The A6 GPU: PowerVR SGX 543MP3?

Apple made a similar "up to 2x" claim for GPU performance. It didn't share any benchmarks, but there are four options here:

1) PowerVR SGX 543MP2 (same as in A5) at 2x the clock speed
 
2) PowerVR SGX 543MP4 at the same clock as the MP2 in the A5
 
3) Marginally higher clocked PowerVR SGX 543MP3
 
4) Next-gen PowerVR Rogue GPU
 
It's too early for #4. The first option makes sense but you run into the same issues as on the CPU side with higher voltages used to ramp clocks up (also possible that you drop voltages in the move to the new process technology). 
 
The second option trades voltage for die area, which based on the A5X Apple is clearly willing to spend where necessary.
 
The third is sort of the best of both worlds. You don't take a huge die area penalty and at the same time don't run at a significantly higher frequency, and you can get to that same 2x value.

The third option is the most elegant and likely what Apple chose here. Remember that overall die size is dictated by the amount of IO you have around the chip. The A5X had four 32-bit LPDDR2 memory controllers, which gave Apple a huge die area to work with. The move to a smaller manufacturing process cuts down the total die area, which means Apple would either have to add a ton of compute (to fill empty space, no sense in shipping a big chip with a bunch of unused area) or reduce the memory interface to compensate. Pair that knowledge with the fact that Apple doesn't have the same memory bandwidth requirements on the iPhone 5 (0.7MP vs. 3.1MP display) and it makes sense that Apple would go for a narrower memory interface with the A6 compared to the A5X.
 
How much narrower? Phil Schiller mentioned the A6 was 22% smaller than the A5. We can assume this is compared to the 45nm A5 and not the 32nm A5r2, which would mean that we don't have any more memory channels compared to the A5. In other words, it's quite likely the A6 has a 2x32-bit LPDDR2 memory interface once again.
 

Final Words

 
There's not much more to add for now. We'll have a device in a week and I suspect the first reviews will be out a day or two before then. Then the real work begins on finding out exactly what Apple has done inside the A6. If anyone has been dying to put together some good low level iOS benchmarks, now is the time to start.
 
This is a huge deal for Apple. It puts the company in another league when it comes to vertical integration. The risks are higher (ARM's own designs are tested and proven across tons of different devices/platforms) but the payoff is potentially much greater. As Qualcomm discovered, it's far easier to differentiate (and dominate?) if you're shipping IP that's truly unique from what everyone else has.
 
Now we get to see just how good Apple's CPU team really is.
The A6's CPU
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