Joseph Huber

> Is there any flags I should add besides maybe those: > > ``` > build:clang --@rules_cuda//cuda:compiler='clang' > build:clang --@rules_cuda//cuda:archs=compute_61:compute_61,sm_61 > build:clang --@rules_cuda//cuda:runtime=@local_cuda//:cuda_runtime_static > build:clang --@rules_cuda//cuda:copts='-stdlib=libc++' > ``` > >...

Does the tool `./bin/nvptx-arch` return anything? Pretty good litmus for if we're detecting the GPU and runtime correctly at all.

> @hypdeb Could you please try `--repo_env=CC=clang`? I am not sure how it goes if you mix gcc as cc compiler and clang as cuda compiler If we're doing `-fno-gpu-rdc`...

https://github.com/llvm/llvm-project/commit/0f6ef9bc2a14be0a5fdb0d05fc6bb2d5474bf0c6