llvm/torch-mlir

Add support for `AtenDivTensorOp` `AtenDivScalarOp` with integer operands

Open

#456 aperta il 2 dic 2021

Vedi su GitHub
 (1 commento) (0 reazioni) (0 assegnatari)C++ (692 fork)github user discovery
help wanted

Metriche repository

Star
 (1840 star)
Metriche merge PR
 (Metriche PR in attesa)

Descrizione

The type promotion rule for div ops are different when both operands are integers (integer operands are promoted to default float type) see https://pytorch.org/docs/stable/generated/torch.div.html.

To support this, AtenDivTensorOp and AtenDivScalarOp need to have some customized logic in RefineTypes rather than using visitBinaryBroadcastingOp or visitBinaryTensorScalarOp directly as it is now https://github.com/llvm/mlir-npcomp/blob/5475d02a0d03b2bda7ef9cc240773041d22a926b/lib/Dialect/Torch/Transforms/RefineTypes.cpp#L305-L308.

Once the changes in RefineTypes are made, the TorchToLinalg lowering code can be updated as well.

Guida contributor