Re:AMD Funded a Drop-In CUDA Implementation Built on ROCm: I...
by iforgotpassword on Monday February 12, 2024 @09:45AM
(#39345302)
Someone built the same a while ago for Intel gpus, I think even still the old pre-Xe ones. With arc/xe on the horizon, people had the same question: why isn't Intel sponsoring this or even building their own. It was speculated that this might get them into legal hot water with Nvidia, Google VS. Oracle was brought up, etc...
[ Parent
| on HN ]
Re:AMD Funded a Drop-In CUDA Implementation Built on ROCm: I...
by my123 on Monday February 12, 2024 @09:46AM
(#39345317)
They financed the prior iteration of Zluda: https://github.com/vosen/ZLUDA?tab=readme-ov-file#faq
but then stopped
Re:AMD Funded a Drop-In CUDA Implementation Built on ROCm: I...
by formerly_proven on Monday February 12, 2024 @09:55AM
(#39345409)
> [2021] After some deliberation, Intel decided that there is no business case for running CUDA applications on Intel GPUs.
oof
Re:AMD Funded a Drop-In CUDA Implementation Built on ROCm: I...
by Cheer2171 on Monday February 12, 2024 @10:43AM
(#39346116)
Are you freaking kidding me!?!? Fire those MBAs immediately.
Re:AMD Funded a Drop-In CUDA Implementation Built on ROCm: I...
by AtheistOfFail on Monday February 12, 2024 @10:20AM
(#39345753)
> After two years of development and some deliberation, AMD decided that there is no business case for running CUDA applications on AMD GPUs.
Oof x2
Re:AMD Funded a Drop-In CUDA Implementation Built on ROCm: I...
by iforgotpassword on Monday February 12, 2024 @10:16AM
(#39345692)
That's an oof indeed. Are AMD and Intel really that delusional, ie "once we get our own version of Cuda right everybody will just rewrite all their software to make use of it", or do they know something we mere mortals don't?
Re:AMD Funded a Drop-In CUDA Implementation Built on ROCm: I...
by garaetjjte on Monday February 12, 2024 @10:34AM
(#39345973)
Maybe their lawyers are afraid of another round of "are APIs copyrightable"?