[VPlan] Only store RecurKind + FastMathFlags in VPReductionRecipe. NFCI

VPReductionRecipes take a RecurrenceDescriptor, but only use the RecurKind and FastMathFlags in it when executing. This patch makes the recipe more lightweight by stripping it to only take the latter, which allows it inherit from VPRecipeWithIRFlags.

This also allows us to remove createReduction in LoopUtils since it now only has one user in VPInstruction::ComputeReductionResult.

The motiviation for this is to simplify an upcoming patch to support in-loop AnyOf reductions. For an in-loop AnyOf reduction we want to create an Or reduction, and by using RecurKind we can create an arbitrary reduction without needing a full RecurrenceDescriptor.

Author: lukel97

llvm/include/llvm/Transforms/Utils/LoopUtils.h

@@ -411,8 +411,8 @@ Value *createSimpleReduction(IRBuilderBase &B, Value *Src,
                              RecurKind RdxKind);
 /// Overloaded function to generate vector-predication intrinsics for
 /// reduction.
-Value *createSimpleReduction(VectorBuilder &VB, Value *Src,
-                             const RecurrenceDescriptor &Desc);
+Value *createSimpleReduction(VectorBuilder &VB, Value *Src, RecurKind RdxKind,
+                             FastMathFlags FMFs);
 
 /// Create a reduction of the given vector \p Src for a reduction of the
 /// kind RecurKind::IAnyOf or RecurKind::FAnyOf. The reduction operation is
@@ -428,14 +428,12 @@ Value *createFindLastIVReduction(IRBuilderBase &B, Value *Src,
                                  const RecurrenceDescriptor &Desc);
 
 /// Create an ordered reduction intrinsic using the given recurrence
-/// descriptor \p Desc.
-Value *createOrderedReduction(IRBuilderBase &B,
-                              const RecurrenceDescriptor &Desc, Value *Src,
+/// kind \p Kind.
+Value *createOrderedReduction(IRBuilderBase &B, RecurKind Kind, Value *Src,
                               Value *Start);
 /// Overloaded function to generate vector-predication intrinsics for ordered
 /// reduction.
-Value *createOrderedReduction(VectorBuilder &VB,
-                              const RecurrenceDescriptor &Desc, Value *Src,
+Value *createOrderedReduction(VectorBuilder &VB, RecurKind Kind, Value *Src,
                               Value *Start);
 
 /// Get the intersection (logical and) of all of the potential IR flags

llvm/lib/Transforms/Utils/LoopUtils.cpp

@@ -1333,36 +1333,31 @@ Value *llvm::createSimpleReduction(IRBuilderBase &Builder, Value *Src,
 }
 
 Value *llvm::createSimpleReduction(VectorBuilder &VBuilder, Value *Src,
-                                   const RecurrenceDescriptor &Desc) {
-  RecurKind Kind = Desc.getRecurrenceKind();
+                                   RecurKind Kind, FastMathFlags FMFs) {
   assert(!RecurrenceDescriptor::isAnyOfRecurrenceKind(Kind) &&
          !RecurrenceDescriptor::isFindLastIVRecurrenceKind(Kind) &&
          "AnyOf or FindLastIV reductions are not supported.");
   Intrinsic::ID Id = getReductionIntrinsicID(Kind);
   auto *SrcTy = cast<VectorType>(Src->getType());
   Type *SrcEltTy = SrcTy->getElementType();
-  Value *Iden = getRecurrenceIdentity(Kind, SrcEltTy, Desc.getFastMathFlags());
+  Value *Iden = getRecurrenceIdentity(Kind, SrcEltTy, FMFs);
   Value *Ops[] = {Iden, Src};
   return VBuilder.createSimpleReduction(Id, SrcTy, Ops);
 }
 
-Value *llvm::createOrderedReduction(IRBuilderBase &B,
-                                    const RecurrenceDescriptor &Desc,
+Value *llvm::createOrderedReduction(IRBuilderBase &B, RecurKind Kind,
                                     Value *Src, Value *Start) {
-  assert((Desc.getRecurrenceKind() == RecurKind::FAdd ||
-          Desc.getRecurrenceKind() == RecurKind::FMulAdd) &&
+  assert((Kind == RecurKind::FAdd || Kind == RecurKind::FMulAdd) &&
          "Unexpected reduction kind");
   assert(Src->getType()->isVectorTy() && "Expected a vector type");
   assert(!Start->getType()->isVectorTy() && "Expected a scalar type");
 
   return B.CreateFAddReduce(Start, Src);
 }
 
-Value *llvm::createOrderedReduction(VectorBuilder &VBuilder,
-                                    const RecurrenceDescriptor &Desc,
+Value *llvm::createOrderedReduction(VectorBuilder &VBuilder, RecurKind Kind,
                                     Value *Src, Value *Start) {
-  assert((Desc.getRecurrenceKind() == RecurKind::FAdd ||
-          Desc.getRecurrenceKind() == RecurKind::FMulAdd) &&
+  assert((Kind == RecurKind::FAdd || Kind == RecurKind::FMulAdd) &&
          "Unexpected reduction kind");
   assert(Src->getType()->isVectorTy() && "Expected a vector type");
   assert(!Start->getType()->isVectorTy() && "Expected a scalar type");

llvm/lib/Transforms/Vectorize/VPlan.h

@@ -2239,22 +2239,21 @@ class VPInterleaveRecipe : public VPRecipeBase {
 /// a vector operand into a scalar value, and adding the result to a chain.
 /// The Operands are {ChainOp, VecOp, [Condition]}.
 class VPReductionRecipe : public VPRecipeWithIRFlags {
-  /// The recurrence decriptor for the reduction in question.
-  const RecurrenceDescriptor &RdxDesc;
+  /// The recurrence kind for the reduction in question.
+  RecurKind RdxKind;
   bool IsOrdered;
   /// Whether the reduction is conditional.
   bool IsConditional = false;
 
 protected:
-  VPReductionRecipe(const unsigned char SC, const RecurrenceDescriptor &R,
-                    Instruction *I, ArrayRef<VPValue *> Operands,
-                    VPValue *CondOp, bool IsOrdered, DebugLoc DL)
-      : VPRecipeWithIRFlags(SC, Operands,
-                            isa_and_nonnull<FPMathOperator>(I)
-                                ? R.getFastMathFlags()
-                                : FastMathFlags(),
-                            DL),
-        RdxDesc(R), IsOrdered(IsOrdered) {
+  VPReductionRecipe(const unsigned char SC, RecurKind RdxKind,
+                    FastMathFlags FMFs, Instruction *I,
+                    ArrayRef<VPValue *> Operands, VPValue *CondOp,
+                    bool IsOrdered, DebugLoc DL)
+      : VPRecipeWithIRFlags(
+            SC, Operands,
+            isa_and_nonnull<FPMathOperator>(I) ? FMFs : FastMathFlags(), DL),
+        RdxKind(RdxKind), IsOrdered(IsOrdered) {
     if (CondOp) {
       IsConditional = true;
       addOperand(CondOp);
@@ -2263,19 +2262,25 @@ class VPReductionRecipe : public VPRecipeWithIRFlags {
   }
 
 public:
-  VPReductionRecipe(const RecurrenceDescriptor &R, Instruction *I,
+  VPReductionRecipe(RecurKind RdxKind, FastMathFlags FMFs, Instruction *I,
                     VPValue *ChainOp, VPValue *VecOp, VPValue *CondOp,
                     bool IsOrdered, DebugLoc DL = {})
-      : VPReductionRecipe(VPDef::VPReductionSC, R, I,
+      : VPReductionRecipe(VPRecipeBase::VPReductionSC, RdxKind, FMFs, I,
                           ArrayRef<VPValue *>({ChainOp, VecOp}), CondOp,
                           IsOrdered, DL) {}
 
+  VPReductionRecipe(const RecurrenceDescriptor &R, Instruction *I,
+                    VPValue *ChainOp, VPValue *VecOp, VPValue *CondOp,
+                    bool IsOrdered, DebugLoc DL = {})
+      : VPReductionRecipe(R.getRecurrenceKind(), R.getFastMathFlags(), I,
+                          ChainOp, VecOp, CondOp, IsOrdered, DL) {}
+
   ~VPReductionRecipe() override = default;
 
   VPReductionRecipe *clone() override {
-    return new VPReductionRecipe(RdxDesc, getUnderlyingInstr(), getChainOp(),
-                                 getVecOp(), getCondOp(), IsOrdered,
-                                 getDebugLoc());
+    return new VPReductionRecipe(RdxKind, getFastMathFlags(),
+                                 getUnderlyingInstr(), getChainOp(), getVecOp(),
+                                 getCondOp(), IsOrdered, getDebugLoc());
   }
 
   static inline bool classof(const VPRecipeBase *R) {
@@ -2301,9 +2306,11 @@ class VPReductionRecipe : public VPRecipeWithIRFlags {
              VPSlotTracker &SlotTracker) const override;
 #endif
 
-  /// Return the recurrence decriptor for the in-loop reduction.
-  const RecurrenceDescriptor &getRecurrenceDescriptor() const {
-    return RdxDesc;
+  /// Return the recurrence kind for the in-loop reduction.
+  RecurKind getRecurrenceKind() const { return RdxKind; }
+  /// Return the opcode for the recurrence for the in-loop reduction.
+  unsigned getOpcode() const {
+    return RecurrenceDescriptor::getOpcode(RdxKind);
   }
   /// Return true if the in-loop reduction is ordered.
   bool isOrdered() const { return IsOrdered; };
@@ -2328,7 +2335,8 @@ class VPReductionEVLRecipe : public VPReductionRecipe {
   VPReductionEVLRecipe(VPReductionRecipe &R, VPValue &EVL, VPValue *CondOp,
                        DebugLoc DL = {})
       : VPReductionRecipe(
-            VPDef::VPReductionEVLSC, R.getRecurrenceDescriptor(),
+            VPDef::VPReductionEVLSC, R.getRecurrenceKind(),
+            R.getFastMathFlags(),
             cast_or_null<Instruction>(R.getUnderlyingValue()),
             ArrayRef<VPValue *>({R.getChainOp(), R.getVecOp(), &EVL}), CondOp,
             R.isOrdered(), DL) {}

llvm/lib/Transforms/Vectorize/VPlanRecipes.cpp

@@ -2285,7 +2285,7 @@ void VPBlendRecipe::print(raw_ostream &O, const Twine &Indent,
 void VPReductionRecipe::execute(VPTransformState &State) {
   assert(!State.Lane && "Reduction being replicated.");
   Value *PrevInChain = State.get(getChainOp(), /*IsScalar*/ true);
-  RecurKind Kind = RdxDesc.getRecurrenceKind();
+  RecurKind Kind = getRecurrenceKind();
   assert(!RecurrenceDescriptor::isAnyOfRecurrenceKind(Kind) &&
          "In-loop AnyOf reductions aren't currently supported");
   // Propagate the fast-math flags carried by the underlying instruction.
@@ -2298,8 +2298,7 @@ void VPReductionRecipe::execute(VPTransformState &State) {
     VectorType *VecTy = dyn_cast<VectorType>(NewVecOp->getType());
     Type *ElementTy = VecTy ? VecTy->getElementType() : NewVecOp->getType();
 
-    Value *Start =
-        getRecurrenceIdentity(Kind, ElementTy, RdxDesc.getFastMathFlags());
+    Value *Start = getRecurrenceIdentity(Kind, ElementTy, getFastMathFlags());
     if (State.VF.isVector())
       Start = State.Builder.CreateVectorSplat(VecTy->getElementCount(), Start);
 
@@ -2311,21 +2310,20 @@ void VPReductionRecipe::execute(VPTransformState &State) {
   if (IsOrdered) {
     if (State.VF.isVector())
       NewRed =
-          createOrderedReduction(State.Builder, RdxDesc, NewVecOp, PrevInChain);
+          createOrderedReduction(State.Builder, Kind, NewVecOp, PrevInChain);
     else
-      NewRed = State.Builder.CreateBinOp(
-          (Instruction::BinaryOps)RdxDesc.getOpcode(), PrevInChain, NewVecOp);
+      NewRed = State.Builder.CreateBinOp((Instruction::BinaryOps)getOpcode(),
+                                         PrevInChain, NewVecOp);
     PrevInChain = NewRed;
     NextInChain = NewRed;
   } else {
     PrevInChain = State.get(getChainOp(), /*IsScalar*/ true);
     NewRed = createSimpleReduction(State.Builder, NewVecOp, Kind);
     if (RecurrenceDescriptor::isMinMaxRecurrenceKind(Kind))
-      NextInChain = createMinMaxOp(State.Builder, RdxDesc.getRecurrenceKind(),
-                                   NewRed, PrevInChain);
+      NextInChain = createMinMaxOp(State.Builder, Kind, NewRed, PrevInChain);
     else
       NextInChain = State.Builder.CreateBinOp(
-          (Instruction::BinaryOps)RdxDesc.getOpcode(), NewRed, PrevInChain);
+          (Instruction::BinaryOps)getOpcode(), NewRed, PrevInChain);
   }
   State.set(this, NextInChain, /*IsScalar*/ true);
 }
@@ -2336,10 +2334,9 @@ void VPReductionEVLRecipe::execute(VPTransformState &State) {
   auto &Builder = State.Builder;
   // Propagate the fast-math flags carried by the underlying instruction.
   IRBuilderBase::FastMathFlagGuard FMFGuard(Builder);
-  const RecurrenceDescriptor &RdxDesc = getRecurrenceDescriptor();
   Builder.setFastMathFlags(getFastMathFlags());
 
-  RecurKind Kind = RdxDesc.getRecurrenceKind();
+  RecurKind Kind = getRecurrenceKind();
   Value *Prev = State.get(getChainOp(), /*IsScalar*/ true);
   Value *VecOp = State.get(getVecOp());
   Value *EVL = State.get(getEVL(), VPLane(0));
@@ -2356,25 +2353,23 @@ void VPReductionEVLRecipe::execute(VPTransformState &State) {
 
   Value *NewRed;
   if (isOrdered()) {
-    NewRed = createOrderedReduction(VBuilder, RdxDesc, VecOp, Prev);
+    NewRed = createOrderedReduction(VBuilder, Kind, VecOp, Prev);
   } else {
-    NewRed = createSimpleReduction(VBuilder, VecOp, RdxDesc);
+    NewRed = createSimpleReduction(VBuilder, VecOp, Kind, getFastMathFlags());
     if (RecurrenceDescriptor::isMinMaxRecurrenceKind(Kind))
       NewRed = createMinMaxOp(Builder, Kind, NewRed, Prev);
     else
-      NewRed = Builder.CreateBinOp((Instruction::BinaryOps)RdxDesc.getOpcode(),
-                                   NewRed, Prev);
+      NewRed = Builder.CreateBinOp((Instruction::BinaryOps)getOpcode(), NewRed,
+                                   Prev);
   }
   State.set(this, NewRed, /*IsScalar*/ true);
 }
 
 InstructionCost VPReductionRecipe::computeCost(ElementCount VF,
                                                VPCostContext &Ctx) const {
-  RecurKind RdxKind = RdxDesc.getRecurrenceKind();
+  RecurKind RdxKind = getRecurrenceKind();
   Type *ElementTy = Ctx.Types.inferScalarType(this);
   auto *VectorTy = cast<VectorType>(toVectorTy(ElementTy, VF));
-  unsigned Opcode = RdxDesc.getOpcode();
-  FastMathFlags FMFs = getFastMathFlags();
 
   // TODO: Support any-of and in-loop reductions.
   assert(
@@ -2386,20 +2381,17 @@ InstructionCost VPReductionRecipe::computeCost(ElementCount VF,
        ForceTargetInstructionCost.getNumOccurrences() > 0) &&
       "In-loop reduction not implemented in VPlan-based cost model currently.");
 
-  assert(ElementTy->getTypeID() == RdxDesc.getRecurrenceType()->getTypeID() &&
-         "Inferred type and recurrence type mismatch.");
-
   // Cost = Reduction cost + BinOp cost
   InstructionCost Cost =
-      Ctx.TTI.getArithmeticInstrCost(Opcode, ElementTy, Ctx.CostKind);
+      Ctx.TTI.getArithmeticInstrCost(getOpcode(), ElementTy, Ctx.CostKind);
   if (RecurrenceDescriptor::isMinMaxRecurrenceKind(RdxKind)) {
     Intrinsic::ID Id = getMinMaxReductionIntrinsicOp(RdxKind);
-    return Cost +
-           Ctx.TTI.getMinMaxReductionCost(Id, VectorTy, FMFs, Ctx.CostKind);
+    return Cost + Ctx.TTI.getMinMaxReductionCost(
+                      Id, VectorTy, getFastMathFlags(), Ctx.CostKind);
   }
 
-  return Cost + Ctx.TTI.getArithmeticReductionCost(Opcode, VectorTy, FMFs,
-                                                   Ctx.CostKind);
+  return Cost + Ctx.TTI.getArithmeticReductionCost(
+                    getOpcode(), VectorTy, getFastMathFlags(), Ctx.CostKind);
 }
 
 #if !defined(NDEBUG) || defined(LLVM_ENABLE_DUMP)
@@ -2411,28 +2403,24 @@ void VPReductionRecipe::print(raw_ostream &O, const Twine &Indent,
   getChainOp()->printAsOperand(O, SlotTracker);
   O << " +";
   printFlags(O);
-  O << " reduce." << Instruction::getOpcodeName(RdxDesc.getOpcode()) << " (";
+  O << " reduce." << Instruction::getOpcodeName(getOpcode()) << " (";
   getVecOp()->printAsOperand(O, SlotTracker);
   if (isConditional()) {
     O << ", ";
     getCondOp()->printAsOperand(O, SlotTracker);
   }
   O << ")";
-  if (RdxDesc.IntermediateStore)
-    O << " (with final reduction value stored in invariant address sank "
-         "outside of loop)";
 }
 
 void VPReductionEVLRecipe::print(raw_ostream &O, const Twine &Indent,
                                  VPSlotTracker &SlotTracker) const {
-  const RecurrenceDescriptor &RdxDesc = getRecurrenceDescriptor();
   O << Indent << "REDUCE ";
   printAsOperand(O, SlotTracker);
   O << " = ";
   getChainOp()->printAsOperand(O, SlotTracker);
   O << " +";
   printFlags(O);
-  O << " vp.reduce." << Instruction::getOpcodeName(RdxDesc.getOpcode()) << " (";
+  O << " vp.reduce." << Instruction::getOpcodeName(getOpcode()) << " (";
   getVecOp()->printAsOperand(O, SlotTracker);
   O << ", ";
   getEVL()->printAsOperand(O, SlotTracker);
@@ -2441,9 +2429,6 @@ void VPReductionEVLRecipe::print(raw_ostream &O, const Twine &Indent,
     getCondOp()->printAsOperand(O, SlotTracker);
   }
   O << ")";
-  if (RdxDesc.IntermediateStore)
-    O << " (with final reduction value stored in invariant address sank "
-         "outside of loop)";
 }
 #endif
 

llvm/test/Transforms/LoopVectorize/vplan-printing.ll

@@ -234,7 +234,7 @@ define void @print_reduction_with_invariant_store(i64 %n, ptr noalias %y, ptr no
 ; CHECK-NEXT:   CLONE ir<%arrayidx> = getelementptr inbounds ir<%y>, vp<[[IV]]>
 ; CHECK-NEXT:   vp<[[VEC_PTR:%.+]]> = vector-pointer ir<%arrayidx>
 ; CHECK-NEXT:   WIDEN ir<%lv> = load vp<[[VEC_PTR]]>
-; CHECK-NEXT:   REDUCE ir<%red.next> = ir<%red> + fast reduce.fadd (ir<%lv>) (with final reduction value stored in invariant address sank outside of loop)
+; CHECK-NEXT:   REDUCE ir<%red.next> = ir<%red> + fast reduce.fadd (ir<%lv>)
 ; CHECK-NEXT:   EMIT vp<[[CAN_IV_NEXT]]> = add nuw vp<[[CAN_IV]]>, vp<[[VFxUF]]>
 ; CHECK-NEXT:   EMIT branch-on-count vp<[[CAN_IV_NEXT]]>, vp<[[VTC]]>
 ; CHECK-NEXT: No successors