Live data from Hacker News

Apple’s new M1 Pro and M1 Max processors

apple.com

481–490 of 1001 posts

Re: Apple’s new M1 Pro and M1 Max processors

#481
post #381

Earlier quoted context omitted.

And in the case for the M1 Pro, apple is showing it to be faster than the Lenovo 82JW0012US - which has a RTX 3050ti. so the performance could be between RTX 3050ti - RTX 3060. All of this with insanely low power draw.

But still not fanless, right? Maybe they'll update the Macbook Air with some better graphics as well, so that one could do some decent gaming without a fan.

Air is already at the thermal limit range with the 8 core GPU, will probably have to wait until the next real iteration of the technology in the chip (M2 or whatever) which increases efficiency instead of just being larger.

Re: Apple’s new M1 Pro and M1 Max processors

#483
post #362

Earlier quoted context omitted.

In terms of Hardware M1 Max is great. On paper you wont find anything match its performance under load. As even Gaming / Content Creation Laptop throttle after a short while. The problem is gaming isn't exactly a Mac thing. From Game selection to general support on the platform. So really performance should be the least of your concern if you are buying a Mac for games.

I'm not aware of a single even semi-major game (including popular indie titles) that run native on M1 yet. Everything is running under Rosetta and game companies so far seem completely uninterested in native support.

World of Warcraft & Eve Online are both native.

Re: Apple’s new M1 Pro and M1 Max processors

#484

So with 57B transistors for the M1 Max you can fit the AMD 5800H (10 B) and the RTX 3080 Ti (28 B) and have 19B transistors left. So the performance should be top notch but cooling and power requirements will be quite high. So battery life of 21 hours is quite the achievement. Still, i prefer the open architecture of the PC any day.

I wish we had real open hardware with everything documented. Sadly that us very rare.

Re: Apple’s new M1 Pro and M1 Max processors

#485

Earlier quoted context omitted.

The Apple cores are full custom, Apple-only designs. The AWS Graviton are Neoverse cores, which are pretty good, but clearly these Apple-only M1 cores are above-and-beyond. --------- That being said: these M1 cores (and Neoverse cores) are missing SMT / Hyperthreading, and a few other features I'd expect in a server product. Servers are fine with the bandwidth/latency tradeoff: more (better) bandwidth but at worse (h…

My understanding is that you don't really need hyperthreading on a RISC CPU because decoding instructions is easier and doesn't have to be parallelised as with hyperthreading.

The DEC Alpha had SMT on their processor roadmap, but it was never implemented as their own engineers told the Compaq overlords that they could never compete with Intel.

"The 21464's origins began in the mid-1990s when computer scientist Joel Emer was inspired by Dean Tullsen's research into simultaneous multithreading (SMT) at the University of Washington."

https://en.wikipedia.org/wiki/Alpha_21464

Re: Apple’s new M1 Pro and M1 Max processors

#486

Earlier quoted context omitted.

You're probably right. Maybe they have inventory to work through!

Yeah, M1 Pro/Max on iMac 30” likely in 2022 H1. Mini also, I imagine.

Yup. Once I saw the 24" iMac I knew the 27" had had it's chips. 30" won't actually be much bigger than the 27" if the bezels shrink to almost nothing - which seems to be the trend.

Re: Apple’s new M1 Pro and M1 Max processors

#487
Prediction for Mac Pros and iMac Pros: several SoCs on the mainboard, interconnected with a new bus, 16 CPU cores for each SoC, 4 SoCs max. The on SoC RAM will act as a L4 Cache and they will share normal, User replaceable DDR5 RAM for „unified“ access.

Re: Apple’s new M1 Pro and M1 Max processors

#488
post #98

Earlier quoted context omitted.

I think the higher memory is also a huge win, with support for up to 64gb.

400GB/s available to the CPU cores in a unified memory, that is going to really help certain workloads that are very memory dominant on modern architectures. Both Intel and AMD are solving this with ever increasing L3 cache sizes but just using attached memory in a SOC has vastly higher memory bandwidth potential and probably better latency too especially on work that doesn't fit in ~32MB of L3 cache.

> 400GB/s available to the CPU cores in a unified memory

It's not just throughput that counts, but latency. Any numbers to compare there?

Re: Apple’s new M1 Pro and M1 Max processors

#489

Earlier quoted context omitted.

Could we use M1 chips on non-apple boards? If yes, I wish Apple releases these for non mac os consumption. Eg. Running linux servers in the cloud.

Wasn't there a rumor that AMD was creating ARM chips? It will be great if we have ARM versions of EPYC chips.

AMD's equivalent of the Intel Management Engine (ME) is based on ARM, I think.

Intel used to use "ARC" cores, but recently converted to and i486.

Re: Apple’s new M1 Pro and M1 Max processors

#490

Based on the numbers it looks like the M1 Max is in the RTX 3070-3080 performance territory. Sounds like mobile AAA gaming has potential to reach new heights :D

If Proton is made to work on Mac with Metal, there's some real future here for proper gaming on Mac. Either that or Parallels successfully running x64 games via Windows on ARM virtualization.

I’ve been looking into trying CrossOver Mac on my M1 Max for exactly this reason. After seeing the kinds of GPUs Apple is comparing themselves to, I’m very hopeful.
Post reply on HN