The iPhone 5's A6 SoC: Not A15 or A9, a Custom Apple Core Instead
by Anand Lal Shimpi on September 15, 2012 2:15 PM EST- Posted in
- Smartphones
- Apple
- Mobile
- SoCs
- iPhone 5
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.
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 alreadyThese 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.