News for hackers. Stuff that matters.
Re:CUDA vs. ROCm: A Case Study by throwaway81523 on Wednesday December 20, 2023 @04:38AM (#38706879)
In these CUDA vs ROCm comparisons I think they mostly compare the C++ dialects. And it's not even particularly the language implementation where ROCm is weak, but rather, the whole tool chain. Am I mistaken?
Re:CUDA vs. ROCm: A Case Study by pjmlp on Wednesday December 20, 2023 @05:34AM (#38707191)
Which is why it will never be a CUDA replacement, for most C++ users maybe, for the whole ecosystem definitly not.
Re:CUDA vs. ROCm: A Case Study by throwaway81523 on Wednesday December 20, 2023 @02:25PM (#38712523)
Well the C++ segment is important and from what I gather, ROCm is failing at that. AMD would be a lot better off if the C++ part worked, even if the other parts don't.
Re:CUDA vs. ROCm: A Case Study by pjmlp on Wednesday December 20, 2023 @04:31PM (#38713909)
True, not even that works that well.