<html>
<head>
<meta content="text/html; charset=utf-8" http-equiv="Content-Type">
</head>
<body bgcolor="#FFFFFF" text="#000000">
So I ran the browser bench samples and the 184845 performed pretty
well there. I couldn't run it with the 145828 version as it crashed
in MarkBlock.isLive() while running the test. <br>
<br>
I then remembered that we compile our port with -Os instead of -O3.
I figured this may have an impact on the inlining of code, so I
recompiled our port with -O3 and the improvement on the SunSpider
tests were dramatic. It went from an overall score of 511 to 306.
So I think what I was seeing was a result of the -Os option. <br>
<br>
The only other question I have is if there is some sort of throttle
on the JavaScript callbacks. The reason I ask is because no matter
what I do, the following page:<br>
<br>
<a class="moz-txt-link-freetext" href="http://bubblemark.com/dhtml.htm">http://bubblemark.com/dhtml.htm</a><br>
<br>
I only get 60 fps. For this page the "fps" is a bit of misnomer
because they are just measuring the number of times they get a call
in to their JavaScript code. It doesn't seem to matter how many
balls I draw on the screen, I always get 60 fps . <br>
<br>
Thanks,<br>
Rodney<br>
<br>
<div class="moz-cite-prefix">On 06/24/2015 05:56 PM, Filip Pizlo
wrote:<br>
</div>
<blockquote
cite="mid:E184D932-D129-49D5-BBD9-583CDFF30485@apple.com"
type="cite">
<meta http-equiv="Content-Type" content="text/html; charset=utf-8">
Couple of thoughts:
<div class=""><br class="">
</div>
<div class="">1) That’s unexpected. You should file a bug on <a
moz-do-not-send="true" href="http://bugs.webkit.org" class="">bugs.webkit.org</a>.</div>
<div class=""><br class="">
</div>
<div class="">2) SunSpider isn’t the best way to measure
performance anymore. Try one of the tests on <a
moz-do-not-send="true" href="http://browserbench.org" class=""><a class="moz-txt-link-freetext" href="http://browserbench.org">http://browserbench.org</a></a> instead,
they are more modern and we tend to use those instead of
SunSpider these days.</div>
<div class=""><br class="">
</div>
<div class="">-Filip</div>
<div class=""><br class="">
</div>
<div class=""><br class="">
<div>
<blockquote type="cite" class="">
<div class="">On Jun 24, 2015, at 2:10 PM, Rodney Dowdall
<<a moz-do-not-send="true"
href="mailto:rdowdall@cranksoftware.com" class="">rdowdall@cranksoftware.com</a>>
wrote:</div>
<br class="Apple-interchange-newline">
<div class="">Hello<br class="">
<br class="">
I have two ports of WebKit. The first is based off of
revision 145828 and the second is based off of 184845. I
have compiled these ports for Linux x86 32 bit. I would
like to know why the port based on revision 145828 is
faster at running the JavaScriptCore tests. I have the
DFG JIT enabled for both, and I do not have the FTL JIT
turned on (obviously because it is not supported for 32
bit builds). I was wondering if maybe I need to enable
another setting the 184845 revision, but I think I have
turned on all of the JavaScriptCore enablements that I
can. I can post these if it makes sense for me to do so.
Here are the numbers that I am getting from the two
builds. I am just wondering if this is what I should
expect.<br class="">
<br class="">
184845 Webkit<br class="">
<br class="">
Total: 522.9ms +/- 4.3%<br class="">
<br class="">
3d: 115.8ms +/- 10.2%<br class="">
cube: 57.1ms +/- 13.8%<br class="">
morph: 26.5ms +/- 10.2%<br class="">
raytrace: 32.2ms +/- 4.5%<br class="">
<br class="">
access: 45.3ms +/- 7.7%<br class="">
binary-trees: 6.0 ms +/- 7.9%<br class="">
fannkuch: 17.0 ms +/- 10.5%<br class="">
nbody: 16.9 ms +/- 8.8%<br class="">
nsieve: 5.4 ms +/- 9.3%<br class="">
<br class="">
bitops: 17.2 ms +/- 12.8%<br class="">
3bits-bits-in-byte: 3.6 ms +/- 31.3%<br class="">
bits-in-byte: 4.4 ms +/- 15.7%<br class="">
bitwise-and: 3.5 ms +/- 14.4%<br class="">
nsieve-bits: 5.7 ms +/- 8.5%<br class="">
<br class="">
controlflow: 6.2 ms +/- 4.9%<br class="">
recursive: 6.3 ms +/- 4.9%<br class="">
<br class="">
crypto: 57.9 ms +/- 4.8%<br class="">
aes: 20.6 ms +/- 5.2%<br class="">
md5: 23.5 ms +/- 4.8%<br class="">
sha1: 13.8 ms +/- 5.3%<br class="">
<br class="">
date: 61.9 ms +/- 3.5%<br class="">
format-tofte: 29.6 ms +/- 3.3%<br class="">
format-xparb: 32.3 ms +/- 3.9%<br class="">
<br class="">
math: 33.4 ms +/- 5.1%<br class="">
cordic: 6.4 ms +/- 14.1%<br class="">
parial-sums: 22.3 ms +/- 4.5%<br class="">
spectral-norm: 4.7 ms +/- 10.3%<br class="">
<br class="">
regexp: 12.2 ms +/- 3.7%<br class="">
dna: 12.2 ms +/- 3.7%<br class="">
<br class="">
string: 173.0 ms +/- 2.2%<br class="">
base64: 13.1 ms +/- 4.8%<br class="">
fasta: 32.6 ms +/- 3.3%<br class="">
tagcloud: 32.5 ms +/- 3.3%<br class="">
unpack-code: 76.3 ms +/- 2.3%<br class="">
validate-input 18.5 ms +/- 2.0%<br class="">
<br class="">
<br class="">
145828 WebKit<br class="">
Total: 377.0 ms +/- 1.1%<br class="">
<br class="">
3d: 56.2 ms +/- 3.1%<br class="">
cube: 20.7 ms +/- 6.7%<br class="">
morph: 15.8 ms +/- 2.9%<br class="">
raytrace: 19.7 ms +/- 2.4%<br class="">
<br class="">
access: 26.3 ms +/- 2.9%<br class="">
binary-trees: 2.1 ms +/- 10.8%<br class="">
fannkuch: 11.2 ms +/- 5.9%<br class="">
nbody: 8.3 ms +/- 4.2%<br class="">
nsieve 4.7 ms +/- 14.4%<br class="">
<br class="">
bitops: 19.3 ms +/- 4.6%<br class="">
3bits-bits-in-byte: 2.1 ms +/- 10.8%<br class="">
bits-in-byte: 11.2 ms +/- 14.6%<br class="">
bitwise-and: 5.1 ms +/- 4.4%<br class="">
nsieve-bits: 8.1 ms +/- 2.8%<br class="">
<br class="">
controlflow: 3.2 ms +/- 9.4%<br class="">
recursive: 3.2 ms +/- 9.4%<br class="">
<br class="">
crypto: 31.2 ms +/- 3.4%<br class="">
aes: 14.6 ms +/- 7.4%<br class="">
md5: 9.5 ms +/- 4.0%<br class="">
sha1: 7.1 ms +/- 3.2%<br class="">
<br class="">
date: 64.8 ms +/- 3.7%<br class="">
format-tofte: 29.4 ms +/- 5.0%<br class="">
format-xparb: 35.4 ms +/- 3.2%<br class="">
<br class="">
math: 39.8 ms +/- 3.8%<br class="">
cordic: 5.8 ms +/- 5.2%<br class="">
partial-sums: 30.2 ms +/- 4.7%<br class="">
spectral-norm: 3.8 ms +/- 14.8%<br class="">
<br class="">
regexp: 11.6 ms +/- 5.2%<br class="">
dns: 11.6 ms +/- 5.2%<br class="">
<br class="">
string: 124.6 ms +/- 1.8%<br class="">
base64: 12.6 ms +/- 6.7%<br class="">
fasta: 22.3 ms +/- 6.4%<br class="">
tagcloud: 24.8 ms +/- 4.0%<br class="">
unpack-code: 49.3 ms +/- 2.75<br class="">
validate-input: 15.6 ms +/- 4.4%<br class="">
<br class="">
Thanks,<br class="">
Rodney<br class="">
<br class="">
_______________________________________________<br
class="">
webkit-dev mailing list<br class="">
<a moz-do-not-send="true"
href="mailto:webkit-dev@lists.webkit.org" class="">webkit-dev@lists.webkit.org</a><br
class="">
<a class="moz-txt-link-freetext" href="https://lists.webkit.org/mailman/listinfo/webkit-dev">https://lists.webkit.org/mailman/listinfo/webkit-dev</a><br
class="">
</div>
</blockquote>
</div>
<br class="">
</div>
</blockquote>
<br>
</body>
</html>