Live data from Hacker News

Apple M1 Ultra

apple.com

671–680 of 855 posts

Re: Apple M1 Ultra

#671
post #247

Earlier quoted context omitted.

I think some of this can be guessed from the SoC codenames https://en.wikipedia.org/wiki/List_of_Apple_codenames M1 Max is Jade C-Die => 64GB M1 Ultra is Jade 2C-Die => 128GB There is a still unreleased SoC called Jade 4C-Die =>256GB So I think that's the most we'll see this generation, unless they somehow add (much slower) slotted RAM If they were to double the max RAM on M2 Pro/Max (Rhodes Chop / Rhodes 1C), which…

Agreed, I think they will use the 4C config to debut M2 and make a slash. They said in the keynote that M1 Ultra completes the M1 family. Timing works out well for November launch with the 2 year apple silicon transition timeline they gave themselves. Not sure what they are going to call it and if it will be A15 or A16 based. A16 would give great performance, and I think it’s safe for them to have a two year iteratio…

Hard to believe it’s already been almost 1.5 years!

Re: Apple M1 Ultra

#672
post #421

Earlier quoted context omitted.

An M1 Ultra is $2000 incrementally over a M1 Max, so there is no price gap, even with the inflated prices 3090s actually go for today.

Wait, you can get a 3090?

3090 is literally the easiest card to get at RRP, at least here in UK. Set up discord alerts, the FE cards stay in stock for hours, the last one in February was in stock for the entire day so anyone who wanted to buy one at RRP(£1399) could do so without any issue at all.

Re: Apple M1 Ultra

#673
post #579

Earlier quoted context omitted.

I have a 5k monitor, but yes. That is literally all I care about.

Congratulations, no video card in the world is able to keep up a 5k res at 60FPS while doing even slightly demanding things. Nor will the M1 Ultra be.

My 3090 can drive 4k100hz for most demanding games at their highest settings.

Some games are a stable 4k120 and others are more like 4k75.

I feel the 3090 could feasibly drive 5k60 as a result.

Re: Apple M1 Ultra

#674

Earlier quoted context omitted.

> 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...

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.

The Mac Pro chip will be a 4x M2 Max

Re: Apple M1 Ultra

#675

Earlier quoted context omitted.

They’d have to go all-in on supporting third party OSs like Linux first. Sure, there are projects to bring linux to the M1, but enterprises that buy commercial server hardware will demand 1st party support

The major Linux providers already offer 1st party supported Linux on AWS. Both RHEL and Ubuntu instances offer support contracts from their respective companies, as well as Amazon Linux from AWS themselves. It is already here and a big force there. You can provision ElastiCache and RDS Graviton instances too.

Yes but on architectures that are already supported outside of AWS. It's not about running Linux in AWS, it's about running Linux on the chosen chip.

Re: Apple M1 Ultra

#676

Earlier quoted context omitted.

Yeah, there are a lot more parameters here than just 'there are two chips and one is the bestestst', like the availability you pointed out. There is raw performance, but there is also performance per watt, availability and scalability (which is both good and bad - M1 is available, but there is no M1 Ultra cloud available). If you want a multi-use setup, an RTX makes more sense than most other options, if you can get…

Note that Geforce RTX on cloud is prohibited by Nvidia.

The part of the EULA which is supposed to enforce that is not enforceable in Germany. It is complicated. There might be other ways you can circumvent agreeing to the EULA based on your location.

Re: Apple M1 Ultra

#677
post #636

Earlier quoted context omitted.

To be fair that $2000 also gets you +32GB RAM, +512GB storage, and +10 CPU cores. It's not just the GPU. Although yeah you can definitely fit a 3090-equipped PC into a $4k budget even with ebay pricing if pure GPU performance is all you really want.

> To be fair that $2000 also gets you +32GB RAM, +512GB storage, and +10 CPU cores. Even though it's not an apples to apples comparison, keep in mind that a 1x32GB DIMM sells for less than 150$, and you can buy 1TB SSDs for less than 100$.

HBM2 is a tad more expensive, but yes.

Re: Apple M1 Ultra

#678

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]…

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…

At some point can we finally admit that Apple's GPU claims just aren't....true? Like, every Apple keynote they put up incredible performance claims, and every time people actually get their hands on the product, it doesn't even come close to holding water in any domain where GPU performance matters (Game performance, ML training perf)

Re: Apple M1 Ultra

#679

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…

At some point can we finally admit that Apple's GPU claims just aren't....true? Like, every Apple keynote they put up incredible performance claims, and every time people actually get their hands on the product, it doesn't even come close to holding water in any domain where GPU performance matters (Game performance, ML training perf)

I thought that would be a given by now.

Won't even get into that it can't run most things you'd want that kind of hardware for.

Re: Apple M1 Ultra

#680
post #463
post #447

Earlier quoted context omitted.

Ehh, I wouldn't put too much stock in graphs of "relative performance" on a 0-200 scale like these. Marketing can cook up whatever they like when they want to make a product look good. Wait for actual benchmarks before trying to judge the product. Their base claim is >2x the m1 max, which is still nowhere close to the performance of a 3090. Apple's footnotes don't even pretend to explain what these charts are. > Perf…

Remember last time Apple put out these weird relative performance charts, and we all thought they were hiding something? The M1 announcement. They turned out to be pretty accurate. So I’ll wait and see real benchmarks, but it wouldn’t surprise me if this does have incredible performance.

_Some_ of the claims were pretty accurate.

A lot of them, particularly the GPU benchmarks, were misleading because they only looked at performance that they had dedicated silicon for.

Post reply on HN