[llvm] [VPlan] Construct initial once and pass clones to tryToBuildVPlan (NFC). (PR #141363)

[via llvm-commits]

llvmbot wrote:


<!--LLVM PR SUMMARY COMMENT-->

@llvm/pr-subscribers-vectorizers

Author: Florian Hahn (fhahn)

<details>
<summary>Changes</summary>

Update to only build an initial, plain-CFG VPlan once, and then transform & optimize clones.

This requires changes to ::clone() for VPInstruction and VPWidenPHIRecipe to allow for proper cloning of the recipes in the initial VPlan.

---
Full diff: https://github.com/llvm/llvm-project/pull/141363.diff


3 Files Affected:

- (modified) llvm/lib/Transforms/Vectorize/LoopVectorizationPlanner.h (+2-1) 
- (modified) llvm/lib/Transforms/Vectorize/LoopVectorize.cpp (+5-5) 
- (modified) llvm/lib/Transforms/Vectorize/VPlan.h (+7-1) 


``````````diff
diff --git a/llvm/lib/Transforms/Vectorize/LoopVectorizationPlanner.h b/llvm/lib/Transforms/Vectorize/LoopVectorizationPlanner.h
index bae53c600c18c..c772c74113d97 100644
--- a/llvm/lib/Transforms/Vectorize/LoopVectorizationPlanner.h
+++ b/llvm/lib/Transforms/Vectorize/LoopVectorizationPlanner.h
@@ -524,7 +524,8 @@ class LoopVectorizationPlanner {
   /// returned VPlan is valid for. If no VPlan can be built for the input range,
   /// set the largest included VF to the maximum VF for which no plan could be
   /// built.
-  VPlanPtr tryToBuildVPlanWithVPRecipes(VFRange &Range, LoopVersioning *LVer);
+  VPlanPtr tryToBuildVPlanWithVPRecipes(VPlanPtr InitialPlan, VFRange &Range,
+                                        LoopVersioning *LVer);
 
   /// Build VPlans for power-of-2 VF's between \p MinVF and \p MaxVF inclusive,
   /// according to the information gathered by Legal when it checked if it is
diff --git a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
index 8636550d4f644..1232538e68dd0 100644
--- a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
+++ b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
@@ -8715,11 +8715,13 @@ void LoopVectorizationPlanner::buildVPlansWithVPRecipes(ElementCount MinVF,
     // overlap across all iterations.
     LVer.prepareNoAliasMetadata();
   }
+  auto VPlan0 = VPlanTransforms::buildPlainCFG(OrigLoop, *LI);
 
   auto MaxVFTimes2 = MaxVF * 2;
   for (ElementCount VF = MinVF; ElementCount::isKnownLT(VF, MaxVFTimes2);) {
     VFRange SubRange = {VF, MaxVFTimes2};
-    if (auto Plan = tryToBuildVPlanWithVPRecipes(SubRange, &LVer)) {
+    if (auto Plan = tryToBuildVPlanWithVPRecipes(
+            std::unique_ptr<VPlan>(VPlan0->duplicate()), SubRange, &LVer)) {
       bool HasScalarVF = Plan->hasScalarVFOnly();
       // Now optimize the initial VPlan.
       if (!HasScalarVF)
@@ -8980,9 +8982,8 @@ static void addExitUsersForFirstOrderRecurrences(
   }
 }
 
-VPlanPtr
-LoopVectorizationPlanner::tryToBuildVPlanWithVPRecipes(VFRange &Range,
-                                                       LoopVersioning *LVer) {
+VPlanPtr LoopVectorizationPlanner::tryToBuildVPlanWithVPRecipes(
+    VPlanPtr Plan, VFRange &Range, LoopVersioning *LVer) {
 
   using namespace llvm::VPlanPatternMatch;
   SmallPtrSet<const InterleaveGroup<Instruction> *, 1> InterleaveGroups;
@@ -9004,7 +9005,6 @@ LoopVectorizationPlanner::tryToBuildVPlanWithVPRecipes(VFRange &Range,
             return !CM.requiresScalarEpilogue(VF.isVector());
           },
           Range);
-  auto Plan = VPlanTransforms::buildPlainCFG(OrigLoop, *LI);
   VPlanTransforms::prepareForVectorization(
       *Plan, Legal->getWidestInductionType(), PSE, RequiresScalarEpilogueCheck,
       CM.foldTailByMasking(), OrigLoop,
diff --git a/llvm/lib/Transforms/Vectorize/VPlan.h b/llvm/lib/Transforms/Vectorize/VPlan.h
index c4e66cd89e69c..940df596e5cec 100644
--- a/llvm/lib/Transforms/Vectorize/VPlan.h
+++ b/llvm/lib/Transforms/Vectorize/VPlan.h
@@ -1004,6 +1004,8 @@ class VPInstruction : public VPRecipeWithIRFlags,
   VPInstruction *clone() override {
     SmallVector<VPValue *, 2> Operands(operands());
     auto *New = new VPInstruction(Opcode, Operands, getDebugLoc(), Name);
+    if (getUnderlyingValue())
+      New->setUnderlyingValue(getUnderlyingInstr());
     New->transferFlags(*this);
     return New;
   }
@@ -2129,7 +2131,11 @@ class VPWidenPHIRecipe : public VPSingleDefRecipe, public VPPhiAccessors {
   }
 
   VPWidenPHIRecipe *clone() override {
-    llvm_unreachable("cloning not implemented yet");
+    auto *C = new VPWidenPHIRecipe(cast<PHINode>(getUnderlyingValue()),
+                                   getOperand(0), getDebugLoc(), Name);
+    for (VPValue *Op : make_range(std::next(op_begin()), op_end()))
+      C->addOperand(Op);
+    return C;
   }
 
   ~VPWidenPHIRecipe() override = default;

``````````

</details>


https://github.com/llvm/llvm-project/pull/141363