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?
POST A COMMENT

162 Comments

View All Comments

  • techconc - Monday, September 17, 2012 - link

    > "They saw f#ck all in ARM. But do go ahead and rewrite history, I am sure St. Steve had a vision and saw potential where none other did."

    Unfortunately, actual history makes you look a bit foolish. Considering the Newton was ARM based, that sort of shoots a hole in your theory. I don't know what Steve's role in this was... probably nothing considering the Newton was Sculley's project. Either way, even back then, it was clear that if mobile was ever going to take off, it was going to be based on ARM rather than something like Intel.
    Reply
  • Pressurge - Saturday, September 15, 2012 - link

    this couldn't have waited for the review, huh? Gotta meet the Apple Article Quota! Reply
  • KineticHummus - Sunday, September 16, 2012 - link

    in its defense, this is a VERY informative article. lots of information. some of us find it interesting, if you don't then why even open it? Reply
  • Pressurge - Sunday, September 16, 2012 - link

    I find the information useful - I just wish Anand would wait until the review (like he used to do).

    You never see them rushing to state immediate speculation for newly-announced/released features about any other manufacturer's product. It always waits until the actual product review, where they break down the product feature-by-feature and discuss it within. But now though, every single thought that seems to come up regarding an Apple product, they throw up a front-page article as soon as possible. When's the last time you saw a front-page article discussing what might be in an HTC or Nokia smartphone within days of its announcement?

    I just find it sad because I've been following Anandtech since the early 2000s, and it used to be that there wasn't really a lean towards any particular company, but over the last few years, it's "Let's overload on Apple info and reduce our effort on everyone else." Intel's IDF probably only gets the treatment it does because Apple uses Intel hardware and thus Haswell/etc. affects future Apple products.

    I love the reviews they do on Apple products (I'm typing this on a 13" MBP), I just wish every single new thought/observation about something Apple is doing didn't demand a near-instantaneous article. Pretty soon they can just piece-meal a review by posting each separate section for the iPhone 5 separately, then just doing a "In summary:" article that ties it all together with links to each separate article. Or just break off and start up "AnandMac" or something. :)
    Reply
  • Kristian Vättö - Sunday, September 16, 2012 - link

    I think here the biggest need for this article was the confusion and misinformation about the SoC. We had been saying that it's Cortex-A15, but as you can see, it's not. Because we had been sharing misinformation, it was important to get the correct information out as soon as possible. Reviewing a big launch like this can easily take a few weeks and by that time it's a bit too late to apologize for wrong information.

    Another important point is exclusivity. As far as I know, we were the first to discover this, which means we don't want to wait and risk someone else finding it.

    With Apple there is also more mystery than with other companies. If this was Samsung or Nokia, they most likely would have told more details about the SoC if Anand/Brian had asked. What Apple tells the media is that it's A6 and twice as fast as A5. That is not much to go by, but many people still want to know the details. Can it really be twice as fast? And can I still get more battery life too? Answering those questions is a lot easier if details about the SoC are known.
    Reply
  • Pressurge - Sunday, September 16, 2012 - link

    Yeah, I understand the "mystery" part, but honestly it's just seems as if over the last year or two, Anandtech has been taking more of a lean towards Apple dominance in so far as the quantity of articles relative to everyone else. Maybe this is just in part that I remember the days when Anand's actual focus was on more than just Apple products and the occasional interesting SSD, relegating the reviews now to most other products to others who don't put in as much effort it seems (and I base that solely off of the length of the reviews, where Anand's Apple reviews will regularly go 15-20 pages while most products seem to be half of that). It's just somewhat depressing to see a priority focus from being generally manufacturer-agnostic in terms of reporting to now more favorability towards Apple (and I do enjoy Apple products, but I also like seeing no one company be treated favorably).

    The confusion regarding the SoC was mostly via Twitter and, if I recall, the live streaming. It just seems as if clarification on the SoC could have waited for the review given that for many of those who are purchasing an iPhone 5, the actual nature of the SoC wasn't going to influence their buying decision on it. I'm just afraid that instead of just waiting for the review to come up now, we'll just start seeing articles every few days now about the iPhone 5: "Here's the camera in the iPhone 5!", "Here's the specific information on the in-line cell for the iPhone 5's panel", "Here's the material the antenna's are made out of specifically!".

    I mean, I've yet to see any article previewing Windows 8 now that it's available on MSDN/DreamSpark/etc. and a lot of people are now installing it, but I guess Anand/the site goes where the money is (Apple). :(
    Reply
  • secretmanofagent - Sunday, September 16, 2012 - link

    You're not doing a very good job of looking, then.
    http://www.anandtech.com/SearchResults?CurrentPage...
    Reply
  • Pressurge - Sunday, September 16, 2012 - link

    And most of those are Pipeline announcements and not front-page articles. Each of the three iPhone 5 articles they've posted in the last two days also are also about equal in length to 3-4 of those articles in your searched COMBINED. What's that say about Anand's favoritism?

    Once again: take off the Apple-obsessing goggles, and look at it from a balanced standpoint: the site is significantly slanted towards Apple now relative to any other company. And I would just like to see them restore the balance a little more to actually saving many of these "Must. Report. Anything. Apple. NOW" articles to the actual product reviews so that I don't come to Anandtech and have 3/4ths of the front page just be Apple Apple Apple.
    Reply
  • darwiniandude - Saturday, September 15, 2012 - link

    Can't wait for the benchmarks and the crazy people to slice open the SOC and examine it under a microscope. Reply
  • 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.
    Reply

Log in

Don't have an account? Sign up now