mirror of https://github.com/llvm/torch-mlir
51e267aa37
This commit replaces the two rewrite patterns of maximize-value-semantics with a single pattern that captures the behavior of both as well as other edge cases previously not supported. The new pattern works by first performing alias analysis on a subgraph to see if pattern is applicable, then rewriting all non-value tensors to value tensors in a single go. |
||
|---|---|---|
| .. | ||
| AdjustCallingConventions.cpp | ||
| CMakeLists.txt | ||
| DecomposeComplexOps.cpp | ||
| GlobalizeObjectGraph.cpp | ||
| InlineGlobalSlots.cpp | ||
| MaximizeValueSemantics.cpp | ||
| PassDetail.h | ||
| Passes.cpp | ||
| PrepareForGlobalizeObjectGraph.cpp | ||
| ReduceOpVariants.cpp | ||
| RefinePublicReturn.cpp | ||
| RefineTypes.cpp | ||