AMD Funded a Drop-In CUDA Implementation Built on ROCm: It's Now Open-Source

Re:AMD Funded a Drop-In CUDA Implementation Built on ROCm: I... by throwawaymaths on Monday February 12, 2024 @10:04AM (#39345522)

IIRC (this could be old news) AMD GPUs are preferred in the supercomputer segment because they offer better flops/unit energy. However without a cuda-like you're missing out on the AI part of supercompute, which is increasing proportion.

The margins on supercompute-related sales are very high. Simplifying, but you can basically take a consumer chip, unlock a few things, add more memory capacity, relicense, and your margin goes up by a huge factor.

[ Parent | on HN ]

Re:AMD Funded a Drop-In CUDA Implementation Built on ROCm: I... by Symmetry on Monday February 12, 2024 @10:19AM (#39345747)

It's more that the resource balance in AMD's compute line of GPUs (the CDNA ones) has been more focused on the double precision operations that most supercomputer code makes heavy use of.

[ Parent | on HN ]

Re:AMD Funded a Drop-In CUDA Implementation Built on ROCm: I... by throwawaymaths on Monday February 12, 2024 @05:03PM (#39351166)

Thanks for clarifying! I had a feeling I had my story slightly wrong

[ Parent | on HN ]

Re:AMD Funded a Drop-In CUDA Implementation Built on ROCm: I... by anonylizard on Monday February 12, 2024 @10:39AM (#39346067)

They are preferred not because of inherent superiority of AMD GPUs. But simply because they have to price lower and have lower margins.

Nvidia could always just half their prices one day, and wipe out every non-state-funded competitor. But Nvidia prefers to collect their extreme margins and funnel it into even more R&D in AI.

[ Parent | on HN ]