Hacker News Reader

Comment by smoldesu | Hacker News Reader

This definitely is a factor. Another thing that people frequently overlook is how competitive Zen 2 is with M1: the 4800u stands toe-to-toe with the M1 in a lot of benchmarks, and consistently beats it in multicore performance.

Make no mistake, the M1 is a truly solid processor. It has seriously stiff competition though, and I get the feeling x86 won't be dead for another half decade or so. By then, Apple will be competing with RISC-V desktop processors with 10x the performance-per-watt, and once again they'll inevitably shift their success metrics to some other arbitrary number ("The 2031 Macbook Pro Max XS has the highest dollars-per-keycap ratio out of any of the competing Windows machines we could find!")

View on HN

> This definitely is a factor. Another thing that people frequently overlook is how competitive Zen 2 is with M1: the 4800u stands toe-to-toe with the M1 in a lot of benchmarks, and consistently beats it in multicore performance.

It's a bit unfair to compare multicore performance of a chip with 8 cores firing full blast against another 8 core chip with half of them being efficiency cores.

The M1 Max (with 8 performance cores) multicore performance score posted on Geekbench is nearly double the top posted multicore performance scores of the 5800U and 4800U (let alone single core, which the original M1 already managed to dominate).

It'll be interesting to see how it goes in terms of performance-per-a-watt. Which is what really matters in this product segment. The graphs Apple presented indicated that this new line up will be less efficient than the original M1 at lower power levels, but they'll be able to hit it out of the park at higher power levels. We'll have to wait to see the results from the likes of Anandtech to get the full story though.

Personally, I'd love to see a MacBook 14 SE with an O.G. M1, 32 GB memory, a crappy 720p webcam, and no notch. I'd buy as many of those as they'd sell me.

I'm curious to see how the M1 Pro compares to the M1 Max. They are both very similar processors with the main differences being the size of the integrated GPU and the memory bandwidth available.

https://browser.geekbench.com/v5/cpu/search?utf8=%E2%9C%93&q...

The M1 Max isn't competing with the 4800u, considering that it's starting price is ~10x that of the Lenovo Ideapad most people will be benching their Ryzen chips with. I don't think it's unfair to compare it with the M1, since it's still more expensive than the aforementioned Ideapad. Oh, and the 4800u came out 18 months before the M1 Air even hit shelves. Seeing as they're both entry-level consumer laptops, what might you have preferred to compare it with? Maybe a Ryzen 9 that would be more commonplace in $1k+ laptops?

It's hard to compare CPUs based on the price of the products they're packaged in. There are obviously a lot of other bits and bobs that go into them. However, it's worth noting that a MacBook Air is $300 cheaper than the list price for the Ideapad 4800U with an equivalent RAM and storage configuration. So by your logic, is it fair to compare the two? Perhaps, a 4700U based laptop would be a fairer comparison?

The gap between the Ideapad 4800U and the base model 14 inch MacBook Pro is a bit wider, but you'll also get a better display panel and LPDDR5-6400[1] memory.

We'll have to see how the lower specced M1 Pros perform, but it's hardly clear cut.

[1] https://www.anandtech.com/show/17019/apple-announced-m1-pro-...

Edit: I just looked up the price of the cheapest MacBook Pro with a M1 Max processor and it's about 70% more expensive than the Ideapad 4800U. However, with double the memory and much better quality memory and a better display and it seems roughly about 70% better multithreaded performance in Geekbench workloads. Furthermore, you may get very similar performance on CPU bound workloads with the 10 core M1 Pro, the cheapest of which is only 52% more expensive than the Ideapad 4800U.

AMD is already planning not only 20% YoY performance improvements for x86 but now has 30x efficiency plan for 2025. I think x86 is in it for much longer than a decade.

Intel otoh, depends on if they can gut all the MBAs infesting them.

Alder lake is looking really good in leaked benchmarks. I definitely think Intel is down, but not out.

Have to see if they can not only catch up, but keep up.

Where can I find these benchmarks?

https://videocardz.com/newz/intel-core-i7-12700-non-k-alder-...

30x efficiency is specifically for 16 bit FP DGEMM operations, and it is in the context of an HPC compute node including GPUs and any other accelerators or fixed function units.

For general purpose compute, so such luck unfortunately. Performance and efficiency follows process technology to a first order approximation.

https://www.tomshardware.com/news/amd-increase-efficiency-of...

also bear in mind that AMD's standards for these "challenges" have always involved some "funny math", like their previous 25x20 goal, where they considered a 5.02x average gain in performance (10x in CB R15 and 2.5x in 3D Mark 11) at iso-power (same TDP) to be a "32x efficiency gain" because they divided it by idle power or some shit like that.

But 5x average performance gain at the same TDP doesn't mean you do 32x as much computation for the same amount of power. Except in AMD marketing world. But it sounds good!

https://www.anandtech.com/show/15881/amd-succeeds-in-its-25x...

Like, even bearing in mind that that's coming from a Bulldozer derivative on GF 32nm (which is probably more like Intel 40nm) 5x gain in actual computation efficiency is still a lot, and it's actually even more in CPU-based workloads, but AMD marketing can't help but stretch the truth with these "challenges".

Wow that's stupid, I didn't look that closely. So it's really a 5x perf/watt improvement. I assume it will be the same deal for this, around 5-6x perf/watt improvement. Which does make more sense, FP16 should already be pretty well optimized on GPUs today so 30x would be a huge stretch or else require specific fixed function units.

it's an odd coincidence (there's no reason this number would be related, there's no idle power factor here or anything) but 5x also happens to be about the expected gain from NVIDIA's tensor core implementation in real-world code afaik. Sure they advertise a much higher number but that's a microbenchmark looking at just that specific bit of the code and not the program as a whole.

it's possible that the implication here is similar, that AMD does a tensor accelerator or something and they hit "30x" but you end up with similar speedups to NVIDIA's tensor accelerator implementation.

I've seen tensor cores really shining in... tensor operations. If your workload can be expressed in convolutions, and are matching the dimensions and batching needs of tensor cores, there's a world of wild performance out there...

To be fair idle power is really important for a lot of use cases.

In a compute focused cloud environment you might be able to have most of your hardware pegged by compute most of the time, but outside of that CPUs spend most of their time either very far under 100% capacity, or totally idle.

In order to actually calculate real efficiency gains you'd probably have to measure power usage under various scenarios though, not just whatever weird math they did here.

That's not really being fair, because the metric is presented to look like traditional perf/watt. And idle is not so important in supercomputers and cloud compute nodes which get optimized to keep them busy at all costs. But even in cases where it is important, averaging between the two might be reasonable but multiplying the loaded efficiency with the idle efficiency increase is ludicrous. A meaningless unit.

I can't see any possible charitable explanation for this stupidity. MBAs and marketing department run amok.

Yep 100% agree with you - see my last sentence. Just trying to clarify that the issue here isn't that idle power consumption isn't important, it's the nonsense math.

the 4800u stands toe-to-toe with the M1 in a lot of benchmarks, and consistently beats it in multicore performance

I had a Lenovo ThinkPad with a 4750U (which is very close to the 4800U) and the M1 is definitely quite a bit faster in parallel builds. This is supported by GeekBench scores, the 4800U scores 1028/5894, while the M1 scores 1744/7600.

If AMD had access to 5nm, the CPUs would probably be more or less or par. Well, unless you look at things like matrix multiplication, where even a 3700X has trouble keeping up with the Apple AMX co-processor with all 3700X's 8 cores fully loaded.

During my time, the Mac line has switched CPUs three times, why would Apple not switch to RISC-V if that one is really so much better than ARM?

Reply on news.ycombinator.com