Remove unnecessary VPEVLBasedIVPHIRecipe.

Author: NexMing

llvm/lib/Transforms/Vectorize/LoopVectorize.cpp

@@ -2426,7 +2426,6 @@ InnerLoopVectorizer::getOrCreateVectorTripCount(BasicBlock *InsertBlock) {
     return VectorTripCount;
 
   Value *TC = getTripCount();
-  Type *Ty = TC->getType();
   IRBuilder<> Builder(InsertBlock->getTerminator());
 
   // Use original trip count as the vector trip count if use predicated EVL
@@ -2438,6 +2437,7 @@ InnerLoopVectorizer::getOrCreateVectorTripCount(BasicBlock *InsertBlock) {
     return VectorTripCount = TC;
   }
 
+  Type *Ty = TC->getType();
   // This is where we can make the step a runtime constant.
   Value *Step = createStepForVF(Builder, Ty, VF, UF);
 
@@ -4453,7 +4453,6 @@ static bool willGenerateVectors(VPlan &Plan, ElementCount VF,
       case VPDef::VPVectorPointerSC:
       case VPDef::VPVectorEndPointerSC:
       case VPDef::VPExpandSCEVSC:
-      case VPDef::VPEVLBasedIVPHISC:
       case VPDef::VPPredInstPHISC:
       case VPDef::VPBranchOnMaskSC:
         continue;

llvm/lib/Transforms/Vectorize/VPlan.h

@@ -506,7 +506,6 @@ class VPSingleDefRecipe : public VPRecipeBase, public VPValue {
   static inline bool classof(const VPRecipeBase *R) {
     switch (R->getVPDefID()) {
     case VPRecipeBase::VPDerivedIVSC:
-    case VPRecipeBase::VPEVLBasedIVPHISC:
     case VPRecipeBase::VPExpandSCEVSC:
     case VPRecipeBase::VPInstructionSC:
     case VPRecipeBase::VPReductionEVLSC:
@@ -2886,49 +2885,6 @@ class VPActiveLaneMaskPHIRecipe : public VPHeaderPHIRecipe {
 #endif
 };
 
-/// A recipe for generating the phi node for the current index of elements,
-/// adjusted in accordance with EVL value. It starts at the start value of the
-/// canonical induction and gets incremented by EVL in each iteration of the
-/// vector loop.
-class VPEVLBasedIVPHIRecipe : public VPHeaderPHIRecipe {
-public:
-  VPEVLBasedIVPHIRecipe(VPValue *StartIV, DebugLoc DL)
-      : VPHeaderPHIRecipe(VPDef::VPEVLBasedIVPHISC, nullptr, StartIV, DL) {}
-
-  ~VPEVLBasedIVPHIRecipe() override = default;
-
-  VPEVLBasedIVPHIRecipe *clone() override {
-    llvm_unreachable("cloning not implemented yet");
-  }
-
-  VP_CLASSOF_IMPL(VPDef::VPEVLBasedIVPHISC)
-
-  void execute(VPTransformState &State) override {
-    llvm_unreachable("cannot execute this recipe, should be replaced by a "
-                     "scalar phi recipe");
-  }
-
-  /// Return the cost of this VPEVLBasedIVPHIRecipe.
-  InstructionCost computeCost(ElementCount VF,
-                              VPCostContext &Ctx) const override {
-    // For now, match the behavior of the legacy cost model.
-    return 0;
-  }
-
-  /// Returns true if the recipe only uses the first lane of operand \p Op.
-  bool onlyFirstLaneUsed(const VPValue *Op) const override {
-    assert(is_contained(operands(), Op) &&
-           "Op must be an operand of the recipe");
-    return true;
-  }
-
-#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 the canonical induction variable of the vector loop.
 class VPWidenCanonicalIVRecipe : public VPSingleDefRecipe,
                                  public VPUnrollPartAccessor<1> {

llvm/lib/Transforms/Vectorize/VPlanAnalysis.cpp

@@ -243,14 +243,13 @@ Type *VPTypeAnalysis::inferScalarType(const VPValue *V) {
       TypeSwitch<const VPRecipeBase *, Type *>(V->getDefiningRecipe())
           .Case<VPActiveLaneMaskPHIRecipe, VPCanonicalIVPHIRecipe,
                 VPFirstOrderRecurrencePHIRecipe, VPReductionPHIRecipe,
-                VPWidenPointerInductionRecipe, VPEVLBasedIVPHIRecipe>(
-              [this](const auto *R) {
-                // Handle header phi recipes, except VPWidenIntOrFpInduction
-                // which needs special handling due it being possibly truncated.
-                // TODO: consider inferring/caching type of siblings, e.g.,
-                // backedge value, here and in cases below.
-                return inferScalarType(R->getStartValue());
-              })
+                VPWidenPointerInductionRecipe>([this](const auto *R) {
+            // Handle header phi recipes, except VPWidenIntOrFpInduction which
+            // needs special handling due it being possibly truncated.
+            // TODO: consider inferring/caching type of siblings, e.g., backedge
+            // value, here and in cases below.
+            return inferScalarType(R->getStartValue());
+          })
           .Case<VPWidenIntOrFpInductionRecipe, VPDerivedIVRecipe>(
               [](const auto *R) { return R->getScalarType(); })
           .Case<VPReductionRecipe, VPPredInstPHIRecipe, VPWidenPHIRecipe,

llvm/lib/Transforms/Vectorize/VPlanRecipes.cpp

@@ -3696,14 +3696,3 @@ void VPActiveLaneMaskPHIRecipe::print(raw_ostream &O, const Twine &Indent,
   printOperands(O, SlotTracker);
 }
 #endif
-
-#if !defined(NDEBUG) || defined(LLVM_ENABLE_DUMP)
-void VPEVLBasedIVPHIRecipe::print(raw_ostream &O, const Twine &Indent,
-                                  VPSlotTracker &SlotTracker) const {
-  O << Indent << "EXPLICIT-VECTOR-LENGTH-BASED-IV-PHI ";
-
-  printAsOperand(O, SlotTracker);
-  O << " = phi ";
-  printOperands(O, SlotTracker);
-}
-#endif

llvm/lib/Transforms/Vectorize/VPlanTransforms.cpp

@@ -1812,10 +1812,9 @@ static void transformRecipestoEVLRecipes(VPlan &Plan, VPValue &EVL) {
   }
 }
 
-/// Add a VPEVLBasedIVPHIRecipe and related recipes to \p Plan and
-/// replaces all uses except the canonical IV increment of
-/// VPCanonicalIVPHIRecipe with a VPEVLBasedIVPHIRecipe. VPCanonicalIVPHIRecipe
-/// is used only for loop iterations counting after this transformation.
+/// Add a VPInstruction::ExplicitVectorLength and related recipes to \p Plan and
+/// adjust the increment of the canonical induction variable to an explicit
+/// vector length.
 ///
 /// The function uses the following definitions:
 ///  %StartV is the canonical induction start value.
@@ -1826,29 +1825,25 @@ static void transformRecipestoEVLRecipes(VPlan &Plan, VPValue &EVL) {
 /// ...
 ///
 /// vector.body:
-/// ...
-/// %EVLPhi = EXPLICIT-VECTOR-LENGTH-BASED-IV-PHI [ %StartV, %vector.ph ],
-///                                               [ %NextEVLIV, %vector.body ]
-/// %AVL = sub original TC, %EVLPhi
+/// %IVPhi = CANONICAL-INDUCTION ir<0>, %IV.NEXT
+/// %AVL = sub original TC, %IVPhi
 /// %VPEVL = EXPLICIT-VECTOR-LENGTH %AVL
 /// ...
-/// %NextEVLIV = add IVSize (cast i32 %VPEVVL to IVSize), %EVLPhi
+/// %IV.NEXT = add %IVPhi IVSize (cast i32 %VPEVL to IVSize)
 /// ...
 ///
 /// If MaxSafeElements is provided, the function adds the following recipes:
 /// vector.ph:
 /// ...
 ///
 /// vector.body:
-/// ...
-/// %EVLPhi = EXPLICIT-VECTOR-LENGTH-BASED-IV-PHI [ %StartV, %vector.ph ],
-///                                               [ %NextEVLIV, %vector.body ]
+/// %IVPhi = CANONICAL-INDUCTION ir<0>, %IV.NEXT
 /// %AVL = sub original TC, %EVLPhi
 /// %cmp = cmp ult %AVL, MaxSafeElements
 /// %SAFE_AVL = select %cmp, %AVL, MaxSafeElements
 /// %VPEVL = EXPLICIT-VECTOR-LENGTH %SAFE_AVL
 /// ...
-/// %NextEVLIV = add IVSize (cast i32 %VPEVL to IVSize), %EVLPhi
+/// %IV.NEXT = add %IVPhi IVSize (cast i32 %VPEVL to IVSize)
 /// ...
 ///
 bool VPlanTransforms::tryAddExplicitVectorLength(
@@ -1864,16 +1859,11 @@ bool VPlanTransforms::tryAddExplicitVectorLength(
     return false;
 
   auto *CanonicalIVPHI = Plan.getCanonicalIV();
-  VPValue *StartV = CanonicalIVPHI->getStartValue();
-
-  // Create the ExplicitVectorLengthPhi recipe in the main loop.
-  auto *EVLPhi = new VPEVLBasedIVPHIRecipe(StartV, DebugLoc());
-  EVLPhi->insertAfter(CanonicalIVPHI);
   VPBuilder Builder(Header, Header->getFirstNonPhi());
   // Compute original TC - IV as the AVL (application vector length).
-  VPValue *AVL = Builder.createNaryOp(Instruction::Sub,
-                                      {&Plan.getVectorTripCount(), EVLPhi},
-                                      DebugLoc(), "avl");
+  VPValue *AVL = Builder.createNaryOp(
+      Instruction::Sub, {&Plan.getVectorTripCount(), CanonicalIVPHI},
+      DebugLoc(), "avl");
   if (MaxSafeElements) {
     // Support for MaxSafeDist for correct loop emission.
     VPValue *AVLSafe = Plan.getOrAddLiveIn(
@@ -1886,29 +1876,20 @@ bool VPlanTransforms::tryAddExplicitVectorLength(
 
   auto *CanonicalIVIncrement =
       cast<VPInstruction>(CanonicalIVPHI->getBackedgeValue());
-  Builder.setInsertPoint(CanonicalIVIncrement);
   VPSingleDefRecipe *OpVPEVL = VPEVL;
   if (unsigned IVSize = CanonicalIVPHI->getScalarType()->getScalarSizeInBits();
       IVSize != 32) {
     OpVPEVL = Builder.createScalarCast(
         IVSize < 32 ? Instruction::Trunc : Instruction::ZExt, OpVPEVL,
         CanonicalIVPHI->getScalarType(), CanonicalIVIncrement->getDebugLoc());
   }
-  auto *NextEVLIV = Builder.createOverflowingOp(
-      Instruction::Add, {OpVPEVL, EVLPhi},
-      {CanonicalIVIncrement->hasNoUnsignedWrap(),
-       CanonicalIVIncrement->hasNoSignedWrap()},
-      CanonicalIVIncrement->getDebugLoc(), "index.evl.next");
-  EVLPhi->addOperand(NextEVLIV);
 
   transformRecipestoEVLRecipes(Plan, *VPEVL);
 
-  // Replace all uses of VPCanonicalIVPHIRecipe by
-  // VPEVLBasedIVPHIRecipe except for the canonical IV increment.
-  CanonicalIVPHI->replaceAllUsesWith(EVLPhi);
-  CanonicalIVIncrement->replaceAllUsesWith(NextEVLIV);
+  // Adjust the increment of the canonical induction variable to an explicit
+  // vector length.
   CanonicalIVIncrement->setOperand(0, CanonicalIVPHI);
-  CanonicalIVPHI->setOperand(1, CanonicalIVIncrement);
+  CanonicalIVIncrement->setOperand(1, OpVPEVL);
   // TODO: support unroll factor > 1.
   Plan.setUF(1);
   return true;
@@ -2092,17 +2073,14 @@ void VPlanTransforms::convertToConcreteRecipes(VPlan &Plan) {
   for (VPBasicBlock *VPBB : VPBlockUtils::blocksOnly<VPBasicBlock>(
            vp_depth_first_deep(Plan.getEntry()))) {
     for (VPRecipeBase &R : make_early_inc_range(VPBB->phis())) {
-      if (!isa<VPCanonicalIVPHIRecipe, VPEVLBasedIVPHIRecipe>(&R))
-        continue;
-      auto *PhiR = cast<VPHeaderPHIRecipe>(&R);
-      StringRef Name =
-          isa<VPCanonicalIVPHIRecipe>(PhiR) ? "index" : "evl.based.iv";
-      auto *ScalarR = new VPInstruction(
-          Instruction::PHI, {PhiR->getStartValue(), PhiR->getBackedgeValue()},
-          PhiR->getDebugLoc(), Name);
-      ScalarR->insertBefore(PhiR);
-      PhiR->replaceAllUsesWith(ScalarR);
-      PhiR->eraseFromParent();
+      if (auto *PhiR = dyn_cast<VPCanonicalIVPHIRecipe>(&R)) {
+        auto *ScalarR = new VPInstruction(
+            Instruction::PHI, {PhiR->getStartValue(), PhiR->getBackedgeValue()},
+            PhiR->getDebugLoc(), "index");
+        ScalarR->insertBefore(PhiR);
+        PhiR->replaceAllUsesWith(ScalarR);
+        PhiR->eraseFromParent();
+      }
     }
   }
 }

llvm/lib/Transforms/Vectorize/VPlanTransforms.h

@@ -143,11 +143,9 @@ struct VPlanTransforms {
       VPlan &Plan,
       const std::function<bool(BasicBlock *)> &BlockNeedsPredication);
 
-  /// Add a VPEVLBasedIVPHIRecipe and related recipes to \p Plan and
-  /// replaces all uses except the canonical IV increment of
-  /// VPCanonicalIVPHIRecipe with a VPEVLBasedIVPHIRecipe.
-  /// VPCanonicalIVPHIRecipe is only used to control the loop after
-  /// this transformation.
+  /// Add a VPInstruction::ExplicitVectorLength and related recipes to \p Plan
+  /// and adjust the increment of the canonical induction variable to an
+  /// explicit vector length.
   /// \returns true if the transformation succeeds, or false if it doesn't.
   static bool
   tryAddExplicitVectorLength(VPlan &Plan,

llvm/lib/Transforms/Vectorize/VPlanValue.h

@@ -356,7 +356,6 @@ class VPDef {
     // VPHeaderPHIRecipe need to be kept together.
     VPCanonicalIVPHISC,
     VPActiveLaneMaskPHISC,
-    VPEVLBasedIVPHISC,
     VPFirstOrderRecurrencePHISC,
     VPWidenIntOrFpInductionSC,
     VPWidenPointerInductionSC,

llvm/lib/Transforms/Vectorize/VPlanVerifier.cpp

@@ -156,16 +156,6 @@ bool VPlanVerifier::verifyEVLRecipe(const VPInstruction &EVL) const {
             errs() << "EVL is used as an operand in non-VPInstruction::Add\n";
             return false;
           }
-          if (!all_of(I->users(), [](VPUser *U) {
-                if (auto *VPI = dyn_cast<VPInstruction>(U))
-                  return VPI->getOpcode() == VPInstruction::BranchOnCount;
-                return isa<VPEVLBasedIVPHIRecipe>(U);
-              })) {
-            errs()
-                << "Result of VPInstruction::Add with EVL operand is not used "
-                   "by VPEVLBasedIVPHIRecipe or VPInstruction::BranchOnCount\n";
-            return false;
-          }
           return true;
         })
         .Default([&](const VPUser *U) {