Index: lib/Transforms/Vectorize/LoopVectorize.cpp
===================================================================
--- lib/Transforms/Vectorize/LoopVectorize.cpp
+++ lib/Transforms/Vectorize/LoopVectorize.cpp
@@ -5241,6 +5241,7 @@
 
 unsigned LoopVectorizationCostModel::getMemInstScalarizationCost(Instruction *I,
                                                                  unsigned VF) {
+  assert(VF > 1 && "Scalarization cost of instruction implies vectorization.");
   Type *ValTy = getMemInstValueType(I);
   auto SE = PSE.getSE();
 
@@ -5258,7 +5259,7 @@
 
   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.
Index: test/Transforms/LoopVectorize/SystemZ/load-scalarization-cost-1.ll
===================================================================
--- /dev/null
+++ test/Transforms/LoopVectorize/SystemZ/load-scalarization-cost-1.ll
@@ -0,0 +1,26 @@
+; RUN: opt -mtriple=s390x-unknown-linux -mcpu=z13 -loop-vectorize \
+; RUN:   -force-vector-width=4 -debug-only=loop-vectorize \
+; RUN:   -enable-interleaved-mem-accesses=false -disable-output < %s 2>&1 \
+; RUN:   | FileCheck %s
+; REQUIRES: asserts
+;
+
+define i32 @fun(i64* %data, i64 %n, i64 %s, i32* %Src) {
+entry:
+  br label %for.body
+
+for.body:
+  %iv = phi i64 [ 0, %entry ], [ %iv.next, %for.body ]
+  %acc = phi i32 [ 0, %entry ], [ %acc_next, %for.body ]
+  %gep = getelementptr inbounds i32, i32* %Src, i64 %iv
+  %ld = load i32, i32* %gep
+  %acc_next = add i32 %acc, %ld
+  %iv.next = add nuw nsw i64 %iv, 2
+  %cmp110.us = icmp slt i64 %iv.next, %n
+  br i1 %cmp110.us, label %for.body, label %for.end
+
+for.end:
+  ret i32 %acc_next
+
+; CHECK: Found an estimated cost of 4 for VF 4 For instruction:   %ld = load i32, i32* %gep
+}