or Connect
AppleInsider › Forums › Mobile › iPhone › Analysis affirms Apple's A7 processor closer to a desktop CPU than regular mobile chip
New Posts  All Forums:Forum Nav:

Analysis affirms Apple's A7 processor closer to a desktop CPU than regular mobile chip

post #1 of 198
Thread Starter 
An independent analysis of the microarchitecture behind Apple's latest A7 processor has shown that the company was not overstating when it called the design "desktop class," with the new silicon matching up well against Intel's recent desktop components.

A7
Apple's latest A7 SoC. | Source: Chipworks


The A7 sports the same number of execution ports as Intel's Ivy Bridge chips and a reorder buffer equal to that found in the Haswell architecture, according to Anand Shimpi of AnandTech. Shimpi arrived at his conclusions by studying the A7 itself as well as Apple code commitments to the LLVM compiler project.

"Apple didn't build a Krait/Silvermont competitor, it built something much closer to Intel's big cores," Shimpi wrote, referring to Intel and Qualcomm's ultra-mobile CPU designs. "At the launch of the iPhone 5s, Apple referred to the A7 as being "desktop class" - it turns out that wasn't an exaggeration."

The number of execution ports is important because it defines how many instructions the processor can handle concurrently. Apple's A7 can process six instructions per clock cycle, the same as Intel's Ivy Bridge chips found in previous-generation Apple laptops and twice the capacity of the A6.

Similarly, a larger reorder buffer gives the processor a bigger pool of instructions to choose from when deciding how to most efficiently complete its tasks. The A7's 192-instruction buffer matches Intel's Haswell designs and is more than four times the A6's 45-instruction buffer.

a7-performance-20131009.jpg
Apple's SVP of worldwide marketing Phil Schiller introduces the A7 system-on-chip.


Shimpi believes that the A7 was designed to be forward-looking, with room to increase performance as Apple moves to smaller fabrication processes. He also raised the possibility that Apple may choose to release yet another new architecture design with the A8, rather than simply refining the A7's "Cyclone" core.

As it stands, Shimpi added, most of the A7's processing power remains untapped due to battery life concerns. Current-generation iOS devices will run out of RAM, he predicts, long before reaching the A7's performance ceiling.

When it debuted in the iPhone 5s last fall, Apple's custom A7 processor was said to have caught the chipmaking industry off guard, sending competitors into an alleged "panic." One unnamed person at Qualcomm reportedly said that the A7 left the company "slack-jawed, and stunned, and unprepared."
post #2 of 198
Could Apple stick 2X A8s in a slim MacBook Air?
Citing unnamed sources with limited but direct knowledge of the rumoured device - Comedy Insider (Feb 2014)
Reply
Citing unnamed sources with limited but direct knowledge of the rumoured device - Comedy Insider (Feb 2014)
Reply
post #3 of 198
For use in the new Macbook Air, or not?
post #4 of 198
Wow the A7 is even better than I thought! Apple definitely makes all the right choices when it comes to chip design.
post #5 of 198
So at this point would iOS be the inhibiting factor in unleashing the A7 power?
post #6 of 198
"Can't innovate my ass" Phil Schiller
post #7 of 198
MacBook Air? No.

Battery life and weight on the Air is already terrific, and performance has been improving. Why harm performance by going to ARM, around the same timeframe as MB Airs NEED more performance due to going retina (whenever that happens)?

And your Intel software would no longer run. And workarounds would involve major work for developers, and fat binaries what waste expensive SSD space.

So it would mean MASSIVE fragmentation for developers, and massive headache for users. The kind of thing you only do if the benefit is HUGE, or if you HAVE to (like the PPC->Intel transition). And you do it for ALL the Macs in the lineup. ARM-based MacBook Pros, iMacs and Mac Pros? Makes no sense any time soon.

Apple already has an ARM-based portable that IS a good idea. They don't need to add one that isn't.
post #8 of 198
Quote:
Originally Posted by acatomic View Post

For use in the new Macbook Air, or not?

Huh? Why would you think Apple will use last years' tech in the MBA?
Send from my iPhone. Excuse brevity and auto-corrupt.
Reply
Send from my iPhone. Excuse brevity and auto-corrupt.
Reply
post #9 of 198
Originally Posted by nagromme View Post
[post]

 

Exactly. PowerPC–>Intel made a ton of sense. Intel–>ARM doesn’t, and won’t, for a very long time without drastic changes.

post #10 of 198
Quote:
Originally Posted by nagromme View Post

MacBook Air? No.

Battery life and weight on the Air is already terrific, and performance has been improving. Why harm performance by going to ARM, around the same timeframe as MB Airs NEED more performance due to going retina (whenever that happens)?

And your Intel software would no longer run. And workarounds would involve major work for developers, and fat binaries what waste expensive SSD space.

So it would mean MASSIVE fragmentation for developers, and massive headache for users. The kind of thing you only do if the benefit is HUGE, or if you HAVE to (like the PPC->Intel transition). And you do it for ALL the Macs in the lineup. ARM-based MacBook Pros, iMacs and Mac Pros? Makes no sense any time soon.

Apple already has an ARM-based portable that IS a good idea. They don't need to add one that isn't.

 

I really have to agree with you. Not much to add to that except some people may say it can compete with a chromebook (which is kinda worthless). But Apple could never price low enough to hurt the small chromebook market. There really doesn't seem much for Apple to gain other than making a more PC-like iPad. Which would be cool but I can imagine the price would be in the ~700 or ~800 range and by that point, might as well go up a bit more and grab the Macbook Air (which is not a laptop for me). I prefer my nice 15.4'' retina macbook pro.

 

All in all, I agree with you.

post #11 of 198
Quote:
Originally Posted by richlo View Post

So at this point would iOS be the inhibiting factor in unleashing the A7 power?

Well that made me sit up.
Possibilities galore. 1cool.gif
post #12 of 198
What if Apple releases Arm-based ultra portables (the next generation) that have a transparent emulation mode like the IBM PPC > Intel solution that was basically transparent to the users? One app packaged in both formats compressed, but only installs the proper chip version from the App Store as required. Is this an impossibility...no. They proved it before...
post #13 of 198
Quote:
Originally Posted by richlo View Post

So at this point would iOS be the inhibiting factor in unleashing the A7 power?

According to the article the A7 is hampered by the amount of RAM available to it... which, in turn is limited by the drain on the battery more RAM would add. That's my take-away..
"That (the) world is moving so quickly that iOS is already amongst the older mobile operating systems in active development today." — The Verge
Reply
"That (the) world is moving so quickly that iOS is already amongst the older mobile operating systems in active development today." — The Verge
Reply
post #14 of 198
Quote:
Originally Posted by nagromme View Post
So it would mean MASSIVE fragmentation for developers, and massive headache for users.

I agree. Fragmentation is bad. Apple will not just convert MBA to A7 chip and keep Intel on MBP, I believe. Can the "Ax" chip become powerful enough for MBP in the next iteration? It would be interesting if it can. How about MacPro? Somehow, it feels hopeless for Apple to stop using Intel chips.

post #15 of 198
Quote:
Originally Posted by Ireland View Post

Could Apple stick 2X A8s in a slim MacBook Air?

 

The increased thermal headroom of a MacBook Air compared to an iPhone or iPad would allow a design to run at faster speeds for more of the time (most of the processing time in an iPhone or iPad is actually spent in "race to idle" mode - long battery lives are only achieved by being idle most of the time).  I don't think they would use two A8s, they would probably fab an A8X or clock the A8 faster due to the increased thermal headroom.

 

But I don't think Apple is in the right place yet to release a ARM device running Mac OS X - all the software is compiled for x86-64 currently, not ARM. There would have to be a period of time where ARM was enabled for all software builds in XCode for Mac OS X.  I believe Apple uses the threat of ARMing themselves to make Intel provide its CPUs at a reasonable price.

post #16 of 198
Quote:
Originally Posted by Macky the Macky View Post

According to the article the A7 is hampered by the amount of RAM available to it... which, in turn is limited by the drain on the battery more RAM would add. That's my take-away..

Yes, I agree. And the other limiting factor is that A7 is currently underclocked (with respect to its capability), to further reduce battery drain.
post #17 of 198
If Apple would to dump the A7 (or A8 if it's coming later this year) into a new device that had the battery capacity of the MBA, and then added more RAM to the mix, and maybe upped the GPU capacity and went retina (or 4K) with the display, Apple could come out with a new product with touch screen or touch pad, or mouse/keyboard control that could go places and do things no current device or computer has gone before.

I'm not bright enough to say what this might look like or do, but if matched with the right new software, it could define a new market as fresh as the iPad was...
"That (the) world is moving so quickly that iOS is already amongst the older mobile operating systems in active development today." — The Verge
Reply
"That (the) world is moving so quickly that iOS is already amongst the older mobile operating systems in active development today." — The Verge
Reply
post #18 of 198
Quote:
Originally Posted by PhilBoogie View Post

Huh? Why would you think Apple will use last years' tech in the MBA?

I wasn't thinking about last year tech but this new A8 that they mentioned.

Anyways we'll see... 1smile.gif
post #19 of 198
Quote:
Originally Posted by acatomic View Post

For use in the new Macbook Air, or not?

No.

post #20 of 198

A crazy idea: A docking station with screen and keyboard, portable or desktop.  The iPhone is the computer.  For many people it's all the computing power they would ever need.  Crazy, but well within the realm of possibility, and already predicted by others.  It could even be an attractive, inexpensive option for the enterprise.  Lots of docks, and everyone carries their own computer in their pocket.  

post #21 of 198
Anand is a smart guy and I appreciate his detective work (and that of his sources), but I found this paragraph a bit odd:

"The challenge is that at full tilt a pair of Cyclone cores can consume quite a bit of power. So for now, Cyclone's performance is really used to exploit race to sleep and get the device into a low power state as quickly as possible. The other problem I see is that although Cyclone is incredibly forward looking, it launched in devices with only 1GB of RAM. It's very likely that you'll run into memory limits before you hit CPU performance limits if you plan on keeping your device for a long time."

The overall impression from this text is that Cyclone, and the iPhone/iPad, are somehow unbalanced -- that there is a lot of performance potential that isn't being fully realized, and might never be fully realized in existing devices. Yet also contained in this text is the explanation for why Cyclone makes perfect sense: "Cyclone's performance is really used to exploit race to sleep and get the device into a low power state as quickly as possible." Anand makes it sound like this is a second or third order concern, but in the context of a mobile device, it's actually one of the most important concerns. Apple is trying to design a chip that gets its work done quickly, using as little power as possible. Given the physics confronting CPU designers, that means that you'd rather have more transistors running at a lower clock speed than the reverse. And given the nature of the software run on mobile devices, you'd rather have greater instruction level parallelism than thread level parallelism.

So the A7 is the perfect mobile SOC -- low clockspeed, high ILP, low TLP. it is perfectly balanced for its job. The fact that the cyclone core could also be the basis for a very credible desktop CPU is what's secondary here.
post #22 of 198
1) Where are the people that laughed at Apple for buying PA Semi?

2) I love how I hear everyday from people that Apple isn't innovating because they define it as releasing an entirely new product category. Now I don't expect the average person to understand how this chip is innovative and well ahead of the market but I do expect them to at least understand that unseen innovations are still innovations.

3) I don't think 2x A8's is the right way to go. Better to use more cores, or simply up the clock as Anand states these handheld devices are clocked too low to take full advantage of this "desktop class" chip.

4) I do think a small, 12", low-power notebook could happen. Between the Apple's ARM chips now being 64-bit, it's performance-per-Watt, the high cost of Intel's CULV CPUs in the MBA, the universality of web-based apps, and the Mac App Store I think it's not out of the realm of possibility that Apple could update Xcode to allow Mac apps to be compiled for x86_64 and AArch_64 for MAS. I wouldn't expect Apple to cut out the old-school download and install method but allow developers who have a viable product that will work on ARM to adjust and recompile like with the transitions from PPC. I also wouldn't expect a Rosetta-like option since the performance envelope will be going the other direction in both the chip and by not starting near the top of the performance line. This move could get Apple to make a MBA-like device that comes in several hundred less expensive than today with more than double the battery life for the current size/weight, that fits the needs of the user who isn't playing Resident Evil 5 on a 12" machine or using the Adobe Suit 6. If Chromebooks can gain some traction without MS Office and Adobe apps then so can an ARM-based Mac-like notebook.

5) QFT: "Looking at [Apple's A7 SoC] makes one thing very clear: the rest of the players in the ultra mobile CPU space didn't aim high enough. I wonder what happens next round." ~Anand Shimpi

This bot has been removed from circulation due to a malfunctioning morality chip.

Reply

This bot has been removed from circulation due to a malfunctioning morality chip.

Reply
post #23 of 198
Would be cool if a future iteration of the iPhone could be wirelessly connected to a keyboard, monitor, external storage and mouse to play the part of an instant Mac mini.

Proud AAPL stock owner.

 

GOA

Reply

Proud AAPL stock owner.

 

GOA

Reply
post #24 of 198

Fragmentation is a serious issue to be sure.

 

But . . .

 

An A8 chip would cost about $12, allowing Apple to sell an A8 laptop for $699 (and at a higher profit margin). It would also have about 120 hours of battery life. Oh, and if they put 8 cores into the thing, it would run circles around Haswell.

 

And since the ARM is basically a PPC, the SDK's are all there, and much of the code is already written. It would just need an updating.

post #25 of 198
The question is how many hypothetical A8X could you stick in a Mac (MBA, MBP, iMac, MacPro) for the same thermal specs as the equivalent Intel chips.
post #26 of 198
This is what I have been saying and some people said that it was not possible. I believe Apples next move is put their own processors in to their laptop products. They do not need Intel at this point. I would not be surprise if they did not have a OSX port for their processors already.
post #27 of 198
Quote:
Originally Posted by Ireland View Post

Could Apple stick 2X A8s in a slim MacBook Air?

What I'd give to see the fully working ARM port of OS-X that for sure Apple has in a lab somewhere deep in the bowels of One Infinity Loop.

post #28 of 198
Quote:
Originally Posted by Ireland View Post

Could Apple stick 2X A8s in a slim MacBook Air?

One would be good enough. The biggest hurdle to SoC performance these days is bandwidth to RAM. If Apple solves that an A8 would be fine.
post #29 of 198
Get me an iPad with keyboard that snaps apps to the side like the surface and I'll replace my Notebook with an iMac and take the iPad on the go! Especially considering the next iPad will have an A8 thats likely going to be comparable with a low/middle-class notebook. I'd love a lighter mobile solution but as long as I need a computer on the go I won't have two computers and therefore have to use the Retina MacBook Pro to be able to do all my work. But on the go the power of an iPad would be more than enough!
post #30 of 198

But they do. It debuted on June 24, 2003 on the Mac Pro G5. ARM and the PPC are both RISC chips made from the same cloth.

Ever wonder how Apple was able to release a fully 64-bit OS with the A7? Wonder no more. The 64-bit version of iOS is 11 years old.

post #31 of 198
Quote:
Originally Posted by richlo View Post

So at this point would iOS be the inhibiting factor in unleashing the A7 power?

Not at all, for the most part iOS is Mac OS with a slightly different GUI and a more restricted execution environment. That being said I'd love to see a Mac OS device that uses A7/A8. Even better if the machine supports easily booting other operating systems.
post #32 of 198
Quote:
Originally Posted by jj.yuan View Post

I agree. Fragmentation is bad. Apple will not just convert MBA to A7 chip and keep Intel on MBP, I believe.

Apple seems to like lateral moves. If release an A-chip-based notebook it might not even be called a Mac or use Mac OS X, at least not at first. This could allow them to build a parallel project and let developers get apps converted, work out any issues, and further advance their A-chips to a point that it could eventually allow them to make the switch much further down the road.

Quote:
Originally Posted by chadbag View Post

The question is how many hypothetical A8X could you stick in a Mac (MBA, MBP, iMac, MacPro) for the same thermal specs as the equivalent Intel chips.

I don't think Apple would work it that way. I'd think they make it at least equivalent performance (if they were going to replace an existing product) but then use all the gains to balance a reduction in materials cost, weight and size, as well make the battery life much, much longer (if we're talking about a notebook).

This bot has been removed from circulation due to a malfunctioning morality chip.

Reply

This bot has been removed from circulation due to a malfunctioning morality chip.

Reply
post #33 of 198
Quote:
Originally Posted by nagromme View Post

MacBook Air? No.
How about maybe! It really depends upon what Apple delivers.
Quote:
Battery life and weight on the Air is already terrific, and performance has been improving. Why harm performance by going to ARM, around the same timeframe as MB Airs NEED more performance due to going retina (whenever that happens)?
Did you not read the article, the performance potential is there. You assume that in a laptop that at they would use the same exact hardware. A faster RAM interface would have a dramatic impact.
Quote:
And your Intel software would no longer run. And workarounds would involve major work for developers, and fat binaries what waste expensive SSD space.
Intel compatibility is only of concern to a few. As to fat binaries that is looking to the past.
Quote:
So it would mean MASSIVE fragmentation for developers, and massive headache for users.
Baloney.
Quote:
The kind of thing you only do if the benefit is HUGE, or if you HAVE to (like the PPC->Intel transition). And you do it for ALL the Macs in the lineup. ARM-based MacBook Pros, iMacs and Mac Pros? Makes no sense any time soon.
The benefits would be huge, laptops that are 2-300 dollars cheaper being one benefit. Piloting your own ship being another.
Quote:
Apple already has an ARM-based portable that IS a good idea. They don't need to add one that isn't.

That is a matter of opinion.
post #34 of 198
Quote:
Originally Posted by nagromme View Post


And your Intel software would no longer run. And workarounds would involve major work for developers, and fat binaries what waste expensive SSD space.

Two points:
  1. According to comments in the original Anandtech article there are ARM emulators for x86 that yield 40%-60% degradation over native x86. These would be adequate for legacy apps where no source code exists. ARM and/or Emulator performance improvement could make x86 on ARM more practical for current apps.
  2. As to fat-binaries, Apple has done a lot of work in Xcode as to application packaging -- for both OSX and iOS. I suspect that at some point, Apple will deliver Fat Packages to the App Stores which will be able to skip unneeded code for the specific device during an intelligent download/install/update/sync process.
"Swift generally gets you to the right way much quicker." - auxio -

"The perfect [birth]day -- A little playtime, a good poop, and a long nap." - Tomato Greeting Cards -
Reply
"Swift generally gets you to the right way much quicker." - auxio -

"The perfect [birth]day -- A little playtime, a good poop, and a long nap." - Tomato Greeting Cards -
Reply
post #35 of 198
The logical procession is that an A8 would make an Apple TV 4 quite powerful as you don't need to worry about battery power.
post #36 of 198
Quote:
Originally Posted by Hattig View Post

Quote:
Originally Posted by Ireland View Post

Could Apple stick 2X A8s in a slim MacBook Air?

The increased thermal headroom of a MacBook Air compared to an iPhone or iPad would allow a design to run at faster speeds for more of the time (most of the processing time in an iPhone or iPad is actually spent in "race to idle" mode - long battery lives are only achieved by being idle most of the time).  I don't think they would use two A8s, they would probably fab an A8X or clock the A8 faster due to the increased thermal headroom.

But I don't think Apple is in the right place yet to release a ARM device running Mac OS X - all the software is compiled for x86-64 currently, not ARM. There would have to be a period of time where ARM was enabled for all software builds in XCode for Mac OS X.  I believe Apple uses the threat of ARMing themselves to make Intel provide its CPUs at a reasonable price.

Would there be technical and/or bargaining advantages by include an A8 in addition to an x86 chip on a Mac device?
"Swift generally gets you to the right way much quicker." - auxio -

"The perfect [birth]day -- A little playtime, a good poop, and a long nap." - Tomato Greeting Cards -
Reply
"Swift generally gets you to the right way much quicker." - auxio -

"The perfect [birth]day -- A little playtime, a good poop, and a long nap." - Tomato Greeting Cards -
Reply
post #37 of 198
Quote:
Originally Posted by DTiconderoga View Post
 

An A8 chip would cost about $12, allowing Apple to sell an A8 laptop for $699 (and at a higher profit margin). It would also have about 120 hours of battery life. Oh, and if they put 8 cores into the thing, it would run circles around Haswell.

 

And since the ARM is basically a PPC, the SDK's are all there, and much of the code is already written. It would just need an updating.

 

120 hours is too high. The CPU is only part of a laptop's power draw. The DRAM, GPU, screen, power supply, wireless, etc... all take up a lot of power. Even if the CPU took zero power you might only see a 10-20% battery life improvement.

 

I think it is also a little far to say 'ARM is basically a PPC' – they are both RISC cores, but the ISAs are very different, and, more importantly, their memory models are different. Porting can be done, but it is very non-trivial.

And while I am sure Apple could manage the transition (as they did with 68K->PPC and then PPC->x86) it would still be tricky. PPC gave a huge performance boost over 68K and x86 gave a future which PPC simply didn't have. The ARM cores do give good performance per watt, but don't give a huge raw performance boost over x86.

 

Apple would also have to improve the 'uncore' part of the A* line to be competitive with x86 - things like more scalable cache coherency, more memory channels, etc... All of this can be done, but is non-trivial.

 

On the other hand, the A* line could be less expensive, and it could allow some interesting integration paths that x86 doesn't support – e.g. integration with stacked memory in the package.

post #38 of 198
Quote:
Originally Posted by jj.yuan View Post

I agree. Fragmentation is bad.
You are assuming that there would be fragmentation. There are a number of ways Apple could pull this off. One way is to make it an iOS laptop. The second would be to make it a Mac laptop that runs iOS apps in a window. That is just two approaches.
Quote:
Apple will not just convert MBA to A7 chip and keep Intel on MBP, I believe. Can the "Ax" chip become powerful enough for MBP in the next iteration? It would be interesting if it can. How about MacPro? Somehow, it feels hopeless for Apple to stop using Intel chips.

You can't look a machines designed for the pro market in the same way as for the general consumer. The fact is, as demonstrated by the iOS world, is that most consumers have zero need for i86 compatibility. Even more so with Windows compatibility. The world is a changing and Apple is in the drivers seat.
post #39 of 198
Confuscious says, the comment section is not what you think it is... It's not meant to talk about the article, but rather to respond to the first comment. 1wink.gif
post #40 of 198
Quote:
Originally Posted by Frac View Post


Well that made me sit up.
Possibilities galore. 1cool.gif

Gaming.  In AppleTV.  High Performance Gaming.  With gesture control.  Gotta be what Apple is thinking.  It's ARM, therefore iOS compatible, where there are more and more immersive games.  That's gotta be where they're taking this.

I don't care about what the ignorant masses perceive as truth. I'm concerned with the facts on the ground.
Reply
I don't care about what the ignorant masses perceive as truth. I'm concerned with the facts on the ground.
Reply
New Posts  All Forums:Forum Nav:
  Return Home
  Back to Forum: iPhone
  • Analysis affirms Apple's A7 processor closer to a desktop CPU than regular mobile chip
AppleInsider › Forums › Mobile › iPhone › Analysis affirms Apple's A7 processor closer to a desktop CPU than regular mobile chip