Discussion Quo vadis Apple Macs - Intel, AMD and/or ARM CPUs? ARM it is!

Page 7 - Seeking answers? Join the AnandTech community: where nearly half-a-million members share solutions and discuss the latest tech.

moinmoin

Diamond Member
Jun 1, 2017
4,944
7,656
136
Due to popular demand I thought somebody should start a proper thread on this pervasive topic. So why not do it myself? ;)

For nearly a decade now Apple has treated their line of Mac laptops, AIOs and Pro workstations more of a stepchild. Their iOS line of products have surpassed it in market size and profit. Their dedicated Mac hardware group was dissolved. Hardware and software updates has been lackluster.

But for Intel Apple clearly is still a major customer, still offering custom chips not to be had outside of Apple products. Clearly Intel is eager to at all costs keep Apple as a major showcase customer.

On the high end of performance Apple's few efforts to create technological impressive products using Intel parts increasingly fall flat. The 3rd gen of MacPros going up to 28 cores could have wowed the audience in earlier years, but when launched in 2019 it already faced 32 core Threadripper/Epyc parts, with 64 core updates of them already on the horizon. A similar fate appears to be coming for the laptops as well, with Ryzen Mobile 4000 besting comparable Intel solutions across the board, with run of the mill OEMs bound to surpass Apple products in battery life. A switch to AMD shouldn't even be a big step considering Apple already has a close work relationship with them, sourcing custom GPUs from them like they do with CPUs from Intel.

On the low end Apple is pushing iPadOS into becoming a workable mutitasking system, with decent keyboard and, most recently, mouse support. Considering the much bigger audience familiar with the iOS mobile interface and App Store, it may make sense to eventually offer a laptop form factor using the already tweaked iPadOS.

By the look of all things Apple Mac products are due to continue stagnating. But just like for Intel, the status quo for Mac products feels increasingly untenable.
 
  • Like
Reactions: Vattila

Carfax83

Diamond Member
Nov 1, 2010
6,841
1,536
136
It isn't IPC, it's scaled benchmark results. It has almost no real-world applicability, just like the benchmarks that produce the result. Case in point: when was the last time someone completed a big project using single-thread-limited SPEC or Geekbench? Because those are the only performance wins the A13 has over current mainstream x86.

You'll have to ask Andrei why he would "throw money and time out of the window by performing totally useless tests" re: single-threaded scaled benchmark results (that are unfairly set up and esoteric to boot). I think you were being sarcastic. I'm not.

This basically. I'm sick of hearing about the A series CPU and how great they are for single threaded performance, without the appropriate context. Out of all the various computing platforms, mobile depends on single threaded performance more than anything; which is why Apple spent so much of their engineering resources on improving single threaded IPC. It would be totally nonsensical for AMD and Intel to follow suit, as they are targeting different platforms that place greater emphasis on scalability and multithreaded IPC so their designs need to reflect this.
 

Glo.

Diamond Member
Apr 25, 2015
5,700
4,545
136
Wow, MacOS GB5 sucks. Also:


Frequencies were pretty high on that chip too. Looks like it had the standard PL1 configuration.

If Apple ever does move A-series ARM chips to MacOS, they may lose some performance right off the rip.
Looking at the fact that MacOS is the fastest currently ONLY in Web Browsing, out of three OSes, its not a matter of only GB5 on MacOS


Check this out. Comparison of MacOS 10.15 performance vs Windows 10 vs Ubuntu 19.10.
 

amrnuke

Golden Member
Apr 24, 2019
1,181
1,772
136
But proves a point that there are differences in performance between platforms that are not related to compilers.
Please note on the first page:
macOS compiler was Xcode / Clang / LLVM
Ubuntu compiler was gcc
Windows compiler not listed

So it could still be the compiler. But agree it's also probably environment.

The concerning thing is that with a software/low-level disadvantage here, what if you tack on a multi-threaded disadvantage from a hardware standpoint as well?
 

Thala

Golden Member
Nov 12, 2014
1,355
653
136
And how is that different than different compilers for iOS and Windows x86? You wanted to disprove, and yet you proven that in fact there are diffeences between PLATFORMS you test on, that yield better performance on iOS.

Hint: comparison was between iOS A12X and Ryzen 7 4700U scores in GB. I hope you get it now.

Changing goal post?

You said:
That is what I don't understand. In all of those comparisons, why nobody takes into account how iOS is optimized, and how it yields performance?

So did explain the part, which you did not understand - namely that the fact how iOS is optimized has no impact.
I am afraid, that there are a few more thing, which you dont understand...
 

Glo.

Diamond Member
Apr 25, 2015
5,700
4,545
136
The concerning thing is that with a software/low-level disadvantage here, what if you tack on a multi-threaded disadvantage from a hardware standpoint as well?
You're left with 65% better IPC than AMD and Intel and 4 years of development advantage.

;)
 

Thala

Golden Member
Nov 12, 2014
1,355
653
136
To bring it full circle, since we know there are differences between compilers on different OS, I think it would be interesting to see how Xcode-compiled on macOS compares to Clang/LLVM on Win10/Ubuntu - all on the same Macbook. Michael Larabel did an Xcode vs GCC over on Phoronix but the variance in compiler is too big to make a call.

The SDK comes with a customized version of clang/llvm - though you can target darwin/machos with the mainstream clang/llvm distribution.
 

amrnuke

Golden Member
Apr 24, 2019
1,181
1,772
136

chrisjames61

Senior member
Dec 31, 2013
721
446
136
How things come full circle. A quote from the article.

"Apple is designing more of its own chips to gain greater control over the performance of its devices and differentiate them from rivals".

Apple used the 68K and then PPC for various reasons. Then finally in 2006 getting in bed with Intel for various reasons including performance and the advantage of being able to dual boot Windows and it worked out great. Now 14 years later they want to differentiate again, Intel stagnating as far as performance goes and maybe dual booting Windows isn't as important anymore? Or is their Windows version that will run on these upcoming cpu's? Windows does run on ARM processors correct? Seems to me like it is a smart move tbh.
 

uzzi38

Platinum Member
Oct 16, 2019
2,607
5,822
146
I would not call this the "beginning" as the rumours exist for a long long time.

This article does not tell us a lot more, maybe the codenames? The core count, the possible usage in Laptops first is something multiple people discussed here in this thread.

My bad for not being clear, but I was referring to the rumours as to the actual SoC itself.

In terms of core count etc, this is the first rumour that's popped up.

Anyway, even just the core count tells us quite a bit. 8 big cores means they're thinking of forcefully removing Intel from everything short of the full Mac Pro IMO. Per core performance of Apple's big cores is more than enough for that.

The big question is: how far will they actually go?
 
  • Like
Reactions: Tlh97 and Etain05

Ajay

Lifer
Jan 8, 2001
15,408
7,833
136
12 cores, 5nm, probably 1-2 day battery life.

I think Apple is poised to leave PC laptop performance in the dust.
I would be surprised if it had 2 day battery support, not if performance is to be comparable to x86 at least. 8+4 cores will be a 'relatively' large die for 5N, IMO. Also, this will be very load dependent, so your statement is overly broad.
 

uzzi38

Platinum Member
Oct 16, 2019
2,607
5,822
146
12 cores, 5nm, probably 1-2 day battery life.

I think Apple is poised to leave PC laptop performance in the dust.
Eh~~

The 8 big cores are nice, should perform extremely well. But there's the software ecosystem to consider. Personally, I would never consider trading up the software side of things for extra battery life I wouldn't use (I see no purpose to battery life over 9-10 hours).

And it's not like you'll see these chips outside of Apple products. As such, I see no reason to care about them.
 

DrMrLordX

Lifer
Apr 27, 2000
21,609
10,803
136
And it's not like you'll see these chips outside of Apple products. As such, I see no reason to care about them.

If they're running MacOS proper, we can actually compare them to hardware from other vendors and see how they perform. So long as they remain locked up behind iOS, I would be inclined to agree.
 

mikegg

Golden Member
Jan 30, 2010
1,755
411
136
Eh~~

The 8 big cores are nice, should perform extremely well. But there's the software ecosystem to consider. Personally, I would never consider trading up the software side of things for extra battery life I wouldn't use (I see no purpose to battery life over 9-10 hours).

And it's not like you'll see these chips outside of Apple products. As such, I see no reason to care about them.
I use Sketch for work which is not available on Windows. MacOS supports every piece of software I need, while Windows does not. Of course, everyone is different.

As someone who does use a Mac, I have plenty of reasons to care about them.
 

beginner99

Diamond Member
Jun 2, 2009
5,210
1,580
136
I see no purpose to battery life over 9-10 hours

9 hours of barley usage yes but if you could actually work for 9-10 hours besides just reading web pages or pdfs or making some power points, then it makes sense to have more battery life. Those 4 core intels will suck a battery dry in 2-3 hours if you really tax them.
 

uzzi38

Platinum Member
Oct 16, 2019
2,607
5,822
146
9 hours of barley usage yes but if you could actually work for 9-10 hours besides just reading web pages or pdfs or making some power points, then it makes sense to have more battery life. Those 4 core intels will suck a battery dry in 2-3 hours if you really tax them.

Big Apple cores can easily use 5-7W each on their own if you stress them with a proper load. They don't on mobile because you can't cool 5-7W there, but in a laptop form factor that's not an issue. With 8 cores that's easily 40+W.

The only thing that helps in your use-case is limiting the maximum power budget of the chip at hand. The benefit of an ARM chip in your case is only if you equalise performance or if you want to get more done with the same sort of battery life.
 

mikegg

Golden Member
Jan 30, 2010
1,755
411
136
I would be surprised if it had 2 day battery support, not if performance is to be comparable to x86 at least. 8+4 cores will be a 'relatively' large die for 5N, IMO. Also, this will be very load dependent, so your statement is overly broad.
To be more specific, I'm talking about basic web browsing and email.

I believe the iPad Pro has a ~36 wh battery and offers 10 hours of battery life. However, Anandtech actually got 25 hours of battery life with basic web browsing: https://www.anandtech.com/show/13661/the-2018-apple-ipad-pro-11-inch-review/8

And that's with the 2018 version which used a SoC manufactured on the first-gen 7nm.

The Macbook Pro 16" has a 100 wh battery. Just extrapolating the numbers would yield 68 hours of basic web browsing. But of course, the Macbook will consume more power than the iPad Pro no matter what due to its size, active cooling, and beefier SoC.

I think 2 days of basic web browsing is realistic. Maybe Apple won't hit it with the first generation but I expect them to within the next 2-3 years for sure.