mirror of https://github.com/llvm/torch-mlir
0cb216a1ad
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. |
||
---|---|---|
.. | ||
finalizing-backend-type-conversion.mlir | ||
func-backend-type-conversion.mlir | ||
ops.mlir | ||
verify-invariants-before-backend-lowering.mlir | ||
verify-linalg-on-tensors-backend-contract.mlir | ||
verify-tosa-backend-contract.mlir |