[all-commits] [llvm/llvm-project] 52ff71: [AMDGPU] Use S_MOV_B64_IMM_PSEUDO when moving 64-b...

[Arseniy Obolenskiy via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 52ff7167af07c3173e0dddebba8c5cf288d45d71
      https://github.com/llvm/llvm-project/commit/52ff7167af07c3173e0dddebba8c5cf288d45d71
  Author: Arseniy Obolenskiy <arseniy.obolenskiy at amd.com>
  Date:   2026-06-01 (Mon, 01 Jun 2026)

  Changed paths:
    M llvm/lib/Target/AMDGPU/SIFixSGPRCopies.cpp
    M llvm/test/CodeGen/AMDGPU/vgpr_constant64_to_sgpr.mir

  Log Message:
  -----------
  [AMDGPU] Use S_MOV_B64_IMM_PSEUDO when moving 64-bit VGPR const to SGPR (#200576)

S_MOV_B64 only encodes a 32-bit literal, so rematerializing a non-inline
64-bit immediate through it silently dropped the high 32 bits



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