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

Nvidia bans using translation layers for CUDA software to run on other chips

tomshardware.com

Post reply on HN
Print view View original

41–50 of 179 posts

Re: Nvidia bans using translation layers for CUDA software to run on other chips

#41

Post by whatshisface »

superkuh wrote: post #5
jstanley wrote: post #4

People keep using proprietary software and keep getting burned by it. When will we learn?

What's the alternative? AMD only supports their (consumer) GPUs for ~4 years via ROCm in some instances. If you buy the card at any time except release day you only get a couple years of compute support. To answer my own question: opencl, and it's just as bad as it was in 2014. Or, slowly, people are starting to do compute with Vulkan. This might be the best way forwards even if it's an awkward choice.

Investment is not rewarded until the platform is used, which won't be until investments are made... it's a multi billion dollar chicken and egg problem that only could have been averted a decade ago by consumers refusing to be locked in to a proprietary standard.

Re: Nvidia bans using translation layers for CUDA software to run on other chips

#42

Post by bee_rider »

andersa wrote: post #8
jstanley wrote: post #4

People keep using proprietary software and keep getting burned by it. When will we learn?

There are no viable alternatives if you require high performance or even just the software to actually work properly.

Trying to best Nvidia’s language on Nvidia’s hardware seems pretty hopeless.

I wonder if that’s the wrong abstraction layer? There exists stuff like CUBLAS, which is of course using CUDA under the hood, but it also is something like a BLAS. Maybe as the AI/ML world keeps developing people will be grow more stubborn about sticking to frameworks. We probably just need a couple rounds of people getting burned by vendor lock-in, I guess.

Re: Nvidia bans using translation layers for CUDA software to run on other chips

#43

Post by samus »

laweijfmvo wrote: post #39
paulryanrogers wrote: post #22

Earlier quoted context omitted.

APIs aren't subject to copyright. So unless CUDA is more than an API they're just going to make some lawyers rich and waste everyone's time.

Making lawyers rich to waste time is how super rich companies stifle competition...

That works against small fishes, but it would be a different story if AMD or Intel take part.

Re: Nvidia bans using translation layers for CUDA software to run on other chips

#44

Post by chatmasta »

I don't understand why Nvidia is so obstinate on this front. They would solidify their lead in hardware if they open sourced the entire CUDA software stack. Their hardware competitors are going to reverse it anyway, so they may as well open source the thing and benefit from all the momentum that comes with owning the community's favored software and the hardware that it runs on.

Re: Nvidia bans using translation layers for CUDA software to run on other chips

#46

Post by segasaturn »

salawat wrote: post #15

Sounds anti-competitive af. How has this not bubbled up to the FTC for anti-trust action yet?

The FTC is not going to take action that would hurt a $2T American corporation and help Chinese hardware manufacturers/reverse engineers, no matter how valid such a case would be.

Re: Nvidia bans using translation layers for CUDA software to run on other chips

#47

Post by muragekibicho »

ronsor wrote: post #17
salawat wrote: post #15

Sounds anti-competitive af. How has this not bubbled up to the FTC for anti-trust action yet?

You can always report it to the FTC yourself, or Nvidia's competitors can sue them for antitrust violations.

Be the change you want to see in the world

Re: Nvidia bans using translation layers for CUDA software to run on other chips

#49

Post by zozbot234 »

jsheard wrote: post #28
paulryanrogers wrote: post #22

Earlier quoted context omitted.

APIs aren't subject to copyright. So unless CUDA is more than an API they're just going to make some lawyers rich and waste everyone's time.

The API may not be copyrightable, but the widely-used official libraries (cuDNN, cuBLAS, OptiX, etc) are, so in practice I think they can at least say that anything which uses those libraries can't be run on competitors hardware.

AIUI, these libraries are generally implemented as shared objects that the resulting binary has to link to. So it should be quite possible to reimplement the interface that they expose, moreover something like ROCM has to do that anyway in order to compile HIP source code from scratch. Looks like that's what https://github.com/ROCm/hipDNN/ does.

Re: Nvidia bans using translation layers for CUDA software to run on other chips

#50

Post by gjsman-1000 »

chatmasta wrote: post #44

I don't understand why Nvidia is so obstinate on this front. They would solidify their lead in hardware if they open sourced the entire CUDA software stack. Their hardware competitors are going to reverse it anyway, so they may as well open source the thing and benefit from all the momentum that comes with owning the community's favored software and the hardware that it runs on.

Exclusivity works. As much as Hacker News likes to dismiss it.
Post reply on HN