News Apple Developing 32-Core ARM CPUs and 128-Core GPUs to Replace AMD Graphics, Report

nofanneeded

Respectable
Sep 29, 2019
1,561
251
2,090
52
Apple will have a hard time convincing people to pay $10000 for a MAC PRO with ARM CPU and Apple made GPU ...

Also 32 cores ARM is like 5GHZ 16 cores /32 threads Ryzen in performance .

I dont think that Apple could clock 32 cores higher than 2.5 Ghz each ..
 
Last edited:
Reactions: artk2219

GoatGuy

Honorable
Feb 22, 2016
22
10
10,515
0
Apple will have a hard time convincing people to pay $10000 for a MAC PRO with ARM CPU and Apple made GPU ...

Also 32 cores ARM is like 5GHZ 16 cores /32 threads Ryzen in performance .

I dont think that Apple could clock 32 cores higher than 2.5 Ghz each ..
I don't think so.

Ryzen (as an example) for a single core, single thread, is about 25% slower than M1, single core/thread. Turn on 2 threads on that same single core, and M1 and Ryzen 3 at the same GHz are about the same, except when very wide X86-extensions are used. X86 beats M1, CORE-for-CORE then. Takes 2 threads per core to do it, but it does.

However, under all but the most contrived circumstances, SMT only adds between 25% and 40% more per-core performance, per GHz. Certainly no-where near 100% better throughput. Nowhere near.

My thinking is that first RYZEN then belatedly (but rather impressively), Intel will both leap full-belly into the 5 nanometer EUV world, stepping up layer counts (at 5 NM) for some truly spectacular performance increases in the next 2 years. And the cores-per-chip will also rise. Cores and cache; for Ryzen, also with increasingly competent on-chip GPU coprocessor services. Like the M1, in a way. But bigger physical pinout package, for dedicated GPU memory not-affiliated with 'unified' memory of the M1. Non Von-Neuman machine.

Basically, we are looking at the breakthru to 6 GHz (or higher!) computing, at sub 0.8 V logic. 5 nm chip structures, very heavily weighted toward big.SMALL.gpu architecture. Also note that with little penalty, even the X86 architecture can be big.SMALL reconfigured. I could easily see AMD popping forth an 8s + 16B chip, single chiplet. 5 GHz before 'turbo'.

That'd give Apple a real run for the money. Never, ever underestimate the ability fo both AMD and INTEN to seriously invest-and-step-up to compete with the 'new guys'. Putting 12 chiplets ona single Threadripper package ... for 192 cores, maybe 300 threads ... seriously changes what a single-package compute device means.

GoatGuy
 
Reactions: artk2219

syadnom

Distinguished
Oct 16, 2010
10
2
18,515
0
Apple will have a hard time convincing people to pay $10000 for a MAC PRO with ARM CPU and Apple made GPU ...

Also 32 cores ARM is like 5GHZ 16 cores /32 threads Ryzen in performance .

I dont think that Apple could clock 32 cores higher than 2.5 Ghz each ..
I have clients with multiple Mac Pros, each costing well over $10k. If it performs, they don't care what's inside.

I happen to own an M1 mac mini and an M1 Macbook Pro. They are fantastic. Smokes my previous Macbook Pro handily without the case getting warm. It runs x86 software faster than my previous macbook pro, including fusion 360 which isn't ported to M1 yet and runs smoother.

I have no doubt apple can put 32 cores together and maintain high speeds because they have the thermal headroom to do it. In a Mac Pro they can put a big heat sink on and crank the volts up.

And an 8 core chip with 4 performance cores (which is all that's being used in benchmarking) is already keeping up with 8 core Ryzens. I don't think your claim that 32 M1 cores is equivalent to 16 ryzen cores holds water at all, if we are measuring M1 performance cores to Ryzen cores they are very similar overall.

I would expect that a 32 core M1 (32 performance + 4 efficient?) will absolutely smash a 16c/32t ryzen and every single core benchmark out there on the M1 supports this.

For the sake of argument, call an M1 performance core roughly equivalent to a Ryzen or intel core in performance.
 

Makaveli

Distinguished
Jan 15, 2001
1,324
366
19,670
4
I don't think so.

Ryzen (as an example) for a single core, single thread, is about 25% slower than M1, single core/thread. Turn on 2 threads on that same single core, and M1 and Ryzen 3 at the same GHz are about the same, except when very wide X86-extensions are used. X86 beats M1, CORE-for-CORE then. Takes 2 threads per core to do it, but it does.

However, under all but the most contrived circumstances, SMT only adds between 25% and 40% more per-core performance, per GHz. Certainly no-where near 100% better throughput. Nowhere near.

My thinking is that first RYZEN then belatedly (but rather impressively), Intel will both leap full-belly into the 5 nanometer EUV world, stepping up layer counts (at 5 NM) for some truly spectacular performance increases in the next 2 years. And the cores-per-chip will also rise. Cores and cache; for Ryzen, also with increasingly competent on-chip GPU coprocessor services. Like the M1, in a way. But bigger physical pinout package, for dedicated GPU memory not-affiliated with 'unified' memory of the M1. Non Von-Neuman machine.

Basically, we are looking at the breakthru to 6 GHz (or higher!) computing, at sub 0.8 V logic. 5 nm chip structures, very heavily weighted toward big.SMALL.gpu architecture. Also note that with little penalty, even the X86 architecture can be big.SMALL reconfigured. I could easily see AMD popping forth an 8s + 16B chip, single chiplet. 5 GHz before 'turbo'.

That'd give Apple a real run for the money. Never, ever underestimate the ability fo both AMD and INTEN to seriously invest-and-step-up to compete with the 'new guys'. Putting 12 chiplets ona single Threadripper package ... for 192 cores, maybe 300 threads ... seriously changes what a single-package compute device means.

GoatGuy
Why is your example for Ryzen using Gen 1?

What is the single core performance for Zen 3 vs M1?
 
Reactions: artk2219

nofanneeded

Respectable
Sep 29, 2019
1,561
251
2,090
52
I happen to own an M1 mac mini and an M1 Macbook Pro. They are fantastic. Smokes my previous Macbook Pro handily without the case getting warm. It runs x86 software faster than my previous macbook pro, including fusion 360 which isn't ported to M1 yet and runs smoother.
Your claims are false. unless your old macbooks are 3gens old.
 
Last edited:

ezst036

Reputable
Oct 5, 2018
290
161
4,870
1
Apple will have a hard time convincing people to pay $10000 for a MAC PRO with ARM CPU and Apple made GPU ...
A large body of Apple's customer base are akin to a cult, just as long as Apple can show reasonable performance within the margins of error now being seen on M1, Apple is in no danger that you suggest.

Its not a gaming platform, thats not how they have built their infrastructure going forward. They need to accel at compute and AI, that's all they need.
 

aldaia

Distinguished
Oct 22, 2010
525
7
18,995
1

nofanneeded

Respectable
Sep 29, 2019
1,561
251
2,090
52
Fair comparison. A 15 W CPU designed for laptops requiring no fans vs a top en desktop CPU consuming well over 150 W and requiring water cooling for max performance. Good luck running your 5950x inside a laptop with no fans.

Wonder who is the fanboy.
Ryzen with 1 core would run on 5-10 watts at that speed as well. 1 core does not require 150 watts wise guy ...
 

Jbelkin

Reputable
Apr 26, 2017
1
0
4,510
0
I wonder how much Apple has to pay Nvidia on licensing fees for using ARM.
Apple used to own ARM (along with others) so they are grandfathered in with the most complete license. And yes, Apple owns the IP above and beyond ARM's instruction set. They have built their own code on top of ARM's original foundation.
 

hotaru251

Distinguished
I don't think so.

Ryzen (as an example) for a single core, single thread, is about 25% slower than M1, single core/thread.
uhh....
you might be being biased?
cause ryzen beats apple's in native and emulation with single thread.
vs desktop cpu's (and rememebr the mac mini IS a sff desktop not a laptop)



and multi is same thing even vs the ryzen laptop (just imagine how bad the desktop 5000 would wreck m1)




it "does" beat ryzen in single geek bench (but then that is not very demanding on cpu as its burst and apple has always been favored in there)

and again if u use even 1 other core it loses hard.




and with rumor that AMD might get into ARM processors again I doubt apple will be king of arm speed for long (assuming that their arm advances like their x86 have)

M1 is nice for what it is (a powerful low power chip) but it isnt worth the apple tax for it unless ur 1 of their sheep and can't live w/o the closed garden. (which i get some ppl liek that ease)
 
Dec 7, 2020
1
1
10
0
I see a lot of comments comparing the M1 with the 5950x and quoting Geekbench, Cinebench and other cross platform solutions.

It's definitely one very valid way of direct comparison to look at FPU/Int in isolation on a per core basis.

However I also feel that these same tests fail to address that apple is not just selling M1 as a processor but also as a SOC and with a software development ecosystem around it designed to be optimized for it (Core ML, Core Animation, Core Video etc....).

Most folks who will buy an M1 type Mac will not be purchasing to utilize cross platform benchmark apps to designed to test isolated parts of a chip. They will be buying to run software to do work like video editing, rendering, photos editing, music production, coding/compilation/gaming etc...

The per core comparison is interesting but irrelevant in real world workloads where rubber meets the road when software is optimized to take advantage of the on chip accelerators for ISP, cryptography, video encode/decode etc... that M1 provides out the gate.

Because Apple controls 'the full widget' optimization for the M1 with native apps, is in my opinion going to show greater improvements for M1 native apps over time.

Already I have seen videos of the M1 editing Canon R5 8k footage without a hiccup but 32 core Xeon systems struggling under the same load.

Even still, comparing with the very best x86 chip to date - the Ryzen 5950X - these benchmarks ( see the poster above) come from a Ryzen chip running at turbo boost @5GHz in comparison to M1 at 3.2GHz.

When you factor in the energy heat comparisons .... that's mind-blowing performance for the M1 particularly considering that it is entry level chip in a small form factor running with a much much much lower TDP.
 
Reactions: hotaru.hino

escksu

Reputable
BANNED
Aug 8, 2019
878
351
5,260
0
Apple will have a hard time convincing people to pay $10000 for a MAC PRO with ARM CPU and Apple made GPU ...

Also 32 cores ARM is like 5GHZ 16 cores /32 threads Ryzen in performance .

I dont think that Apple could clock 32 cores higher than 2.5 Ghz each ..
MAC Pro is different from PC. ITs more than just CPU. Its an entirely different platform. Pple who buy apple doesn't care about the hardware inside.
 

ASK THE COMMUNITY

TRENDING THREADS