ARM refactor am6offset usage for VLD1.

Split am6offset into fixed and register offset variants so the instruction
encodings are explicit rather than relying an a magic reg0 marker.
Needed to being able to parse these.



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@142853 91177308-0d34-0410-b5e6-96231b3b80d8

5 files changed, 181 insertions, 71 deletions

diff --git a/lib/Target/ARM/ARMBaseInstrInfo.cpp b/lib/Target/ARM/ARMBaseInstrInfo.cpp
index 24cd228279..211f937d95 100644
--- a/lib/Target/ARM/ARMBaseInstrInfo.cpp
+++ b/lib/Target/ARM/ARMBaseInstrInfo.cpp
@@ -2401,10 +2401,14 @@ ARMBaseInstrInfo::getOperandLatency(const InstrItineraryData *ItinData,
     case ARM::VLD1q16:
     case ARM::VLD1q32:
     case ARM::VLD1q64:
-    case ARM::VLD1q8_UPD:
-    case ARM::VLD1q16_UPD:
-    case ARM::VLD1q32_UPD:
-    case ARM::VLD1q64_UPD:
+    case ARM::VLD1q8wb_fixed:
+    case ARM::VLD1q16wb_fixed:
+    case ARM::VLD1q32wb_fixed:
+    case ARM::VLD1q64wb_fixed:
+    case ARM::VLD1q8wb_register:
+    case ARM::VLD1q16wb_register:
+    case ARM::VLD1q32wb_register:
+    case ARM::VLD1q64wb_register:
     case ARM::VLD2d8:
     case ARM::VLD2d16:
     case ARM::VLD2d32:
@@ -2562,10 +2566,14 @@ ARMBaseInstrInfo::getOperandLatency(const InstrItineraryData *ItinData,
     case ARM::VLD1q16Pseudo:
     case ARM::VLD1q32Pseudo:
     case ARM::VLD1q64Pseudo:
-    case ARM::VLD1q8Pseudo_UPD:
-    case ARM::VLD1q16Pseudo_UPD:
-    case ARM::VLD1q32Pseudo_UPD:
-    case ARM::VLD1q64Pseudo_UPD:
+    case ARM::VLD1q8PseudoWB_register:
+    case ARM::VLD1q16PseudoWB_register:
+    case ARM::VLD1q32PseudoWB_register:
+    case ARM::VLD1q64PseudoWB_register:
+    case ARM::VLD1q8PseudoWB_fixed:
+    case ARM::VLD1q16PseudoWB_fixed:
+    case ARM::VLD1q32PseudoWB_fixed:
+    case ARM::VLD1q64PseudoWB_fixed:
     case ARM::VLD2d8Pseudo:
     case ARM::VLD2d16Pseudo:
     case ARM::VLD2d32Pseudo:
diff --git a/lib/Target/ARM/ARMExpandPseudoInsts.cpp b/lib/Target/ARM/ARMExpandPseudoInsts.cpp
index 77bad0c11e..c8f9756f4d 100644
--- a/lib/Target/ARM/ARMExpandPseudoInsts.cpp
+++ b/lib/Target/ARM/ARMExpandPseudoInsts.cpp
@@ -102,7 +102,7 @@ namespace {
     unsigned PseudoOpc;
     unsigned RealOpc;
     bool IsLoad;
-    bool HasWriteBack;
+    bool HasWritebackOperand;
     NEONRegSpacing RegSpacing;
     unsigned char NumRegs; // D registers loaded or stored
     unsigned char RegElts; // elements per D register; used for lane ops
@@ -148,13 +148,17 @@ static const NEONLdStTableEntry NEONLdStTable[] = {
 { ARM::VLD1d64TPseudo_UPD,  ARM::VLD1d64T_UPD, true,  true,  SingleSpc,  3, 1 ,false},
 
 { ARM::VLD1q16Pseudo,       ARM::VLD1q16,      true,  false, SingleSpc,  2, 4 ,false},
-{ ARM::VLD1q16Pseudo_UPD,   ARM::VLD1q16_UPD,  true,  true,  SingleSpc,  2, 4 ,false},
+{ ARM::VLD1q16PseudoWB_fixed, ARM::VLD1q16wb_fixed,true,false,SingleSpc, 2, 4 ,false},
+{ ARM::VLD1q16PseudoWB_register, ARM::VLD1q16wb_register, true, true, SingleSpc, 2, 4 ,false},
 { ARM::VLD1q32Pseudo,       ARM::VLD1q32,      true,  false, SingleSpc,  2, 2 ,false},
-{ ARM::VLD1q32Pseudo_UPD,   ARM::VLD1q32_UPD,  true,  true,  SingleSpc,  2, 2 ,false},
+{ ARM::VLD1q32PseudoWB_fixed, ARM::VLD1q32wb_fixed,true,false,SingleSpc, 2, 2 ,false},
+{ ARM::VLD1q32PseudoWB_register, ARM::VLD1q32wb_register, true, true, SingleSpc, 2, 2 ,false},
 { ARM::VLD1q64Pseudo,       ARM::VLD1q64,      true,  false, SingleSpc,  2, 1 ,false},
-{ ARM::VLD1q64Pseudo_UPD,   ARM::VLD1q64_UPD,  true,  true,  SingleSpc,  2, 1 ,false},
+{ ARM::VLD1q64PseudoWB_fixed, ARM::VLD1q64wb_fixed,true,false,SingleSpc, 2, 2 ,false},
+{ ARM::VLD1q64PseudoWB_register, ARM::VLD1q64wb_register, true, true, SingleSpc, 2, 1 ,false},
 { ARM::VLD1q8Pseudo,        ARM::VLD1q8,       true,  false, SingleSpc,  2, 8 ,false},
-{ ARM::VLD1q8Pseudo_UPD,    ARM::VLD1q8_UPD,   true,  true,  SingleSpc,  2, 8 ,false},
+{ ARM::VLD1q8PseudoWB_fixed, ARM::VLD1q8wb_fixed,true,false, SingleSpc,  2, 8 ,false},
+{ ARM::VLD1q8PseudoWB_register, ARM::VLD1q8wb_register,true,true,SingleSpc,2,8,false},
 
 { ARM::VLD2DUPd16Pseudo,     ARM::VLD2DUPd16,     true, false, SingleSpc, 2, 4,true},
 { ARM::VLD2DUPd16Pseudo_UPD, ARM::VLD2DUPd16_UPD, true, true,  SingleSpc, 2, 4,true},
@@ -436,14 +440,14 @@ void ARMExpandPseudo::ExpandVLD(MachineBasicBlock::iterator &MBBI) {
   if (NumRegs > 3 && TableEntry->copyAllListRegs)
     MIB.addReg(D3, RegState::Define | getDeadRegState(DstIsDead));
 
-  if (TableEntry->HasWriteBack)
+  if (TableEntry->HasWritebackOperand)
     MIB.addOperand(MI.getOperand(OpIdx++));
 
   // Copy the addrmode6 operands.
   MIB.addOperand(MI.getOperand(OpIdx++));
   MIB.addOperand(MI.getOperand(OpIdx++));
   // Copy the am6offset operand.
-  if (TableEntry->HasWriteBack)
+  if (TableEntry->HasWritebackOperand)
     MIB.addOperand(MI.getOperand(OpIdx++));
 
   // For an instruction writing double-spaced subregs, the pseudo instruction
@@ -488,14 +492,14 @@ void ARMExpandPseudo::ExpandVST(MachineBasicBlock::iterator &MBBI) {
   MachineInstrBuilder MIB = BuildMI(MBB, MBBI, MI.getDebugLoc(),
                                     TII->get(TableEntry->RealOpc));
   unsigned OpIdx = 0;
-  if (TableEntry->HasWriteBack)
+  if (TableEntry->HasWritebackOperand)
     MIB.addOperand(MI.getOperand(OpIdx++));
 
   // Copy the addrmode6 operands.
   MIB.addOperand(MI.getOperand(OpIdx++));
   MIB.addOperand(MI.getOperand(OpIdx++));
   // Copy the am6offset operand.
-  if (TableEntry->HasWriteBack)
+  if (TableEntry->HasWritebackOperand)
     MIB.addOperand(MI.getOperand(OpIdx++));
 
   bool SrcIsKill = MI.getOperand(OpIdx).isKill();
@@ -565,14 +569,14 @@ void ARMExpandPseudo::ExpandLaneOp(MachineBasicBlock::iterator &MBBI) {
       MIB.addReg(D3, RegState::Define | getDeadRegState(DstIsDead));
   }
 
-  if (TableEntry->HasWriteBack)
+  if (TableEntry->HasWritebackOperand)
     MIB.addOperand(MI.getOperand(OpIdx++));
 
   // Copy the addrmode6 operands.
   MIB.addOperand(MI.getOperand(OpIdx++));
   MIB.addOperand(MI.getOperand(OpIdx++));
   // Copy the am6offset operand.
-  if (TableEntry->HasWriteBack)
+  if (TableEntry->HasWritebackOperand)
     MIB.addOperand(MI.getOperand(OpIdx++));
 
   // Grab the super-register source.
@@ -1068,10 +1072,14 @@ bool ARMExpandPseudo::ExpandMI(MachineBasicBlock &MBB,
     case ARM::VLD1q16Pseudo:
     case ARM::VLD1q32Pseudo:
     case ARM::VLD1q64Pseudo:
-    case ARM::VLD1q8Pseudo_UPD:
-    case ARM::VLD1q16Pseudo_UPD:
-    case ARM::VLD1q32Pseudo_UPD:
-    case ARM::VLD1q64Pseudo_UPD:
+    case ARM::VLD1q8PseudoWB_register:
+    case ARM::VLD1q16PseudoWB_register:
+    case ARM::VLD1q32PseudoWB_register:
+    case ARM::VLD1q64PseudoWB_register:
+    case ARM::VLD1q8PseudoWB_fixed:
+    case ARM::VLD1q16PseudoWB_fixed:
+    case ARM::VLD1q32PseudoWB_fixed:
+    case ARM::VLD1q64PseudoWB_fixed:
     case ARM::VLD2d8Pseudo:
     case ARM::VLD2d16Pseudo:
     case ARM::VLD2d32Pseudo:
diff --git a/lib/Target/ARM/ARMISelDAGToDAG.cpp b/lib/Target/ARM/ARMISelDAGToDAG.cpp
index ca777bd8c3..8a1b618b96 100644
--- a/lib/Target/ARM/ARMISelDAGToDAG.cpp
+++ b/lib/Target/ARM/ARMISelDAGToDAG.cpp
@@ -1549,6 +1549,23 @@ SDValue ARMDAGToDAGISel::GetVLDSTAlign(SDValue Align, unsigned NumVecs,
   return CurDAG->getTargetConstant(Alignment, MVT::i32);
 }
 
+// Get the register stride update opcode of a VLD/VST instruction that
+// is otherwise equivalent to the given fixed stride updating instruction.
+static unsigned getVLDSTRegisterUpdateOpcode(unsigned Opc) {
+  switch (Opc) {
+  default: break;
+  case ARM::VLD1d8wb_fixed: return ARM::VLD1d8wb_register;
+  case ARM::VLD1d16wb_fixed: return ARM::VLD1d16wb_register;
+  case ARM::VLD1d32wb_fixed: return ARM::VLD1d32wb_register;
+  case ARM::VLD1d64wb_fixed: return ARM::VLD1d64wb_register;
+  case ARM::VLD1q8wb_fixed: return ARM::VLD1q8wb_register;
+  case ARM::VLD1q16wb_fixed: return ARM::VLD1q16wb_register;
+  case ARM::VLD1q32wb_fixed: return ARM::VLD1q32wb_register;
+  case ARM::VLD1q64wb_fixed: return ARM::VLD1q64wb_register;
+  }
+  return Opc; // If not one we handle, return it unchanged.
+}
+
 SDNode *ARMDAGToDAGISel::SelectVLD(SDNode *N, bool isUpdating, unsigned NumVecs,
                                    unsigned *DOpcodes, unsigned *QOpcodes0,
                                    unsigned *QOpcodes1) {
@@ -1612,7 +1629,14 @@ SDNode *ARMDAGToDAGISel::SelectVLD(SDNode *N, bool isUpdating, unsigned NumVecs,
     Ops.push_back(Align);
     if (isUpdating) {
       SDValue Inc = N->getOperand(AddrOpIdx + 1);
-      Ops.push_back(isa<ConstantSDNode>(Inc.getNode()) ? Reg0 : Inc);
+      // FIXME: VLD1 fixed increment doesn't need Reg0. Remove the reg0
+      // case entirely when the rest are updated to that form, too.
+      // Do that before committing this change. Likewise, the opcode
+      // update call will become unconditional.
+      if (NumVecs == 1 && !isa<ConstantSDNode>(Inc.getNode()))
+        Opc = getVLDSTRegisterUpdateOpcode(Opc);
+      if (NumVecs != 1 || !isa<ConstantSDNode>(Inc.getNode()))
+        Ops.push_back(isa<ConstantSDNode>(Inc.getNode()) ? Reg0 : Inc);
     }
     Ops.push_back(Pred);
     Ops.push_back(Reg0);
@@ -2750,16 +2774,18 @@ SDNode *ARMDAGToDAGISel::Select(SDNode *N) {
   }
 
   case ARMISD::VLD1_UPD: {
-    unsigned DOpcodes[] = { ARM::VLD1d8_UPD, ARM::VLD1d16_UPD,
-                            ARM::VLD1d32_UPD, ARM::VLD1d64_UPD };
-    unsigned QOpcodes[] = { ARM::VLD1q8Pseudo_UPD, ARM::VLD1q16Pseudo_UPD,
-                            ARM::VLD1q32Pseudo_UPD, ARM::VLD1q64Pseudo_UPD };
+    unsigned DOpcodes[] = { ARM::VLD1d8wb_fixed, ARM::VLD1d16wb_fixed,
+                            ARM::VLD1d32wb_fixed, ARM::VLD1d64wb_fixed };
+    unsigned QOpcodes[] = { ARM::VLD1q8PseudoWB_fixed,
+                            ARM::VLD1q16PseudoWB_fixed,
+                            ARM::VLD1q32PseudoWB_fixed,
+                            ARM::VLD1q64PseudoWB_fixed };
     return SelectVLD(N, true, 1, DOpcodes, QOpcodes, 0);
   }
 
   case ARMISD::VLD2_UPD: {
     unsigned DOpcodes[] = { ARM::VLD2d8Pseudo_UPD, ARM::VLD2d16Pseudo_UPD,
-                            ARM::VLD2d32Pseudo_UPD, ARM::VLD1q64Pseudo_UPD };
+                            ARM::VLD2d32Pseudo_UPD, ARM::VLD1q64PseudoWB_fixed};
     unsigned QOpcodes[] = { ARM::VLD2q8Pseudo_UPD, ARM::VLD2q16Pseudo_UPD,
                             ARM::VLD2q32Pseudo_UPD };
     return SelectVLD(N, true, 2, DOpcodes, QOpcodes, 0);
@@ -2767,7 +2793,7 @@ SDNode *ARMDAGToDAGISel::Select(SDNode *N) {
 
   case ARMISD::VLD3_UPD: {
     unsigned DOpcodes[] = { ARM::VLD3d8Pseudo_UPD, ARM::VLD3d16Pseudo_UPD,
-                            ARM::VLD3d32Pseudo_UPD, ARM::VLD1d64TPseudo_UPD };
+                            ARM::VLD3d32Pseudo_UPD, ARM::VLD1q64PseudoWB_fixed};
     unsigned QOpcodes0[] = { ARM::VLD3q8Pseudo_UPD,
                              ARM::VLD3q16Pseudo_UPD,
                              ARM::VLD3q32Pseudo_UPD };
@@ -2779,7 +2805,7 @@ SDNode *ARMDAGToDAGISel::Select(SDNode *N) {
 
   case ARMISD::VLD4_UPD: {
     unsigned DOpcodes[] = { ARM::VLD4d8Pseudo_UPD, ARM::VLD4d16Pseudo_UPD,
-                            ARM::VLD4d32Pseudo_UPD, ARM::VLD1d64QPseudo_UPD };
+                            ARM::VLD4d32Pseudo_UPD, ARM::VLD1q64PseudoWB_fixed};
     unsigned QOpcodes0[] = { ARM::VLD4q8Pseudo_UPD,
                              ARM::VLD4q16Pseudo_UPD,
                              ARM::VLD4q32Pseudo_UPD };
diff --git a/lib/Target/ARM/ARMInstrNEON.td b/lib/Target/ARM/ARMInstrNEON.td
index 1efe68165a..9bea53b41a 100644
--- a/lib/Target/ARM/ARMInstrNEON.td
+++ b/lib/Target/ARM/ARMInstrNEON.td
@@ -259,6 +259,14 @@ class VLDQWBPseudo<InstrItinClass itin>
   : PseudoNLdSt<(outs QPR:$dst, GPR:$wb),
                 (ins addrmode6:$addr, am6offset:$offset), itin,
                 "$addr.addr = $wb">;
+class VLDQWBfixedPseudo<InstrItinClass itin>
+  : PseudoNLdSt<(outs QPR:$dst, GPR:$wb),
+                (ins addrmode6:$addr), itin,
+                "$addr.addr = $wb">;
+class VLDQWBregisterPseudo<InstrItinClass itin>
+  : PseudoNLdSt<(outs QPR:$dst, GPR:$wb),
+                (ins addrmode6:$addr, rGPR:$offset), itin,
+                "$addr.addr = $wb">;
 class VLDQQPseudo<InstrItinClass itin>
   : PseudoNLdSt<(outs QQPR:$dst), (ins addrmode6:$addr), itin, "">;
 class VLDQQWBPseudo<InstrItinClass itin>
@@ -309,37 +317,58 @@ def  VLD1q32Pseudo : VLDQPseudo<IIC_VLD1x2>;
 def  VLD1q64Pseudo : VLDQPseudo<IIC_VLD1x2>;
 
 // ...with address register writeback:
-class VLD1DWB<bits<4> op7_4, string Dt>
-  : NLdSt<0,0b10,0b0111,op7_4, (outs DPR:$Vd, GPR:$wb),
-          (ins addrmode6:$Rn, am6offset:$Rm), IIC_VLD1u,
-          "vld1", Dt, "\\{$Vd\\}, $Rn$Rm",
-          "$Rn.addr = $wb", []> {
-  let Inst{4} = Rn{4};
-  let DecoderMethod = "DecodeVLDInstruction";
+multiclass VLD1DWB<bits<4> op7_4, string Dt> {
+  def _fixed : NLdSt<0,0b10, 0b0111,op7_4, (outs VecListOneD:$Vd, GPR:$wb),
+                     (ins addrmode6:$Rn), IIC_VLD1u,
+                     "vld1", Dt, "$Vd, $Rn!",
+                     "$Rn.addr = $wb", []> {
+    let Rm = 0b1101; // NLdSt will assign to the right encoding bits.
+    let Inst{4} = Rn{4};
+    let DecoderMethod = "DecodeVLDInstruction";
+  }
+  def _register : NLdSt<0,0b10,0b0111,op7_4, (outs VecListOneD:$Vd, GPR:$wb),
+                        (ins addrmode6:$Rn, rGPR:$Rm), IIC_VLD1u,
+                        "vld1", Dt, "$Vd, $Rn, $Rm",
+                        "$Rn.addr = $wb", []> {
+    let Inst{4} = Rn{4};
+    let DecoderMethod = "DecodeVLDInstruction";
+  }
 }
-class VLD1QWB<bits<4> op7_4, string Dt>
-  : NLdSt<0,0b10,0b1010,op7_4, (outs VecListTwoD:$Vd, GPR:$wb),
-          (ins addrmode6:$Rn, am6offset:$Rm), IIC_VLD1x2u,
-          "vld1", Dt, "$Vd, $Rn$Rm",
-          "$Rn.addr = $wb", []> {
-  let Inst{5-4} = Rn{5-4};
-  let DecoderMethod = "DecodeVLDInstruction";
+multiclass VLD1QWB<bits<4> op7_4, string Dt> {
+  def _fixed : NLdSt<0,0b10,0b1010,op7_4, (outs VecListTwoD:$Vd, GPR:$wb),
+                    (ins addrmode6:$Rn), IIC_VLD1x2u,
+                     "vld1", Dt, "$Vd, $Rn!",
+                     "$Rn.addr = $wb", []> {
+    let Rm = 0b1101; // NLdSt will assign to the right encoding bits.
+    let Inst{5-4} = Rn{5-4};
+    let DecoderMethod = "DecodeVLDInstruction";
+  }
+  def _register : NLdSt<0,0b10,0b1010,op7_4, (outs VecListTwoD:$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";
+  }
 }
 
-def VLD1d8_UPD  : VLD1DWB<{0,0,0,?}, "8">;
-def VLD1d16_UPD : VLD1DWB<{0,1,0,?}, "16">;
-def VLD1d32_UPD : VLD1DWB<{1,0,0,?}, "32">;
-def VLD1d64_UPD : VLD1DWB<{1,1,0,?}, "64">;
-
-def VLD1q8_UPD  : VLD1QWB<{0,0,?,?}, "8">;
-def VLD1q16_UPD : VLD1QWB<{0,1,?,?}, "16">;
-def VLD1q32_UPD : VLD1QWB<{1,0,?,?}, "32">;
-def VLD1q64_UPD : VLD1QWB<{1,1,?,?}, "64">;
-
-def VLD1q8Pseudo_UPD  : VLDQWBPseudo<IIC_VLD1x2u>;
-def VLD1q16Pseudo_UPD : VLDQWBPseudo<IIC_VLD1x2u>;
-def VLD1q32Pseudo_UPD : VLDQWBPseudo<IIC_VLD1x2u>;
-def VLD1q64Pseudo_UPD : VLDQWBPseudo<IIC_VLD1x2u>;
+defm VLD1d8wb  : VLD1DWB<{0,0,0,?}, "8">;
+defm VLD1d16wb : VLD1DWB<{0,1,0,?}, "16">;
+defm VLD1d32wb : VLD1DWB<{1,0,0,?}, "32">;
+defm VLD1d64wb : VLD1DWB<{1,1,0,?}, "64">;
+defm VLD1q8wb  : VLD1QWB<{0,0,?,?}, "8">;
+defm VLD1q16wb : VLD1QWB<{0,1,?,?}, "16">;
+defm VLD1q32wb : VLD1QWB<{1,0,?,?}, "32">;
+defm VLD1q64wb : VLD1QWB<{1,1,?,?}, "64">;
+
+def VLD1q8PseudoWB_fixed  : VLDQWBfixedPseudo<IIC_VLD1x2u>;
+def VLD1q16PseudoWB_fixed : VLDQWBfixedPseudo<IIC_VLD1x2u>;
+def VLD1q32PseudoWB_fixed : VLDQWBfixedPseudo<IIC_VLD1x2u>;
+def VLD1q64PseudoWB_fixed : VLDQWBfixedPseudo<IIC_VLD1x2u>;
+def VLD1q8PseudoWB_register  : VLDQWBregisterPseudo<IIC_VLD1x2u>;
+def VLD1q16PseudoWB_register : VLDQWBregisterPseudo<IIC_VLD1x2u>;
+def VLD1q32PseudoWB_register : VLDQWBregisterPseudo<IIC_VLD1x2u>;
+def VLD1q64PseudoWB_register : VLDQWBregisterPseudo<IIC_VLD1x2u>;
 
 // ...with 3 registers
 class VLD1D3<bits<4> op7_4, string Dt>
diff --git a/lib/Target/ARM/Disassembler/ARMDisassembler.cpp b/lib/Target/ARM/Disassembler/ARMDisassembler.cpp
index bc9a09fb99..d6b9260157 100644
--- a/lib/Target/ARM/Disassembler/ARMDisassembler.cpp
+++ b/lib/Target/ARM/Disassembler/ARMDisassembler.cpp
@@ -2054,14 +2054,22 @@ static DecodeStatus DecodeVLDInstruction(llvm::MCInst &Inst, unsigned Insn,
 
   // Writeback operand
   switch (Inst.getOpcode()) {
-    case ARM::VLD1d8_UPD:
-    case ARM::VLD1d16_UPD:
-    case ARM::VLD1d32_UPD:
-    case ARM::VLD1d64_UPD:
-    case ARM::VLD1q8_UPD:
-    case ARM::VLD1q16_UPD:
-    case ARM::VLD1q32_UPD:
-    case ARM::VLD1q64_UPD:
+    case ARM::VLD1d8wb_fixed:
+    case ARM::VLD1d16wb_fixed:
+    case ARM::VLD1d32wb_fixed:
+    case ARM::VLD1d64wb_fixed:
+    case ARM::VLD1d8wb_register:
+    case ARM::VLD1d16wb_register:
+    case ARM::VLD1d32wb_register:
+    case ARM::VLD1d64wb_register:
+    case ARM::VLD1q8wb_fixed:
+    case ARM::VLD1q16wb_fixed:
+    case ARM::VLD1q32wb_fixed:
+    case ARM::VLD1q64wb_fixed:
+    case ARM::VLD1q8wb_register:
+    case ARM::VLD1q16wb_register:
+    case ARM::VLD1q32wb_register:
+    case ARM::VLD1q64wb_register:
     case ARM::VLD1d8T_UPD:
     case ARM::VLD1d16T_UPD:
     case ARM::VLD1d32T_UPD:
@@ -2103,11 +2111,42 @@ static DecodeStatus DecodeVLDInstruction(llvm::MCInst &Inst, unsigned Insn,
     return MCDisassembler::Fail;
 
   // AddrMode6 Offset (register)
-  if (Rm == 0xD)
-    Inst.addOperand(MCOperand::CreateReg(0));
-  else if (Rm != 0xF) {
-    if (!Check(S, DecodeGPRRegisterClass(Inst, Rm, Address, Decoder)))
+  switch (Inst.getOpcode()) {
+  default:
+    // The below have been updated to have explicit am6offset split
+    // between fixed and register offset. For those instructions not
+    // yet updated, we need to add an additional reg0 operand for the
+    // fixed variant.
+    //
+    // The fixed offset encodes as Rm == 0xd, so we check for that.
+    if (Rm == 0xd) {
+      Inst.addOperand(MCOperand::CreateReg(0));
+      break;
+    }
+    // Fall through to handle the register offset variant.
+  case ARM::VLD1d8wb_fixed:
+  case ARM::VLD1d16wb_fixed:
+  case ARM::VLD1d32wb_fixed:
+  case ARM::VLD1d64wb_fixed:
+  case ARM::VLD1d8wb_register:
+  case ARM::VLD1d16wb_register:
+  case ARM::VLD1d32wb_register:
+  case ARM::VLD1d64wb_register:
+  case ARM::VLD1q8wb_fixed:
+  case ARM::VLD1q16wb_fixed:
+  case ARM::VLD1q32wb_fixed:
+  case ARM::VLD1q64wb_fixed:
+  case ARM::VLD1q8wb_register:
+  case ARM::VLD1q16wb_register:
+  case ARM::VLD1q32wb_register:
+  case ARM::VLD1q64wb_register:
+    // The fixed offset post-increment encodes Rm == 0xd. The no-writeback
+    // variant encodes Rm == 0xf. Anything else is a register offset post-
+    // increment and we need to add the register operand to the instruction.
+    if (Rm != 0xD && Rm != 0xF &&
+        !Check(S, DecodeGPRRegisterClass(Inst, Rm, Address, Decoder)))
       return MCDisassembler::Fail;
+    break;
   }
 
   return S;