Index: llvm/lib/Transforms/InstCombine/InstCombineInternal.h
===================================================================
--- llvm/lib/Transforms/InstCombine/InstCombineInternal.h
+++ llvm/lib/Transforms/InstCombine/InstCombineInternal.h
@@ -296,6 +296,7 @@
   AssumptionCache ∾
   TargetLibraryInfo &TLI;
   DominatorTree &DT;
+  TargetTransformInfo &TTI;
   const DataLayout &DL;
   const SimplifyQuery SQ;
   OptimizationRemarkEmitter &ORE;
@@ -310,11 +311,12 @@
   InstCombiner(InstCombineWorklist &Worklist, BuilderTy &Builder,
                bool MinimizeSize, bool ExpensiveCombines, AliasAnalysis *AA,
                AssumptionCache &AC, TargetLibraryInfo &TLI, DominatorTree &DT,
+               TargetTransformInfo &TTI ,
                OptimizationRemarkEmitter &ORE, const DataLayout &DL,
                LoopInfo *LI)
       : Worklist(Worklist), Builder(Builder), MinimizeSize(MinimizeSize),
         ExpensiveCombines(ExpensiveCombines), AA(AA), AC(AC), TLI(TLI), DT(DT),
-        DL(DL), SQ(DL, &TLI, &DT, &AC), ORE(ORE), LI(LI) {}
+        TTI(TTI), DL(DL), SQ(DL, &TLI, &DT, &AC), ORE(ORE), LI(LI) {}
 
   /// Run the combiner over the entire worklist until it is empty.
   ///
Index: llvm/lib/Transforms/InstCombine/InstructionCombining.cpp
===================================================================
--- llvm/lib/Transforms/InstCombine/InstructionCombining.cpp
+++ llvm/lib/Transforms/InstCombine/InstructionCombining.cpp
@@ -57,6 +57,7 @@
 #include "llvm/Analysis/OptimizationRemarkEmitter.h"
 #include "llvm/Analysis/TargetFolder.h"
 #include "llvm/Analysis/TargetLibraryInfo.h"
+#include "llvm/Analysis/TargetTransformInfo.h"
 #include "llvm/Transforms/Utils/Local.h"
 #include "llvm/Analysis/ValueTracking.h"
 #include "llvm/IR/BasicBlock.h"
@@ -1676,6 +1677,15 @@
          I != E; ++I)
       EndsWithSequential = I.isSequential();
 
+    if (isa<Instruction>(Src) && !Src->hasOneUse() &&
+        TTI.getUserCost(Src) != TargetTransformInfo::TCC_Free) {
+      BasicBlock *CurBB = GEP.getParent();
+      for (User *U : Src->users())
+        if (Instruction *UI = dyn_cast<Instruction>(U))
+          if (UI->getParent() != CurBB)
+            return nullptr;
+    }
+
     // Can we combine the two pointer arithmetics offsets?
     if (EndsWithSequential) {
       // Replace: gep (gep %P, long B), long A, ...
@@ -3257,6 +3267,7 @@
 static bool combineInstructionsOverFunction(
     Function &F, InstCombineWorklist &Worklist, AliasAnalysis *AA,
     AssumptionCache &AC, TargetLibraryInfo &TLI, DominatorTree &DT,
+    TargetTransformInfo &TTI,
     OptimizationRemarkEmitter &ORE, bool ExpensiveCombines = true,
     LoopInfo *LI = nullptr) {
   auto &DL = F.getParent()->getDataLayout();
@@ -3288,7 +3299,7 @@
     MadeIRChange |= prepareICWorklistFromFunction(F, DL, &TLI, Worklist);
 
     InstCombiner IC(Worklist, Builder, F.optForMinSize(), ExpensiveCombines, AA,
-                    AC, TLI, DT, ORE, DL, LI);
+                    AC, TLI, DT, TTI, ORE, DL, LI);
     IC.MaxArraySizeForCombine = MaxArraySize;
 
     if (!IC.run())
@@ -3304,11 +3315,12 @@
   auto &DT = AM.getResult<DominatorTreeAnalysis>(F);
   auto &TLI = AM.getResult<TargetLibraryAnalysis>(F);
   auto &ORE = AM.getResult<OptimizationRemarkEmitterAnalysis>(F);
+  auto &TTI = AM.getResult<TargetIRAnalysis>(F);
 
   auto *LI = AM.getCachedResult<LoopAnalysis>(F);
 
   auto *AA = &AM.getResult<AAManager>(F);
-  if (!combineInstructionsOverFunction(F, Worklist, AA, AC, TLI, DT, ORE,
+  if (!combineInstructionsOverFunction(F, Worklist, AA, AC, TLI, DT, TTI, ORE,
                                        ExpensiveCombines, LI))
     // No changes, all analyses are preserved.
     return PreservedAnalyses::all();
@@ -3329,6 +3341,7 @@
   AU.addRequired<TargetLibraryInfoWrapperPass>();
   AU.addRequired<DominatorTreeWrapperPass>();
   AU.addRequired<OptimizationRemarkEmitterWrapperPass>();
+  AU.addRequired<TargetTransformInfoWrapperPass>();
   AU.addPreserved<DominatorTreeWrapperPass>();
   AU.addPreserved<AAResultsWrapperPass>();
   AU.addPreserved<BasicAAWrapperPass>();
@@ -3345,12 +3358,13 @@
   auto &TLI = getAnalysis<TargetLibraryInfoWrapperPass>().getTLI();
   auto &DT = getAnalysis<DominatorTreeWrapperPass>().getDomTree();
   auto &ORE = getAnalysis<OptimizationRemarkEmitterWrapperPass>().getORE();
+  auto &TTI = getAnalysis<TargetTransformInfoWrapperPass>().getTTI(F);
 
   // Optional analyses.
   auto *LIWP = getAnalysisIfAvailable<LoopInfoWrapperPass>();
   auto *LI = LIWP ? &LIWP->getLoopInfo() : nullptr;
 
-  return combineInstructionsOverFunction(F, Worklist, AA, AC, TLI, DT, ORE,
+  return combineInstructionsOverFunction(F, Worklist, AA, AC, TLI, DT, TTI, ORE,
                                          ExpensiveCombines, LI);
 }
 
@@ -3364,6 +3378,7 @@
 INITIALIZE_PASS_DEPENDENCY(AAResultsWrapperPass)
 INITIALIZE_PASS_DEPENDENCY(GlobalsAAWrapperPass)
 INITIALIZE_PASS_DEPENDENCY(OptimizationRemarkEmitterWrapperPass)
+INITIALIZE_PASS_DEPENDENCY(TargetTransformInfoWrapperPass)
 INITIALIZE_PASS_END(InstructionCombiningPass, "instcombine",
                     "Combine redundant instructions", false, false)
 
Index: llvm/test/Transforms/InstCombine/unit_skip_gep_merge.ll
===================================================================
--- /dev/null
+++ llvm/test/Transforms/InstCombine/unit_skip_gep_merge.ll
@@ -0,0 +1,28 @@
+; RUN: opt -instcombine -S < %s |  FileCheck %s
+
+%ST = type {i8*, i8*, i8*}
+declare void @bar(i8*)
+
+; CHECK-LABEL: @foo
+; CHECK-LABEL: entry
+; CHECK: %tmp1 = getelementptr inbounds %ST, %ST* %arrayidx8
+; CHECK-LABEL: BB0
+; CHECK: %tmp2 = getelementptr inbounds %ST, %ST* %arrayidx8
+define void @foo(%ST* %B, i1 %c, i64 %v, i8** %S, i8** %S2) {
+entry:
+  %arrayidx8 = getelementptr inbounds %ST, %ST* %B, i64 %v
+  %tmp1 = getelementptr inbounds %ST, %ST* %arrayidx8, i64 0, i32 1
+  %r = load i8*, i8** %tmp1
+  store i8* %r, i8** %S2
+  br i1 %c, label %BB0, label %BB2
+
+BB0:
+  %tmp2 = getelementptr inbounds %ST, %ST* %arrayidx8, i64 0, i32 2
+  %l = load i8*, i8** %tmp2
+  store i8* %l, i8** %S
+  br label %BB2
+
+BB2:
+  ret void
+}
+