Apple A9x chip discussion

Page 2 - Seeking answers? Join the AnandTech community: where nearly half-a-million members share solutions and discuss the latest tech.

StrangerGuy

Diamond Member
May 9, 2004
8,443
124
106
Kinda funny to think about that the most powerful ARM SoC will find its way to users who are exactly the kind that won't give a single hoot to it.
 

Mondozei

Golden Member
Jul 7, 2013
1,043
41
86
Kinda funny to think about that the most powerful ARM SoC will find its way to users who are exactly the kind that won't give a single hoot to it.

Yeah iPad pro users don't care about performance.
(Yeah I know what you meant but you just phrased that incredibly badly).

Speaking of the A8X. Here's a reminder from last year.
http://www.anandtech.com/show/8716/apple-a8xs-gpu-gxa6850-even-better-than-i-thought

So Apple claims a 2X performance increase from that. I didn't get last years iPad Air 2(or the year before it), but there are several things going through my mind:

1. Does Apple need this? The only logical conclusion I have is if they are going with a 4K display, but Apple has often been good at ignoring fads. Look at their core count. Apple completely sidestepped the MOAR CORES hypetrain and with good reason. Do people really need 4K at 10-13 inches?

So if not 4K, why would they need this massive GPU increase? They talked vaguely about how this will "unlock new applications" but from what I saw being demoed, I doubt that you couldn't do that with an A8X quite well.

2. Given that it is now 2X faster in GPU performance when are we at PS4 levels? Are we even close?

3.
This last thing is a total wild guess but do you think they are going for GPU performance for a VR project? Or possibly to help them in their car program? Cars need a lot of really powerful GPUs for deep learning and I guess that could make sense to push GPUs as far as possible.

Right now I just don't see reasons to keep seeing 2X increases per year in GPU performance if you're only aiming at an iPad. There's gotta be something else they are shooting for, but what?
 
Last edited:

IntelUser2000

Elite Member
Oct 14, 2003
8,686
3,785
136
Nothing yet released about Skylake, that I can find. I don't think the Gen 9 HD 515 GPU in Core M 6Y's will beat whatever PowerVR has cooking in the A9X. Regardless, the Broadwell based Core M has always been pretty terrible at gaming due to the 4.5w TDP limit. I don't think that will change with Skylake?

It looks extremely bad for Core M Skylake GPU compared to the A9X. Core M Broadwell is already significantly slower than A8X. Intel claims 40% gain for Skylake on GPU, but A9X is 2x the performance of A8X. Simple calculation nets 2.3x the performance or Iris 540(15W eDRAM, 48EU) if that carries onto games.

Only thing that holds Intel back from making competitive chips are that they can fall back to the same spot - Windows market. If that is opened they'd be in trouble long ago.

I have to say, this is significant in a lot of ways if its true.

-It would mean ISA does have a meaningful difference. x86 holding it back
-Intel's process is nowhere near good as they claim.
 
Last edited:

Zodiark1593

Platinum Member
Oct 21, 2012
2,230
4
81
It looks extremely bad for Core M Skylake GPU compared to the A9X. Core M Broadwell is already significantly slower than A8X. Intel claims 40% gain for Skylake on GPU, but A9X is 2x the performance of A8X. Simple calculation nets 2.3x the performance or Iris 540(15W eDRAM, 48EU) if that carries onto games.

Only thing that holds Intel back from making competitive chips are that they can fall back to the same spot - Windows market. If that is opened they'd be in trouble long ago.

I have to say, this is significant in a lot of ways if its true.

-It would mean ISA does have a meaningful difference. x86 holding it back
-Intel's process is nowhere near good as they claim.

What would probably really make Intel sweat is should Apple start making server blades filled with their cpu cores (or otherwise becoming a chip provider). Even if the A9x uses 10 watts, fitting 20-40 of them on a single blade will yield quite a lot of power.
 

coercitiv

Diamond Member
Jan 24, 2014
6,400
12,849
136
[Later EDIT] I mixed up claims between A9X and A9, point still stands since claimed gains are similar. (A9x up to 1.8x over A8x, A9 up to 1.7x over A8)

Just so we're clear, all it took for so many people to get excited over A9 was a keynote slide claiming "up to 70% faster" than A8? The slides also mentioned the chip is "optimized for real-world use" while Phil Schiller said the following before making performance claims:
and the software team has worked together with our chip team to enable it to be maximum performance for the kinds of tasks we do every day
Be weary to draw early conclusions based solely on a "optimized" performance claim, Apple knows how to tell the truth in a way that it looks far more promising.



Remember these slides? People saw them one at a time, and many probably thought Metal will bring a 50% graphics performance improvement.
 
Last edited:

amyklai

Senior member
Nov 11, 2008
262
8
81
Yeah, let's wait until this thing is thoroughly benchmarked before we jump to any conclusions purely based on marketing-speak.
 

ShintaiDK

Lifer
Apr 22, 2012
20,378
145
106
The 2xbandwidth part may be the key factor to the so called speed claim. If its not just some vector instruction.

We already seen plenty of the reality distortion field at work.
 

Dribble

Platinum Member
Aug 9, 2005
2,076
611
136
Back to all the discussion where everyone points out that Apples eventual aim is to combine iOS and OSX, dump Intel and just use their chips everywhere which imo has seemed pretty obvious for years now. A lot of Intel fans seem to disagree however.
 

coercitiv

Diamond Member
Jan 24, 2014
6,400
12,849
136
Back to all the discussion where everyone points out that Apples eventual aim is to combine iOS and OSX, dump Intel and just use their chips everywhere which imo has seemed pretty obvious for years now. A lot of Intel fans seem to disagree however.
Let's talk again when "real-world" performance numbers come in, shall we? Apple makes some really nice & powerful chips, but let's judge them for how they perform in devices, not on stage.

Also, interesting metrics: everyone vs. many Intel fans.
 
Last edited:

erunion

Senior member
Jan 20, 2013
765
0
0
If it's Desktop-class, maybe Apple eventually will migrate Mac Book Air to the A* CPU too. That should save them a lot of money, using their own CPU. Also CPU does perform very well, and has good perf/watt.

I'd say the opposite is true. Apple creating an iPad Pro, that competes more closely with the MBA than ever, ensures that the lines are remaining separate.

If an iOS MBA, or some other fusion device, was around the corner then the iPad Pro would not exist.
 

BUnit1701

Senior member
May 1, 2013
853
1
0
I'd say the opposite is true. Apple creating an iPad Pro, that competes more closely with the MBA than ever, ensures that the lines are remaining separate.

If an iOS MBA, or some other fusion device, was around the corner then the iPad Pro would not exist.

Yes, because the MBA is totally usable as a tablet...

No one said anything about form factor, merely the hardware and software that power it. Absolutely nothing prevents MBA and iPad Pro from co-existing to service both markets while sporting the same SOC and OS.
 

coercitiv

Diamond Member
Jan 24, 2014
6,400
12,849
136
Absolutely nothing prevents MBA and iPad Pro from co-existing to service both markets while sporting the same SOC and OS.
A Macbook running iOS would require touch capabilities, hence the only real difference left would be the keyboard. Make the screen detachable through some clever engineering and both products are suddenly equivalent. Therefore something prevents MBA and iPad Pro from co-existing while sporting both the same SOC and OS.
 

witeken

Diamond Member
Dec 25, 2013
3,899
193
106
Transistor count? Die area? Architecture?

Anyway, they don't even need the quadcore everyone is saying. Just do the generational 10% Tock, bump clock speed a bit, and use 20nm FinFET instead of those leaky 20nm planars to bump sustained performance. Or heck, just introduce boost, which can be sustained for short time, and you also have the 1.8X, wich is very easy.

I'm guessing the second, and Core m will still leapfrog in sustained performance, which will be up much less than 1.8X.

Wonder what the GPU comparison will be. The denser design of A9X is more favorable for Apple, though.
 

Hans de Vries

Senior member
May 2, 2008
321
1,018
136
www.chip-architect.com
============================================
CPU according to the presentation: A9X vs A8X up to 1.8x
============================================

Looks like A9X is quad core at ~2GHz versus A8X with triple
core at 1.5GHz plus IPC improvements.

(In GB3 metric that would be: Single threaded ~ 2400, Multi
threaded ~ 8000)


============================================
GPU according to the presentation: A9X vs A8X up 2.0x
============================================

Seems that Apple implemented the new top end PowerVR
Series 7 GPU, the 16 cluster GT7900.
http://www.anandtech.com/show/8706/imagination-announces-powervr-series7-gpus-series7xt-series7xe/2





====================================================
Memory bandwidth according to the presentation: A9X vs A8X up 2.0x
====================================================

Most likely 2 LPDDR4 64 bit packages, (128 bit total) at 3200 Mb/s
for a total bandwidth 51.2 GByte/s
 
Last edited:

coercitiv

Diamond Member
Jan 24, 2014
6,400
12,849
136
============================================
CPU according to the presentation: A9X vs A8X up to 1.8x
============================================

Looks like A9X is quad core at ~2GHz versus A8X with triple
core at 1.5GHz plus IPC improvements.

(In GB3 metric that would be: Single threaded ~ 2400, Multi
threaded ~ 8000)

New Core m3-6Y30 Geekbench score:
ST: 2485
MT: 4749

https://browser.primatelabs.com/geekbench3/3404121

This is a low-end Core M, the fastest Skylake-Y version operates at 40-45% higher Turbo clocks. Can't wait to see how the best Core m7-6Y75 retail implementations perform.

This will be fun to watch.
 

Hugo Drax

Diamond Member
Nov 20, 2011
5,647
47
91
If generational performance leaps continue to be 80% a year then eventually it is going to leapfrog intel.

They are not stuck with having that front end hack and associated hardware to translate 1980s vintage, patched on machine code into uOps back and forth.
 

dahorns

Senior member
Sep 13, 2013
550
83
91
It looks extremely bad for Core M Skylake GPU compared to the A9X. Core M Broadwell is already significantly slower than A8X. Intel claims 40% gain for Skylake on GPU, but A9X is 2x the performance of A8X. Simple calculation nets 2.3x the performance or Iris 540(15W eDRAM, 48EU) if that carries onto games.

Is that really true for the GPU? The Core M GPU scores lower in the GFX benches, but it scores much higher in 3dmark. I don't know if that is a driver issue or some other limitation of Intel's GPUs. And we don't really know if that is an issue that has been addressed with Gen 9.

And unfortunately we can't compare actual games, making it all the more difficult to compare the products.
 
sale-70-410-exam    | Exam-200-125-pdf    | we-sale-70-410-exam    | hot-sale-70-410-exam    | Latest-exam-700-603-Dumps    | Dumps-98-363-exams-date    | Certs-200-125-date    | Dumps-300-075-exams-date    | hot-sale-book-C8010-726-book    | Hot-Sale-200-310-Exam    | Exam-Description-200-310-dumps?    | hot-sale-book-200-125-book    | Latest-Updated-300-209-Exam    | Dumps-210-260-exams-date    | Download-200-125-Exam-PDF    | Exam-Description-300-101-dumps    | Certs-300-101-date    | Hot-Sale-300-075-Exam    | Latest-exam-200-125-Dumps    | Exam-Description-200-125-dumps    | Latest-Updated-300-075-Exam    | hot-sale-book-210-260-book    | Dumps-200-901-exams-date    | Certs-200-901-date    | Latest-exam-1Z0-062-Dumps    | Hot-Sale-1Z0-062-Exam    | Certs-CSSLP-date    | 100%-Pass-70-383-Exams    | Latest-JN0-360-real-exam-questions    | 100%-Pass-4A0-100-Real-Exam-Questions    | Dumps-300-135-exams-date    | Passed-200-105-Tech-Exams    | Latest-Updated-200-310-Exam    | Download-300-070-Exam-PDF    | Hot-Sale-JN0-360-Exam    | 100%-Pass-JN0-360-Exams    | 100%-Pass-JN0-360-Real-Exam-Questions    | Dumps-JN0-360-exams-date    | Exam-Description-1Z0-876-dumps    | Latest-exam-1Z0-876-Dumps    | Dumps-HPE0-Y53-exams-date    | 2017-Latest-HPE0-Y53-Exam    | 100%-Pass-HPE0-Y53-Real-Exam-Questions    | Pass-4A0-100-Exam    | Latest-4A0-100-Questions    | Dumps-98-365-exams-date    | 2017-Latest-98-365-Exam    | 100%-Pass-VCS-254-Exams    | 2017-Latest-VCS-273-Exam    | Dumps-200-355-exams-date    | 2017-Latest-300-320-Exam    | Pass-300-101-Exam    | 100%-Pass-300-115-Exams    |
http://www.portvapes.co.uk/    | http://www.portvapes.co.uk/    |