[all-commits] [llvm/llvm-project] 4456f3: [AMDGPU][True16] Use COPY instead of V_MOV for non...

[Brox Chen via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 4456f31a8fcc9f9083480378662cdc50b93768fa
      https://github.com/llvm/llvm-project/commit/4456f31a8fcc9f9083480378662cdc50b93768fa
  Author: Brox Chen <guochen2 at amd.com>
  Date:   2026-03-12 (Thu, 12 Mar 2026)

  Changed paths:
    M llvm/lib/Target/AMDGPU/SIInstrInfo.cpp
    M llvm/test/CodeGen/AMDGPU/amdgcn.bitcast.1024bit.ll
    M llvm/test/CodeGen/AMDGPU/amdgcn.bitcast.512bit.ll
    M llvm/test/CodeGen/AMDGPU/amdgcn.bitcast.576bit.ll
    M llvm/test/CodeGen/AMDGPU/amdgcn.bitcast.640bit.ll
    M llvm/test/CodeGen/AMDGPU/amdgcn.bitcast.704bit.ll
    M llvm/test/CodeGen/AMDGPU/amdgcn.bitcast.768bit.ll
    M llvm/test/CodeGen/AMDGPU/amdgcn.bitcast.832bit.ll
    M llvm/test/CodeGen/AMDGPU/amdgcn.bitcast.896bit.ll
    M llvm/test/CodeGen/AMDGPU/amdgcn.bitcast.960bit.ll
    M llvm/test/CodeGen/AMDGPU/fix-sgpr-copies-f16-true16.mir
    M llvm/test/CodeGen/AMDGPU/llvm.rint.f16.ll
    M llvm/test/CodeGen/AMDGPU/llvm.sqrt.f16.ll
    M llvm/test/CodeGen/AMDGPU/llvm.trunc.f16.ll
    M llvm/test/CodeGen/AMDGPU/load-constant-i8.ll
    M llvm/test/CodeGen/AMDGPU/vector-reduce-and.ll
    M llvm/test/CodeGen/AMDGPU/vector-reduce-mul.ll
    M llvm/test/CodeGen/AMDGPU/vector-reduce-or.ll
    M llvm/test/CodeGen/AMDGPU/vector-reduce-xor.ll

  Log Message:
  -----------
  [AMDGPU][True16] Use COPY instead of V_MOV for non-imm operand in movePackToVALU lowering (#185754)

We should use COPY here for no-imm operands to reduce the number of
generated mov in the isa. However, there is an issue in
https://github.com/llvm/llvm-project/pull/162389#discussion_r2430459341
here that blocked me from doing it.

With https://github.com/llvm/llvm-project/pull/185751 this should work
now



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