News for hackers. Stuff that matters.
Re:AMD Instinct MI300 Data Center APU – 146B Transistors, Sh... by brucethemoose2 on Wednesday March 01, 2023 @02:50AM (#34979814)
Arch is packaging ROCm natively in testing, and PyTorch has official-ish builds of it now (and maybe Arch will build it too).

But you should also check out MLIR which, for instance, is used very sucessfully here and is benching way faster than rocm: https://github.com/nod-ai/SHARK/

Re:AMD Instinct MI300 Data Center APU – 146B Transistors, Sh... by bayindirh on Wednesday March 01, 2023 @09:09AM (#34982543)
Debian also has a lot of ROCm related packages from base library to software packages. Looks like AMD is in a push for making it widely available and easy to work with.
Re:AMD Instinct MI300 Data Center APU – 146B Transistors, Sh... by pclmulqdq on Wednesday March 01, 2023 @11:18AM (#34984041)
I think we should clarify that this push is for making it easy to use, not to develop. They are trying to capture the python-based ML community, but care a lot less about people who actually want to write code in ROCm than Nvidia cares about CUDA coders.
Re:AMD Instinct MI300 Data Center APU – 146B Transistors, Sh... by brucethemoose2 on Wednesday March 01, 2023 @12:49PM (#34985607)
And the datacenter cards (which are even less accessible than an A100) are still the first class citizens, while CUDA performance on the desktop cards is quite excellent.