The intrinsics were already supported and vector.transfer_read/write lowered
direclty into these operations. By providing them as individual ops, however,
clients can used them directly, and it opens up progressively lowering transfer
operations at higher levels (rather than direct lowering to LLVM IR as done now).
Details
Details
Diff Detail
Diff Detail
- Repository
- rG LLVM Github Monorepo
Event Timeline
Comment Actions
lg
mlir/lib/Conversion/VectorToLLVM/ConvertVectorToLLVM.cpp | ||
---|---|---|
174 ↗ | (On Diff #283379) | Does a GEP without indices actually do something? |
Comment Actions
Thanks!
mlir/lib/Conversion/VectorToLLVM/ConvertVectorToLLVM.cpp | ||
---|---|---|
174 ↗ | (On Diff #283379) | It is a nop. It seemed a bit cleaner to make all memoperations use a GEPOp, but perhaps I should remove it for the non-index cases (and use the base directly). This part is subject to change anyway, since I plan to general this for the cases not handled above, and move this into core utilities perhaps. |