mirror of https://github.com/llvm/torch-mlir
1e357ae680
Currently implemented as a simple intraprocedural dataflow analysis over a standard ShapedType lattice (hasRank, sizes, and elementType). It currently hardcodes a few key pieces of information: - shape transfer functions - whether it is legal to update the operand type of an op This needs to be made pluggable obviously and the core propagation logic moved somewhere agnostic. |
||
---|---|---|
.. | ||
Backend/Iree | ||
CAPI | ||
Conversion | ||
Dialect | ||
Python | ||
RefBackend | ||
npcomp-run-mlir | ||
CMakeLists.txt | ||
lit.cfg.py | ||
lit.site.cfg.py.in |