mirror of https://github.com/llvm/torch-mlir
776426ea4e
The logic in the rewriting phase had a bug in case of a read-only op coming before mutation ops. The logic would use the op itself as the "latest literal", but that is not correct, because later on we replace the op itself with the *final* "latest literal", assuming that all uses of the op have been rewritten -- that was working in general, except for any read-only ops at the beginning. Big thanks to @ljfitz for the tiny reproducer! Fixes #704 |
||
---|---|---|
.. | ||
AdjustCallingConventions.cpp | ||
CMakeLists.txt | ||
DecomposeComplexOps.cpp | ||
DropShapeCalculations.cpp | ||
GlobalizeObjectGraph.cpp | ||
InlineGlobalSlots.cpp | ||
MaximizeValueSemantics.cpp | ||
PassDetail.h | ||
Passes.cpp | ||
PrepareForGlobalizeObjectGraph.cpp | ||
ReduceOpVariants.cpp | ||
RefinePublicReturn.cpp | ||
RefineTypes.cpp | ||
ReifyShapeCalculations.cpp | ||
ShapeLibrary.cpp | ||
SimplifyShapeCalculations.cpp |