[all-commits] [llvm/llvm-project] 0b31f0: [flang][cuda] Add support for NV_CUDAFOR_DEVICE_IS...

Valentin Clement (バレンタイン クレメン) via All-commits all-commits at lists.llvm.org
Mon Mar 31 13:17:43 PDT 2025


  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 0b31f08537746beff4d5e0df44221cbe5a9237c5
      https://github.com/llvm/llvm-project/commit/0b31f08537746beff4d5e0df44221cbe5a9237c5
  Author: Valentin Clement (バレンタイン クレメン) <clementval at gmail.com>
  Date:   2025-03-31 (Mon, 31 Mar 2025)

  Changed paths:
    M flang-rt/include/flang-rt/runtime/environment.h
    M flang-rt/lib/cuda/allocator.cpp
    M flang-rt/lib/cuda/memory.cpp
    M flang-rt/lib/runtime/environment.cpp

  Log Message:
  -----------
  [flang][cuda] Add support for NV_CUDAFOR_DEVICE_IS_MANAGED (#133778)

Add support for the environment variable `NV_CUDAFOR_DEVICE_IS_MANAGED`
as described in the documentation:
https://docs.nvidia.com/hpc-sdk/compilers/cuda-fortran-prog-guide/index.html#controlling-device-data-is-managed.

This mainly switch device allocation to managed allocation.



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