[VPlan] Set branch weight metadata on middle term in VPlan (NFC) (#143035)

Manage branch weights for the BranchOnCond in the middle block in VPlan.
This requires updating VPInstruction to inherit from VPIRMetadata, which
in general makes sense as there are a number of opcodes that could take
metadata.

There are other branches (part of the skeleton) that also need branch
weights adding.

PR: #143035

Author: fhahn

llvm/lib/Transforms/Vectorize/LoopVectorize.cpp

@@ -7273,6 +7273,33 @@ static void fixReductionScalarResumeWhenVectorizingEpilog(
       BypassBlock, MainResumePhi->getIncomingValueForBlock(BypassBlock));
 }
 
+/// Add branch weight metadata, if the \p Plan's middle block is terminated by a
+/// BranchOnCond recipe.
+static void addBranchWeightToMiddleTerminator(VPlan &Plan, ElementCount VF,
+                                              Loop *OrigLoop) {
+  // 4. Adjust branch weight of the branch in the middle block.
+  Instruction *LatchTerm = OrigLoop->getLoopLatch()->getTerminator();
+  if (!hasBranchWeightMD(*LatchTerm))
+    return;
+
+  VPBasicBlock *MiddleVPBB = Plan.getMiddleBlock();
+  auto *MiddleTerm =
+      dyn_cast_or_null<VPInstruction>(MiddleVPBB->getTerminator());
+  // Only add branch metadata if there is a (conditional) terminator.
+  if (!MiddleTerm)
+    return;
+
+  assert(MiddleTerm->getOpcode() == VPInstruction::BranchOnCond &&
+         "must have a BranchOnCond");
+  // Assume that `Count % VectorTripCount` is equally distributed.
+  unsigned TripCount = Plan.getUF() * VF.getKnownMinValue();
+  assert(TripCount > 0 && "trip count should not be zero");
+  MDBuilder MDB(LatchTerm->getContext());
+  MDNode *BranchWeights =
+      MDB.createBranchWeights({1, TripCount - 1}, /*IsExpected=*/false);
+  MiddleTerm->addMetadata(LLVMContext::MD_prof, BranchWeights);
+}
+
 DenseMap<const SCEV *, Value *> LoopVectorizationPlanner::executePlan(
     ElementCount BestVF, unsigned BestUF, VPlan &BestVPlan,
     InnerLoopVectorizer &ILV, DominatorTree *DT, bool VectorizingEpilogue) {
@@ -7295,11 +7322,8 @@ DenseMap<const SCEV *, Value *> LoopVectorizationPlanner::executePlan(
 
   VPlanTransforms::convertToConcreteRecipes(BestVPlan,
                                             *Legal->getWidestInductionType());
-  // Retrieve and store the middle block before dissolving regions. Regions are
-  // dissolved after optimizing for VF and UF, which completely removes unneeded
-  // loop regions first.
-  VPBasicBlock *MiddleVPBB =
-      BestVPlan.getVectorLoopRegion() ? BestVPlan.getMiddleBlock() : nullptr;
+
+  addBranchWeightToMiddleTerminator(BestVPlan, BestVF, OrigLoop);
   VPlanTransforms::dissolveLoopRegions(BestVPlan);
   // Perform the actual loop transformation.
   VPTransformState State(&TTI, BestVF, LI, DT, ILV.AC, ILV.Builder, &BestVPlan,
@@ -7442,20 +7466,6 @@ DenseMap<const SCEV *, Value *> LoopVectorizationPlanner::executePlan(
 
   ILV.printDebugTracesAtEnd();
 
-  // 4. Adjust branch weight of the branch in the middle block.
-  if (HeaderVPBB) {
-    auto *MiddleTerm =
-        cast<BranchInst>(State.CFG.VPBB2IRBB[MiddleVPBB]->getTerminator());
-    if (MiddleTerm->isConditional() &&
-        hasBranchWeightMD(*OrigLoop->getLoopLatch()->getTerminator())) {
-      // Assume that `Count % VectorTripCount` is equally distributed.
-      unsigned TripCount = BestVPlan.getUF() * State.VF.getKnownMinValue();
-      assert(TripCount > 0 && "trip count should not be zero");
-      const uint32_t Weights[] = {1, TripCount - 1};
-      setBranchWeights(*MiddleTerm, Weights, /*IsExpected=*/false);
-    }
-  }
-
   return ExpandedSCEVs;
 }
 

llvm/lib/Transforms/Vectorize/VPlan.h

@@ -882,11 +882,39 @@ template <unsigned PartOpIdx> class VPUnrollPartAccessor {
   unsigned getUnrollPart(VPUser &U) const;
 };
 
+/// Helper to manage IR metadata for recipes. It filters out metadata that
+/// cannot be propagated.
+class VPIRMetadata {
+  SmallVector<std::pair<unsigned, MDNode *>> Metadata;
+
+public:
+  VPIRMetadata() {}
+
+  /// Adds metatadata that can be preserved from the original instruction
+  /// \p I.
+  VPIRMetadata(Instruction &I) { getMetadataToPropagate(&I, Metadata); }
+
+  /// Adds metatadata that can be preserved from the original instruction
+  /// \p I and noalias metadata guaranteed by runtime checks using \p LVer.
+  VPIRMetadata(Instruction &I, LoopVersioning *LVer);
+
+  /// Copy constructor for cloning.
+  VPIRMetadata(const VPIRMetadata &Other) : Metadata(Other.Metadata) {}
+
+  /// Add all metadata to \p I.
+  void applyMetadata(Instruction &I) const;
+
+  void addMetadata(unsigned Kind, MDNode *Node) {
+    Metadata.emplace_back(Kind, Node);
+  }
+};
+
 /// This is a concrete Recipe that models a single VPlan-level instruction.
 /// While as any Recipe it may generate a sequence of IR instructions when
 /// executed, these instructions would always form a single-def expression as
 /// the VPInstruction is also a single def-use vertex.
 class VPInstruction : public VPRecipeWithIRFlags,
+                      public VPIRMetadata,
                       public VPUnrollPartAccessor<1> {
   friend class VPlanSlp;
 
@@ -976,7 +1004,7 @@ class VPInstruction : public VPRecipeWithIRFlags,
   VPInstruction(unsigned Opcode, ArrayRef<VPValue *> Operands, DebugLoc DL = {},
                 const Twine &Name = "")
       : VPRecipeWithIRFlags(VPDef::VPInstructionSC, Operands, DL),
-        Opcode(Opcode), Name(Name.str()) {}
+        VPIRMetadata(), Opcode(Opcode), Name(Name.str()) {}
 
   VPInstruction(unsigned Opcode, ArrayRef<VPValue *> Operands,
                 const VPIRFlags &Flags, DebugLoc DL = {},
@@ -1268,29 +1296,6 @@ struct VPIRPhi : public VPIRInstruction, public VPPhiAccessors {
   const VPRecipeBase *getAsRecipe() const override { return this; }
 };
 
-/// Helper to manage IR metadata for recipes. It filters out metadata that
-/// cannot be propagated.
-class VPIRMetadata {
-  SmallVector<std::pair<unsigned, MDNode *>> Metadata;
-
-public:
-  VPIRMetadata() {}
-
-  /// Adds metatadata that can be preserved from the original instruction
-  /// \p I.
-  VPIRMetadata(Instruction &I) { getMetadataToPropagate(&I, Metadata); }
-
-  /// Adds metatadata that can be preserved from the original instruction
-  /// \p I and noalias metadata guaranteed by runtime checks using \p LVer.
-  VPIRMetadata(Instruction &I, LoopVersioning *LVer);
-
-  /// Copy constructor for cloning.
-  VPIRMetadata(const VPIRMetadata &Other) : Metadata(Other.Metadata) {}
-
-  /// Add all metadata to \p I.
-  void applyMetadata(Instruction &I) const;
-};
-
 /// VPWidenRecipe is a recipe for producing a widened instruction using the
 /// opcode and operands of the recipe. This recipe covers most of the
 /// traditional vectorization cases where each recipe transforms into a

llvm/lib/Transforms/Vectorize/VPlanRecipes.cpp

@@ -410,7 +410,7 @@ VPInstruction::VPInstruction(unsigned Opcode, ArrayRef<VPValue *> Operands,
                              const VPIRFlags &Flags, DebugLoc DL,
                              const Twine &Name)
     : VPRecipeWithIRFlags(VPDef::VPInstructionSC, Operands, Flags, DL),
-      Opcode(Opcode), Name(Name.str()) {
+      VPIRMetadata(), Opcode(Opcode), Name(Name.str()) {
   assert(flagsValidForOpcode(getOpcode()) &&
          "Set flags not supported for the provided opcode");
 }
@@ -591,7 +591,9 @@ Value *VPInstruction::generate(VPTransformState &State) {
   }
   case VPInstruction::BranchOnCond: {
     Value *Cond = State.get(getOperand(0), VPLane(0));
-    return createCondBranch(Cond, getParent(), State);
+    auto *Br = createCondBranch(Cond, getParent(), State);
+    applyMetadata(*Br);
+    return Br;
   }
   case VPInstruction::BranchOnCount: {
     // First create the compare.