While working on our Haswell piece, I've been religiously checking the Geekbench and GLBenchmark results browsers to see if anyone ran either benchmark and decided to tap upload. This usually happens before every major smartphone launch, but in the case of the iPhone 5 the details these applications can give us are even more important.

Yesterday we confirmed that Apple is using its own custom designed ARM based CPU cores in its A6 SoC. Apple opted not to design in a vanilla ARM Cortex A9 likely to avoid relying on pure voltage/frequency scaling to improve performance, and chose not to integrate a Cortex A15 likely because of power consumption concerns as well.

There's absolutely no chance of Apple sending us a nice block diagram of the A6 CPU cores, so we have to work with what clues we can get elsewhere. Geekbench is particularly useful because it reports clock speed. Why does clock speed matter? Because, if reported accurately, it can tell us a lot about how the A6's CPU design has improved from an IPC standpoint. Remember that clock speed doesn't matter, but rather the combination of clock frequency and instructions executed per clock that define single threaded performance.

Apple iPhone 5 Models
iPhone 5 Model GSM/EDGE Bands WCDMA Bands CDMA 1x/EVDO Rev.A/B Bands LTE Bands (FCC+Apple)
A1428 "GSM" 850/900/1800/1900 MHz 850/900/1900/2100 MHz N/A 2/4/5/17
A1429 "CDMA" 850/900/1800/1900 MHz 850/900/1900/2100 MHz 800/1900/2100 MHz 1/3/5/13/25
A1429 "GSM" 850/900/1800/1900 MHz 850/900/1900/2100 MHz NA 1/3/5 (13/25 unused)

A short while ago, Geekbench results for a device identifying itself as an iPhone5,2 appeared. Brian believes this is likely the A1429 Verizon device (A1428 being iPhone 5,1) - perhaps one presampled to a reviewer looking to test their luck.

MacRumors appears to be first on the scene, having been tipped by an employee at PrimateLabs (the creators of Geekbench). I need to preface the rest of this post with a giant caution sign: I have no inside knowledge of whether or not these results are legitimate. They seem believable, but anything can happen. The rest of this post is simply my initial thoughts on what these mean, should the results be accurate. Update: The first iPhone 5 reviews are out and this Geekbench data looks accurate.

Cache sizes haven't changed, which either tells us Apple isn't feeling as generous with die size as perhaps it once was or that working sets in iOS are still small enough to fit inside of a 1MB L2. I suspect it's mostly the latter, although all microprocessor design is a constantly evaluated series of tradeoffs (often made through giant, awesomely protected spreadsheets). 

The first real change is clock speed. Apple clocked its A4 and A5 CPU core(s) at 800MHz, although these Geekbench results point to a 25% increase in frequency at 1GHz. Some of the headroom is likely enabled by the move to 32nm, although it's very possible that Apple also went with a slightly deeper pipeline to gain frequency headroom. The latter makes sense. We've seen conservative/manageable increases in pipeline depth to hit frequency targets and improve performance before. 

The fairly low clock speed also points to an increase in IPC (instructions executed per clock) over the Cortex A9 design. As I mentioned in our A6 analysis post, simple voltage/frequency scaling is a very power inefficient way to scale performance. A combination of IPC and frequency increases are necessary. If these results are accurate and the CPU cores are only running at 1GHz, it does lend credibility to the idea of a tangibly wider design.

It's also unclear if Apple is doing any sort of dynamic thermal allocation here, ala Intel's Turbo Boost. You can't get more power constrained than in a smartphone, and power gating is already common within ARM based SoCs, so that 1GHz value could be under load for both cores. A single core could run at higher frequencies for short bursts. 

The next thing that stood out to me was the memory data:

Geekbench Comparison
Memory Performance iPhone 4S iPhone 5 (unconfirmed) Scaling
Read Sequential ST 0.32 GB/s 1.78 GB/s 5.63x
Write Sequential ST 0.86 GB/s 1.35 GB/s 1.57x
Stdlib Allocate ST 1.44 Mallocs/s 1.92 Mallocs/s 1.33x
Stdlib Write 2.7 GB/s 6.06 GB/s 2.24x
Stdlib Copy 0.55 GB/s 2.26 GB/s 4.13x

 

Geekbench Comparison
Stream Performance iPhone 4S iPhone 5 (unconfirmed) Scaling
Stream Copy 0.42 GB/s 1.9 GB/s 4.55x
Stream Scale 319 MB/s 994 MB/s 3.11x
Stream Add 0.59 GB/s 1.39 GB/s 2.34x
Stream Triad 377 MB/s 1019 MB/s 2.70x

It's well known that ARM's Cortex A9 doesn't have the world's best interface outside of the compute core and its memory performance suffered as a result. If this data is accurate, it points to significantly overhauled cache and memory interfaces. Perhaps an additional load port, deeper buffers, etc...

Also pay close attention to peak bandwidth utilization. The 4S had 6.4GB/s of theoretical bandwidth out to main memory, the 5 raises that to 8.5GB/s. In the Stdlib write test the 4S couldn't even hit 50% of that peak bandwidth. The iPhone 5 on the other hand manages to hit over 70% of its peak memory bandwidth. I will say that if these numbers are indeed faked, whoever faked them was smart enough not to violate reality when coming up with these memory bandwidth numbers (e.g. no 95% efficiency numbers show up). It's also clear that these results aren't a simply doubling across the board over the 4S, lending some credibility to them.

Some of the largest performance improvements promised by the Geekbench data appear here in the memory results. It's whatever work Apple did here that helped enable the gains in the integer and floating point results below:

Geekbench Comparison
Integer Performance iPhone 4S iPhone 5 (unconfirmed) Scaling
Blowfish ST 10.7 MB/s 23.4 MB/s 2.18x
Blowfish MT 20.7 MB/s 45.6 MB/s 2.20x
Text Compress ST 1.21 MB/s 2.79 MB/s 2.30x
Text Compress MT 2.28 MB/s 5.19 MB/s 2.27x
Text Decompress ST 1.71 MB/s 3.82 MB/s 2.23x
Text Decompress MT 2.84 MB/s 5.60 MB/s 2.67x
Image Compress ST 3.32 Mpixels/s 7.31 Mpixels/s 2.20x
Image Compress MT 6.59 Mpixels/s 14.2 Mpixels/s 2.15x
Image Decompress ST 5.32 Mpixels/s 12.4 Mpixels/s 2.33x
Image Decompress MT 10.5 Mpixels/s 23.0 Mpixels/s 2.19x
Lua ST 215.4 Knodes/s 455 Knodes/s 2.11x
Lua MT 425.6 Knodes/s 887 Knodes/s 2.08x
MT Scaling 1.90x 1.92x  

On average we see around 2.2x scaling from the 4S to the 5 in Geekbench's integer tests. There's no major improvement in multicore scaling, confirming what Geekbench tells us that we're looking at a two core/two thread machine. 

The gains here are huge and are likely directly embodied in the performance claims that Apple made at the iPhone 5 launch event. Many smartphone workloads (under Android, iOS and Windows Phone despite what Microsoft may tell you) are still very CPU bound. Big increases in integer performance will be apparent in application level improvements.

Don't be surprised to see greater than 2x scaling here even though Apple only promised 2x at the event. Remember that what you're looking at is raw compute tests without many of the constraints that apply to application level benchmarks. While Apple has used benchmarks in the past to showcase performance, all of its performance claims at launch were application level tests. Those types of tests are more constrained and will show less scaling. That being said, I am surprised to see application level tests that were so close to the 2.2x average scaling we see here. Apple could have moved to faster NAND/storage controller here as well, which could help most if not all of these situations.

Geekbench Comparison
Floating Point Performance iPhone 4S iPhone 5 (unconfirmed) Scaling
Mandelbrot ST 223 MFLOPS 397 MFLOPS 1.77x
Mandelbrot MT 438 MFLOPS 766 MFLOPS 1.74x
Dot Product ST 177 MFLOPS 322 MFLOPS 1.81x
Dot Product MT 353 MFLOPS 627 MFLOPS 1.77x
LU Decomposition ST 171 MFLOPS 387 MFLOPS 2.25x
LU Decomposition MT 348 MFLOPS 767 MFLOPS 2.20x
Primality ST 142 MFLOPS 370 MFLOPS 2.59x
Primality MT 260 MFLOPS 676 MFLOPS 2.59x
Sharpen Image ST 1.35 Mpixels/s 4.85 Mpixels/s 3.59x
Sharpen Image MT 2.67 Mpixels/s 9.28 Mpixels/s 3.47x
Blur Image ST 0.53 Mpixels/s 1.96 Mpixels/s 3.68x
Blur Image MT 1.06 Mpixels/s 3.78 Mpixels/s 3.56x
MT Scaling 1.96x 1.92x  

The floating point benchmarks show "milder" scaling in the first few tests (sub-2x) but big scaling in the latter ones. My guess here is we're seeing some of the impacts of increased memory bandwidth at the end there. If you look at our iPhone 5 hands-on video you'll see Brian talking about how super fast the new flyover mode in iOS 6 Maps is on the 5 compared to the 4S. That's likely due in no small part to the improved memory interface.

Although Geekbench is cross platform, I wouldn't recommend using this data to do anything other than compare iOS devices. I've looked at using Geekbench to compare iOS to Android in the past and I've sometimes seen odd results.

I'm sure we'll learn a lot more about the A6 SoC over the coming days/weeks. 

POST A COMMENT

118 Comments

View All Comments

  • kyuu - Monday, September 17, 2012 - link

    The benchmarks only show scaling of the supposed iPhone 5 Geekbench results versus the iPhone 4S. It isn't compared against Android phones at all.

    Also, it's highly debatable whether the benchmark results between iOS and Android on Geekbench are even comparable. Anand specifically mentioned that when attempting to do so, things didn't add up, meaning it's likely Geekbench isn't OS agnostic and results, therefore, aren't directly comparable between different platforms.
    Reply
  • robinthakur - Monday, September 17, 2012 - link

    It's never seen as interesting when iOS wins, don't you know anything? The Samsung genius ad makes me laugh as an owner, especially all their pointless bullets they stick on the end like "Smart stay" which I could hardly say works as intended and the absurd claim that S Assist is anywhere like as good as Siri. Wow, you can pan between screens to move an app icon using your gyroscope and zoom in photos, how...useful. It's clearly not at all because you have to come up with workarounds to Apple's patents.
    They forgot to add:

    -a handful of apps that take advantage of the powerful graphics and quad core. Lots of major apps on iOS are missing. Others are the poor cousins of their iOS equivalents (e.g. Facebook, Shareprice)
    -No practical way to put music on the phone other than old fashioned drag and drop which will lock your phone for the duration of the copy. Either that or attempt to piggy back on iTunes using DoubleTwist or iSyncr which are hit and miss and didn't support ICS when I tested. If iTunes is so bad, why not code your own solution Samsung, or is that what Kies is meant to be?
    -The way the device begins to pause all the time when its internal memory approaches 3/4 full.
    -Fragmentation and delay for the next OS when it was released back in June. Jelly Bean might well arrive just in time for the Galaxy 4's release
    -A cheap plastic phone back that feels like it came in a christmas cracker. When the iphone 5 weighs less and is better constructed from quality materials it's time to fire your designers.
    -Jealous and miserable owners. Every Android person I asked to try and help get my S3 working as I wished seemed shocked that I didn't prefer it to the iPhone while obsessed with the superiority of their device, sort of like they accuse iPhone owners of being. Anyone who thinks otherwise is labelled an iSheep or a moron, which is beyond deluded. I think this comes from a deep-seated fear that their device will be outdated within a couple of months when the latest and greatest is refreshed by HTC and Samsung, which is probably justified.

    I'm not really bothered that you can flash it with a custom rom and use a small selection of widgets on the lock screen. I'm not even bothered that Android does "proper" multi tasking when it works so much worse in practice than Apple's "fake" multi tasking which doesn't muller the battery life. Considering this is Samsung's flagship device (for now) it feels unpolished and cobbled together in some places, like the support software. Most of the benefits of Android can be summed up for most of them by saying "It's not Apple".
    Reply
  • Sufo - Tuesday, September 18, 2012 - link

    I completely agree with the criticisms concerning device polish. I'm certainly with you on your points about handset quality, too. However, to criticise an Android device for using drag and drop to transfer files seems crazy to me.

    This feature is one of the biggest selling points for me. I can drag and drop any type of file (FLAC, Vorbis, anything) without having to launch any shitty 3rd party application. Having done that, I can then listen to my music with *true* gapless playback.

    Android has its fair share of criticisms and I think it's as simple as, until you're a legitimate power user (you're going to flash a custom ROM, you're going to be using linux features etc) then an iPhone is more likely better suited to you.
    Reply
  • agoyal - Monday, September 17, 2012 - link

    Krait was an improvement over the A9 but required a process shrink to 28nm. A6 is 1.35x krait despite the same process node (if not higher at 32 nm - Samsung).
    There is no reason to believe that apple could not have gone with higher clock. They have always chosen battery life and small form factore over performance. Suspect Ipad will see slightly higher clock. Once the process node shrinks to 20-22nm, this will likely get clocked higher.
    Reply
  • SanX - Monday, September 17, 2012 - link

    iphone will get down the drain starting from April quarter if Apple will give up larger formfactor models to the competition. Should make 4.5" and 5.0" phones and phablets asap, current gear is not usable for any serious work at all. Reply
  • serversurfer - Monday, September 17, 2012 - link

    So you're predicting that iPhone sales will start to drop off 6-9 months after the new models are released?

    That's a pretty bold claim there, champ.
    Reply
  • reddog007 - Monday, September 17, 2012 - link

    I'm a little iffy On that benchmark.
    1 what is geekbench? Barely been downloaded on Play Store. A few thousand times.
    2 a Samsung nexus at the same clocks is just 200 points away from the SGS3 Krait edition.
    3 the krait version of the SGS3 scored a lot less then the tegra 3. We all know, especially in single thread performance that the krait beats a tegra 3. Even nudges it out in multithreading.
    4 if the A6 is 1ghz and does own any CPU, apple skipped the A15 generation. Leaped frog it. I find kinda hard to believe as Intel can't even beat ARM still.
    5 If it is at 1GHz, and 32nm, dual core, with just a 4in screen, how the heck does it not improve battery life over the smaller older tech 4S? The SGS3 is just 20g heavier with a much larger screen and owns it in terms of advertised battery life.
    Reply
  • doobydoo - Monday, September 17, 2012 - link

    Advertised battery life being the key word.

    The SG3 is a brick - it's heavier, wider, taller and fatter.

    As a result they managed to fit a larger battery in, but Anandtechs own real world tests prove that even the iPhone 4S beats the SG3 in battery life benchmarks (winning in 2 of the 3 tests, and overall), despite having a far smaller capacity battery.

    Since Apple claims to have improved battery life, we can be relatively confident that the iPhone 5 battery outperforms the SG3 in the same way.

    You have to remember that the iPhone 5 is the thinnest smartphone in the world, and way lighter than most Android phones.
    Reply
  • kyuu - Monday, September 17, 2012 - link

    "You have to remember that the iPhone 5 is the thinnest smartphone in the world, and way lighter than most Android phones. "

    Sure... but at what point does thinner and lighter cease to be desirable? I've carried an iPhone 4 since its release and the thought of carrying a device that's thinner and lighter just isn't something I find appealing. I'd much rather have a bigger, better screen and more features. Plus, iPhones are so fragile that you have to slap a case on them if you want it to survive an accidental drop, which adds bulk anyway.
    Reply
  • web2dot0 - Monday, September 17, 2012 - link

    So you are saying that iPhone 5 is "too light".

    What's next, the GPU is "too fast"?

    I guess that is a hugely undesirable feature. hahaha.

    Why don't you wake up to the real world. People like lighter phones. Longer battery life.

    "Survive in the case of a drop"? It's called getting a protective case with your iPhone. That's what "AFTERMARKET" assesories are for! You wouldn't want Apple to kill that market too right? ;-D You need a lesson on business buddy.
    Reply

Log in

Don't have an account? Sign up now