[PATCH] D82087: AMDGPU/clang: Add builtins for llvm.amdgcn.ballot

[Sameer Sahasrabuddhe via Phabricator via cfe-commits]

sameerds added a comment.

The documentation for HIP __ballot seems to indicate that the user does not have to explicitly specify the warp size. How is that achieved with these new builtins? Can this  be captured in a lit test here?

https://github.com/ROCm-Developer-Tools/HIP/blob/master/docs/markdown/hip_kernel_language.md#warp-vote-and-ballot-functions



================
Comment at: clang/lib/Basic/Targets/AMDGPU.cpp:288
+  if (!IsNullCPU) {
+    // Default to wave32 if available, or wave64 if not
+    if (Features.count("wavefrontsize32") == 0 &&
----------------
So the implication here is that wave32 is the preferred choice on newer architectures, and hence the default when available?


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D82087/new/

https://reviews.llvm.org/D82087