iPhone 4S Preliminary Benchmarks: ~800MHz A5, Slightly Slower GPU than iPad 2, Still Very Fast
by Anand Lal Shimpi & Brian Klug on October 11, 2011 3:22 AM EST- Posted in
- Smartphones
- Apple
- Mobile
- iPhone 4S
- SoCs
Apple's ability to control the entire information chain, down to the point of limiting leaks, appears to be gradually slipping as it grows as a company. Case in point are the numerous hardware and performance leaks surrounding the newly launched iPhone 4S. Little did we know that several weeks ago we were staring at photos of the 4S' PCB, and more recently we've seen the first performance results from Apple's first A5 based smartphone thanks to a few eager users around the web. We've compiled these results here from various sources (all linked below) and compared them to our existing database of tests.
The results are pretty much as expected. Javascript performance finally catches up to Tegra 2 based Honeycomb devices, while general CPU performance is significantly higher than the iPhone 4. I suspect Ice Cream Sandwich will bridge the Android smartphone gap (the Honeycomb equipped Gtab 8.9 is here to give you an idea of where a more modern Android browser ends up).
Keep in mind that all of these tests measure performance of the software stack in addition to the hardware. In particular the web browser tests depend largely on browser optimizations, which is why we see differences between similar hardware running different browser versions. Also note that all results were run at stock, with the stock browser. Finally, although these browser tests were captured on video we'll still be running our official tests once our 4Ses arrive and will update accordingly.
Using some of the integer and fp tests of published Geekbench scores we can already conclude that Apple is shipping a lower clocked A5 in the iPhone 4S than it does in the iPad 2. This naturally makes sense as the iPhone 4S has a much smaller 5.25 Whr battery. Based on the Geekbench results it looks like the iPad 2 is clocked around 25% higher than the iPhone 4S, pegging the latter's clock speed at 800MHz.
A lower clock not only means higher yields from the factory, but likely a lower operating voltage as well. Dropping a CPU's core voltage, yields a greater-than-linear decrease in power consumption, making the marginal loss in clock speed a good choice. At a lower operating frequency than its Android competitors, Apple does have to exploit its strengths in software to avoid any tangible performance penalties. Apple has traditionally done this very well in the past, so I don't expect the loss of frequency to be a huge deal to the few who do cross-shop iOS and Android.
Unsurprisingly, memory bandwidth doesn't appear to have gone up either compared to the iPad 2's A5 (taking into account scaling due to CPU clock increases). The Samsung part number on the iPad 2's A5 indicates two LPDDR2-800 die on package, it's safe to assume that whatever Apple clocked the memory interface at in the iPad 2 remains unchanged in the iPhone 4S.
The GPU results tell a similar story courtesy of some early GLBenchmark 2.1 results. The 960 x 640 results are useless as they are bound by vsync at ~60 fps. Luckly GLBenchmark 2.1 added an off-screen render mode at 1280 x 720 where we can really see the differences between the iPad 2 and iPhone 4S A5 implementations:
Here the iPad 2 holds a ~21% performance advantage, which once again I assume to be all related to clock speed. Also note the huge advantage over the existing iPhone 4. The GPU power in the 4S should be more than enough to run any well written, current generation title at well north of 30 fps on its display.
We'll be reviewing the iPhone 4S in the coming weeks, stay tuned!
Source: GLBenchmark Database, Geekbench Database, Macrumors
Facebook
Twitter
RSS
216 Comments
View All Comments
KoolAidMan1 - Thursday, October 13, 2011 - link
Yes. The same goes for Windows Mobile 7 as well. Both WP7 and iOS on 2010 hardware are snappier and smoother than Android on the latest handsets.Android is a trash OS. No real focus has been made on performance, it's mostly been about serving ads to as many people as possible while zealots brag about being on an "open" platform.
I'll enjoy the closed platform that has the best developer support and best performance, thanks.
ab303 - Wednesday, October 12, 2011 - link
can anandtech check with Kishonti, the validity of glbenchmarks for iOS (IPAD-2/IPhone4S)?for e.g.
- are we sure that the iOS offscreen test is indeed rendering 720p, similar to android?
- this is an offscreen test, the underlying drivers and GPU in iOS could be smart enough to detect that the same FBO is being used for rendering over and over again without any reads. The drivers/GPU could very well be ignoring all the commands coming from the application layer. In this case, the test would be CPU bound and not GPU bound
- if the same test is repeated for different resolutions on iOS, is the FPS really changing? If the FPS doesnt change, then we can know for sure the offscreen testing result is not trust worthy
i kindly request anandtech to sanity check these points. Otherwise the results give a wrong picture of the GPUs.
AnandReader1999 - Wednesday, October 12, 2011 - link
I'm a long time Anand fan and have appreciated the depth which articles were done, from both a technical and fairness standpoint. Having reviewed the above 'preview' of the new iPhone 4S, I'm wondering if the actual forthcoming review will be as in depth as it needs to be give a fair shack to both sides (Android & iPhone).Some points I'm expecting.
- Both reviews will use the latest synthetic benchmarks. Any shortcomings of said benchmarks will be noted, including any software that may be taking advantage of hardware or not taking advantage of it.
- That the actual strengths of BOTH platforms be highlighted and displayed during the review. The iPhone is a LOCKED platform and circumventing it is very difficult. Stock browser's and stock apps are the norm. The Android platform is an OPEN platform with many choices for browsers and even rooting/ROM's is acceptable and supported by some manufacturer's. When comparing, the iPhone for should be Stock apps (as the norm) to Android Stock AND the Best Available, because that's what Android is. Free choice to chose the best of the best. If Cyanogen (or whatever stable ROM) is available for for Android phones, do the same tests using it. There should be a REAL comparison of platforms, not just a phone to a phone, locked down to stock browsers and constricted to Apples view of the world.
- The iPhone 4S is a HUGE leap in performance from the 4 and 3GS. How about some logical statements. Like why on earth would someone take a 3GS or 4 for ANY amount of money, when you can buy an Android Samsung Galaxy for $25 bucks on sale? I don't care if the iPhone 4S is faster (now), I'm still only paying $180 on contract at the worst and its routinely no sale for $75 or $25 here in Canada. (The USA will have them on sale more in the next month or so). The iPhone is NEVER on sale. They just drop the price to dump them before the next release.
I'm hoping to see the REAL advantages of the iPhone 4S vs Android (Samsung Galaxy S2 & S2X). The Prime can always be added at a later date for comparison to showcase newer hardware and OS update improvements...as this is also a strength of the Android phones.
Comments Anand?
doobydoo - Sunday, October 16, 2011 - link
allow me to translate this whole post:'Waa waa, please Anand, make sure you don't compare the iPhone 4S to the Android. Please try to unbalance the test in Androids favour with non-stock browsers (but ignore the non-stock browsers on iPhone) because we want our geek-droids to look less owned. Please Please.'
Swapzzz - Thursday, October 13, 2011 - link
http://www.webkit.org/perf/sunspider-0.9.1/sunspid...Mentioned URL proved that the Scores over there are Fudged I benchmarked my phone HTC Sensation 2.3.3 and guess what you guys suck because you try to beat competition with fake results.
Also, even though the HTC Sensation is running a stock browser that uses single core it still beats most of it Can wait till i get the Icescream Sandwich to see some real dual core processing.
ON YOUR FACE ! FANBOYS!
lang999 - Thursday, October 13, 2011 - link
Its pretty clear that even with android 3.x it gets the same resluts as ios5.And soon android 4 is out.
So this test is pretty much USELESS:
Not compententertive. No nothing.
!
BrandoHD - Thursday, October 13, 2011 - link
I think a lot of people would be surprised by how fast Samsung would update the SGS2, it has been rumoured that a device is already running 4.0 with Touchwiz, I have a SGS2 and I am running 2.3.5, while I cant speak for the carrier versions, the international versions of the SGS 2 should hopefully see the first 4.0 Roms coming out by the ending of 2011.TunaSandwich - Sunday, October 16, 2011 - link
The iPhone 4S is great without a doubt but this article is not well written. The article almost misrepresents reality by only reporting select information. I expect more from AnandTech. Regardless, I've learned more about benchmarks and the potential for biased reporting by taking a closer look.The SunSpider Benchmark is biased depending on the browser. Some benchmarks on the Samsung with alternate browsers do much better.
Samsung Galaxy SII @ 1.2Ghz with Android 2.3.3 & Firefox Beta – 1370
Samsung Galaxy SII @ 1.2Ghz with Android 2.3.3 & Opera Browser – 1600
Apple iPhone 4S with iOS5 – 2222
Samsung Galaxy SII @ 1.2Ghz with Android 2.3.3 – 3371
http://www.bestsmartphone.com/2011/09/26/javascrip...
The Rightware BrowserMark also has issues and is browser specific. A Firefox browser on the Samsung does great (but maybe too good to be true).
Samsung Galaxy SII with Firefox Beta: 94834 http://www.youtube.com/watch?v=ld0KMsxax2I
Apple iPhone 4S: 89567
There is a reported problem with Firefox and Safari on this test so maybe neither value is of any good.
http://www.bestsmartphone.com/2011/10/11/browserma...
Anandtech has only reported on the GLBenchmark 2.1 "offscreen benchmark 720p" without looking at other tests that show a lot of similarity between the iPhone and Samsung. There are also some funny things happening in this benchmark. If you take a look at the individual tests at GLBenchmark for the iPad2 50% are around 80 fps while 50% are around 50 fps. So does this mean that the iPhone 4s is faster than the iPad2? This offscreen benchmark is at 720p to which many devices may not be optimized simply because they were never intended to run at 720p. I've decided to misrepresent things a little in using only the top benchmark values for the Samsun in this test (see below).
iPhone 4s Samsung Galaxy SII
GLBenchmark 2.1 Egypt Fixed Time : 47930 ms 47595 ms
GLBenchmark 2.1 Egypt High : 57.5 Fps 59.2 Fps
GLBenchmark 2.1 Egypt Offscreen 720p : 73.1 Fps 49.9 Fps
GLBenchmark 2.1 Egypt Standard : 58.2 Fps 59.7 Fps
GLBenchmark 2.1 Pro Fixed Time : 21049 ms 20870 ms
GLBenchmark 2.1 Pro High : 58.5 Fps 59.9 Fps
GLBenchmark 2.1 Pro Offscreen 720p : 122.7 Fps 97.2 Fps
GLBenchmark 2.1 Pro Standard : 59.1 Fps 59.9 Fps
http://www.glbenchmark.com/phonedetails.jsp?benchm...
http://www.glbenchmark.com/phonedetails.jsp?benchm...
doobydoo - Sunday, October 16, 2011 - link
The benchmarks which SG2 wins are due to VSync on the iPhone.The iPhone beats the SG2 in ALL benchmarks if you ignore VSync.
The offscreen benchmarks are the only ones that do this.
krumme - Monday, October 17, 2011 - link
One day more for ip4s superiority - in an area that doesnt matter anymore.Then all is left is siri, and the subjective interpretation of build quality, that last until this unnessesary heavy brick hits the floor.
I hate this iphone 4 reminds me of the old B&O remote controls, that was made heavy to signal quality. Worlds oldest marketing trick. Its like colouring the washing powder blue, to signal its good at taking the hard dirt. Lol. People walking around with iron in their pockets. How stupid is that?