[LV] Use getScalarizationOverhead in memory instruction costs (NFC)

This patch refactors the cost estimation of scalarized loads and stores to
reuse getScalarizationOverhead for the cost of the extractelement and
insertelement instructions we might create. The existing code accounted for
this cost, but it was functionally equivalent to the helper function.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@283364 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/Transforms/Vectorize/LoopVectorize.cpp b/lib/Transforms/Vectorize/LoopVectorize.cpp
index 9bffb1d..be45b6b 100644 (file)
--- a/lib/Transforms/Vectorize/LoopVectorize.cpp
+++ b/lib/Transforms/Vectorize/LoopVectorize.cpp
@@ -6676,27 +6676,23 @@ unsigned LoopVectorizationCostModel::getInstructionCost(Instruction *I,
 
     // Check if the memory instruction will be scalarized.
     if (Legal->memoryInstructionMustBeScalarized(I, VF)) {
-      bool IsComplexComputation =
-          isLikelyComplexAddressComputation(Ptr, Legal, SE, TheLoop);
       unsigned Cost = 0;
-      // The cost of extracting from the value vector and pointer vector.
       Type *PtrTy = ToVectorTy(Ptr->getType(), VF);
-      for (unsigned i = 0; i < VF; ++i) {
-        //  The cost of extracting the pointer operand.
-        Cost += TTI.getVectorInstrCost(Instruction::ExtractElement, PtrTy, i);
-        // In case of STORE, the cost of ExtractElement from the vector.
-        // In case of LOAD, the cost of InsertElement into the returned
-        // vector.
-        Cost += TTI.getVectorInstrCost(SI ? Instruction::ExtractElement
-                                          : Instruction::InsertElement,
-                                       VectorTy, i);
-      }
 
-      // The cost of the scalar loads/stores.
+      // True if the memory instruction's address computation is complex.
+      bool IsComplexComputation =
+          isLikelyComplexAddressComputation(Ptr, Legal, SE, TheLoop);
+
+      // Get the cost of the scalar memory instruction and address computation.
       Cost += VF * TTI.getAddressComputationCost(PtrTy, IsComplexComputation);
       Cost += VF *
               TTI.getMemoryOpCost(I->getOpcode(), ValTy->getScalarType(),
                                   Alignment, AS);
+
+      // Get the overhead of the extractelement and insertelement instructions
+      // we might create due to scalarization.
+      Cost += getScalarizationOverhead(I, VF, false, TTI);
+
       return Cost;
     }