The first iPhone 5 reviews have lifted, confirming the leaked Geekbench data we saw in our earlier post. Apple's A6 appears to feature two custom ARM cores running at up to 1GHz. A new datapoint comes courtesy of our own Brian Klug who's currently visiting LG in Seoul, South Korea. He ran into Vincent Nguyen of Slashgear fame, who kindly let him run SunSpider 0.9.1 on Vincent's iPhone 5 review sample. The score? 914.7ms.

SunSpider is quickly outlasting its welcome as a smartphone benchmark, but it does do a great job of highlighting issues with the Cortex A9's 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. As we surmised in our A6 Geekbench post, it looks like Apple specifically targeted improvements in the memory subsystem when designing the A6's CPU cores. The result is the fastest SunSpider test we've ever recorded on a smartphone - faster even than Intel's Atom Z2460.

This doesn't tell us much about the A6's architecture other than it's likely got a better cache/memory interface than ARM's Cortex A9. What we really need is for someone to port SPECint to iOS...

POST A COMMENT

110 Comments

View All Comments

  • madmilk - Thursday, September 20, 2012 - link

    There just aren't very many cross-platform benchmarks.

    Coremark is even worse: remember all of Nvidia's claims that Tegra 3 was faster than a Core 2 Duo? Maybe if your whole dataset is in L1 cache...
    Reply
  • tipoo - Wednesday, September 19, 2012 - link

    Well, the 4S went down from 2300MS to 1700, but the 5s score of 900-1000 is still much lower, so comparing the same software on different hardware we can still say it's just short of 2x. Reply
  • abishekmuw - Wednesday, September 19, 2012 - link

    My HOX running ICS 4.0.4 scores 1200ms in the stock browser. Jellybean is supposed to be faster.. Reply
  • Bpease - Wednesday, September 19, 2012 - link

    Well done to Apple on the new A6, it seems an intelligently designed piece of silicon. However Jelly Bean will significantly boost Sunspider / JS performance.

    The Galaxy Note 2 was previewed by gsmarena, and it scored 972 ms in its stock browser, the International S3 also improved its score by around 20% in another preview of the Jelly Bean update. It is worth noting that the tests were done with Beta software, so actual performance may improve or worsen!

    Hopefully the A6 will push Samsung to launch the Eyxnos A-15 based 5450, quad core @ 2.0 GHz and Mali T-658, pretty soon. A Nexus phone with that SoC might persuade me to ditch my WP7 and return to a pure Android stack, currently I run a Lumia 710, alongside a Nexus 7 ( + old iPod Touch for teh exercising)

    http://www.gsmarena.com/samsung_galaxy_note_ii-rev...
    Reply
  • vision33r - Wednesday, September 19, 2012 - link

    1GHZ iPhone outperforming so many 1.2~1.5GHZ Android phones

    Efficiency > Raw processing power
    Reply
  • superman3gsm - Thursday, September 20, 2012 - link

    The latest Sunspider scores on current Medfield SW builds beats the iPhone5 scores shown Reply
  • thunng8 - Thursday, September 20, 2012 - link

    No it doesn't:

    http://www.engadget.com/2012/09/18/motorolas-razr-...
    Reply
  • yogi6807 - Thursday, September 20, 2012 - link

    found this

    "A little bit of casual benchmarking using the GLBenchmark Egypt High test yielded a score of 6766, while the iPhone 4S got 1158. The Offscreen test was closer: 16681 vs 8346. This looks like a lot more than day to day usage bears out, but it suggests that there's headroom for the iPhone 5 to do some pretty impressive stuff."

    http://www.stuff.tv/review/apple-iphone-5
    Reply
  • tipoo - Friday, September 21, 2012 - link

    Double the performance of the 4S should put it near the iPad 3, but those reported scores are WAY higher.

    http://www.glbenchmark.com/result.jsp
    Reply
  • tipoo - Friday, September 21, 2012 - link

    Actually I was looking at the wrong thing, but in the Egypt High test the 4S gets 6000 too... Reply

Log in

Don't have an account? Sign up now