[all-commits] [llvm/llvm-project] 97a66a: [AMDGPU] Prohibit load/store merge if scale_offset...

[Stanislav Mekhanoshin via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 97a66a897caeb1445160d1862fd5b35bb5416ffb
      https://github.com/llvm/llvm-project/commit/97a66a897caeb1445160d1862fd5b35bb5416ffb
  Author: Stanislav Mekhanoshin <Stanislav.Mekhanoshin at amd.com>
  Date:   2025-07-21 (Mon, 21 Jul 2025)

  Changed paths:
    M llvm/lib/Target/AMDGPU/SILoadStoreOptimizer.cpp
    A llvm/test/CodeGen/AMDGPU/load-store-opt-scale-offset.mir

  Log Message:
  -----------
  [AMDGPU] Prohibit load/store merge if scale_offset is set on gfx1250 (#149895)

Scaling is done on the operation size, by merging instructions we
would need to generate code to scale the offset and reset the
auto-scale bit. This is unclear if that would be beneficial, just
disable such merge for now.



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