[all-commits] [llvm/llvm-project] eb5280: [NVPTX] Fixup AutoUpgrade of llvm.nvvm.atomic.load...

[Alex MacLean via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: eb5280938bf282053e1b3d281d45b522f1cdcc2e
      https://github.com/llvm/llvm-project/commit/eb5280938bf282053e1b3d281d45b522f1cdcc2e
  Author: Alex MacLean <amaclean at nvidia.com>
  Date:   2025-05-08 (Thu, 08 May 2025)

  Changed paths:
    M llvm/lib/IR/AutoUpgrade.cpp
    M llvm/test/Assembler/auto_upgrade_nvvm_intrinsics.ll

  Log Message:
  -----------
  [NVPTX] Fixup AutoUpgrade of llvm.nvvm.atomic.load.{inc,dec}.32 (#138907)

The previous implementation failed to account for the fact that these
intrinsics have an overloaded pointer type. This version handles the
pointer type and adds tests for llvm.nvvm.atomic.load.add.{f32,f64}.



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