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. |
||
|---|---|---|
| .. | ||
| GlobalizeObjectGraph | ||
| adjust-calling-conventions.mlir | ||
| canonicalize.mlir | ||
| decompose-complex-ops.mlir | ||
| inline-global-slots.mlir | ||
| invalid.mlir | ||
| maximize-value-semantics.mlir | ||
| ops.mlir | ||
| prepare-for-globalize-object-graph.mlir | ||
| promote-types.mlir | ||
| reduce-op-variants-error.mlir | ||
| reduce-op-variants.mlir | ||
| refine-public-return.mlir | ||
| refine-types-branch.mlir | ||
| refine-types.mlir | ||