Next-Gen iPhone & iPhone Nano Speculation

Well, they did pretty much design them in-house.

Remember all the companies they have absorbed during the years who specializes in custom ARM implementations, P.A. semi and Intrinsity (they helped ATI with their FastCore expertise to speed up their Radeon line of graphic chips) comes to mind.

The Hummingbird based on Cortex-A8 was even made by Intrinsity, commissioned by Samsung, probably for Apple. At least that is the current rumors.

But they didn't design the CPU, the GPU, or the video encode/decode, at least not at the RTL level. There's a big difference between hardening an ARM design like Intrinisty does and making an ARM design like ARM, Qualcomm, or Marvell does. Saying that Intrinisty "made" the Cortex-A8 in Hummingbird is an unfair credit to ARM.

Allegedly Apple has a design license and a totally custom core is an inevitability, possibly even already existing in the A6. But that's not relevant to A4 and A5.

As far as Apple is concerned I'm sure they feel just as well if people were always under the (incorrect) guise that Apple does all the design work.

http://www.anandtech.com/show/6292/iphone-5-a6-not-a15-custom-core

Quote: 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.

Intriguing, but I'm taking Anand with some serious salt for the time being. This quote is full of whatever:

"As far as Apple is concerned I'm sure they feel just as well if people were always under the (incorrect) guise that Apple does all the design work."

Yeah, I'm sure the close to nothing VFPv4 adds over VFPv3 really bloats up the core </sarcasm>

Apple not trumpeting this is really aggravating :(
 
Last edited by a moderator:
http://www.anandtech.com/show/6292/iphone-5-a6-not-a15-custom-core

Quote: 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.

I think this makes the most sense. A15 has too much baggage with its server ambitions. Wider not deeper sounds better and is a lesson Intel learned with NetBurst.

I also think Apple is the best candidate to do full custom implementation because they know exactly what OS is going to be running on it and what it's demands are. I'm excited for the future direction of Apple.

BTW, anyone else see that Nvidia lost their mobile design chief? I wonder who got him.
 
Intriguing, but I'm taking Anand with some serious salt for the time being. This quote is full of whatever:

"As far as Apple is concerned I'm sure they feel just as well if people were always under the (incorrect) guise that Apple does all the design work."

Yeah, I'm sure the close to nothing VFPv4 adds over VFPv3 really bloats up the core </sarcasm>

Apple not trumpeting this is really aggravating :(


Why would they? Would it help the sales if they tell the customers that "we designed this CPU ourselves and not licensed it from somewhere else"? Besides they call it A6 and not A5xx, don't they. I am not saying that Anand is right, but it is clear that there is something unique about this CPU. It simply cannot be a higher clocked A5x.
 
Why go on about how their products are using the new A4, A5, or whatever Apple designed chip in the first place? You don't think that going on about how it's using their special new Ax chip is even more superficial than talking about how it uses a special new totally custom CPU? Does the former help sales more? Is mentioning something at a keynote a huge expense if it only helps sales slightly?

But forget that, I said it was AGGRAVATING, not surprising or "wrong." Maybe you don't care about the details of a new microarchitecture (or maybe you do, I don't know), but I do, and I like it when companies talk about it.
 
Why go on about how their products are using the new A4, A5, or whatever Apple designed chip in the first place? You don't think that going on about how it's using their special new Ax chip is even more superficial than talking about how it uses a special new totally custom CPU? Does the former help sales more? Is mentioning something at a keynote a huge expense if it only helps sales slightly?

But forget that, I said it was AGGRAVATING, not surprising or "wrong." Maybe you don't care about the details of a new microarchitecture (or maybe you do, I don't know), but I do, and I like it when companies talk about it.
I wonder it it would be any different if Apple announced the A6 at WWDC? Certainly developers could use a few words about differences in architecture. Admittedly the WWDC keynote is mainly for public consumption so Apple wouldn't take too mainly liberties with developer focused technical details there, but they could have added some tips in their developer sessions that deal with optimization.
 
http://www.anandtech.com/show/6292/iphone-5-a6-not-a15-custom-core

Quote: 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.
This really makes more sense. When the A5 came out, there was (private) grumbling from long time Apple employees about how Intrinsity and PA Semi got all the credit for something they didn't do. The A5 timeline was too aggressive for this anyway. Looks like the new core is finally there. Can't wait for the die shots to see CPU area.

Too bad we'll probably never get hard data about internal architecture (other than cache size etc.)
 
Why go on about how their products are using the new A4, A5, or whatever Apple designed chip in the first place? You don't think that going on about how it's using their special new Ax chip is even more superficial than talking about how it uses a special new totally custom CPU? Does the former help sales more? Is mentioning something at a keynote a huge expense if it only helps sales slightly?

But forget that, I said it was AGGRAVATING, not surprising or "wrong." Maybe you don't care about the details of a new microarchitecture (or maybe you do, I don't know), but I do, and I like it when companies talk about it.


They usually do not reveal clock speed, core count or even memory amount of their products. The only information they give out is the performance comparisons to the product they replace. I believe they deliberately conceal these information from the public, probably because they don't like people making purchasing decisions based on just these specifications.
 
So what do these VFPv4 extensions enable?

Are they like SIMD extensions? Or do they just help raise total CPU performance?

I think touting an architecture change just for its own sake goes against the brand Apple cultivated. They have to be able to say that the new architecture enables better video decoding or whatever.

Of course, they did tout this ISP -- image signal processor -- which improved camera performance, capturing up to 40% faster than the 4S.
 
IIRC VFPv4 adds half precision instructions plus fused mul/add. For half prec some (all?) already exist on Cortex-A9.

I found something on the web that seems to show the SDK also generates integer divide instructions.
 
Well I wasn't as nuts as I myself thought I am with my 'funky" ideas. Anand is correct in hinting that the timespan for a custom design must have been tight; I didn't myself expect it as early. Apple's engineers must have been chasing their heels for a long time now in order to get it done.

Now I'm of course dead curious what they've exactly done, but since they have their own OS they'd be extremely dumb if the processor wasn't tailored to fit the sw platform's actual needs like a glove.
 
If tbat's their chip, it's definitely an impressive achievement. They bought PA semi about 4 years ago, so they had some experienced designers and probably usable functional blocks. But even then implementing and validating an ARMv7 core is certainly not an easy task.
 
Maybe the real achievement will be a device which has leading performance, battery life and thinness compared to other A15 or Krait-based devices.

Some other manufacturers may stuff more power-hungry SOCs into thicker, heavier enclosures along with much bigger batteries to get decent battery life.
 
Maybe the real achievement will be a device which has leading performance, battery life and thinness compared to other A15 or Krait-based devices.

Some other manufacturers may stuff more power-hungry SOCs into thicker, heavier enclosures along with much bigger batteries to get decent battery life.
Only in fanboys wet dreams. Krait isn't something special on single thread workloads in comparison with A9, I am highly doubt that Apple will be able to beat ARM on ARM's own field anytime soon
 
I think the reason that Apple is not making much of a fuss about a "custom" CPU design on iphone 5 is that, at the end of the day, 2x CPU performance vs. iphone 4s (with 800MHz dual core A9 CPU) is really nothing much to brag about. The overall CPU performance of commercial devices with dual-core Krait or quad-core Tegra is arguably better in comparison to "2x" iphone 4s CPU. Now, regarding benefits of custom CPU design with respect to power consumption, there are far too many variables involved to know for sure what the impact would be. Power consumption is a function of both hardware (including architectural and fabrication process improvements) and software.
 
By the way, with respect to the relatively light weight of the iphone 5, that is partly due to the new in-cell screen technology, and also partly due to the extensive use of aluminum on the chassis. I'm sure we will see more of the same from other companies moving forward. Just as the auto industry is focusing on reducing weight and improving fuel consumption, the mobile industry is focusing on reducing weight and improving power consumption.
 
The weight reduction is pretty simple really....

In terms of volumetric area both Stainless Steel and Glass is heavier than Aluminum. Since the chassis is aluminum now and there's no glass back and the front glass is thinner it's logical that it was made lighter even if the battery slightly increased in size.

The next step will probably be carbon fiber composite unibody.
 
Back
Top