[PATCH] D80917: [OpenMP][AMDGCN] Support OpenMP offloading for AMDGCN architecture - Part 2

[Jon Chesterfield via Phabricator via llvm-commits]

JonChesterfield added inline comments.


================
Comment at: llvm/include/llvm/Frontend/OpenMP/OMPGridValues.h:66
+  /// for NVPTX.
+  GV_Warp_Size_32,
+  /// The number of bits required to represent the max number of threads in warp
----------------
What's the point of warp_size_32? It's always set to 32 and seems redundant with warp_size


================
Comment at: llvm/include/llvm/Frontend/OpenMP/OMPGridValues.h:68
+  /// The number of bits required to represent the max number of threads in warp
+  GV_Warp_Size_Log2,
+  /// GV_Warp_Size * GV_Slot_Size,
----------------
log2 of a compile time constant would be computed at compile time, we don't need this field


================
Comment at: llvm/include/llvm/Frontend/OpenMP/OMPGridValues.h:76
+  /// (~0u >> (GV_Warp_Size - GV_Warp_Size_Log2))
+  GV_Warp_Size_Log2_Mask,
+  // An alternative to the heavy data sharing infrastructure that uses global
----------------
As above, this can be computed at compile time, e.g. from that expression


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D80917/new/

https://reviews.llvm.org/D80917