[PATCH] D121618: [LV] Move code to place pointer induction increment to VPlan post-processing.

[Ayal Zaks via Phabricator via llvm-commits]

Ayal added inline comments.


================
Comment at: llvm/lib/Transforms/Vectorize/LoopVectorize.cpp:9592
   // A pointer induction, performed by using a gep
-  BasicBlock *LoopLatch =
-      State.LI->getLoopFor(State.CFG.PrevBB)->getLoopLatch();
-
-  const DataLayout &DL = LoopLatch->getModule()->getDataLayout();
-  Instruction *InductionLoc = LoopLatch->getTerminator();
+  const DataLayout &DL = Phi->getModule()->getDataLayout();
   const SCEV *ScalarStep = IndDesc.getStep();
----------------
nit: set   Instruction *InductionLoc = &*State.Builder.GetInsertPoint() ?


================
Comment at: llvm/lib/Transforms/Vectorize/LoopVectorize.cpp:9604
+      &*State.Builder.GetInsertPoint());
+  NewPointerPhi->addIncoming(InductionGEP, State.CFG.VectorPreHeader);
 
----------------
Deserves a comment that this is temporary?


================
Comment at: llvm/lib/Transforms/Vectorize/VPlan.cpp:986
     // Skip phi-like recipes that generate their backedege values themselves.
     // TODO: Model their backedge values explicitly.
+    if (isa<VPWidenPHIRecipe>(&R))
----------------
Above TODO is obsolete?


================
Comment at: llvm/lib/Transforms/Vectorize/VPlan.cpp:995
+        if (all_of(WidenPhi->users(), [WidenPhi](const VPUser *U) {
+              return cast<VPRecipeBase>(U)->usesScalars(WidenPhi);
+            }))
----------------
An induction phi feeding only scalar users deserves a separate, non-'Widen', VP[Replicate]PointerInductionRecipe ?


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D121618/new/

https://reviews.llvm.org/D121618