torch-mlir/lib/Conversion/TorchToLinalg
Stella Laurenzo 00efec0b73
[linalg] Implement strict mode lowering for aten.view. (#3319)
* Enables assume_strict_symbolic_shapes on fx_importer imported
programs, indicating strict shape semantics.
* Reworks the view->reshape lowering to take advantage of strict mode
and do one of:
  * Collapse to 0D
  * Flatten/Unflatten when there is an inferred dim.
  * Fallback to tensor.reshape
* Splits some test cases up and adds an attribute to control the old
pattern (so new corners can be tested in strict mode in isolation).
* Dynamic inferred mode needs upstream work to generalize expand_shape
(so that case is suppressed here).
* Deletes the assert from the existing tensor.reshape lowering if strict
shape mode is enabled (since the condition it is dynamically asserting
cannot happen).
2024-05-10 13:45:50 -07:00
..
CMakeLists.txt Re-organize project structure to separate PyTorch dependencies from core project. (#2542) 2023-11-02 19:45:55 -07:00
DataMovement.cpp [linalg] Implement strict mode lowering for aten.view. (#3319) 2024-05-10 13:45:50 -07:00
IndirectDataMovement.cpp Fix deprecated uses of cast/dyn_cast/dyn_cast_or_null/isa (#3243) 2024-04-27 14:00:56 -07:00
Linear.cpp [TorchToLinalg] Adds Quantization Support for ConvTranspose (#3240) 2024-04-30 09:23:09 -07:00
Pooling.cpp MaxPool1d lowering to linalg (#3295) 2024-05-10 22:05:26 +05:30
PopulatePatterns.h Re-enable custom op support 2022-08-16 22:49:08 +05:30
Random.cpp Fix deprecated uses of cast/dyn_cast/dyn_cast_or_null/isa (#3243) 2024-04-27 14:00:56 -07:00
Reduction.cpp Fix deprecated uses of cast/dyn_cast/dyn_cast_or_null/isa (#3243) 2024-04-27 14:00:56 -07:00
TensorConstructors.cpp Fix deprecated uses of cast/dyn_cast/dyn_cast_or_null/isa (#3243) 2024-04-27 14:00:56 -07:00
TensorScalarInterop.cpp Fix deprecated uses of cast/dyn_cast/dyn_cast_or_null/isa (#3243) 2024-04-27 14:00:56 -07:00
TorchToLinalg.cpp [torch-mlir][sparse] recognize sparse tensor conversion (#3226) 2024-04-26 02:32:07 +08:00
Uncategorized.cpp [onnx] Gridsampler addition of nearest mode (#3320) 2024-05-10 11:42:10 -07:00
Utils.cpp Fix deprecated uses of cast/dyn_cast/dyn_cast_or_null/isa (#3243) 2024-04-27 14:00:56 -07:00