2 files changed, 7 insertions, 3 deletions
diff --git a/llvm/lib/Target/ARM/ARMTargetTransformInfo.cpp b/llvm/lib/Target/ARM/ARMTargetTransformInfo.cpp
index 10e6297ef1e..cc001b59678 100644
--- a/llvm/lib/Target/ARM/ARMTargetTransformInfo.cpp
+++ b/llvm/lib/Target/ARM/ARMTargetTransformInfo.cpp
@@ -338,14 +338,17 @@ int ARMTTIImpl::getCmpSelInstrCost(unsigned Opcode, Type *ValTy, Type *CondTy) {
   return BaseT::getCmpSelInstrCost(Opcode, ValTy, CondTy);
 }
 
-int ARMTTIImpl::getAddressComputationCost(Type *Ty, bool IsComplex) {
+int ARMTTIImpl::getAddressComputationCost(Type *Ty, ScalarEvolution *SE,
+                                          const SCEV *Ptr) {
   // Address computations in vectorized code with non-consecutive addresses will
   // likely result in more instructions compared to scalar code where the
   // computation can more often be merged into the index mode. The resulting
   // extra micro-ops can significantly decrease throughput.
   unsigned NumVectorInstToHideOverhead = 10;
+  int MaxMergeDistance = 64;
 
-  if (Ty->isVectorTy() && IsComplex)
+  if (Ty->isVectorTy() && SE && 
+      !BaseT::isConstantStridedAccessLessThan(SE, Ptr, MaxMergeDistance + 1))
     return NumVectorInstToHideOverhead;
 
   // In many cases the address computation is not merged into the instruction
diff --git a/llvm/lib/Target/ARM/ARMTargetTransformInfo.h b/llvm/lib/Target/ARM/ARMTargetTransformInfo.h
index d83228afb0a..731a5adf3d7 100644
--- a/llvm/lib/Target/ARM/ARMTargetTransformInfo.h
+++ b/llvm/lib/Target/ARM/ARMTargetTransformInfo.h
@@ -104,7 +104,8 @@ public:
 
   int getVectorInstrCost(unsigned Opcode, Type *Val, unsigned Index);
 
-  int getAddressComputationCost(Type *Val, bool IsComplex);
+  int getAddressComputationCost(Type *Val, ScalarEvolution *SE, 
+                                const SCEV *Ptr);
 
   int getFPOpCost(Type *Ty);