Index: lib/Target/AArch64/AArch64ISelLowering.cpp
===================================================================
--- lib/Target/AArch64/AArch64ISelLowering.cpp
+++ lib/Target/AArch64/AArch64ISelLowering.cpp
@@ -41,6 +41,7 @@
 #include "llvm/CodeGen/MachineValueType.h"
 #include "llvm/CodeGen/RuntimeLibcalls.h"
 #include "llvm/CodeGen/SelectionDAG.h"
+#include "llvm/CodeGen/SelectionDAGAddressAnalysis.h"
 #include "llvm/CodeGen/SelectionDAGNodes.h"
 #include "llvm/CodeGen/ValueTypes.h"
 #include "llvm/IR/Attributes.h"
@@ -9310,11 +9311,33 @@
   if (StVal.getOpcode() != ISD::BUILD_VECTOR)
     return SDValue();
 
-  // If the zero constant has more than one use then the vector store could be
-  // better since the constant mov will be amortized and stp q instructions
-  // should be able to be formed.
-  if (!StVal.hasOneUse())
-    return SDValue();
+  // If the zero constant has more than one use then the vector store
+  // could be better since the constant mov will be amortized and stp
+  // q instructions should be able to be formed. The exception to this
+  // is when all uses of StVal are non-consecutive ST16 instances. In
+  // this case, it is better to replace each instance with stp xzr, xzr.
+
+  if (!StVal.hasOneUse()) {
+    if (VT.getVectorElementType().getSizeInBits() != 64)
+      return SDValue();
+    SmallVector<SDValue, 8> STAddrs;
+    for (auto *U : StVal->uses()) {
+      if ((U->getOpcode() != ISD::STORE) ||
+          (U->getOperand(1).getValueType().getSizeInBits() != 16 * 8))
+        return SDValue();
+      SDValue Addr = U->getOperand(2);
+      auto AddrDecomp = BaseIndexOffset::match(Addr, DAG);
+      for (SDValue &OtherAddr : STAddrs) {
+        auto OtherAddrDecomp = BaseIndexOffset::match(OtherAddr, DAG);
+        int64_t Offset = 0;
+        AddrDecomp.equalBaseIndex(OtherAddrDecomp, DAG, Offset);
+        if (Offset == 16 || Offset == -16)
+          return SDValue();
+      }
+
+      STAddrs.push_back(Addr);
+    }
+  }
 
   // If the immediate offset of the address operand is too large for the stp
   // instruction, then bail out.
Index: test/CodeGen/AArch64/ldst-opt.ll
===================================================================
--- test/CodeGen/AArch64/ldst-opt.ll
+++ test/CodeGen/AArch64/ldst-opt.ll
@@ -1613,13 +1613,9 @@
 define void @merge_multiple_128bit_stores(i64* %p) {
 ; CHECK-LABEL: merge_multiple_128bit_stores
 ; CHECK: // %entry
-; NOSTRICTALIGN-NEXT: movi v[[REG:[0-9]]].2d, #0000000000000000
-; NOSTRICTALIGN-NEXT: str q0, [x0]
-; NOSTRICTALIGN-NEXT: stur q0, [x0, #24]
-; NOSTRICTALIGN-NEXT: str q0, [x0, #48]
-; STRICTALIGN-NEXT: stp xzr, xzr, [x0]
-; STRICTALIGN-NEXT: stp xzr, xzr, [x0, #24]
-; STRICTALIGN-NEXT: stp xzr, xzr, [x0, #48]
+; CHECK-NEXT: stp xzr, xzr, [x{{[0-9]+}}]
+; CHECK-NEXT: stp xzr, xzr, [x{{[0-9]+}}, #24]
+; CHECK-NEXT: stp xzr, xzr, [x{{[0-9]+}}, #48]
 ; CHECK-NEXT: ret
 entry:
   store i64 0, i64* %p