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

321–330 of 855 posts

Re: Apple M1 Ultra

#321

Post by cassac »

Omniusaspirer wrote: post #190
cassac wrote: post #142

Earlier quoted context omitted.

What on earth are you talking about. That link shows it’s not even half as fast as the 3060, let alone the 3080. In borderlands it got 24 FPS while the 3080 got 52 FPS. How is that on par?

Gaming benchmarks are completely irrelevant when discussing the actual raw power of the GPU. As the other commenter said- look at the actual GPU benchmark in the first graph. Legacy games written for x86 CPUs obviously are going to perform poorly. I recommend you actually read the review and don't just scroll to the worst gaming benchmark you can find.

There are only two real gaming benchmarks and they are both real bad for the M1. In Tomb Raider it fairs even worse at 4K than it does in borderlands.

It’s a great chip but it doesn’t trade blows with anything Nvidia puts out especially at comparable price points.

Maybe you buy things to run benchmarks. I buy them to run the software I own. For games they come up short on fps and high on price. That is the inverse of what I’m looking for.

Re: Apple M1 Ultra

#322

Post by ghshephard »

hu3 wrote: post #279
forrestthewoods wrote: post #234

Earlier quoted context omitted.

> The performance per watt isn’t in the same universe and that matters. I couldn’t give less of a shit about performance-per-watt. The ONLY metric I care about is performance-per-dollar. A Mac Studio and Threadripper are both boxes that sit on/under my desk. I don’t work from a laptop. I don’t care about energy usage. I even don’t really care about noise. My Threadripper is fine. I would not trade less power for less…

This is what some folks miss. One hour of my time is more expensive than an entire month of a computer electricity bill. Some people just want tasks to perform as fast as possible regardless of power consumption or portability. Life's short and time is finite. Every second adds up for repetitive tasks.

The power is only relevant because it makes the machine quite in a compact form. If you've got a bit of space, then a water cooled system accomplishes a lot of the same thing. For some people there is an aesthetic element.

Power does make a big difference in data centers though - it's often the case that you run out of power before you run out of rack space.

Where power for a computer might make a difference could be in power-constrained (solar/off grid) scenarios.

I don't know if I've ever heard anyone make an argument based on $$$.

Re: Apple M1 Ultra

#323

Post by bpye »

1123581321 wrote: post #135
MuffinFlavored wrote: post #92

Earlier quoted context omitted.

What is M2 really going to be difference wise?

~15-20% faster if releases start this year, plus whatever optimizations learned from M1 in wide release such as perhaps tuning the silicon allocation given the various system. If next year, M2 or M3 (get it) will use Taiwan Semi's so-called 3nm, which should be a significant jump just like 7-5nm several years ago for the phones and iPads.

I doubt there will be much learned after actually shipping M1. Developing silicon takes a long time. I wouldn’t be surprised if the design was more or less fixed by the time the M1 released.

Re: Apple M1 Ultra

#324

Post by e4e78a06 »

Teknoman117 wrote: post #245
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…

Something is seriously fishy about those geekbench results. 24-core scores 20k, 32-core scores 22.3k, and 64-core score 25k. Something isn't scaling there.

Many GB5 (and real world) tasks are memory bandwidth bottlenecked, which greatly favors M1 Max because it has over double a Threadripper's memory bandwidth.

Re: Apple M1 Ultra

#325

Post by fivea »

kiratp wrote: post #288
fivea wrote: post #261

Earlier quoted context omitted.

> The 3990x runs a bit faster on the initial compile stage but the linking is single threaded and the M1 Max catches up at that point. Isn't linking IO-bound?

Exposing my limited understanding of that level of the computing stack - it is but Apple seems to have very very good caching strategies - filesystem and L1/2/3. https://llvm.org/devmtg/2017-10/slides/Ueyama-lld.pdf There is a breakdown in those slides discussing what parts of lld are single threaded and hard to parallelize so I suspect single thread performance plays a big role too. I generally observe one core pegg…

> Exposing my limited understanding of that level of the computing stack - it is but Apple seems to have very very good caching strategies - filesystem and L1/2/3.

That would mean that these comparisons between Threadripper and the M1 Ultra do not reflect CPU performance but instead showcase whatever choice of SSD they've been using.

Re: Apple M1 Ultra

#326

Post by ChuckMcM »

jamesfmilne wrote: post #292
ChuckMcM wrote: post #276

In some ways I wish this processor was available from a CPU chip seller. As a compute engine it gets a lot "right" (in my opinion) and would be fun to hack on. That said, the idea that USB C/Thunderbolt is the new PCIe bus has some merit. I have yet to find someone who makes a peripheral card cage that is fed by USBC/TB but there are of course standalone GPUs.

https://www.sonnettech.com/product/thunderbolt/pcie-card-exp...

Thanks! Of course they are bit GPU centric but the idea is there.

Very interesting stuff. I wonder both if the Zynq Ultrascale RFSOC PCIe card would work in that chassis and if I could get register level access out of MacOS.

Re: Apple M1 Ultra

#327

Post by paulmd »

crest wrote: post #315
paulmd wrote: post #264

Earlier quoted context omitted.

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.

So now the follow-on question I really wanted to ask: if the CPU can't access all the memory channels does that mean it can only address a fraction of the total memory as CPU memory? Or is it a situation where all the channels go into a controller/bus, but the CPU link out of the controller is only wide enough to handle a fraction of the bandwidth?

Re: Apple M1 Ultra

#328

Post by nicoburns »

arcticbull wrote: post #102
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 likely won't re-visit the Xserve, IMO. No reason to. They can't sell them at a premium compared to peers and its outside their area of expertise.

I doubt they'll go after the web server market. But I wonder if they might go after the sort of rendering farms that animation studios like Pixar use. Those guys are willing to pay silly money for hardware, and are market Apple has a long history with.

Re: Apple M1 Ultra

#329

Post by brigade »

enneff wrote: post #256
Teknoman117 wrote: post #245

Earlier quoted context omitted.

Something is seriously fishy about those geekbench results. 24-core scores 20k, 32-core scores 22.3k, and 64-core score 25k. Something isn't scaling there.

Yeah, it’s the real world tasks that GeekBench tries to simulate that don’t tend to scale linearity with processor count. A lot of software does not take good advantage of multiple cores.

Does Geekbench actually attempt to simulate that in their multi-core score? And how?

I was under the impression that all of their multi-core tests were "run N independent copies of the single-threaded test", just like SPECrate does.

Re: Apple M1 Ultra

#330

Post by altcognito »

hu3 wrote: post #279
forrestthewoods wrote: post #234

Earlier quoted context omitted.

> The performance per watt isn’t in the same universe and that matters. I couldn’t give less of a shit about performance-per-watt. The ONLY metric I care about is performance-per-dollar. A Mac Studio and Threadripper are both boxes that sit on/under my desk. I don’t work from a laptop. I don’t care about energy usage. I even don’t really care about noise. My Threadripper is fine. I would not trade less power for less…

This is what some folks miss. One hour of my time is more expensive than an entire month of a computer electricity bill. Some people just want tasks to perform as fast as possible regardless of power consumption or portability. Life's short and time is finite. Every second adds up for repetitive tasks.

The only reason I've ever cared about watts is that generally speaking 120 watt and 180 watt processors require more complicated cooling solutions. That's less true today than it ever was. Cases are designed for things like liquid cooling, and they tend to be pretty silent. The processors stay cool, and are pretty reliable.

I personally stick to the lower wattage ones because I don't generally need high end stuff, so I think Apple is going the right direction here, but it should be noted that Intel has also started down the path of high performance and efficiency cores already. AMD will find itself there too if it turns out that for home use, we just don't need a ton of cores, but instead a small group of fast cores surrounded by a bunch of specialist cores.

Post reply on HN