[VPlan] Introduce VPWidenIntrinsicRecipe to separate from libcall.

This patch splits off intrinsic hanlding to a new
VPWidenIntrinsicRecipe. VPWidenIntrinsicRecipes only need access to the
intrinsic ID to widen and the scalar result type (in case the intrinsic
is overloaded on the result type). It does not need access to an
underlying IR call instruction or function.

This means VPWidenIntrinsicRecipe can be created easily without access
to underlying IR.

Author: fhahn

llvm/lib/Transforms/Vectorize/LoopVectorize.cpp

@@ -4367,7 +4367,7 @@ void LoopVectorizationPlanner::emitInvalidCostRemarks(
                 [](const auto *R) { return Instruction::Store; })
             .Case<VPWidenLoadRecipe>(
                 [](const auto *R) { return Instruction::Load; })
-            .Case<VPWidenCallRecipe>(
+            .Case<VPWidenCallRecipe, VPWidenIntrinsicRecipe>(
                 [](const auto *R) { return Instruction::Call; })
             .Case<VPInstruction, VPWidenRecipe, VPReplicateRecipe,
                   VPWidenCastRecipe>(
@@ -4392,11 +4392,17 @@ void LoopVectorizationPlanner::emitInvalidCostRemarks(
       OS << "):";
       if (Opcode == Instruction::Call) {
         auto *WidenCall = dyn_cast<VPWidenCallRecipe>(R);
-        Function *CalledFn =
-            WidenCall ? WidenCall->getCalledScalarFunction()
-                      : cast<Function>(R->getOperand(R->getNumOperands() - 1)
-                                           ->getLiveInIRValue());
-        OS << " call to " << CalledFn->getName();
+        StringRef Name = "";
+        if (auto *Int = dyn_cast<VPWidenIntrinsicRecipe>(R))
+          Name = Int->getIntrinsicName();
+        else {
+          Function *CalledFn =
+              WidenCall ? WidenCall->getCalledScalarFunction()
+                        : cast<Function>(R->getOperand(R->getNumOperands() - 1)
+                                             ->getLiveInIRValue());
+          Name = CalledFn->getName();
+        }
+        OS << " call to " << Name;
       } else
         OS << " " << Instruction::getOpcodeName(Opcode);
       reportVectorizationInfo(OutString, "InvalidCost", ORE, OrigLoop, nullptr,
@@ -4447,6 +4453,7 @@ static bool willGenerateVectors(VPlan &Plan, ElementCount VF,
       case VPDef::VPWidenCanonicalIVSC:
       case VPDef::VPWidenCastSC:
       case VPDef::VPWidenGEPSC:
+      case VPDef::VPWidenIntrinsicSC:
       case VPDef::VPWidenSC:
       case VPDef::VPWidenSelectSC:
       case VPDef::VPBlendSC:
@@ -8266,7 +8273,7 @@ VPBlendRecipe *VPRecipeBuilder::tryToBlend(PHINode *Phi,
   return new VPBlendRecipe(Phi, OperandsWithMask);
 }
 
-VPWidenCallRecipe *VPRecipeBuilder::tryToWidenCall(CallInst *CI,
+VPSingleDefRecipe *VPRecipeBuilder::tryToWidenCall(CallInst *CI,
                                                    ArrayRef<VPValue *> Operands,
                                                    VFRange &Range) {
   bool IsPredicated = LoopVectorizationPlanner::getDecisionAndClampRange(
@@ -8297,8 +8304,9 @@ VPWidenCallRecipe *VPRecipeBuilder::tryToWidenCall(CallInst *CI,
                 },
                 Range);
   if (ShouldUseVectorIntrinsic)
-    return new VPWidenCallRecipe(CI, make_range(Ops.begin(), Ops.end()), ID,
-                                 CI->getDebugLoc());
+    return new VPWidenIntrinsicRecipe(CI, ID,
+                                      make_range(Ops.begin(), Ops.end() - 1),
+                                      CI->getType(), CI->getDebugLoc());
 
   Function *Variant = nullptr;
   std::optional<unsigned> MaskPos;
@@ -8350,9 +8358,8 @@ VPWidenCallRecipe *VPRecipeBuilder::tryToWidenCall(CallInst *CI,
       Ops.insert(Ops.begin() + *MaskPos, Mask);
     }
 
-    return new VPWidenCallRecipe(CI, make_range(Ops.begin(), Ops.end()),
-                                 Intrinsic::not_intrinsic, CI->getDebugLoc(),
-                                 Variant);
+    return new VPWidenCallRecipe(
+        CI, Variant, make_range(Ops.begin(), Ops.end()), CI->getDebugLoc());
   }
 
   return nullptr;
@@ -9218,7 +9225,7 @@ void LoopVectorizationPlanner::adjustRecipesForReductions(
             RecurrenceDescriptor::isFMulAddIntrinsic(CurrentLinkI) &&
             "Expected instruction to be a call to the llvm.fmuladd intrinsic");
         assert(((MinVF.isScalar() && isa<VPReplicateRecipe>(CurrentLink)) ||
-                isa<VPWidenCallRecipe>(CurrentLink)) &&
+                isa<VPWidenIntrinsicRecipe>(CurrentLink)) &&
                CurrentLink->getOperand(2) == PreviousLink &&
                "expected a call where the previous link is the added operand");
 

llvm/lib/Transforms/Vectorize/VPRecipeBuilder.h

@@ -93,9 +93,9 @@ class VPRecipeBuilder {
   VPBlendRecipe *tryToBlend(PHINode *Phi, ArrayRef<VPValue *> Operands);
 
   /// Handle call instructions. If \p CI can be widened for \p Range.Start,
-  /// return a new VPWidenCallRecipe. Range.End may be decreased to ensure same
-  /// decision from \p Range.Start to \p Range.End.
-  VPWidenCallRecipe *tryToWidenCall(CallInst *CI, ArrayRef<VPValue *> Operands,
+  /// return a new VPWidenCallRecipe or VPWidenIntrinsicRecipe. Range.End may be
+  /// decreased to ensure same decision from \p Range.Start to \p Range.End.
+  VPSingleDefRecipe *tryToWidenCall(CallInst *CI, ArrayRef<VPValue *> Operands,
                                     VFRange &Range);
 
   /// Check if \p I has an opcode that can be widened and return a VPWidenRecipe

llvm/lib/Transforms/Vectorize/VPlan.h

@@ -886,6 +886,7 @@ class VPSingleDefRecipe : public VPRecipeBase, public VPValue {
     case VPRecipeBase::VPWidenCanonicalIVSC:
     case VPRecipeBase::VPWidenCastSC:
     case VPRecipeBase::VPWidenGEPSC:
+    case VPRecipeBase::VPWidenIntrinsicSC:
     case VPRecipeBase::VPWidenSC:
     case VPRecipeBase::VPWidenEVLSC:
     case VPRecipeBase::VPWidenSelectSC:
@@ -1608,24 +1609,63 @@ class VPScalarCastRecipe : public VPSingleDefRecipe {
   }
 };
 
-/// A recipe for widening Call instructions.
-class VPWidenCallRecipe : public VPSingleDefRecipe {
-  /// ID of the vector intrinsic to call when widening the call. If set the
-  /// Intrinsic::not_intrinsic, a library call will be used instead.
+/// A recipe for widening vector intrinsics.
+class VPWidenIntrinsicRecipe : public VPSingleDefRecipe {
+  /// ID of the vector intrinsic to widen.
   Intrinsic::ID VectorIntrinsicID;
-  /// If this recipe represents a library call, Variant stores a pointer to
-  /// the chosen function. There is a 1:1 mapping between a given VF and the
-  /// chosen vectorized variant, so there will be a different vplan for each
-  /// VF with a valid variant.
+
+  /// Scalar type of the result produced by the intrinsic.
+  Type *ResultTy;
+
+public:
+  template <typename IterT>
+  VPWidenIntrinsicRecipe(Value *UV, Intrinsic::ID VectorIntrinsicID,
+                         iterator_range<IterT> CallArguments, Type *Ty,
+                         DebugLoc DL = {})
+      : VPSingleDefRecipe(VPDef::VPWidenIntrinsicSC, CallArguments, UV, DL),
+        VectorIntrinsicID(VectorIntrinsicID), ResultTy(Ty) {}
+
+  ~VPWidenIntrinsicRecipe() override = default;
+
+  VPWidenIntrinsicRecipe *clone() override {
+    return new VPWidenIntrinsicRecipe(getUnderlyingValue(), VectorIntrinsicID,
+                                      operands(), ResultTy, getDebugLoc());
+  }
+
+  VP_CLASSOF_IMPL(VPDef::VPWidenIntrinsicSC)
+
+  /// Produce a widened version of the vector intrinsic.
+  void execute(VPTransformState &State) override;
+
+  /// Return the cost of this vector intrinsic.
+  InstructionCost computeCost(ElementCount VF,
+                              VPCostContext &Ctx) const override;
+
+  Type *getResultTy() const { return ResultTy; }
+
+  /// Return to name of the intrinsic as string.
+  StringRef getIntrinsicName() const;
+
+#if !defined(NDEBUG) || defined(LLVM_ENABLE_DUMP)
+  /// Print the recipe.
+  void print(raw_ostream &O, const Twine &Indent,
+             VPSlotTracker &SlotTracker) const override;
+#endif
+};
+
+/// A recipe for widening Call instructions using library calls.
+class VPWidenCallRecipe : public VPSingleDefRecipe {
+  /// Variant stores a pointer to the chosen function. There is a 1:1 mapping
+  /// between a given VF and the chosen vectorized variant, so there will be a
+  /// different VPlan for each VF with a valid variant.
   Function *Variant;
 
 public:
   template <typename IterT>
-  VPWidenCallRecipe(Value *UV, iterator_range<IterT> CallArguments,
-                    Intrinsic::ID VectorIntrinsicID, DebugLoc DL = {},
-                    Function *Variant = nullptr)
+  VPWidenCallRecipe(Value *UV, Function *Variant,
+                    iterator_range<IterT> CallArguments, DebugLoc DL = {})
       : VPSingleDefRecipe(VPDef::VPWidenCallSC, CallArguments, UV, DL),
-        VectorIntrinsicID(VectorIntrinsicID), Variant(Variant) {
+        Variant(Variant) {
     assert(
         isa<Function>(getOperand(getNumOperands() - 1)->getLiveInIRValue()) &&
         "last operand must be the called function");
@@ -1634,8 +1674,8 @@ class VPWidenCallRecipe : public VPSingleDefRecipe {
   ~VPWidenCallRecipe() override = default;
 
   VPWidenCallRecipe *clone() override {
-    return new VPWidenCallRecipe(getUnderlyingValue(), operands(),
-                                 VectorIntrinsicID, getDebugLoc(), Variant);
+    return new VPWidenCallRecipe(getUnderlyingValue(), Variant, operands(),
+                                 getDebugLoc());
   }
 
   VP_CLASSOF_IMPL(VPDef::VPWidenCallSC)

llvm/lib/Transforms/Vectorize/VPlanAnalysis.cpp

@@ -268,6 +268,8 @@ Type *VPTypeAnalysis::inferScalarType(const VPValue *V) {
                 VPReplicateRecipe, VPWidenCallRecipe, VPWidenMemoryRecipe,
                 VPWidenSelectRecipe>(
               [this](const auto *R) { return inferScalarTypeForRecipe(R); })
+          .Case<VPWidenIntrinsicRecipe>(
+              [](const VPWidenIntrinsicRecipe *R) { return R->getResultTy(); })
           .Case<VPInterleaveRecipe>([V](const VPInterleaveRecipe *R) {
             // TODO: Use info from interleave group.
             return V->getUnderlyingValue()->getType();