torch-mlir/test/Dialect/TorchConversion
Yi Zhang 0cb216a1ad [Torch][Linalg] Add basic support for RNG
This PR include the following pieces:
- Add torch `Generator` type. `Generator` type is converted to i64 in
refbackend type converter.
- Add seed managment support for the default global generator.
`torch_c.getNextSeed` op is used to get the seed. On refbackend, the
`torch_c.getNextSeed` is lowered to load/store from [0] of global
variable `default_generator` memref<i64> in `InsertRngGlobals` pass.
- Add `aten.uniform_` and testing as an example op for RNG ops. Add
`torch.pseudo.aten.uniform` op. It has the same operands and return as
the `aten.uniform_` from the op registry except for value semantics.
2022-01-31 18:56:42 -05:00
..
finalizing-backend-type-conversion.mlir [Torch][Linalg] Add basic support for RNG 2022-01-31 18:56:42 -05:00
func-backend-type-conversion.mlir [Torch][Linalg] Add basic support for RNG 2022-01-31 18:56:42 -05:00
ops.mlir Move external/torch-mlir to the root of the repo. 2021-09-27 17:11:08 -07:00
verify-invariants-before-backend-lowering.mlir Move external/torch-mlir to the root of the repo. 2021-09-27 17:11:08 -07:00
verify-linalg-on-tensors-backend-contract.mlir Update llvm-project to a54f4eae0e1d0ef5adccdcf9f6c2b518dc1101aa 2021-10-18 13:36:42 -04:00
verify-tosa-backend-contract.mlir Add a basic TOSA E2E backend. 2021-10-08 09:59:45 -07:00