mirror of https://github.com/llvm/torch-mlir
9bc606c384
One of the simplifications made by the pass `RefinePublicReturn` currently only happens if the tensor in question only has one user. However, the current method of checking this does not correctly handle the case of a user having multiple uses of the same tensor. This commit makes sure only unique users are considered. |
||
|---|---|---|
| .. | ||
| AdjustCallingConventions.cpp | ||
| CMakeLists.txt | ||
| DecomposeComplexOps.cpp | ||
| DropShapeCalculations.cpp | ||
| EraseModuleInitializer.cpp | ||
| GlobalizeObjectGraph.cpp | ||
| InlineGlobalSlots.cpp | ||
| LowerToBackendContract.cpp | ||
| MaximizeValueSemantics.cpp | ||
| PassDetail.h | ||
| Passes.cpp | ||
| PrepareForGlobalizeObjectGraph.cpp | ||
| ReduceOpVariants.cpp | ||
| RefinePublicReturn.cpp | ||
| RefineTypes.cpp | ||
| ReifyShapeCalculations.cpp | ||
| ShapeLibrary.cpp | ||
| SimplifyShapeCalculations.cpp | ||