Hacker News Reader

Comment by causality0 | Hacker News Reader

Don't forget the drivers. As someone who just switched from Nvidia to AMD, it is downright painful how bad AMD's implementations of Vulkan and OpenGL are. I might be getting more bang for my buck but damn do I miss not having unfixable glitches.

View on HN

AMD is good at being the underdog, hopefully it will focus more on its software, the ROCm thing, which really needs some love, a lot of love indeed. The software ecosystem for AMD's RDNA(gpu) and CDNA(MI2xx MI300) is at its best a mess.

AMD shall own OpenCL and boost it heavily and make it a central piece for its ROCm framework as the preferred backend, in my opinion.

No one cares about OpenCL and its C only programming model.

OpenCL is deprecated.

Apple has ditched it for metal. AMD has ditched it for ROCm which is just a AMD compiler for CUDA PTX.

ROCm does not compile PTX IR to AMD assembly, if it did you'd be able to run nearly any compiled CUDA program on and AMD GPU without the source. ROCm is a source level compiler for CUDA (technically HIP is the actual compiler, but whatever), it allows you to a substantial fraction of the CUDA APIs. This notably also means that any Nvidia open source library that uses inline PTX assembly won't work, but fortunately AMD does have alternatives to many of the Nvidia libraries.

it's not, Nvidia just added support to OpenCL 3.0, AMD also continues to support it. Apple always does things its own way.

OpenCL 3.0 is basically OpenCL 1.0 rebranded, hence why NVidia didn't had any issue adding support for what they already had anyway.

both OneAPI and ROCm are, or should, or could provide higher level APIs to isolate you from OpenCL's C APIs, or just leverage SPIR-V. Other than CUDA, I failed to see any other open alternatives to get heterogeneous computing working yet, OpenCL is the only one on the table as far as I can tell for now. Yes there are Vulkan compute shader etc but they're still pretty far behind, and they could be made OpenCL compatible too. While CUDA is great, OpenCL can be made by OneAPI and ROCm more open source friendly, I hope.

C APIs are one half of the coin, the other being what is actually running on the GPU.

OneAPI is focused on C++, and it remains to be seen if Data Parallel C++ isn't also Intel's CUDA, even if based on SYCL.

SPIR so far has hardly got any adoption to the level of PTX, regarding polyglot compute.

OpenCL works. Give me anything that works, and I can wrap around it if I don't like the interface it provides, and still use it because it works.

It needs a bit more than that to gain adoption.

Reply on news.ycombinator.com