Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Dissecting the Apple M1 GPU, Part II

rosenzweig.io

Post reply on HN
Print view View original

21–30 of 195 posts

Re: Dissecting the Apple M1 GPU, Part II

#21

Post by tyingq »

devwastaken wrote: post #14
cambalache wrote: post #6

OK I love this, but I am pretty sure my chances of getting a mac in the future are zero. From which side should I expect the PC response? Intel? AMD? Microsoft? ARM? Samsung? I think Apple willingly or not has just obliterated the whole consumer pc market.

I'd be excited to see arm competition in the desktop space but I don't believe there are any arm chips that compete in performance to high end x86. Arm can do lots of cores which is very good for servers, but single threading performance is still a significant necessity on user end hardware. The M1 is great because it's low power with optimized performance, but on a desktop you can have well over 500W+ and that's nor…

I do think that's a relevant point for desktops. The M1 is incredible, but if you don't care about TDP, desktop can catch up fairly quickly for either Intel or AMD.

I don't see an obvious player currently working on a "broad market" high performance ARM chip for the commodity desktop.

Re: Dissecting the Apple M1 GPU, Part II

#22

Post by wlesieutre »

devwastaken wrote: post #14
cambalache wrote: post #6

OK I love this, but I am pretty sure my chances of getting a mac in the future are zero. From which side should I expect the PC response? Intel? AMD? Microsoft? ARM? Samsung? I think Apple willingly or not has just obliterated the whole consumer pc market.

I'd be excited to see arm competition in the desktop space but I don't believe there are any arm chips that compete in performance to high end x86. Arm can do lots of cores which is very good for servers, but single threading performance is still a significant necessity on user end hardware. The M1 is great because it's low power with optimized performance, but on a desktop you can have well over 500W+ and that's nor…

> I don't see anyone else making only mobile arm chips for laptops other than trying to be like a Windows Chromebook. The software compatability will be a nightmare.

I'd expect Microsoft to make a run at this with their Surface line.

They've been trying to make ARM tablets for a years (see Windows RT), and they just recently added the x86-64 compatibility layer so that it could be actually useful instead of "it's an iPad but worse".

https://blogs.windows.com/windows-insider/2020/12/10/introdu...

Will it see any success with 3rd party developers probably not bothering to support ARM? Maybe for some people who spend most of their time in Edge, Mail, or Office. I have a hard time seeing it being as successful as Apple's change, since the messaging from Apple is "This is happening in 2 years, get on board or you'll be left behind" and the messaging from Microsoft is "Look, we made an ARM tablet, and will probably sell at least 10 of them."

Re: Dissecting the Apple M1 GPU, Part II

#23

Post by MetaWhirledPeas »

cambalache wrote: post #6

OK I love this, but I am pretty sure my chances of getting a mac in the future are zero. From which side should I expect the PC response? Intel? AMD? Microsoft? ARM? Samsung? I think Apple willingly or not has just obliterated the whole consumer pc market.

They have bitten off an even bigger chunk of the meal they had nearly finished already:

- Developers

- Creatives

- Dutiful citizens of The Ecosystem

What they are no closer to biting off is gamers and hardware enthusiasts. Anyone who actually needs to open their PC for any purpose whatsoever.

I know Apple wants to be the glossy Eve to all the PC market's Wall-E's, but I will continue to shun them forcefully as long as they remain hell-bent on stifling the nerdy half of all of their users.

I assume the developer popularity is a result of the iPhone gold rush, which Apple exploited using exclusivity tactics. Therefore I consider it an abomination to see developers embrace the platform so thoroughly. iPhone development should feel shameful, and when there's no way to avoid it, it should be done on a dusty Mac Mini pulled from a cardboard box that was sitting in the closet ;)

Re: Dissecting the Apple M1 GPU, Part II

#24

Post by imhoguy »

gnarbarian wrote: post #10
flatiron wrote: post #8

Earlier quoted context omitted.

The new Ryzen mobile processors should be interesting. Their GPU drivers (while not of the best code quality) are in the mainline Linux kernel. So it all should just “work”

Currently using a Renoir laptop. It's smoking fast but I had to install a bleeding edge kernel to get the display driver to work at all. That should be fixed in the next ubuntu release though.

5.10.x kernels are very stable and feature complete with AMD Ryzen Renoir - I update one almost weekly once new patch version is out on Ubuntu Kernel PPA. Here is nice script which makes the update trivial: https://github.com/pimlie/ubuntu-mainline-kernel.sh

Re: Dissecting the Apple M1 GPU, Part II

#25

Post by tambourine_man »

cambalache wrote: post #6

OK I love this, but I am pretty sure my chances of getting a mac in the future are zero. From which side should I expect the PC response? Intel? AMD? Microsoft? ARM? Samsung? I think Apple willingly or not has just obliterated the whole consumer pc market.

> but I am pretty sure my chances of getting a mac in the future are zero

Why?

Re: Dissecting the Apple M1 GPU, Part II

#26

Post by cambalache »

tambourine_man wrote: post #25
cambalache wrote: post #6

OK I love this, but I am pretty sure my chances of getting a mac in the future are zero. From which side should I expect the PC response? Intel? AMD? Microsoft? ARM? Samsung? I think Apple willingly or not has just obliterated the whole consumer pc market.

> but I am pretty sure my chances of getting a mac in the future are zero Why?

Price for one, also I still consider PC and Linux (and god heavens even windows) more open than Mac. I also work with many windows-only automation software.

Re: Dissecting the Apple M1 GPU, Part II

#27

Post by ogre_codes »

While this is a long way from being a proper graphics driver, it is a good indication that we're going to see a functional driver for Linux before too long. I was concerned this bit would take years to work out, this suggests it'll be months to get a working driver.

Chuffed.

Re: Dissecting the Apple M1 GPU, Part II

#28

Post by perardi »

supernova87a wrote: post #2

[*Sure I get it, it's not interesting to talk meta about whether a post is interesting. I'm already downvoted off the planet. Fine.] I'm sure it's a good blog post for the right reader, but for something to land on HN front page, I generally look for either: 1) a story that, while specialized, reveals something accessibly technical and interesting to a semi-expert crowd, or 2) explains something at a sufficient level…

You’re complaining this is too technical…on a site called “Hacker News”…which is run by a firm named after an abstract mathematical concept.

OK, kiddo. Upworthy is over that-away.

Re: Dissecting the Apple M1 GPU, Part II

#29

Post by jandrese »

supernova87a wrote: post #2

[*Sure I get it, it's not interesting to talk meta about whether a post is interesting. I'm already downvoted off the planet. Fine.] I'm sure it's a good blog post for the right reader, but for something to land on HN front page, I generally look for either: 1) a story that, while specialized, reveals something accessibly technical and interesting to a semi-expert crowd, or 2) explains something at a sufficient level…

Are you saying this post is too nerdy for Hacker News? Stories come all the time, if you don't like it don't read it.

I didn't understand everything the author said, but I was able to get the gist of it. There GPU has a list of valid addresses and it's stored in a C style array with a terminator instead of a 1 indexed array with an object count in the Apple API style. The mismatch caused the author some confusion even after he discovered the existence of the buffer due to his code failing.

It's one of the many details that has to be understood in order to write an open source driver for the hardware. The open source driver will be necessary for people who want to install Linux on this Apple hardware.

Re: Dissecting the Apple M1 GPU, Part II

#30

Post by monkmartinez »

tambourine_man wrote: post #25
cambalache wrote: post #6

OK I love this, but I am pretty sure my chances of getting a mac in the future are zero. From which side should I expect the PC response? Intel? AMD? Microsoft? ARM? Samsung? I think Apple willingly or not has just obliterated the whole consumer pc market.

> but I am pretty sure my chances of getting a mac in the future are zero Why?

I cannot speak for OP, but software is the reason for me. I can not run Solidworks on MacOS without bootcamp or other tricks, for example. Photogrammetry apps? GIS apps? CNC CAM apps? I mean, compare the Mac[1] compatible apps to the catalog of Apps Autodesk has.

The fact of the matter is GPU support on MacOS is just not there in the same way it is with windows. It is really hard to justify the price of Apple when you compare directly to Windows offerings spec for spec. When you compare the sheer volume of software available for Windows as compared to MacOS, especially if you need a discrete GPU there are really no comparisons.

[1]https://www.autodesk.com/solutions/mac-compatible-software

Post reply on HN