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

551–560 of 855 posts

Re: Apple M1 Ultra

#551

Post by fomine3 »

bee_rider wrote: post #342
marcan_42 wrote: post #172

Earlier quoted context omitted.

I've been saying 4x M1 Max is not a thing and never will be a thing ever since the week I got my M1 Max and saw that the IRQ controller was only instantiated to support 2 dies, but everyone kept parroting that nonsense the Bloomberg reporter said about a 4-die version regardless... Turns out I was right. The Mac Pro chip will be a different thing/die.

Could they do a multi-socket board for the Mac Pro?

I expect this for CPU side. Multiple SoC introduces NUMA but it's already done on Dual Xeon based Mac. I wonder how their GPU work for the configuration.

Re: Apple M1 Ultra

#552

Post by schmuelio »

TheKarateKid wrote: post #413
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…

What we're seeing right now with Apple's M1 chips for desktop computing is on the same level of revolutionary as what the original iPhone did for mobile phones. The advancements in such a short period of time in the amount of computing power, low power usage, size, and heat usage of these chips is unbelievable and game-changing.

Don't get me wrong, the benefits of using ARM architectures for general purpose vs. x86 are really compelling.

The performance of x86 has been a leader for a while mostly because of the sheer amount of optimization work that has gone into them, but the cruft of the x86 instruction set and the architectural stuff you have to do to make the instruction set work is really showing it's age.

That being said, the GPU performance claims are incredibly misleading. The previous "relative performance" benchmarks that were done on the M1 Max for GPU performance were misleading as well, they definitely cannot keep up with a mid-tier modern discrete GPU.

The GPU claim isn't an ARM/x86 comparison like the CPU performance would be. This is comparing a 64 core 800GB/s GPU with a 10k core 900GB/s GPU and trying to make them look equivalent through misleading marketing.

None of this is to say that the M1 Ultra is bad necessarily, even if it performs roughly the same as a mobile GPU or powerful iGPU it would still be a very good chip, and I'd love to use one if I could use it in my environment properly. I'm just saying don't put too much faith in the GPU performance measurements provided here.

Re: Apple M1 Ultra

#553

Post by fomine3 »

arcticbull wrote: post #80
dagmx wrote: post #36

Earlier quoted context omitted.

A few points to make... - the shared CPU+GPU RAM doesn't necessarily mean the GPU has to eat up system RAM when in use, because it can share addressing. So whereas the current Mac pro would require two copies of data (CPU+GPU) the new Mac studio can have one. Theoretically. - they do have very significant video decoder blocks. That means that you may use less RAM than without since you can keep frames compressed in f…

Also, the memory model is quite different - with the ultra-fast SSD and ultra-fast on-die RAM. You can get away with significantly less RAM for the same tasks, not just because of de-duplication but because data comes in so quickly from the SSD that paging isn't nearly the hit it is on say an Intel based Mac. I'd expect it to work more like a game console, streaming in content from the SSD to working memory on the fl…

This is myth.

Re: Apple M1 Ultra

#554

Post by Geee »

tanduv wrote: post #522
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…

HL Alyx is actually quite well optimized, and you can definitely run it on Ultra with super-sampling on a 3090. [1] https://www.youtube.com/watch?v=kjNaC0-hiPE

I didn't see display resolution (or the model of HMD) mentioned in the video. I'm using Varjo Aero, which has 2880x2720 per eye, which is almost quapruple (per eye) compared to Valve Index. I think this resolution is enough for a good VR experience; pixels are almost invisible, and even small text is readable. However, HL Alyx doesn't run at 90 fps on full resolution.

Re: Apple M1 Ultra

#555

Post by ihuman »

Geee wrote: post #554
tanduv wrote: post #522

Earlier quoted context omitted.

HL Alyx is actually quite well optimized, and you can definitely run it on Ultra with super-sampling on a 3090. [1] https://www.youtube.com/watch?v=kjNaC0-hiPE

I didn't see display resolution (or the model of HMD) mentioned in the video. I'm using Varjo Aero, which has 2880x2720 per eye, which is almost quapruple (per eye) compared to Valve Index. I think this resolution is enough for a good VR experience; pixels are almost invisible, and even small text is readable. However, HL Alyx doesn't run at 90 fps on full resolution.

The author of that video is using the valve index, which is 1440×1600 per eye

Re: Apple M1 Ultra

#556

Post by jsjohnst »

lmilcin wrote: post #467
kllrnohj wrote: post #360

Earlier quoted context omitted.

The GPU claims on the M1 Pro & Max were, let's say, cherry picked to put it nicely. The M1 Ultra claims already look suspicious since the GPU graph tops out at ~120W & the CPU graph tops out at ~60W yet the M1 Studio is rated for 370W continuous power draw. Since you mention ML specifically, looking at some benchmarks out there (like https://tlkh.dev/benchmarking-the-apple-m1-max#heading-gpu & https://wandb.ai/tcapel…

> The M1 Ultra claims already look suspicious since the GPU graph tops out at ~120W & the CPU graph tops out at ~60W yet the M1 Studio is rated for 370W continuous power draw. And that is expected, a lot has to be reserved for USB devices.

SSD and those two large fans also use a fair amount of power too.

Re: Apple M1 Ultra

#557

Post by ip26 »

gjsman-1000 wrote: post #171
cehrlich wrote: post #158

Earlier quoted context omitted.

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…

Also of note is that half of the Mac Studio's case is dedicated to cooling. Up to this point, all M1 Max benchmarks are within laptops while all Threadripper benchmarks are in desktops. The M1 Max in the Mac Studio will probably perform better than expected.

Maybe; every chip hits a point where feeding in more power doesn’t make it go any faster.

If I was to guess, the increased cooling probably helps the Studio sustain similar boost clocks as the laptops, but for longer.

Although it’s possible these are on N4x, which might increase the attainable boost.

Re: Apple M1 Ultra

#558

Post by needle0 »

Geee wrote: post #554
tanduv wrote: post #522

Earlier quoted context omitted.

HL Alyx is actually quite well optimized, and you can definitely run it on Ultra with super-sampling on a 3090. [1] https://www.youtube.com/watch?v=kjNaC0-hiPE

I didn't see display resolution (or the model of HMD) mentioned in the video. I'm using Varjo Aero, which has 2880x2720 per eye, which is almost quapruple (per eye) compared to Valve Index. I think this resolution is enough for a good VR experience; pixels are almost invisible, and even small text is readable. However, HL Alyx doesn't run at 90 fps on full resolution.

Uh, Varjo Aero is a clear outlier in terms of resolution and definitely does not represent the current typical VR headset experience (which in early 2022 would be around Quest 2 or Valve Index). If you went out of your way to get an expensive niche high-end headset, it struggling on a 3090 is your problem, not HL:A's.

Re: Apple M1 Ultra

#559

Post by moflome »

TuringNYC wrote: post #491
polyrand wrote: post #258

I think the GPU claims are interesting. According to the graph's footer, the M1 Ultra was compared to an RTX 3090. If the performance/wattage claims are correct, I'm wondering if the Mac Studio could become an "affordable" personal machine learning workstation (which also won't make the electricity bill skyrocket). If Pytorch becomes stable and easy to use on Apple Silicon [0][1], it could be an appealing choice. [0]…

It shocks me how much payroll and cap-ex is spent on the M1 and how little is invested in getting TensorFlow/Pytorch to work on it. I could 10x my M1 purchases for our business if we could reliably run TensorFlow on it. Seems pretty shortsighted. The GPU claims wouldnt even need to be on parity with NVIDIA, it would just need to offer a vertically integrated alternative to having to use EC2.

> reliably run TensorFlow

What reliability issues are you having with TensorFlow on M1 Macs?

Re: Apple M1 Ultra

#560

Post by jamesy0ung »

Thaxll wrote: post #242
squeaky-clean wrote: post #146

Earlier quoted context omitted.

> Take all the time you need Check your replies in 10 years and I'll be able to list a dozen ;P But sarcasm aside yeah this chip looks insane.

It took less than 6month to have a faster amd / intel CPU than the m1 back then, Apple charts are showing performance / watt which for a desktop PC is kind of irrelevant. In pure speed amd / intel are faster or will be very soon. For graphic card I don't try to argue because fps on Mac are very inferior in games than a average modern card. It's not even on the same league.

> For graphic card I don't try to argue because fps on Mac are very inferior in games than a average modern card. It's not even on the same league.

The M1 is as fast as the 1650. I'm getting great frame rates at 1440P High on X-Plane

> It took less than 6month to have a faster amd / intel CPU than the m1 back then, Apple charts are showing performance / watt which for a desktop PC is kind of irrelevant. In pure speed amd / intel are faster or will be very soon.

Perf/Watt is very relevant. Electricity costs money and you also want a cool room.

Post reply on HN