Index: lib/Target/AArch64/AArch64LoadStoreOptimizer.cpp
===================================================================
--- lib/Target/AArch64/AArch64LoadStoreOptimizer.cpp
+++ lib/Target/AArch64/AArch64LoadStoreOptimizer.cpp
@@ -382,10 +382,24 @@
   const MachineOperand &BaseRegOp =
       MergeForward ? getLdStBaseOp(Paired) : getLdStBaseOp(I);
 
+  int Offset = getLdStOffsetOp(I).getImm();
+  int PairedOffset = getLdStOffsetOp(Paired).getImm();
+  bool PairedIsUnscaled = isUnscaledLdSt(Paired->getOpcode());
+
+  // We're trying to pair instructions that differ in how they are scaled.
+  // If I is scaled then scale the offset of Paired accordingly.
+  // Otherwise, do the opposite (i.e., make Paired's offset unscaled).
+  if (IsUnscaled != PairedIsUnscaled) {
+    int MemSize = getMemSize(Paired);
+    assert(!(PairedOffset % getMemSize(Paired)) &&
+           "Offset should be a multiple of the stride!");
+    PairedOffset =
+        PairedIsUnscaled ? PairedOffset / MemSize : PairedOffset * MemSize;
+  }
+
   // Which register is Rt and which is Rt2 depends on the offset order.
   MachineInstr *RtMI, *Rt2MI;
-  if (getLdStOffsetOp(I).getImm() ==
-      getLdStOffsetOp(Paired).getImm() + OffsetStride) {
+  if (Offset == PairedOffset + OffsetStride) {
     RtMI = Paired;
     Rt2MI = I;
     // Here we swapped the assumption made for SExtIdx.
@@ -397,10 +411,13 @@
     RtMI = I;
     Rt2MI = Paired;
   }
-  // Handle Unscaled
+  // Scale the immediate offset, if necessary.
   int OffsetImm = getLdStOffsetOp(RtMI).getImm();
-  if (IsUnscaled && EnableAArch64UnscaledMemOp)
-    OffsetImm /= OffsetStride;
+  if (isUnscaledLdSt(RtMI->getOpcode()) && EnableAArch64UnscaledMemOp) {
+    assert(!(OffsetImm % getMemSize(RtMI)) &&
+           "Offset should be a multiple of the stride!");
+    OffsetImm /= getMemSize(RtMI);
+  }
 
   // Construct the new instruction.
   MachineInstrBuilder MIB = BuildMI(*I->getParent(), InsertionPoint,
@@ -494,8 +511,13 @@
 static bool inBoundsForPair(bool IsUnscaled, int Offset, int OffsetStride) {
   // Convert the byte-offset used by unscaled into an "element" offset used
   // by the scaled pair load/store instructions.
-  if (IsUnscaled)
+  if (IsUnscaled) {
+    // If the byte-offset isn't a multiple of the stride, there's no point
+    // trying to match it.
+    if (Offset % OffsetStride)
+      return false;
     Offset /= OffsetStride;
+  }
 
   return Offset <= 63 && Offset >= -64;
 }
@@ -531,6 +553,34 @@
   return false;
 }
 
+static bool canMergeOpc(unsigned Opc, unsigned PairOpc, LdStPairFlags &Flags) {
+  // Opcodes match: nothing more to check.
+  if (Opc == PairOpc)
+    return true;
+
+  // Try to match a sign-extended load/store with a zero-extended load/store.
+  Flags.setSExtIdx(-1);
+  bool IsValidLdStrOpc, PairIsValidLdStrOpc;
+  unsigned NonSExtOpc = getMatchingNonSExtOpcode(Opc, &IsValidLdStrOpc);
+  assert(IsValidLdStrOpc &&
+         "Given Opc should be a Load or Store with an immediate");
+  // Opc will be the first instruction in the pair.
+  if (NonSExtOpc == getMatchingNonSExtOpcode(PairOpc, &PairIsValidLdStrOpc)) {
+    Flags.setSExtIdx(NonSExtOpc == (unsigned)Opc ? 1 : 0);
+    return true;
+  }
+
+  // FIXME: Can we also match a mixed sext/zext unscaled/scaled pair?
+
+  // If the second instruction isn't even a load/store, bail out.
+  if (!PairIsValidLdStrOpc)
+    return false;
+
+  // Try to match an unscaled load/store with a scaled load/store.
+  return isUnscaledLdSt(Opc) != isUnscaledLdSt(PairOpc) &&
+         getMatchingPairOpcode(Opc) == getMatchingPairOpcode(PairOpc);
+}
+
 /// findMatchingInsn - Scan the instructions looking for a load/store that can
 /// be combined with the current instruction into a load/store pair.
 MachineBasicBlock::iterator
@@ -581,19 +631,8 @@
     // Now that we know this is a real instruction, count it.
     ++Count;
 
-    bool CanMergeOpc = Opc == MI->getOpcode();
-    Flags.setSExtIdx(-1);
-    if (!CanMergeOpc) {
-      bool IsValidLdStrOpc;
-      unsigned NonSExtOpc = getMatchingNonSExtOpcode(Opc, &IsValidLdStrOpc);
-      assert(IsValidLdStrOpc &&
-             "Given Opc should be a Load or Store with an immediate");
-      // Opc will be the first instruction in the pair.
-      Flags.setSExtIdx(NonSExtOpc == (unsigned)Opc ? 1 : 0);
-      CanMergeOpc = NonSExtOpc == getMatchingNonSExtOpcode(MI->getOpcode());
-    }
-
-    if (CanMergeOpc && getLdStOffsetOp(MI).isImm()) {
+    if (canMergeOpc(Opc, MI->getOpcode(), Flags) &&
+        getLdStOffsetOp(MI).isImm()) {
       assert(MI->mayLoadOrStore() && "Expected memory operation.");
       // If we've found another instruction with the same opcode, check to see
       // if the base and offset are compatible with our starting instruction.
@@ -607,6 +646,24 @@
       // final offset must be in range.
       unsigned MIBaseReg = getLdStBaseOp(MI).getReg();
       int MIOffset = getLdStOffsetOp(MI).getImm();
+
+      // We're trying to pair instructions that differ in how they are scaled.
+      // If FirstMI is scaled then scale the offset of MI accordingly.
+      // Otherwise, do the opposite (i.e., make MI's offset unscaled).
+      bool MIIsUnscaled = isUnscaledLdSt(MI);
+      if (IsUnscaled != MIIsUnscaled) {
+        int MemSize = getMemSize(MI);
+        if (MIIsUnscaled) {
+          // If the unscaled offset isn't a multiple of the MemSize, we can't
+          // pair the operations together: bail and keep looking.
+          if (MIOffset % MemSize)
+            continue;
+          MIOffset /= MemSize;
+        } else {
+          MIOffset *= MemSize;
+        }
+      }
+
       if (BaseReg == MIBaseReg && ((Offset == MIOffset + OffsetStride) ||
                                    (Offset + OffsetStride == MIOffset))) {
         int MinOffset = Offset < MIOffset ? Offset : MIOffset;
@@ -617,8 +674,7 @@
           return E;
         // If the resultant immediate offset of merging these instructions
         // is out of range for a pairwise instruction, bail and keep looking.
-        bool MIIsUnscaled = isUnscaledLdSt(MI);
-        if (!inBoundsForPair(MIIsUnscaled, MinOffset, OffsetStride)) {
+        if (!inBoundsForPair(IsUnscaled, MinOffset, OffsetStride)) {
           trackRegDefsUses(MI, ModifiedRegs, UsedRegs, TRI);
           MemInsns.push_back(MI);
           continue;
Index: test/CodeGen/AArch64/ldp-stp-scaled-unscaled-pairs.ll
===================================================================
--- test/CodeGen/AArch64/ldp-stp-scaled-unscaled-pairs.ll
+++ test/CodeGen/AArch64/ldp-stp-scaled-unscaled-pairs.ll
@@ -0,0 +1,105 @@
+; RUN: llc < %s -march=aarch64 -aarch64-stp-suppress=false -verify-machineinstrs -asm-verbose=false | FileCheck %s
+
+; CHECK-LABEL: test_strd_sturd:
+; CHECK-NEXT: stp d0, d1, [x0, #-8]
+; CHECK-NEXT: ret
+define void @test_strd_sturd(float* %ptr, <2 x float> %v1, <2 x float> %v2) #0 {
+  %tmp1 = bitcast float* %ptr to <2 x float>*
+  store <2 x float> %v2, <2 x float>* %tmp1, align 16
+  %add.ptr = getelementptr inbounds float, float* %ptr, i64 -2
+  %tmp = bitcast float* %add.ptr to <2 x float>*
+  store <2 x float> %v1, <2 x float>* %tmp, align 16
+  ret void
+}
+
+; CHECK-LABEL: test_sturd_strd:
+; CHECK-NEXT: stp d0, d1, [x0, #-8]
+; CHECK-NEXT: ret
+define void @test_sturd_strd(float* %ptr, <2 x float> %v1, <2 x float> %v2) #0 {
+  %add.ptr = getelementptr inbounds float, float* %ptr, i64 -2
+  %tmp = bitcast float* %add.ptr to <2 x float>*
+  store <2 x float> %v1, <2 x float>* %tmp, align 16
+  %tmp1 = bitcast float* %ptr to <2 x float>*
+  store <2 x float> %v2, <2 x float>* %tmp1, align 16
+  ret void
+}
+
+; CHECK-LABEL: test_strq_sturq:
+; CHECK-NEXT: stp q0, q1, [x0, #-16]
+; CHECK-NEXT: ret
+define void @test_strq_sturq(double* %ptr, <2 x double> %v1, <2 x double> %v2) #0 {
+  %tmp1 = bitcast double* %ptr to <2 x double>*
+  store <2 x double> %v2, <2 x double>* %tmp1, align 16
+  %add.ptr = getelementptr inbounds double, double* %ptr, i64 -2
+  %tmp = bitcast double* %add.ptr to <2 x double>*
+  store <2 x double> %v1, <2 x double>* %tmp, align 16
+  ret void
+}
+
+; CHECK-LABEL: test_sturq_strq:
+; CHECK-NEXT: stp q0, q1, [x0, #-16]
+; CHECK-NEXT: ret
+define void @test_sturq_strq(double* %ptr, <2 x double> %v1, <2 x double> %v2) #0 {
+  %add.ptr = getelementptr inbounds double, double* %ptr, i64 -2
+  %tmp = bitcast double* %add.ptr to <2 x double>*
+  store <2 x double> %v1, <2 x double>* %tmp, align 16
+  %tmp1 = bitcast double* %ptr to <2 x double>*
+  store <2 x double> %v2, <2 x double>* %tmp1, align 16
+  ret void
+}
+
+; CHECK-LABEL: test_ldrx_ldurx:
+; CHECK-NEXT: ldp [[V0:x[0-9]+]], [[V1:x[0-9]+]], [x0, #-8]
+; CHECK-NEXT: add x0, [[V0]], [[V1]]
+; CHECK-NEXT: ret
+define i64 @test_ldrx_ldurx(i64* %p) #0 {
+  %tmp = load i64, i64* %p, align 4
+  %add.ptr = getelementptr inbounds i64, i64* %p, i64 -1
+  %tmp1 = load i64, i64* %add.ptr, align 4
+  %add = add nsw i64 %tmp1, %tmp
+  ret i64 %add
+}
+
+; CHECK-LABEL: test_ldurx_ldrx:
+; CHECK-NEXT: ldp [[V0:x[0-9]+]], [[V1:x[0-9]+]], [x0, #-8]
+; CHECK-NEXT: add x0, [[V0]], [[V1]]
+; CHECK-NEXT: ret
+define i64 @test_ldurx_ldrx(i64* %p) #0 {
+  %add.ptr = getelementptr inbounds i64, i64* %p, i64 -1
+  %tmp1 = load i64, i64* %add.ptr, align 4
+  %tmp = load i64, i64* %p, align 4
+  %add = add nsw i64 %tmp1, %tmp
+  ret i64 %add
+}
+
+; CHECK-LABEL: test_ldrsw_ldursw:
+; CHECK-NEXT: ldpsw [[V0:x[0-9]+]], [[V1:x[0-9]+]], [x0, #-4]
+; CHECK-NEXT: add x0, [[V0]], [[V1]]
+; CHECK-NEXT: ret
+define i64 @test_ldrsw_ldursw(i32* %p) #0 {
+  %tmp = load i32, i32* %p, align 4
+  %add.ptr = getelementptr inbounds i32, i32* %p, i64 -1
+  %tmp1 = load i32, i32* %add.ptr, align 4
+  %sexttmp = sext i32 %tmp to i64
+  %sexttmp1 = sext i32 %tmp1 to i64
+  %add = add nsw i64 %sexttmp1, %sexttmp
+  ret i64 %add
+}
+
+; Also make sure we only match valid offsets.
+; CHECK-LABEL: test_ldrq_ldruq_invalidoffset:
+; CHECK-NEXT: ldr q[[V0:[0-9]+]], [x0]
+; CHECK-NEXT: ldur q[[V1:[0-9]+]], [x0, #24]
+; CHECK-NEXT: add.2d v0, v[[V0]], v[[V1]]
+; CHECK-NEXT: ret
+define <2 x i64> @test_ldrq_ldruq_invalidoffset(i64* %p) nounwind {
+  %a1 = bitcast i64* %p to <2 x i64>*
+  %tmp1 = load <2 x i64>, < 2 x i64>* %a1, align 8           
+  %add.ptr2 = getelementptr inbounds i64, i64* %p, i64 3
+  %a2 = bitcast i64* %add.ptr2 to <2 x i64>*
+  %tmp2 = load <2 x i64>, <2 x i64>* %a2, align 8            
+  %add = add nsw <2 x i64> %tmp1, %tmp2
+  ret <2 x i64> %add
+}
+
+attributes #0 = { nounwind }