Javascript Performance Thread
- patrickjdempsey
- Posts: 23686
- Joined: October 23rd, 2008, 11:43 am
- Location: Asheville NC
- Contact:
Re: Firefox 4.0 TM and JM Performance Thread
I think the problem with "real world" benchmarking is that "real world" means dynamic. It means that you never know WHEN the user is going to press a button and chances are, the user will probably press the button to engage the next action at exactly the wrong time. You also don't know if the user is impatient and pressed the button 10 times and therefore launched the script 10 times even though he didn't intent to. Obviously, a benchmark test would never test that situation. And benchmarks are rarely made on computers running pathetic processors with pathetic amounts of memory available, and tons of weird software running in the background, which is actually pretty typical for the average user. So the question is not, can I play SNES on my computer in Flash? the question is, can I play SNES on my pathetically old computer running an outdated version of Flash whilst simultaneously downloading my emails with bottlenecked bandwidth, preforming a virus scan and having a stubborn and ineffective Firewall lording over it all?
Tip of the day: If it has "toolbar" in the name, it's crap.
What my avatar is about: https://addons.mozilla.org/en-US/seamonkey/addon/sea-fox/
What my avatar is about: https://addons.mozilla.org/en-US/seamonkey/addon/sea-fox/
- Adrian1
- Posts: 154
- Joined: May 5th, 2010, 4:40 am
Re: Firefox 4.0 TM and JM Performance Thread
Some new performance improvment in http://arewefastyet.com/ for SS
- Erunno
- Posts: 746
- Joined: December 5th, 2008, 10:56 am
Re: Firefox 4.0 TM and JM Performance Thread
JägerMonkey has also been added to the x64 builds recently: http://arewefastyet.com/?machine=4
The previous signature has been removed again. Enjoy your month off, Erunno.
-
- Posts: 1033
- Joined: July 18th, 2003, 10:09 pm
Re: Firefox 4.0 TM and JM Performance Thread
Looking at those individual test results, While V8 and JSCore stay constant, Trace and Jager was flexing up and down.
In the best scenario, We want trace to beat V8 and JsCore with huge margin where it can, and Jager to stay close or equal to V8 and JScore with other test.
In the best scenario, We want trace to beat V8 and JsCore with huge margin where it can, and Jager to stay close or equal to V8 and JScore with other test.
-
- Posts: 124
- Joined: July 21st, 2008, 2:53 pm
Re: Firefox 4.0 TM and JM Performance Thread
Erunno wrote:JägerMonkey has also been added to the x64 builds recently: http://arewefastyet.com/?machine=4
Ouch... Nearly twice as bad as the tracing JIT
- Bluefang
- Posts: 7857
- Joined: August 10th, 2005, 2:55 pm
- Location: Vermont
- Contact:
Re: Firefox 4.0 TM and JM Performance Thread
That's not surprising. It probably needs the same amount of optimization work that x86 needed.
There have always been ghosts in the machine... random segments of code that have grouped together to form unexpected protocols. Unanticipated, these free radicals engender questions of free will, creativity, and even the nature of what we might call the soul...
-
- Posts: 1021
- Joined: November 7th, 2002, 11:15 pm
Re: Firefox 4.0 TM and JM Performance Thread
Adrian1 wrote:Some new performance improvment in http://arewefastyet.com/ for SS
Yeah, getting exciting now.
- bogas04
- Posts: 977
- Joined: May 18th, 2010, 1:14 am
Re: Firefox 4.0 TM and JM Performance Thread
Can anyone test all browsers in peacekeeper test with latest preB3?
- _Alexander
- Posts: 1197
- Joined: April 1st, 2010, 2:24 pm
- Location: Your augmented reality
Re: Firefox 4.0 TM and JM Performance Thread
Tracing seems to have issues, while methods seems just fine...
http://magneticpudding.com/ <- My Blog
i5 3570k @ 4.5 Ghz / NV 660 / 32GB DDR3 / 1080p LCD / SSD (120 + 180) / W8 ||| Atom N270 / NV ION / 3GB DDR3 / SSD / 1366x768 / W8
i5 3570k @ 4.5 Ghz / NV 660 / 32GB DDR3 / 1080p LCD / SSD (120 + 180) / W8 ||| Atom N270 / NV ION / 3GB DDR3 / SSD / 1366x768 / W8
-
- Posts: 245
- Joined: June 21st, 2010, 12:57 pm
Re: Firefox 4.0 TM and JM Performance Thread
guys if i were to rely only on sunspider v8 speed and whats not other browser like chrome,opera etc i wouldnt be using firefox!do you honestly believei use firefoxd by random luck or just lunacy.come on guys!it is not our fault if you run your browser improperly .yes bug do come in firefox.but lets face it:there are lot more factor then js speed if you cannot see this then im sorry to say just go with chrome or opera and all your percieved issue will be solve!for those other still here,dont sweat it firefox is one of the top browser .but like any average there are pros and there are con .for me i tend to like the pros of firefox a lot more then the pros of other browser.
-
- Posts: 403
- Joined: October 30th, 2005, 9:15 am
Re: Firefox 4.0 TM and JM Performance Thread
drbaltazar, please get your interpunction correctly and use paragraphs... I suppose you are not a native speaker, but you can at least try to get the text formatted correctly.
- bogas04
- Posts: 977
- Joined: May 18th, 2010, 1:14 am
Re: Firefox 4.0 TM and JM Performance Thread
IE9 PP4 is out , and so are new demos !
Waiting for someone to perform tests , as i am on a netbook (sent PC's HDD for RMA)
Waiting for someone to perform tests , as i am on a netbook (sent PC's HDD for RMA)
- ioiokzkz
- Posts: 243
- Joined: December 17th, 2008, 9:38 pm
Re: Firefox 4.0 TM and JM Performance Thread
Well guys, I think this is what we've been waiting for... moz JM+TM
http://arewefastyet.com/?machine=6
http://arewefastyet.com/?machine=6
-
- Posts: 669
- Joined: May 20th, 2010, 8:12 am
Re: Firefox 4.0 TM and JM Performance Thread
ioiokzkz wrote:Well guys, I think this is what we've been waiting for... moz JM+TM
http://arewefastyet.com/?machine=6
Considering those are really WIP heuristics that's actually impressive. It can only get better from now on.
- Omega X
- Posts: 8225
- Joined: October 18th, 2007, 2:38 pm
- Location: A Parallel Dimension...
Re: Firefox 4.0 TM and JM Performance Thread
Wow, I was just on that page a second ago.