[AArch64][CostModel] Improve cost estimate of scalarizing a vector division

In the backend, last resort of finding the vector division cost is to use its scalar cost. However, without knowledge about the division operands, the cost can be off in certain cases.

For SLP, this patch tries to pass scalars for better scalar cost estimation in the backend.

Author: sushgokh

llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp

@@ -3572,6 +3572,20 @@ InstructionCost AArch64TTIImpl::getArithmeticInstrCost(
           Cost *= 4;
         return Cost;
       } else {
+        // If the information about individual scalars being vectorized is
+        // available, this yeilds better cost estimation.
+        if (auto *VTy = dyn_cast<FixedVectorType>(Ty); VTy && !Args.empty()) {
+          InstructionCost InsertExtractCost =
+              ST->getVectorInsertExtractBaseCost();
+          Cost = (3 * InsertExtractCost) * VTy->getNumElements();
+          for (int i = 0, Sz = Args.size(); i < Sz; i += 2) {
+            Cost += getArithmeticInstrCost(
+                Opcode, VTy->getScalarType(), CostKind,
+                TTI::getOperandInfo(Args[i]), TTI::getOperandInfo(Args[i + 1]));
+          }
+          return Cost;
+        }
+
         // If one of the operands is a uniform constant then the cost for each
         // element is Cost for insertion, extraction and division.
         // Insertion cost = 2, Extraction Cost = 2, Division = cost for the

llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp

@@ -11650,9 +11650,20 @@ BoUpSLP::getEntryCost(const TreeEntry *E, ArrayRef<Value *> VectorizedVals,
       unsigned OpIdx = isa<UnaryOperator>(VL0) ? 0 : 1;
       TTI::OperandValueInfo Op1Info = getOperandInfo(E->getOperand(0));
       TTI::OperandValueInfo Op2Info = getOperandInfo(E->getOperand(OpIdx));
-      return TTI->getArithmeticInstrCost(ShuffleOrOp, VecTy, CostKind, Op1Info,
-                                         Op2Info, {}, nullptr, TLI) +
-             CommonCost;
+      SmallVector<Value *, 16> Operands;
+      if (all_of(E->Scalars, [ShuffleOrOp](Value *V) {
+            return !IsaPred<UndefValue, PoisonValue>(V) &&
+                   cast<Instruction>(V)->getOpcode() == ShuffleOrOp;
+          })) {
+        for (auto *Scalar : E->Scalars) {
+          Instruction *I = cast<Instruction>(Scalar);
+          auto IOperands = I->operand_values();
+          Operands.insert(Operands.end(), IOperands.begin(), IOperands.end());
+        }
+      }
+      return CommonCost +
+             TTI->getArithmeticInstrCost(ShuffleOrOp, VecTy, CostKind, Op1Info,
+                                         Op2Info, Operands, nullptr, TLI);
     };
     return GetCostDiff(GetScalarCost, GetVectorCost);
   }