[all-commits] [llvm/llvm-project] 1df4af: Reapply "[AArch64][SVE] Pair SVE fill/spill into L...

[Ricardo Jesus via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 1df4af6cbcc3bda86fa76b9aba01424ab39077a4
      https://github.com/llvm/llvm-project/commit/1df4af6cbcc3bda86fa76b9aba01424ab39077a4
  Author: Ricardo Jesus <rjj at nvidia.com>
  Date:   2025-04-14 (Mon, 14 Apr 2025)

  Changed paths:
    M llvm/lib/Target/AArch64/AArch64InstrInfo.cpp
    M llvm/lib/Target/AArch64/AArch64LoadStoreOptimizer.cpp
    A llvm/test/CodeGen/AArch64/aarch64-sve-fill-spill-pair.ll
    A llvm/test/CodeGen/AArch64/sve-vls-ldst-opt.mir

  Log Message:
  -----------
  Reapply "[AArch64][SVE] Pair SVE fill/spill into LDP/STP with -msve-vector-bits=128." (#135177)

Reapplies #134068.

The first patch was missing a check to prevent attempts to pair SVE
fill/spill with other Neon load/store instructions, which could happen
specifically if the Neon instruction was unscaled.



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