Thursday, March 6th, 2008

Backbase tests browser JavaScript and Render performance including IE 8

Category: Browsers, JavaScript, Performance

Sjoerd Mulder of Backbase ran a couple of performance tests on a slew of browsers, including IE 8 beta. He tested both the JavaScript performance, and the rendering performance:

A lot of respect and thanks to all the browser teams pushing the boundary of performance. I think it’s an awesome result that the current nightlies of both Webkit and Gecko are 2x / 3x faster than the current production versions. Can’t wait until Firefox 3 is released to the public!

It seems the IE team still needs to do a lot of optimization in the render engine, but still we have to consider that it’s a beta 1. So let’s hope they either improve some more or everybody switches to Firefox / Safari.

JavaScript Performance

The first section is the Javascript Engine of Backbase and testing various scenarios, for instance:

  • TDL Compiling / parsing
  • Javascript XPath 2.0 Engine
  • XEL execution / event propagation

Backbase Performance: JavaScript

Render Performance (DOM)

The second part is rendering widgets, for example:

  • Rendering 1 accordion
  • Rendering 5 accordions
  • Rendering a listGrid
  • etc..

Backbase Performance: Render

The full specification and timings is available to see.

Posted by Dion Almaer at 8:11 am

4.1 rating from 33 votes


Comments feed TrackBack URI

Those graphs don’t seem to make any sense. For example, Safari’s js engine is no where near as slow as it’s displayed there.

Comment by Anonymous — March 6, 2008

A label on the y-axis would be helpful. From the original article, the y-axis represents “the time it takes to execute the different engine performance tests.” Units wouldn’t hurt either.

Comment by pwnedd — March 6, 2008

Anonymous, I think you need to take another look at the graph. Safari is actually represented very well.

FireFox 2 has been a pig for me as of late. I am also eagerly awaiting the public FF3 release.

Comment by leveille — March 6, 2008

So the shorter the bar the better right?

Comment by JeromeLapointe — March 6, 2008

Even if the y-axis is time, the graph still doesn’t make any sense. That would mean Opera is the slowest of the bunch, while in reality it has one of the fastes js engines available.

Comment by Anonymous — March 6, 2008

Hi Anonymous, I encourage you to read the article at it gives the reason for Opera seeming slow: “the main reason for this is the test for the event propagation being 5x slower in Opera than Firefox”.

Comment by JepCastelein — March 6, 2008

interesting results – however they do not correspond to most speed tests I have came across before….

Comment by OndraM — March 6, 2008

Hi OndraM, can you provide some links and more detail? Please note that 3 of the browsers tested have been released in the last week, so I doubt there will be many tests around. Thanks, Jep

Comment by JepCastelein — March 6, 2008

Hi Jep, one was recently here on Ajaxian:

I guess it depends quite a lot on chosen methodology. How else can one explain this bizzare thing ;)

I went through the methodology of the Backbase and detailed results – of course – after posting my previous message :( – and it seem very thorough, however.

Comment by OndraM — March 7, 2008

The thing about the IE8 tests is it really seems to matter what mode you’re running it in.. whether its the new IE8 standards mode, or IE7 mode and so-on. My experience (at least with the beta build) is that the rendering performance in ie8 standards is Abysmal. I’m curious what other people have experienced.

Comment by alexeiwhite — March 7, 2008

OndraM, the results of the first test that you link to are actually quite similar. Our figures also show that Firefox nightly is faster than Safari 3.0.4b, and that Safari 3.0.4b is close to Firefox 3 beta 3 (our test shows Safari slightly faster, the other test Firefox). We spent a lot of time optimizing our code for IE, so maybe that’s why IE looks faster in our test compared to Firefox 2. Opera is an anomaly because we tested event propagation extensively, and Opera is apparently not very fast in that.
Of course, the results of any benchmark depend on the exact operations you include, so there will always be variation. Nevertheless, it’s clear that both Firefox 3.x and Safari 3.x are really fast, and getting faster in the nightly builds. IE is still pretty slow, but getting better. Not sure about the Wired News test results: they don’t seem very scientific.
@ Alexei: we’ve used IE7 mode, but we’ll do some further testing in the other modes.

Comment by JepCastelein — March 7, 2008

Leave a comment

You must be logged in to post a comment.