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

Intel CEO: 'The entire industry is motivated to eliminate the CUDA market'

tomshardware.com

Post reply on HN
Print view View original

141–150 of 380 posts

Re: Intel CEO: 'The entire industry is motivated to eliminate the CUDA market'

#141

Post by JonChesterfield »

rbanffy wrote: post #11
sorenjan wrote: post #10

Earlier quoted context omitted.

SYCL is a better analog to Cuda than OpenCL, and Intel have their own implementation of that. Don't really see anyone writing anything in SYCL though, and when I looked into trying it out it was a bit of a mess with different implementations, each supporting their own subset of OSs and hardware. https://www.intel.com/content/www/us/en/developer/tools/onea...

I am unfamiliar with the implementation, but why would it be difficult to implement a Cuda-compatible software layer on top of other platforms? This would be the first step. Then, if we want to move away from Cuda into hardware that's as ubiquitous and performant as Nvidia's (or better), someone would need to write an abstraction layer that's more convenient to use than Cuda. I did play a little bit with Cuda and Ope…

Worth noting that cuda seems prone to using inline ptx assembly and that latter is really obnoxious to deal with on other platforms.

Implementing programming languages and runtimes is pretty difficult in general. Note that cuda doesn't have the same semantics as c++ despite looking kind of similar. Wherever you differ from expected behaviour people consider it a bug, and implementing based on cuda's docs wouldn't get you the behaviour people expect.

Pretty horrendous task overall. It would be much better for people to stop developing programs that only run on a gnarly proprietary language.

Re: Intel CEO: 'The entire industry is motivated to eliminate the CUDA market'

#142

Post by AnthonyMouse »

nvm0n2 wrote: post #137
AnthonyMouse wrote: post #121

Earlier quoted context omitted.

Its purpose was to create compatibility between Unix vendors so developers could write software compatible with different flavors. The primary market for Unix vendors is servers, which to this day are still about CLI and daemons, and POSIX systems continue to have dominant market share in that market.

Arguably the dominant APIs in the server space are the cloud APIs not POSIX.

Many of which are also open, like OpenStack or K8s, or have third party implementations, like Ceph implementing the Amazon S3 API.

Re: Intel CEO: 'The entire industry is motivated to eliminate the CUDA market'

#143

Post by JonChesterfield »

PeterisP wrote: post #50
bragr wrote: post #34

People don't seem particularly motivated to move away from CUDA to me. I've been poking around various models and tooling over the last couple months, and they pretty much all have something like device = "cuda" if torch.cuda.is_available() else "cpu" and I've yet to see a single one implement the AMD NN middleware: https://www.amd.com/en/developer/zendnn.html

This is a bit of a chicken and egg problem, because the developers of these projects probably don't even have relevant AMD devices to test that, because why would they? The only reasonable way to break the cycle would be proactive intervention by AMD to contribute code and testing and easy "works out of the box" installation to all the major popular projects to add AMD support so they can sell more their hardware lat…

Like the pytorch one? Or the onnx? Or Triton? There's loads of these machine learning things, each of which built their thing assuming Nvidia, to which AMD is stoically working to implement support for their hardware. It's a task of unbounded scope with unclear return on investment and they're doing it anyway.

Re: Intel CEO: 'The entire industry is motivated to eliminate the CUDA market'

#144

Post by JonChesterfield »

mschuetz wrote: post #84
PeterisP wrote: post #50

Earlier quoted context omitted.

This is a bit of a chicken and egg problem, because the developers of these projects probably don't even have relevant AMD devices to test that, because why would they? The only reasonable way to break the cycle would be proactive intervention by AMD to contribute code and testing and easy "works out of the box" installation to all the major popular projects to add AMD support so they can sell more their hardware lat…

CUDA is just way to good in terms of UX with nothing platform-independent coming close to it. I wish there was a competitor, but there simply isn't. I wish AMD&Intel would extend compute shaders with pointers&pointer casting, arbitrary large buffers instead of just 4GB, device-wide sync, and function pointers. Those are kinda my must-have functionality. Even better, just use C++ for compute shaders.

Freestanding C++ can be compiled to amdgpu or nvptx using clang. There are rough edges but it's usable.

Re: Intel CEO: 'The entire industry is motivated to eliminate the CUDA market'

#145

Post by paulddraper »

AnthonyMouse wrote: post #140
paulddraper wrote: post #128

Earlier quoted context omitted.

I think OP's point was less that the tech didn't work (e.g. OpenGL was fantastically successful) and that it didn't produce a good outcome for the "loser" companies that supported it.

The point of the open standard is to untether your prospective customers from the incumbent. That means nobody is going to monopolize that technology anymore, but that works out fine when it's not the thing you're trying to sell -- AMD and Intel aren't trying to sell software libraries, they're trying to sell GPUs. And this strategy regularly works out for companies. It's Commoditize Your Complement. If you're Intel…

> The point of the open standard is to untether your prospective customers from the incumbent.

That is the point.

But FWIW the incumbent adopts it and dominates anyway. (Though you now are technically "untethered.")

Re: Intel CEO: 'The entire industry is motivated to eliminate the CUDA market'

#146

Post by jzl »

bartwr wrote: post #30
ttoinou wrote: post #19

Earlier quoted context omitted.

What's wrong with compute shaders ?

I shipped a dozen products with them (mostly video games), so there's nothing "wrong" that would make them unusable. But programming them and setting up the graphics pipe (and all the passes, structured buffers, compiling, binding, weird errors, and synchronization) is a huge PITA as compared to the convenience of CUDA. Compilers are way less mature, especially on some platforms cough . Some GPU capabilities are not…

This. It's crazy how primitive the GPU development process still is in the year 2023. Yeah it's gotten better, but there's still a massive gap with traditional development.

Re: Intel CEO: 'The entire industry is motivated to eliminate the CUDA market'

#147

Post by rqtwteye »

ryanjshaw wrote: post #44
rbanffy wrote: post #4

Earlier quoted context omitted.

While we are at it, why not both? Also, can we move away from Windows and Office as well? And SharePoint, please? And add good search capabilities to Confluence.

I've got bad news for you. AD, Office, SharePoint, Teams, BI, etc. are becoming unified in the cloud around Power Platform. Any new business problem in a Microsoft shop is going to go with a Power Platform/Teams/SharePoint Online solution as first prize. Personally, I like it, even if it has some annoying challenges. I've not seen anything else come close in terms of rapid application development, integration and dep…

But don't forget: It's Sharepoint all the way down.

Re: Intel CEO: 'The entire industry is motivated to eliminate the CUDA market'

#148

Post by AnthonyMouse »

paulddraper wrote: post #145
AnthonyMouse wrote: post #140

Earlier quoted context omitted.

The point of the open standard is to untether your prospective customers from the incumbent. That means nobody is going to monopolize that technology anymore, but that works out fine when it's not the thing you're trying to sell -- AMD and Intel aren't trying to sell software libraries, they're trying to sell GPUs. And this strategy regularly works out for companies. It's Commoditize Your Complement. If you're Intel…

> The point of the open standard is to untether your prospective customers from the incumbent. That is the point. But FWIW the incumbent adopts it and dominates anyway. (Though you now are technically "untethered.")

> But FWIW the incumbent adopts it and dominates anyway. (Though you now are technically "untethered.")

That's assuming the incumbent's advantage isn't rooted in the lock-in.

If ML was suddenly untethered from CUDA, now you're competing on hardware. Intel would still have mediocre GPUs, but AMD's are competitive, and Intel's could be in the near future if they execute competently.

The open standard doesn't automatically give you the win, but it puts you in the ring.

And either of them have the potential to gain an advantage over Nvidia by integrating GPUs with their x86_64 CPUs, e.g. so the CPU and GPU can share memory, avoiding copying over PCIe and giving the CPU direct access to HBM. They could even put a cut down but compatible version of the technology in every commodity PC by default, giving them a huge installed base of hardware that encourages developers to target it.

Re: Intel CEO: 'The entire industry is motivated to eliminate the CUDA market'

#149

Post by TheAlchemist »

Can anybody with a deep knowledge of the AI space, explain to me what's the real moat of CUDA ?

It's clear to everybody that it's not the hardware but the software - which is the CUDA ecosystem.

I've played a bit in the past with ML, but at the level of understanding I had - training some models, tweaking things, I was using higher level libraries and as far as I know, it's pretty much an if statement in those libraries to decide which backend use.

So let's suppose Intel and others does manage to implement a viable competitor - am I wrong in thinking that the transitions for many users would be seamless ? That's probably not the case for researchers and people pushing the boundaries, but for most companies, my understanding is there would be not a lot of migration costs involved ?

Re: Intel CEO: 'The entire industry is motivated to eliminate the CUDA market'

#150

Post by nradov »

shihab wrote: post #83
lacker wrote: post #66

Earlier quoted context omitted.

The funny thing to me is that so much of the "AI software ecosystem" is just PyTorch. You don't need to develop some new framework and make it popular. You don't need to support a zillion end libraries. Just literally support PyTorch. If PyTorch worked fine on Intel GPUs, a lot of people would be happy to switch.

But you can't support Pytorch without a proper foundation in place. They don't need to support zillion _end_ libraries, sure, but they do need to have at least a very good set of standard libraries, equivalent of Cublas, Curand etc. And they don't. My work recently had me working with rocRAND (Rocm's answer to Curand). It was frankly pretty bad- the design, performance (50% slower in places that don't make any sense…

Instead of generating pseudorandom numbers you can just download files of them.

https://archive.random.org/

Post reply on HN