[llvm] [SLP] Avoid seeding related affine loop address computations (PR #226220)

Alexey Bataev via llvm-commits llvm-commits at lists.llvm.org
Sun Oct 11 09:48:52 PDT 2026


================
@@ -210,6 +212,10 @@ struct SLPVectorizerPass : public OptionalPassInfoMixin<SLPVectorizerPass> {
 
   /// The getelementptr instructions in a basic block organized by base pointer.
   GEPListMap GEPs;
+
+  /// The getelementptr instructions whose indices are candidates for
+  /// vectorizeGEPIndices, organized by basic block.
+  DenseMap<BasicBlock *, SmallVector<WeakTrackingVH>> IndexedGEPs;
----------------
alexey-bataev wrote:

```suggestion
  /// The arithmetic of index computations left to loop strength reduction,
  /// organized by basic block.
  SmallDenseMap<BasicBlock *, SmallVector<WeakTrackingVH>> SkippedIndexOps;
```

https://github.com/llvm/llvm-project/pull/226220


More information about the llvm-commits mailing list