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

371–380 of 855 posts

Re: Apple M1 Ultra

#371

Post by Dylan16807 »

outworlder wrote: post #357
olliej wrote: post #346

Earlier quoted context omitted.

I’m find the slow drip of M1 extensions to be kind of ehn - like the tick part of the old intel cycle, only in this case it’s literally just gluing more of the same cores together (obviously work is involved, but not at the level of an architecture rev) (edit: calm down people, I recognize it's impressive, but it's just not as fun an announcement as an architecture rev, which I was hoping for after a year :D )

If 'gluing cores together' were this simple, every random desktop CPU would have 20 cores. That's not the case.

You're forgetting price. If simplicity was the main concern, every random desktop CPU would have 16+ cores right now.

Re: Apple M1 Ultra

#372

Post by kllrnohj »

cehrlich wrote: post #158
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...

Seems like for things that are: 1. Perfectly parallel 2. Not accelerated by some of the other stuff that's on the Apple Silicon SoC's ...it will be a toss-up. Threadripper 3990X get about 25k in Geekbench Multicore [1] M1 Max gets about 12.5k in Geekbench Multicore, so pretty much exactly half [2] Obviously different tasks will have _vastly_ different performance profiles. For example it's likely that the M1 Ultra wi…

Geekbench is extremely sensitive to the OS. Like the same CPU on Windows & Linux score wildly different on Geekbench. For example the 3990X regularly hits 35k multicore geekbench when run on Linux: https://browser.geekbench.com/v5/cpu/11237183

Re: Apple M1 Ultra

#373

Post by jdgoesmarching »

lambda_dn wrote: post #177
msoad wrote: post #76

At what point Apple will put those chips in their servers or sell server chips? It only makes sense for them to take this architecture to the cloud deployments

They could be secretly working on their own cloud platform, with their data centres having a choice between M1, Pro Max ultra instances. $$$$

For a company betting so heavily on “services,” it would be borderline incompetence if they weren’t working on this. Even just for internal use it would still be a better investment than the stupid car.

Re: Apple M1 Ultra

#374

Post by rowanG077 »

rocqua wrote: post #331
rowanG077 wrote: post #128

Earlier quoted context omitted.

51GB/s * 8 (octa-channel, not dual channel as you are calculating) is 408 GB/s. Basically the same as the M1 Max. It's not fair to use an off the shelf product since even if the RAM is slotted Apple wouldn't use an off the shelf product. Whether they use slotted RAM or not has nothing to do with performance. It's a design choice. For the mobile processors it makes total sense to save space. But for the Mac pro they m…

Is 8 channel RAM doable, are there downsides? If no to both, why don't high end x86 processors have it?

High-end x86 do have it. Threadripper 3995WX for example.

Re: Apple M1 Ultra

#375

Post by thfuran »

maronato wrote: post #113
thfuran wrote: post #13

Earlier quoted context omitted.

That thing has four times as many transistors as a 3090.

Although true, transistor count is only tangentially related to performance

It's certainly not the sole determinant of performance but given two reasonably solid designs, one with a vastly larger transistor budget and major node advantage to boot, I know which one I'd pick as likely winner.

Re: Apple M1 Ultra

#376

Post by EugeneOZ »

Geee wrote: post #307

This is insane. They claim that its GPU performance tops the RTX 3090, while using 200W less power. I happen to have this GPU on my PC and not only it costs over $3000, but its also very power-hungry and loud. Currently, you need this kind of GPU performance for high resolution VR gaming at 90 fps, but its just barely enough. This means that the GPU will run very loudly and heat up the room, and running games like HL…

But it's still impossible to replace RTX 3090 with this new Mac Studio because games just will not run on MacOS.

Re: Apple M1 Ultra

#377

Post by kllrnohj »

gzer0 wrote: post #267
Nition wrote: post #239

Earlier quoted context omitted.

The question is in relation to Apple's claim that it's "the world’s most powerful and capable chip for a personal computer".

It might also be reasonable to say that the threadripper is a workstation chip, not a chip for personal computers. Edit: even AMD themselves call their threadripper lineup workstation chips, not personal. https://www.amd.com/en/processors/workstation

Threadripper Pro is the workstation chip. Regular Threadripper (non-Pro) was not aimed at workstations, it was aimed at the "HEDT" market. Strictly speaking it's considered a consumer market (albeit for the enthusiasts of enthusiasts)

Re: Apple M1 Ultra

#378

Post by bobbylarrybobby »

outworlder wrote: post #367
Geee wrote: post #307

This is insane. They claim that its GPU performance tops the RTX 3090, while using 200W less power. I happen to have this GPU on my PC and not only it costs over $3000, but its also very power-hungry and loud. Currently, you need this kind of GPU performance for high resolution VR gaming at 90 fps, but its just barely enough. This means that the GPU will run very loudly and heat up the room, and running games like HL…

Too bad that historically Apple has not given any attention to Mac gaming.

Part of Apple's historic MO has been to not invest in areas they don't see themselves having a competitive advantage in. Now that they can make gaming happen with a very low wattage budget they may well try to enter that space in earnest.

Re: Apple M1 Ultra

#379

Post by my123 »

paulmd wrote: post #286
zitterbewegung wrote: post #54

Earlier quoted context omitted.

They might have to have the unified memory more dense to get to 1.5 TB max of RAM on the machine (also since this would be originally shared with a GPU). Maybe they could stack the RAM on the SoC or just get the RAM at a lower process node.

The M1 Max/Ultra is already extremely dense design for that approach, it's really almost as dense as you can make it. There's packages stacked on top, and around, etc. I guess you could put more memory on the backside but that's not going to do more than double it, assuming it even has the pinout for that (let's say you could run it in clamshell mode like GDDR, no idea if that's actually possible, but just hypothetic…

> You're not going to find a way to get 12x the memory while still doing the embedded memory packages.

https://www.anandtech.com/show/17058/samsung-announces-lpddr...

> It’s also possible to allow for 64GB memory modules of a single package, which would correspond to 32 dies.

It is possible, and I guess that NVIDIA’s Grace server CPU will use those massive capacity LPDDR5X modules too.

The M1 Ultra has 8 memory packages today, and Apple could also use 32-bit wide ones (instead of 64-bit) if they want more chips.

Post reply on HN