diff --git a/llvm/lib/Target/ARM/ARMExpandPseudoInsts.cpp b/llvm/lib/Target/ARM/ARMExpandPseudoInsts.cpp
index f0b69b0b09809..0f7858a3be9f9 100644
--- a/llvm/lib/Target/ARM/ARMExpandPseudoInsts.cpp
+++ b/llvm/lib/Target/ARM/ARMExpandPseudoInsts.cpp
@@ -1470,13 +1470,19 @@ void ARMExpandPseudo::CMSESaveClearFPRegsV8(
 
   // Lazy store all fp registers to the stack.
   // This executes as NOP in the absence of floating-point support.
-  MachineInstrBuilder VLSTM = BuildMI(MBB, MBBI, DL, TII->get(ARM::VLSTM))
-                                  .addReg(ARM::SP)
-                                  .add(predOps(ARMCC::AL));
-  for (auto R : {ARM::VPR, ARM::FPSCR, ARM::FPSCR_NZCV, ARM::Q0, ARM::Q1,
-                 ARM::Q2, ARM::Q3, ARM::Q4, ARM::Q5, ARM::Q6, ARM::Q7})
-    VLSTM.addReg(R, RegState::Implicit |
-                        (LiveRegs.contains(R) ? 0 : RegState::Undef));
+  MachineInstrBuilder VLSTM =
+      BuildMI(MBB, MBBI, DL, TII->get(ARM::VLSTM))
+          .addReg(ARM::SP)
+          .add(predOps(ARMCC::AL))
+          .addImm(0); // Represents a pseoudo register list, has no effect on
+                      // the encoding.
+  // Mark non-live registers as undef
+  for (MachineOperand &MO : VLSTM->implicit_operands()) {
+    if (MO.isReg() && !MO.isDef()) {
+      Register Reg = MO.getReg();
+      MO.setIsUndef(!LiveRegs.contains(Reg));
+    }
+  }
 
   // Restore all arguments
   for (const auto &Regs : ClearedFPRegs) {
@@ -1564,13 +1570,19 @@ void ARMExpandPseudo::CMSESaveClearFPRegsV81(MachineBasicBlock &MBB,
         .add(predOps(ARMCC::AL));
 
     // Lazy store all FP registers to the stack
-    MachineInstrBuilder VLSTM = BuildMI(MBB, MBBI, DL, TII->get(ARM::VLSTM))
-                                    .addReg(ARM::SP)
-                                    .add(predOps(ARMCC::AL));
-    for (auto R : {ARM::VPR, ARM::FPSCR, ARM::FPSCR_NZCV, ARM::Q0, ARM::Q1,
-                   ARM::Q2, ARM::Q3, ARM::Q4, ARM::Q5, ARM::Q6, ARM::Q7})
-      VLSTM.addReg(R, RegState::Implicit |
-                          (LiveRegs.contains(R) ? 0 : RegState::Undef));
+    MachineInstrBuilder VLSTM =
+        BuildMI(MBB, MBBI, DL, TII->get(ARM::VLSTM))
+            .addReg(ARM::SP)
+            .add(predOps(ARMCC::AL))
+            .addImm(0); // Represents a pseoudo register list, has no effect on
+                        // the encoding.
+    // Mark non-live registers as undef
+    for (MachineOperand &MO : VLSTM->implicit_operands()) {
+      if (MO.isReg() && MO.isImplicit() && !MO.isDef()) {
+        Register Reg = MO.getReg();
+        MO.setIsUndef(!LiveRegs.contains(Reg));
+      }
+    }
   } else {
     // Push all the callee-saved registers (s16-s31).
     MachineInstrBuilder VPUSH =
@@ -1673,9 +1685,12 @@ void ARMExpandPseudo::CMSERestoreFPRegsV8(
 
   // Lazy load fp regs from stack.
   // This executes as NOP in the absence of floating-point support.
-  MachineInstrBuilder VLLDM = BuildMI(MBB, MBBI, DL, TII->get(ARM::VLLDM))
-                                  .addReg(ARM::SP)
-                                  .add(predOps(ARMCC::AL));
+  MachineInstrBuilder VLLDM =
+      BuildMI(MBB, MBBI, DL, TII->get(ARM::VLLDM))
+          .addReg(ARM::SP)
+          .add(predOps(ARMCC::AL))
+          .addImm(0); // Represents a pseoudo register list, has no effect on
+                      // the encoding.
 
   if (STI->fixCMSE_CVE_2021_35465()) {
     auto Bundler = MIBundleBuilder(MBB, VLLDM);
@@ -1757,7 +1772,9 @@ void ARMExpandPseudo::CMSERestoreFPRegsV81(
     // Load FP registers from stack.
     BuildMI(MBB, MBBI, DL, TII->get(ARM::VLLDM))
         .addReg(ARM::SP)
-        .add(predOps(ARMCC::AL));
+        .add(predOps(ARMCC::AL))
+        .addImm(0); // Represents a pseoudo register list, has no effect on the
+                    // encoding.
 
     // Pop the stack space
     BuildMI(MBB, MBBI, DL, TII->get(ARM::tADDspi), ARM::SP)
diff --git a/llvm/lib/Target/ARM/ARMInstrFormats.td b/llvm/lib/Target/ARM/ARMInstrFormats.td
index 14e315534570d..404085820a666 100644
--- a/llvm/lib/Target/ARM/ARMInstrFormats.td
+++ b/llvm/lib/Target/ARM/ARMInstrFormats.td
@@ -1749,6 +1749,37 @@ class AXSI4<dag oops, dag iops, IndexMode im, InstrItinClass itin,
   let Inst{8}     = 0;          // Single precision
 }
 
+// Single Precision with fixed registers.
+// For when the registers-to-be-stored/loaded are fixed, e.g. VLLDM and VLSTM
+class AXSI4FR<string asm, bit et, bit load>
+    : InstARM<AddrMode4, 4, IndexModeNone, VFPLdStMulFrm, VFPDomain, "", NoItinerary> {
+  // Instruction operands.
+  bits<4> Rn;
+  bits<13> regs;    // Does not affect encoding, for assembly/disassembly only.
+  list<Predicate> Predicates = [HasVFP2];
+  let OutOperandList = (outs);
+  let InOperandList = (ins GPRnopc:$Rn, pred:$p, dpr_reglist:$regs);
+  let AsmString = asm;
+  let Pattern = [];
+  let DecoderNamespace = "VFP";
+  // Encode instruction operands.
+  let Inst{19-16} = Rn;
+  let Inst{31-28} = 0b1110;
+  let Inst{27-25} = 0b110;
+  let Inst{24}    = 0b0;
+  let Inst{23}    = 0b0;
+  let Inst{22}    = 0b0;
+  let Inst{21}    = 0b1;
+  let Inst{20}    = load;       // Distinguishes vlldm from vlstm
+  let Inst{15-12} = 0b0000;
+  let Inst{11-9}  = 0b101;
+  let Inst{8}     = 0;          // Single precision
+  let Inst{7}     = et;         // encoding type, 0 for T1 and 1 for T2.
+  let Inst{6-0}   = 0b0000000;
+  let mayLoad     = load;
+  let mayStore    = !eq(load, 0);
+}
+
 // Double precision, unary
 class ADuI<bits<5> opcod1, bits<2> opcod2, bits<4> opcod3, bits<2> opcod4,
            bit opcod5, dag oops, dag iops, InstrItinClass itin, string opc,
diff --git a/llvm/lib/Target/ARM/ARMInstrVFP.td b/llvm/lib/Target/ARM/ARMInstrVFP.td
index 55d3efbd9b9a2..3094a4db2b4d1 100644
--- a/llvm/lib/Target/ARM/ARMInstrVFP.td
+++ b/llvm/lib/Target/ARM/ARMInstrVFP.td
@@ -313,29 +313,51 @@ def : MnemonicAlias<"vstm", "vstmia">;
 //===----------------------------------------------------------------------===//
 //  Lazy load / store multiple Instructions
 //
-def VLLDM : AXSI4<(outs), (ins GPRnopc:$Rn, pred:$p), IndexModeNone,
-                  NoItinerary, "vlldm${p}\t$Rn", "", []>,
+// VLLDM and VLSTM:
+// 2 encoding options:
+// T1 (bit 7 is 0):
+// T1 takes an optional dpr_reglist, must be '{d0-d15}' (exactly)
+// T1 require v8-M.Main, secure state, target with 16 D registers (or with no D registers - NOP)
+// T2 (bit 7 is 1):
+// T2 takes a mandatory dpr_reglist, must be '{d0-d31}' (exactly)
+// T2 require v8.1-M.Main, secure state, target with 16/32 D registers (or with no D registers - NOP)
+// (source: Arm v8-M ARM, DDI0553B.v ID16122022)
+
+def VLLDM : AXSI4FR<"vlldm${p}\t$Rn, $regs", 0, 1>,
             Requires<[HasV8MMainline, Has8MSecExt]> {
-    let Inst{24-23} = 0b00;
-    let Inst{22}    = 0;
-    let Inst{21}    = 1;
-    let Inst{20}    = 1;
-    let Inst{15-12} = 0;
-    let Inst{7-0}   = 0;
-    let mayLoad     = 1;
-    let Defs = [Q0, Q1, Q2, Q3, Q4, Q5, Q6, Q7, VPR, FPSCR, FPSCR_NZCV];
-}
-
-def VLSTM : AXSI4<(outs), (ins GPRnopc:$Rn, pred:$p), IndexModeNone,
-                  NoItinerary, "vlstm${p}\t$Rn", "", []>,
+    let Defs = [VPR, FPSCR, FPSCR_NZCV, D0, D1, D2, D3, D4, D5, D6, D7, D8, D9, D10, D11, D12, D13, D14, D15];
+    let DecoderMethod = "DecodeLazyLoadStoreMul";
+}
+// T1: assembly does not contains the register list.
+def : InstAlias<"vlldm${p}\t$Rn", (VLLDM GPRnopc:$Rn, pred:$p, 0)>,
+                Requires<[HasV8MMainline, Has8MSecExt]>;
+// T2: assembly must contains the register list.
+// The register list has no effect on the encoding, it is for assembly/disassembly purposes only.
+def VLLDM_T2 : AXSI4FR<"vlldm${p}\t$Rn, $regs", 1, 1>,
+            Requires<[HasV8_1MMainline, Has8MSecExt]> {
+    let Defs = [VPR, FPSCR, FPSCR_NZCV, D0,  D1,  D2,  D3,  D4,  D5,  D6,  D7,  D8,  D9,  D10, D11, D12, D13, D14, D15,
+                                        D16, D17, D18, D19, D20, D21, D22, D23, D24, D25, D26, D27, D28, D29, D30, D31];
+    let DecoderMethod = "DecodeLazyLoadStoreMul";
+}
+// T1: assembly contains the register list.
+// The register list has no effect on the encoding, it is for assembly/disassembly purposes only.
+def VLSTM : AXSI4FR<"vlstm${p}\t$Rn, $regs", 0, 0>,
             Requires<[HasV8MMainline, Has8MSecExt]> {
-    let Inst{24-23} = 0b00;
-    let Inst{22}    = 0;
-    let Inst{21}    = 1;
-    let Inst{20}    = 0;
-    let Inst{15-12} = 0;
-    let Inst{7-0}   = 0;
-    let mayStore    = 1;
+    let Defs = [VPR, FPSCR, FPSCR_NZCV];
+    let Uses = [VPR, FPSCR, FPSCR_NZCV, D0, D1, D2, D3, D4, D5, D6, D7, D8, D9, D10, D11, D12, D13, D14, D15];
+    let DecoderMethod = "DecodeLazyLoadStoreMul";
+}
+// T1: assembly does not contain the register list.
+def : InstAlias<"vlstm${p}\t$Rn", (VLSTM GPRnopc:$Rn, pred:$p, 0)>,
+                Requires<[HasV8MMainline, Has8MSecExt]>;
+// T2: assembly must contain the register list.
+// The register list has no effect on the encoding, it is for assembly/disassembly purposes only.
+def VLSTM_T2 : AXSI4FR<"vlstm${p}\t$Rn, $regs", 1, 0>,
+            Requires<[HasV8_1MMainline, Has8MSecExt]> {
+    let Defs = [VPR, FPSCR, FPSCR_NZCV];
+    let Uses = [VPR, FPSCR, FPSCR_NZCV, D0,  D1,  D2,  D3,  D4,  D5,  D6,  D7,  D8,  D9,  D10, D11, D12, D13, D14, D15,
+                                        D16, D17, D18, D19, D20, D21, D22, D23, D24, D25, D26, D27, D28, D29, D30, D31];
+    let DecoderMethod = "DecodeLazyLoadStoreMul";
 }
 
 def : InstAlias<"vpush${p} $r", (VSTMDDB_UPD SP, pred:$p, dpr_reglist:$r), 0>,
diff --git a/llvm/lib/Target/ARM/AsmParser/ARMAsmParser.cpp b/llvm/lib/Target/ARM/AsmParser/ARMAsmParser.cpp
index efec163c6ed63..c320bf723c88b 100644
--- a/llvm/lib/Target/ARM/AsmParser/ARMAsmParser.cpp
+++ b/llvm/lib/Target/ARM/AsmParser/ARMAsmParser.cpp
@@ -450,11 +450,12 @@ class ARMAsmParser : public MCTargetAsmParser {
   bool validatetSTMRegList(const MCInst &Inst, const OperandVector &Operands,
                            unsigned ListNo);
 
-  int tryParseRegister();
+  int tryParseRegister(bool AllowOutofBoundReg = false);
   bool tryParseRegisterWithWriteBack(OperandVector &);
   int tryParseShiftRegister(OperandVector &);
   bool parseRegisterList(OperandVector &, bool EnforceOrder = true,
-                         bool AllowRAAC = false);
+                         bool AllowRAAC = false,
+                         bool AllowOutOfBoundReg = false);
   bool parseMemory(OperandVector &);
   bool parseOperand(OperandVector &, StringRef Mnemonic);
   bool parseImmExpr(int64_t &Out);
@@ -4073,7 +4074,7 @@ ParseStatus ARMAsmParser::tryParseRegister(MCRegister &Reg, SMLoc &StartLoc,
 /// Try to parse a register name.  The token must be an Identifier when called,
 /// and if it is a register name the token is eaten and the register number is
 /// returned.  Otherwise return -1.
-int ARMAsmParser::tryParseRegister() {
+int ARMAsmParser::tryParseRegister(bool AllowOutOfBoundReg) {
   MCAsmParser &Parser = getParser();
   const AsmToken &Tok = Parser.getTok();
   if (Tok.isNot(AsmToken::Identifier)) return -1;
@@ -4117,7 +4118,8 @@ int ARMAsmParser::tryParseRegister() {
   }
 
   // Some FPUs only have 16 D registers, so D16-D31 are invalid
-  if (!hasD32() && RegNum >= ARM::D16 && RegNum <= ARM::D31)
+  if (!AllowOutOfBoundReg && !hasD32() && RegNum >= ARM::D16 &&
+      RegNum <= ARM::D31)
     return -1;
 
   Parser.Lex(); // Eat identifier token.
@@ -4457,7 +4459,7 @@ insertNoDuplicates(SmallVectorImpl<std::pair<unsigned, unsigned>> &Regs,
 
 /// Parse a register list.
 bool ARMAsmParser::parseRegisterList(OperandVector &Operands, bool EnforceOrder,
-                                     bool AllowRAAC) {
+                                     bool AllowRAAC, bool AllowOutOfBoundReg) {
   MCAsmParser &Parser = getParser();
   if (Parser.getTok().isNot(AsmToken::LCurly))
     return TokError("Token is not a Left Curly Brace");
@@ -4511,7 +4513,7 @@ bool ARMAsmParser::parseRegisterList(OperandVector &Operands, bool EnforceOrder,
         return Error(RegLoc, "pseudo-register not allowed");
       Parser.Lex(); // Eat the minus.
       SMLoc AfterMinusLoc = Parser.getTok().getLoc();
-      int EndReg = tryParseRegister();
+      int EndReg = tryParseRegister(AllowOutOfBoundReg);
       if (EndReg == -1)
         return Error(AfterMinusLoc, "register expected");
       if (EndReg == ARM::RA_AUTH_CODE)
@@ -4546,7 +4548,7 @@ bool ARMAsmParser::parseRegisterList(OperandVector &Operands, bool EnforceOrder,
     RegLoc = Parser.getTok().getLoc();
     int OldReg = Reg;
     const AsmToken RegTok = Parser.getTok();
-    Reg = tryParseRegister();
+    Reg = tryParseRegister(AllowOutOfBoundReg);
     if (Reg == -1)
       return Error(RegLoc, "register expected");
     if (!AllowRAAC && Reg == ARM::RA_AUTH_CODE)
@@ -6086,8 +6088,11 @@ bool ARMAsmParser::parseOperand(OperandVector &Operands, StringRef Mnemonic) {
   }
   case AsmToken::LBrac:
     return parseMemory(Operands);
-  case AsmToken::LCurly:
-    return parseRegisterList(Operands, !Mnemonic.starts_with("clr"));
+  case AsmToken::LCurly: {
+    bool AllowOutOfBoundReg = Mnemonic == "vlldm" || Mnemonic == "vlstm";
+    return parseRegisterList(Operands, !Mnemonic.starts_with("clr"), false,
+                             AllowOutOfBoundReg);
+  }
   case AsmToken::Dollar:
   case AsmToken::Hash: {
     // #42 -> immediate
@@ -7597,6 +7602,33 @@ bool ARMAsmParser::validateInstruction(MCInst &Inst,
 
   const unsigned Opcode = Inst.getOpcode();
   switch (Opcode) {
+  case ARM::VLLDM:
+  case ARM::VLLDM_T2:
+  case ARM::VLSTM:
+  case ARM::VLSTM_T2: {
+    // Since in some cases both T1 and T2 are valid, tablegen can not always
+    // pick the correct instruction.
+    if (Operands.size() == 4) { // a register list has been provided
+      ARMOperand &Op = static_cast<ARMOperand &>(
+          *Operands[3]); // the register list, a dpr_reglist
+      assert(Op.isDPRRegList());
+      auto &RegList = Op.getRegList();
+      // T2 requires v8.1-M.Main (cannot be handled by tablegen)
+      if (RegList.size() == 32 && !hasV8_1MMainline()) {
+        return Error(Op.getEndLoc(), "T2 version requires v8.1-M.Main");
+      }
+      // When target has 32 D registers, T1 is undefined.
+      if (hasD32() && RegList.size() != 32) {
+        return Error(Op.getEndLoc(), "operand must be exactly {d0-d31}");
+      }
+      // When target has 16 D registers, both T1 and T2 are valid.
+      if (!hasD32() && (RegList.size() != 16 && RegList.size() != 32)) {
+        return Error(Op.getEndLoc(),
+                     "operand must be exactly {d0-d15} (T1) or {d0-d31} (T2)");
+      }
+    }
+    return false;
+  }
   case ARM::t2IT: {
     // Encoding is unpredictable if it ever results in a notional 'NV'
     // predicate. Since we don't parse 'NV' directly this means an 'AL'
@@ -8732,6 +8764,32 @@ bool ARMAsmParser::processInstruction(MCInst &Inst,
   }
 
   switch (Inst.getOpcode()) {
+  case ARM::VLLDM:
+  case ARM::VLSTM: {
+    // In some cases both T1 and T2 are valid, causing tablegen pick T1 instead
+    // of T2
+    if (Operands.size() == 4) { // a register list has been provided
+      ARMOperand &Op = static_cast<ARMOperand &>(
+          *Operands[3]); // the register list, a dpr_reglist
+      assert(Op.isDPRRegList());
+      auto &RegList = Op.getRegList();
+      // When the register list is {d0-d31} the instruction has to be the T2
+      // variant
+      if (RegList.size() == 32) {
+        const unsigned Opcode =
+            (Inst.getOpcode() == ARM::VLLDM) ? ARM::VLLDM_T2 : ARM::VLSTM_T2;
+        MCInst TmpInst;
+        TmpInst.setOpcode(Opcode);
+        TmpInst.addOperand(Inst.getOperand(0));
+        TmpInst.addOperand(Inst.getOperand(1));
+        TmpInst.addOperand(Inst.getOperand(2));
+        TmpInst.addOperand(Inst.getOperand(3));
+        Inst = TmpInst;
+        return true;
+      }
+    }
+    return false;
+  }
   // Alias for alternate form of 'ldr{,b}t Rt, [Rn], #imm' instruction.
   case ARM::LDRT_POST:
   case ARM::LDRBT_POST: {
diff --git a/llvm/lib/Target/ARM/Disassembler/ARMDisassembler.cpp b/llvm/lib/Target/ARM/Disassembler/ARMDisassembler.cpp
index 604f22d711190..705f3cbce12f0 100644
--- a/llvm/lib/Target/ARM/Disassembler/ARMDisassembler.cpp
+++ b/llvm/lib/Target/ARM/Disassembler/ARMDisassembler.cpp
@@ -700,6 +700,9 @@ DecodeMVEOverlappingLongShift(MCInst &Inst, unsigned Insn, uint64_t Address,
 static DecodeStatus DecodeT2AddSubSPImm(MCInst &Inst, unsigned Insn,
                                         uint64_t Address,
                                         const MCDisassembler *Decoder);
+static DecodeStatus DecodeLazyLoadStoreMul(MCInst &Inst, unsigned Insn,
+                                           uint64_t Address,
+                                           const MCDisassembler *Decoder);
 
 #include "ARMGenDisassemblerTables.inc"
 
@@ -7030,3 +7033,23 @@ static DecodeStatus DecodeT2AddSubSPImm(MCInst &Inst, unsigned Insn,
 
   return DS;
 }
+
+static DecodeStatus DecodeLazyLoadStoreMul(MCInst &Inst, unsigned Insn,
+                                           uint64_t Address,
+                                           const MCDisassembler *Decoder) {
+  DecodeStatus S = MCDisassembler::Success;
+
+  const unsigned Rn = fieldFromInstruction(Insn, 16, 4);
+  // Adding Rn, holding memory location to save/load to/from, the only argument
+  // that is being encoded.
+  // '$Rn' in the assembly.
+  if (!Check(S, DecodeGPRRegisterClass(Inst, Rn, Address, Decoder)))
+    return MCDisassembler::Fail;
+  // An optional predicate, '$p' in the assembly.
+  DecodePredicateOperand(Inst, ARMCC::AL, Address, Decoder);
+  // An immediate that represents a floating point registers list. '$regs' in
+  // the assembly.
+  Inst.addOperand(MCOperand::createImm(0)); // Arbitrary value, has no effect.
+
+  return S;
+}
diff --git a/llvm/lib/Target/ARM/MCTargetDesc/ARMInstPrinter.cpp b/llvm/lib/Target/ARM/MCTargetDesc/ARMInstPrinter.cpp
index fbd067d79af0b..24e627cd9a4e1 100644
--- a/llvm/lib/Target/ARM/MCTargetDesc/ARMInstPrinter.cpp
+++ b/llvm/lib/Target/ARM/MCTargetDesc/ARMInstPrinter.cpp
@@ -91,6 +91,38 @@ void ARMInstPrinter::printInst(const MCInst *MI, uint64_t Address,
   unsigned Opcode = MI->getOpcode();
 
   switch (Opcode) {
+  case ARM::VLLDM: {
+    const MCOperand &Reg = MI->getOperand(0);
+    O << '\t' << "vlldm" << '\t';
+    printRegName(O, Reg.getReg());
+    O << ", "
+      << "{d0 - d15}";
+    return;
+  }
+  case ARM::VLLDM_T2: {
+    const MCOperand &Reg = MI->getOperand(0);
+    O << '\t' << "vlldm" << '\t';
+    printRegName(O, Reg.getReg());
+    O << ", "
+      << "{d0 - d31}";
+    return;
+  }
+  case ARM::VLSTM: {
+    const MCOperand &Reg = MI->getOperand(0);
+    O << '\t' << "vlstm" << '\t';
+    printRegName(O, Reg.getReg());
+    O << ", "
+      << "{d0 - d15}";
+    return;
+  }
+  case ARM::VLSTM_T2: {
+    const MCOperand &Reg = MI->getOperand(0);
+    O << '\t' << "vlstm" << '\t';
+    printRegName(O, Reg.getReg());
+    O << ", "
+      << "{d0 - d31}";
+    return;
+  }
   // Check for MOVs and print canonical forms, instead.
   case ARM::MOVsr: {
     // FIXME: Thumb variants?
diff --git a/llvm/test/CodeGen/ARM/cmse-vlldm-no-reorder.mir b/llvm/test/CodeGen/ARM/cmse-vlldm-no-reorder.mir
index 2bc4288884f19..3d49fee8fdaf4 100644
--- a/llvm/test/CodeGen/ARM/cmse-vlldm-no-reorder.mir
+++ b/llvm/test/CodeGen/ARM/cmse-vlldm-no-reorder.mir
@@ -89,7 +89,7 @@ body:             |
 # CHECK: $sp = t2STMDB_UPD $sp, 14 /* CC::al */, $noreg, $r4, $r5, $r6, undef $r7, $r8, $r9, $r10, $r11
 # CHECK-NEXT:  $r0 = t2BICri $r0, 1, 14 /* CC::al */, $noreg, $noreg
 # CHECK-NEXT:  $sp = tSUBspi $sp, 34, 14 /* CC::al */, $noreg
-# CHECK-NEXT:  VLSTM $sp, 14 /* CC::al */, $noreg, implicit undef $vpr, implicit undef $fpscr, implicit undef $fpscr_nzcv, implicit undef $q0, implicit undef $q1, implicit undef $q2, implicit undef $q3, implicit undef $q4, implicit undef $q5, implicit undef $q6, implicit undef $q7
+# CHECK-NEXT:  VLSTM $sp, 14 /* CC::al */, $noreg, 0, implicit-def $vpr, implicit-def $fpscr, implicit-def $fpscr_nzcv, implicit undef $vpr, implicit undef $fpscr, implicit undef $fpscr_nzcv, implicit undef $d0, implicit undef $d1, implicit undef $d2, implicit undef $d3, implicit undef $d4, implicit undef $d5, implicit undef $d6, implicit undef $d7, implicit $d8, implicit $d9, implicit $d10, implicit $d11, implicit $d12, implicit $d13, implicit $d14, implicit $d15
 # CHECK-NEXT:  $r1 = tMOVr $r0, 14 /* CC::al */, $noreg
 # CHECK-NEXT:  $r2 = tMOVr $r0, 14 /* CC::al */, $noreg
 # CHECK-NEXT:  $r3 = tMOVr $r0, 14 /* CC::al */, $noreg
@@ -105,8 +105,7 @@ body:             |
 # CHECK-NEXT:  t2MSR_M 3072, $r0, 14 /* CC::al */, $noreg, implicit-def $cpsr
 # CHECK-NEXT:  tBLXNSr 14 /* CC::al */, $noreg, killed $r0, csr_aapcs, implicit-def $lr, implicit $sp, implicit-def dead $lr, implicit $sp, implicit-def $sp, implicit-def $s0
 # CHECK-NEXT:  $r12 = VMOVRS $s0, 14 /* CC::al */, $noreg
-# CHECK-NEXT:  VLLDM $sp, 14 /* CC::al */, $noreg, implicit-def $q0, implicit-def $q1, implicit-def $q2, implicit-def $q3, implicit-def $q4, implicit-def $q5, implicit-def $q6, implicit-def $q7, implicit-def $vpr, implicit-def $fpscr, implicit-def $fpscr_nzcv
+# CHECK-NEXT:  VLLDM $sp, 14 /* CC::al */, $noreg, 0, implicit-def $vpr, implicit-def $fpscr, implicit-def $fpscr_nzcv, implicit-def $d0, implicit-def $d1, implicit-def $d2, implicit-def $d3, implicit-def $d4, implicit-def $d5, implicit-def $d6, implicit-def $d7, implicit-def $d8, implicit-def $d9, implicit-def $d10, implicit-def $d11, implicit-def $d12, implicit-def $d13, implicit-def $d14, implicit-def $d15
 # CHECK-NEXT:  $s0 = VMOVSR $r12, 14 /* CC::al */, $noreg
 # CHECK-NEXT:  $sp = tADDspi $sp, 34, 14 /* CC::al */, $noreg
 # CHECK-NEXT:  $sp = t2LDMIA_UPD $sp, 14 /* CC::al */, $noreg, def $r4, def $r5, def $r6, def $r7, def $r8, def $r9, def $r10, def $r11
- 
diff --git a/llvm/test/CodeGen/ARM/vlldm-vlstm-uops.mir b/llvm/test/CodeGen/ARM/vlldm-vlstm-uops.mir
index 8c49a53167411..8fa9337eae6cd 100644
--- a/llvm/test/CodeGen/ARM/vlldm-vlstm-uops.mir
+++ b/llvm/test/CodeGen/ARM/vlldm-vlstm-uops.mir
@@ -60,9 +60,9 @@ body:             |
     $sp = t2STMDB_UPD $sp, 14, $noreg, $r4, killed $r5, killed $r6, killed $r7, killed $r8, killed $r9, killed $r10, killed $r11
     $r4 = t2BICri $r4, 1, 14, $noreg, $noreg
     $sp = tSUBspi $sp, 34, 14, $noreg
-    VLSTM $sp, 14, $noreg
-    tBLXNSr 14, $noreg, killed $r4, csr_aapcs, implicit-def $lr, implicit $sp, implicit-def dead $lr, implicit $sp, implicit-def $sp
-    VLLDM $sp, 14, $noreg, implicit-def $q0, implicit-def $q1, implicit-def $q2, implicit-def $q3, implicit-def $q4, implicit-def $q5, implicit-def $q6, implicit-def $q7, implicit-def $vpr, implicit-def $fpscr, implicit-def $fpscr_nzcv
+    VLSTM $sp, 14 /* CC::al */, $noreg, 0, implicit-def $vpr, implicit-def $fpscr, implicit-def $fpscr_nzcv, implicit undef $vpr, implicit undef $fpscr, implicit undef $fpscr_nzcv, implicit undef $d0, implicit undef $d1, implicit undef $d2, implicit undef $d3, implicit undef $d4, implicit undef $d5, implicit undef $d6, implicit undef $d7, implicit $d8, implicit $d9, implicit $d10, implicit $d11, implicit $d12, implicit $d13, implicit $d14, implicit $d15
+    tBLXNSr 14, $noreg, killed $r4, csr_aapcs, implicit-def $lr, implicit $sp, implicit-def dead $lr, implicit $sp, implicit-def $sp, implicit-def $q0, implicit-def $q1, implicit-def $q2, implicit-def $q3, implicit-def $q4, implicit-def $q5, implicit-def $q6, implicit-def $q7
+    VLLDM $sp, 14 /* CC::al */, $noreg, 0, implicit-def $vpr, implicit-def $fpscr, implicit-def $fpscr_nzcv, implicit-def $d0, implicit-def $d1, implicit-def $d2, implicit-def $d3, implicit-def $d4, implicit-def $d5, implicit-def $d6, implicit-def $d7, implicit-def $d8, implicit-def $d9, implicit-def $d10, implicit-def $d11, implicit-def $d12, implicit-def $d13, implicit-def $d14, implicit-def $d15
     $sp = tADDspi $sp, 34, 14, $noreg
     $sp = t2LDMIA_UPD $sp, 14, $noreg, def $r4, def $r5, def $r6, def $r7, def $r8, def $r9, def $r10, def $r11
     $sp = t2LDMIA_RET $sp, 14, $noreg, def $r4, def $pc
diff --git a/llvm/test/MC/ARM/thumbv8m.s b/llvm/test/MC/ARM/thumbv8m.s
index 0e9ab4a9b3bf9..f03dd03dae3a4 100644
--- a/llvm/test/MC/ARM/thumbv8m.s
+++ b/llvm/test/MC/ARM/thumbv8m.s
@@ -184,13 +184,13 @@ ttat r0, r1
 // 'Lazy Load/Store Multiple'
 
 // UNDEF-BASELINE: error: instruction requires: armv8m.main
-// CHECK-MAINLINE: vlldm r5          @ encoding: [0x35,0xec,0x00,0x0a]
-// CHECK-MAINLINE_DSP: vlldm r5      @ encoding: [0x35,0xec,0x00,0x0a]
+// CHECK-MAINLINE: vlldm r5, {d0 - d15} @ encoding: [0x35,0xec,0x00,0x0a]
+// CHECK-MAINLINE_DSP: vlldm r5, {d0 - d15} @ encoding: [0x35,0xec,0x00,0x0a]
 vlldm r5
 
 // UNDEF-BASELINE: error: instruction requires: armv8m.main
-// CHECK-MAINLINE: vlstm r10         @ encoding: [0x2a,0xec,0x00,0x0a]
-// CHECK-MAINLINE_DSP: vlstm r10     @ encoding: [0x2a,0xec,0x00,0x0a]
+// CHECK-MAINLINE: vlstm r10, {d0 - d15} @ encoding: [0x2a,0xec,0x00,0x0a]
+// CHECK-MAINLINE_DSP: vlstm r10, {d0 - d15} @ encoding: [0x2a,0xec,0x00,0x0a]
 vlstm r10
 
 // New SYSm's
diff --git a/llvm/test/MC/ARM/vlstm-vlldm-8.1m.s b/llvm/test/MC/ARM/vlstm-vlldm-8.1m.s
new file mode 100644
index 0000000000000..4e35883ffe433
--- /dev/null
+++ b/llvm/test/MC/ARM/vlstm-vlldm-8.1m.s
@@ -0,0 +1,11 @@
+// RUN: llvm-mc -triple=armv8.1m.main-arm-none-eabi -mcpu=generic -show-encoding %s \
+// RUN: | FileCheck --check-prefixes=CHECK %s
+
+// RUN: llvm-mc -triple=thumbv8.1m.main-none-eabi -mcpu=generic -show-encoding %s \
+// RUN: | FileCheck --check-prefixes=CHECK %s
+
+vlstm r8, {d0 - d31}
+// CHECK: vlstm	r8, {d0 - d31} @ encoding: [0x28,0xec,0x80,0x0a]
+
+vlldm r8, {d0 - d31}
+// CHECK: vlldm	r8, {d0 - d31} @ encoding: [0x38,0xec,0x80,0x0a]
diff --git a/llvm/test/MC/ARM/vlstm-vlldm-8m.s b/llvm/test/MC/ARM/vlstm-vlldm-8m.s
new file mode 100644
index 0000000000000..bbc95318aeb3d
--- /dev/null
+++ b/llvm/test/MC/ARM/vlstm-vlldm-8m.s
@@ -0,0 +1,17 @@
+// RUN: llvm-mc -triple=armv8m.main-arm-none-eabi -mcpu=generic -show-encoding %s \
+// RUN: | FileCheck --check-prefixes=CHECK %s
+
+// RUN: llvm-mc -triple=thumbv8m.main-none-eabi -mcpu=generic -show-encoding %s \
+// RUN: | FileCheck --check-prefixes=CHECK %s
+
+vlstm r8, {d0 - d15}
+// CHECK: vlstm	r8, {d0 - d15} @ encoding: [0x28,0xec,0x00,0x0a]
+
+vlldm r8, {d0 - d15}
+// CHECK: vlldm	r8, {d0 - d15} @ encoding: [0x38,0xec,0x00,0x0a]
+
+vlstm r8
+// CHECK: vlstm	r8, {d0 - d15} @ encoding: [0x28,0xec,0x00,0x0a]
+
+vlldm r8
+// CHECK: vlldm r8, {d0 - d15} @ encoding: [0x38,0xec,0x00,0x0a]
diff --git a/llvm/test/MC/ARM/vlstm-vlldm-diag.s b/llvm/test/MC/ARM/vlstm-vlldm-diag.s
new file mode 100644
index 0000000000000..b57f535c6a25c
--- /dev/null
+++ b/llvm/test/MC/ARM/vlstm-vlldm-diag.s
@@ -0,0 +1,61 @@
+// RUN: not llvm-mc -triple=armv8.1m.main-arm-none-eabi -mcpu=generic -show-encoding %s 2>&1 >/dev/null \
+// RUN: | FileCheck --check-prefixes=ERR %s
+
+// RUN: not llvm-mc -triple=armv8.1m.main-arm-none-eabi -mcpu=generic -show-encoding %s 2>&1 >/dev/null \
+// RUN: | FileCheck --check-prefixes=ERRT2 %s
+
+vlstm r8, {d0 - d11}
+// ERR: error: operand must be exactly {d0-d15} (T1) or {d0-d31} (T2)
+// ERR-NEXT: vlstm r8, {d0 - d11}
+
+vlldm r8, {d0 - d11}
+// ERR: error: operand must be exactly {d0-d15} (T1) or {d0-d31} (T2)
+// ERR-NEXT: vlldm r8, {d0 - d11}
+
+vlstm r8, {d3 - d15}
+// ERR: error: operand must be exactly {d0-d15} (T1) or {d0-d31} (T2)
+// ERR-NEXT: vlstm r8, {d3 - d15}
+
+vlldm r8, {d3 - d15}
+// ERR: error: operand must be exactly {d0-d15} (T1) or {d0-d31} (T2)
+// ERR-NEXT: vlldm r8, {d3 - d15}
+
+vlstm r8, {d0 - d29}
+// ERR: error: operand must be exactly {d0-d15} (T1) or {d0-d31} (T2)
+// ERR-NEXT: vlstm r8, {d0 - d29}
+
+vlldm r8, {d0 - d29}
+// ERR: error: operand must be exactly {d0-d15} (T1) or {d0-d31} (T2)
+// ERR-NEXT: vlldm r8, {d0 - d29}
+
+vlstm r8, {d3 - d31}
+// ERR: error: operand must be exactly {d0-d15} (T1) or {d0-d31} (T2)
+// ERR-NEXT: vlstm r8, {d3 - d31}
+
+vlldm r8, {d3 - d31}
+// ERR: error: operand must be exactly {d0-d15} (T1) or {d0-d31} (T2)
+// ERR-NEXT: vlldm r8, {d3 - d31}
+
+vlstm r8, {d0 - d35}
+// ERR: error: register expected
+// ERR-NEXT: vlstm r8, {d0 - d35}
+
+vlldm r8, {d0 - d35}
+// ERR: error: register expected
+// ERR-NEXT: vlldm r8, {d0 - d35}
+
+vlstm pc
+// ERR: error: operand must be a register in range [r0, r14]
+// ERR-NEXT: vlstm pc
+
+vlldm pc
+// ERR: error: operand must be a register in range [r0, r14]
+// ERR-NEXT: vlldm pc
+
+vlstm pc
+// ERRT2: error: operand must be a register in range [r0, r14]
+// ERRT2-NEXT: vlstm pc
+
+vlldm pc
+// ERRT2: error: operand must be a register in range [r0, r14]
+// ERRT2-NEXT: vlldm pc
\ No newline at end of file
diff --git a/llvm/test/MC/Disassembler/ARM/armv8.1m-vlldm_vlstm-8.1.main.txt b/llvm/test/MC/Disassembler/ARM/armv8.1m-vlldm_vlstm-8.1.main.txt
new file mode 100644
index 0000000000000..6b9882454c06a
--- /dev/null
+++ b/llvm/test/MC/Disassembler/ARM/armv8.1m-vlldm_vlstm-8.1.main.txt
@@ -0,0 +1,11 @@
+// RUN: llvm-mc -triple=armv8.1m.main-arm-none-eabi -mcpu=generic -show-encoding -disassemble %s \
+// RUN: | FileCheck %s --check-prefixes=CHECK-DISS
+
+// RUN: llvm-mc -triple=thumbv8.1m.main-none-eabi -mcpu=generic -show-encoding -disassemble %s \
+// RUN: | FileCheck %s --check-prefixes=CHECK-DISS
+
+[0x28,0xec,0x80,0x0a]
+// CHECK-DISS: vlstm r8, {d0 - d31} @ encoding: [0x28,0xec,0x80,0x0a]
+
+[0x38,0xec,0x80,0x0a]
+// CHECK-DISS: vlldm r8, {d0 - d31} @ encoding: [0x38,0xec,0x80,0x0a]
\ No newline at end of file
diff --git a/llvm/test/MC/Disassembler/ARM/armv8.1m-vlldm_vlstm-8.main.txt b/llvm/test/MC/Disassembler/ARM/armv8.1m-vlldm_vlstm-8.main.txt
new file mode 100644
index 0000000000000..1e28d5284c5b2
--- /dev/null
+++ b/llvm/test/MC/Disassembler/ARM/armv8.1m-vlldm_vlstm-8.main.txt
@@ -0,0 +1,17 @@
+// RUN: llvm-mc -triple=armv8m.main-arm-none-eabi -mcpu=generic -show-encoding -disassemble %s \
+// RUN: | FileCheck %s --check-prefixes=CHECK-DISS
+
+// RUN: llvm-mc -triple=thumbv8m.main-none-eabi -mcpu=generic -show-encoding -disassemble %s \
+// RUN: | FileCheck %s --check-prefixes=CHECK-DISS
+
+[0x28,0xec,0x00,0x0a]
+// CHECK-DISS: vlstm r8, {d0 - d15} @ encoding: [0x28,0xec,0x00,0x0a]
+
+[0x38,0xec,0x00,0x0a]
+// CHECK-DISS: vlldm r8, {d0 - d15} @ encoding: [0x38,0xec,0x00,0x0a]
+
+[0x28,0xec,0x00,0x0a]
+// CHECK-DISS: vlstm r8, {d0 - d15} @ encoding: [0x28,0xec,0x00,0x0a]
+
+[0x38,0xec,0x00,0x0a]
+// CHECK-DISS: vlldm r8, {d0 - d15} @ encoding: [0x38,0xec,0x00,0x0a]
\ No newline at end of file
diff --git a/llvm/unittests/Target/ARM/MachineInstrTest.cpp b/llvm/unittests/Target/ARM/MachineInstrTest.cpp
index aeb25bf012d03..3a76054ca4f36 100644
--- a/llvm/unittests/Target/ARM/MachineInstrTest.cpp
+++ b/llvm/unittests/Target/ARM/MachineInstrTest.cpp
@@ -1126,7 +1126,9 @@ TEST(MachineInstr, HasSideEffects) {
       VLDR_VPR_post,
       VLDR_VPR_pre,
       VLLDM,
+      VLLDM_T2,
       VLSTM,
+      VLSTM_T2,
       VMRS,
       VMRS_FPCXTNS,
       VMRS_FPCXTS,