diff --git a/llvm/lib/Transforms/Scalar/MergedLoadStoreMotion.cpp b/llvm/lib/Transforms/Scalar/MergedLoadStoreMotion.cpp
--- a/llvm/lib/Transforms/Scalar/MergedLoadStoreMotion.cpp
+++ b/llvm/lib/Transforms/Scalar/MergedLoadStoreMotion.cpp
@@ -121,6 +121,8 @@
   bool canSinkStoresAndGEPs(StoreInst *S0, StoreInst *S1) const;
   void sinkStoresAndGEPs(BasicBlock *BB, StoreInst *SinkCand,
                          StoreInst *ElseInst);
+  bool canSinkStoresWithSameGEPs(StoreInst *S0, StoreInst *S1) const;
+  void sinkStores(BasicBlock *BB, StoreInst *SinkCand, StoreInst *ElseInst);
   bool mergeStores(BasicBlock *BB);
 };
 } // end anonymous namespace
@@ -244,9 +246,9 @@
   // Only one definition?
   auto *A0 = dyn_cast<Instruction>(S0->getPointerOperand());
   auto *A1 = dyn_cast<Instruction>(S1->getPointerOperand());
-  LLVM_DEBUG(dbgs() << "Sink Instruction into BB \n"; BB->dump();
-             dbgs() << "Instruction Left\n"; S0->dump(); dbgs() << "\n";
-             dbgs() << "Instruction Right\n"; S1->dump(); dbgs() << "\n");
+  LLVM_DEBUG(dbgs() << "Sink Stores and GEPs into BB \n"; BB->dump();
+             dbgs() << "Store Left\n"; S0->dump(); dbgs() << "\n";
+             dbgs() << "Store Right\n"; S1->dump(); dbgs() << "\n");
   // Hoist the instruction.
   BasicBlock::iterator InsertPt = BB->getFirstInsertionPt();
   // Intersect optional metadata.
@@ -274,6 +276,40 @@
 }
 
 ///
+/// Check if 2 stores can be sunk if they have the same GEP
+///
+bool MergedLoadStoreMotion::canSinkStoresWithSameGEPs(StoreInst *S0,
+                                                      StoreInst *S1) const {
+  auto *A0 = dyn_cast<GetElementPtrInst>(S0->getPointerOperand());
+  auto *A1 = dyn_cast<GetElementPtrInst>(S1->getPointerOperand());
+  return A0 && A1 && A0 == A1;
+}
+
+///
+/// Merge two stores to same address and sink into \p BB
+///
+void MergedLoadStoreMotion::sinkStores(BasicBlock *BB, StoreInst *S0,
+                                       StoreInst *S1) {
+  LLVM_DEBUG(dbgs() << "Sink Stores into BB \n"; BB->dump();
+             dbgs() << "Store Left\n"; S0->dump(); dbgs() << "\n";
+             dbgs() << "Store Right\n"; S1->dump(); dbgs() << "\n");
+  BasicBlock::iterator InsertPt = BB->getFirstInsertionPt();
+  // Intersect optional metadata.
+  S0->andIRFlags(S1);
+  S0->dropUnknownNonDebugMetadata();
+
+  // Create the new store to be inserted at the join point.
+  StoreInst *SNew = cast<StoreInst>(S0->clone());
+  SNew->insertBefore(&*InsertPt);
+
+  // New PHI operand? Use it.
+  if (PHINode *NewPN = getPHIOperand(BB, S0, S1))
+    SNew->setOperand(0, NewPN);
+  S0->eraseFromParent();
+  S1->eraseFromParent();
+}
+
+///
 /// True when two stores are equivalent and can sink into the footer
 ///
 /// Starting from a diamond head block, iterate over the instructions in one
@@ -318,7 +354,9 @@
     if (NStores * Size1 >= MagicCompileTimeControl)
       break;
     if (StoreInst *S1 = canSinkFromBlock(Pred1, S0)) {
-      if (!canSinkStoresAndGEPs(S0, S1))
+      bool SinkWithGEPs = canSinkStoresAndGEPs(S0, S1);
+      bool SinkOnlyStores = canSinkStoresWithSameGEPs(S0, S1);
+      if (!SinkWithGEPs && !SinkOnlyStores)
         // Don't attempt to sink below stores that had to stick around
         // But after removal of a store and some of its feeding
         // instruction search again from the beginning since the iterator
@@ -334,7 +372,10 @@
       }
 
       MergedStores = true;
-      sinkStoresAndGEPs(SinkBB, S0, S1);
+      if (SinkWithGEPs)
+        sinkStoresAndGEPs(SinkBB, S0, S1);
+      else if (SinkOnlyStores)
+        sinkStores(SinkBB, S0, S1);
       RBI = Pred0->rbegin();
       RBE = Pred0->rend();
       LLVM_DEBUG(dbgs() << "Search again\n"; Instruction *I = &*RBI; I->dump());
@@ -351,7 +392,7 @@
 
   // Merge unconditional branches, allowing PRE to catch more
   // optimization opportunities.
-  // This loop doesn't care about newly inserted/split blocks 
+  // This loop doesn't care about newly inserted/split blocks
   // since they never will be diamond heads.
   for (Function::iterator FI = F.begin(), FE = F.end(); FI != FE;) {
     BasicBlock *BB = &*FI++;
diff --git a/llvm/test/Transforms/InstMerge/st_sink_no_geps.ll b/llvm/test/Transforms/InstMerge/st_sink_no_geps.ll
new file mode 100644
--- /dev/null
+++ b/llvm/test/Transforms/InstMerge/st_sink_no_geps.ll
@@ -0,0 +1,35 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
+; Test to make sure that we sink stores if they have common GEP.
+; RUN: opt -basicaa -memdep -mldst-motion -S < %s | FileCheck %s
+; RUN: opt -aa-pipeline=basic-aa -passes='require<memdep>,mldst-motion' -S < %s 2>&1 | FileCheck %s
+target datalayout = "e-m:o-i64:64-i128:128-n32:64-S128"
+
+; Function Attrs: nounwind uwtable
+define dso_local void @st_sink_no_geps(i32* nocapture %arg1, i1 zeroext %arg2) local_unnamed_addr {
+; CHECK-LABEL: @st_sink_no_geps(
+; CHECK-NEXT:  bb1:
+; CHECK-NEXT:    [[TMP:%.*]] = getelementptr inbounds i32, i32* [[ARG1:%.*]], i64 1
+; CHECK-NEXT:    br i1 [[ARG2:%.*]], label [[BB2:%.*]], label [[BB3:%.*]]
+; CHECK:       bb2:
+; CHECK-NEXT:    br label [[BB4:%.*]]
+; CHECK:       bb3:
+; CHECK-NEXT:    br label [[BB4]]
+; CHECK:       bb4:
+; CHECK-NEXT:    store i32 42, i32* [[TMP]], align 4
+; CHECK-NEXT:    ret void
+;
+bb1:
+  %tmp = getelementptr inbounds i32, i32* %arg1, i64 1
+  br i1 %arg2, label %bb2, label %bb3
+
+bb2:                                              ; preds = %bb1
+  store i32 42, i32* %tmp, align 4
+  br label %bb4
+
+bb3:                                              ; preds = %bb1
+  store i32 42, i32* %tmp, align 4
+  br label %bb4
+
+bb4:                                              ; preds = %bb2, %bb3
+  ret void
+}