[PATCH] D112053: [cuda] Add address space predicate funuctions.

Artem Belevich via Phabricator via cfe-commits cfe-commits at lists.llvm.org
Tue Oct 19 11:27:50 PDT 2021


tra accepted this revision.
tra added a comment.
This revision is now accepted and ready to land.

LGTM in general.



================
Comment at: clang/include/clang/Basic/BuiltinsNVPTX.def:691-694
+BUILTIN(__nvvm_isspacep_const, "bvC*", "nc")
+BUILTIN(__nvvm_isspacep_global, "bvC*", "nc")
+BUILTIN(__nvvm_isspacep_local, "bvC*", "nc")
+BUILTIN(__nvvm_isspacep_shared, "bvC*", "nc")
----------------
CUDA appears to be using `__nv_isGlobal_impl` for the AS predicates. Perhaps we want to add those, too, forwarding them to the `__nvvm_...` implementations above. I've already added a few other AS-related `__nv_*` builtins in `lib/Headers/__clang_cuda_intrinsics.h`.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D112053/new/

https://reviews.llvm.org/D112053



More information about the cfe-commits mailing list