[all-commits] [llvm/llvm-project] 654b76: [flang][cuda] Allow to set the stack limit size (#...

[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: 654b76321a602db4d68734e9fd11efbb7d8eb617
      https://github.com/llvm/llvm-project/commit/654b76321a602db4d68734e9fd11efbb7d8eb617
  Author: Valentin Clement (バレンタイン クレメン) <clementval at gmail.com>
  Date:   2025-01-28 (Tue, 28 Jan 2025)

  Changed paths:
    M flang/CMakeLists.txt
    M flang/include/flang/Optimizer/Builder/Runtime/Main.h
    A flang/include/flang/Runtime/CUDA/init.h
    M flang/lib/Lower/Bridge.cpp
    M flang/lib/Optimizer/Builder/Runtime/Main.cpp
    M flang/runtime/CUDA/CMakeLists.txt
    A flang/runtime/CUDA/init.cpp
    M flang/runtime/environment.cpp
    M flang/runtime/environment.h

  Log Message:
  -----------
  [flang][cuda] Allow to set the stack limit size (#124859)

This patch adds a call to the CUFInit function just after `ProgramStart`
when CUDA Fortran is enabled to initialize the CUDA context. This allows
us to set up some context information like the stack limit that can be
defined by an environment variable `ACC_OFFLOAD_STACKSIZE=<value>`.



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