search

alpaka-group / llama

A Low-Level Abstraction of Memory Access
https://llama-doc.rtfd.io/
Mozilla Public License 2.0
79 stars 10 forks source link

Add CI run for HIP #657

Open bernhardmgruber opened 1 year ago

bernhardmgruber commented 1 year ago

Currently, the CI only tests CPU targets and CUDA. We should extend it to also test compilation for AMD's HIP.

psychocoderHPC commented 1 year ago

Compile tests can be performed in the current github runners. But to test runtime CUDA and HIP must be executed in our HZDR gitlab CI.

bernhardmgruber commented 1 year ago

I am already totally fine with just compilation tests. I had a quick look into the ROCm docs and it seemed I would have to build their clang myself, so I bailed out. If you have a good resource for how to setup a HIP compilation environment, please link it here! Thx!

psychocoderHPC commented 1 year ago

I suggest using the apt repositories. If you like to build ROCm you should use spack because AMD is maintaining spack better than their documentation on how to build ROCm.

For manual build I have only an outdated script: https://gist.github.com/psychocoderHPC/0f451dbbd79ee9a15dfaf3cb8298406e