[Openmp-commits] [PATCH] D94745: [OpenMP][WIP] Build the deviceRTLs with OpenMP instead of target dependent language - NOT FOR REVIEW

Shilei Tian via Phabricator via Openmp-commits openmp-commits at lists.llvm.org
Fri Jan 22 18:37:58 PST 2021


tianshilei1992 added inline comments.


================
Comment at: openmp/libomptarget/deviceRTLs/nvptx/CMakeLists.txt:24
+  return()
+endif()
+
----------------
JonChesterfield wrote:
> jdoerfert wrote:
> > we need the 32 bit versions as well, I guess?
> We could limit to 64 and see if a feature request for 32 comes in.
I agree.


================
Comment at: openmp/libomptarget/deviceRTLs/nvptx/src/target_impl.h:62
 #else
+#error "Wrong number!"
 #define MAX_SM 16
----------------
JonChesterfield wrote:
> Unintended?
Oh, yeah. I was testing whether `__CUDA_ARCH__` can be set by CUDA FE automatically but it turns out no.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D94745/new/

https://reviews.llvm.org/D94745



More information about the Openmp-commits mailing list