1 files changed, 41 insertions, 21 deletions

diff --git a/llvm/lib/Transforms/Vectorize/LoopVectorizationPlanner.h b/llvm/lib/Transforms/Vectorize/LoopVectorizationPlanner.h
index 13357cb06c55..577ce8000de2 100644
--- a/llvm/lib/Transforms/Vectorize/LoopVectorizationPlanner.h
+++ b/llvm/lib/Transforms/Vectorize/LoopVectorizationPlanner.h
@@ -31,6 +31,7 @@
 namespace llvm {
 
 class LoopInfo;
+class DominatorTree;
 class LoopVectorizationLegality;
 class LoopVectorizationCostModel;
 class PredicatedScalarEvolution;
@@ -45,13 +46,17 @@ class VPBuilder {
   VPBasicBlock *BB = nullptr;
   VPBasicBlock::iterator InsertPt = VPBasicBlock::iterator();
 
+  /// Insert \p VPI in BB at InsertPt if BB is set.
+  VPInstruction *tryInsertInstruction(VPInstruction *VPI) {
+    if (BB)
+      BB->insert(VPI, InsertPt);
+    return VPI;
+  }
+
   VPInstruction *createInstruction(unsigned Opcode,
                                    ArrayRef<VPValue *> Operands, DebugLoc DL,
                                    const Twine &Name = "") {
-    VPInstruction *Instr = new VPInstruction(Opcode, Operands, DL, Name);
-    if (BB)
-      BB->insert(Instr, InsertPt);
-    return Instr;
+    return tryInsertInstruction(new VPInstruction(Opcode, Operands, DL, Name));
   }
 
   VPInstruction *createInstruction(unsigned Opcode,
@@ -62,6 +67,7 @@ class VPBuilder {
 
 public:
   VPBuilder() = default;
+  VPBuilder(VPBasicBlock *InsertBB) { setInsertPoint(InsertBB); }
 
   /// Clear the insertion point: created instructions will not be inserted into
   /// a block.
@@ -116,10 +122,11 @@ public:
     InsertPt = IP;
   }
 
-  /// Insert and return the specified instruction.
-  VPInstruction *insert(VPInstruction *I) const {
-    BB->insert(I, InsertPt);
-    return I;
+  /// This specifies that created instructions should be inserted at the
+  /// specified point.
+  void setInsertPoint(VPRecipeBase *IP) {
+    BB = IP->getParent();
+    InsertPt = IP->getIterator();
   }
 
   /// Create an N-ary operation with \p Opcode, \p Operands and set \p Inst as
@@ -138,6 +145,13 @@ public:
     return createInstruction(Opcode, Operands, DL, Name);
   }
 
+  VPInstruction *createOverflowingOp(unsigned Opcode,
+                                     std::initializer_list<VPValue *> Operands,
+                                     VPRecipeWithIRFlags::WrapFlagsTy WrapFlags,
+                                     DebugLoc DL, const Twine &Name = "") {
+    return tryInsertInstruction(
+        new VPInstruction(Opcode, Operands, WrapFlags, DL, Name));
+  }
   VPValue *createNot(VPValue *Operand, DebugLoc DL, const Twine &Name = "") {
     return createInstruction(VPInstruction::Not, {Operand}, DL, Name);
   }
@@ -158,6 +172,12 @@ public:
                         Name);
   }
 
+  /// Create a new ICmp VPInstruction with predicate \p Pred and operands \p A
+  /// and \p B.
+  /// TODO: add createFCmp when needed.
+  VPValue *createICmp(CmpInst::Predicate Pred, VPValue *A, VPValue *B,
+                      DebugLoc DL = {}, const Twine &Name = "");
+
   //===--------------------------------------------------------------------===//
   // RAII helpers.
   //===--------------------------------------------------------------------===//
@@ -268,6 +288,9 @@ class LoopVectorizationPlanner {
   /// Loop Info analysis.
   LoopInfo *LI;
 
+  /// The dominator tree.
+  DominatorTree *DT;
+
   /// Target Library Info.
   const TargetLibraryInfo *TLI;
 
@@ -298,16 +321,14 @@ class LoopVectorizationPlanner {
   VPBuilder Builder;
 
 public:
-  LoopVectorizationPlanner(Loop *L, LoopInfo *LI, const TargetLibraryInfo *TLI,
-                           const TargetTransformInfo &TTI,
-                           LoopVectorizationLegality *Legal,
-                           LoopVectorizationCostModel &CM,
-                           InterleavedAccessInfo &IAI,
-                           PredicatedScalarEvolution &PSE,
-                           const LoopVectorizeHints &Hints,
-                           OptimizationRemarkEmitter *ORE)
-      : OrigLoop(L), LI(LI), TLI(TLI), TTI(TTI), Legal(Legal), CM(CM), IAI(IAI),
-        PSE(PSE), Hints(Hints), ORE(ORE) {}
+  LoopVectorizationPlanner(
+      Loop *L, LoopInfo *LI, DominatorTree *DT, const TargetLibraryInfo *TLI,
+      const TargetTransformInfo &TTI, LoopVectorizationLegality *Legal,
+      LoopVectorizationCostModel &CM, InterleavedAccessInfo &IAI,
+      PredicatedScalarEvolution &PSE, const LoopVectorizeHints &Hints,
+      OptimizationRemarkEmitter *ORE)
+      : OrigLoop(L), LI(LI), DT(DT), TLI(TLI), TTI(TTI), Legal(Legal), CM(CM),
+        IAI(IAI), PSE(PSE), Hints(Hints), ORE(ORE) {}
 
   /// Plan how to best vectorize, return the best VF and its cost, or
   /// std::nullopt if vectorization and interleaving should be avoided up front.
@@ -333,7 +354,7 @@ public:
   executePlan(ElementCount VF, unsigned UF, VPlan &BestPlan,
               InnerLoopVectorizer &LB, DominatorTree *DT,
               bool IsEpilogueVectorization,
-              DenseMap<const SCEV *, Value *> *ExpandedSCEVs = nullptr);
+              const DenseMap<const SCEV *, Value *> *ExpandedSCEVs = nullptr);
 
 #if !defined(NDEBUG) || defined(LLVM_ENABLE_DUMP)
   void printPlans(raw_ostream &O);
@@ -377,8 +398,7 @@ private:
   /// returned VPlan is valid for. If no VPlan can be built for the input range,
   /// set the largest included VF to the maximum VF for which no plan could be
   /// built.
-  std::optional<VPlanPtr> tryToBuildVPlanWithVPRecipes(
-      VFRange &Range, SmallPtrSetImpl<Instruction *> &DeadInstructions);
+  VPlanPtr tryToBuildVPlanWithVPRecipes(VFRange &Range);
 
   /// Build VPlans for power-of-2 VF's between \p MinVF and \p MaxVF inclusive,
   /// according to the information gathered by Legal when it checked if it is