[all-commits] [llvm/llvm-project] a3ccae: [flang][cuda] Allocate local descriptor in managed...

[Valentin Clement (バレンタイン クレメン) via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: a3ccaed3b9f6a1fe9b7f2ef019259f88072639b2
      https://github.com/llvm/llvm-project/commit/a3ccaed3b9f6a1fe9b7f2ef019259f88072639b2
  Author: Valentin Clement (バレンタイン クレメン) <clementval at gmail.com>
  Date:   2024-08-06 (Tue, 06 Aug 2024)

  Changed paths:
    A flang/include/flang/Runtime/CUDA/descriptor.h
    M flang/lib/Optimizer/Transforms/CufOpConversion.cpp
    M flang/runtime/CUDA/CMakeLists.txt
    A flang/runtime/CUDA/descriptor.cpp
    M flang/test/Fir/CUDA/cuda-allocate.fir
    M flang/unittests/Runtime/CUDA/AllocatorCUF.cpp

  Log Message:
  -----------
  [flang][cuda] Allocate local descriptor in managed memory (#102060)

This patch adds entry point in the runtime to be able to allocate
descriptors in managed memory. These entry points currently only call
`CUFAllocManaged` and `CUFFreeManaged` but could be more complicated in
the future.

`cuf.alloc` and `cuf.free` related to local descriptors are converted
into runtime calls.



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