[LoopVectorizer] Fix for cost values of memory accesses.

This commit is a combination of two patches:

* "Fix in getScalarizationOverhead()"

   If target returns false in TTI.prefersVectorizedAddressing(), it means the
   address registers will not need to be extracted. Therefore, there should
   be no operands scalarization overhead for a load instruction.

* "Don't pass the instruction pointer from getMemInstScalarizationCost."

   Since VF is always > 1, this is a cost query for an instruction in the
   vectorized loop and it should not be evaluated within the scalar
   context of the instruction.

Review: Ulrich Weigand, Hal Finkel
https://reviews.llvm.org/D52351
https://reviews.llvm.org/D52417

llvm-svn: 345603

1 files changed, 8 insertions, 1 deletions

diff --git a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
index f0a07eddc3b..006c13c233e 100644
--- a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
+++ b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
@@ -2982,6 +2982,10 @@ static unsigned getScalarizationOverhead(Instruction *I, unsigned VF,
        !TTI.supportsEfficientVectorElementLoadStore()))
     Cost += TTI.getScalarizationOverhead(RetTy, true, false);
 
+  // Some targets keep addresses scalar.
+  if (isa<LoadInst>(I) && !TTI.prefersVectorizedAddressing())
+    return Cost;
+
   if (CallInst *CI = dyn_cast<CallInst>(I)) {
     SmallVector<const Value *, 4> Operands(CI->arg_operands());
     Cost += TTI.getOperandsScalarizationOverhead(Operands, VF);
@@ -5372,6 +5376,7 @@ static bool isStrideMul(Instruction *I, LoopVectorizationLegality *Legal) {
 
 unsigned LoopVectorizationCostModel::getMemInstScalarizationCost(Instruction *I,
                                                                  unsigned VF) {
+  assert(VF > 1 && "Scalarization cost of instruction implies vectorization.");
   Type *ValTy = getMemInstValueType(I);
   auto SE = PSE.getSE();
 
@@ -5387,9 +5392,11 @@ unsigned LoopVectorizationCostModel::getMemInstScalarizationCost(Instruction *I,
   // Get the cost of the scalar memory instruction and address computation.
   unsigned Cost = VF * TTI.getAddressComputationCost(PtrTy, SE, PtrSCEV);
 
+  // Don't pass *I here, since it is scalar but will actually be part of a
+  // vectorized loop where the user of it is a vectorized instruction.
   Cost += VF *
           TTI.getMemoryOpCost(I->getOpcode(), ValTy->getScalarType(), Alignment,
-                              AS, I);
+                              AS);
 
   // Get the overhead of the extractelement and insertelement instructions
   // we might create due to scalarization.