Details
Details
- Reviewers
kzhuravl msearles foad - Commits
- rGe7b362d75d2a: [AMDGPU] Add v_mov_b64 gfx940 opcode
Diff Detail
Diff Detail
- Repository
- rG LLVM Github Monorepo
Event Timeline
Comment Actions
Looks OK to me. I have never really understood why we have duplicate logic for expanding 64-bit vgpr copies in both copyToPhysReg and expandPostRAPseudo.
llvm/lib/Target/AMDGPU/SIInstrInfo.cpp | ||
---|---|---|
1846 | I think the setDesc should logically be inside this "if", but I guess it doesn't make any difference in practice. |
Comment Actions
One is needed for phys regs, the other was mostly created to handle and fold immediate moves (even though works with registers). So the logic isn't really duplicated, copyToPhysReg does not have immediate handling logic.
I think the setDesc should logically be inside this "if", but I guess it doesn't make any difference in practice.