andykaylor wrote: BTW, I think this is the first PR upstreaming CUDA support. Taking off my "open-source developer" hat for a moment and putting on my "NVIDIA employee" hat, I'd like to mention that my review of CUDA support PRs should not be construed as NVIDIA's endorsement of the Clang implementation of CUDA. There are some incompatibilities between Clang's implementation of CUDA and CUDA as it is supported in NVIDIA's compilers.
https://github.com/llvm/llvm-project/pull/177790 _______________________________________________ cfe-commits mailing list [email protected] https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
