[webkit-reviews] review requested: [Bug 96979] Update RenderText to use String instead of UChar* for text : [Attachment 166782] Patch

bugzilla-daemon at webkit.org bugzilla-daemon at webkit.org
Tue Oct 2 17:10:37 PDT 2012


Michael Saboff <msaboff at apple.com> has asked  for review:
Bug 96979: Update RenderText to use String instead of UChar* for text
https://bugs.webkit.org/show_bug.cgi?id=96979

Attachment 166782: Patch
https://bugs.webkit.org/attachment.cgi?id=166782&action=review

------- Additional Comments from Michael Saboff <msaboff at apple.com>
Here is the performance results of this patch on the Performance/LayoutTests:

			Baseline    With Changes
flexbox-column-nowrap	102202.6	105725.9   runs/s
flexbox-column-nowrap	102850.4	105806.4
flexbox-column-nowrap	103790.0	107004.1
flexbox-column-nowrap	103997.7	107176.2
    Mean		103210.2	106428.2   Diff    3.12%
flexbox-column-wrap	102530.4	104567.0   runs/s
flexbox-column-wrap	105323.5	107327.2
flexbox-column-wrap	107329.5	107771.2
flexbox-column-wrap	107347.2	109178.8
    Mean		105632.7	107211.0   Diff    1.49%
flexbox-row-nowrap	138271.6	142910.7   runs/s
flexbox-row-nowrap	140718.1	143366.9
flexbox-row-nowrap	144811.8	144682.2
flexbox-row-nowrap	146147.0	150649.8
    Mean		142487.1	145402.4   Diff    2.05%
flexbox-row-wrap	103482.7	104720.6   runs/s	
flexbox-row-wrap	103778.7	106867.7		
flexbox-row-wrap	104554.4	108036.3	
flexbox-row-wrap	105866.3	108196.2	
    Mean		104420.5	106955.2   Diff    2.43%
floats_100_100		   200.0	   198.0   ms 
floats_100_100		   201.0	   200.5
floats_100_100		   201.5	   201.0   
floats_100_100		   202.5	   201.5   
    Mean		   201.3	   200.3   Diff    0.50%
floats_100_100_nested	   215.5	   216.0   ms
floats_100_100_nested	   215.5	   216.5
floats_100_100_nested	   217.5	   218.0   
floats_100_100_nested	   218.5	   221.5   
    Mean		   216.8	   218.0   Diff   -0.58%
floats_20_100		   409.9	   414.9   ms
floats_20_100		   411.4	   416.3
floats_20_100		   413.0	   416.4   
floats_20_100		   416.3	   419.1   
    Mean		   412.6	   416.7   Diff   -0.98%
floats_20_100_nested	   612.3	   619.8   ms
floats_20_100_nested	   618.3	   622.7	  
floats_20_100_nested	   635.2	   625.2   
floats_20_100_nested	   635.7	   628.7   
    Mean		   625.4	   624.1   Diff    0.21%
floats_2_100		   204.6	   209.5   ms
floats_2_100		   205.7	   210.4
floats_2_100		   205.9	   210.4   
floats_2_100		   206.0	   210.9   
    Mean		   205.6	   210.3   Diff   -2.31%
floats_2_100_nested	   463.6	   460.5   ms
floats_2_100_nested	   463.9	   461.5
floats_2_100_nested	   464.5	   462.6   
floats_2_100_nested	   466.7	   463.2   
    Mean		   464.7	   462.0   Diff    0.59%
floats_50_100		   305.6	   313.4   ms	  
floats_50_100		   312.4	   314.6
floats_50_100		   313.0	   314.8   
floats_50_100		   314.4	   317.8   
    Mean		   311.4	   315.2   Diff   -1.22%
floats_50_100_nested	   367.6	   371.8   ms	  
floats_50_100_nested	   370.8	   373.2
floats_50_100_nested	   371.8	   373.6   
floats_50_100_nested	   375.6	   377.0   
    Mean		   371.5	   373.9   Diff   -0.66%
line-layout		    79.6	    83.3   runs/s
line-layout		    80.0	    83.7 
line-layout		    80.1	    83.9    
line-layout		    80.1	    83.9    
    Mean		    80.0	    83.7   Diff    4.70%


I don't have the details for the slowdown in floats_20_100, floats_2_100 and
floats_50_100.	Profiling doesn't point to cade I changed.


More information about the webkit-reviews mailing list