[all-commits] [llvm/llvm-project] a88d58: [NVPTX] Pull invariant load identification into IR...

[Alex MacLean via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: a88d580860b88bbb02797bae95032b6eb0c4579c
      https://github.com/llvm/llvm-project/commit/a88d580860b88bbb02797bae95032b6eb0c4579c
  Author: Alex MacLean <amaclean at nvidia.com>
  Date:   2025-05-01 (Thu, 01 May 2025)

  Changed paths:
    M llvm/lib/Target/NVPTX/CMakeLists.txt
    M llvm/lib/Target/NVPTX/NVPTX.h
    M llvm/lib/Target/NVPTX/NVPTXISelDAGToDAG.cpp
    M llvm/lib/Target/NVPTX/NVPTXPassRegistry.def
    A llvm/lib/Target/NVPTX/NVPTXTagInvariantLoads.cpp
    M llvm/lib/Target/NVPTX/NVPTXTargetMachine.cpp
    A llvm/test/CodeGen/NVPTX/byval-const-global.ll
    A llvm/test/CodeGen/NVPTX/tag-invariant-loads.ll

  Log Message:
  -----------
  [NVPTX] Pull invariant load identification into IR pass (#138015)

Pull invariant load identification, which was previously part of
DAGToDAG ISel, into a new IR pass NVPTXTagInvariantLoads. This makes it
possible to disable this optimization at O0 and reduces the complexity
of the SelectionDAG pass. Moving this logic to an IR pass also allows
for implementing a more powerful traversal in the future.

Fixes https://github.com/llvm/llvm-project/issues/138138



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