[all-commits] [llvm/llvm-project] b73771: [AArch64] Increase scatter overhead on Neoverse-V2...

[Madhur Amilkanthwar via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: b73771cf0fc49675ee850d197a6e56a0e8b90cae
      https://github.com/llvm/llvm-project/commit/b73771cf0fc49675ee850d197a6e56a0e8b90cae
  Author: Madhur Amilkanthwar <madhura at nvidia.com>
  Date:   2024-08-14 (Wed, 14 Aug 2024)

  Changed paths:
    M llvm/lib/Target/AArch64/AArch64Subtarget.cpp
    M llvm/lib/Target/AArch64/AArch64Subtarget.h
    M llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
    A llvm/test/Transforms/LoopVectorize/AArch64/scatter-cost.ll

  Log Message:
  -----------
  [AArch64] Increase scatter overhead on Neoverse-V2 (#101296)

This patch increases scatter overhead on Neoverse-V2 to 13. This
benefits s128 kernel from TSVC_2 test suite.
SPEC 17, RAJAPerf, and Sptter are unaffected by this patch.

This patch boosts s128 kernel's performance from TSVC test suite by about
40% as this enables vectorization. Also, handle minor code refactoring
for gather related part.



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