[LV] Move code from widenInstruction to VPWidenRecipe. (NFC)

[fhahn]

Summary

The code in widenInstruction has already been transitioned to
only rely on information provided by VPWidenRecipe directly.

Moving the code directly to VPWidenRecipe::execute completes
the transition for the recipe.

It provides the following advantages:

1. Less indirection, easier to see what's going on.
2. Removes accesses to fields of ILV.

2. in particular ensures that no dependencies on

fields in ILV for vector code generation are re-introduced.

[fhahn]

rebased after 4348cd42c385

[Ayal]

Looks good to me, with a small nit.

llvm/lib/Transforms/Vectorize/LoopVectorize.cpp

480

Above comment for widenCallInstruction() should be retained.

[fhahn]

llvm/lib/Transforms/Vectorize/LoopVectorize.cpp

480

Thanks, the committed version retains the accidentally dropped comment.

llvm/lib/Transforms/Vectorize/LoopVectorize.cpp

public:
   /// on, while the old loop will be used as the scalar remainder. Control flow
   /// is generated around the vectorized (and scalar epilogue) loops consisting
   /// of various checks and bypasses. Return the pre-header block of the new
   /// loop.
   /// In the case of epilogue vectorization, this function is overriden to
   /// handle the more complex control flow around the loops.
   virtual BasicBlock *createVectorizedLoopSkeleton();
 
-  /// Widen a single instruction within the innermost loop.
-  void widenInstruction(Instruction &I, VPWidenRecipe *WidenRec,
-                        VPTransformState &State);
-
-  /// Widen a single call instruction within the innermost loop.
   void widenCallInstruction(CallInst &I, VPValue *Def, VPUser &ArgOperands,
                             VPTransformState &State);
 
   /// Widen a single select instruction within the innermost loop.
   void widenSelectInstruction(SelectInst &I, VPValue *VPDef, VPUser &Operands,
                               bool InvariantCond, VPTransformState &State);
 
   /// Fix the vectorized code, taking care of header phi's, live-outs, and more.
assert((I.getOpcode() == Instruction::UDiv ||
           I.getOpcode() == Instruction::URem ||
           I.getOpcode() == Instruction::SRem) &&
          "Unexpected instruction");
   Value *Divisor = I.getOperand(1);
   auto *CInt = dyn_cast<ConstantInt>(Divisor);
   return !CInt || CInt->isZero();
 }
 
-void InnerLoopVectorizer::widenInstruction(Instruction &I,
-                                           VPWidenRecipe *WidenRec,
-                                           VPTransformState &State) {
-  switch (I.getOpcode()) {
-  case Instruction::Call:
-  case Instruction::Br:
-  case Instruction::PHI:
-  case Instruction::GetElementPtr:
-  case Instruction::Select:
-    llvm_unreachable("This instruction is handled by a different recipe.");
-  case Instruction::UDiv:
-  case Instruction::SDiv:
-  case Instruction::SRem:
-  case Instruction::URem:
-  case Instruction::Add:
-  case Instruction::FAdd:
-  case Instruction::Sub:
-  case Instruction::FSub:
-  case Instruction::FNeg:
-  case Instruction::Mul:
-  case Instruction::FMul:
-  case Instruction::FDiv:
-  case Instruction::FRem:
-  case Instruction::Shl:
-  case Instruction::LShr:
-  case Instruction::AShr:
-  case Instruction::And:
-  case Instruction::Or:
-  case Instruction::Xor: {
-    // Just widen unops and binops.
-    setDebugLocFromInst(&I);
-
-    for (unsigned Part = 0; Part < UF; ++Part) {
-      SmallVector<Value *, 2> Ops;
-      for (VPValue *VPOp : WidenRec->operands())
-        Ops.push_back(State.get(VPOp, Part));
-
-      Value *V = Builder.CreateNAryOp(I.getOpcode(), Ops);
-
-      if (auto *VecOp = dyn_cast<Instruction>(V)) {
-        VecOp->copyIRFlags(&I);
-
-        // If the instruction is vectorized and was in a basic block that needed
-        // predication, we can't propagate poison-generating flags (nuw/nsw,
-        // exact, etc.). The control flow has been linearized and the
-        // instruction is no longer guarded by the predicate, which could make
-        // the flag properties to no longer hold.
-        if (State.MayGeneratePoisonRecipes.count(WidenRec) > 0)
-          VecOp->dropPoisonGeneratingFlags();
-      }
-
-      // Use this vector value for all users of the original instruction.
-      State.set(WidenRec, V, Part);
-      addMetadata(V, &I);
-    }
-
-    break;
-  }
-  case Instruction::ICmp:
-  case Instruction::FCmp: {
-    // Widen compares. Generate vector compares.
-    bool FCmp = (I.getOpcode() == Instruction::FCmp);
-    auto *Cmp = cast<CmpInst>(&I);
-    setDebugLocFromInst(Cmp);
-    for (unsigned Part = 0; Part < UF; ++Part) {
-      Value *A = State.get(WidenRec->getOperand(0), Part);
-      Value *B = State.get(WidenRec->getOperand(1), Part);
-      Value *C = nullptr;
-      if (FCmp) {
-        // Propagate fast math flags.
-        IRBuilder<>::FastMathFlagGuard FMFG(Builder);
-        Builder.setFastMathFlags(Cmp->getFastMathFlags());
-        C = Builder.CreateFCmp(Cmp->getPredicate(), A, B);
-      } else {
-        C = Builder.CreateICmp(Cmp->getPredicate(), A, B);
-      }
-      State.set(WidenRec, C, Part);
-      addMetadata(C, &I);
-    }
-
-    break;
-  }
-
-  case Instruction::ZExt:
-  case Instruction::SExt:
-  case Instruction::FPToUI:
-  case Instruction::FPToSI:
-  case Instruction::FPExt:
-  case Instruction::PtrToInt:
-  case Instruction::IntToPtr:
-  case Instruction::SIToFP:
-  case Instruction::UIToFP:
-  case Instruction::Trunc:
-  case Instruction::FPTrunc:
-  case Instruction::BitCast: {
-    auto *CI = cast<CastInst>(&I);
-    setDebugLocFromInst(CI);
-
-    /// Vectorize casts.
-    Type *DestTy =
-        (VF.isScalar()) ? CI->getType() : VectorType::get(CI->getType(), VF);
-
-    for (unsigned Part = 0; Part < UF; ++Part) {
-      Value *A = State.get(WidenRec->getOperand(0), Part);
-      Value *Cast = Builder.CreateCast(CI->getOpcode(), A, DestTy);
-      State.set(WidenRec, Cast, Part);
-      addMetadata(Cast, &I);
-    }
-    break;
-  }
-  default:
-    // This instruction is not vectorized by simple widening.
-    LLVM_DEBUG(dbgs() << "LV: Found an unhandled instruction: " << I);
-    llvm_unreachable("Unhandled instruction!");
-  } // end of switch.
-}
-
 void InnerLoopVectorizer::widenCallInstruction(CallInst &I, VPValue *Def,
                                                VPUser &ArgOperands,
                                                VPTransformState &State) {
   assert(!isa<DbgInfoIntrinsic>(I) &&
          "DbgInfoIntrinsic should have been dropped during VPlan construction");
   setDebugLocFromInst(&I);
 
   Module *M = I.getParent()->getParent()->getParent();

 }
 
 void VPWidenSelectRecipe::execute(VPTransformState &State) {
   State.ILV->widenSelectInstruction(*cast<SelectInst>(getUnderlyingInstr()),
                                     this, *this, InvariantCond, State);
 }
 
 void VPWidenRecipe::execute(VPTransformState &State) {
-  State.ILV->widenInstruction(*getUnderlyingInstr(), this, State);
+  auto &I = *cast<Instruction>(getUnderlyingValue());
+  auto &Builder = State.Builder;
+  switch (I.getOpcode()) {
+  case Instruction::Call:
+  case Instruction::Br:
+  case Instruction::PHI:
+  case Instruction::GetElementPtr:
+  case Instruction::Select:
+    llvm_unreachable("This instruction is handled by a different recipe.");
+  case Instruction::UDiv:
+  case Instruction::SDiv:
+  case Instruction::SRem:
+  case Instruction::URem:
+  case Instruction::Add:
+  case Instruction::FAdd:
+  case Instruction::Sub:
+  case Instruction::FSub:
+  case Instruction::FNeg:
+  case Instruction::Mul:
+  case Instruction::FMul:
+  case Instruction::FDiv:
+  case Instruction::FRem:
+  case Instruction::Shl:
+  case Instruction::LShr:
+  case Instruction::AShr:
+  case Instruction::And:
+  case Instruction::Or:
+  case Instruction::Xor: {
+    // Just widen unops and binops.
+    State.ILV->setDebugLocFromInst(&I);
+
+    for (unsigned Part = 0; Part < State.UF; ++Part) {
+      SmallVector<Value *, 2> Ops;
+      for (VPValue *VPOp : operands())
+        Ops.push_back(State.get(VPOp, Part));
+
+      Value *V = Builder.CreateNAryOp(I.getOpcode(), Ops);
+
+      if (auto *VecOp = dyn_cast<Instruction>(V)) {
+        VecOp->copyIRFlags(&I);
+
+        // If the instruction is vectorized and was in a basic block that needed
+        // predication, we can't propagate poison-generating flags (nuw/nsw,
+        // exact, etc.). The control flow has been linearized and the
+        // instruction is no longer guarded by the predicate, which could make
+        // the flag properties to no longer hold.
+        if (State.MayGeneratePoisonRecipes.count(this) > 0)
+          VecOp->dropPoisonGeneratingFlags();
+      }
+
+      // Use this vector value for all users of the original instruction.
+      State.set(this, V, Part);
+      State.ILV->addMetadata(V, &I);
+    }
+
+    break;
+  }
+  case Instruction::ICmp:
+  case Instruction::FCmp: {
+    // Widen compares. Generate vector compares.
+    bool FCmp = (I.getOpcode() == Instruction::FCmp);
+    auto *Cmp = cast<CmpInst>(&I);
+    State.ILV->setDebugLocFromInst(Cmp);
+    for (unsigned Part = 0; Part < State.UF; ++Part) {
+      Value *A = State.get(getOperand(0), Part);
+      Value *B = State.get(getOperand(1), Part);
+      Value *C = nullptr;
+      if (FCmp) {
+        // Propagate fast math flags.
+        IRBuilder<>::FastMathFlagGuard FMFG(Builder);
+        Builder.setFastMathFlags(Cmp->getFastMathFlags());
+        C = Builder.CreateFCmp(Cmp->getPredicate(), A, B);
+      } else {
+        C = Builder.CreateICmp(Cmp->getPredicate(), A, B);
+      }
+      State.set(this, C, Part);
+      State.ILV->addMetadata(C, &I);
+    }
+
+    break;
+  }
+
+  case Instruction::ZExt:
+  case Instruction::SExt:
+  case Instruction::FPToUI:
+  case Instruction::FPToSI:
+  case Instruction::FPExt:
+  case Instruction::PtrToInt:
+  case Instruction::IntToPtr:
+  case Instruction::SIToFP:
+  case Instruction::UIToFP:
+  case Instruction::Trunc:
+  case Instruction::FPTrunc:
+  case Instruction::BitCast: {
+    auto *CI = cast<CastInst>(&I);
+    State.ILV->setDebugLocFromInst(CI);
+
+    /// Vectorize casts.
+    Type *DestTy = (State.VF.isScalar())
+                       ? CI->getType()
+                       : VectorType::get(CI->getType(), State.VF);
+
+    for (unsigned Part = 0; Part < State.UF; ++Part) {
+      Value *A = State.get(getOperand(0), Part);
+      Value *Cast = Builder.CreateCast(CI->getOpcode(), A, DestTy);
+      State.set(this, Cast, Part);
+      State.ILV->addMetadata(Cast, &I);
+    }
+    break;
+  }
+  default:
+    // This instruction is not vectorized by simple widening.
+    LLVM_DEBUG(dbgs() << "LV: Found an unhandled instruction: " << I);
+    llvm_unreachable("Unhandled instruction!");
+  } // end of switch.
 }
 
 void VPWidenGEPRecipe::execute(VPTransformState &State) {
   auto *GEP = cast<GetElementPtrInst>(getUnderlyingInstr());
   // Construct a vector GEP by widening the operands of the scalar GEP as
   // necessary. We mark the vector GEP 'inbounds' if appropriate. A GEP
   // results in a vector of pointers when at least one operand of the GEP
   // is vector-typed. Thus, to keep the representation compact, we only use