diff --git a/lib/Target/ARM/ARMBaseInstrInfo.cpp b/lib/Target/ARM/ARMBaseInstrInfo.cpp
index 23fae3e0806..7a7267a719b 100644
--- a/lib/Target/ARM/ARMBaseInstrInfo.cpp
+++ b/lib/Target/ARM/ARMBaseInstrInfo.cpp
@@ -2440,7 +2440,8 @@ ARMBaseInstrInfo::getOperandLatency(const InstrItineraryData *ItinData,
     case ARM::VLD4d8_UPD:
     case ARM::VLD4d16_UPD:
     case ARM::VLD4d32_UPD:
-    case ARM::VLD1d64Q_UPD:
+    case ARM::VLD1d64Qwb_fixed:
+    case ARM::VLD1d64Qwb_register:
     case ARM::VLD4q8_UPD:
     case ARM::VLD4q16_UPD:
     case ARM::VLD4q32_UPD:
diff --git a/lib/Target/ARM/ARMInstrNEON.td b/lib/Target/ARM/ARMInstrNEON.td
index 9d0350b322d..75418aa9758 100644
--- a/lib/Target/ARM/ARMInstrNEON.td
+++ b/lib/Target/ARM/ARMInstrNEON.td
@@ -424,13 +424,24 @@ class VLD1D4<bits<4> op7_4, string Dt>
   let Inst{5-4} = Rn{5-4};
   let DecoderMethod = "DecodeVLDInstruction";
 }
-class VLD1D4WB<bits<4> op7_4, string Dt>
-  : NLdSt<0, 0b10, 0b0010, op7_4, (outs VecListFourD:$Vd, GPR:$wb),
-          (ins addrmode6:$Rn, am6offset:$Rm), IIC_VLD1x4u, "vld1", Dt,
-          "$Vd, $Rn$Rm", "$Rn.addr = $wb",
-          []> {
-  let Inst{5-4} = Rn{5-4};
-  let DecoderMethod = "DecodeVLDInstruction";
+multiclass VLD1D4WB<bits<4> op7_4, string Dt> {
+  def _fixed : NLdSt<0,0b10,0b0010, op7_4, (outs VecListFourD:$Vd, GPR:$wb),
+                    (ins addrmode6:$Rn), IIC_VLD1x2u,
+                     "vld1", Dt, "$Vd, $Rn!",
+                     "$Rn.addr = $wb", []> {
+    let Rm = 0b1101; // NLdSt will assign to the right encoding bits.
+    let Inst{5-4} = Rn{5-4};
+    let DecoderMethod = "DecodeVLDInstruction";
+    let AsmMatchConverter = "cvtVLDwbFixed";
+  }
+  def _register : NLdSt<0,0b10,0b0010,op7_4, (outs VecListFourD:$Vd, GPR:$wb),
+                        (ins addrmode6:$Rn, rGPR:$Rm), IIC_VLD1x2u,
+                        "vld1", Dt, "$Vd, $Rn, $Rm",
+                        "$Rn.addr = $wb", []> {
+    let Inst{5-4} = Rn{5-4};
+    let DecoderMethod = "DecodeVLDInstruction";
+    let AsmMatchConverter = "cvtVLDwbRegister";
+  }
 }
 
 def VLD1d8Q      : VLD1D4<{0,0,?,?}, "8">;
@@ -438,12 +449,12 @@ def VLD1d16Q     : VLD1D4<{0,1,?,?}, "16">;
 def VLD1d32Q     : VLD1D4<{1,0,?,?}, "32">;
 def VLD1d64Q     : VLD1D4<{1,1,?,?}, "64">;
 
-def VLD1d8Q_UPD  : VLD1D4WB<{0,0,?,?}, "8">;
-def VLD1d16Q_UPD : VLD1D4WB<{0,1,?,?}, "16">;
-def VLD1d32Q_UPD : VLD1D4WB<{1,0,?,?}, "32">;
-def VLD1d64Q_UPD : VLD1D4WB<{1,1,?,?}, "64">;
+defm VLD1d8Qwb   : VLD1D4WB<{0,0,?,?}, "8">;
+defm VLD1d16Qwb  : VLD1D4WB<{0,1,?,?}, "16">;
+defm VLD1d32Qwb  : VLD1D4WB<{1,0,?,?}, "32">;
+defm VLD1d64Qwb  : VLD1D4WB<{1,1,?,?}, "64">;
 
-def VLD1d64QPseudo     : VLDQQPseudo<IIC_VLD1x4>;
+def VLD1d64QPseudo : VLDQQPseudo<IIC_VLD1x4>;
 
 //   VLD2     : Vector Load (multiple 2-element structures)
 class VLD2D<bits<4> op11_8, bits<4> op7_4, string Dt, RegisterOperand VdTy>
diff --git a/lib/Target/ARM/Disassembler/ARMDisassembler.cpp b/lib/Target/ARM/Disassembler/ARMDisassembler.cpp
index ddc5c99d364..5174134c465 100644
--- a/lib/Target/ARM/Disassembler/ARMDisassembler.cpp
+++ b/lib/Target/ARM/Disassembler/ARMDisassembler.cpp
@@ -2078,10 +2078,14 @@ static DecodeStatus DecodeVLDInstruction(llvm::MCInst &Inst, unsigned Insn,
     case ARM::VLD1d32Twb_register:
     case ARM::VLD1d64Twb_fixed:
     case ARM::VLD1d64Twb_register:
-    case ARM::VLD1d8Q_UPD:
-    case ARM::VLD1d16Q_UPD:
-    case ARM::VLD1d32Q_UPD:
-    case ARM::VLD1d64Q_UPD:
+    case ARM::VLD1d8Qwb_fixed:
+    case ARM::VLD1d8Qwb_register:
+    case ARM::VLD1d16Qwb_fixed:
+    case ARM::VLD1d16Qwb_register:
+    case ARM::VLD1d32Qwb_fixed:
+    case ARM::VLD1d32Qwb_register:
+    case ARM::VLD1d64Qwb_fixed:
+    case ARM::VLD1d64Qwb_register:
     case ARM::VLD2d8_UPD:
     case ARM::VLD2d16_UPD:
     case ARM::VLD2d32_UPD:
diff --git a/test/MC/ARM/neon-vld-encoding.s b/test/MC/ARM/neon-vld-encoding.s
index 08eb88403ad..1a77966bca0 100644
--- a/test/MC/ARM/neon-vld-encoding.s
+++ b/test/MC/ARM/neon-vld-encoding.s
@@ -45,6 +45,16 @@
 	vld1.32 {d5, d6, d7}, [r3], r6
 	vld1.64 {d6, d7, d8}, [r3, :64], r6
 
+	vld1.8 {d1, d2, d3, d4}, [r3]!
+	vld1.16 {d4, d5, d6, d7}, [r3, :64]!
+	vld1.32 {d5, d6, d7, d8}, [r3]!
+	vld1.64 {d6, d7, d8, d9}, [r3, :64]!
+
+	vld1.8 {d1, d2, d3, d4}, [r3], r8
+	vld1.16 {d4, d5, d6, d7}, [r3, :64], r8
+	vld1.32 {d5, d6, d7, d8}, [r3], r8
+	vld1.64 {d6, d7, d8, d9}, [r3, :64], r8
+
 @ CHECK: vld1.8 {d16}, [r0, :64]        @ encoding: [0x1f,0x07,0x60,0xf4]
 @ CHECK: vld1.16 {d16}, [r0]            @ encoding: [0x4f,0x07,0x60,0xf4]
 @ CHECK: vld1.32 {d16}, [r0]            @ encoding: [0x8f,0x07,0x60,0xf4]
@@ -90,6 +100,16 @@
 @ CHECK: vld1.32 {d5, d6, d7}, [r3], r6  @ encoding: [0x86,0x56,0x23,0xf4]
 @ CHECK: vld1.64 {d6, d7, d8}, [r3, :64], r6 @ encoding: [0xd6,0x66,0x23,0xf4]
 
+@ CHECK: vld1.8	{d1, d2, d3, d4}, [r3]! @ encoding: [0x0d,0x12,0x23,0xf4]
+@ CHECK: vld1.16 {d4, d5, d6, d7}, [r3, :64]! @ encoding: [0x5d,0x42,0x23,0xf4]
+@ CHECK: vld1.32 {d5, d6, d7, d8}, [r3]! @ encoding: [0x8d,0x52,0x23,0xf4]
+@ CHECK: vld1.64 {d6, d7, d8, d9}, [r3, :64]! @ encoding: [0xdd,0x62,0x23,0xf4]
+
+@ CHECK: vld1.8	{d1, d2, d3, d4}, [r3], r8 @ encoding: [0x08,0x12,0x23,0xf4]
+@ CHECK: vld1.16 {d4, d5, d6, d7}, [r3, :64], r8 @ encoding: [0x58,0x42,0x23,0xf4]
+@ CHECK: vld1.32 {d5, d6, d7, d8}, [r3], r8 @ encoding: [0x88,0x52,0x23,0xf4]
+@ CHECK: vld1.64 {d6, d7, d8, d9}, [r3, :64], r8 @ encoding: [0xd8,0x62,0x23,0xf4]
+
 
 	vld2.8	{d16, d17}, [r0, :64]
 	vld2.16	{d16, d17}, [r0, :128]