diff --git a/llvm/include/llvm/CodeGen/MachinePipeliner.h b/llvm/include/llvm/CodeGen/MachinePipeliner.h
--- a/llvm/include/llvm/CodeGen/MachinePipeliner.h
+++ b/llvm/include/llvm/CodeGen/MachinePipeliner.h
@@ -330,10 +330,22 @@
   NodeSet() = default;
   NodeSet(iterator S, iterator E) : Nodes(S, E), HasRecurrence(true) {
     Latency = 0;
-    for (unsigned i = 0, e = Nodes.size(); i < e; ++i)
-      for (const SDep &Succ : Nodes[i]->Succs)
-        if (Nodes.count(Succ.getSUnit()))
-          Latency += Succ.getLatency();
+    for (unsigned i = 0, e = Nodes.size(); i < e; ++i) {
+      DenseMap<SUnit *, unsigned> SuccSUnitLatency;
+      for (const SDep &Succ : Nodes[i]->Succs) {
+        auto SuccSUnit = Succ.getSUnit();
+        if (!Nodes.count(SuccSUnit))
+          continue;
+        unsigned CurLatency = Succ.getLatency();
+        unsigned MaxLatency = 0;
+        if (SuccSUnitLatency.count(SuccSUnit))
+          MaxLatency = SuccSUnitLatency[SuccSUnit];
+        if (CurLatency > MaxLatency)
+          SuccSUnitLatency[SuccSUnit] = CurLatency;
+      }
+      for (auto SUnitLatency : SuccSUnitLatency)
+        Latency += SUnitLatency.second;
+    }
   }
 
   bool insert(SUnit *SU) { return Nodes.insert(SU); }