[ARM] Add MVE vector bit-operations (register inputs).

This includes all the obvious bitwise operations (AND, OR, BIC, ORN, MVN) in register-to-register forms, and the immediate forms of AND/OR/BIC/ORN; byte-order reverse instructions; and the VMOVs that access a single lane of a vector. Some of those VMOVs (specifically, the ones that access a 32-bit lane) share an encoding with existing instructions that were disassembled as accessing half of a d-register (e.g. `vmov.32 r0, d1[0]`), but in 8.1-M they're now written as accessing a quarter of a q-register (e.g. `vmov.32 r0, q0[2]`). The older syntax is still accepted by the assembler. Reviewers: dmgreen, samparker, SjoerdMeijer, t.p.northover Subscribers: javed.absar, kristof.beyls, hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D62673 llvm-svn: 363838
2025-02-01 05:01:59 +01:00 · 2019-06-19 16:43:53 +00:00 · 2019-06-19 16:43:53 +00:00 · bc0266a9ee
commit bc0266a9ee
parent 41fc96e85e
12 changed files with 1097 additions and 25 deletions
--- a/lib/Target/ARM/ARMInstrFormats.td
+++ b/lib/Target/ARM/ARMInstrFormats.td
@ -465,6 +465,8 @@ class VFP2AsmPseudo<string asm, dag iops, dag oops = (outs)>
  : AsmPseudoInst<asm, iops, oops>, Requires<[HasVFP2]>;
 class NEONAsmPseudo<string asm, dag iops, dag oops = (outs)>
  : AsmPseudoInst<asm, iops, oops>, Requires<[HasNEON]>;
+class MVEAsmPseudo<string asm, dag iops, dag oops = (outs)>
+  : AsmPseudoInst<asm, iops, oops>, Requires<[HasMVEInt]>;

 // Pseudo instructions for the code generator.
 class PseudoInst<dag oops, dag iops, InstrItinClass itin, list<dag> pattern>
--- a/lib/Target/ARM/ARMInstrInfo.td
+++ b/lib/Target/ARM/ARMInstrInfo.td
@ -461,6 +461,19 @@ def rot_imm : Operand<i32>, PatLeaf<(i32 imm), [{
  let ParserMatchClass = RotImmAsmOperand;
 }

+// Vector indexing
+class MVEVectorIndexOperand<int NumLanes> : AsmOperandClass {
+  let Name = "MVEVectorIndex"#NumLanes;
+  let RenderMethod = "addMVEVectorIndexOperands";
+  let PredicateMethod = "isVectorIndexInRange<"#NumLanes#">";
+}
+
+class MVEVectorIndex<int NumLanes> : Operand<i32> {
+  let PrintMethod = "printVectorIndex";
+  let ParserMatchClass = MVEVectorIndexOperand<NumLanes>;
+  let MIOperandInfo = (ops i32imm);
+}
+
 // shift_imm: An integer that encodes a shift amount and the type of shift
 // (asr or lsl). The 6-bit immediate encodes as:
 //    {5}     0 ==> lsl
--- a/lib/Target/ARM/ARMInstrMVE.td
+++ b/lib/Target/ARM/ARMInstrMVE.td
@ -10,6 +10,44 @@
 //
 //===----------------------------------------------------------------------===//

+class ExpandImmAsmOp<string shift> : AsmOperandClass {
+  let Name = !strconcat("ExpandImm", shift);
+  let PredicateMethod = !strconcat("isExpImm<", shift, ">");
+  let RenderMethod = "addImmOperands";
+}
+class InvertedExpandImmAsmOp<string shift, string size> : AsmOperandClass {
+  let Name = !strconcat("InvertedExpandImm", shift, "_", size);
+  let PredicateMethod = !strconcat("isInvertedExpImm<", shift, ",", size, ">");
+  let RenderMethod = "addImmOperands";
+}
+
+class ExpandImm<string shift> : Operand<i32> {
+  let ParserMatchClass = ExpandImmAsmOp<shift>;
+  let EncoderMethod = !strconcat("getExpandedImmOpValue<",shift,",false>");
+  let DecoderMethod = !strconcat("DecodeExpandedImmOperand<",shift,">");
+  let PrintMethod = "printExpandedImmOperand";
+}
+class InvertedExpandImm<string shift, string size> : Operand<i32> {
+  let ParserMatchClass = InvertedExpandImmAsmOp<shift, size>;
+  let EncoderMethod = !strconcat("getExpandedImmOpValue<",shift,",true>");
+  let PrintMethod = "printExpandedImmOperand";
+  // No decoder method needed, because this operand type is only used
+  // by aliases (VAND and VORN)
+}
+
+def expzero00 : ExpandImm<"0">;
+def expzero08 : ExpandImm<"8">;
+def expzero16 : ExpandImm<"16">;
+def expzero24 : ExpandImm<"24">;
+
+def expzero00inv16 : InvertedExpandImm<"0", "16">;
+def expzero08inv16 : InvertedExpandImm<"8", "16">;
+
+def expzero00inv32 : InvertedExpandImm<"0", "32">;
+def expzero08inv32 : InvertedExpandImm<"8", "32">;
+def expzero16inv32 : InvertedExpandImm<"16", "32">;
+def expzero24inv32 : InvertedExpandImm<"24", "32">;
+
 // VPT condition mask
 def vpt_mask : Operand<i32> {
  let PrintMethod = "printVPTMask";
@ -113,6 +151,17 @@ class MVE_MI_with_pred<dag oops, dag iops, InstrItinClass itin, string asm,
  let DecoderNamespace = "MVE";
 }

+class MVE_VMOV_lane_base<dag oops, dag iops, InstrItinClass itin, string asm,
+                         string suffix, string ops, string cstr,
+                         list<dag> pattern>
+  : Thumb2I<oops, iops, AddrModeNone, 4, itin, asm,
+            !if(!eq(suffix, ""), "", "." # suffix) # "\t" # ops,
+            cstr, pattern>,
+    Requires<[HasV8_1MMainline, HasMVEInt]> {
+  let D = MVEDomain;
+  let DecoderNamespace = "MVE";
+}
+
 class MVE_ScalarShift<string iname, dag oops, dag iops, string asm, string cstr,
            list<dag> pattern=[]>
  : MVE_MI_with_pred<oops, iops, NoItinerary, iname, asm, cstr, pattern> {
@ -1217,6 +1266,261 @@ def MVE_VSHL_immi32 : MVE_VSHL_imm<"i32", (ins imm0_31:$imm)> {
 }
 // end of mve_shift instructions

+// start of mve_bit instructions
+
+class MVE_bit_arith<dag oops, dag iops, string iname, string suffix,
+                    string ops, string cstr, list<dag> pattern=[]>
+  : MVE_p<oops, iops, NoItinerary, iname, suffix, ops, vpred_r, cstr, pattern> {
+  bits<4> Qd;
+  bits<4> Qm;
+
+  let Inst{22} = Qd{3};
+  let Inst{15-13} = Qd{2-0};
+  let Inst{5} = Qm{3};
+  let Inst{3-1} = Qm{2-0};
+}
+
+def MVE_VBIC : MVE_bit_arith<(outs MQPR:$Qd), (ins MQPR:$Qn, MQPR:$Qm),
+                             "vbic", "", "$Qd, $Qn, $Qm", ""> {
+  bits<4> Qn;
+
+  let Inst{28} = 0b0;
+  let Inst{25-23} = 0b110;
+  let Inst{21-20} = 0b01;
+  let Inst{19-17} = Qn{2-0};
+  let Inst{16} = 0b0;
+  let Inst{12-8} = 0b00001;
+  let Inst{7} = Qn{3};
+  let Inst{6} = 0b1;
+  let Inst{4} = 0b1;
+  let Inst{0} = 0b0;
+}
+
+class MVE_VREV<string iname, string suffix, bits<2> size, bits<2> bit_8_7>
+  : MVE_bit_arith<(outs MQPR:$Qd), (ins MQPR:$Qm), iname,
+                  suffix, "$Qd, $Qm", ""> {
+
+  let Inst{28} = 0b1;
+  let Inst{25-23} = 0b111;
+  let Inst{21-20} = 0b11;
+  let Inst{19-18} = size;
+  let Inst{17-16} = 0b00;
+  let Inst{12-9} = 0b0000;
+  let Inst{8-7} = bit_8_7;
+  let Inst{6} = 0b1;
+  let Inst{4} = 0b0;
+  let Inst{0} = 0b0;
+}
+
+def MVE_VREV64_8  : MVE_VREV<"vrev64", "8", 0b00, 0b00>;
+def MVE_VREV64_16 : MVE_VREV<"vrev64", "16", 0b01, 0b00>;
+def MVE_VREV64_32 : MVE_VREV<"vrev64", "32", 0b10, 0b00>;
+
+def MVE_VREV32_8  : MVE_VREV<"vrev32", "8", 0b00, 0b01>;
+def MVE_VREV32_16 : MVE_VREV<"vrev32", "16", 0b01, 0b01>;
+
+def MVE_VREV16_8  : MVE_VREV<"vrev16", "8", 0b00, 0b10>;
+
+def MVE_VMVN : MVE_bit_arith<(outs MQPR:$Qd), (ins MQPR:$Qm),
+                             "vmvn", "", "$Qd, $Qm", ""> {
+  let Inst{28} = 0b1;
+  let Inst{25-23} = 0b111;
+  let Inst{21-16} = 0b110000;
+  let Inst{12-6} = 0b0010111;
+  let Inst{4} = 0b0;
+  let Inst{0} = 0b0;
+}
+
+class MVE_bit_ops<string iname, bits<2> bit_21_20, bit bit_28>
+  : MVE_bit_arith<(outs MQPR:$Qd), (ins MQPR:$Qn, MQPR:$Qm),
+                  iname, "", "$Qd, $Qn, $Qm", ""> {
+  bits<4> Qn;
+
+  let Inst{28} = bit_28;
+  let Inst{25-23} = 0b110;
+  let Inst{21-20} = bit_21_20;
+  let Inst{19-17} = Qn{2-0};
+  let Inst{16} = 0b0;
+  let Inst{12-8} = 0b00001;
+  let Inst{7} = Qn{3};
+  let Inst{6} = 0b1;
+  let Inst{4} = 0b1;
+  let Inst{0} = 0b0;
+}
+
+def MVE_VEOR : MVE_bit_ops<"veor", 0b00, 0b1>;
+def MVE_VORN : MVE_bit_ops<"vorn", 0b11, 0b0>;
+def MVE_VORR : MVE_bit_ops<"vorr", 0b10, 0b0>;
+def MVE_VAND : MVE_bit_ops<"vand", 0b00, 0b0>;
+
+// add ignored suffixes as aliases
+
+foreach s=["s8", "s16", "s32", "u8", "u16", "u32", "i8", "i16", "i32", "f16", "f32"] in {
+  def : MVEInstAlias<"vbic${vp}." # s # "\t$QdSrc, $QnSrc, $QmSrc",
+        (MVE_VBIC MQPR:$QdSrc, MQPR:$QnSrc, MQPR:$QmSrc, vpred_r:$vp)>;
+  def : MVEInstAlias<"veor${vp}." # s # "\t$QdSrc, $QnSrc, $QmSrc",
+        (MVE_VEOR MQPR:$QdSrc, MQPR:$QnSrc, MQPR:$QmSrc, vpred_r:$vp)>;
+  def : MVEInstAlias<"vorn${vp}." # s # "\t$QdSrc, $QnSrc, $QmSrc",
+        (MVE_VORN MQPR:$QdSrc, MQPR:$QnSrc, MQPR:$QmSrc, vpred_r:$vp)>;
+  def : MVEInstAlias<"vorr${vp}." # s # "\t$QdSrc, $QnSrc, $QmSrc",
+        (MVE_VORR MQPR:$QdSrc, MQPR:$QnSrc, MQPR:$QmSrc, vpred_r:$vp)>;
+  def : MVEInstAlias<"vand${vp}." # s # "\t$QdSrc, $QnSrc, $QmSrc",
+        (MVE_VAND MQPR:$QdSrc, MQPR:$QnSrc, MQPR:$QmSrc, vpred_r:$vp)>;
+}
+
+class MVE_bit_cmode<string iname, string suffix, bits<4> cmode, dag inOps>
+  : MVE_p<(outs MQPR:$Qd), inOps, NoItinerary,
+          iname, suffix, "$Qd, $imm", vpred_n, "$Qd = $Qd_src"> {
+  bits<8> imm;
+  bits<4> Qd;
+
+  let Inst{28} = imm{7};
+  let Inst{27-23} = 0b11111;
+  let Inst{22} = Qd{3};
+  let Inst{21-19} = 0b000;
+  let Inst{18-16} = imm{6-4};
+  let Inst{15-13} = Qd{2-0};
+  let Inst{12} = 0b0;
+  let Inst{11-8} = cmode;
+  let Inst{7-6} = 0b01;
+  let Inst{4} = 0b1;
+  let Inst{3-0} = imm{3-0};
+}
+
+class MVE_VORR<string suffix, bits<4> cmode, ExpandImm imm_type>
+  : MVE_bit_cmode<"vorr", suffix, cmode, (ins MQPR:$Qd_src, imm_type:$imm)> {
+  let Inst{5} = 0b0;
+}
+
+def MVE_VORRIZ0v4i32  : MVE_VORR<"i32", 0b0001, expzero00>;
+def MVE_VORRIZ0v8i16  : MVE_VORR<"i16", 0b1001, expzero00>;
+def MVE_VORRIZ8v4i32  : MVE_VORR<"i32", 0b0011, expzero08>;
+def MVE_VORRIZ8v8i16  : MVE_VORR<"i16", 0b1011, expzero08>;
+def MVE_VORRIZ16v4i32 : MVE_VORR<"i32", 0b0101, expzero16>;
+def MVE_VORRIZ24v4i32 : MVE_VORR<"i32", 0b0111, expzero24>;
+
+def MVE_VORNIZ0v4i32 : MVEAsmPseudo<"vorn${vp}.i32\t$Qd, $imm",
+    (ins MQPR:$Qd_src, expzero00inv32:$imm, vpred_n:$vp), (outs MQPR:$Qd)>;
+def MVE_VORNIZ0v8i16 : MVEAsmPseudo<"vorn${vp}.i16\t$Qd, $imm",
+    (ins MQPR:$Qd_src, expzero00inv16:$imm, vpred_n:$vp), (outs MQPR:$Qd)>;
+def MVE_VORNIZ8v4i32 : MVEAsmPseudo<"vorn${vp}.i32\t$Qd, $imm",
+    (ins MQPR:$Qd_src, expzero08inv32:$imm, vpred_n:$vp), (outs MQPR:$Qd)>;
+def MVE_VORNIZ8v8i16 : MVEAsmPseudo<"vorn${vp}.i16\t$Qd, $imm",
+    (ins MQPR:$Qd_src, expzero08inv16:$imm, vpred_n:$vp), (outs MQPR:$Qd)>;
+def MVE_VORNIZ16v4i32 : MVEAsmPseudo<"vorn${vp}.i32\t$Qd, $imm",
+    (ins MQPR:$Qd_src, expzero16inv32:$imm, vpred_n:$vp), (outs MQPR:$Qd)>;
+def MVE_VORNIZ24v4i32 : MVEAsmPseudo<"vorn${vp}.i32\t$Qd, $imm",
+    (ins MQPR:$Qd_src, expzero24inv32:$imm, vpred_n:$vp), (outs MQPR:$Qd)>;
+
+def MVE_VMOV : MVEInstAlias<"vmov${vp}\t$Qd, $Qm",
+    (MVE_VORR MQPR:$Qd, MQPR:$Qm, MQPR:$Qm, vpred_r:$vp)>;
+
+class MVE_VBIC<string suffix, bits<4> cmode, ExpandImm imm_type>
+  : MVE_bit_cmode<"vbic", suffix, cmode, (ins MQPR:$Qd_src, imm_type:$imm)> {
+  let Inst{5} = 0b1;
+}
+
+def MVE_VBICIZ0v4i32  : MVE_VBIC<"i32", 0b0001, expzero00>;
+def MVE_VBICIZ0v8i16  : MVE_VBIC<"i16", 0b1001, expzero00>;
+def MVE_VBICIZ8v4i32  : MVE_VBIC<"i32", 0b0011, expzero08>;
+def MVE_VBICIZ8v8i16  : MVE_VBIC<"i16", 0b1011, expzero08>;
+def MVE_VBICIZ16v4i32 : MVE_VBIC<"i32", 0b0101, expzero16>;
+def MVE_VBICIZ24v4i32 : MVE_VBIC<"i32", 0b0111, expzero24>;
+
+def MVE_VANDIZ0v4i32 : MVEAsmPseudo<"vand${vp}.i32\t$Qda, $imm",
+    (ins MQPR:$Qda_src, expzero00inv32:$imm, vpred_n:$vp), (outs MQPR:$Qda)>;
+def MVE_VANDIZ0v8i16 : MVEAsmPseudo<"vand${vp}.i16\t$Qda, $imm",
+    (ins MQPR:$Qda_src, expzero00inv16:$imm, vpred_n:$vp), (outs MQPR:$Qda)>;
+def MVE_VANDIZ8v4i32 : MVEAsmPseudo<"vand${vp}.i32\t$Qda, $imm",
+    (ins MQPR:$Qda_src, expzero08inv32:$imm, vpred_n:$vp), (outs MQPR:$Qda)>;
+def MVE_VANDIZ8v8i16 : MVEAsmPseudo<"vand${vp}.i16\t$Qda, $imm",
+    (ins MQPR:$Qda_src, expzero08inv16:$imm, vpred_n:$vp), (outs MQPR:$Qda)>;
+def MVE_VANDIZ16v4i32 : MVEAsmPseudo<"vand${vp}.i32\t$Qda, $imm",
+    (ins MQPR:$Qda_src, expzero16inv32:$imm, vpred_n:$vp), (outs MQPR:$Qda)>;
+def MVE_VANDIZ24v4i32 : MVEAsmPseudo<"vand${vp}.i32\t$Qda, $imm",
+    (ins MQPR:$Qda_src, expzero24inv32:$imm, vpred_n:$vp), (outs MQPR:$Qda)>;
+
+class MVE_VMOV_lane_direction {
+  bit bit_20;
+  dag oops;
+  dag iops;
+  string ops;
+  string cstr;
+}
+def MVE_VMOV_from_lane : MVE_VMOV_lane_direction {
+  let bit_20 = 0b1;
+  let oops = (outs rGPR:$Rt);
+  let iops = (ins MQPR:$Qd);
+  let ops = "$Rt, $Qd$Idx";
+  let cstr = "";
+}
+def MVE_VMOV_to_lane : MVE_VMOV_lane_direction {
+  let bit_20 = 0b0;
+  let oops = (outs MQPR:$Qd);
+  let iops = (ins MQPR:$Qd_src, rGPR:$Rt);
+  let ops = "$Qd$Idx, $Rt";
+  let cstr = "$Qd = $Qd_src";
+}
+
+class MVE_VMOV_lane<string suffix, bit U, dag indexop,
+                    MVE_VMOV_lane_direction dir>
+  : MVE_VMOV_lane_base<dir.oops, !con(dir.iops, indexop), NoItinerary,
+                       "vmov", suffix, dir.ops, dir.cstr, []> {
+  bits<4> Qd;
+  bits<5> Rt;
+
+  let Inst{31-24} = 0b11101110;
+  let Inst{23} = U;
+  let Inst{20} = dir.bit_20;
+  let Inst{19-17} = Qd{2-0};
+  let Inst{15-12} = Rt{3-0};
+  let Inst{11-8} = 0b1011;
+  let Inst{7} = Qd{3};
+  let Inst{4-0} = 0b10000;
+}
+
+class MVE_VMOV_lane_32<MVE_VMOV_lane_direction dir>
+    : MVE_VMOV_lane<"32", 0b0, (ins MVEVectorIndex<4>:$Idx), dir> {
+  bits<2> Idx;
+  let Inst{22} = 0b0;
+  let Inst{6-5} = 0b00;
+  let Inst{16} = Idx{1};
+  let Inst{21} = Idx{0};
+
+  let Predicates = [HasFPRegsV8_1M];
+}
+
+class MVE_VMOV_lane_16<string suffix, bit U, MVE_VMOV_lane_direction dir>
+  : MVE_VMOV_lane<suffix, U, (ins MVEVectorIndex<8>:$Idx), dir> {
+  bits<3> Idx;
+  let Inst{22} = 0b0;
+  let Inst{5} = 0b1;
+  let Inst{16} = Idx{2};
+  let Inst{21} = Idx{1};
+  let Inst{6} = Idx{0};
+}
+
+class MVE_VMOV_lane_8<string suffix, bit U, MVE_VMOV_lane_direction dir>
+  : MVE_VMOV_lane<suffix, U, (ins MVEVectorIndex<16>:$Idx), dir> {
+  bits<4> Idx;
+  let Inst{22} = 0b1;
+  let Inst{16} = Idx{3};
+  let Inst{21} = Idx{2};
+  let Inst{6} = Idx{1};
+  let Inst{5} = Idx{0};
+}
+
+def MVE_VMOV_from_lane_32  : MVE_VMOV_lane_32<            MVE_VMOV_from_lane>;
+def MVE_VMOV_to_lane_32    : MVE_VMOV_lane_32<            MVE_VMOV_to_lane>;
+def MVE_VMOV_from_lane_s16 : MVE_VMOV_lane_16<"s16", 0b0, MVE_VMOV_from_lane>;
+def MVE_VMOV_from_lane_u16 : MVE_VMOV_lane_16<"u16", 0b1, MVE_VMOV_from_lane>;
+def MVE_VMOV_to_lane_16    : MVE_VMOV_lane_16< "16", 0b0, MVE_VMOV_to_lane>;
+def MVE_VMOV_from_lane_s8  : MVE_VMOV_lane_8 < "s8", 0b0, MVE_VMOV_from_lane>;
+def MVE_VMOV_from_lane_u8  : MVE_VMOV_lane_8 < "u8", 0b1, MVE_VMOV_from_lane>;
+def MVE_VMOV_to_lane_8     : MVE_VMOV_lane_8 <  "8", 0b0, MVE_VMOV_to_lane>;
+
+// end of mve_bit instructions
+
 class MVE_VPT<string suffix, bits<2> size, dag iops, string asm, list<dag> pattern=[]>
  : MVE_MI<(outs ), iops, NoItinerary, !strconcat("vpt", "${Mk}", ".", suffix), asm, "", pattern> {
  bits<3> fc;
--- a/lib/Target/ARM/AsmParser/ARMAsmParser.cpp
+++ b/lib/Target/ARM/AsmParser/ARMAsmParser.cpp
@ -1143,6 +1143,34 @@ public:
    return isImmediate<1, 33>();
  }

+  template<int shift>
+  bool isExpImmValue(uint64_t Value) const {
+    uint64_t mask = (1 << shift) - 1;
+    if ((Value & mask) != 0 || (Value >> shift) > 0xff)
+      return false;
+    return true;
+  }
+
+  template<int shift>
+  bool isExpImm() const {
+    if (!isImm()) return false;
+    const MCConstantExpr *CE = dyn_cast<MCConstantExpr>(getImm());
+    if (!CE) return false;
+
+    return isExpImmValue<shift>(CE->getValue());
+  }
+
+  template<int shift, int size>
+  bool isInvertedExpImm() const {
+    if (!isImm()) return false;
+    const MCConstantExpr *CE = dyn_cast<MCConstantExpr>(getImm());
+    if (!CE) return false;
+
+    uint64_t OriginalValue = CE->getValue();
+    uint64_t InvertedValue = OriginalValue ^ (((uint64_t)1 << size) - 1);
+    return isExpImmValue<shift>(InvertedValue);
+  }
+
  bool isPKHLSLImm() const {
    return isImmediate<0, 32>();
  }
@ -1897,24 +1925,16 @@ public:

  bool isVectorIndex() const { return Kind == k_VectorIndex; }

-  bool isVectorIndex8() const {
+  template <unsigned NumLanes>
+  bool isVectorIndexInRange() const {
    if (Kind != k_VectorIndex) return false;
-    return VectorIndex.Val < 8;
+    return VectorIndex.Val < NumLanes;
  }

-  bool isVectorIndex16() const {
-    if (Kind != k_VectorIndex) return false;
-    return VectorIndex.Val < 4;
-  }
-
-  bool isVectorIndex32() const {
-    if (Kind != k_VectorIndex) return false;
-    return VectorIndex.Val < 2;
-  }
-  bool isVectorIndex64() const {
-    if (Kind != k_VectorIndex) return false;
-    return VectorIndex.Val < 1;
-  }
+  bool isVectorIndex8()  const { return isVectorIndexInRange<8>(); }
+  bool isVectorIndex16() const { return isVectorIndexInRange<4>(); }
+  bool isVectorIndex32() const { return isVectorIndexInRange<2>(); }
+  bool isVectorIndex64() const { return isVectorIndexInRange<1>(); }

  bool isNEONi8splat() const {
    if (!isImm()) return false;
@ -2961,6 +2981,11 @@ public:
    Inst.addOperand(MCOperand::createImm(getVectorIndex()));
  }

+  void addMVEVectorIndexOperands(MCInst &Inst, unsigned N) const {
+    assert(N == 1 && "Invalid number of operands!");
+    Inst.addOperand(MCOperand::createImm(getVectorIndex()));
+  }
+
  void addNEONi8splatOperands(MCInst &Inst, unsigned N) const {
    assert(N == 1 && "Invalid number of operands!");
    // The immediate encodes the type of constant as well as the value.
@ -5936,7 +5961,8 @@ StringRef ARMAsmParser::splitMnemonic(StringRef Mnemonic,
      Mnemonic != "sbcs" && Mnemonic != "rscs" &&
      !(hasMVE() &&
        (Mnemonic == "vmine" ||
-         Mnemonic == "vshle" || Mnemonic == "vshlt" || Mnemonic == "vshllt"))) {
+         Mnemonic == "vshle" || Mnemonic == "vshlt" || Mnemonic == "vshllt" ||
+         Mnemonic == "vmvne" || Mnemonic == "vorne"))) {
    unsigned CC = ARMCondCodeFromString(Mnemonic.substr(Mnemonic.size()-2));
    if (CC != ~0U) {
      Mnemonic = Mnemonic.slice(0, Mnemonic.size() - 2);
@ -6310,17 +6336,33 @@ bool ARMAsmParser::shouldOmitVectorPredicateOperand(StringRef Mnemonic,
  if (!hasMVE() || Operands.size() < 3)
    return true;

-  for (auto &Operand : Operands) {
-    // We check the larger class QPR instead of just the legal class
-    // MQPR, to more accurately report errors when using Q registers
-    // outside of the allowed range.
-    if (static_cast<ARMOperand &>(*Operand).isVectorIndex() ||
-        (Operand->isReg() &&
-         (ARMMCRegisterClasses[ARM::QPRRegClassID].contains(
+  if (Mnemonic.startswith("vmov") &&
+      !(Mnemonic.startswith("vmovl") || Mnemonic.startswith("vmovn") ||
+        Mnemonic.startswith("vmovx"))) {
+    for (auto &Operand : Operands) {
+      if (static_cast<ARMOperand &>(*Operand).isVectorIndex() ||
+          ((*Operand).isReg() &&
+           (ARMMCRegisterClasses[ARM::SPRRegClassID].contains(
+             (*Operand).getReg()) ||
+            ARMMCRegisterClasses[ARM::DPRRegClassID].contains(
+              (*Operand).getReg())))) {
+        return true;
+      }
+    }
+    return false;
+  } else {
+    for (auto &Operand : Operands) {
+      // We check the larger class QPR instead of just the legal class
+      // MQPR, to more accurately report errors when using Q registers
+      // outside of the allowed range.
+      if (static_cast<ARMOperand &>(*Operand).isVectorIndex() ||
+          (Operand->isReg() &&
+           (ARMMCRegisterClasses[ARM::QPRRegClassID].contains(
             Operand->getReg()))))
-      return false;
+        return false;
+    }
+    return true;
  }
-  return true;
 }

 static bool isDataTypeToken(StringRef Tok) {
@ -6618,6 +6660,21 @@ bool ARMAsmParser::ParseInstruction(ParseInstructionInfo &Info, StringRef Name,
                      ARMOperand::CreateVPTPred(ARMVCC::None, PLoc));
      Operands.insert(Operands.begin(),
                      ARMOperand::CreateToken(StringRef("vmovlt"), MLoc));
+    }
+    // For vmov instructions, as mentioned earlier, we did not add the vector
+    // predication code, since these may contain operands that require
+    // special parsing.  So now we have to see if they require vector
+    // predication and replace the scalar one with the vector predication
+    // operand if that is the case.
+    else if (Mnemonic == "vmov") {
+      if (!shouldOmitVectorPredicateOperand(Mnemonic, Operands)) {
+        Operands.erase(Operands.begin() + 1);
+        SMLoc PLoc = SMLoc::getFromPointer(NameLoc.getPointer() +
+                                          Mnemonic.size() + CarrySetting);
+        Operands.insert(Operands.begin() + 1,
+                        ARMOperand::CreateVPTPred(
+                            ARMVCC::VPTCodes(VPTPredicationCode), PLoc));
+      }
    } else if (CanAcceptVPTPredicationCode) {
      // For all other instructions, make sure only one of the two
      // predication operands is left behind, depending on whether we should
@ -7714,6 +7771,50 @@ bool ARMAsmParser::processInstruction(MCInst &Inst,
  }

  switch (Inst.getOpcode()) {
+  case ARM::MVE_VORNIZ0v4i32:
+  case ARM::MVE_VORNIZ0v8i16:
+  case ARM::MVE_VORNIZ8v4i32:
+  case ARM::MVE_VORNIZ8v8i16:
+  case ARM::MVE_VORNIZ16v4i32:
+  case ARM::MVE_VORNIZ24v4i32:
+  case ARM::MVE_VANDIZ0v4i32:
+  case ARM::MVE_VANDIZ0v8i16:
+  case ARM::MVE_VANDIZ8v4i32:
+  case ARM::MVE_VANDIZ8v8i16:
+  case ARM::MVE_VANDIZ16v4i32:
+  case ARM::MVE_VANDIZ24v4i32: {
+    unsigned Opcode;
+    bool imm16 = false;
+    switch(Inst.getOpcode()) {
+    case ARM::MVE_VORNIZ0v4i32: Opcode = ARM::MVE_VORRIZ0v4i32; break;
+    case ARM::MVE_VORNIZ0v8i16: Opcode = ARM::MVE_VORRIZ0v8i16; imm16 = true; break;
+    case ARM::MVE_VORNIZ8v4i32: Opcode = ARM::MVE_VORRIZ8v4i32; break;
+    case ARM::MVE_VORNIZ8v8i16: Opcode = ARM::MVE_VORRIZ8v8i16; imm16 = true; break;
+    case ARM::MVE_VORNIZ16v4i32: Opcode = ARM::MVE_VORRIZ16v4i32; break;
+    case ARM::MVE_VORNIZ24v4i32: Opcode = ARM::MVE_VORRIZ24v4i32; break;
+    case ARM::MVE_VANDIZ0v4i32: Opcode = ARM::MVE_VBICIZ0v4i32; break;
+    case ARM::MVE_VANDIZ0v8i16: Opcode = ARM::MVE_VBICIZ0v8i16; imm16 = true; break;
+    case ARM::MVE_VANDIZ8v4i32: Opcode = ARM::MVE_VBICIZ8v4i32; break;
+    case ARM::MVE_VANDIZ8v8i16: Opcode = ARM::MVE_VBICIZ8v8i16; imm16 = true; break;
+    case ARM::MVE_VANDIZ16v4i32: Opcode = ARM::MVE_VBICIZ16v4i32; break;
+    case ARM::MVE_VANDIZ24v4i32: Opcode = ARM::MVE_VBICIZ24v4i32; break;
+    default: llvm_unreachable("unexpected opcode");
+    }
+
+    MCInst TmpInst;
+    TmpInst.setOpcode(Opcode);
+    TmpInst.addOperand(Inst.getOperand(0));
+    TmpInst.addOperand(Inst.getOperand(1));
+
+    // invert immediate
+    unsigned imm = ~Inst.getOperand(2).getImm() & (imm16 ? 0xffff : 0xffffffff);
+    TmpInst.addOperand(MCOperand::createImm(imm));
+
+    TmpInst.addOperand(Inst.getOperand(3));
+    TmpInst.addOperand(Inst.getOperand(4));
+    Inst = TmpInst;
+    return true;
+  }
  // Alias for alternate form of 'ldr{,b}t Rt, [Rn], #imm' instruction.
  case ARM::LDRT_POST:
  case ARM::LDRBT_POST: {
--- a/lib/Target/ARM/Disassembler/ARMDisassembler.cpp
+++ b/lib/Target/ARM/Disassembler/ARMDisassembler.cpp
@ -504,6 +504,10 @@ template<bool Writeback>
 static DecodeStatus DecodeVSTRVLDR_SYSREG(MCInst &Inst, unsigned Insn,
                                          uint64_t Address,
                                          const void *Decoder);
+template <int shift>
+static DecodeStatus DecodeExpandedImmOperand(MCInst &Inst, unsigned Val,
+                                             uint64_t Address,
+                                             const void *Decoder);
 static DecodeStatus DecodeMVEOverlappingLongShift(MCInst &Inst, unsigned Insn,
                                                  uint64_t Address,
                                                  const void *Decoder);
@ -6025,6 +6029,16 @@ static DecodeStatus DecodeVSTRVLDR_SYSREG(MCInst &Inst, unsigned Val,
  return S;
 }

+template <int shift>
+static DecodeStatus DecodeExpandedImmOperand(MCInst &Inst, unsigned Val,
+                                             uint64_t Address,
+                                             const void *Decoder) {
+    Val <<= shift;
+
+    Inst.addOperand(MCOperand::createImm(Val));
+    return MCDisassembler::Success;
+}
+
 static DecodeStatus DecodeMVEOverlappingLongShift(
  MCInst &Inst, unsigned Insn, uint64_t Address, const void *Decoder) {
  DecodeStatus S = MCDisassembler::Success;
--- a/lib/Target/ARM/MCTargetDesc/ARMInstPrinter.cpp
+++ b/lib/Target/ARM/MCTargetDesc/ARMInstPrinter.cpp
@ -1620,3 +1620,11 @@ void ARMInstPrinter::printVPTMask(const MCInst *MI, unsigned OpNum,
  }
 }

+void ARMInstPrinter::printExpandedImmOperand(const MCInst *MI, unsigned OpNum,
+                                             const MCSubtargetInfo &STI,
+                                             raw_ostream &O) {
+  uint32_t Val = MI->getOperand(OpNum).getImm();
+  O << markup("<imm:") << "#0x";
+  O.write_hex(Val);
+  O << markup(">");
+}
--- a/lib/Target/ARM/MCTargetDesc/ARMInstPrinter.h
+++ b/lib/Target/ARM/MCTargetDesc/ARMInstPrinter.h
@ -252,6 +252,8 @@ public:
                                raw_ostream &O);
  void printVPTMask(const MCInst *MI, unsigned OpNum,
                    const MCSubtargetInfo &STI, raw_ostream &O);
+  void printExpandedImmOperand(const MCInst *MI, unsigned OpNum,
+                               const MCSubtargetInfo &STI, raw_ostream &O);

 private:
  unsigned DefaultAltIdx = ARM::NoRegAltName;
--- a/lib/Target/ARM/MCTargetDesc/ARMMCCodeEmitter.cpp
+++ b/lib/Target/ARM/MCTargetDesc/ARMMCCodeEmitter.cpp
@ -398,6 +398,14 @@ public:
  unsigned getThumbSRImmOpValue(const MCInst &MI, unsigned Op,
                                 SmallVectorImpl<MCFixup> &Fixups,
                                 const MCSubtargetInfo &STI) const;
+  template <uint8_t shift, bool invert>
+  unsigned getExpandedImmOpValue(const MCInst &MI, unsigned Op,
+                                 SmallVectorImpl<MCFixup> &Fixups,
+                                 const MCSubtargetInfo &STI) const {
+    static_assert(shift <= 32, "Shift count must be less than or equal to 32.");
+    const MCOperand MO = MI.getOperand(Op);
+    return (invert ? (MO.getImm() ^ 0xff) : MO.getImm()) >> shift;
+  }

  unsigned NEONThumb2DataIPostEncoder(const MCInst &MI,
                                      unsigned EncodedValue,
--- a/test/MC/ARM/mve-bitops.s
+++ b/test/MC/ARM/mve-bitops.s
@ -0,0 +1,441 @@
+# RUN: not llvm-mc -triple=thumbv8.1m.main-none-eabi -mattr=+mve -show-encoding  < %s \
+# RUN:   | FileCheck --check-prefix=CHECK-NOFP %s
+# RUN: not llvm-mc -triple=thumbv8.1m.main-none-eabi -mattr=+mve.fp,+fp64 -show-encoding  < %s 2>%t \
+# RUN:   | FileCheck --check-prefix=CHECK %s
+# RUN:     FileCheck --check-prefix=ERROR < %t %s
+
+# CHECK: vorr.i16 q0, #0x12  @ encoding: [0x81,0xef,0x52,0x09]
+# CHECK-NOFP: vorr.i16 q0, #0x12  @ encoding: [0x81,0xef,0x52,0x09]
+vorr.i16 q0, #0x12
+
+# CHECK: vorr.i32 q0, #0x1200  @ encoding: [0x81,0xef,0x52,0x03]
+# CHECK-NOFP: vorr.i32 q0, #0x1200  @ encoding: [0x81,0xef,0x52,0x03]
+vorr.i32 q0, #0x1200
+
+# CHECK: vorr.i16 q0, #0xed  @ encoding: [0x86,0xff,0x5d,0x09]
+# CHECK-NOFP: vorr.i16 q0, #0xed  @ encoding: [0x86,0xff,0x5d,0x09]
+vorn.i16 q0, #0xff12
+
+# CHECK: vorr.i32 q0, #0xed00  @ encoding: [0x86,0xff,0x5d,0x03]
+# CHECK-NOFP: vorr.i32 q0, #0xed00  @ encoding: [0x86,0xff,0x5d,0x03]
+vorn.i32 q0, #0xffff12ff
+
+# CHECK: vorr.i32 q0, #0xed0000  @ encoding: [0x86,0xff,0x5d,0x05]
+# CHECK-NOFP: vorr.i32 q0, #0xed0000  @ encoding: [0x86,0xff,0x5d,0x05]
+vorn.i32 q0, #0xff12ffff
+
+# CHECK: vorr.i32 q0, #0xed000000  @ encoding: [0x86,0xff,0x5d,0x07]
+# CHECK-NOFP: vorr.i32 q0, #0xed000000  @ encoding: [0x86,0xff,0x5d,0x07]
+vorn.i32 q0, #0x12ffffff
+
+# ERROR: [[@LINE+1]]:{{[0-9]+}}: {{error|note}}: invalid operand for instruction
+vorn.i16 q0, #0xed00
+
+# ERROR: [[@LINE+1]]:{{[0-9]+}}: {{error|note}}: invalid operand for instruction
+vorn.i16 q0, #0x00ed
+
+# ERROR: [[@LINE+1]]:{{[0-9]+}}: {{error|note}}: invalid operand for instruction
+vorn.i32 q0, #0xed000000
+
+# ERROR: [[@LINE+1]]:{{[0-9]+}}: {{error|note}}: invalid operand for instruction
+vorn.i32 q0, #0x00ed0000
+
+# ERROR: [[@LINE+1]]:{{[0-9]+}}: {{error|note}}: invalid operand for instruction
+vorn.i32 q0, #0x0000ed00
+
+# ERROR: [[@LINE+1]]:{{[0-9]+}}: {{error|note}}: invalid operand for instruction
+vorn.i32 q0, #0x000000ed
+
+# CHECK: vbic.i16 q0, #0x22  @ encoding: [0x82,0xef,0x72,0x09]
+# CHECK-NOFP: vbic.i16 q0, #0x22  @ encoding: [0x82,0xef,0x72,0x09]
+vbic.i16 q0, #0x22
+
+# CHECK: vbic.i32 q0, #0x1100  @ encoding: [0x81,0xef,0x71,0x03]
+# CHECK-NOFP: vbic.i32 q0, #0x1100  @ encoding: [0x81,0xef,0x71,0x03]
+vbic.i32 q0, #0x1100
+
+# CHECK: vbic.i16 q0, #0xdd  @ encoding: [0x85,0xff,0x7d,0x09]
+# CHECK-NOFP: vbic.i16 q0, #0xdd  @ encoding: [0x85,0xff,0x7d,0x09]
+vand.i16 q0, #0xff22
+
+# CHECK: vbic.i16 q0, #0xdd00  @ encoding: [0x85,0xff,0x7d,0x0b]
+# CHECK-NOFP: vbic.i16 q0, #0xdd00  @ encoding: [0x85,0xff,0x7d,0x0b]
+vand.i16 q0, #0x22ff
+
+# CHECK: vbic.i32 q0, #0xee  @ encoding: [0x86,0xff,0x7e,0x01]
+# CHECK-NOFP: vbic.i32 q0, #0xee  @ encoding: [0x86,0xff,0x7e,0x01]
+vand.i32 q0, #0xffffff11
+
+# CHECK: vbic.i32 q0, #0xee00  @ encoding: [0x86,0xff,0x7e,0x03]
+# CHECK-NOFP: vbic.i32 q0, #0xee00  @ encoding: [0x86,0xff,0x7e,0x03]
+vand.i32 q0, #0xffff11ff
+
+# CHECK: vbic.i32 q0, #0xee0000  @ encoding: [0x86,0xff,0x7e,0x05]
+# CHECK-NOFP: vbic.i32 q0, #0xee0000  @ encoding: [0x86,0xff,0x7e,0x05]
+vand.i32 q0, #0xff11ffff
+
+# CHECK: vbic.i32 q0, #0xee000000  @ encoding: [0x86,0xff,0x7e,0x07]
+# CHECK-NOFP: vbic.i32 q0, #0xee000000  @ encoding: [0x86,0xff,0x7e,0x07]
+vand.i32 q0, #0x11ffffff
+
+# ERROR: [[@LINE+1]]:{{[0-9]+}}: {{error|note}}: invalid operand for instruction
+vand.i16 q0, #0xed00
+
+# ERROR: [[@LINE+1]]:{{[0-9]+}}: {{error|note}}: invalid operand for instruction
+vand.i16 q0, #0x00ed
+
+# ERROR: [[@LINE+1]]:{{[0-9]+}}: {{error|note}}: invalid operand for instruction
+vand.i32 q0, #0xed000000
+
+# ERROR: [[@LINE+1]]:{{[0-9]+}}: {{error|note}}: invalid operand for instruction
+vand.i32 q0, #0x00ed0000
+
+# ERROR: [[@LINE+1]]:{{[0-9]+}}: {{error|note}}: invalid operand for instruction
+vand.i32 q0, #0x0000ed00
+
+# ERROR: [[@LINE+1]]:{{[0-9]+}}: {{error|note}}: invalid operand for instruction
+vand.i32 q0, #0x000000ed
+
+# CHECK: vbic q0, q1, q7  @ encoding: [0x12,0xef,0x5e,0x01]
+# CHECK-NOFP: vbic q0, q1, q7  @ encoding: [0x12,0xef,0x5e,0x01]
+vbic q0, q1, q7
+
+# CHECK: vbic q0, q1, q7  @ encoding: [0x12,0xef,0x5e,0x01]
+# CHECK-NOFP: vbic q0, q1, q7  @ encoding: [0x12,0xef,0x5e,0x01]
+vbic.s8 q0, q1, q7
+
+# CHECK: vbic q0, q1, q7  @ encoding: [0x12,0xef,0x5e,0x01]
+# CHECK-NOFP: vbic q0, q1, q7  @ encoding: [0x12,0xef,0x5e,0x01]
+vbic.s16 q0, q1, q7
+
+# CHECK: vbic q0, q1, q7  @ encoding: [0x12,0xef,0x5e,0x01]
+# CHECK-NOFP: vbic q0, q1, q7  @ encoding: [0x12,0xef,0x5e,0x01]
+vbic.s32 q0, q1, q7
+
+# CHECK: vbic q0, q1, q7  @ encoding: [0x12,0xef,0x5e,0x01]
+# CHECK-NOFP: vbic q0, q1, q7  @ encoding: [0x12,0xef,0x5e,0x01]
+vbic.u8 q0, q1, q7
+
+# CHECK: vbic q0, q1, q7  @ encoding: [0x12,0xef,0x5e,0x01]
+# CHECK-NOFP: vbic q0, q1, q7  @ encoding: [0x12,0xef,0x5e,0x01]
+vbic.u16 q0, q1, q7
+
+# CHECK: vbic q0, q1, q7  @ encoding: [0x12,0xef,0x5e,0x01]
+# CHECK-NOFP: vbic q0, q1, q7  @ encoding: [0x12,0xef,0x5e,0x01]
+vbic.u32 q0, q1, q7
+
+# CHECK: vbic q0, q1, q7  @ encoding: [0x12,0xef,0x5e,0x01]
+# CHECK-NOFP: vbic q0, q1, q7  @ encoding: [0x12,0xef,0x5e,0x01]
+vbic.i8 q0, q1, q7
+
+# CHECK: vbic q0, q1, q7  @ encoding: [0x12,0xef,0x5e,0x01]
+# CHECK-NOFP: vbic q0, q1, q7  @ encoding: [0x12,0xef,0x5e,0x01]
+vbic.i16 q0, q1, q7
+
+# CHECK: vbic q0, q1, q7  @ encoding: [0x12,0xef,0x5e,0x01]
+# CHECK-NOFP: vbic q0, q1, q7  @ encoding: [0x12,0xef,0x5e,0x01]
+vbic.i32 q0, q1, q7
+
+# CHECK: vbic q0, q1, q7  @ encoding: [0x12,0xef,0x5e,0x01]
+# CHECK-NOFP: vbic q0, q1, q7  @ encoding: [0x12,0xef,0x5e,0x01]
+vbic.f16 q0, q1, q7
+
+# CHECK: vbic q0, q1, q7  @ encoding: [0x12,0xef,0x5e,0x01]
+# CHECK-NOFP: vbic q0, q1, q7  @ encoding: [0x12,0xef,0x5e,0x01]
+vbic.f32 q0, q1, q7
+
+# CHECK: vrev64.8 q0, q4  @ encoding: [0xb0,0xff,0x48,0x00]
+# CHECK-NOFP: vrev64.8 q0, q4  @ encoding: [0xb0,0xff,0x48,0x00]
+vrev64.8 q0, q4
+
+# CHECK: vrev64.16 q1, q3  @ encoding: [0xb4,0xff,0x46,0x20]
+# CHECK-NOFP: vrev64.16 q1, q3  @ encoding: [0xb4,0xff,0x46,0x20]
+vrev64.16 q1, q3
+
+# CHECK: vrev64.32 q0, q2  @ encoding: [0xb8,0xff,0x44,0x00]
+# CHECK-NOFP: vrev64.32 q0, q2  @ encoding: [0xb8,0xff,0x44,0x00]
+vrev64.32 q0, q2
+
+# CHECK: vrev32.8 q0, q1  @ encoding: [0xb0,0xff,0xc2,0x00]
+# CHECK-NOFP: vrev32.8 q0, q1  @ encoding: [0xb0,0xff,0xc2,0x00]
+vrev32.8 q0, q1
+
+# CHECK: vrev32.16 q0, q5  @ encoding: [0xb4,0xff,0xca,0x00]
+# CHECK-NOFP: vrev32.16 q0, q5  @ encoding: [0xb4,0xff,0xca,0x00]
+vrev32.16 q0, q5
+
+# CHECK: vrev16.8 q0, q2  @ encoding: [0xb0,0xff,0x44,0x01]
+# CHECK-NOFP: vrev16.8 q0, q2  @ encoding: [0xb0,0xff,0x44,0x01]
+vrev16.8 q0, q2
+
+# CHECK: vmvn q0, q2  @ encoding: [0xb0,0xff,0xc4,0x05]
+# CHECK-NOFP: vmvn q0, q2  @ encoding: [0xb0,0xff,0xc4,0x05]
+vmvn q0, q2
+
+# CHECK: veor q2, q1, q7  @ encoding: [0x02,0xff,0x5e,0x41]
+# CHECK-NOFP: veor q2, q1, q7  @ encoding: [0x02,0xff,0x5e,0x41]
+veor q2, q1, q7
+
+# CHECK: veor q2, q1, q7  @ encoding: [0x02,0xff,0x5e,0x41]
+# CHECK-NOFP: veor q2, q1, q7  @ encoding: [0x02,0xff,0x5e,0x41]
+veor.s8 q2, q1, q7
+
+# CHECK: veor q2, q1, q7  @ encoding: [0x02,0xff,0x5e,0x41]
+# CHECK-NOFP: veor q2, q1, q7  @ encoding: [0x02,0xff,0x5e,0x41]
+veor.s16 q2, q1, q7
+
+# CHECK: veor q2, q1, q7  @ encoding: [0x02,0xff,0x5e,0x41]
+# CHECK-NOFP: veor q2, q1, q7  @ encoding: [0x02,0xff,0x5e,0x41]
+veor.s32 q2, q1, q7
+
+# CHECK: veor q2, q1, q7  @ encoding: [0x02,0xff,0x5e,0x41]
+# CHECK-NOFP: veor q2, q1, q7  @ encoding: [0x02,0xff,0x5e,0x41]
+veor.u8 q2, q1, q7
+
+# CHECK: veor q2, q1, q7  @ encoding: [0x02,0xff,0x5e,0x41]
+# CHECK-NOFP: veor q2, q1, q7  @ encoding: [0x02,0xff,0x5e,0x41]
+veor.u16 q2, q1, q7
+
+# CHECK: veor q2, q1, q7  @ encoding: [0x02,0xff,0x5e,0x41]
+# CHECK-NOFP: veor q2, q1, q7  @ encoding: [0x02,0xff,0x5e,0x41]
+veor.u32 q2, q1, q7
+
+# CHECK: veor q2, q1, q7  @ encoding: [0x02,0xff,0x5e,0x41]
+# CHECK-NOFP: veor q2, q1, q7  @ encoding: [0x02,0xff,0x5e,0x41]
+veor.i8 q2, q1, q7
+
+# CHECK: veor q2, q1, q7  @ encoding: [0x02,0xff,0x5e,0x41]
+# CHECK-NOFP: veor q2, q1, q7  @ encoding: [0x02,0xff,0x5e,0x41]
+veor.i16 q2, q1, q7
+
+# CHECK: veor q2, q1, q7  @ encoding: [0x02,0xff,0x5e,0x41]
+# CHECK-NOFP: veor q2, q1, q7  @ encoding: [0x02,0xff,0x5e,0x41]
+veor.i32 q2, q1, q7
+
+# CHECK: veor q2, q1, q7  @ encoding: [0x02,0xff,0x5e,0x41]
+# CHECK-NOFP: veor q2, q1, q7  @ encoding: [0x02,0xff,0x5e,0x41]
+veor.f16 q2, q1, q7
+
+# CHECK: veor q2, q1, q7  @ encoding: [0x02,0xff,0x5e,0x41]
+# CHECK-NOFP: veor q2, q1, q7  @ encoding: [0x02,0xff,0x5e,0x41]
+veor.f32 q2, q1, q7
+
+# CHECK: vorn q0, q3, q2  @ encoding: [0x36,0xef,0x54,0x01]
+# CHECK-NOFP: vorn q0, q3, q2  @ encoding: [0x36,0xef,0x54,0x01]
+vorn q0, q3, q2
+
+# CHECK: vorn q0, q3, q2  @ encoding: [0x36,0xef,0x54,0x01]
+# CHECK-NOFP: vorn q0, q3, q2  @ encoding: [0x36,0xef,0x54,0x01]
+vorn.s8 q0, q3, q2
+
+# CHECK: vorn q0, q3, q2  @ encoding: [0x36,0xef,0x54,0x01]
+# CHECK-NOFP: vorn q0, q3, q2  @ encoding: [0x36,0xef,0x54,0x01]
+vorn.s16 q0, q3, q2
+
+# CHECK: vorn q0, q3, q2  @ encoding: [0x36,0xef,0x54,0x01]
+# CHECK-NOFP: vorn q0, q3, q2  @ encoding: [0x36,0xef,0x54,0x01]
+vorn.s32 q0, q3, q2
+
+# CHECK: vorn q0, q3, q2  @ encoding: [0x36,0xef,0x54,0x01]
+# CHECK-NOFP: vorn q0, q3, q2  @ encoding: [0x36,0xef,0x54,0x01]
+vorn.u8 q0, q3, q2
+
+# CHECK: vorn q0, q3, q2  @ encoding: [0x36,0xef,0x54,0x01]
+# CHECK-NOFP: vorn q0, q3, q2  @ encoding: [0x36,0xef,0x54,0x01]
+vorn.u16 q0, q3, q2
+
+# CHECK: vorn q0, q3, q2  @ encoding: [0x36,0xef,0x54,0x01]
+# CHECK-NOFP: vorn q0, q3, q2  @ encoding: [0x36,0xef,0x54,0x01]
+vorn.u32 q0, q3, q2
+
+# CHECK: vorn q0, q3, q2  @ encoding: [0x36,0xef,0x54,0x01]
+# CHECK-NOFP: vorn q0, q3, q2  @ encoding: [0x36,0xef,0x54,0x01]
+vorn.i8 q0, q3, q2
+
+# CHECK: vorn q0, q3, q2  @ encoding: [0x36,0xef,0x54,0x01]
+# CHECK-NOFP: vorn q0, q3, q2  @ encoding: [0x36,0xef,0x54,0x01]
+vorn.i16 q0, q3, q2
+
+# CHECK: vorn q0, q3, q2  @ encoding: [0x36,0xef,0x54,0x01]
+# CHECK-NOFP: vorn q0, q3, q2  @ encoding: [0x36,0xef,0x54,0x01]
+vorn.i32 q0, q3, q2
+
+# CHECK: vorn q0, q3, q2  @ encoding: [0x36,0xef,0x54,0x01]
+# CHECK-NOFP: vorn q0, q3, q2  @ encoding: [0x36,0xef,0x54,0x01]
+vorn.f16 q0, q3, q2
+
+# CHECK: vorn q0, q3, q2  @ encoding: [0x36,0xef,0x54,0x01]
+# CHECK-NOFP: vorn q0, q3, q2  @ encoding: [0x36,0xef,0x54,0x01]
+vorn.f32 q0, q3, q2
+
+# CHECK: vorr q1, q2, q1  @ encoding: [0x24,0xef,0x52,0x21]
+# CHECK-NOFP: vorr q1, q2, q1  @ encoding: [0x24,0xef,0x52,0x21]
+vorr q1, q2, q1
+
+# CHECK: vorr q1, q2, q1  @ encoding: [0x24,0xef,0x52,0x21]
+# CHECK-NOFP: vorr q1, q2, q1  @ encoding: [0x24,0xef,0x52,0x21]
+vorr.s8 q1, q2, q1
+
+# CHECK: vorr q1, q2, q1  @ encoding: [0x24,0xef,0x52,0x21]
+# CHECK-NOFP: vorr q1, q2, q1  @ encoding: [0x24,0xef,0x52,0x21]
+vorr.s16 q1, q2, q1
+
+# CHECK: vorr q1, q2, q1  @ encoding: [0x24,0xef,0x52,0x21]
+# CHECK-NOFP: vorr q1, q2, q1  @ encoding: [0x24,0xef,0x52,0x21]
+vorr.s32 q1, q2, q1
+
+# CHECK: vorr q1, q2, q1  @ encoding: [0x24,0xef,0x52,0x21]
+# CHECK-NOFP: vorr q1, q2, q1  @ encoding: [0x24,0xef,0x52,0x21]
+vorr.u8 q1, q2, q1
+
+# CHECK: vorr q1, q2, q1  @ encoding: [0x24,0xef,0x52,0x21]
+# CHECK-NOFP: vorr q1, q2, q1  @ encoding: [0x24,0xef,0x52,0x21]
+vorr.u16 q1, q2, q1
+
+# CHECK: vorr q1, q2, q1  @ encoding: [0x24,0xef,0x52,0x21]
+# CHECK-NOFP: vorr q1, q2, q1  @ encoding: [0x24,0xef,0x52,0x21]
+vorr.u32 q1, q2, q1
+
+# CHECK: vorr q1, q2, q1  @ encoding: [0x24,0xef,0x52,0x21]
+# CHECK-NOFP: vorr q1, q2, q1  @ encoding: [0x24,0xef,0x52,0x21]
+vorr.i8 q1, q2, q1
+
+# CHECK: vorr q1, q2, q1  @ encoding: [0x24,0xef,0x52,0x21]
+# CHECK-NOFP: vorr q1, q2, q1  @ encoding: [0x24,0xef,0x52,0x21]
+vorr.i16 q1, q2, q1
+
+# CHECK: vorr q1, q2, q1  @ encoding: [0x24,0xef,0x52,0x21]
+# CHECK-NOFP: vorr q1, q2, q1  @ encoding: [0x24,0xef,0x52,0x21]
+vorr.i32 q1, q2, q1
+
+# CHECK: vorr q1, q2, q1  @ encoding: [0x24,0xef,0x52,0x21]
+# CHECK-NOFP: vorr q1, q2, q1  @ encoding: [0x24,0xef,0x52,0x21]
+vorr.f16 q1, q2, q1
+
+# CHECK: vorr q1, q2, q1  @ encoding: [0x24,0xef,0x52,0x21]
+# CHECK-NOFP: vorr q1, q2, q1  @ encoding: [0x24,0xef,0x52,0x21]
+vorr.f32 q1, q2, q1
+
+# CHECK: vand q0, q2, q0  @ encoding: [0x04,0xef,0x50,0x01]
+# CHECK-NOFP: vand q0, q2, q0  @ encoding: [0x04,0xef,0x50,0x01]
+vand q0, q2, q0
+
+# CHECK: vand q0, q2, q0  @ encoding: [0x04,0xef,0x50,0x01]
+# CHECK-NOFP: vand q0, q2, q0  @ encoding: [0x04,0xef,0x50,0x01]
+vand.s8 q0, q2, q0
+
+# CHECK: vand q0, q2, q0  @ encoding: [0x04,0xef,0x50,0x01]
+# CHECK-NOFP: vand q0, q2, q0  @ encoding: [0x04,0xef,0x50,0x01]
+vand.s16 q0, q2, q0
+
+# CHECK: vand q0, q2, q0  @ encoding: [0x04,0xef,0x50,0x01]
+# CHECK-NOFP: vand q0, q2, q0  @ encoding: [0x04,0xef,0x50,0x01]
+vand.s32 q0, q2, q0
+
+# CHECK: vand q0, q2, q0  @ encoding: [0x04,0xef,0x50,0x01]
+# CHECK-NOFP: vand q0, q2, q0  @ encoding: [0x04,0xef,0x50,0x01]
+vand.u8 q0, q2, q0
+
+# CHECK: vand q0, q2, q0  @ encoding: [0x04,0xef,0x50,0x01]
+# CHECK-NOFP: vand q0, q2, q0  @ encoding: [0x04,0xef,0x50,0x01]
+vand.u16 q0, q2, q0
+
+# CHECK: vand q0, q2, q0  @ encoding: [0x04,0xef,0x50,0x01]
+# CHECK-NOFP: vand q0, q2, q0  @ encoding: [0x04,0xef,0x50,0x01]
+vand.u32 q0, q2, q0
+
+# CHECK: vand q0, q2, q0  @ encoding: [0x04,0xef,0x50,0x01]
+# CHECK-NOFP: vand q0, q2, q0  @ encoding: [0x04,0xef,0x50,0x01]
+vand.i8 q0, q2, q0
+
+# CHECK: vand q0, q2, q0  @ encoding: [0x04,0xef,0x50,0x01]
+# CHECK-NOFP: vand q0, q2, q0  @ encoding: [0x04,0xef,0x50,0x01]
+vand.i16 q0, q2, q0
+
+# CHECK: vand q0, q2, q0  @ encoding: [0x04,0xef,0x50,0x01]
+# CHECK-NOFP: vand q0, q2, q0  @ encoding: [0x04,0xef,0x50,0x01]
+vand.i32 q0, q2, q0
+
+# CHECK: vand q0, q2, q0  @ encoding: [0x04,0xef,0x50,0x01]
+# CHECK-NOFP: vand q0, q2, q0  @ encoding: [0x04,0xef,0x50,0x01]
+vand.f16 q0, q2, q0
+
+# CHECK: vand q0, q2, q0  @ encoding: [0x04,0xef,0x50,0x01]
+# CHECK-NOFP: vand q0, q2, q0  @ encoding: [0x04,0xef,0x50,0x01]
+vand.f32 q0, q2, q0
+
+# CHECK: vmov.8 q0[1], r8  @ encoding: [0x40,0xee,0x30,0x8b]
+# CHECK-NOFP: vmov.8 q0[1], r8  @ encoding: [0x40,0xee,0x30,0x8b]
+vmov.8 q0[1], r8
+
+# ERROR: [[@LINE+1]]:{{[0-9]+}}: {{error|note}}: invalid operand for instruction
+vmov.8 q0[16], r8
+
+# CHECK: vmov.16 q0[2], r5  @ encoding: [0x20,0xee,0x30,0x5b]
+# CHECK-NOFP: vmov.16 q0[2], r5  @ encoding: [0x20,0xee,0x30,0x5b]
+vmov.16 q0[2], r5
+
+# ERROR: [[@LINE+1]]:{{[0-9]+}}: {{error|note}}: invalid operand for instruction
+vmov.16 q0[8], r5
+
+# CHECK: vmov.32 q6[3], r11  @ encoding: [0x2d,0xee,0x10,0xbb]
+# CHECK-NOFP: vmov.32 q6[3], r11  @ encoding: [0x2d,0xee,0x10,0xbb]
+vmov.32 q6[3], r11
+
+# ERROR: [[@LINE+1]]:{{[0-9]+}}: {{error|note}}: invalid operand for instruction
+vmov.32 q6[4], r11
+
+# CHECK: vmov.32 r0, q1[0]  @ encoding: [0x12,0xee,0x10,0x0b]
+# CHECK-NOFP: vmov.32 r0, q1[0]  @ encoding: [0x12,0xee,0x10,0x0b]
+vmov.32 r0, q1[0]
+
+# ERROR: [[@LINE+1]]:{{[0-9]+}}: {{error|note}}: invalid operand for instruction
+vmov.32 r0, q1[4]
+
+# CHECK: vmov.s16 r1, q2[7]  @ encoding: [0x35,0xee,0x70,0x1b]
+# CHECK-NOFP: vmov.s16 r1, q2[7]  @ encoding: [0x35,0xee,0x70,0x1b]
+vmov.s16 r1, q2[7]
+
+# ERROR: [[@LINE+1]]:{{[0-9]+}}: {{error|note}}: invalid operand for instruction
+vmov.s16 r1, q2[8]
+
+# CHECK: vmov.s8 r0, q4[13]  @ encoding: [0x79,0xee,0x30,0x0b]
+# CHECK-NOFP: vmov.s8 r0, q4[13]  @ encoding: [0x79,0xee,0x30,0x0b]
+vmov.s8 r0, q4[13]
+
+# ERROR: [[@LINE+1]]:{{[0-9]+}}: {{error|note}}: invalid operand for instruction
+vmov.s8 r0, q4[16]
+
+# CHECK: vmov.u16 r0, q1[4]  @ encoding: [0x93,0xee,0x30,0x0b]
+# CHECK-NOFP: vmov.u16 r0, q1[4]  @ encoding: [0x93,0xee,0x30,0x0b]
+vmov.u16 r0, q1[4]
+
+# ERROR: [[@LINE+1]]:{{[0-9]+}}: {{error|note}}: invalid operand for instruction
+vmov.u16 r0, q1[8]
+
+# CHECK: vmov.u8 r0, q5[7]  @ encoding: [0xfa,0xee,0x70,0x0b]
+# CHECK-NOFP: vmov.u8 r0, q5[7]  @ encoding: [0xfa,0xee,0x70,0x0b]
+vmov.u8 r0, q5[7]
+
+# ERROR: [[@LINE+1]]:{{[0-9]+}}: {{error|note}}: invalid operand for instruction
+vmov.u8 r0, q5[16]
+
+vpste
+vmvnt q0, q1
+vmvne q0, q1
+# CHECK: vpste @ encoding: [0x71,0xfe,0x4d,0x8f]
+# CHECK-NOFP: vpste @ encoding: [0x71,0xfe,0x4d,0x8f]
+# CHECK: vmvnt q0, q1 @ encoding: [0xb0,0xff,0xc2,0x05]
+# CHECK-NOFP: vmvnt q0, q1 @ encoding: [0xb0,0xff,0xc2,0x05]
+# CHECK: vmvne q0, q1 @ encoding: [0xb0,0xff,0xc2,0x05]
+# CHECK-NOFP: vmvne q0, q1 @ encoding: [0xb0,0xff,0xc2,0x05]
+
+vpste
+vornt.s8 q0, q1, q2
+vorne.s8 q0, q1, q2
+# CHECK: vpste @ encoding: [0x71,0xfe,0x4d,0x8f]
+# CHECK-NOFP: vpste @ encoding: [0x71,0xfe,0x4d,0x8f]
+# CHECK: vornt q0, q1, q2 @ encoding: [0x32,0xef,0x54,0x01]
+# CHECK-NOFP: vornt q0, q1, q2 @ encoding: [0x32,0xef,0x54,0x01]
+# CHECK: vorne q0, q1, q2 @ encoding: [0x32,0xef,0x54,0x01]
+# CHECK-NOFP: vorne q0, q1, q2 @ encoding: [0x32,0xef,0x54,0x01]
--- a/test/MC/ARM/mve-vmov-lane.s
+++ b/test/MC/ARM/mve-vmov-lane.s
@ -0,0 +1,16 @@
+// RUN: not llvm-mc -triple=thumbv8m.main   -mattr=+fp-armv8 -show-encoding < %s 2>%t | FileCheck %s --check-prefix=V80M
+// RUN: FileCheck %s < %t --check-prefix=V80M-ERROR
+// RUN:     llvm-mc -triple=thumbv8.1m.main -mattr=+fp-armv8 -show-encoding < %s 2>%t
+// RUN:     llvm-mc -triple=thumbv8.1m.main -mattr=+mve      -show-encoding < %s 2>%t
+
+// v8.1M added the Q register syntax for this instruction. The v8.1M spec does
+// not list the D register syntax as valid, but we accept it as an extension to
+// make porting code from v8.0M to v8.1M easier.
+
+vmov.32 r0, d1[0]
+// V80M: vmov.32 r0, d1[0]               @ encoding: [0x11,0xee,0x10,0x0b]
+// V81M: vmov.32 r0, d1[0]               @ encoding: [0x11,0xee,0x10,0x0b]
+
+vmov.32 r0, q0[2]
+// V80M-ERROR: :[[@LINE-1]]:{{[0-9]+}}: error: instruction requires: armv8.1m.main with FP or MVE
+// V81M: vmov.32 r0, q0[2]               @ encoding: [0x11,0xee,0x10,0x0b]
--- a/test/MC/Disassembler/ARM/mve-bitops.txt
+++ b/test/MC/Disassembler/ARM/mve-bitops.txt
@ -0,0 +1,150 @@
+# RUN: llvm-mc -disassemble -triple=thumbv8.1m.main-none-eabi -mattr=+mve.fp,+fp64 -show-encoding %s 2> %t | FileCheck %s
+# RUN: FileCheck --check-prefix=ERROR < %t %s
+# RUN: not llvm-mc -disassemble -triple=thumbv8.1m.main-none-eabi -show-encoding %s &> %t
+# RUN: FileCheck --check-prefix=CHECK-NOMVE < %t %s
+
+# CHECK: vbic q0, q1, q7  @ encoding: [0x12,0xef,0x5e,0x01]
+# CHECK-NOMVE: [[@LINE+1]]:2: warning: invalid instruction encoding
+[0x12,0xef,0x5e,0x01]
+
+# CHECK: vrev64.8 q0, q4  @ encoding: [0xb0,0xff,0x48,0x00]
+# CHECK-NOMVE: [[@LINE+1]]:2: warning: invalid instruction encoding
+[0xb0,0xff,0x48,0x00]
+
+# CHECK: vrev64.16 q1, q3  @ encoding: [0xb4,0xff,0x46,0x20]
+# CHECK-NOMVE: [[@LINE+1]]:2: warning: invalid instruction encoding
+[0xb4,0xff,0x46,0x20]
+
+# CHECK: vrev64.32 q0, q2  @ encoding: [0xb8,0xff,0x44,0x00]
+# CHECK-NOMVE: [[@LINE+1]]:2: warning: invalid instruction encoding
+[0xb8,0xff,0x44,0x00]
+
+# CHECK: vrev32.8 q0, q1  @ encoding: [0xb0,0xff,0xc2,0x00]
+# CHECK-NOMVE: [[@LINE+1]]:2: warning: invalid instruction encoding
+[0xb0,0xff,0xc2,0x00]
+
+# CHECK: vrev32.16 q0, q5  @ encoding: [0xb4,0xff,0xca,0x00]
+# CHECK-NOMVE: [[@LINE+1]]:2: warning: invalid instruction encoding
+[0xb4,0xff,0xca,0x00]
+
+# CHECK: vrev16.8 q0, q2  @ encoding: [0xb0,0xff,0x44,0x01]
+# CHECK-NOMVE: [[@LINE+1]]:2: warning: invalid instruction encoding
+[0xb0,0xff,0x44,0x01]
+
+# CHECK: vmvn q0, q2  @ encoding: [0xb0,0xff,0xc4,0x05]
+# CHECK-NOMVE: [[@LINE+1]]:2: warning: invalid instruction encoding
+[0xb0,0xff,0xc4,0x05]
+
+# CHECK: veor q2, q1, q7  @ encoding: [0x02,0xff,0x5e,0x41]
+# CHECK-NOMVE: [[@LINE+1]]:2: warning: invalid instruction encoding
+[0x02,0xff,0x5e,0x41]
+
+# CHECK: vorn q0, q3, q2  @ encoding: [0x36,0xef,0x54,0x01]
+# CHECK-NOMVE: [[@LINE+1]]:2: warning: invalid instruction encoding
+[0x36,0xef,0x54,0x01]
+
+# CHECK: vorr q1, q2, q1  @ encoding: [0x24,0xef,0x52,0x21]
+# CHECK-NOMVE: [[@LINE+1]]:2: warning: invalid instruction encoding
+[0x24,0xef,0x52,0x21]
+
+# CHECK: vand q0, q2, q0  @ encoding: [0x04,0xef,0x50,0x01]
+# CHECK-NOMVE: [[@LINE+1]]:2: warning: invalid instruction encoding
+[0x04,0xef,0x50,0x01]
+
+# CHECK: vorr.i16 q0, #0x12  @ encoding: [0x81,0xef,0x52,0x09]
+# CHECK-NOMVE: [[@LINE+1]]:2: warning: invalid instruction encoding
+[0x81,0xef,0x52,0x09]
+
+# CHECK: vorr.i32 q0, #0x1200  @ encoding: [0x81,0xef,0x52,0x03]
+# CHECK-NOMVE: [[@LINE+1]]:2: warning: invalid instruction encoding
+[0x81,0xef,0x52,0x03]
+
+# CHECK: vbic.i32 q0, #0x35 @ encoding: [0x83,0xef,0x75,0x01]
+[0x83,0xef,0x75,0x01]
+
+# CHECK: vbic.i32 q0, #0x3500 @ encoding: [0x83,0xef,0x75,0x03]
+[0x83,0xef,0x75,0x03]
+
+# CHECK: vbic.i32 q0, #0x350000 @ encoding: [0x83,0xef,0x75,0x05]
+[0x83,0xef,0x75,0x05]
+
+# CHECK: vbic.i32 q0, #0x35000000 @ encoding: [0x83,0xef,0x75,0x07]
+[0x83,0xef,0x75,0x07]
+
+# CHECK: vbic.i16 q0, #0x35 @ encoding: [0x83,0xef,0x75,0x09]
+[0x83,0xef,0x75,0x09]
+
+# CHECK: vbic.i16 q0, #0x3500 @ encoding: [0x83,0xef,0x75,0x0b]
+[0x83,0xef,0x75,0x0b]
+
+# CHECK: vmov.8 q0[1], r8  @ encoding: [0x40,0xee,0x30,0x8b]
+# CHECK-NOMVE: [[@LINE+1]]:2: warning: invalid instruction encoding
+[0x40,0xee,0x30,0x8b]
+
+# CHECK: vmov.16 q0[2], r5  @ encoding: [0x20,0xee,0x30,0x5b]
+# CHECK-NOMVE: [[@LINE+1]]:2: warning: invalid instruction encoding
+[0x20,0xee,0x30,0x5b]
+
+# CHECK: vmov.32 q6[3], r11  @ encoding: [0x2d,0xee,0x10,0xbb]
+# CHECK-NOMVE: [[@LINE+1]]:2: warning: invalid instruction encoding
+[0x2d,0xee,0x10,0xbb]
+
+# CHECK: vmov.32 r0, q1[0]  @ encoding: [0x12,0xee,0x10,0x0b]
+# CHECK-NOMVE: [[@LINE+1]]:2: warning: invalid instruction encoding
+[0x12,0xee,0x10,0x0b]
+
+# CHECK: vmov.s16 r1, q2[7]  @ encoding: [0x35,0xee,0x70,0x1b]
+# CHECK-NOMVE: [[@LINE+1]]:2: warning: invalid instruction encoding
+[0x35,0xee,0x70,0x1b]
+
+# CHECK: vmov.s8 r0, q4[13]  @ encoding: [0x79,0xee,0x30,0x0b]
+# CHECK-NOMVE: [[@LINE+1]]:2: warning: invalid instruction encoding
+[0x79,0xee,0x30,0x0b]
+
+# CHECK: vmov.u16 r0, q1[4]  @ encoding: [0x93,0xee,0x30,0x0b]
+# CHECK-NOMVE: [[@LINE+1]]:2: warning: invalid instruction encoding
+[0x93,0xee,0x30,0x0b]
+
+# CHECK: vmov.u8 r0, q5[7]  @ encoding: [0xfa,0xee,0x70,0x0b]
+# CHECK-NOMVE: [[@LINE+1]]:2: warning: invalid instruction encoding
+[0xfa,0xee,0x70,0x0b]
+
+# CHECK: vmov.f16 s7, r8 @ encoding: [0x03,0xee,0x90,0x89]
+# CHECK-NOMVE: [[@LINE+1]]:2: warning: invalid instruction encoding
+[0x03,0xee,0x90,0x89]
+
+# CHECK: vmov.f16 s10, r5 @ encoding: [0x05,0xee,0x10,0x59]
+# CHECK-NOMVE: [[@LINE+1]]:2: warning: invalid instruction encoding
+[0x05,0xee,0x10,0x59]
+
+# CHECK: vmov.f16 s10, sp @ encoding: [0x05,0xee,0x10,0xd9]
+# CHECK-NOMVE: [[@LINE+1]]:2: warning: invalid instruction encoding
+[0x05,0xee,0x10,0xd9]
+
+# CHECK: vmov.f16 s31, r10 @ encoding: [0x0f,0xee,0x90,0xa9]
+# CHECK-NOMVE: [[@LINE+1]]:2: warning: invalid instruction encoding
+[0x0f,0xee,0x90,0xa9]
+
+# CHECK: vmov.f16 r8, s7 @ encoding: [0x13,0xee,0x90,0x89]
+# CHECK-NOMVE: [[@LINE+1]]:2: warning: invalid instruction encoding
+[0x13,0xee,0x90,0x89]
+
+# CHECK: vmov.f16 r5, s10 @ encoding: [0x15,0xee,0x10,0x59]
+# CHECK-NOMVE: [[@LINE+1]]:2: warning: invalid instruction encoding
+[0x15,0xee,0x10,0x59]
+
+# CHECK: vmov.f16 sp, s10 @ encoding: [0x15,0xee,0x10,0xd9]
+# CHECK-NOMVE: [[@LINE+1]]:2: warning: invalid instruction encoding
+[0x15,0xee,0x10,0xd9]
+
+# CHECK: vmov.f16 r10, s31 @ encoding: [0x1f,0xee,0x90,0xa9]
+# CHECK-NOMVE: [[@LINE+1]]:2: warning: invalid instruction encoding
+[0x1f,0xee,0x90,0xa9]
+
+# ERROR: [[@LINE+2]]:2: warning: potentially undefined instruction encoding
+# CHECK-NOMVE: [[@LINE+1]]:2: warning: invalid instruction encoding
+[0x05,0xee,0x10,0xf9]
+
+# ERROR: [[@LINE+2]]:2: warning: potentially undefined instruction encoding
+# CHECK-NOMVE: [[@LINE+1]]:2: warning: invalid instruction encoding
+[0x1f,0xee,0x90,0xf9]
--- a/test/MC/Disassembler/ARM/mve-vmov-lane.txt
+++ b/test/MC/Disassembler/ARM/mve-vmov-lane.txt
@ -0,0 +1,13 @@
+# RUN: llvm-mc -triple=thumbv8m.main   -mattr=+fp-armv8 -disassemble < %s | FileCheck %s --check-prefix=D_REG
+# RUN: llvm-mc -triple=thumbv8a        -mattr=+fp-armv8 -disassemble < %s | FileCheck %s --check-prefix=D_REG
+# RUN: llvm-mc -triple=thumbv8.1m.main -mattr=+fp-armv8 -disassemble < %s | FileCheck %s --check-prefix=Q_REG
+# RUN: llvm-mc -triple=thumbv8.1m.main -mattr=+mve      -disassemble < %s | FileCheck %s --check-prefix=Q_REG
+
+# The disassembly for this instruction varies between v8.1M and other
+# architectures. In v8.1M (with either scalar flotaing point, MVE or both), we
+# use the Q register syntax, and for all other architectures we use the D
+# register syntax.
+
+[0x11,0xee,0x10,0x0b]
+# D_REG: vmov.32 r0, d1[0]
+# Q_REG: vmov.32 r0, q0[2]