torch-mlir/projects/ltc/csrc/base_lazy_backend
Stella Laurenzo 606dc45896 Get LTC building. 2023-11-18 17:56:00 -08:00
..
ops Initial moves 2023-11-18 17:25:16 -08:00
utils Initial moves 2023-11-18 17:25:16 -08:00
CMakeLists.txt Get LTC building. 2023-11-18 17:56:00 -08:00
README.md Initial moves 2023-11-18 17:25:16 -08:00
backend_impl.cpp Initial moves 2023-11-18 17:25:16 -08:00
backend_impl.h Initial moves 2023-11-18 17:25:16 -08:00
dynamic_ir.cpp Initial moves 2023-11-18 17:25:16 -08:00
dynamic_ir.h Initial moves 2023-11-18 17:25:16 -08:00
ir_builder.h Initial moves 2023-11-18 17:25:16 -08:00
mlir_lowering_context.cpp Get LTC building. 2023-11-18 17:56:00 -08:00
mlir_lowering_context.h Initial moves 2023-11-18 17:25:16 -08:00
mlir_native_functions.cpp Initial moves 2023-11-18 17:25:16 -08:00
mlir_node.cpp Initial moves 2023-11-18 17:25:16 -08:00
mlir_node.h Initial moves 2023-11-18 17:25:16 -08:00
mlir_node_lowering.cpp Initial moves 2023-11-18 17:25:16 -08:00
mlir_node_lowering.h Initial moves 2023-11-18 17:25:16 -08:00
shape_inference.cpp Initial moves 2023-11-18 17:25:16 -08:00
tensor.cpp Initial moves 2023-11-18 17:25:16 -08:00
tensor.h Initial moves 2023-11-18 17:25:16 -08:00

README.md

Torch-MLIR Lazy Tensor Core Backend

Detailed Documentation

Detailed documentation about the architecture of this LTC backend is available here.

Summary

Contained within this directory are the components that implements the Torch-MLIR LTC backend. Note that the code style for LTC components is consistent with that of LTC itself, rather than the rest of Torch-MLIR.

The components are subclasses of the backend API interface classes found under torch/csrc/lazy/backend.

Importantly, the subclasses are still abstract classes. Pure virtual methods such as Compile were purposefully not overridden as Torch-MLIR does not know how to compile the model for the target hardware.

The intent is that vendor hardware specific plugins will subclass the Torch-MLIR backend classes and override the remaining pure virtual functions to complete the backend.

The Torch-MLIR LTC backend's job is to perform the lowering from ATen to MLIR. A hardware vendor's backend job is to take care of the actual compile and execution of the lowered MLIR.