[all-commits] [llvm/llvm-project] eb0d61: [LoongArch] Optimize 128-to-256-bit vector inserti...

[hev via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: eb0d61af6e5ede942365c0e4760a75e0e725d388
      https://github.com/llvm/llvm-project/commit/eb0d61af6e5ede942365c0e4760a75e0e725d388
  Author: hev <wangrui at loongson.cn>
  Date:   2025-07-11 (Fri, 11 Jul 2025)

  Changed paths:
    M llvm/lib/Target/LoongArch/LoongArchISelLowering.cpp
    M llvm/lib/Target/LoongArch/LoongArchISelLowering.h
    M llvm/lib/Target/LoongArch/LoongArchLASXInstrInfo.td
    M llvm/test/CodeGen/LoongArch/lasx/concat-vectors.ll
    M llvm/test/CodeGen/LoongArch/lasx/insert-extract-subvector.ll
    M llvm/test/CodeGen/LoongArch/lasx/issue107355.ll

  Log Message:
  -----------
  [LoongArch] Optimize 128-to-256-bit vector insertion and 256-to-128-bit subvector extraction (#146300)

This patch replaces stack-based accesses with register moves when
converting between 128-bit and 256-bit vectors. A 128-bit subvector
extract from, or insert to, the lower half of a 256-bit vector is now
treated as a subregister copy that needs no instruction.

Fixes #147769



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