torch-mlir/lib/Conversion
Sean Silva 4a0eb44d17 Add a !torch.float type.
This removes the dependence of the `torch` dialect on the low-level
builtin types.
Now the `torch` dialect is a standalone layer, suitable for targeting
from higher-level Python abstractions without any premature lowering to
primitive types.
2021-06-17 09:24:18 -07:00
..
BasicpyToStd Bump llvm-project to 12011b5217929ef8a56c2099c6f3233934ea4fbc 2021-04-27 13:12:33 -07:00
NumpyToTCF Bump llvm-project to 0524a09cc7e1a0797982feacf505825231efbee7 2021-03-23 14:29:05 -07:00
TCFToLinalg Bump llvm-project to 12011b5217929ef8a56c2099c6f3233934ea4fbc 2021-04-27 13:12:33 -07:00
TCFToStd Bump llvm-project to 12011b5217929ef8a56c2099c6f3233934ea4fbc 2021-04-27 13:12:33 -07:00
TCFToTCP Bump llvm-project to 12011b5217929ef8a56c2099c6f3233934ea4fbc 2021-04-27 13:12:33 -07:00
TorchToLinalg Add a !torch.float type. 2021-06-17 09:24:18 -07:00
TorchToStd Add `!torch.int` type. 2021-06-17 07:28:23 -07:00
CMakeLists.txt Significantly restructure torch/aten import design. 2021-05-19 13:37:39 -07:00
PassDetail.h Initial TCF/TCP E2E seed. 2020-05-08 20:20:41 -07:00
Passes.cpp Significantly restructure torch/aten import design. 2021-05-19 13:37:39 -07:00