When Apple announced the iPhone 5, Phil Schiller officially announced what had leaked several days earlier: the phone is powered by Apple's new A6 SoC.

As always, Apple didn't announce clock speeds, CPU microarchitecture, memory bandwidth or GPU details. It did however give us an indication of expected CPU performance:
 
 
Prior to the announcement we speculated the iPhone 5's SoC would simply be a higher clocked version of the 32nm A5r2 used in the iPad 2,4. After all, Apple seems to like saving major architecture shifts for the iPad. 
 
However, just prior to the announcement I received some information pointing to a move away from the ARM Cortex A9 used in the A5. Given Apple's reliance on fully licensed ARM cores in the past, the expected performance gains and unpublishable information that started all of this I concluded Apple's A6 SoC likely featured two ARM Cortex A15 cores. 
 
It turns out I was wrong. But pleasantly surprised.
 
The A6 is the first Apple SoC to use its own ARMv7 based processor design. The CPU core(s) aren't based on a vanilla A9 or A15 design from ARM IP, but instead are something of Apple's own creation.
 

Hints in Xcode 4.5

 
The iPhone 5 will ship with and only run iOS 6.0. To coincide with the launch of iOS 6.0, Apple has seeded developers with a newer version of its development tools. Xcode 4.5 makes two major changes: it drops support for the ARMv6 ISA (used by the ARM11 core in the iPhone 2G and iPhone 3G), keeps support for ARMv7 (used by modern ARM cores) and it adds support for a new architecture target designed to support the new A6 SoC: armv7s.
 

 
What's the main difference between the armv7 and armv7s architecture targets for the LLVM C compiler? The presence of VFPv4 support. The armv7s target supports it, the v7 target doesn't. Why does this matter?
 
Only the Cortex A5, A7 and A15 support the VFPv4 extensions to the ARMv7-A ISA. The Cortex A8 and A9 top out at VFPv3. If you want to get really specific, the Cortex A5 and A7 implement a 16 register VFPv4 FPU, while the A15 features a 32 register implementation. The point is, if your architecture supports VFPv4 then it isn't a Cortex A8 or A9.
 
It's pretty easy to dismiss the A5 and A7 as neither of those architectures is significantly faster than the Cortex A9 used in Apple's A5. The obvious conclusion then is Apple implemented a pair of A15s in its A6 SoC.
 
For unpublishable reasons, I knew the A6 SoC wasn't based on ARM's Cortex A9, but I immediately assumed that the only other option was the Cortex A15. I foolishly cast aside the other major possibility: an Apple developed ARMv7 processor core.
 

Balancing Battery Life and Performance

 
There are two types of ARM licensees: those who license a specific processor core (e.g. Cortex A8, A9, A15), and those who license an ARM instruction set architecture for custom implementation (e.g. ARMv7 ISA). For a long time it's been known that Apple has both types of licenses. Qualcomm is in a similar situation; it licenses individual ARM cores for use in some SoCs (e.g. the MSM8x25/Snapdragon S4 Play uses ARM Cortex A5s) as well as licenses the ARM instruction set for use by its own processors (e.g. Scorpion/Krait implement in the ARMv7 ISA).
 
For a while now I'd heard that Apple was working on its own ARM based CPU core, but last I heard Apple was having issues making it work. I assumed that it was too early for Apple's own design to be ready. It turns out that it's not. Based on a lot of digging over the past couple of days, and conversations with the right people, I've confirmed that Apple's A6 SoC is based on Apple's own ARM based CPU core and not the Cortex A15.
 
Implementing VFPv4 tells us that this isn't simply another Cortex A9 design targeted at higher clocks. If I had to guess, I would assume Apple did something similar to Qualcomm this generation: go wider without going substantially deeper. Remember Qualcomm moved from a dual-issue mostly in-order architecture to a three-wide out-of-order machine with Krait. ARM went from two-wide OoO to three-wide OoO but in the process also heavily pursued clock speed by dramatically increasing the depth of the machine.
 
The deeper machine plus much wider front end and execution engines drives both power and performance up. Rumor has it that the original design goal for ARM's Cortex A15 was servers, and it's only through big.LITTLE (or other clever techniques) that the A15 would be suitable for smartphones. Given Apple's intense focus on power consumption, skipping the A15 would make sense but performance still had to improve.

Why not just run the Cortex A9 cores from Apple's A5 at higher frequencies? It's tempting, after all that's what many others have done in the space, but sub-optimal from a design perspective. As we learned during the Pentium 4 days, simply relying on frequency scaling to deliver generational performance improvements results in reduced power efficiency over the long run. 
 
To push frequency you have to push voltage, which has an exponential impact on power consumption. Running your cores as close as possible to their minimum voltage is ideal for battery life. The right approach to scaling CPU performance is a combination of increasing architectural efficiency (instructions executed per clock goes up), multithreading and conservative frequency scaling. Remember that in 2005 Intel hit 3.73GHz with the Pentium Extreme Edition. Seven years later Intel's fastest client CPU only runs at 3.5GHz (3.9GHz with turbo) but has four times the cores and up to 3x the single threaded performance. Architecture, not just frequency, must improve over time.
 
At its keynote, Apple promised longer battery life and 2x better CPU performance. It's clear that the A6 moved to 32nm but it's impossible to extract 2x better performance from the same CPU architecture while improving battery life over only a single process node shrink.
 
Despite all of this, had it not been for some external confirmation, I would've probably settled on a pair of higher clocked A9s as the likely option for the A6. In fact, higher clocked A9s was what we originally claimed would be in the iPhone 5 in our NFC post.
 
I should probably give Apple's CPU team more credit in the future.
 
The bad news is I have no details on the design of Apple's custom core. Despite Apple's willingness to spend on die area, I believe an A15/Krait class CPU core is a likely target. Slightly wider front end, more execution resources, more flexible OoO execution engine, deeper buffers, bigger windows, etc... Support for VFPv4 guarantees a bigger core size than the Cortex A9, it only makes sense that Apple would push the envelope everywhere else as well. I'm particularly interested in frequency targets and whether there's any clever dynamic clock work happening. Someone needs to run Geekbench on an iPhone 5 pronto.
 
I also have no indication how many cores there are. I am assuming two but Apple was careful not to report core count (as it has in the past). We'll get more details as we get our hands on devices in a week. I'm really interested to see what happens once Chipworks and UBM go to town on the A6.
The A6 GPU: PowerVR SGX 543MP3?
Comments Locked

163 Comments

View All Comments

  • derektrotter - Sunday, September 16, 2012 - link

    Cortex-A5 has 32 double (64-bit) registers. See page 2-9 of the ARM Technical Reference Manual for the Cortex A5 NEON variant. Cortex-A7 also supports 32 doubles.

    The deciding thing is really whether your core includes NEON (Advanced SIMD) support. A5, A7, A8, A9 and A15 all have NEON variants.
  • derektrotter - Sunday, September 16, 2012 - link

    Or be more explicit. If your core supports NEON, then it supports 32 doubles. So there are versions of A5, A7, A8, A9 and A15 that support 32 doubles.
  • nfineon - Sunday, September 16, 2012 - link

    The possibility for Apple using A15 cores in the new iPhone 5 was actually one of, if not the one and only, hope I had that Apple didn't completely compromise in every aspect of the new iPhone. That would have been an impressive step forward and another first within the industry which is what apple was known for in the jobsian era. But I was always a bit pessimistic given the lackluster ness of almost everything around the new iPhone, so I take this news with little shock and commend you and your team for all the efforts in breaking this information to us before anyone!

    I am even more doubtful now, that we will be seeing anywhere near 2x performance as those figures were for cherry picked apps that apple has had several months to optimize for the new custom core. I will reserve judgement until your next major break in the A6 silicon story...
  • Rectified - Sunday, September 16, 2012 - link

    The article states that voltage has an exponential effect on power consumption. This is false; it is quadratic.
  • lmcd - Sunday, September 16, 2012 - link

    It seems like there was no reason for Apple to have hired all of those big names just to integrate a SoC. This has probably been in the works since before the release of the A4, at minimum. And those engineers left like a few months ago also; this was probably what they were working on and getting integrated, and left on completion.
  • nickager - Sunday, September 16, 2012 - link

    Fascinating.

    Does this indicate a vote against ARM A15 for use in phones vs tablets? Will ARM A15 only fit well in the power-envelope for phones when paired with an ARM A7 in a big.LITTLE configuration?
    Will Apple be able to develop/interested in developing an A6 into a big.LITTLE configuration?
    What does this mean for the next iPad? I'd assumed that it would have an ARM A15 based SOC, if not, how will an iPad based on a development of the A6 perform against ARM A15 based competitors?

    How do the number of engineers at Apple working on CPU architecture compare with the number of engineers at ARM working on advanced architectures? For comparison Jobs boasted that Apple had 1,000 engineers working on the "chip project". From wikipedia ARM has 2000 employees.
  • meloz - Sunday, September 16, 2012 - link

    I am disappointed with the increasing pro-Apple bias Anand is infusing in his once great website.

    Each day the article on this website read more and more as if they have been prepared by Apple marketing department and handed out to Anandtech for wider circulation. The podcasts are even worse, anything and everything there in is Apple-this & Apple-that.

    Today -aside from benchmarks and occasional niche articles by likes of Johan and Cutress- there is little to seperate Anandtech from trash like Engadget. How the mighty have fallen.

    First, Anand made the ridiculous "mistake" and hyped as the iphone 5 as having A15. Even the most illeterate people on forums could not come up with that propoganda. Apparently there was not much positive about the iphone, so Anand must find anything we can praise. And if he cannot find anything, he must invent a story?

    And now he "corrects" his mistake, by praising the invented "A7".

    By all means, keep loving Apple. I am sure it is financially beneficial for you. But do not throw away the last vestiges of integrity in the process.

    When your bias is so evident in articles that cover all-things-Apple, they also raise doubts in the minds of readers about the integrity of increasingly fewer articles you publish which do not have the word 'Apple' mentioned once.

    If you are going to sell out so blatantly, do the decent thing and rename yourself Apple-tech or something. Because you are not about covering technology anymore, but praising Apple.
  • iwod - Sunday, September 16, 2012 - link

    Do you read tech news? Do u understand any tech related things? By all knowledge, knowing that Apple did not increase the Frequency, and it has twice the performance, what would you have guess the CPU was using?

    And you could also say that Anand was praising Intel as well. And i am a AMD users here. And there is nothing wrong to admit, AMD has slower performing CPU then Intel. Intel has better CPU then AMD. And that is a Fact.

    And Engadget speculate, but with out technology background and reason. Anand prove his point, admit his mistake and gave you the reason why he thought it was, and why it happened to be wrong.

    And Apple cares about battery life of their SoC rather then performance. Anand simply just state that. If there anything wrong with that. So people cares about using renewable energy paying for a Electric Car like Telsa should be put off because others think they should have got a Ferrari instead for the same price?

    And to quote you, by all means, keep hating apple. We tech lovers would continue to enjoy the technological advance and discovery with anand.
  • dugbug - Sunday, September 16, 2012 - link

    Oh god go away already

    These articles are fantastic. There is no apple bias. Apple are big news in the world of mobile and their secrecy makes it intriguing.
  • jamyryals - Sunday, September 16, 2012 - link

    I agree with this. I love these articles. Keep it up Anand and Brian.

Log in

Don't have an account? Sign up now