diff --git a/llvm/lib/Transforms/Scalar/DeadStoreElimination.cpp b/llvm/lib/Transforms/Scalar/DeadStoreElimination.cpp
--- a/llvm/lib/Transforms/Scalar/DeadStoreElimination.cpp
+++ b/llvm/lib/Transforms/Scalar/DeadStoreElimination.cpp
@@ -1535,7 +1535,7 @@
 
         auto *MD = dyn_cast_or_null<MemoryDef>(MA);
         if (MD && State.MemDefs.size() < MemorySSADefsPerBlockLimit &&
-            hasAnalyzableMemoryWrite(&I, TLI) && isRemovable(&I))
+            State.getLocForWriteEx(&I) && isRemovable(&I))
           State.MemDefs.push_back(MD);
 
         // Track whether alloca and alloca-like objects are visible in the
@@ -1617,6 +1617,52 @@
   }
 
   /// Returns true if \p Use may read from \p DefLoc.
+
+  bool isEnd(MemoryDef *Def) {
+    LLVM_DEBUG(dbgs() << "  Check if def " << *Def << " ("
+                      << *Def->getMemoryInst()
+                      << ") is at the end the function \n");
+
+    auto MaybeLoc = getLocForWriteEx(Def->getMemoryInst());
+    if (!MaybeLoc) {
+      LLVM_DEBUG(dbgs() << "  ... could not get location for write.\n");
+      return false;
+    }
+
+    SmallVector<MemoryAccess *, 4> WorkList;
+    SmallPtrSet<MemoryAccess *, 8> Visited;
+    auto PushMemUses = [&WorkList, &Visited](MemoryAccess *Acc) {
+      if (!Visited.insert(Acc).second)
+        return;
+      for (Use &U : Acc->uses())
+        WorkList.push_back(cast<MemoryAccess>(U.getUser()));
+    };
+    PushMemUses(Def);
+    for (unsigned I = 0; I < WorkList.size(); I++) {
+      if (WorkList.size() >= 100) {
+        LLVM_DEBUG(dbgs() << "  ... hit exploration limit.\n");
+        return false;
+      }
+
+      MemoryAccess *UseAccess = WorkList[I];
+      if (isa<MemoryPhi>(UseAccess)) {
+        PushMemUses(UseAccess);
+        continue;
+      }
+
+      Instruction *UseInst = cast<MemoryUseOrDef>(UseAccess)->getMemoryInst();
+      if (isReadClobber(*MaybeLoc, UseInst)) {
+        LLVM_DEBUG(dbgs() << "  ... hit read clobber " << *UseInst << ".\n");
+        return false;
+      }
+
+      if (MemoryDef *UseDef = dyn_cast<MemoryDef>(UseAccess))
+        PushMemUses(UseDef);
+    }
+    return true;
+  }
+
+  // Returns true if \p Use may read from \p DefLoc.
   bool isReadClobber(MemoryLocation DefLoc, Instruction *UseInst) const {
     if (!UseInst->mayReadFromMemory())
       return false;
@@ -1916,6 +1962,42 @@
 
     return false;
   }
+
+  bool eliminateEnds() {
+    const DataLayout &DL = F.getParent()->getDataLayout();
+    bool MadeChange = false;
+    LLVM_DEBUG(
+        dbgs()
+        << "Trying to eliminate MemoryDefs at the end of the function\n");
+    for (int I = MemDefs.size() - 1; I >= 0; I--) {
+      MemoryDef *Def = MemDefs[I];
+      if (SkipStores.find(Def) != SkipStores.end())
+        continue;
+      if (isEnd(Def)) {
+        Instruction *DefI = Def->getMemoryInst();
+        // See through pointer-to-pointer bitcasts
+        SmallVector<const Value *, 4> Pointers;
+        GetUnderlyingObjects(getLocForWriteEx(DefI)->Ptr, Pointers, DL);
+
+        LLVM_DEBUG(dbgs() << "   ... MemoryDef is not accessed until the end "
+                             "of the function\n");
+        bool CanKill = true;
+        for (const Value *Pointer : Pointers) {
+          if (!InvisibleToCallerAfterRet.count(Pointer)) {
+            CanKill = false;
+            break;
+          }
+        }
+
+        if (CanKill) {
+          deleteDeadInstruction(DefI);
+          ++NumFastStores;
+          MadeChange = true;
+        }
+      }
+    }
+    return MadeChange;
+  }
 };
 
 /// \returns true if \p KillingDef stores the result of \p Load to the source of
@@ -2079,6 +2161,7 @@
     for (auto &KV : State.IOLs)
       MadeChange |= removePartiallyOverlappedStores(&AA, DL, KV.second);
 
+  MadeChange |= State.eliminateEnds();
   return MadeChange;
 }
 } // end anonymous namespace
diff --git a/llvm/test/Transforms/DeadStoreElimination/MSSA/2011-09-06-EndOfFunction.ll b/llvm/test/Transforms/DeadStoreElimination/MSSA/2011-09-06-EndOfFunction.ll
--- a/llvm/test/Transforms/DeadStoreElimination/MSSA/2011-09-06-EndOfFunction.ll
+++ b/llvm/test/Transforms/DeadStoreElimination/MSSA/2011-09-06-EndOfFunction.ll
@@ -1,4 +1,3 @@
-; XFAIL: *
 ; RUN: opt -dse -enable-dse-memoryssa -S < %s | FileCheck %s
 
 target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64"
diff --git a/llvm/test/Transforms/DeadStoreElimination/MSSA/libcalls.ll b/llvm/test/Transforms/DeadStoreElimination/MSSA/libcalls.ll
--- a/llvm/test/Transforms/DeadStoreElimination/MSSA/libcalls.ll
+++ b/llvm/test/Transforms/DeadStoreElimination/MSSA/libcalls.ll
@@ -1,4 +1,3 @@
-; XFAIL: *
 ; RUN: opt -S -basicaa -dse -enable-dse-memoryssa < %s | FileCheck %s
 
 declare i8* @strcpy(i8* %dest, i8* %src) nounwind
diff --git a/llvm/test/Transforms/DeadStoreElimination/MSSA/mda-with-dbg-values.ll b/llvm/test/Transforms/DeadStoreElimination/MSSA/mda-with-dbg-values.ll
--- a/llvm/test/Transforms/DeadStoreElimination/MSSA/mda-with-dbg-values.ll
+++ b/llvm/test/Transforms/DeadStoreElimination/MSSA/mda-with-dbg-values.ll
@@ -72,5 +72,5 @@
 ; Check that the store is removed and that the memcpy is still there
 ; CHECK-LABEL: foo
 ; CHECK-NOT:   store i8
-; CHECK:       call void @llvm.memcpy
+; CHECK-NOT:   call void @llvm.memcpy
 ; CHECK:       ret void
diff --git a/llvm/test/Transforms/DeadStoreElimination/MSSA/multiblock-captures.ll b/llvm/test/Transforms/DeadStoreElimination/MSSA/multiblock-captures.ll
--- a/llvm/test/Transforms/DeadStoreElimination/MSSA/multiblock-captures.ll
+++ b/llvm/test/Transforms/DeadStoreElimination/MSSA/multiblock-captures.ll
@@ -211,11 +211,9 @@
 ; Stores to stack objects can be eliminated if they are not captured inside the function.
 define void @test_alloca_nocapture_1() {
 ; CHECK-LABEL: @test_alloca_nocapture_1(
-; CHECK-NEXT:    [[M:%.*]] = alloca i8
 ; CHECK-NEXT:    call void @foo()
 ; CHECK-NEXT:    br label [[EXIT:%.*]]
 ; CHECK:       exit:
-; CHECK-NEXT:    store i8 1, i8* [[M]]
 ; CHECK-NEXT:    ret void
 ;
   %m = alloca i8
@@ -237,7 +235,6 @@
 ; CHECK-NEXT:    call void @capture(i8* [[M]])
 ; CHECK-NEXT:    br label [[EXIT:%.*]]
 ; CHECK:       exit:
-; CHECK-NEXT:    store i8 1, i8* [[M]]
 ; CHECK-NEXT:    ret void
 ;
   %m = alloca i8
@@ -260,7 +257,6 @@
 ; CHECK:       exit:
 ; CHECK-NEXT:    [[F_PTR:%.*]] = getelementptr [[S1:%.*]], %S1* [[E:%.*]], i32 0, i32 0
 ; CHECK-NEXT:    store i8* [[M]], i8** [[F_PTR]]
-; CHECK-NEXT:    store i8 1, i8* [[M]]
 ; CHECK-NEXT:    ret void
 ;
   %m = alloca i8
diff --git a/llvm/test/Transforms/DeadStoreElimination/MSSA/multiblock-exceptions.ll b/llvm/test/Transforms/DeadStoreElimination/MSSA/multiblock-exceptions.ll
--- a/llvm/test/Transforms/DeadStoreElimination/MSSA/multiblock-exceptions.ll
+++ b/llvm/test/Transforms/DeadStoreElimination/MSSA/multiblock-exceptions.ll
@@ -29,7 +29,6 @@
 ; CHECK-NEXT:    [[C1:%.*]] = cleanuppad within none []
 ; CHECK-NEXT:    br label [[EXIT]]
 ; CHECK:       exit:
-; CHECK-NEXT:    store i32 40, i32* [[SV]]
 ; CHECK-NEXT:    ret void
 ;
 block1:
diff --git a/llvm/test/Transforms/DeadStoreElimination/MSSA/multiblock-malloc-free.ll b/llvm/test/Transforms/DeadStoreElimination/MSSA/multiblock-malloc-free.ll
--- a/llvm/test/Transforms/DeadStoreElimination/MSSA/multiblock-malloc-free.ll
+++ b/llvm/test/Transforms/DeadStoreElimination/MSSA/multiblock-malloc-free.ll
@@ -246,7 +246,6 @@
 ; CHECK-NEXT:    br i1 true, label [[BB2:%.*]], label [[BB3:%.*]]
 ; CHECK:       bb2:
 ; CHECK-NEXT:    [[M:%.*]] = call noalias i8* @malloc(i64 10)
-; CHECK-NEXT:    store i8 1, i8* [[M]]
 ; CHECK-NEXT:    br label [[BB3]]
 ; CHECK:       bb3:
 ; CHECK-NEXT:    [[R:%.*]] = phi i8* [ null, [[BB1:%.*]] ], [ [[M]], [[BB2]] ]
diff --git a/llvm/test/Transforms/DeadStoreElimination/MSSA/multiblock-memintrinsics.ll b/llvm/test/Transforms/DeadStoreElimination/MSSA/multiblock-memintrinsics.ll
--- a/llvm/test/Transforms/DeadStoreElimination/MSSA/multiblock-memintrinsics.ll
+++ b/llvm/test/Transforms/DeadStoreElimination/MSSA/multiblock-memintrinsics.ll
@@ -123,18 +123,10 @@
 define void @alloca_1(i1 %c) {
 ; CHECK-LABEL: @alloca_1(
 ; CHECK-NEXT:  entry:
-; CHECK-NEXT:    [[P_ALLOCA:%.*]] = alloca [32 x i32]
-; CHECK-NEXT:    [[P:%.*]] = bitcast [32 x i32]* [[P_ALLOCA]] to i32*
-; CHECK-NEXT:    [[ARRAYIDX0:%.*]] = getelementptr inbounds i32, i32* [[P]], i64 1
-; CHECK-NEXT:    [[P3:%.*]] = bitcast i32* [[ARRAYIDX0]] to i8*
-; CHECK-NEXT:    [[TMP0:%.*]] = getelementptr inbounds i8, i8* [[P3]], i64 4
-; CHECK-NEXT:    call void @llvm.memset.p0i8.i64(i8* align 4 [[TMP0]], i8 0, i64 24, i1 false)
 ; CHECK-NEXT:    br i1 [[C:%.*]], label [[BB1:%.*]], label [[BB2:%.*]]
 ; CHECK:       bb1:
 ; CHECK-NEXT:    br label [[BB3:%.*]]
 ; CHECK:       bb2:
-; CHECK-NEXT:    [[ARRAYIDX1:%.*]] = getelementptr inbounds i32, i32* [[P]], i64 1
-; CHECK-NEXT:    store i32 1, i32* [[ARRAYIDX1]], align 4
 ; CHECK-NEXT:    br label [[BB3]]
 ; CHECK:       bb3:
 ; CHECK-NEXT:    ret void
@@ -160,20 +152,10 @@
 define void @alloca_2(i1 %c) {
 ; CHECK-LABEL: @alloca_2(
 ; CHECK-NEXT:  entry:
-; CHECK-NEXT:    [[P_ALLOCA:%.*]] = alloca [32 x i32]
-; CHECK-NEXT:    [[P:%.*]] = bitcast [32 x i32]* [[P_ALLOCA]] to i32*
-; CHECK-NEXT:    [[ARRAYIDX0:%.*]] = getelementptr inbounds i32, i32* [[P]], i64 1
-; CHECK-NEXT:    [[P3:%.*]] = bitcast i32* [[ARRAYIDX0]] to i8*
-; CHECK-NEXT:    [[TMP0:%.*]] = getelementptr inbounds i8, i8* [[P3]], i64 4
-; CHECK-NEXT:    call void @llvm.memset.p0i8.i64(i8* align 4 [[TMP0]], i8 0, i64 24, i1 false)
 ; CHECK-NEXT:    br i1 [[C:%.*]], label [[BB1:%.*]], label [[BB2:%.*]]
 ; CHECK:       bb1:
-; CHECK-NEXT:    [[ARRAYIDX1:%.*]] = getelementptr inbounds i32, i32* [[P]], i64 1
-; CHECK-NEXT:    store i32 1, i32* [[ARRAYIDX1]], align 4
 ; CHECK-NEXT:    br label [[BB3:%.*]]
 ; CHECK:       bb2:
-; CHECK-NEXT:    [[ARRAYIDX2:%.*]] = getelementptr inbounds i32, i32* [[P]], i64 1
-; CHECK-NEXT:    store i32 1, i32* [[ARRAYIDX2]], align 4
 ; CHECK-NEXT:    br label [[BB3]]
 ; CHECK:       bb3:
 ; CHECK-NEXT:    ret void
@@ -204,20 +186,12 @@
 define void @alloca_3(i1 %c) {
 ; CHECK-LABEL: @alloca_3(
 ; CHECK-NEXT:  entry:
-; CHECK-NEXT:    [[P_ALLOCA:%.*]] = alloca [32 x i32]
-; CHECK-NEXT:    [[P:%.*]] = bitcast [32 x i32]* [[P_ALLOCA]] to i32*
-; CHECK-NEXT:    [[ARRAYIDX0:%.*]] = getelementptr inbounds i32, i32* [[P]], i64 1
-; CHECK-NEXT:    [[P3:%.*]] = bitcast i32* [[ARRAYIDX0]] to i8*
-; CHECK-NEXT:    [[TMP0:%.*]] = getelementptr inbounds i8, i8* [[P3]], i64 4
-; CHECK-NEXT:    call void @llvm.memset.p0i8.i64(i8* align 4 [[TMP0]], i8 0, i64 24, i1 false)
 ; CHECK-NEXT:    br i1 [[C:%.*]], label [[BB1:%.*]], label [[BB2:%.*]]
 ; CHECK:       bb1:
 ; CHECK-NEXT:    br label [[BB3:%.*]]
 ; CHECK:       bb2:
 ; CHECK-NEXT:    br label [[BB3]]
 ; CHECK:       bb3:
-; CHECK-NEXT:    [[ARRAYIDX1:%.*]] = getelementptr inbounds i32, i32* [[P]], i64 1
-; CHECK-NEXT:    store i32 1, i32* [[ARRAYIDX1]], align 4
 ; CHECK-NEXT:    ret void
 ;
 entry:
diff --git a/llvm/test/Transforms/DeadStoreElimination/MSSA/multiblock-multipath.ll b/llvm/test/Transforms/DeadStoreElimination/MSSA/multiblock-multipath.ll
--- a/llvm/test/Transforms/DeadStoreElimination/MSSA/multiblock-multipath.ll
+++ b/llvm/test/Transforms/DeadStoreElimination/MSSA/multiblock-multipath.ll
@@ -589,14 +589,11 @@
 ; CHECK-LABEL: @alloca_5(
 ; CHECK-NEXT:  bb:
 ; CHECK-NEXT:    [[TMP:%.*]] = alloca [[STRUCT_BLAM_4:%.*]], align 8
-; CHECK-NEXT:    [[TMP36:%.*]] = getelementptr inbounds [[STRUCT_BLAM_4]], %struct.blam.4* [[TMP]], i64 0, i32 0, i32 1
-; CHECK-NEXT:    [[TMP37:%.*]] = bitcast i64** [[TMP36]] to i8*
 ; CHECK-NEXT:    [[TMP38:%.*]] = getelementptr inbounds [[STRUCT_BLAM_4]], %struct.blam.4* [[TMP]], i64 0, i32 0, i32 3
 ; CHECK-NEXT:    [[TMP39:%.*]] = bitcast i64* [[TMP38]] to i64*
 ; CHECK-NEXT:    store i64 0, i64* [[TMP39]], align 4
 ; CHECK-NEXT:    br i1 [[C:%.*]], label [[BB46:%.*]], label [[BB47:%.*]]
 ; CHECK:       bb46:
-; CHECK-NEXT:    call void @llvm.memset.p0i8.i64(i8* nonnull align 8 dereferenceable(20) [[TMP37]], i8 0, i64 26, i1 false)
 ; CHECK-NEXT:    ret void
 ; CHECK:       bb47:
 ; CHECK-NEXT:    [[TMP48:%.*]] = getelementptr inbounds [[STRUCT_BLAM_4]], %struct.blam.4* [[TMP]], i64 0, i32 0, i32 2
diff --git a/llvm/test/Transforms/DeadStoreElimination/MSSA/multiblock-simple.ll b/llvm/test/Transforms/DeadStoreElimination/MSSA/multiblock-simple.ll
--- a/llvm/test/Transforms/DeadStoreElimination/MSSA/multiblock-simple.ll
+++ b/llvm/test/Transforms/DeadStoreElimination/MSSA/multiblock-simple.ll
@@ -174,10 +174,8 @@
 
 define void @test11() {
 ; CHECK-LABEL: @test11(
-; CHECK-NEXT:    [[P:%.*]] = alloca i32, align 4
 ; CHECK-NEXT:    br i1 true, label [[BB1:%.*]], label [[BB2:%.*]]
 ; CHECK:       bb1:
-; CHECK-NEXT:    store i32 0, i32* [[P]], align 4
 ; CHECK-NEXT:    br label [[BB3:%.*]]
 ; CHECK:       bb2:
 ; CHECK-NEXT:    ret void
diff --git a/llvm/test/Transforms/DeadStoreElimination/MSSA/simple-todo.ll b/llvm/test/Transforms/DeadStoreElimination/MSSA/simple-todo.ll
--- a/llvm/test/Transforms/DeadStoreElimination/MSSA/simple-todo.ll
+++ b/llvm/test/Transforms/DeadStoreElimination/MSSA/simple-todo.ll
@@ -74,35 +74,6 @@
 declare noalias i8* @malloc(i32)
 declare noalias i8* @calloc(i32, i32)
 
-define void @test14(i32* %Q) {
-; CHECK-LABEL: @test14(
-; CHECK-NEXT:    ret void
-;
-  %P = alloca i32
-  %DEAD = load i32, i32* %Q
-  store i32 %DEAD, i32* %P
-  ret void
-
-}
-
-define void @test20() {
-; CHECK-LABEL: @test20(
-; CHECK-NEXT:    ret void
-;
-  %m = call i8* @malloc(i32 24)
-  store i8 0, i8* %m
-  ret void
-}
-
-define void @test21() {
-; CHECK-LABEL: @test21(
-; CHECK-NEXT:    ret void
-;
-  %m = call i8* @calloc(i32 9, i32 7)
-  store i8 0, i8* %m
-  ret void
-}
-
 define void @test22(i1 %i, i32 %k, i32 %m) nounwind {
 ; CHECK-LABEL: @test22(
 ; CHECK-NEXT:    ret void
diff --git a/llvm/test/Transforms/DeadStoreElimination/MSSA/simple.ll b/llvm/test/Transforms/DeadStoreElimination/MSSA/simple.ll
--- a/llvm/test/Transforms/DeadStoreElimination/MSSA/simple.ll
+++ b/llvm/test/Transforms/DeadStoreElimination/MSSA/simple.ll
@@ -178,6 +178,35 @@
 declare noalias i8* @malloc(i32)
 declare noalias i8* @calloc(i32, i32)
 
+define void @test14(i32* %Q) {
+; CHECK-LABEL: @test14(
+; CHECK-NEXT:    ret void
+;
+  %P = alloca i32
+  %DEAD = load i32, i32* %Q
+  store i32 %DEAD, i32* %P
+  ret void
+
+}
+
+define void @test20() {
+; CHECK-LABEL: @test20(
+; CHECK-NEXT:    ret void
+;
+  %m = call i8* @malloc(i32 24)
+  store i8 0, i8* %m
+  ret void
+}
+
+define void @test21() {
+; CHECK-LABEL: @test21(
+; CHECK-NEXT:    ret void
+;
+  %m = call i8* @calloc(i32 9, i32 7)
+  store i8 0, i8* %m
+  ret void
+}
+
 ; The store here is not dead because the byval call reads it.
 declare void @test19f({i32}* byval align 4 %P)