc
(r151875)
"FixString" at
/Volumes/Data/pizlo/fourthTier/primary/OpenSource/WebKitBuild/Release/jsc
(r151873)

Collected 30 samples per benchmark/VM, with 10 VM invocations per benchmark.
Emitted a call to gc() between sample
measurements. 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		 
FixString				      

string-get-by-val-big-char		      8.6687+-0.3165	       
8.4542+-0.2872		might be 1.0254x faster
string-get-by-val-out-of-bounds-insane	      7.2589+-0.3855	 ^     
5.9114+-0.2240	      ^ definitely 1.2280x faster
string-get-by-val-out-of-bounds 	     54.9499+-0.7410	 ^     
2.5956+-0.0318	      ^ definitely 21.1704x faster
string-get-by-val			      2.3552+-0.1035	       
2.3321+-0.0938	      

<arithmetic>				     18.3082+-0.2274	 ^     
4.8233+-0.0892	      ^ definitely 3.7958x faster
<geometric> *				      9.4639+-0.1531	 ^     
4.1602+-0.0602	      ^ definitely 2.2749x faster
<harmonic>				      5.7086+-0.1329	 ^     
3.6167+-0.0511	      ^ definitely 1.5784x faster