mlir-hlo/lib/Dialect/mhlo
Jacques Pienaar 95ba03534f Allow variadic operands/result in MHLO while
This just adds support for it in the op, but keeps the production/uses as is (e.g., single tensor or tuple) matching what XLA export requires. In follow up here, would be to add pass for export to retuple and then the canonical form could be changed. Tuple'ing given control flow via regions & multi-result operations does not add representational power and all the get_tuple_element ops obscure the computation.

The old form allowed single tensor or tuple. The new variadic number of tensor or tuples as tuples may be nested, so the input could have (Tensor<..>, Tuple<Tensor<...>, Tuple<...>, ...>, Tensor<...>) and HLO_Tensor doesn't allow Tuples.

PiperOrigin-RevId: 378934388
2021-06-11 13:08:28 -07:00
..
IR PR #50100: [MLIR][DISC] Bufferize DynamicIotaOp and DynamicPadOp 2021-06-10 14:20:45 -07:00
transforms Allow variadic operands/result in MHLO while 2021-06-11 13:08:28 -07:00
CMakeLists.txt Add CMake files and lit configurations, enough for `ninja check-mlir-hlo` to pass on all the tests 2020-08-07 22:14:34 -07:00