[all-commits] [llvm/llvm-project] c4caf9: [AArch64][MachineCombiner] Recombine long chains o...

[Jonathan Cohen via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: c4caf949aa934a219e84d4ba0530bd535e698cdb
      https://github.com/llvm/llvm-project/commit/c4caf949aa934a219e84d4ba0530bd535e698cdb
  Author: Jonathan Cohen <joncoh at apple.com>
  Date:   2025-03-23 (Sun, 23 Mar 2025)

  Changed paths:
    M llvm/include/llvm/CodeGen/MachineCombinerPattern.h
    M llvm/include/llvm/CodeGen/TargetInstrInfo.h
    M llvm/lib/CodeGen/TargetInstrInfo.cpp
    M llvm/lib/Target/AArch64/AArch64InstrInfo.cpp
    M llvm/lib/Target/AArch64/AArch64InstrInfo.h
    A llvm/test/CodeGen/AArch64/aarch64-reassociate-accumulators-sve.ll
    A llvm/test/CodeGen/AArch64/aarch64-reassociate-accumulators.ll
    A llvm/test/CodeGen/AArch64/machine-combiner-reassociate-accumulators.mir

  Log Message:
  -----------
  [AArch64][MachineCombiner] Recombine long chains of accumulation instructions into a tree to increase ILP (#126060)

This pattern shows up often in media libraries. The optimization should only
kick in for O3. Currently only supports a single family of accumulation
instructions, but can easily be expanded to support additional
instructions in the future.



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