[all-commits] [llvm/llvm-project] 85f8bd: [NVPTX] Combine addressing-mode variants of ld, st...

[Alex MacLean via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 85f8bd111f0553699baa7ec8ea396a373497cf45
      https://github.com/llvm/llvm-project/commit/85f8bd111f0553699baa7ec8ea396a373497cf45
  Author: Alex MacLean <amaclean at nvidia.com>
  Date:   2025-02-27 (Thu, 27 Feb 2025)

  Changed paths:
    M llvm/lib/Target/NVPTX/NVPTXISelDAGToDAG.cpp
    M llvm/lib/Target/NVPTX/NVPTXISelDAGToDAG.h
    M llvm/lib/Target/NVPTX/NVPTXInstrInfo.td
    M llvm/lib/Target/NVPTX/NVPTXIntrinsics.td
    M llvm/lib/Target/NVPTX/NVPTXReplaceImageHandles.cpp
    M llvm/test/CodeGen/MIR/NVPTX/expected-floating-point-literal.mir
    M llvm/test/CodeGen/MIR/NVPTX/floating-point-immediate-operands.mir
    M llvm/test/CodeGen/MIR/NVPTX/floating-point-invalid-type-error.mir

  Log Message:
  -----------
  [NVPTX] Combine addressing-mode variants of ld, st, wmma (#129102)

This change fold together the _ari, _ari64, and _asi variants of these
instructions into a single instruction capable of holding any address.
This allows for the removal of a lot of unnecessary code and moves us
towards a standard way of representing an address in NVPTX.



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