[PATCH] D91336: AMDGPU/GlobalISel: Fix negative offset folding for buffer_load

[Petar Avramovic via Phabricator via llvm-commits]

Petar.Avramovic added inline comments.


================
Comment at: llvm/lib/Target/AMDGPU/AMDGPURegisterBankInfo.cpp:1375
 
   // Handle the variable sgpr + vgpr case.
+  MachineInstr *Add = getOpcodeDef(AMDGPU::G_ADD, CombinedOffset, *MRI);
----------------
foad wrote:
> The DAG version of setBufferOffsets doesn't have this case. Is it done later on when the register classes are known?
SDAG just gives up and uses add as base (1 extra instruction compared to what global-isel does). See `@s_buffer_load_f32_offset_add_vgpr_sgpr` in `GlobalISel/llvm.amdgcn.s.buffer.load.ll` for example.


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D91336/new/

https://reviews.llvm.org/D91336