or Connect
AppleInsider › Forums › General › General Discussion › Apple A6 SoC outperforms Intel Atom in JavaScript test
New Posts  All Forums:Forum Nav:

Apple A6 SoC outperforms Intel Atom in JavaScript test

post #1 of 27
Thread Starter 
A test of the iPhone 5's new A6 processor yielded a surprisingly quick score on SunSpider's JavaScript benchmarking tool, with the system on chip topping even the Medfield Atom Z2460.

While not an official test, AnandTech was able to run SunSpider v0.9.1 on an iPhone 5 review sample on Wednesday, and watched as the dual-core A6 chip chewed through the benchmark in 914.7 milliseconds, outpacing the second place Lava XOLO X900's time of 1279.4 milliseconds. The Lava XOLO runs a single-core Intel Atom Z2460 Penwell SoC built on the chip maker's Medfield platform.

width=
Source: AnandTech


As noted by the publication, SunSpider is slowly becoming outdated as a smartphone benchmark, however it highlights issues pertaining to ARM's Cortex A9 memory interface.

"Intel originally hinted at issues in the A9's memory interface as being why Atom was able to so easily outperform other ARM based SoCs in SunSpider," reports Anand Shimpi.

In a Monday report, online benchmarking site Geekbench reportedly logged an iPhone 5's performance data, outing the specifications of the handset's A6 chip. At the time, it was thought that Apple made dramatic improvements to the standard ARM core's memory interface as the Geekbench data suggested a drastic improvement from previous Cortex A9 chips.

Although it hasn't yet been confirmed, the A6 chip is reportedly Apple's first attempt at designing an ARM core in-house.
post #2 of 27
"At the time, it was thought that Apple made dramatic improvements to the standard ARM core's memory interface as the Geekbench data suggested a drastic improvement from previous Cortex A9 chips."


"At the time..." that was then... so what do they think now?
post #3 of 27
Quote:
Originally Posted by Douglas Bailey View Post

"At the time, it was thought that Apple made dramatic improvements to the standard ARM core's memory interface as the Geekbench data suggested a drastic improvement from previous Cortex A9 chips."
"At the time..." that was then... so what do they think now?


They think it's apple's own in-house arm design now, and not based off of the cortex a9 or a15, but it's not confirmed.

post #4 of 27

They should have added both 4S iOS 5 and 4S iOS 6 results as any speed increase in sunspider cannot be attributed to the SoC alone.

post #5 of 27
Quote:
Originally Posted by AppleInsider View Post

 outpacing the second place Lava XOLO X900's time of 1279.4 milliseconds. The Lava XOLO runs a single-core Intel Atom Z2460 Penwell SoC built on the chip maker's Medfield platform.
 

 

So as per the previous discussion with Geekbench, the single core Atom actually does quite well compared to the dual core A6.

 

My own opinion is that Ghz and core count is irrelevant, performance / Watt is the only relevant number for these kinds of devices and the iPhone5 is a winner in that regard.


Edited by mausz - 9/19/12 at 3:06am
post #6 of 27
Quote:
Originally Posted by mausz View Post

 

So as per the previous discussion with Geekbench, the single core Atom actually does quite well compared to the dual core A6.

In difference to Geekbench Sunspider does only utilize 1 Core.

post #7 of 27
Quote:
Originally Posted by smalM View Post

In difference to Geekbench Sunspider does only utilize 1 Core.

 

How can you force the use of 1 cpu core from javascript ? You cannot as javascript has no notion of cpu cores or affinity.

 

I know most javascript engines use only 1 core (although IE uses multithreading for compiling and running) but in speculation maybe the biggest change with ios6 is the new javascript engine in mobile safari which uses both cores.

 

That's why the performance with a 4S with ios 6 is relevant. Googling found a few results which show the 4S went from 2200 to 1800 with ios6, so 18% improvement is due to ios6, So iPhone5 with ios5 (not correct to extrapolate this but still) would probably have scored 1165 in sunspider. Still good.


Edited by mausz - 9/19/12 at 3:54am
post #8 of 27
Quote:
Originally Posted by smalM View Post

In difference to Geekbench Sunspider does only utilize 1 Core.

 

Can you then explain why 4-core international S3 is significantly faster than US (AT&T) version with 2-cores ?

post #9 of 27
Quote:
Originally Posted by smalM View Post

In difference to Geekbench Sunspider does only utilize 1 Core.

 

So how does that explain the variation in the Galaxy S III scores, between quad core with  1GB of RAM, dual core with 2GB RAM, etc?


Edited by hill60 - 9/19/12 at 4:07am
Better than my Bose, better than my Skullcandy's, listening to Mozart through my LeBron James limited edition PowerBeats by Dre is almost as good as my Sennheisers.
Reply
Better than my Bose, better than my Skullcandy's, listening to Mozart through my LeBron James limited edition PowerBeats by Dre is almost as good as my Sennheisers.
Reply
post #10 of 27
Quote:
Originally Posted by hill60 View Post

 

So how does that explain the variation in the Galaxy S III scores, between quad core with  1GB of RAM, dual core with 2GB RAM, etc?

 

As a general point, people often state multi cores are not handy because each process is single-threaded and most mobile apps do not employ multithreading. However, with multiple cores processes can be run on different cores. So a single core javascript benchmark can run on one, and for instance whatsapp and other multitasking processes can run on other cores. So with multiple cores and single-threaded apps you will see better performance because the processes do not (or less) hinder eachother.

 

Wether this explains the large differences.... I know android took a big leap in sunspider scores when the chrome browser arrived to take the place of the stock android browser. Also large differences have been seen in 3.x,4.0.x en 4.1.x. As Anandtech does not state this information it's hard to tell what's going on here.

post #11 of 27
Ha and some people on MR are claiming Apple purposely downplayed this in the keynote so it would look more impressive when it came out. I suppose these are the same people who claimed Apple constrained supply in order to increase demand. lol.gif
post #12 of 27
I bet there is a team inside Apple working on a future version of OS X that runs on their own in house technology too. Maybe a future Mac will have an 'option' of an additional Intel chip for those that want to run Windows in a VM.
Edited by digitalclips - 9/19/12 at 5:29am
From Apple ][ - to new Mac Pro I've used them all.
Long on AAPL so biased
"Google doesn't sell you anything, they just sell you!"
Reply
From Apple ][ - to new Mac Pro I've used them all.
Long on AAPL so biased
"Google doesn't sell you anything, they just sell you!"
Reply
post #13 of 27
Jeez. That Nokia Lumia 900 is a snail. I sure hope the Lumia 920 does a lot better.
post #14 of 27
Quote:
Originally Posted by Constable Odo View Post

Jeez. That Nokia Lumia 900 is a snail. I sure hope the Lumia 920 does a lot better.

 

Absolutely, the new Lumia 920 has the Qualcomm S4, and the new wp8 ie10 browser, so should do a lot better (I hope for them ;)

post #15 of 27
Quote:
Originally Posted by Rogifan View Post

Ha and some people on MR are claiming Apple purposely downplayed this in the keynote so it would look more impressive when it came out. I suppose these are the same people who claimed Apple constrained supply in order to increase demand. lol.gif

LOL

The truth is I suspect that it was more a case of the Jobsian 'keep it simple stupid' philosophy in action. Apple long ago decided talking too technically is a bad way to go.
From Apple ][ - to new Mac Pro I've used them all.
Long on AAPL so biased
"Google doesn't sell you anything, they just sell you!"
Reply
From Apple ][ - to new Mac Pro I've used them all.
Long on AAPL so biased
"Google doesn't sell you anything, they just sell you!"
Reply
post #16 of 27
A sure sign it is time to upgrade your laptop? When your phone beats it in benchmarks...
OSX, because making UNIX user friendly is easier than debugging windows.
Reply
OSX, because making UNIX user friendly is easier than debugging windows.
Reply
post #17 of 27
Quote:
Originally Posted by shen View Post

A sure sign it is time to upgrade your laptop? When your phone beats it in benchmarks...

LOL, I bet a few cheepo PC owners must be thinking that.
From Apple ][ - to new Mac Pro I've used them all.
Long on AAPL so biased
"Google doesn't sell you anything, they just sell you!"
Reply
From Apple ][ - to new Mac Pro I've used them all.
Long on AAPL so biased
"Google doesn't sell you anything, they just sell you!"
Reply
post #18 of 27
Quote:
Originally Posted by mausz View Post

They should have added both 4S iOS 5 and 4S iOS 6 results as any speed increase in sunspider cannot be attributed to the SoC alone.
iOS 6 on 4S tested at 1,8xx so the A6 is still twice as fast.
post #19 of 27
Quote:
Originally Posted by jason98 View Post

 

Can you then explain why 4-core international S3 is significantly faster than US (AT&T) version with 2-cores ?

 

As was explained above, SunSpider is not the only process running. The more cores you have OTHER processes can be spread around freeing up CPU time for SunSpider to run. We also don't know what other processes are running on AT&T's phones. Just look at T-Mobile. Why is their S3 faster? 

 

If the test was multi-core aware, then theoretically having twice as many cores would cut the time in half, or at least approach it. 

 

Another factor could be the clock speed. Maybe the international S3 is clocked higher than the US model?

Disclaimer: The things I say are merely my own personal opinion and may or may not be based on facts. At certain points in any discussion, sarcasm may ensue.
Reply
Disclaimer: The things I say are merely my own personal opinion and may or may not be based on facts. At certain points in any discussion, sarcasm may ensue.
Reply
post #20 of 27
Quote:
Originally Posted by mjtomlin View Post

 

As was explained above, SunSpider is not the only process running. The more cores you have OTHER processes can be spread around freeing up CPU time for SunSpider to run. We also don't know what other processes are running on AT&T's phones. Just look at T-Mobile. Why is their S3 faster? 

 

If the test was multi-core aware, then theoretically having twice as many cores would cut the time in half, or at least approach it.

Another factor could be the clock speed. Maybe the international S3 is clocked higher than the US model?

 

I doubt that Anand did not take care of eliminating influences of "other" apps while running these tests. As for the frequencies, I believe they both have 1.4GHz.

Seems like browser tests are utilizing multi-cores somehow but they are not type of scalable linearly. 

post #21 of 27
Quote:
Originally Posted by mjtomlin View Post

 

As was explained above, SunSpider is not the only process running. The more cores you have OTHER processes can be spread around freeing up CPU time for SunSpider to run. We also don't know what other processes are running on AT&T's phones. Just look at T-Mobile. Why is their S3 faster? 

 

If the test was multi-core aware, then theoretically having twice as many cores would cut the time in half, or at least approach it. 

 

Another factor could be the clock speed. Maybe the international S3 is clocked higher than the US model?

 

And just to add another factor. I've read reports which have suggested newer ARM cores could employ turbo modes just like Intel desktop processors. So when a benchmark runs and only stresses one core, this core gets 'overclocked' as long as its within the thermal evelope.

 

This is one of the issues I have with some benchmarks. Sometimes a SoC uses more power while stressed but it's doing the work faster as well so in practice it would use more power but for a shorter amount of time. The net effect should be looked at.

post #22 of 27
Quote:
Originally Posted by mjtomlin View Post

 

As was explained above, SunSpider is not the only process running. The more cores you have OTHER processes can be spread around freeing up CPU time for SunSpider to run. We also don't know what other processes are running on AT&T's phones. Just look at T-Mobile. Why is their S3 faster? 

 

If the test was multi-core aware, then theoretically having twice as many cores would cut the time in half, or at least approach it. 

 

Another factor could be the clock speed. Maybe the international S3 is clocked higher than the US model?

 

So you think Android enthusiasts aren't aware of that, so will run a custom ROM with a minimum of background processes on over clocked hardware.

 

Like what happened when the iPhone 5 topped Geekbench, all of a sudden all these new results showed up.

 

A PC with it's CPU running at 6+ GHz and cooled with liquid nitrogen is not terribly practical for anything except topping benchmark scores.

 

I suspect the same is true of these Android ROM's.

Better than my Bose, better than my Skullcandy's, listening to Mozart through my LeBron James limited edition PowerBeats by Dre is almost as good as my Sennheisers.
Reply
Better than my Bose, better than my Skullcandy's, listening to Mozart through my LeBron James limited edition PowerBeats by Dre is almost as good as my Sennheisers.
Reply
post #23 of 27
It's nice that the phone I'll shortly own is not only ahead but far ahead but I think JS efficiency is good enough now that it's not a great indicator of how fast a page will render. I'm much more interested in Anand's review that will show times it takes to load pages.

I would like to see the speed of WebKit within an app to compare the JS differences between the two

This bot has been removed from circulation due to a malfunctioning morality chip.

Reply

This bot has been removed from circulation due to a malfunctioning morality chip.

Reply
post #24 of 27
Quote:
Originally Posted by mjtomlin View Post

 

As was explained above, SunSpider is not the only process running. The more cores you have OTHER processes can be spread around freeing up CPU time for SunSpider to run. We also don't know what other processes are running on AT&T's phones. Just look at T-Mobile. Why is their S3 faster? 

 

...

 

Another factor could be the clock speed. Maybe the international S3 is clocked higher than the US model?

 

Quote:
Originally Posted by hill60 View Post

 

So you think Android enthusiasts aren't aware of that, so will run a custom ROM with a minimum of background processes on over clocked hardware.

 

Like what happened when the iPhone 5 topped Geekbench, all of a sudden all these new results showed up.

 

...

 

I suspect the same is true of these Android ROM's.

 

 

Isn't this kind of indicative of the overall Android situation? Inefficient/bloated software fighting fast hardware?  The loser in the battle being battery life/device size.  The important part here being even if you *can* strip out some bloat, the vast majority of users *won't*.

 

I'd be curious to see the results of a jailbroken iPhone 5 with all unnecessary background process killed.  Not so much to one-up the tuned Android phones, more so to measure the "bloat" ratio of how close a stock iPhone 5 performs in relation to a carefully tuned one.  It's pretty much a given the iPhone 5 will best any Android phone on that test...

post #25 of 27
Quote:
Originally Posted by mausz View Post

How can you force the use of 1 cpu core from javascript ? You cannot as javascript has no notion of cpu cores or affinity.
True. However they might be using two cores under the hood for system calls and like. JavaScript itself is single threaded in most implementations though.
Quote:
I know most javascript engines use only 1 core (although IE uses multithreading for compiling and running) but in speculation maybe the biggest change with ios6 is the new javascript engine in mobile safari which uses both cores.
That still doesn't explain the vast improvement over existing iPhones running iOS 6. It still comes back to the SoC running much better.
Quote:
That's why the performance with a 4S with ios 6 is relevant. Googling found a few results which show the 4S went from 2200 to 1800 with ios6, so 18% improvement is due to ios6, So iPhone5 with ios5 (not correct to extrapolate this but still) would probably have scored 1165 in sunspider. Still good.

Where are you pulling those numbers from? We, at this point, simply don't know how optimized iOS is for the new instruction set. Who knows the cold come out with iOS 6.1 built on a new compiler version that optimizes for Apples new hardware and get even better results. This assumes that the compilers haven't already been optimized.

What we have here is a new processor architecture and as such potentially new avenues for optimization. That is just in running existing ARM code, if Apple added special co processors or custom instructions those would be additional improvements.

Sadly over the years Apple has filed for many patents related to CPUs but with their secrecy we may never know what exactly has been implemented in this SoC. obviously considering the slow clock on this chip there is some special sauce in the mix.
post #26 of 27
Quote:
Originally Posted by neosum View Post


They think it's apple's own in-house arm design now, and not based off of the cortex a9 or a15, but it's not confirmed.

It's possible that OTHER hardware along with the chip coupled with improvements to iOS could speed up JavaScript.

 

But I think it's all that PLUS Apple tweaking the A6. 

Did anyone mention which iOS version was being tested?

post #27 of 27
Quote:
Originally Posted by shen View Post

A sure sign it is time to upgrade your laptop? When your phone beats it in benchmarks...

 

what laptop runs a medfield atom? 

Household: MacBook, iPad 16gb wifi, iPad 64gb wifi, iPad Mini 32gb, coming iPhone 5S, iPhone 4S 32gb, iPhone 32gb, iPod Touch 4th gen x1, iPod nano 16gb gen 5 x2, iPod nano gen 3 8gb, iPod classic...
Reply
Household: MacBook, iPad 16gb wifi, iPad 64gb wifi, iPad Mini 32gb, coming iPhone 5S, iPhone 4S 32gb, iPhone 32gb, iPod Touch 4th gen x1, iPod nano 16gb gen 5 x2, iPod nano gen 3 8gb, iPod classic...
Reply
New Posts  All Forums:Forum Nav:
  Return Home
  Back to Forum: General Discussion
AppleInsider › Forums › General › General Discussion › Apple A6 SoC outperforms Intel Atom in JavaScript test