[PATCH] D104316: [AMDGPU] Propagate LDS align into to instructions
Mahesha S via Phabricator via llvm-commits
llvm-commits at lists.llvm.org
Mon Jun 21 22:28:58 PDT 2021
hsmhsm added inline comments.
================
Comment at: llvm/lib/Target/AMDGPU/AMDGPULowerModuleLDSPass.cpp:324
+ uint64_t Off = DL.getStructLayout(LDSTy)->getElementOffset(I);
+ Align A = commonAlignment(MaxAlign, Off);
+ refineUsesAlignment(GEP, A, DL);
----------------
Did not understand the logic behind calling commonAlignment() here. I thought, alignment of GV and GEP are same, and we just need to propogate the alignment of GV? Because, we already have properly updated the alignment of GV?
================
Comment at: llvm/lib/Target/AMDGPU/AMDGPULowerModuleLDSPass.cpp:374
+ Align GA = commonAlignment(A, Off.getLimitedValue());
+ refineUsesAlignment(GEP, GA, DL, MaxDepth - 1);
+ }
----------------
In case of GEP instruction, I thought, we should be exploring the uses of GEP?
================
Comment at: llvm/lib/Target/AMDGPU/AMDGPULowerModuleLDSPass.cpp:381
+ I->getOpcode() == Instruction::AddrSpaceCast)
+ refineUsesAlignment(I, A, DL, MaxDepth - 1);
+ }
----------------
Same here, in case of bitcast instruction, I thought, we should be exploring uses of bitcast?
CHANGES SINCE LAST ACTION
https://reviews.llvm.org/D104316/new/
https://reviews.llvm.org/D104316
More information about the llvm-commits
mailing list