Eyes Above The Waves

Robert O'Callahan. Christian. Repatriate Kiwi. Hacker.

Monday 27 October 2014

Are We Fast Yet? Yes We Are!

Spidermonkey has passed V8 on Octane performance on arewefastyet, and is now leading V8 and JSC on Octane, Sunspider and Kraken.

Does this matter? Yes and no. On one hand, it's just a few JS benchmarks, real-world performance is much more complicated, and it's entirely possible that V8 (or even Chakra) could take the lead again in the future. On the other hand, beating your competitors on their own benchmarks is much more impressive than beating your competitors on benchmarks which you co-designed along with your engine to win on, which is the story behind most JS benchmarking to date.

This puts us in a position of strength, so we can say "these benchmarks are not very interesting; let's talk about other benchmarks (e.g. asm.js-related) and language features" without being accused of being sore losers.

Congratulations to the Spidermonkey team; great job!

Comments

Mike
So how can i use it to run my nodejs app?
KryDos
I thought Node.JS is using V8 and you can't choose another JS engine. Is it not true?
Robert
There was this, but it's no longer maintained: https://github.com/zpao/spidernode If the gap between V8 and Spidermonkey continues to widen, maybe someone should resurrect that or something like it. I guess it'd be a lot of work though. Regardless, the choices made by Node.JS aren't really our problem (except where our embedding API needs improvement...).
Harry Moreno
yep. If the difference in speed widens you bet someone will resurrect the project. I'd love to see that happen but I agree with the OP - asm.js and real-world related benchmarks are more interesting.
Anonymous
You can use Narwhal, which is a server-side Node.js-like platform with Spidermonkey, Rhino, V8 and more engines.
Dave Conrad
Why would it have Rhino rather than Nashorn?
mayank
asm.js and the ongoing SIMD work are quite interesting. And whatever happened to the Intel Rivertrail project?
Anonymous
In real world V8 still feels much faster.Also I think Firefox is not good css animations (smoothnes) and ui performance (needs e10s)
Nils
Well, to be fair: Firefox has come quite a long way when it comes down to rendering performance. Even though others might be able to display CSS animations with a higher perceived smoothness, they tend to be quite heavy on system resources. Opposed to that: FF's perceived performance in WebGL and Canvas rendering is almost always better than its' competitors' on my machine (at least). As for E10S: That is actively being worked on and made huge improvements over the last nightly releases.
Anonymous
I think ram usage not important.Because almost everyone have minimum 4gb ram.Peoples are looking fast and smooth experience. I think firefox is the best browser but unfortunately Chrome much faster and smooth.
Anonymous
"i think ram usage not important" now you went full retard
Anonymous
What is your choise performance or ram usage ?
Anonymous
Firefox and Chrome run on Android, and there are still new Android devices with 1GB of RAM or less. Firefox even runs on Firefox OS devices with 256MB of RAM - but on Firefox OS, there's no intermediary graphical layer and window manager that eats resources too. So memory usage is important, and will remain important until a $25 disposable phone has 8GB of RAM.
Anonymous
I am talking about pc's.For Android you're right.But current pc's are powerful and performance is important than ram usage for me.
Oberon
Lots of people still have slightly older, but perfectly functional machines and would like to be able to browser while their 2-4gb of RAM isn't eaten up by a browser just for a tiny performance edge. Even Chromebooks and Macbook Airs often still have 2gb. Asking people to upgrade their RAM when there's a browser that can match the performance at half the RAM usage is bizarre.
zxz
Simple test: http://jsbin.com/oNiVUYe/5/quiet Chrome win.
Oberon
@Lukasz: Firefox wins for me on that one, hands down. But it's easy to find a highly-contrived test where one beats the other, so I fail to see why this matters as much as benchmarks actually trying to measure real-world performance.
Anonymous
Amazing! Congrats guys!
skribi
No test in a Linux Machine?
Mathias Panzenböck (panzi)
Well, there is Android in the list.
Anonymous
When you make the separation process for the tabs?