- 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
Rahul Joshi
Mehdi Amini
A. Unique TensorFlower
Marius Brehler
Jacques Pienaar