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
@@ -1458,6 +1458,8 @@
   // accesses are executed before another access.
   DenseMap<BasicBlock *, unsigned> PostOrderNumbers;
 
+  DenseMap<BasicBlock *, InstOverlapIntervalsTy> IOLs;
+
   DSEState(Function &F, AliasAnalysis &AA, MemorySSA &MSSA, DominatorTree &DT,
            PostDominatorTree &PDT, const TargetLibraryInfo &TLI)
       : F(F), AA(AA), MSSA(MSSA), DT(DT), PDT(PDT), TLI(TLI) {}
@@ -1693,6 +1695,9 @@
         Updater.removeMemoryAccess(MA);
       }
 
+      auto I = IOLs.find(DeadInst->getParent());
+      if (I != IOLs.end())
+        I->second.erase(DeadInst);
       // Remove its operands
       for (Use &O : DeadInst->operands())
         if (Instruction *OpI = dyn_cast<Instruction>(O)) {
@@ -1846,7 +1851,10 @@
 
       // Check if NI overwrites SI.
       int64_t InstWriteOffset, DepWriteOffset;
-      InstOverlapIntervalsTy IOL;
+      auto Iter = State.IOLs.insert(
+          std::make_pair<BasicBlock *, InstOverlapIntervalsTy>(
+              NI->getParent(), InstOverlapIntervalsTy()));
+      auto &IOL = Iter.first->second;
       OverwriteResult OR = isOverwrite(SILoc, NILoc, DL, TLI, DepWriteOffset,
                                        InstWriteOffset, NI, IOL, AA, &F);
 
@@ -1861,6 +1869,10 @@
     }
   }
 
+  if (EnablePartialOverwriteTracking)
+    for (auto &KV : State.IOLs)
+      MadeChange |= removePartiallyOverlappedStores(&AA, DL, KV.second);
+
   return MadeChange;
 }
 } // end anonymous namespace
diff --git a/llvm/test/Transforms/DeadStoreElimination/MSSA/OverwriteStoreBegin.ll b/llvm/test/Transforms/DeadStoreElimination/MSSA/OverwriteStoreBegin.ll
--- a/llvm/test/Transforms/DeadStoreElimination/MSSA/OverwriteStoreBegin.ll
+++ b/llvm/test/Transforms/DeadStoreElimination/MSSA/OverwriteStoreBegin.ll
@@ -1,5 +1,4 @@
 ; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
-; XFAIL: *
 ; RUN: opt < %s -basicaa -dse -enable-dse-memoryssa -S | FileCheck %s
 
 define void @write4to7(i32* nocapture %p) {
diff --git a/llvm/test/Transforms/DeadStoreElimination/MSSA/OverwriteStoreEnd.ll b/llvm/test/Transforms/DeadStoreElimination/MSSA/OverwriteStoreEnd.ll
--- a/llvm/test/Transforms/DeadStoreElimination/MSSA/OverwriteStoreEnd.ll
+++ b/llvm/test/Transforms/DeadStoreElimination/MSSA/OverwriteStoreEnd.ll
@@ -1,5 +1,4 @@
 ; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
-; XFAIL: *
 ; RUN: opt < %s -basicaa -dse -enable-dse-memoryssa -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-S128"
 
diff --git a/llvm/test/Transforms/DeadStoreElimination/MSSA/memset-missing-debugloc.ll b/llvm/test/Transforms/DeadStoreElimination/MSSA/memset-missing-debugloc.ll
--- a/llvm/test/Transforms/DeadStoreElimination/MSSA/memset-missing-debugloc.ll
+++ b/llvm/test/Transforms/DeadStoreElimination/MSSA/memset-missing-debugloc.ll
@@ -1,7 +1,6 @@
 ; Test that the getelementptr generated when the dse pass determines that
 ; a memset can be shortened has the debugloc carried over from the memset.
 
-; XFAIL: *
 ; RUN: opt -S -march=native -dse -enable-dse-memoryssa < %s| FileCheck %s
 ; CHECK: bitcast [5 x i64]* %{{[a-zA-Z_][a-zA-Z0-9_]*}} to i8*, !dbg
 ; CHECK-NEXT: %{{[0-9]+}} = getelementptr inbounds i8, i8* %0, i64 32, !dbg ![[DBG:[0-9]+]]
diff --git a/llvm/test/Transforms/DeadStoreElimination/MSSA/multiblock-loops.ll b/llvm/test/Transforms/DeadStoreElimination/MSSA/multiblock-loops.ll
--- a/llvm/test/Transforms/DeadStoreElimination/MSSA/multiblock-loops.ll
+++ b/llvm/test/Transforms/DeadStoreElimination/MSSA/multiblock-loops.ll
@@ -76,7 +76,8 @@
 ; CHECK-NEXT:  entry:
 ; CHECK-NEXT:    [[ARRAYIDX0:%.*]] = getelementptr inbounds i32, i32* [[P:%.*]], i64 1
 ; CHECK-NEXT:    [[P3:%.*]] = bitcast i32* [[ARRAYIDX0]] to i8*
-; CHECK-NEXT:    call void @llvm.memset.p0i8.i64(i8* align 4 [[P3]], i8 0, i64 28, i1 false)
+; 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 label [[FOR:%.*]]
 ; CHECK:       for:
 ; CHECK-NEXT:    [[ARRAYIDX1:%.*]] = getelementptr inbounds i32, i32* [[P]], i64 1
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
@@ -43,7 +43,8 @@
 ; CHECK-NEXT:  entry:
 ; CHECK-NEXT:    [[ARRAYIDX0:%.*]] = getelementptr inbounds i32, i32* [[P:%.*]], i64 1
 ; CHECK-NEXT:    [[P3:%.*]] = bitcast i32* [[ARRAYIDX0]] to i8*
-; CHECK-NEXT:    call void @llvm.memset.p0i8.i64(i8* align 4 [[P3]], i8 0, i64 28, i1 false)
+; 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 true, label [[BB1:%.*]], label [[BB2:%.*]]
 ; CHECK:       bb1:
 ; CHECK-NEXT:    br label [[BB3:%.*]]