Hacker News Reader

Comment by renewiltord | Hacker News Reader

Haha, bloody hell, what a monster of a chip. I find my M1 Max already remarkably fast. The change is so huge. It's like in the old days when you'd get a new computer and it felt like it could do things before you could think of doing them.

But surely the GPU things can't be real? The GPU in the M1 Ultra beats the top-of-the-line Nvidia? That's nuts.

View on HN

Based on Anandtech benchmarks the M1 Max GPU is basically on par with a mobile 3080, which a quick search tells me is about 60% as fast as a desktop 3080. Not unreasonable to believe 2 of them combined will outperform a 3090- with nearly 128 GB of VRAM to boot.

Even more incredible Anandtech reports the M1 max GPU block maxing at 43W in their testing. So a 90W GPU in the M1 Ultra is trading blows with a 350+ watt 3090.

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

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.

> Gaming benchmarks are completely irrelevant when discussing the actual raw power of the GPU.

Maybe, but the "raw power" is useless if it can't be exploited.

> Legacy games written for x86 CPUs obviously are going to perform poorly.

Not if they're GPU-bound. Even native performance isn't that impressive

If the power is substantial enough it will get exploited eventually. Hopefully even if Metal ports don't occur the eventual Asahi-adjacent open source drivers will open the gaming doors.

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.

If your interest is purely in playing unoptimized games coded for different architectures then absolutely there's better options.

However if your workloads are in a more professional domain as mine are then it's entirely fair to say this chip is trading blows with Nvidia's best at lower prices. Don't forget this is an entire SOC and not just a GPU, power saving aren't irrelevant either if you actually work your hardware consistently as I do.

If you buy a Mac for gaming, you're going to have a bad time. Look at the GFXBench 5.0 benchmark. The first graph on the page.

GPU scaling is absolutely not linear in that way. nvidia gave up on that in recent generations as without software support to match, you had situations where double 1080s were 95% as fast as one 1080 with worse frame times.

Might be nice for e.g. ML where you can effectively treat them as entirely independent GPUs but for games I would be surprised if this matches a high end GPU.

macOS will see it as one gpu.

https://www.theverge.com/22981815/apple-mac-studio-m1-ultra-...

The first benchmarks are in, and it's mostly a 40-50% improvement in the M1 Max, not 100%.

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.

Cache size is very related to performance.

That counts memory, right?

No, but it does include cache; the M1 Ultra should have 96MB of cache (>6B transistors) while Nvidia GPUs have relatively little cache. 128GB of DRAM has 1 trillion transistors.

> The GPU in the M1 Ultra beats the top-of-the-line Nvidia? That's nuts.

We don't know yet. Apple is benchmarking against Workstation graphics cards

"production 2.5GHz 28-core Intel Xeon W-based Mac Pro systems with 384GB of RAM and AMD Radeon Pro W6900X graphics with 32GB of GDDR6"

> Highest-end discrete GPU performance data tested from Core i9-12900K with DDR5 memory and GeForce RTX 3090.

From the linked article. Apple is comparing against RTX 3090.

Given that it's basically double the performance of the Max, with massive memory bandwidth, seems reasonable to me. But Apple always fudges things a bit. Like, which Nvidia exactly is this being compared to, and under what workload exactly?

Insane claims requires insane evidence. We don't have that there.

For some workloads i would not be surprised at all. But for all workloads, ...

> But surely the GPU things can't be real? The GPU in the M1 Ultra beats the top-of-the-line Nvidia?

Dubious. https://www.pcgamer.com/apple-m1-max-nvidia-rtx-3080-perform...

From the article:

> Apple even says its new GPU is a match for Nvidia's RTX 3080 mobile chip, though you'll have to take Apple's word for it on that one. We've also reached out to Nvidia to see what it might have to say on the matter.

> RTX 3080 mobile chip

> mobile chip

There's a 50%[1] (!) difference with mobile and non-mobile versions of the chip. So that's hardly a deal breaker.

[1] https://www.videocardbenchmark.net/high_end_gpus.html

The "mobile" scam in GPUs is terrible. Nvidia flat out lies about Mobile performance by giving misleading product names (same as the desktop names).

its beyond that. the same chip might have several tdps and drastic performance differences between models, such that a high tdp 3070 mobile is faster than a low tdp 3080. you end up having to get benchmarks for each particular laptop configuration.

Just for clarity, that article is about the M1 Pro and the M1 Max chips from October.

the problem on mac is the super tiny game selection

Nvidia 3090, I wonder what Relative Performance equates to.

Can't wait for the (real world) reviews to be published

Just to add in any case Apple is solving a big problem related to limited GPU memory, which is quite cool

Hopefully AMD, Nvidia, others can follow the trend

> But surely the GPU things can't be real? The GPU in the M1 Ultra beats the top-of-the-line Nvidia? That's nuts.

People that game on Mac know it's a lie, GPU for gaming on mac is vastly slower than recent graphic cards.

Reply on news.ycombinator.com