Index: llvm/trunk/lib/CodeGen/SelectionDAG/SelectionDAG.cpp
===================================================================
--- llvm/trunk/lib/CodeGen/SelectionDAG/SelectionDAG.cpp
+++ llvm/trunk/lib/CodeGen/SelectionDAG/SelectionDAG.cpp
@@ -9031,8 +9031,11 @@
 
 void SelectionDAG::createOperands(SDNode *Node, ArrayRef<SDValue> Vals) {
   assert(!Node->OperandList && "Node already has operands");
+  assert(std::numeric_limits<decltype(SDNode::NumOperands)>::max() >
+             Vals.size() &&
+         "too many operands to fit into SDNode");
   SDUse *Ops = OperandRecycler.allocate(
-    ArrayRecycler<SDUse>::Capacity::get(Vals.size()), OperandAllocator);
+      ArrayRecycler<SDUse>::Capacity::get(Vals.size()), OperandAllocator);
 
   bool IsDivergent = false;
   for (unsigned I = 0; I != Vals.size(); ++I) {
Index: llvm/trunk/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp
===================================================================
--- llvm/trunk/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp
+++ llvm/trunk/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp
@@ -1032,8 +1032,19 @@
   }
 
   // Otherwise, we have to make a token factor node.
-  SDValue Root = DAG.getNode(ISD::TokenFactor, getCurSDLoc(), MVT::Other,
-                             PendingLoads);
+  // If we have >= 2^16 loads then split across multiple token factors as
+  // there's a 64k limit on the number of SDNode operands.
+  SDValue Root;
+  size_t Limit = (1 << 16) - 1;
+  while (PendingLoads.size() > Limit) {
+    unsigned SliceIdx = PendingLoads.size() - Limit;
+    auto ExtractedTFs = ArrayRef<SDValue>(PendingLoads).slice(SliceIdx, Limit);
+    SDValue NewTF =
+        DAG.getNode(ISD::TokenFactor, getCurSDLoc(), MVT::Other, ExtractedTFs);
+    PendingLoads.erase(PendingLoads.begin() + SliceIdx, PendingLoads.end());
+    PendingLoads.emplace_back(NewTF);
+  }
+  Root = DAG.getNode(ISD::TokenFactor, getCurSDLoc(), MVT::Other, PendingLoads);
   PendingLoads.clear();
   DAG.setRoot(Root);
   return Root;