Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Apple M1 Ultra

apple.com

Post reply on HN
Print view View original

311–320 of 855 posts

Re: Apple M1 Ultra

#311

Post by runako »

paulmd wrote: post #264
runako wrote: post #159

Earlier quoted context omitted.

Having not seen benchmarks, I would imagine that claimed memory bandwidth of ~800 GB/s vs Threadripper's claimed ~166 GB/s would make a significant difference for a number of real-world workloads.

Someone will probably chime in and correct me (such is the way of the internet - Cunningham's Law in action) but I don't think the CPU itself can access all 800 GB/s? I think someone in one of the previous M1 Pro/Max threads mentioned that several of the memory channels on Pro/Max are dedicated for the GPU. So you can't just get a 800 GB/s postgres server here. You could still write OpenCL kernels of course. Doesn't…

Fascinating!

Linking this[1] because TIL that the memory bandwidth number is more about the SoC as a whole. The discussion in the article is interesting because they are actively trying to saturate the memory bandwidth. Maybe the huge bandwidth is a relevant factor for the real-world uses of a machine called "Studio" that retails for over $3,000, but not as much for people running postgres?

1 - https://www.anandtech.com/show/17024/apple-m1-max-performanc...

Re: Apple M1 Ultra

#312

Post by secondcoming »

adfgadfgaery wrote: post #226
sharikous wrote: post #108

Earlier quoted context omitted.

And massively behind in terms of power consuption

Yes, certainly. I don't think that's relevant in this case, though. Why would anyone care if their workstation CPU draws 60W or 200W? It's easy to cool in either case and the power consumption is trivial. M1 is clearly the best design on the market for mobile devices and is merely very good for desktops. Let's keep the enthusiasm realistic.

>Why would anyone care if their workstation CPU draws 60W or 200W?

I care. I work from home and my main power sink is my desktop. Considering the soaring energy prices these days I really do care about what my usage is.

Re: Apple M1 Ultra

#314

Post by manmal »

marcan_42 wrote: post #150
willcipriano wrote: post #87

Is it actually more powerful than a top of the line threadripper[0] or is that not a "personal computer" CPU by this definition? I feel like 64 cores would beat 20 on some workloads even if the 20 were way faster in single core performance. [0] https://www.amd.com/en/products/cpu/amd-ryzen-threadripper-3...

My 1st gen 16 core Threadripper is barely faster than an M1 Pro/Max at kernel builds, so a 64 core TR3 should handily double the M1 Ultra performance. But you know, I'm still happy to double my current build perf in a small box I can stick in my closet. Ordered one :-)

I wouldn’t automatically expect a linear decrease in compile time with growing core count. That would have to be tried.

Re: Apple M1 Ultra

#315

Post by crest »

paulmd wrote: post #264
runako wrote: post #159

Earlier quoted context omitted.

Having not seen benchmarks, I would imagine that claimed memory bandwidth of ~800 GB/s vs Threadripper's claimed ~166 GB/s would make a significant difference for a number of real-world workloads.

Someone will probably chime in and correct me (such is the way of the internet - Cunningham's Law in action) but I don't think the CPU itself can access all 800 GB/s? I think someone in one of the previous M1 Pro/Max threads mentioned that several of the memory channels on Pro/Max are dedicated for the GPU. So you can't just get a 800 GB/s postgres server here. You could still write OpenCL kernels of course. Doesn't…

On an M1 Max MacBook Pro the CPU (8P+2E) cores peak at a combined ~240GB/s the rest of the advertised 400GB/s memory bandwidth is only useable by the other bus masters e.g. GPU, NPU, video encoding/decoding etc.

Re: Apple M1 Ultra

#316

Post by otherjason »

grork wrote: post #243
pphysch wrote: post #116

> This enables M1 Ultra to behave and be recognized by software as one chip, so developers don’t need to rewrite code to take advantage of its performance. There’s never been anything like it. Since when did the average developer care about how many sockets a mobo has...? Surely you still have to carefully pin processes and reason about memory access patterns if you want maximum performance.

I thought that to extract peak performance out of NUMA based systems, you had to get down-and-dirty with memory access & locality to ensure you don’t cross sockets for data thats stored in RAM attached to other CPUs. Or am I out of date on NUMA systems?

This is what they were referring to. To get optimum performance out of NUMA systems, you need to be careful about memory allocation and usage to maximize the proportion of your accesses that are local to the NUMA domain where the code is running. Apple's answer here is essentially "we made the link between NUMA domains have such high bandwidth, you don't even have to think about this."

Re: Apple M1 Ultra

#318

Post by bpye »

adfgadfgaery wrote: post #250
alwillis wrote: post #212

Earlier quoted context omitted.

It doesn’t support your argument when we’re talking about a massive processor like a threadripper vs. a M1 Ultra. The performance per watt isn’t in the same universe and that matters.

The M1 Ultra is by a very wide margin the bigger of the two. According to Tom's Hardware [1], top-of-the-line Epycs have 39.54 billion transistors. That is about a third of the 117 billion in the M1 Ultra. Apple builds bigger than anyone else, thanks largely to their access to TSMC's best process. The M1 Ultra is a workstation part. It goes in machines that start at $4,000. The competition is Xeons, Epycs, and Thread…

That’s not really a fair comparison. Apples chip spends most of that on their GPU, and the neural engine takes a chunk too. Threadripper is only a CPU.

Re: Apple M1 Ultra

#319

Post by nicoburns »

kasperni wrote: post #72
cube2222 wrote: post #4

Looks like all the people saying "just start fusing those M1 CPU's into bigger ones" were right, that's basically what they did here (fused two M1 Max'es together). And since the presenter mentioned the Mac Pro would come on another day, I wonder if they'll just do 4x M1 Max for that.

> I wonder if they'll just do 4x M1 Max for that. Unlikely, M1 Ultra is the last chip in the M1 family according to Apple [1]. "M1 Ultra completes the M1 family as the world’s most powerful and capable chip for a personal computer.”" [1] https://www.apple.com/newsroom/2022/03/apple-unveils-m1-ultr...

They also said that the Mac Pro is still yet to transition. So they'll have to come up with something for that. My suspicion is that it won't be M branded. Perhaps P1 for pro?
Post reply on HN