Re: JavaScript Benchmark and more

On 9/25/10 9:00 PM, DQ wrote:
> Results were astonishing

They were?

> latest Chrome (7.0.517.17) at 352ms, Opra 10.62 at 367ms, and latest Minefield 32bit [with hardware acceleration
> enabled]  at 502ms, while the 64bit Minefield browser [with hardware
 > acceleration enabled] (latest) measured 631.4ms! (link below),

You're running sunspider.  Hardware acceleration is irrelevant.

Why is any of this astonishing?  http://arewefastyet.com/ has all this data.

> especially because my system is high-end (Quad core 2.66Ghz, 3MB
> cache, 4GB DDR3 RAM with Vista 6bit) and 4the MOZdev team boasts FF4b
> to be fast.

You seem to think that "fast" is a one-dimensional absolute metric.

The Fx4 betas are generally much faster than Fx 3.6.

On some tasks, the Fx4 betas are much faster than Opera or Chrome.

On some tasks, the Fx4 betas are much slower than Opera or Chrome.

And in fact, the same will probably be true for the final release.  Some 
things will be faster; some will be slower.  It's up to you whether the 
things that matter to you personally are performance of web apps or 
execution time of a buggy benchmark that has code that's specifically 
designed to make some browsers run slower by executing different tasks 
in different browsers.

> So, Mozilla, what gives?

Bogus expectations on your end?  ;)

-Boris