This makes tf-opt more strict on the dialect dependencies, and immediately reduces
the number of dialects loaded.
The canonicalization of TensorFlow graphs showed on the profile that Linalg pattern
were dominated the time, which is unexpected since Linalg is not even intended to be
used there.
PiperOrigin-RevId: 364087027
- Introduce operations in a new lmhlo_gpu dialect that map to GPU library function calls
in the XLA:GPU backend.
- Add basic unit tests as well.
PiperOrigin-RevId: 337132166
Imported from GitHub PR https://github.com/tensorflow/tensorflow/pull/42473
Adds a call to mlir_check_all_link_libraries() to check all libraries
linked into mlir-hlo-opt.
Copybara import of the project:
--
0bf620f5f2708e730689eab8a5512fb00eaf1706 by Marius Brehler <marius.brehler@iml.fraunhofer.de>:
Check libraries linked into mlir-hlo-opt
Adds a call to mlir_check_all_link_libraries() to check all libraries
linked into mlir-hlo-opt.
COPYBARA_INTEGRATE_REVIEW=https://github.com/tensorflow/tensorflow/pull/42473 from marbre:check_link_libraries 0bf620f5f2708e730689eab8a5512fb00eaf1706
PiperOrigin-RevId: 327463012
Shuffle files around, use TableGen to register passes, and introduce
a `mlir-hlo-opt.cpp` file to hold the main entry point of the -opt tool
and stop relying on static registration for dialect/passes.
PiperOrigin-RevId: 323674455