Index: lib/Analysis/InlineCost.cpp
===================================================================
--- lib/Analysis/InlineCost.cpp
+++ lib/Analysis/InlineCost.cpp
@@ -134,6 +134,7 @@
   void accumulateSROACost(DenseMap<Value *, int>::iterator CostIt,
                           int InstructionCost);
   bool isGEPOffsetConstant(GetElementPtrInst &GEP);
+  bool isGEPFree(GetElementPtrInst &GEP);
   bool accumulateGEPOffset(GEPOperator &GEP, APInt &Offset);
   bool simplifyCallSite(Function *F, CallSite CS);
   ConstantInt *stripAndComputeInBoundsConstantOffsets(Value *&V);
@@ -331,6 +332,21 @@
   return true;
 }
 
+/// \brief Use TTI to check whether a GEP is free.
+///
+/// Respects any simplified values known during the analysis of this callsite.
+bool CallAnalyzer::isGEPFree(GetElementPtrInst &GEP) {
+  SmallVector<Value *, 4> Indices;
+  for (User::op_iterator I = GEP.idx_begin(), E = GEP.idx_end(); I != E; ++I)
+    if (Constant *SimpleOp = SimplifiedValues.lookup(*I))
+       Indices.push_back(SimpleOp);
+     else
+       Indices.push_back(*I);
+  return TargetTransformInfo::TCC_Free ==
+         TTI.getGEPCost(GEP.getSourceElementType(), GEP.getPointerOperand(),
+                        Indices);
+}
+
 bool CallAnalyzer::visitAlloca(AllocaInst &I) {
   // Check whether inlining will turn a dynamic alloca into a static
   // alloca and handle that case.
@@ -396,7 +412,7 @@
         // Non-constant GEPs aren't folded, and disable SROA.
         if (SROACandidate)
           disableSROA(CostIt);
-        return false;
+        return isGEPFree(I);
       }
 
       // Add the result as a new mapping to Base + Offset.
@@ -422,7 +438,7 @@
   // Variable GEPs will require math and will disable SROA.
   if (SROACandidate)
     disableSROA(CostIt);
-  return false;
+  return isGEPFree(I);
 }
 
 bool CallAnalyzer::visitBitCast(BitCastInst &I) {
Index: test/Transforms/Inline/gep-cost.ll
===================================================================
--- /dev/null
+++ test/Transforms/Inline/gep-cost.ll
@@ -0,0 +1,25 @@
+; RUN: opt -inline < %s -S -debug-only=inline-cost 2>&1 | FileCheck %s
+
+target datalayout = "e-m:e-i64:64-i128:128-n32:64-S128"
+target triple = "aarch64--linux-gnu"
+
+define void @outer1([4 x i32]* %ptr1, [4 x [4 x i32]]* %ptr2, i32 %i) {
+  call void @inner1([4 x i32]* %ptr1, i32 %i)
+  call void @inner2([4 x [4 x i32]]* %ptr2, i32 %i)
+  ret void
+}
+; CHECK: Analyzing call of inner1
+; CHECK: NumInstructionsSimplified: 2
+; CHECK: NumInstructions: 2
+define void @inner1([4 x i32]* %ptr, i32 %i) {
+  %G = getelementptr inbounds [4 x i32], [4 x i32]* %ptr, i32 %i
+  ret void
+}
+
+; CHECK: Analyzing call of inner2
+; CHECK: NumInstructionsSimplified: 1
+; CHECK: NumInstructions: 2
+define void @inner2([4 x [4 x i32]]* %ptr, i32 %i) {
+  %G = getelementptr inbounds [4 x [4 x i32]], [4 x [4 x i32]]* %ptr, i32 1, i32 %i
+  ret void
+}