[all-commits] [llvm/llvm-project] 841327: [flang][cuda] Convert cuf.alloc for box to fir.all...

Valentin Clement (バレンタイン クレメン) via All-commits all-commits at lists.llvm.org
Fri Aug 9 13:42:13 PDT 2024


  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 841327db4ecaf5ac4703670a18f8d3edcdb91f1b
      https://github.com/llvm/llvm-project/commit/841327db4ecaf5ac4703670a18f8d3edcdb91f1b
  Author: Valentin Clement (バレンタイン クレメン) <clementval at gmail.com>
  Date:   2024-08-09 (Fri, 09 Aug 2024)

  Changed paths:
    M flang/lib/Optimizer/Transforms/CufOpConversion.cpp
    M flang/test/Fir/CUDA/cuda-allocate.fir

  Log Message:
  -----------
  [flang][cuda] Convert cuf.alloc for box to fir.alloca in device context (#102662)

In device context managed memory is not available so it makes no sense
to allocate the descriptor using it. Fall back to fir.alloca as it is
handled well in device code.
cuf.free is just dropped.



To unsubscribe from these emails, change your notification settings at https://github.com/llvm/llvm-project/settings/notifications


More information about the All-commits mailing list