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

AMD funded a drop-in CUDA implementation built on ROCm: It's now open-source

phoronix.com

Post reply on HN
Print view View original

311–320 of 425 posts

Re: AMD funded a drop-in CUDA implementation built on ROCm: It's now open-source

#311

Post by latchkey »

beebeepka wrote: post #310
latchkey wrote: post #264

Earlier quoted context omitted.

I probably can't comment on that, but what I can comment on is this: H100's are hard to get. Nearly impossible. CoreWeave and others have scooped them all up for the foreseeable future. So, if you are looking at only price as the factor, then it becomes somewhat irrelevant, if you can't even buy them [0]. I don't really understand the focus on price because of this fact. Even if you do manage to score yourself some H…

Pretty sweet. I do envy you. For what it's worth, I would prefer AMD to charge as much as possible for these little beasts.

They definitely aren't cheap.

Re: AMD funded a drop-in CUDA implementation built on ROCm: It's now open-source

#312

Post by latchkey »

sophrocyne wrote: post #307
Cu3PO42 wrote: post #122

I'm really rooting for AMD to break the CUDA monopoly. To this end, I genuinely don't know whether a translation layer is a good thing or not. On the upside it makes the hardware much more viable instantly and will boost adoption, on the downside you run the risk that devs will never support ROCm, because you can just use the translation layer. I think this is essentially the same situation as Proton+DXVK for Linux g…

Hey there - I'm a maintainer (and CEO) of Invoke. It's something we're monitoring as well. ROCm has been challenging to work with - we're actively talking to AMD to keep apprised of ways we can mitigate some of the more troublesome experiences that users have with getting Invoke running on AMD (and hoping to expand official support to Windows AMD) The problem is that a lot of the solutions proposed involve significan…

Invoke is awesome. Let me know if you guys want some MI300x to develop/test on. =) We've also got some good contacts at AMD if you need help there as well.

Re: AMD funded a drop-in CUDA implementation built on ROCm: It's now open-source

#313

Post by tgsovlerkhgsel »

Keyframe wrote: post #173

This event of release is however a result of AMD stopped funding it per "After two years of development and some deliberation, AMD decided that there is no business case for running CUDA applications on AMD GPUs. One of the terms of my contract with AMD was that if AMD did not find it fit for further development, I could release it. Which brings us to today." from https://github.com/vosen/ZLUDA?tab=readme-ov-file#faq…

How is this not priority #1 for them, with NVIDIA stock shooting to the moon because everyone does machine learning using CUDA-centric tools?

If AMD could get 90% of the CUDA ML stuff to seamlessly run on AMD hardware, and could provide hardware at a competitive cost-per-performance (which I assume they probably could since NVIDIA must have an insane profit margin on their GPUs), wouldn't that be the opportunity to eat NVIDIA's lunch?

Re: AMD funded a drop-in CUDA implementation built on ROCm: It's now open-source

#314

Post by machomaster »

NekkoDroid wrote: post #43
marcus0x62 wrote: post #29

Earlier quoted context omitted.

That, and it only runs on a handful of their GPUs.

If you are talking about the "supported" list of GPUs, those listed are only the ones they fully validate and QA test, other of same gen are likely to work, but most likely with some bumps along the way. In one of the a bit older phoronix posts about ROCm one of their engeneers did say they are trying to expand the list of validated & QA'd cards, as well as destinguishing between "validated", "supported" and "non-fun…

They can say whatever but the action is what matters, not wishes and promises. And the reality is that list of supported GPUs has been unchanged since they first announced it a year ago.

Re: AMD funded a drop-in CUDA implementation built on ROCm: It's now open-source

#315

Post by make3 »

tgsovlerkhgsel wrote: post #313
Keyframe wrote: post #173

This event of release is however a result of AMD stopped funding it per "After two years of development and some deliberation, AMD decided that there is no business case for running CUDA applications on AMD GPUs. One of the terms of my contract with AMD was that if AMD did not find it fit for further development, I could release it. Which brings us to today." from https://github.com/vosen/ZLUDA?tab=readme-ov-file#faq…

How is this not priority #1 for them, with NVIDIA stock shooting to the moon because everyone does machine learning using CUDA-centric tools? If AMD could get 90% of the CUDA ML stuff to seamlessly run on AMD hardware, and could provide hardware at a competitive cost-per-performance (which I assume they probably could since NVIDIA must have an insane profit margin on their GPUs), wouldn't that be the opportunity to e…

it's a common misconception that deep learning stuff is built in cuda. it's actually built on CUDNN kernels that don't use cuda but are actually gpu assembly written by hand by phds. I'm really not convinced that this project here would be able to be used for this. the ROCm kernels that are analogue to cudnn though, yes

Re: AMD funded a drop-in CUDA implementation built on ROCm: It's now open-source

#316

Post by pheatherlite »

tgsovlerkhgsel wrote: post #313
Keyframe wrote: post #173

This event of release is however a result of AMD stopped funding it per "After two years of development and some deliberation, AMD decided that there is no business case for running CUDA applications on AMD GPUs. One of the terms of my contract with AMD was that if AMD did not find it fit for further development, I could release it. Which brings us to today." from https://github.com/vosen/ZLUDA?tab=readme-ov-file#faq…

How is this not priority #1 for them, with NVIDIA stock shooting to the moon because everyone does machine learning using CUDA-centric tools? If AMD could get 90% of the CUDA ML stuff to seamlessly run on AMD hardware, and could provide hardware at a competitive cost-per-performance (which I assume they probably could since NVIDIA must have an insane profit margin on their GPUs), wouldn't that be the opportunity to e…

The only reason our lab bought 20k worth of Nvidia gpu cards rather than amd was the cuda industry standard (might as wellbe). It's kind of mind boggling how much business amd must be losing over this.

Re: AMD funded a drop-in CUDA implementation built on ROCm: It's now open-source

#317

Post by paulmd »

incrudible wrote: post #294
paulmd wrote: post #229

Earlier quoted context omitted.

> However, Microsoft has definitely been drinking the IBM koolaid a little to long and has lost the mandate of heaven. I think in the next 7-10 years we will reach a point where there is nothing Windows can do that linux cannot do better and easier without spying on you that's a fascinating statement with the clear ascendancy of neural-assisted algorithms etc. Things like DLSS are the future - small models that just…

"Neural assisted algorithms" are just algorithms with large lookup tables. Another magnitude of binary bloat, but that's nothing we haven't experienced before. There's no need to fundamentally change the OS paradigm for it.

I think we're well past the "dlss is just FSR2 with lookup tables, you can ALWAYS replicate the outcomes of neural algorithms with deterministic ones" phase, imo.

if that's the case you have billion-dollar opportunities waiting for you to prove it!

Re: AMD funded a drop-in CUDA implementation built on ROCm: It's now open-source

#318

Post by rekado »

Farfignoggen wrote: post #283

Phoronix Article from earlier(1): "While AMD ships pre-built ROCm/HIP stacks for the major enterprise Linux distributions, if you are using not one of them or just want to be adventurous and compile your own stack for building HIP programs for running on AMD GPUs, one of the AMD Linux developers has written a how-to guide. "(1) (1) "Building An AMD HIP Stack From Upstream Open-Source Code Written by Michael Larabel i…

You can also install HIP/ROCm via Guix:

https://hpc.guix.info/blog/2024/01/hip-and-rocm-come-to-guix...

> AMD has just contributed 100+ Guix packages adding several versions of the whole HIP and ROCm stack

Re: AMD funded a drop-in CUDA implementation built on ROCm: It's now open-source

#319

Post by Keyframe »

weebull wrote: post #296
whywhywhywhy wrote: post #215

Earlier quoted context omitted.

> I'm really rooting for AMD to break the CUDA monopoly Personally I want Nvidia to break the x86-64 monopoly, with how amazing properly spec'd Nvidia cards are to work with I can only dream of a world where Nvidia is my CPU too.

> Personally I want Nvidia to break the x86-64 monopoly The one supplied by two companies?

Maybe he meant homogeneity which Nvidia did try and tries with Arm.. but, on the other hand how wild would it be for Nvidia to enter x86-64 as well? It's probably never going to happen due to licensing if nothing else, lest we remember nForce chipset ordeal with intel legal.

Re: AMD funded a drop-in CUDA implementation built on ROCm: It's now open-source

#320

Post by lambdaone »

freeone3000 wrote: post #151
RamRodification wrote: post #94

Earlier quoted context omitted.

> and would also act as a disincentive for NVIDIA to make breaking changes to CUDA I don't know about that. You could kinda argue the opposite. "We improved CUDA. Oh it stopped working for you on AMD hardware? Too bad. Buy Nvidia next time"

Most CUDA applications do not target the newest CUDA version! Despite 12.1 being out, lots of code still targets 7 or 8 to support old NVIDIA cards. Similar support for AMD isn’t unthinkable (but a rewrite to rocm would be).

That's exactly the point I was making above.
Post reply on HN