Stephan Herhut 5d9f33aaa0 [MLIR][Shape] Add conversion for missing ops to standard ...

This adds conversions for const_size and to_extent_tensor. Also, cast-like operations are now folded away if the source and target types are the same.

Differential Revision: https://reviews.llvm.org/D84745

2020-07-29 12:46:18 +02:00

..

IR

[MLIR][Shape] Add conversion for missing ops to standard

2020-07-29 12:46:18 +02:00

Transforms

[MLIR][Shape] Support transforming shape.num_elements on tensors

2020-07-28 14:13:06 +02:00

CMakeLists.txt

Revert "Revert "[MLIR] Lower shape.num_elements -> shape.reduce.""

2020-06-08 12:19:54 +02:00