[all-commits] [llvm/llvm-project] 4af885: [AArch64] Fix performZExtUZPCombine() DAG combine ...

[Gaëtan Bossu via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 4af885c0c13c0cf1fe9aee554634020d801b4999
      https://github.com/llvm/llvm-project/commit/4af885c0c13c0cf1fe9aee554634020d801b4999
  Author: Gaëtan Bossu <gaetan.bossu at arm.com>
  Date:   2026-03-02 (Mon, 02 Mar 2026)

  Changed paths:
    M llvm/lib/Target/AArch64/AArch64ISelLowering.cpp
    M llvm/test/CodeGen/AArch64/zext-shuffle.ll

  Log Message:
  -----------
  [AArch64] Fix performZExtUZPCombine() DAG combine (#183765)

This used to look through all extract_subvector nodes, including those
extracting a fixed vector from a scalable one. One consequence is that
we could end up generating a NVCAST from a scalable vector to a fixed
one, even when vscale was unknown.



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