https://github.com/jhuber6 approved this pull request.
I'm not going to block this, but I think long term being divergent with CUDA code generation here is unwise. We should let both lower to the same but change the runtime calls, the runtime call then goes to `cuLaunchkernel` which expects a struct + size. https://github.com/llvm/llvm-project/pull/156229 _______________________________________________ cfe-commits mailing list cfe-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
