diff --git a/lib/Target/ARM/ARMInstrFormats.td b/lib/Target/ARM/ARMInstrFormats.td
index 84b4319b76b..e5cda4ec88a 100644
--- a/lib/Target/ARM/ARMInstrFormats.td
+++ b/lib/Target/ARM/ARMInstrFormats.td
@@ -1994,7 +1994,7 @@ class NEONFPPat<dag pattern, dag result> : Pat<pattern, result> {
 
 // VFP/NEON Instruction aliases for type suffices.
 class VFPDataTypeInstAlias<string opc, string dt, string asm, dag Result> :
-  InstAlias<!strconcat(opc, dt, asm), Result>;
+  InstAlias<!strconcat(opc, dt, "\t", asm), Result>;
 multiclass VFPDT8ReqInstAlias<string opc, string asm, dag Result> {
   def I8 : VFPDataTypeInstAlias<opc, ".i8", asm, Result>;
   def S8 : VFPDataTypeInstAlias<opc, ".s8", asm, Result>;
@@ -2071,7 +2071,7 @@ multiclass VFPDTAnyNoF64InstAlias<string opc, string asm, dag Result> {
 // above, as we care about the ultimate instruction enum names generated, unlike
 // for instalias defs.
 class NEONDataTypeAsmPseudoInst<string opc, string dt, string asm, dag iops> :
-  AsmPseudoInst<!strconcat(opc, dt, asm), iops>, Requires<[HasNEON]>;
+  AsmPseudoInst<!strconcat(opc, dt, "\t", asm), iops>, Requires<[HasNEON]>;
 multiclass NEONDT8ReqAsmPseudoInst<string opc, string asm, dag iops> {
   def I8 : NEONDataTypeAsmPseudoInst<opc, ".i8", asm, iops>;
   def S8 : NEONDataTypeAsmPseudoInst<opc, ".s8", asm, iops>;
diff --git a/lib/Target/ARM/ARMInstrNEON.td b/lib/Target/ARM/ARMInstrNEON.td
index a395db8868d..5427db8f162 100644
--- a/lib/Target/ARM/ARMInstrNEON.td
+++ b/lib/Target/ARM/ARMInstrNEON.td
@@ -5593,11 +5593,30 @@ defm : VFPDT16ReqInstAlias<"vtrn${p}", "$Qd, $Qm",
 defm : VFPDT32ReqInstAlias<"vtrn${p}", "$Qd, $Qm",
                           (VTRNq32 QPR:$Qd, QPR:$Qm, pred:$p)>;
 
-// FIXME: Proof of concept pseudos. We want to parameterize these for all
-// the suffices we have to support.
+// VLD1 single-lane pseudo-instructions. These need special handling for
+// the lane index that an InstAlias can't handle, so we use these instead.
 defm VLD1LNdAsm : NEONDT8AsmPseudoInst<"vld1${p}", "$list, $addr",
                   (ins VecListOneDByteIndexed:$list, addrmode6:$addr, pred:$p)>;
 defm VLD1LNdAsm : NEONDT16AsmPseudoInst<"vld1${p}", "$list, $addr",
                   (ins VecListOneDByteIndexed:$list, addrmode6:$addr, pred:$p)>;
 defm VLD1LNdAsm : NEONDT32AsmPseudoInst<"vld1${p}", "$list, $addr",
                   (ins VecListOneDByteIndexed:$list, addrmode6:$addr, pred:$p)>;
+
+defm VLD1LNdWB_fixed_Asm : NEONDT8AsmPseudoInst<"vld1${p}", "$list, $addr!",
+                  (ins VecListOneDByteIndexed:$list, addrmode6:$addr, pred:$p)>;
+defm VLD1LNdWB_fixed_Asm : NEONDT16AsmPseudoInst<"vld1${p}", "$list, $addr!",
+                  (ins VecListOneDByteIndexed:$list, addrmode6:$addr, pred:$p)>;
+defm VLD1LNdWB_fixed_Asm : NEONDT32AsmPseudoInst<"vld1${p}", "$list, $addr!",
+                  (ins VecListOneDByteIndexed:$list, addrmode6:$addr, pred:$p)>;
+defm VLD1LNdWB_register_Asm :
+        NEONDT8AsmPseudoInst<"vld1${p}", "$list, $addr, $Rm",
+                  (ins VecListOneDByteIndexed:$list, addrmode6:$addr,
+                       rGPR:$Rm, pred:$p)>;
+defm VLD1LNdWB_register_Asm :
+        NEONDT16AsmPseudoInst<"vld1${p}", "$list, $addr, $Rm",
+                  (ins VecListOneDByteIndexed:$list, addrmode6:$addr,
+                       rGPR:$Rm, pred:$p)>;
+defm VLD1LNdWB_register_Asm :
+        NEONDT32AsmPseudoInst<"vld1${p}", "$list, $addr, $Rm",
+                  (ins VecListOneDByteIndexed:$list, addrmode6:$addr,
+                       rGPR:$Rm, pred:$p)>;
diff --git a/lib/Target/ARM/AsmParser/ARMAsmParser.cpp b/lib/Target/ARM/AsmParser/ARMAsmParser.cpp
index 33b7eef67c6..23353eb10ab 100644
--- a/lib/Target/ARM/AsmParser/ARMAsmParser.cpp
+++ b/lib/Target/ARM/AsmParser/ARMAsmParser.cpp
@@ -4754,16 +4754,48 @@ validateInstruction(MCInst &Inst,
 static unsigned getRealVLDNOpcode(unsigned Opc) {
   switch(Opc) {
   default: assert(0 && "unexpected opcode!");
+  case ARM::VLD1LNdWB_fixed_Asm_8:   return ARM::VLD1LNd8_UPD;
+  case ARM::VLD1LNdWB_fixed_Asm_P8:  return ARM::VLD1LNd8_UPD;
+  case ARM::VLD1LNdWB_fixed_Asm_I8:  return ARM::VLD1LNd8_UPD;
+  case ARM::VLD1LNdWB_fixed_Asm_S8:  return ARM::VLD1LNd8_UPD;
+  case ARM::VLD1LNdWB_fixed_Asm_U8:  return ARM::VLD1LNd8_UPD;
+  case ARM::VLD1LNdWB_fixed_Asm_16:  return ARM::VLD1LNd16_UPD;
+  case ARM::VLD1LNdWB_fixed_Asm_P16: return ARM::VLD1LNd16_UPD;
+  case ARM::VLD1LNdWB_fixed_Asm_I16: return ARM::VLD1LNd16_UPD;
+  case ARM::VLD1LNdWB_fixed_Asm_S16: return ARM::VLD1LNd16_UPD;
+  case ARM::VLD1LNdWB_fixed_Asm_U16: return ARM::VLD1LNd16_UPD;
+  case ARM::VLD1LNdWB_fixed_Asm_32:  return ARM::VLD1LNd32_UPD;
+  case ARM::VLD1LNdWB_fixed_Asm_F:   return ARM::VLD1LNd32_UPD;
+  case ARM::VLD1LNdWB_fixed_Asm_F32: return ARM::VLD1LNd32_UPD;
+  case ARM::VLD1LNdWB_fixed_Asm_I32: return ARM::VLD1LNd32_UPD;
+  case ARM::VLD1LNdWB_fixed_Asm_S32: return ARM::VLD1LNd32_UPD;
+  case ARM::VLD1LNdWB_fixed_Asm_U32: return ARM::VLD1LNd32_UPD;
+  case ARM::VLD1LNdWB_register_Asm_8:   return ARM::VLD1LNd8_UPD;
+  case ARM::VLD1LNdWB_register_Asm_P8:  return ARM::VLD1LNd8_UPD;
+  case ARM::VLD1LNdWB_register_Asm_I8:  return ARM::VLD1LNd8_UPD;
+  case ARM::VLD1LNdWB_register_Asm_S8:  return ARM::VLD1LNd8_UPD;
+  case ARM::VLD1LNdWB_register_Asm_U8:  return ARM::VLD1LNd8_UPD;
+  case ARM::VLD1LNdWB_register_Asm_16:  return ARM::VLD1LNd16_UPD;
+  case ARM::VLD1LNdWB_register_Asm_P16: return ARM::VLD1LNd16_UPD;
+  case ARM::VLD1LNdWB_register_Asm_I16: return ARM::VLD1LNd16_UPD;
+  case ARM::VLD1LNdWB_register_Asm_S16: return ARM::VLD1LNd16_UPD;
+  case ARM::VLD1LNdWB_register_Asm_U16: return ARM::VLD1LNd16_UPD;
+  case ARM::VLD1LNdWB_register_Asm_32:  return ARM::VLD1LNd32_UPD;
+  case ARM::VLD1LNdWB_register_Asm_F:   return ARM::VLD1LNd32_UPD;
+  case ARM::VLD1LNdWB_register_Asm_F32: return ARM::VLD1LNd32_UPD;
+  case ARM::VLD1LNdWB_register_Asm_I32: return ARM::VLD1LNd32_UPD;
+  case ARM::VLD1LNdWB_register_Asm_S32: return ARM::VLD1LNd32_UPD;
+  case ARM::VLD1LNdWB_register_Asm_U32: return ARM::VLD1LNd32_UPD;
   case ARM::VLD1LNdAsm_8:   return ARM::VLD1LNd8;
   case ARM::VLD1LNdAsm_P8:  return ARM::VLD1LNd8;
   case ARM::VLD1LNdAsm_I8:  return ARM::VLD1LNd8;
   case ARM::VLD1LNdAsm_S8:  return ARM::VLD1LNd8;
   case ARM::VLD1LNdAsm_U8:  return ARM::VLD1LNd8;
-  case ARM::VLD1LNdAsm_16:   return ARM::VLD1LNd16;
-  case ARM::VLD1LNdAsm_P16:  return ARM::VLD1LNd16;
-  case ARM::VLD1LNdAsm_I16:  return ARM::VLD1LNd16;
-  case ARM::VLD1LNdAsm_S16:  return ARM::VLD1LNd16;
-  case ARM::VLD1LNdAsm_U16:  return ARM::VLD1LNd16;
+  case ARM::VLD1LNdAsm_16:  return ARM::VLD1LNd16;
+  case ARM::VLD1LNdAsm_P16: return ARM::VLD1LNd16;
+  case ARM::VLD1LNdAsm_I16: return ARM::VLD1LNd16;
+  case ARM::VLD1LNdAsm_S16: return ARM::VLD1LNd16;
+  case ARM::VLD1LNdAsm_U16: return ARM::VLD1LNd16;
   case ARM::VLD1LNdAsm_32:  return ARM::VLD1LNd32;
   case ARM::VLD1LNdAsm_F:   return ARM::VLD1LNd32;
   case ARM::VLD1LNdAsm_F32: return ARM::VLD1LNd32;
@@ -4778,6 +4810,70 @@ processInstruction(MCInst &Inst,
                    const SmallVectorImpl<MCParsedAsmOperand*> &Operands) {
   switch (Inst.getOpcode()) {
   // Handle NEON VLD1 complex aliases.
+  case ARM::VLD1LNdWB_register_Asm_8:
+  case ARM::VLD1LNdWB_register_Asm_P8:
+  case ARM::VLD1LNdWB_register_Asm_I8:
+  case ARM::VLD1LNdWB_register_Asm_S8:
+  case ARM::VLD1LNdWB_register_Asm_U8:
+  case ARM::VLD1LNdWB_register_Asm_16:
+  case ARM::VLD1LNdWB_register_Asm_P16:
+  case ARM::VLD1LNdWB_register_Asm_I16:
+  case ARM::VLD1LNdWB_register_Asm_S16:
+  case ARM::VLD1LNdWB_register_Asm_U16:
+  case ARM::VLD1LNdWB_register_Asm_32:
+  case ARM::VLD1LNdWB_register_Asm_F:
+  case ARM::VLD1LNdWB_register_Asm_F32:
+  case ARM::VLD1LNdWB_register_Asm_I32:
+  case ARM::VLD1LNdWB_register_Asm_S32:
+  case ARM::VLD1LNdWB_register_Asm_U32: {
+    MCInst TmpInst;
+    // Shuffle the operands around so the lane index operand is in the
+    // right place.
+    TmpInst.setOpcode(getRealVLDNOpcode(Inst.getOpcode()));
+    TmpInst.addOperand(Inst.getOperand(0)); // Vd
+    TmpInst.addOperand(Inst.getOperand(2)); // Rn_wb
+    TmpInst.addOperand(Inst.getOperand(2)); // Rn
+    TmpInst.addOperand(Inst.getOperand(3)); // alignment
+    TmpInst.addOperand(Inst.getOperand(4)); // Rm
+    TmpInst.addOperand(Inst.getOperand(0)); // Tied operand src (== Vd)
+    TmpInst.addOperand(Inst.getOperand(1)); // lane
+    TmpInst.addOperand(Inst.getOperand(5)); // CondCode
+    TmpInst.addOperand(Inst.getOperand(6));
+    Inst = TmpInst;
+    return true;
+  }
+  case ARM::VLD1LNdWB_fixed_Asm_8:
+  case ARM::VLD1LNdWB_fixed_Asm_P8:
+  case ARM::VLD1LNdWB_fixed_Asm_I8:
+  case ARM::VLD1LNdWB_fixed_Asm_S8:
+  case ARM::VLD1LNdWB_fixed_Asm_U8:
+  case ARM::VLD1LNdWB_fixed_Asm_16:
+  case ARM::VLD1LNdWB_fixed_Asm_P16:
+  case ARM::VLD1LNdWB_fixed_Asm_I16:
+  case ARM::VLD1LNdWB_fixed_Asm_S16:
+  case ARM::VLD1LNdWB_fixed_Asm_U16:
+  case ARM::VLD1LNdWB_fixed_Asm_32:
+  case ARM::VLD1LNdWB_fixed_Asm_F:
+  case ARM::VLD1LNdWB_fixed_Asm_F32:
+  case ARM::VLD1LNdWB_fixed_Asm_I32:
+  case ARM::VLD1LNdWB_fixed_Asm_S32:
+  case ARM::VLD1LNdWB_fixed_Asm_U32: {
+    MCInst TmpInst;
+    // Shuffle the operands around so the lane index operand is in the
+    // right place.
+    TmpInst.setOpcode(getRealVLDNOpcode(Inst.getOpcode()));
+    TmpInst.addOperand(Inst.getOperand(0)); // Vd
+    TmpInst.addOperand(Inst.getOperand(2)); // Rn_wb
+    TmpInst.addOperand(Inst.getOperand(2)); // Rn
+    TmpInst.addOperand(Inst.getOperand(3)); // alignment
+    TmpInst.addOperand(MCOperand::CreateReg(0)); // Rm
+    TmpInst.addOperand(Inst.getOperand(0)); // Tied operand src (== Vd)
+    TmpInst.addOperand(Inst.getOperand(1)); // lane
+    TmpInst.addOperand(Inst.getOperand(4)); // CondCode
+    TmpInst.addOperand(Inst.getOperand(5));
+    Inst = TmpInst;
+    return true;
+  }
   case ARM::VLD1LNdAsm_8:
   case ARM::VLD1LNdAsm_P8:
   case ARM::VLD1LNdAsm_I8: