[all-commits] [llvm/llvm-project] 0ef231: [AMDGPU] Re-enable closed-world assumption as an o...

[Shilei Tian via All-commits]

  Branch: refs/heads/users/shiltian/closed-world-assumption-opt-in-by-default
  Home:   https://github.com/llvm/llvm-project
  Commit: 0ef2313eecc010403c0fd293dd2b931856a8d4e8
      https://github.com/llvm/llvm-project/commit/0ef2313eecc010403c0fd293dd2b931856a8d4e8
  Author: Shilei Tian <i at tianshilei.me>
  Date:   2024-11-07 (Thu, 07 Nov 2024)

  Changed paths:
    M llvm/lib/Target/AMDGPU/AMDGPUAttributor.cpp
    M llvm/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp
    A llvm/test/LTO/AMDGPU/closed-world-assumption.ll

  Log Message:
  -----------
  [AMDGPU] Re-enable closed-world assumption as an opt-out feature

Although the ABI (if any exists) doesn’t explicitly prohibit cross-device-image
function calls, especially since our loader can handle them, for all officially
supported programming models, this is not actually allowed. Given this, assuming
a closed-world model at link time is safe. However, there are certain cases,
such as the GPU libc project, that use non-standard approaches which could break
this assumption. This PR introduces an option to disable this assumption when
needed.



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