[PATCH] D97378: [VPlan] Support to vectorize inner loops with VPlan native path enabled

[Florian Hahn via Phabricator via llvm-commits]

fhahn added inline comments.


================
Comment at: llvm/lib/Transforms/Vectorize/LoopVectorize.cpp:4443
   PHINode *P = cast<PHINode>(PN);
-  if (EnableVPlanNativePath) {
-    // Currently we enter here in the VPlan-native path for non-induction
-    // PHIs where all control flow is uniform. We simply widen these PHIs.
+  if (EnableVPlanNativePath && !OrigLoop->isInnermost()) {
+    // We enter here in the VPlan-native path and when the loop is not the
----------------
I think we should probably have a `UseVPlanNativePath` variable in `ILV`, which is true if `EnableVPlanNativePath && !OrigLoop->isInnerMost()` and replace all checks of `EnableVPlanNativePath` with checking `UseVPlanNativePath`.


================
Comment at: llvm/lib/Transforms/Vectorize/LoopVectorize.cpp:5184
     if (isa<LoadInst>(I) && Legal->isUniformMemOp(*I)) {
-      assert(WideningDecision == CM_Scalarize);
+      assert(WideningDecision == CM_Scalarize ||
+             WideningDecision == CM_GatherScatter);
----------------
Why is this needed? If we handle inner loops with the regular ILV even in the VPlanNativePath, the assert should not change I think. Is it possible that we need to update other parts to set the right decision for ILV in VPlanNativePath?


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D97378/new/

https://reviews.llvm.org/D97378