Closed paulirish closed 5 years ago
IE6 is throwing the following exception when trying to run Sunspider 0.9.1
Line: 71 Character: 9 Code: 0 Error Message: 'contentDocument' is null or not an object URL: http://www2.webkit.org/perf/sunspider-0.9.1/sunspider-0.9.1/driver.html
SunSpider 0.9.1 on Firefox 3.6.12 : http://goo.gl/IqBn
That gives it a total of 1540.7ms, how does that relate to the stat above that sits between 500 - 1000?
IE8 SunSpider 0.9.1 - 8930.8ms : http://goo.gl/myL8
Chrome 7.0.517.41 - 518.1ms : http://goo.gl/Pcf9
Opera 10.62 - SunSpider 0.9.1 - 442.6ms : http://goo.gl/Enuh Opera 11 Alpha - SunSpider 0.9.1 - 438.3ms : http://goo.gl/TCfM
Safari 5.0.2 (Windows) - SunSpider 0.9.1 - 653.9ms : http://goo.gl/LTiG
Finally ran IE9 Beta, as expected, huge leap forward:
IE9 Beta - SunSpider 0.9.1 - 680.5ms : http://goo.gl/f1f6
awesome. thx for running the tests.. i really wish we could get ie6 and 7 in there. :( shoddy javascript!
Hey Paul,
I put it all together here: http://goo.gl/Xutw
Will try to get IE6 against SunSpider again, if it fails again, perhaps logging a bug against SunSpider is in order.
Schalk
Hey Paul,
I got IE6 running against SunSpider 0.9, the results are not good ;D
Running on Windows7 using IETester, the results are: IE6 on IETester - SunSpider 0.9 : 48451.0ms : http://goo.gl/PYC3
Running on a WindowsXP VirtualPC, the results are: IE6 - SunSpider 0.9 : 120014.2ms : http://goo.gl/OPU46
If you look at the expanded results you will see that it is definitely the String operation that brings it to it's knees especially, base64, validate input and tag cloud.
Hey Paul,
I just launched thebrowsereview.com and added a chart combining all of the results from the above tests.
Schalk
Really nice work Schalk. :)
Thanks Paul, currently putting the browsers through the Dromaeo tests. Will add the results of these there as well.
I'd like to put a vote in for mobile browsers on different devices under different OS versions (See: Android fragmentation)
Would definitely like to add that, although that will obviously be much more difficult to attain as you will have to run the tests on the actual device. I guess someone like the jQuery Mobile folks could help out with something like this.
Yeah—not something to be taken lightly. I really feel like this arm developers with more knowledge about particular facets of javascript performance.
Sure thing, I agree. I will drop a note to the jQuery Mobile developers. I am sure they are doing something along these lines already.
Used that data to make.....
with something other than google docs that chart could be sexier.
oh man here's another good datapoint.. iPhone results for sunspider http://www.blaze.io/mobile/javascript-pre-execution-for-mobile-taking-scripts-out-of-the-loop/
Very cool Paul, I will run some tests on my Xoom and see how the Android stock browser as well as FF and Opera performs
Here is the results of running Sunspider 0.9.1 on Honeycomb standard browser : http://goo.gl/siOLS
also relevant:
dromaeo on ie8 through june 2012's browsers:
Anyone wanna take a swipe at updating that Dromaeo data with the the latest browsers? sheet: https://docs.google.com/spreadsheet/ccc?key=0ArK1Uipy0SbDdE9rN2UydUFpQTlDcnhWaWRjY3I1aEE&usp=drive_web#gid=0
I've made a new "May 2014" sheet and added the results from all the tests I was able to get to run. Unfortunately IE8 and Opera tests both don't complete for me :/.
Couldn't we automate this using SauceLabs or something?
This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions.
This issue has been automatically closed because it has not had recent activity. Thank you for your contributions.
So this chart..
shows ie8 relative to everyone else
we need one that adds in ie7 and ie6.. hopefully progressively for the big WOW effect.
but it needs to be more obvious the sort of scale of js performance we're dealing with.