[RISCV] Support vector crypto extension LLVM IR

[4vtomat]

Summary

Depends on D141672

[4vtomat]

Fixed the comment from Craig Topper and Philip Reames

[craig.topper]

llvm/include/llvm/IR/IntrinsicsRISCV.td

320

DefaultAttrsIntrinsic

430

DefaultAttrsIntrinsic

[craig.topper]

llvm/lib/Target/RISCV/RISCVInstrInfoVPseudos.td

2962

This parameter is never used.

2970

I think this can use VPseudoBinaryV_VV

2972

I think this can use VPseudoBinaryV_VX

4147

I don't think using "PPat" instead of "VPat" meaningful highlights the difference between these patterns. The instructions being OP_P is an encoding detail only.

[craig.topper]

llvm/lib/Target/RISCV/RISCVInstrInfoVPseudos.td

4366

I think this might be the same as VPatTernaryNoMaskWithPolicy

[4vtomat]

Some NFCs.

[4vtomat]

NFC, add accidentally deleted blank line.

[4vtomat]

Updated to spec version 20230206.

[4vtomat]

Some updates on last commit.

[4vtomat]

Update to version 0.5.1.

[4vtomat]

Ready for review

[craig.topper]

llvm/include/llvm/IR/IntrinsicsRISCV.td

1620

Capitalize the Z in extension names in comments.

1645

I think vaeskf1 needs something like ImmArg<ArgIndex<X>> for the immediate.

Same for any other instruction with constant arguments.

[michaelmaitland]

llvm/include/llvm/IR/IntrinsicsRISCV.td

316

nit: destination vector type is the same as the source vector type

318

From @craig.topper's comment https://reviews.llvm.org/D138810#inline-1494421

What does P in this name mean? Is this because they use OP_P as their opcode? If so I don't think that should be part of how we name intrinsics.

Can we drop P here too and reuse RISCVUnaryAAUnMasked? After adding DefaultAttrsIntrinsic it may be the same? If not, I have two questions:

1. Is P the most descriptive suffix to use?
2. If so, can we at least document where P comes from?

429

Can you please add a docstring for this class?

1638

IsVS should be renamed to HasVS to match class definition. Do you need to pass HasVS since it defaults to 1?

llvm/lib/Target/RISCV/RISCVInstrInfoVPseudos.td

1044

Is there a reason behind using PPseudo instead of VPseudo? If its the same P as the other parts of this patch, should we keep it a suffix instead of prefix?

2701

Docstring for MxListVF4 says for zext/sext.vf4. Are you able to update this docstring now that it has more uses?

4754

I raise the same question about whether this should be VPatUnary as above and if P is needed, should it be suffixed?

6534

It looks like this is part of the Vector Compress Instruction section. Should we add a vector crypto comment to separate?

7169

It looks like this is part of the Vector Compress Instruction section. Should we add a vector crypto comment to separate?

[4vtomat]

Updates Craig's and Michael's comments.

[4vtomat]

llvm/include/llvm/IR/IntrinsicsRISCV.td

318

Yeah, I think you and Craig are right, I should change it to more descriptive name, thanks!

429

Sure, I just added a comment above

1620

Sure~

1638

For vgmul,
it uses the def which chooses the class instead of multiclass definition:

class RISCVUnaryAAUnMaskedP<bit IsVS>

And for the class definition, argument IsVS means: If this intrinsic is a VS intrinsic, then it will use llvm_anyvector_ty as it's 2nd input arg type and use LLVMMatchType<2> as 4th input arg type.

However for multiclass definition, argument HasVS means, If this intrinsic has VS, then define one for it.

1638

IsVS should be renamed to HasVS to match class definition. Do you need to pass HasVS since it defaults to 1?

1645

Oh, I forgot this part, thanks for reminding!

llvm/lib/Target/RISCV/RISCVInstrInfoVPseudos.td

2701

You are right, thanks!

6534

Sure, thanks!

[michaelmaitland]

LGTM.

[craig.topper]

llvm/test/CodeGen/RISCV/rvv/vwsll.ll

1459

shift amounts should be iXLen like the non widening shift

[craig.topper]

llvm/test/CodeGen/RISCV/rvv/vror.ll

2186

Shift amounts should be iXLen.

[craig.topper]

llvm/lib/Target/RISCV/RISCVInstrInfoVPseudos.td

7180

We will need to implement a VI version of the vrol intrinsic using the vror.vi instruction by changing the amount to sew-rotamount.

7181

VPatBinaryV_VV_VX_VI defaults simm5, but vror.vi uses uimm6.

[4vtomat]

This update includes:

1. Add the constraint: LMUL*VLEN < EGW during lowering instructions.
2. Enumerate over all of lmul less or equal to vd type's lmul for those instructions that have scalar operand.

[craig.topper]

llvm/lib/Target/RISCV/RISCVISelDAGToDAG.cpp

1551 ↗

(On Diff #544294)

This seems unnecessarily complex. https://reviews.llvm.org/D155439 already did this for non-intrinsics using an SDNodeXForm in tablegen

llvm/lib/Target/RISCV/RISCVISelLowering.cpp

7121 ↗

(On Diff #544294)

This is dead code in release builds and will give a build warning.

7261 ↗

(On Diff #544294)

This assert isn't helpful to compiler users. It's not part of release builds.

[4vtomat]

Resolved Craig's comments.

[craig.topper]

llvm/lib/Target/RISCV/RISCVInstrInfoZvk.td

678 ↗

(On Diff #544621)

timm5 uses isInt<5>, but I think you want isUInt<5>?

[4vtomat]

Resolved Craig's comment.

llvm/lib/Target/RISCV/RISCVISelDAGToDAG.cpp

1551 ↗

(On Diff #544294)

Oh, that's much better, thanks!

llvm/lib/Target/RISCV/RISCVISelLowering.cpp

7261 ↗

(On Diff #544294)

Oh, ok. I just changed it to report_fatal_error~

llvm/lib/Target/RISCV/RISCVInstrInfoVPseudos.td

7181

Oh, I forgot this instruction has different encoding of immediate, thanks!

llvm/lib/Target/RISCV/RISCVInstrInfoZvk.td

678 ↗

(On Diff #544621)

Oh, correct, thanks!

[craig.topper]

llvm/lib/Target/RISCV/RISCVISelLowering.cpp

7135 ↗

(On Diff #545025)

Doesn't this need to consider the value of vscale or VLEN? getKnownMinValue() always returns 64 for <vscale x 2 x i32>.

llvm/lib/Target/RISCV/RISCVInstrInfoZvk.td

758 ↗

(On Diff #545025)

NegImm64 no longer exists. I changed it in https://reviews.llvm.org/D156348

[4vtomat]

llvm/lib/Target/RISCV/RISCVISelLowering.cpp

7135 ↗

(On Diff #545025)

My thought was: For each <vscale x N x M>, if N * M >= EGS * M == [4|8] * M, namely if N >= EGS, then it's valid.
So, for vaesdf.vv vd, vs1, vs2, <vscale x 2 x i32> is invalid, however, <vscale x 4 x i32> and larger is valid.

[4vtomat]

Resolved Craig's comment.

[craig.topper]

llvm/lib/Target/RISCV/RISCVISelLowering.cpp

7135 ↗

(On Diff #545025)

<vscale x 4 x i32> is LMUL=2. I thought based on our conversation here https://github.com/riscv-non-isa/rvv-intrinsic-doc/pull/234#discussion_r1271843685 that we wanted to allow LMUL=1 with Zvl128b?

[4vtomat]

Resolved Craig's comment.

[4vtomat]

llvm/lib/Target/RISCV/RISCVISelLowering.cpp

7135 ↗

(On Diff #545025)

Oh, I misunderstood how LMUL is calculated, I thought it was VLEN / (N x M), so if zvl128b, <vscale x 4 x i32> would have LMUL=1.
But seems it's not calculated this way, the VLEN here is always 64. So if we want to support LMUL=1, <vscale x 2 x i32> should be valid.

[craig.topper]

llvm/lib/Target/RISCV/RISCVISelLowering.cpp

7187 ↗

(On Diff #546000)

Use RVVBitsPerBlock instead of 64

[craig.topper]

llvm/lib/Target/RISCV/RISCVISelLowering.cpp

7187 ↗

(On Diff #546000)

Please add extra parentheses to Subtarget.getRealMinVLen() * VT.getSizeInBits().getKnownMinValue() / 64 to make the operator precedence clear

[4vtomat]

llvm/lib/Target/RISCV/RISCVISelLowering.cpp

7187 ↗

(On Diff #546000)

The reason I didn't add parentheses between VT.getSizeInBits().getKnownMinValue() / 64 is because if I do so, I need to case VT.getSizeInBits().getKnownMinValue() to either double or float since it could be fractional. Do you think it's better to do it this way?

[craig.topper]

llvm/lib/Target/RISCV/RISCVISelLowering.cpp

7187 ↗

(On Diff #546000)

Use (Subtarget.getRealMinVLen() * VT.getSizeInBits().getKnownMinValue()) / 64. It's the operator precedence the compiler will use for the current code. I just don't want to think about the operator precedence when reading the code.

[4vtomat]

llvm/lib/Target/RISCV/RISCVISelLowering.cpp

7187 ↗

(On Diff #546000)

Oh, I see~

[4vtomat]

Update Craig's comment.

[craig.topper]

LGTM

[zixuan-wu]

llvm/lib/Target/RISCV/RISCVInstrInfo.td

240 ↗

(On Diff #546534)

Should it be [{return isUInt<6>(Imm);}]? @4vtomat

[4vtomat]

llvm/lib/Target/RISCV/RISCVInstrInfo.td

240 ↗

(On Diff #546534)

Yeah, you are right, let me have a patch to fix it, thanks!

llvm/include/llvm/IR/IntrinsicsRISCV.td

let TargetPrefix = "riscv" in {
   // For destination vector type is the same as source vector.
   // Input: (passthru, vector_in, vl)
   class RISCVUnaryAAUnMasked
         : DefaultAttrsIntrinsic<[llvm_anyvector_ty],
                     [LLVMMatchType<0>, LLVMMatchType<0>, llvm_anyint_ty],
                     [IntrNoMem]>, RISCVVIntrinsic {
     let VLOperand = 2;
   }
+  // For destination vector type is the same as source vector.
+  // Input: (passthru, vector_in, vl, policy)
+  class RISCVUnaryAAUnMaskedP<bit IsVS>
+        : Intrinsic<[llvm_anyvector_ty],
+                    [LLVMMatchType<0>, !if(IsVS, llvm_anyvector_ty, LLVMMatchType<0>),
+                     llvm_anyint_ty, !if(IsVS, LLVMMatchType<2>, LLVMMatchType<1>)],
+                    [ImmArg<ArgIndex<3>>, IntrNoMem]>, RISCVVIntrinsic {
+    let VLOperand = 2;
+  }
+
+  multiclass RISCVUnaryAAUnMaskedP<bit HasVV = 1, bit HasVS = 1> {
+    if HasVV then
+      def "int_riscv_" # NAME # "_vv" : RISCVUnaryAAUnMaskedP</*IsVS*/0>;
+
+    if HasVS then
+      def "int_riscv_" # NAME # "_vs" : RISCVUnaryAAUnMaskedP</*IsVS*/1>;
+  }
   // For destination vector type is the same as first source vector (with mask).
   // Input: (vector_in, vector_in, mask, vl, policy)
   class RISCVUnaryAAMasked
         : DefaultAttrsIntrinsic<[llvm_anyvector_ty],
                     [LLVMMatchType<0>, LLVMMatchType<0>,
                      LLVMScalarOrSameVectorWidth<0, llvm_i1_ty>, llvm_anyint_ty,
                      LLVMMatchType<1>],
                     [ImmArg<ArgIndex<4>>, IntrNoMem]>, RISCVVIntrinsic {
let TargetPrefix = "riscv" in {
   class RISCVBinaryAAXUnMasked
         : DefaultAttrsIntrinsic<[llvm_anyvector_ty],
                     [LLVMMatchType<0>, LLVMMatchType<0>, llvm_any_ty,
                      llvm_anyint_ty],
                     [IntrNoMem]>, RISCVVIntrinsic {
     let ScalarOperand = 2;
     let VLOperand = 3;
   }
+  class RISCVBinaryAAXUnMaskedP
+        : DefaultAttrsIntrinsic<[llvm_anyvector_ty],
+                                [LLVMMatchType<0>, LLVMMatchType<0>,
+                                 llvm_any_ty, llvm_anyint_ty, LLVMMatchType<2>],
+                                [ImmArg<ArgIndex<4>>, IntrNoMem]>,
+                                RISCVVIntrinsic {
+    let ScalarOperand = 2;
+    let VLOperand = 3;
+  }
   // For destination vector type is the same as first source vector (with mask).
   // Input: (maskedoff, vector_in, vector_in/scalar_in, mask, vl, policy)
   class RISCVBinaryAAXMasked
        : DefaultAttrsIntrinsic<[llvm_anyvector_ty],
                    [LLVMMatchType<0>, LLVMMatchType<0>, llvm_any_ty,
                     LLVMScalarOrSameVectorWidth<0, llvm_i1_ty>, llvm_anyint_ty,
                     LLVMMatchType<2>],
                    [ImmArg<ArgIndex<5>>, IntrNoMem]>, RISCVVIntrinsic {

 def int_riscv_sm4ed      : ScalarCryptoByteSelectAny;
 
 // Zksh
 def int_riscv_sm3p0      : ScalarCryptoGprIntrinsicAny;
 def int_riscv_sm3p1      : ScalarCryptoGprIntrinsicAny;
 } // TargetPrefix = "riscv"
 
 //===----------------------------------------------------------------------===//
+// Vector Cryptography
+//
+// These intrinsics will lower directly into the corresponding instructions
+// added by the vector cyptography extension, if the extension is present.
+let TargetPrefix = "riscv" in {
+  // zvbb
+  defm vandn            : RISCVBinaryAAX;
+  defm vbrev            : RISCVUnaryAA;
+  defm vbrev8           : RISCVUnaryAA;
+  defm vrev8            : RISCVUnaryAA;
+  defm vclz             : RISCVUnaryAA;
+  defm vctz             : RISCVUnaryAA;
+  defm vcpopv           : RISCVUnaryAA;
+  defm vrol             : RISCVBinaryAAX;
+  defm vror             : RISCVBinaryAAX;
+  defm vwsll            : RISCVBinaryABX;
+
+  // zvbc
+  defm vclmul           : RISCVBinaryAAX;
+  defm vclmulh          : RISCVBinaryAAX;
+
+  // zvkg
+  def int_riscv_vghsh   : RISCVBinaryAAXUnMaskedP;
+  def int_riscv_vgmul   : RISCVBinaryAAXUnMaskedP;
+
+  // zvkned
+  defm vaesdf           : RISCVUnaryAAUnMaskedP;
+  defm vaesdm           : RISCVUnaryAAUnMaskedP;
+  defm vaesef           : RISCVUnaryAAUnMaskedP;
+  defm vaesem           : RISCVUnaryAAUnMaskedP;
+  def int_riscv_vaeskf1 : RISCVBinaryAAXUnMasked;
+  def int_riscv_vaeskf2 : RISCVBinaryAAXUnMaskedP;
+  defm vaesz            : RISCVUnaryAAUnMaskedP</*HasVV*/0>;
+
+  // zvknha or zvknhb
+  def int_riscv_vsha2ch : RISCVBinaryAAXUnMaskedP;
+  def int_riscv_vsha2cl : RISCVBinaryAAXUnMaskedP;
+  def int_riscv_vsha2ms : RISCVBinaryAAXUnMaskedP;
+
+  // zvksed
+  def int_riscv_vsm4k   : RISCVBinaryAAXUnMasked;
+  defm vsm4r            : RISCVUnaryAAUnMaskedP;
+
+  // zvksh
+  def int_riscv_vsm3c   : RISCVBinaryAAXUnMaskedP;
+  def int_riscv_vsm3me  : RISCVBinaryAAXUnMasked;
+} // TargetPrefix = "riscv"
+
 // Vendor extensions
 //===----------------------------------------------------------------------===//
 include "llvm/IR/IntrinsicsRISCVXTHead.td"
 include "llvm/IR/IntrinsicsRISCVXsf.td"

llvm/lib/Target/RISCV/RISCVInstrInfoVPseudos.td

 class GroupVTypeInfo<ValueType Vec, ValueType VecM1, ValueType Mas, int Sew,
                      VReg Reg, LMULInfo M, ValueType Scal = XLenVT,
                      RegisterClass ScalarReg = GPR>
     : VTypeInfo<Vec, Mas, Sew, Reg, M, Scal, ScalarReg>
 {
   ValueType VectorM1 = VecM1;
 }
 
+defset list<VTypeInfo> I32I64IntegerVectors = {
+  defset list<VTypeInfo> I32IntegerVectors = {
+    def : VTypeInfo<vint32mf2_t, vbool64_t, 32, VR, V_MF2>;
+    def : VTypeInfo<vint32m1_t,  vbool32_t, 32, VR, V_M1>;
+    def : GroupVTypeInfo<vint32m2_t,vint32m1_t,vbool16_t,32,VRM2, V_M2>;
+    def : GroupVTypeInfo<vint32m4_t,vint32m1_t,vbool8_t, 32,VRM4, V_M4>;
+    def : GroupVTypeInfo<vint32m8_t,vint32m1_t,vbool4_t, 32,VRM8, V_M8>;
+  }
+  defset list<VTypeInfo> I64IntegerVectors = {
+    def : VTypeInfo<vint64m1_t,  vbool64_t, 64, VR, V_M1>;
+    def : GroupVTypeInfo<vint64m2_t,vint64m1_t,vbool32_t,64,VRM2, V_M2>;
+    def : GroupVTypeInfo<vint64m4_t,vint64m1_t,vbool16_t,64,VRM4, V_M4>;
+    def : GroupVTypeInfo<vint64m8_t,vint64m1_t,vbool8_t, 64,VRM8, V_M8>;
+  }
+}
+
 defset list<VTypeInfo> AllVectors = {
   defset list<VTypeInfo> AllIntegerVectors = {
     defset list<VTypeInfo> NoGroupIntegerVectors = {
       defset list<VTypeInfo> FractionalGroupIntegerVectors = {
         def VI8MF8: VTypeInfo<vint8mf8_t,  vbool64_t,  8, VR, V_MF8>;
         def VI8MF4: VTypeInfo<vint8mf4_t,  vbool32_t,  8, VR, V_MF4>;
         def VI8MF2: VTypeInfo<vint8mf2_t,  vbool16_t,  8, VR, V_MF2>;
         def VI16MF4: VTypeInfo<vint16mf4_t, vbool64_t, 16, VR, V_MF4>;
class VPseudoUnaryNoMaskTU<DAGOperand RetClass, VReg OpClass, string Constraint = ""> :
   let hasSideEffects = 0;
   let Constraints = Join<[Constraint, "$rd = $merge"], ",">.ret;
   let HasVLOp = 1;
   let HasSEWOp = 1;
   let HasDummyMask = 1;
   let HasMergeOp = 1;
 }
 
+class PPseudoUnaryNoMask<DAGOperand RetClass, VReg OpClass, string Constraint = ""> :
+      Pseudo<(outs RetClass:$rd),
+        (ins RetClass:$merge, OpClass:$rs2, AVL:$vl, ixlenimm:$sew, ixlenimm:$policy), []>,
+        RISCVVPseudo {
+  let mayLoad = 0;
+  let mayStore = 0;
+  let hasSideEffects = 0;
+  let Constraints = Join<[Constraint, "$rd = $merge"], ",">.ret;
+  let HasVLOp = 1;
+  let HasSEWOp = 1;
+  let HasDummyMask = 1;
+  let HasVecPolicyOp = 1;
+  let HasMergeOp = 1;
+  let BaseInstr = !cast<Instruction>(PseudoToVInst<NAME>.VInst);
+}
+
 class VPseudoUnaryMask<VReg RetClass, VReg OpClass, string Constraint = ""> :
         Pseudo<(outs GetVRegNoV0<RetClass>.R:$rd),
                (ins GetVRegNoV0<RetClass>.R:$merge, OpClass:$rs2,
                     VMaskOp:$vm, AVL:$vl, ixlenimm:$sew), []>,
         RISCVVPseudo {
   let mayLoad = 0;
   let mayStore = 0;
   let hasSideEffects = 0;
class VPseudoBinaryNoMaskTU<VReg RetClass,
   let hasSideEffects = 0;
   let Constraints = Join<[Constraint, "$rd = $merge"], ",">.ret;
   let HasVLOp = 1;
   let HasSEWOp = 1;
   let HasDummyMask = 1;
   let HasMergeOp = 1;
 }
 
+class PPseudoBinaryNoMask<VReg RetClass,
+                          VReg Op1Class,
+                          DAGOperand Op2Class,
+                          string Constraint> :
+        Pseudo<(outs RetClass:$rd),
+               (ins RetClass:$merge, Op1Class:$rs2, Op2Class:$rs1,
+                    AVL:$vl, ixlenimm:$sew, ixlenimm:$policy), []>,
+        RISCVVPseudo {
+  let mayLoad = 0;
+  let mayStore = 0;
+  let hasSideEffects = 0;
+  let Constraints = Join<[Constraint, "$rd = $merge"], ",">.ret;
+  let HasVLOp = 1;
+  let HasSEWOp = 1;
+  let HasDummyMask = 1;
+  let HasVecPolicyOp = 1;
+  let HasMergeOp = 1;
+  let BaseInstr = !cast<Instruction>(PseudoToVInst<NAME>.VInst);
+}
+
 // Special version of VPseudoBinaryNoMask where we pretend the first source is
 // tied to the destination.
 // This allows maskedoff and rs2 to be the same register.
 class VPseudoTiedBinaryNoMask<VReg RetClass,
                               DAGOperand Op2Class,
                               string Constraint> :
         Pseudo<(outs RetClass:$rd),
                (ins RetClass:$rs2, Op2Class:$rs1, AVL:$vl, ixlenimm:$sew,

 
 multiclass VPseudoVPOP_M {
   foreach mti = AllMasks in
   {
     defvar mx = mti.LMul.MX;
     defvar WriteVMPopV_MX = !cast<SchedWrite>("WriteVMPopV_" # mx);
     defvar ReadVMPopV_MX = !cast<SchedRead>("ReadVMPopV_" # mx);
     let VLMul = mti.LMul.value in {
-      def "_M_" # mti.BX : VPseudoUnaryNoMask<GPR, VR>,
-                           Sched<[WriteVMPopV_MX, ReadVMPopV_MX, ReadVMPopV_MX]>;
-      def "_M_" # mti.BX # "_MASK" : VPseudoMaskUnarySOutMask,
-                                     Sched<[WriteVMPopV_MX, ReadVMPopV_MX, ReadVMPopV_MX]>;
+      def "_" # mti.BX : VPseudoUnaryNoMask<GPR, VR>,
+      def "_" # mti.BX # "_MASK" : VPseudoMaskUnarySOutMask,
     }
   }
 }
 
 multiclass VPseudoV1ST_M {
   foreach mti = AllMasks in
   {
     defvar mx = mti.LMul.MX;

 multiclass VPseudoBinaryV_VV<LMULInfo m, string Constraint = ""> {
   defm _VV : VPseudoBinary<m.vrclass, m.vrclass, m.vrclass, m, Constraint>;
 }
 
 multiclass VPseudoBinaryV_VV_E<LMULInfo m, int sew, string Constraint = ""> {
   defm _VV : VPseudoBinary_E<m.vrclass, m.vrclass, m.vrclass, m, sew, Constraint>;
 }
 
+multiclass PPseudoBinaryNoMask<VReg RetClass,
+                               VReg Op1Class,
+                               DAGOperand Op2Class,
+                               LMULInfo MInfo,
+                               string Constraint = ""> {
+  let VLMul = MInfo.value in
+    def "_" # MInfo.MX : PPseudoBinaryNoMask<RetClass, Op1Class, Op2Class,
+                                             Constraint>;
+}
+
+multiclass PPseudoBinaryV_VV_NoMask<LMULInfo m, string Constraint = ""> {
+  defm _VV : PPseudoBinaryNoMask<m.vrclass, m.vrclass, m.vrclass, m, Constraint>;
+}
+
+multiclass VPseudoUnaryV_V<LMULInfo m, string Constraint = ""> {
+  let VLMul = m.value in {
+    def "_V_" # m.MX : VPseudoUnaryNoMask<m.vrclass, m.vrclass, Constraint>;
+
+    def "_V_" # m.MX # "_TU": VPseudoUnaryNoMaskTU<m.vrclass, m.vrclass, Constraint>;
+
+    def "_V_" # m.MX # "_MASK" : VPseudoUnaryMaskTA<m.vrclass, m.vrclass, Constraint>,
+                                 RISCVMaskedPseudo</*MaskOpIdx*/ 2>;
+  }
+}
+
+multiclass PPseudoUnaryV_V_NoMask<LMULInfo m, string Constraint = ""> {
+  let VLMul = m.value in {
+    def "_VV_" # m.MX : PPseudoUnaryNoMask<m.vrclass, m.vrclass, Constraint>;
+  }
+}
+
+multiclass PPseudoUnaryV_S_NoMask<LMULInfo m, string Constraint = ""> {
+  let VLMul = m.value in {
+    def "_VS_" # m.MX : PPseudoUnaryNoMask<m.vrclass, V_M1.vrclass, Constraint>;
+  }
+}
+
 // Similar to VPseudoBinaryV_VV, but uses MxListF.
 multiclass VPseudoBinaryFV_VV<LMULInfo m, string Constraint = ""> {
   defm _VV : VPseudoBinary<m.vrclass, m.vrclass, m.vrclass, m, Constraint>;
 }
 
 multiclass VPseudoBinaryFV_VV_E<LMULInfo m, int sew, string Constraint = ""> {
   defm _VV : VPseudoBinary_E<m.vrclass, m.vrclass, m.vrclass, m, sew, Constraint>;
 }
foreach f = FPList in {
     }
   }
 }
 
 multiclass VPseudoBinaryV_VI<Operand ImmType = simm5, LMULInfo m, string Constraint = ""> {
   defm _VI : VPseudoBinary<m.vrclass, m.vrclass, ImmType, m, Constraint>;
 }
 
+multiclass PPseudoBinaryV_VI<LMULInfo m, Operand ImmType = simm5, string Constraint = ""> {
+  defm _VI : VPseudoBinary<m.vrclass, m.vrclass, ImmType, m, Constraint>;
+}
+
+multiclass PPseudoBinaryV_VI_NoMask<LMULInfo m, Operand ImmType = simm5, string Constraint = ""> {
+  defm _VI : PPseudoBinaryNoMask<m.vrclass, m.vrclass, ImmType, m, Constraint>;
+}
+
 multiclass VPseudoVALU_MM {
   foreach m = MxList in {
     defvar mx = m.MX;
     defvar WriteVMALUV_MX = !cast<SchedWrite>("WriteVMALUV_" # mx);
     defvar ReadVMALUV_MX = !cast<SchedRead>("ReadVMALUV_" # mx);
 
     let VLMul = m.value in {
       def "_MM_" # mx : VPseudoBinaryNoMask<VR, VR, VR, "", /*DummyMask*/0>,
defm _VV : VPseudoBinary<m.wvrclass, m.vrclass, m.vrclass, m,
                            "@earlyclobber $rd">;
 }
 
 multiclass VPseudoBinaryW_VX<LMULInfo m> {
   defm "_VX" : VPseudoBinary<m.wvrclass, m.vrclass, GPR, m,
                              "@earlyclobber $rd">;
 }
 
+multiclass VPseudoBinaryW_VI<LMULInfo m, Operand ImmType = uimm5> {
+  defm "_VI" : VPseudoBinary<m.wvrclass, m.vrclass, ImmType, m,
+                             "@earlyclobber $rd">;
+}
+
 multiclass VPseudoBinaryW_VF<LMULInfo m, FPR_Info f> {
   defm "_V" # f.FX : VPseudoBinary<m.wvrclass, m.vrclass,
                                    f.fprclass, m,
                                    "@earlyclobber $rd">;
 }
 
 multiclass VPseudoBinaryW_WV<LMULInfo m> {
   defm _WV : VPseudoBinary<m.wvrclass, m.wvrclass, m.vrclass, m,
defm "" : VPseudoBinaryV_VV<m, Constraint>,
             Sched<[WriteVIALUV_MX, ReadVIALUV_MX, ReadVIALUV_MX, ReadVMask]>;
     defm "" : VPseudoBinaryV_VX<m, Constraint>,
             Sched<[WriteVIALUX_MX, ReadVIALUV_MX, ReadVIALUX_MX, ReadVMask]>;
     defm "" : VPseudoBinaryV_VI<ImmType, m, Constraint>,
             Sched<[WriteVIALUI_MX, ReadVIALUV_MX, ReadVMask]>;
   }
 }
 
+multiclass VPseudoVALU_V<string Constraint = ""> {
+  foreach m = MxList in {
+    defvar mx = m.MX;
+    defvar WriteVIALUV_MX = !cast<SchedWrite>("WriteVIALUV_" # mx);
+    defvar ReadVIALUV_MX = !cast<SchedRead>("ReadVIALUV_" # mx);
+
+    defm "" : VPseudoUnaryV_V<m, Constraint>,
+              Sched<[WriteVIALUV_MX, ReadVIALUV_MX, ReadVIALUV_MX, ReadVMask]>;
+  }
+}
+
+multiclass PPseudoVALU_V_NoMask<string Constraint = ""> {
+  foreach m = MxListVF4 in {
+    defvar mx = m.MX;
+    defvar WriteVIALUV_MX = !cast<SchedWrite>("WriteVIALUV_" # mx);
+    defvar ReadVIALUV_MX = !cast<SchedRead>("ReadVIALUV_" # mx);
+
+    defm "" : PPseudoUnaryV_V_NoMask<m, Constraint>,
+              Sched<[WriteVIALUV_MX, ReadVIALUV_MX, ReadVIALUV_MX, ReadVMask]>;
+  }
+}
+
+multiclass PPseudoVALU_S_NoMask<string Constraint = ""> {
+  foreach m = MxListVF4 in {
+    defvar mx = m.MX;
+    defvar WriteVIALUV_MX = !cast<SchedWrite>("WriteVIALUV_" # mx);
+    defvar ReadVIALUV_MX = !cast<SchedRead>("ReadVIALUV_" # mx);
+
+    defm "" : PPseudoUnaryV_S_NoMask<m, Constraint>,
+              Sched<[WriteVIALUV_MX, ReadVIALUV_MX, ReadVIALUV_MX, ReadVMask]>;
+  }
+}
+
+multiclass PPseudoVALU_V_S_NoMask<string Constraint = ""> {
+  defm "" : PPseudoVALU_V_NoMask<Constraint>;
+  defm "" : PPseudoVALU_S_NoMask<Constraint>;
+}
+
+multiclass PPseudoVALU_VV_NoMask<string Constraint = ""> {
+  foreach m = MxListVF4 in {
+    defvar mx = m.MX;
+    defvar WriteVIALUV_MX = !cast<SchedWrite>("WriteVIALUV_" # mx);
+    defvar ReadVIALUV_MX = !cast<SchedRead>("ReadVIALUV_" # mx);
+
+    defm "" : PPseudoBinaryV_VV_NoMask<m, Constraint>,
+              Sched<[WriteVIALUV_MX, ReadVIALUV_MX, ReadVIALUV_MX, ReadVMask]>;
+  }
+}
+
+multiclass PPseudoVALU_VI<Operand ImmType = simm5, string Constraint = ""> {
+  foreach m = MxListVF4 in {
+    defvar mx = m.MX;
+    defvar WriteVIALUV_MX = !cast<SchedWrite>("WriteVIALUV_" # mx);
+    defvar ReadVIALUV_MX = !cast<SchedRead>("ReadVIALUV_" # mx);
+
+    defm "" : PPseudoBinaryV_VI<m, ImmType, Constraint>,
+              Sched<[WriteVIALUV_MX, ReadVIALUV_MX, ReadVIALUV_MX, ReadVMask]>;
+  }
+}
+
+multiclass PPseudoVALU_VI_NoMask<Operand ImmType = simm5, string Constraint = ""> {
+  foreach m = MxListVF4 in {
+    defvar mx = m.MX;
+    defvar WriteVIALUV_MX = !cast<SchedWrite>("WriteVIALUV_" # mx);
+    defvar ReadVIALUV_MX = !cast<SchedRead>("ReadVIALUV_" # mx);
+
+    defm "" : PPseudoBinaryV_VI_NoMask<m, ImmType, Constraint>,
+              Sched<[WriteVIALUV_MX, ReadVIALUV_MX, ReadVIALUV_MX, ReadVMask]>;
+  }
+}
+
+multiclass PPseudoVALU_VI_NoMaskTU<Operand ImmType = uimm5, string Constraint = ""> {
+  foreach m = MxListVF4 in {
+    defvar mx = m.MX;
+    defvar WriteVIALUV_MX = !cast<SchedWrite>("WriteVIALUV_" # mx);
+    defvar ReadVIALUV_MX = !cast<SchedRead>("ReadVIALUV_" # mx);
+
+    def "_VI_" # m.MX : VPseudoBinaryNoMask<m.vrclass, m.vrclass, ImmType, Constraint>,
+                        Sched<[WriteVIALUV_MX, ReadVIALUV_MX, ReadVIALUV_MX, ReadVMask]>;
+    def "_VI_" # m.MX # "_TU" : VPseudoBinaryNoMaskTU<m.vrclass, m.vrclass, ImmType, Constraint>,
+                                Sched<[WriteVIALUV_MX, ReadVIALUV_MX, ReadVIALUV_MX, ReadVMask]>;
+  }
+}
+
+multiclass PPseudoVALU_VV_NoMaskTU<string Constraint = ""> {
+  foreach m = MxListVF4 in {
+    defvar mx = m.MX;
+    defvar WriteVIALUV_MX = !cast<SchedWrite>("WriteVIALUV_" # mx);
+    defvar ReadVIALUV_MX = !cast<SchedRead>("ReadVIALUV_" # mx);
+
+    def "_VV_" # m.MX : VPseudoBinaryNoMask<m.vrclass, m.vrclass, m.vrclass, Constraint>,
+                        Sched<[WriteVIALUV_MX, ReadVIALUV_MX, ReadVIALUV_MX, ReadVMask]>;
+    def "_VV_" # m.MX # "_TU" : VPseudoBinaryNoMaskTU<m.vrclass, m.vrclass, m.vrclass, Constraint>,
+                                Sched<[WriteVIALUV_MX, ReadVIALUV_MX, ReadVIALUV_MX, ReadVMask]>;
+  }
+}
 multiclass VPseudoVSALU_VV_VX {
   foreach m = MxList in {
     defvar mx = m.MX;
     defvar WriteVSALUV_MX = !cast<SchedWrite>("WriteVSALUV_" # mx);
     defvar WriteVSALUX_MX = !cast<SchedWrite>("WriteVSALUX_" # mx);
     defvar ReadVSALUV_MX = !cast<SchedRead>("ReadVSALUV_" # mx);
     defvar ReadVSALUX_MX = !cast<SchedRead>("ReadVSALUX_" # mx);
 
foreach m = MxList in {
 
     defm "" : VPseudoBinaryV_VV<m>,
             Sched<[WriteVIALUV_MX, ReadVIALUV_MX, ReadVIALUV_MX, ReadVMask]>;
     defm "" : VPseudoBinaryV_VX<m>,
             Sched<[WriteVIALUX_MX, ReadVIALUV_MX, ReadVIALUX_MX, ReadVMask]>;
   }
 }
 
+multiclass VPseudoVCLMUL_VV_VX {
+  foreach m = MxList in {
+    defvar mx = m.MX;
+    defvar WriteVIALUV_MX = !cast<SchedWrite>("WriteVIALUV_" # mx);
+    defvar WriteVIALUX_MX = !cast<SchedWrite>("WriteVIALUV_" # mx);
+    defvar ReadVIALUV_MX = !cast<SchedRead>("ReadVIALUV_" # mx);
+    defvar ReadVIALUX_MX = !cast<SchedRead>("ReadVIALUX_" # mx);
+
+    defm "" : VPseudoBinaryV_VV<m>,
+              Sched<[WriteVIALUV_MX, ReadVIALUV_MX, ReadVIALUV_MX, ReadVMask]>;
+    defm "" : VPseudoBinaryV_VX<m>,
+              Sched<[WriteVIALUX_MX, ReadVIALUV_MX, ReadVIALUX_MX, ReadVMask]>;
+  }
+}
+
 multiclass VPseudoVSGNJ_VV_VF {
   foreach m = MxListF in {
     defvar mx = m.MX;
     defvar WriteVFSgnjV_MX = !cast<SchedWrite>("WriteVFSgnjV_" # mx);
     defvar ReadVFSgnjV_MX = !cast<SchedRead>("ReadVFSgnjV_" # mx);
 
     defm "" : VPseudoBinaryFV_VV<m>,
               Sched<[WriteVFSgnjV_MX, ReadVFSgnjV_MX, ReadVFSgnjV_MX, ReadVMask]>;
foreach m = MxListW in {
 
     defm "" : VPseudoBinaryW_VV<m>,
             Sched<[WriteVIWALUV_MX, ReadVIWALUV_MX, ReadVIWALUV_MX, ReadVMask]>;
     defm "" : VPseudoBinaryW_VX<m>,
             Sched<[WriteVIWALUX_MX, ReadVIWALUV_MX, ReadVIWALUX_MX, ReadVMask]>;
   }
 }
 
+multiclass VPseudoVWALU_VV_VX_VI {
+  foreach m = MxListW in {
+    defvar mx = m.MX;
+    defvar WriteVIWALUV_MX = !cast<SchedWrite>("WriteVIWALUV_" # mx);
+    defvar WriteVIWALUX_MX = !cast<SchedWrite>("WriteVIWALUX_" # mx);
+    defvar WriteVIWALUI_MX = !cast<SchedWrite>("WriteVIWALUI_" # mx);
+    defvar ReadVIWALUV_MX = !cast<SchedRead>("ReadVIWALUV_" # mx);
+    defvar ReadVIWALUX_MX = !cast<SchedRead>("ReadVIWALUX_" # mx);
+
+    defm "" : VPseudoBinaryW_VV<m>,
+            Sched<[WriteVIWALUV_MX, ReadVIWALUV_MX, ReadVIWALUV_MX, ReadVMask]>;
+    defm "" : VPseudoBinaryW_VX<m>,
+            Sched<[WriteVIWALUX_MX, ReadVIWALUV_MX, ReadVIWALUX_MX, ReadVMask]>;
+    defm "" : VPseudoBinaryW_VI<m>,
+            Sched<[WriteVIWALUI_MX, ReadVIWALUV_MX, ReadVMask]>;
+  }
+}
+
 multiclass VPseudoVWMUL_VV_VX {
   foreach m = MxListW in {
     defvar mx = m.MX;
     defvar WriteVIWMulV_MX = !cast<SchedWrite>("WriteVIWMulV_" # mx);
     defvar WriteVIWMulX_MX = !cast<SchedWrite>("WriteVIWMulX_" # mx);
     defvar ReadVIWMulV_MX = !cast<SchedRead>("ReadVIWMulV_" # mx);
     defvar ReadVIWMulX_MX = !cast<SchedRead>("ReadVIWMulX_" # mx);
 
Pat<(result_type (!cast<Intrinsic>(intrinsic_name)
                    (result_type result_reg_class:$merge),
                    (op2_type op2_reg_class:$rs2),
                    VLOpFrag)),
                    (!cast<Instruction>(inst#"_"#kind#"_"#vlmul.MX#"_TU")
                    (result_type result_reg_class:$merge),
                    (op2_type op2_reg_class:$rs2),
                    GPR:$vl, sew)>;
 
 class VPatUnaryNoMaskTU_E<string intrinsic_name,
                           string inst,
                           string kind,
                           ValueType result_type,
                           ValueType op2_type,
                           int log2sew,
                           LMULInfo vlmul,
                           int sew,
                           VReg result_reg_class,
                           VReg op2_reg_class> :
   Pat<(result_type (!cast<Intrinsic>(intrinsic_name)
                    (result_type result_reg_class:$merge),
                    (op2_type op2_reg_class:$rs2),
                    VLOpFrag)),
                    (!cast<Instruction>(inst#"_"#kind#"_"#vlmul.MX#"_E"#sew#"_TU")
                    (result_type result_reg_class:$merge),
                    (op2_type op2_reg_class:$rs2),
                    GPR:$vl, log2sew)>;
 
+class PPatUnaryNoMask<string intrinsic_name,
+                      string inst,
+                      string kind,
+                      ValueType result_type,
+                      ValueType op2_type,
+                      int sew,
+                      LMULInfo vlmul,
+                      VReg result_reg_class,
+                      VReg op2_reg_class> :
+  Pat<(result_type (!cast<Intrinsic>(intrinsic_name)
+                   (result_type result_reg_class:$merge),
+                   (op2_type op2_reg_class:$rs2),
+                   VLOpFrag, (XLenVT timm:$policy))),
+                   (!cast<Instruction>(inst#"_"#kind#"_"#vlmul.MX)
+                   (result_type result_reg_class:$merge),
+                   (op2_type op2_reg_class:$rs2),
+                   GPR:$vl, sew, (XLenVT timm:$policy))>;
+
 class VPatUnaryMask<string intrinsic_name,
                     string inst,
                     string kind,
                     ValueType result_type,
                     ValueType op2_type,
                     ValueType mask_type,
                     int sew,
                     LMULInfo vlmul,
Pat<(result_type (!cast<Intrinsic>(intrinsic_name)
                    (op2_type op2_kind:$rs2),
                    VLOpFrag)),
                    (!cast<Instruction>(inst#"_TU")
                    (result_type result_reg_class:$merge),
                    (op1_type op1_reg_class:$rs1),
                    (op2_type op2_kind:$rs2),
                    GPR:$vl, sew)>;
 
 // Same as above but source operands are swapped.
 class VPatBinaryNoMaskSwapped<string intrinsic_name,
                               string inst,
                               ValueType result_type,
                               ValueType op1_type,
                               ValueType op2_type,
                               int sew,
                               VReg op1_reg_class,
                               DAGOperand op2_kind> :
def : VPatUnaryNoMaskTU_E<intrinsic, instruction, "V",
                               vti.RegClass, vti.RegClass>;
     def : VPatUnaryMaskTA_E<intrinsic, instruction, "V",
                             vti.Vector, vti.Vector, vti.Mask,
                             vti.Log2SEW, vti.LMul, vti.SEW,
                             vti.RegClass, vti.RegClass>;
   }
 }
 
+multiclass PPatUnaryV_V_NoMask<string intrinsic, string instruction,
+             list<VTypeInfo> vtilist> {
+  foreach vti = vtilist in
+    def : PPatUnaryNoMask<intrinsic # "_vv", instruction, "VV",
+                          vti.Vector, vti.Vector, vti.Log2SEW,
+                          vti.LMul, vti.RegClass, vti.RegClass>;
+}
+
+multiclass PPatUnaryV_S_NoMask<string intrinsic, string instruction,
+                        list<VTypeInfo> vtilist> {
+  foreach vti = vtilist in {
+    defvar vectorM1 = !cast<VTypeInfo>("VI" # vti.SEW # "M1");
+    def : PPatUnaryNoMask<intrinsic # "_vs", instruction, "VS",
+                          vti.Vector, vectorM1.Vector, vti.Log2SEW,
+                          vti.LMul, vti.RegClass, VR>;
+  }
+}
+
+multiclass PPatUnaryV_V_S_NoMask<string intrinsic, string instruction,
+               list<VTypeInfo> vtilist> {
+  defm : PPatUnaryV_V_NoMask<intrinsic, instruction, vtilist>;
+  defm : PPatUnaryV_S_NoMask<intrinsic, instruction, vtilist>;
+}
+
 multiclass VPatNullaryV<string intrinsic, string instruction>
 {
   foreach vti = AllIntegerVectors in {
     def : Pat<(vti.Vector (!cast<Intrinsic>(intrinsic)
                           (vti.Vector undef),
                           VLOpFrag)),
                           (!cast<Instruction>(instruction#"_V_" # vti.LMul.MX)
                           GPR:$vl, vti.Log2SEW)>;
def : VPatBinaryNoMaskTA<intrinsic, inst, result_type, op1_type, op2_type,
                            sew, op1_reg_class, op2_kind>;
   def : VPatBinaryNoMaskTU<intrinsic, inst, result_type, op1_type, op2_type,
                            sew, result_reg_class, op1_reg_class, op2_kind>;
   def : VPatBinaryMaskTA<intrinsic, inst, result_type, op1_type, op2_type,
                          mask_type, sew, result_reg_class, op1_reg_class,
                          op2_kind>;
 }
 
+multiclass VPatBinaryTANoMask<string intrinsic,
+                              string inst,
+                              ValueType result_type,
+                              ValueType op1_type,
+                              ValueType op2_type,
+                              int sew,
+                              VReg result_reg_class,
+                              VReg op1_reg_class,
+                              DAGOperand op2_kind>
+{
+  def : VPatBinaryNoMaskTA<intrinsic, inst, result_type, op1_type, op2_type,
+                           sew, op1_reg_class, op2_kind>;
+  def : VPatBinaryNoMaskTU<intrinsic, inst, result_type, op1_type, op2_type,
+                           sew, result_reg_class, op1_reg_class, op2_kind>;
+}
+
 multiclass VPatBinarySwapped<string intrinsic,
                       string inst,
                       ValueType result_type,
                       ValueType op1_type,
                       ValueType op2_type,
                       ValueType mask_type,
                       int sew,
                       VReg result_reg_class,
multiclass VPatBinaryV_VV_E<string intrinsic, string instruction,
   foreach vti = vtilist in
     defm : VPatBinaryTA<intrinsic,
                         instruction # "_VV_" # vti.LMul.MX # "_E" # vti.SEW,
                         vti.Vector, vti.Vector, vti.Vector,vti.Mask,
                         vti.Log2SEW, vti.RegClass,
                         vti.RegClass, vti.RegClass>;
 }
 
+multiclass VPatBinaryV_VV_NoMask<string intrinsic, string instruction,
+                          list<VTypeInfo> vtilist> {
+  foreach vti = vtilist in
+    def : VPatTernaryNoMaskWithPolicy<intrinsic, instruction, "VV",
+                                      vti.Vector, vti.Vector, vti.Vector,
+                                      vti.Log2SEW, vti.LMul, vti.RegClass,
+                                      vti.RegClass, vti.RegClass>;
+}
+
 multiclass VPatBinaryV_VV_INT_E<string intrinsic, string instruction,
                           list<VTypeInfo> vtilist> {
   foreach vti = vtilist in {
     defvar ivti = GetIntVTypeInfo<vti>.Vti;
     defm : VPatBinaryTA<intrinsic,
                         instruction # "_VV_" # vti.LMul.MX # "_E" # vti.SEW,
                         vti.Vector, vti.Vector, ivti.Vector, vti.Mask,
                         vti.Log2SEW, vti.RegClass,
multiclass VPatBinaryV_VI<string intrinsic, string instruction,
                           list<VTypeInfo> vtilist, Operand imm_type> {
   foreach vti = vtilist in
     defm : VPatBinaryTA<intrinsic, instruction # "_VI_" # vti.LMul.MX,
                         vti.Vector, vti.Vector, XLenVT, vti.Mask,
                         vti.Log2SEW, vti.RegClass,
                         vti.RegClass, imm_type>;
 }
 
+multiclass VPatBinaryV_VI_NoMask<string intrinsic, string instruction,
+                          list<VTypeInfo> vtilist, Operand imm_type = simm5> {
+  foreach vti = vtilist in
+    def : VPatTernaryNoMaskWithPolicy<intrinsic, instruction, "VI",
+                                      vti.Vector, vti.Vector, XLenVT,
+                                      vti.Log2SEW, vti.LMul, vti.RegClass,
+                                      vti.RegClass, imm_type>;
+}
+
+multiclass VPatBinaryV_VI_NoMaskTA<string intrinsic, string instruction,
+                          list<VTypeInfo> vtilist, Operand imm_type = simm5> {
+  foreach vti = vtilist in
+    defm : VPatBinaryTANoMask<intrinsic, instruction # "_VI_" # vti.LMul.MX,
+                        vti.Vector, vti.Vector, XLenVT, vti.Log2SEW,
+                        vti.RegClass, vti.RegClass, imm_type>;
+}
+
+multiclass VPatBinaryV_VV_NoMaskTA<string intrinsic, string instruction,
+                          list<VTypeInfo> vtilist> {
+  foreach vti = vtilist in
+    defm : VPatBinaryTANoMask<intrinsic, instruction # "_VV_" # vti.LMul.MX,
+                        vti.Vector, vti.Vector, vti.Vector, vti.Log2SEW,
+                        vti.RegClass, vti.RegClass, vti.RegClass>;
+}
+
 multiclass VPatBinaryM_MM<string intrinsic, string instruction> {
   foreach mti = AllMasks in
     def : VPatBinaryM<intrinsic, instruction # "_MM_" # mti.LMul.MX,
                       mti.Mask, mti.Mask, mti.Mask,
                       mti.Log2SEW, VR, VR>;
 }
 
 multiclass VPatBinaryW_VV<string intrinsic, string instruction,
foreach VtiToWti = vtilist in {
     defvar kind = "V"#Vti.ScalarSuffix;
     defm : VPatBinaryTA<intrinsic, instruction#"_"#kind#"_"#Vti.LMul.MX,
                         Wti.Vector, Vti.Vector, Vti.Scalar, Vti.Mask,
                         Vti.Log2SEW, Wti.RegClass,
                         Vti.RegClass, Vti.ScalarRegClass>;
   }
 }
 
+multiclass VPatBinaryW_VI<string intrinsic, string instruction,
+                          list<VTypeInfoToWide> vtilist> {
+  foreach VtiToWti = vtilist in {
+    defvar Vti = VtiToWti.Vti;
+    defvar Wti = VtiToWti.Wti;
+    defm : VPatBinaryTA<intrinsic, instruction # "_VI_" # Vti.LMul.MX,
+                        Wti.Vector, Vti.Vector, Vti.Scalar, Vti.Mask,
+                        Vti.Log2SEW, Wti.RegClass,
+                        Vti.RegClass, uimm5>;
+  }
+}
+
 multiclass VPatBinaryW_WV<string intrinsic, string instruction,
                           list<VTypeInfoToWide> vtilist> {
   foreach VtiToWti = vtilist in {
     defvar Vti = VtiToWti.Vti;
     defvar Wti = VtiToWti.Wti;
     def : VPatTiedBinaryNoMask<intrinsic, instruction # "_WV_" # Vti.LMul.MX,
                                Wti.Vector, Vti.Vector,
                                Vti.Log2SEW, Wti.RegClass, Vti.RegClass>;
multiclass VPatBinaryV_VX_VI<string intrinsic, string instruction,
     : VPatBinaryV_VX<intrinsic, instruction, vtilist>,
       VPatBinaryV_VI<intrinsic, instruction, vtilist, simm5>;
 
 multiclass VPatBinaryW_VV_VX<string intrinsic, string instruction,
                              list<VTypeInfoToWide> vtilist>
     : VPatBinaryW_VV<intrinsic, instruction, vtilist>,
       VPatBinaryW_VX<intrinsic, instruction, vtilist>;
 
+multiclass VPatBinaryW_VV_VX_VI<string intrinsic, string instruction,
+                             list<VTypeInfoToWide> vtilist>
+    : VPatBinaryW_VV<intrinsic, instruction, vtilist>,
+      VPatBinaryW_VX<intrinsic, instruction, vtilist>,
+      VPatBinaryW_VI<intrinsic, instruction, vtilist>;
+
 multiclass VPatBinaryW_WV_WX<string intrinsic, string instruction,
                              list<VTypeInfoToWide> vtilist>
     : VPatBinaryW_WV<intrinsic, instruction, vtilist>,
       VPatBinaryW_WX<intrinsic, instruction, vtilist>;
 
 multiclass VPatBinaryV_WV_WX_WI<string intrinsic, string instruction,
                                 list<VTypeInfoToWide> vtilist>
     : VPatBinaryV_WV<intrinsic, instruction, vtilist>,

 // Pseudo instructions
 defm PseudoVMCLR : VPseudoNullaryPseudoM<"VMXOR">;
 defm PseudoVMSET : VPseudoNullaryPseudoM<"VMXNOR">;
 
 //===----------------------------------------------------------------------===//
 // 15.2. Vector mask population count vcpop
 //===----------------------------------------------------------------------===//
 
-defm PseudoVCPOP: VPseudoVPOP_M;
+defm PseudoVCPOP_M: VPseudoVPOP_M;
 
 //===----------------------------------------------------------------------===//
 // 15.3. vfirst find-first-set mask bit
 //===----------------------------------------------------------------------===//
 
 defm PseudoVFIRST: VPseudoV1ST_M;
 
 //===----------------------------------------------------------------------===//

 defm PseudoVRGATHER     : VPseudoVGTR_VV_VX_VI<uimm5, "@earlyclobber $rd">;
 defm PseudoVRGATHEREI16 : VPseudoVGTR_VV_EEW</* eew */ 16, "@earlyclobber $rd">;
 
 //===----------------------------------------------------------------------===//
 // 16.5. Vector Compress Instruction
 //===----------------------------------------------------------------------===//
 defm PseudoVCOMPRESS : VPseudoVCPR_V;
 
+let Predicates = [HasStdExtZvbb] in {
+  defm PseudoVANDN : VPseudoVALU_VV_VX;
+  defm PseudoVBREV : VPseudoVALU_V;
+  defm PseudoVBREV8 : VPseudoVALU_V;
+  defm PseudoVREV8 : VPseudoVALU_V;
+  defm PseudoVCLZ : VPseudoVALU_V;
+  defm PseudoVCTZ : VPseudoVALU_V;
+  defm PseudoVCPOP : VPseudoVALU_V;
+  defm PseudoVROL : VPseudoVALU_VV_VX;
+  defm PseudoVROR : VPseudoVALU_VV_VX_VI;
+  defm PseudoVWSLL : VPseudoVWALU_VV_VX_VI;
+} // Predicates = [HasStdExtZvbb]
+
+let Predicates = [HasStdExtZvbc] in {
+  defm PseudoVCLMUL : VPseudoVCLMUL_VV_VX;
+  defm PseudoVCLMULH : VPseudoVCLMUL_VV_VX;
+} // Predicates = [HasStdExtZvbc]
+
+let Predicates = [HasStdExtZvkg] in {
+  defm PseudoVGHSH : PPseudoVALU_VV_NoMask;
+  defm PseudoVGMUL : PPseudoVALU_VV_NoMask;
+} // Predicates = [HasStdExtZvkg]
+
+let Predicates = [HasStdExtZvkned] in {
+  defm PseudoVAESDF : PPseudoVALU_V_S_NoMask;
+  defm PseudoVAESDM : PPseudoVALU_V_S_NoMask;
+  defm PseudoVAESEF : PPseudoVALU_V_S_NoMask;
+  defm PseudoVAESEM : PPseudoVALU_V_S_NoMask;
+  defm PseudoVAESKF1 : PPseudoVALU_VI_NoMaskTU;
+  defm PseudoVAESKF2 : PPseudoVALU_VI_NoMask<uimm5>;
+  defm PseudoVAESZ : PPseudoVALU_S_NoMask;
+} // Predicates = [HasStdExtZvkned]
+
+let Predicates = [HasStdExtZvknha] in {
+  defm PseudoVSHA2CH : PPseudoVALU_VV_NoMask;
+  defm PseudoVSHA2CL : PPseudoVALU_VV_NoMask;
+  defm PseudoVSHA2MS : PPseudoVALU_VV_NoMask;
+} // Predicates = [HasStdExtZvknha]
+
+let Predicates = [HasStdExtZvksed] in {
+  defm PseudoVSM4K : PPseudoVALU_VI_NoMaskTU;
+  defm PseudoVSM4R : PPseudoVALU_V_S_NoMask;
+} // Predicates = [HasStdExtZvksed]
+
+let Predicates = [HasStdExtZvksh] in {
+  defm PseudoVSM3C : PPseudoVALU_VI_NoMask<uimm5>;
+  defm PseudoVSM3ME : PPseudoVALU_VV_NoMaskTU;
+} // Predicates = [HasStdExtZvksh]
+
 //===----------------------------------------------------------------------===//
 // Patterns.
 //===----------------------------------------------------------------------===//
 
 //===----------------------------------------------------------------------===//
 // 11. Vector Integer Arithmetic Instructions
 //===----------------------------------------------------------------------===//
 

 let Predicates = [HasVInstructions] in {
   defm : VPatUnaryV_V_AnyMask_E<"int_riscv_vcompress", "PseudoVCOMPRESS", AllIntegerVectors>;
 } // Predicates = [HasVInstructions]
 
 let Predicates = [HasVInstructionsAnyF] in {
   defm : VPatUnaryV_V_AnyMask_E<"int_riscv_vcompress", "PseudoVCOMPRESS", AllFloatVectors>;
 } // Predicates = [HasVInstructionsAnyF]
 
+let Predicates = [HasStdExtZvbb] in {
+  defm : VPatBinaryV_VV_VX<"int_riscv_vandn", "PseudoVANDN", AllIntegerVectors>;
+  defm : VPatUnaryV_V<"int_riscv_vbrev", "PseudoVBREV", AllIntegerVectors>;
+  defm : VPatUnaryV_V<"int_riscv_vbrev8", "PseudoVBREV8", AllIntegerVectors>;
+  defm : VPatUnaryV_V<"int_riscv_vrev8", "PseudoVREV8", AllIntegerVectors>;
+  defm : VPatUnaryV_V<"int_riscv_vclz", "PseudoVCLZ", AllIntegerVectors>;
+  defm : VPatUnaryV_V<"int_riscv_vctz", "PseudoVCTZ", AllIntegerVectors>;
+  defm : VPatUnaryV_V<"int_riscv_vcpopv", "PseudoVCPOP", AllIntegerVectors>;
+  defm : VPatBinaryV_VV_VX<"int_riscv_vrol", "PseudoVROL", AllIntegerVectors>;
+  defm : VPatBinaryV_VV_VX_VI<"int_riscv_vror", "PseudoVROR", AllIntegerVectors>;
+  defm : VPatBinaryW_VV_VX_VI<"int_riscv_vwsll", "PseudoVWSLL", AllWidenableIntVectors>;
+} // Predicates = [HasStdExtZvbb]
+
+let Predicates = [HasStdExtZvbc] in {
+  defm : VPatBinaryV_VV_VX<"int_riscv_vclmul", "PseudoVCLMUL", I64IntegerVectors>;
+  defm : VPatBinaryV_VV_VX<"int_riscv_vclmulh", "PseudoVCLMULH", I64IntegerVectors>;
+} // Predicates = [HasStdExtZvbc]
+
+let Predicates = [HasStdExtZvkg] in {
+  defm : VPatBinaryV_VV_NoMask<"int_riscv_vghsh", "PseudoVGHSH", I32IntegerVectors>;
+  defm : VPatBinaryV_VV_NoMask<"int_riscv_vgmul", "PseudoVGMUL", I32IntegerVectors>;
+} // Predicates = [HasStdExtZvkg]
+
+let Predicates = [HasStdExtZvkned] in {
+  defm : PPatUnaryV_V_S_NoMask<"int_riscv_vaesdf", "PseudoVAESDF", I32IntegerVectors>;
+  defm : PPatUnaryV_V_S_NoMask<"int_riscv_vaesdm", "PseudoVAESDM", I32IntegerVectors>;
+  defm : PPatUnaryV_V_S_NoMask<"int_riscv_vaesef", "PseudoVAESEF", I32IntegerVectors>;
+  defm : PPatUnaryV_V_S_NoMask<"int_riscv_vaesem", "PseudoVAESEM", I32IntegerVectors>;
+  defm : VPatBinaryV_VI_NoMaskTA<"int_riscv_vaeskf1", "PseudoVAESKF1", I32IntegerVectors, uimm5>;
+  defm : VPatBinaryV_VI_NoMask<"int_riscv_vaeskf2", "PseudoVAESKF2", I32IntegerVectors, uimm5>;
+  defm : PPatUnaryV_S_NoMask<"int_riscv_vaesz", "PseudoVAESZ", I32IntegerVectors>;
+} // Predicates = [HasStdExtZvkned]
+
+let Predicates = [HasStdExtZvknha] in {
+  defm : VPatBinaryV_VV_NoMask<"int_riscv_vsha2ch", "PseudoVSHA2CH", I32I64IntegerVectors>;
+  defm : VPatBinaryV_VV_NoMask<"int_riscv_vsha2cl", "PseudoVSHA2CH", I32I64IntegerVectors>;
+  defm : VPatBinaryV_VV_NoMask<"int_riscv_vsha2ms", "PseudoVSHA2MS", I32I64IntegerVectors>;
+} // Predicates = [HasStdExtZvknha]
+
+let Predicates = [HasStdExtZvksed] in {
+  defm : VPatBinaryV_VI_NoMaskTA<"int_riscv_vsm4k", "PseudoVSM4K", I32IntegerVectors, uimm5>;
+  defm : PPatUnaryV_V_S_NoMask<"int_riscv_vsm4r", "PseudoVSM4R", I32IntegerVectors>;
+} // Predicates = [HasStdExtZvksed]
+
+let Predicates = [HasStdExtZvksh] in {
+  defm : VPatBinaryV_VI_NoMask<"int_riscv_vsm3c", "PseudoVSM3C", I32IntegerVectors, uimm5>;
+  defm : VPatBinaryV_VV_NoMaskTA<"int_riscv_vsm3me", "PseudoVSM3ME", I32IntegerVectors>;
+} // Predicates = [HasStdExtZvksh]
+
 // Include the non-intrinsic ISel patterns
 include "RISCVInstrInfoVVLPatterns.td"
 include "RISCVInstrInfoVSDPatterns.td"

llvm/test/CodeGen/RISCV/rvv/vaesdf.ll

+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: sed 's/iXLen/i32/g' %s | llc -mtriple=riscv32 -mattr=+v,+experimental-zvkned \
+; RUN:   -verify-machineinstrs | FileCheck %s --check-prefixes=CHECK
+; RUN: sed 's/iXLen/i64/g' %s | llc -mtriple=riscv64 -mattr=+v,+experimental-zvkned \
+; RUN:   -verify-machineinstrs | FileCheck %s --check-prefixes=CHECK
+
+declare <vscale x 1 x i32> @llvm.riscv.vaesdf.vv.nxv1i32(
+  <vscale x 1 x i32>,
+  <vscale x 1 x i32>,
+  iXLen, iXLen);
+
+define <vscale x 1 x i32> @intrinsic_vaesdf_vv_nxv1i32(<vscale x 1 x i32> %0, <vscale x 1 x i32> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vaesdf_vv_nxv1i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, mf2, tu, ma
+; CHECK-NEXT:    vaesdf.vv v8, v9
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i32> @llvm.riscv.vaesdf.vv.nxv1i32(
+    <vscale x 1 x i32> %0,
+    <vscale x 1 x i32> %1,
+    iXLen %2, iXLen 2)
+
+  ret <vscale x 1 x i32> %a
+}
+
+declare <vscale x 2 x i32> @llvm.riscv.vaesdf.vv.nxv2i32(
+  <vscale x 2 x i32>,
+  <vscale x 2 x i32>,
+  iXLen, iXLen);
+
+define <vscale x 2 x i32> @intrinsic_vaesdf_vv_nxv2i32(<vscale x 2 x i32> %0, <vscale x 2 x i32> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vaesdf_vv_nxv2i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m1, tu, ma
+; CHECK-NEXT:    vaesdf.vv v8, v9
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i32> @llvm.riscv.vaesdf.vv.nxv2i32(
+    <vscale x 2 x i32> %0,
+    <vscale x 2 x i32> %1,
+    iXLen %2, iXLen 2)
+
+  ret <vscale x 2 x i32> %a
+}
+
+declare <vscale x 4 x i32> @llvm.riscv.vaesdf.vv.nxv4i32(
+  <vscale x 4 x i32>,
+  <vscale x 4 x i32>,
+  iXLen, iXLen);
+
+define <vscale x 4 x i32> @intrinsic_vaesdf_vv_nxv4i32(<vscale x 4 x i32> %0, <vscale x 4 x i32> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vaesdf_vv_nxv4i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m2, tu, ma
+; CHECK-NEXT:    vaesdf.vv v8, v10
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i32> @llvm.riscv.vaesdf.vv.nxv4i32(
+    <vscale x 4 x i32> %0,
+    <vscale x 4 x i32> %1,
+    iXLen %2, iXLen 2)
+
+  ret <vscale x 4 x i32> %a
+}
+
+declare <vscale x 8 x i32> @llvm.riscv.vaesdf.vv.nxv8i32(
+  <vscale x 8 x i32>,
+  <vscale x 8 x i32>,
+  iXLen, iXLen);
+
+define <vscale x 8 x i32> @intrinsic_vaesdf_vv_nxv8i32(<vscale x 8 x i32> %0, <vscale x 8 x i32> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vaesdf_vv_nxv8i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m4, tu, ma
+; CHECK-NEXT:    vaesdf.vv v8, v12
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i32> @llvm.riscv.vaesdf.vv.nxv8i32(
+    <vscale x 8 x i32> %0,
+    <vscale x 8 x i32> %1,
+    iXLen %2, iXLen 2)
+
+  ret <vscale x 8 x i32> %a
+}
+
+declare <vscale x 16 x i32> @llvm.riscv.vaesdf.vv.nxv16i32(
+  <vscale x 16 x i32>,
+  <vscale x 16 x i32>,
+  iXLen, iXLen);
+
+define <vscale x 16 x i32> @intrinsic_vaesdf_vv_nxv16i32(<vscale x 16 x i32> %0, <vscale x 16 x i32> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vaesdf_vv_nxv16i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m8, tu, ma
+; CHECK-NEXT:    vaesdf.vv v8, v16
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 16 x i32> @llvm.riscv.vaesdf.vv.nxv16i32(
+    <vscale x 16 x i32> %0,
+    <vscale x 16 x i32> %1,
+    iXLen %2, iXLen 2)
+
+  ret <vscale x 16 x i32> %a
+}
+
+declare <vscale x 1 x i32> @llvm.riscv.vaesdf.vs.nxv1i32(
+  <vscale x 1 x i32>,
+  <vscale x 2 x i32>,
+  iXLen, iXLen);
+
+define <vscale x 1 x i32> @intrinsic_vaesdf_vs_nxv1i32(<vscale x 1 x i32> %0, <vscale x 2 x i32> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vaesdf_vs_nxv1i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, mf2, tu, ma
+; CHECK-NEXT:    vaesdf.vs v8, v9
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i32> @llvm.riscv.vaesdf.vs.nxv1i32(
+    <vscale x 1 x i32> %0,
+    <vscale x 2 x i32> %1,
+    iXLen %2, iXLen 2)
+
+  ret <vscale x 1 x i32> %a
+}
+
+declare <vscale x 2 x i32> @llvm.riscv.vaesdf.vs.nxv2i32(
+  <vscale x 2 x i32>,
+  <vscale x 2 x i32>,
+  iXLen, iXLen);
+
+define <vscale x 2 x i32> @intrinsic_vaesdf_vs_nxv2i32(<vscale x 2 x i32> %0, <vscale x 2 x i32> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vaesdf_vs_nxv2i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m1, tu, ma
+; CHECK-NEXT:    vaesdf.vs v8, v9
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i32> @llvm.riscv.vaesdf.vs.nxv2i32(
+    <vscale x 2 x i32> %0,
+    <vscale x 2 x i32> %1,
+    iXLen %2, iXLen 2)
+
+  ret <vscale x 2 x i32> %a
+}
+
+declare <vscale x 4 x i32> @llvm.riscv.vaesdf.vs.nxv4i32(
+  <vscale x 4 x i32>,
+  <vscale x 2 x i32>,
+  iXLen, iXLen);
+
+define <vscale x 4 x i32> @intrinsic_vaesdf_vs_nxv4i32(<vscale x 4 x i32> %0, <vscale x 2 x i32> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vaesdf_vs_nxv4i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m2, tu, ma
+; CHECK-NEXT:    vaesdf.vs v8, v10
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i32> @llvm.riscv.vaesdf.vs.nxv4i32(
+    <vscale x 4 x i32> %0,
+    <vscale x 2 x i32> %1,
+    iXLen %2, iXLen 2)
+
+  ret <vscale x 4 x i32> %a
+}
+
+declare <vscale x 8 x i32> @llvm.riscv.vaesdf.vs.nxv8i32(
+  <vscale x 8 x i32>,
+  <vscale x 2 x i32>,
+  iXLen, iXLen);
+
+define <vscale x 8 x i32> @intrinsic_vaesdf_vs_nxv8i32(<vscale x 8 x i32> %0, <vscale x 2 x i32> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vaesdf_vs_nxv8i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m4, tu, ma
+; CHECK-NEXT:    vaesdf.vs v8, v12
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i32> @llvm.riscv.vaesdf.vs.nxv8i32(
+    <vscale x 8 x i32> %0,
+    <vscale x 2 x i32> %1,
+    iXLen %2, iXLen 2)
+
+  ret <vscale x 8 x i32> %a
+}
+
+declare <vscale x 16 x i32> @llvm.riscv.vaesdf.vs.nxv16i32(
+  <vscale x 16 x i32>,
+  <vscale x 2 x i32>,
+  iXLen, iXLen);
+
+define <vscale x 16 x i32> @intrinsic_vaesdf_vs_nxv16i32(<vscale x 16 x i32> %0, <vscale x 2 x i32> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vaesdf_vs_nxv16i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m8, tu, ma
+; CHECK-NEXT:    vaesdf.vs v8, v16
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 16 x i32> @llvm.riscv.vaesdf.vs.nxv16i32(
+    <vscale x 16 x i32> %0,
+    <vscale x 2 x i32> %1,
+    iXLen %2, iXLen 2)
+
+  ret <vscale x 16 x i32> %a
+}

llvm/test/CodeGen/RISCV/rvv/vaesdm.ll

+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: sed 's/iXLen/i32/g' %s | llc -mtriple=riscv32 -mattr=+v,+experimental-zvkned \
+; RUN:   -verify-machineinstrs | FileCheck %s --check-prefixes=CHECK
+; RUN: sed 's/iXLen/i64/g' %s | llc -mtriple=riscv64 -mattr=+v,+experimental-zvkned \
+; RUN:   -verify-machineinstrs | FileCheck %s --check-prefixes=CHECK
+
+declare <vscale x 1 x i32> @llvm.riscv.vaesdm.vv.nxv1i32(
+  <vscale x 1 x i32>,
+  <vscale x 1 x i32>,
+  iXLen, iXLen);
+
+define <vscale x 1 x i32> @intrinsic_vaesdm_vv_nxv1i32(<vscale x 1 x i32> %0, <vscale x 1 x i32> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vaesdm_vv_nxv1i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, mf2, tu, ma
+; CHECK-NEXT:    vaesdm.vv v8, v9
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i32> @llvm.riscv.vaesdm.vv.nxv1i32(
+    <vscale x 1 x i32> %0,
+    <vscale x 1 x i32> %1,
+    iXLen %2, iXLen 2)
+
+  ret <vscale x 1 x i32> %a
+}
+
+declare <vscale x 2 x i32> @llvm.riscv.vaesdm.vv.nxv2i32(
+  <vscale x 2 x i32>,
+  <vscale x 2 x i32>,
+  iXLen, iXLen);
+
+define <vscale x 2 x i32> @intrinsic_vaesdm_vv_nxv2i32(<vscale x 2 x i32> %0, <vscale x 2 x i32> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vaesdm_vv_nxv2i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m1, tu, ma
+; CHECK-NEXT:    vaesdm.vv v8, v9
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i32> @llvm.riscv.vaesdm.vv.nxv2i32(
+    <vscale x 2 x i32> %0,
+    <vscale x 2 x i32> %1,
+    iXLen %2, iXLen 2)
+
+  ret <vscale x 2 x i32> %a
+}
+
+declare <vscale x 4 x i32> @llvm.riscv.vaesdm.vv.nxv4i32(
+  <vscale x 4 x i32>,
+  <vscale x 4 x i32>,
+  iXLen, iXLen);
+
+define <vscale x 4 x i32> @intrinsic_vaesdm_vv_nxv4i32(<vscale x 4 x i32> %0, <vscale x 4 x i32> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vaesdm_vv_nxv4i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m2, tu, ma
+; CHECK-NEXT:    vaesdm.vv v8, v10
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i32> @llvm.riscv.vaesdm.vv.nxv4i32(
+    <vscale x 4 x i32> %0,
+    <vscale x 4 x i32> %1,
+    iXLen %2, iXLen 2)
+
+  ret <vscale x 4 x i32> %a
+}
+
+declare <vscale x 8 x i32> @llvm.riscv.vaesdm.vv.nxv8i32(
+  <vscale x 8 x i32>,
+  <vscale x 8 x i32>,
+  iXLen, iXLen);
+
+define <vscale x 8 x i32> @intrinsic_vaesdm_vv_nxv8i32(<vscale x 8 x i32> %0, <vscale x 8 x i32> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vaesdm_vv_nxv8i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m4, tu, ma
+; CHECK-NEXT:    vaesdm.vv v8, v12
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i32> @llvm.riscv.vaesdm.vv.nxv8i32(
+    <vscale x 8 x i32> %0,
+    <vscale x 8 x i32> %1,
+    iXLen %2, iXLen 2)
+
+  ret <vscale x 8 x i32> %a
+}
+
+declare <vscale x 16 x i32> @llvm.riscv.vaesdm.vv.nxv16i32(
+  <vscale x 16 x i32>,
+  <vscale x 16 x i32>,
+  iXLen, iXLen);
+
+define <vscale x 16 x i32> @intrinsic_vaesdm_vv_nxv16i32(<vscale x 16 x i32> %0, <vscale x 16 x i32> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vaesdm_vv_nxv16i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m8, tu, ma
+; CHECK-NEXT:    vaesdm.vv v8, v16
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 16 x i32> @llvm.riscv.vaesdm.vv.nxv16i32(
+    <vscale x 16 x i32> %0,
+    <vscale x 16 x i32> %1,
+    iXLen %2, iXLen 2)
+
+  ret <vscale x 16 x i32> %a
+}
+
+declare <vscale x 1 x i32> @llvm.riscv.vaesdm.vs.nxv1i32(
+  <vscale x 1 x i32>,
+  <vscale x 2 x i32>,
+  iXLen, iXLen);
+
+define <vscale x 1 x i32> @intrinsic_vaesdm_vs_nxv1i32(<vscale x 1 x i32> %0, <vscale x 2 x i32> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vaesdm_vs_nxv1i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, mf2, tu, ma
+; CHECK-NEXT:    vaesdm.vs v8, v9
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i32> @llvm.riscv.vaesdm.vs.nxv1i32(
+    <vscale x 1 x i32> %0,
+    <vscale x 2 x i32> %1,
+    iXLen %2, iXLen 2)
+
+  ret <vscale x 1 x i32> %a
+}
+
+declare <vscale x 2 x i32> @llvm.riscv.vaesdm.vs.nxv2i32(
+  <vscale x 2 x i32>,
+  <vscale x 2 x i32>,
+  iXLen, iXLen);
+
+define <vscale x 2 x i32> @intrinsic_vaesdm_vs_nxv2i32(<vscale x 2 x i32> %0, <vscale x 2 x i32> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vaesdm_vs_nxv2i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m1, tu, ma
+; CHECK-NEXT:    vaesdm.vs v8, v9
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i32> @llvm.riscv.vaesdm.vs.nxv2i32(
+    <vscale x 2 x i32> %0,
+    <vscale x 2 x i32> %1,
+    iXLen %2, iXLen 2)
+
+  ret <vscale x 2 x i32> %a
+}
+
+declare <vscale x 4 x i32> @llvm.riscv.vaesdm.vs.nxv4i32(
+  <vscale x 4 x i32>,
+  <vscale x 2 x i32>,
+  iXLen, iXLen);
+
+define <vscale x 4 x i32> @intrinsic_vaesdm_vs_nxv4i32(<vscale x 4 x i32> %0, <vscale x 2 x i32> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vaesdm_vs_nxv4i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m2, tu, ma
+; CHECK-NEXT:    vaesdm.vs v8, v10
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i32> @llvm.riscv.vaesdm.vs.nxv4i32(
+    <vscale x 4 x i32> %0,
+    <vscale x 2 x i32> %1,
+    iXLen %2, iXLen 2)
+
+  ret <vscale x 4 x i32> %a
+}
+
+declare <vscale x 8 x i32> @llvm.riscv.vaesdm.vs.nxv8i32(
+  <vscale x 8 x i32>,
+  <vscale x 2 x i32>,
+  iXLen, iXLen);
+
+define <vscale x 8 x i32> @intrinsic_vaesdm_vs_nxv8i32(<vscale x 8 x i32> %0, <vscale x 2 x i32> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vaesdm_vs_nxv8i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m4, tu, ma
+; CHECK-NEXT:    vaesdm.vs v8, v12
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i32> @llvm.riscv.vaesdm.vs.nxv8i32(
+    <vscale x 8 x i32> %0,
+    <vscale x 2 x i32> %1,
+    iXLen %2, iXLen 2)
+
+  ret <vscale x 8 x i32> %a
+}
+
+declare <vscale x 16 x i32> @llvm.riscv.vaesdm.vs.nxv16i32(
+  <vscale x 16 x i32>,
+  <vscale x 2 x i32>,
+  iXLen, iXLen);
+
+define <vscale x 16 x i32> @intrinsic_vaesdm_vs_nxv16i32(<vscale x 16 x i32> %0, <vscale x 2 x i32> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vaesdm_vs_nxv16i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m8, tu, ma
+; CHECK-NEXT:    vaesdm.vs v8, v16
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 16 x i32> @llvm.riscv.vaesdm.vs.nxv16i32(
+    <vscale x 16 x i32> %0,
+    <vscale x 2 x i32> %1,
+    iXLen %2, iXLen 2)
+
+  ret <vscale x 16 x i32> %a
+}

llvm/test/CodeGen/RISCV/rvv/vaesef.ll

+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: sed 's/iXLen/i32/g' %s | llc -mtriple=riscv32 -mattr=+v,+experimental-zvkned \
+; RUN:   -verify-machineinstrs | FileCheck %s --check-prefixes=CHECK
+; RUN: sed 's/iXLen/i64/g' %s | llc -mtriple=riscv64 -mattr=+v,+experimental-zvkned \
+; RUN:   -verify-machineinstrs | FileCheck %s --check-prefixes=CHECK
+
+declare <vscale x 1 x i32> @llvm.riscv.vaesef.vv.nxv1i32(
+  <vscale x 1 x i32>,
+  <vscale x 1 x i32>,
+  iXLen, iXLen);
+
+define <vscale x 1 x i32> @intrinsic_vaesef_vv_nxv1i32(<vscale x 1 x i32> %0, <vscale x 1 x i32> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vaesef_vv_nxv1i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, mf2, tu, ma
+; CHECK-NEXT:    vaesef.vv v8, v9
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i32> @llvm.riscv.vaesef.vv.nxv1i32(
+    <vscale x 1 x i32> %0,
+    <vscale x 1 x i32> %1,
+    iXLen %2, iXLen 2)
+
+  ret <vscale x 1 x i32> %a
+}
+
+declare <vscale x 2 x i32> @llvm.riscv.vaesef.vv.nxv2i32(
+  <vscale x 2 x i32>,
+  <vscale x 2 x i32>,
+  iXLen, iXLen);
+
+define <vscale x 2 x i32> @intrinsic_vaesef_vv_nxv2i32(<vscale x 2 x i32> %0, <vscale x 2 x i32> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vaesef_vv_nxv2i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m1, tu, ma
+; CHECK-NEXT:    vaesef.vv v8, v9
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i32> @llvm.riscv.vaesef.vv.nxv2i32(
+    <vscale x 2 x i32> %0,
+    <vscale x 2 x i32> %1,
+    iXLen %2, iXLen 2)
+
+  ret <vscale x 2 x i32> %a
+}
+
+declare <vscale x 4 x i32> @llvm.riscv.vaesef.vv.nxv4i32(
+  <vscale x 4 x i32>,
+  <vscale x 4 x i32>,
+  iXLen, iXLen);
+
+define <vscale x 4 x i32> @intrinsic_vaesef_vv_nxv4i32(<vscale x 4 x i32> %0, <vscale x 4 x i32> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vaesef_vv_nxv4i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m2, tu, ma
+; CHECK-NEXT:    vaesef.vv v8, v10
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i32> @llvm.riscv.vaesef.vv.nxv4i32(
+    <vscale x 4 x i32> %0,
+    <vscale x 4 x i32> %1,
+    iXLen %2, iXLen 2)
+
+  ret <vscale x 4 x i32> %a
+}
+
+declare <vscale x 8 x i32> @llvm.riscv.vaesef.vv.nxv8i32(
+  <vscale x 8 x i32>,
+  <vscale x 8 x i32>,
+  iXLen, iXLen);
+
+define <vscale x 8 x i32> @intrinsic_vaesef_vv_nxv8i32(<vscale x 8 x i32> %0, <vscale x 8 x i32> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vaesef_vv_nxv8i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m4, tu, ma
+; CHECK-NEXT:    vaesef.vv v8, v12
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i32> @llvm.riscv.vaesef.vv.nxv8i32(
+    <vscale x 8 x i32> %0,
+    <vscale x 8 x i32> %1,
+    iXLen %2, iXLen 2)
+
+  ret <vscale x 8 x i32> %a
+}
+
+declare <vscale x 16 x i32> @llvm.riscv.vaesef.vv.nxv16i32(
+  <vscale x 16 x i32>,
+  <vscale x 16 x i32>,
+  iXLen, iXLen);
+
+define <vscale x 16 x i32> @intrinsic_vaesef_vv_nxv16i32(<vscale x 16 x i32> %0, <vscale x 16 x i32> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vaesef_vv_nxv16i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m8, tu, ma
+; CHECK-NEXT:    vaesef.vv v8, v16
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 16 x i32> @llvm.riscv.vaesef.vv.nxv16i32(
+    <vscale x 16 x i32> %0,
+    <vscale x 16 x i32> %1,
+    iXLen %2, iXLen 2)
+
+  ret <vscale x 16 x i32> %a
+}
+
+declare <vscale x 1 x i32> @llvm.riscv.vaesef.vs.nxv1i32(
+  <vscale x 1 x i32>,
+  <vscale x 2 x i32>,
+  iXLen, iXLen);
+
+define <vscale x 1 x i32> @intrinsic_vaesef_vs_nxv1i32(<vscale x 1 x i32> %0, <vscale x 2 x i32> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vaesef_vs_nxv1i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, mf2, tu, ma
+; CHECK-NEXT:    vaesef.vs v8, v9
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i32> @llvm.riscv.vaesef.vs.nxv1i32(
+    <vscale x 1 x i32> %0,
+    <vscale x 2 x i32> %1,
+    iXLen %2, iXLen 2)
+
+  ret <vscale x 1 x i32> %a
+}
+
+declare <vscale x 2 x i32> @llvm.riscv.vaesef.vs.nxv2i32(
+  <vscale x 2 x i32>,
+  <vscale x 2 x i32>,
+  iXLen, iXLen);
+
+define <vscale x 2 x i32> @intrinsic_vaesef_vs_nxv2i32(<vscale x 2 x i32> %0, <vscale x 2 x i32> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vaesef_vs_nxv2i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m1, tu, ma
+; CHECK-NEXT:    vaesef.vs v8, v9
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i32> @llvm.riscv.vaesef.vs.nxv2i32(
+    <vscale x 2 x i32> %0,
+    <vscale x 2 x i32> %1,
+    iXLen %2, iXLen 2)
+
+  ret <vscale x 2 x i32> %a
+}
+
+declare <vscale x 4 x i32> @llvm.riscv.vaesef.vs.nxv4i32(
+  <vscale x 4 x i32>,
+  <vscale x 2 x i32>,
+  iXLen, iXLen);
+
+define <vscale x 4 x i32> @intrinsic_vaesef_vs_nxv4i32(<vscale x 4 x i32> %0, <vscale x 2 x i32> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vaesef_vs_nxv4i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m2, tu, ma
+; CHECK-NEXT:    vaesef.vs v8, v10
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i32> @llvm.riscv.vaesef.vs.nxv4i32(
+    <vscale x 4 x i32> %0,
+    <vscale x 2 x i32> %1,
+    iXLen %2, iXLen 2)
+
+  ret <vscale x 4 x i32> %a
+}
+
+declare <vscale x 8 x i32> @llvm.riscv.vaesef.vs.nxv8i32(
+  <vscale x 8 x i32>,
+  <vscale x 2 x i32>,
+  iXLen, iXLen);
+
+define <vscale x 8 x i32> @intrinsic_vaesef_vs_nxv8i32(<vscale x 8 x i32> %0, <vscale x 2 x i32> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vaesef_vs_nxv8i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m4, tu, ma
+; CHECK-NEXT:    vaesef.vs v8, v12
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i32> @llvm.riscv.vaesef.vs.nxv8i32(
+    <vscale x 8 x i32> %0,
+    <vscale x 2 x i32> %1,
+    iXLen %2, iXLen 2)
+
+  ret <vscale x 8 x i32> %a
+}
+
+declare <vscale x 16 x i32> @llvm.riscv.vaesef.vs.nxv16i32(
+  <vscale x 16 x i32>,
+  <vscale x 2 x i32>,
+  iXLen, iXLen);
+
+define <vscale x 16 x i32> @intrinsic_vaesef_vs_nxv16i32(<vscale x 16 x i32> %0, <vscale x 2 x i32> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vaesef_vs_nxv16i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m8, tu, ma
+; CHECK-NEXT:    vaesef.vs v8, v16
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 16 x i32> @llvm.riscv.vaesef.vs.nxv16i32(
+    <vscale x 16 x i32> %0,
+    <vscale x 2 x i32> %1,
+    iXLen %2, iXLen 2)
+
+  ret <vscale x 16 x i32> %a
+}

llvm/test/CodeGen/RISCV/rvv/vaesem.ll

+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: sed 's/iXLen/i32/g' %s | llc -mtriple=riscv32 -mattr=+v,+experimental-zvkned \
+; RUN:   -verify-machineinstrs | FileCheck %s --check-prefixes=CHECK
+; RUN: sed 's/iXLen/i64/g' %s | llc -mtriple=riscv64 -mattr=+v,+experimental-zvkned \
+; RUN:   -verify-machineinstrs | FileCheck %s --check-prefixes=CHECK
+
+declare <vscale x 1 x i32> @llvm.riscv.vaesem.vv.nxv1i32(
+  <vscale x 1 x i32>,
+  <vscale x 1 x i32>,
+  iXLen, iXLen);
+
+define <vscale x 1 x i32> @intrinsic_vaesem_vv_nxv1i32(<vscale x 1 x i32> %0, <vscale x 1 x i32> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vaesem_vv_nxv1i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, mf2, tu, ma
+; CHECK-NEXT:    vaesem.vv v8, v9
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i32> @llvm.riscv.vaesem.vv.nxv1i32(
+    <vscale x 1 x i32> %0,
+    <vscale x 1 x i32> %1,
+    iXLen %2, iXLen 2)
+
+  ret <vscale x 1 x i32> %a
+}
+
+declare <vscale x 2 x i32> @llvm.riscv.vaesem.vv.nxv2i32(
+  <vscale x 2 x i32>,
+  <vscale x 2 x i32>,
+  iXLen, iXLen);
+
+define <vscale x 2 x i32> @intrinsic_vaesem_vv_nxv2i32(<vscale x 2 x i32> %0, <vscale x 2 x i32> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vaesem_vv_nxv2i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m1, tu, ma
+; CHECK-NEXT:    vaesem.vv v8, v9
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i32> @llvm.riscv.vaesem.vv.nxv2i32(
+    <vscale x 2 x i32> %0,
+    <vscale x 2 x i32> %1,
+    iXLen %2, iXLen 2)
+
+  ret <vscale x 2 x i32> %a
+}
+
+declare <vscale x 4 x i32> @llvm.riscv.vaesem.vv.nxv4i32(
+  <vscale x 4 x i32>,
+  <vscale x 4 x i32>,
+  iXLen, iXLen);
+
+define <vscale x 4 x i32> @intrinsic_vaesem_vv_nxv4i32(<vscale x 4 x i32> %0, <vscale x 4 x i32> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vaesem_vv_nxv4i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m2, tu, ma
+; CHECK-NEXT:    vaesem.vv v8, v10
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i32> @llvm.riscv.vaesem.vv.nxv4i32(
+    <vscale x 4 x i32> %0,
+    <vscale x 4 x i32> %1,
+    iXLen %2, iXLen 2)
+
+  ret <vscale x 4 x i32> %a
+}
+
+declare <vscale x 8 x i32> @llvm.riscv.vaesem.vv.nxv8i32(
+  <vscale x 8 x i32>,
+  <vscale x 8 x i32>,
+  iXLen, iXLen);
+
+define <vscale x 8 x i32> @intrinsic_vaesem_vv_nxv8i32(<vscale x 8 x i32> %0, <vscale x 8 x i32> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vaesem_vv_nxv8i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m4, tu, ma
+; CHECK-NEXT:    vaesem.vv v8, v12
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i32> @llvm.riscv.vaesem.vv.nxv8i32(
+    <vscale x 8 x i32> %0,
+    <vscale x 8 x i32> %1,
+    iXLen %2, iXLen 2)
+
+  ret <vscale x 8 x i32> %a
+}
+
+declare <vscale x 16 x i32> @llvm.riscv.vaesem.vv.nxv16i32(
+  <vscale x 16 x i32>,
+  <vscale x 16 x i32>,
+  iXLen, iXLen);
+
+define <vscale x 16 x i32> @intrinsic_vaesem_vv_nxv16i32(<vscale x 16 x i32> %0, <vscale x 16 x i32> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vaesem_vv_nxv16i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m8, tu, ma
+; CHECK-NEXT:    vaesem.vv v8, v16
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 16 x i32> @llvm.riscv.vaesem.vv.nxv16i32(
+    <vscale x 16 x i32> %0,
+    <vscale x 16 x i32> %1,
+    iXLen %2, iXLen 2)
+
+  ret <vscale x 16 x i32> %a
+}
+
+declare <vscale x 1 x i32> @llvm.riscv.vaesem.vs.nxv1i32(
+  <vscale x 1 x i32>,
+  <vscale x 2 x i32>,
+  iXLen, iXLen);
+
+define <vscale x 1 x i32> @intrinsic_vaesem_vs_nxv1i32(<vscale x 1 x i32> %0, <vscale x 2 x i32> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vaesem_vs_nxv1i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, mf2, tu, ma
+; CHECK-NEXT:    vaesem.vs v8, v9
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i32> @llvm.riscv.vaesem.vs.nxv1i32(
+    <vscale x 1 x i32> %0,
+    <vscale x 2 x i32> %1,
+    iXLen %2, iXLen 2)
+
+  ret <vscale x 1 x i32> %a
+}
+
+declare <vscale x 2 x i32> @llvm.riscv.vaesem.vs.nxv2i32(
+  <vscale x 2 x i32>,
+  <vscale x 2 x i32>,
+  iXLen, iXLen);
+
+define <vscale x 2 x i32> @intrinsic_vaesem_vs_nxv2i32(<vscale x 2 x i32> %0, <vscale x 2 x i32> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vaesem_vs_nxv2i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m1, tu, ma
+; CHECK-NEXT:    vaesem.vs v8, v9
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i32> @llvm.riscv.vaesem.vs.nxv2i32(
+    <vscale x 2 x i32> %0,
+    <vscale x 2 x i32> %1,
+    iXLen %2, iXLen 2)
+
+  ret <vscale x 2 x i32> %a
+}
+
+declare <vscale x 4 x i32> @llvm.riscv.vaesem.vs.nxv4i32(
+  <vscale x 4 x i32>,
+  <vscale x 2 x i32>,
+  iXLen, iXLen);
+
+define <vscale x 4 x i32> @intrinsic_vaesem_vs_nxv4i32(<vscale x 4 x i32> %0, <vscale x 2 x i32> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vaesem_vs_nxv4i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m2, tu, ma
+; CHECK-NEXT:    vaesem.vs v8, v10
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i32> @llvm.riscv.vaesem.vs.nxv4i32(
+    <vscale x 4 x i32> %0,
+    <vscale x 2 x i32> %1,
+    iXLen %2, iXLen 2)
+
+  ret <vscale x 4 x i32> %a
+}
+
+declare <vscale x 8 x i32> @llvm.riscv.vaesem.vs.nxv8i32(
+  <vscale x 8 x i32>,
+  <vscale x 2 x i32>,
+  iXLen, iXLen);
+
+define <vscale x 8 x i32> @intrinsic_vaesem_vs_nxv8i32(<vscale x 8 x i32> %0, <vscale x 2 x i32> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vaesem_vs_nxv8i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m4, tu, ma
+; CHECK-NEXT:    vaesem.vs v8, v12
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i32> @llvm.riscv.vaesem.vs.nxv8i32(
+    <vscale x 8 x i32> %0,
+    <vscale x 2 x i32> %1,
+    iXLen %2, iXLen 2)
+
+  ret <vscale x 8 x i32> %a
+}
+
+declare <vscale x 16 x i32> @llvm.riscv.vaesem.vs.nxv16i32(
+  <vscale x 16 x i32>,
+  <vscale x 2 x i32>,
+  iXLen, iXLen);
+
+define <vscale x 16 x i32> @intrinsic_vaesem_vs_nxv16i32(<vscale x 16 x i32> %0, <vscale x 2 x i32> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vaesem_vs_nxv16i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m8, tu, ma
+; CHECK-NEXT:    vaesem.vs v8, v16
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 16 x i32> @llvm.riscv.vaesem.vs.nxv16i32(
+    <vscale x 16 x i32> %0,
+    <vscale x 2 x i32> %1,
+    iXLen %2, iXLen 2)
+
+  ret <vscale x 16 x i32> %a
+}

llvm/test/CodeGen/RISCV/rvv/vaeskf1.ll

+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: sed 's/iXLen/i32/g' %s | llc -mtriple=riscv32 -mattr=+v,+experimental-zvkned \
+; RUN:   -verify-machineinstrs | FileCheck %s --check-prefixes=CHECK
+; RUN: sed 's/iXLen/i64/g' %s | llc -mtriple=riscv64 -mattr=+v,+experimental-zvkned \
+; RUN:   -verify-machineinstrs | FileCheck %s --check-prefixes=CHECK
+
+declare <vscale x 1 x i32> @llvm.riscv.vaeskf1.nxv1i32.i32(
+  <vscale x 1 x i32>,
+  <vscale x 1 x i32>,
+  i32,
+  iXLen)
+
+define <vscale x 1 x i32> @intrinsic_vaeskf1_vi_nxv1i32_i32(<vscale x 1 x i32> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vaeskf1_vi_nxv1i32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m1, ta, ma
+; CHECK-NEXT:    vaeskf1.vi v8, v8, 2
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i32> @llvm.riscv.vaeskf1.nxv1i32.i32(
+    <vscale x 1 x i32> undef,
+    <vscale x 1 x i32> %0,
+    i32 2,
+    iXLen %1)
+
+  ret <vscale x 1 x i32> %a
+}
+
+declare <vscale x 2 x i32> @llvm.riscv.vaeskf1.nxv2i32.i32(
+  <vscale x 2 x i32>,
+  <vscale x 2 x i32>,
+  i32,
+  iXLen)
+
+define <vscale x 2 x i32> @intrinsic_vaeskf1_vi_nxv2i32_i32(<vscale x 2 x i32> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vaeskf1_vi_nxv2i32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m1, ta, ma
+; CHECK-NEXT:    vaeskf1.vi v8, v8, 2
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i32> @llvm.riscv.vaeskf1.nxv2i32.i32(
+    <vscale x 2 x i32> undef,
+    <vscale x 2 x i32> %0,
+    i32 2,
+    iXLen %1)
+
+  ret <vscale x 2 x i32> %a
+}
+
+declare <vscale x 4 x i32> @llvm.riscv.vaeskf1.nxv4i32.i32(
+  <vscale x 4 x i32>,
+  <vscale x 4 x i32>,
+  i32,
+  iXLen)
+
+define <vscale x 4 x i32> @intrinsic_vaeskf1_vi_nxv4i32_i32(<vscale x 4 x i32> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vaeskf1_vi_nxv4i32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m1, ta, ma
+; CHECK-NEXT:    vaeskf1.vi v8, v8, 2
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i32> @llvm.riscv.vaeskf1.nxv4i32.i32(
+    <vscale x 4 x i32> undef,
+    <vscale x 4 x i32> %0,
+    i32 2,
+    iXLen %1)
+
+  ret <vscale x 4 x i32> %a
+}
+
+declare <vscale x 8 x i32> @llvm.riscv.vaeskf1.nxv8i32.i32(
+  <vscale x 8 x i32>,
+  <vscale x 8 x i32>,
+  i32,
+  iXLen)
+
+define <vscale x 8 x i32> @intrinsic_vaeskf1_vi_nxv8i32_i32(<vscale x 8 x i32> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vaeskf1_vi_nxv8i32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m1, ta, ma
+; CHECK-NEXT:    vaeskf1.vi v8, v8, 2
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i32> @llvm.riscv.vaeskf1.nxv8i32.i32(
+    <vscale x 8 x i32> undef,
+    <vscale x 8 x i32> %0,
+    i32 2,
+    iXLen %1)
+
+  ret <vscale x 8 x i32> %a
+}
+
+declare <vscale x 16 x i32> @llvm.riscv.vaeskf1.nxv16i32.i32(
+  <vscale x 16 x i32>,
+  <vscale x 16 x i32>,
+  i32,
+  iXLen)
+
+define <vscale x 16 x i32> @intrinsic_vaeskf1_vi_nxv16i32_i32(<vscale x 16 x i32> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vaeskf1_vi_nxv16i32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m1, ta, ma
+; CHECK-NEXT:    vaeskf1.vi v8, v8, 2
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 16 x i32> @llvm.riscv.vaeskf1.nxv16i32.i32(
+    <vscale x 16 x i32> undef,
+    <vscale x 16 x i32> %0,
+    i32 2,
+    iXLen %1)
+
+  ret <vscale x 16 x i32> %a
+}

llvm/test/CodeGen/RISCV/rvv/vaeskf2.ll

+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: sed 's/iXLen/i32/g' %s | llc -mtriple=riscv32 -mattr=+v,+experimental-zvkned \
+; RUN:   -verify-machineinstrs | FileCheck %s --check-prefixes=CHECK
+; RUN: sed 's/iXLen/i64/g' %s | llc -mtriple=riscv64 -mattr=+v,+experimental-zvkned \
+; RUN:   -verify-machineinstrs | FileCheck %s --check-prefixes=CHECK
+
+declare <vscale x 1 x i32> @llvm.riscv.vaeskf2.nxv1i32.i32(
+  <vscale x 1 x i32>,
+  <vscale x 1 x i32>,
+  i32,
+  iXLen,
+  iXLen)
+
+define <vscale x 1 x i32> @intrinsic_vaeskf2_vi_nxv1i32_i32(<vscale x 1 x i32> %0, <vscale x 1 x i32> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vaeskf2_vi_nxv1i32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, mf2, tu, ma
+; CHECK-NEXT:    vaeskf2.vi v8, v9, 2
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i32> @llvm.riscv.vaeskf2.nxv1i32.i32(
+    <vscale x 1 x i32> %0,
+    <vscale x 1 x i32> %1,
+    i32 2,
+    iXLen %2,
+    iXLen 2)
+
+  ret <vscale x 1 x i32> %a
+}
+
+declare <vscale x 2 x i32> @llvm.riscv.vaeskf2.nxv2i32.i32(
+  <vscale x 2 x i32>,
+  <vscale x 2 x i32>,
+  i32,
+  iXLen,
+  iXLen)
+
+define <vscale x 2 x i32> @intrinsic_vaeskf2_vi_nxv2i32_i32(<vscale x 2 x i32> %0, <vscale x 2 x i32> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vaeskf2_vi_nxv2i32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m1, tu, ma
+; CHECK-NEXT:    vaeskf2.vi v8, v9, 2
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i32> @llvm.riscv.vaeskf2.nxv2i32.i32(
+    <vscale x 2 x i32> %0,
+    <vscale x 2 x i32> %1,
+    i32 2,
+    iXLen %2,
+    iXLen 2)
+
+  ret <vscale x 2 x i32> %a
+}
+
+declare <vscale x 4 x i32> @llvm.riscv.vaeskf2.nxv4i32.i32(
+  <vscale x 4 x i32>,
+  <vscale x 4 x i32>,
+  i32,
+  iXLen,
+  iXLen)
+
+define <vscale x 4 x i32> @intrinsic_vaeskf2_vi_nxv4i32_i32(<vscale x 4 x i32> %0, <vscale x 4 x i32> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vaeskf2_vi_nxv4i32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m2, tu, ma
+; CHECK-NEXT:    vaeskf2.vi v8, v10, 2
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i32> @llvm.riscv.vaeskf2.nxv4i32.i32(
+    <vscale x 4 x i32> %0,
+    <vscale x 4 x i32> %1,
+    i32 2,
+    iXLen %2,
+    iXLen 2)
+
+  ret <vscale x 4 x i32> %a
+}
+
+declare <vscale x 8 x i32> @llvm.riscv.vaeskf2.nxv8i32.i32(
+  <vscale x 8 x i32>,
+  <vscale x 8 x i32>,
+  i32,
+  iXLen,
+  iXLen)
+
+define <vscale x 8 x i32> @intrinsic_vaeskf2_vi_nxv8i32_i32(<vscale x 8 x i32> %0, <vscale x 8 x i32> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vaeskf2_vi_nxv8i32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m4, tu, ma
+; CHECK-NEXT:    vaeskf2.vi v8, v12, 2
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i32> @llvm.riscv.vaeskf2.nxv8i32.i32(
+    <vscale x 8 x i32> %0,
+    <vscale x 8 x i32> %1,
+    i32 2,
+    iXLen %2,
+    iXLen 2)
+
+  ret <vscale x 8 x i32> %a
+}
+
+declare <vscale x 16 x i32> @llvm.riscv.vaeskf2.nxv16i32.i32(
+  <vscale x 16 x i32>,
+  <vscale x 16 x i32>,
+  i32,
+  iXLen,
+  iXLen)
+
+define <vscale x 16 x i32> @intrinsic_vaeskf2_vi_nxv16i32_i32(<vscale x 16 x i32> %0, <vscale x 16 x i32> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vaeskf2_vi_nxv16i32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m8, tu, ma
+; CHECK-NEXT:    vaeskf2.vi v8, v16, 2
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 16 x i32> @llvm.riscv.vaeskf2.nxv16i32.i32(
+    <vscale x 16 x i32> %0,
+    <vscale x 16 x i32> %1,
+    i32 2,
+    iXLen %2,
+    iXLen 2)
+
+  ret <vscale x 16 x i32> %a
+}

llvm/test/CodeGen/RISCV/rvv/vaesz.ll

+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: sed 's/iXLen/i32/g' %s | llc -mtriple=riscv32 -mattr=+v,+experimental-zvkned \
+; RUN:   -verify-machineinstrs | FileCheck %s --check-prefixes=CHECK
+; RUN: sed 's/iXLen/i64/g' %s | llc -mtriple=riscv64 -mattr=+v,+experimental-zvkned \
+; RUN:   -verify-machineinstrs | FileCheck %s --check-prefixes=CHECK
+
+declare <vscale x 1 x i32> @llvm.riscv.vaesz.vs.nxv1i32(
+  <vscale x 1 x i32>,
+  <vscale x 2 x i32>,
+  iXLen, iXLen);
+
+define <vscale x 1 x i32> @intrinsic_vaesz_vs_nxv1i32(<vscale x 1 x i32> %0, <vscale x 2 x i32> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vaesz_vs_nxv1i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, mf2, tu, ma
+; CHECK-NEXT:    vaesz.vs v8, v9
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i32> @llvm.riscv.vaesz.vs.nxv1i32(
+    <vscale x 1 x i32> %0,
+    <vscale x 2 x i32> %1,
+    iXLen %2, iXLen 2)
+
+  ret <vscale x 1 x i32> %a
+}
+
+declare <vscale x 2 x i32> @llvm.riscv.vaesz.vs.nxv2i32(
+  <vscale x 2 x i32>,
+  <vscale x 2 x i32>,
+  iXLen, iXLen);
+
+define <vscale x 2 x i32> @intrinsic_vaesz_vs_nxv2i32(<vscale x 2 x i32> %0, <vscale x 2 x i32> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vaesz_vs_nxv2i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m1, tu, ma
+; CHECK-NEXT:    vaesz.vs v8, v9
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i32> @llvm.riscv.vaesz.vs.nxv2i32(
+    <vscale x 2 x i32> %0,
+    <vscale x 2 x i32> %1,
+    iXLen %2, iXLen 2)
+
+  ret <vscale x 2 x i32> %a
+}
+
+declare <vscale x 4 x i32> @llvm.riscv.vaesz.vs.nxv4i32(
+  <vscale x 4 x i32>,
+  <vscale x 2 x i32>,
+  iXLen, iXLen);
+
+define <vscale x 4 x i32> @intrinsic_vaesz_vs_nxv4i32(<vscale x 4 x i32> %0, <vscale x 2 x i32> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vaesz_vs_nxv4i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m2, tu, ma
+; CHECK-NEXT:    vaesz.vs v8, v10
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i32> @llvm.riscv.vaesz.vs.nxv4i32(
+    <vscale x 4 x i32> %0,
+    <vscale x 2 x i32> %1,
+    iXLen %2, iXLen 2)
+
+  ret <vscale x 4 x i32> %a
+}
+
+declare <vscale x 8 x i32> @llvm.riscv.vaesz.vs.nxv8i32(
+  <vscale x 8 x i32>,
+  <vscale x 2 x i32>,
+  iXLen, iXLen);
+
+define <vscale x 8 x i32> @intrinsic_vaesz_vs_nxv8i32(<vscale x 8 x i32> %0, <vscale x 2 x i32> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vaesz_vs_nxv8i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m4, tu, ma
+; CHECK-NEXT:    vaesz.vs v8, v12
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i32> @llvm.riscv.vaesz.vs.nxv8i32(
+    <vscale x 8 x i32> %0,
+    <vscale x 2 x i32> %1,
+    iXLen %2, iXLen 2)
+
+  ret <vscale x 8 x i32> %a
+}
+
+declare <vscale x 16 x i32> @llvm.riscv.vaesz.vs.nxv16i32(
+  <vscale x 16 x i32>,
+  <vscale x 2 x i32>,
+  iXLen, iXLen);
+
+define <vscale x 16 x i32> @intrinsic_vaesz_vs_nxv16i32(<vscale x 16 x i32> %0, <vscale x 2 x i32> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vaesz_vs_nxv16i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m8, tu, ma
+; CHECK-NEXT:    vaesz.vs v8, v16
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 16 x i32> @llvm.riscv.vaesz.vs.nxv16i32(
+    <vscale x 16 x i32> %0,
+    <vscale x 2 x i32> %1,
+    iXLen %2, iXLen 2)
+
+  ret <vscale x 16 x i32> %a
+}

llvm/test/CodeGen/RISCV/rvv/vandn.ll

+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: sed 's/iXLen/i32/g' %s | llc -mtriple=riscv32 -mattr=+v,+experimental-zvbb \
+; RUN:   -verify-machineinstrs | FileCheck %s --check-prefixes=CHECK,RV32
+; RUN: sed 's/iXLen/i64/g' %s | llc -mtriple=riscv64 -mattr=+v,+experimental-zvbb \
+; RUN:   -verify-machineinstrs | FileCheck %s --check-prefixes=CHECK,RV64
+
+declare <vscale x 1 x i8> @llvm.riscv.vandn.nxv1i8.nxv1i8(
+  <vscale x 1 x i8>,
+  <vscale x 1 x i8>,
+  <vscale x 1 x i8>,
+  iXLen)
+
+define <vscale x 1 x i8> @intrinsic_vandn_vv_nxv1i8_nxv1i8(<vscale x 1 x i8> %0, <vscale x 1 x i8> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vandn_vv_nxv1i8_nxv1i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, mf8, ta, ma
+; CHECK-NEXT:    vandn.vv v8, v8, v9
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i8> @llvm.riscv.vandn.nxv1i8.nxv1i8(
+    <vscale x 1 x i8> undef,
+    <vscale x 1 x i8> %0,
+    <vscale x 1 x i8> %1,
+    iXLen %2)
+
+  ret <vscale x 1 x i8> %a
+}
+
+declare <vscale x 1 x i8> @llvm.riscv.vandn.mask.nxv1i8.nxv1i8(
+  <vscale x 1 x i8>,
+  <vscale x 1 x i8>,
+  <vscale x 1 x i8>,
+  <vscale x 1 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 1 x i8> @intrinsic_vandn_mask_vv_nxv1i8_nxv1i8(<vscale x 1 x i8> %0, <vscale x 1 x i8> %1, <vscale x 1 x i8> %2, <vscale x 1 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vandn_mask_vv_nxv1i8_nxv1i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, mf8, ta, mu
+; CHECK-NEXT:    vandn.vv v8, v9, v10, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i8> @llvm.riscv.vandn.mask.nxv1i8.nxv1i8(
+    <vscale x 1 x i8> %0,
+    <vscale x 1 x i8> %1,
+    <vscale x 1 x i8> %2,
+    <vscale x 1 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 1 x i8> %a
+}
+
+declare <vscale x 2 x i8> @llvm.riscv.vandn.nxv2i8.nxv2i8(
+  <vscale x 2 x i8>,
+  <vscale x 2 x i8>,
+  <vscale x 2 x i8>,
+  iXLen)
+
+define <vscale x 2 x i8> @intrinsic_vandn_vv_nxv2i8_nxv2i8(<vscale x 2 x i8> %0, <vscale x 2 x i8> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vandn_vv_nxv2i8_nxv2i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, mf4, ta, ma
+; CHECK-NEXT:    vandn.vv v8, v8, v9
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i8> @llvm.riscv.vandn.nxv2i8.nxv2i8(
+    <vscale x 2 x i8> undef,
+    <vscale x 2 x i8> %0,
+    <vscale x 2 x i8> %1,
+    iXLen %2)
+
+  ret <vscale x 2 x i8> %a
+}
+
+declare <vscale x 2 x i8> @llvm.riscv.vandn.mask.nxv2i8.nxv2i8(
+  <vscale x 2 x i8>,
+  <vscale x 2 x i8>,
+  <vscale x 2 x i8>,
+  <vscale x 2 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 2 x i8> @intrinsic_vandn_mask_vv_nxv2i8_nxv2i8(<vscale x 2 x i8> %0, <vscale x 2 x i8> %1, <vscale x 2 x i8> %2, <vscale x 2 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vandn_mask_vv_nxv2i8_nxv2i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, mf4, ta, mu
+; CHECK-NEXT:    vandn.vv v8, v9, v10, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i8> @llvm.riscv.vandn.mask.nxv2i8.nxv2i8(
+    <vscale x 2 x i8> %0,
+    <vscale x 2 x i8> %1,
+    <vscale x 2 x i8> %2,
+    <vscale x 2 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 2 x i8> %a
+}
+
+declare <vscale x 4 x i8> @llvm.riscv.vandn.nxv4i8.nxv4i8(
+  <vscale x 4 x i8>,
+  <vscale x 4 x i8>,
+  <vscale x 4 x i8>,
+  iXLen)
+
+define <vscale x 4 x i8> @intrinsic_vandn_vv_nxv4i8_nxv4i8(<vscale x 4 x i8> %0, <vscale x 4 x i8> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vandn_vv_nxv4i8_nxv4i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, mf2, ta, ma
+; CHECK-NEXT:    vandn.vv v8, v8, v9
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i8> @llvm.riscv.vandn.nxv4i8.nxv4i8(
+    <vscale x 4 x i8> undef,
+    <vscale x 4 x i8> %0,
+    <vscale x 4 x i8> %1,
+    iXLen %2)
+
+  ret <vscale x 4 x i8> %a
+}
+
+declare <vscale x 4 x i8> @llvm.riscv.vandn.mask.nxv4i8.nxv4i8(
+  <vscale x 4 x i8>,
+  <vscale x 4 x i8>,
+  <vscale x 4 x i8>,
+  <vscale x 4 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 4 x i8> @intrinsic_vandn_mask_vv_nxv4i8_nxv4i8(<vscale x 4 x i8> %0, <vscale x 4 x i8> %1, <vscale x 4 x i8> %2, <vscale x 4 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vandn_mask_vv_nxv4i8_nxv4i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, mf2, ta, mu
+; CHECK-NEXT:    vandn.vv v8, v9, v10, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i8> @llvm.riscv.vandn.mask.nxv4i8.nxv4i8(
+    <vscale x 4 x i8> %0,
+    <vscale x 4 x i8> %1,
+    <vscale x 4 x i8> %2,
+    <vscale x 4 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 4 x i8> %a
+}
+
+declare <vscale x 8 x i8> @llvm.riscv.vandn.nxv8i8.nxv8i8(
+  <vscale x 8 x i8>,
+  <vscale x 8 x i8>,
+  <vscale x 8 x i8>,
+  iXLen)
+
+define <vscale x 8 x i8> @intrinsic_vandn_vv_nxv8i8_nxv8i8(<vscale x 8 x i8> %0, <vscale x 8 x i8> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vandn_vv_nxv8i8_nxv8i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, m1, ta, ma
+; CHECK-NEXT:    vandn.vv v8, v8, v9
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i8> @llvm.riscv.vandn.nxv8i8.nxv8i8(
+    <vscale x 8 x i8> undef,
+    <vscale x 8 x i8> %0,
+    <vscale x 8 x i8> %1,
+    iXLen %2)
+
+  ret <vscale x 8 x i8> %a
+}
+
+declare <vscale x 8 x i8> @llvm.riscv.vandn.mask.nxv8i8.nxv8i8(
+  <vscale x 8 x i8>,
+  <vscale x 8 x i8>,
+  <vscale x 8 x i8>,
+  <vscale x 8 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 8 x i8> @intrinsic_vandn_mask_vv_nxv8i8_nxv8i8(<vscale x 8 x i8> %0, <vscale x 8 x i8> %1, <vscale x 8 x i8> %2, <vscale x 8 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vandn_mask_vv_nxv8i8_nxv8i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, m1, ta, mu
+; CHECK-NEXT:    vandn.vv v8, v9, v10, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i8> @llvm.riscv.vandn.mask.nxv8i8.nxv8i8(
+    <vscale x 8 x i8> %0,
+    <vscale x 8 x i8> %1,
+    <vscale x 8 x i8> %2,
+    <vscale x 8 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 8 x i8> %a
+}
+
+declare <vscale x 16 x i8> @llvm.riscv.vandn.nxv16i8.nxv16i8(
+  <vscale x 16 x i8>,
+  <vscale x 16 x i8>,
+  <vscale x 16 x i8>,
+  iXLen)
+
+define <vscale x 16 x i8> @intrinsic_vandn_vv_nxv16i8_nxv16i8(<vscale x 16 x i8> %0, <vscale x 16 x i8> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vandn_vv_nxv16i8_nxv16i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, m2, ta, ma
+; CHECK-NEXT:    vandn.vv v8, v8, v10
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 16 x i8> @llvm.riscv.vandn.nxv16i8.nxv16i8(
+    <vscale x 16 x i8> undef,
+    <vscale x 16 x i8> %0,
+    <vscale x 16 x i8> %1,
+    iXLen %2)
+
+  ret <vscale x 16 x i8> %a
+}
+
+declare <vscale x 16 x i8> @llvm.riscv.vandn.mask.nxv16i8.nxv16i8(
+  <vscale x 16 x i8>,
+  <vscale x 16 x i8>,
+  <vscale x 16 x i8>,
+  <vscale x 16 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 16 x i8> @intrinsic_vandn_mask_vv_nxv16i8_nxv16i8(<vscale x 16 x i8> %0, <vscale x 16 x i8> %1, <vscale x 16 x i8> %2, <vscale x 16 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vandn_mask_vv_nxv16i8_nxv16i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, m2, ta, mu
+; CHECK-NEXT:    vandn.vv v8, v10, v12, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 16 x i8> @llvm.riscv.vandn.mask.nxv16i8.nxv16i8(
+    <vscale x 16 x i8> %0,
+    <vscale x 16 x i8> %1,
+    <vscale x 16 x i8> %2,
+    <vscale x 16 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 16 x i8> %a
+}
+
+declare <vscale x 32 x i8> @llvm.riscv.vandn.nxv32i8.nxv32i8(
+  <vscale x 32 x i8>,
+  <vscale x 32 x i8>,
+  <vscale x 32 x i8>,
+  iXLen)
+
+define <vscale x 32 x i8> @intrinsic_vandn_vv_nxv32i8_nxv32i8(<vscale x 32 x i8> %0, <vscale x 32 x i8> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vandn_vv_nxv32i8_nxv32i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, m4, ta, ma
+; CHECK-NEXT:    vandn.vv v8, v8, v12
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 32 x i8> @llvm.riscv.vandn.nxv32i8.nxv32i8(
+    <vscale x 32 x i8> undef,
+    <vscale x 32 x i8> %0,
+    <vscale x 32 x i8> %1,
+    iXLen %2)
+
+  ret <vscale x 32 x i8> %a
+}
+
+declare <vscale x 32 x i8> @llvm.riscv.vandn.mask.nxv32i8.nxv32i8(
+  <vscale x 32 x i8>,
+  <vscale x 32 x i8>,
+  <vscale x 32 x i8>,
+  <vscale x 32 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 32 x i8> @intrinsic_vandn_mask_vv_nxv32i8_nxv32i8(<vscale x 32 x i8> %0, <vscale x 32 x i8> %1, <vscale x 32 x i8> %2, <vscale x 32 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vandn_mask_vv_nxv32i8_nxv32i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, m4, ta, mu
+; CHECK-NEXT:    vandn.vv v8, v12, v16, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 32 x i8> @llvm.riscv.vandn.mask.nxv32i8.nxv32i8(
+    <vscale x 32 x i8> %0,
+    <vscale x 32 x i8> %1,
+    <vscale x 32 x i8> %2,
+    <vscale x 32 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 32 x i8> %a
+}
+
+declare <vscale x 64 x i8> @llvm.riscv.vandn.nxv64i8.nxv64i8(
+  <vscale x 64 x i8>,
+  <vscale x 64 x i8>,
+  <vscale x 64 x i8>,
+  iXLen)
+
+define <vscale x 64 x i8> @intrinsic_vandn_vv_nxv64i8_nxv64i8(<vscale x 64 x i8> %0, <vscale x 64 x i8> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vandn_vv_nxv64i8_nxv64i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, m8, ta, ma
+; CHECK-NEXT:    vandn.vv v8, v8, v16
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 64 x i8> @llvm.riscv.vandn.nxv64i8.nxv64i8(
+    <vscale x 64 x i8> undef,
+    <vscale x 64 x i8> %0,
+    <vscale x 64 x i8> %1,
+    iXLen %2)
+
+  ret <vscale x 64 x i8> %a
+}
+
+declare <vscale x 64 x i8> @llvm.riscv.vandn.mask.nxv64i8.nxv64i8(
+  <vscale x 64 x i8>,
+  <vscale x 64 x i8>,
+  <vscale x 64 x i8>,
+  <vscale x 64 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 64 x i8> @intrinsic_vandn_mask_vv_nxv64i8_nxv64i8(<vscale x 64 x i8> %0, <vscale x 64 x i8> %1, <vscale x 64 x i8> %2, <vscale x 64 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vandn_mask_vv_nxv64i8_nxv64i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vl8r.v v24, (a0)
+; CHECK-NEXT:    vsetvli zero, a1, e8, m8, ta, mu
+; CHECK-NEXT:    vandn.vv v8, v16, v24, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 64 x i8> @llvm.riscv.vandn.mask.nxv64i8.nxv64i8(
+    <vscale x 64 x i8> %0,
+    <vscale x 64 x i8> %1,
+    <vscale x 64 x i8> %2,
+    <vscale x 64 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 64 x i8> %a
+}
+
+declare <vscale x 1 x i16> @llvm.riscv.vandn.nxv1i16.nxv1i16(
+  <vscale x 1 x i16>,
+  <vscale x 1 x i16>,
+  <vscale x 1 x i16>,
+  iXLen)
+
+define <vscale x 1 x i16> @intrinsic_vandn_vv_nxv1i16_nxv1i16(<vscale x 1 x i16> %0, <vscale x 1 x i16> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vandn_vv_nxv1i16_nxv1i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, mf4, ta, ma
+; CHECK-NEXT:    vandn.vv v8, v8, v9
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i16> @llvm.riscv.vandn.nxv1i16.nxv1i16(
+    <vscale x 1 x i16> undef,
+    <vscale x 1 x i16> %0,
+    <vscale x 1 x i16> %1,
+    iXLen %2)
+
+  ret <vscale x 1 x i16> %a
+}
+
+declare <vscale x 1 x i16> @llvm.riscv.vandn.mask.nxv1i16.nxv1i16(
+  <vscale x 1 x i16>,
+  <vscale x 1 x i16>,
+  <vscale x 1 x i16>,
+  <vscale x 1 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 1 x i16> @intrinsic_vandn_mask_vv_nxv1i16_nxv1i16(<vscale x 1 x i16> %0, <vscale x 1 x i16> %1, <vscale x 1 x i16> %2, <vscale x 1 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vandn_mask_vv_nxv1i16_nxv1i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, mf4, ta, mu
+; CHECK-NEXT:    vandn.vv v8, v9, v10, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i16> @llvm.riscv.vandn.mask.nxv1i16.nxv1i16(
+    <vscale x 1 x i16> %0,
+    <vscale x 1 x i16> %1,
+    <vscale x 1 x i16> %2,
+    <vscale x 1 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 1 x i16> %a
+}
+
+declare <vscale x 2 x i16> @llvm.riscv.vandn.nxv2i16.nxv2i16(
+  <vscale x 2 x i16>,
+  <vscale x 2 x i16>,
+  <vscale x 2 x i16>,
+  iXLen)
+
+define <vscale x 2 x i16> @intrinsic_vandn_vv_nxv2i16_nxv2i16(<vscale x 2 x i16> %0, <vscale x 2 x i16> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vandn_vv_nxv2i16_nxv2i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, mf2, ta, ma
+; CHECK-NEXT:    vandn.vv v8, v8, v9
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i16> @llvm.riscv.vandn.nxv2i16.nxv2i16(
+    <vscale x 2 x i16> undef,
+    <vscale x 2 x i16> %0,
+    <vscale x 2 x i16> %1,
+    iXLen %2)
+
+  ret <vscale x 2 x i16> %a
+}
+
+declare <vscale x 2 x i16> @llvm.riscv.vandn.mask.nxv2i16.nxv2i16(
+  <vscale x 2 x i16>,
+  <vscale x 2 x i16>,
+  <vscale x 2 x i16>,
+  <vscale x 2 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 2 x i16> @intrinsic_vandn_mask_vv_nxv2i16_nxv2i16(<vscale x 2 x i16> %0, <vscale x 2 x i16> %1, <vscale x 2 x i16> %2, <vscale x 2 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vandn_mask_vv_nxv2i16_nxv2i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, mf2, ta, mu
+; CHECK-NEXT:    vandn.vv v8, v9, v10, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i16> @llvm.riscv.vandn.mask.nxv2i16.nxv2i16(
+    <vscale x 2 x i16> %0,
+    <vscale x 2 x i16> %1,
+    <vscale x 2 x i16> %2,
+    <vscale x 2 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 2 x i16> %a
+}
+
+declare <vscale x 4 x i16> @llvm.riscv.vandn.nxv4i16.nxv4i16(
+  <vscale x 4 x i16>,
+  <vscale x 4 x i16>,
+  <vscale x 4 x i16>,
+  iXLen)
+
+define <vscale x 4 x i16> @intrinsic_vandn_vv_nxv4i16_nxv4i16(<vscale x 4 x i16> %0, <vscale x 4 x i16> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vandn_vv_nxv4i16_nxv4i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, m1, ta, ma
+; CHECK-NEXT:    vandn.vv v8, v8, v9
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i16> @llvm.riscv.vandn.nxv4i16.nxv4i16(
+    <vscale x 4 x i16> undef,
+    <vscale x 4 x i16> %0,
+    <vscale x 4 x i16> %1,
+    iXLen %2)
+
+  ret <vscale x 4 x i16> %a
+}
+
+declare <vscale x 4 x i16> @llvm.riscv.vandn.mask.nxv4i16.nxv4i16(
+  <vscale x 4 x i16>,
+  <vscale x 4 x i16>,
+  <vscale x 4 x i16>,
+  <vscale x 4 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 4 x i16> @intrinsic_vandn_mask_vv_nxv4i16_nxv4i16(<vscale x 4 x i16> %0, <vscale x 4 x i16> %1, <vscale x 4 x i16> %2, <vscale x 4 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vandn_mask_vv_nxv4i16_nxv4i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, m1, ta, mu
+; CHECK-NEXT:    vandn.vv v8, v9, v10, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i16> @llvm.riscv.vandn.mask.nxv4i16.nxv4i16(
+    <vscale x 4 x i16> %0,
+    <vscale x 4 x i16> %1,
+    <vscale x 4 x i16> %2,
+    <vscale x 4 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 4 x i16> %a
+}
+
+declare <vscale x 8 x i16> @llvm.riscv.vandn.nxv8i16.nxv8i16(
+  <vscale x 8 x i16>,
+  <vscale x 8 x i16>,
+  <vscale x 8 x i16>,
+  iXLen)
+
+define <vscale x 8 x i16> @intrinsic_vandn_vv_nxv8i16_nxv8i16(<vscale x 8 x i16> %0, <vscale x 8 x i16> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vandn_vv_nxv8i16_nxv8i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, m2, ta, ma
+; CHECK-NEXT:    vandn.vv v8, v8, v10
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i16> @llvm.riscv.vandn.nxv8i16.nxv8i16(
+    <vscale x 8 x i16> undef,
+    <vscale x 8 x i16> %0,
+    <vscale x 8 x i16> %1,
+    iXLen %2)
+
+  ret <vscale x 8 x i16> %a
+}
+
+declare <vscale x 8 x i16> @llvm.riscv.vandn.mask.nxv8i16.nxv8i16(
+  <vscale x 8 x i16>,
+  <vscale x 8 x i16>,
+  <vscale x 8 x i16>,
+  <vscale x 8 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 8 x i16> @intrinsic_vandn_mask_vv_nxv8i16_nxv8i16(<vscale x 8 x i16> %0, <vscale x 8 x i16> %1, <vscale x 8 x i16> %2, <vscale x 8 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vandn_mask_vv_nxv8i16_nxv8i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, m2, ta, mu
+; CHECK-NEXT:    vandn.vv v8, v10, v12, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i16> @llvm.riscv.vandn.mask.nxv8i16.nxv8i16(
+    <vscale x 8 x i16> %0,
+    <vscale x 8 x i16> %1,
+    <vscale x 8 x i16> %2,
+    <vscale x 8 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 8 x i16> %a
+}
+
+declare <vscale x 16 x i16> @llvm.riscv.vandn.nxv16i16.nxv16i16(
+  <vscale x 16 x i16>,
+  <vscale x 16 x i16>,
+  <vscale x 16 x i16>,
+  iXLen)
+
+define <vscale x 16 x i16> @intrinsic_vandn_vv_nxv16i16_nxv16i16(<vscale x 16 x i16> %0, <vscale x 16 x i16> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vandn_vv_nxv16i16_nxv16i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, m4, ta, ma
+; CHECK-NEXT:    vandn.vv v8, v8, v12
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 16 x i16> @llvm.riscv.vandn.nxv16i16.nxv16i16(
+    <vscale x 16 x i16> undef,
+    <vscale x 16 x i16> %0,
+    <vscale x 16 x i16> %1,
+    iXLen %2)
+
+  ret <vscale x 16 x i16> %a
+}
+
+declare <vscale x 16 x i16> @llvm.riscv.vandn.mask.nxv16i16.nxv16i16(
+  <vscale x 16 x i16>,
+  <vscale x 16 x i16>,
+  <vscale x 16 x i16>,
+  <vscale x 16 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 16 x i16> @intrinsic_vandn_mask_vv_nxv16i16_nxv16i16(<vscale x 16 x i16> %0, <vscale x 16 x i16> %1, <vscale x 16 x i16> %2, <vscale x 16 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vandn_mask_vv_nxv16i16_nxv16i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, m4, ta, mu
+; CHECK-NEXT:    vandn.vv v8, v12, v16, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 16 x i16> @llvm.riscv.vandn.mask.nxv16i16.nxv16i16(
+    <vscale x 16 x i16> %0,
+    <vscale x 16 x i16> %1,
+    <vscale x 16 x i16> %2,
+    <vscale x 16 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 16 x i16> %a
+}
+
+declare <vscale x 32 x i16> @llvm.riscv.vandn.nxv32i16.nxv32i16(
+  <vscale x 32 x i16>,
+  <vscale x 32 x i16>,
+  <vscale x 32 x i16>,
+  iXLen)
+
+define <vscale x 32 x i16> @intrinsic_vandn_vv_nxv32i16_nxv32i16(<vscale x 32 x i16> %0, <vscale x 32 x i16> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vandn_vv_nxv32i16_nxv32i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, m8, ta, ma
+; CHECK-NEXT:    vandn.vv v8, v8, v16
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 32 x i16> @llvm.riscv.vandn.nxv32i16.nxv32i16(
+    <vscale x 32 x i16> undef,
+    <vscale x 32 x i16> %0,
+    <vscale x 32 x i16> %1,
+    iXLen %2)
+
+  ret <vscale x 32 x i16> %a
+}
+
+declare <vscale x 32 x i16> @llvm.riscv.vandn.mask.nxv32i16.nxv32i16(
+  <vscale x 32 x i16>,
+  <vscale x 32 x i16>,
+  <vscale x 32 x i16>,
+  <vscale x 32 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 32 x i16> @intrinsic_vandn_mask_vv_nxv32i16_nxv32i16(<vscale x 32 x i16> %0, <vscale x 32 x i16> %1, <vscale x 32 x i16> %2, <vscale x 32 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vandn_mask_vv_nxv32i16_nxv32i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vl8re16.v v24, (a0)
+; CHECK-NEXT:    vsetvli zero, a1, e16, m8, ta, mu
+; CHECK-NEXT:    vandn.vv v8, v16, v24, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 32 x i16> @llvm.riscv.vandn.mask.nxv32i16.nxv32i16(
+    <vscale x 32 x i16> %0,
+    <vscale x 32 x i16> %1,
+    <vscale x 32 x i16> %2,
+    <vscale x 32 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 32 x i16> %a
+}
+
+declare <vscale x 1 x i32> @llvm.riscv.vandn.nxv1i32.nxv1i32(
+  <vscale x 1 x i32>,
+  <vscale x 1 x i32>,
+  <vscale x 1 x i32>,
+  iXLen)
+
+define <vscale x 1 x i32> @intrinsic_vandn_vv_nxv1i32_nxv1i32(<vscale x 1 x i32> %0, <vscale x 1 x i32> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vandn_vv_nxv1i32_nxv1i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, mf2, ta, ma
+; CHECK-NEXT:    vandn.vv v8, v8, v9
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i32> @llvm.riscv.vandn.nxv1i32.nxv1i32(
+    <vscale x 1 x i32> undef,
+    <vscale x 1 x i32> %0,
+    <vscale x 1 x i32> %1,
+    iXLen %2)
+
+  ret <vscale x 1 x i32> %a
+}
+
+declare <vscale x 1 x i32> @llvm.riscv.vandn.mask.nxv1i32.nxv1i32(
+  <vscale x 1 x i32>,
+  <vscale x 1 x i32>,
+  <vscale x 1 x i32>,
+  <vscale x 1 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 1 x i32> @intrinsic_vandn_mask_vv_nxv1i32_nxv1i32(<vscale x 1 x i32> %0, <vscale x 1 x i32> %1, <vscale x 1 x i32> %2, <vscale x 1 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vandn_mask_vv_nxv1i32_nxv1i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, mf2, ta, mu
+; CHECK-NEXT:    vandn.vv v8, v9, v10, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i32> @llvm.riscv.vandn.mask.nxv1i32.nxv1i32(
+    <vscale x 1 x i32> %0,
+    <vscale x 1 x i32> %1,
+    <vscale x 1 x i32> %2,
+    <vscale x 1 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 1 x i32> %a
+}
+
+declare <vscale x 2 x i32> @llvm.riscv.vandn.nxv2i32.nxv2i32(
+  <vscale x 2 x i32>,
+  <vscale x 2 x i32>,
+  <vscale x 2 x i32>,
+  iXLen)
+
+define <vscale x 2 x i32> @intrinsic_vandn_vv_nxv2i32_nxv2i32(<vscale x 2 x i32> %0, <vscale x 2 x i32> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vandn_vv_nxv2i32_nxv2i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m1, ta, ma
+; CHECK-NEXT:    vandn.vv v8, v8, v9
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i32> @llvm.riscv.vandn.nxv2i32.nxv2i32(
+    <vscale x 2 x i32> undef,
+    <vscale x 2 x i32> %0,
+    <vscale x 2 x i32> %1,
+    iXLen %2)
+
+  ret <vscale x 2 x i32> %a
+}
+
+declare <vscale x 2 x i32> @llvm.riscv.vandn.mask.nxv2i32.nxv2i32(
+  <vscale x 2 x i32>,
+  <vscale x 2 x i32>,
+  <vscale x 2 x i32>,
+  <vscale x 2 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 2 x i32> @intrinsic_vandn_mask_vv_nxv2i32_nxv2i32(<vscale x 2 x i32> %0, <vscale x 2 x i32> %1, <vscale x 2 x i32> %2, <vscale x 2 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vandn_mask_vv_nxv2i32_nxv2i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m1, ta, mu
+; CHECK-NEXT:    vandn.vv v8, v9, v10, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i32> @llvm.riscv.vandn.mask.nxv2i32.nxv2i32(
+    <vscale x 2 x i32> %0,
+    <vscale x 2 x i32> %1,
+    <vscale x 2 x i32> %2,
+    <vscale x 2 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 2 x i32> %a
+}
+
+declare <vscale x 4 x i32> @llvm.riscv.vandn.nxv4i32.nxv4i32(
+  <vscale x 4 x i32>,
+  <vscale x 4 x i32>,
+  <vscale x 4 x i32>,
+  iXLen)
+
+define <vscale x 4 x i32> @intrinsic_vandn_vv_nxv4i32_nxv4i32(<vscale x 4 x i32> %0, <vscale x 4 x i32> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vandn_vv_nxv4i32_nxv4i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m2, ta, ma
+; CHECK-NEXT:    vandn.vv v8, v8, v10
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i32> @llvm.riscv.vandn.nxv4i32.nxv4i32(
+    <vscale x 4 x i32> undef,
+    <vscale x 4 x i32> %0,
+    <vscale x 4 x i32> %1,
+    iXLen %2)
+
+  ret <vscale x 4 x i32> %a
+}
+
+declare <vscale x 4 x i32> @llvm.riscv.vandn.mask.nxv4i32.nxv4i32(
+  <vscale x 4 x i32>,
+  <vscale x 4 x i32>,
+  <vscale x 4 x i32>,
+  <vscale x 4 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 4 x i32> @intrinsic_vandn_mask_vv_nxv4i32_nxv4i32(<vscale x 4 x i32> %0, <vscale x 4 x i32> %1, <vscale x 4 x i32> %2, <vscale x 4 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vandn_mask_vv_nxv4i32_nxv4i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m2, ta, mu
+; CHECK-NEXT:    vandn.vv v8, v10, v12, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i32> @llvm.riscv.vandn.mask.nxv4i32.nxv4i32(
+    <vscale x 4 x i32> %0,
+    <vscale x 4 x i32> %1,
+    <vscale x 4 x i32> %2,
+    <vscale x 4 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 4 x i32> %a
+}
+
+declare <vscale x 8 x i32> @llvm.riscv.vandn.nxv8i32.nxv8i32(
+  <vscale x 8 x i32>,
+  <vscale x 8 x i32>,
+  <vscale x 8 x i32>,
+  iXLen)
+
+define <vscale x 8 x i32> @intrinsic_vandn_vv_nxv8i32_nxv8i32(<vscale x 8 x i32> %0, <vscale x 8 x i32> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vandn_vv_nxv8i32_nxv8i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m4, ta, ma
+; CHECK-NEXT:    vandn.vv v8, v8, v12
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i32> @llvm.riscv.vandn.nxv8i32.nxv8i32(
+    <vscale x 8 x i32> undef,
+    <vscale x 8 x i32> %0,
+    <vscale x 8 x i32> %1,
+    iXLen %2)
+
+  ret <vscale x 8 x i32> %a
+}
+
+declare <vscale x 8 x i32> @llvm.riscv.vandn.mask.nxv8i32.nxv8i32(
+  <vscale x 8 x i32>,
+  <vscale x 8 x i32>,
+  <vscale x 8 x i32>,
+  <vscale x 8 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 8 x i32> @intrinsic_vandn_mask_vv_nxv8i32_nxv8i32(<vscale x 8 x i32> %0, <vscale x 8 x i32> %1, <vscale x 8 x i32> %2, <vscale x 8 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vandn_mask_vv_nxv8i32_nxv8i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m4, ta, mu
+; CHECK-NEXT:    vandn.vv v8, v12, v16, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i32> @llvm.riscv.vandn.mask.nxv8i32.nxv8i32(
+    <vscale x 8 x i32> %0,
+    <vscale x 8 x i32> %1,
+    <vscale x 8 x i32> %2,
+    <vscale x 8 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 8 x i32> %a
+}
+
+declare <vscale x 16 x i32> @llvm.riscv.vandn.nxv16i32.nxv16i32(
+  <vscale x 16 x i32>,
+  <vscale x 16 x i32>,
+  <vscale x 16 x i32>,
+  iXLen)
+
+define <vscale x 16 x i32> @intrinsic_vandn_vv_nxv16i32_nxv16i32(<vscale x 16 x i32> %0, <vscale x 16 x i32> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vandn_vv_nxv16i32_nxv16i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m8, ta, ma
+; CHECK-NEXT:    vandn.vv v8, v8, v16
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 16 x i32> @llvm.riscv.vandn.nxv16i32.nxv16i32(
+    <vscale x 16 x i32> undef,
+    <vscale x 16 x i32> %0,
+    <vscale x 16 x i32> %1,
+    iXLen %2)
+
+  ret <vscale x 16 x i32> %a
+}
+
+declare <vscale x 16 x i32> @llvm.riscv.vandn.mask.nxv16i32.nxv16i32(
+  <vscale x 16 x i32>,
+  <vscale x 16 x i32>,
+  <vscale x 16 x i32>,
+  <vscale x 16 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 16 x i32> @intrinsic_vandn_mask_vv_nxv16i32_nxv16i32(<vscale x 16 x i32> %0, <vscale x 16 x i32> %1, <vscale x 16 x i32> %2, <vscale x 16 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vandn_mask_vv_nxv16i32_nxv16i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vl8re32.v v24, (a0)
+; CHECK-NEXT:    vsetvli zero, a1, e32, m8, ta, mu
+; CHECK-NEXT:    vandn.vv v8, v16, v24, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 16 x i32> @llvm.riscv.vandn.mask.nxv16i32.nxv16i32(
+    <vscale x 16 x i32> %0,
+    <vscale x 16 x i32> %1,
+    <vscale x 16 x i32> %2,
+    <vscale x 16 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 16 x i32> %a
+}
+
+declare <vscale x 1 x i64> @llvm.riscv.vandn.nxv1i64.nxv1i64(
+  <vscale x 1 x i64>,
+  <vscale x 1 x i64>,
+  <vscale x 1 x i64>,
+  iXLen)
+
+define <vscale x 1 x i64> @intrinsic_vandn_vv_nxv1i64_nxv1i64(<vscale x 1 x i64> %0, <vscale x 1 x i64> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vandn_vv_nxv1i64_nxv1i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e64, m1, ta, ma
+; CHECK-NEXT:    vandn.vv v8, v8, v9
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i64> @llvm.riscv.vandn.nxv1i64.nxv1i64(
+    <vscale x 1 x i64> undef,
+    <vscale x 1 x i64> %0,
+    <vscale x 1 x i64> %1,
+    iXLen %2)
+
+  ret <vscale x 1 x i64> %a
+}
+
+declare <vscale x 1 x i64> @llvm.riscv.vandn.mask.nxv1i64.nxv1i64(
+  <vscale x 1 x i64>,
+  <vscale x 1 x i64>,
+  <vscale x 1 x i64>,
+  <vscale x 1 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 1 x i64> @intrinsic_vandn_mask_vv_nxv1i64_nxv1i64(<vscale x 1 x i64> %0, <vscale x 1 x i64> %1, <vscale x 1 x i64> %2, <vscale x 1 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vandn_mask_vv_nxv1i64_nxv1i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e64, m1, ta, mu
+; CHECK-NEXT:    vandn.vv v8, v9, v10, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i64> @llvm.riscv.vandn.mask.nxv1i64.nxv1i64(
+    <vscale x 1 x i64> %0,
+    <vscale x 1 x i64> %1,
+    <vscale x 1 x i64> %2,
+    <vscale x 1 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 1 x i64> %a
+}
+
+declare <vscale x 2 x i64> @llvm.riscv.vandn.nxv2i64.nxv2i64(
+  <vscale x 2 x i64>,
+  <vscale x 2 x i64>,
+  <vscale x 2 x i64>,
+  iXLen)
+
+define <vscale x 2 x i64> @intrinsic_vandn_vv_nxv2i64_nxv2i64(<vscale x 2 x i64> %0, <vscale x 2 x i64> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vandn_vv_nxv2i64_nxv2i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e64, m2, ta, ma
+; CHECK-NEXT:    vandn.vv v8, v8, v10
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i64> @llvm.riscv.vandn.nxv2i64.nxv2i64(
+    <vscale x 2 x i64> undef,
+    <vscale x 2 x i64> %0,
+    <vscale x 2 x i64> %1,
+    iXLen %2)
+
+  ret <vscale x 2 x i64> %a
+}
+
+declare <vscale x 2 x i64> @llvm.riscv.vandn.mask.nxv2i64.nxv2i64(
+  <vscale x 2 x i64>,
+  <vscale x 2 x i64>,
+  <vscale x 2 x i64>,
+  <vscale x 2 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 2 x i64> @intrinsic_vandn_mask_vv_nxv2i64_nxv2i64(<vscale x 2 x i64> %0, <vscale x 2 x i64> %1, <vscale x 2 x i64> %2, <vscale x 2 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vandn_mask_vv_nxv2i64_nxv2i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e64, m2, ta, mu
+; CHECK-NEXT:    vandn.vv v8, v10, v12, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i64> @llvm.riscv.vandn.mask.nxv2i64.nxv2i64(
+    <vscale x 2 x i64> %0,
+    <vscale x 2 x i64> %1,
+    <vscale x 2 x i64> %2,
+    <vscale x 2 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 2 x i64> %a
+}
+
+declare <vscale x 4 x i64> @llvm.riscv.vandn.nxv4i64.nxv4i64(
+  <vscale x 4 x i64>,
+  <vscale x 4 x i64>,
+  <vscale x 4 x i64>,
+  iXLen)
+
+define <vscale x 4 x i64> @intrinsic_vandn_vv_nxv4i64_nxv4i64(<vscale x 4 x i64> %0, <vscale x 4 x i64> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vandn_vv_nxv4i64_nxv4i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e64, m4, ta, ma
+; CHECK-NEXT:    vandn.vv v8, v8, v12
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i64> @llvm.riscv.vandn.nxv4i64.nxv4i64(
+    <vscale x 4 x i64> undef,
+    <vscale x 4 x i64> %0,
+    <vscale x 4 x i64> %1,
+    iXLen %2)
+
+  ret <vscale x 4 x i64> %a
+}
+
+declare <vscale x 4 x i64> @llvm.riscv.vandn.mask.nxv4i64.nxv4i64(
+  <vscale x 4 x i64>,
+  <vscale x 4 x i64>,
+  <vscale x 4 x i64>,
+  <vscale x 4 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 4 x i64> @intrinsic_vandn_mask_vv_nxv4i64_nxv4i64(<vscale x 4 x i64> %0, <vscale x 4 x i64> %1, <vscale x 4 x i64> %2, <vscale x 4 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vandn_mask_vv_nxv4i64_nxv4i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e64, m4, ta, mu
+; CHECK-NEXT:    vandn.vv v8, v12, v16, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i64> @llvm.riscv.vandn.mask.nxv4i64.nxv4i64(
+    <vscale x 4 x i64> %0,
+    <vscale x 4 x i64> %1,
+    <vscale x 4 x i64> %2,
+    <vscale x 4 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 4 x i64> %a
+}
+
+declare <vscale x 8 x i64> @llvm.riscv.vandn.nxv8i64.nxv8i64(
+  <vscale x 8 x i64>,
+  <vscale x 8 x i64>,
+  <vscale x 8 x i64>,
+  iXLen)
+
+define <vscale x 8 x i64> @intrinsic_vandn_vv_nxv8i64_nxv8i64(<vscale x 8 x i64> %0, <vscale x 8 x i64> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vandn_vv_nxv8i64_nxv8i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
+; CHECK-NEXT:    vandn.vv v8, v8, v16
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i64> @llvm.riscv.vandn.nxv8i64.nxv8i64(
+    <vscale x 8 x i64> undef,
+    <vscale x 8 x i64> %0,
+    <vscale x 8 x i64> %1,
+    iXLen %2)
+
+  ret <vscale x 8 x i64> %a
+}
+
+declare <vscale x 8 x i64> @llvm.riscv.vandn.mask.nxv8i64.nxv8i64(
+  <vscale x 8 x i64>,
+  <vscale x 8 x i64>,
+  <vscale x 8 x i64>,
+  <vscale x 8 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 8 x i64> @intrinsic_vandn_mask_vv_nxv8i64_nxv8i64(<vscale x 8 x i64> %0, <vscale x 8 x i64> %1, <vscale x 8 x i64> %2, <vscale x 8 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vandn_mask_vv_nxv8i64_nxv8i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vl8re64.v v24, (a0)
+; CHECK-NEXT:    vsetvli zero, a1, e64, m8, ta, mu
+; CHECK-NEXT:    vandn.vv v8, v16, v24, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i64> @llvm.riscv.vandn.mask.nxv8i64.nxv8i64(
+    <vscale x 8 x i64> %0,
+    <vscale x 8 x i64> %1,
+    <vscale x 8 x i64> %2,
+    <vscale x 8 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 8 x i64> %a
+}
+
+declare <vscale x 1 x i8> @llvm.riscv.vandn.nxv1i8.i8(
+  <vscale x 1 x i8>,
+  <vscale x 1 x i8>,
+  i8,
+  iXLen)
+
+define <vscale x 1 x i8> @intrinsic_vandn_vx_nxv1i8_i8(<vscale x 1 x i8> %0, i8 %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vandn_vx_nxv1i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e8, mf8, ta, ma
+; CHECK-NEXT:    vandn.vx v8, v8, a0
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i8> @llvm.riscv.vandn.nxv1i8.i8(
+    <vscale x 1 x i8> undef,
+    <vscale x 1 x i8> %0,
+    i8 %1,
+    iXLen %2)
+
+  ret <vscale x 1 x i8> %a
+}
+
+declare <vscale x 1 x i8> @llvm.riscv.vandn.mask.nxv1i8.i8(
+  <vscale x 1 x i8>,
+  <vscale x 1 x i8>,
+  i8,
+  <vscale x 1 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 1 x i8> @intrinsic_vandn_mask_vx_nxv1i8_i8(<vscale x 1 x i8> %0, <vscale x 1 x i8> %1, i8 %2, <vscale x 1 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vandn_mask_vx_nxv1i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e8, mf8, ta, mu
+; CHECK-NEXT:    vandn.vx v8, v9, a0, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i8> @llvm.riscv.vandn.mask.nxv1i8.i8(
+    <vscale x 1 x i8> %0,
+    <vscale x 1 x i8> %1,
+    i8 %2,
+    <vscale x 1 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 1 x i8> %a
+}
+
+declare <vscale x 2 x i8> @llvm.riscv.vandn.nxv2i8.i8(
+  <vscale x 2 x i8>,
+  <vscale x 2 x i8>,
+  i8,
+  iXLen)
+
+define <vscale x 2 x i8> @intrinsic_vandn_vx_nxv2i8_i8(<vscale x 2 x i8> %0, i8 %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vandn_vx_nxv2i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e8, mf4, ta, ma
+; CHECK-NEXT:    vandn.vx v8, v8, a0
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i8> @llvm.riscv.vandn.nxv2i8.i8(
+    <vscale x 2 x i8> undef,
+    <vscale x 2 x i8> %0,
+    i8 %1,
+    iXLen %2)
+
+  ret <vscale x 2 x i8> %a
+}
+
+declare <vscale x 2 x i8> @llvm.riscv.vandn.mask.nxv2i8.i8(
+  <vscale x 2 x i8>,
+  <vscale x 2 x i8>,
+  i8,
+  <vscale x 2 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 2 x i8> @intrinsic_vandn_mask_vx_nxv2i8_i8(<vscale x 2 x i8> %0, <vscale x 2 x i8> %1, i8 %2, <vscale x 2 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vandn_mask_vx_nxv2i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e8, mf4, ta, mu
+; CHECK-NEXT:    vandn.vx v8, v9, a0, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i8> @llvm.riscv.vandn.mask.nxv2i8.i8(
+    <vscale x 2 x i8> %0,
+    <vscale x 2 x i8> %1,
+    i8 %2,
+    <vscale x 2 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 2 x i8> %a
+}
+
+declare <vscale x 4 x i8> @llvm.riscv.vandn.nxv4i8.i8(
+  <vscale x 4 x i8>,
+  <vscale x 4 x i8>,
+  i8,
+  iXLen)
+
+define <vscale x 4 x i8> @intrinsic_vandn_vx_nxv4i8_i8(<vscale x 4 x i8> %0, i8 %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vandn_vx_nxv4i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e8, mf2, ta, ma
+; CHECK-NEXT:    vandn.vx v8, v8, a0
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i8> @llvm.riscv.vandn.nxv4i8.i8(
+    <vscale x 4 x i8> undef,
+    <vscale x 4 x i8> %0,
+    i8 %1,
+    iXLen %2)
+
+  ret <vscale x 4 x i8> %a
+}
+
+declare <vscale x 4 x i8> @llvm.riscv.vandn.mask.nxv4i8.i8(
+  <vscale x 4 x i8>,
+  <vscale x 4 x i8>,
+  i8,
+  <vscale x 4 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 4 x i8> @intrinsic_vandn_mask_vx_nxv4i8_i8(<vscale x 4 x i8> %0, <vscale x 4 x i8> %1, i8 %2, <vscale x 4 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vandn_mask_vx_nxv4i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e8, mf2, ta, mu
+; CHECK-NEXT:    vandn.vx v8, v9, a0, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i8> @llvm.riscv.vandn.mask.nxv4i8.i8(
+    <vscale x 4 x i8> %0,
+    <vscale x 4 x i8> %1,
+    i8 %2,
+    <vscale x 4 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 4 x i8> %a
+}
+
+declare <vscale x 8 x i8> @llvm.riscv.vandn.nxv8i8.i8(
+  <vscale x 8 x i8>,
+  <vscale x 8 x i8>,
+  i8,
+  iXLen)
+
+define <vscale x 8 x i8> @intrinsic_vandn_vx_nxv8i8_i8(<vscale x 8 x i8> %0, i8 %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vandn_vx_nxv8i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e8, m1, ta, ma
+; CHECK-NEXT:    vandn.vx v8, v8, a0
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i8> @llvm.riscv.vandn.nxv8i8.i8(
+    <vscale x 8 x i8> undef,
+    <vscale x 8 x i8> %0,
+    i8 %1,
+    iXLen %2)
+
+  ret <vscale x 8 x i8> %a
+}
+
+declare <vscale x 8 x i8> @llvm.riscv.vandn.mask.nxv8i8.i8(
+  <vscale x 8 x i8>,
+  <vscale x 8 x i8>,
+  i8,
+  <vscale x 8 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 8 x i8> @intrinsic_vandn_mask_vx_nxv8i8_i8(<vscale x 8 x i8> %0, <vscale x 8 x i8> %1, i8 %2, <vscale x 8 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vandn_mask_vx_nxv8i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e8, m1, ta, mu
+; CHECK-NEXT:    vandn.vx v8, v9, a0, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i8> @llvm.riscv.vandn.mask.nxv8i8.i8(
+    <vscale x 8 x i8> %0,
+    <vscale x 8 x i8> %1,
+    i8 %2,
+    <vscale x 8 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 8 x i8> %a
+}
+
+declare <vscale x 16 x i8> @llvm.riscv.vandn.nxv16i8.i8(
+  <vscale x 16 x i8>,
+  <vscale x 16 x i8>,
+  i8,
+  iXLen)
+
+define <vscale x 16 x i8> @intrinsic_vandn_vx_nxv16i8_i8(<vscale x 16 x i8> %0, i8 %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vandn_vx_nxv16i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e8, m2, ta, ma
+; CHECK-NEXT:    vandn.vx v8, v8, a0
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 16 x i8> @llvm.riscv.vandn.nxv16i8.i8(
+    <vscale x 16 x i8> undef,
+    <vscale x 16 x i8> %0,
+    i8 %1,
+    iXLen %2)
+
+  ret <vscale x 16 x i8> %a
+}
+
+declare <vscale x 16 x i8> @llvm.riscv.vandn.mask.nxv16i8.i8(
+  <vscale x 16 x i8>,
+  <vscale x 16 x i8>,
+  i8,
+  <vscale x 16 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 16 x i8> @intrinsic_vandn_mask_vx_nxv16i8_i8(<vscale x 16 x i8> %0, <vscale x 16 x i8> %1, i8 %2, <vscale x 16 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vandn_mask_vx_nxv16i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e8, m2, ta, mu
+; CHECK-NEXT:    vandn.vx v8, v10, a0, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 16 x i8> @llvm.riscv.vandn.mask.nxv16i8.i8(
+    <vscale x 16 x i8> %0,
+    <vscale x 16 x i8> %1,
+    i8 %2,
+    <vscale x 16 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 16 x i8> %a
+}
+
+declare <vscale x 32 x i8> @llvm.riscv.vandn.nxv32i8.i8(
+  <vscale x 32 x i8>,
+  <vscale x 32 x i8>,
+  i8,
+  iXLen)
+
+define <vscale x 32 x i8> @intrinsic_vandn_vx_nxv32i8_i8(<vscale x 32 x i8> %0, i8 %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vandn_vx_nxv32i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e8, m4, ta, ma
+; CHECK-NEXT:    vandn.vx v8, v8, a0
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 32 x i8> @llvm.riscv.vandn.nxv32i8.i8(
+    <vscale x 32 x i8> undef,
+    <vscale x 32 x i8> %0,
+    i8 %1,
+    iXLen %2)
+
+  ret <vscale x 32 x i8> %a
+}
+
+declare <vscale x 32 x i8> @llvm.riscv.vandn.mask.nxv32i8.i8(
+  <vscale x 32 x i8>,
+  <vscale x 32 x i8>,
+  i8,
+  <vscale x 32 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 32 x i8> @intrinsic_vandn_mask_vx_nxv32i8_i8(<vscale x 32 x i8> %0, <vscale x 32 x i8> %1, i8 %2, <vscale x 32 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vandn_mask_vx_nxv32i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e8, m4, ta, mu
+; CHECK-NEXT:    vandn.vx v8, v12, a0, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 32 x i8> @llvm.riscv.vandn.mask.nxv32i8.i8(
+    <vscale x 32 x i8> %0,
+    <vscale x 32 x i8> %1,
+    i8 %2,
+    <vscale x 32 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 32 x i8> %a
+}
+
+declare <vscale x 64 x i8> @llvm.riscv.vandn.nxv64i8.i8(
+  <vscale x 64 x i8>,
+  <vscale x 64 x i8>,
+  i8,
+  iXLen)
+
+define <vscale x 64 x i8> @intrinsic_vandn_vx_nxv64i8_i8(<vscale x 64 x i8> %0, i8 %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vandn_vx_nxv64i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e8, m8, ta, ma
+; CHECK-NEXT:    vandn.vx v8, v8, a0
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 64 x i8> @llvm.riscv.vandn.nxv64i8.i8(
+    <vscale x 64 x i8> undef,
+    <vscale x 64 x i8> %0,
+    i8 %1,
+    iXLen %2)
+
+  ret <vscale x 64 x i8> %a
+}
+
+declare <vscale x 64 x i8> @llvm.riscv.vandn.mask.nxv64i8.i8(
+  <vscale x 64 x i8>,
+  <vscale x 64 x i8>,
+  i8,
+  <vscale x 64 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 64 x i8> @intrinsic_vandn_mask_vx_nxv64i8_i8(<vscale x 64 x i8> %0, <vscale x 64 x i8> %1, i8 %2, <vscale x 64 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vandn_mask_vx_nxv64i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e8, m8, ta, mu
+; CHECK-NEXT:    vandn.vx v8, v16, a0, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 64 x i8> @llvm.riscv.vandn.mask.nxv64i8.i8(
+    <vscale x 64 x i8> %0,
+    <vscale x 64 x i8> %1,
+    i8 %2,
+    <vscale x 64 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 64 x i8> %a
+}
+
+declare <vscale x 1 x i16> @llvm.riscv.vandn.nxv1i16.i16(
+  <vscale x 1 x i16>,
+  <vscale x 1 x i16>,
+  i16,
+  iXLen)
+
+define <vscale x 1 x i16> @intrinsic_vandn_vx_nxv1i16_i16(<vscale x 1 x i16> %0, i16 %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vandn_vx_nxv1i16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e16, mf4, ta, ma
+; CHECK-NEXT:    vandn.vx v8, v8, a0
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i16> @llvm.riscv.vandn.nxv1i16.i16(
+    <vscale x 1 x i16> undef,
+    <vscale x 1 x i16> %0,
+    i16 %1,
+    iXLen %2)
+
+  ret <vscale x 1 x i16> %a
+}
+
+declare <vscale x 1 x i16> @llvm.riscv.vandn.mask.nxv1i16.i16(
+  <vscale x 1 x i16>,
+  <vscale x 1 x i16>,
+  i16,
+  <vscale x 1 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 1 x i16> @intrinsic_vandn_mask_vx_nxv1i16_i16(<vscale x 1 x i16> %0, <vscale x 1 x i16> %1, i16 %2, <vscale x 1 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vandn_mask_vx_nxv1i16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e16, mf4, ta, mu
+; CHECK-NEXT:    vandn.vx v8, v9, a0, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i16> @llvm.riscv.vandn.mask.nxv1i16.i16(
+    <vscale x 1 x i16> %0,
+    <vscale x 1 x i16> %1,
+    i16 %2,
+    <vscale x 1 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 1 x i16> %a
+}
+
+declare <vscale x 2 x i16> @llvm.riscv.vandn.nxv2i16.i16(
+  <vscale x 2 x i16>,
+  <vscale x 2 x i16>,
+  i16,
+  iXLen)
+
+define <vscale x 2 x i16> @intrinsic_vandn_vx_nxv2i16_i16(<vscale x 2 x i16> %0, i16 %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vandn_vx_nxv2i16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e16, mf2, ta, ma
+; CHECK-NEXT:    vandn.vx v8, v8, a0
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i16> @llvm.riscv.vandn.nxv2i16.i16(
+    <vscale x 2 x i16> undef,
+    <vscale x 2 x i16> %0,
+    i16 %1,
+    iXLen %2)
+
+  ret <vscale x 2 x i16> %a
+}
+
+declare <vscale x 2 x i16> @llvm.riscv.vandn.mask.nxv2i16.i16(
+  <vscale x 2 x i16>,
+  <vscale x 2 x i16>,
+  i16,
+  <vscale x 2 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 2 x i16> @intrinsic_vandn_mask_vx_nxv2i16_i16(<vscale x 2 x i16> %0, <vscale x 2 x i16> %1, i16 %2, <vscale x 2 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vandn_mask_vx_nxv2i16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e16, mf2, ta, mu
+; CHECK-NEXT:    vandn.vx v8, v9, a0, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i16> @llvm.riscv.vandn.mask.nxv2i16.i16(
+    <vscale x 2 x i16> %0,
+    <vscale x 2 x i16> %1,
+    i16 %2,
+    <vscale x 2 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 2 x i16> %a
+}
+
+declare <vscale x 4 x i16> @llvm.riscv.vandn.nxv4i16.i16(
+  <vscale x 4 x i16>,
+  <vscale x 4 x i16>,
+  i16,
+  iXLen)
+
+define <vscale x 4 x i16> @intrinsic_vandn_vx_nxv4i16_i16(<vscale x 4 x i16> %0, i16 %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vandn_vx_nxv4i16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e16, m1, ta, ma
+; CHECK-NEXT:    vandn.vx v8, v8, a0
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i16> @llvm.riscv.vandn.nxv4i16.i16(
+    <vscale x 4 x i16> undef,
+    <vscale x 4 x i16> %0,
+    i16 %1,
+    iXLen %2)
+
+  ret <vscale x 4 x i16> %a
+}
+
+declare <vscale x 4 x i16> @llvm.riscv.vandn.mask.nxv4i16.i16(
+  <vscale x 4 x i16>,
+  <vscale x 4 x i16>,
+  i16,
+  <vscale x 4 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 4 x i16> @intrinsic_vandn_mask_vx_nxv4i16_i16(<vscale x 4 x i16> %0, <vscale x 4 x i16> %1, i16 %2, <vscale x 4 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vandn_mask_vx_nxv4i16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e16, m1, ta, mu
+; CHECK-NEXT:    vandn.vx v8, v9, a0, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i16> @llvm.riscv.vandn.mask.nxv4i16.i16(
+    <vscale x 4 x i16> %0,
+    <vscale x 4 x i16> %1,
+    i16 %2,
+    <vscale x 4 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 4 x i16> %a
+}
+
+declare <vscale x 8 x i16> @llvm.riscv.vandn.nxv8i16.i16(
+  <vscale x 8 x i16>,
+  <vscale x 8 x i16>,
+  i16,
+  iXLen)
+
+define <vscale x 8 x i16> @intrinsic_vandn_vx_nxv8i16_i16(<vscale x 8 x i16> %0, i16 %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vandn_vx_nxv8i16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e16, m2, ta, ma
+; CHECK-NEXT:    vandn.vx v8, v8, a0
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i16> @llvm.riscv.vandn.nxv8i16.i16(
+    <vscale x 8 x i16> undef,
+    <vscale x 8 x i16> %0,
+    i16 %1,
+    iXLen %2)
+
+  ret <vscale x 8 x i16> %a
+}
+
+declare <vscale x 8 x i16> @llvm.riscv.vandn.mask.nxv8i16.i16(
+  <vscale x 8 x i16>,
+  <vscale x 8 x i16>,
+  i16,
+  <vscale x 8 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 8 x i16> @intrinsic_vandn_mask_vx_nxv8i16_i16(<vscale x 8 x i16> %0, <vscale x 8 x i16> %1, i16 %2, <vscale x 8 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vandn_mask_vx_nxv8i16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e16, m2, ta, mu
+; CHECK-NEXT:    vandn.vx v8, v10, a0, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i16> @llvm.riscv.vandn.mask.nxv8i16.i16(
+    <vscale x 8 x i16> %0,
+    <vscale x 8 x i16> %1,
+    i16 %2,
+    <vscale x 8 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 8 x i16> %a
+}
+
+declare <vscale x 16 x i16> @llvm.riscv.vandn.nxv16i16.i16(
+  <vscale x 16 x i16>,
+  <vscale x 16 x i16>,
+  i16,
+  iXLen)
+
+define <vscale x 16 x i16> @intrinsic_vandn_vx_nxv16i16_i16(<vscale x 16 x i16> %0, i16 %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vandn_vx_nxv16i16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e16, m4, ta, ma
+; CHECK-NEXT:    vandn.vx v8, v8, a0
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 16 x i16> @llvm.riscv.vandn.nxv16i16.i16(
+    <vscale x 16 x i16> undef,
+    <vscale x 16 x i16> %0,
+    i16 %1,
+    iXLen %2)
+
+  ret <vscale x 16 x i16> %a
+}
+
+declare <vscale x 16 x i16> @llvm.riscv.vandn.mask.nxv16i16.i16(
+  <vscale x 16 x i16>,
+  <vscale x 16 x i16>,
+  i16,
+  <vscale x 16 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 16 x i16> @intrinsic_vandn_mask_vx_nxv16i16_i16(<vscale x 16 x i16> %0, <vscale x 16 x i16> %1, i16 %2, <vscale x 16 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vandn_mask_vx_nxv16i16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e16, m4, ta, mu
+; CHECK-NEXT:    vandn.vx v8, v12, a0, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 16 x i16> @llvm.riscv.vandn.mask.nxv16i16.i16(
+    <vscale x 16 x i16> %0,
+    <vscale x 16 x i16> %1,
+    i16 %2,
+    <vscale x 16 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 16 x i16> %a
+}
+
+declare <vscale x 32 x i16> @llvm.riscv.vandn.nxv32i16.i16(
+  <vscale x 32 x i16>,
+  <vscale x 32 x i16>,
+  i16,
+  iXLen)
+
+define <vscale x 32 x i16> @intrinsic_vandn_vx_nxv32i16_i16(<vscale x 32 x i16> %0, i16 %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vandn_vx_nxv32i16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e16, m8, ta, ma
+; CHECK-NEXT:    vandn.vx v8, v8, a0
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 32 x i16> @llvm.riscv.vandn.nxv32i16.i16(
+    <vscale x 32 x i16> undef,
+    <vscale x 32 x i16> %0,
+    i16 %1,
+    iXLen %2)
+
+  ret <vscale x 32 x i16> %a
+}
+
+declare <vscale x 32 x i16> @llvm.riscv.vandn.mask.nxv32i16.i16(
+  <vscale x 32 x i16>,
+  <vscale x 32 x i16>,
+  i16,
+  <vscale x 32 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 32 x i16> @intrinsic_vandn_mask_vx_nxv32i16_i16(<vscale x 32 x i16> %0, <vscale x 32 x i16> %1, i16 %2, <vscale x 32 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vandn_mask_vx_nxv32i16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e16, m8, ta, mu
+; CHECK-NEXT:    vandn.vx v8, v16, a0, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 32 x i16> @llvm.riscv.vandn.mask.nxv32i16.i16(
+    <vscale x 32 x i16> %0,
+    <vscale x 32 x i16> %1,
+    i16 %2,
+    <vscale x 32 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 32 x i16> %a
+}
+
+declare <vscale x 1 x i32> @llvm.riscv.vandn.nxv1i32.i32(
+  <vscale x 1 x i32>,
+  <vscale x 1 x i32>,
+  i32,
+  iXLen)
+
+define <vscale x 1 x i32> @intrinsic_vandn_vx_nxv1i32_i32(<vscale x 1 x i32> %0, i32 %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vandn_vx_nxv1i32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e32, mf2, ta, ma
+; CHECK-NEXT:    vandn.vx v8, v8, a0
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i32> @llvm.riscv.vandn.nxv1i32.i32(
+    <vscale x 1 x i32> undef,
+    <vscale x 1 x i32> %0,
+    i32 %1,
+    iXLen %2)
+
+  ret <vscale x 1 x i32> %a
+}
+
+declare <vscale x 1 x i32> @llvm.riscv.vandn.mask.nxv1i32.i32(
+  <vscale x 1 x i32>,
+  <vscale x 1 x i32>,
+  i32,
+  <vscale x 1 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 1 x i32> @intrinsic_vandn_mask_vx_nxv1i32_i32(<vscale x 1 x i32> %0, <vscale x 1 x i32> %1, i32 %2, <vscale x 1 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vandn_mask_vx_nxv1i32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e32, mf2, ta, mu
+; CHECK-NEXT:    vandn.vx v8, v9, a0, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i32> @llvm.riscv.vandn.mask.nxv1i32.i32(
+    <vscale x 1 x i32> %0,
+    <vscale x 1 x i32> %1,
+    i32 %2,
+    <vscale x 1 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 1 x i32> %a
+}
+
+declare <vscale x 2 x i32> @llvm.riscv.vandn.nxv2i32.i32(
+  <vscale x 2 x i32>,
+  <vscale x 2 x i32>,
+  i32,
+  iXLen)
+
+define <vscale x 2 x i32> @intrinsic_vandn_vx_nxv2i32_i32(<vscale x 2 x i32> %0, i32 %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vandn_vx_nxv2i32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e32, m1, ta, ma
+; CHECK-NEXT:    vandn.vx v8, v8, a0
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i32> @llvm.riscv.vandn.nxv2i32.i32(
+    <vscale x 2 x i32> undef,
+    <vscale x 2 x i32> %0,
+    i32 %1,
+    iXLen %2)
+
+  ret <vscale x 2 x i32> %a
+}
+
+declare <vscale x 2 x i32> @llvm.riscv.vandn.mask.nxv2i32.i32(
+  <vscale x 2 x i32>,
+  <vscale x 2 x i32>,
+  i32,
+  <vscale x 2 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 2 x i32> @intrinsic_vandn_mask_vx_nxv2i32_i32(<vscale x 2 x i32> %0, <vscale x 2 x i32> %1, i32 %2, <vscale x 2 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vandn_mask_vx_nxv2i32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e32, m1, ta, mu
+; CHECK-NEXT:    vandn.vx v8, v9, a0, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i32> @llvm.riscv.vandn.mask.nxv2i32.i32(
+    <vscale x 2 x i32> %0,
+    <vscale x 2 x i32> %1,
+    i32 %2,
+    <vscale x 2 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 2 x i32> %a
+}
+
+declare <vscale x 4 x i32> @llvm.riscv.vandn.nxv4i32.i32(
+  <vscale x 4 x i32>,
+  <vscale x 4 x i32>,
+  i32,
+  iXLen)
+
+define <vscale x 4 x i32> @intrinsic_vandn_vx_nxv4i32_i32(<vscale x 4 x i32> %0, i32 %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vandn_vx_nxv4i32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e32, m2, ta, ma
+; CHECK-NEXT:    vandn.vx v8, v8, a0
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i32> @llvm.riscv.vandn.nxv4i32.i32(
+    <vscale x 4 x i32> undef,
+    <vscale x 4 x i32> %0,
+    i32 %1,
+    iXLen %2)
+
+  ret <vscale x 4 x i32> %a
+}
+
+declare <vscale x 4 x i32> @llvm.riscv.vandn.mask.nxv4i32.i32(
+  <vscale x 4 x i32>,
+  <vscale x 4 x i32>,
+  i32,
+  <vscale x 4 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 4 x i32> @intrinsic_vandn_mask_vx_nxv4i32_i32(<vscale x 4 x i32> %0, <vscale x 4 x i32> %1, i32 %2, <vscale x 4 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vandn_mask_vx_nxv4i32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e32, m2, ta, mu
+; CHECK-NEXT:    vandn.vx v8, v10, a0, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i32> @llvm.riscv.vandn.mask.nxv4i32.i32(
+    <vscale x 4 x i32> %0,
+    <vscale x 4 x i32> %1,
+    i32 %2,
+    <vscale x 4 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 4 x i32> %a
+}
+
+declare <vscale x 8 x i32> @llvm.riscv.vandn.nxv8i32.i32(
+  <vscale x 8 x i32>,
+  <vscale x 8 x i32>,
+  i32,
+  iXLen)
+
+define <vscale x 8 x i32> @intrinsic_vandn_vx_nxv8i32_i32(<vscale x 8 x i32> %0, i32 %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vandn_vx_nxv8i32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e32, m4, ta, ma
+; CHECK-NEXT:    vandn.vx v8, v8, a0
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i32> @llvm.riscv.vandn.nxv8i32.i32(
+    <vscale x 8 x i32> undef,
+    <vscale x 8 x i32> %0,
+    i32 %1,
+    iXLen %2)
+
+  ret <vscale x 8 x i32> %a
+}
+
+declare <vscale x 8 x i32> @llvm.riscv.vandn.mask.nxv8i32.i32(
+  <vscale x 8 x i32>,
+  <vscale x 8 x i32>,
+  i32,
+  <vscale x 8 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 8 x i32> @intrinsic_vandn_mask_vx_nxv8i32_i32(<vscale x 8 x i32> %0, <vscale x 8 x i32> %1, i32 %2, <vscale x 8 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vandn_mask_vx_nxv8i32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e32, m4, ta, mu
+; CHECK-NEXT:    vandn.vx v8, v12, a0, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i32> @llvm.riscv.vandn.mask.nxv8i32.i32(
+    <vscale x 8 x i32> %0,
+    <vscale x 8 x i32> %1,
+    i32 %2,
+    <vscale x 8 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 8 x i32> %a
+}
+
+declare <vscale x 16 x i32> @llvm.riscv.vandn.nxv16i32.i32(
+  <vscale x 16 x i32>,
+  <vscale x 16 x i32>,
+  i32,
+  iXLen)
+
+define <vscale x 16 x i32> @intrinsic_vandn_vx_nxv16i32_i32(<vscale x 16 x i32> %0, i32 %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vandn_vx_nxv16i32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e32, m8, ta, ma
+; CHECK-NEXT:    vandn.vx v8, v8, a0
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 16 x i32> @llvm.riscv.vandn.nxv16i32.i32(
+    <vscale x 16 x i32> undef,
+    <vscale x 16 x i32> %0,
+    i32 %1,
+    iXLen %2)
+
+  ret <vscale x 16 x i32> %a
+}
+
+declare <vscale x 16 x i32> @llvm.riscv.vandn.mask.nxv16i32.i32(
+  <vscale x 16 x i32>,
+  <vscale x 16 x i32>,
+  i32,
+  <vscale x 16 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 16 x i32> @intrinsic_vandn_mask_vx_nxv16i32_i32(<vscale x 16 x i32> %0, <vscale x 16 x i32> %1, i32 %2, <vscale x 16 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vandn_mask_vx_nxv16i32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e32, m8, ta, mu
+; CHECK-NEXT:    vandn.vx v8, v16, a0, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 16 x i32> @llvm.riscv.vandn.mask.nxv16i32.i32(
+    <vscale x 16 x i32> %0,
+    <vscale x 16 x i32> %1,
+    i32 %2,
+    <vscale x 16 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 16 x i32> %a
+}
+
+declare <vscale x 1 x i64> @llvm.riscv.vandn.nxv1i64.i64(
+  <vscale x 1 x i64>,
+  <vscale x 1 x i64>,
+  i64,
+  iXLen)
+
+define <vscale x 1 x i64> @intrinsic_vandn_vx_nxv1i64_i64(<vscale x 1 x i64> %0, i64 %1, iXLen %2) nounwind {
+; RV32-LABEL: intrinsic_vandn_vx_nxv1i64_i64:
+; RV32:       # %bb.0: # %entry
+; RV32-NEXT:    addi sp, sp, -16
+; RV32-NEXT:    sw a1, 12(sp)
+; RV32-NEXT:    sw a0, 8(sp)
+; RV32-NEXT:    addi a0, sp, 8
+; RV32-NEXT:    vsetvli zero, a2, e64, m1, ta, ma
+; RV32-NEXT:    vlse64.v v9, (a0), zero
+; RV32-NEXT:    vandn.vv v8, v8, v9
+; RV32-NEXT:    addi sp, sp, 16
+; RV32-NEXT:    ret
+;
+; RV64-LABEL: intrinsic_vandn_vx_nxv1i64_i64:
+; RV64:       # %bb.0: # %entry
+; RV64-NEXT:    vsetvli zero, a1, e64, m1, ta, ma
+; RV64-NEXT:    vandn.vx v8, v8, a0
+; RV64-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i64> @llvm.riscv.vandn.nxv1i64.i64(
+    <vscale x 1 x i64> undef,
+    <vscale x 1 x i64> %0,
+    i64 %1,
+    iXLen %2)
+
+  ret <vscale x 1 x i64> %a
+}
+
+declare <vscale x 1 x i64> @llvm.riscv.vandn.mask.nxv1i64.i64(
+  <vscale x 1 x i64>,
+  <vscale x 1 x i64>,
+  i64,
+  <vscale x 1 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 1 x i64> @intrinsic_vandn_mask_vx_nxv1i64_i64(<vscale x 1 x i64> %0, <vscale x 1 x i64> %1, i64 %2, <vscale x 1 x i1> %3, iXLen %4) nounwind {
+; RV32-LABEL: intrinsic_vandn_mask_vx_nxv1i64_i64:
+; RV32:       # %bb.0: # %entry
+; RV32-NEXT:    addi sp, sp, -16
+; RV32-NEXT:    sw a1, 12(sp)
+; RV32-NEXT:    sw a0, 8(sp)
+; RV32-NEXT:    addi a0, sp, 8
+; RV32-NEXT:    vsetvli zero, a2, e64, m1, ta, mu
+; RV32-NEXT:    vlse64.v v10, (a0), zero
+; RV32-NEXT:    vandn.vv v8, v9, v10, v0.t
+; RV32-NEXT:    addi sp, sp, 16
+; RV32-NEXT:    ret
+;
+; RV64-LABEL: intrinsic_vandn_mask_vx_nxv1i64_i64:
+; RV64:       # %bb.0: # %entry
+; RV64-NEXT:    vsetvli zero, a1, e64, m1, ta, mu
+; RV64-NEXT:    vandn.vx v8, v9, a0, v0.t
+; RV64-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i64> @llvm.riscv.vandn.mask.nxv1i64.i64(
+    <vscale x 1 x i64> %0,
+    <vscale x 1 x i64> %1,
+    i64 %2,
+    <vscale x 1 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 1 x i64> %a
+}
+
+declare <vscale x 2 x i64> @llvm.riscv.vandn.nxv2i64.i64(
+  <vscale x 2 x i64>,
+  <vscale x 2 x i64>,
+  i64,
+  iXLen)
+
+define <vscale x 2 x i64> @intrinsic_vandn_vx_nxv2i64_i64(<vscale x 2 x i64> %0, i64 %1, iXLen %2) nounwind {
+; RV32-LABEL: intrinsic_vandn_vx_nxv2i64_i64:
+; RV32:       # %bb.0: # %entry
+; RV32-NEXT:    addi sp, sp, -16
+; RV32-NEXT:    sw a1, 12(sp)
+; RV32-NEXT:    sw a0, 8(sp)
+; RV32-NEXT:    addi a0, sp, 8
+; RV32-NEXT:    vsetvli zero, a2, e64, m2, ta, ma
+; RV32-NEXT:    vlse64.v v10, (a0), zero
+; RV32-NEXT:    vandn.vv v8, v8, v10
+; RV32-NEXT:    addi sp, sp, 16
+; RV32-NEXT:    ret
+;
+; RV64-LABEL: intrinsic_vandn_vx_nxv2i64_i64:
+; RV64:       # %bb.0: # %entry
+; RV64-NEXT:    vsetvli zero, a1, e64, m2, ta, ma
+; RV64-NEXT:    vandn.vx v8, v8, a0
+; RV64-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i64> @llvm.riscv.vandn.nxv2i64.i64(
+    <vscale x 2 x i64> undef,
+    <vscale x 2 x i64> %0,
+    i64 %1,
+    iXLen %2)
+
+  ret <vscale x 2 x i64> %a
+}
+
+declare <vscale x 2 x i64> @llvm.riscv.vandn.mask.nxv2i64.i64(
+  <vscale x 2 x i64>,
+  <vscale x 2 x i64>,
+  i64,
+  <vscale x 2 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 2 x i64> @intrinsic_vandn_mask_vx_nxv2i64_i64(<vscale x 2 x i64> %0, <vscale x 2 x i64> %1, i64 %2, <vscale x 2 x i1> %3, iXLen %4) nounwind {
+; RV32-LABEL: intrinsic_vandn_mask_vx_nxv2i64_i64:
+; RV32:       # %bb.0: # %entry
+; RV32-NEXT:    addi sp, sp, -16
+; RV32-NEXT:    sw a1, 12(sp)
+; RV32-NEXT:    sw a0, 8(sp)
+; RV32-NEXT:    addi a0, sp, 8
+; RV32-NEXT:    vsetvli zero, a2, e64, m2, ta, mu
+; RV32-NEXT:    vlse64.v v12, (a0), zero
+; RV32-NEXT:    vandn.vv v8, v10, v12, v0.t
+; RV32-NEXT:    addi sp, sp, 16
+; RV32-NEXT:    ret
+;
+; RV64-LABEL: intrinsic_vandn_mask_vx_nxv2i64_i64:
+; RV64:       # %bb.0: # %entry
+; RV64-NEXT:    vsetvli zero, a1, e64, m2, ta, mu
+; RV64-NEXT:    vandn.vx v8, v10, a0, v0.t
+; RV64-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i64> @llvm.riscv.vandn.mask.nxv2i64.i64(
+    <vscale x 2 x i64> %0,
+    <vscale x 2 x i64> %1,
+    i64 %2,
+    <vscale x 2 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 2 x i64> %a
+}
+
+declare <vscale x 4 x i64> @llvm.riscv.vandn.nxv4i64.i64(
+  <vscale x 4 x i64>,
+  <vscale x 4 x i64>,
+  i64,
+  iXLen)
+
+define <vscale x 4 x i64> @intrinsic_vandn_vx_nxv4i64_i64(<vscale x 4 x i64> %0, i64 %1, iXLen %2) nounwind {
+; RV32-LABEL: intrinsic_vandn_vx_nxv4i64_i64:
+; RV32:       # %bb.0: # %entry
+; RV32-NEXT:    addi sp, sp, -16
+; RV32-NEXT:    sw a1, 12(sp)
+; RV32-NEXT:    sw a0, 8(sp)
+; RV32-NEXT:    addi a0, sp, 8
+; RV32-NEXT:    vsetvli zero, a2, e64, m4, ta, ma
+; RV32-NEXT:    vlse64.v v12, (a0), zero
+; RV32-NEXT:    vandn.vv v8, v8, v12
+; RV32-NEXT:    addi sp, sp, 16
+; RV32-NEXT:    ret
+;
+; RV64-LABEL: intrinsic_vandn_vx_nxv4i64_i64:
+; RV64:       # %bb.0: # %entry
+; RV64-NEXT:    vsetvli zero, a1, e64, m4, ta, ma
+; RV64-NEXT:    vandn.vx v8, v8, a0
+; RV64-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i64> @llvm.riscv.vandn.nxv4i64.i64(
+    <vscale x 4 x i64> undef,
+    <vscale x 4 x i64> %0,
+    i64 %1,
+    iXLen %2)
+
+  ret <vscale x 4 x i64> %a
+}
+
+declare <vscale x 4 x i64> @llvm.riscv.vandn.mask.nxv4i64.i64(
+  <vscale x 4 x i64>,
+  <vscale x 4 x i64>,
+  i64,
+  <vscale x 4 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 4 x i64> @intrinsic_vandn_mask_vx_nxv4i64_i64(<vscale x 4 x i64> %0, <vscale x 4 x i64> %1, i64 %2, <vscale x 4 x i1> %3, iXLen %4) nounwind {
+; RV32-LABEL: intrinsic_vandn_mask_vx_nxv4i64_i64:
+; RV32:       # %bb.0: # %entry
+; RV32-NEXT:    addi sp, sp, -16
+; RV32-NEXT:    sw a1, 12(sp)
+; RV32-NEXT:    sw a0, 8(sp)
+; RV32-NEXT:    addi a0, sp, 8
+; RV32-NEXT:    vsetvli zero, a2, e64, m4, ta, mu
+; RV32-NEXT:    vlse64.v v16, (a0), zero
+; RV32-NEXT:    vandn.vv v8, v12, v16, v0.t
+; RV32-NEXT:    addi sp, sp, 16
+; RV32-NEXT:    ret
+;
+; RV64-LABEL: intrinsic_vandn_mask_vx_nxv4i64_i64:
+; RV64:       # %bb.0: # %entry
+; RV64-NEXT:    vsetvli zero, a1, e64, m4, ta, mu
+; RV64-NEXT:    vandn.vx v8, v12, a0, v0.t
+; RV64-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i64> @llvm.riscv.vandn.mask.nxv4i64.i64(
+    <vscale x 4 x i64> %0,
+    <vscale x 4 x i64> %1,
+    i64 %2,
+    <vscale x 4 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 4 x i64> %a
+}
+
+declare <vscale x 8 x i64> @llvm.riscv.vandn.nxv8i64.i64(
+  <vscale x 8 x i64>,
+  <vscale x 8 x i64>,
+  i64,
+  iXLen)
+
+define <vscale x 8 x i64> @intrinsic_vandn_vx_nxv8i64_i64(<vscale x 8 x i64> %0, i64 %1, iXLen %2) nounwind {
+; RV32-LABEL: intrinsic_vandn_vx_nxv8i64_i64:
+; RV32:       # %bb.0: # %entry
+; RV32-NEXT:    addi sp, sp, -16
+; RV32-NEXT:    sw a1, 12(sp)
+; RV32-NEXT:    sw a0, 8(sp)
+; RV32-NEXT:    addi a0, sp, 8
+; RV32-NEXT:    vsetvli zero, a2, e64, m8, ta, ma
+; RV32-NEXT:    vlse64.v v16, (a0), zero
+; RV32-NEXT:    vandn.vv v8, v8, v16
+; RV32-NEXT:    addi sp, sp, 16
+; RV32-NEXT:    ret
+;
+; RV64-LABEL: intrinsic_vandn_vx_nxv8i64_i64:
+; RV64:       # %bb.0: # %entry
+; RV64-NEXT:    vsetvli zero, a1, e64, m8, ta, ma
+; RV64-NEXT:    vandn.vx v8, v8, a0
+; RV64-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i64> @llvm.riscv.vandn.nxv8i64.i64(
+    <vscale x 8 x i64> undef,
+    <vscale x 8 x i64> %0,
+    i64 %1,
+    iXLen %2)
+
+  ret <vscale x 8 x i64> %a
+}
+
+declare <vscale x 8 x i64> @llvm.riscv.vandn.mask.nxv8i64.i64(
+  <vscale x 8 x i64>,
+  <vscale x 8 x i64>,
+  i64,
+  <vscale x 8 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 8 x i64> @intrinsic_vandn_mask_vx_nxv8i64_i64(<vscale x 8 x i64> %0, <vscale x 8 x i64> %1, i64 %2, <vscale x 8 x i1> %3, iXLen %4) nounwind {
+; RV32-LABEL: intrinsic_vandn_mask_vx_nxv8i64_i64:
+; RV32:       # %bb.0: # %entry
+; RV32-NEXT:    addi sp, sp, -16
+; RV32-NEXT:    sw a1, 12(sp)
+; RV32-NEXT:    sw a0, 8(sp)
+; RV32-NEXT:    addi a0, sp, 8
+; RV32-NEXT:    vsetvli zero, a2, e64, m8, ta, mu
+; RV32-NEXT:    vlse64.v v24, (a0), zero
+; RV32-NEXT:    vandn.vv v8, v16, v24, v0.t
+; RV32-NEXT:    addi sp, sp, 16
+; RV32-NEXT:    ret
+;
+; RV64-LABEL: intrinsic_vandn_mask_vx_nxv8i64_i64:
+; RV64:       # %bb.0: # %entry
+; RV64-NEXT:    vsetvli zero, a1, e64, m8, ta, mu
+; RV64-NEXT:    vandn.vx v8, v16, a0, v0.t
+; RV64-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i64> @llvm.riscv.vandn.mask.nxv8i64.i64(
+    <vscale x 8 x i64> %0,
+    <vscale x 8 x i64> %1,
+    i64 %2,
+    <vscale x 8 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 8 x i64> %a
+}

llvm/test/CodeGen/RISCV/rvv/vbrev.ll

+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: sed 's/iXLen/i32/g' %s | llc -mtriple=riscv32 -mattr=+v,+experimental-zvbb \
+; RUN:   -verify-machineinstrs | FileCheck %s --check-prefixes=CHECK
+; RUN: sed 's/iXLen/i64/g' %s | llc -mtriple=riscv64 -mattr=+v,+experimental-zvbb \
+; RUN:   -verify-machineinstrs | FileCheck %s --check-prefixes=CHECK
+
+declare <vscale x 1 x i8> @llvm.riscv.vbrev.nxv1i8(
+  <vscale x 1 x i8>,
+  <vscale x 1 x i8>,
+  iXLen);
+
+define <vscale x 1 x i8> @intrinsic_vbrev_vs_nxv1i8(<vscale x 1 x i8> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vbrev_vs_nxv1i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, mf8, ta, ma
+; CHECK-NEXT:    vbrev.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i8> @llvm.riscv.vbrev.nxv1i8(
+    <vscale x 1 x i8> undef,
+    <vscale x 1 x i8> %0,
+    iXLen %1)
+
+  ret <vscale x 1 x i8> %a
+}
+
+declare <vscale x 1 x i8> @llvm.riscv.vbrev.mask.nxv1i8(
+  <vscale x 1 x i8>,
+  <vscale x 1 x i8>,
+  <vscale x 1 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 1 x i8> @intrinsic_vbrev_mask_vs_nxv1i8(<vscale x 1 x i1> %0, <vscale x 1 x i8> %1, <vscale x 1 x i8> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vbrev_mask_vs_nxv1i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, mf8, ta, mu
+; CHECK-NEXT:    vbrev.v v8, v9, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i8> @llvm.riscv.vbrev.mask.nxv1i8(
+    <vscale x 1 x i8> %1,
+    <vscale x 1 x i8> %2,
+    <vscale x 1 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 1 x i8> %a
+}
+
+declare <vscale x 2 x i8> @llvm.riscv.vbrev.nxv2i8(
+  <vscale x 2 x i8>,
+  <vscale x 2 x i8>,
+  iXLen);
+
+define <vscale x 2 x i8> @intrinsic_vbrev_vs_nxv2i8(<vscale x 2 x i8> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vbrev_vs_nxv2i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, mf4, ta, ma
+; CHECK-NEXT:    vbrev.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i8> @llvm.riscv.vbrev.nxv2i8(
+    <vscale x 2 x i8> undef,
+    <vscale x 2 x i8> %0,
+    iXLen %1)
+
+  ret <vscale x 2 x i8> %a
+}
+
+declare <vscale x 2 x i8> @llvm.riscv.vbrev.mask.nxv2i8(
+  <vscale x 2 x i8>,
+  <vscale x 2 x i8>,
+  <vscale x 2 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 2 x i8> @intrinsic_vbrev_mask_vs_nxv2i8(<vscale x 2 x i1> %0, <vscale x 2 x i8> %1, <vscale x 2 x i8> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vbrev_mask_vs_nxv2i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, mf4, ta, mu
+; CHECK-NEXT:    vbrev.v v8, v9, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i8> @llvm.riscv.vbrev.mask.nxv2i8(
+    <vscale x 2 x i8> %1,
+    <vscale x 2 x i8> %2,
+    <vscale x 2 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 2 x i8> %a
+}
+
+declare <vscale x 4 x i8> @llvm.riscv.vbrev.nxv4i8(
+  <vscale x 4 x i8>,
+  <vscale x 4 x i8>,
+  iXLen);
+
+define <vscale x 4 x i8> @intrinsic_vbrev_vs_nxv4i8(<vscale x 4 x i8> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vbrev_vs_nxv4i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, mf2, ta, ma
+; CHECK-NEXT:    vbrev.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i8> @llvm.riscv.vbrev.nxv4i8(
+    <vscale x 4 x i8> undef,
+    <vscale x 4 x i8> %0,
+    iXLen %1)
+
+  ret <vscale x 4 x i8> %a
+}
+
+declare <vscale x 4 x i8> @llvm.riscv.vbrev.mask.nxv4i8(
+  <vscale x 4 x i8>,
+  <vscale x 4 x i8>,
+  <vscale x 4 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 4 x i8> @intrinsic_vbrev_mask_vs_nxv4i8(<vscale x 4 x i1> %0, <vscale x 4 x i8> %1, <vscale x 4 x i8> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vbrev_mask_vs_nxv4i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, mf2, ta, mu
+; CHECK-NEXT:    vbrev.v v8, v9, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i8> @llvm.riscv.vbrev.mask.nxv4i8(
+    <vscale x 4 x i8> %1,
+    <vscale x 4 x i8> %2,
+    <vscale x 4 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 4 x i8> %a
+}
+
+declare <vscale x 8 x i8> @llvm.riscv.vbrev.nxv8i8(
+  <vscale x 8 x i8>,
+  <vscale x 8 x i8>,
+  iXLen);
+
+define <vscale x 8 x i8> @intrinsic_vbrev_vs_nxv8i8(<vscale x 8 x i8> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vbrev_vs_nxv8i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, m1, ta, ma
+; CHECK-NEXT:    vbrev.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i8> @llvm.riscv.vbrev.nxv8i8(
+    <vscale x 8 x i8> undef,
+    <vscale x 8 x i8> %0,
+    iXLen %1)
+
+  ret <vscale x 8 x i8> %a
+}
+
+declare <vscale x 8 x i8> @llvm.riscv.vbrev.mask.nxv8i8(
+  <vscale x 8 x i8>,
+  <vscale x 8 x i8>,
+  <vscale x 8 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 8 x i8> @intrinsic_vbrev_mask_vs_nxv8i8(<vscale x 8 x i1> %0, <vscale x 8 x i8> %1, <vscale x 8 x i8> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vbrev_mask_vs_nxv8i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, m1, ta, mu
+; CHECK-NEXT:    vbrev.v v8, v9, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i8> @llvm.riscv.vbrev.mask.nxv8i8(
+    <vscale x 8 x i8> %1,
+    <vscale x 8 x i8> %2,
+    <vscale x 8 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 8 x i8> %a
+}
+
+declare <vscale x 16 x i8> @llvm.riscv.vbrev.nxv16i8(
+  <vscale x 16 x i8>,
+  <vscale x 16 x i8>,
+  iXLen);
+
+define <vscale x 16 x i8> @intrinsic_vbrev_vs_nxv16i8(<vscale x 16 x i8> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vbrev_vs_nxv16i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, m2, ta, ma
+; CHECK-NEXT:    vbrev.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 16 x i8> @llvm.riscv.vbrev.nxv16i8(
+    <vscale x 16 x i8> undef,
+    <vscale x 16 x i8> %0,
+    iXLen %1)
+
+  ret <vscale x 16 x i8> %a
+}
+
+declare <vscale x 16 x i8> @llvm.riscv.vbrev.mask.nxv16i8(
+  <vscale x 16 x i8>,
+  <vscale x 16 x i8>,
+  <vscale x 16 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 16 x i8> @intrinsic_vbrev_mask_vs_nxv16i8(<vscale x 16 x i1> %0, <vscale x 16 x i8> %1, <vscale x 16 x i8> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vbrev_mask_vs_nxv16i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, m2, ta, mu
+; CHECK-NEXT:    vbrev.v v8, v10, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 16 x i8> @llvm.riscv.vbrev.mask.nxv16i8(
+    <vscale x 16 x i8> %1,
+    <vscale x 16 x i8> %2,
+    <vscale x 16 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 16 x i8> %a
+}
+
+declare <vscale x 32 x i8> @llvm.riscv.vbrev.nxv32i8(
+  <vscale x 32 x i8>,
+  <vscale x 32 x i8>,
+  iXLen);
+
+define <vscale x 32 x i8> @intrinsic_vbrev_vs_nxv32i8(<vscale x 32 x i8> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vbrev_vs_nxv32i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, m4, ta, ma
+; CHECK-NEXT:    vbrev.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 32 x i8> @llvm.riscv.vbrev.nxv32i8(
+    <vscale x 32 x i8> undef,
+    <vscale x 32 x i8> %0,
+    iXLen %1)
+
+  ret <vscale x 32 x i8> %a
+}
+
+declare <vscale x 32 x i8> @llvm.riscv.vbrev.mask.nxv32i8(
+  <vscale x 32 x i8>,
+  <vscale x 32 x i8>,
+  <vscale x 32 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 32 x i8> @intrinsic_vbrev_mask_vs_nxv32i8(<vscale x 32 x i1> %0, <vscale x 32 x i8> %1, <vscale x 32 x i8> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vbrev_mask_vs_nxv32i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, m4, ta, mu
+; CHECK-NEXT:    vbrev.v v8, v12, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 32 x i8> @llvm.riscv.vbrev.mask.nxv32i8(
+    <vscale x 32 x i8> %1,
+    <vscale x 32 x i8> %2,
+    <vscale x 32 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 32 x i8> %a
+}
+
+declare <vscale x 64 x i8> @llvm.riscv.vbrev.nxv64i8(
+  <vscale x 64 x i8>,
+  <vscale x 64 x i8>,
+  iXLen);
+
+define <vscale x 64 x i8> @intrinsic_vbrev_vs_nxv64i8(<vscale x 64 x i8> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vbrev_vs_nxv64i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, m8, ta, ma
+; CHECK-NEXT:    vbrev.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 64 x i8> @llvm.riscv.vbrev.nxv64i8(
+    <vscale x 64 x i8> undef,
+    <vscale x 64 x i8> %0,
+    iXLen %1)
+
+  ret <vscale x 64 x i8> %a
+}
+
+declare <vscale x 64 x i8> @llvm.riscv.vbrev.mask.nxv64i8(
+  <vscale x 64 x i8>,
+  <vscale x 64 x i8>,
+  <vscale x 64 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 64 x i8> @intrinsic_vbrev_mask_vs_nxv64i8(<vscale x 64 x i1> %0, <vscale x 64 x i8> %1, <vscale x 64 x i8> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vbrev_mask_vs_nxv64i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, m8, ta, mu
+; CHECK-NEXT:    vbrev.v v8, v16, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 64 x i8> @llvm.riscv.vbrev.mask.nxv64i8(
+    <vscale x 64 x i8> %1,
+    <vscale x 64 x i8> %2,
+    <vscale x 64 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 64 x i8> %a
+}
+
+declare <vscale x 1 x i16> @llvm.riscv.vbrev.nxv1i16(
+  <vscale x 1 x i16>,
+  <vscale x 1 x i16>,
+  iXLen);
+
+define <vscale x 1 x i16> @intrinsic_vbrev_vs_nxv1i16(<vscale x 1 x i16> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vbrev_vs_nxv1i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, mf4, ta, ma
+; CHECK-NEXT:    vbrev.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i16> @llvm.riscv.vbrev.nxv1i16(
+    <vscale x 1 x i16> undef,
+    <vscale x 1 x i16> %0,
+    iXLen %1)
+
+  ret <vscale x 1 x i16> %a
+}
+
+declare <vscale x 1 x i16> @llvm.riscv.vbrev.mask.nxv1i16(
+  <vscale x 1 x i16>,
+  <vscale x 1 x i16>,
+  <vscale x 1 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 1 x i16> @intrinsic_vbrev_mask_vs_nxv1i16(<vscale x 1 x i1> %0, <vscale x 1 x i16> %1, <vscale x 1 x i16> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vbrev_mask_vs_nxv1i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, mf4, ta, mu
+; CHECK-NEXT:    vbrev.v v8, v9, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i16> @llvm.riscv.vbrev.mask.nxv1i16(
+    <vscale x 1 x i16> %1,
+    <vscale x 1 x i16> %2,
+    <vscale x 1 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 1 x i16> %a
+}
+
+declare <vscale x 2 x i16> @llvm.riscv.vbrev.nxv2i16(
+  <vscale x 2 x i16>,
+  <vscale x 2 x i16>,
+  iXLen);
+
+define <vscale x 2 x i16> @intrinsic_vbrev_vs_nxv2i16(<vscale x 2 x i16> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vbrev_vs_nxv2i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, mf2, ta, ma
+; CHECK-NEXT:    vbrev.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i16> @llvm.riscv.vbrev.nxv2i16(
+    <vscale x 2 x i16> undef,
+    <vscale x 2 x i16> %0,
+    iXLen %1)
+
+  ret <vscale x 2 x i16> %a
+}
+
+declare <vscale x 2 x i16> @llvm.riscv.vbrev.mask.nxv2i16(
+  <vscale x 2 x i16>,
+  <vscale x 2 x i16>,
+  <vscale x 2 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 2 x i16> @intrinsic_vbrev_mask_vs_nxv2i16(<vscale x 2 x i1> %0, <vscale x 2 x i16> %1, <vscale x 2 x i16> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vbrev_mask_vs_nxv2i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, mf2, ta, mu
+; CHECK-NEXT:    vbrev.v v8, v9, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i16> @llvm.riscv.vbrev.mask.nxv2i16(
+    <vscale x 2 x i16> %1,
+    <vscale x 2 x i16> %2,
+    <vscale x 2 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 2 x i16> %a
+}
+
+declare <vscale x 4 x i16> @llvm.riscv.vbrev.nxv4i16(
+  <vscale x 4 x i16>,
+  <vscale x 4 x i16>,
+  iXLen);
+
+define <vscale x 4 x i16> @intrinsic_vbrev_vs_nxv4i16(<vscale x 4 x i16> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vbrev_vs_nxv4i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, m1, ta, ma
+; CHECK-NEXT:    vbrev.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i16> @llvm.riscv.vbrev.nxv4i16(
+    <vscale x 4 x i16> undef,
+    <vscale x 4 x i16> %0,
+    iXLen %1)
+
+  ret <vscale x 4 x i16> %a
+}
+
+declare <vscale x 4 x i16> @llvm.riscv.vbrev.mask.nxv4i16(
+  <vscale x 4 x i16>,
+  <vscale x 4 x i16>,
+  <vscale x 4 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 4 x i16> @intrinsic_vbrev_mask_vs_nxv4i16(<vscale x 4 x i1> %0, <vscale x 4 x i16> %1, <vscale x 4 x i16> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vbrev_mask_vs_nxv4i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, m1, ta, mu
+; CHECK-NEXT:    vbrev.v v8, v9, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i16> @llvm.riscv.vbrev.mask.nxv4i16(
+    <vscale x 4 x i16> %1,
+    <vscale x 4 x i16> %2,
+    <vscale x 4 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 4 x i16> %a
+}
+
+declare <vscale x 8 x i16> @llvm.riscv.vbrev.nxv8i16(
+  <vscale x 8 x i16>,
+  <vscale x 8 x i16>,
+  iXLen);
+
+define <vscale x 8 x i16> @intrinsic_vbrev_vs_nxv8i16(<vscale x 8 x i16> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vbrev_vs_nxv8i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, m2, ta, ma
+; CHECK-NEXT:    vbrev.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i16> @llvm.riscv.vbrev.nxv8i16(
+    <vscale x 8 x i16> undef,
+    <vscale x 8 x i16> %0,
+    iXLen %1)
+
+  ret <vscale x 8 x i16> %a
+}
+
+declare <vscale x 8 x i16> @llvm.riscv.vbrev.mask.nxv8i16(
+  <vscale x 8 x i16>,
+  <vscale x 8 x i16>,
+  <vscale x 8 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 8 x i16> @intrinsic_vbrev_mask_vs_nxv8i16(<vscale x 8 x i1> %0, <vscale x 8 x i16> %1, <vscale x 8 x i16> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vbrev_mask_vs_nxv8i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, m2, ta, mu
+; CHECK-NEXT:    vbrev.v v8, v10, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i16> @llvm.riscv.vbrev.mask.nxv8i16(
+    <vscale x 8 x i16> %1,
+    <vscale x 8 x i16> %2,
+    <vscale x 8 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 8 x i16> %a
+}
+
+declare <vscale x 16 x i16> @llvm.riscv.vbrev.nxv16i16(
+  <vscale x 16 x i16>,
+  <vscale x 16 x i16>,
+  iXLen);
+
+define <vscale x 16 x i16> @intrinsic_vbrev_vs_nxv16i16(<vscale x 16 x i16> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vbrev_vs_nxv16i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, m4, ta, ma
+; CHECK-NEXT:    vbrev.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 16 x i16> @llvm.riscv.vbrev.nxv16i16(
+    <vscale x 16 x i16> undef,
+    <vscale x 16 x i16> %0,
+    iXLen %1)
+
+  ret <vscale x 16 x i16> %a
+}
+
+declare <vscale x 16 x i16> @llvm.riscv.vbrev.mask.nxv16i16(
+  <vscale x 16 x i16>,
+  <vscale x 16 x i16>,
+  <vscale x 16 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 16 x i16> @intrinsic_vbrev_mask_vs_nxv16i16(<vscale x 16 x i1> %0, <vscale x 16 x i16> %1, <vscale x 16 x i16> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vbrev_mask_vs_nxv16i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, m4, ta, mu
+; CHECK-NEXT:    vbrev.v v8, v12, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 16 x i16> @llvm.riscv.vbrev.mask.nxv16i16(
+    <vscale x 16 x i16> %1,
+    <vscale x 16 x i16> %2,
+    <vscale x 16 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 16 x i16> %a
+}
+
+declare <vscale x 32 x i16> @llvm.riscv.vbrev.nxv32i16(
+  <vscale x 32 x i16>,
+  <vscale x 32 x i16>,
+  iXLen);
+
+define <vscale x 32 x i16> @intrinsic_vbrev_vs_nxv32i16(<vscale x 32 x i16> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vbrev_vs_nxv32i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, m8, ta, ma
+; CHECK-NEXT:    vbrev.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 32 x i16> @llvm.riscv.vbrev.nxv32i16(
+    <vscale x 32 x i16> undef,
+    <vscale x 32 x i16> %0,
+    iXLen %1)
+
+  ret <vscale x 32 x i16> %a
+}
+
+declare <vscale x 32 x i16> @llvm.riscv.vbrev.mask.nxv32i16(
+  <vscale x 32 x i16>,
+  <vscale x 32 x i16>,
+  <vscale x 32 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 32 x i16> @intrinsic_vbrev_mask_vs_nxv32i16(<vscale x 32 x i1> %0, <vscale x 32 x i16> %1, <vscale x 32 x i16> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vbrev_mask_vs_nxv32i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, m8, ta, mu
+; CHECK-NEXT:    vbrev.v v8, v16, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 32 x i16> @llvm.riscv.vbrev.mask.nxv32i16(
+    <vscale x 32 x i16> %1,
+    <vscale x 32 x i16> %2,
+    <vscale x 32 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 32 x i16> %a
+}
+
+declare <vscale x 1 x i32> @llvm.riscv.vbrev.nxv1i32(
+  <vscale x 1 x i32>,
+  <vscale x 1 x i32>,
+  iXLen);
+
+define <vscale x 1 x i32> @intrinsic_vbrev_vs_nxv1i32(<vscale x 1 x i32> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vbrev_vs_nxv1i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, mf2, ta, ma
+; CHECK-NEXT:    vbrev.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i32> @llvm.riscv.vbrev.nxv1i32(
+    <vscale x 1 x i32> undef,
+    <vscale x 1 x i32> %0,
+    iXLen %1)
+
+  ret <vscale x 1 x i32> %a
+}
+
+declare <vscale x 1 x i32> @llvm.riscv.vbrev.mask.nxv1i32(
+  <vscale x 1 x i32>,
+  <vscale x 1 x i32>,
+  <vscale x 1 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 1 x i32> @intrinsic_vbrev_mask_vs_nxv1i32(<vscale x 1 x i1> %0, <vscale x 1 x i32> %1, <vscale x 1 x i32> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vbrev_mask_vs_nxv1i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, mf2, ta, mu
+; CHECK-NEXT:    vbrev.v v8, v9, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i32> @llvm.riscv.vbrev.mask.nxv1i32(
+    <vscale x 1 x i32> %1,
+    <vscale x 1 x i32> %2,
+    <vscale x 1 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 1 x i32> %a
+}
+
+declare <vscale x 2 x i32> @llvm.riscv.vbrev.nxv2i32(
+  <vscale x 2 x i32>,
+  <vscale x 2 x i32>,
+  iXLen);
+
+define <vscale x 2 x i32> @intrinsic_vbrev_vs_nxv2i32(<vscale x 2 x i32> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vbrev_vs_nxv2i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m1, ta, ma
+; CHECK-NEXT:    vbrev.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i32> @llvm.riscv.vbrev.nxv2i32(
+    <vscale x 2 x i32> undef,
+    <vscale x 2 x i32> %0,
+    iXLen %1)
+
+  ret <vscale x 2 x i32> %a
+}
+
+declare <vscale x 2 x i32> @llvm.riscv.vbrev.mask.nxv2i32(
+  <vscale x 2 x i32>,
+  <vscale x 2 x i32>,
+  <vscale x 2 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 2 x i32> @intrinsic_vbrev_mask_vs_nxv2i32(<vscale x 2 x i1> %0, <vscale x 2 x i32> %1, <vscale x 2 x i32> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vbrev_mask_vs_nxv2i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m1, ta, mu
+; CHECK-NEXT:    vbrev.v v8, v9, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i32> @llvm.riscv.vbrev.mask.nxv2i32(
+    <vscale x 2 x i32> %1,
+    <vscale x 2 x i32> %2,
+    <vscale x 2 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 2 x i32> %a
+}
+
+declare <vscale x 4 x i32> @llvm.riscv.vbrev.nxv4i32(
+  <vscale x 4 x i32>,
+  <vscale x 4 x i32>,
+  iXLen);
+
+define <vscale x 4 x i32> @intrinsic_vbrev_vs_nxv4i32(<vscale x 4 x i32> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vbrev_vs_nxv4i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m2, ta, ma
+; CHECK-NEXT:    vbrev.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i32> @llvm.riscv.vbrev.nxv4i32(
+    <vscale x 4 x i32> undef,
+    <vscale x 4 x i32> %0,
+    iXLen %1)
+
+  ret <vscale x 4 x i32> %a
+}
+
+declare <vscale x 4 x i32> @llvm.riscv.vbrev.mask.nxv4i32(
+  <vscale x 4 x i32>,
+  <vscale x 4 x i32>,
+  <vscale x 4 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 4 x i32> @intrinsic_vbrev_mask_vs_nxv4i32(<vscale x 4 x i1> %0, <vscale x 4 x i32> %1, <vscale x 4 x i32> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vbrev_mask_vs_nxv4i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m2, ta, mu
+; CHECK-NEXT:    vbrev.v v8, v10, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i32> @llvm.riscv.vbrev.mask.nxv4i32(
+    <vscale x 4 x i32> %1,
+    <vscale x 4 x i32> %2,
+    <vscale x 4 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 4 x i32> %a
+}
+
+declare <vscale x 8 x i32> @llvm.riscv.vbrev.nxv8i32(
+  <vscale x 8 x i32>,
+  <vscale x 8 x i32>,
+  iXLen);
+
+define <vscale x 8 x i32> @intrinsic_vbrev_vs_nxv8i32(<vscale x 8 x i32> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vbrev_vs_nxv8i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m4, ta, ma
+; CHECK-NEXT:    vbrev.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i32> @llvm.riscv.vbrev.nxv8i32(
+    <vscale x 8 x i32> undef,
+    <vscale x 8 x i32> %0,
+    iXLen %1)
+
+  ret <vscale x 8 x i32> %a
+}
+
+declare <vscale x 8 x i32> @llvm.riscv.vbrev.mask.nxv8i32(
+  <vscale x 8 x i32>,
+  <vscale x 8 x i32>,
+  <vscale x 8 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 8 x i32> @intrinsic_vbrev_mask_vs_nxv8i32(<vscale x 8 x i1> %0, <vscale x 8 x i32> %1, <vscale x 8 x i32> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vbrev_mask_vs_nxv8i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m4, ta, mu
+; CHECK-NEXT:    vbrev.v v8, v12, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i32> @llvm.riscv.vbrev.mask.nxv8i32(
+    <vscale x 8 x i32> %1,
+    <vscale x 8 x i32> %2,
+    <vscale x 8 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 8 x i32> %a
+}
+
+declare <vscale x 16 x i32> @llvm.riscv.vbrev.nxv16i32(
+  <vscale x 16 x i32>,
+  <vscale x 16 x i32>,
+  iXLen);
+
+define <vscale x 16 x i32> @intrinsic_vbrev_vs_nxv16i32(<vscale x 16 x i32> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vbrev_vs_nxv16i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m8, ta, ma
+; CHECK-NEXT:    vbrev.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 16 x i32> @llvm.riscv.vbrev.nxv16i32(
+    <vscale x 16 x i32> undef,
+    <vscale x 16 x i32> %0,
+    iXLen %1)
+
+  ret <vscale x 16 x i32> %a
+}
+
+declare <vscale x 16 x i32> @llvm.riscv.vbrev.mask.nxv16i32(
+  <vscale x 16 x i32>,
+  <vscale x 16 x i32>,
+  <vscale x 16 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 16 x i32> @intrinsic_vbrev_mask_vs_nxv16i32(<vscale x 16 x i1> %0, <vscale x 16 x i32> %1, <vscale x 16 x i32> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vbrev_mask_vs_nxv16i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m8, ta, mu
+; CHECK-NEXT:    vbrev.v v8, v16, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 16 x i32> @llvm.riscv.vbrev.mask.nxv16i32(
+    <vscale x 16 x i32> %1,
+    <vscale x 16 x i32> %2,
+    <vscale x 16 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 16 x i32> %a
+}
+
+declare <vscale x 1 x i64> @llvm.riscv.vbrev.nxv1i64(
+  <vscale x 1 x i64>,
+  <vscale x 1 x i64>,
+  iXLen);
+
+define <vscale x 1 x i64> @intrinsic_vbrev_vs_nxv1i64(<vscale x 1 x i64> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vbrev_vs_nxv1i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e64, m1, ta, ma
+; CHECK-NEXT:    vbrev.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i64> @llvm.riscv.vbrev.nxv1i64(
+    <vscale x 1 x i64> undef,
+    <vscale x 1 x i64> %0,
+    iXLen %1)
+
+  ret <vscale x 1 x i64> %a
+}
+
+declare <vscale x 1 x i64> @llvm.riscv.vbrev.mask.nxv1i64(
+  <vscale x 1 x i64>,
+  <vscale x 1 x i64>,
+  <vscale x 1 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 1 x i64> @intrinsic_vbrev_mask_vs_nxv1i64(<vscale x 1 x i1> %0, <vscale x 1 x i64> %1, <vscale x 1 x i64> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vbrev_mask_vs_nxv1i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e64, m1, ta, mu
+; CHECK-NEXT:    vbrev.v v8, v9, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i64> @llvm.riscv.vbrev.mask.nxv1i64(
+    <vscale x 1 x i64> %1,
+    <vscale x 1 x i64> %2,
+    <vscale x 1 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 1 x i64> %a
+}
+
+declare <vscale x 2 x i64> @llvm.riscv.vbrev.nxv2i64(
+  <vscale x 2 x i64>,
+  <vscale x 2 x i64>,
+  iXLen);
+
+define <vscale x 2 x i64> @intrinsic_vbrev_vs_nxv2i64(<vscale x 2 x i64> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vbrev_vs_nxv2i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e64, m2, ta, ma
+; CHECK-NEXT:    vbrev.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i64> @llvm.riscv.vbrev.nxv2i64(
+    <vscale x 2 x i64> undef,
+    <vscale x 2 x i64> %0,
+    iXLen %1)
+
+  ret <vscale x 2 x i64> %a
+}
+
+declare <vscale x 2 x i64> @llvm.riscv.vbrev.mask.nxv2i64(
+  <vscale x 2 x i64>,
+  <vscale x 2 x i64>,
+  <vscale x 2 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 2 x i64> @intrinsic_vbrev_mask_vs_nxv2i64(<vscale x 2 x i1> %0, <vscale x 2 x i64> %1, <vscale x 2 x i64> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vbrev_mask_vs_nxv2i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e64, m2, ta, mu
+; CHECK-NEXT:    vbrev.v v8, v10, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i64> @llvm.riscv.vbrev.mask.nxv2i64(
+    <vscale x 2 x i64> %1,
+    <vscale x 2 x i64> %2,
+    <vscale x 2 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 2 x i64> %a
+}
+
+declare <vscale x 4 x i64> @llvm.riscv.vbrev.nxv4i64(
+  <vscale x 4 x i64>,
+  <vscale x 4 x i64>,
+  iXLen);
+
+define <vscale x 4 x i64> @intrinsic_vbrev_vs_nxv4i64(<vscale x 4 x i64> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vbrev_vs_nxv4i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e64, m4, ta, ma
+; CHECK-NEXT:    vbrev.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i64> @llvm.riscv.vbrev.nxv4i64(
+    <vscale x 4 x i64> undef,
+    <vscale x 4 x i64> %0,
+    iXLen %1)
+
+  ret <vscale x 4 x i64> %a
+}
+
+declare <vscale x 4 x i64> @llvm.riscv.vbrev.mask.nxv4i64(
+  <vscale x 4 x i64>,
+  <vscale x 4 x i64>,
+  <vscale x 4 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 4 x i64> @intrinsic_vbrev_mask_vs_nxv4i64(<vscale x 4 x i1> %0, <vscale x 4 x i64> %1, <vscale x 4 x i64> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vbrev_mask_vs_nxv4i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e64, m4, ta, mu
+; CHECK-NEXT:    vbrev.v v8, v12, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i64> @llvm.riscv.vbrev.mask.nxv4i64(
+    <vscale x 4 x i64> %1,
+    <vscale x 4 x i64> %2,
+    <vscale x 4 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 4 x i64> %a
+}
+
+declare <vscale x 8 x i64> @llvm.riscv.vbrev.nxv8i64(
+  <vscale x 8 x i64>,
+  <vscale x 8 x i64>,
+  iXLen);
+
+define <vscale x 8 x i64> @intrinsic_vbrev_vs_nxv8i64(<vscale x 8 x i64> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vbrev_vs_nxv8i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
+; CHECK-NEXT:    vbrev.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i64> @llvm.riscv.vbrev.nxv8i64(
+    <vscale x 8 x i64> undef,
+    <vscale x 8 x i64> %0,
+    iXLen %1)
+
+  ret <vscale x 8 x i64> %a
+}
+
+declare <vscale x 8 x i64> @llvm.riscv.vbrev.mask.nxv8i64(
+  <vscale x 8 x i64>,
+  <vscale x 8 x i64>,
+  <vscale x 8 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 8 x i64> @intrinsic_vbrev_mask_vs_nxv8i64(<vscale x 8 x i1> %0, <vscale x 8 x i64> %1, <vscale x 8 x i64> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vbrev_mask_vs_nxv8i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, mu
+; CHECK-NEXT:    vbrev.v v8, v16, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i64> @llvm.riscv.vbrev.mask.nxv8i64(
+    <vscale x 8 x i64> %1,
+    <vscale x 8 x i64> %2,
+    <vscale x 8 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 8 x i64> %a
+}

llvm/test/CodeGen/RISCV/rvv/vbrev8.ll

+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: sed 's/iXLen/i32/g' %s | llc -mtriple=riscv32 -mattr=+v,+experimental-zvbb \
+; RUN:   -verify-machineinstrs | FileCheck %s --check-prefixes=CHECK
+; RUN: sed 's/iXLen/i64/g' %s | llc -mtriple=riscv64 -mattr=+v,+experimental-zvbb \
+; RUN:   -verify-machineinstrs | FileCheck %s --check-prefixes=CHECK
+
+declare <vscale x 1 x i8> @llvm.riscv.vbrev8.nxv1i8(
+  <vscale x 1 x i8>,
+  <vscale x 1 x i8>,
+  iXLen);
+
+define <vscale x 1 x i8> @intrinsic_vbrev8_vs_nxv1i8(<vscale x 1 x i8> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vbrev8_vs_nxv1i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, mf8, ta, ma
+; CHECK-NEXT:    vbrev8.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i8> @llvm.riscv.vbrev8.nxv1i8(
+    <vscale x 1 x i8> undef,
+    <vscale x 1 x i8> %0,
+    iXLen %1)
+
+  ret <vscale x 1 x i8> %a
+}
+
+declare <vscale x 1 x i8> @llvm.riscv.vbrev8.mask.nxv1i8(
+  <vscale x 1 x i8>,
+  <vscale x 1 x i8>,
+  <vscale x 1 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 1 x i8> @intrinsic_vbrev8_mask_vs_nxv1i8(<vscale x 1 x i1> %0, <vscale x 1 x i8> %1, <vscale x 1 x i8> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vbrev8_mask_vs_nxv1i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, mf8, ta, mu
+; CHECK-NEXT:    vbrev8.v v8, v9, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i8> @llvm.riscv.vbrev8.mask.nxv1i8(
+    <vscale x 1 x i8> %1,
+    <vscale x 1 x i8> %2,
+    <vscale x 1 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 1 x i8> %a
+}
+
+declare <vscale x 2 x i8> @llvm.riscv.vbrev8.nxv2i8(
+  <vscale x 2 x i8>,
+  <vscale x 2 x i8>,
+  iXLen);
+
+define <vscale x 2 x i8> @intrinsic_vbrev8_vs_nxv2i8(<vscale x 2 x i8> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vbrev8_vs_nxv2i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, mf4, ta, ma
+; CHECK-NEXT:    vbrev8.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i8> @llvm.riscv.vbrev8.nxv2i8(
+    <vscale x 2 x i8> undef,
+    <vscale x 2 x i8> %0,
+    iXLen %1)
+
+  ret <vscale x 2 x i8> %a
+}
+
+declare <vscale x 2 x i8> @llvm.riscv.vbrev8.mask.nxv2i8(
+  <vscale x 2 x i8>,
+  <vscale x 2 x i8>,
+  <vscale x 2 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 2 x i8> @intrinsic_vbrev8_mask_vs_nxv2i8(<vscale x 2 x i1> %0, <vscale x 2 x i8> %1, <vscale x 2 x i8> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vbrev8_mask_vs_nxv2i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, mf4, ta, mu
+; CHECK-NEXT:    vbrev8.v v8, v9, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i8> @llvm.riscv.vbrev8.mask.nxv2i8(
+    <vscale x 2 x i8> %1,
+    <vscale x 2 x i8> %2,
+    <vscale x 2 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 2 x i8> %a
+}
+
+declare <vscale x 4 x i8> @llvm.riscv.vbrev8.nxv4i8(
+  <vscale x 4 x i8>,
+  <vscale x 4 x i8>,
+  iXLen);
+
+define <vscale x 4 x i8> @intrinsic_vbrev8_vs_nxv4i8(<vscale x 4 x i8> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vbrev8_vs_nxv4i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, mf2, ta, ma
+; CHECK-NEXT:    vbrev8.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i8> @llvm.riscv.vbrev8.nxv4i8(
+    <vscale x 4 x i8> undef,
+    <vscale x 4 x i8> %0,
+    iXLen %1)
+
+  ret <vscale x 4 x i8> %a
+}
+
+declare <vscale x 4 x i8> @llvm.riscv.vbrev8.mask.nxv4i8(
+  <vscale x 4 x i8>,
+  <vscale x 4 x i8>,
+  <vscale x 4 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 4 x i8> @intrinsic_vbrev8_mask_vs_nxv4i8(<vscale x 4 x i1> %0, <vscale x 4 x i8> %1, <vscale x 4 x i8> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vbrev8_mask_vs_nxv4i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, mf2, ta, mu
+; CHECK-NEXT:    vbrev8.v v8, v9, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i8> @llvm.riscv.vbrev8.mask.nxv4i8(
+    <vscale x 4 x i8> %1,
+    <vscale x 4 x i8> %2,
+    <vscale x 4 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 4 x i8> %a
+}
+
+declare <vscale x 8 x i8> @llvm.riscv.vbrev8.nxv8i8(
+  <vscale x 8 x i8>,
+  <vscale x 8 x i8>,
+  iXLen);
+
+define <vscale x 8 x i8> @intrinsic_vbrev8_vs_nxv8i8(<vscale x 8 x i8> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vbrev8_vs_nxv8i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, m1, ta, ma
+; CHECK-NEXT:    vbrev8.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i8> @llvm.riscv.vbrev8.nxv8i8(
+    <vscale x 8 x i8> undef,
+    <vscale x 8 x i8> %0,
+    iXLen %1)
+
+  ret <vscale x 8 x i8> %a
+}
+
+declare <vscale x 8 x i8> @llvm.riscv.vbrev8.mask.nxv8i8(
+  <vscale x 8 x i8>,
+  <vscale x 8 x i8>,
+  <vscale x 8 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 8 x i8> @intrinsic_vbrev8_mask_vs_nxv8i8(<vscale x 8 x i1> %0, <vscale x 8 x i8> %1, <vscale x 8 x i8> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vbrev8_mask_vs_nxv8i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, m1, ta, mu
+; CHECK-NEXT:    vbrev8.v v8, v9, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i8> @llvm.riscv.vbrev8.mask.nxv8i8(
+    <vscale x 8 x i8> %1,
+    <vscale x 8 x i8> %2,
+    <vscale x 8 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 8 x i8> %a
+}
+
+declare <vscale x 16 x i8> @llvm.riscv.vbrev8.nxv16i8(
+  <vscale x 16 x i8>,
+  <vscale x 16 x i8>,
+  iXLen);
+
+define <vscale x 16 x i8> @intrinsic_vbrev8_vs_nxv16i8(<vscale x 16 x i8> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vbrev8_vs_nxv16i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, m2, ta, ma
+; CHECK-NEXT:    vbrev8.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 16 x i8> @llvm.riscv.vbrev8.nxv16i8(
+    <vscale x 16 x i8> undef,
+    <vscale x 16 x i8> %0,
+    iXLen %1)
+
+  ret <vscale x 16 x i8> %a
+}
+
+declare <vscale x 16 x i8> @llvm.riscv.vbrev8.mask.nxv16i8(
+  <vscale x 16 x i8>,
+  <vscale x 16 x i8>,
+  <vscale x 16 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 16 x i8> @intrinsic_vbrev8_mask_vs_nxv16i8(<vscale x 16 x i1> %0, <vscale x 16 x i8> %1, <vscale x 16 x i8> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vbrev8_mask_vs_nxv16i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, m2, ta, mu
+; CHECK-NEXT:    vbrev8.v v8, v10, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 16 x i8> @llvm.riscv.vbrev8.mask.nxv16i8(
+    <vscale x 16 x i8> %1,
+    <vscale x 16 x i8> %2,
+    <vscale x 16 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 16 x i8> %a
+}
+
+declare <vscale x 32 x i8> @llvm.riscv.vbrev8.nxv32i8(
+  <vscale x 32 x i8>,
+  <vscale x 32 x i8>,
+  iXLen);
+
+define <vscale x 32 x i8> @intrinsic_vbrev8_vs_nxv32i8(<vscale x 32 x i8> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vbrev8_vs_nxv32i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, m4, ta, ma
+; CHECK-NEXT:    vbrev8.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 32 x i8> @llvm.riscv.vbrev8.nxv32i8(
+    <vscale x 32 x i8> undef,
+    <vscale x 32 x i8> %0,
+    iXLen %1)
+
+  ret <vscale x 32 x i8> %a
+}
+
+declare <vscale x 32 x i8> @llvm.riscv.vbrev8.mask.nxv32i8(
+  <vscale x 32 x i8>,
+  <vscale x 32 x i8>,
+  <vscale x 32 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 32 x i8> @intrinsic_vbrev8_mask_vs_nxv32i8(<vscale x 32 x i1> %0, <vscale x 32 x i8> %1, <vscale x 32 x i8> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vbrev8_mask_vs_nxv32i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, m4, ta, mu
+; CHECK-NEXT:    vbrev8.v v8, v12, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 32 x i8> @llvm.riscv.vbrev8.mask.nxv32i8(
+    <vscale x 32 x i8> %1,
+    <vscale x 32 x i8> %2,
+    <vscale x 32 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 32 x i8> %a
+}
+
+declare <vscale x 64 x i8> @llvm.riscv.vbrev8.nxv64i8(
+  <vscale x 64 x i8>,
+  <vscale x 64 x i8>,
+  iXLen);
+
+define <vscale x 64 x i8> @intrinsic_vbrev8_vs_nxv64i8(<vscale x 64 x i8> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vbrev8_vs_nxv64i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, m8, ta, ma
+; CHECK-NEXT:    vbrev8.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 64 x i8> @llvm.riscv.vbrev8.nxv64i8(
+    <vscale x 64 x i8> undef,
+    <vscale x 64 x i8> %0,
+    iXLen %1)
+
+  ret <vscale x 64 x i8> %a
+}
+
+declare <vscale x 64 x i8> @llvm.riscv.vbrev8.mask.nxv64i8(
+  <vscale x 64 x i8>,
+  <vscale x 64 x i8>,
+  <vscale x 64 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 64 x i8> @intrinsic_vbrev8_mask_vs_nxv64i8(<vscale x 64 x i1> %0, <vscale x 64 x i8> %1, <vscale x 64 x i8> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vbrev8_mask_vs_nxv64i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, m8, ta, mu
+; CHECK-NEXT:    vbrev8.v v8, v16, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 64 x i8> @llvm.riscv.vbrev8.mask.nxv64i8(
+    <vscale x 64 x i8> %1,
+    <vscale x 64 x i8> %2,
+    <vscale x 64 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 64 x i8> %a
+}
+
+declare <vscale x 1 x i16> @llvm.riscv.vbrev8.nxv1i16(
+  <vscale x 1 x i16>,
+  <vscale x 1 x i16>,
+  iXLen);
+
+define <vscale x 1 x i16> @intrinsic_vbrev8_vs_nxv1i16(<vscale x 1 x i16> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vbrev8_vs_nxv1i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, mf4, ta, ma
+; CHECK-NEXT:    vbrev8.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i16> @llvm.riscv.vbrev8.nxv1i16(
+    <vscale x 1 x i16> undef,
+    <vscale x 1 x i16> %0,
+    iXLen %1)
+
+  ret <vscale x 1 x i16> %a
+}
+
+declare <vscale x 1 x i16> @llvm.riscv.vbrev8.mask.nxv1i16(
+  <vscale x 1 x i16>,
+  <vscale x 1 x i16>,
+  <vscale x 1 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 1 x i16> @intrinsic_vbrev8_mask_vs_nxv1i16(<vscale x 1 x i1> %0, <vscale x 1 x i16> %1, <vscale x 1 x i16> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vbrev8_mask_vs_nxv1i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, mf4, ta, mu
+; CHECK-NEXT:    vbrev8.v v8, v9, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i16> @llvm.riscv.vbrev8.mask.nxv1i16(
+    <vscale x 1 x i16> %1,
+    <vscale x 1 x i16> %2,
+    <vscale x 1 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 1 x i16> %a
+}
+
+declare <vscale x 2 x i16> @llvm.riscv.vbrev8.nxv2i16(
+  <vscale x 2 x i16>,
+  <vscale x 2 x i16>,
+  iXLen);
+
+define <vscale x 2 x i16> @intrinsic_vbrev8_vs_nxv2i16(<vscale x 2 x i16> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vbrev8_vs_nxv2i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, mf2, ta, ma
+; CHECK-NEXT:    vbrev8.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i16> @llvm.riscv.vbrev8.nxv2i16(
+    <vscale x 2 x i16> undef,
+    <vscale x 2 x i16> %0,
+    iXLen %1)
+
+  ret <vscale x 2 x i16> %a
+}
+
+declare <vscale x 2 x i16> @llvm.riscv.vbrev8.mask.nxv2i16(
+  <vscale x 2 x i16>,
+  <vscale x 2 x i16>,
+  <vscale x 2 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 2 x i16> @intrinsic_vbrev8_mask_vs_nxv2i16(<vscale x 2 x i1> %0, <vscale x 2 x i16> %1, <vscale x 2 x i16> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vbrev8_mask_vs_nxv2i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, mf2, ta, mu
+; CHECK-NEXT:    vbrev8.v v8, v9, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i16> @llvm.riscv.vbrev8.mask.nxv2i16(
+    <vscale x 2 x i16> %1,
+    <vscale x 2 x i16> %2,
+    <vscale x 2 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 2 x i16> %a
+}
+
+declare <vscale x 4 x i16> @llvm.riscv.vbrev8.nxv4i16(
+  <vscale x 4 x i16>,
+  <vscale x 4 x i16>,
+  iXLen);
+
+define <vscale x 4 x i16> @intrinsic_vbrev8_vs_nxv4i16(<vscale x 4 x i16> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vbrev8_vs_nxv4i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, m1, ta, ma
+; CHECK-NEXT:    vbrev8.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i16> @llvm.riscv.vbrev8.nxv4i16(
+    <vscale x 4 x i16> undef,
+    <vscale x 4 x i16> %0,
+    iXLen %1)
+
+  ret <vscale x 4 x i16> %a
+}
+
+declare <vscale x 4 x i16> @llvm.riscv.vbrev8.mask.nxv4i16(
+  <vscale x 4 x i16>,
+  <vscale x 4 x i16>,
+  <vscale x 4 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 4 x i16> @intrinsic_vbrev8_mask_vs_nxv4i16(<vscale x 4 x i1> %0, <vscale x 4 x i16> %1, <vscale x 4 x i16> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vbrev8_mask_vs_nxv4i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, m1, ta, mu
+; CHECK-NEXT:    vbrev8.v v8, v9, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i16> @llvm.riscv.vbrev8.mask.nxv4i16(
+    <vscale x 4 x i16> %1,
+    <vscale x 4 x i16> %2,
+    <vscale x 4 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 4 x i16> %a
+}
+
+declare <vscale x 8 x i16> @llvm.riscv.vbrev8.nxv8i16(
+  <vscale x 8 x i16>,
+  <vscale x 8 x i16>,
+  iXLen);
+
+define <vscale x 8 x i16> @intrinsic_vbrev8_vs_nxv8i16(<vscale x 8 x i16> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vbrev8_vs_nxv8i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, m2, ta, ma
+; CHECK-NEXT:    vbrev8.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i16> @llvm.riscv.vbrev8.nxv8i16(
+    <vscale x 8 x i16> undef,
+    <vscale x 8 x i16> %0,
+    iXLen %1)
+
+  ret <vscale x 8 x i16> %a
+}
+
+declare <vscale x 8 x i16> @llvm.riscv.vbrev8.mask.nxv8i16(
+  <vscale x 8 x i16>,
+  <vscale x 8 x i16>,
+  <vscale x 8 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 8 x i16> @intrinsic_vbrev8_mask_vs_nxv8i16(<vscale x 8 x i1> %0, <vscale x 8 x i16> %1, <vscale x 8 x i16> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vbrev8_mask_vs_nxv8i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, m2, ta, mu
+; CHECK-NEXT:    vbrev8.v v8, v10, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i16> @llvm.riscv.vbrev8.mask.nxv8i16(
+    <vscale x 8 x i16> %1,
+    <vscale x 8 x i16> %2,
+    <vscale x 8 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 8 x i16> %a
+}
+
+declare <vscale x 16 x i16> @llvm.riscv.vbrev8.nxv16i16(
+  <vscale x 16 x i16>,
+  <vscale x 16 x i16>,
+  iXLen);
+
+define <vscale x 16 x i16> @intrinsic_vbrev8_vs_nxv16i16(<vscale x 16 x i16> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vbrev8_vs_nxv16i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, m4, ta, ma
+; CHECK-NEXT:    vbrev8.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 16 x i16> @llvm.riscv.vbrev8.nxv16i16(
+    <vscale x 16 x i16> undef,
+    <vscale x 16 x i16> %0,
+    iXLen %1)
+
+  ret <vscale x 16 x i16> %a
+}
+
+declare <vscale x 16 x i16> @llvm.riscv.vbrev8.mask.nxv16i16(
+  <vscale x 16 x i16>,
+  <vscale x 16 x i16>,
+  <vscale x 16 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 16 x i16> @intrinsic_vbrev8_mask_vs_nxv16i16(<vscale x 16 x i1> %0, <vscale x 16 x i16> %1, <vscale x 16 x i16> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vbrev8_mask_vs_nxv16i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, m4, ta, mu
+; CHECK-NEXT:    vbrev8.v v8, v12, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 16 x i16> @llvm.riscv.vbrev8.mask.nxv16i16(
+    <vscale x 16 x i16> %1,
+    <vscale x 16 x i16> %2,
+    <vscale x 16 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 16 x i16> %a
+}
+
+declare <vscale x 32 x i16> @llvm.riscv.vbrev8.nxv32i16(
+  <vscale x 32 x i16>,
+  <vscale x 32 x i16>,
+  iXLen);
+
+define <vscale x 32 x i16> @intrinsic_vbrev8_vs_nxv32i16(<vscale x 32 x i16> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vbrev8_vs_nxv32i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, m8, ta, ma
+; CHECK-NEXT:    vbrev8.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 32 x i16> @llvm.riscv.vbrev8.nxv32i16(
+    <vscale x 32 x i16> undef,
+    <vscale x 32 x i16> %0,
+    iXLen %1)
+
+  ret <vscale x 32 x i16> %a
+}
+
+declare <vscale x 32 x i16> @llvm.riscv.vbrev8.mask.nxv32i16(
+  <vscale x 32 x i16>,
+  <vscale x 32 x i16>,
+  <vscale x 32 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 32 x i16> @intrinsic_vbrev8_mask_vs_nxv32i16(<vscale x 32 x i1> %0, <vscale x 32 x i16> %1, <vscale x 32 x i16> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vbrev8_mask_vs_nxv32i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, m8, ta, mu
+; CHECK-NEXT:    vbrev8.v v8, v16, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 32 x i16> @llvm.riscv.vbrev8.mask.nxv32i16(
+    <vscale x 32 x i16> %1,
+    <vscale x 32 x i16> %2,
+    <vscale x 32 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 32 x i16> %a
+}
+
+declare <vscale x 1 x i32> @llvm.riscv.vbrev8.nxv1i32(
+  <vscale x 1 x i32>,
+  <vscale x 1 x i32>,
+  iXLen);
+
+define <vscale x 1 x i32> @intrinsic_vbrev8_vs_nxv1i32(<vscale x 1 x i32> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vbrev8_vs_nxv1i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, mf2, ta, ma
+; CHECK-NEXT:    vbrev8.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i32> @llvm.riscv.vbrev8.nxv1i32(
+    <vscale x 1 x i32> undef,
+    <vscale x 1 x i32> %0,
+    iXLen %1)
+
+  ret <vscale x 1 x i32> %a
+}
+
+declare <vscale x 1 x i32> @llvm.riscv.vbrev8.mask.nxv1i32(
+  <vscale x 1 x i32>,
+  <vscale x 1 x i32>,
+  <vscale x 1 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 1 x i32> @intrinsic_vbrev8_mask_vs_nxv1i32(<vscale x 1 x i1> %0, <vscale x 1 x i32> %1, <vscale x 1 x i32> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vbrev8_mask_vs_nxv1i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, mf2, ta, mu
+; CHECK-NEXT:    vbrev8.v v8, v9, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i32> @llvm.riscv.vbrev8.mask.nxv1i32(
+    <vscale x 1 x i32> %1,
+    <vscale x 1 x i32> %2,
+    <vscale x 1 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 1 x i32> %a
+}
+
+declare <vscale x 2 x i32> @llvm.riscv.vbrev8.nxv2i32(
+  <vscale x 2 x i32>,
+  <vscale x 2 x i32>,
+  iXLen);
+
+define <vscale x 2 x i32> @intrinsic_vbrev8_vs_nxv2i32(<vscale x 2 x i32> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vbrev8_vs_nxv2i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m1, ta, ma
+; CHECK-NEXT:    vbrev8.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i32> @llvm.riscv.vbrev8.nxv2i32(
+    <vscale x 2 x i32> undef,
+    <vscale x 2 x i32> %0,
+    iXLen %1)
+
+  ret <vscale x 2 x i32> %a
+}
+
+declare <vscale x 2 x i32> @llvm.riscv.vbrev8.mask.nxv2i32(
+  <vscale x 2 x i32>,
+  <vscale x 2 x i32>,
+  <vscale x 2 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 2 x i32> @intrinsic_vbrev8_mask_vs_nxv2i32(<vscale x 2 x i1> %0, <vscale x 2 x i32> %1, <vscale x 2 x i32> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vbrev8_mask_vs_nxv2i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m1, ta, mu
+; CHECK-NEXT:    vbrev8.v v8, v9, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i32> @llvm.riscv.vbrev8.mask.nxv2i32(
+    <vscale x 2 x i32> %1,
+    <vscale x 2 x i32> %2,
+    <vscale x 2 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 2 x i32> %a
+}
+
+declare <vscale x 4 x i32> @llvm.riscv.vbrev8.nxv4i32(
+  <vscale x 4 x i32>,
+  <vscale x 4 x i32>,
+  iXLen);
+
+define <vscale x 4 x i32> @intrinsic_vbrev8_vs_nxv4i32(<vscale x 4 x i32> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vbrev8_vs_nxv4i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m2, ta, ma
+; CHECK-NEXT:    vbrev8.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i32> @llvm.riscv.vbrev8.nxv4i32(
+    <vscale x 4 x i32> undef,
+    <vscale x 4 x i32> %0,
+    iXLen %1)
+
+  ret <vscale x 4 x i32> %a
+}
+
+declare <vscale x 4 x i32> @llvm.riscv.vbrev8.mask.nxv4i32(
+  <vscale x 4 x i32>,
+  <vscale x 4 x i32>,
+  <vscale x 4 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 4 x i32> @intrinsic_vbrev8_mask_vs_nxv4i32(<vscale x 4 x i1> %0, <vscale x 4 x i32> %1, <vscale x 4 x i32> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vbrev8_mask_vs_nxv4i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m2, ta, mu
+; CHECK-NEXT:    vbrev8.v v8, v10, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i32> @llvm.riscv.vbrev8.mask.nxv4i32(
+    <vscale x 4 x i32> %1,
+    <vscale x 4 x i32> %2,
+    <vscale x 4 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 4 x i32> %a
+}
+
+declare <vscale x 8 x i32> @llvm.riscv.vbrev8.nxv8i32(
+  <vscale x 8 x i32>,
+  <vscale x 8 x i32>,
+  iXLen);
+
+define <vscale x 8 x i32> @intrinsic_vbrev8_vs_nxv8i32(<vscale x 8 x i32> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vbrev8_vs_nxv8i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m4, ta, ma
+; CHECK-NEXT:    vbrev8.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i32> @llvm.riscv.vbrev8.nxv8i32(
+    <vscale x 8 x i32> undef,
+    <vscale x 8 x i32> %0,
+    iXLen %1)
+
+  ret <vscale x 8 x i32> %a
+}
+
+declare <vscale x 8 x i32> @llvm.riscv.vbrev8.mask.nxv8i32(
+  <vscale x 8 x i32>,
+  <vscale x 8 x i32>,
+  <vscale x 8 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 8 x i32> @intrinsic_vbrev8_mask_vs_nxv8i32(<vscale x 8 x i1> %0, <vscale x 8 x i32> %1, <vscale x 8 x i32> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vbrev8_mask_vs_nxv8i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m4, ta, mu
+; CHECK-NEXT:    vbrev8.v v8, v12, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i32> @llvm.riscv.vbrev8.mask.nxv8i32(
+    <vscale x 8 x i32> %1,
+    <vscale x 8 x i32> %2,
+    <vscale x 8 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 8 x i32> %a
+}
+
+declare <vscale x 16 x i32> @llvm.riscv.vbrev8.nxv16i32(
+  <vscale x 16 x i32>,
+  <vscale x 16 x i32>,
+  iXLen);
+
+define <vscale x 16 x i32> @intrinsic_vbrev8_vs_nxv16i32(<vscale x 16 x i32> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vbrev8_vs_nxv16i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m8, ta, ma
+; CHECK-NEXT:    vbrev8.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 16 x i32> @llvm.riscv.vbrev8.nxv16i32(
+    <vscale x 16 x i32> undef,
+    <vscale x 16 x i32> %0,
+    iXLen %1)
+
+  ret <vscale x 16 x i32> %a
+}
+
+declare <vscale x 16 x i32> @llvm.riscv.vbrev8.mask.nxv16i32(
+  <vscale x 16 x i32>,
+  <vscale x 16 x i32>,
+  <vscale x 16 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 16 x i32> @intrinsic_vbrev8_mask_vs_nxv16i32(<vscale x 16 x i1> %0, <vscale x 16 x i32> %1, <vscale x 16 x i32> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vbrev8_mask_vs_nxv16i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m8, ta, mu
+; CHECK-NEXT:    vbrev8.v v8, v16, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 16 x i32> @llvm.riscv.vbrev8.mask.nxv16i32(
+    <vscale x 16 x i32> %1,
+    <vscale x 16 x i32> %2,
+    <vscale x 16 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 16 x i32> %a
+}
+
+declare <vscale x 1 x i64> @llvm.riscv.vbrev8.nxv1i64(
+  <vscale x 1 x i64>,
+  <vscale x 1 x i64>,
+  iXLen);
+
+define <vscale x 1 x i64> @intrinsic_vbrev8_vs_nxv1i64(<vscale x 1 x i64> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vbrev8_vs_nxv1i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e64, m1, ta, ma
+; CHECK-NEXT:    vbrev8.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i64> @llvm.riscv.vbrev8.nxv1i64(
+    <vscale x 1 x i64> undef,
+    <vscale x 1 x i64> %0,
+    iXLen %1)
+
+  ret <vscale x 1 x i64> %a
+}
+
+declare <vscale x 1 x i64> @llvm.riscv.vbrev8.mask.nxv1i64(
+  <vscale x 1 x i64>,
+  <vscale x 1 x i64>,
+  <vscale x 1 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 1 x i64> @intrinsic_vbrev8_mask_vs_nxv1i64(<vscale x 1 x i1> %0, <vscale x 1 x i64> %1, <vscale x 1 x i64> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vbrev8_mask_vs_nxv1i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e64, m1, ta, mu
+; CHECK-NEXT:    vbrev8.v v8, v9, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i64> @llvm.riscv.vbrev8.mask.nxv1i64(
+    <vscale x 1 x i64> %1,
+    <vscale x 1 x i64> %2,
+    <vscale x 1 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 1 x i64> %a
+}
+
+declare <vscale x 2 x i64> @llvm.riscv.vbrev8.nxv2i64(
+  <vscale x 2 x i64>,
+  <vscale x 2 x i64>,
+  iXLen);
+
+define <vscale x 2 x i64> @intrinsic_vbrev8_vs_nxv2i64(<vscale x 2 x i64> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vbrev8_vs_nxv2i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e64, m2, ta, ma
+; CHECK-NEXT:    vbrev8.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i64> @llvm.riscv.vbrev8.nxv2i64(
+    <vscale x 2 x i64> undef,
+    <vscale x 2 x i64> %0,
+    iXLen %1)
+
+  ret <vscale x 2 x i64> %a
+}
+
+declare <vscale x 2 x i64> @llvm.riscv.vbrev8.mask.nxv2i64(
+  <vscale x 2 x i64>,
+  <vscale x 2 x i64>,
+  <vscale x 2 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 2 x i64> @intrinsic_vbrev8_mask_vs_nxv2i64(<vscale x 2 x i1> %0, <vscale x 2 x i64> %1, <vscale x 2 x i64> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vbrev8_mask_vs_nxv2i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e64, m2, ta, mu
+; CHECK-NEXT:    vbrev8.v v8, v10, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i64> @llvm.riscv.vbrev8.mask.nxv2i64(
+    <vscale x 2 x i64> %1,
+    <vscale x 2 x i64> %2,
+    <vscale x 2 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 2 x i64> %a
+}
+
+declare <vscale x 4 x i64> @llvm.riscv.vbrev8.nxv4i64(
+  <vscale x 4 x i64>,
+  <vscale x 4 x i64>,
+  iXLen);
+
+define <vscale x 4 x i64> @intrinsic_vbrev8_vs_nxv4i64(<vscale x 4 x i64> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vbrev8_vs_nxv4i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e64, m4, ta, ma
+; CHECK-NEXT:    vbrev8.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i64> @llvm.riscv.vbrev8.nxv4i64(
+    <vscale x 4 x i64> undef,
+    <vscale x 4 x i64> %0,
+    iXLen %1)
+
+  ret <vscale x 4 x i64> %a
+}
+
+declare <vscale x 4 x i64> @llvm.riscv.vbrev8.mask.nxv4i64(
+  <vscale x 4 x i64>,
+  <vscale x 4 x i64>,
+  <vscale x 4 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 4 x i64> @intrinsic_vbrev8_mask_vs_nxv4i64(<vscale x 4 x i1> %0, <vscale x 4 x i64> %1, <vscale x 4 x i64> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vbrev8_mask_vs_nxv4i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e64, m4, ta, mu
+; CHECK-NEXT:    vbrev8.v v8, v12, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i64> @llvm.riscv.vbrev8.mask.nxv4i64(
+    <vscale x 4 x i64> %1,
+    <vscale x 4 x i64> %2,
+    <vscale x 4 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 4 x i64> %a
+}
+
+declare <vscale x 8 x i64> @llvm.riscv.vbrev8.nxv8i64(
+  <vscale x 8 x i64>,
+  <vscale x 8 x i64>,
+  iXLen);
+
+define <vscale x 8 x i64> @intrinsic_vbrev8_vs_nxv8i64(<vscale x 8 x i64> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vbrev8_vs_nxv8i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
+; CHECK-NEXT:    vbrev8.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i64> @llvm.riscv.vbrev8.nxv8i64(
+    <vscale x 8 x i64> undef,
+    <vscale x 8 x i64> %0,
+    iXLen %1)
+
+  ret <vscale x 8 x i64> %a
+}
+
+declare <vscale x 8 x i64> @llvm.riscv.vbrev8.mask.nxv8i64(
+  <vscale x 8 x i64>,
+  <vscale x 8 x i64>,
+  <vscale x 8 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 8 x i64> @intrinsic_vbrev8_mask_vs_nxv8i64(<vscale x 8 x i1> %0, <vscale x 8 x i64> %1, <vscale x 8 x i64> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vbrev8_mask_vs_nxv8i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, mu
+; CHECK-NEXT:    vbrev8.v v8, v16, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i64> @llvm.riscv.vbrev8.mask.nxv8i64(
+    <vscale x 8 x i64> %1,
+    <vscale x 8 x i64> %2,
+    <vscale x 8 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 8 x i64> %a
+}

llvm/test/CodeGen/RISCV/rvv/vclmul.ll

+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: sed 's/iXLen/i32/g' %s | llc -mtriple=riscv32 -mattr=+v,+experimental-zvbc \
+; RUN:   -verify-machineinstrs | FileCheck %s --check-prefixes=CHECK,RV32
+; RUN: sed 's/iXLen/i64/g' %s | llc -mtriple=riscv64 -mattr=+v,+experimental-zvbc \
+; RUN:   -verify-machineinstrs | FileCheck %s --check-prefixes=CHECK,RV64
+
+declare <vscale x 1 x i64> @llvm.riscv.vclmul.nxv1i64.nxv1i64(
+  <vscale x 1 x i64>,
+  <vscale x 1 x i64>,
+  <vscale x 1 x i64>,
+  iXLen)
+
+define <vscale x 1 x i64> @intrinsic_vclmul_vv_nxv1i64_nxv1i64(<vscale x 1 x i64> %0, <vscale x 1 x i64> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vclmul_vv_nxv1i64_nxv1i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e64, m1, ta, ma
+; CHECK-NEXT:    vclmul.vv v8, v8, v9
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i64> @llvm.riscv.vclmul.nxv1i64.nxv1i64(
+    <vscale x 1 x i64> undef,
+    <vscale x 1 x i64> %0,
+    <vscale x 1 x i64> %1,
+    iXLen %2)
+
+  ret <vscale x 1 x i64> %a
+}
+
+declare <vscale x 1 x i64> @llvm.riscv.vclmul.mask.nxv1i64.nxv1i64(
+  <vscale x 1 x i64>,
+  <vscale x 1 x i64>,
+  <vscale x 1 x i64>,
+  <vscale x 1 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 1 x i64> @intrinsic_vclmul_mask_vv_nxv1i64_nxv1i64(<vscale x 1 x i64> %0, <vscale x 1 x i64> %1, <vscale x 1 x i64> %2, <vscale x 1 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vclmul_mask_vv_nxv1i64_nxv1i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e64, m1, ta, mu
+; CHECK-NEXT:    vclmul.vv v8, v9, v10
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i64> @llvm.riscv.vclmul.mask.nxv1i64.nxv1i64(
+    <vscale x 1 x i64> %0,
+    <vscale x 1 x i64> %1,
+    <vscale x 1 x i64> %2,
+    <vscale x 1 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 1 x i64> %a
+}
+
+declare <vscale x 2 x i64> @llvm.riscv.vclmul.nxv2i64.nxv2i64(
+  <vscale x 2 x i64>,
+  <vscale x 2 x i64>,
+  <vscale x 2 x i64>,
+  iXLen)
+
+define <vscale x 2 x i64> @intrinsic_vclmul_vv_nxv2i64_nxv2i64(<vscale x 2 x i64> %0, <vscale x 2 x i64> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vclmul_vv_nxv2i64_nxv2i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e64, m2, ta, ma
+; CHECK-NEXT:    vclmul.vv v8, v8, v10
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i64> @llvm.riscv.vclmul.nxv2i64.nxv2i64(
+    <vscale x 2 x i64> undef,
+    <vscale x 2 x i64> %0,
+    <vscale x 2 x i64> %1,
+    iXLen %2)
+
+  ret <vscale x 2 x i64> %a
+}
+
+declare <vscale x 2 x i64> @llvm.riscv.vclmul.mask.nxv2i64.nxv2i64(
+  <vscale x 2 x i64>,
+  <vscale x 2 x i64>,
+  <vscale x 2 x i64>,
+  <vscale x 2 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 2 x i64> @intrinsic_vclmul_mask_vv_nxv2i64_nxv2i64(<vscale x 2 x i64> %0, <vscale x 2 x i64> %1, <vscale x 2 x i64> %2, <vscale x 2 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vclmul_mask_vv_nxv2i64_nxv2i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e64, m2, ta, mu
+; CHECK-NEXT:    vclmul.vv v8, v10, v12
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i64> @llvm.riscv.vclmul.mask.nxv2i64.nxv2i64(
+    <vscale x 2 x i64> %0,
+    <vscale x 2 x i64> %1,
+    <vscale x 2 x i64> %2,
+    <vscale x 2 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 2 x i64> %a
+}
+
+declare <vscale x 4 x i64> @llvm.riscv.vclmul.nxv4i64.nxv4i64(
+  <vscale x 4 x i64>,
+  <vscale x 4 x i64>,
+  <vscale x 4 x i64>,
+  iXLen)
+
+define <vscale x 4 x i64> @intrinsic_vclmul_vv_nxv4i64_nxv4i64(<vscale x 4 x i64> %0, <vscale x 4 x i64> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vclmul_vv_nxv4i64_nxv4i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e64, m4, ta, ma
+; CHECK-NEXT:    vclmul.vv v8, v8, v12
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i64> @llvm.riscv.vclmul.nxv4i64.nxv4i64(
+    <vscale x 4 x i64> undef,
+    <vscale x 4 x i64> %0,
+    <vscale x 4 x i64> %1,
+    iXLen %2)
+
+  ret <vscale x 4 x i64> %a
+}
+
+declare <vscale x 4 x i64> @llvm.riscv.vclmul.mask.nxv4i64.nxv4i64(
+  <vscale x 4 x i64>,
+  <vscale x 4 x i64>,
+  <vscale x 4 x i64>,
+  <vscale x 4 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 4 x i64> @intrinsic_vclmul_mask_vv_nxv4i64_nxv4i64(<vscale x 4 x i64> %0, <vscale x 4 x i64> %1, <vscale x 4 x i64> %2, <vscale x 4 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vclmul_mask_vv_nxv4i64_nxv4i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e64, m4, ta, mu
+; CHECK-NEXT:    vclmul.vv v8, v12, v16
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i64> @llvm.riscv.vclmul.mask.nxv4i64.nxv4i64(
+    <vscale x 4 x i64> %0,
+    <vscale x 4 x i64> %1,
+    <vscale x 4 x i64> %2,
+    <vscale x 4 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 4 x i64> %a
+}
+
+declare <vscale x 8 x i64> @llvm.riscv.vclmul.nxv8i64.nxv8i64(
+  <vscale x 8 x i64>,
+  <vscale x 8 x i64>,
+  <vscale x 8 x i64>,
+  iXLen)
+
+define <vscale x 8 x i64> @intrinsic_vclmul_vv_nxv8i64_nxv8i64(<vscale x 8 x i64> %0, <vscale x 8 x i64> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vclmul_vv_nxv8i64_nxv8i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
+; CHECK-NEXT:    vclmul.vv v8, v8, v16
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i64> @llvm.riscv.vclmul.nxv8i64.nxv8i64(
+    <vscale x 8 x i64> undef,
+    <vscale x 8 x i64> %0,
+    <vscale x 8 x i64> %1,
+    iXLen %2)
+
+  ret <vscale x 8 x i64> %a
+}
+
+declare <vscale x 8 x i64> @llvm.riscv.vclmul.mask.nxv8i64.nxv8i64(
+  <vscale x 8 x i64>,
+  <vscale x 8 x i64>,
+  <vscale x 8 x i64>,
+  <vscale x 8 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 8 x i64> @intrinsic_vclmul_mask_vv_nxv8i64_nxv8i64(<vscale x 8 x i64> %0, <vscale x 8 x i64> %1, <vscale x 8 x i64> %2, <vscale x 8 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vclmul_mask_vv_nxv8i64_nxv8i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vl8re64.v v24, (a0)
+; CHECK-NEXT:    vsetvli zero, a1, e64, m8, ta, mu
+; CHECK-NEXT:    vclmul.vv v8, v16, v24
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i64> @llvm.riscv.vclmul.mask.nxv8i64.nxv8i64(
+    <vscale x 8 x i64> %0,
+    <vscale x 8 x i64> %1,
+    <vscale x 8 x i64> %2,
+    <vscale x 8 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 8 x i64> %a
+}
+
+declare <vscale x 1 x i64> @llvm.riscv.vclmul.nxv1i64.i64(
+  <vscale x 1 x i64>,
+  <vscale x 1 x i64>,
+  i64,
+  iXLen)
+
+define <vscale x 1 x i64> @intrinsic_vclmul_vx_nxv1i64_i64(<vscale x 1 x i64> %0, i64 %1, iXLen %2) nounwind {
+; RV32-LABEL: intrinsic_vclmul_vx_nxv1i64_i64:
+; RV32:       # %bb.0: # %entry
+; RV32-NEXT:    addi sp, sp, -16
+; RV32-NEXT:    sw a1, 12(sp)
+; RV32-NEXT:    sw a0, 8(sp)
+; RV32-NEXT:    addi a0, sp, 8
+; RV32-NEXT:    vsetvli zero, a2, e64, m1, ta, ma
+; RV32-NEXT:    vlse64.v v9, (a0), zero
+; RV32-NEXT:    vclmul.vv v8, v8, v9
+; RV32-NEXT:    addi sp, sp, 16
+; RV32-NEXT:    ret
+;
+; RV64-LABEL: intrinsic_vclmul_vx_nxv1i64_i64:
+; RV64:       # %bb.0: # %entry
+; RV64-NEXT:    vsetvli zero, a1, e64, m1, ta, ma
+; RV64-NEXT:    vclmul.vx v8, v8, a0
+; RV64-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i64> @llvm.riscv.vclmul.nxv1i64.i64(
+    <vscale x 1 x i64> undef,
+    <vscale x 1 x i64> %0,
+    i64 %1,
+    iXLen %2)
+
+  ret <vscale x 1 x i64> %a
+}
+
+declare <vscale x 1 x i64> @llvm.riscv.vclmul.mask.nxv1i64.i64(
+  <vscale x 1 x i64>,
+  <vscale x 1 x i64>,
+  i64,
+  <vscale x 1 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 1 x i64> @intrinsic_vclmul_mask_vx_nxv1i64_i64(<vscale x 1 x i64> %0, <vscale x 1 x i64> %1, i64 %2, <vscale x 1 x i1> %3, iXLen %4) nounwind {
+; RV32-LABEL: intrinsic_vclmul_mask_vx_nxv1i64_i64:
+; RV32:       # %bb.0: # %entry
+; RV32-NEXT:    addi sp, sp, -16
+; RV32-NEXT:    sw a1, 12(sp)
+; RV32-NEXT:    sw a0, 8(sp)
+; RV32-NEXT:    addi a0, sp, 8
+; RV32-NEXT:    vsetvli zero, a2, e64, m1, ta, mu
+; RV32-NEXT:    vlse64.v v10, (a0), zero
+; RV32-NEXT:    vclmul.vv v8, v9, v10
+; RV32-NEXT:    addi sp, sp, 16
+; RV32-NEXT:    ret
+;
+; RV64-LABEL: intrinsic_vclmul_mask_vx_nxv1i64_i64:
+; RV64:       # %bb.0: # %entry
+; RV64-NEXT:    vsetvli zero, a1, e64, m1, ta, mu
+; RV64-NEXT:    vclmul.vx v8, v9, a0
+; RV64-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i64> @llvm.riscv.vclmul.mask.nxv1i64.i64(
+    <vscale x 1 x i64> %0,
+    <vscale x 1 x i64> %1,
+    i64 %2,
+    <vscale x 1 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 1 x i64> %a
+}
+
+declare <vscale x 2 x i64> @llvm.riscv.vclmul.nxv2i64.i64(
+  <vscale x 2 x i64>,
+  <vscale x 2 x i64>,
+  i64,
+  iXLen)
+
+define <vscale x 2 x i64> @intrinsic_vclmul_vx_nxv2i64_i64(<vscale x 2 x i64> %0, i64 %1, iXLen %2) nounwind {
+; RV32-LABEL: intrinsic_vclmul_vx_nxv2i64_i64:
+; RV32:       # %bb.0: # %entry
+; RV32-NEXT:    addi sp, sp, -16
+; RV32-NEXT:    sw a1, 12(sp)
+; RV32-NEXT:    sw a0, 8(sp)
+; RV32-NEXT:    addi a0, sp, 8
+; RV32-NEXT:    vsetvli zero, a2, e64, m2, ta, ma
+; RV32-NEXT:    vlse64.v v10, (a0), zero
+; RV32-NEXT:    vclmul.vv v8, v8, v10
+; RV32-NEXT:    addi sp, sp, 16
+; RV32-NEXT:    ret
+;
+; RV64-LABEL: intrinsic_vclmul_vx_nxv2i64_i64:
+; RV64:       # %bb.0: # %entry
+; RV64-NEXT:    vsetvli zero, a1, e64, m2, ta, ma
+; RV64-NEXT:    vclmul.vx v8, v8, a0
+; RV64-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i64> @llvm.riscv.vclmul.nxv2i64.i64(
+    <vscale x 2 x i64> undef,
+    <vscale x 2 x i64> %0,
+    i64 %1,
+    iXLen %2)
+
+  ret <vscale x 2 x i64> %a
+}
+
+declare <vscale x 2 x i64> @llvm.riscv.vclmul.mask.nxv2i64.i64(
+  <vscale x 2 x i64>,
+  <vscale x 2 x i64>,
+  i64,
+  <vscale x 2 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 2 x i64> @intrinsic_vclmul_mask_vx_nxv2i64_i64(<vscale x 2 x i64> %0, <vscale x 2 x i64> %1, i64 %2, <vscale x 2 x i1> %3, iXLen %4) nounwind {
+; RV32-LABEL: intrinsic_vclmul_mask_vx_nxv2i64_i64:
+; RV32:       # %bb.0: # %entry
+; RV32-NEXT:    addi sp, sp, -16
+; RV32-NEXT:    sw a1, 12(sp)
+; RV32-NEXT:    sw a0, 8(sp)
+; RV32-NEXT:    addi a0, sp, 8
+; RV32-NEXT:    vsetvli zero, a2, e64, m2, ta, mu
+; RV32-NEXT:    vlse64.v v12, (a0), zero
+; RV32-NEXT:    vclmul.vv v8, v10, v12
+; RV32-NEXT:    addi sp, sp, 16
+; RV32-NEXT:    ret
+;
+; RV64-LABEL: intrinsic_vclmul_mask_vx_nxv2i64_i64:
+; RV64:       # %bb.0: # %entry
+; RV64-NEXT:    vsetvli zero, a1, e64, m2, ta, mu
+; RV64-NEXT:    vclmul.vx v8, v10, a0
+; RV64-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i64> @llvm.riscv.vclmul.mask.nxv2i64.i64(
+    <vscale x 2 x i64> %0,
+    <vscale x 2 x i64> %1,
+    i64 %2,
+    <vscale x 2 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 2 x i64> %a
+}
+
+declare <vscale x 4 x i64> @llvm.riscv.vclmul.nxv4i64.i64(
+  <vscale x 4 x i64>,
+  <vscale x 4 x i64>,
+  i64,
+  iXLen)
+
+define <vscale x 4 x i64> @intrinsic_vclmul_vx_nxv4i64_i64(<vscale x 4 x i64> %0, i64 %1, iXLen %2) nounwind {
+; RV32-LABEL: intrinsic_vclmul_vx_nxv4i64_i64:
+; RV32:       # %bb.0: # %entry
+; RV32-NEXT:    addi sp, sp, -16
+; RV32-NEXT:    sw a1, 12(sp)
+; RV32-NEXT:    sw a0, 8(sp)
+; RV32-NEXT:    addi a0, sp, 8
+; RV32-NEXT:    vsetvli zero, a2, e64, m4, ta, ma
+; RV32-NEXT:    vlse64.v v12, (a0), zero
+; RV32-NEXT:    vclmul.vv v8, v8, v12
+; RV32-NEXT:    addi sp, sp, 16
+; RV32-NEXT:    ret
+;
+; RV64-LABEL: intrinsic_vclmul_vx_nxv4i64_i64:
+; RV64:       # %bb.0: # %entry
+; RV64-NEXT:    vsetvli zero, a1, e64, m4, ta, ma
+; RV64-NEXT:    vclmul.vx v8, v8, a0
+; RV64-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i64> @llvm.riscv.vclmul.nxv4i64.i64(
+    <vscale x 4 x i64> undef,
+    <vscale x 4 x i64> %0,
+    i64 %1,
+    iXLen %2)
+
+  ret <vscale x 4 x i64> %a
+}
+
+declare <vscale x 4 x i64> @llvm.riscv.vclmul.mask.nxv4i64.i64(
+  <vscale x 4 x i64>,
+  <vscale x 4 x i64>,
+  i64,
+  <vscale x 4 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 4 x i64> @intrinsic_vclmul_mask_vx_nxv4i64_i64(<vscale x 4 x i64> %0, <vscale x 4 x i64> %1, i64 %2, <vscale x 4 x i1> %3, iXLen %4) nounwind {
+; RV32-LABEL: intrinsic_vclmul_mask_vx_nxv4i64_i64:
+; RV32:       # %bb.0: # %entry
+; RV32-NEXT:    addi sp, sp, -16
+; RV32-NEXT:    sw a1, 12(sp)
+; RV32-NEXT:    sw a0, 8(sp)
+; RV32-NEXT:    addi a0, sp, 8
+; RV32-NEXT:    vsetvli zero, a2, e64, m4, ta, mu
+; RV32-NEXT:    vlse64.v v16, (a0), zero
+; RV32-NEXT:    vclmul.vv v8, v12, v16
+; RV32-NEXT:    addi sp, sp, 16
+; RV32-NEXT:    ret
+;
+; RV64-LABEL: intrinsic_vclmul_mask_vx_nxv4i64_i64:
+; RV64:       # %bb.0: # %entry
+; RV64-NEXT:    vsetvli zero, a1, e64, m4, ta, mu
+; RV64-NEXT:    vclmul.vx v8, v12, a0
+; RV64-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i64> @llvm.riscv.vclmul.mask.nxv4i64.i64(
+    <vscale x 4 x i64> %0,
+    <vscale x 4 x i64> %1,
+    i64 %2,
+    <vscale x 4 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 4 x i64> %a
+}
+
+declare <vscale x 8 x i64> @llvm.riscv.vclmul.nxv8i64.i64(
+  <vscale x 8 x i64>,
+  <vscale x 8 x i64>,
+  i64,
+  iXLen)
+
+define <vscale x 8 x i64> @intrinsic_vclmul_vx_nxv8i64_i64(<vscale x 8 x i64> %0, i64 %1, iXLen %2) nounwind {
+; RV32-LABEL: intrinsic_vclmul_vx_nxv8i64_i64:
+; RV32:       # %bb.0: # %entry
+; RV32-NEXT:    addi sp, sp, -16
+; RV32-NEXT:    sw a1, 12(sp)
+; RV32-NEXT:    sw a0, 8(sp)
+; RV32-NEXT:    addi a0, sp, 8
+; RV32-NEXT:    vsetvli zero, a2, e64, m8, ta, ma
+; RV32-NEXT:    vlse64.v v16, (a0), zero
+; RV32-NEXT:    vclmul.vv v8, v8, v16
+; RV32-NEXT:    addi sp, sp, 16
+; RV32-NEXT:    ret
+;
+; RV64-LABEL: intrinsic_vclmul_vx_nxv8i64_i64:
+; RV64:       # %bb.0: # %entry
+; RV64-NEXT:    vsetvli zero, a1, e64, m8, ta, ma
+; RV64-NEXT:    vclmul.vx v8, v8, a0
+; RV64-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i64> @llvm.riscv.vclmul.nxv8i64.i64(
+    <vscale x 8 x i64> undef,
+    <vscale x 8 x i64> %0,
+    i64 %1,
+    iXLen %2)
+
+  ret <vscale x 8 x i64> %a
+}
+
+declare <vscale x 8 x i64> @llvm.riscv.vclmul.mask.nxv8i64.i64(
+  <vscale x 8 x i64>,
+  <vscale x 8 x i64>,
+  i64,
+  <vscale x 8 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 8 x i64> @intrinsic_vclmul_mask_vx_nxv8i64_i64(<vscale x 8 x i64> %0, <vscale x 8 x i64> %1, i64 %2, <vscale x 8 x i1> %3, iXLen %4) nounwind {
+; RV32-LABEL: intrinsic_vclmul_mask_vx_nxv8i64_i64:
+; RV32:       # %bb.0: # %entry
+; RV32-NEXT:    addi sp, sp, -16
+; RV32-NEXT:    sw a1, 12(sp)
+; RV32-NEXT:    sw a0, 8(sp)
+; RV32-NEXT:    addi a0, sp, 8
+; RV32-NEXT:    vsetvli zero, a2, e64, m8, ta, mu
+; RV32-NEXT:    vlse64.v v24, (a0), zero
+; RV32-NEXT:    vclmul.vv v8, v16, v24
+; RV32-NEXT:    addi sp, sp, 16
+; RV32-NEXT:    ret
+;
+; RV64-LABEL: intrinsic_vclmul_mask_vx_nxv8i64_i64:
+; RV64:       # %bb.0: # %entry
+; RV64-NEXT:    vsetvli zero, a1, e64, m8, ta, mu
+; RV64-NEXT:    vclmul.vx v8, v16, a0
+; RV64-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i64> @llvm.riscv.vclmul.mask.nxv8i64.i64(
+    <vscale x 8 x i64> %0,
+    <vscale x 8 x i64> %1,
+    i64 %2,
+    <vscale x 8 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 8 x i64> %a
+}

llvm/test/CodeGen/RISCV/rvv/vclmulh.ll

+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: sed 's/iXLen/i32/g' %s | llc -mtriple=riscv32 -mattr=+v,+experimental-zvbc \
+; RUN:   -verify-machineinstrs | FileCheck %s --check-prefixes=CHECK,RV32
+; RUN: sed 's/iXLen/i64/g' %s | llc -mtriple=riscv64 -mattr=+v,+experimental-zvbc \
+; RUN:   -verify-machineinstrs | FileCheck %s --check-prefixes=CHECK,RV64
+
+declare <vscale x 1 x i64> @llvm.riscv.vclmulh.nxv1i64.nxv1i64(
+  <vscale x 1 x i64>,
+  <vscale x 1 x i64>,
+  <vscale x 1 x i64>,
+  iXLen)
+
+define <vscale x 1 x i64> @intrinsic_vclmulh_vv_nxv1i64_nxv1i64(<vscale x 1 x i64> %0, <vscale x 1 x i64> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vclmulh_vv_nxv1i64_nxv1i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e64, m1, ta, ma
+; CHECK-NEXT:    vclmulh.vv v8, v8, v9
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i64> @llvm.riscv.vclmulh.nxv1i64.nxv1i64(
+    <vscale x 1 x i64> undef,
+    <vscale x 1 x i64> %0,
+    <vscale x 1 x i64> %1,
+    iXLen %2)
+
+  ret <vscale x 1 x i64> %a
+}
+
+declare <vscale x 1 x i64> @llvm.riscv.vclmulh.mask.nxv1i64.nxv1i64(
+  <vscale x 1 x i64>,
+  <vscale x 1 x i64>,
+  <vscale x 1 x i64>,
+  <vscale x 1 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 1 x i64> @intrinsic_vclmulh_mask_vv_nxv1i64_nxv1i64(<vscale x 1 x i64> %0, <vscale x 1 x i64> %1, <vscale x 1 x i64> %2, <vscale x 1 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vclmulh_mask_vv_nxv1i64_nxv1i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e64, m1, ta, mu
+; CHECK-NEXT:    vclmulh.vv v8, v9, v10
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i64> @llvm.riscv.vclmulh.mask.nxv1i64.nxv1i64(
+    <vscale x 1 x i64> %0,
+    <vscale x 1 x i64> %1,
+    <vscale x 1 x i64> %2,
+    <vscale x 1 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 1 x i64> %a
+}
+
+declare <vscale x 2 x i64> @llvm.riscv.vclmulh.nxv2i64.nxv2i64(
+  <vscale x 2 x i64>,
+  <vscale x 2 x i64>,
+  <vscale x 2 x i64>,
+  iXLen)
+
+define <vscale x 2 x i64> @intrinsic_vclmulh_vv_nxv2i64_nxv2i64(<vscale x 2 x i64> %0, <vscale x 2 x i64> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vclmulh_vv_nxv2i64_nxv2i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e64, m2, ta, ma
+; CHECK-NEXT:    vclmulh.vv v8, v8, v10
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i64> @llvm.riscv.vclmulh.nxv2i64.nxv2i64(
+    <vscale x 2 x i64> undef,
+    <vscale x 2 x i64> %0,
+    <vscale x 2 x i64> %1,
+    iXLen %2)
+
+  ret <vscale x 2 x i64> %a
+}
+
+declare <vscale x 2 x i64> @llvm.riscv.vclmulh.mask.nxv2i64.nxv2i64(
+  <vscale x 2 x i64>,
+  <vscale x 2 x i64>,
+  <vscale x 2 x i64>,
+  <vscale x 2 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 2 x i64> @intrinsic_vclmulh_mask_vv_nxv2i64_nxv2i64(<vscale x 2 x i64> %0, <vscale x 2 x i64> %1, <vscale x 2 x i64> %2, <vscale x 2 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vclmulh_mask_vv_nxv2i64_nxv2i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e64, m2, ta, mu
+; CHECK-NEXT:    vclmulh.vv v8, v10, v12
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i64> @llvm.riscv.vclmulh.mask.nxv2i64.nxv2i64(
+    <vscale x 2 x i64> %0,
+    <vscale x 2 x i64> %1,
+    <vscale x 2 x i64> %2,
+    <vscale x 2 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 2 x i64> %a
+}
+
+declare <vscale x 4 x i64> @llvm.riscv.vclmulh.nxv4i64.nxv4i64(
+  <vscale x 4 x i64>,
+  <vscale x 4 x i64>,
+  <vscale x 4 x i64>,
+  iXLen)
+
+define <vscale x 4 x i64> @intrinsic_vclmulh_vv_nxv4i64_nxv4i64(<vscale x 4 x i64> %0, <vscale x 4 x i64> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vclmulh_vv_nxv4i64_nxv4i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e64, m4, ta, ma
+; CHECK-NEXT:    vclmulh.vv v8, v8, v12
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i64> @llvm.riscv.vclmulh.nxv4i64.nxv4i64(
+    <vscale x 4 x i64> undef,
+    <vscale x 4 x i64> %0,
+    <vscale x 4 x i64> %1,
+    iXLen %2)
+
+  ret <vscale x 4 x i64> %a
+}
+
+declare <vscale x 4 x i64> @llvm.riscv.vclmulh.mask.nxv4i64.nxv4i64(
+  <vscale x 4 x i64>,
+  <vscale x 4 x i64>,
+  <vscale x 4 x i64>,
+  <vscale x 4 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 4 x i64> @intrinsic_vclmulh_mask_vv_nxv4i64_nxv4i64(<vscale x 4 x i64> %0, <vscale x 4 x i64> %1, <vscale x 4 x i64> %2, <vscale x 4 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vclmulh_mask_vv_nxv4i64_nxv4i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e64, m4, ta, mu
+; CHECK-NEXT:    vclmulh.vv v8, v12, v16
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i64> @llvm.riscv.vclmulh.mask.nxv4i64.nxv4i64(
+    <vscale x 4 x i64> %0,
+    <vscale x 4 x i64> %1,
+    <vscale x 4 x i64> %2,
+    <vscale x 4 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 4 x i64> %a
+}
+
+declare <vscale x 8 x i64> @llvm.riscv.vclmulh.nxv8i64.nxv8i64(
+  <vscale x 8 x i64>,
+  <vscale x 8 x i64>,
+  <vscale x 8 x i64>,
+  iXLen)
+
+define <vscale x 8 x i64> @intrinsic_vclmulh_vv_nxv8i64_nxv8i64(<vscale x 8 x i64> %0, <vscale x 8 x i64> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vclmulh_vv_nxv8i64_nxv8i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
+; CHECK-NEXT:    vclmulh.vv v8, v8, v16
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i64> @llvm.riscv.vclmulh.nxv8i64.nxv8i64(
+    <vscale x 8 x i64> undef,
+    <vscale x 8 x i64> %0,
+    <vscale x 8 x i64> %1,
+    iXLen %2)
+
+  ret <vscale x 8 x i64> %a
+}
+
+declare <vscale x 8 x i64> @llvm.riscv.vclmulh.mask.nxv8i64.nxv8i64(
+  <vscale x 8 x i64>,
+  <vscale x 8 x i64>,
+  <vscale x 8 x i64>,
+  <vscale x 8 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 8 x i64> @intrinsic_vclmulh_mask_vv_nxv8i64_nxv8i64(<vscale x 8 x i64> %0, <vscale x 8 x i64> %1, <vscale x 8 x i64> %2, <vscale x 8 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vclmulh_mask_vv_nxv8i64_nxv8i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vl8re64.v v24, (a0)
+; CHECK-NEXT:    vsetvli zero, a1, e64, m8, ta, mu
+; CHECK-NEXT:    vclmulh.vv v8, v16, v24
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i64> @llvm.riscv.vclmulh.mask.nxv8i64.nxv8i64(
+    <vscale x 8 x i64> %0,
+    <vscale x 8 x i64> %1,
+    <vscale x 8 x i64> %2,
+    <vscale x 8 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 8 x i64> %a
+}
+
+declare <vscale x 1 x i64> @llvm.riscv.vclmulh.nxv1i64.i64(
+  <vscale x 1 x i64>,
+  <vscale x 1 x i64>,
+  i64,
+  iXLen)
+
+define <vscale x 1 x i64> @intrinsic_vclmulh_vx_nxv1i64_i64(<vscale x 1 x i64> %0, i64 %1, iXLen %2) nounwind {
+; RV32-LABEL: intrinsic_vclmulh_vx_nxv1i64_i64:
+; RV32:       # %bb.0: # %entry
+; RV32-NEXT:    addi sp, sp, -16
+; RV32-NEXT:    sw a1, 12(sp)
+; RV32-NEXT:    sw a0, 8(sp)
+; RV32-NEXT:    addi a0, sp, 8
+; RV32-NEXT:    vsetvli zero, a2, e64, m1, ta, ma
+; RV32-NEXT:    vlse64.v v9, (a0), zero
+; RV32-NEXT:    vclmulh.vv v8, v8, v9
+; RV32-NEXT:    addi sp, sp, 16
+; RV32-NEXT:    ret
+;
+; RV64-LABEL: intrinsic_vclmulh_vx_nxv1i64_i64:
+; RV64:       # %bb.0: # %entry
+; RV64-NEXT:    vsetvli zero, a1, e64, m1, ta, ma
+; RV64-NEXT:    vclmulh.vx v8, v8, a0
+; RV64-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i64> @llvm.riscv.vclmulh.nxv1i64.i64(
+    <vscale x 1 x i64> undef,
+    <vscale x 1 x i64> %0,
+    i64 %1,
+    iXLen %2)
+
+  ret <vscale x 1 x i64> %a
+}
+
+declare <vscale x 1 x i64> @llvm.riscv.vclmulh.mask.nxv1i64.i64(
+  <vscale x 1 x i64>,
+  <vscale x 1 x i64>,
+  i64,
+  <vscale x 1 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 1 x i64> @intrinsic_vclmulh_mask_vx_nxv1i64_i64(<vscale x 1 x i64> %0, <vscale x 1 x i64> %1, i64 %2, <vscale x 1 x i1> %3, iXLen %4) nounwind {
+; RV32-LABEL: intrinsic_vclmulh_mask_vx_nxv1i64_i64:
+; RV32:       # %bb.0: # %entry
+; RV32-NEXT:    addi sp, sp, -16
+; RV32-NEXT:    sw a1, 12(sp)
+; RV32-NEXT:    sw a0, 8(sp)
+; RV32-NEXT:    addi a0, sp, 8
+; RV32-NEXT:    vsetvli zero, a2, e64, m1, ta, mu
+; RV32-NEXT:    vlse64.v v10, (a0), zero
+; RV32-NEXT:    vclmulh.vv v8, v9, v10
+; RV32-NEXT:    addi sp, sp, 16
+; RV32-NEXT:    ret
+;
+; RV64-LABEL: intrinsic_vclmulh_mask_vx_nxv1i64_i64:
+; RV64:       # %bb.0: # %entry
+; RV64-NEXT:    vsetvli zero, a1, e64, m1, ta, mu
+; RV64-NEXT:    vclmulh.vx v8, v9, a0
+; RV64-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i64> @llvm.riscv.vclmulh.mask.nxv1i64.i64(
+    <vscale x 1 x i64> %0,
+    <vscale x 1 x i64> %1,
+    i64 %2,
+    <vscale x 1 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 1 x i64> %a
+}
+
+declare <vscale x 2 x i64> @llvm.riscv.vclmulh.nxv2i64.i64(
+  <vscale x 2 x i64>,
+  <vscale x 2 x i64>,
+  i64,
+  iXLen)
+
+define <vscale x 2 x i64> @intrinsic_vclmulh_vx_nxv2i64_i64(<vscale x 2 x i64> %0, i64 %1, iXLen %2) nounwind {
+; RV32-LABEL: intrinsic_vclmulh_vx_nxv2i64_i64:
+; RV32:       # %bb.0: # %entry
+; RV32-NEXT:    addi sp, sp, -16
+; RV32-NEXT:    sw a1, 12(sp)
+; RV32-NEXT:    sw a0, 8(sp)
+; RV32-NEXT:    addi a0, sp, 8
+; RV32-NEXT:    vsetvli zero, a2, e64, m2, ta, ma
+; RV32-NEXT:    vlse64.v v10, (a0), zero
+; RV32-NEXT:    vclmulh.vv v8, v8, v10
+; RV32-NEXT:    addi sp, sp, 16
+; RV32-NEXT:    ret
+;
+; RV64-LABEL: intrinsic_vclmulh_vx_nxv2i64_i64:
+; RV64:       # %bb.0: # %entry
+; RV64-NEXT:    vsetvli zero, a1, e64, m2, ta, ma
+; RV64-NEXT:    vclmulh.vx v8, v8, a0
+; RV64-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i64> @llvm.riscv.vclmulh.nxv2i64.i64(
+    <vscale x 2 x i64> undef,
+    <vscale x 2 x i64> %0,
+    i64 %1,
+    iXLen %2)
+
+  ret <vscale x 2 x i64> %a
+}
+
+declare <vscale x 2 x i64> @llvm.riscv.vclmulh.mask.nxv2i64.i64(
+  <vscale x 2 x i64>,
+  <vscale x 2 x i64>,
+  i64,
+  <vscale x 2 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 2 x i64> @intrinsic_vclmulh_mask_vx_nxv2i64_i64(<vscale x 2 x i64> %0, <vscale x 2 x i64> %1, i64 %2, <vscale x 2 x i1> %3, iXLen %4) nounwind {
+; RV32-LABEL: intrinsic_vclmulh_mask_vx_nxv2i64_i64:
+; RV32:       # %bb.0: # %entry
+; RV32-NEXT:    addi sp, sp, -16
+; RV32-NEXT:    sw a1, 12(sp)
+; RV32-NEXT:    sw a0, 8(sp)
+; RV32-NEXT:    addi a0, sp, 8
+; RV32-NEXT:    vsetvli zero, a2, e64, m2, ta, mu
+; RV32-NEXT:    vlse64.v v12, (a0), zero
+; RV32-NEXT:    vclmulh.vv v8, v10, v12
+; RV32-NEXT:    addi sp, sp, 16
+; RV32-NEXT:    ret
+;
+; RV64-LABEL: intrinsic_vclmulh_mask_vx_nxv2i64_i64:
+; RV64:       # %bb.0: # %entry
+; RV64-NEXT:    vsetvli zero, a1, e64, m2, ta, mu
+; RV64-NEXT:    vclmulh.vx v8, v10, a0
+; RV64-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i64> @llvm.riscv.vclmulh.mask.nxv2i64.i64(
+    <vscale x 2 x i64> %0,
+    <vscale x 2 x i64> %1,
+    i64 %2,
+    <vscale x 2 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 2 x i64> %a
+}
+
+declare <vscale x 4 x i64> @llvm.riscv.vclmulh.nxv4i64.i64(
+  <vscale x 4 x i64>,
+  <vscale x 4 x i64>,
+  i64,
+  iXLen)
+
+define <vscale x 4 x i64> @intrinsic_vclmulh_vx_nxv4i64_i64(<vscale x 4 x i64> %0, i64 %1, iXLen %2) nounwind {
+; RV32-LABEL: intrinsic_vclmulh_vx_nxv4i64_i64:
+; RV32:       # %bb.0: # %entry
+; RV32-NEXT:    addi sp, sp, -16
+; RV32-NEXT:    sw a1, 12(sp)
+; RV32-NEXT:    sw a0, 8(sp)
+; RV32-NEXT:    addi a0, sp, 8
+; RV32-NEXT:    vsetvli zero, a2, e64, m4, ta, ma
+; RV32-NEXT:    vlse64.v v12, (a0), zero
+; RV32-NEXT:    vclmulh.vv v8, v8, v12
+; RV32-NEXT:    addi sp, sp, 16
+; RV32-NEXT:    ret
+;
+; RV64-LABEL: intrinsic_vclmulh_vx_nxv4i64_i64:
+; RV64:       # %bb.0: # %entry
+; RV64-NEXT:    vsetvli zero, a1, e64, m4, ta, ma
+; RV64-NEXT:    vclmulh.vx v8, v8, a0
+; RV64-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i64> @llvm.riscv.vclmulh.nxv4i64.i64(
+    <vscale x 4 x i64> undef,
+    <vscale x 4 x i64> %0,
+    i64 %1,
+    iXLen %2)
+
+  ret <vscale x 4 x i64> %a
+}
+
+declare <vscale x 4 x i64> @llvm.riscv.vclmulh.mask.nxv4i64.i64(
+  <vscale x 4 x i64>,
+  <vscale x 4 x i64>,
+  i64,
+  <vscale x 4 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 4 x i64> @intrinsic_vclmulh_mask_vx_nxv4i64_i64(<vscale x 4 x i64> %0, <vscale x 4 x i64> %1, i64 %2, <vscale x 4 x i1> %3, iXLen %4) nounwind {
+; RV32-LABEL: intrinsic_vclmulh_mask_vx_nxv4i64_i64:
+; RV32:       # %bb.0: # %entry
+; RV32-NEXT:    addi sp, sp, -16
+; RV32-NEXT:    sw a1, 12(sp)
+; RV32-NEXT:    sw a0, 8(sp)
+; RV32-NEXT:    addi a0, sp, 8
+; RV32-NEXT:    vsetvli zero, a2, e64, m4, ta, mu
+; RV32-NEXT:    vlse64.v v16, (a0), zero
+; RV32-NEXT:    vclmulh.vv v8, v12, v16
+; RV32-NEXT:    addi sp, sp, 16
+; RV32-NEXT:    ret
+;
+; RV64-LABEL: intrinsic_vclmulh_mask_vx_nxv4i64_i64:
+; RV64:       # %bb.0: # %entry
+; RV64-NEXT:    vsetvli zero, a1, e64, m4, ta, mu
+; RV64-NEXT:    vclmulh.vx v8, v12, a0
+; RV64-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i64> @llvm.riscv.vclmulh.mask.nxv4i64.i64(
+    <vscale x 4 x i64> %0,
+    <vscale x 4 x i64> %1,
+    i64 %2,
+    <vscale x 4 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 4 x i64> %a
+}
+
+declare <vscale x 8 x i64> @llvm.riscv.vclmulh.nxv8i64.i64(
+  <vscale x 8 x i64>,
+  <vscale x 8 x i64>,
+  i64,
+  iXLen)
+
+define <vscale x 8 x i64> @intrinsic_vclmulh_vx_nxv8i64_i64(<vscale x 8 x i64> %0, i64 %1, iXLen %2) nounwind {
+; RV32-LABEL: intrinsic_vclmulh_vx_nxv8i64_i64:
+; RV32:       # %bb.0: # %entry
+; RV32-NEXT:    addi sp, sp, -16
+; RV32-NEXT:    sw a1, 12(sp)
+; RV32-NEXT:    sw a0, 8(sp)
+; RV32-NEXT:    addi a0, sp, 8
+; RV32-NEXT:    vsetvli zero, a2, e64, m8, ta, ma
+; RV32-NEXT:    vlse64.v v16, (a0), zero
+; RV32-NEXT:    vclmulh.vv v8, v8, v16
+; RV32-NEXT:    addi sp, sp, 16
+; RV32-NEXT:    ret
+;
+; RV64-LABEL: intrinsic_vclmulh_vx_nxv8i64_i64:
+; RV64:       # %bb.0: # %entry
+; RV64-NEXT:    vsetvli zero, a1, e64, m8, ta, ma
+; RV64-NEXT:    vclmulh.vx v8, v8, a0
+; RV64-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i64> @llvm.riscv.vclmulh.nxv8i64.i64(
+    <vscale x 8 x i64> undef,
+    <vscale x 8 x i64> %0,
+    i64 %1,
+    iXLen %2)
+
+  ret <vscale x 8 x i64> %a
+}
+
+declare <vscale x 8 x i64> @llvm.riscv.vclmulh.mask.nxv8i64.i64(
+  <vscale x 8 x i64>,
+  <vscale x 8 x i64>,
+  i64,
+  <vscale x 8 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 8 x i64> @intrinsic_vclmulh_mask_vx_nxv8i64_i64(<vscale x 8 x i64> %0, <vscale x 8 x i64> %1, i64 %2, <vscale x 8 x i1> %3, iXLen %4) nounwind {
+; RV32-LABEL: intrinsic_vclmulh_mask_vx_nxv8i64_i64:
+; RV32:       # %bb.0: # %entry
+; RV32-NEXT:    addi sp, sp, -16
+; RV32-NEXT:    sw a1, 12(sp)
+; RV32-NEXT:    sw a0, 8(sp)
+; RV32-NEXT:    addi a0, sp, 8
+; RV32-NEXT:    vsetvli zero, a2, e64, m8, ta, mu
+; RV32-NEXT:    vlse64.v v24, (a0), zero
+; RV32-NEXT:    vclmulh.vv v8, v16, v24
+; RV32-NEXT:    addi sp, sp, 16
+; RV32-NEXT:    ret
+;
+; RV64-LABEL: intrinsic_vclmulh_mask_vx_nxv8i64_i64:
+; RV64:       # %bb.0: # %entry
+; RV64-NEXT:    vsetvli zero, a1, e64, m8, ta, mu
+; RV64-NEXT:    vclmulh.vx v8, v16, a0
+; RV64-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i64> @llvm.riscv.vclmulh.mask.nxv8i64.i64(
+    <vscale x 8 x i64> %0,
+    <vscale x 8 x i64> %1,
+    i64 %2,
+    <vscale x 8 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 8 x i64> %a
+}

llvm/test/CodeGen/RISCV/rvv/vclz.ll

+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: sed 's/iXLen/i32/g' %s | llc -mtriple=riscv32 -mattr=+v,+experimental-zvbb \
+; RUN:   -verify-machineinstrs | FileCheck %s --check-prefixes=CHECK
+; RUN: sed 's/iXLen/i64/g' %s | llc -mtriple=riscv64 -mattr=+v,+experimental-zvbb \
+; RUN:   -verify-machineinstrs | FileCheck %s --check-prefixes=CHECK
+
+declare <vscale x 1 x i8> @llvm.riscv.vclz.nxv1i8(
+  <vscale x 1 x i8>,
+  <vscale x 1 x i8>,
+  iXLen);
+
+define <vscale x 1 x i8> @intrinsic_vclz_vs_nxv1i8(<vscale x 1 x i8> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vclz_vs_nxv1i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, mf8, ta, ma
+; CHECK-NEXT:    vclz.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i8> @llvm.riscv.vclz.nxv1i8(
+    <vscale x 1 x i8> undef,
+    <vscale x 1 x i8> %0,
+    iXLen %1)
+
+  ret <vscale x 1 x i8> %a
+}
+
+declare <vscale x 1 x i8> @llvm.riscv.vclz.mask.nxv1i8(
+  <vscale x 1 x i8>,
+  <vscale x 1 x i8>,
+  <vscale x 1 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 1 x i8> @intrinsic_vclz_mask_vs_nxv1i8(<vscale x 1 x i1> %0, <vscale x 1 x i8> %1, <vscale x 1 x i8> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vclz_mask_vs_nxv1i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, mf8, ta, mu
+; CHECK-NEXT:    vclz.v v8, v9, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i8> @llvm.riscv.vclz.mask.nxv1i8(
+    <vscale x 1 x i8> %1,
+    <vscale x 1 x i8> %2,
+    <vscale x 1 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 1 x i8> %a
+}
+
+declare <vscale x 2 x i8> @llvm.riscv.vclz.nxv2i8(
+  <vscale x 2 x i8>,
+  <vscale x 2 x i8>,
+  iXLen);
+
+define <vscale x 2 x i8> @intrinsic_vclz_vs_nxv2i8(<vscale x 2 x i8> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vclz_vs_nxv2i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, mf4, ta, ma
+; CHECK-NEXT:    vclz.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i8> @llvm.riscv.vclz.nxv2i8(
+    <vscale x 2 x i8> undef,
+    <vscale x 2 x i8> %0,
+    iXLen %1)
+
+  ret <vscale x 2 x i8> %a
+}
+
+declare <vscale x 2 x i8> @llvm.riscv.vclz.mask.nxv2i8(
+  <vscale x 2 x i8>,
+  <vscale x 2 x i8>,
+  <vscale x 2 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 2 x i8> @intrinsic_vclz_mask_vs_nxv2i8(<vscale x 2 x i1> %0, <vscale x 2 x i8> %1, <vscale x 2 x i8> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vclz_mask_vs_nxv2i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, mf4, ta, mu
+; CHECK-NEXT:    vclz.v v8, v9, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i8> @llvm.riscv.vclz.mask.nxv2i8(
+    <vscale x 2 x i8> %1,
+    <vscale x 2 x i8> %2,
+    <vscale x 2 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 2 x i8> %a
+}
+
+declare <vscale x 4 x i8> @llvm.riscv.vclz.nxv4i8(
+  <vscale x 4 x i8>,
+  <vscale x 4 x i8>,
+  iXLen);
+
+define <vscale x 4 x i8> @intrinsic_vclz_vs_nxv4i8(<vscale x 4 x i8> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vclz_vs_nxv4i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, mf2, ta, ma
+; CHECK-NEXT:    vclz.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i8> @llvm.riscv.vclz.nxv4i8(
+    <vscale x 4 x i8> undef,
+    <vscale x 4 x i8> %0,
+    iXLen %1)
+
+  ret <vscale x 4 x i8> %a
+}
+
+declare <vscale x 4 x i8> @llvm.riscv.vclz.mask.nxv4i8(
+  <vscale x 4 x i8>,
+  <vscale x 4 x i8>,
+  <vscale x 4 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 4 x i8> @intrinsic_vclz_mask_vs_nxv4i8(<vscale x 4 x i1> %0, <vscale x 4 x i8> %1, <vscale x 4 x i8> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vclz_mask_vs_nxv4i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, mf2, ta, mu
+; CHECK-NEXT:    vclz.v v8, v9, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i8> @llvm.riscv.vclz.mask.nxv4i8(
+    <vscale x 4 x i8> %1,
+    <vscale x 4 x i8> %2,
+    <vscale x 4 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 4 x i8> %a
+}
+
+declare <vscale x 8 x i8> @llvm.riscv.vclz.nxv8i8(
+  <vscale x 8 x i8>,
+  <vscale x 8 x i8>,
+  iXLen);
+
+define <vscale x 8 x i8> @intrinsic_vclz_vs_nxv8i8(<vscale x 8 x i8> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vclz_vs_nxv8i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, m1, ta, ma
+; CHECK-NEXT:    vclz.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i8> @llvm.riscv.vclz.nxv8i8(
+    <vscale x 8 x i8> undef,
+    <vscale x 8 x i8> %0,
+    iXLen %1)
+
+  ret <vscale x 8 x i8> %a
+}
+
+declare <vscale x 8 x i8> @llvm.riscv.vclz.mask.nxv8i8(
+  <vscale x 8 x i8>,
+  <vscale x 8 x i8>,
+  <vscale x 8 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 8 x i8> @intrinsic_vclz_mask_vs_nxv8i8(<vscale x 8 x i1> %0, <vscale x 8 x i8> %1, <vscale x 8 x i8> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vclz_mask_vs_nxv8i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, m1, ta, mu
+; CHECK-NEXT:    vclz.v v8, v9, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i8> @llvm.riscv.vclz.mask.nxv8i8(
+    <vscale x 8 x i8> %1,
+    <vscale x 8 x i8> %2,
+    <vscale x 8 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 8 x i8> %a
+}
+
+declare <vscale x 16 x i8> @llvm.riscv.vclz.nxv16i8(
+  <vscale x 16 x i8>,
+  <vscale x 16 x i8>,
+  iXLen);
+
+define <vscale x 16 x i8> @intrinsic_vclz_vs_nxv16i8(<vscale x 16 x i8> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vclz_vs_nxv16i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, m2, ta, ma
+; CHECK-NEXT:    vclz.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 16 x i8> @llvm.riscv.vclz.nxv16i8(
+    <vscale x 16 x i8> undef,
+    <vscale x 16 x i8> %0,
+    iXLen %1)
+
+  ret <vscale x 16 x i8> %a
+}
+
+declare <vscale x 16 x i8> @llvm.riscv.vclz.mask.nxv16i8(
+  <vscale x 16 x i8>,
+  <vscale x 16 x i8>,
+  <vscale x 16 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 16 x i8> @intrinsic_vclz_mask_vs_nxv16i8(<vscale x 16 x i1> %0, <vscale x 16 x i8> %1, <vscale x 16 x i8> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vclz_mask_vs_nxv16i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, m2, ta, mu
+; CHECK-NEXT:    vclz.v v8, v10, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 16 x i8> @llvm.riscv.vclz.mask.nxv16i8(
+    <vscale x 16 x i8> %1,
+    <vscale x 16 x i8> %2,
+    <vscale x 16 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 16 x i8> %a
+}
+
+declare <vscale x 32 x i8> @llvm.riscv.vclz.nxv32i8(
+  <vscale x 32 x i8>,
+  <vscale x 32 x i8>,
+  iXLen);
+
+define <vscale x 32 x i8> @intrinsic_vclz_vs_nxv32i8(<vscale x 32 x i8> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vclz_vs_nxv32i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, m4, ta, ma
+; CHECK-NEXT:    vclz.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 32 x i8> @llvm.riscv.vclz.nxv32i8(
+    <vscale x 32 x i8> undef,
+    <vscale x 32 x i8> %0,
+    iXLen %1)
+
+  ret <vscale x 32 x i8> %a
+}
+
+declare <vscale x 32 x i8> @llvm.riscv.vclz.mask.nxv32i8(
+  <vscale x 32 x i8>,
+  <vscale x 32 x i8>,
+  <vscale x 32 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 32 x i8> @intrinsic_vclz_mask_vs_nxv32i8(<vscale x 32 x i1> %0, <vscale x 32 x i8> %1, <vscale x 32 x i8> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vclz_mask_vs_nxv32i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, m4, ta, mu
+; CHECK-NEXT:    vclz.v v8, v12, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 32 x i8> @llvm.riscv.vclz.mask.nxv32i8(
+    <vscale x 32 x i8> %1,
+    <vscale x 32 x i8> %2,
+    <vscale x 32 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 32 x i8> %a
+}
+
+declare <vscale x 64 x i8> @llvm.riscv.vclz.nxv64i8(
+  <vscale x 64 x i8>,
+  <vscale x 64 x i8>,
+  iXLen);
+
+define <vscale x 64 x i8> @intrinsic_vclz_vs_nxv64i8(<vscale x 64 x i8> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vclz_vs_nxv64i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, m8, ta, ma
+; CHECK-NEXT:    vclz.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 64 x i8> @llvm.riscv.vclz.nxv64i8(
+    <vscale x 64 x i8> undef,
+    <vscale x 64 x i8> %0,
+    iXLen %1)
+
+  ret <vscale x 64 x i8> %a
+}
+
+declare <vscale x 64 x i8> @llvm.riscv.vclz.mask.nxv64i8(
+  <vscale x 64 x i8>,
+  <vscale x 64 x i8>,
+  <vscale x 64 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 64 x i8> @intrinsic_vclz_mask_vs_nxv64i8(<vscale x 64 x i1> %0, <vscale x 64 x i8> %1, <vscale x 64 x i8> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vclz_mask_vs_nxv64i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, m8, ta, mu
+; CHECK-NEXT:    vclz.v v8, v16, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 64 x i8> @llvm.riscv.vclz.mask.nxv64i8(
+    <vscale x 64 x i8> %1,
+    <vscale x 64 x i8> %2,
+    <vscale x 64 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 64 x i8> %a
+}
+
+declare <vscale x 1 x i16> @llvm.riscv.vclz.nxv1i16(
+  <vscale x 1 x i16>,
+  <vscale x 1 x i16>,
+  iXLen);
+
+define <vscale x 1 x i16> @intrinsic_vclz_vs_nxv1i16(<vscale x 1 x i16> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vclz_vs_nxv1i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, mf4, ta, ma
+; CHECK-NEXT:    vclz.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i16> @llvm.riscv.vclz.nxv1i16(
+    <vscale x 1 x i16> undef,
+    <vscale x 1 x i16> %0,
+    iXLen %1)
+
+  ret <vscale x 1 x i16> %a
+}
+
+declare <vscale x 1 x i16> @llvm.riscv.vclz.mask.nxv1i16(
+  <vscale x 1 x i16>,
+  <vscale x 1 x i16>,
+  <vscale x 1 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 1 x i16> @intrinsic_vclz_mask_vs_nxv1i16(<vscale x 1 x i1> %0, <vscale x 1 x i16> %1, <vscale x 1 x i16> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vclz_mask_vs_nxv1i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, mf4, ta, mu
+; CHECK-NEXT:    vclz.v v8, v9, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i16> @llvm.riscv.vclz.mask.nxv1i16(
+    <vscale x 1 x i16> %1,
+    <vscale x 1 x i16> %2,
+    <vscale x 1 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 1 x i16> %a
+}
+
+declare <vscale x 2 x i16> @llvm.riscv.vclz.nxv2i16(
+  <vscale x 2 x i16>,
+  <vscale x 2 x i16>,
+  iXLen);
+
+define <vscale x 2 x i16> @intrinsic_vclz_vs_nxv2i16(<vscale x 2 x i16> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vclz_vs_nxv2i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, mf2, ta, ma
+; CHECK-NEXT:    vclz.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i16> @llvm.riscv.vclz.nxv2i16(
+    <vscale x 2 x i16> undef,
+    <vscale x 2 x i16> %0,
+    iXLen %1)
+
+  ret <vscale x 2 x i16> %a
+}
+
+declare <vscale x 2 x i16> @llvm.riscv.vclz.mask.nxv2i16(
+  <vscale x 2 x i16>,
+  <vscale x 2 x i16>,
+  <vscale x 2 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 2 x i16> @intrinsic_vclz_mask_vs_nxv2i16(<vscale x 2 x i1> %0, <vscale x 2 x i16> %1, <vscale x 2 x i16> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vclz_mask_vs_nxv2i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, mf2, ta, mu
+; CHECK-NEXT:    vclz.v v8, v9, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i16> @llvm.riscv.vclz.mask.nxv2i16(
+    <vscale x 2 x i16> %1,
+    <vscale x 2 x i16> %2,
+    <vscale x 2 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 2 x i16> %a
+}
+
+declare <vscale x 4 x i16> @llvm.riscv.vclz.nxv4i16(
+  <vscale x 4 x i16>,
+  <vscale x 4 x i16>,
+  iXLen);
+
+define <vscale x 4 x i16> @intrinsic_vclz_vs_nxv4i16(<vscale x 4 x i16> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vclz_vs_nxv4i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, m1, ta, ma
+; CHECK-NEXT:    vclz.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i16> @llvm.riscv.vclz.nxv4i16(
+    <vscale x 4 x i16> undef,
+    <vscale x 4 x i16> %0,
+    iXLen %1)
+
+  ret <vscale x 4 x i16> %a
+}
+
+declare <vscale x 4 x i16> @llvm.riscv.vclz.mask.nxv4i16(
+  <vscale x 4 x i16>,
+  <vscale x 4 x i16>,
+  <vscale x 4 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 4 x i16> @intrinsic_vclz_mask_vs_nxv4i16(<vscale x 4 x i1> %0, <vscale x 4 x i16> %1, <vscale x 4 x i16> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vclz_mask_vs_nxv4i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, m1, ta, mu
+; CHECK-NEXT:    vclz.v v8, v9, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i16> @llvm.riscv.vclz.mask.nxv4i16(
+    <vscale x 4 x i16> %1,
+    <vscale x 4 x i16> %2,
+    <vscale x 4 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 4 x i16> %a
+}
+
+declare <vscale x 8 x i16> @llvm.riscv.vclz.nxv8i16(
+  <vscale x 8 x i16>,
+  <vscale x 8 x i16>,
+  iXLen);
+
+define <vscale x 8 x i16> @intrinsic_vclz_vs_nxv8i16(<vscale x 8 x i16> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vclz_vs_nxv8i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, m2, ta, ma
+; CHECK-NEXT:    vclz.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i16> @llvm.riscv.vclz.nxv8i16(
+    <vscale x 8 x i16> undef,
+    <vscale x 8 x i16> %0,
+    iXLen %1)
+
+  ret <vscale x 8 x i16> %a
+}
+
+declare <vscale x 8 x i16> @llvm.riscv.vclz.mask.nxv8i16(
+  <vscale x 8 x i16>,
+  <vscale x 8 x i16>,
+  <vscale x 8 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 8 x i16> @intrinsic_vclz_mask_vs_nxv8i16(<vscale x 8 x i1> %0, <vscale x 8 x i16> %1, <vscale x 8 x i16> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vclz_mask_vs_nxv8i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, m2, ta, mu
+; CHECK-NEXT:    vclz.v v8, v10, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i16> @llvm.riscv.vclz.mask.nxv8i16(
+    <vscale x 8 x i16> %1,
+    <vscale x 8 x i16> %2,
+    <vscale x 8 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 8 x i16> %a
+}
+
+declare <vscale x 16 x i16> @llvm.riscv.vclz.nxv16i16(
+  <vscale x 16 x i16>,
+  <vscale x 16 x i16>,
+  iXLen);
+
+define <vscale x 16 x i16> @intrinsic_vclz_vs_nxv16i16(<vscale x 16 x i16> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vclz_vs_nxv16i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, m4, ta, ma
+; CHECK-NEXT:    vclz.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 16 x i16> @llvm.riscv.vclz.nxv16i16(
+    <vscale x 16 x i16> undef,
+    <vscale x 16 x i16> %0,
+    iXLen %1)
+
+  ret <vscale x 16 x i16> %a
+}
+
+declare <vscale x 16 x i16> @llvm.riscv.vclz.mask.nxv16i16(
+  <vscale x 16 x i16>,
+  <vscale x 16 x i16>,
+  <vscale x 16 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 16 x i16> @intrinsic_vclz_mask_vs_nxv16i16(<vscale x 16 x i1> %0, <vscale x 16 x i16> %1, <vscale x 16 x i16> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vclz_mask_vs_nxv16i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, m4, ta, mu
+; CHECK-NEXT:    vclz.v v8, v12, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 16 x i16> @llvm.riscv.vclz.mask.nxv16i16(
+    <vscale x 16 x i16> %1,
+    <vscale x 16 x i16> %2,
+    <vscale x 16 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 16 x i16> %a
+}
+
+declare <vscale x 32 x i16> @llvm.riscv.vclz.nxv32i16(
+  <vscale x 32 x i16>,
+  <vscale x 32 x i16>,
+  iXLen);
+
+define <vscale x 32 x i16> @intrinsic_vclz_vs_nxv32i16(<vscale x 32 x i16> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vclz_vs_nxv32i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, m8, ta, ma
+; CHECK-NEXT:    vclz.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 32 x i16> @llvm.riscv.vclz.nxv32i16(
+    <vscale x 32 x i16> undef,
+    <vscale x 32 x i16> %0,
+    iXLen %1)
+
+  ret <vscale x 32 x i16> %a
+}
+
+declare <vscale x 32 x i16> @llvm.riscv.vclz.mask.nxv32i16(
+  <vscale x 32 x i16>,
+  <vscale x 32 x i16>,
+  <vscale x 32 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 32 x i16> @intrinsic_vclz_mask_vs_nxv32i16(<vscale x 32 x i1> %0, <vscale x 32 x i16> %1, <vscale x 32 x i16> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vclz_mask_vs_nxv32i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, m8, ta, mu
+; CHECK-NEXT:    vclz.v v8, v16, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 32 x i16> @llvm.riscv.vclz.mask.nxv32i16(
+    <vscale x 32 x i16> %1,
+    <vscale x 32 x i16> %2,
+    <vscale x 32 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 32 x i16> %a
+}
+
+declare <vscale x 1 x i32> @llvm.riscv.vclz.nxv1i32(
+  <vscale x 1 x i32>,
+  <vscale x 1 x i32>,
+  iXLen);
+
+define <vscale x 1 x i32> @intrinsic_vclz_vs_nxv1i32(<vscale x 1 x i32> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vclz_vs_nxv1i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, mf2, ta, ma
+; CHECK-NEXT:    vclz.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i32> @llvm.riscv.vclz.nxv1i32(
+    <vscale x 1 x i32> undef,
+    <vscale x 1 x i32> %0,
+    iXLen %1)
+
+  ret <vscale x 1 x i32> %a
+}
+
+declare <vscale x 1 x i32> @llvm.riscv.vclz.mask.nxv1i32(
+  <vscale x 1 x i32>,
+  <vscale x 1 x i32>,
+  <vscale x 1 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 1 x i32> @intrinsic_vclz_mask_vs_nxv1i32(<vscale x 1 x i1> %0, <vscale x 1 x i32> %1, <vscale x 1 x i32> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vclz_mask_vs_nxv1i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, mf2, ta, mu
+; CHECK-NEXT:    vclz.v v8, v9, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i32> @llvm.riscv.vclz.mask.nxv1i32(
+    <vscale x 1 x i32> %1,
+    <vscale x 1 x i32> %2,
+    <vscale x 1 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 1 x i32> %a
+}
+
+declare <vscale x 2 x i32> @llvm.riscv.vclz.nxv2i32(
+  <vscale x 2 x i32>,
+  <vscale x 2 x i32>,
+  iXLen);
+
+define <vscale x 2 x i32> @intrinsic_vclz_vs_nxv2i32(<vscale x 2 x i32> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vclz_vs_nxv2i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m1, ta, ma
+; CHECK-NEXT:    vclz.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i32> @llvm.riscv.vclz.nxv2i32(
+    <vscale x 2 x i32> undef,
+    <vscale x 2 x i32> %0,
+    iXLen %1)
+
+  ret <vscale x 2 x i32> %a
+}
+
+declare <vscale x 2 x i32> @llvm.riscv.vclz.mask.nxv2i32(
+  <vscale x 2 x i32>,
+  <vscale x 2 x i32>,
+  <vscale x 2 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 2 x i32> @intrinsic_vclz_mask_vs_nxv2i32(<vscale x 2 x i1> %0, <vscale x 2 x i32> %1, <vscale x 2 x i32> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vclz_mask_vs_nxv2i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m1, ta, mu
+; CHECK-NEXT:    vclz.v v8, v9, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i32> @llvm.riscv.vclz.mask.nxv2i32(
+    <vscale x 2 x i32> %1,
+    <vscale x 2 x i32> %2,
+    <vscale x 2 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 2 x i32> %a
+}
+
+declare <vscale x 4 x i32> @llvm.riscv.vclz.nxv4i32(
+  <vscale x 4 x i32>,
+  <vscale x 4 x i32>,
+  iXLen);
+
+define <vscale x 4 x i32> @intrinsic_vclz_vs_nxv4i32(<vscale x 4 x i32> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vclz_vs_nxv4i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m2, ta, ma
+; CHECK-NEXT:    vclz.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i32> @llvm.riscv.vclz.nxv4i32(
+    <vscale x 4 x i32> undef,
+    <vscale x 4 x i32> %0,
+    iXLen %1)
+
+  ret <vscale x 4 x i32> %a
+}
+
+declare <vscale x 4 x i32> @llvm.riscv.vclz.mask.nxv4i32(
+  <vscale x 4 x i32>,
+  <vscale x 4 x i32>,
+  <vscale x 4 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 4 x i32> @intrinsic_vclz_mask_vs_nxv4i32(<vscale x 4 x i1> %0, <vscale x 4 x i32> %1, <vscale x 4 x i32> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vclz_mask_vs_nxv4i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m2, ta, mu
+; CHECK-NEXT:    vclz.v v8, v10, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i32> @llvm.riscv.vclz.mask.nxv4i32(
+    <vscale x 4 x i32> %1,
+    <vscale x 4 x i32> %2,
+    <vscale x 4 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 4 x i32> %a
+}
+
+declare <vscale x 8 x i32> @llvm.riscv.vclz.nxv8i32(
+  <vscale x 8 x i32>,
+  <vscale x 8 x i32>,
+  iXLen);
+
+define <vscale x 8 x i32> @intrinsic_vclz_vs_nxv8i32(<vscale x 8 x i32> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vclz_vs_nxv8i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m4, ta, ma
+; CHECK-NEXT:    vclz.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i32> @llvm.riscv.vclz.nxv8i32(
+    <vscale x 8 x i32> undef,
+    <vscale x 8 x i32> %0,
+    iXLen %1)
+
+  ret <vscale x 8 x i32> %a
+}
+
+declare <vscale x 8 x i32> @llvm.riscv.vclz.mask.nxv8i32(
+  <vscale x 8 x i32>,
+  <vscale x 8 x i32>,
+  <vscale x 8 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 8 x i32> @intrinsic_vclz_mask_vs_nxv8i32(<vscale x 8 x i1> %0, <vscale x 8 x i32> %1, <vscale x 8 x i32> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vclz_mask_vs_nxv8i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m4, ta, mu
+; CHECK-NEXT:    vclz.v v8, v12, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i32> @llvm.riscv.vclz.mask.nxv8i32(
+    <vscale x 8 x i32> %1,
+    <vscale x 8 x i32> %2,
+    <vscale x 8 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 8 x i32> %a
+}
+
+declare <vscale x 16 x i32> @llvm.riscv.vclz.nxv16i32(
+  <vscale x 16 x i32>,
+  <vscale x 16 x i32>,
+  iXLen);
+
+define <vscale x 16 x i32> @intrinsic_vclz_vs_nxv16i32(<vscale x 16 x i32> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vclz_vs_nxv16i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m8, ta, ma
+; CHECK-NEXT:    vclz.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 16 x i32> @llvm.riscv.vclz.nxv16i32(
+    <vscale x 16 x i32> undef,
+    <vscale x 16 x i32> %0,
+    iXLen %1)
+
+  ret <vscale x 16 x i32> %a
+}
+
+declare <vscale x 16 x i32> @llvm.riscv.vclz.mask.nxv16i32(
+  <vscale x 16 x i32>,
+  <vscale x 16 x i32>,
+  <vscale x 16 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 16 x i32> @intrinsic_vclz_mask_vs_nxv16i32(<vscale x 16 x i1> %0, <vscale x 16 x i32> %1, <vscale x 16 x i32> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vclz_mask_vs_nxv16i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m8, ta, mu
+; CHECK-NEXT:    vclz.v v8, v16, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 16 x i32> @llvm.riscv.vclz.mask.nxv16i32(
+    <vscale x 16 x i32> %1,
+    <vscale x 16 x i32> %2,
+    <vscale x 16 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 16 x i32> %a
+}
+
+declare <vscale x 1 x i64> @llvm.riscv.vclz.nxv1i64(
+  <vscale x 1 x i64>,
+  <vscale x 1 x i64>,
+  iXLen);
+
+define <vscale x 1 x i64> @intrinsic_vclz_vs_nxv1i64(<vscale x 1 x i64> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vclz_vs_nxv1i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e64, m1, ta, ma
+; CHECK-NEXT:    vclz.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i64> @llvm.riscv.vclz.nxv1i64(
+    <vscale x 1 x i64> undef,
+    <vscale x 1 x i64> %0,
+    iXLen %1)
+
+  ret <vscale x 1 x i64> %a
+}
+
+declare <vscale x 1 x i64> @llvm.riscv.vclz.mask.nxv1i64(
+  <vscale x 1 x i64>,
+  <vscale x 1 x i64>,
+  <vscale x 1 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 1 x i64> @intrinsic_vclz_mask_vs_nxv1i64(<vscale x 1 x i1> %0, <vscale x 1 x i64> %1, <vscale x 1 x i64> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vclz_mask_vs_nxv1i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e64, m1, ta, mu
+; CHECK-NEXT:    vclz.v v8, v9, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i64> @llvm.riscv.vclz.mask.nxv1i64(
+    <vscale x 1 x i64> %1,
+    <vscale x 1 x i64> %2,
+    <vscale x 1 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 1 x i64> %a
+}
+
+declare <vscale x 2 x i64> @llvm.riscv.vclz.nxv2i64(
+  <vscale x 2 x i64>,
+  <vscale x 2 x i64>,
+  iXLen);
+
+define <vscale x 2 x i64> @intrinsic_vclz_vs_nxv2i64(<vscale x 2 x i64> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vclz_vs_nxv2i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e64, m2, ta, ma
+; CHECK-NEXT:    vclz.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i64> @llvm.riscv.vclz.nxv2i64(
+    <vscale x 2 x i64> undef,
+    <vscale x 2 x i64> %0,
+    iXLen %1)
+
+  ret <vscale x 2 x i64> %a
+}
+
+declare <vscale x 2 x i64> @llvm.riscv.vclz.mask.nxv2i64(
+  <vscale x 2 x i64>,
+  <vscale x 2 x i64>,
+  <vscale x 2 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 2 x i64> @intrinsic_vclz_mask_vs_nxv2i64(<vscale x 2 x i1> %0, <vscale x 2 x i64> %1, <vscale x 2 x i64> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vclz_mask_vs_nxv2i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e64, m2, ta, mu
+; CHECK-NEXT:    vclz.v v8, v10, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i64> @llvm.riscv.vclz.mask.nxv2i64(
+    <vscale x 2 x i64> %1,
+    <vscale x 2 x i64> %2,
+    <vscale x 2 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 2 x i64> %a
+}
+
+declare <vscale x 4 x i64> @llvm.riscv.vclz.nxv4i64(
+  <vscale x 4 x i64>,
+  <vscale x 4 x i64>,
+  iXLen);
+
+define <vscale x 4 x i64> @intrinsic_vclz_vs_nxv4i64(<vscale x 4 x i64> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vclz_vs_nxv4i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e64, m4, ta, ma
+; CHECK-NEXT:    vclz.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i64> @llvm.riscv.vclz.nxv4i64(
+    <vscale x 4 x i64> undef,
+    <vscale x 4 x i64> %0,
+    iXLen %1)
+
+  ret <vscale x 4 x i64> %a
+}
+
+declare <vscale x 4 x i64> @llvm.riscv.vclz.mask.nxv4i64(
+  <vscale x 4 x i64>,
+  <vscale x 4 x i64>,
+  <vscale x 4 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 4 x i64> @intrinsic_vclz_mask_vs_nxv4i64(<vscale x 4 x i1> %0, <vscale x 4 x i64> %1, <vscale x 4 x i64> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vclz_mask_vs_nxv4i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e64, m4, ta, mu
+; CHECK-NEXT:    vclz.v v8, v12, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i64> @llvm.riscv.vclz.mask.nxv4i64(
+    <vscale x 4 x i64> %1,
+    <vscale x 4 x i64> %2,
+    <vscale x 4 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 4 x i64> %a
+}
+
+declare <vscale x 8 x i64> @llvm.riscv.vclz.nxv8i64(
+  <vscale x 8 x i64>,
+  <vscale x 8 x i64>,
+  iXLen);
+
+define <vscale x 8 x i64> @intrinsic_vclz_vs_nxv8i64(<vscale x 8 x i64> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vclz_vs_nxv8i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
+; CHECK-NEXT:    vclz.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i64> @llvm.riscv.vclz.nxv8i64(
+    <vscale x 8 x i64> undef,
+    <vscale x 8 x i64> %0,
+    iXLen %1)
+
+  ret <vscale x 8 x i64> %a
+}
+
+declare <vscale x 8 x i64> @llvm.riscv.vclz.mask.nxv8i64(
+  <vscale x 8 x i64>,
+  <vscale x 8 x i64>,
+  <vscale x 8 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 8 x i64> @intrinsic_vclz_mask_vs_nxv8i64(<vscale x 8 x i1> %0, <vscale x 8 x i64> %1, <vscale x 8 x i64> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vclz_mask_vs_nxv8i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, mu
+; CHECK-NEXT:    vclz.v v8, v16, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i64> @llvm.riscv.vclz.mask.nxv8i64(
+    <vscale x 8 x i64> %1,
+    <vscale x 8 x i64> %2,
+    <vscale x 8 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 8 x i64> %a
+}

llvm/test/CodeGen/RISCV/rvv/vcpopv.ll

+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: sed 's/iXLen/i32/g' %s | llc -mtriple=riscv32 -mattr=+v,+experimental-zvbb \
+; RUN:   -verify-machineinstrs | FileCheck %s --check-prefixes=CHECK
+; RUN: sed 's/iXLen/i64/g' %s | llc -mtriple=riscv64 -mattr=+v,+experimental-zvbb \
+; RUN:   -verify-machineinstrs | FileCheck %s --check-prefixes=CHECK
+
+declare <vscale x 1 x i8> @llvm.riscv.vcpopv.nxv1i8(
+  <vscale x 1 x i8>,
+  <vscale x 1 x i8>,
+  iXLen);
+
+define <vscale x 1 x i8> @intrinsic_vcpopv_vs_nxv1i8(<vscale x 1 x i8> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vcpopv_vs_nxv1i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, mf8, ta, ma
+; CHECK-NEXT:    vcpop.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i8> @llvm.riscv.vcpopv.nxv1i8(
+    <vscale x 1 x i8> undef,
+    <vscale x 1 x i8> %0,
+    iXLen %1)
+
+  ret <vscale x 1 x i8> %a
+}
+
+declare <vscale x 1 x i8> @llvm.riscv.vcpopv.mask.nxv1i8(
+  <vscale x 1 x i8>,
+  <vscale x 1 x i8>,
+  <vscale x 1 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 1 x i8> @intrinsic_vcpopv_mask_vs_nxv1i8(<vscale x 1 x i1> %0, <vscale x 1 x i8> %1, <vscale x 1 x i8> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vcpopv_mask_vs_nxv1i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, mf8, ta, mu
+; CHECK-NEXT:    vcpop.v v8, v9, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i8> @llvm.riscv.vcpopv.mask.nxv1i8(
+    <vscale x 1 x i8> %1,
+    <vscale x 1 x i8> %2,
+    <vscale x 1 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 1 x i8> %a
+}
+
+declare <vscale x 2 x i8> @llvm.riscv.vcpopv.nxv2i8(
+  <vscale x 2 x i8>,
+  <vscale x 2 x i8>,
+  iXLen);
+
+define <vscale x 2 x i8> @intrinsic_vcpopv_vs_nxv2i8(<vscale x 2 x i8> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vcpopv_vs_nxv2i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, mf4, ta, ma
+; CHECK-NEXT:    vcpop.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i8> @llvm.riscv.vcpopv.nxv2i8(
+    <vscale x 2 x i8> undef,
+    <vscale x 2 x i8> %0,
+    iXLen %1)
+
+  ret <vscale x 2 x i8> %a
+}
+
+declare <vscale x 2 x i8> @llvm.riscv.vcpopv.mask.nxv2i8(
+  <vscale x 2 x i8>,
+  <vscale x 2 x i8>,
+  <vscale x 2 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 2 x i8> @intrinsic_vcpopv_mask_vs_nxv2i8(<vscale x 2 x i1> %0, <vscale x 2 x i8> %1, <vscale x 2 x i8> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vcpopv_mask_vs_nxv2i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, mf4, ta, mu
+; CHECK-NEXT:    vcpop.v v8, v9, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i8> @llvm.riscv.vcpopv.mask.nxv2i8(
+    <vscale x 2 x i8> %1,
+    <vscale x 2 x i8> %2,
+    <vscale x 2 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 2 x i8> %a
+}
+
+declare <vscale x 4 x i8> @llvm.riscv.vcpopv.nxv4i8(
+  <vscale x 4 x i8>,
+  <vscale x 4 x i8>,
+  iXLen);
+
+define <vscale x 4 x i8> @intrinsic_vcpopv_vs_nxv4i8(<vscale x 4 x i8> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vcpopv_vs_nxv4i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, mf2, ta, ma
+; CHECK-NEXT:    vcpop.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i8> @llvm.riscv.vcpopv.nxv4i8(
+    <vscale x 4 x i8> undef,
+    <vscale x 4 x i8> %0,
+    iXLen %1)
+
+  ret <vscale x 4 x i8> %a
+}
+
+declare <vscale x 4 x i8> @llvm.riscv.vcpopv.mask.nxv4i8(
+  <vscale x 4 x i8>,
+  <vscale x 4 x i8>,
+  <vscale x 4 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 4 x i8> @intrinsic_vcpopv_mask_vs_nxv4i8(<vscale x 4 x i1> %0, <vscale x 4 x i8> %1, <vscale x 4 x i8> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vcpopv_mask_vs_nxv4i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, mf2, ta, mu
+; CHECK-NEXT:    vcpop.v v8, v9, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i8> @llvm.riscv.vcpopv.mask.nxv4i8(
+    <vscale x 4 x i8> %1,
+    <vscale x 4 x i8> %2,
+    <vscale x 4 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 4 x i8> %a
+}
+
+declare <vscale x 8 x i8> @llvm.riscv.vcpopv.nxv8i8(
+  <vscale x 8 x i8>,
+  <vscale x 8 x i8>,
+  iXLen);
+
+define <vscale x 8 x i8> @intrinsic_vcpopv_vs_nxv8i8(<vscale x 8 x i8> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vcpopv_vs_nxv8i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, m1, ta, ma
+; CHECK-NEXT:    vcpop.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i8> @llvm.riscv.vcpopv.nxv8i8(
+    <vscale x 8 x i8> undef,
+    <vscale x 8 x i8> %0,
+    iXLen %1)
+
+  ret <vscale x 8 x i8> %a
+}
+
+declare <vscale x 8 x i8> @llvm.riscv.vcpopv.mask.nxv8i8(
+  <vscale x 8 x i8>,
+  <vscale x 8 x i8>,
+  <vscale x 8 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 8 x i8> @intrinsic_vcpopv_mask_vs_nxv8i8(<vscale x 8 x i1> %0, <vscale x 8 x i8> %1, <vscale x 8 x i8> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vcpopv_mask_vs_nxv8i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, m1, ta, mu
+; CHECK-NEXT:    vcpop.v v8, v9, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i8> @llvm.riscv.vcpopv.mask.nxv8i8(
+    <vscale x 8 x i8> %1,
+    <vscale x 8 x i8> %2,
+    <vscale x 8 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 8 x i8> %a
+}
+
+declare <vscale x 16 x i8> @llvm.riscv.vcpopv.nxv16i8(
+  <vscale x 16 x i8>,
+  <vscale x 16 x i8>,
+  iXLen);
+
+define <vscale x 16 x i8> @intrinsic_vcpopv_vs_nxv16i8(<vscale x 16 x i8> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vcpopv_vs_nxv16i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, m2, ta, ma
+; CHECK-NEXT:    vcpop.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 16 x i8> @llvm.riscv.vcpopv.nxv16i8(
+    <vscale x 16 x i8> undef,
+    <vscale x 16 x i8> %0,
+    iXLen %1)
+
+  ret <vscale x 16 x i8> %a
+}
+
+declare <vscale x 16 x i8> @llvm.riscv.vcpopv.mask.nxv16i8(
+  <vscale x 16 x i8>,
+  <vscale x 16 x i8>,
+  <vscale x 16 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 16 x i8> @intrinsic_vcpopv_mask_vs_nxv16i8(<vscale x 16 x i1> %0, <vscale x 16 x i8> %1, <vscale x 16 x i8> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vcpopv_mask_vs_nxv16i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, m2, ta, mu
+; CHECK-NEXT:    vcpop.v v8, v10, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 16 x i8> @llvm.riscv.vcpopv.mask.nxv16i8(
+    <vscale x 16 x i8> %1,
+    <vscale x 16 x i8> %2,
+    <vscale x 16 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 16 x i8> %a
+}
+
+declare <vscale x 32 x i8> @llvm.riscv.vcpopv.nxv32i8(
+  <vscale x 32 x i8>,
+  <vscale x 32 x i8>,
+  iXLen);
+
+define <vscale x 32 x i8> @intrinsic_vcpopv_vs_nxv32i8(<vscale x 32 x i8> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vcpopv_vs_nxv32i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, m4, ta, ma
+; CHECK-NEXT:    vcpop.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 32 x i8> @llvm.riscv.vcpopv.nxv32i8(
+    <vscale x 32 x i8> undef,
+    <vscale x 32 x i8> %0,
+    iXLen %1)
+
+  ret <vscale x 32 x i8> %a
+}
+
+declare <vscale x 32 x i8> @llvm.riscv.vcpopv.mask.nxv32i8(
+  <vscale x 32 x i8>,
+  <vscale x 32 x i8>,
+  <vscale x 32 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 32 x i8> @intrinsic_vcpopv_mask_vs_nxv32i8(<vscale x 32 x i1> %0, <vscale x 32 x i8> %1, <vscale x 32 x i8> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vcpopv_mask_vs_nxv32i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, m4, ta, mu
+; CHECK-NEXT:    vcpop.v v8, v12, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 32 x i8> @llvm.riscv.vcpopv.mask.nxv32i8(
+    <vscale x 32 x i8> %1,
+    <vscale x 32 x i8> %2,
+    <vscale x 32 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 32 x i8> %a
+}
+
+declare <vscale x 64 x i8> @llvm.riscv.vcpopv.nxv64i8(
+  <vscale x 64 x i8>,
+  <vscale x 64 x i8>,
+  iXLen);
+
+define <vscale x 64 x i8> @intrinsic_vcpopv_vs_nxv64i8(<vscale x 64 x i8> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vcpopv_vs_nxv64i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, m8, ta, ma
+; CHECK-NEXT:    vcpop.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 64 x i8> @llvm.riscv.vcpopv.nxv64i8(
+    <vscale x 64 x i8> undef,
+    <vscale x 64 x i8> %0,
+    iXLen %1)
+
+  ret <vscale x 64 x i8> %a
+}
+
+declare <vscale x 64 x i8> @llvm.riscv.vcpopv.mask.nxv64i8(
+  <vscale x 64 x i8>,
+  <vscale x 64 x i8>,
+  <vscale x 64 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 64 x i8> @intrinsic_vcpopv_mask_vs_nxv64i8(<vscale x 64 x i1> %0, <vscale x 64 x i8> %1, <vscale x 64 x i8> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vcpopv_mask_vs_nxv64i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, m8, ta, mu
+; CHECK-NEXT:    vcpop.v v8, v16, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 64 x i8> @llvm.riscv.vcpopv.mask.nxv64i8(
+    <vscale x 64 x i8> %1,
+    <vscale x 64 x i8> %2,
+    <vscale x 64 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 64 x i8> %a
+}
+
+declare <vscale x 1 x i16> @llvm.riscv.vcpopv.nxv1i16(
+  <vscale x 1 x i16>,
+  <vscale x 1 x i16>,
+  iXLen);
+
+define <vscale x 1 x i16> @intrinsic_vcpopv_vs_nxv1i16(<vscale x 1 x i16> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vcpopv_vs_nxv1i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, mf4, ta, ma
+; CHECK-NEXT:    vcpop.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i16> @llvm.riscv.vcpopv.nxv1i16(
+    <vscale x 1 x i16> undef,
+    <vscale x 1 x i16> %0,
+    iXLen %1)
+
+  ret <vscale x 1 x i16> %a
+}
+
+declare <vscale x 1 x i16> @llvm.riscv.vcpopv.mask.nxv1i16(
+  <vscale x 1 x i16>,
+  <vscale x 1 x i16>,
+  <vscale x 1 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 1 x i16> @intrinsic_vcpopv_mask_vs_nxv1i16(<vscale x 1 x i1> %0, <vscale x 1 x i16> %1, <vscale x 1 x i16> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vcpopv_mask_vs_nxv1i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, mf4, ta, mu
+; CHECK-NEXT:    vcpop.v v8, v9, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i16> @llvm.riscv.vcpopv.mask.nxv1i16(
+    <vscale x 1 x i16> %1,
+    <vscale x 1 x i16> %2,
+    <vscale x 1 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 1 x i16> %a
+}
+
+declare <vscale x 2 x i16> @llvm.riscv.vcpopv.nxv2i16(
+  <vscale x 2 x i16>,
+  <vscale x 2 x i16>,
+  iXLen);
+
+define <vscale x 2 x i16> @intrinsic_vcpopv_vs_nxv2i16(<vscale x 2 x i16> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vcpopv_vs_nxv2i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, mf2, ta, ma
+; CHECK-NEXT:    vcpop.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i16> @llvm.riscv.vcpopv.nxv2i16(
+    <vscale x 2 x i16> undef,
+    <vscale x 2 x i16> %0,
+    iXLen %1)
+
+  ret <vscale x 2 x i16> %a
+}
+
+declare <vscale x 2 x i16> @llvm.riscv.vcpopv.mask.nxv2i16(
+  <vscale x 2 x i16>,
+  <vscale x 2 x i16>,
+  <vscale x 2 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 2 x i16> @intrinsic_vcpopv_mask_vs_nxv2i16(<vscale x 2 x i1> %0, <vscale x 2 x i16> %1, <vscale x 2 x i16> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vcpopv_mask_vs_nxv2i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, mf2, ta, mu
+; CHECK-NEXT:    vcpop.v v8, v9, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i16> @llvm.riscv.vcpopv.mask.nxv2i16(
+    <vscale x 2 x i16> %1,
+    <vscale x 2 x i16> %2,
+    <vscale x 2 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 2 x i16> %a
+}
+
+declare <vscale x 4 x i16> @llvm.riscv.vcpopv.nxv4i16(
+  <vscale x 4 x i16>,
+  <vscale x 4 x i16>,
+  iXLen);
+
+define <vscale x 4 x i16> @intrinsic_vcpopv_vs_nxv4i16(<vscale x 4 x i16> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vcpopv_vs_nxv4i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, m1, ta, ma
+; CHECK-NEXT:    vcpop.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i16> @llvm.riscv.vcpopv.nxv4i16(
+    <vscale x 4 x i16> undef,
+    <vscale x 4 x i16> %0,
+    iXLen %1)
+
+  ret <vscale x 4 x i16> %a
+}
+
+declare <vscale x 4 x i16> @llvm.riscv.vcpopv.mask.nxv4i16(
+  <vscale x 4 x i16>,
+  <vscale x 4 x i16>,
+  <vscale x 4 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 4 x i16> @intrinsic_vcpopv_mask_vs_nxv4i16(<vscale x 4 x i1> %0, <vscale x 4 x i16> %1, <vscale x 4 x i16> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vcpopv_mask_vs_nxv4i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, m1, ta, mu
+; CHECK-NEXT:    vcpop.v v8, v9, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i16> @llvm.riscv.vcpopv.mask.nxv4i16(
+    <vscale x 4 x i16> %1,
+    <vscale x 4 x i16> %2,
+    <vscale x 4 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 4 x i16> %a
+}
+
+declare <vscale x 8 x i16> @llvm.riscv.vcpopv.nxv8i16(
+  <vscale x 8 x i16>,
+  <vscale x 8 x i16>,
+  iXLen);
+
+define <vscale x 8 x i16> @intrinsic_vcpopv_vs_nxv8i16(<vscale x 8 x i16> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vcpopv_vs_nxv8i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, m2, ta, ma
+; CHECK-NEXT:    vcpop.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i16> @llvm.riscv.vcpopv.nxv8i16(
+    <vscale x 8 x i16> undef,
+    <vscale x 8 x i16> %0,
+    iXLen %1)
+
+  ret <vscale x 8 x i16> %a
+}
+
+declare <vscale x 8 x i16> @llvm.riscv.vcpopv.mask.nxv8i16(
+  <vscale x 8 x i16>,
+  <vscale x 8 x i16>,
+  <vscale x 8 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 8 x i16> @intrinsic_vcpopv_mask_vs_nxv8i16(<vscale x 8 x i1> %0, <vscale x 8 x i16> %1, <vscale x 8 x i16> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vcpopv_mask_vs_nxv8i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, m2, ta, mu
+; CHECK-NEXT:    vcpop.v v8, v10, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i16> @llvm.riscv.vcpopv.mask.nxv8i16(
+    <vscale x 8 x i16> %1,
+    <vscale x 8 x i16> %2,
+    <vscale x 8 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 8 x i16> %a
+}
+
+declare <vscale x 16 x i16> @llvm.riscv.vcpopv.nxv16i16(
+  <vscale x 16 x i16>,
+  <vscale x 16 x i16>,
+  iXLen);
+
+define <vscale x 16 x i16> @intrinsic_vcpopv_vs_nxv16i16(<vscale x 16 x i16> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vcpopv_vs_nxv16i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, m4, ta, ma
+; CHECK-NEXT:    vcpop.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 16 x i16> @llvm.riscv.vcpopv.nxv16i16(
+    <vscale x 16 x i16> undef,
+    <vscale x 16 x i16> %0,
+    iXLen %1)
+
+  ret <vscale x 16 x i16> %a
+}
+
+declare <vscale x 16 x i16> @llvm.riscv.vcpopv.mask.nxv16i16(
+  <vscale x 16 x i16>,
+  <vscale x 16 x i16>,
+  <vscale x 16 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 16 x i16> @intrinsic_vcpopv_mask_vs_nxv16i16(<vscale x 16 x i1> %0, <vscale x 16 x i16> %1, <vscale x 16 x i16> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vcpopv_mask_vs_nxv16i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, m4, ta, mu
+; CHECK-NEXT:    vcpop.v v8, v12, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 16 x i16> @llvm.riscv.vcpopv.mask.nxv16i16(
+    <vscale x 16 x i16> %1,
+    <vscale x 16 x i16> %2,
+    <vscale x 16 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 16 x i16> %a
+}
+
+declare <vscale x 32 x i16> @llvm.riscv.vcpopv.nxv32i16(
+  <vscale x 32 x i16>,
+  <vscale x 32 x i16>,
+  iXLen);
+
+define <vscale x 32 x i16> @intrinsic_vcpopv_vs_nxv32i16(<vscale x 32 x i16> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vcpopv_vs_nxv32i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, m8, ta, ma
+; CHECK-NEXT:    vcpop.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 32 x i16> @llvm.riscv.vcpopv.nxv32i16(
+    <vscale x 32 x i16> undef,
+    <vscale x 32 x i16> %0,
+    iXLen %1)
+
+  ret <vscale x 32 x i16> %a
+}
+
+declare <vscale x 32 x i16> @llvm.riscv.vcpopv.mask.nxv32i16(
+  <vscale x 32 x i16>,
+  <vscale x 32 x i16>,
+  <vscale x 32 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 32 x i16> @intrinsic_vcpopv_mask_vs_nxv32i16(<vscale x 32 x i1> %0, <vscale x 32 x i16> %1, <vscale x 32 x i16> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vcpopv_mask_vs_nxv32i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, m8, ta, mu
+; CHECK-NEXT:    vcpop.v v8, v16, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 32 x i16> @llvm.riscv.vcpopv.mask.nxv32i16(
+    <vscale x 32 x i16> %1,
+    <vscale x 32 x i16> %2,
+    <vscale x 32 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 32 x i16> %a
+}
+
+declare <vscale x 1 x i32> @llvm.riscv.vcpopv.nxv1i32(
+  <vscale x 1 x i32>,
+  <vscale x 1 x i32>,
+  iXLen);
+
+define <vscale x 1 x i32> @intrinsic_vcpopv_vs_nxv1i32(<vscale x 1 x i32> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vcpopv_vs_nxv1i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, mf2, ta, ma
+; CHECK-NEXT:    vcpop.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i32> @llvm.riscv.vcpopv.nxv1i32(
+    <vscale x 1 x i32> undef,
+    <vscale x 1 x i32> %0,
+    iXLen %1)
+
+  ret <vscale x 1 x i32> %a
+}
+
+declare <vscale x 1 x i32> @llvm.riscv.vcpopv.mask.nxv1i32(
+  <vscale x 1 x i32>,
+  <vscale x 1 x i32>,
+  <vscale x 1 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 1 x i32> @intrinsic_vcpopv_mask_vs_nxv1i32(<vscale x 1 x i1> %0, <vscale x 1 x i32> %1, <vscale x 1 x i32> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vcpopv_mask_vs_nxv1i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, mf2, ta, mu
+; CHECK-NEXT:    vcpop.v v8, v9, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i32> @llvm.riscv.vcpopv.mask.nxv1i32(
+    <vscale x 1 x i32> %1,
+    <vscale x 1 x i32> %2,
+    <vscale x 1 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 1 x i32> %a
+}
+
+declare <vscale x 2 x i32> @llvm.riscv.vcpopv.nxv2i32(
+  <vscale x 2 x i32>,
+  <vscale x 2 x i32>,
+  iXLen);
+
+define <vscale x 2 x i32> @intrinsic_vcpopv_vs_nxv2i32(<vscale x 2 x i32> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vcpopv_vs_nxv2i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m1, ta, ma
+; CHECK-NEXT:    vcpop.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i32> @llvm.riscv.vcpopv.nxv2i32(
+    <vscale x 2 x i32> undef,
+    <vscale x 2 x i32> %0,
+    iXLen %1)
+
+  ret <vscale x 2 x i32> %a
+}
+
+declare <vscale x 2 x i32> @llvm.riscv.vcpopv.mask.nxv2i32(
+  <vscale x 2 x i32>,
+  <vscale x 2 x i32>,
+  <vscale x 2 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 2 x i32> @intrinsic_vcpopv_mask_vs_nxv2i32(<vscale x 2 x i1> %0, <vscale x 2 x i32> %1, <vscale x 2 x i32> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vcpopv_mask_vs_nxv2i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m1, ta, mu
+; CHECK-NEXT:    vcpop.v v8, v9, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i32> @llvm.riscv.vcpopv.mask.nxv2i32(
+    <vscale x 2 x i32> %1,
+    <vscale x 2 x i32> %2,
+    <vscale x 2 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 2 x i32> %a
+}
+
+declare <vscale x 4 x i32> @llvm.riscv.vcpopv.nxv4i32(
+  <vscale x 4 x i32>,
+  <vscale x 4 x i32>,
+  iXLen);
+
+define <vscale x 4 x i32> @intrinsic_vcpopv_vs_nxv4i32(<vscale x 4 x i32> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vcpopv_vs_nxv4i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m2, ta, ma
+; CHECK-NEXT:    vcpop.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i32> @llvm.riscv.vcpopv.nxv4i32(
+    <vscale x 4 x i32> undef,
+    <vscale x 4 x i32> %0,
+    iXLen %1)
+
+  ret <vscale x 4 x i32> %a
+}
+
+declare <vscale x 4 x i32> @llvm.riscv.vcpopv.mask.nxv4i32(
+  <vscale x 4 x i32>,
+  <vscale x 4 x i32>,
+  <vscale x 4 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 4 x i32> @intrinsic_vcpopv_mask_vs_nxv4i32(<vscale x 4 x i1> %0, <vscale x 4 x i32> %1, <vscale x 4 x i32> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vcpopv_mask_vs_nxv4i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m2, ta, mu
+; CHECK-NEXT:    vcpop.v v8, v10, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i32> @llvm.riscv.vcpopv.mask.nxv4i32(
+    <vscale x 4 x i32> %1,
+    <vscale x 4 x i32> %2,
+    <vscale x 4 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 4 x i32> %a
+}
+
+declare <vscale x 8 x i32> @llvm.riscv.vcpopv.nxv8i32(
+  <vscale x 8 x i32>,
+  <vscale x 8 x i32>,
+  iXLen);
+
+define <vscale x 8 x i32> @intrinsic_vcpopv_vs_nxv8i32(<vscale x 8 x i32> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vcpopv_vs_nxv8i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m4, ta, ma
+; CHECK-NEXT:    vcpop.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i32> @llvm.riscv.vcpopv.nxv8i32(
+    <vscale x 8 x i32> undef,
+    <vscale x 8 x i32> %0,
+    iXLen %1)
+
+  ret <vscale x 8 x i32> %a
+}
+
+declare <vscale x 8 x i32> @llvm.riscv.vcpopv.mask.nxv8i32(
+  <vscale x 8 x i32>,
+  <vscale x 8 x i32>,
+  <vscale x 8 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 8 x i32> @intrinsic_vcpopv_mask_vs_nxv8i32(<vscale x 8 x i1> %0, <vscale x 8 x i32> %1, <vscale x 8 x i32> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vcpopv_mask_vs_nxv8i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m4, ta, mu
+; CHECK-NEXT:    vcpop.v v8, v12, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i32> @llvm.riscv.vcpopv.mask.nxv8i32(
+    <vscale x 8 x i32> %1,
+    <vscale x 8 x i32> %2,
+    <vscale x 8 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 8 x i32> %a
+}
+
+declare <vscale x 16 x i32> @llvm.riscv.vcpopv.nxv16i32(
+  <vscale x 16 x i32>,
+  <vscale x 16 x i32>,
+  iXLen);
+
+define <vscale x 16 x i32> @intrinsic_vcpopv_vs_nxv16i32(<vscale x 16 x i32> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vcpopv_vs_nxv16i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m8, ta, ma
+; CHECK-NEXT:    vcpop.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 16 x i32> @llvm.riscv.vcpopv.nxv16i32(
+    <vscale x 16 x i32> undef,
+    <vscale x 16 x i32> %0,
+    iXLen %1)
+
+  ret <vscale x 16 x i32> %a
+}
+
+declare <vscale x 16 x i32> @llvm.riscv.vcpopv.mask.nxv16i32(
+  <vscale x 16 x i32>,
+  <vscale x 16 x i32>,
+  <vscale x 16 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 16 x i32> @intrinsic_vcpopv_mask_vs_nxv16i32(<vscale x 16 x i1> %0, <vscale x 16 x i32> %1, <vscale x 16 x i32> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vcpopv_mask_vs_nxv16i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m8, ta, mu
+; CHECK-NEXT:    vcpop.v v8, v16, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 16 x i32> @llvm.riscv.vcpopv.mask.nxv16i32(
+    <vscale x 16 x i32> %1,
+    <vscale x 16 x i32> %2,
+    <vscale x 16 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 16 x i32> %a
+}
+
+declare <vscale x 1 x i64> @llvm.riscv.vcpopv.nxv1i64(
+  <vscale x 1 x i64>,
+  <vscale x 1 x i64>,
+  iXLen);
+
+define <vscale x 1 x i64> @intrinsic_vcpopv_vs_nxv1i64(<vscale x 1 x i64> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vcpopv_vs_nxv1i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e64, m1, ta, ma
+; CHECK-NEXT:    vcpop.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i64> @llvm.riscv.vcpopv.nxv1i64(
+    <vscale x 1 x i64> undef,
+    <vscale x 1 x i64> %0,
+    iXLen %1)
+
+  ret <vscale x 1 x i64> %a
+}
+
+declare <vscale x 1 x i64> @llvm.riscv.vcpopv.mask.nxv1i64(
+  <vscale x 1 x i64>,
+  <vscale x 1 x i64>,
+  <vscale x 1 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 1 x i64> @intrinsic_vcpopv_mask_vs_nxv1i64(<vscale x 1 x i1> %0, <vscale x 1 x i64> %1, <vscale x 1 x i64> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vcpopv_mask_vs_nxv1i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e64, m1, ta, mu
+; CHECK-NEXT:    vcpop.v v8, v9, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i64> @llvm.riscv.vcpopv.mask.nxv1i64(
+    <vscale x 1 x i64> %1,
+    <vscale x 1 x i64> %2,
+    <vscale x 1 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 1 x i64> %a
+}
+
+declare <vscale x 2 x i64> @llvm.riscv.vcpopv.nxv2i64(
+  <vscale x 2 x i64>,
+  <vscale x 2 x i64>,
+  iXLen);
+
+define <vscale x 2 x i64> @intrinsic_vcpopv_vs_nxv2i64(<vscale x 2 x i64> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vcpopv_vs_nxv2i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e64, m2, ta, ma
+; CHECK-NEXT:    vcpop.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i64> @llvm.riscv.vcpopv.nxv2i64(
+    <vscale x 2 x i64> undef,
+    <vscale x 2 x i64> %0,
+    iXLen %1)
+
+  ret <vscale x 2 x i64> %a
+}
+
+declare <vscale x 2 x i64> @llvm.riscv.vcpopv.mask.nxv2i64(
+  <vscale x 2 x i64>,
+  <vscale x 2 x i64>,
+  <vscale x 2 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 2 x i64> @intrinsic_vcpopv_mask_vs_nxv2i64(<vscale x 2 x i1> %0, <vscale x 2 x i64> %1, <vscale x 2 x i64> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vcpopv_mask_vs_nxv2i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e64, m2, ta, mu
+; CHECK-NEXT:    vcpop.v v8, v10, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i64> @llvm.riscv.vcpopv.mask.nxv2i64(
+    <vscale x 2 x i64> %1,
+    <vscale x 2 x i64> %2,
+    <vscale x 2 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 2 x i64> %a
+}
+
+declare <vscale x 4 x i64> @llvm.riscv.vcpopv.nxv4i64(
+  <vscale x 4 x i64>,
+  <vscale x 4 x i64>,
+  iXLen);
+
+define <vscale x 4 x i64> @intrinsic_vcpopv_vs_nxv4i64(<vscale x 4 x i64> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vcpopv_vs_nxv4i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e64, m4, ta, ma
+; CHECK-NEXT:    vcpop.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i64> @llvm.riscv.vcpopv.nxv4i64(
+    <vscale x 4 x i64> undef,
+    <vscale x 4 x i64> %0,
+    iXLen %1)
+
+  ret <vscale x 4 x i64> %a
+}
+
+declare <vscale x 4 x i64> @llvm.riscv.vcpopv.mask.nxv4i64(
+  <vscale x 4 x i64>,
+  <vscale x 4 x i64>,
+  <vscale x 4 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 4 x i64> @intrinsic_vcpopv_mask_vs_nxv4i64(<vscale x 4 x i1> %0, <vscale x 4 x i64> %1, <vscale x 4 x i64> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vcpopv_mask_vs_nxv4i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e64, m4, ta, mu
+; CHECK-NEXT:    vcpop.v v8, v12, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i64> @llvm.riscv.vcpopv.mask.nxv4i64(
+    <vscale x 4 x i64> %1,
+    <vscale x 4 x i64> %2,
+    <vscale x 4 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 4 x i64> %a
+}
+
+declare <vscale x 8 x i64> @llvm.riscv.vcpopv.nxv8i64(
+  <vscale x 8 x i64>,
+  <vscale x 8 x i64>,
+  iXLen);
+
+define <vscale x 8 x i64> @intrinsic_vcpopv_vs_nxv8i64(<vscale x 8 x i64> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vcpopv_vs_nxv8i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
+; CHECK-NEXT:    vcpop.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i64> @llvm.riscv.vcpopv.nxv8i64(
+    <vscale x 8 x i64> undef,
+    <vscale x 8 x i64> %0,
+    iXLen %1)
+
+  ret <vscale x 8 x i64> %a
+}
+
+declare <vscale x 8 x i64> @llvm.riscv.vcpopv.mask.nxv8i64(
+  <vscale x 8 x i64>,
+  <vscale x 8 x i64>,
+  <vscale x 8 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 8 x i64> @intrinsic_vcpopv_mask_vs_nxv8i64(<vscale x 8 x i1> %0, <vscale x 8 x i64> %1, <vscale x 8 x i64> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vcpopv_mask_vs_nxv8i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, mu
+; CHECK-NEXT:    vcpop.v v8, v16, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i64> @llvm.riscv.vcpopv.mask.nxv8i64(
+    <vscale x 8 x i64> %1,
+    <vscale x 8 x i64> %2,
+    <vscale x 8 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 8 x i64> %a
+}

llvm/test/CodeGen/RISCV/rvv/vctz.ll

+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: sed 's/iXLen/i32/g' %s | llc -mtriple=riscv32 -mattr=+v,+experimental-zvbb \
+; RUN:   -verify-machineinstrs | FileCheck %s --check-prefixes=CHECK
+; RUN: sed 's/iXLen/i64/g' %s | llc -mtriple=riscv64 -mattr=+v,+experimental-zvbb \
+; RUN:   -verify-machineinstrs | FileCheck %s --check-prefixes=CHECK
+
+declare <vscale x 1 x i8> @llvm.riscv.vctz.nxv1i8(
+  <vscale x 1 x i8>,
+  <vscale x 1 x i8>,
+  iXLen);
+
+define <vscale x 1 x i8> @intrinsic_vctz_vs_nxv1i8(<vscale x 1 x i8> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vctz_vs_nxv1i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, mf8, ta, ma
+; CHECK-NEXT:    vctz.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i8> @llvm.riscv.vctz.nxv1i8(
+    <vscale x 1 x i8> undef,
+    <vscale x 1 x i8> %0,
+    iXLen %1)
+
+  ret <vscale x 1 x i8> %a
+}
+
+declare <vscale x 1 x i8> @llvm.riscv.vctz.mask.nxv1i8(
+  <vscale x 1 x i8>,
+  <vscale x 1 x i8>,
+  <vscale x 1 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 1 x i8> @intrinsic_vctz_mask_vs_nxv1i8(<vscale x 1 x i1> %0, <vscale x 1 x i8> %1, <vscale x 1 x i8> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vctz_mask_vs_nxv1i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, mf8, ta, mu
+; CHECK-NEXT:    vctz.v v8, v9, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i8> @llvm.riscv.vctz.mask.nxv1i8(
+    <vscale x 1 x i8> %1,
+    <vscale x 1 x i8> %2,
+    <vscale x 1 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 1 x i8> %a
+}
+
+declare <vscale x 2 x i8> @llvm.riscv.vctz.nxv2i8(
+  <vscale x 2 x i8>,
+  <vscale x 2 x i8>,
+  iXLen);
+
+define <vscale x 2 x i8> @intrinsic_vctz_vs_nxv2i8(<vscale x 2 x i8> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vctz_vs_nxv2i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, mf4, ta, ma
+; CHECK-NEXT:    vctz.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i8> @llvm.riscv.vctz.nxv2i8(
+    <vscale x 2 x i8> undef,
+    <vscale x 2 x i8> %0,
+    iXLen %1)
+
+  ret <vscale x 2 x i8> %a
+}
+
+declare <vscale x 2 x i8> @llvm.riscv.vctz.mask.nxv2i8(
+  <vscale x 2 x i8>,
+  <vscale x 2 x i8>,
+  <vscale x 2 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 2 x i8> @intrinsic_vctz_mask_vs_nxv2i8(<vscale x 2 x i1> %0, <vscale x 2 x i8> %1, <vscale x 2 x i8> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vctz_mask_vs_nxv2i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, mf4, ta, mu
+; CHECK-NEXT:    vctz.v v8, v9, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i8> @llvm.riscv.vctz.mask.nxv2i8(
+    <vscale x 2 x i8> %1,
+    <vscale x 2 x i8> %2,
+    <vscale x 2 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 2 x i8> %a
+}
+
+declare <vscale x 4 x i8> @llvm.riscv.vctz.nxv4i8(
+  <vscale x 4 x i8>,
+  <vscale x 4 x i8>,
+  iXLen);
+
+define <vscale x 4 x i8> @intrinsic_vctz_vs_nxv4i8(<vscale x 4 x i8> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vctz_vs_nxv4i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, mf2, ta, ma
+; CHECK-NEXT:    vctz.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i8> @llvm.riscv.vctz.nxv4i8(
+    <vscale x 4 x i8> undef,
+    <vscale x 4 x i8> %0,
+    iXLen %1)
+
+  ret <vscale x 4 x i8> %a
+}
+
+declare <vscale x 4 x i8> @llvm.riscv.vctz.mask.nxv4i8(
+  <vscale x 4 x i8>,
+  <vscale x 4 x i8>,
+  <vscale x 4 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 4 x i8> @intrinsic_vctz_mask_vs_nxv4i8(<vscale x 4 x i1> %0, <vscale x 4 x i8> %1, <vscale x 4 x i8> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vctz_mask_vs_nxv4i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, mf2, ta, mu
+; CHECK-NEXT:    vctz.v v8, v9, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i8> @llvm.riscv.vctz.mask.nxv4i8(
+    <vscale x 4 x i8> %1,
+    <vscale x 4 x i8> %2,
+    <vscale x 4 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 4 x i8> %a
+}
+
+declare <vscale x 8 x i8> @llvm.riscv.vctz.nxv8i8(
+  <vscale x 8 x i8>,
+  <vscale x 8 x i8>,
+  iXLen);
+
+define <vscale x 8 x i8> @intrinsic_vctz_vs_nxv8i8(<vscale x 8 x i8> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vctz_vs_nxv8i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, m1, ta, ma
+; CHECK-NEXT:    vctz.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i8> @llvm.riscv.vctz.nxv8i8(
+    <vscale x 8 x i8> undef,
+    <vscale x 8 x i8> %0,
+    iXLen %1)
+
+  ret <vscale x 8 x i8> %a
+}
+
+declare <vscale x 8 x i8> @llvm.riscv.vctz.mask.nxv8i8(
+  <vscale x 8 x i8>,
+  <vscale x 8 x i8>,
+  <vscale x 8 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 8 x i8> @intrinsic_vctz_mask_vs_nxv8i8(<vscale x 8 x i1> %0, <vscale x 8 x i8> %1, <vscale x 8 x i8> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vctz_mask_vs_nxv8i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, m1, ta, mu
+; CHECK-NEXT:    vctz.v v8, v9, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i8> @llvm.riscv.vctz.mask.nxv8i8(
+    <vscale x 8 x i8> %1,
+    <vscale x 8 x i8> %2,
+    <vscale x 8 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 8 x i8> %a
+}
+
+declare <vscale x 16 x i8> @llvm.riscv.vctz.nxv16i8(
+  <vscale x 16 x i8>,
+  <vscale x 16 x i8>,
+  iXLen);
+
+define <vscale x 16 x i8> @intrinsic_vctz_vs_nxv16i8(<vscale x 16 x i8> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vctz_vs_nxv16i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, m2, ta, ma
+; CHECK-NEXT:    vctz.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 16 x i8> @llvm.riscv.vctz.nxv16i8(
+    <vscale x 16 x i8> undef,
+    <vscale x 16 x i8> %0,
+    iXLen %1)
+
+  ret <vscale x 16 x i8> %a
+}
+
+declare <vscale x 16 x i8> @llvm.riscv.vctz.mask.nxv16i8(
+  <vscale x 16 x i8>,
+  <vscale x 16 x i8>,
+  <vscale x 16 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 16 x i8> @intrinsic_vctz_mask_vs_nxv16i8(<vscale x 16 x i1> %0, <vscale x 16 x i8> %1, <vscale x 16 x i8> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vctz_mask_vs_nxv16i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, m2, ta, mu
+; CHECK-NEXT:    vctz.v v8, v10, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 16 x i8> @llvm.riscv.vctz.mask.nxv16i8(
+    <vscale x 16 x i8> %1,
+    <vscale x 16 x i8> %2,
+    <vscale x 16 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 16 x i8> %a
+}
+
+declare <vscale x 32 x i8> @llvm.riscv.vctz.nxv32i8(
+  <vscale x 32 x i8>,
+  <vscale x 32 x i8>,
+  iXLen);
+
+define <vscale x 32 x i8> @intrinsic_vctz_vs_nxv32i8(<vscale x 32 x i8> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vctz_vs_nxv32i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, m4, ta, ma
+; CHECK-NEXT:    vctz.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 32 x i8> @llvm.riscv.vctz.nxv32i8(
+    <vscale x 32 x i8> undef,
+    <vscale x 32 x i8> %0,
+    iXLen %1)
+
+  ret <vscale x 32 x i8> %a
+}
+
+declare <vscale x 32 x i8> @llvm.riscv.vctz.mask.nxv32i8(
+  <vscale x 32 x i8>,
+  <vscale x 32 x i8>,
+  <vscale x 32 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 32 x i8> @intrinsic_vctz_mask_vs_nxv32i8(<vscale x 32 x i1> %0, <vscale x 32 x i8> %1, <vscale x 32 x i8> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vctz_mask_vs_nxv32i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, m4, ta, mu
+; CHECK-NEXT:    vctz.v v8, v12, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 32 x i8> @llvm.riscv.vctz.mask.nxv32i8(
+    <vscale x 32 x i8> %1,
+    <vscale x 32 x i8> %2,
+    <vscale x 32 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 32 x i8> %a
+}
+
+declare <vscale x 64 x i8> @llvm.riscv.vctz.nxv64i8(
+  <vscale x 64 x i8>,
+  <vscale x 64 x i8>,
+  iXLen);
+
+define <vscale x 64 x i8> @intrinsic_vctz_vs_nxv64i8(<vscale x 64 x i8> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vctz_vs_nxv64i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, m8, ta, ma
+; CHECK-NEXT:    vctz.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 64 x i8> @llvm.riscv.vctz.nxv64i8(
+    <vscale x 64 x i8> undef,
+    <vscale x 64 x i8> %0,
+    iXLen %1)
+
+  ret <vscale x 64 x i8> %a
+}
+
+declare <vscale x 64 x i8> @llvm.riscv.vctz.mask.nxv64i8(
+  <vscale x 64 x i8>,
+  <vscale x 64 x i8>,
+  <vscale x 64 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 64 x i8> @intrinsic_vctz_mask_vs_nxv64i8(<vscale x 64 x i1> %0, <vscale x 64 x i8> %1, <vscale x 64 x i8> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vctz_mask_vs_nxv64i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, m8, ta, mu
+; CHECK-NEXT:    vctz.v v8, v16, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 64 x i8> @llvm.riscv.vctz.mask.nxv64i8(
+    <vscale x 64 x i8> %1,
+    <vscale x 64 x i8> %2,
+    <vscale x 64 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 64 x i8> %a
+}
+
+declare <vscale x 1 x i16> @llvm.riscv.vctz.nxv1i16(
+  <vscale x 1 x i16>,
+  <vscale x 1 x i16>,
+  iXLen);
+
+define <vscale x 1 x i16> @intrinsic_vctz_vs_nxv1i16(<vscale x 1 x i16> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vctz_vs_nxv1i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, mf4, ta, ma
+; CHECK-NEXT:    vctz.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i16> @llvm.riscv.vctz.nxv1i16(
+    <vscale x 1 x i16> undef,
+    <vscale x 1 x i16> %0,
+    iXLen %1)
+
+  ret <vscale x 1 x i16> %a
+}
+
+declare <vscale x 1 x i16> @llvm.riscv.vctz.mask.nxv1i16(
+  <vscale x 1 x i16>,
+  <vscale x 1 x i16>,
+  <vscale x 1 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 1 x i16> @intrinsic_vctz_mask_vs_nxv1i16(<vscale x 1 x i1> %0, <vscale x 1 x i16> %1, <vscale x 1 x i16> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vctz_mask_vs_nxv1i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, mf4, ta, mu
+; CHECK-NEXT:    vctz.v v8, v9, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i16> @llvm.riscv.vctz.mask.nxv1i16(
+    <vscale x 1 x i16> %1,
+    <vscale x 1 x i16> %2,
+    <vscale x 1 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 1 x i16> %a
+}
+
+declare <vscale x 2 x i16> @llvm.riscv.vctz.nxv2i16(
+  <vscale x 2 x i16>,
+  <vscale x 2 x i16>,
+  iXLen);
+
+define <vscale x 2 x i16> @intrinsic_vctz_vs_nxv2i16(<vscale x 2 x i16> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vctz_vs_nxv2i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, mf2, ta, ma
+; CHECK-NEXT:    vctz.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i16> @llvm.riscv.vctz.nxv2i16(
+    <vscale x 2 x i16> undef,
+    <vscale x 2 x i16> %0,
+    iXLen %1)
+
+  ret <vscale x 2 x i16> %a
+}
+
+declare <vscale x 2 x i16> @llvm.riscv.vctz.mask.nxv2i16(
+  <vscale x 2 x i16>,
+  <vscale x 2 x i16>,
+  <vscale x 2 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 2 x i16> @intrinsic_vctz_mask_vs_nxv2i16(<vscale x 2 x i1> %0, <vscale x 2 x i16> %1, <vscale x 2 x i16> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vctz_mask_vs_nxv2i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, mf2, ta, mu
+; CHECK-NEXT:    vctz.v v8, v9, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i16> @llvm.riscv.vctz.mask.nxv2i16(
+    <vscale x 2 x i16> %1,
+    <vscale x 2 x i16> %2,
+    <vscale x 2 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 2 x i16> %a
+}
+
+declare <vscale x 4 x i16> @llvm.riscv.vctz.nxv4i16(
+  <vscale x 4 x i16>,
+  <vscale x 4 x i16>,
+  iXLen);
+
+define <vscale x 4 x i16> @intrinsic_vctz_vs_nxv4i16(<vscale x 4 x i16> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vctz_vs_nxv4i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, m1, ta, ma
+; CHECK-NEXT:    vctz.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i16> @llvm.riscv.vctz.nxv4i16(
+    <vscale x 4 x i16> undef,
+    <vscale x 4 x i16> %0,
+    iXLen %1)
+
+  ret <vscale x 4 x i16> %a
+}
+
+declare <vscale x 4 x i16> @llvm.riscv.vctz.mask.nxv4i16(
+  <vscale x 4 x i16>,
+  <vscale x 4 x i16>,
+  <vscale x 4 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 4 x i16> @intrinsic_vctz_mask_vs_nxv4i16(<vscale x 4 x i1> %0, <vscale x 4 x i16> %1, <vscale x 4 x i16> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vctz_mask_vs_nxv4i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, m1, ta, mu
+; CHECK-NEXT:    vctz.v v8, v9, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i16> @llvm.riscv.vctz.mask.nxv4i16(
+    <vscale x 4 x i16> %1,
+    <vscale x 4 x i16> %2,
+    <vscale x 4 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 4 x i16> %a
+}
+
+declare <vscale x 8 x i16> @llvm.riscv.vctz.nxv8i16(
+  <vscale x 8 x i16>,
+  <vscale x 8 x i16>,
+  iXLen);
+
+define <vscale x 8 x i16> @intrinsic_vctz_vs_nxv8i16(<vscale x 8 x i16> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vctz_vs_nxv8i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, m2, ta, ma
+; CHECK-NEXT:    vctz.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i16> @llvm.riscv.vctz.nxv8i16(
+    <vscale x 8 x i16> undef,
+    <vscale x 8 x i16> %0,
+    iXLen %1)
+
+  ret <vscale x 8 x i16> %a
+}
+
+declare <vscale x 8 x i16> @llvm.riscv.vctz.mask.nxv8i16(
+  <vscale x 8 x i16>,
+  <vscale x 8 x i16>,
+  <vscale x 8 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 8 x i16> @intrinsic_vctz_mask_vs_nxv8i16(<vscale x 8 x i1> %0, <vscale x 8 x i16> %1, <vscale x 8 x i16> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vctz_mask_vs_nxv8i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, m2, ta, mu
+; CHECK-NEXT:    vctz.v v8, v10, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i16> @llvm.riscv.vctz.mask.nxv8i16(
+    <vscale x 8 x i16> %1,
+    <vscale x 8 x i16> %2,
+    <vscale x 8 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 8 x i16> %a
+}
+
+declare <vscale x 16 x i16> @llvm.riscv.vctz.nxv16i16(
+  <vscale x 16 x i16>,
+  <vscale x 16 x i16>,
+  iXLen);
+
+define <vscale x 16 x i16> @intrinsic_vctz_vs_nxv16i16(<vscale x 16 x i16> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vctz_vs_nxv16i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, m4, ta, ma
+; CHECK-NEXT:    vctz.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 16 x i16> @llvm.riscv.vctz.nxv16i16(
+    <vscale x 16 x i16> undef,
+    <vscale x 16 x i16> %0,
+    iXLen %1)
+
+  ret <vscale x 16 x i16> %a
+}
+
+declare <vscale x 16 x i16> @llvm.riscv.vctz.mask.nxv16i16(
+  <vscale x 16 x i16>,
+  <vscale x 16 x i16>,
+  <vscale x 16 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 16 x i16> @intrinsic_vctz_mask_vs_nxv16i16(<vscale x 16 x i1> %0, <vscale x 16 x i16> %1, <vscale x 16 x i16> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vctz_mask_vs_nxv16i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, m4, ta, mu
+; CHECK-NEXT:    vctz.v v8, v12, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 16 x i16> @llvm.riscv.vctz.mask.nxv16i16(
+    <vscale x 16 x i16> %1,
+    <vscale x 16 x i16> %2,
+    <vscale x 16 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 16 x i16> %a
+}
+
+declare <vscale x 32 x i16> @llvm.riscv.vctz.nxv32i16(
+  <vscale x 32 x i16>,
+  <vscale x 32 x i16>,
+  iXLen);
+
+define <vscale x 32 x i16> @intrinsic_vctz_vs_nxv32i16(<vscale x 32 x i16> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vctz_vs_nxv32i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, m8, ta, ma
+; CHECK-NEXT:    vctz.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 32 x i16> @llvm.riscv.vctz.nxv32i16(
+    <vscale x 32 x i16> undef,
+    <vscale x 32 x i16> %0,
+    iXLen %1)
+
+  ret <vscale x 32 x i16> %a
+}
+
+declare <vscale x 32 x i16> @llvm.riscv.vctz.mask.nxv32i16(
+  <vscale x 32 x i16>,
+  <vscale x 32 x i16>,
+  <vscale x 32 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 32 x i16> @intrinsic_vctz_mask_vs_nxv32i16(<vscale x 32 x i1> %0, <vscale x 32 x i16> %1, <vscale x 32 x i16> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vctz_mask_vs_nxv32i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, m8, ta, mu
+; CHECK-NEXT:    vctz.v v8, v16, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 32 x i16> @llvm.riscv.vctz.mask.nxv32i16(
+    <vscale x 32 x i16> %1,
+    <vscale x 32 x i16> %2,
+    <vscale x 32 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 32 x i16> %a
+}
+
+declare <vscale x 1 x i32> @llvm.riscv.vctz.nxv1i32(
+  <vscale x 1 x i32>,
+  <vscale x 1 x i32>,
+  iXLen);
+
+define <vscale x 1 x i32> @intrinsic_vctz_vs_nxv1i32(<vscale x 1 x i32> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vctz_vs_nxv1i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, mf2, ta, ma
+; CHECK-NEXT:    vctz.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i32> @llvm.riscv.vctz.nxv1i32(
+    <vscale x 1 x i32> undef,
+    <vscale x 1 x i32> %0,
+    iXLen %1)
+
+  ret <vscale x 1 x i32> %a
+}
+
+declare <vscale x 1 x i32> @llvm.riscv.vctz.mask.nxv1i32(
+  <vscale x 1 x i32>,
+  <vscale x 1 x i32>,
+  <vscale x 1 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 1 x i32> @intrinsic_vctz_mask_vs_nxv1i32(<vscale x 1 x i1> %0, <vscale x 1 x i32> %1, <vscale x 1 x i32> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vctz_mask_vs_nxv1i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, mf2, ta, mu
+; CHECK-NEXT:    vctz.v v8, v9, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i32> @llvm.riscv.vctz.mask.nxv1i32(
+    <vscale x 1 x i32> %1,
+    <vscale x 1 x i32> %2,
+    <vscale x 1 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 1 x i32> %a
+}
+
+declare <vscale x 2 x i32> @llvm.riscv.vctz.nxv2i32(
+  <vscale x 2 x i32>,
+  <vscale x 2 x i32>,
+  iXLen);
+
+define <vscale x 2 x i32> @intrinsic_vctz_vs_nxv2i32(<vscale x 2 x i32> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vctz_vs_nxv2i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m1, ta, ma
+; CHECK-NEXT:    vctz.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i32> @llvm.riscv.vctz.nxv2i32(
+    <vscale x 2 x i32> undef,
+    <vscale x 2 x i32> %0,
+    iXLen %1)
+
+  ret <vscale x 2 x i32> %a
+}
+
+declare <vscale x 2 x i32> @llvm.riscv.vctz.mask.nxv2i32(
+  <vscale x 2 x i32>,
+  <vscale x 2 x i32>,
+  <vscale x 2 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 2 x i32> @intrinsic_vctz_mask_vs_nxv2i32(<vscale x 2 x i1> %0, <vscale x 2 x i32> %1, <vscale x 2 x i32> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vctz_mask_vs_nxv2i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m1, ta, mu
+; CHECK-NEXT:    vctz.v v8, v9, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i32> @llvm.riscv.vctz.mask.nxv2i32(
+    <vscale x 2 x i32> %1,
+    <vscale x 2 x i32> %2,
+    <vscale x 2 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 2 x i32> %a
+}
+
+declare <vscale x 4 x i32> @llvm.riscv.vctz.nxv4i32(
+  <vscale x 4 x i32>,
+  <vscale x 4 x i32>,
+  iXLen);
+
+define <vscale x 4 x i32> @intrinsic_vctz_vs_nxv4i32(<vscale x 4 x i32> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vctz_vs_nxv4i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m2, ta, ma
+; CHECK-NEXT:    vctz.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i32> @llvm.riscv.vctz.nxv4i32(
+    <vscale x 4 x i32> undef,
+    <vscale x 4 x i32> %0,
+    iXLen %1)
+
+  ret <vscale x 4 x i32> %a
+}
+
+declare <vscale x 4 x i32> @llvm.riscv.vctz.mask.nxv4i32(
+  <vscale x 4 x i32>,
+  <vscale x 4 x i32>,
+  <vscale x 4 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 4 x i32> @intrinsic_vctz_mask_vs_nxv4i32(<vscale x 4 x i1> %0, <vscale x 4 x i32> %1, <vscale x 4 x i32> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vctz_mask_vs_nxv4i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m2, ta, mu
+; CHECK-NEXT:    vctz.v v8, v10, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i32> @llvm.riscv.vctz.mask.nxv4i32(
+    <vscale x 4 x i32> %1,
+    <vscale x 4 x i32> %2,
+    <vscale x 4 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 4 x i32> %a
+}
+
+declare <vscale x 8 x i32> @llvm.riscv.vctz.nxv8i32(
+  <vscale x 8 x i32>,
+  <vscale x 8 x i32>,
+  iXLen);
+
+define <vscale x 8 x i32> @intrinsic_vctz_vs_nxv8i32(<vscale x 8 x i32> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vctz_vs_nxv8i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m4, ta, ma
+; CHECK-NEXT:    vctz.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i32> @llvm.riscv.vctz.nxv8i32(
+    <vscale x 8 x i32> undef,
+    <vscale x 8 x i32> %0,
+    iXLen %1)
+
+  ret <vscale x 8 x i32> %a
+}
+
+declare <vscale x 8 x i32> @llvm.riscv.vctz.mask.nxv8i32(
+  <vscale x 8 x i32>,
+  <vscale x 8 x i32>,
+  <vscale x 8 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 8 x i32> @intrinsic_vctz_mask_vs_nxv8i32(<vscale x 8 x i1> %0, <vscale x 8 x i32> %1, <vscale x 8 x i32> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vctz_mask_vs_nxv8i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m4, ta, mu
+; CHECK-NEXT:    vctz.v v8, v12, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i32> @llvm.riscv.vctz.mask.nxv8i32(
+    <vscale x 8 x i32> %1,
+    <vscale x 8 x i32> %2,
+    <vscale x 8 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 8 x i32> %a
+}
+
+declare <vscale x 16 x i32> @llvm.riscv.vctz.nxv16i32(
+  <vscale x 16 x i32>,
+  <vscale x 16 x i32>,
+  iXLen);
+
+define <vscale x 16 x i32> @intrinsic_vctz_vs_nxv16i32(<vscale x 16 x i32> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vctz_vs_nxv16i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m8, ta, ma
+; CHECK-NEXT:    vctz.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 16 x i32> @llvm.riscv.vctz.nxv16i32(
+    <vscale x 16 x i32> undef,
+    <vscale x 16 x i32> %0,
+    iXLen %1)
+
+  ret <vscale x 16 x i32> %a
+}
+
+declare <vscale x 16 x i32> @llvm.riscv.vctz.mask.nxv16i32(
+  <vscale x 16 x i32>,
+  <vscale x 16 x i32>,
+  <vscale x 16 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 16 x i32> @intrinsic_vctz_mask_vs_nxv16i32(<vscale x 16 x i1> %0, <vscale x 16 x i32> %1, <vscale x 16 x i32> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vctz_mask_vs_nxv16i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m8, ta, mu
+; CHECK-NEXT:    vctz.v v8, v16, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 16 x i32> @llvm.riscv.vctz.mask.nxv16i32(
+    <vscale x 16 x i32> %1,
+    <vscale x 16 x i32> %2,
+    <vscale x 16 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 16 x i32> %a
+}
+
+declare <vscale x 1 x i64> @llvm.riscv.vctz.nxv1i64(
+  <vscale x 1 x i64>,
+  <vscale x 1 x i64>,
+  iXLen);
+
+define <vscale x 1 x i64> @intrinsic_vctz_vs_nxv1i64(<vscale x 1 x i64> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vctz_vs_nxv1i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e64, m1, ta, ma
+; CHECK-NEXT:    vctz.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i64> @llvm.riscv.vctz.nxv1i64(
+    <vscale x 1 x i64> undef,
+    <vscale x 1 x i64> %0,
+    iXLen %1)
+
+  ret <vscale x 1 x i64> %a
+}
+
+declare <vscale x 1 x i64> @llvm.riscv.vctz.mask.nxv1i64(
+  <vscale x 1 x i64>,
+  <vscale x 1 x i64>,
+  <vscale x 1 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 1 x i64> @intrinsic_vctz_mask_vs_nxv1i64(<vscale x 1 x i1> %0, <vscale x 1 x i64> %1, <vscale x 1 x i64> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vctz_mask_vs_nxv1i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e64, m1, ta, mu
+; CHECK-NEXT:    vctz.v v8, v9, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i64> @llvm.riscv.vctz.mask.nxv1i64(
+    <vscale x 1 x i64> %1,
+    <vscale x 1 x i64> %2,
+    <vscale x 1 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 1 x i64> %a
+}
+
+declare <vscale x 2 x i64> @llvm.riscv.vctz.nxv2i64(
+  <vscale x 2 x i64>,
+  <vscale x 2 x i64>,
+  iXLen);
+
+define <vscale x 2 x i64> @intrinsic_vctz_vs_nxv2i64(<vscale x 2 x i64> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vctz_vs_nxv2i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e64, m2, ta, ma
+; CHECK-NEXT:    vctz.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i64> @llvm.riscv.vctz.nxv2i64(
+    <vscale x 2 x i64> undef,
+    <vscale x 2 x i64> %0,
+    iXLen %1)
+
+  ret <vscale x 2 x i64> %a
+}
+
+declare <vscale x 2 x i64> @llvm.riscv.vctz.mask.nxv2i64(
+  <vscale x 2 x i64>,
+  <vscale x 2 x i64>,
+  <vscale x 2 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 2 x i64> @intrinsic_vctz_mask_vs_nxv2i64(<vscale x 2 x i1> %0, <vscale x 2 x i64> %1, <vscale x 2 x i64> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vctz_mask_vs_nxv2i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e64, m2, ta, mu
+; CHECK-NEXT:    vctz.v v8, v10, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i64> @llvm.riscv.vctz.mask.nxv2i64(
+    <vscale x 2 x i64> %1,
+    <vscale x 2 x i64> %2,
+    <vscale x 2 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 2 x i64> %a
+}
+
+declare <vscale x 4 x i64> @llvm.riscv.vctz.nxv4i64(
+  <vscale x 4 x i64>,
+  <vscale x 4 x i64>,
+  iXLen);
+
+define <vscale x 4 x i64> @intrinsic_vctz_vs_nxv4i64(<vscale x 4 x i64> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vctz_vs_nxv4i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e64, m4, ta, ma
+; CHECK-NEXT:    vctz.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i64> @llvm.riscv.vctz.nxv4i64(
+    <vscale x 4 x i64> undef,
+    <vscale x 4 x i64> %0,
+    iXLen %1)
+
+  ret <vscale x 4 x i64> %a
+}
+
+declare <vscale x 4 x i64> @llvm.riscv.vctz.mask.nxv4i64(
+  <vscale x 4 x i64>,
+  <vscale x 4 x i64>,
+  <vscale x 4 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 4 x i64> @intrinsic_vctz_mask_vs_nxv4i64(<vscale x 4 x i1> %0, <vscale x 4 x i64> %1, <vscale x 4 x i64> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vctz_mask_vs_nxv4i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e64, m4, ta, mu
+; CHECK-NEXT:    vctz.v v8, v12, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i64> @llvm.riscv.vctz.mask.nxv4i64(
+    <vscale x 4 x i64> %1,
+    <vscale x 4 x i64> %2,
+    <vscale x 4 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 4 x i64> %a
+}
+
+declare <vscale x 8 x i64> @llvm.riscv.vctz.nxv8i64(
+  <vscale x 8 x i64>,
+  <vscale x 8 x i64>,
+  iXLen);
+
+define <vscale x 8 x i64> @intrinsic_vctz_vs_nxv8i64(<vscale x 8 x i64> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vctz_vs_nxv8i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
+; CHECK-NEXT:    vctz.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i64> @llvm.riscv.vctz.nxv8i64(
+    <vscale x 8 x i64> undef,
+    <vscale x 8 x i64> %0,
+    iXLen %1)
+
+  ret <vscale x 8 x i64> %a
+}
+
+declare <vscale x 8 x i64> @llvm.riscv.vctz.mask.nxv8i64(
+  <vscale x 8 x i64>,
+  <vscale x 8 x i64>,
+  <vscale x 8 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 8 x i64> @intrinsic_vctz_mask_vs_nxv8i64(<vscale x 8 x i1> %0, <vscale x 8 x i64> %1, <vscale x 8 x i64> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vctz_mask_vs_nxv8i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, mu
+; CHECK-NEXT:    vctz.v v8, v16, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i64> @llvm.riscv.vctz.mask.nxv8i64(
+    <vscale x 8 x i64> %1,
+    <vscale x 8 x i64> %2,
+    <vscale x 8 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 8 x i64> %a
+}

llvm/test/CodeGen/RISCV/rvv/vghsh.ll

+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: sed 's/iXLen/i32/g' %s | llc -mtriple=riscv32 -mattr=+v,+experimental-zvkg \
+; RUN:   -verify-machineinstrs | FileCheck %s --check-prefixes=CHECK
+; RUN: sed 's/iXLen/i64/g' %s | llc -mtriple=riscv64 -mattr=+v,+experimental-zvkg \
+; RUN:   -verify-machineinstrs | FileCheck %s --check-prefixes=CHECK
+
+declare <vscale x 1 x i32> @llvm.riscv.vghsh.nxv1i32.nxv1i32(
+  <vscale x 1 x i32>,
+  <vscale x 1 x i32>,
+  <vscale x 1 x i32>,
+  iXLen,
+  iXLen)
+
+define <vscale x 1 x i32> @intrinsic_vghsh_vv_nxv1i32_nxv1i32(<vscale x 1 x i32> %0, <vscale x 1 x i32> %1, <vscale x 1 x i32> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vghsh_vv_nxv1i32_nxv1i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, mf2, tu, ma
+; CHECK-NEXT:    vghsh.vv v8, v9, v10
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i32> @llvm.riscv.vghsh.nxv1i32.nxv1i32(
+    <vscale x 1 x i32> %0,
+    <vscale x 1 x i32> %1,
+    <vscale x 1 x i32> %2,
+    iXLen %3,
+    iXLen 2)
+
+  ret <vscale x 1 x i32> %a
+}
+
+declare <vscale x 2 x i32> @llvm.riscv.vghsh.nxv2i32.nxv2i32(
+  <vscale x 2 x i32>,
+  <vscale x 2 x i32>,
+  <vscale x 2 x i32>,
+  iXLen,
+  iXLen)
+
+define <vscale x 2 x i32> @intrinsic_vghsh_vv_nxv2i32_nxv2i32(<vscale x 2 x i32> %0, <vscale x 2 x i32> %1, <vscale x 2 x i32> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vghsh_vv_nxv2i32_nxv2i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m1, tu, ma
+; CHECK-NEXT:    vghsh.vv v8, v9, v10
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i32> @llvm.riscv.vghsh.nxv2i32.nxv2i32(
+    <vscale x 2 x i32> %0,
+    <vscale x 2 x i32> %1,
+    <vscale x 2 x i32> %2,
+    iXLen %3,
+    iXLen 2)
+
+  ret <vscale x 2 x i32> %a
+}
+
+declare <vscale x 4 x i32> @llvm.riscv.vghsh.nxv4i32.nxv4i32(
+  <vscale x 4 x i32>,
+  <vscale x 4 x i32>,
+  <vscale x 4 x i32>,
+  iXLen,
+  iXLen)
+
+define <vscale x 4 x i32> @intrinsic_vghsh_vv_nxv4i32_nxv4i32(<vscale x 4 x i32> %0, <vscale x 4 x i32> %1, <vscale x 4 x i32> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vghsh_vv_nxv4i32_nxv4i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m2, tu, ma
+; CHECK-NEXT:    vghsh.vv v8, v10, v12
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i32> @llvm.riscv.vghsh.nxv4i32.nxv4i32(
+    <vscale x 4 x i32> %0,
+    <vscale x 4 x i32> %1,
+    <vscale x 4 x i32> %2,
+    iXLen %3,
+    iXLen 2)
+
+  ret <vscale x 4 x i32> %a
+}
+
+declare <vscale x 8 x i32> @llvm.riscv.vghsh.nxv8i32.nxv8i32(
+  <vscale x 8 x i32>,
+  <vscale x 8 x i32>,
+  <vscale x 8 x i32>,
+  iXLen,
+  iXLen)
+
+define <vscale x 8 x i32> @intrinsic_vghsh_vv_nxv8i32_nxv8i32(<vscale x 8 x i32> %0, <vscale x 8 x i32> %1, <vscale x 8 x i32> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vghsh_vv_nxv8i32_nxv8i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m4, tu, ma
+; CHECK-NEXT:    vghsh.vv v8, v12, v16
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i32> @llvm.riscv.vghsh.nxv8i32.nxv8i32(
+    <vscale x 8 x i32> %0,
+    <vscale x 8 x i32> %1,
+    <vscale x 8 x i32> %2,
+    iXLen %3,
+    iXLen 2)
+
+  ret <vscale x 8 x i32> %a
+}
+
+declare <vscale x 16 x i32> @llvm.riscv.vghsh.nxv16i32.nxv16i32(
+  <vscale x 16 x i32>,
+  <vscale x 16 x i32>,
+  <vscale x 16 x i32>,
+  iXLen,
+  iXLen)
+
+define <vscale x 16 x i32> @intrinsic_vghsh_vv_nxv16i32_nxv16i32(<vscale x 16 x i32> %0, <vscale x 16 x i32> %1, <vscale x 16 x i32> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vghsh_vv_nxv16i32_nxv16i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vl8re32.v v24, (a0)
+; CHECK-NEXT:    vsetvli zero, a1, e32, m8, tu, ma
+; CHECK-NEXT:    vghsh.vv v8, v16, v24
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 16 x i32> @llvm.riscv.vghsh.nxv16i32.nxv16i32(
+    <vscale x 16 x i32> %0,
+    <vscale x 16 x i32> %1,
+    <vscale x 16 x i32> %2,
+    iXLen %3,
+    iXLen 2)
+
+  ret <vscale x 16 x i32> %a
+}

llvm/test/CodeGen/RISCV/rvv/vgmul.ll

+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: sed 's/iXLen/i32/g' %s | llc -mtriple=riscv32 -mattr=+v,+experimental-zvkg \
+; RUN:   -verify-machineinstrs | FileCheck %s --check-prefixes=CHECK
+; RUN: sed 's/iXLen/i64/g' %s | llc -mtriple=riscv64 -mattr=+v,+experimental-zvkg \
+; RUN:   -verify-machineinstrs | FileCheck %s --check-prefixes=CHECK
+
+declare <vscale x 1 x i32> @llvm.riscv.vgmul.nxv1i32.nxv1i32(
+  <vscale x 1 x i32>,
+  <vscale x 1 x i32>,
+  <vscale x 1 x i32>,
+  iXLen,
+  iXLen)
+
+define <vscale x 1 x i32> @intrinsic_vgmul_vv_nxv1i32_nxv1i32(<vscale x 1 x i32> %0, <vscale x 1 x i32> %1, <vscale x 1 x i32> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vgmul_vv_nxv1i32_nxv1i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, mf2, tu, ma
+; CHECK-NEXT:    vgmul.vv v8, v9
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i32> @llvm.riscv.vgmul.nxv1i32.nxv1i32(
+    <vscale x 1 x i32> %0,
+    <vscale x 1 x i32> %1,
+    <vscale x 1 x i32> %2,
+    iXLen %3,
+    iXLen 2)
+
+  ret <vscale x 1 x i32> %a
+}
+
+declare <vscale x 2 x i32> @llvm.riscv.vgmul.nxv2i32.nxv2i32(
+  <vscale x 2 x i32>,
+  <vscale x 2 x i32>,
+  <vscale x 2 x i32>,
+  iXLen,
+  iXLen)
+
+define <vscale x 2 x i32> @intrinsic_vgmul_vv_nxv2i32_nxv2i32(<vscale x 2 x i32> %0, <vscale x 2 x i32> %1, <vscale x 2 x i32> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vgmul_vv_nxv2i32_nxv2i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m1, tu, ma
+; CHECK-NEXT:    vgmul.vv v8, v9
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i32> @llvm.riscv.vgmul.nxv2i32.nxv2i32(
+    <vscale x 2 x i32> %0,
+    <vscale x 2 x i32> %1,
+    <vscale x 2 x i32> %2,
+    iXLen %3,
+    iXLen 2)
+
+  ret <vscale x 2 x i32> %a
+}
+
+declare <vscale x 4 x i32> @llvm.riscv.vgmul.nxv4i32.nxv4i32(
+  <vscale x 4 x i32>,
+  <vscale x 4 x i32>,
+  <vscale x 4 x i32>,
+  iXLen,
+  iXLen)
+
+define <vscale x 4 x i32> @intrinsic_vgmul_vv_nxv4i32_nxv4i32(<vscale x 4 x i32> %0, <vscale x 4 x i32> %1, <vscale x 4 x i32> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vgmul_vv_nxv4i32_nxv4i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m2, tu, ma
+; CHECK-NEXT:    vgmul.vv v8, v10
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i32> @llvm.riscv.vgmul.nxv4i32.nxv4i32(
+    <vscale x 4 x i32> %0,
+    <vscale x 4 x i32> %1,
+    <vscale x 4 x i32> %2,
+    iXLen %3,
+    iXLen 2)
+
+  ret <vscale x 4 x i32> %a
+}
+
+declare <vscale x 8 x i32> @llvm.riscv.vgmul.nxv8i32.nxv8i32(
+  <vscale x 8 x i32>,
+  <vscale x 8 x i32>,
+  <vscale x 8 x i32>,
+  iXLen,
+  iXLen)
+
+define <vscale x 8 x i32> @intrinsic_vgmul_vv_nxv8i32_nxv8i32(<vscale x 8 x i32> %0, <vscale x 8 x i32> %1, <vscale x 8 x i32> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vgmul_vv_nxv8i32_nxv8i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m4, tu, ma
+; CHECK-NEXT:    vgmul.vv v8, v12
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i32> @llvm.riscv.vgmul.nxv8i32.nxv8i32(
+    <vscale x 8 x i32> %0,
+    <vscale x 8 x i32> %1,
+    <vscale x 8 x i32> %2,
+    iXLen %3,
+    iXLen 2)
+
+  ret <vscale x 8 x i32> %a
+}
+
+declare <vscale x 16 x i32> @llvm.riscv.vgmul.nxv16i32.nxv16i32(
+  <vscale x 16 x i32>,
+  <vscale x 16 x i32>,
+  <vscale x 16 x i32>,
+  iXLen,
+  iXLen)
+
+define <vscale x 16 x i32> @intrinsic_vgmul_vv_nxv16i32_nxv16i32(<vscale x 16 x i32> %0, <vscale x 16 x i32> %1, <vscale x 16 x i32> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vgmul_vv_nxv16i32_nxv16i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vl8re32.v v24, (a0)
+; CHECK-NEXT:    vsetvli zero, a1, e32, m8, tu, ma
+; CHECK-NEXT:    vgmul.vv v8, v16
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 16 x i32> @llvm.riscv.vgmul.nxv16i32.nxv16i32(
+    <vscale x 16 x i32> %0,
+    <vscale x 16 x i32> %1,
+    <vscale x 16 x i32> %2,
+    iXLen %3,
+    iXLen 2)
+
+  ret <vscale x 16 x i32> %a
+}

llvm/test/CodeGen/RISCV/rvv/vrev8.ll

+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: sed 's/iXLen/i32/g' %s | llc -mtriple=riscv32 -mattr=+v,+experimental-zvbb \
+; RUN:   -verify-machineinstrs | FileCheck %s --check-prefixes=CHECK
+; RUN: sed 's/iXLen/i64/g' %s | llc -mtriple=riscv64 -mattr=+v,+experimental-zvbb \
+; RUN:   -verify-machineinstrs | FileCheck %s --check-prefixes=CHECK
+
+declare <vscale x 1 x i8> @llvm.riscv.vrev8.nxv1i8(
+  <vscale x 1 x i8>,
+  <vscale x 1 x i8>,
+  iXLen);
+
+define <vscale x 1 x i8> @intrinsic_vrev8_vs_nxv1i8(<vscale x 1 x i8> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vrev8_vs_nxv1i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, mf8, ta, ma
+; CHECK-NEXT:    vrev8.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i8> @llvm.riscv.vrev8.nxv1i8(
+    <vscale x 1 x i8> undef,
+    <vscale x 1 x i8> %0,
+    iXLen %1)
+
+  ret <vscale x 1 x i8> %a
+}
+
+declare <vscale x 1 x i8> @llvm.riscv.vrev8.mask.nxv1i8(
+  <vscale x 1 x i8>,
+  <vscale x 1 x i8>,
+  <vscale x 1 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 1 x i8> @intrinsic_vrev8_mask_vs_nxv1i8(<vscale x 1 x i1> %0, <vscale x 1 x i8> %1, <vscale x 1 x i8> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vrev8_mask_vs_nxv1i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, mf8, ta, mu
+; CHECK-NEXT:    vrev8.v v8, v9, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i8> @llvm.riscv.vrev8.mask.nxv1i8(
+    <vscale x 1 x i8> %1,
+    <vscale x 1 x i8> %2,
+    <vscale x 1 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 1 x i8> %a
+}
+
+declare <vscale x 2 x i8> @llvm.riscv.vrev8.nxv2i8(
+  <vscale x 2 x i8>,
+  <vscale x 2 x i8>,
+  iXLen);
+
+define <vscale x 2 x i8> @intrinsic_vrev8_vs_nxv2i8(<vscale x 2 x i8> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vrev8_vs_nxv2i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, mf4, ta, ma
+; CHECK-NEXT:    vrev8.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i8> @llvm.riscv.vrev8.nxv2i8(
+    <vscale x 2 x i8> undef,
+    <vscale x 2 x i8> %0,
+    iXLen %1)
+
+  ret <vscale x 2 x i8> %a
+}
+
+declare <vscale x 2 x i8> @llvm.riscv.vrev8.mask.nxv2i8(
+  <vscale x 2 x i8>,
+  <vscale x 2 x i8>,
+  <vscale x 2 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 2 x i8> @intrinsic_vrev8_mask_vs_nxv2i8(<vscale x 2 x i1> %0, <vscale x 2 x i8> %1, <vscale x 2 x i8> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vrev8_mask_vs_nxv2i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, mf4, ta, mu
+; CHECK-NEXT:    vrev8.v v8, v9, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i8> @llvm.riscv.vrev8.mask.nxv2i8(
+    <vscale x 2 x i8> %1,
+    <vscale x 2 x i8> %2,
+    <vscale x 2 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 2 x i8> %a
+}
+
+declare <vscale x 4 x i8> @llvm.riscv.vrev8.nxv4i8(
+  <vscale x 4 x i8>,
+  <vscale x 4 x i8>,
+  iXLen);
+
+define <vscale x 4 x i8> @intrinsic_vrev8_vs_nxv4i8(<vscale x 4 x i8> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vrev8_vs_nxv4i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, mf2, ta, ma
+; CHECK-NEXT:    vrev8.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i8> @llvm.riscv.vrev8.nxv4i8(
+    <vscale x 4 x i8> undef,
+    <vscale x 4 x i8> %0,
+    iXLen %1)
+
+  ret <vscale x 4 x i8> %a
+}
+
+declare <vscale x 4 x i8> @llvm.riscv.vrev8.mask.nxv4i8(
+  <vscale x 4 x i8>,
+  <vscale x 4 x i8>,
+  <vscale x 4 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 4 x i8> @intrinsic_vrev8_mask_vs_nxv4i8(<vscale x 4 x i1> %0, <vscale x 4 x i8> %1, <vscale x 4 x i8> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vrev8_mask_vs_nxv4i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, mf2, ta, mu
+; CHECK-NEXT:    vrev8.v v8, v9, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i8> @llvm.riscv.vrev8.mask.nxv4i8(
+    <vscale x 4 x i8> %1,
+    <vscale x 4 x i8> %2,
+    <vscale x 4 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 4 x i8> %a
+}
+
+declare <vscale x 8 x i8> @llvm.riscv.vrev8.nxv8i8(
+  <vscale x 8 x i8>,
+  <vscale x 8 x i8>,
+  iXLen);
+
+define <vscale x 8 x i8> @intrinsic_vrev8_vs_nxv8i8(<vscale x 8 x i8> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vrev8_vs_nxv8i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, m1, ta, ma
+; CHECK-NEXT:    vrev8.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i8> @llvm.riscv.vrev8.nxv8i8(
+    <vscale x 8 x i8> undef,
+    <vscale x 8 x i8> %0,
+    iXLen %1)
+
+  ret <vscale x 8 x i8> %a
+}
+
+declare <vscale x 8 x i8> @llvm.riscv.vrev8.mask.nxv8i8(
+  <vscale x 8 x i8>,
+  <vscale x 8 x i8>,
+  <vscale x 8 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 8 x i8> @intrinsic_vrev8_mask_vs_nxv8i8(<vscale x 8 x i1> %0, <vscale x 8 x i8> %1, <vscale x 8 x i8> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vrev8_mask_vs_nxv8i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, m1, ta, mu
+; CHECK-NEXT:    vrev8.v v8, v9, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i8> @llvm.riscv.vrev8.mask.nxv8i8(
+    <vscale x 8 x i8> %1,
+    <vscale x 8 x i8> %2,
+    <vscale x 8 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 8 x i8> %a
+}
+
+declare <vscale x 16 x i8> @llvm.riscv.vrev8.nxv16i8(
+  <vscale x 16 x i8>,
+  <vscale x 16 x i8>,
+  iXLen);
+
+define <vscale x 16 x i8> @intrinsic_vrev8_vs_nxv16i8(<vscale x 16 x i8> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vrev8_vs_nxv16i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, m2, ta, ma
+; CHECK-NEXT:    vrev8.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 16 x i8> @llvm.riscv.vrev8.nxv16i8(
+    <vscale x 16 x i8> undef,
+    <vscale x 16 x i8> %0,
+    iXLen %1)
+
+  ret <vscale x 16 x i8> %a
+}
+
+declare <vscale x 16 x i8> @llvm.riscv.vrev8.mask.nxv16i8(
+  <vscale x 16 x i8>,
+  <vscale x 16 x i8>,
+  <vscale x 16 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 16 x i8> @intrinsic_vrev8_mask_vs_nxv16i8(<vscale x 16 x i1> %0, <vscale x 16 x i8> %1, <vscale x 16 x i8> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vrev8_mask_vs_nxv16i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, m2, ta, mu
+; CHECK-NEXT:    vrev8.v v8, v10, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 16 x i8> @llvm.riscv.vrev8.mask.nxv16i8(
+    <vscale x 16 x i8> %1,
+    <vscale x 16 x i8> %2,
+    <vscale x 16 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 16 x i8> %a
+}
+
+declare <vscale x 32 x i8> @llvm.riscv.vrev8.nxv32i8(
+  <vscale x 32 x i8>,
+  <vscale x 32 x i8>,
+  iXLen);
+
+define <vscale x 32 x i8> @intrinsic_vrev8_vs_nxv32i8(<vscale x 32 x i8> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vrev8_vs_nxv32i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, m4, ta, ma
+; CHECK-NEXT:    vrev8.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 32 x i8> @llvm.riscv.vrev8.nxv32i8(
+    <vscale x 32 x i8> undef,
+    <vscale x 32 x i8> %0,
+    iXLen %1)
+
+  ret <vscale x 32 x i8> %a
+}
+
+declare <vscale x 32 x i8> @llvm.riscv.vrev8.mask.nxv32i8(
+  <vscale x 32 x i8>,
+  <vscale x 32 x i8>,
+  <vscale x 32 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 32 x i8> @intrinsic_vrev8_mask_vs_nxv32i8(<vscale x 32 x i1> %0, <vscale x 32 x i8> %1, <vscale x 32 x i8> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vrev8_mask_vs_nxv32i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, m4, ta, mu
+; CHECK-NEXT:    vrev8.v v8, v12, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 32 x i8> @llvm.riscv.vrev8.mask.nxv32i8(
+    <vscale x 32 x i8> %1,
+    <vscale x 32 x i8> %2,
+    <vscale x 32 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 32 x i8> %a
+}
+
+declare <vscale x 64 x i8> @llvm.riscv.vrev8.nxv64i8(
+  <vscale x 64 x i8>,
+  <vscale x 64 x i8>,
+  iXLen);
+
+define <vscale x 64 x i8> @intrinsic_vrev8_vs_nxv64i8(<vscale x 64 x i8> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vrev8_vs_nxv64i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, m8, ta, ma
+; CHECK-NEXT:    vrev8.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 64 x i8> @llvm.riscv.vrev8.nxv64i8(
+    <vscale x 64 x i8> undef,
+    <vscale x 64 x i8> %0,
+    iXLen %1)
+
+  ret <vscale x 64 x i8> %a
+}
+
+declare <vscale x 64 x i8> @llvm.riscv.vrev8.mask.nxv64i8(
+  <vscale x 64 x i8>,
+  <vscale x 64 x i8>,
+  <vscale x 64 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 64 x i8> @intrinsic_vrev8_mask_vs_nxv64i8(<vscale x 64 x i1> %0, <vscale x 64 x i8> %1, <vscale x 64 x i8> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vrev8_mask_vs_nxv64i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, m8, ta, mu
+; CHECK-NEXT:    vrev8.v v8, v16, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 64 x i8> @llvm.riscv.vrev8.mask.nxv64i8(
+    <vscale x 64 x i8> %1,
+    <vscale x 64 x i8> %2,
+    <vscale x 64 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 64 x i8> %a
+}
+
+declare <vscale x 1 x i16> @llvm.riscv.vrev8.nxv1i16(
+  <vscale x 1 x i16>,
+  <vscale x 1 x i16>,
+  iXLen);
+
+define <vscale x 1 x i16> @intrinsic_vrev8_vs_nxv1i16(<vscale x 1 x i16> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vrev8_vs_nxv1i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, mf4, ta, ma
+; CHECK-NEXT:    vrev8.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i16> @llvm.riscv.vrev8.nxv1i16(
+    <vscale x 1 x i16> undef,
+    <vscale x 1 x i16> %0,
+    iXLen %1)
+
+  ret <vscale x 1 x i16> %a
+}
+
+declare <vscale x 1 x i16> @llvm.riscv.vrev8.mask.nxv1i16(
+  <vscale x 1 x i16>,
+  <vscale x 1 x i16>,
+  <vscale x 1 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 1 x i16> @intrinsic_vrev8_mask_vs_nxv1i16(<vscale x 1 x i1> %0, <vscale x 1 x i16> %1, <vscale x 1 x i16> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vrev8_mask_vs_nxv1i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, mf4, ta, mu
+; CHECK-NEXT:    vrev8.v v8, v9, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i16> @llvm.riscv.vrev8.mask.nxv1i16(
+    <vscale x 1 x i16> %1,
+    <vscale x 1 x i16> %2,
+    <vscale x 1 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 1 x i16> %a
+}
+
+declare <vscale x 2 x i16> @llvm.riscv.vrev8.nxv2i16(
+  <vscale x 2 x i16>,
+  <vscale x 2 x i16>,
+  iXLen);
+
+define <vscale x 2 x i16> @intrinsic_vrev8_vs_nxv2i16(<vscale x 2 x i16> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vrev8_vs_nxv2i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, mf2, ta, ma
+; CHECK-NEXT:    vrev8.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i16> @llvm.riscv.vrev8.nxv2i16(
+    <vscale x 2 x i16> undef,
+    <vscale x 2 x i16> %0,
+    iXLen %1)
+
+  ret <vscale x 2 x i16> %a
+}
+
+declare <vscale x 2 x i16> @llvm.riscv.vrev8.mask.nxv2i16(
+  <vscale x 2 x i16>,
+  <vscale x 2 x i16>,
+  <vscale x 2 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 2 x i16> @intrinsic_vrev8_mask_vs_nxv2i16(<vscale x 2 x i1> %0, <vscale x 2 x i16> %1, <vscale x 2 x i16> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vrev8_mask_vs_nxv2i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, mf2, ta, mu
+; CHECK-NEXT:    vrev8.v v8, v9, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i16> @llvm.riscv.vrev8.mask.nxv2i16(
+    <vscale x 2 x i16> %1,
+    <vscale x 2 x i16> %2,
+    <vscale x 2 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 2 x i16> %a
+}
+
+declare <vscale x 4 x i16> @llvm.riscv.vrev8.nxv4i16(
+  <vscale x 4 x i16>,
+  <vscale x 4 x i16>,
+  iXLen);
+
+define <vscale x 4 x i16> @intrinsic_vrev8_vs_nxv4i16(<vscale x 4 x i16> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vrev8_vs_nxv4i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, m1, ta, ma
+; CHECK-NEXT:    vrev8.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i16> @llvm.riscv.vrev8.nxv4i16(
+    <vscale x 4 x i16> undef,
+    <vscale x 4 x i16> %0,
+    iXLen %1)
+
+  ret <vscale x 4 x i16> %a
+}
+
+declare <vscale x 4 x i16> @llvm.riscv.vrev8.mask.nxv4i16(
+  <vscale x 4 x i16>,
+  <vscale x 4 x i16>,
+  <vscale x 4 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 4 x i16> @intrinsic_vrev8_mask_vs_nxv4i16(<vscale x 4 x i1> %0, <vscale x 4 x i16> %1, <vscale x 4 x i16> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vrev8_mask_vs_nxv4i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, m1, ta, mu
+; CHECK-NEXT:    vrev8.v v8, v9, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i16> @llvm.riscv.vrev8.mask.nxv4i16(
+    <vscale x 4 x i16> %1,
+    <vscale x 4 x i16> %2,
+    <vscale x 4 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 4 x i16> %a
+}
+
+declare <vscale x 8 x i16> @llvm.riscv.vrev8.nxv8i16(
+  <vscale x 8 x i16>,
+  <vscale x 8 x i16>,
+  iXLen);
+
+define <vscale x 8 x i16> @intrinsic_vrev8_vs_nxv8i16(<vscale x 8 x i16> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vrev8_vs_nxv8i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, m2, ta, ma
+; CHECK-NEXT:    vrev8.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i16> @llvm.riscv.vrev8.nxv8i16(
+    <vscale x 8 x i16> undef,
+    <vscale x 8 x i16> %0,
+    iXLen %1)
+
+  ret <vscale x 8 x i16> %a
+}
+
+declare <vscale x 8 x i16> @llvm.riscv.vrev8.mask.nxv8i16(
+  <vscale x 8 x i16>,
+  <vscale x 8 x i16>,
+  <vscale x 8 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 8 x i16> @intrinsic_vrev8_mask_vs_nxv8i16(<vscale x 8 x i1> %0, <vscale x 8 x i16> %1, <vscale x 8 x i16> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vrev8_mask_vs_nxv8i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, m2, ta, mu
+; CHECK-NEXT:    vrev8.v v8, v10, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i16> @llvm.riscv.vrev8.mask.nxv8i16(
+    <vscale x 8 x i16> %1,
+    <vscale x 8 x i16> %2,
+    <vscale x 8 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 8 x i16> %a
+}
+
+declare <vscale x 16 x i16> @llvm.riscv.vrev8.nxv16i16(
+  <vscale x 16 x i16>,
+  <vscale x 16 x i16>,
+  iXLen);
+
+define <vscale x 16 x i16> @intrinsic_vrev8_vs_nxv16i16(<vscale x 16 x i16> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vrev8_vs_nxv16i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, m4, ta, ma
+; CHECK-NEXT:    vrev8.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 16 x i16> @llvm.riscv.vrev8.nxv16i16(
+    <vscale x 16 x i16> undef,
+    <vscale x 16 x i16> %0,
+    iXLen %1)
+
+  ret <vscale x 16 x i16> %a
+}
+
+declare <vscale x 16 x i16> @llvm.riscv.vrev8.mask.nxv16i16(
+  <vscale x 16 x i16>,
+  <vscale x 16 x i16>,
+  <vscale x 16 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 16 x i16> @intrinsic_vrev8_mask_vs_nxv16i16(<vscale x 16 x i1> %0, <vscale x 16 x i16> %1, <vscale x 16 x i16> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vrev8_mask_vs_nxv16i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, m4, ta, mu
+; CHECK-NEXT:    vrev8.v v8, v12, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 16 x i16> @llvm.riscv.vrev8.mask.nxv16i16(
+    <vscale x 16 x i16> %1,
+    <vscale x 16 x i16> %2,
+    <vscale x 16 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 16 x i16> %a
+}
+
+declare <vscale x 32 x i16> @llvm.riscv.vrev8.nxv32i16(
+  <vscale x 32 x i16>,
+  <vscale x 32 x i16>,
+  iXLen);
+
+define <vscale x 32 x i16> @intrinsic_vrev8_vs_nxv32i16(<vscale x 32 x i16> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vrev8_vs_nxv32i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, m8, ta, ma
+; CHECK-NEXT:    vrev8.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 32 x i16> @llvm.riscv.vrev8.nxv32i16(
+    <vscale x 32 x i16> undef,
+    <vscale x 32 x i16> %0,
+    iXLen %1)
+
+  ret <vscale x 32 x i16> %a
+}
+
+declare <vscale x 32 x i16> @llvm.riscv.vrev8.mask.nxv32i16(
+  <vscale x 32 x i16>,
+  <vscale x 32 x i16>,
+  <vscale x 32 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 32 x i16> @intrinsic_vrev8_mask_vs_nxv32i16(<vscale x 32 x i1> %0, <vscale x 32 x i16> %1, <vscale x 32 x i16> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vrev8_mask_vs_nxv32i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, m8, ta, mu
+; CHECK-NEXT:    vrev8.v v8, v16, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 32 x i16> @llvm.riscv.vrev8.mask.nxv32i16(
+    <vscale x 32 x i16> %1,
+    <vscale x 32 x i16> %2,
+    <vscale x 32 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 32 x i16> %a
+}
+
+declare <vscale x 1 x i32> @llvm.riscv.vrev8.nxv1i32(
+  <vscale x 1 x i32>,
+  <vscale x 1 x i32>,
+  iXLen);
+
+define <vscale x 1 x i32> @intrinsic_vrev8_vs_nxv1i32(<vscale x 1 x i32> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vrev8_vs_nxv1i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, mf2, ta, ma
+; CHECK-NEXT:    vrev8.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i32> @llvm.riscv.vrev8.nxv1i32(
+    <vscale x 1 x i32> undef,
+    <vscale x 1 x i32> %0,
+    iXLen %1)
+
+  ret <vscale x 1 x i32> %a
+}
+
+declare <vscale x 1 x i32> @llvm.riscv.vrev8.mask.nxv1i32(
+  <vscale x 1 x i32>,
+  <vscale x 1 x i32>,
+  <vscale x 1 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 1 x i32> @intrinsic_vrev8_mask_vs_nxv1i32(<vscale x 1 x i1> %0, <vscale x 1 x i32> %1, <vscale x 1 x i32> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vrev8_mask_vs_nxv1i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, mf2, ta, mu
+; CHECK-NEXT:    vrev8.v v8, v9, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i32> @llvm.riscv.vrev8.mask.nxv1i32(
+    <vscale x 1 x i32> %1,
+    <vscale x 1 x i32> %2,
+    <vscale x 1 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 1 x i32> %a
+}
+
+declare <vscale x 2 x i32> @llvm.riscv.vrev8.nxv2i32(
+  <vscale x 2 x i32>,
+  <vscale x 2 x i32>,
+  iXLen);
+
+define <vscale x 2 x i32> @intrinsic_vrev8_vs_nxv2i32(<vscale x 2 x i32> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vrev8_vs_nxv2i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m1, ta, ma
+; CHECK-NEXT:    vrev8.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i32> @llvm.riscv.vrev8.nxv2i32(
+    <vscale x 2 x i32> undef,
+    <vscale x 2 x i32> %0,
+    iXLen %1)
+
+  ret <vscale x 2 x i32> %a
+}
+
+declare <vscale x 2 x i32> @llvm.riscv.vrev8.mask.nxv2i32(
+  <vscale x 2 x i32>,
+  <vscale x 2 x i32>,
+  <vscale x 2 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 2 x i32> @intrinsic_vrev8_mask_vs_nxv2i32(<vscale x 2 x i1> %0, <vscale x 2 x i32> %1, <vscale x 2 x i32> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vrev8_mask_vs_nxv2i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m1, ta, mu
+; CHECK-NEXT:    vrev8.v v8, v9, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i32> @llvm.riscv.vrev8.mask.nxv2i32(
+    <vscale x 2 x i32> %1,
+    <vscale x 2 x i32> %2,
+    <vscale x 2 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 2 x i32> %a
+}
+
+declare <vscale x 4 x i32> @llvm.riscv.vrev8.nxv4i32(
+  <vscale x 4 x i32>,
+  <vscale x 4 x i32>,
+  iXLen);
+
+define <vscale x 4 x i32> @intrinsic_vrev8_vs_nxv4i32(<vscale x 4 x i32> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vrev8_vs_nxv4i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m2, ta, ma
+; CHECK-NEXT:    vrev8.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i32> @llvm.riscv.vrev8.nxv4i32(
+    <vscale x 4 x i32> undef,
+    <vscale x 4 x i32> %0,
+    iXLen %1)
+
+  ret <vscale x 4 x i32> %a
+}
+
+declare <vscale x 4 x i32> @llvm.riscv.vrev8.mask.nxv4i32(
+  <vscale x 4 x i32>,
+  <vscale x 4 x i32>,
+  <vscale x 4 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 4 x i32> @intrinsic_vrev8_mask_vs_nxv4i32(<vscale x 4 x i1> %0, <vscale x 4 x i32> %1, <vscale x 4 x i32> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vrev8_mask_vs_nxv4i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m2, ta, mu
+; CHECK-NEXT:    vrev8.v v8, v10, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i32> @llvm.riscv.vrev8.mask.nxv4i32(
+    <vscale x 4 x i32> %1,
+    <vscale x 4 x i32> %2,
+    <vscale x 4 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 4 x i32> %a
+}
+
+declare <vscale x 8 x i32> @llvm.riscv.vrev8.nxv8i32(
+  <vscale x 8 x i32>,
+  <vscale x 8 x i32>,
+  iXLen);
+
+define <vscale x 8 x i32> @intrinsic_vrev8_vs_nxv8i32(<vscale x 8 x i32> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vrev8_vs_nxv8i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m4, ta, ma
+; CHECK-NEXT:    vrev8.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i32> @llvm.riscv.vrev8.nxv8i32(
+    <vscale x 8 x i32> undef,
+    <vscale x 8 x i32> %0,
+    iXLen %1)
+
+  ret <vscale x 8 x i32> %a
+}
+
+declare <vscale x 8 x i32> @llvm.riscv.vrev8.mask.nxv8i32(
+  <vscale x 8 x i32>,
+  <vscale x 8 x i32>,
+  <vscale x 8 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 8 x i32> @intrinsic_vrev8_mask_vs_nxv8i32(<vscale x 8 x i1> %0, <vscale x 8 x i32> %1, <vscale x 8 x i32> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vrev8_mask_vs_nxv8i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m4, ta, mu
+; CHECK-NEXT:    vrev8.v v8, v12, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i32> @llvm.riscv.vrev8.mask.nxv8i32(
+    <vscale x 8 x i32> %1,
+    <vscale x 8 x i32> %2,
+    <vscale x 8 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 8 x i32> %a
+}
+
+declare <vscale x 16 x i32> @llvm.riscv.vrev8.nxv16i32(
+  <vscale x 16 x i32>,
+  <vscale x 16 x i32>,
+  iXLen);
+
+define <vscale x 16 x i32> @intrinsic_vrev8_vs_nxv16i32(<vscale x 16 x i32> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vrev8_vs_nxv16i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m8, ta, ma
+; CHECK-NEXT:    vrev8.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 16 x i32> @llvm.riscv.vrev8.nxv16i32(
+    <vscale x 16 x i32> undef,
+    <vscale x 16 x i32> %0,
+    iXLen %1)
+
+  ret <vscale x 16 x i32> %a
+}
+
+declare <vscale x 16 x i32> @llvm.riscv.vrev8.mask.nxv16i32(
+  <vscale x 16 x i32>,
+  <vscale x 16 x i32>,
+  <vscale x 16 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 16 x i32> @intrinsic_vrev8_mask_vs_nxv16i32(<vscale x 16 x i1> %0, <vscale x 16 x i32> %1, <vscale x 16 x i32> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vrev8_mask_vs_nxv16i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m8, ta, mu
+; CHECK-NEXT:    vrev8.v v8, v16, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 16 x i32> @llvm.riscv.vrev8.mask.nxv16i32(
+    <vscale x 16 x i32> %1,
+    <vscale x 16 x i32> %2,
+    <vscale x 16 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 16 x i32> %a
+}
+
+declare <vscale x 1 x i64> @llvm.riscv.vrev8.nxv1i64(
+  <vscale x 1 x i64>,
+  <vscale x 1 x i64>,
+  iXLen);
+
+define <vscale x 1 x i64> @intrinsic_vrev8_vs_nxv1i64(<vscale x 1 x i64> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vrev8_vs_nxv1i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e64, m1, ta, ma
+; CHECK-NEXT:    vrev8.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i64> @llvm.riscv.vrev8.nxv1i64(
+    <vscale x 1 x i64> undef,
+    <vscale x 1 x i64> %0,
+    iXLen %1)
+
+  ret <vscale x 1 x i64> %a
+}
+
+declare <vscale x 1 x i64> @llvm.riscv.vrev8.mask.nxv1i64(
+  <vscale x 1 x i64>,
+  <vscale x 1 x i64>,
+  <vscale x 1 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 1 x i64> @intrinsic_vrev8_mask_vs_nxv1i64(<vscale x 1 x i1> %0, <vscale x 1 x i64> %1, <vscale x 1 x i64> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vrev8_mask_vs_nxv1i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e64, m1, ta, mu
+; CHECK-NEXT:    vrev8.v v8, v9, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i64> @llvm.riscv.vrev8.mask.nxv1i64(
+    <vscale x 1 x i64> %1,
+    <vscale x 1 x i64> %2,
+    <vscale x 1 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 1 x i64> %a
+}
+
+declare <vscale x 2 x i64> @llvm.riscv.vrev8.nxv2i64(
+  <vscale x 2 x i64>,
+  <vscale x 2 x i64>,
+  iXLen);
+
+define <vscale x 2 x i64> @intrinsic_vrev8_vs_nxv2i64(<vscale x 2 x i64> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vrev8_vs_nxv2i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e64, m2, ta, ma
+; CHECK-NEXT:    vrev8.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i64> @llvm.riscv.vrev8.nxv2i64(
+    <vscale x 2 x i64> undef,
+    <vscale x 2 x i64> %0,
+    iXLen %1)
+
+  ret <vscale x 2 x i64> %a
+}
+
+declare <vscale x 2 x i64> @llvm.riscv.vrev8.mask.nxv2i64(
+  <vscale x 2 x i64>,
+  <vscale x 2 x i64>,
+  <vscale x 2 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 2 x i64> @intrinsic_vrev8_mask_vs_nxv2i64(<vscale x 2 x i1> %0, <vscale x 2 x i64> %1, <vscale x 2 x i64> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vrev8_mask_vs_nxv2i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e64, m2, ta, mu
+; CHECK-NEXT:    vrev8.v v8, v10, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i64> @llvm.riscv.vrev8.mask.nxv2i64(
+    <vscale x 2 x i64> %1,
+    <vscale x 2 x i64> %2,
+    <vscale x 2 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 2 x i64> %a
+}
+
+declare <vscale x 4 x i64> @llvm.riscv.vrev8.nxv4i64(
+  <vscale x 4 x i64>,
+  <vscale x 4 x i64>,
+  iXLen);
+
+define <vscale x 4 x i64> @intrinsic_vrev8_vs_nxv4i64(<vscale x 4 x i64> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vrev8_vs_nxv4i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e64, m4, ta, ma
+; CHECK-NEXT:    vrev8.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i64> @llvm.riscv.vrev8.nxv4i64(
+    <vscale x 4 x i64> undef,
+    <vscale x 4 x i64> %0,
+    iXLen %1)
+
+  ret <vscale x 4 x i64> %a
+}
+
+declare <vscale x 4 x i64> @llvm.riscv.vrev8.mask.nxv4i64(
+  <vscale x 4 x i64>,
+  <vscale x 4 x i64>,
+  <vscale x 4 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 4 x i64> @intrinsic_vrev8_mask_vs_nxv4i64(<vscale x 4 x i1> %0, <vscale x 4 x i64> %1, <vscale x 4 x i64> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vrev8_mask_vs_nxv4i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e64, m4, ta, mu
+; CHECK-NEXT:    vrev8.v v8, v12, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i64> @llvm.riscv.vrev8.mask.nxv4i64(
+    <vscale x 4 x i64> %1,
+    <vscale x 4 x i64> %2,
+    <vscale x 4 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 4 x i64> %a
+}
+
+declare <vscale x 8 x i64> @llvm.riscv.vrev8.nxv8i64(
+  <vscale x 8 x i64>,
+  <vscale x 8 x i64>,
+  iXLen);
+
+define <vscale x 8 x i64> @intrinsic_vrev8_vs_nxv8i64(<vscale x 8 x i64> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vrev8_vs_nxv8i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
+; CHECK-NEXT:    vrev8.v v8, v8
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i64> @llvm.riscv.vrev8.nxv8i64(
+    <vscale x 8 x i64> undef,
+    <vscale x 8 x i64> %0,
+    iXLen %1)
+
+  ret <vscale x 8 x i64> %a
+}
+
+declare <vscale x 8 x i64> @llvm.riscv.vrev8.mask.nxv8i64(
+  <vscale x 8 x i64>,
+  <vscale x 8 x i64>,
+  <vscale x 8 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 8 x i64> @intrinsic_vrev8_mask_vs_nxv8i64(<vscale x 8 x i1> %0, <vscale x 8 x i64> %1, <vscale x 8 x i64> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vrev8_mask_vs_nxv8i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, mu
+; CHECK-NEXT:    vrev8.v v8, v16, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i64> @llvm.riscv.vrev8.mask.nxv8i64(
+    <vscale x 8 x i64> %1,
+    <vscale x 8 x i64> %2,
+    <vscale x 8 x i1> %0,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 8 x i64> %a
+}

llvm/test/CodeGen/RISCV/rvv/vrol.ll

+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: sed 's/iXLen/i32/g' %s | llc -mtriple=riscv32 -mattr=+v,+experimental-zvbb \
+; RUN:   -verify-machineinstrs | FileCheck %s --check-prefixes=CHECK,RV32
+; RUN: sed 's/iXLen/i64/g' %s | llc -mtriple=riscv64 -mattr=+v,+experimental-zvbb \
+; RUN:   -verify-machineinstrs | FileCheck %s --check-prefixes=CHECK,RV64
+
+declare <vscale x 1 x i8> @llvm.riscv.vrol.nxv1i8.nxv1i8(
+  <vscale x 1 x i8>,
+  <vscale x 1 x i8>,
+  <vscale x 1 x i8>,
+  iXLen)
+
+define <vscale x 1 x i8> @intrinsic_vrol_vv_nxv1i8_nxv1i8(<vscale x 1 x i8> %0, <vscale x 1 x i8> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vrol_vv_nxv1i8_nxv1i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, mf8, ta, ma
+; CHECK-NEXT:    vrol.vv v8, v8, v9
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i8> @llvm.riscv.vrol.nxv1i8.nxv1i8(
+    <vscale x 1 x i8> undef,
+    <vscale x 1 x i8> %0,
+    <vscale x 1 x i8> %1,
+    iXLen %2)
+
+  ret <vscale x 1 x i8> %a
+}
+
+declare <vscale x 1 x i8> @llvm.riscv.vrol.mask.nxv1i8.nxv1i8(
+  <vscale x 1 x i8>,
+  <vscale x 1 x i8>,
+  <vscale x 1 x i8>,
+  <vscale x 1 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 1 x i8> @intrinsic_vrol_mask_vv_nxv1i8_nxv1i8(<vscale x 1 x i8> %0, <vscale x 1 x i8> %1, <vscale x 1 x i8> %2, <vscale x 1 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vrol_mask_vv_nxv1i8_nxv1i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, mf8, ta, mu
+; CHECK-NEXT:    vrol.vv v8, v9, v10, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i8> @llvm.riscv.vrol.mask.nxv1i8.nxv1i8(
+    <vscale x 1 x i8> %0,
+    <vscale x 1 x i8> %1,
+    <vscale x 1 x i8> %2,
+    <vscale x 1 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 1 x i8> %a
+}
+
+declare <vscale x 2 x i8> @llvm.riscv.vrol.nxv2i8.nxv2i8(
+  <vscale x 2 x i8>,
+  <vscale x 2 x i8>,
+  <vscale x 2 x i8>,
+  iXLen)
+
+define <vscale x 2 x i8> @intrinsic_vrol_vv_nxv2i8_nxv2i8(<vscale x 2 x i8> %0, <vscale x 2 x i8> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vrol_vv_nxv2i8_nxv2i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, mf4, ta, ma
+; CHECK-NEXT:    vrol.vv v8, v8, v9
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i8> @llvm.riscv.vrol.nxv2i8.nxv2i8(
+    <vscale x 2 x i8> undef,
+    <vscale x 2 x i8> %0,
+    <vscale x 2 x i8> %1,
+    iXLen %2)
+
+  ret <vscale x 2 x i8> %a
+}
+
+declare <vscale x 2 x i8> @llvm.riscv.vrol.mask.nxv2i8.nxv2i8(
+  <vscale x 2 x i8>,
+  <vscale x 2 x i8>,
+  <vscale x 2 x i8>,
+  <vscale x 2 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 2 x i8> @intrinsic_vrol_mask_vv_nxv2i8_nxv2i8(<vscale x 2 x i8> %0, <vscale x 2 x i8> %1, <vscale x 2 x i8> %2, <vscale x 2 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vrol_mask_vv_nxv2i8_nxv2i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, mf4, ta, mu
+; CHECK-NEXT:    vrol.vv v8, v9, v10, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i8> @llvm.riscv.vrol.mask.nxv2i8.nxv2i8(
+    <vscale x 2 x i8> %0,
+    <vscale x 2 x i8> %1,
+    <vscale x 2 x i8> %2,
+    <vscale x 2 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 2 x i8> %a
+}
+
+declare <vscale x 4 x i8> @llvm.riscv.vrol.nxv4i8.nxv4i8(
+  <vscale x 4 x i8>,
+  <vscale x 4 x i8>,
+  <vscale x 4 x i8>,
+  iXLen)
+
+define <vscale x 4 x i8> @intrinsic_vrol_vv_nxv4i8_nxv4i8(<vscale x 4 x i8> %0, <vscale x 4 x i8> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vrol_vv_nxv4i8_nxv4i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, mf2, ta, ma
+; CHECK-NEXT:    vrol.vv v8, v8, v9
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i8> @llvm.riscv.vrol.nxv4i8.nxv4i8(
+    <vscale x 4 x i8> undef,
+    <vscale x 4 x i8> %0,
+    <vscale x 4 x i8> %1,
+    iXLen %2)
+
+  ret <vscale x 4 x i8> %a
+}
+
+declare <vscale x 4 x i8> @llvm.riscv.vrol.mask.nxv4i8.nxv4i8(
+  <vscale x 4 x i8>,
+  <vscale x 4 x i8>,
+  <vscale x 4 x i8>,
+  <vscale x 4 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 4 x i8> @intrinsic_vrol_mask_vv_nxv4i8_nxv4i8(<vscale x 4 x i8> %0, <vscale x 4 x i8> %1, <vscale x 4 x i8> %2, <vscale x 4 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vrol_mask_vv_nxv4i8_nxv4i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, mf2, ta, mu
+; CHECK-NEXT:    vrol.vv v8, v9, v10, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i8> @llvm.riscv.vrol.mask.nxv4i8.nxv4i8(
+    <vscale x 4 x i8> %0,
+    <vscale x 4 x i8> %1,
+    <vscale x 4 x i8> %2,
+    <vscale x 4 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 4 x i8> %a
+}
+
+declare <vscale x 8 x i8> @llvm.riscv.vrol.nxv8i8.nxv8i8(
+  <vscale x 8 x i8>,
+  <vscale x 8 x i8>,
+  <vscale x 8 x i8>,
+  iXLen)
+
+define <vscale x 8 x i8> @intrinsic_vrol_vv_nxv8i8_nxv8i8(<vscale x 8 x i8> %0, <vscale x 8 x i8> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vrol_vv_nxv8i8_nxv8i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, m1, ta, ma
+; CHECK-NEXT:    vrol.vv v8, v8, v9
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i8> @llvm.riscv.vrol.nxv8i8.nxv8i8(
+    <vscale x 8 x i8> undef,
+    <vscale x 8 x i8> %0,
+    <vscale x 8 x i8> %1,
+    iXLen %2)
+
+  ret <vscale x 8 x i8> %a
+}
+
+declare <vscale x 8 x i8> @llvm.riscv.vrol.mask.nxv8i8.nxv8i8(
+  <vscale x 8 x i8>,
+  <vscale x 8 x i8>,
+  <vscale x 8 x i8>,
+  <vscale x 8 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 8 x i8> @intrinsic_vrol_mask_vv_nxv8i8_nxv8i8(<vscale x 8 x i8> %0, <vscale x 8 x i8> %1, <vscale x 8 x i8> %2, <vscale x 8 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vrol_mask_vv_nxv8i8_nxv8i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, m1, ta, mu
+; CHECK-NEXT:    vrol.vv v8, v9, v10, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i8> @llvm.riscv.vrol.mask.nxv8i8.nxv8i8(
+    <vscale x 8 x i8> %0,
+    <vscale x 8 x i8> %1,
+    <vscale x 8 x i8> %2,
+    <vscale x 8 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 8 x i8> %a
+}
+
+declare <vscale x 16 x i8> @llvm.riscv.vrol.nxv16i8.nxv16i8(
+  <vscale x 16 x i8>,
+  <vscale x 16 x i8>,
+  <vscale x 16 x i8>,
+  iXLen)
+
+define <vscale x 16 x i8> @intrinsic_vrol_vv_nxv16i8_nxv16i8(<vscale x 16 x i8> %0, <vscale x 16 x i8> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vrol_vv_nxv16i8_nxv16i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, m2, ta, ma
+; CHECK-NEXT:    vrol.vv v8, v8, v10
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 16 x i8> @llvm.riscv.vrol.nxv16i8.nxv16i8(
+    <vscale x 16 x i8> undef,
+    <vscale x 16 x i8> %0,
+    <vscale x 16 x i8> %1,
+    iXLen %2)
+
+  ret <vscale x 16 x i8> %a
+}
+
+declare <vscale x 16 x i8> @llvm.riscv.vrol.mask.nxv16i8.nxv16i8(
+  <vscale x 16 x i8>,
+  <vscale x 16 x i8>,
+  <vscale x 16 x i8>,
+  <vscale x 16 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 16 x i8> @intrinsic_vrol_mask_vv_nxv16i8_nxv16i8(<vscale x 16 x i8> %0, <vscale x 16 x i8> %1, <vscale x 16 x i8> %2, <vscale x 16 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vrol_mask_vv_nxv16i8_nxv16i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, m2, ta, mu
+; CHECK-NEXT:    vrol.vv v8, v10, v12, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 16 x i8> @llvm.riscv.vrol.mask.nxv16i8.nxv16i8(
+    <vscale x 16 x i8> %0,
+    <vscale x 16 x i8> %1,
+    <vscale x 16 x i8> %2,
+    <vscale x 16 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 16 x i8> %a
+}
+
+declare <vscale x 32 x i8> @llvm.riscv.vrol.nxv32i8.nxv32i8(
+  <vscale x 32 x i8>,
+  <vscale x 32 x i8>,
+  <vscale x 32 x i8>,
+  iXLen)
+
+define <vscale x 32 x i8> @intrinsic_vrol_vv_nxv32i8_nxv32i8(<vscale x 32 x i8> %0, <vscale x 32 x i8> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vrol_vv_nxv32i8_nxv32i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, m4, ta, ma
+; CHECK-NEXT:    vrol.vv v8, v8, v12
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 32 x i8> @llvm.riscv.vrol.nxv32i8.nxv32i8(
+    <vscale x 32 x i8> undef,
+    <vscale x 32 x i8> %0,
+    <vscale x 32 x i8> %1,
+    iXLen %2)
+
+  ret <vscale x 32 x i8> %a
+}
+
+declare <vscale x 32 x i8> @llvm.riscv.vrol.mask.nxv32i8.nxv32i8(
+  <vscale x 32 x i8>,
+  <vscale x 32 x i8>,
+  <vscale x 32 x i8>,
+  <vscale x 32 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 32 x i8> @intrinsic_vrol_mask_vv_nxv32i8_nxv32i8(<vscale x 32 x i8> %0, <vscale x 32 x i8> %1, <vscale x 32 x i8> %2, <vscale x 32 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vrol_mask_vv_nxv32i8_nxv32i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, m4, ta, mu
+; CHECK-NEXT:    vrol.vv v8, v12, v16, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 32 x i8> @llvm.riscv.vrol.mask.nxv32i8.nxv32i8(
+    <vscale x 32 x i8> %0,
+    <vscale x 32 x i8> %1,
+    <vscale x 32 x i8> %2,
+    <vscale x 32 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 32 x i8> %a
+}
+
+declare <vscale x 64 x i8> @llvm.riscv.vrol.nxv64i8.nxv64i8(
+  <vscale x 64 x i8>,
+  <vscale x 64 x i8>,
+  <vscale x 64 x i8>,
+  iXLen)
+
+define <vscale x 64 x i8> @intrinsic_vrol_vv_nxv64i8_nxv64i8(<vscale x 64 x i8> %0, <vscale x 64 x i8> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vrol_vv_nxv64i8_nxv64i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, m8, ta, ma
+; CHECK-NEXT:    vrol.vv v8, v8, v16
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 64 x i8> @llvm.riscv.vrol.nxv64i8.nxv64i8(
+    <vscale x 64 x i8> undef,
+    <vscale x 64 x i8> %0,
+    <vscale x 64 x i8> %1,
+    iXLen %2)
+
+  ret <vscale x 64 x i8> %a
+}
+
+declare <vscale x 64 x i8> @llvm.riscv.vrol.mask.nxv64i8.nxv64i8(
+  <vscale x 64 x i8>,
+  <vscale x 64 x i8>,
+  <vscale x 64 x i8>,
+  <vscale x 64 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 64 x i8> @intrinsic_vrol_mask_vv_nxv64i8_nxv64i8(<vscale x 64 x i8> %0, <vscale x 64 x i8> %1, <vscale x 64 x i8> %2, <vscale x 64 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vrol_mask_vv_nxv64i8_nxv64i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vl8r.v v24, (a0)
+; CHECK-NEXT:    vsetvli zero, a1, e8, m8, ta, mu
+; CHECK-NEXT:    vrol.vv v8, v16, v24, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 64 x i8> @llvm.riscv.vrol.mask.nxv64i8.nxv64i8(
+    <vscale x 64 x i8> %0,
+    <vscale x 64 x i8> %1,
+    <vscale x 64 x i8> %2,
+    <vscale x 64 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 64 x i8> %a
+}
+
+declare <vscale x 1 x i16> @llvm.riscv.vrol.nxv1i16.nxv1i16(
+  <vscale x 1 x i16>,
+  <vscale x 1 x i16>,
+  <vscale x 1 x i16>,
+  iXLen)
+
+define <vscale x 1 x i16> @intrinsic_vrol_vv_nxv1i16_nxv1i16(<vscale x 1 x i16> %0, <vscale x 1 x i16> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vrol_vv_nxv1i16_nxv1i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, mf4, ta, ma
+; CHECK-NEXT:    vrol.vv v8, v8, v9
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i16> @llvm.riscv.vrol.nxv1i16.nxv1i16(
+    <vscale x 1 x i16> undef,
+    <vscale x 1 x i16> %0,
+    <vscale x 1 x i16> %1,
+    iXLen %2)
+
+  ret <vscale x 1 x i16> %a
+}
+
+declare <vscale x 1 x i16> @llvm.riscv.vrol.mask.nxv1i16.nxv1i16(
+  <vscale x 1 x i16>,
+  <vscale x 1 x i16>,
+  <vscale x 1 x i16>,
+  <vscale x 1 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 1 x i16> @intrinsic_vrol_mask_vv_nxv1i16_nxv1i16(<vscale x 1 x i16> %0, <vscale x 1 x i16> %1, <vscale x 1 x i16> %2, <vscale x 1 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vrol_mask_vv_nxv1i16_nxv1i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, mf4, ta, mu
+; CHECK-NEXT:    vrol.vv v8, v9, v10, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i16> @llvm.riscv.vrol.mask.nxv1i16.nxv1i16(
+    <vscale x 1 x i16> %0,
+    <vscale x 1 x i16> %1,
+    <vscale x 1 x i16> %2,
+    <vscale x 1 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 1 x i16> %a
+}
+
+declare <vscale x 2 x i16> @llvm.riscv.vrol.nxv2i16.nxv2i16(
+  <vscale x 2 x i16>,
+  <vscale x 2 x i16>,
+  <vscale x 2 x i16>,
+  iXLen)
+
+define <vscale x 2 x i16> @intrinsic_vrol_vv_nxv2i16_nxv2i16(<vscale x 2 x i16> %0, <vscale x 2 x i16> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vrol_vv_nxv2i16_nxv2i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, mf2, ta, ma
+; CHECK-NEXT:    vrol.vv v8, v8, v9
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i16> @llvm.riscv.vrol.nxv2i16.nxv2i16(
+    <vscale x 2 x i16> undef,
+    <vscale x 2 x i16> %0,
+    <vscale x 2 x i16> %1,
+    iXLen %2)
+
+  ret <vscale x 2 x i16> %a
+}
+
+declare <vscale x 2 x i16> @llvm.riscv.vrol.mask.nxv2i16.nxv2i16(
+  <vscale x 2 x i16>,
+  <vscale x 2 x i16>,
+  <vscale x 2 x i16>,
+  <vscale x 2 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 2 x i16> @intrinsic_vrol_mask_vv_nxv2i16_nxv2i16(<vscale x 2 x i16> %0, <vscale x 2 x i16> %1, <vscale x 2 x i16> %2, <vscale x 2 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vrol_mask_vv_nxv2i16_nxv2i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, mf2, ta, mu
+; CHECK-NEXT:    vrol.vv v8, v9, v10, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i16> @llvm.riscv.vrol.mask.nxv2i16.nxv2i16(
+    <vscale x 2 x i16> %0,
+    <vscale x 2 x i16> %1,
+    <vscale x 2 x i16> %2,
+    <vscale x 2 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 2 x i16> %a
+}
+
+declare <vscale x 4 x i16> @llvm.riscv.vrol.nxv4i16.nxv4i16(
+  <vscale x 4 x i16>,
+  <vscale x 4 x i16>,
+  <vscale x 4 x i16>,
+  iXLen)
+
+define <vscale x 4 x i16> @intrinsic_vrol_vv_nxv4i16_nxv4i16(<vscale x 4 x i16> %0, <vscale x 4 x i16> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vrol_vv_nxv4i16_nxv4i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, m1, ta, ma
+; CHECK-NEXT:    vrol.vv v8, v8, v9
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i16> @llvm.riscv.vrol.nxv4i16.nxv4i16(
+    <vscale x 4 x i16> undef,
+    <vscale x 4 x i16> %0,
+    <vscale x 4 x i16> %1,
+    iXLen %2)
+
+  ret <vscale x 4 x i16> %a
+}
+
+declare <vscale x 4 x i16> @llvm.riscv.vrol.mask.nxv4i16.nxv4i16(
+  <vscale x 4 x i16>,
+  <vscale x 4 x i16>,
+  <vscale x 4 x i16>,
+  <vscale x 4 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 4 x i16> @intrinsic_vrol_mask_vv_nxv4i16_nxv4i16(<vscale x 4 x i16> %0, <vscale x 4 x i16> %1, <vscale x 4 x i16> %2, <vscale x 4 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vrol_mask_vv_nxv4i16_nxv4i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, m1, ta, mu
+; CHECK-NEXT:    vrol.vv v8, v9, v10, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i16> @llvm.riscv.vrol.mask.nxv4i16.nxv4i16(
+    <vscale x 4 x i16> %0,
+    <vscale x 4 x i16> %1,
+    <vscale x 4 x i16> %2,
+    <vscale x 4 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 4 x i16> %a
+}
+
+declare <vscale x 8 x i16> @llvm.riscv.vrol.nxv8i16.nxv8i16(
+  <vscale x 8 x i16>,
+  <vscale x 8 x i16>,
+  <vscale x 8 x i16>,
+  iXLen)
+
+define <vscale x 8 x i16> @intrinsic_vrol_vv_nxv8i16_nxv8i16(<vscale x 8 x i16> %0, <vscale x 8 x i16> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vrol_vv_nxv8i16_nxv8i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, m2, ta, ma
+; CHECK-NEXT:    vrol.vv v8, v8, v10
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i16> @llvm.riscv.vrol.nxv8i16.nxv8i16(
+    <vscale x 8 x i16> undef,
+    <vscale x 8 x i16> %0,
+    <vscale x 8 x i16> %1,
+    iXLen %2)
+
+  ret <vscale x 8 x i16> %a
+}
+
+declare <vscale x 8 x i16> @llvm.riscv.vrol.mask.nxv8i16.nxv8i16(
+  <vscale x 8 x i16>,
+  <vscale x 8 x i16>,
+  <vscale x 8 x i16>,
+  <vscale x 8 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 8 x i16> @intrinsic_vrol_mask_vv_nxv8i16_nxv8i16(<vscale x 8 x i16> %0, <vscale x 8 x i16> %1, <vscale x 8 x i16> %2, <vscale x 8 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vrol_mask_vv_nxv8i16_nxv8i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, m2, ta, mu
+; CHECK-NEXT:    vrol.vv v8, v10, v12, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i16> @llvm.riscv.vrol.mask.nxv8i16.nxv8i16(
+    <vscale x 8 x i16> %0,
+    <vscale x 8 x i16> %1,
+    <vscale x 8 x i16> %2,
+    <vscale x 8 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 8 x i16> %a
+}
+
+declare <vscale x 16 x i16> @llvm.riscv.vrol.nxv16i16.nxv16i16(
+  <vscale x 16 x i16>,
+  <vscale x 16 x i16>,
+  <vscale x 16 x i16>,
+  iXLen)
+
+define <vscale x 16 x i16> @intrinsic_vrol_vv_nxv16i16_nxv16i16(<vscale x 16 x i16> %0, <vscale x 16 x i16> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vrol_vv_nxv16i16_nxv16i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, m4, ta, ma
+; CHECK-NEXT:    vrol.vv v8, v8, v12
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 16 x i16> @llvm.riscv.vrol.nxv16i16.nxv16i16(
+    <vscale x 16 x i16> undef,
+    <vscale x 16 x i16> %0,
+    <vscale x 16 x i16> %1,
+    iXLen %2)
+
+  ret <vscale x 16 x i16> %a
+}
+
+declare <vscale x 16 x i16> @llvm.riscv.vrol.mask.nxv16i16.nxv16i16(
+  <vscale x 16 x i16>,
+  <vscale x 16 x i16>,
+  <vscale x 16 x i16>,
+  <vscale x 16 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 16 x i16> @intrinsic_vrol_mask_vv_nxv16i16_nxv16i16(<vscale x 16 x i16> %0, <vscale x 16 x i16> %1, <vscale x 16 x i16> %2, <vscale x 16 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vrol_mask_vv_nxv16i16_nxv16i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, m4, ta, mu
+; CHECK-NEXT:    vrol.vv v8, v12, v16, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 16 x i16> @llvm.riscv.vrol.mask.nxv16i16.nxv16i16(
+    <vscale x 16 x i16> %0,
+    <vscale x 16 x i16> %1,
+    <vscale x 16 x i16> %2,
+    <vscale x 16 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 16 x i16> %a
+}
+
+declare <vscale x 32 x i16> @llvm.riscv.vrol.nxv32i16.nxv32i16(
+  <vscale x 32 x i16>,
+  <vscale x 32 x i16>,
+  <vscale x 32 x i16>,
+  iXLen)
+
+define <vscale x 32 x i16> @intrinsic_vrol_vv_nxv32i16_nxv32i16(<vscale x 32 x i16> %0, <vscale x 32 x i16> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vrol_vv_nxv32i16_nxv32i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, m8, ta, ma
+; CHECK-NEXT:    vrol.vv v8, v8, v16
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 32 x i16> @llvm.riscv.vrol.nxv32i16.nxv32i16(
+    <vscale x 32 x i16> undef,
+    <vscale x 32 x i16> %0,
+    <vscale x 32 x i16> %1,
+    iXLen %2)
+
+  ret <vscale x 32 x i16> %a
+}
+
+declare <vscale x 32 x i16> @llvm.riscv.vrol.mask.nxv32i16.nxv32i16(
+  <vscale x 32 x i16>,
+  <vscale x 32 x i16>,
+  <vscale x 32 x i16>,
+  <vscale x 32 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 32 x i16> @intrinsic_vrol_mask_vv_nxv32i16_nxv32i16(<vscale x 32 x i16> %0, <vscale x 32 x i16> %1, <vscale x 32 x i16> %2, <vscale x 32 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vrol_mask_vv_nxv32i16_nxv32i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vl8re16.v v24, (a0)
+; CHECK-NEXT:    vsetvli zero, a1, e16, m8, ta, mu
+; CHECK-NEXT:    vrol.vv v8, v16, v24, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 32 x i16> @llvm.riscv.vrol.mask.nxv32i16.nxv32i16(
+    <vscale x 32 x i16> %0,
+    <vscale x 32 x i16> %1,
+    <vscale x 32 x i16> %2,
+    <vscale x 32 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 32 x i16> %a
+}
+
+declare <vscale x 1 x i32> @llvm.riscv.vrol.nxv1i32.nxv1i32(
+  <vscale x 1 x i32>,
+  <vscale x 1 x i32>,
+  <vscale x 1 x i32>,
+  iXLen)
+
+define <vscale x 1 x i32> @intrinsic_vrol_vv_nxv1i32_nxv1i32(<vscale x 1 x i32> %0, <vscale x 1 x i32> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vrol_vv_nxv1i32_nxv1i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, mf2, ta, ma
+; CHECK-NEXT:    vrol.vv v8, v8, v9
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i32> @llvm.riscv.vrol.nxv1i32.nxv1i32(
+    <vscale x 1 x i32> undef,
+    <vscale x 1 x i32> %0,
+    <vscale x 1 x i32> %1,
+    iXLen %2)
+
+  ret <vscale x 1 x i32> %a
+}
+
+declare <vscale x 1 x i32> @llvm.riscv.vrol.mask.nxv1i32.nxv1i32(
+  <vscale x 1 x i32>,
+  <vscale x 1 x i32>,
+  <vscale x 1 x i32>,
+  <vscale x 1 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 1 x i32> @intrinsic_vrol_mask_vv_nxv1i32_nxv1i32(<vscale x 1 x i32> %0, <vscale x 1 x i32> %1, <vscale x 1 x i32> %2, <vscale x 1 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vrol_mask_vv_nxv1i32_nxv1i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, mf2, ta, mu
+; CHECK-NEXT:    vrol.vv v8, v9, v10, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i32> @llvm.riscv.vrol.mask.nxv1i32.nxv1i32(
+    <vscale x 1 x i32> %0,
+    <vscale x 1 x i32> %1,
+    <vscale x 1 x i32> %2,
+    <vscale x 1 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 1 x i32> %a
+}
+
+declare <vscale x 2 x i32> @llvm.riscv.vrol.nxv2i32.nxv2i32(
+  <vscale x 2 x i32>,
+  <vscale x 2 x i32>,
+  <vscale x 2 x i32>,
+  iXLen)
+
+define <vscale x 2 x i32> @intrinsic_vrol_vv_nxv2i32_nxv2i32(<vscale x 2 x i32> %0, <vscale x 2 x i32> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vrol_vv_nxv2i32_nxv2i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m1, ta, ma
+; CHECK-NEXT:    vrol.vv v8, v8, v9
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i32> @llvm.riscv.vrol.nxv2i32.nxv2i32(
+    <vscale x 2 x i32> undef,
+    <vscale x 2 x i32> %0,
+    <vscale x 2 x i32> %1,
+    iXLen %2)
+
+  ret <vscale x 2 x i32> %a
+}
+
+declare <vscale x 2 x i32> @llvm.riscv.vrol.mask.nxv2i32.nxv2i32(
+  <vscale x 2 x i32>,
+  <vscale x 2 x i32>,
+  <vscale x 2 x i32>,
+  <vscale x 2 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 2 x i32> @intrinsic_vrol_mask_vv_nxv2i32_nxv2i32(<vscale x 2 x i32> %0, <vscale x 2 x i32> %1, <vscale x 2 x i32> %2, <vscale x 2 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vrol_mask_vv_nxv2i32_nxv2i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m1, ta, mu
+; CHECK-NEXT:    vrol.vv v8, v9, v10, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i32> @llvm.riscv.vrol.mask.nxv2i32.nxv2i32(
+    <vscale x 2 x i32> %0,
+    <vscale x 2 x i32> %1,
+    <vscale x 2 x i32> %2,
+    <vscale x 2 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 2 x i32> %a
+}
+
+declare <vscale x 4 x i32> @llvm.riscv.vrol.nxv4i32.nxv4i32(
+  <vscale x 4 x i32>,
+  <vscale x 4 x i32>,
+  <vscale x 4 x i32>,
+  iXLen)
+
+define <vscale x 4 x i32> @intrinsic_vrol_vv_nxv4i32_nxv4i32(<vscale x 4 x i32> %0, <vscale x 4 x i32> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vrol_vv_nxv4i32_nxv4i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m2, ta, ma
+; CHECK-NEXT:    vrol.vv v8, v8, v10
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i32> @llvm.riscv.vrol.nxv4i32.nxv4i32(
+    <vscale x 4 x i32> undef,
+    <vscale x 4 x i32> %0,
+    <vscale x 4 x i32> %1,
+    iXLen %2)
+
+  ret <vscale x 4 x i32> %a
+}
+
+declare <vscale x 4 x i32> @llvm.riscv.vrol.mask.nxv4i32.nxv4i32(
+  <vscale x 4 x i32>,
+  <vscale x 4 x i32>,
+  <vscale x 4 x i32>,
+  <vscale x 4 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 4 x i32> @intrinsic_vrol_mask_vv_nxv4i32_nxv4i32(<vscale x 4 x i32> %0, <vscale x 4 x i32> %1, <vscale x 4 x i32> %2, <vscale x 4 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vrol_mask_vv_nxv4i32_nxv4i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m2, ta, mu
+; CHECK-NEXT:    vrol.vv v8, v10, v12, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i32> @llvm.riscv.vrol.mask.nxv4i32.nxv4i32(
+    <vscale x 4 x i32> %0,
+    <vscale x 4 x i32> %1,
+    <vscale x 4 x i32> %2,
+    <vscale x 4 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 4 x i32> %a
+}
+
+declare <vscale x 8 x i32> @llvm.riscv.vrol.nxv8i32.nxv8i32(
+  <vscale x 8 x i32>,
+  <vscale x 8 x i32>,
+  <vscale x 8 x i32>,
+  iXLen)
+
+define <vscale x 8 x i32> @intrinsic_vrol_vv_nxv8i32_nxv8i32(<vscale x 8 x i32> %0, <vscale x 8 x i32> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vrol_vv_nxv8i32_nxv8i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m4, ta, ma
+; CHECK-NEXT:    vrol.vv v8, v8, v12
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i32> @llvm.riscv.vrol.nxv8i32.nxv8i32(
+    <vscale x 8 x i32> undef,
+    <vscale x 8 x i32> %0,
+    <vscale x 8 x i32> %1,
+    iXLen %2)
+
+  ret <vscale x 8 x i32> %a
+}
+
+declare <vscale x 8 x i32> @llvm.riscv.vrol.mask.nxv8i32.nxv8i32(
+  <vscale x 8 x i32>,
+  <vscale x 8 x i32>,
+  <vscale x 8 x i32>,
+  <vscale x 8 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 8 x i32> @intrinsic_vrol_mask_vv_nxv8i32_nxv8i32(<vscale x 8 x i32> %0, <vscale x 8 x i32> %1, <vscale x 8 x i32> %2, <vscale x 8 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vrol_mask_vv_nxv8i32_nxv8i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m4, ta, mu
+; CHECK-NEXT:    vrol.vv v8, v12, v16, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i32> @llvm.riscv.vrol.mask.nxv8i32.nxv8i32(
+    <vscale x 8 x i32> %0,
+    <vscale x 8 x i32> %1,
+    <vscale x 8 x i32> %2,
+    <vscale x 8 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 8 x i32> %a
+}
+
+declare <vscale x 16 x i32> @llvm.riscv.vrol.nxv16i32.nxv16i32(
+  <vscale x 16 x i32>,
+  <vscale x 16 x i32>,
+  <vscale x 16 x i32>,
+  iXLen)
+
+define <vscale x 16 x i32> @intrinsic_vrol_vv_nxv16i32_nxv16i32(<vscale x 16 x i32> %0, <vscale x 16 x i32> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vrol_vv_nxv16i32_nxv16i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m8, ta, ma
+; CHECK-NEXT:    vrol.vv v8, v8, v16
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 16 x i32> @llvm.riscv.vrol.nxv16i32.nxv16i32(
+    <vscale x 16 x i32> undef,
+    <vscale x 16 x i32> %0,
+    <vscale x 16 x i32> %1,
+    iXLen %2)
+
+  ret <vscale x 16 x i32> %a
+}
+
+declare <vscale x 16 x i32> @llvm.riscv.vrol.mask.nxv16i32.nxv16i32(
+  <vscale x 16 x i32>,
+  <vscale x 16 x i32>,
+  <vscale x 16 x i32>,
+  <vscale x 16 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 16 x i32> @intrinsic_vrol_mask_vv_nxv16i32_nxv16i32(<vscale x 16 x i32> %0, <vscale x 16 x i32> %1, <vscale x 16 x i32> %2, <vscale x 16 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vrol_mask_vv_nxv16i32_nxv16i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vl8re32.v v24, (a0)
+; CHECK-NEXT:    vsetvli zero, a1, e32, m8, ta, mu
+; CHECK-NEXT:    vrol.vv v8, v16, v24, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 16 x i32> @llvm.riscv.vrol.mask.nxv16i32.nxv16i32(
+    <vscale x 16 x i32> %0,
+    <vscale x 16 x i32> %1,
+    <vscale x 16 x i32> %2,
+    <vscale x 16 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 16 x i32> %a
+}
+
+declare <vscale x 1 x i64> @llvm.riscv.vrol.nxv1i64.nxv1i64(
+  <vscale x 1 x i64>,
+  <vscale x 1 x i64>,
+  <vscale x 1 x i64>,
+  iXLen)
+
+define <vscale x 1 x i64> @intrinsic_vrol_vv_nxv1i64_nxv1i64(<vscale x 1 x i64> %0, <vscale x 1 x i64> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vrol_vv_nxv1i64_nxv1i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e64, m1, ta, ma
+; CHECK-NEXT:    vrol.vv v8, v8, v9
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i64> @llvm.riscv.vrol.nxv1i64.nxv1i64(
+    <vscale x 1 x i64> undef,
+    <vscale x 1 x i64> %0,
+    <vscale x 1 x i64> %1,
+    iXLen %2)
+
+  ret <vscale x 1 x i64> %a
+}
+
+declare <vscale x 1 x i64> @llvm.riscv.vrol.mask.nxv1i64.nxv1i64(
+  <vscale x 1 x i64>,
+  <vscale x 1 x i64>,
+  <vscale x 1 x i64>,
+  <vscale x 1 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 1 x i64> @intrinsic_vrol_mask_vv_nxv1i64_nxv1i64(<vscale x 1 x i64> %0, <vscale x 1 x i64> %1, <vscale x 1 x i64> %2, <vscale x 1 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vrol_mask_vv_nxv1i64_nxv1i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e64, m1, ta, mu
+; CHECK-NEXT:    vrol.vv v8, v9, v10, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i64> @llvm.riscv.vrol.mask.nxv1i64.nxv1i64(
+    <vscale x 1 x i64> %0,
+    <vscale x 1 x i64> %1,
+    <vscale x 1 x i64> %2,
+    <vscale x 1 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 1 x i64> %a
+}
+
+declare <vscale x 2 x i64> @llvm.riscv.vrol.nxv2i64.nxv2i64(
+  <vscale x 2 x i64>,
+  <vscale x 2 x i64>,
+  <vscale x 2 x i64>,
+  iXLen)
+
+define <vscale x 2 x i64> @intrinsic_vrol_vv_nxv2i64_nxv2i64(<vscale x 2 x i64> %0, <vscale x 2 x i64> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vrol_vv_nxv2i64_nxv2i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e64, m2, ta, ma
+; CHECK-NEXT:    vrol.vv v8, v8, v10
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i64> @llvm.riscv.vrol.nxv2i64.nxv2i64(
+    <vscale x 2 x i64> undef,
+    <vscale x 2 x i64> %0,
+    <vscale x 2 x i64> %1,
+    iXLen %2)
+
+  ret <vscale x 2 x i64> %a
+}
+
+declare <vscale x 2 x i64> @llvm.riscv.vrol.mask.nxv2i64.nxv2i64(
+  <vscale x 2 x i64>,
+  <vscale x 2 x i64>,
+  <vscale x 2 x i64>,
+  <vscale x 2 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 2 x i64> @intrinsic_vrol_mask_vv_nxv2i64_nxv2i64(<vscale x 2 x i64> %0, <vscale x 2 x i64> %1, <vscale x 2 x i64> %2, <vscale x 2 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vrol_mask_vv_nxv2i64_nxv2i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e64, m2, ta, mu
+; CHECK-NEXT:    vrol.vv v8, v10, v12, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i64> @llvm.riscv.vrol.mask.nxv2i64.nxv2i64(
+    <vscale x 2 x i64> %0,
+    <vscale x 2 x i64> %1,
+    <vscale x 2 x i64> %2,
+    <vscale x 2 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 2 x i64> %a
+}
+
+declare <vscale x 4 x i64> @llvm.riscv.vrol.nxv4i64.nxv4i64(
+  <vscale x 4 x i64>,
+  <vscale x 4 x i64>,
+  <vscale x 4 x i64>,
+  iXLen)
+
+define <vscale x 4 x i64> @intrinsic_vrol_vv_nxv4i64_nxv4i64(<vscale x 4 x i64> %0, <vscale x 4 x i64> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vrol_vv_nxv4i64_nxv4i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e64, m4, ta, ma
+; CHECK-NEXT:    vrol.vv v8, v8, v12
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i64> @llvm.riscv.vrol.nxv4i64.nxv4i64(
+    <vscale x 4 x i64> undef,
+    <vscale x 4 x i64> %0,
+    <vscale x 4 x i64> %1,
+    iXLen %2)
+
+  ret <vscale x 4 x i64> %a
+}
+
+declare <vscale x 4 x i64> @llvm.riscv.vrol.mask.nxv4i64.nxv4i64(
+  <vscale x 4 x i64>,
+  <vscale x 4 x i64>,
+  <vscale x 4 x i64>,
+  <vscale x 4 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 4 x i64> @intrinsic_vrol_mask_vv_nxv4i64_nxv4i64(<vscale x 4 x i64> %0, <vscale x 4 x i64> %1, <vscale x 4 x i64> %2, <vscale x 4 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vrol_mask_vv_nxv4i64_nxv4i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e64, m4, ta, mu
+; CHECK-NEXT:    vrol.vv v8, v12, v16, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i64> @llvm.riscv.vrol.mask.nxv4i64.nxv4i64(
+    <vscale x 4 x i64> %0,
+    <vscale x 4 x i64> %1,
+    <vscale x 4 x i64> %2,
+    <vscale x 4 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 4 x i64> %a
+}
+
+declare <vscale x 8 x i64> @llvm.riscv.vrol.nxv8i64.nxv8i64(
+  <vscale x 8 x i64>,
+  <vscale x 8 x i64>,
+  <vscale x 8 x i64>,
+  iXLen)
+
+define <vscale x 8 x i64> @intrinsic_vrol_vv_nxv8i64_nxv8i64(<vscale x 8 x i64> %0, <vscale x 8 x i64> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vrol_vv_nxv8i64_nxv8i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
+; CHECK-NEXT:    vrol.vv v8, v8, v16
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i64> @llvm.riscv.vrol.nxv8i64.nxv8i64(
+    <vscale x 8 x i64> undef,
+    <vscale x 8 x i64> %0,
+    <vscale x 8 x i64> %1,
+    iXLen %2)
+
+  ret <vscale x 8 x i64> %a
+}
+
+declare <vscale x 8 x i64> @llvm.riscv.vrol.mask.nxv8i64.nxv8i64(
+  <vscale x 8 x i64>,
+  <vscale x 8 x i64>,
+  <vscale x 8 x i64>,
+  <vscale x 8 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 8 x i64> @intrinsic_vrol_mask_vv_nxv8i64_nxv8i64(<vscale x 8 x i64> %0, <vscale x 8 x i64> %1, <vscale x 8 x i64> %2, <vscale x 8 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vrol_mask_vv_nxv8i64_nxv8i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vl8re64.v v24, (a0)
+; CHECK-NEXT:    vsetvli zero, a1, e64, m8, ta, mu
+; CHECK-NEXT:    vrol.vv v8, v16, v24, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i64> @llvm.riscv.vrol.mask.nxv8i64.nxv8i64(
+    <vscale x 8 x i64> %0,
+    <vscale x 8 x i64> %1,
+    <vscale x 8 x i64> %2,
+    <vscale x 8 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 8 x i64> %a
+}
+
+declare <vscale x 1 x i8> @llvm.riscv.vrol.nxv1i8.i8(
+  <vscale x 1 x i8>,
+  <vscale x 1 x i8>,
+  i8,
+  iXLen)
+
+define <vscale x 1 x i8> @intrinsic_vrol_vx_nxv1i8_i8(<vscale x 1 x i8> %0, i8 %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vrol_vx_nxv1i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e8, mf8, ta, ma
+; CHECK-NEXT:    vrol.vx v8, v8, a0
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i8> @llvm.riscv.vrol.nxv1i8.i8(
+    <vscale x 1 x i8> undef,
+    <vscale x 1 x i8> %0,
+    i8 %1,
+    iXLen %2)
+
+  ret <vscale x 1 x i8> %a
+}
+
+declare <vscale x 1 x i8> @llvm.riscv.vrol.mask.nxv1i8.i8(
+  <vscale x 1 x i8>,
+  <vscale x 1 x i8>,
+  i8,
+  <vscale x 1 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 1 x i8> @intrinsic_vrol_mask_vx_nxv1i8_i8(<vscale x 1 x i8> %0, <vscale x 1 x i8> %1, i8 %2, <vscale x 1 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vrol_mask_vx_nxv1i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e8, mf8, ta, mu
+; CHECK-NEXT:    vrol.vx v8, v9, a0, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i8> @llvm.riscv.vrol.mask.nxv1i8.i8(
+    <vscale x 1 x i8> %0,
+    <vscale x 1 x i8> %1,
+    i8 %2,
+    <vscale x 1 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 1 x i8> %a
+}
+
+declare <vscale x 2 x i8> @llvm.riscv.vrol.nxv2i8.i8(
+  <vscale x 2 x i8>,
+  <vscale x 2 x i8>,
+  i8,
+  iXLen)
+
+define <vscale x 2 x i8> @intrinsic_vrol_vx_nxv2i8_i8(<vscale x 2 x i8> %0, i8 %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vrol_vx_nxv2i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e8, mf4, ta, ma
+; CHECK-NEXT:    vrol.vx v8, v8, a0
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i8> @llvm.riscv.vrol.nxv2i8.i8(
+    <vscale x 2 x i8> undef,
+    <vscale x 2 x i8> %0,
+    i8 %1,
+    iXLen %2)
+
+  ret <vscale x 2 x i8> %a
+}
+
+declare <vscale x 2 x i8> @llvm.riscv.vrol.mask.nxv2i8.i8(
+  <vscale x 2 x i8>,
+  <vscale x 2 x i8>,
+  i8,
+  <vscale x 2 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 2 x i8> @intrinsic_vrol_mask_vx_nxv2i8_i8(<vscale x 2 x i8> %0, <vscale x 2 x i8> %1, i8 %2, <vscale x 2 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vrol_mask_vx_nxv2i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e8, mf4, ta, mu
+; CHECK-NEXT:    vrol.vx v8, v9, a0, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i8> @llvm.riscv.vrol.mask.nxv2i8.i8(
+    <vscale x 2 x i8> %0,
+    <vscale x 2 x i8> %1,
+    i8 %2,
+    <vscale x 2 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 2 x i8> %a
+}
+
+declare <vscale x 4 x i8> @llvm.riscv.vrol.nxv4i8.i8(
+  <vscale x 4 x i8>,
+  <vscale x 4 x i8>,
+  i8,
+  iXLen)
+
+define <vscale x 4 x i8> @intrinsic_vrol_vx_nxv4i8_i8(<vscale x 4 x i8> %0, i8 %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vrol_vx_nxv4i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e8, mf2, ta, ma
+; CHECK-NEXT:    vrol.vx v8, v8, a0
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i8> @llvm.riscv.vrol.nxv4i8.i8(
+    <vscale x 4 x i8> undef,
+    <vscale x 4 x i8> %0,
+    i8 %1,
+    iXLen %2)
+
+  ret <vscale x 4 x i8> %a
+}
+
+declare <vscale x 4 x i8> @llvm.riscv.vrol.mask.nxv4i8.i8(
+  <vscale x 4 x i8>,
+  <vscale x 4 x i8>,
+  i8,
+  <vscale x 4 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 4 x i8> @intrinsic_vrol_mask_vx_nxv4i8_i8(<vscale x 4 x i8> %0, <vscale x 4 x i8> %1, i8 %2, <vscale x 4 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vrol_mask_vx_nxv4i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e8, mf2, ta, mu
+; CHECK-NEXT:    vrol.vx v8, v9, a0, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i8> @llvm.riscv.vrol.mask.nxv4i8.i8(
+    <vscale x 4 x i8> %0,
+    <vscale x 4 x i8> %1,
+    i8 %2,
+    <vscale x 4 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 4 x i8> %a
+}
+
+declare <vscale x 8 x i8> @llvm.riscv.vrol.nxv8i8.i8(
+  <vscale x 8 x i8>,
+  <vscale x 8 x i8>,
+  i8,
+  iXLen)
+
+define <vscale x 8 x i8> @intrinsic_vrol_vx_nxv8i8_i8(<vscale x 8 x i8> %0, i8 %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vrol_vx_nxv8i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e8, m1, ta, ma
+; CHECK-NEXT:    vrol.vx v8, v8, a0
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i8> @llvm.riscv.vrol.nxv8i8.i8(
+    <vscale x 8 x i8> undef,
+    <vscale x 8 x i8> %0,
+    i8 %1,
+    iXLen %2)
+
+  ret <vscale x 8 x i8> %a
+}
+
+declare <vscale x 8 x i8> @llvm.riscv.vrol.mask.nxv8i8.i8(
+  <vscale x 8 x i8>,
+  <vscale x 8 x i8>,
+  i8,
+  <vscale x 8 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 8 x i8> @intrinsic_vrol_mask_vx_nxv8i8_i8(<vscale x 8 x i8> %0, <vscale x 8 x i8> %1, i8 %2, <vscale x 8 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vrol_mask_vx_nxv8i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e8, m1, ta, mu
+; CHECK-NEXT:    vrol.vx v8, v9, a0, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i8> @llvm.riscv.vrol.mask.nxv8i8.i8(
+    <vscale x 8 x i8> %0,
+    <vscale x 8 x i8> %1,
+    i8 %2,
+    <vscale x 8 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 8 x i8> %a
+}
+
+declare <vscale x 16 x i8> @llvm.riscv.vrol.nxv16i8.i8(
+  <vscale x 16 x i8>,
+  <vscale x 16 x i8>,
+  i8,
+  iXLen)
+
+define <vscale x 16 x i8> @intrinsic_vrol_vx_nxv16i8_i8(<vscale x 16 x i8> %0, i8 %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vrol_vx_nxv16i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e8, m2, ta, ma
+; CHECK-NEXT:    vrol.vx v8, v8, a0
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 16 x i8> @llvm.riscv.vrol.nxv16i8.i8(
+    <vscale x 16 x i8> undef,
+    <vscale x 16 x i8> %0,
+    i8 %1,
+    iXLen %2)
+
+  ret <vscale x 16 x i8> %a
+}
+
+declare <vscale x 16 x i8> @llvm.riscv.vrol.mask.nxv16i8.i8(
+  <vscale x 16 x i8>,
+  <vscale x 16 x i8>,
+  i8,
+  <vscale x 16 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 16 x i8> @intrinsic_vrol_mask_vx_nxv16i8_i8(<vscale x 16 x i8> %0, <vscale x 16 x i8> %1, i8 %2, <vscale x 16 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vrol_mask_vx_nxv16i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e8, m2, ta, mu
+; CHECK-NEXT:    vrol.vx v8, v10, a0, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 16 x i8> @llvm.riscv.vrol.mask.nxv16i8.i8(
+    <vscale x 16 x i8> %0,
+    <vscale x 16 x i8> %1,
+    i8 %2,
+    <vscale x 16 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 16 x i8> %a
+}
+
+declare <vscale x 32 x i8> @llvm.riscv.vrol.nxv32i8.i8(
+  <vscale x 32 x i8>,
+  <vscale x 32 x i8>,
+  i8,
+  iXLen)
+
+define <vscale x 32 x i8> @intrinsic_vrol_vx_nxv32i8_i8(<vscale x 32 x i8> %0, i8 %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vrol_vx_nxv32i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e8, m4, ta, ma
+; CHECK-NEXT:    vrol.vx v8, v8, a0
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 32 x i8> @llvm.riscv.vrol.nxv32i8.i8(
+    <vscale x 32 x i8> undef,
+    <vscale x 32 x i8> %0,
+    i8 %1,
+    iXLen %2)
+
+  ret <vscale x 32 x i8> %a
+}
+
+declare <vscale x 32 x i8> @llvm.riscv.vrol.mask.nxv32i8.i8(
+  <vscale x 32 x i8>,
+  <vscale x 32 x i8>,
+  i8,
+  <vscale x 32 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 32 x i8> @intrinsic_vrol_mask_vx_nxv32i8_i8(<vscale x 32 x i8> %0, <vscale x 32 x i8> %1, i8 %2, <vscale x 32 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vrol_mask_vx_nxv32i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e8, m4, ta, mu
+; CHECK-NEXT:    vrol.vx v8, v12, a0, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 32 x i8> @llvm.riscv.vrol.mask.nxv32i8.i8(
+    <vscale x 32 x i8> %0,
+    <vscale x 32 x i8> %1,
+    i8 %2,
+    <vscale x 32 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 32 x i8> %a
+}
+
+declare <vscale x 64 x i8> @llvm.riscv.vrol.nxv64i8.i8(
+  <vscale x 64 x i8>,
+  <vscale x 64 x i8>,
+  i8,
+  iXLen)
+
+define <vscale x 64 x i8> @intrinsic_vrol_vx_nxv64i8_i8(<vscale x 64 x i8> %0, i8 %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vrol_vx_nxv64i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e8, m8, ta, ma
+; CHECK-NEXT:    vrol.vx v8, v8, a0
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 64 x i8> @llvm.riscv.vrol.nxv64i8.i8(
+    <vscale x 64 x i8> undef,
+    <vscale x 64 x i8> %0,
+    i8 %1,
+    iXLen %2)
+
+  ret <vscale x 64 x i8> %a
+}
+
+declare <vscale x 64 x i8> @llvm.riscv.vrol.mask.nxv64i8.i8(
+  <vscale x 64 x i8>,
+  <vscale x 64 x i8>,
+  i8,
+  <vscale x 64 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 64 x i8> @intrinsic_vrol_mask_vx_nxv64i8_i8(<vscale x 64 x i8> %0, <vscale x 64 x i8> %1, i8 %2, <vscale x 64 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vrol_mask_vx_nxv64i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e8, m8, ta, mu
+; CHECK-NEXT:    vrol.vx v8, v16, a0, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 64 x i8> @llvm.riscv.vrol.mask.nxv64i8.i8(
+    <vscale x 64 x i8> %0,
+    <vscale x 64 x i8> %1,
+    i8 %2,
+    <vscale x 64 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 64 x i8> %a
+}
+
+declare <vscale x 1 x i16> @llvm.riscv.vrol.nxv1i16.i16(
+  <vscale x 1 x i16>,
+  <vscale x 1 x i16>,
+  i16,
+  iXLen)
+
+define <vscale x 1 x i16> @intrinsic_vrol_vx_nxv1i16_i16(<vscale x 1 x i16> %0, i16 %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vrol_vx_nxv1i16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e16, mf4, ta, ma
+; CHECK-NEXT:    vrol.vx v8, v8, a0
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i16> @llvm.riscv.vrol.nxv1i16.i16(
+    <vscale x 1 x i16> undef,
+    <vscale x 1 x i16> %0,
+    i16 %1,
+    iXLen %2)
+
+  ret <vscale x 1 x i16> %a
+}
+
+declare <vscale x 1 x i16> @llvm.riscv.vrol.mask.nxv1i16.i16(
+  <vscale x 1 x i16>,
+  <vscale x 1 x i16>,
+  i16,
+  <vscale x 1 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 1 x i16> @intrinsic_vrol_mask_vx_nxv1i16_i16(<vscale x 1 x i16> %0, <vscale x 1 x i16> %1, i16 %2, <vscale x 1 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vrol_mask_vx_nxv1i16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e16, mf4, ta, mu
+; CHECK-NEXT:    vrol.vx v8, v9, a0, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i16> @llvm.riscv.vrol.mask.nxv1i16.i16(
+    <vscale x 1 x i16> %0,
+    <vscale x 1 x i16> %1,
+    i16 %2,
+    <vscale x 1 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 1 x i16> %a
+}
+
+declare <vscale x 2 x i16> @llvm.riscv.vrol.nxv2i16.i16(
+  <vscale x 2 x i16>,
+  <vscale x 2 x i16>,
+  i16,
+  iXLen)
+
+define <vscale x 2 x i16> @intrinsic_vrol_vx_nxv2i16_i16(<vscale x 2 x i16> %0, i16 %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vrol_vx_nxv2i16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e16, mf2, ta, ma
+; CHECK-NEXT:    vrol.vx v8, v8, a0
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i16> @llvm.riscv.vrol.nxv2i16.i16(
+    <vscale x 2 x i16> undef,
+    <vscale x 2 x i16> %0,
+    i16 %1,
+    iXLen %2)
+
+  ret <vscale x 2 x i16> %a
+}
+
+declare <vscale x 2 x i16> @llvm.riscv.vrol.mask.nxv2i16.i16(
+  <vscale x 2 x i16>,
+  <vscale x 2 x i16>,
+  i16,
+  <vscale x 2 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 2 x i16> @intrinsic_vrol_mask_vx_nxv2i16_i16(<vscale x 2 x i16> %0, <vscale x 2 x i16> %1, i16 %2, <vscale x 2 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vrol_mask_vx_nxv2i16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e16, mf2, ta, mu
+; CHECK-NEXT:    vrol.vx v8, v9, a0, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i16> @llvm.riscv.vrol.mask.nxv2i16.i16(
+    <vscale x 2 x i16> %0,
+    <vscale x 2 x i16> %1,
+    i16 %2,
+    <vscale x 2 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 2 x i16> %a
+}
+
+declare <vscale x 4 x i16> @llvm.riscv.vrol.nxv4i16.i16(
+  <vscale x 4 x i16>,
+  <vscale x 4 x i16>,
+  i16,
+  iXLen)
+
+define <vscale x 4 x i16> @intrinsic_vrol_vx_nxv4i16_i16(<vscale x 4 x i16> %0, i16 %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vrol_vx_nxv4i16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e16, m1, ta, ma
+; CHECK-NEXT:    vrol.vx v8, v8, a0
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i16> @llvm.riscv.vrol.nxv4i16.i16(
+    <vscale x 4 x i16> undef,
+    <vscale x 4 x i16> %0,
+    i16 %1,
+    iXLen %2)
+
+  ret <vscale x 4 x i16> %a
+}
+
+declare <vscale x 4 x i16> @llvm.riscv.vrol.mask.nxv4i16.i16(
+  <vscale x 4 x i16>,
+  <vscale x 4 x i16>,
+  i16,
+  <vscale x 4 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 4 x i16> @intrinsic_vrol_mask_vx_nxv4i16_i16(<vscale x 4 x i16> %0, <vscale x 4 x i16> %1, i16 %2, <vscale x 4 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vrol_mask_vx_nxv4i16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e16, m1, ta, mu
+; CHECK-NEXT:    vrol.vx v8, v9, a0, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i16> @llvm.riscv.vrol.mask.nxv4i16.i16(
+    <vscale x 4 x i16> %0,
+    <vscale x 4 x i16> %1,
+    i16 %2,
+    <vscale x 4 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 4 x i16> %a
+}
+
+declare <vscale x 8 x i16> @llvm.riscv.vrol.nxv8i16.i16(
+  <vscale x 8 x i16>,
+  <vscale x 8 x i16>,
+  i16,
+  iXLen)
+
+define <vscale x 8 x i16> @intrinsic_vrol_vx_nxv8i16_i16(<vscale x 8 x i16> %0, i16 %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vrol_vx_nxv8i16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e16, m2, ta, ma
+; CHECK-NEXT:    vrol.vx v8, v8, a0
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i16> @llvm.riscv.vrol.nxv8i16.i16(
+    <vscale x 8 x i16> undef,
+    <vscale x 8 x i16> %0,
+    i16 %1,
+    iXLen %2)
+
+  ret <vscale x 8 x i16> %a
+}
+
+declare <vscale x 8 x i16> @llvm.riscv.vrol.mask.nxv8i16.i16(
+  <vscale x 8 x i16>,
+  <vscale x 8 x i16>,
+  i16,
+  <vscale x 8 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 8 x i16> @intrinsic_vrol_mask_vx_nxv8i16_i16(<vscale x 8 x i16> %0, <vscale x 8 x i16> %1, i16 %2, <vscale x 8 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vrol_mask_vx_nxv8i16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e16, m2, ta, mu
+; CHECK-NEXT:    vrol.vx v8, v10, a0, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i16> @llvm.riscv.vrol.mask.nxv8i16.i16(
+    <vscale x 8 x i16> %0,
+    <vscale x 8 x i16> %1,
+    i16 %2,
+    <vscale x 8 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 8 x i16> %a
+}
+
+declare <vscale x 16 x i16> @llvm.riscv.vrol.nxv16i16.i16(
+  <vscale x 16 x i16>,
+  <vscale x 16 x i16>,
+  i16,
+  iXLen)
+
+define <vscale x 16 x i16> @intrinsic_vrol_vx_nxv16i16_i16(<vscale x 16 x i16> %0, i16 %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vrol_vx_nxv16i16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e16, m4, ta, ma
+; CHECK-NEXT:    vrol.vx v8, v8, a0
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 16 x i16> @llvm.riscv.vrol.nxv16i16.i16(
+    <vscale x 16 x i16> undef,
+    <vscale x 16 x i16> %0,
+    i16 %1,
+    iXLen %2)
+
+  ret <vscale x 16 x i16> %a
+}
+
+declare <vscale x 16 x i16> @llvm.riscv.vrol.mask.nxv16i16.i16(
+  <vscale x 16 x i16>,
+  <vscale x 16 x i16>,
+  i16,
+  <vscale x 16 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 16 x i16> @intrinsic_vrol_mask_vx_nxv16i16_i16(<vscale x 16 x i16> %0, <vscale x 16 x i16> %1, i16 %2, <vscale x 16 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vrol_mask_vx_nxv16i16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e16, m4, ta, mu
+; CHECK-NEXT:    vrol.vx v8, v12, a0, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 16 x i16> @llvm.riscv.vrol.mask.nxv16i16.i16(
+    <vscale x 16 x i16> %0,
+    <vscale x 16 x i16> %1,
+    i16 %2,
+    <vscale x 16 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 16 x i16> %a
+}
+
+declare <vscale x 32 x i16> @llvm.riscv.vrol.nxv32i16.i16(
+  <vscale x 32 x i16>,
+  <vscale x 32 x i16>,
+  i16,
+  iXLen)
+
+define <vscale x 32 x i16> @intrinsic_vrol_vx_nxv32i16_i16(<vscale x 32 x i16> %0, i16 %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vrol_vx_nxv32i16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e16, m8, ta, ma
+; CHECK-NEXT:    vrol.vx v8, v8, a0
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 32 x i16> @llvm.riscv.vrol.nxv32i16.i16(
+    <vscale x 32 x i16> undef,
+    <vscale x 32 x i16> %0,
+    i16 %1,
+    iXLen %2)
+
+  ret <vscale x 32 x i16> %a
+}
+
+declare <vscale x 32 x i16> @llvm.riscv.vrol.mask.nxv32i16.i16(
+  <vscale x 32 x i16>,
+  <vscale x 32 x i16>,
+  i16,
+  <vscale x 32 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 32 x i16> @intrinsic_vrol_mask_vx_nxv32i16_i16(<vscale x 32 x i16> %0, <vscale x 32 x i16> %1, i16 %2, <vscale x 32 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vrol_mask_vx_nxv32i16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e16, m8, ta, mu
+; CHECK-NEXT:    vrol.vx v8, v16, a0, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 32 x i16> @llvm.riscv.vrol.mask.nxv32i16.i16(
+    <vscale x 32 x i16> %0,
+    <vscale x 32 x i16> %1,
+    i16 %2,
+    <vscale x 32 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 32 x i16> %a
+}
+
+declare <vscale x 1 x i32> @llvm.riscv.vrol.nxv1i32.i32(
+  <vscale x 1 x i32>,
+  <vscale x 1 x i32>,
+  i32,
+  iXLen)
+
+define <vscale x 1 x i32> @intrinsic_vrol_vx_nxv1i32_i32(<vscale x 1 x i32> %0, i32 %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vrol_vx_nxv1i32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e32, mf2, ta, ma
+; CHECK-NEXT:    vrol.vx v8, v8, a0
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i32> @llvm.riscv.vrol.nxv1i32.i32(
+    <vscale x 1 x i32> undef,
+    <vscale x 1 x i32> %0,
+    i32 %1,
+    iXLen %2)
+
+  ret <vscale x 1 x i32> %a
+}
+
+declare <vscale x 1 x i32> @llvm.riscv.vrol.mask.nxv1i32.i32(
+  <vscale x 1 x i32>,
+  <vscale x 1 x i32>,
+  i32,
+  <vscale x 1 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 1 x i32> @intrinsic_vrol_mask_vx_nxv1i32_i32(<vscale x 1 x i32> %0, <vscale x 1 x i32> %1, i32 %2, <vscale x 1 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vrol_mask_vx_nxv1i32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e32, mf2, ta, mu
+; CHECK-NEXT:    vrol.vx v8, v9, a0, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i32> @llvm.riscv.vrol.mask.nxv1i32.i32(
+    <vscale x 1 x i32> %0,
+    <vscale x 1 x i32> %1,
+    i32 %2,
+    <vscale x 1 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 1 x i32> %a
+}
+
+declare <vscale x 2 x i32> @llvm.riscv.vrol.nxv2i32.i32(
+  <vscale x 2 x i32>,
+  <vscale x 2 x i32>,
+  i32,
+  iXLen)
+
+define <vscale x 2 x i32> @intrinsic_vrol_vx_nxv2i32_i32(<vscale x 2 x i32> %0, i32 %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vrol_vx_nxv2i32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e32, m1, ta, ma
+; CHECK-NEXT:    vrol.vx v8, v8, a0
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i32> @llvm.riscv.vrol.nxv2i32.i32(
+    <vscale x 2 x i32> undef,
+    <vscale x 2 x i32> %0,
+    i32 %1,
+    iXLen %2)
+
+  ret <vscale x 2 x i32> %a
+}
+
+declare <vscale x 2 x i32> @llvm.riscv.vrol.mask.nxv2i32.i32(
+  <vscale x 2 x i32>,
+  <vscale x 2 x i32>,
+  i32,
+  <vscale x 2 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 2 x i32> @intrinsic_vrol_mask_vx_nxv2i32_i32(<vscale x 2 x i32> %0, <vscale x 2 x i32> %1, i32 %2, <vscale x 2 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vrol_mask_vx_nxv2i32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e32, m1, ta, mu
+; CHECK-NEXT:    vrol.vx v8, v9, a0, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i32> @llvm.riscv.vrol.mask.nxv2i32.i32(
+    <vscale x 2 x i32> %0,
+    <vscale x 2 x i32> %1,
+    i32 %2,
+    <vscale x 2 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 2 x i32> %a
+}
+
+declare <vscale x 4 x i32> @llvm.riscv.vrol.nxv4i32.i32(
+  <vscale x 4 x i32>,
+  <vscale x 4 x i32>,
+  i32,
+  iXLen)
+
+define <vscale x 4 x i32> @intrinsic_vrol_vx_nxv4i32_i32(<vscale x 4 x i32> %0, i32 %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vrol_vx_nxv4i32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e32, m2, ta, ma
+; CHECK-NEXT:    vrol.vx v8, v8, a0
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i32> @llvm.riscv.vrol.nxv4i32.i32(
+    <vscale x 4 x i32> undef,
+    <vscale x 4 x i32> %0,
+    i32 %1,
+    iXLen %2)
+
+  ret <vscale x 4 x i32> %a
+}
+
+declare <vscale x 4 x i32> @llvm.riscv.vrol.mask.nxv4i32.i32(
+  <vscale x 4 x i32>,
+  <vscale x 4 x i32>,
+  i32,
+  <vscale x 4 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 4 x i32> @intrinsic_vrol_mask_vx_nxv4i32_i32(<vscale x 4 x i32> %0, <vscale x 4 x i32> %1, i32 %2, <vscale x 4 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vrol_mask_vx_nxv4i32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e32, m2, ta, mu
+; CHECK-NEXT:    vrol.vx v8, v10, a0, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i32> @llvm.riscv.vrol.mask.nxv4i32.i32(
+    <vscale x 4 x i32> %0,
+    <vscale x 4 x i32> %1,
+    i32 %2,
+    <vscale x 4 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 4 x i32> %a
+}
+
+declare <vscale x 8 x i32> @llvm.riscv.vrol.nxv8i32.i32(
+  <vscale x 8 x i32>,
+  <vscale x 8 x i32>,
+  i32,
+  iXLen)
+
+define <vscale x 8 x i32> @intrinsic_vrol_vx_nxv8i32_i32(<vscale x 8 x i32> %0, i32 %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vrol_vx_nxv8i32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e32, m4, ta, ma
+; CHECK-NEXT:    vrol.vx v8, v8, a0
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i32> @llvm.riscv.vrol.nxv8i32.i32(
+    <vscale x 8 x i32> undef,
+    <vscale x 8 x i32> %0,
+    i32 %1,
+    iXLen %2)
+
+  ret <vscale x 8 x i32> %a
+}
+
+declare <vscale x 8 x i32> @llvm.riscv.vrol.mask.nxv8i32.i32(
+  <vscale x 8 x i32>,
+  <vscale x 8 x i32>,
+  i32,
+  <vscale x 8 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 8 x i32> @intrinsic_vrol_mask_vx_nxv8i32_i32(<vscale x 8 x i32> %0, <vscale x 8 x i32> %1, i32 %2, <vscale x 8 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vrol_mask_vx_nxv8i32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e32, m4, ta, mu
+; CHECK-NEXT:    vrol.vx v8, v12, a0, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i32> @llvm.riscv.vrol.mask.nxv8i32.i32(
+    <vscale x 8 x i32> %0,
+    <vscale x 8 x i32> %1,
+    i32 %2,
+    <vscale x 8 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 8 x i32> %a
+}
+
+declare <vscale x 16 x i32> @llvm.riscv.vrol.nxv16i32.i32(
+  <vscale x 16 x i32>,
+  <vscale x 16 x i32>,
+  i32,
+  iXLen)
+
+define <vscale x 16 x i32> @intrinsic_vrol_vx_nxv16i32_i32(<vscale x 16 x i32> %0, i32 %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vrol_vx_nxv16i32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e32, m8, ta, ma
+; CHECK-NEXT:    vrol.vx v8, v8, a0
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 16 x i32> @llvm.riscv.vrol.nxv16i32.i32(
+    <vscale x 16 x i32> undef,
+    <vscale x 16 x i32> %0,
+    i32 %1,
+    iXLen %2)
+
+  ret <vscale x 16 x i32> %a
+}
+
+declare <vscale x 16 x i32> @llvm.riscv.vrol.mask.nxv16i32.i32(
+  <vscale x 16 x i32>,
+  <vscale x 16 x i32>,
+  i32,
+  <vscale x 16 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 16 x i32> @intrinsic_vrol_mask_vx_nxv16i32_i32(<vscale x 16 x i32> %0, <vscale x 16 x i32> %1, i32 %2, <vscale x 16 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vrol_mask_vx_nxv16i32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e32, m8, ta, mu
+; CHECK-NEXT:    vrol.vx v8, v16, a0, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 16 x i32> @llvm.riscv.vrol.mask.nxv16i32.i32(
+    <vscale x 16 x i32> %0,
+    <vscale x 16 x i32> %1,
+    i32 %2,
+    <vscale x 16 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 16 x i32> %a
+}
+
+declare <vscale x 1 x i64> @llvm.riscv.vrol.nxv1i64.i64(
+  <vscale x 1 x i64>,
+  <vscale x 1 x i64>,
+  i64,
+  iXLen)
+
+define <vscale x 1 x i64> @intrinsic_vrol_vx_nxv1i64_i64(<vscale x 1 x i64> %0, i64 %1, iXLen %2) nounwind {
+; RV32-LABEL: intrinsic_vrol_vx_nxv1i64_i64:
+; RV32:       # %bb.0: # %entry
+; RV32-NEXT:    addi sp, sp, -16
+; RV32-NEXT:    sw a1, 12(sp)
+; RV32-NEXT:    sw a0, 8(sp)
+; RV32-NEXT:    addi a0, sp, 8
+; RV32-NEXT:    vsetvli zero, a2, e64, m1, ta, ma
+; RV32-NEXT:    vlse64.v v9, (a0), zero
+; RV32-NEXT:    vrol.vv v8, v8, v9
+; RV32-NEXT:    addi sp, sp, 16
+; RV32-NEXT:    ret
+;
+; RV64-LABEL: intrinsic_vrol_vx_nxv1i64_i64:
+; RV64:       # %bb.0: # %entry
+; RV64-NEXT:    vsetvli zero, a1, e64, m1, ta, ma
+; RV64-NEXT:    vrol.vx v8, v8, a0
+; RV64-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i64> @llvm.riscv.vrol.nxv1i64.i64(
+    <vscale x 1 x i64> undef,
+    <vscale x 1 x i64> %0,
+    i64 %1,
+    iXLen %2)
+
+  ret <vscale x 1 x i64> %a
+}
+
+declare <vscale x 1 x i64> @llvm.riscv.vrol.mask.nxv1i64.i64(
+  <vscale x 1 x i64>,
+  <vscale x 1 x i64>,
+  i64,
+  <vscale x 1 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 1 x i64> @intrinsic_vrol_mask_vx_nxv1i64_i64(<vscale x 1 x i64> %0, <vscale x 1 x i64> %1, i64 %2, <vscale x 1 x i1> %3, iXLen %4) nounwind {
+; RV32-LABEL: intrinsic_vrol_mask_vx_nxv1i64_i64:
+; RV32:       # %bb.0: # %entry
+; RV32-NEXT:    addi sp, sp, -16
+; RV32-NEXT:    sw a1, 12(sp)
+; RV32-NEXT:    sw a0, 8(sp)
+; RV32-NEXT:    addi a0, sp, 8
+; RV32-NEXT:    vsetvli zero, a2, e64, m1, ta, mu
+; RV32-NEXT:    vlse64.v v10, (a0), zero
+; RV32-NEXT:    vrol.vv v8, v9, v10, v0.t
+; RV32-NEXT:    addi sp, sp, 16
+; RV32-NEXT:    ret
+;
+; RV64-LABEL: intrinsic_vrol_mask_vx_nxv1i64_i64:
+; RV64:       # %bb.0: # %entry
+; RV64-NEXT:    vsetvli zero, a1, e64, m1, ta, mu
+; RV64-NEXT:    vrol.vx v8, v9, a0, v0.t
+; RV64-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i64> @llvm.riscv.vrol.mask.nxv1i64.i64(
+    <vscale x 1 x i64> %0,
+    <vscale x 1 x i64> %1,
+    i64 %2,
+    <vscale x 1 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 1 x i64> %a
+}
+
+declare <vscale x 2 x i64> @llvm.riscv.vrol.nxv2i64.i64(
+  <vscale x 2 x i64>,
+  <vscale x 2 x i64>,
+  i64,
+  iXLen)
+
+define <vscale x 2 x i64> @intrinsic_vrol_vx_nxv2i64_i64(<vscale x 2 x i64> %0, i64 %1, iXLen %2) nounwind {
+; RV32-LABEL: intrinsic_vrol_vx_nxv2i64_i64:
+; RV32:       # %bb.0: # %entry
+; RV32-NEXT:    addi sp, sp, -16
+; RV32-NEXT:    sw a1, 12(sp)
+; RV32-NEXT:    sw a0, 8(sp)
+; RV32-NEXT:    addi a0, sp, 8
+; RV32-NEXT:    vsetvli zero, a2, e64, m2, ta, ma
+; RV32-NEXT:    vlse64.v v10, (a0), zero
+; RV32-NEXT:    vrol.vv v8, v8, v10
+; RV32-NEXT:    addi sp, sp, 16
+; RV32-NEXT:    ret
+;
+; RV64-LABEL: intrinsic_vrol_vx_nxv2i64_i64:
+; RV64:       # %bb.0: # %entry
+; RV64-NEXT:    vsetvli zero, a1, e64, m2, ta, ma
+; RV64-NEXT:    vrol.vx v8, v8, a0
+; RV64-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i64> @llvm.riscv.vrol.nxv2i64.i64(
+    <vscale x 2 x i64> undef,
+    <vscale x 2 x i64> %0,
+    i64 %1,
+    iXLen %2)
+
+  ret <vscale x 2 x i64> %a
+}
+
+declare <vscale x 2 x i64> @llvm.riscv.vrol.mask.nxv2i64.i64(
+  <vscale x 2 x i64>,
+  <vscale x 2 x i64>,
+  i64,
+  <vscale x 2 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 2 x i64> @intrinsic_vrol_mask_vx_nxv2i64_i64(<vscale x 2 x i64> %0, <vscale x 2 x i64> %1, i64 %2, <vscale x 2 x i1> %3, iXLen %4) nounwind {
+; RV32-LABEL: intrinsic_vrol_mask_vx_nxv2i64_i64:
+; RV32:       # %bb.0: # %entry
+; RV32-NEXT:    addi sp, sp, -16
+; RV32-NEXT:    sw a1, 12(sp)
+; RV32-NEXT:    sw a0, 8(sp)
+; RV32-NEXT:    addi a0, sp, 8
+; RV32-NEXT:    vsetvli zero, a2, e64, m2, ta, mu
+; RV32-NEXT:    vlse64.v v12, (a0), zero
+; RV32-NEXT:    vrol.vv v8, v10, v12, v0.t
+; RV32-NEXT:    addi sp, sp, 16
+; RV32-NEXT:    ret
+;
+; RV64-LABEL: intrinsic_vrol_mask_vx_nxv2i64_i64:
+; RV64:       # %bb.0: # %entry
+; RV64-NEXT:    vsetvli zero, a1, e64, m2, ta, mu
+; RV64-NEXT:    vrol.vx v8, v10, a0, v0.t
+; RV64-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i64> @llvm.riscv.vrol.mask.nxv2i64.i64(
+    <vscale x 2 x i64> %0,
+    <vscale x 2 x i64> %1,
+    i64 %2,
+    <vscale x 2 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 2 x i64> %a
+}
+
+declare <vscale x 4 x i64> @llvm.riscv.vrol.nxv4i64.i64(
+  <vscale x 4 x i64>,
+  <vscale x 4 x i64>,
+  i64,
+  iXLen)
+
+define <vscale x 4 x i64> @intrinsic_vrol_vx_nxv4i64_i64(<vscale x 4 x i64> %0, i64 %1, iXLen %2) nounwind {
+; RV32-LABEL: intrinsic_vrol_vx_nxv4i64_i64:
+; RV32:       # %bb.0: # %entry
+; RV32-NEXT:    addi sp, sp, -16
+; RV32-NEXT:    sw a1, 12(sp)
+; RV32-NEXT:    sw a0, 8(sp)
+; RV32-NEXT:    addi a0, sp, 8
+; RV32-NEXT:    vsetvli zero, a2, e64, m4, ta, ma
+; RV32-NEXT:    vlse64.v v12, (a0), zero
+; RV32-NEXT:    vrol.vv v8, v8, v12
+; RV32-NEXT:    addi sp, sp, 16
+; RV32-NEXT:    ret
+;
+; RV64-LABEL: intrinsic_vrol_vx_nxv4i64_i64:
+; RV64:       # %bb.0: # %entry
+; RV64-NEXT:    vsetvli zero, a1, e64, m4, ta, ma
+; RV64-NEXT:    vrol.vx v8, v8, a0
+; RV64-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i64> @llvm.riscv.vrol.nxv4i64.i64(
+    <vscale x 4 x i64> undef,
+    <vscale x 4 x i64> %0,
+    i64 %1,
+    iXLen %2)
+
+  ret <vscale x 4 x i64> %a
+}
+
+declare <vscale x 4 x i64> @llvm.riscv.vrol.mask.nxv4i64.i64(
+  <vscale x 4 x i64>,
+  <vscale x 4 x i64>,
+  i64,
+  <vscale x 4 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 4 x i64> @intrinsic_vrol_mask_vx_nxv4i64_i64(<vscale x 4 x i64> %0, <vscale x 4 x i64> %1, i64 %2, <vscale x 4 x i1> %3, iXLen %4) nounwind {
+; RV32-LABEL: intrinsic_vrol_mask_vx_nxv4i64_i64:
+; RV32:       # %bb.0: # %entry
+; RV32-NEXT:    addi sp, sp, -16
+; RV32-NEXT:    sw a1, 12(sp)
+; RV32-NEXT:    sw a0, 8(sp)
+; RV32-NEXT:    addi a0, sp, 8
+; RV32-NEXT:    vsetvli zero, a2, e64, m4, ta, mu
+; RV32-NEXT:    vlse64.v v16, (a0), zero
+; RV32-NEXT:    vrol.vv v8, v12, v16, v0.t
+; RV32-NEXT:    addi sp, sp, 16
+; RV32-NEXT:    ret
+;
+; RV64-LABEL: intrinsic_vrol_mask_vx_nxv4i64_i64:
+; RV64:       # %bb.0: # %entry
+; RV64-NEXT:    vsetvli zero, a1, e64, m4, ta, mu
+; RV64-NEXT:    vrol.vx v8, v12, a0, v0.t
+; RV64-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i64> @llvm.riscv.vrol.mask.nxv4i64.i64(
+    <vscale x 4 x i64> %0,
+    <vscale x 4 x i64> %1,
+    i64 %2,
+    <vscale x 4 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 4 x i64> %a
+}
+
+declare <vscale x 8 x i64> @llvm.riscv.vrol.nxv8i64.i64(
+  <vscale x 8 x i64>,
+  <vscale x 8 x i64>,
+  i64,
+  iXLen)
+
+define <vscale x 8 x i64> @intrinsic_vrol_vx_nxv8i64_i64(<vscale x 8 x i64> %0, i64 %1, iXLen %2) nounwind {
+; RV32-LABEL: intrinsic_vrol_vx_nxv8i64_i64:
+; RV32:       # %bb.0: # %entry
+; RV32-NEXT:    addi sp, sp, -16
+; RV32-NEXT:    sw a1, 12(sp)
+; RV32-NEXT:    sw a0, 8(sp)
+; RV32-NEXT:    addi a0, sp, 8
+; RV32-NEXT:    vsetvli zero, a2, e64, m8, ta, ma
+; RV32-NEXT:    vlse64.v v16, (a0), zero
+; RV32-NEXT:    vrol.vv v8, v8, v16
+; RV32-NEXT:    addi sp, sp, 16
+; RV32-NEXT:    ret
+;
+; RV64-LABEL: intrinsic_vrol_vx_nxv8i64_i64:
+; RV64:       # %bb.0: # %entry
+; RV64-NEXT:    vsetvli zero, a1, e64, m8, ta, ma
+; RV64-NEXT:    vrol.vx v8, v8, a0
+; RV64-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i64> @llvm.riscv.vrol.nxv8i64.i64(
+    <vscale x 8 x i64> undef,
+    <vscale x 8 x i64> %0,
+    i64 %1,
+    iXLen %2)
+
+  ret <vscale x 8 x i64> %a
+}
+
+declare <vscale x 8 x i64> @llvm.riscv.vrol.mask.nxv8i64.i64(
+  <vscale x 8 x i64>,
+  <vscale x 8 x i64>,
+  i64,
+  <vscale x 8 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 8 x i64> @intrinsic_vrol_mask_vx_nxv8i64_i64(<vscale x 8 x i64> %0, <vscale x 8 x i64> %1, i64 %2, <vscale x 8 x i1> %3, iXLen %4) nounwind {
+; RV32-LABEL: intrinsic_vrol_mask_vx_nxv8i64_i64:
+; RV32:       # %bb.0: # %entry
+; RV32-NEXT:    addi sp, sp, -16
+; RV32-NEXT:    sw a1, 12(sp)
+; RV32-NEXT:    sw a0, 8(sp)
+; RV32-NEXT:    addi a0, sp, 8
+; RV32-NEXT:    vsetvli zero, a2, e64, m8, ta, mu
+; RV32-NEXT:    vlse64.v v24, (a0), zero
+; RV32-NEXT:    vrol.vv v8, v16, v24, v0.t
+; RV32-NEXT:    addi sp, sp, 16
+; RV32-NEXT:    ret
+;
+; RV64-LABEL: intrinsic_vrol_mask_vx_nxv8i64_i64:
+; RV64:       # %bb.0: # %entry
+; RV64-NEXT:    vsetvli zero, a1, e64, m8, ta, mu
+; RV64-NEXT:    vrol.vx v8, v16, a0, v0.t
+; RV64-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i64> @llvm.riscv.vrol.mask.nxv8i64.i64(
+    <vscale x 8 x i64> %0,
+    <vscale x 8 x i64> %1,
+    i64 %2,
+    <vscale x 8 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 8 x i64> %a
+}

llvm/test/CodeGen/RISCV/rvv/vror.ll

+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: sed 's/iXLen/i32/g' %s | llc -mtriple=riscv32 -mattr=+v,+experimental-zvbb \
+; RUN:   -verify-machineinstrs | FileCheck %s --check-prefixes=CHECK,RV32
+; RUN: sed 's/iXLen/i64/g' %s | llc -mtriple=riscv64 -mattr=+v,+experimental-zvbb \
+; RUN:   -verify-machineinstrs | FileCheck %s --check-prefixes=CHECK,RV64
+
+declare <vscale x 1 x i8> @llvm.riscv.vror.nxv1i8.nxv1i8(
+  <vscale x 1 x i8>,
+  <vscale x 1 x i8>,
+  <vscale x 1 x i8>,
+  iXLen)
+
+define <vscale x 1 x i8> @intrinsic_vror_vv_nxv1i8_nxv1i8(<vscale x 1 x i8> %0, <vscale x 1 x i8> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vror_vv_nxv1i8_nxv1i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, mf8, ta, ma
+; CHECK-NEXT:    vror.vv v8, v8, v9
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i8> @llvm.riscv.vror.nxv1i8.nxv1i8(
+    <vscale x 1 x i8> undef,
+    <vscale x 1 x i8> %0,
+    <vscale x 1 x i8> %1,
+    iXLen %2)
+
+  ret <vscale x 1 x i8> %a
+}
+
+declare <vscale x 1 x i8> @llvm.riscv.vror.mask.nxv1i8.nxv1i8(
+  <vscale x 1 x i8>,
+  <vscale x 1 x i8>,
+  <vscale x 1 x i8>,
+  <vscale x 1 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 1 x i8> @intrinsic_vror_mask_vv_nxv1i8_nxv1i8(<vscale x 1 x i8> %0, <vscale x 1 x i8> %1, <vscale x 1 x i8> %2, <vscale x 1 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vror_mask_vv_nxv1i8_nxv1i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, mf8, ta, mu
+; CHECK-NEXT:    vror.vv v8, v9, v10, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i8> @llvm.riscv.vror.mask.nxv1i8.nxv1i8(
+    <vscale x 1 x i8> %0,
+    <vscale x 1 x i8> %1,
+    <vscale x 1 x i8> %2,
+    <vscale x 1 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 1 x i8> %a
+}
+
+declare <vscale x 2 x i8> @llvm.riscv.vror.nxv2i8.nxv2i8(
+  <vscale x 2 x i8>,
+  <vscale x 2 x i8>,
+  <vscale x 2 x i8>,
+  iXLen)
+
+define <vscale x 2 x i8> @intrinsic_vror_vv_nxv2i8_nxv2i8(<vscale x 2 x i8> %0, <vscale x 2 x i8> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vror_vv_nxv2i8_nxv2i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, mf4, ta, ma
+; CHECK-NEXT:    vror.vv v8, v8, v9
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i8> @llvm.riscv.vror.nxv2i8.nxv2i8(
+    <vscale x 2 x i8> undef,
+    <vscale x 2 x i8> %0,
+    <vscale x 2 x i8> %1,
+    iXLen %2)
+
+  ret <vscale x 2 x i8> %a
+}
+
+declare <vscale x 2 x i8> @llvm.riscv.vror.mask.nxv2i8.nxv2i8(
+  <vscale x 2 x i8>,
+  <vscale x 2 x i8>,
+  <vscale x 2 x i8>,
+  <vscale x 2 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 2 x i8> @intrinsic_vror_mask_vv_nxv2i8_nxv2i8(<vscale x 2 x i8> %0, <vscale x 2 x i8> %1, <vscale x 2 x i8> %2, <vscale x 2 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vror_mask_vv_nxv2i8_nxv2i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, mf4, ta, mu
+; CHECK-NEXT:    vror.vv v8, v9, v10, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i8> @llvm.riscv.vror.mask.nxv2i8.nxv2i8(
+    <vscale x 2 x i8> %0,
+    <vscale x 2 x i8> %1,
+    <vscale x 2 x i8> %2,
+    <vscale x 2 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 2 x i8> %a
+}
+
+declare <vscale x 4 x i8> @llvm.riscv.vror.nxv4i8.nxv4i8(
+  <vscale x 4 x i8>,
+  <vscale x 4 x i8>,
+  <vscale x 4 x i8>,
+  iXLen)
+
+define <vscale x 4 x i8> @intrinsic_vror_vv_nxv4i8_nxv4i8(<vscale x 4 x i8> %0, <vscale x 4 x i8> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vror_vv_nxv4i8_nxv4i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, mf2, ta, ma
+; CHECK-NEXT:    vror.vv v8, v8, v9
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i8> @llvm.riscv.vror.nxv4i8.nxv4i8(
+    <vscale x 4 x i8> undef,
+    <vscale x 4 x i8> %0,
+    <vscale x 4 x i8> %1,
+    iXLen %2)
+
+  ret <vscale x 4 x i8> %a
+}
+
+declare <vscale x 4 x i8> @llvm.riscv.vror.mask.nxv4i8.nxv4i8(
+  <vscale x 4 x i8>,
+  <vscale x 4 x i8>,
+  <vscale x 4 x i8>,
+  <vscale x 4 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 4 x i8> @intrinsic_vror_mask_vv_nxv4i8_nxv4i8(<vscale x 4 x i8> %0, <vscale x 4 x i8> %1, <vscale x 4 x i8> %2, <vscale x 4 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vror_mask_vv_nxv4i8_nxv4i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, mf2, ta, mu
+; CHECK-NEXT:    vror.vv v8, v9, v10, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i8> @llvm.riscv.vror.mask.nxv4i8.nxv4i8(
+    <vscale x 4 x i8> %0,
+    <vscale x 4 x i8> %1,
+    <vscale x 4 x i8> %2,
+    <vscale x 4 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 4 x i8> %a
+}
+
+declare <vscale x 8 x i8> @llvm.riscv.vror.nxv8i8.nxv8i8(
+  <vscale x 8 x i8>,
+  <vscale x 8 x i8>,
+  <vscale x 8 x i8>,
+  iXLen)
+
+define <vscale x 8 x i8> @intrinsic_vror_vv_nxv8i8_nxv8i8(<vscale x 8 x i8> %0, <vscale x 8 x i8> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vror_vv_nxv8i8_nxv8i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, m1, ta, ma
+; CHECK-NEXT:    vror.vv v8, v8, v9
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i8> @llvm.riscv.vror.nxv8i8.nxv8i8(
+    <vscale x 8 x i8> undef,
+    <vscale x 8 x i8> %0,
+    <vscale x 8 x i8> %1,
+    iXLen %2)
+
+  ret <vscale x 8 x i8> %a
+}
+
+declare <vscale x 8 x i8> @llvm.riscv.vror.mask.nxv8i8.nxv8i8(
+  <vscale x 8 x i8>,
+  <vscale x 8 x i8>,
+  <vscale x 8 x i8>,
+  <vscale x 8 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 8 x i8> @intrinsic_vror_mask_vv_nxv8i8_nxv8i8(<vscale x 8 x i8> %0, <vscale x 8 x i8> %1, <vscale x 8 x i8> %2, <vscale x 8 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vror_mask_vv_nxv8i8_nxv8i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, m1, ta, mu
+; CHECK-NEXT:    vror.vv v8, v9, v10, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i8> @llvm.riscv.vror.mask.nxv8i8.nxv8i8(
+    <vscale x 8 x i8> %0,
+    <vscale x 8 x i8> %1,
+    <vscale x 8 x i8> %2,
+    <vscale x 8 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 8 x i8> %a
+}
+
+declare <vscale x 16 x i8> @llvm.riscv.vror.nxv16i8.nxv16i8(
+  <vscale x 16 x i8>,
+  <vscale x 16 x i8>,
+  <vscale x 16 x i8>,
+  iXLen)
+
+define <vscale x 16 x i8> @intrinsic_vror_vv_nxv16i8_nxv16i8(<vscale x 16 x i8> %0, <vscale x 16 x i8> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vror_vv_nxv16i8_nxv16i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, m2, ta, ma
+; CHECK-NEXT:    vror.vv v8, v8, v10
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 16 x i8> @llvm.riscv.vror.nxv16i8.nxv16i8(
+    <vscale x 16 x i8> undef,
+    <vscale x 16 x i8> %0,
+    <vscale x 16 x i8> %1,
+    iXLen %2)
+
+  ret <vscale x 16 x i8> %a
+}
+
+declare <vscale x 16 x i8> @llvm.riscv.vror.mask.nxv16i8.nxv16i8(
+  <vscale x 16 x i8>,
+  <vscale x 16 x i8>,
+  <vscale x 16 x i8>,
+  <vscale x 16 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 16 x i8> @intrinsic_vror_mask_vv_nxv16i8_nxv16i8(<vscale x 16 x i8> %0, <vscale x 16 x i8> %1, <vscale x 16 x i8> %2, <vscale x 16 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vror_mask_vv_nxv16i8_nxv16i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, m2, ta, mu
+; CHECK-NEXT:    vror.vv v8, v10, v12, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 16 x i8> @llvm.riscv.vror.mask.nxv16i8.nxv16i8(
+    <vscale x 16 x i8> %0,
+    <vscale x 16 x i8> %1,
+    <vscale x 16 x i8> %2,
+    <vscale x 16 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 16 x i8> %a
+}
+
+declare <vscale x 32 x i8> @llvm.riscv.vror.nxv32i8.nxv32i8(
+  <vscale x 32 x i8>,
+  <vscale x 32 x i8>,
+  <vscale x 32 x i8>,
+  iXLen)
+
+define <vscale x 32 x i8> @intrinsic_vror_vv_nxv32i8_nxv32i8(<vscale x 32 x i8> %0, <vscale x 32 x i8> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vror_vv_nxv32i8_nxv32i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, m4, ta, ma
+; CHECK-NEXT:    vror.vv v8, v8, v12
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 32 x i8> @llvm.riscv.vror.nxv32i8.nxv32i8(
+    <vscale x 32 x i8> undef,
+    <vscale x 32 x i8> %0,
+    <vscale x 32 x i8> %1,
+    iXLen %2)
+
+  ret <vscale x 32 x i8> %a
+}
+
+declare <vscale x 32 x i8> @llvm.riscv.vror.mask.nxv32i8.nxv32i8(
+  <vscale x 32 x i8>,
+  <vscale x 32 x i8>,
+  <vscale x 32 x i8>,
+  <vscale x 32 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 32 x i8> @intrinsic_vror_mask_vv_nxv32i8_nxv32i8(<vscale x 32 x i8> %0, <vscale x 32 x i8> %1, <vscale x 32 x i8> %2, <vscale x 32 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vror_mask_vv_nxv32i8_nxv32i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, m4, ta, mu
+; CHECK-NEXT:    vror.vv v8, v12, v16, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 32 x i8> @llvm.riscv.vror.mask.nxv32i8.nxv32i8(
+    <vscale x 32 x i8> %0,
+    <vscale x 32 x i8> %1,
+    <vscale x 32 x i8> %2,
+    <vscale x 32 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 32 x i8> %a
+}
+
+declare <vscale x 64 x i8> @llvm.riscv.vror.nxv64i8.nxv64i8(
+  <vscale x 64 x i8>,
+  <vscale x 64 x i8>,
+  <vscale x 64 x i8>,
+  iXLen)
+
+define <vscale x 64 x i8> @intrinsic_vror_vv_nxv64i8_nxv64i8(<vscale x 64 x i8> %0, <vscale x 64 x i8> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vror_vv_nxv64i8_nxv64i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, m8, ta, ma
+; CHECK-NEXT:    vror.vv v8, v8, v16
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 64 x i8> @llvm.riscv.vror.nxv64i8.nxv64i8(
+    <vscale x 64 x i8> undef,
+    <vscale x 64 x i8> %0,
+    <vscale x 64 x i8> %1,
+    iXLen %2)
+
+  ret <vscale x 64 x i8> %a
+}
+
+declare <vscale x 64 x i8> @llvm.riscv.vror.mask.nxv64i8.nxv64i8(
+  <vscale x 64 x i8>,
+  <vscale x 64 x i8>,
+  <vscale x 64 x i8>,
+  <vscale x 64 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 64 x i8> @intrinsic_vror_mask_vv_nxv64i8_nxv64i8(<vscale x 64 x i8> %0, <vscale x 64 x i8> %1, <vscale x 64 x i8> %2, <vscale x 64 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vror_mask_vv_nxv64i8_nxv64i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vl8r.v v24, (a0)
+; CHECK-NEXT:    vsetvli zero, a1, e8, m8, ta, mu
+; CHECK-NEXT:    vror.vv v8, v16, v24, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 64 x i8> @llvm.riscv.vror.mask.nxv64i8.nxv64i8(
+    <vscale x 64 x i8> %0,
+    <vscale x 64 x i8> %1,
+    <vscale x 64 x i8> %2,
+    <vscale x 64 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 64 x i8> %a
+}
+
+declare <vscale x 1 x i16> @llvm.riscv.vror.nxv1i16.nxv1i16(
+  <vscale x 1 x i16>,
+  <vscale x 1 x i16>,
+  <vscale x 1 x i16>,
+  iXLen)
+
+define <vscale x 1 x i16> @intrinsic_vror_vv_nxv1i16_nxv1i16(<vscale x 1 x i16> %0, <vscale x 1 x i16> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vror_vv_nxv1i16_nxv1i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, mf4, ta, ma
+; CHECK-NEXT:    vror.vv v8, v8, v9
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i16> @llvm.riscv.vror.nxv1i16.nxv1i16(
+    <vscale x 1 x i16> undef,
+    <vscale x 1 x i16> %0,
+    <vscale x 1 x i16> %1,
+    iXLen %2)
+
+  ret <vscale x 1 x i16> %a
+}
+
+declare <vscale x 1 x i16> @llvm.riscv.vror.mask.nxv1i16.nxv1i16(
+  <vscale x 1 x i16>,
+  <vscale x 1 x i16>,
+  <vscale x 1 x i16>,
+  <vscale x 1 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 1 x i16> @intrinsic_vror_mask_vv_nxv1i16_nxv1i16(<vscale x 1 x i16> %0, <vscale x 1 x i16> %1, <vscale x 1 x i16> %2, <vscale x 1 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vror_mask_vv_nxv1i16_nxv1i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, mf4, ta, mu
+; CHECK-NEXT:    vror.vv v8, v9, v10, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i16> @llvm.riscv.vror.mask.nxv1i16.nxv1i16(
+    <vscale x 1 x i16> %0,
+    <vscale x 1 x i16> %1,
+    <vscale x 1 x i16> %2,
+    <vscale x 1 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 1 x i16> %a
+}
+
+declare <vscale x 2 x i16> @llvm.riscv.vror.nxv2i16.nxv2i16(
+  <vscale x 2 x i16>,
+  <vscale x 2 x i16>,
+  <vscale x 2 x i16>,
+  iXLen)
+
+define <vscale x 2 x i16> @intrinsic_vror_vv_nxv2i16_nxv2i16(<vscale x 2 x i16> %0, <vscale x 2 x i16> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vror_vv_nxv2i16_nxv2i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, mf2, ta, ma
+; CHECK-NEXT:    vror.vv v8, v8, v9
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i16> @llvm.riscv.vror.nxv2i16.nxv2i16(
+    <vscale x 2 x i16> undef,
+    <vscale x 2 x i16> %0,
+    <vscale x 2 x i16> %1,
+    iXLen %2)
+
+  ret <vscale x 2 x i16> %a
+}
+
+declare <vscale x 2 x i16> @llvm.riscv.vror.mask.nxv2i16.nxv2i16(
+  <vscale x 2 x i16>,
+  <vscale x 2 x i16>,
+  <vscale x 2 x i16>,
+  <vscale x 2 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 2 x i16> @intrinsic_vror_mask_vv_nxv2i16_nxv2i16(<vscale x 2 x i16> %0, <vscale x 2 x i16> %1, <vscale x 2 x i16> %2, <vscale x 2 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vror_mask_vv_nxv2i16_nxv2i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, mf2, ta, mu
+; CHECK-NEXT:    vror.vv v8, v9, v10, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i16> @llvm.riscv.vror.mask.nxv2i16.nxv2i16(
+    <vscale x 2 x i16> %0,
+    <vscale x 2 x i16> %1,
+    <vscale x 2 x i16> %2,
+    <vscale x 2 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 2 x i16> %a
+}
+
+declare <vscale x 4 x i16> @llvm.riscv.vror.nxv4i16.nxv4i16(
+  <vscale x 4 x i16>,
+  <vscale x 4 x i16>,
+  <vscale x 4 x i16>,
+  iXLen)
+
+define <vscale x 4 x i16> @intrinsic_vror_vv_nxv4i16_nxv4i16(<vscale x 4 x i16> %0, <vscale x 4 x i16> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vror_vv_nxv4i16_nxv4i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, m1, ta, ma
+; CHECK-NEXT:    vror.vv v8, v8, v9
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i16> @llvm.riscv.vror.nxv4i16.nxv4i16(
+    <vscale x 4 x i16> undef,
+    <vscale x 4 x i16> %0,
+    <vscale x 4 x i16> %1,
+    iXLen %2)
+
+  ret <vscale x 4 x i16> %a
+}
+
+declare <vscale x 4 x i16> @llvm.riscv.vror.mask.nxv4i16.nxv4i16(
+  <vscale x 4 x i16>,
+  <vscale x 4 x i16>,
+  <vscale x 4 x i16>,
+  <vscale x 4 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 4 x i16> @intrinsic_vror_mask_vv_nxv4i16_nxv4i16(<vscale x 4 x i16> %0, <vscale x 4 x i16> %1, <vscale x 4 x i16> %2, <vscale x 4 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vror_mask_vv_nxv4i16_nxv4i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, m1, ta, mu
+; CHECK-NEXT:    vror.vv v8, v9, v10, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i16> @llvm.riscv.vror.mask.nxv4i16.nxv4i16(
+    <vscale x 4 x i16> %0,
+    <vscale x 4 x i16> %1,
+    <vscale x 4 x i16> %2,
+    <vscale x 4 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 4 x i16> %a
+}
+
+declare <vscale x 8 x i16> @llvm.riscv.vror.nxv8i16.nxv8i16(
+  <vscale x 8 x i16>,
+  <vscale x 8 x i16>,
+  <vscale x 8 x i16>,
+  iXLen)
+
+define <vscale x 8 x i16> @intrinsic_vror_vv_nxv8i16_nxv8i16(<vscale x 8 x i16> %0, <vscale x 8 x i16> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vror_vv_nxv8i16_nxv8i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, m2, ta, ma
+; CHECK-NEXT:    vror.vv v8, v8, v10
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i16> @llvm.riscv.vror.nxv8i16.nxv8i16(
+    <vscale x 8 x i16> undef,
+    <vscale x 8 x i16> %0,
+    <vscale x 8 x i16> %1,
+    iXLen %2)
+
+  ret <vscale x 8 x i16> %a
+}
+
+declare <vscale x 8 x i16> @llvm.riscv.vror.mask.nxv8i16.nxv8i16(
+  <vscale x 8 x i16>,
+  <vscale x 8 x i16>,
+  <vscale x 8 x i16>,
+  <vscale x 8 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 8 x i16> @intrinsic_vror_mask_vv_nxv8i16_nxv8i16(<vscale x 8 x i16> %0, <vscale x 8 x i16> %1, <vscale x 8 x i16> %2, <vscale x 8 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vror_mask_vv_nxv8i16_nxv8i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, m2, ta, mu
+; CHECK-NEXT:    vror.vv v8, v10, v12, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i16> @llvm.riscv.vror.mask.nxv8i16.nxv8i16(
+    <vscale x 8 x i16> %0,
+    <vscale x 8 x i16> %1,
+    <vscale x 8 x i16> %2,
+    <vscale x 8 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 8 x i16> %a
+}
+
+declare <vscale x 16 x i16> @llvm.riscv.vror.nxv16i16.nxv16i16(
+  <vscale x 16 x i16>,
+  <vscale x 16 x i16>,
+  <vscale x 16 x i16>,
+  iXLen)
+
+define <vscale x 16 x i16> @intrinsic_vror_vv_nxv16i16_nxv16i16(<vscale x 16 x i16> %0, <vscale x 16 x i16> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vror_vv_nxv16i16_nxv16i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, m4, ta, ma
+; CHECK-NEXT:    vror.vv v8, v8, v12
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 16 x i16> @llvm.riscv.vror.nxv16i16.nxv16i16(
+    <vscale x 16 x i16> undef,
+    <vscale x 16 x i16> %0,
+    <vscale x 16 x i16> %1,
+    iXLen %2)
+
+  ret <vscale x 16 x i16> %a
+}
+
+declare <vscale x 16 x i16> @llvm.riscv.vror.mask.nxv16i16.nxv16i16(
+  <vscale x 16 x i16>,
+  <vscale x 16 x i16>,
+  <vscale x 16 x i16>,
+  <vscale x 16 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 16 x i16> @intrinsic_vror_mask_vv_nxv16i16_nxv16i16(<vscale x 16 x i16> %0, <vscale x 16 x i16> %1, <vscale x 16 x i16> %2, <vscale x 16 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vror_mask_vv_nxv16i16_nxv16i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, m4, ta, mu
+; CHECK-NEXT:    vror.vv v8, v12, v16, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 16 x i16> @llvm.riscv.vror.mask.nxv16i16.nxv16i16(
+    <vscale x 16 x i16> %0,
+    <vscale x 16 x i16> %1,
+    <vscale x 16 x i16> %2,
+    <vscale x 16 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 16 x i16> %a
+}
+
+declare <vscale x 32 x i16> @llvm.riscv.vror.nxv32i16.nxv32i16(
+  <vscale x 32 x i16>,
+  <vscale x 32 x i16>,
+  <vscale x 32 x i16>,
+  iXLen)
+
+define <vscale x 32 x i16> @intrinsic_vror_vv_nxv32i16_nxv32i16(<vscale x 32 x i16> %0, <vscale x 32 x i16> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vror_vv_nxv32i16_nxv32i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, m8, ta, ma
+; CHECK-NEXT:    vror.vv v8, v8, v16
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 32 x i16> @llvm.riscv.vror.nxv32i16.nxv32i16(
+    <vscale x 32 x i16> undef,
+    <vscale x 32 x i16> %0,
+    <vscale x 32 x i16> %1,
+    iXLen %2)
+
+  ret <vscale x 32 x i16> %a
+}
+
+declare <vscale x 32 x i16> @llvm.riscv.vror.mask.nxv32i16.nxv32i16(
+  <vscale x 32 x i16>,
+  <vscale x 32 x i16>,
+  <vscale x 32 x i16>,
+  <vscale x 32 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 32 x i16> @intrinsic_vror_mask_vv_nxv32i16_nxv32i16(<vscale x 32 x i16> %0, <vscale x 32 x i16> %1, <vscale x 32 x i16> %2, <vscale x 32 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vror_mask_vv_nxv32i16_nxv32i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vl8re16.v v24, (a0)
+; CHECK-NEXT:    vsetvli zero, a1, e16, m8, ta, mu
+; CHECK-NEXT:    vror.vv v8, v16, v24, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 32 x i16> @llvm.riscv.vror.mask.nxv32i16.nxv32i16(
+    <vscale x 32 x i16> %0,
+    <vscale x 32 x i16> %1,
+    <vscale x 32 x i16> %2,
+    <vscale x 32 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 32 x i16> %a
+}
+
+declare <vscale x 1 x i32> @llvm.riscv.vror.nxv1i32.nxv1i32(
+  <vscale x 1 x i32>,
+  <vscale x 1 x i32>,
+  <vscale x 1 x i32>,
+  iXLen)
+
+define <vscale x 1 x i32> @intrinsic_vror_vv_nxv1i32_nxv1i32(<vscale x 1 x i32> %0, <vscale x 1 x i32> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vror_vv_nxv1i32_nxv1i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, mf2, ta, ma
+; CHECK-NEXT:    vror.vv v8, v8, v9
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i32> @llvm.riscv.vror.nxv1i32.nxv1i32(
+    <vscale x 1 x i32> undef,
+    <vscale x 1 x i32> %0,
+    <vscale x 1 x i32> %1,
+    iXLen %2)
+
+  ret <vscale x 1 x i32> %a
+}
+
+declare <vscale x 1 x i32> @llvm.riscv.vror.mask.nxv1i32.nxv1i32(
+  <vscale x 1 x i32>,
+  <vscale x 1 x i32>,
+  <vscale x 1 x i32>,
+  <vscale x 1 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 1 x i32> @intrinsic_vror_mask_vv_nxv1i32_nxv1i32(<vscale x 1 x i32> %0, <vscale x 1 x i32> %1, <vscale x 1 x i32> %2, <vscale x 1 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vror_mask_vv_nxv1i32_nxv1i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, mf2, ta, mu
+; CHECK-NEXT:    vror.vv v8, v9, v10, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i32> @llvm.riscv.vror.mask.nxv1i32.nxv1i32(
+    <vscale x 1 x i32> %0,
+    <vscale x 1 x i32> %1,
+    <vscale x 1 x i32> %2,
+    <vscale x 1 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 1 x i32> %a
+}
+
+declare <vscale x 2 x i32> @llvm.riscv.vror.nxv2i32.nxv2i32(
+  <vscale x 2 x i32>,
+  <vscale x 2 x i32>,
+  <vscale x 2 x i32>,
+  iXLen)
+
+define <vscale x 2 x i32> @intrinsic_vror_vv_nxv2i32_nxv2i32(<vscale x 2 x i32> %0, <vscale x 2 x i32> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vror_vv_nxv2i32_nxv2i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m1, ta, ma
+; CHECK-NEXT:    vror.vv v8, v8, v9
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i32> @llvm.riscv.vror.nxv2i32.nxv2i32(
+    <vscale x 2 x i32> undef,
+    <vscale x 2 x i32> %0,
+    <vscale x 2 x i32> %1,
+    iXLen %2)
+
+  ret <vscale x 2 x i32> %a
+}
+
+declare <vscale x 2 x i32> @llvm.riscv.vror.mask.nxv2i32.nxv2i32(
+  <vscale x 2 x i32>,
+  <vscale x 2 x i32>,
+  <vscale x 2 x i32>,
+  <vscale x 2 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 2 x i32> @intrinsic_vror_mask_vv_nxv2i32_nxv2i32(<vscale x 2 x i32> %0, <vscale x 2 x i32> %1, <vscale x 2 x i32> %2, <vscale x 2 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vror_mask_vv_nxv2i32_nxv2i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m1, ta, mu
+; CHECK-NEXT:    vror.vv v8, v9, v10, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i32> @llvm.riscv.vror.mask.nxv2i32.nxv2i32(
+    <vscale x 2 x i32> %0,
+    <vscale x 2 x i32> %1,
+    <vscale x 2 x i32> %2,
+    <vscale x 2 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 2 x i32> %a
+}
+
+declare <vscale x 4 x i32> @llvm.riscv.vror.nxv4i32.nxv4i32(
+  <vscale x 4 x i32>,
+  <vscale x 4 x i32>,
+  <vscale x 4 x i32>,
+  iXLen)
+
+define <vscale x 4 x i32> @intrinsic_vror_vv_nxv4i32_nxv4i32(<vscale x 4 x i32> %0, <vscale x 4 x i32> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vror_vv_nxv4i32_nxv4i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m2, ta, ma
+; CHECK-NEXT:    vror.vv v8, v8, v10
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i32> @llvm.riscv.vror.nxv4i32.nxv4i32(
+    <vscale x 4 x i32> undef,
+    <vscale x 4 x i32> %0,
+    <vscale x 4 x i32> %1,
+    iXLen %2)
+
+  ret <vscale x 4 x i32> %a
+}
+
+declare <vscale x 4 x i32> @llvm.riscv.vror.mask.nxv4i32.nxv4i32(
+  <vscale x 4 x i32>,
+  <vscale x 4 x i32>,
+  <vscale x 4 x i32>,
+  <vscale x 4 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 4 x i32> @intrinsic_vror_mask_vv_nxv4i32_nxv4i32(<vscale x 4 x i32> %0, <vscale x 4 x i32> %1, <vscale x 4 x i32> %2, <vscale x 4 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vror_mask_vv_nxv4i32_nxv4i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m2, ta, mu
+; CHECK-NEXT:    vror.vv v8, v10, v12, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i32> @llvm.riscv.vror.mask.nxv4i32.nxv4i32(
+    <vscale x 4 x i32> %0,
+    <vscale x 4 x i32> %1,
+    <vscale x 4 x i32> %2,
+    <vscale x 4 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 4 x i32> %a
+}
+
+declare <vscale x 8 x i32> @llvm.riscv.vror.nxv8i32.nxv8i32(
+  <vscale x 8 x i32>,
+  <vscale x 8 x i32>,
+  <vscale x 8 x i32>,
+  iXLen)
+
+define <vscale x 8 x i32> @intrinsic_vror_vv_nxv8i32_nxv8i32(<vscale x 8 x i32> %0, <vscale x 8 x i32> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vror_vv_nxv8i32_nxv8i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m4, ta, ma
+; CHECK-NEXT:    vror.vv v8, v8, v12
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i32> @llvm.riscv.vror.nxv8i32.nxv8i32(
+    <vscale x 8 x i32> undef,
+    <vscale x 8 x i32> %0,
+    <vscale x 8 x i32> %1,
+    iXLen %2)
+
+  ret <vscale x 8 x i32> %a
+}
+
+declare <vscale x 8 x i32> @llvm.riscv.vror.mask.nxv8i32.nxv8i32(
+  <vscale x 8 x i32>,
+  <vscale x 8 x i32>,
+  <vscale x 8 x i32>,
+  <vscale x 8 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 8 x i32> @intrinsic_vror_mask_vv_nxv8i32_nxv8i32(<vscale x 8 x i32> %0, <vscale x 8 x i32> %1, <vscale x 8 x i32> %2, <vscale x 8 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vror_mask_vv_nxv8i32_nxv8i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m4, ta, mu
+; CHECK-NEXT:    vror.vv v8, v12, v16, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i32> @llvm.riscv.vror.mask.nxv8i32.nxv8i32(
+    <vscale x 8 x i32> %0,
+    <vscale x 8 x i32> %1,
+    <vscale x 8 x i32> %2,
+    <vscale x 8 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 8 x i32> %a
+}
+
+declare <vscale x 16 x i32> @llvm.riscv.vror.nxv16i32.nxv16i32(
+  <vscale x 16 x i32>,
+  <vscale x 16 x i32>,
+  <vscale x 16 x i32>,
+  iXLen)
+
+define <vscale x 16 x i32> @intrinsic_vror_vv_nxv16i32_nxv16i32(<vscale x 16 x i32> %0, <vscale x 16 x i32> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vror_vv_nxv16i32_nxv16i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m8, ta, ma
+; CHECK-NEXT:    vror.vv v8, v8, v16
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 16 x i32> @llvm.riscv.vror.nxv16i32.nxv16i32(
+    <vscale x 16 x i32> undef,
+    <vscale x 16 x i32> %0,
+    <vscale x 16 x i32> %1,
+    iXLen %2)
+
+  ret <vscale x 16 x i32> %a
+}
+
+declare <vscale x 16 x i32> @llvm.riscv.vror.mask.nxv16i32.nxv16i32(
+  <vscale x 16 x i32>,
+  <vscale x 16 x i32>,
+  <vscale x 16 x i32>,
+  <vscale x 16 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 16 x i32> @intrinsic_vror_mask_vv_nxv16i32_nxv16i32(<vscale x 16 x i32> %0, <vscale x 16 x i32> %1, <vscale x 16 x i32> %2, <vscale x 16 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vror_mask_vv_nxv16i32_nxv16i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vl8re32.v v24, (a0)
+; CHECK-NEXT:    vsetvli zero, a1, e32, m8, ta, mu
+; CHECK-NEXT:    vror.vv v8, v16, v24, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 16 x i32> @llvm.riscv.vror.mask.nxv16i32.nxv16i32(
+    <vscale x 16 x i32> %0,
+    <vscale x 16 x i32> %1,
+    <vscale x 16 x i32> %2,
+    <vscale x 16 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 16 x i32> %a
+}
+
+declare <vscale x 1 x i64> @llvm.riscv.vror.nxv1i64.nxv1i64(
+  <vscale x 1 x i64>,
+  <vscale x 1 x i64>,
+  <vscale x 1 x i64>,
+  iXLen)
+
+define <vscale x 1 x i64> @intrinsic_vror_vv_nxv1i64_nxv1i64(<vscale x 1 x i64> %0, <vscale x 1 x i64> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vror_vv_nxv1i64_nxv1i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e64, m1, ta, ma
+; CHECK-NEXT:    vror.vv v8, v8, v9
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i64> @llvm.riscv.vror.nxv1i64.nxv1i64(
+    <vscale x 1 x i64> undef,
+    <vscale x 1 x i64> %0,
+    <vscale x 1 x i64> %1,
+    iXLen %2)
+
+  ret <vscale x 1 x i64> %a
+}
+
+declare <vscale x 1 x i64> @llvm.riscv.vror.mask.nxv1i64.nxv1i64(
+  <vscale x 1 x i64>,
+  <vscale x 1 x i64>,
+  <vscale x 1 x i64>,
+  <vscale x 1 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 1 x i64> @intrinsic_vror_mask_vv_nxv1i64_nxv1i64(<vscale x 1 x i64> %0, <vscale x 1 x i64> %1, <vscale x 1 x i64> %2, <vscale x 1 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vror_mask_vv_nxv1i64_nxv1i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e64, m1, ta, mu
+; CHECK-NEXT:    vror.vv v8, v9, v10, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i64> @llvm.riscv.vror.mask.nxv1i64.nxv1i64(
+    <vscale x 1 x i64> %0,
+    <vscale x 1 x i64> %1,
+    <vscale x 1 x i64> %2,
+    <vscale x 1 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 1 x i64> %a
+}
+
+declare <vscale x 2 x i64> @llvm.riscv.vror.nxv2i64.nxv2i64(
+  <vscale x 2 x i64>,
+  <vscale x 2 x i64>,
+  <vscale x 2 x i64>,
+  iXLen)
+
+define <vscale x 2 x i64> @intrinsic_vror_vv_nxv2i64_nxv2i64(<vscale x 2 x i64> %0, <vscale x 2 x i64> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vror_vv_nxv2i64_nxv2i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e64, m2, ta, ma
+; CHECK-NEXT:    vror.vv v8, v8, v10
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i64> @llvm.riscv.vror.nxv2i64.nxv2i64(
+    <vscale x 2 x i64> undef,
+    <vscale x 2 x i64> %0,
+    <vscale x 2 x i64> %1,
+    iXLen %2)
+
+  ret <vscale x 2 x i64> %a
+}
+
+declare <vscale x 2 x i64> @llvm.riscv.vror.mask.nxv2i64.nxv2i64(
+  <vscale x 2 x i64>,
+  <vscale x 2 x i64>,
+  <vscale x 2 x i64>,
+  <vscale x 2 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 2 x i64> @intrinsic_vror_mask_vv_nxv2i64_nxv2i64(<vscale x 2 x i64> %0, <vscale x 2 x i64> %1, <vscale x 2 x i64> %2, <vscale x 2 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vror_mask_vv_nxv2i64_nxv2i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e64, m2, ta, mu
+; CHECK-NEXT:    vror.vv v8, v10, v12, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i64> @llvm.riscv.vror.mask.nxv2i64.nxv2i64(
+    <vscale x 2 x i64> %0,
+    <vscale x 2 x i64> %1,
+    <vscale x 2 x i64> %2,
+    <vscale x 2 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 2 x i64> %a
+}
+
+declare <vscale x 4 x i64> @llvm.riscv.vror.nxv4i64.nxv4i64(
+  <vscale x 4 x i64>,
+  <vscale x 4 x i64>,
+  <vscale x 4 x i64>,
+  iXLen)
+
+define <vscale x 4 x i64> @intrinsic_vror_vv_nxv4i64_nxv4i64(<vscale x 4 x i64> %0, <vscale x 4 x i64> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vror_vv_nxv4i64_nxv4i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e64, m4, ta, ma
+; CHECK-NEXT:    vror.vv v8, v8, v12
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i64> @llvm.riscv.vror.nxv4i64.nxv4i64(
+    <vscale x 4 x i64> undef,
+    <vscale x 4 x i64> %0,
+    <vscale x 4 x i64> %1,
+    iXLen %2)
+
+  ret <vscale x 4 x i64> %a
+}
+
+declare <vscale x 4 x i64> @llvm.riscv.vror.mask.nxv4i64.nxv4i64(
+  <vscale x 4 x i64>,
+  <vscale x 4 x i64>,
+  <vscale x 4 x i64>,
+  <vscale x 4 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 4 x i64> @intrinsic_vror_mask_vv_nxv4i64_nxv4i64(<vscale x 4 x i64> %0, <vscale x 4 x i64> %1, <vscale x 4 x i64> %2, <vscale x 4 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vror_mask_vv_nxv4i64_nxv4i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e64, m4, ta, mu
+; CHECK-NEXT:    vror.vv v8, v12, v16, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i64> @llvm.riscv.vror.mask.nxv4i64.nxv4i64(
+    <vscale x 4 x i64> %0,
+    <vscale x 4 x i64> %1,
+    <vscale x 4 x i64> %2,
+    <vscale x 4 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 4 x i64> %a
+}
+
+declare <vscale x 8 x i64> @llvm.riscv.vror.nxv8i64.nxv8i64(
+  <vscale x 8 x i64>,
+  <vscale x 8 x i64>,
+  <vscale x 8 x i64>,
+  iXLen)
+
+define <vscale x 8 x i64> @intrinsic_vror_vv_nxv8i64_nxv8i64(<vscale x 8 x i64> %0, <vscale x 8 x i64> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vror_vv_nxv8i64_nxv8i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
+; CHECK-NEXT:    vror.vv v8, v8, v16
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i64> @llvm.riscv.vror.nxv8i64.nxv8i64(
+    <vscale x 8 x i64> undef,
+    <vscale x 8 x i64> %0,
+    <vscale x 8 x i64> %1,
+    iXLen %2)
+
+  ret <vscale x 8 x i64> %a
+}
+
+declare <vscale x 8 x i64> @llvm.riscv.vror.mask.nxv8i64.nxv8i64(
+  <vscale x 8 x i64>,
+  <vscale x 8 x i64>,
+  <vscale x 8 x i64>,
+  <vscale x 8 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 8 x i64> @intrinsic_vror_mask_vv_nxv8i64_nxv8i64(<vscale x 8 x i64> %0, <vscale x 8 x i64> %1, <vscale x 8 x i64> %2, <vscale x 8 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vror_mask_vv_nxv8i64_nxv8i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vl8re64.v v24, (a0)
+; CHECK-NEXT:    vsetvli zero, a1, e64, m8, ta, mu
+; CHECK-NEXT:    vror.vv v8, v16, v24, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i64> @llvm.riscv.vror.mask.nxv8i64.nxv8i64(
+    <vscale x 8 x i64> %0,
+    <vscale x 8 x i64> %1,
+    <vscale x 8 x i64> %2,
+    <vscale x 8 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 8 x i64> %a
+}
+
+declare <vscale x 1 x i8> @llvm.riscv.vror.nxv1i8.i8(
+  <vscale x 1 x i8>,
+  <vscale x 1 x i8>,
+  i8,
+  iXLen)
+
+define <vscale x 1 x i8> @intrinsic_vror_vx_nxv1i8_i8(<vscale x 1 x i8> %0, i8 %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vror_vx_nxv1i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e8, mf8, ta, ma
+; CHECK-NEXT:    vror.vx v8, v8, a0
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i8> @llvm.riscv.vror.nxv1i8.i8(
+    <vscale x 1 x i8> undef,
+    <vscale x 1 x i8> %0,
+    i8 %1,
+    iXLen %2)
+
+  ret <vscale x 1 x i8> %a
+}
+
+declare <vscale x 1 x i8> @llvm.riscv.vror.mask.nxv1i8.i8(
+  <vscale x 1 x i8>,
+  <vscale x 1 x i8>,
+  i8,
+  <vscale x 1 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 1 x i8> @intrinsic_vror_mask_vx_nxv1i8_i8(<vscale x 1 x i8> %0, <vscale x 1 x i8> %1, i8 %2, <vscale x 1 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vror_mask_vx_nxv1i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e8, mf8, ta, mu
+; CHECK-NEXT:    vror.vx v8, v9, a0, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i8> @llvm.riscv.vror.mask.nxv1i8.i8(
+    <vscale x 1 x i8> %0,
+    <vscale x 1 x i8> %1,
+    i8 %2,
+    <vscale x 1 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 1 x i8> %a
+}
+
+declare <vscale x 2 x i8> @llvm.riscv.vror.nxv2i8.i8(
+  <vscale x 2 x i8>,
+  <vscale x 2 x i8>,
+  i8,
+  iXLen)
+
+define <vscale x 2 x i8> @intrinsic_vror_vx_nxv2i8_i8(<vscale x 2 x i8> %0, i8 %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vror_vx_nxv2i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e8, mf4, ta, ma
+; CHECK-NEXT:    vror.vx v8, v8, a0
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i8> @llvm.riscv.vror.nxv2i8.i8(
+    <vscale x 2 x i8> undef,
+    <vscale x 2 x i8> %0,
+    i8 %1,
+    iXLen %2)
+
+  ret <vscale x 2 x i8> %a
+}
+
+declare <vscale x 2 x i8> @llvm.riscv.vror.mask.nxv2i8.i8(
+  <vscale x 2 x i8>,
+  <vscale x 2 x i8>,
+  i8,
+  <vscale x 2 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 2 x i8> @intrinsic_vror_mask_vx_nxv2i8_i8(<vscale x 2 x i8> %0, <vscale x 2 x i8> %1, i8 %2, <vscale x 2 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vror_mask_vx_nxv2i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e8, mf4, ta, mu
+; CHECK-NEXT:    vror.vx v8, v9, a0, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i8> @llvm.riscv.vror.mask.nxv2i8.i8(
+    <vscale x 2 x i8> %0,
+    <vscale x 2 x i8> %1,
+    i8 %2,
+    <vscale x 2 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 2 x i8> %a
+}
+
+declare <vscale x 4 x i8> @llvm.riscv.vror.nxv4i8.i8(
+  <vscale x 4 x i8>,
+  <vscale x 4 x i8>,
+  i8,
+  iXLen)
+
+define <vscale x 4 x i8> @intrinsic_vror_vx_nxv4i8_i8(<vscale x 4 x i8> %0, i8 %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vror_vx_nxv4i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e8, mf2, ta, ma
+; CHECK-NEXT:    vror.vx v8, v8, a0
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i8> @llvm.riscv.vror.nxv4i8.i8(
+    <vscale x 4 x i8> undef,
+    <vscale x 4 x i8> %0,
+    i8 %1,
+    iXLen %2)
+
+  ret <vscale x 4 x i8> %a
+}
+
+declare <vscale x 4 x i8> @llvm.riscv.vror.mask.nxv4i8.i8(
+  <vscale x 4 x i8>,
+  <vscale x 4 x i8>,
+  i8,
+  <vscale x 4 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 4 x i8> @intrinsic_vror_mask_vx_nxv4i8_i8(<vscale x 4 x i8> %0, <vscale x 4 x i8> %1, i8 %2, <vscale x 4 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vror_mask_vx_nxv4i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e8, mf2, ta, mu
+; CHECK-NEXT:    vror.vx v8, v9, a0, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i8> @llvm.riscv.vror.mask.nxv4i8.i8(
+    <vscale x 4 x i8> %0,
+    <vscale x 4 x i8> %1,
+    i8 %2,
+    <vscale x 4 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 4 x i8> %a
+}
+
+declare <vscale x 8 x i8> @llvm.riscv.vror.nxv8i8.i8(
+  <vscale x 8 x i8>,
+  <vscale x 8 x i8>,
+  i8,
+  iXLen)
+
+define <vscale x 8 x i8> @intrinsic_vror_vx_nxv8i8_i8(<vscale x 8 x i8> %0, i8 %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vror_vx_nxv8i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e8, m1, ta, ma
+; CHECK-NEXT:    vror.vx v8, v8, a0
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i8> @llvm.riscv.vror.nxv8i8.i8(
+    <vscale x 8 x i8> undef,
+    <vscale x 8 x i8> %0,
+    i8 %1,
+    iXLen %2)
+
+  ret <vscale x 8 x i8> %a
+}
+
+declare <vscale x 8 x i8> @llvm.riscv.vror.mask.nxv8i8.i8(
+  <vscale x 8 x i8>,
+  <vscale x 8 x i8>,
+  i8,
+  <vscale x 8 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 8 x i8> @intrinsic_vror_mask_vx_nxv8i8_i8(<vscale x 8 x i8> %0, <vscale x 8 x i8> %1, i8 %2, <vscale x 8 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vror_mask_vx_nxv8i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e8, m1, ta, mu
+; CHECK-NEXT:    vror.vx v8, v9, a0, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i8> @llvm.riscv.vror.mask.nxv8i8.i8(
+    <vscale x 8 x i8> %0,
+    <vscale x 8 x i8> %1,
+    i8 %2,
+    <vscale x 8 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 8 x i8> %a
+}
+
+declare <vscale x 16 x i8> @llvm.riscv.vror.nxv16i8.i8(
+  <vscale x 16 x i8>,
+  <vscale x 16 x i8>,
+  i8,
+  iXLen)
+
+define <vscale x 16 x i8> @intrinsic_vror_vx_nxv16i8_i8(<vscale x 16 x i8> %0, i8 %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vror_vx_nxv16i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e8, m2, ta, ma
+; CHECK-NEXT:    vror.vx v8, v8, a0
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 16 x i8> @llvm.riscv.vror.nxv16i8.i8(
+    <vscale x 16 x i8> undef,
+    <vscale x 16 x i8> %0,
+    i8 %1,
+    iXLen %2)
+
+  ret <vscale x 16 x i8> %a
+}
+
+declare <vscale x 16 x i8> @llvm.riscv.vror.mask.nxv16i8.i8(
+  <vscale x 16 x i8>,
+  <vscale x 16 x i8>,
+  i8,
+  <vscale x 16 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 16 x i8> @intrinsic_vror_mask_vx_nxv16i8_i8(<vscale x 16 x i8> %0, <vscale x 16 x i8> %1, i8 %2, <vscale x 16 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vror_mask_vx_nxv16i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e8, m2, ta, mu
+; CHECK-NEXT:    vror.vx v8, v10, a0, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 16 x i8> @llvm.riscv.vror.mask.nxv16i8.i8(
+    <vscale x 16 x i8> %0,
+    <vscale x 16 x i8> %1,
+    i8 %2,
+    <vscale x 16 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 16 x i8> %a
+}
+
+declare <vscale x 32 x i8> @llvm.riscv.vror.nxv32i8.i8(
+  <vscale x 32 x i8>,
+  <vscale x 32 x i8>,
+  i8,
+  iXLen)
+
+define <vscale x 32 x i8> @intrinsic_vror_vx_nxv32i8_i8(<vscale x 32 x i8> %0, i8 %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vror_vx_nxv32i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e8, m4, ta, ma
+; CHECK-NEXT:    vror.vx v8, v8, a0
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 32 x i8> @llvm.riscv.vror.nxv32i8.i8(
+    <vscale x 32 x i8> undef,
+    <vscale x 32 x i8> %0,
+    i8 %1,
+    iXLen %2)
+
+  ret <vscale x 32 x i8> %a
+}
+
+declare <vscale x 32 x i8> @llvm.riscv.vror.mask.nxv32i8.i8(
+  <vscale x 32 x i8>,
+  <vscale x 32 x i8>,
+  i8,
+  <vscale x 32 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 32 x i8> @intrinsic_vror_mask_vx_nxv32i8_i8(<vscale x 32 x i8> %0, <vscale x 32 x i8> %1, i8 %2, <vscale x 32 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vror_mask_vx_nxv32i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e8, m4, ta, mu
+; CHECK-NEXT:    vror.vx v8, v12, a0, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 32 x i8> @llvm.riscv.vror.mask.nxv32i8.i8(
+    <vscale x 32 x i8> %0,
+    <vscale x 32 x i8> %1,
+    i8 %2,
+    <vscale x 32 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 32 x i8> %a
+}
+
+declare <vscale x 64 x i8> @llvm.riscv.vror.nxv64i8.i8(
+  <vscale x 64 x i8>,
+  <vscale x 64 x i8>,
+  i8,
+  iXLen)
+
+define <vscale x 64 x i8> @intrinsic_vror_vx_nxv64i8_i8(<vscale x 64 x i8> %0, i8 %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vror_vx_nxv64i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e8, m8, ta, ma
+; CHECK-NEXT:    vror.vx v8, v8, a0
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 64 x i8> @llvm.riscv.vror.nxv64i8.i8(
+    <vscale x 64 x i8> undef,
+    <vscale x 64 x i8> %0,
+    i8 %1,
+    iXLen %2)
+
+  ret <vscale x 64 x i8> %a
+}
+
+declare <vscale x 64 x i8> @llvm.riscv.vror.mask.nxv64i8.i8(
+  <vscale x 64 x i8>,
+  <vscale x 64 x i8>,
+  i8,
+  <vscale x 64 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 64 x i8> @intrinsic_vror_mask_vx_nxv64i8_i8(<vscale x 64 x i8> %0, <vscale x 64 x i8> %1, i8 %2, <vscale x 64 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vror_mask_vx_nxv64i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e8, m8, ta, mu
+; CHECK-NEXT:    vror.vx v8, v16, a0, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 64 x i8> @llvm.riscv.vror.mask.nxv64i8.i8(
+    <vscale x 64 x i8> %0,
+    <vscale x 64 x i8> %1,
+    i8 %2,
+    <vscale x 64 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 64 x i8> %a
+}
+
+declare <vscale x 1 x i16> @llvm.riscv.vror.nxv1i16.i16(
+  <vscale x 1 x i16>,
+  <vscale x 1 x i16>,
+  i16,
+  iXLen)
+
+define <vscale x 1 x i16> @intrinsic_vror_vx_nxv1i16_i16(<vscale x 1 x i16> %0, i16 %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vror_vx_nxv1i16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e16, mf4, ta, ma
+; CHECK-NEXT:    vror.vx v8, v8, a0
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i16> @llvm.riscv.vror.nxv1i16.i16(
+    <vscale x 1 x i16> undef,
+    <vscale x 1 x i16> %0,
+    i16 %1,
+    iXLen %2)
+
+  ret <vscale x 1 x i16> %a
+}
+
+declare <vscale x 1 x i16> @llvm.riscv.vror.mask.nxv1i16.i16(
+  <vscale x 1 x i16>,
+  <vscale x 1 x i16>,
+  i16,
+  <vscale x 1 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 1 x i16> @intrinsic_vror_mask_vx_nxv1i16_i16(<vscale x 1 x i16> %0, <vscale x 1 x i16> %1, i16 %2, <vscale x 1 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vror_mask_vx_nxv1i16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e16, mf4, ta, mu
+; CHECK-NEXT:    vror.vx v8, v9, a0, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i16> @llvm.riscv.vror.mask.nxv1i16.i16(
+    <vscale x 1 x i16> %0,
+    <vscale x 1 x i16> %1,
+    i16 %2,
+    <vscale x 1 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 1 x i16> %a
+}
+
+declare <vscale x 2 x i16> @llvm.riscv.vror.nxv2i16.i16(
+  <vscale x 2 x i16>,
+  <vscale x 2 x i16>,
+  i16,
+  iXLen)
+
+define <vscale x 2 x i16> @intrinsic_vror_vx_nxv2i16_i16(<vscale x 2 x i16> %0, i16 %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vror_vx_nxv2i16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e16, mf2, ta, ma
+; CHECK-NEXT:    vror.vx v8, v8, a0
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i16> @llvm.riscv.vror.nxv2i16.i16(
+    <vscale x 2 x i16> undef,
+    <vscale x 2 x i16> %0,
+    i16 %1,
+    iXLen %2)
+
+  ret <vscale x 2 x i16> %a
+}
+
+declare <vscale x 2 x i16> @llvm.riscv.vror.mask.nxv2i16.i16(
+  <vscale x 2 x i16>,
+  <vscale x 2 x i16>,
+  i16,
+  <vscale x 2 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 2 x i16> @intrinsic_vror_mask_vx_nxv2i16_i16(<vscale x 2 x i16> %0, <vscale x 2 x i16> %1, i16 %2, <vscale x 2 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vror_mask_vx_nxv2i16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e16, mf2, ta, mu
+; CHECK-NEXT:    vror.vx v8, v9, a0, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i16> @llvm.riscv.vror.mask.nxv2i16.i16(
+    <vscale x 2 x i16> %0,
+    <vscale x 2 x i16> %1,
+    i16 %2,
+    <vscale x 2 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 2 x i16> %a
+}
+
+declare <vscale x 4 x i16> @llvm.riscv.vror.nxv4i16.i16(
+  <vscale x 4 x i16>,
+  <vscale x 4 x i16>,
+  i16,
+  iXLen)
+
+define <vscale x 4 x i16> @intrinsic_vror_vx_nxv4i16_i16(<vscale x 4 x i16> %0, i16 %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vror_vx_nxv4i16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e16, m1, ta, ma
+; CHECK-NEXT:    vror.vx v8, v8, a0
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i16> @llvm.riscv.vror.nxv4i16.i16(
+    <vscale x 4 x i16> undef,
+    <vscale x 4 x i16> %0,
+    i16 %1,
+    iXLen %2)
+
+  ret <vscale x 4 x i16> %a
+}
+
+declare <vscale x 4 x i16> @llvm.riscv.vror.mask.nxv4i16.i16(
+  <vscale x 4 x i16>,
+  <vscale x 4 x i16>,
+  i16,
+  <vscale x 4 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 4 x i16> @intrinsic_vror_mask_vx_nxv4i16_i16(<vscale x 4 x i16> %0, <vscale x 4 x i16> %1, i16 %2, <vscale x 4 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vror_mask_vx_nxv4i16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e16, m1, ta, mu
+; CHECK-NEXT:    vror.vx v8, v9, a0, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i16> @llvm.riscv.vror.mask.nxv4i16.i16(
+    <vscale x 4 x i16> %0,
+    <vscale x 4 x i16> %1,
+    i16 %2,
+    <vscale x 4 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 4 x i16> %a
+}
+
+declare <vscale x 8 x i16> @llvm.riscv.vror.nxv8i16.i16(
+  <vscale x 8 x i16>,
+  <vscale x 8 x i16>,
+  i16,
+  iXLen)
+
+define <vscale x 8 x i16> @intrinsic_vror_vx_nxv8i16_i16(<vscale x 8 x i16> %0, i16 %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vror_vx_nxv8i16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e16, m2, ta, ma
+; CHECK-NEXT:    vror.vx v8, v8, a0
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i16> @llvm.riscv.vror.nxv8i16.i16(
+    <vscale x 8 x i16> undef,
+    <vscale x 8 x i16> %0,
+    i16 %1,
+    iXLen %2)
+
+  ret <vscale x 8 x i16> %a
+}
+
+declare <vscale x 8 x i16> @llvm.riscv.vror.mask.nxv8i16.i16(
+  <vscale x 8 x i16>,
+  <vscale x 8 x i16>,
+  i16,
+  <vscale x 8 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 8 x i16> @intrinsic_vror_mask_vx_nxv8i16_i16(<vscale x 8 x i16> %0, <vscale x 8 x i16> %1, i16 %2, <vscale x 8 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vror_mask_vx_nxv8i16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e16, m2, ta, mu
+; CHECK-NEXT:    vror.vx v8, v10, a0, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i16> @llvm.riscv.vror.mask.nxv8i16.i16(
+    <vscale x 8 x i16> %0,
+    <vscale x 8 x i16> %1,
+    i16 %2,
+    <vscale x 8 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 8 x i16> %a
+}
+
+declare <vscale x 16 x i16> @llvm.riscv.vror.nxv16i16.i16(
+  <vscale x 16 x i16>,
+  <vscale x 16 x i16>,
+  i16,
+  iXLen)
+
+define <vscale x 16 x i16> @intrinsic_vror_vx_nxv16i16_i16(<vscale x 16 x i16> %0, i16 %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vror_vx_nxv16i16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e16, m4, ta, ma
+; CHECK-NEXT:    vror.vx v8, v8, a0
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 16 x i16> @llvm.riscv.vror.nxv16i16.i16(
+    <vscale x 16 x i16> undef,
+    <vscale x 16 x i16> %0,
+    i16 %1,
+    iXLen %2)
+
+  ret <vscale x 16 x i16> %a
+}
+
+declare <vscale x 16 x i16> @llvm.riscv.vror.mask.nxv16i16.i16(
+  <vscale x 16 x i16>,
+  <vscale x 16 x i16>,
+  i16,
+  <vscale x 16 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 16 x i16> @intrinsic_vror_mask_vx_nxv16i16_i16(<vscale x 16 x i16> %0, <vscale x 16 x i16> %1, i16 %2, <vscale x 16 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vror_mask_vx_nxv16i16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e16, m4, ta, mu
+; CHECK-NEXT:    vror.vx v8, v12, a0, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 16 x i16> @llvm.riscv.vror.mask.nxv16i16.i16(
+    <vscale x 16 x i16> %0,
+    <vscale x 16 x i16> %1,
+    i16 %2,
+    <vscale x 16 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 16 x i16> %a
+}
+
+declare <vscale x 32 x i16> @llvm.riscv.vror.nxv32i16.i16(
+  <vscale x 32 x i16>,
+  <vscale x 32 x i16>,
+  i16,
+  iXLen)
+
+define <vscale x 32 x i16> @intrinsic_vror_vx_nxv32i16_i16(<vscale x 32 x i16> %0, i16 %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vror_vx_nxv32i16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e16, m8, ta, ma
+; CHECK-NEXT:    vror.vx v8, v8, a0
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 32 x i16> @llvm.riscv.vror.nxv32i16.i16(
+    <vscale x 32 x i16> undef,
+    <vscale x 32 x i16> %0,
+    i16 %1,
+    iXLen %2)
+
+  ret <vscale x 32 x i16> %a
+}
+
+declare <vscale x 32 x i16> @llvm.riscv.vror.mask.nxv32i16.i16(
+  <vscale x 32 x i16>,
+  <vscale x 32 x i16>,
+  i16,
+  <vscale x 32 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 32 x i16> @intrinsic_vror_mask_vx_nxv32i16_i16(<vscale x 32 x i16> %0, <vscale x 32 x i16> %1, i16 %2, <vscale x 32 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vror_mask_vx_nxv32i16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e16, m8, ta, mu
+; CHECK-NEXT:    vror.vx v8, v16, a0, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 32 x i16> @llvm.riscv.vror.mask.nxv32i16.i16(
+    <vscale x 32 x i16> %0,
+    <vscale x 32 x i16> %1,
+    i16 %2,
+    <vscale x 32 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 32 x i16> %a
+}
+
+declare <vscale x 1 x i32> @llvm.riscv.vror.nxv1i32.i32(
+  <vscale x 1 x i32>,
+  <vscale x 1 x i32>,
+  i32,
+  iXLen)
+
+define <vscale x 1 x i32> @intrinsic_vror_vx_nxv1i32_i32(<vscale x 1 x i32> %0, i32 %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vror_vx_nxv1i32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e32, mf2, ta, ma
+; CHECK-NEXT:    vror.vx v8, v8, a0
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i32> @llvm.riscv.vror.nxv1i32.i32(
+    <vscale x 1 x i32> undef,
+    <vscale x 1 x i32> %0,
+    i32 %1,
+    iXLen %2)
+
+  ret <vscale x 1 x i32> %a
+}
+
+declare <vscale x 1 x i32> @llvm.riscv.vror.mask.nxv1i32.i32(
+  <vscale x 1 x i32>,
+  <vscale x 1 x i32>,
+  i32,
+  <vscale x 1 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 1 x i32> @intrinsic_vror_mask_vx_nxv1i32_i32(<vscale x 1 x i32> %0, <vscale x 1 x i32> %1, i32 %2, <vscale x 1 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vror_mask_vx_nxv1i32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e32, mf2, ta, mu
+; CHECK-NEXT:    vror.vx v8, v9, a0, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i32> @llvm.riscv.vror.mask.nxv1i32.i32(
+    <vscale x 1 x i32> %0,
+    <vscale x 1 x i32> %1,
+    i32 %2,
+    <vscale x 1 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 1 x i32> %a
+}
+
+declare <vscale x 2 x i32> @llvm.riscv.vror.nxv2i32.i32(
+  <vscale x 2 x i32>,
+  <vscale x 2 x i32>,
+  i32,
+  iXLen)
+
+define <vscale x 2 x i32> @intrinsic_vror_vx_nxv2i32_i32(<vscale x 2 x i32> %0, i32 %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vror_vx_nxv2i32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e32, m1, ta, ma
+; CHECK-NEXT:    vror.vx v8, v8, a0
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i32> @llvm.riscv.vror.nxv2i32.i32(
+    <vscale x 2 x i32> undef,
+    <vscale x 2 x i32> %0,
+    i32 %1,
+    iXLen %2)
+
+  ret <vscale x 2 x i32> %a
+}
+
+declare <vscale x 2 x i32> @llvm.riscv.vror.mask.nxv2i32.i32(
+  <vscale x 2 x i32>,
+  <vscale x 2 x i32>,
+  i32,
+  <vscale x 2 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 2 x i32> @intrinsic_vror_mask_vx_nxv2i32_i32(<vscale x 2 x i32> %0, <vscale x 2 x i32> %1, i32 %2, <vscale x 2 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vror_mask_vx_nxv2i32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e32, m1, ta, mu
+; CHECK-NEXT:    vror.vx v8, v9, a0, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i32> @llvm.riscv.vror.mask.nxv2i32.i32(
+    <vscale x 2 x i32> %0,
+    <vscale x 2 x i32> %1,
+    i32 %2,
+    <vscale x 2 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 2 x i32> %a
+}
+
+declare <vscale x 4 x i32> @llvm.riscv.vror.nxv4i32.i32(
+  <vscale x 4 x i32>,
+  <vscale x 4 x i32>,
+  i32,
+  iXLen)
+
+define <vscale x 4 x i32> @intrinsic_vror_vx_nxv4i32_i32(<vscale x 4 x i32> %0, i32 %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vror_vx_nxv4i32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e32, m2, ta, ma
+; CHECK-NEXT:    vror.vx v8, v8, a0
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i32> @llvm.riscv.vror.nxv4i32.i32(
+    <vscale x 4 x i32> undef,
+    <vscale x 4 x i32> %0,
+    i32 %1,
+    iXLen %2)
+
+  ret <vscale x 4 x i32> %a
+}
+
+declare <vscale x 4 x i32> @llvm.riscv.vror.mask.nxv4i32.i32(
+  <vscale x 4 x i32>,
+  <vscale x 4 x i32>,
+  i32,
+  <vscale x 4 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 4 x i32> @intrinsic_vror_mask_vx_nxv4i32_i32(<vscale x 4 x i32> %0, <vscale x 4 x i32> %1, i32 %2, <vscale x 4 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vror_mask_vx_nxv4i32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e32, m2, ta, mu
+; CHECK-NEXT:    vror.vx v8, v10, a0, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i32> @llvm.riscv.vror.mask.nxv4i32.i32(
+    <vscale x 4 x i32> %0,
+    <vscale x 4 x i32> %1,
+    i32 %2,
+    <vscale x 4 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 4 x i32> %a
+}
+
+declare <vscale x 8 x i32> @llvm.riscv.vror.nxv8i32.i32(
+  <vscale x 8 x i32>,
+  <vscale x 8 x i32>,
+  i32,
+  iXLen)
+
+define <vscale x 8 x i32> @intrinsic_vror_vx_nxv8i32_i32(<vscale x 8 x i32> %0, i32 %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vror_vx_nxv8i32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e32, m4, ta, ma
+; CHECK-NEXT:    vror.vx v8, v8, a0
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i32> @llvm.riscv.vror.nxv8i32.i32(
+    <vscale x 8 x i32> undef,
+    <vscale x 8 x i32> %0,
+    i32 %1,
+    iXLen %2)
+
+  ret <vscale x 8 x i32> %a
+}
+
+declare <vscale x 8 x i32> @llvm.riscv.vror.mask.nxv8i32.i32(
+  <vscale x 8 x i32>,
+  <vscale x 8 x i32>,
+  i32,
+  <vscale x 8 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 8 x i32> @intrinsic_vror_mask_vx_nxv8i32_i32(<vscale x 8 x i32> %0, <vscale x 8 x i32> %1, i32 %2, <vscale x 8 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vror_mask_vx_nxv8i32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e32, m4, ta, mu
+; CHECK-NEXT:    vror.vx v8, v12, a0, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i32> @llvm.riscv.vror.mask.nxv8i32.i32(
+    <vscale x 8 x i32> %0,
+    <vscale x 8 x i32> %1,
+    i32 %2,
+    <vscale x 8 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 8 x i32> %a
+}
+
+declare <vscale x 16 x i32> @llvm.riscv.vror.nxv16i32.i32(
+  <vscale x 16 x i32>,
+  <vscale x 16 x i32>,
+  i32,
+  iXLen)
+
+define <vscale x 16 x i32> @intrinsic_vror_vx_nxv16i32_i32(<vscale x 16 x i32> %0, i32 %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vror_vx_nxv16i32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e32, m8, ta, ma
+; CHECK-NEXT:    vror.vx v8, v8, a0
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 16 x i32> @llvm.riscv.vror.nxv16i32.i32(
+    <vscale x 16 x i32> undef,
+    <vscale x 16 x i32> %0,
+    i32 %1,
+    iXLen %2)
+
+  ret <vscale x 16 x i32> %a
+}
+
+declare <vscale x 16 x i32> @llvm.riscv.vror.mask.nxv16i32.i32(
+  <vscale x 16 x i32>,
+  <vscale x 16 x i32>,
+  i32,
+  <vscale x 16 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 16 x i32> @intrinsic_vror_mask_vx_nxv16i32_i32(<vscale x 16 x i32> %0, <vscale x 16 x i32> %1, i32 %2, <vscale x 16 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vror_mask_vx_nxv16i32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e32, m8, ta, mu
+; CHECK-NEXT:    vror.vx v8, v16, a0, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 16 x i32> @llvm.riscv.vror.mask.nxv16i32.i32(
+    <vscale x 16 x i32> %0,
+    <vscale x 16 x i32> %1,
+    i32 %2,
+    <vscale x 16 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 16 x i32> %a
+}
+
+declare <vscale x 1 x i64> @llvm.riscv.vror.nxv1i64.i64(
+  <vscale x 1 x i64>,
+  <vscale x 1 x i64>,
+  i64,
+  iXLen)
+
+define <vscale x 1 x i64> @intrinsic_vror_vx_nxv1i64_i64(<vscale x 1 x i64> %0, i64 %1, iXLen %2) nounwind {
+; RV32-LABEL: intrinsic_vror_vx_nxv1i64_i64:
+; RV32:       # %bb.0: # %entry
+; RV32-NEXT:    addi sp, sp, -16
+; RV32-NEXT:    sw a1, 12(sp)
+; RV32-NEXT:    sw a0, 8(sp)
+; RV32-NEXT:    addi a0, sp, 8
+; RV32-NEXT:    vsetvli zero, a2, e64, m1, ta, ma
+; RV32-NEXT:    vlse64.v v9, (a0), zero
+; RV32-NEXT:    vror.vv v8, v8, v9
+; RV32-NEXT:    addi sp, sp, 16
+; RV32-NEXT:    ret
+;
+; RV64-LABEL: intrinsic_vror_vx_nxv1i64_i64:
+; RV64:       # %bb.0: # %entry
+; RV64-NEXT:    vsetvli zero, a1, e64, m1, ta, ma
+; RV64-NEXT:    vror.vx v8, v8, a0
+; RV64-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i64> @llvm.riscv.vror.nxv1i64.i64(
+    <vscale x 1 x i64> undef,
+    <vscale x 1 x i64> %0,
+    i64 %1,
+    iXLen %2)
+
+  ret <vscale x 1 x i64> %a
+}
+
+declare <vscale x 1 x i64> @llvm.riscv.vror.mask.nxv1i64.i64(
+  <vscale x 1 x i64>,
+  <vscale x 1 x i64>,
+  i64,
+  <vscale x 1 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 1 x i64> @intrinsic_vror_mask_vx_nxv1i64_i64(<vscale x 1 x i64> %0, <vscale x 1 x i64> %1, i64 %2, <vscale x 1 x i1> %3, iXLen %4) nounwind {
+; RV32-LABEL: intrinsic_vror_mask_vx_nxv1i64_i64:
+; RV32:       # %bb.0: # %entry
+; RV32-NEXT:    addi sp, sp, -16
+; RV32-NEXT:    sw a1, 12(sp)
+; RV32-NEXT:    sw a0, 8(sp)
+; RV32-NEXT:    addi a0, sp, 8
+; RV32-NEXT:    vsetvli zero, a2, e64, m1, ta, mu
+; RV32-NEXT:    vlse64.v v10, (a0), zero
+; RV32-NEXT:    vror.vv v8, v9, v10, v0.t
+; RV32-NEXT:    addi sp, sp, 16
+; RV32-NEXT:    ret
+;
+; RV64-LABEL: intrinsic_vror_mask_vx_nxv1i64_i64:
+; RV64:       # %bb.0: # %entry
+; RV64-NEXT:    vsetvli zero, a1, e64, m1, ta, mu
+; RV64-NEXT:    vror.vx v8, v9, a0, v0.t
+; RV64-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i64> @llvm.riscv.vror.mask.nxv1i64.i64(
+    <vscale x 1 x i64> %0,
+    <vscale x 1 x i64> %1,
+    i64 %2,
+    <vscale x 1 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 1 x i64> %a
+}
+
+declare <vscale x 2 x i64> @llvm.riscv.vror.nxv2i64.i64(
+  <vscale x 2 x i64>,
+  <vscale x 2 x i64>,
+  i64,
+  iXLen)
+
+define <vscale x 2 x i64> @intrinsic_vror_vx_nxv2i64_i64(<vscale x 2 x i64> %0, i64 %1, iXLen %2) nounwind {
+; RV32-LABEL: intrinsic_vror_vx_nxv2i64_i64:
+; RV32:       # %bb.0: # %entry
+; RV32-NEXT:    addi sp, sp, -16
+; RV32-NEXT:    sw a1, 12(sp)
+; RV32-NEXT:    sw a0, 8(sp)
+; RV32-NEXT:    addi a0, sp, 8
+; RV32-NEXT:    vsetvli zero, a2, e64, m2, ta, ma
+; RV32-NEXT:    vlse64.v v10, (a0), zero
+; RV32-NEXT:    vror.vv v8, v8, v10
+; RV32-NEXT:    addi sp, sp, 16
+; RV32-NEXT:    ret
+;
+; RV64-LABEL: intrinsic_vror_vx_nxv2i64_i64:
+; RV64:       # %bb.0: # %entry
+; RV64-NEXT:    vsetvli zero, a1, e64, m2, ta, ma
+; RV64-NEXT:    vror.vx v8, v8, a0
+; RV64-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i64> @llvm.riscv.vror.nxv2i64.i64(
+    <vscale x 2 x i64> undef,
+    <vscale x 2 x i64> %0,
+    i64 %1,
+    iXLen %2)
+
+  ret <vscale x 2 x i64> %a
+}
+
+declare <vscale x 2 x i64> @llvm.riscv.vror.mask.nxv2i64.i64(
+  <vscale x 2 x i64>,
+  <vscale x 2 x i64>,
+  i64,
+  <vscale x 2 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 2 x i64> @intrinsic_vror_mask_vx_nxv2i64_i64(<vscale x 2 x i64> %0, <vscale x 2 x i64> %1, i64 %2, <vscale x 2 x i1> %3, iXLen %4) nounwind {
+; RV32-LABEL: intrinsic_vror_mask_vx_nxv2i64_i64:
+; RV32:       # %bb.0: # %entry
+; RV32-NEXT:    addi sp, sp, -16
+; RV32-NEXT:    sw a1, 12(sp)
+; RV32-NEXT:    sw a0, 8(sp)
+; RV32-NEXT:    addi a0, sp, 8
+; RV32-NEXT:    vsetvli zero, a2, e64, m2, ta, mu
+; RV32-NEXT:    vlse64.v v12, (a0), zero
+; RV32-NEXT:    vror.vv v8, v10, v12, v0.t
+; RV32-NEXT:    addi sp, sp, 16
+; RV32-NEXT:    ret
+;
+; RV64-LABEL: intrinsic_vror_mask_vx_nxv2i64_i64:
+; RV64:       # %bb.0: # %entry
+; RV64-NEXT:    vsetvli zero, a1, e64, m2, ta, mu
+; RV64-NEXT:    vror.vx v8, v10, a0, v0.t
+; RV64-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i64> @llvm.riscv.vror.mask.nxv2i64.i64(
+    <vscale x 2 x i64> %0,
+    <vscale x 2 x i64> %1,
+    i64 %2,
+    <vscale x 2 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 2 x i64> %a
+}
+
+declare <vscale x 4 x i64> @llvm.riscv.vror.nxv4i64.i64(
+  <vscale x 4 x i64>,
+  <vscale x 4 x i64>,
+  i64,
+  iXLen)
+
+define <vscale x 4 x i64> @intrinsic_vror_vx_nxv4i64_i64(<vscale x 4 x i64> %0, i64 %1, iXLen %2) nounwind {
+; RV32-LABEL: intrinsic_vror_vx_nxv4i64_i64:
+; RV32:       # %bb.0: # %entry
+; RV32-NEXT:    addi sp, sp, -16
+; RV32-NEXT:    sw a1, 12(sp)
+; RV32-NEXT:    sw a0, 8(sp)
+; RV32-NEXT:    addi a0, sp, 8
+; RV32-NEXT:    vsetvli zero, a2, e64, m4, ta, ma
+; RV32-NEXT:    vlse64.v v12, (a0), zero
+; RV32-NEXT:    vror.vv v8, v8, v12
+; RV32-NEXT:    addi sp, sp, 16
+; RV32-NEXT:    ret
+;
+; RV64-LABEL: intrinsic_vror_vx_nxv4i64_i64:
+; RV64:       # %bb.0: # %entry
+; RV64-NEXT:    vsetvli zero, a1, e64, m4, ta, ma
+; RV64-NEXT:    vror.vx v8, v8, a0
+; RV64-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i64> @llvm.riscv.vror.nxv4i64.i64(
+    <vscale x 4 x i64> undef,
+    <vscale x 4 x i64> %0,
+    i64 %1,
+    iXLen %2)
+
+  ret <vscale x 4 x i64> %a
+}
+
+declare <vscale x 4 x i64> @llvm.riscv.vror.mask.nxv4i64.i64(
+  <vscale x 4 x i64>,
+  <vscale x 4 x i64>,
+  i64,
+  <vscale x 4 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 4 x i64> @intrinsic_vror_mask_vx_nxv4i64_i64(<vscale x 4 x i64> %0, <vscale x 4 x i64> %1, i64 %2, <vscale x 4 x i1> %3, iXLen %4) nounwind {
+; RV32-LABEL: intrinsic_vror_mask_vx_nxv4i64_i64:
+; RV32:       # %bb.0: # %entry
+; RV32-NEXT:    addi sp, sp, -16
+; RV32-NEXT:    sw a1, 12(sp)
+; RV32-NEXT:    sw a0, 8(sp)
+; RV32-NEXT:    addi a0, sp, 8
+; RV32-NEXT:    vsetvli zero, a2, e64, m4, ta, mu
+; RV32-NEXT:    vlse64.v v16, (a0), zero
+; RV32-NEXT:    vror.vv v8, v12, v16, v0.t
+; RV32-NEXT:    addi sp, sp, 16
+; RV32-NEXT:    ret
+;
+; RV64-LABEL: intrinsic_vror_mask_vx_nxv4i64_i64:
+; RV64:       # %bb.0: # %entry
+; RV64-NEXT:    vsetvli zero, a1, e64, m4, ta, mu
+; RV64-NEXT:    vror.vx v8, v12, a0, v0.t
+; RV64-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i64> @llvm.riscv.vror.mask.nxv4i64.i64(
+    <vscale x 4 x i64> %0,
+    <vscale x 4 x i64> %1,
+    i64 %2,
+    <vscale x 4 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 4 x i64> %a
+}
+
+declare <vscale x 8 x i64> @llvm.riscv.vror.nxv8i64.i64(
+  <vscale x 8 x i64>,
+  <vscale x 8 x i64>,
+  i64,
+  iXLen)
+
+define <vscale x 8 x i64> @intrinsic_vror_vx_nxv8i64_i64(<vscale x 8 x i64> %0, i64 %1, iXLen %2) nounwind {
+; RV32-LABEL: intrinsic_vror_vx_nxv8i64_i64:
+; RV32:       # %bb.0: # %entry
+; RV32-NEXT:    addi sp, sp, -16
+; RV32-NEXT:    sw a1, 12(sp)
+; RV32-NEXT:    sw a0, 8(sp)
+; RV32-NEXT:    addi a0, sp, 8
+; RV32-NEXT:    vsetvli zero, a2, e64, m8, ta, ma
+; RV32-NEXT:    vlse64.v v16, (a0), zero
+; RV32-NEXT:    vror.vv v8, v8, v16
+; RV32-NEXT:    addi sp, sp, 16
+; RV32-NEXT:    ret
+;
+; RV64-LABEL: intrinsic_vror_vx_nxv8i64_i64:
+; RV64:       # %bb.0: # %entry
+; RV64-NEXT:    vsetvli zero, a1, e64, m8, ta, ma
+; RV64-NEXT:    vror.vx v8, v8, a0
+; RV64-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i64> @llvm.riscv.vror.nxv8i64.i64(
+    <vscale x 8 x i64> undef,
+    <vscale x 8 x i64> %0,
+    i64 %1,
+    iXLen %2)
+
+  ret <vscale x 8 x i64> %a
+}
+
+declare <vscale x 8 x i64> @llvm.riscv.vror.mask.nxv8i64.i64(
+  <vscale x 8 x i64>,
+  <vscale x 8 x i64>,
+  i64,
+  <vscale x 8 x i1>,
+  iXLen,
+  iXLen)
+
+define <vscale x 8 x i64> @intrinsic_vror_mask_vx_nxv8i64_i64(<vscale x 8 x i64> %0, <vscale x 8 x i64> %1, i64 %2, <vscale x 8 x i1> %3, iXLen %4) nounwind {
+; RV32-LABEL: intrinsic_vror_mask_vx_nxv8i64_i64:
+; RV32:       # %bb.0: # %entry
+; RV32-NEXT:    addi sp, sp, -16
+; RV32-NEXT:    sw a1, 12(sp)
+; RV32-NEXT:    sw a0, 8(sp)
+; RV32-NEXT:    addi a0, sp, 8
+; RV32-NEXT:    vsetvli zero, a2, e64, m8, ta, mu
+; RV32-NEXT:    vlse64.v v24, (a0), zero
+; RV32-NEXT:    vror.vv v8, v16, v24, v0.t
+; RV32-NEXT:    addi sp, sp, 16
+; RV32-NEXT:    ret
+;
+; RV64-LABEL: intrinsic_vror_mask_vx_nxv8i64_i64:
+; RV64:       # %bb.0: # %entry
+; RV64-NEXT:    vsetvli zero, a1, e64, m8, ta, mu
+; RV64-NEXT:    vror.vx v8, v16, a0, v0.t
+; RV64-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i64> @llvm.riscv.vror.mask.nxv8i64.i64(
+    <vscale x 8 x i64> %0,
+    <vscale x 8 x i64> %1,
+    i64 %2,
+    <vscale x 8 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 8 x i64> %a
+}
+
+define <vscale x 1 x i8> @intrinsic_vror_vi_nxv1i8_i8(<vscale x 1 x i8> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vror_vi_nxv1i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, mf8, ta, ma
+; CHECK-NEXT:    vror.vi v8, v8, 2
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i8> @llvm.riscv.vror.nxv1i8.i8(
+    <vscale x 1 x i8> undef,
+    <vscale x 1 x i8> %0,
+    i8 2,
+    iXLen %1)
+
+  ret <vscale x 1 x i8> %a
+}
+
+define <vscale x 1 x i8> @intrinsic_vror_mask_vi_nxv1i8_i8(<vscale x 1 x i8> %0, <vscale x 1 x i8> %1, <vscale x 1 x i1> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vror_mask_vi_nxv1i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, mf8, ta, mu
+; CHECK-NEXT:    vror.vi v8, v9, 2, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i8> @llvm.riscv.vror.mask.nxv1i8.i8(
+    <vscale x 1 x i8> %0,
+    <vscale x 1 x i8> %1,
+    i8 2,
+    <vscale x 1 x i1> %2,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 1 x i8> %a
+}
+
+define <vscale x 2 x i8> @intrinsic_vror_vi_nxv2i8_i8(<vscale x 2 x i8> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vror_vi_nxv2i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, mf4, ta, ma
+; CHECK-NEXT:    vror.vi v8, v8, 2
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i8> @llvm.riscv.vror.nxv2i8.i8(
+    <vscale x 2 x i8> undef,
+    <vscale x 2 x i8> %0,
+    i8 2,
+    iXLen %1)
+
+  ret <vscale x 2 x i8> %a
+}
+
+define <vscale x 2 x i8> @intrinsic_vror_mask_vi_nxv2i8_i8(<vscale x 2 x i8> %0, <vscale x 2 x i8> %1, <vscale x 2 x i1> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vror_mask_vi_nxv2i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, mf4, ta, mu
+; CHECK-NEXT:    vror.vi v8, v9, 2, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i8> @llvm.riscv.vror.mask.nxv2i8.i8(
+    <vscale x 2 x i8> %0,
+    <vscale x 2 x i8> %1,
+    i8 2,
+    <vscale x 2 x i1> %2,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 2 x i8> %a
+}
+
+define <vscale x 4 x i8> @intrinsic_vror_vi_nxv4i8_i8(<vscale x 4 x i8> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vror_vi_nxv4i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, mf2, ta, ma
+; CHECK-NEXT:    vror.vi v8, v8, 2
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i8> @llvm.riscv.vror.nxv4i8.i8(
+    <vscale x 4 x i8> undef,
+    <vscale x 4 x i8> %0,
+    i8 2,
+    iXLen %1)
+
+  ret <vscale x 4 x i8> %a
+}
+
+define <vscale x 4 x i8> @intrinsic_vror_mask_vi_nxv4i8_i8(<vscale x 4 x i8> %0, <vscale x 4 x i8> %1, <vscale x 4 x i1> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vror_mask_vi_nxv4i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, mf2, ta, mu
+; CHECK-NEXT:    vror.vi v8, v9, 2, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i8> @llvm.riscv.vror.mask.nxv4i8.i8(
+    <vscale x 4 x i8> %0,
+    <vscale x 4 x i8> %1,
+    i8 2,
+    <vscale x 4 x i1> %2,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 4 x i8> %a
+}
+
+define <vscale x 8 x i8> @intrinsic_vror_vi_nxv8i8_i8(<vscale x 8 x i8> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vror_vi_nxv8i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, m1, ta, ma
+; CHECK-NEXT:    vror.vi v8, v8, 2
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i8> @llvm.riscv.vror.nxv8i8.i8(
+    <vscale x 8 x i8> undef,
+    <vscale x 8 x i8> %0,
+    i8 2,
+    iXLen %1)
+
+  ret <vscale x 8 x i8> %a
+}
+
+define <vscale x 8 x i8> @intrinsic_vror_mask_vi_nxv8i8_i8(<vscale x 8 x i8> %0, <vscale x 8 x i8> %1, <vscale x 8 x i1> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vror_mask_vi_nxv8i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, m1, ta, mu
+; CHECK-NEXT:    vror.vi v8, v9, 2, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i8> @llvm.riscv.vror.mask.nxv8i8.i8(
+    <vscale x 8 x i8> %0,
+    <vscale x 8 x i8> %1,
+    i8 2,
+    <vscale x 8 x i1> %2,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 8 x i8> %a
+}
+
+define <vscale x 16 x i8> @intrinsic_vror_vi_nxv16i8_i8(<vscale x 16 x i8> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vror_vi_nxv16i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, m2, ta, ma
+; CHECK-NEXT:    vror.vi v8, v8, 2
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 16 x i8> @llvm.riscv.vror.nxv16i8.i8(
+    <vscale x 16 x i8> undef,
+    <vscale x 16 x i8> %0,
+    i8 2,
+    iXLen %1)
+
+  ret <vscale x 16 x i8> %a
+}
+
+define <vscale x 16 x i8> @intrinsic_vror_mask_vi_nxv16i8_i8(<vscale x 16 x i8> %0, <vscale x 16 x i8> %1, <vscale x 16 x i1> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vror_mask_vi_nxv16i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, m2, ta, mu
+; CHECK-NEXT:    vror.vi v8, v10, 2, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 16 x i8> @llvm.riscv.vror.mask.nxv16i8.i8(
+    <vscale x 16 x i8> %0,
+    <vscale x 16 x i8> %1,
+    i8 2,
+    <vscale x 16 x i1> %2,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 16 x i8> %a
+}
+
+define <vscale x 32 x i8> @intrinsic_vror_vi_nxv32i8_i8(<vscale x 32 x i8> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vror_vi_nxv32i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, m4, ta, ma
+; CHECK-NEXT:    vror.vi v8, v8, 2
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 32 x i8> @llvm.riscv.vror.nxv32i8.i8(
+    <vscale x 32 x i8> undef,
+    <vscale x 32 x i8> %0,
+    i8 2,
+    iXLen %1)
+
+  ret <vscale x 32 x i8> %a
+}
+
+define <vscale x 32 x i8> @intrinsic_vror_mask_vi_nxv32i8_i8(<vscale x 32 x i8> %0, <vscale x 32 x i8> %1, <vscale x 32 x i1> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vror_mask_vi_nxv32i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, m4, ta, mu
+; CHECK-NEXT:    vror.vi v8, v12, 2, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 32 x i8> @llvm.riscv.vror.mask.nxv32i8.i8(
+    <vscale x 32 x i8> %0,
+    <vscale x 32 x i8> %1,
+    i8 2,
+    <vscale x 32 x i1> %2,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 32 x i8> %a
+}
+
+define <vscale x 64 x i8> @intrinsic_vror_vi_nxv64i8_i8(<vscale x 64 x i8> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vror_vi_nxv64i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, m8, ta, ma
+; CHECK-NEXT:    vror.vi v8, v8, 2
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 64 x i8> @llvm.riscv.vror.nxv64i8.i8(
+    <vscale x 64 x i8> undef,
+    <vscale x 64 x i8> %0,
+    i8 2,
+    iXLen %1)
+
+  ret <vscale x 64 x i8> %a
+}
+
+define <vscale x 64 x i8> @intrinsic_vror_mask_vi_nxv64i8_i8(<vscale x 64 x i8> %0, <vscale x 64 x i8> %1, <vscale x 64 x i1> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vror_mask_vi_nxv64i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, m8, ta, mu
+; CHECK-NEXT:    vror.vi v8, v16, 2, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 64 x i8> @llvm.riscv.vror.mask.nxv64i8.i8(
+    <vscale x 64 x i8> %0,
+    <vscale x 64 x i8> %1,
+    i8 2,
+    <vscale x 64 x i1> %2,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 64 x i8> %a
+}
+
+define <vscale x 1 x i16> @intrinsic_vror_vi_nxv1i16_i16(<vscale x 1 x i16> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vror_vi_nxv1i16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, mf4, ta, ma
+; CHECK-NEXT:    vror.vi v8, v8, 2
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i16> @llvm.riscv.vror.nxv1i16.i16(
+    <vscale x 1 x i16> undef,
+    <vscale x 1 x i16> %0,
+    i16 2,
+    iXLen %1)
+
+  ret <vscale x 1 x i16> %a
+}
+
+define <vscale x 1 x i16> @intrinsic_vror_mask_vi_nxv1i16_i16(<vscale x 1 x i16> %0, <vscale x 1 x i16> %1, <vscale x 1 x i1> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vror_mask_vi_nxv1i16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, mf4, ta, mu
+; CHECK-NEXT:    vror.vi v8, v9, 2, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i16> @llvm.riscv.vror.mask.nxv1i16.i16(
+    <vscale x 1 x i16> %0,
+    <vscale x 1 x i16> %1,
+    i16 2,
+    <vscale x 1 x i1> %2,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 1 x i16> %a
+}
+
+define <vscale x 2 x i16> @intrinsic_vror_vi_nxv2i16_i16(<vscale x 2 x i16> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vror_vi_nxv2i16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, mf2, ta, ma
+; CHECK-NEXT:    vror.vi v8, v8, 2
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i16> @llvm.riscv.vror.nxv2i16.i16(
+    <vscale x 2 x i16> undef,
+    <vscale x 2 x i16> %0,
+    i16 2,
+    iXLen %1)
+
+  ret <vscale x 2 x i16> %a
+}
+
+define <vscale x 2 x i16> @intrinsic_vror_mask_vi_nxv2i16_i16(<vscale x 2 x i16> %0, <vscale x 2 x i16> %1, <vscale x 2 x i1> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vror_mask_vi_nxv2i16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, mf2, ta, mu
+; CHECK-NEXT:    vror.vi v8, v9, 2, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i16> @llvm.riscv.vror.mask.nxv2i16.i16(
+    <vscale x 2 x i16> %0,
+    <vscale x 2 x i16> %1,
+    i16 2,
+    <vscale x 2 x i1> %2,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 2 x i16> %a
+}
+
+define <vscale x 4 x i16> @intrinsic_vror_vi_nxv4i16_i16(<vscale x 4 x i16> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vror_vi_nxv4i16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, m1, ta, ma
+; CHECK-NEXT:    vror.vi v8, v8, 2
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i16> @llvm.riscv.vror.nxv4i16.i16(
+    <vscale x 4 x i16> undef,
+    <vscale x 4 x i16> %0,
+    i16 2,
+    iXLen %1)
+
+  ret <vscale x 4 x i16> %a
+}
+
+define <vscale x 4 x i16> @intrinsic_vror_mask_vi_nxv4i16_i16(<vscale x 4 x i16> %0, <vscale x 4 x i16> %1, <vscale x 4 x i1> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vror_mask_vi_nxv4i16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, m1, ta, mu
+; CHECK-NEXT:    vror.vi v8, v9, 2, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i16> @llvm.riscv.vror.mask.nxv4i16.i16(
+    <vscale x 4 x i16> %0,
+    <vscale x 4 x i16> %1,
+    i16 2,
+    <vscale x 4 x i1> %2,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 4 x i16> %a
+}
+
+define <vscale x 8 x i16> @intrinsic_vror_vi_nxv8i16_i16(<vscale x 8 x i16> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vror_vi_nxv8i16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, m2, ta, ma
+; CHECK-NEXT:    vror.vi v8, v8, 2
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i16> @llvm.riscv.vror.nxv8i16.i16(
+    <vscale x 8 x i16> undef,
+    <vscale x 8 x i16> %0,
+    i16 2,
+    iXLen %1)
+
+  ret <vscale x 8 x i16> %a
+}
+
+define <vscale x 8 x i16> @intrinsic_vror_mask_vi_nxv8i16_i16(<vscale x 8 x i16> %0, <vscale x 8 x i16> %1, <vscale x 8 x i1> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vror_mask_vi_nxv8i16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, m2, ta, mu
+; CHECK-NEXT:    vror.vi v8, v10, 2, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i16> @llvm.riscv.vror.mask.nxv8i16.i16(
+    <vscale x 8 x i16> %0,
+    <vscale x 8 x i16> %1,
+    i16 2,
+    <vscale x 8 x i1> %2,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 8 x i16> %a
+}
+
+define <vscale x 16 x i16> @intrinsic_vror_vi_nxv16i16_i16(<vscale x 16 x i16> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vror_vi_nxv16i16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, m4, ta, ma
+; CHECK-NEXT:    vror.vi v8, v8, 2
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 16 x i16> @llvm.riscv.vror.nxv16i16.i16(
+    <vscale x 16 x i16> undef,
+    <vscale x 16 x i16> %0,
+    i16 2,
+    iXLen %1)
+
+  ret <vscale x 16 x i16> %a
+}
+
+define <vscale x 16 x i16> @intrinsic_vror_mask_vi_nxv16i16_i16(<vscale x 16 x i16> %0, <vscale x 16 x i16> %1, <vscale x 16 x i1> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vror_mask_vi_nxv16i16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, m4, ta, mu
+; CHECK-NEXT:    vror.vi v8, v12, 2, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 16 x i16> @llvm.riscv.vror.mask.nxv16i16.i16(
+    <vscale x 16 x i16> %0,
+    <vscale x 16 x i16> %1,
+    i16 2,
+    <vscale x 16 x i1> %2,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 16 x i16> %a
+}
+
+define <vscale x 32 x i16> @intrinsic_vror_vi_nxv32i16_i16(<vscale x 32 x i16> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vror_vi_nxv32i16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, m8, ta, ma
+; CHECK-NEXT:    vror.vi v8, v8, 2
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 32 x i16> @llvm.riscv.vror.nxv32i16.i16(
+    <vscale x 32 x i16> undef,
+    <vscale x 32 x i16> %0,
+    i16 2,
+    iXLen %1)
+
+  ret <vscale x 32 x i16> %a
+}
+
+define <vscale x 32 x i16> @intrinsic_vror_mask_vi_nxv32i16_i16(<vscale x 32 x i16> %0, <vscale x 32 x i16> %1, <vscale x 32 x i1> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vror_mask_vi_nxv32i16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, m8, ta, mu
+; CHECK-NEXT:    vror.vi v8, v16, 2, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 32 x i16> @llvm.riscv.vror.mask.nxv32i16.i16(
+    <vscale x 32 x i16> %0,
+    <vscale x 32 x i16> %1,
+    i16 2,
+    <vscale x 32 x i1> %2,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 32 x i16> %a
+}
+
+define <vscale x 1 x i32> @intrinsic_vror_vi_nxv1i32_i32(<vscale x 1 x i32> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vror_vi_nxv1i32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, mf2, ta, ma
+; CHECK-NEXT:    vror.vi v8, v8, 2
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i32> @llvm.riscv.vror.nxv1i32.i32(
+    <vscale x 1 x i32> undef,
+    <vscale x 1 x i32> %0,
+    i32 2,
+    iXLen %1)
+
+  ret <vscale x 1 x i32> %a
+}
+
+define <vscale x 1 x i32> @intrinsic_vror_mask_vi_nxv1i32_i32(<vscale x 1 x i32> %0, <vscale x 1 x i32> %1, <vscale x 1 x i1> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vror_mask_vi_nxv1i32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, mf2, ta, mu
+; CHECK-NEXT:    vror.vi v8, v9, 2, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i32> @llvm.riscv.vror.mask.nxv1i32.i32(
+    <vscale x 1 x i32> %0,
+    <vscale x 1 x i32> %1,
+    i32 2,
+    <vscale x 1 x i1> %2,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 1 x i32> %a
+}
+
+define <vscale x 2 x i32> @intrinsic_vror_vi_nxv2i32_i32(<vscale x 2 x i32> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vror_vi_nxv2i32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m1, ta, ma
+; CHECK-NEXT:    vror.vi v8, v8, 2
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i32> @llvm.riscv.vror.nxv2i32.i32(
+    <vscale x 2 x i32> undef,
+    <vscale x 2 x i32> %0,
+    i32 2,
+    iXLen %1)
+
+  ret <vscale x 2 x i32> %a
+}
+
+define <vscale x 2 x i32> @intrinsic_vror_mask_vi_nxv2i32_i32(<vscale x 2 x i32> %0, <vscale x 2 x i32> %1, <vscale x 2 x i1> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vror_mask_vi_nxv2i32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m1, ta, mu
+; CHECK-NEXT:    vror.vi v8, v9, 2, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i32> @llvm.riscv.vror.mask.nxv2i32.i32(
+    <vscale x 2 x i32> %0,
+    <vscale x 2 x i32> %1,
+    i32 2,
+    <vscale x 2 x i1> %2,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 2 x i32> %a
+}
+
+define <vscale x 4 x i32> @intrinsic_vror_vi_nxv4i32_i32(<vscale x 4 x i32> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vror_vi_nxv4i32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m2, ta, ma
+; CHECK-NEXT:    vror.vi v8, v8, 2
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i32> @llvm.riscv.vror.nxv4i32.i32(
+    <vscale x 4 x i32> undef,
+    <vscale x 4 x i32> %0,
+    i32 2,
+    iXLen %1)
+
+  ret <vscale x 4 x i32> %a
+}
+
+define <vscale x 4 x i32> @intrinsic_vror_mask_vi_nxv4i32_i32(<vscale x 4 x i32> %0, <vscale x 4 x i32> %1, <vscale x 4 x i1> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vror_mask_vi_nxv4i32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m2, ta, mu
+; CHECK-NEXT:    vror.vi v8, v10, 2, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i32> @llvm.riscv.vror.mask.nxv4i32.i32(
+    <vscale x 4 x i32> %0,
+    <vscale x 4 x i32> %1,
+    i32 2,
+    <vscale x 4 x i1> %2,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 4 x i32> %a
+}
+
+define <vscale x 8 x i32> @intrinsic_vror_vi_nxv8i32_i32(<vscale x 8 x i32> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vror_vi_nxv8i32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m4, ta, ma
+; CHECK-NEXT:    vror.vi v8, v8, 2
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i32> @llvm.riscv.vror.nxv8i32.i32(
+    <vscale x 8 x i32> undef,
+    <vscale x 8 x i32> %0,
+    i32 2,
+    iXLen %1)
+
+  ret <vscale x 8 x i32> %a
+}
+
+define <vscale x 8 x i32> @intrinsic_vror_mask_vi_nxv8i32_i32(<vscale x 8 x i32> %0, <vscale x 8 x i32> %1, <vscale x 8 x i1> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vror_mask_vi_nxv8i32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m4, ta, mu
+; CHECK-NEXT:    vror.vi v8, v12, 2, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i32> @llvm.riscv.vror.mask.nxv8i32.i32(
+    <vscale x 8 x i32> %0,
+    <vscale x 8 x i32> %1,
+    i32 2,
+    <vscale x 8 x i1> %2,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 8 x i32> %a
+}
+
+define <vscale x 16 x i32> @intrinsic_vror_vi_nxv16i32_i32(<vscale x 16 x i32> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vror_vi_nxv16i32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m8, ta, ma
+; CHECK-NEXT:    vror.vi v8, v8, 2
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 16 x i32> @llvm.riscv.vror.nxv16i32.i32(
+    <vscale x 16 x i32> undef,
+    <vscale x 16 x i32> %0,
+    i32 2,
+    iXLen %1)
+
+  ret <vscale x 16 x i32> %a
+}
+
+define <vscale x 16 x i32> @intrinsic_vror_mask_vi_nxv16i32_i32(<vscale x 16 x i32> %0, <vscale x 16 x i32> %1, <vscale x 16 x i1> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vror_mask_vi_nxv16i32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m8, ta, mu
+; CHECK-NEXT:    vror.vi v8, v16, 2, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 16 x i32> @llvm.riscv.vror.mask.nxv16i32.i32(
+    <vscale x 16 x i32> %0,
+    <vscale x 16 x i32> %1,
+    i32 2,
+    <vscale x 16 x i1> %2,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 16 x i32> %a
+}
+
+define <vscale x 1 x i64> @intrinsic_vror_vi_nxv1i64_i64(<vscale x 1 x i64> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vror_vi_nxv1i64_i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e64, m1, ta, ma
+; CHECK-NEXT:    vror.vi v8, v8, 2
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i64> @llvm.riscv.vror.nxv1i64.i64(
+    <vscale x 1 x i64> undef,
+    <vscale x 1 x i64> %0,
+    i64 2,
+    iXLen %1)
+
+  ret <vscale x 1 x i64> %a
+}
+
+define <vscale x 1 x i64> @intrinsic_vror_mask_vi_nxv1i64_i64(<vscale x 1 x i64> %0, <vscale x 1 x i64> %1, <vscale x 1 x i1> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vror_mask_vi_nxv1i64_i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e64, m1, ta, mu
+; CHECK-NEXT:    vror.vi v8, v9, 2, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i64> @llvm.riscv.vror.mask.nxv1i64.i64(
+    <vscale x 1 x i64> %0,
+    <vscale x 1 x i64> %1,
+    i64 2,
+    <vscale x 1 x i1> %2,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 1 x i64> %a
+}
+
+define <vscale x 2 x i64> @intrinsic_vror_vi_nxv2i64_i64(<vscale x 2 x i64> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vror_vi_nxv2i64_i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e64, m2, ta, ma
+; CHECK-NEXT:    vror.vi v8, v8, 2
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i64> @llvm.riscv.vror.nxv2i64.i64(
+    <vscale x 2 x i64> undef,
+    <vscale x 2 x i64> %0,
+    i64 2,
+    iXLen %1)
+
+  ret <vscale x 2 x i64> %a
+}
+
+define <vscale x 2 x i64> @intrinsic_vror_mask_vi_nxv2i64_i64(<vscale x 2 x i64> %0, <vscale x 2 x i64> %1, <vscale x 2 x i1> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vror_mask_vi_nxv2i64_i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e64, m2, ta, mu
+; CHECK-NEXT:    vror.vi v8, v10, 2, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i64> @llvm.riscv.vror.mask.nxv2i64.i64(
+    <vscale x 2 x i64> %0,
+    <vscale x 2 x i64> %1,
+    i64 2,
+    <vscale x 2 x i1> %2,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 2 x i64> %a
+}
+
+define <vscale x 4 x i64> @intrinsic_vror_vi_nxv4i64_i64(<vscale x 4 x i64> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vror_vi_nxv4i64_i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e64, m4, ta, ma
+; CHECK-NEXT:    vror.vi v8, v8, 2
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i64> @llvm.riscv.vror.nxv4i64.i64(
+    <vscale x 4 x i64> undef,
+    <vscale x 4 x i64> %0,
+    i64 2,
+    iXLen %1)
+
+  ret <vscale x 4 x i64> %a
+}
+
+define <vscale x 4 x i64> @intrinsic_vror_mask_vi_nxv4i64_i64(<vscale x 4 x i64> %0, <vscale x 4 x i64> %1, <vscale x 4 x i1> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vror_mask_vi_nxv4i64_i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e64, m4, ta, mu
+; CHECK-NEXT:    vror.vi v8, v12, 2, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i64> @llvm.riscv.vror.mask.nxv4i64.i64(
+    <vscale x 4 x i64> %0,
+    <vscale x 4 x i64> %1,
+    i64 2,
+    <vscale x 4 x i1> %2,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 4 x i64> %a
+}
+
+define <vscale x 8 x i64> @intrinsic_vror_vi_nxv8i64_i64(<vscale x 8 x i64> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vror_vi_nxv8i64_i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
+; CHECK-NEXT:    vror.vi v8, v8, 2
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i64> @llvm.riscv.vror.nxv8i64.i64(
+    <vscale x 8 x i64> undef,
+    <vscale x 8 x i64> %0,
+    i64 2,
+    iXLen %1)
+
+  ret <vscale x 8 x i64> %a
+}
+
+define <vscale x 8 x i64> @intrinsic_vror_mask_vi_nxv8i64_i64(<vscale x 8 x i64> %0, <vscale x 8 x i64> %1, <vscale x 8 x i1> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vror_mask_vi_nxv8i64_i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, mu
+; CHECK-NEXT:    vror.vi v8, v16, 2, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i64> @llvm.riscv.vror.mask.nxv8i64.i64(
+    <vscale x 8 x i64> %0,
+    <vscale x 8 x i64> %1,
+    i64 2,
+    <vscale x 8 x i1> %2,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 8 x i64> %a
+}

llvm/test/CodeGen/RISCV/rvv/vsha2ch.ll

+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: sed 's/iXLen/i32/g' %s | llc -mtriple=riscv32 -mattr=+v,+experimental-zvknha \
+; RUN:   -verify-machineinstrs | FileCheck %s --check-prefixes=CHECK
+; RUN: sed 's/iXLen/i64/g' %s | llc -mtriple=riscv64 -mattr=+v,+experimental-zvknha \
+; RUN:   -verify-machineinstrs | FileCheck %s --check-prefixes=CHECK
+
+declare <vscale x 1 x i32> @llvm.riscv.vsha2ch.nxv1i32.nxv1i32(
+  <vscale x 1 x i32>,
+  <vscale x 1 x i32>,
+  <vscale x 1 x i32>,
+  iXLen,
+  iXLen)
+
+define <vscale x 1 x i32> @intrinsic_vsha2ch_vv_nxv1i32_nxv1i32(<vscale x 1 x i32> %0, <vscale x 1 x i32> %1, <vscale x 1 x i32> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vsha2ch_vv_nxv1i32_nxv1i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, mf2, tu, ma
+; CHECK-NEXT:    vsha2ch.vv v8, v9, v10
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i32> @llvm.riscv.vsha2ch.nxv1i32.nxv1i32(
+    <vscale x 1 x i32> %0,
+    <vscale x 1 x i32> %1,
+    <vscale x 1 x i32> %2,
+    iXLen %3,
+    iXLen 2)
+
+  ret <vscale x 1 x i32> %a
+}
+
+declare <vscale x 2 x i32> @llvm.riscv.vsha2ch.nxv2i32.nxv2i32(
+  <vscale x 2 x i32>,
+  <vscale x 2 x i32>,
+  <vscale x 2 x i32>,
+  iXLen,
+  iXLen)
+
+define <vscale x 2 x i32> @intrinsic_vsha2ch_vv_nxv2i32_nxv2i32(<vscale x 2 x i32> %0, <vscale x 2 x i32> %1, <vscale x 2 x i32> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vsha2ch_vv_nxv2i32_nxv2i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m1, tu, ma
+; CHECK-NEXT:    vsha2ch.vv v8, v9, v10
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i32> @llvm.riscv.vsha2ch.nxv2i32.nxv2i32(
+    <vscale x 2 x i32> %0,
+    <vscale x 2 x i32> %1,
+    <vscale x 2 x i32> %2,
+    iXLen %3,
+    iXLen 2)
+
+  ret <vscale x 2 x i32> %a
+}
+
+declare <vscale x 4 x i32> @llvm.riscv.vsha2ch.nxv4i32.nxv4i32(
+  <vscale x 4 x i32>,
+  <vscale x 4 x i32>,
+  <vscale x 4 x i32>,
+  iXLen,
+  iXLen)
+
+define <vscale x 4 x i32> @intrinsic_vsha2ch_vv_nxv4i32_nxv4i32(<vscale x 4 x i32> %0, <vscale x 4 x i32> %1, <vscale x 4 x i32> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vsha2ch_vv_nxv4i32_nxv4i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m2, tu, ma
+; CHECK-NEXT:    vsha2ch.vv v8, v10, v12
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i32> @llvm.riscv.vsha2ch.nxv4i32.nxv4i32(
+    <vscale x 4 x i32> %0,
+    <vscale x 4 x i32> %1,
+    <vscale x 4 x i32> %2,
+    iXLen %3,
+    iXLen 2)
+
+  ret <vscale x 4 x i32> %a
+}
+
+declare <vscale x 8 x i32> @llvm.riscv.vsha2ch.nxv8i32.nxv8i32(
+  <vscale x 8 x i32>,
+  <vscale x 8 x i32>,
+  <vscale x 8 x i32>,
+  iXLen,
+  iXLen)
+
+define <vscale x 8 x i32> @intrinsic_vsha2ch_vv_nxv8i32_nxv8i32(<vscale x 8 x i32> %0, <vscale x 8 x i32> %1, <vscale x 8 x i32> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vsha2ch_vv_nxv8i32_nxv8i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m4, tu, ma
+; CHECK-NEXT:    vsha2ch.vv v8, v12, v16
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i32> @llvm.riscv.vsha2ch.nxv8i32.nxv8i32(
+    <vscale x 8 x i32> %0,
+    <vscale x 8 x i32> %1,
+    <vscale x 8 x i32> %2,
+    iXLen %3,
+    iXLen 2)
+
+  ret <vscale x 8 x i32> %a
+}
+
+declare <vscale x 16 x i32> @llvm.riscv.vsha2ch.nxv16i32.nxv16i32(
+  <vscale x 16 x i32>,
+  <vscale x 16 x i32>,
+  <vscale x 16 x i32>,
+  iXLen,
+  iXLen)
+
+define <vscale x 16 x i32> @intrinsic_vsha2ch_vv_nxv16i32_nxv16i32(<vscale x 16 x i32> %0, <vscale x 16 x i32> %1, <vscale x 16 x i32> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vsha2ch_vv_nxv16i32_nxv16i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vl8re32.v v24, (a0)
+; CHECK-NEXT:    vsetvli zero, a1, e32, m8, tu, ma
+; CHECK-NEXT:    vsha2ch.vv v8, v16, v24
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 16 x i32> @llvm.riscv.vsha2ch.nxv16i32.nxv16i32(
+    <vscale x 16 x i32> %0,
+    <vscale x 16 x i32> %1,
+    <vscale x 16 x i32> %2,
+    iXLen %3,
+    iXLen 2)
+
+  ret <vscale x 16 x i32> %a
+}
+
+declare <vscale x 1 x i64> @llvm.riscv.vsha2ch.nxv1i64.nxv1i64(
+  <vscale x 1 x i64>,
+  <vscale x 1 x i64>,
+  <vscale x 1 x i64>,
+  iXLen,
+  iXLen)
+
+define <vscale x 1 x i64> @intrinsic_vsha2ch_vv_nxv1i64_nxv1i64(<vscale x 1 x i64> %0, <vscale x 1 x i64> %1, <vscale x 1 x i64> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vsha2ch_vv_nxv1i64_nxv1i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e64, m1, tu, ma
+; CHECK-NEXT:    vsha2ch.vv v8, v9, v10
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i64> @llvm.riscv.vsha2ch.nxv1i64.nxv1i64(
+    <vscale x 1 x i64> %0,
+    <vscale x 1 x i64> %1,
+    <vscale x 1 x i64> %2,
+    iXLen %3,
+    iXLen 2)
+
+  ret <vscale x 1 x i64> %a
+}
+
+declare <vscale x 2 x i64> @llvm.riscv.vsha2ch.nxv2i64.nxv2i64(
+  <vscale x 2 x i64>,
+  <vscale x 2 x i64>,
+  <vscale x 2 x i64>,
+  iXLen,
+  iXLen)
+
+define <vscale x 2 x i64> @intrinsic_vsha2ch_vv_nxv2i64_nxv2i64(<vscale x 2 x i64> %0, <vscale x 2 x i64> %1, <vscale x 2 x i64> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vsha2ch_vv_nxv2i64_nxv2i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e64, m2, tu, ma
+; CHECK-NEXT:    vsha2ch.vv v8, v10, v12
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i64> @llvm.riscv.vsha2ch.nxv2i64.nxv2i64(
+    <vscale x 2 x i64> %0,
+    <vscale x 2 x i64> %1,
+    <vscale x 2 x i64> %2,
+    iXLen %3,
+    iXLen 2)
+
+  ret <vscale x 2 x i64> %a
+}
+
+declare <vscale x 4 x i64> @llvm.riscv.vsha2ch.nxv4i64.nxv4i64(
+  <vscale x 4 x i64>,
+  <vscale x 4 x i64>,
+  <vscale x 4 x i64>,
+  iXLen,
+  iXLen)
+
+define <vscale x 4 x i64> @intrinsic_vsha2ch_vv_nxv4i64_nxv4i64(<vscale x 4 x i64> %0, <vscale x 4 x i64> %1, <vscale x 4 x i64> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vsha2ch_vv_nxv4i64_nxv4i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e64, m4, tu, ma
+; CHECK-NEXT:    vsha2ch.vv v8, v12, v16
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i64> @llvm.riscv.vsha2ch.nxv4i64.nxv4i64(
+    <vscale x 4 x i64> %0,
+    <vscale x 4 x i64> %1,
+    <vscale x 4 x i64> %2,
+    iXLen %3,
+    iXLen 2)
+
+  ret <vscale x 4 x i64> %a
+}
+
+declare <vscale x 8 x i64> @llvm.riscv.vsha2ch.nxv8i64.nxv8i64(
+  <vscale x 8 x i64>,
+  <vscale x 8 x i64>,
+  <vscale x 8 x i64>,
+  iXLen,
+  iXLen)
+
+define <vscale x 8 x i64> @intrinsic_vsha2ch_vv_nxv8i64_nxv8i64(<vscale x 8 x i64> %0, <vscale x 8 x i64> %1, <vscale x 8 x i64> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vsha2ch_vv_nxv8i64_nxv8i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vl8re64.v v24, (a0)
+; CHECK-NEXT:    vsetvli zero, a1, e64, m8, tu, ma
+; CHECK-NEXT:    vsha2ch.vv v8, v16, v24
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i64> @llvm.riscv.vsha2ch.nxv8i64.nxv8i64(
+    <vscale x 8 x i64> %0,
+    <vscale x 8 x i64> %1,
+    <vscale x 8 x i64> %2,
+    iXLen %3,
+    iXLen 2)
+
+  ret <vscale x 8 x i64> %a
+}

llvm/test/CodeGen/RISCV/rvv/vsha2cl.ll

+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: sed 's/iXLen/i32/g' %s | llc -mtriple=riscv32 -mattr=+v,+experimental-zvknhb \
+; RUN:   -verify-machineinstrs | FileCheck %s --check-prefixes=CHECK
+; RUN: sed 's/iXLen/i64/g' %s | llc -mtriple=riscv64 -mattr=+v,+experimental-zvknhb \
+; RUN:   -verify-machineinstrs | FileCheck %s --check-prefixes=CHECK
+
+declare <vscale x 1 x i32> @llvm.riscv.vsha2cl.nxv1i32.nxv1i32(
+  <vscale x 1 x i32>,
+  <vscale x 1 x i32>,
+  <vscale x 1 x i32>,
+  iXLen,
+  iXLen)
+
+define <vscale x 1 x i32> @intrinsic_vsha2cl_vv_nxv1i32_nxv1i32(<vscale x 1 x i32> %0, <vscale x 1 x i32> %1, <vscale x 1 x i32> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vsha2cl_vv_nxv1i32_nxv1i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, mf2, tu, ma
+; CHECK-NEXT:    vsha2ch.vv v8, v9, v10
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i32> @llvm.riscv.vsha2cl.nxv1i32.nxv1i32(
+    <vscale x 1 x i32> %0,
+    <vscale x 1 x i32> %1,
+    <vscale x 1 x i32> %2,
+    iXLen %3,
+    iXLen 2)
+
+  ret <vscale x 1 x i32> %a
+}
+
+declare <vscale x 2 x i32> @llvm.riscv.vsha2cl.nxv2i32.nxv2i32(
+  <vscale x 2 x i32>,
+  <vscale x 2 x i32>,
+  <vscale x 2 x i32>,
+  iXLen,
+  iXLen)
+
+define <vscale x 2 x i32> @intrinsic_vsha2cl_vv_nxv2i32_nxv2i32(<vscale x 2 x i32> %0, <vscale x 2 x i32> %1, <vscale x 2 x i32> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vsha2cl_vv_nxv2i32_nxv2i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m1, tu, ma
+; CHECK-NEXT:    vsha2ch.vv v8, v9, v10
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i32> @llvm.riscv.vsha2cl.nxv2i32.nxv2i32(
+    <vscale x 2 x i32> %0,
+    <vscale x 2 x i32> %1,
+    <vscale x 2 x i32> %2,
+    iXLen %3,
+    iXLen 2)
+
+  ret <vscale x 2 x i32> %a
+}
+
+declare <vscale x 4 x i32> @llvm.riscv.vsha2cl.nxv4i32.nxv4i32(
+  <vscale x 4 x i32>,
+  <vscale x 4 x i32>,
+  <vscale x 4 x i32>,
+  iXLen,
+  iXLen)
+
+define <vscale x 4 x i32> @intrinsic_vsha2cl_vv_nxv4i32_nxv4i32(<vscale x 4 x i32> %0, <vscale x 4 x i32> %1, <vscale x 4 x i32> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vsha2cl_vv_nxv4i32_nxv4i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m2, tu, ma
+; CHECK-NEXT:    vsha2ch.vv v8, v10, v12
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i32> @llvm.riscv.vsha2cl.nxv4i32.nxv4i32(
+    <vscale x 4 x i32> %0,
+    <vscale x 4 x i32> %1,
+    <vscale x 4 x i32> %2,
+    iXLen %3,
+    iXLen 2)
+
+  ret <vscale x 4 x i32> %a
+}
+
+declare <vscale x 8 x i32> @llvm.riscv.vsha2cl.nxv8i32.nxv8i32(
+  <vscale x 8 x i32>,
+  <vscale x 8 x i32>,
+  <vscale x 8 x i32>,
+  iXLen,
+  iXLen)
+
+define <vscale x 8 x i32> @intrinsic_vsha2cl_vv_nxv8i32_nxv8i32(<vscale x 8 x i32> %0, <vscale x 8 x i32> %1, <vscale x 8 x i32> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vsha2cl_vv_nxv8i32_nxv8i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m4, tu, ma
+; CHECK-NEXT:    vsha2ch.vv v8, v12, v16
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i32> @llvm.riscv.vsha2cl.nxv8i32.nxv8i32(
+    <vscale x 8 x i32> %0,
+    <vscale x 8 x i32> %1,
+    <vscale x 8 x i32> %2,
+    iXLen %3,
+    iXLen 2)
+
+  ret <vscale x 8 x i32> %a
+}
+
+declare <vscale x 16 x i32> @llvm.riscv.vsha2cl.nxv16i32.nxv16i32(
+  <vscale x 16 x i32>,
+  <vscale x 16 x i32>,
+  <vscale x 16 x i32>,
+  iXLen,
+  iXLen)
+
+define <vscale x 16 x i32> @intrinsic_vsha2cl_vv_nxv16i32_nxv16i32(<vscale x 16 x i32> %0, <vscale x 16 x i32> %1, <vscale x 16 x i32> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vsha2cl_vv_nxv16i32_nxv16i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vl8re32.v v24, (a0)
+; CHECK-NEXT:    vsetvli zero, a1, e32, m8, tu, ma
+; CHECK-NEXT:    vsha2ch.vv v8, v16, v24
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 16 x i32> @llvm.riscv.vsha2cl.nxv16i32.nxv16i32(
+    <vscale x 16 x i32> %0,
+    <vscale x 16 x i32> %1,
+    <vscale x 16 x i32> %2,
+    iXLen %3,
+    iXLen 2)
+
+  ret <vscale x 16 x i32> %a
+}
+
+declare <vscale x 1 x i64> @llvm.riscv.vsha2cl.nxv1i64.nxv1i64(
+  <vscale x 1 x i64>,
+  <vscale x 1 x i64>,
+  <vscale x 1 x i64>,
+  iXLen,
+  iXLen)
+
+define <vscale x 1 x i64> @intrinsic_vsha2cl_vv_nxv1i64_nxv1i64(<vscale x 1 x i64> %0, <vscale x 1 x i64> %1, <vscale x 1 x i64> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vsha2cl_vv_nxv1i64_nxv1i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e64, m1, tu, ma
+; CHECK-NEXT:    vsha2ch.vv v8, v9, v10
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i64> @llvm.riscv.vsha2cl.nxv1i64.nxv1i64(
+    <vscale x 1 x i64> %0,
+    <vscale x 1 x i64> %1,
+    <vscale x 1 x i64> %2,
+    iXLen %3,
+    iXLen 2)
+
+  ret <vscale x 1 x i64> %a
+}
+
+declare <vscale x 2 x i64> @llvm.riscv.vsha2cl.nxv2i64.nxv2i64(
+  <vscale x 2 x i64>,
+  <vscale x 2 x i64>,
+  <vscale x 2 x i64>,
+  iXLen,
+  iXLen)
+
+define <vscale x 2 x i64> @intrinsic_vsha2cl_vv_nxv2i64_nxv2i64(<vscale x 2 x i64> %0, <vscale x 2 x i64> %1, <vscale x 2 x i64> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vsha2cl_vv_nxv2i64_nxv2i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e64, m2, tu, ma
+; CHECK-NEXT:    vsha2ch.vv v8, v10, v12
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i64> @llvm.riscv.vsha2cl.nxv2i64.nxv2i64(
+    <vscale x 2 x i64> %0,
+    <vscale x 2 x i64> %1,
+    <vscale x 2 x i64> %2,
+    iXLen %3,
+    iXLen 2)
+
+  ret <vscale x 2 x i64> %a
+}
+
+declare <vscale x 4 x i64> @llvm.riscv.vsha2cl.nxv4i64.nxv4i64(
+  <vscale x 4 x i64>,
+  <vscale x 4 x i64>,
+  <vscale x 4 x i64>,
+  iXLen,
+  iXLen)
+
+define <vscale x 4 x i64> @intrinsic_vsha2cl_vv_nxv4i64_nxv4i64(<vscale x 4 x i64> %0, <vscale x 4 x i64> %1, <vscale x 4 x i64> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vsha2cl_vv_nxv4i64_nxv4i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e64, m4, tu, ma
+; CHECK-NEXT:    vsha2ch.vv v8, v12, v16
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i64> @llvm.riscv.vsha2cl.nxv4i64.nxv4i64(
+    <vscale x 4 x i64> %0,
+    <vscale x 4 x i64> %1,
+    <vscale x 4 x i64> %2,
+    iXLen %3,
+    iXLen 2)
+
+  ret <vscale x 4 x i64> %a
+}
+
+declare <vscale x 8 x i64> @llvm.riscv.vsha2cl.nxv8i64.nxv8i64(
+  <vscale x 8 x i64>,
+  <vscale x 8 x i64>,
+  <vscale x 8 x i64>,
+  iXLen,
+  iXLen)
+
+define <vscale x 8 x i64> @intrinsic_vsha2cl_vv_nxv8i64_nxv8i64(<vscale x 8 x i64> %0, <vscale x 8 x i64> %1, <vscale x 8 x i64> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vsha2cl_vv_nxv8i64_nxv8i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vl8re64.v v24, (a0)
+; CHECK-NEXT:    vsetvli zero, a1, e64, m8, tu, ma
+; CHECK-NEXT:    vsha2ch.vv v8, v16, v24
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i64> @llvm.riscv.vsha2cl.nxv8i64.nxv8i64(
+    <vscale x 8 x i64> %0,
+    <vscale x 8 x i64> %1,
+    <vscale x 8 x i64> %2,
+    iXLen %3,
+    iXLen 2)
+
+  ret <vscale x 8 x i64> %a
+}

llvm/test/CodeGen/RISCV/rvv/vsha2ms.ll

+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: sed 's/iXLen/i32/g' %s | llc -mtriple=riscv32 -mattr=+v,+experimental-zvknha,+experimental-zvknhb \
+; RUN:   -verify-machineinstrs | FileCheck %s --check-prefixes=CHECK
+; RUN: sed 's/iXLen/i64/g' %s | llc -mtriple=riscv64 -mattr=+v,+experimental-zvknha,+experimental-zvknhb \
+; RUN:   -verify-machineinstrs | FileCheck %s --check-prefixes=CHECK
+
+declare <vscale x 1 x i32> @llvm.riscv.vsha2ms.nxv1i32.nxv1i32(
+  <vscale x 1 x i32>,
+  <vscale x 1 x i32>,
+  <vscale x 1 x i32>,
+  iXLen,
+  iXLen)
+
+define <vscale x 1 x i32> @intrinsic_vsha2ms_vv_nxv1i32_nxv1i32(<vscale x 1 x i32> %0, <vscale x 1 x i32> %1, <vscale x 1 x i32> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vsha2ms_vv_nxv1i32_nxv1i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, mf2, tu, ma
+; CHECK-NEXT:    vsha2ms.vv v8, v9, v10
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i32> @llvm.riscv.vsha2ms.nxv1i32.nxv1i32(
+    <vscale x 1 x i32> %0,
+    <vscale x 1 x i32> %1,
+    <vscale x 1 x i32> %2,
+    iXLen %3,
+    iXLen 2)
+
+  ret <vscale x 1 x i32> %a
+}
+
+declare <vscale x 2 x i32> @llvm.riscv.vsha2ms.nxv2i32.nxv2i32(
+  <vscale x 2 x i32>,
+  <vscale x 2 x i32>,
+  <vscale x 2 x i32>,
+  iXLen,
+  iXLen)
+
+define <vscale x 2 x i32> @intrinsic_vsha2ms_vv_nxv2i32_nxv2i32(<vscale x 2 x i32> %0, <vscale x 2 x i32> %1, <vscale x 2 x i32> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vsha2ms_vv_nxv2i32_nxv2i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m1, tu, ma
+; CHECK-NEXT:    vsha2ms.vv v8, v9, v10
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i32> @llvm.riscv.vsha2ms.nxv2i32.nxv2i32(
+    <vscale x 2 x i32> %0,
+    <vscale x 2 x i32> %1,
+    <vscale x 2 x i32> %2,
+    iXLen %3,
+    iXLen 2)
+
+  ret <vscale x 2 x i32> %a
+}
+
+declare <vscale x 4 x i32> @llvm.riscv.vsha2ms.nxv4i32.nxv4i32(
+  <vscale x 4 x i32>,
+  <vscale x 4 x i32>,
+  <vscale x 4 x i32>,
+  iXLen,
+  iXLen)
+
+define <vscale x 4 x i32> @intrinsic_vsha2ms_vv_nxv4i32_nxv4i32(<vscale x 4 x i32> %0, <vscale x 4 x i32> %1, <vscale x 4 x i32> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vsha2ms_vv_nxv4i32_nxv4i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m2, tu, ma
+; CHECK-NEXT:    vsha2ms.vv v8, v10, v12
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i32> @llvm.riscv.vsha2ms.nxv4i32.nxv4i32(
+    <vscale x 4 x i32> %0,
+    <vscale x 4 x i32> %1,
+    <vscale x 4 x i32> %2,
+    iXLen %3,
+    iXLen 2)
+
+  ret <vscale x 4 x i32> %a
+}
+
+declare <vscale x 8 x i32> @llvm.riscv.vsha2ms.nxv8i32.nxv8i32(
+  <vscale x 8 x i32>,
+  <vscale x 8 x i32>,
+  <vscale x 8 x i32>,
+  iXLen,
+  iXLen)
+
+define <vscale x 8 x i32> @intrinsic_vsha2ms_vv_nxv8i32_nxv8i32(<vscale x 8 x i32> %0, <vscale x 8 x i32> %1, <vscale x 8 x i32> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vsha2ms_vv_nxv8i32_nxv8i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m4, tu, ma
+; CHECK-NEXT:    vsha2ms.vv v8, v12, v16
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i32> @llvm.riscv.vsha2ms.nxv8i32.nxv8i32(
+    <vscale x 8 x i32> %0,
+    <vscale x 8 x i32> %1,
+    <vscale x 8 x i32> %2,
+    iXLen %3,
+    iXLen 2)
+
+  ret <vscale x 8 x i32> %a
+}
+
+declare <vscale x 16 x i32> @llvm.riscv.vsha2ms.nxv16i32.nxv16i32(
+  <vscale x 16 x i32>,
+  <vscale x 16 x i32>,
+  <vscale x 16 x i32>,
+  iXLen,
+  iXLen)
+
+define <vscale x 16 x i32> @intrinsic_vsha2ms_vv_nxv16i32_nxv16i32(<vscale x 16 x i32> %0, <vscale x 16 x i32> %1, <vscale x 16 x i32> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vsha2ms_vv_nxv16i32_nxv16i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vl8re32.v v24, (a0)
+; CHECK-NEXT:    vsetvli zero, a1, e32, m8, tu, ma
+; CHECK-NEXT:    vsha2ms.vv v8, v16, v24
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 16 x i32> @llvm.riscv.vsha2ms.nxv16i32.nxv16i32(
+    <vscale x 16 x i32> %0,
+    <vscale x 16 x i32> %1,
+    <vscale x 16 x i32> %2,
+    iXLen %3,
+    iXLen 2)
+
+  ret <vscale x 16 x i32> %a
+}
+
+declare <vscale x 1 x i64> @llvm.riscv.vsha2ms.nxv1i64.nxv1i64(
+  <vscale x 1 x i64>,
+  <vscale x 1 x i64>,
+  <vscale x 1 x i64>,
+  iXLen,
+  iXLen)
+
+define <vscale x 1 x i64> @intrinsic_vsha2ms_vv_nxv1i64_nxv1i64(<vscale x 1 x i64> %0, <vscale x 1 x i64> %1, <vscale x 1 x i64> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vsha2ms_vv_nxv1i64_nxv1i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e64, m1, tu, ma
+; CHECK-NEXT:    vsha2ms.vv v8, v9, v10
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i64> @llvm.riscv.vsha2ms.nxv1i64.nxv1i64(
+    <vscale x 1 x i64> %0,
+    <vscale x 1 x i64> %1,
+    <vscale x 1 x i64> %2,
+    iXLen %3,
+    iXLen 2)
+
+  ret <vscale x 1 x i64> %a
+}
+
+declare <vscale x 2 x i64> @llvm.riscv.vsha2ms.nxv2i64.nxv2i64(
+  <vscale x 2 x i64>,
+  <vscale x 2 x i64>,
+  <vscale x 2 x i64>,
+  iXLen,
+  iXLen)
+
+define <vscale x 2 x i64> @intrinsic_vsha2ms_vv_nxv2i64_nxv2i64(<vscale x 2 x i64> %0, <vscale x 2 x i64> %1, <vscale x 2 x i64> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vsha2ms_vv_nxv2i64_nxv2i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e64, m2, tu, ma
+; CHECK-NEXT:    vsha2ms.vv v8, v10, v12
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i64> @llvm.riscv.vsha2ms.nxv2i64.nxv2i64(
+    <vscale x 2 x i64> %0,
+    <vscale x 2 x i64> %1,
+    <vscale x 2 x i64> %2,
+    iXLen %3,
+    iXLen 2)
+
+  ret <vscale x 2 x i64> %a
+}
+
+declare <vscale x 4 x i64> @llvm.riscv.vsha2ms.nxv4i64.nxv4i64(
+  <vscale x 4 x i64>,
+  <vscale x 4 x i64>,
+  <vscale x 4 x i64>,
+  iXLen,
+  iXLen)
+
+define <vscale x 4 x i64> @intrinsic_vsha2ms_vv_nxv4i64_nxv4i64(<vscale x 4 x i64> %0, <vscale x 4 x i64> %1, <vscale x 4 x i64> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vsha2ms_vv_nxv4i64_nxv4i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e64, m4, tu, ma
+; CHECK-NEXT:    vsha2ms.vv v8, v12, v16
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i64> @llvm.riscv.vsha2ms.nxv4i64.nxv4i64(
+    <vscale x 4 x i64> %0,
+    <vscale x 4 x i64> %1,
+    <vscale x 4 x i64> %2,
+    iXLen %3,
+    iXLen 2)
+
+  ret <vscale x 4 x i64> %a
+}
+
+declare <vscale x 8 x i64> @llvm.riscv.vsha2ms.nxv8i64.nxv8i64(
+  <vscale x 8 x i64>,
+  <vscale x 8 x i64>,
+  <vscale x 8 x i64>,
+  iXLen,
+  iXLen)
+
+define <vscale x 8 x i64> @intrinsic_vsha2ms_vv_nxv8i64_nxv8i64(<vscale x 8 x i64> %0, <vscale x 8 x i64> %1, <vscale x 8 x i64> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vsha2ms_vv_nxv8i64_nxv8i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vl8re64.v v24, (a0)
+; CHECK-NEXT:    vsetvli zero, a1, e64, m8, tu, ma
+; CHECK-NEXT:    vsha2ms.vv v8, v16, v24
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i64> @llvm.riscv.vsha2ms.nxv8i64.nxv8i64(
+    <vscale x 8 x i64> %0,
+    <vscale x 8 x i64> %1,
+    <vscale x 8 x i64> %2,
+    iXLen %3,
+    iXLen 2)
+
+  ret <vscale x 8 x i64> %a
+}

llvm/test/CodeGen/RISCV/rvv/vsm3c.ll

+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: sed 's/iXLen/i32/g' %s | llc -mtriple=riscv32 -mattr=+v,+experimental-zvksh \
+; RUN:   -verify-machineinstrs | FileCheck %s --check-prefixes=CHECK
+; RUN: sed 's/iXLen/i64/g' %s | llc -mtriple=riscv64 -mattr=+v,+experimental-zvksh \
+; RUN:   -verify-machineinstrs | FileCheck %s --check-prefixes=CHECK
+
+declare <vscale x 1 x i32> @llvm.riscv.vsm3c.nxv1i32.i32(
+  <vscale x 1 x i32>,
+  <vscale x 1 x i32>,
+  i32,
+  iXLen,
+  iXLen)
+
+define <vscale x 1 x i32> @intrinsic_vsm3c_vi_nxv1i32_i32(<vscale x 1 x i32> %0, <vscale x 1 x i32> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vsm3c_vi_nxv1i32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, mf2, tu, ma
+; CHECK-NEXT:    vsm3c.vi v8, v9, 2
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i32> @llvm.riscv.vsm3c.nxv1i32.i32(
+    <vscale x 1 x i32> %0,
+    <vscale x 1 x i32> %1,
+    i32 2,
+    iXLen %2,
+    iXLen 2)
+
+  ret <vscale x 1 x i32> %a
+}
+
+declare <vscale x 2 x i32> @llvm.riscv.vsm3c.nxv2i32.i32(
+  <vscale x 2 x i32>,
+  <vscale x 2 x i32>,
+  i32,
+  iXLen,
+  iXLen)
+
+define <vscale x 2 x i32> @intrinsic_vsm3c_vi_nxv2i32_i32(<vscale x 2 x i32> %0, <vscale x 2 x i32> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vsm3c_vi_nxv2i32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m1, tu, ma
+; CHECK-NEXT:    vsm3c.vi v8, v9, 2
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i32> @llvm.riscv.vsm3c.nxv2i32.i32(
+    <vscale x 2 x i32> %0,
+    <vscale x 2 x i32> %1,
+    i32 2,
+    iXLen %2,
+    iXLen 2)
+
+  ret <vscale x 2 x i32> %a
+}
+
+declare <vscale x 4 x i32> @llvm.riscv.vsm3c.nxv4i32.i32(
+  <vscale x 4 x i32>,
+  <vscale x 4 x i32>,
+  i32,
+  iXLen,
+  iXLen)
+
+define <vscale x 4 x i32> @intrinsic_vsm3c_vi_nxv4i32_i32(<vscale x 4 x i32> %0, <vscale x 4 x i32> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vsm3c_vi_nxv4i32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m2, tu, ma
+; CHECK-NEXT:    vsm3c.vi v8, v10, 2
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i32> @llvm.riscv.vsm3c.nxv4i32.i32(
+    <vscale x 4 x i32> %0,
+    <vscale x 4 x i32> %1,
+    i32 2,
+    iXLen %2,
+    iXLen 2)
+
+  ret <vscale x 4 x i32> %a
+}
+
+declare <vscale x 8 x i32> @llvm.riscv.vsm3c.nxv8i32.i32(
+  <vscale x 8 x i32>,
+  <vscale x 8 x i32>,
+  i32,
+  iXLen,
+  iXLen)
+
+define <vscale x 8 x i32> @intrinsic_vsm3c_vi_nxv8i32_i32(<vscale x 8 x i32> %0, <vscale x 8 x i32> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vsm3c_vi_nxv8i32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m4, tu, ma
+; CHECK-NEXT:    vsm3c.vi v8, v12, 2
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i32> @llvm.riscv.vsm3c.nxv8i32.i32(
+    <vscale x 8 x i32> %0,
+    <vscale x 8 x i32> %1,
+    i32 2,
+    iXLen %2,
+    iXLen 2)
+
+  ret <vscale x 8 x i32> %a
+}
+
+declare <vscale x 16 x i32> @llvm.riscv.vsm3c.nxv16i32.i32(
+  <vscale x 16 x i32>,
+  <vscale x 16 x i32>,
+  i32,
+  iXLen,
+  iXLen)
+
+define <vscale x 16 x i32> @intrinsic_vsm3c_vi_nxv16i32_i32(<vscale x 16 x i32> %0, <vscale x 16 x i32> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vsm3c_vi_nxv16i32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m8, tu, ma
+; CHECK-NEXT:    vsm3c.vi v8, v16, 2
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 16 x i32> @llvm.riscv.vsm3c.nxv16i32.i32(
+    <vscale x 16 x i32> %0,
+    <vscale x 16 x i32> %1,
+    i32 2,
+    iXLen %2,
+    iXLen 2)
+
+  ret <vscale x 16 x i32> %a
+}

llvm/test/CodeGen/RISCV/rvv/vsm3me.ll

+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: sed 's/iXLen/i32/g' %s | llc -mtriple=riscv32 -mattr=+v,+experimental-zvksh \
+; RUN:   -verify-machineinstrs | FileCheck %s --check-prefixes=CHECK
+; RUN: sed 's/iXLen/i64/g' %s | llc -mtriple=riscv64 -mattr=+v,+experimental-zvksh \
+; RUN:   -verify-machineinstrs | FileCheck %s --check-prefixes=CHECK
+
+declare <vscale x 1 x i32> @llvm.riscv.vsm3me.nxv1i32.nxv1i32(
+  <vscale x 1 x i32>,
+  <vscale x 1 x i32>,
+  <vscale x 1 x i32>,
+  iXLen)
+
+define <vscale x 1 x i32> @intrinsic_vsm3me_vv_nxv1i32_nxv1i32(<vscale x 1 x i32> %0, <vscale x 1 x i32> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vsm3me_vv_nxv1i32_nxv1i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m1, ta, ma
+; CHECK-NEXT:    vsm3me.vv v8, v8, v9
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i32> @llvm.riscv.vsm3me.nxv1i32.nxv1i32(
+    <vscale x 1 x i32> undef,
+    <vscale x 1 x i32> %0,
+    <vscale x 1 x i32> %1,
+    iXLen %2)
+
+  ret <vscale x 1 x i32> %a
+}
+
+declare <vscale x 2 x i32> @llvm.riscv.vsm3me.nxv2i32.nxv2i32(
+  <vscale x 2 x i32>,
+  <vscale x 2 x i32>,
+  <vscale x 2 x i32>,
+  iXLen)
+
+define <vscale x 2 x i32> @intrinsic_vsm3me_vv_nxv2i32_nxv2i32(<vscale x 2 x i32> %0, <vscale x 2 x i32> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vsm3me_vv_nxv2i32_nxv2i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m1, ta, ma
+; CHECK-NEXT:    vsm3me.vv v8, v8, v9
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i32> @llvm.riscv.vsm3me.nxv2i32.nxv2i32(
+    <vscale x 2 x i32> undef,
+    <vscale x 2 x i32> %0,
+    <vscale x 2 x i32> %1,
+    iXLen %2)
+
+  ret <vscale x 2 x i32> %a
+}
+
+declare <vscale x 4 x i32> @llvm.riscv.vsm3me.nxv4i32.nxv4i32(
+  <vscale x 4 x i32>,
+  <vscale x 4 x i32>,
+  <vscale x 4 x i32>,
+  iXLen)
+
+define <vscale x 4 x i32> @intrinsic_vsm3me_vv_nxv4i32_nxv4i32(<vscale x 4 x i32> %0, <vscale x 4 x i32> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vsm3me_vv_nxv4i32_nxv4i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m1, ta, ma
+; CHECK-NEXT:    vsm3me.vv v8, v8, v10
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i32> @llvm.riscv.vsm3me.nxv4i32.nxv4i32(
+    <vscale x 4 x i32> undef,
+    <vscale x 4 x i32> %0,
+    <vscale x 4 x i32> %1,
+    iXLen %2)
+
+  ret <vscale x 4 x i32> %a
+}
+
+declare <vscale x 8 x i32> @llvm.riscv.vsm3me.nxv8i32.nxv8i32(
+  <vscale x 8 x i32>,
+  <vscale x 8 x i32>,
+  <vscale x 8 x i32>,
+  iXLen)
+
+define <vscale x 8 x i32> @intrinsic_vsm3me_vv_nxv8i32_nxv8i32(<vscale x 8 x i32> %0, <vscale x 8 x i32> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vsm3me_vv_nxv8i32_nxv8i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m1, ta, ma
+; CHECK-NEXT:    vsm3me.vv v8, v8, v12
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i32> @llvm.riscv.vsm3me.nxv8i32.nxv8i32(
+    <vscale x 8 x i32> undef,
+    <vscale x 8 x i32> %0,
+    <vscale x 8 x i32> %1,
+    iXLen %2)
+
+  ret <vscale x 8 x i32> %a
+}
+
+declare <vscale x 16 x i32> @llvm.riscv.vsm3me.nxv16i32.nxv16i32(
+  <vscale x 16 x i32>,
+  <vscale x 16 x i32>,
+  <vscale x 16 x i32>,
+  iXLen)
+
+define <vscale x 16 x i32> @intrinsic_vsm3me_vv_nxv16i32_nxv16i32(<vscale x 16 x i32> %0, <vscale x 16 x i32> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vsm3me_vv_nxv16i32_nxv16i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m1, ta, ma
+; CHECK-NEXT:    vsm3me.vv v8, v8, v16
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 16 x i32> @llvm.riscv.vsm3me.nxv16i32.nxv16i32(
+    <vscale x 16 x i32> undef,
+    <vscale x 16 x i32> %0,
+    <vscale x 16 x i32> %1,
+    iXLen %2)
+
+  ret <vscale x 16 x i32> %a
+}

llvm/test/CodeGen/RISCV/rvv/vsm4k.ll

+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: sed 's/iXLen/i32/g' %s | llc -mtriple=riscv32 -mattr=+v,+experimental-zvksed \
+; RUN:   -verify-machineinstrs | FileCheck %s --check-prefixes=CHECK
+; RUN: sed 's/iXLen/i64/g' %s | llc -mtriple=riscv64 -mattr=+v,+experimental-zvksed \
+; RUN:   -verify-machineinstrs | FileCheck %s --check-prefixes=CHECK
+
+declare <vscale x 1 x i32> @llvm.riscv.vsm4k.nxv1i32.i32(
+  <vscale x 1 x i32>,
+  <vscale x 1 x i32>,
+  i32,
+  iXLen)
+
+define <vscale x 1 x i32> @intrinsic_vsm4k_vi_nxv1i32_i32(<vscale x 1 x i32> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vsm4k_vi_nxv1i32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m1, ta, ma
+; CHECK-NEXT:    vsm4k.vi v8, v8, 2
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i32> @llvm.riscv.vsm4k.nxv1i32.i32(
+    <vscale x 1 x i32> undef,
+    <vscale x 1 x i32> %0,
+    i32 2,
+    iXLen %1)
+
+  ret <vscale x 1 x i32> %a
+}
+
+declare <vscale x 2 x i32> @llvm.riscv.vsm4k.nxv2i32.i32(
+  <vscale x 2 x i32>,
+  <vscale x 2 x i32>,
+  i32,
+  iXLen)
+
+define <vscale x 2 x i32> @intrinsic_vsm4k_vi_nxv2i32_i32(<vscale x 2 x i32> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vsm4k_vi_nxv2i32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m1, ta, ma
+; CHECK-NEXT:    vsm4k.vi v8, v8, 2
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i32> @llvm.riscv.vsm4k.nxv2i32.i32(
+    <vscale x 2 x i32> undef,
+    <vscale x 2 x i32> %0,
+    i32 2,
+    iXLen %1)
+
+  ret <vscale x 2 x i32> %a
+}
+
+declare <vscale x 4 x i32> @llvm.riscv.vsm4k.nxv4i32.i32(
+  <vscale x 4 x i32>,
+  <vscale x 4 x i32>,
+  i32,
+  iXLen)
+
+define <vscale x 4 x i32> @intrinsic_vsm4k_vi_nxv4i32_i32(<vscale x 4 x i32> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vsm4k_vi_nxv4i32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m1, ta, ma
+; CHECK-NEXT:    vsm4k.vi v8, v8, 2
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i32> @llvm.riscv.vsm4k.nxv4i32.i32(
+    <vscale x 4 x i32> undef,
+    <vscale x 4 x i32> %0,
+    i32 2,
+    iXLen %1)
+
+  ret <vscale x 4 x i32> %a
+}
+
+declare <vscale x 8 x i32> @llvm.riscv.vsm4k.nxv8i32.i32(
+  <vscale x 8 x i32>,
+  <vscale x 8 x i32>,
+  i32,
+  iXLen)
+
+define <vscale x 8 x i32> @intrinsic_vsm4k_vi_nxv8i32_i32(<vscale x 8 x i32> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vsm4k_vi_nxv8i32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m1, ta, ma
+; CHECK-NEXT:    vsm4k.vi v8, v8, 2
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i32> @llvm.riscv.vsm4k.nxv8i32.i32(
+    <vscale x 8 x i32> undef,
+    <vscale x 8 x i32> %0,
+    i32 2,
+    iXLen %1)
+
+  ret <vscale x 8 x i32> %a
+}
+
+declare <vscale x 16 x i32> @llvm.riscv.vsm4k.nxv16i32.i32(
+  <vscale x 16 x i32>,
+  <vscale x 16 x i32>,
+  i32,
+  iXLen)
+
+define <vscale x 16 x i32> @intrinsic_vsm4k_vi_nxv16i32_i32(<vscale x 16 x i32> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vsm4k_vi_nxv16i32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m1, ta, ma
+; CHECK-NEXT:    vsm4k.vi v8, v8, 2
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 16 x i32> @llvm.riscv.vsm4k.nxv16i32.i32(
+    <vscale x 16 x i32> undef,
+    <vscale x 16 x i32> %0,
+    i32 2,
+    iXLen %1)
+
+  ret <vscale x 16 x i32> %a
+}

llvm/test/CodeGen/RISCV/rvv/vsm4r.ll

+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: sed 's/iXLen/i32/g' %s | llc -mtriple=riscv32 -mattr=+v,+experimental-zvksed \
+; RUN:   -verify-machineinstrs | FileCheck %s --check-prefixes=CHECK
+; RUN: sed 's/iXLen/i64/g' %s | llc -mtriple=riscv64 -mattr=+v,+experimental-zvksed \
+; RUN:   -verify-machineinstrs | FileCheck %s --check-prefixes=CHECK
+
+declare <vscale x 1 x i32> @llvm.riscv.vsm4r.vv.nxv1i32(
+  <vscale x 1 x i32>,
+  <vscale x 1 x i32>,
+  iXLen, iXLen);
+
+define <vscale x 1 x i32> @intrinsic_vsm4r_vv_nxv1i32(<vscale x 1 x i32> %0, <vscale x 1 x i32> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vsm4r_vv_nxv1i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, mf2, tu, ma
+; CHECK-NEXT:    vsm4r.vv v8, v9
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i32> @llvm.riscv.vsm4r.vv.nxv1i32(
+    <vscale x 1 x i32> %0,
+    <vscale x 1 x i32> %1,
+    iXLen %2, iXLen 2)
+
+  ret <vscale x 1 x i32> %a
+}
+
+declare <vscale x 2 x i32> @llvm.riscv.vsm4r.vv.nxv2i32(
+  <vscale x 2 x i32>,
+  <vscale x 2 x i32>,
+  iXLen, iXLen);
+
+define <vscale x 2 x i32> @intrinsic_vsm4r_vv_nxv2i32(<vscale x 2 x i32> %0, <vscale x 2 x i32> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vsm4r_vv_nxv2i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m1, tu, ma
+; CHECK-NEXT:    vsm4r.vv v8, v9
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i32> @llvm.riscv.vsm4r.vv.nxv2i32(
+    <vscale x 2 x i32> %0,
+    <vscale x 2 x i32> %1,
+    iXLen %2, iXLen 2)
+
+  ret <vscale x 2 x i32> %a
+}
+
+declare <vscale x 4 x i32> @llvm.riscv.vsm4r.vv.nxv4i32(
+  <vscale x 4 x i32>,
+  <vscale x 4 x i32>,
+  iXLen, iXLen);
+
+define <vscale x 4 x i32> @intrinsic_vsm4r_vv_nxv4i32(<vscale x 4 x i32> %0, <vscale x 4 x i32> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vsm4r_vv_nxv4i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m2, tu, ma
+; CHECK-NEXT:    vsm4r.vv v8, v10
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i32> @llvm.riscv.vsm4r.vv.nxv4i32(
+    <vscale x 4 x i32> %0,
+    <vscale x 4 x i32> %1,
+    iXLen %2, iXLen 2)
+
+  ret <vscale x 4 x i32> %a
+}
+
+declare <vscale x 8 x i32> @llvm.riscv.vsm4r.vv.nxv8i32(
+  <vscale x 8 x i32>,
+  <vscale x 8 x i32>,
+  iXLen, iXLen);
+
+define <vscale x 8 x i32> @intrinsic_vsm4r_vv_nxv8i32(<vscale x 8 x i32> %0, <vscale x 8 x i32> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vsm4r_vv_nxv8i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m4, tu, ma
+; CHECK-NEXT:    vsm4r.vv v8, v12
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i32> @llvm.riscv.vsm4r.vv.nxv8i32(
+    <vscale x 8 x i32> %0,
+    <vscale x 8 x i32> %1,
+    iXLen %2, iXLen 2)
+
+  ret <vscale x 8 x i32> %a
+}
+
+declare <vscale x 16 x i32> @llvm.riscv.vsm4r.vv.nxv16i32(
+  <vscale x 16 x i32>,
+  <vscale x 16 x i32>,
+  iXLen, iXLen);
+
+define <vscale x 16 x i32> @intrinsic_vsm4r_vv_nxv16i32(<vscale x 16 x i32> %0, <vscale x 16 x i32> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vsm4r_vv_nxv16i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m8, tu, ma
+; CHECK-NEXT:    vsm4r.vv v8, v16
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 16 x i32> @llvm.riscv.vsm4r.vv.nxv16i32(
+    <vscale x 16 x i32> %0,
+    <vscale x 16 x i32> %1,
+    iXLen %2, iXLen 2)
+
+  ret <vscale x 16 x i32> %a
+}
+
+declare <vscale x 1 x i32> @llvm.riscv.vsm4r.vs.nxv1i32(
+  <vscale x 1 x i32>,
+  <vscale x 2 x i32>,
+  iXLen, iXLen);
+
+
+define <vscale x 1 x i32> @intrinsic_vsm4r_vs_nxv1i32(<vscale x 1 x i32> %0, <vscale x 2 x i32> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vsm4r_vs_nxv1i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, mf2, tu, ma
+; CHECK-NEXT:    vsm4r.vs v8, v9
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i32> @llvm.riscv.vsm4r.vs.nxv1i32(
+    <vscale x 1 x i32> %0,
+    <vscale x 2 x i32> %1,
+    iXLen %2, iXLen 2)
+
+  ret <vscale x 1 x i32> %a
+}
+
+declare <vscale x 2 x i32> @llvm.riscv.vsm4r.vs.nxv2i32(
+  <vscale x 2 x i32>,
+  <vscale x 2 x i32>,
+  iXLen, iXLen);
+
+define <vscale x 2 x i32> @intrinsic_vsm4r_vs_nxv2i32(<vscale x 2 x i32> %0, <vscale x 2 x i32> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vsm4r_vs_nxv2i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m1, tu, ma
+; CHECK-NEXT:    vsm4r.vs v8, v9
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i32> @llvm.riscv.vsm4r.vs.nxv2i32(
+    <vscale x 2 x i32> %0,
+    <vscale x 2 x i32> %1,
+    iXLen %2, iXLen 2)
+
+  ret <vscale x 2 x i32> %a
+}
+
+declare <vscale x 4 x i32> @llvm.riscv.vsm4r.vs.nxv4i32(
+  <vscale x 4 x i32>,
+  <vscale x 2 x i32>,
+  iXLen, iXLen);
+
+define <vscale x 4 x i32> @intrinsic_vsm4r_vs_nxv4i32(<vscale x 4 x i32> %0, <vscale x 2 x i32> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vsm4r_vs_nxv4i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m2, tu, ma
+; CHECK-NEXT:    vsm4r.vs v8, v10
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i32> @llvm.riscv.vsm4r.vs.nxv4i32(
+    <vscale x 4 x i32> %0,
+    <vscale x 2 x i32> %1,
+    iXLen %2, iXLen 2)
+
+  ret <vscale x 4 x i32> %a
+}
+
+declare <vscale x 8 x i32> @llvm.riscv.vsm4r.vs.nxv8i32(
+  <vscale x 8 x i32>,
+  <vscale x 2 x i32>,
+  iXLen, iXLen);
+
+define <vscale x 8 x i32> @intrinsic_vsm4r_vs_nxv8i32(<vscale x 8 x i32> %0, <vscale x 2 x i32> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vsm4r_vs_nxv8i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m4, tu, ma
+; CHECK-NEXT:    vsm4r.vs v8, v12
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i32> @llvm.riscv.vsm4r.vs.nxv8i32(
+    <vscale x 8 x i32> %0,
+    <vscale x 2 x i32> %1,
+    iXLen %2, iXLen 2)
+
+  ret <vscale x 8 x i32> %a
+}
+
+declare <vscale x 16 x i32> @llvm.riscv.vsm4r.vs.nxv16i32(
+  <vscale x 16 x i32>,
+  <vscale x 2 x i32>,
+  iXLen, iXLen);
+
+define <vscale x 16 x i32> @intrinsic_vsm4r_vs_nxv16i32(<vscale x 16 x i32> %0, <vscale x 2 x i32> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vsm4r_vs_nxv16i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m8, tu, ma
+; CHECK-NEXT:    vsm4r.vs v8, v16
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 16 x i32> @llvm.riscv.vsm4r.vs.nxv16i32(
+    <vscale x 16 x i32> %0,
+    <vscale x 2 x i32> %1,
+    iXLen %2, iXLen 2)
+
+  ret <vscale x 16 x i32> %a
+}

llvm/test/CodeGen/RISCV/rvv/vwsll.ll

+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: sed 's/iXLen/i32/g' %s | llc -mtriple=riscv32 -mattr=+v,+experimental-zvbb \
+; RUN:   -verify-machineinstrs | FileCheck %s --check-prefixes=CHECK
+; RUN: sed 's/iXLen/i64/g' %s | llc -mtriple=riscv64 -mattr=+v,+experimental-zvbb \
+; RUN:   -verify-machineinstrs | FileCheck %s --check-prefixes=CHECK
+
+declare <vscale x 1 x i16> @llvm.riscv.vwsll.nxv1i16.nxv1i8.nxv1i8(
+  <vscale x 1 x i16>,
+  <vscale x 1 x i8>,
+  <vscale x 1 x i8>,
+  iXLen);
+
+define <vscale x 1 x i16> @intrinsic_vwsll_vv_nxv1i16_nxv1i8_nxv1i8(<vscale x 1 x i8> %0, <vscale x 1 x i8> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vwsll_vv_nxv1i16_nxv1i8_nxv1i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, mf8, ta, ma
+; CHECK-NEXT:    vwsll.vv v10, v8, v9
+; CHECK-NEXT:    vmv1r.v v8, v10
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i16> @llvm.riscv.vwsll.nxv1i16.nxv1i8.nxv1i8(
+    <vscale x 1 x i16> undef,
+    <vscale x 1 x i8> %0,
+    <vscale x 1 x i8> %1,
+    iXLen %2)
+
+  ret <vscale x 1 x i16> %a
+}
+
+declare <vscale x 1 x i16> @llvm.riscv.vwsll.mask.nxv1i16.nxv1i8.nxv1i8(
+  <vscale x 1 x i16>,
+  <vscale x 1 x i8>,
+  <vscale x 1 x i8>,
+  <vscale x 1 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 1 x i16> @intrinsic_vwsll_mask_vv_nxv1i16_nxv1i8_nxv1i8(<vscale x 1 x i16> %0, <vscale x 1 x i8> %1, <vscale x 1 x i8> %2, <vscale x 1 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vwsll_mask_vv_nxv1i16_nxv1i8_nxv1i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, mf8, ta, mu
+; CHECK-NEXT:    vwsll.vv v8, v9, v10, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i16> @llvm.riscv.vwsll.mask.nxv1i16.nxv1i8.nxv1i8(
+    <vscale x 1 x i16> %0,
+    <vscale x 1 x i8> %1,
+    <vscale x 1 x i8> %2,
+    <vscale x 1 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 1 x i16> %a
+}
+
+declare <vscale x 2 x i16> @llvm.riscv.vwsll.nxv2i16.nxv2i8.nxv2i8(
+  <vscale x 2 x i16>,
+  <vscale x 2 x i8>,
+  <vscale x 2 x i8>,
+  iXLen);
+
+define <vscale x 2 x i16> @intrinsic_vwsll_vv_nxv2i16_nxv2i8_nxv2i8(<vscale x 2 x i8> %0, <vscale x 2 x i8> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vwsll_vv_nxv2i16_nxv2i8_nxv2i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, mf4, ta, ma
+; CHECK-NEXT:    vwsll.vv v10, v8, v9
+; CHECK-NEXT:    vmv1r.v v8, v10
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i16> @llvm.riscv.vwsll.nxv2i16.nxv2i8.nxv2i8(
+    <vscale x 2 x i16> undef,
+    <vscale x 2 x i8> %0,
+    <vscale x 2 x i8> %1,
+    iXLen %2)
+
+  ret <vscale x 2 x i16> %a
+}
+
+declare <vscale x 2 x i16> @llvm.riscv.vwsll.mask.nxv2i16.nxv2i8.nxv2i8(
+  <vscale x 2 x i16>,
+  <vscale x 2 x i8>,
+  <vscale x 2 x i8>,
+  <vscale x 2 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 2 x i16> @intrinsic_vwsll_mask_vv_nxv2i16_nxv2i8_nxv2i8(<vscale x 2 x i16> %0, <vscale x 2 x i8> %1, <vscale x 2 x i8> %2, <vscale x 2 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vwsll_mask_vv_nxv2i16_nxv2i8_nxv2i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, mf4, ta, mu
+; CHECK-NEXT:    vwsll.vv v8, v9, v10, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i16> @llvm.riscv.vwsll.mask.nxv2i16.nxv2i8.nxv2i8(
+    <vscale x 2 x i16> %0,
+    <vscale x 2 x i8> %1,
+    <vscale x 2 x i8> %2,
+    <vscale x 2 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 2 x i16> %a
+}
+
+declare <vscale x 4 x i16> @llvm.riscv.vwsll.nxv4i16.nxv4i8.nxv4i8(
+  <vscale x 4 x i16>,
+  <vscale x 4 x i8>,
+  <vscale x 4 x i8>,
+  iXLen);
+
+define <vscale x 4 x i16> @intrinsic_vwsll_vv_nxv4i16_nxv4i8_nxv4i8(<vscale x 4 x i8> %0, <vscale x 4 x i8> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vwsll_vv_nxv4i16_nxv4i8_nxv4i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, mf2, ta, ma
+; CHECK-NEXT:    vwsll.vv v10, v8, v9
+; CHECK-NEXT:    vmv1r.v v8, v10
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i16> @llvm.riscv.vwsll.nxv4i16.nxv4i8.nxv4i8(
+    <vscale x 4 x i16> undef,
+    <vscale x 4 x i8> %0,
+    <vscale x 4 x i8> %1,
+    iXLen %2)
+
+  ret <vscale x 4 x i16> %a
+}
+
+declare <vscale x 4 x i16> @llvm.riscv.vwsll.mask.nxv4i16.nxv4i8.nxv4i8(
+  <vscale x 4 x i16>,
+  <vscale x 4 x i8>,
+  <vscale x 4 x i8>,
+  <vscale x 4 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 4 x i16> @intrinsic_vwsll_mask_vv_nxv4i16_nxv4i8_nxv4i8(<vscale x 4 x i16> %0, <vscale x 4 x i8> %1, <vscale x 4 x i8> %2, <vscale x 4 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vwsll_mask_vv_nxv4i16_nxv4i8_nxv4i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, mf2, ta, mu
+; CHECK-NEXT:    vwsll.vv v8, v9, v10, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i16> @llvm.riscv.vwsll.mask.nxv4i16.nxv4i8.nxv4i8(
+    <vscale x 4 x i16> %0,
+    <vscale x 4 x i8> %1,
+    <vscale x 4 x i8> %2,
+    <vscale x 4 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 4 x i16> %a
+}
+
+declare <vscale x 8 x i16> @llvm.riscv.vwsll.nxv8i16.nxv8i8.nxv8i8(
+  <vscale x 8 x i16>,
+  <vscale x 8 x i8>,
+  <vscale x 8 x i8>,
+  iXLen);
+
+define <vscale x 8 x i16> @intrinsic_vwsll_vv_nxv8i16_nxv8i8_nxv8i8(<vscale x 8 x i8> %0, <vscale x 8 x i8> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vwsll_vv_nxv8i16_nxv8i8_nxv8i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, m1, ta, ma
+; CHECK-NEXT:    vwsll.vv v10, v8, v9
+; CHECK-NEXT:    vmv2r.v v8, v10
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i16> @llvm.riscv.vwsll.nxv8i16.nxv8i8.nxv8i8(
+    <vscale x 8 x i16> undef,
+    <vscale x 8 x i8> %0,
+    <vscale x 8 x i8> %1,
+    iXLen %2)
+
+  ret <vscale x 8 x i16> %a
+}
+
+declare <vscale x 8 x i16> @llvm.riscv.vwsll.mask.nxv8i16.nxv8i8.nxv8i8(
+  <vscale x 8 x i16>,
+  <vscale x 8 x i8>,
+  <vscale x 8 x i8>,
+  <vscale x 8 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 8 x i16> @intrinsic_vwsll_mask_vv_nxv8i16_nxv8i8_nxv8i8(<vscale x 8 x i16> %0, <vscale x 8 x i8> %1, <vscale x 8 x i8> %2, <vscale x 8 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vwsll_mask_vv_nxv8i16_nxv8i8_nxv8i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, m1, ta, mu
+; CHECK-NEXT:    vwsll.vv v8, v10, v11, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i16> @llvm.riscv.vwsll.mask.nxv8i16.nxv8i8.nxv8i8(
+    <vscale x 8 x i16> %0,
+    <vscale x 8 x i8> %1,
+    <vscale x 8 x i8> %2,
+    <vscale x 8 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 8 x i16> %a
+}
+
+declare <vscale x 16 x i16> @llvm.riscv.vwsll.nxv16i16.nxv16i8.nxv16i8(
+  <vscale x 16 x i16>,
+  <vscale x 16 x i8>,
+  <vscale x 16 x i8>,
+  iXLen);
+
+define <vscale x 16 x i16> @intrinsic_vwsll_vv_nxv16i16_nxv16i8_nxv16i8(<vscale x 16 x i8> %0, <vscale x 16 x i8> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vwsll_vv_nxv16i16_nxv16i8_nxv16i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, m2, ta, ma
+; CHECK-NEXT:    vwsll.vv v12, v8, v10
+; CHECK-NEXT:    vmv4r.v v8, v12
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 16 x i16> @llvm.riscv.vwsll.nxv16i16.nxv16i8.nxv16i8(
+    <vscale x 16 x i16> undef,
+    <vscale x 16 x i8> %0,
+    <vscale x 16 x i8> %1,
+    iXLen %2)
+
+  ret <vscale x 16 x i16> %a
+}
+
+declare <vscale x 16 x i16> @llvm.riscv.vwsll.mask.nxv16i16.nxv16i8.nxv16i8(
+  <vscale x 16 x i16>,
+  <vscale x 16 x i8>,
+  <vscale x 16 x i8>,
+  <vscale x 16 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 16 x i16> @intrinsic_vwsll_mask_vv_nxv16i16_nxv16i8_nxv16i8(<vscale x 16 x i16> %0, <vscale x 16 x i8> %1, <vscale x 16 x i8> %2, <vscale x 16 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vwsll_mask_vv_nxv16i16_nxv16i8_nxv16i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, m2, ta, mu
+; CHECK-NEXT:    vwsll.vv v8, v12, v14, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 16 x i16> @llvm.riscv.vwsll.mask.nxv16i16.nxv16i8.nxv16i8(
+    <vscale x 16 x i16> %0,
+    <vscale x 16 x i8> %1,
+    <vscale x 16 x i8> %2,
+    <vscale x 16 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 16 x i16> %a
+}
+
+declare <vscale x 32 x i16> @llvm.riscv.vwsll.nxv32i16.nxv32i8.nxv32i8(
+  <vscale x 32 x i16>,
+  <vscale x 32 x i8>,
+  <vscale x 32 x i8>,
+  iXLen);
+
+define <vscale x 32 x i16> @intrinsic_vwsll_vv_nxv32i16_nxv32i8_nxv32i8(<vscale x 32 x i8> %0, <vscale x 32 x i8> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vwsll_vv_nxv32i16_nxv32i8_nxv32i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, m4, ta, ma
+; CHECK-NEXT:    vwsll.vv v16, v8, v12
+; CHECK-NEXT:    vmv8r.v v8, v16
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 32 x i16> @llvm.riscv.vwsll.nxv32i16.nxv32i8.nxv32i8(
+    <vscale x 32 x i16> undef,
+    <vscale x 32 x i8> %0,
+    <vscale x 32 x i8> %1,
+    iXLen %2)
+
+  ret <vscale x 32 x i16> %a
+}
+
+declare <vscale x 32 x i16> @llvm.riscv.vwsll.mask.nxv32i16.nxv32i8.nxv32i8(
+  <vscale x 32 x i16>,
+  <vscale x 32 x i8>,
+  <vscale x 32 x i8>,
+  <vscale x 32 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 32 x i16> @intrinsic_vwsll_mask_vv_nxv32i16_nxv32i8_nxv32i8(<vscale x 32 x i16> %0, <vscale x 32 x i8> %1, <vscale x 32 x i8> %2, <vscale x 32 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vwsll_mask_vv_nxv32i16_nxv32i8_nxv32i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, m4, ta, mu
+; CHECK-NEXT:    vwsll.vv v8, v16, v20, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 32 x i16> @llvm.riscv.vwsll.mask.nxv32i16.nxv32i8.nxv32i8(
+    <vscale x 32 x i16> %0,
+    <vscale x 32 x i8> %1,
+    <vscale x 32 x i8> %2,
+    <vscale x 32 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 32 x i16> %a
+}
+
+declare <vscale x 1 x i32> @llvm.riscv.vwsll.nxv1i32.nxv1i16.nxv1i16(
+  <vscale x 1 x i32>,
+  <vscale x 1 x i16>,
+  <vscale x 1 x i16>,
+  iXLen);
+
+define <vscale x 1 x i32> @intrinsic_vwsll_vv_nxv1i32_nxv1i16_nxv1i16(<vscale x 1 x i16> %0, <vscale x 1 x i16> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vwsll_vv_nxv1i32_nxv1i16_nxv1i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, mf4, ta, ma
+; CHECK-NEXT:    vwsll.vv v10, v8, v9
+; CHECK-NEXT:    vmv1r.v v8, v10
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i32> @llvm.riscv.vwsll.nxv1i32.nxv1i16.nxv1i16(
+    <vscale x 1 x i32> undef,
+    <vscale x 1 x i16> %0,
+    <vscale x 1 x i16> %1,
+    iXLen %2)
+
+  ret <vscale x 1 x i32> %a
+}
+
+declare <vscale x 1 x i32> @llvm.riscv.vwsll.mask.nxv1i32.nxv1i16.nxv1i16(
+  <vscale x 1 x i32>,
+  <vscale x 1 x i16>,
+  <vscale x 1 x i16>,
+  <vscale x 1 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 1 x i32> @intrinsic_vwsll_mask_vv_nxv1i32_nxv1i16_nxv1i16(<vscale x 1 x i32> %0, <vscale x 1 x i16> %1, <vscale x 1 x i16> %2, <vscale x 1 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vwsll_mask_vv_nxv1i32_nxv1i16_nxv1i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, mf4, ta, mu
+; CHECK-NEXT:    vwsll.vv v8, v9, v10, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i32> @llvm.riscv.vwsll.mask.nxv1i32.nxv1i16.nxv1i16(
+    <vscale x 1 x i32> %0,
+    <vscale x 1 x i16> %1,
+    <vscale x 1 x i16> %2,
+    <vscale x 1 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 1 x i32> %a
+}
+
+declare <vscale x 2 x i32> @llvm.riscv.vwsll.nxv2i32.nxv2i16.nxv2i16(
+  <vscale x 2 x i32>,
+  <vscale x 2 x i16>,
+  <vscale x 2 x i16>,
+  iXLen);
+
+define <vscale x 2 x i32> @intrinsic_vwsll_vv_nxv2i32_nxv2i16_nxv2i16(<vscale x 2 x i16> %0, <vscale x 2 x i16> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vwsll_vv_nxv2i32_nxv2i16_nxv2i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, mf2, ta, ma
+; CHECK-NEXT:    vwsll.vv v10, v8, v9
+; CHECK-NEXT:    vmv1r.v v8, v10
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i32> @llvm.riscv.vwsll.nxv2i32.nxv2i16.nxv2i16(
+    <vscale x 2 x i32> undef,
+    <vscale x 2 x i16> %0,
+    <vscale x 2 x i16> %1,
+    iXLen %2)
+
+  ret <vscale x 2 x i32> %a
+}
+
+declare <vscale x 2 x i32> @llvm.riscv.vwsll.mask.nxv2i32.nxv2i16.nxv2i16(
+  <vscale x 2 x i32>,
+  <vscale x 2 x i16>,
+  <vscale x 2 x i16>,
+  <vscale x 2 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 2 x i32> @intrinsic_vwsll_mask_vv_nxv2i32_nxv2i16_nxv2i16(<vscale x 2 x i32> %0, <vscale x 2 x i16> %1, <vscale x 2 x i16> %2, <vscale x 2 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vwsll_mask_vv_nxv2i32_nxv2i16_nxv2i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, mf2, ta, mu
+; CHECK-NEXT:    vwsll.vv v8, v9, v10, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i32> @llvm.riscv.vwsll.mask.nxv2i32.nxv2i16.nxv2i16(
+    <vscale x 2 x i32> %0,
+    <vscale x 2 x i16> %1,
+    <vscale x 2 x i16> %2,
+    <vscale x 2 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 2 x i32> %a
+}
+
+declare <vscale x 4 x i32> @llvm.riscv.vwsll.nxv4i32.nxv4i16.nxv4i16(
+  <vscale x 4 x i32>,
+  <vscale x 4 x i16>,
+  <vscale x 4 x i16>,
+  iXLen);
+
+define <vscale x 4 x i32> @intrinsic_vwsll_vv_nxv4i32_nxv4i16_nxv4i16(<vscale x 4 x i16> %0, <vscale x 4 x i16> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vwsll_vv_nxv4i32_nxv4i16_nxv4i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, m1, ta, ma
+; CHECK-NEXT:    vwsll.vv v10, v8, v9
+; CHECK-NEXT:    vmv2r.v v8, v10
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i32> @llvm.riscv.vwsll.nxv4i32.nxv4i16.nxv4i16(
+    <vscale x 4 x i32> undef,
+    <vscale x 4 x i16> %0,
+    <vscale x 4 x i16> %1,
+    iXLen %2)
+
+  ret <vscale x 4 x i32> %a
+}
+
+declare <vscale x 4 x i32> @llvm.riscv.vwsll.mask.nxv4i32.nxv4i16.nxv4i16(
+  <vscale x 4 x i32>,
+  <vscale x 4 x i16>,
+  <vscale x 4 x i16>,
+  <vscale x 4 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 4 x i32> @intrinsic_vwsll_mask_vv_nxv4i32_nxv4i16_nxv4i16(<vscale x 4 x i32> %0, <vscale x 4 x i16> %1, <vscale x 4 x i16> %2, <vscale x 4 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vwsll_mask_vv_nxv4i32_nxv4i16_nxv4i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, m1, ta, mu
+; CHECK-NEXT:    vwsll.vv v8, v10, v11, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i32> @llvm.riscv.vwsll.mask.nxv4i32.nxv4i16.nxv4i16(
+    <vscale x 4 x i32> %0,
+    <vscale x 4 x i16> %1,
+    <vscale x 4 x i16> %2,
+    <vscale x 4 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 4 x i32> %a
+}
+
+declare <vscale x 8 x i32> @llvm.riscv.vwsll.nxv8i32.nxv8i16.nxv8i16(
+  <vscale x 8 x i32>,
+  <vscale x 8 x i16>,
+  <vscale x 8 x i16>,
+  iXLen);
+
+define <vscale x 8 x i32> @intrinsic_vwsll_vv_nxv8i32_nxv8i16_nxv8i16(<vscale x 8 x i16> %0, <vscale x 8 x i16> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vwsll_vv_nxv8i32_nxv8i16_nxv8i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, m2, ta, ma
+; CHECK-NEXT:    vwsll.vv v12, v8, v10
+; CHECK-NEXT:    vmv4r.v v8, v12
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i32> @llvm.riscv.vwsll.nxv8i32.nxv8i16.nxv8i16(
+    <vscale x 8 x i32> undef,
+    <vscale x 8 x i16> %0,
+    <vscale x 8 x i16> %1,
+    iXLen %2)
+
+  ret <vscale x 8 x i32> %a
+}
+
+declare <vscale x 8 x i32> @llvm.riscv.vwsll.mask.nxv8i32.nxv8i16.nxv8i16(
+  <vscale x 8 x i32>,
+  <vscale x 8 x i16>,
+  <vscale x 8 x i16>,
+  <vscale x 8 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 8 x i32> @intrinsic_vwsll_mask_vv_nxv8i32_nxv8i16_nxv8i16(<vscale x 8 x i32> %0, <vscale x 8 x i16> %1, <vscale x 8 x i16> %2, <vscale x 8 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vwsll_mask_vv_nxv8i32_nxv8i16_nxv8i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, m2, ta, mu
+; CHECK-NEXT:    vwsll.vv v8, v12, v14, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i32> @llvm.riscv.vwsll.mask.nxv8i32.nxv8i16.nxv8i16(
+    <vscale x 8 x i32> %0,
+    <vscale x 8 x i16> %1,
+    <vscale x 8 x i16> %2,
+    <vscale x 8 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 8 x i32> %a
+}
+
+declare <vscale x 16 x i32> @llvm.riscv.vwsll.nxv16i32.nxv16i16.nxv16i16(
+  <vscale x 16 x i32>,
+  <vscale x 16 x i16>,
+  <vscale x 16 x i16>,
+  iXLen);
+
+define <vscale x 16 x i32> @intrinsic_vwsll_vv_nxv16i32_nxv16i16_nxv16i16(<vscale x 16 x i16> %0, <vscale x 16 x i16> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vwsll_vv_nxv16i32_nxv16i16_nxv16i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, m4, ta, ma
+; CHECK-NEXT:    vwsll.vv v16, v8, v12
+; CHECK-NEXT:    vmv8r.v v8, v16
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 16 x i32> @llvm.riscv.vwsll.nxv16i32.nxv16i16.nxv16i16(
+    <vscale x 16 x i32> undef,
+    <vscale x 16 x i16> %0,
+    <vscale x 16 x i16> %1,
+    iXLen %2)
+
+  ret <vscale x 16 x i32> %a
+}
+
+declare <vscale x 16 x i32> @llvm.riscv.vwsll.mask.nxv16i32.nxv16i16.nxv16i16(
+  <vscale x 16 x i32>,
+  <vscale x 16 x i16>,
+  <vscale x 16 x i16>,
+  <vscale x 16 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 16 x i32> @intrinsic_vwsll_mask_vv_nxv16i32_nxv16i16_nxv16i16(<vscale x 16 x i32> %0, <vscale x 16 x i16> %1, <vscale x 16 x i16> %2, <vscale x 16 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vwsll_mask_vv_nxv16i32_nxv16i16_nxv16i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, m4, ta, mu
+; CHECK-NEXT:    vwsll.vv v8, v16, v20, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 16 x i32> @llvm.riscv.vwsll.mask.nxv16i32.nxv16i16.nxv16i16(
+    <vscale x 16 x i32> %0,
+    <vscale x 16 x i16> %1,
+    <vscale x 16 x i16> %2,
+    <vscale x 16 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 16 x i32> %a
+}
+
+declare <vscale x 1 x i64> @llvm.riscv.vwsll.nxv1i64.nxv1i32.nxv1i32(
+  <vscale x 1 x i64>,
+  <vscale x 1 x i32>,
+  <vscale x 1 x i32>,
+  iXLen);
+
+define <vscale x 1 x i64> @intrinsic_vwsll_vv_nxv1i64_nxv1i32_nxv1i32(<vscale x 1 x i32> %0, <vscale x 1 x i32> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vwsll_vv_nxv1i64_nxv1i32_nxv1i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, mf2, ta, ma
+; CHECK-NEXT:    vwsll.vv v10, v8, v9
+; CHECK-NEXT:    vmv1r.v v8, v10
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i64> @llvm.riscv.vwsll.nxv1i64.nxv1i32.nxv1i32(
+    <vscale x 1 x i64> undef,
+    <vscale x 1 x i32> %0,
+    <vscale x 1 x i32> %1,
+    iXLen %2)
+
+  ret <vscale x 1 x i64> %a
+}
+
+declare <vscale x 1 x i64> @llvm.riscv.vwsll.mask.nxv1i64.nxv1i32.nxv1i32(
+  <vscale x 1 x i64>,
+  <vscale x 1 x i32>,
+  <vscale x 1 x i32>,
+  <vscale x 1 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 1 x i64> @intrinsic_vwsll_mask_vv_nxv1i64_nxv1i32_nxv1i32(<vscale x 1 x i64> %0, <vscale x 1 x i32> %1, <vscale x 1 x i32> %2, <vscale x 1 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vwsll_mask_vv_nxv1i64_nxv1i32_nxv1i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, mf2, ta, mu
+; CHECK-NEXT:    vwsll.vv v8, v9, v10, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i64> @llvm.riscv.vwsll.mask.nxv1i64.nxv1i32.nxv1i32(
+    <vscale x 1 x i64> %0,
+    <vscale x 1 x i32> %1,
+    <vscale x 1 x i32> %2,
+    <vscale x 1 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 1 x i64> %a
+}
+
+declare <vscale x 2 x i64> @llvm.riscv.vwsll.nxv2i64.nxv2i32.nxv2i32(
+  <vscale x 2 x i64>,
+  <vscale x 2 x i32>,
+  <vscale x 2 x i32>,
+  iXLen);
+
+define <vscale x 2 x i64> @intrinsic_vwsll_vv_nxv2i64_nxv2i32_nxv2i32(<vscale x 2 x i32> %0, <vscale x 2 x i32> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vwsll_vv_nxv2i64_nxv2i32_nxv2i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m1, ta, ma
+; CHECK-NEXT:    vwsll.vv v10, v8, v9
+; CHECK-NEXT:    vmv2r.v v8, v10
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i64> @llvm.riscv.vwsll.nxv2i64.nxv2i32.nxv2i32(
+    <vscale x 2 x i64> undef,
+    <vscale x 2 x i32> %0,
+    <vscale x 2 x i32> %1,
+    iXLen %2)
+
+  ret <vscale x 2 x i64> %a
+}
+
+declare <vscale x 2 x i64> @llvm.riscv.vwsll.mask.nxv2i64.nxv2i32.nxv2i32(
+  <vscale x 2 x i64>,
+  <vscale x 2 x i32>,
+  <vscale x 2 x i32>,
+  <vscale x 2 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 2 x i64> @intrinsic_vwsll_mask_vv_nxv2i64_nxv2i32_nxv2i32(<vscale x 2 x i64> %0, <vscale x 2 x i32> %1, <vscale x 2 x i32> %2, <vscale x 2 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vwsll_mask_vv_nxv2i64_nxv2i32_nxv2i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m1, ta, mu
+; CHECK-NEXT:    vwsll.vv v8, v10, v11, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i64> @llvm.riscv.vwsll.mask.nxv2i64.nxv2i32.nxv2i32(
+    <vscale x 2 x i64> %0,
+    <vscale x 2 x i32> %1,
+    <vscale x 2 x i32> %2,
+    <vscale x 2 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 2 x i64> %a
+}
+
+declare <vscale x 4 x i64> @llvm.riscv.vwsll.nxv4i64.nxv4i32.nxv4i32(
+  <vscale x 4 x i64>,
+  <vscale x 4 x i32>,
+  <vscale x 4 x i32>,
+  iXLen);
+
+define <vscale x 4 x i64> @intrinsic_vwsll_vv_nxv4i64_nxv4i32_nxv4i32(<vscale x 4 x i32> %0, <vscale x 4 x i32> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vwsll_vv_nxv4i64_nxv4i32_nxv4i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m2, ta, ma
+; CHECK-NEXT:    vwsll.vv v12, v8, v10
+; CHECK-NEXT:    vmv4r.v v8, v12
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i64> @llvm.riscv.vwsll.nxv4i64.nxv4i32.nxv4i32(
+    <vscale x 4 x i64> undef,
+    <vscale x 4 x i32> %0,
+    <vscale x 4 x i32> %1,
+    iXLen %2)
+
+  ret <vscale x 4 x i64> %a
+}
+
+declare <vscale x 4 x i64> @llvm.riscv.vwsll.mask.nxv4i64.nxv4i32.nxv4i32(
+  <vscale x 4 x i64>,
+  <vscale x 4 x i32>,
+  <vscale x 4 x i32>,
+  <vscale x 4 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 4 x i64> @intrinsic_vwsll_mask_vv_nxv4i64_nxv4i32_nxv4i32(<vscale x 4 x i64> %0, <vscale x 4 x i32> %1, <vscale x 4 x i32> %2, <vscale x 4 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vwsll_mask_vv_nxv4i64_nxv4i32_nxv4i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m2, ta, mu
+; CHECK-NEXT:    vwsll.vv v8, v12, v14, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i64> @llvm.riscv.vwsll.mask.nxv4i64.nxv4i32.nxv4i32(
+    <vscale x 4 x i64> %0,
+    <vscale x 4 x i32> %1,
+    <vscale x 4 x i32> %2,
+    <vscale x 4 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 4 x i64> %a
+}
+
+declare <vscale x 8 x i64> @llvm.riscv.vwsll.nxv8i64.nxv8i32.nxv8i32(
+  <vscale x 8 x i64>,
+  <vscale x 8 x i32>,
+  <vscale x 8 x i32>,
+  iXLen);
+
+define <vscale x 8 x i64> @intrinsic_vwsll_vv_nxv8i64_nxv8i32_nxv8i32(<vscale x 8 x i32> %0, <vscale x 8 x i32> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vwsll_vv_nxv8i64_nxv8i32_nxv8i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m4, ta, ma
+; CHECK-NEXT:    vwsll.vv v16, v8, v12
+; CHECK-NEXT:    vmv8r.v v8, v16
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i64> @llvm.riscv.vwsll.nxv8i64.nxv8i32.nxv8i32(
+    <vscale x 8 x i64> undef,
+    <vscale x 8 x i32> %0,
+    <vscale x 8 x i32> %1,
+    iXLen %2)
+
+  ret <vscale x 8 x i64> %a
+}
+
+declare <vscale x 8 x i64> @llvm.riscv.vwsll.mask.nxv8i64.nxv8i32.nxv8i32(
+  <vscale x 8 x i64>,
+  <vscale x 8 x i32>,
+  <vscale x 8 x i32>,
+  <vscale x 8 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 8 x i64> @intrinsic_vwsll_mask_vv_nxv8i64_nxv8i32_nxv8i32(<vscale x 8 x i64> %0, <vscale x 8 x i32> %1, <vscale x 8 x i32> %2, <vscale x 8 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vwsll_mask_vv_nxv8i64_nxv8i32_nxv8i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m4, ta, mu
+; CHECK-NEXT:    vwsll.vv v8, v16, v20, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i64> @llvm.riscv.vwsll.mask.nxv8i64.nxv8i32.nxv8i32(
+    <vscale x 8 x i64> %0,
+    <vscale x 8 x i32> %1,
+    <vscale x 8 x i32> %2,
+    <vscale x 8 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 8 x i64> %a
+}
+
+declare <vscale x 1 x i16> @llvm.riscv.vwsll.nxv1i16.nxv1i8.i8(
+  <vscale x 1 x i16>,
+  <vscale x 1 x i8>,
+  i8,
+  iXLen);
+
+define <vscale x 1 x i16> @intrinsic_vwsll_vx_nxv1i16_nxv1i8_i8(<vscale x 1 x i8> %0, i8 %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vwsll_vx_nxv1i16_nxv1i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e8, mf8, ta, ma
+; CHECK-NEXT:    vwsll.vx v9, v8, a0
+; CHECK-NEXT:    vmv1r.v v8, v9
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i16> @llvm.riscv.vwsll.nxv1i16.nxv1i8.i8(
+    <vscale x 1 x i16> undef,
+    <vscale x 1 x i8> %0,
+    i8 %1,
+    iXLen %2)
+
+  ret <vscale x 1 x i16> %a
+}
+
+declare <vscale x 1 x i16> @llvm.riscv.vwsll.mask.nxv1i16.nxv1i8.i8(
+  <vscale x 1 x i16>,
+  <vscale x 1 x i8>,
+  i8,
+  <vscale x 1 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 1 x i16> @intrinsic_vwsll_mask_vx_nxv1i16_nxv1i8_i8(<vscale x 1 x i16> %0, <vscale x 1 x i8> %1, i8 %2, <vscale x 1 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vwsll_mask_vx_nxv1i16_nxv1i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e8, mf8, ta, mu
+; CHECK-NEXT:    vwsll.vx v8, v9, a0, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i16> @llvm.riscv.vwsll.mask.nxv1i16.nxv1i8.i8(
+    <vscale x 1 x i16> %0,
+    <vscale x 1 x i8> %1,
+    i8 %2,
+    <vscale x 1 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 1 x i16> %a
+}
+
+declare <vscale x 2 x i16> @llvm.riscv.vwsll.nxv2i16.nxv2i8.i8(
+  <vscale x 2 x i16>,
+  <vscale x 2 x i8>,
+  i8,
+  iXLen);
+
+define <vscale x 2 x i16> @intrinsic_vwsll_vx_nxv2i16_nxv2i8_i8(<vscale x 2 x i8> %0, i8 %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vwsll_vx_nxv2i16_nxv2i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e8, mf4, ta, ma
+; CHECK-NEXT:    vwsll.vx v9, v8, a0
+; CHECK-NEXT:    vmv1r.v v8, v9
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i16> @llvm.riscv.vwsll.nxv2i16.nxv2i8.i8(
+    <vscale x 2 x i16> undef,
+    <vscale x 2 x i8> %0,
+    i8 %1,
+    iXLen %2)
+
+  ret <vscale x 2 x i16> %a
+}
+
+declare <vscale x 2 x i16> @llvm.riscv.vwsll.mask.nxv2i16.nxv2i8.i8(
+  <vscale x 2 x i16>,
+  <vscale x 2 x i8>,
+  i8,
+  <vscale x 2 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 2 x i16> @intrinsic_vwsll_mask_vx_nxv2i16_nxv2i8_i8(<vscale x 2 x i16> %0, <vscale x 2 x i8> %1, i8 %2, <vscale x 2 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vwsll_mask_vx_nxv2i16_nxv2i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e8, mf4, ta, mu
+; CHECK-NEXT:    vwsll.vx v8, v9, a0, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i16> @llvm.riscv.vwsll.mask.nxv2i16.nxv2i8.i8(
+    <vscale x 2 x i16> %0,
+    <vscale x 2 x i8> %1,
+    i8 %2,
+    <vscale x 2 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 2 x i16> %a
+}
+
+declare <vscale x 4 x i16> @llvm.riscv.vwsll.nxv4i16.nxv4i8.i8(
+  <vscale x 4 x i16>,
+  <vscale x 4 x i8>,
+  i8,
+  iXLen);
+
+define <vscale x 4 x i16> @intrinsic_vwsll_vx_nxv4i16_nxv4i8_i8(<vscale x 4 x i8> %0, i8 %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vwsll_vx_nxv4i16_nxv4i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e8, mf2, ta, ma
+; CHECK-NEXT:    vwsll.vx v9, v8, a0
+; CHECK-NEXT:    vmv1r.v v8, v9
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i16> @llvm.riscv.vwsll.nxv4i16.nxv4i8.i8(
+    <vscale x 4 x i16> undef,
+    <vscale x 4 x i8> %0,
+    i8 %1,
+    iXLen %2)
+
+  ret <vscale x 4 x i16> %a
+}
+
+declare <vscale x 4 x i16> @llvm.riscv.vwsll.mask.nxv4i16.nxv4i8.i8(
+  <vscale x 4 x i16>,
+  <vscale x 4 x i8>,
+  i8,
+  <vscale x 4 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 4 x i16> @intrinsic_vwsll_mask_vx_nxv4i16_nxv4i8_i8(<vscale x 4 x i16> %0, <vscale x 4 x i8> %1, i8 %2, <vscale x 4 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vwsll_mask_vx_nxv4i16_nxv4i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e8, mf2, ta, mu
+; CHECK-NEXT:    vwsll.vx v8, v9, a0, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i16> @llvm.riscv.vwsll.mask.nxv4i16.nxv4i8.i8(
+    <vscale x 4 x i16> %0,
+    <vscale x 4 x i8> %1,
+    i8 %2,
+    <vscale x 4 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 4 x i16> %a
+}
+
+declare <vscale x 8 x i16> @llvm.riscv.vwsll.nxv8i16.nxv8i8.i8(
+  <vscale x 8 x i16>,
+  <vscale x 8 x i8>,
+  i8,
+  iXLen);
+
+define <vscale x 8 x i16> @intrinsic_vwsll_vx_nxv8i16_nxv8i8_i8(<vscale x 8 x i8> %0, i8 %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vwsll_vx_nxv8i16_nxv8i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e8, m1, ta, ma
+; CHECK-NEXT:    vwsll.vx v10, v8, a0
+; CHECK-NEXT:    vmv2r.v v8, v10
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i16> @llvm.riscv.vwsll.nxv8i16.nxv8i8.i8(
+    <vscale x 8 x i16> undef,
+    <vscale x 8 x i8> %0,
+    i8 %1,
+    iXLen %2)
+
+  ret <vscale x 8 x i16> %a
+}
+
+declare <vscale x 8 x i16> @llvm.riscv.vwsll.mask.nxv8i16.nxv8i8.i8(
+  <vscale x 8 x i16>,
+  <vscale x 8 x i8>,
+  i8,
+  <vscale x 8 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 8 x i16> @intrinsic_vwsll_mask_vx_nxv8i16_nxv8i8_i8(<vscale x 8 x i16> %0, <vscale x 8 x i8> %1, i8 %2, <vscale x 8 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vwsll_mask_vx_nxv8i16_nxv8i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e8, m1, ta, mu
+; CHECK-NEXT:    vwsll.vx v8, v10, a0, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i16> @llvm.riscv.vwsll.mask.nxv8i16.nxv8i8.i8(
+    <vscale x 8 x i16> %0,
+    <vscale x 8 x i8> %1,
+    i8 %2,
+    <vscale x 8 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 8 x i16> %a
+}
+
+declare <vscale x 16 x i16> @llvm.riscv.vwsll.nxv16i16.nxv16i8.i8(
+  <vscale x 16 x i16>,
+  <vscale x 16 x i8>,
+  i8,
+  iXLen);
+
+define <vscale x 16 x i16> @intrinsic_vwsll_vx_nxv16i16_nxv16i8_i8(<vscale x 16 x i8> %0, i8 %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vwsll_vx_nxv16i16_nxv16i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e8, m2, ta, ma
+; CHECK-NEXT:    vwsll.vx v12, v8, a0
+; CHECK-NEXT:    vmv4r.v v8, v12
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 16 x i16> @llvm.riscv.vwsll.nxv16i16.nxv16i8.i8(
+    <vscale x 16 x i16> undef,
+    <vscale x 16 x i8> %0,
+    i8 %1,
+    iXLen %2)
+
+  ret <vscale x 16 x i16> %a
+}
+
+declare <vscale x 16 x i16> @llvm.riscv.vwsll.mask.nxv16i16.nxv16i8.i8(
+  <vscale x 16 x i16>,
+  <vscale x 16 x i8>,
+  i8,
+  <vscale x 16 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 16 x i16> @intrinsic_vwsll_mask_vx_nxv16i16_nxv16i8_i8(<vscale x 16 x i16> %0, <vscale x 16 x i8> %1, i8 %2, <vscale x 16 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vwsll_mask_vx_nxv16i16_nxv16i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e8, m2, ta, mu
+; CHECK-NEXT:    vwsll.vx v8, v12, a0, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 16 x i16> @llvm.riscv.vwsll.mask.nxv16i16.nxv16i8.i8(
+    <vscale x 16 x i16> %0,
+    <vscale x 16 x i8> %1,
+    i8 %2,
+    <vscale x 16 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 16 x i16> %a
+}
+
+declare <vscale x 32 x i16> @llvm.riscv.vwsll.nxv32i16.nxv32i8.i8(
+  <vscale x 32 x i16>,
+  <vscale x 32 x i8>,
+  i8,
+  iXLen);
+
+define <vscale x 32 x i16> @intrinsic_vwsll_vx_nxv32i16_nxv32i8_i8(<vscale x 32 x i8> %0, i8 %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vwsll_vx_nxv32i16_nxv32i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e8, m4, ta, ma
+; CHECK-NEXT:    vwsll.vx v16, v8, a0
+; CHECK-NEXT:    vmv8r.v v8, v16
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 32 x i16> @llvm.riscv.vwsll.nxv32i16.nxv32i8.i8(
+    <vscale x 32 x i16> undef,
+    <vscale x 32 x i8> %0,
+    i8 %1,
+    iXLen %2)
+
+  ret <vscale x 32 x i16> %a
+}
+
+declare <vscale x 32 x i16> @llvm.riscv.vwsll.mask.nxv32i16.nxv32i8.i8(
+  <vscale x 32 x i16>,
+  <vscale x 32 x i8>,
+  i8,
+  <vscale x 32 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 32 x i16> @intrinsic_vwsll_mask_vx_nxv32i16_nxv32i8_i8(<vscale x 32 x i16> %0, <vscale x 32 x i8> %1, i8 %2, <vscale x 32 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vwsll_mask_vx_nxv32i16_nxv32i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e8, m4, ta, mu
+; CHECK-NEXT:    vwsll.vx v8, v16, a0, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 32 x i16> @llvm.riscv.vwsll.mask.nxv32i16.nxv32i8.i8(
+    <vscale x 32 x i16> %0,
+    <vscale x 32 x i8> %1,
+    i8 %2,
+    <vscale x 32 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 32 x i16> %a
+}
+
+declare <vscale x 1 x i32> @llvm.riscv.vwsll.nxv1i32.nxv1i16.i16(
+  <vscale x 1 x i32>,
+  <vscale x 1 x i16>,
+  i16,
+  iXLen);
+
+define <vscale x 1 x i32> @intrinsic_vwsll_vx_nxv1i32_nxv1i16_i16(<vscale x 1 x i16> %0, i16 %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vwsll_vx_nxv1i32_nxv1i16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e16, mf4, ta, ma
+; CHECK-NEXT:    vwsll.vx v9, v8, a0
+; CHECK-NEXT:    vmv1r.v v8, v9
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i32> @llvm.riscv.vwsll.nxv1i32.nxv1i16.i16(
+    <vscale x 1 x i32> undef,
+    <vscale x 1 x i16> %0,
+    i16 %1,
+    iXLen %2)
+
+  ret <vscale x 1 x i32> %a
+}
+
+declare <vscale x 1 x i32> @llvm.riscv.vwsll.mask.nxv1i32.nxv1i16.i16(
+  <vscale x 1 x i32>,
+  <vscale x 1 x i16>,
+  i16,
+  <vscale x 1 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 1 x i32> @intrinsic_vwsll_mask_vx_nxv1i32_nxv1i16_i16(<vscale x 1 x i32> %0, <vscale x 1 x i16> %1, i16 %2, <vscale x 1 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vwsll_mask_vx_nxv1i32_nxv1i16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e16, mf4, ta, mu
+; CHECK-NEXT:    vwsll.vx v8, v9, a0, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i32> @llvm.riscv.vwsll.mask.nxv1i32.nxv1i16.i16(
+    <vscale x 1 x i32> %0,
+    <vscale x 1 x i16> %1,
+    i16 %2,
+    <vscale x 1 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 1 x i32> %a
+}
+
+declare <vscale x 2 x i32> @llvm.riscv.vwsll.nxv2i32.nxv2i16.i16(
+  <vscale x 2 x i32>,
+  <vscale x 2 x i16>,
+  i16,
+  iXLen);
+
+define <vscale x 2 x i32> @intrinsic_vwsll_vx_nxv2i32_nxv2i16_i16(<vscale x 2 x i16> %0, i16 %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vwsll_vx_nxv2i32_nxv2i16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e16, mf2, ta, ma
+; CHECK-NEXT:    vwsll.vx v9, v8, a0
+; CHECK-NEXT:    vmv1r.v v8, v9
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i32> @llvm.riscv.vwsll.nxv2i32.nxv2i16.i16(
+    <vscale x 2 x i32> undef,
+    <vscale x 2 x i16> %0,
+    i16 %1,
+    iXLen %2)
+
+  ret <vscale x 2 x i32> %a
+}
+
+declare <vscale x 2 x i32> @llvm.riscv.vwsll.mask.nxv2i32.nxv2i16.i16(
+  <vscale x 2 x i32>,
+  <vscale x 2 x i16>,
+  i16,
+  <vscale x 2 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 2 x i32> @intrinsic_vwsll_mask_vx_nxv2i32_nxv2i16_i16(<vscale x 2 x i32> %0, <vscale x 2 x i16> %1, i16 %2, <vscale x 2 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vwsll_mask_vx_nxv2i32_nxv2i16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e16, mf2, ta, mu
+; CHECK-NEXT:    vwsll.vx v8, v9, a0, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i32> @llvm.riscv.vwsll.mask.nxv2i32.nxv2i16.i16(
+    <vscale x 2 x i32> %0,
+    <vscale x 2 x i16> %1,
+    i16 %2,
+    <vscale x 2 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 2 x i32> %a
+}
+
+declare <vscale x 4 x i32> @llvm.riscv.vwsll.nxv4i32.nxv4i16.i16(
+  <vscale x 4 x i32>,
+  <vscale x 4 x i16>,
+  i16,
+  iXLen);
+
+define <vscale x 4 x i32> @intrinsic_vwsll_vx_nxv4i32_nxv4i16_i16(<vscale x 4 x i16> %0, i16 %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vwsll_vx_nxv4i32_nxv4i16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e16, m1, ta, ma
+; CHECK-NEXT:    vwsll.vx v10, v8, a0
+; CHECK-NEXT:    vmv2r.v v8, v10
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i32> @llvm.riscv.vwsll.nxv4i32.nxv4i16.i16(
+    <vscale x 4 x i32> undef,
+    <vscale x 4 x i16> %0,
+    i16 %1,
+    iXLen %2)
+
+  ret <vscale x 4 x i32> %a
+}
+
+declare <vscale x 4 x i32> @llvm.riscv.vwsll.mask.nxv4i32.nxv4i16.i16(
+  <vscale x 4 x i32>,
+  <vscale x 4 x i16>,
+  i16,
+  <vscale x 4 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 4 x i32> @intrinsic_vwsll_mask_vx_nxv4i32_nxv4i16_i16(<vscale x 4 x i32> %0, <vscale x 4 x i16> %1, i16 %2, <vscale x 4 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vwsll_mask_vx_nxv4i32_nxv4i16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e16, m1, ta, mu
+; CHECK-NEXT:    vwsll.vx v8, v10, a0, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i32> @llvm.riscv.vwsll.mask.nxv4i32.nxv4i16.i16(
+    <vscale x 4 x i32> %0,
+    <vscale x 4 x i16> %1,
+    i16 %2,
+    <vscale x 4 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 4 x i32> %a
+}
+
+declare <vscale x 8 x i32> @llvm.riscv.vwsll.nxv8i32.nxv8i16.i16(
+  <vscale x 8 x i32>,
+  <vscale x 8 x i16>,
+  i16,
+  iXLen);
+
+define <vscale x 8 x i32> @intrinsic_vwsll_vx_nxv8i32_nxv8i16_i16(<vscale x 8 x i16> %0, i16 %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vwsll_vx_nxv8i32_nxv8i16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e16, m2, ta, ma
+; CHECK-NEXT:    vwsll.vx v12, v8, a0
+; CHECK-NEXT:    vmv4r.v v8, v12
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i32> @llvm.riscv.vwsll.nxv8i32.nxv8i16.i16(
+    <vscale x 8 x i32> undef,
+    <vscale x 8 x i16> %0,
+    i16 %1,
+    iXLen %2)
+
+  ret <vscale x 8 x i32> %a
+}
+
+declare <vscale x 8 x i32> @llvm.riscv.vwsll.mask.nxv8i32.nxv8i16.i16(
+  <vscale x 8 x i32>,
+  <vscale x 8 x i16>,
+  i16,
+  <vscale x 8 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 8 x i32> @intrinsic_vwsll_mask_vx_nxv8i32_nxv8i16_i16(<vscale x 8 x i32> %0, <vscale x 8 x i16> %1, i16 %2, <vscale x 8 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vwsll_mask_vx_nxv8i32_nxv8i16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e16, m2, ta, mu
+; CHECK-NEXT:    vwsll.vx v8, v12, a0, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i32> @llvm.riscv.vwsll.mask.nxv8i32.nxv8i16.i16(
+    <vscale x 8 x i32> %0,
+    <vscale x 8 x i16> %1,
+    i16 %2,
+    <vscale x 8 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 8 x i32> %a
+}
+
+declare <vscale x 16 x i32> @llvm.riscv.vwsll.nxv16i32.nxv16i16.i16(
+  <vscale x 16 x i32>,
+  <vscale x 16 x i16>,
+  i16,
+  iXLen);
+
+define <vscale x 16 x i32> @intrinsic_vwsll_vx_nxv16i32_nxv16i16_i16(<vscale x 16 x i16> %0, i16 %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vwsll_vx_nxv16i32_nxv16i16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e16, m4, ta, ma
+; CHECK-NEXT:    vwsll.vx v16, v8, a0
+; CHECK-NEXT:    vmv8r.v v8, v16
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 16 x i32> @llvm.riscv.vwsll.nxv16i32.nxv16i16.i16(
+    <vscale x 16 x i32> undef,
+    <vscale x 16 x i16> %0,
+    i16 %1,
+    iXLen %2)
+
+  ret <vscale x 16 x i32> %a
+}
+
+declare <vscale x 16 x i32> @llvm.riscv.vwsll.mask.nxv16i32.nxv16i16.i16(
+  <vscale x 16 x i32>,
+  <vscale x 16 x i16>,
+  i16,
+  <vscale x 16 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 16 x i32> @intrinsic_vwsll_mask_vx_nxv16i32_nxv16i16_i16(<vscale x 16 x i32> %0, <vscale x 16 x i16> %1, i16 %2, <vscale x 16 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vwsll_mask_vx_nxv16i32_nxv16i16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e16, m4, ta, mu
+; CHECK-NEXT:    vwsll.vx v8, v16, a0, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 16 x i32> @llvm.riscv.vwsll.mask.nxv16i32.nxv16i16.i16(
+    <vscale x 16 x i32> %0,
+    <vscale x 16 x i16> %1,
+    i16 %2,
+    <vscale x 16 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 16 x i32> %a
+}
+
+declare <vscale x 1 x i64> @llvm.riscv.vwsll.nxv1i64.nxv1i32.i32(
+  <vscale x 1 x i64>,
+  <vscale x 1 x i32>,
+  i32,
+  iXLen);
+
+define <vscale x 1 x i64> @intrinsic_vwsll_vx_nxv1i64_nxv1i32(<vscale x 1 x i32> %0, i32 %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vwsll_vx_nxv1i64_nxv1i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e32, mf2, ta, ma
+; CHECK-NEXT:    vwsll.vx v9, v8, a0
+; CHECK-NEXT:    vmv1r.v v8, v9
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i64> @llvm.riscv.vwsll.nxv1i64.nxv1i32.i32(
+    <vscale x 1 x i64> undef,
+    <vscale x 1 x i32> %0,
+    i32 %1,
+    iXLen %2)
+
+  ret <vscale x 1 x i64> %a
+}
+
+declare <vscale x 1 x i64> @llvm.riscv.vwsll.mask.nxv1i64.nxv1i32.i32(
+  <vscale x 1 x i64>,
+  <vscale x 1 x i32>,
+  i32,
+  <vscale x 1 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 1 x i64> @intrinsic_vwsll_mask_vx_nxv1i64_nxv1i32(<vscale x 1 x i64> %0, <vscale x 1 x i32> %1, i32 %2, <vscale x 1 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vwsll_mask_vx_nxv1i64_nxv1i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e32, mf2, ta, mu
+; CHECK-NEXT:    vwsll.vx v8, v9, a0, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i64> @llvm.riscv.vwsll.mask.nxv1i64.nxv1i32.i32(
+    <vscale x 1 x i64> %0,
+    <vscale x 1 x i32> %1,
+    i32 %2,
+    <vscale x 1 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 1 x i64> %a
+}
+
+declare <vscale x 2 x i64> @llvm.riscv.vwsll.nxv2i64.nxv2i32.i32(
+  <vscale x 2 x i64>,
+  <vscale x 2 x i32>,
+  i32,
+  iXLen);
+
+define <vscale x 2 x i64> @intrinsic_vwsll_vx_nxv2i64_nxv2i32(<vscale x 2 x i32> %0, i32 %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vwsll_vx_nxv2i64_nxv2i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e32, m1, ta, ma
+; CHECK-NEXT:    vwsll.vx v10, v8, a0
+; CHECK-NEXT:    vmv2r.v v8, v10
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i64> @llvm.riscv.vwsll.nxv2i64.nxv2i32.i32(
+    <vscale x 2 x i64> undef,
+    <vscale x 2 x i32> %0,
+    i32 %1,
+    iXLen %2)
+
+  ret <vscale x 2 x i64> %a
+}
+
+declare <vscale x 2 x i64> @llvm.riscv.vwsll.mask.nxv2i64.nxv2i32.i32(
+  <vscale x 2 x i64>,
+  <vscale x 2 x i32>,
+  i32,
+  <vscale x 2 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 2 x i64> @intrinsic_vwsll_mask_vx_nxv2i64_nxv2i32(<vscale x 2 x i64> %0, <vscale x 2 x i32> %1, i32 %2, <vscale x 2 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vwsll_mask_vx_nxv2i64_nxv2i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e32, m1, ta, mu
+; CHECK-NEXT:    vwsll.vx v8, v10, a0, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i64> @llvm.riscv.vwsll.mask.nxv2i64.nxv2i32.i32(
+    <vscale x 2 x i64> %0,
+    <vscale x 2 x i32> %1,
+    i32 %2,
+    <vscale x 2 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 2 x i64> %a
+}
+
+declare <vscale x 4 x i64> @llvm.riscv.vwsll.nxv4i64.nxv4i32.i32(
+  <vscale x 4 x i64>,
+  <vscale x 4 x i32>,
+  i32,
+  iXLen);
+
+define <vscale x 4 x i64> @intrinsic_vwsll_vx_nxv4i64_nxv4i32(<vscale x 4 x i32> %0, i32 %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vwsll_vx_nxv4i64_nxv4i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e32, m2, ta, ma
+; CHECK-NEXT:    vwsll.vx v12, v8, a0
+; CHECK-NEXT:    vmv4r.v v8, v12
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i64> @llvm.riscv.vwsll.nxv4i64.nxv4i32.i32(
+    <vscale x 4 x i64> undef,
+    <vscale x 4 x i32> %0,
+    i32 %1,
+    iXLen %2)
+
+  ret <vscale x 4 x i64> %a
+}
+
+declare <vscale x 4 x i64> @llvm.riscv.vwsll.mask.nxv4i64.nxv4i32.i32(
+  <vscale x 4 x i64>,
+  <vscale x 4 x i32>,
+  i32,
+  <vscale x 4 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 4 x i64> @intrinsic_vwsll_mask_vx_nxv4i64_nxv4i32(<vscale x 4 x i64> %0, <vscale x 4 x i32> %1, i32 %2, <vscale x 4 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vwsll_mask_vx_nxv4i64_nxv4i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e32, m2, ta, mu
+; CHECK-NEXT:    vwsll.vx v8, v12, a0, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i64> @llvm.riscv.vwsll.mask.nxv4i64.nxv4i32.i32(
+    <vscale x 4 x i64> %0,
+    <vscale x 4 x i32> %1,
+    i32 %2,
+    <vscale x 4 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 4 x i64> %a
+}
+
+declare <vscale x 8 x i64> @llvm.riscv.vwsll.nxv8i64.nxv8i32.i32(
+  <vscale x 8 x i64>,
+  <vscale x 8 x i32>,
+  i32,
+  iXLen);
+
+define <vscale x 8 x i64> @intrinsic_vwsll_vx_nxv8i64_nxv8i32(<vscale x 8 x i32> %0, i32 %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vwsll_vx_nxv8i64_nxv8i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e32, m4, ta, ma
+; CHECK-NEXT:    vwsll.vx v16, v8, a0
+; CHECK-NEXT:    vmv8r.v v8, v16
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i64> @llvm.riscv.vwsll.nxv8i64.nxv8i32.i32(
+    <vscale x 8 x i64> undef,
+    <vscale x 8 x i32> %0,
+    i32 %1,
+    iXLen %2)
+
+  ret <vscale x 8 x i64> %a
+}
+
+declare <vscale x 8 x i64> @llvm.riscv.vwsll.mask.nxv8i64.nxv8i32.i32(
+  <vscale x 8 x i64>,
+  <vscale x 8 x i32>,
+  i32,
+  <vscale x 8 x i1>,
+  iXLen,
+  iXLen);
+
+define <vscale x 8 x i64> @intrinsic_vwsll_mask_vx_nxv8i64_nxv8i32(<vscale x 8 x i64> %0, <vscale x 8 x i32> %1, i32 %2, <vscale x 8 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vwsll_mask_vx_nxv8i64_nxv8i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e32, m4, ta, mu
+; CHECK-NEXT:    vwsll.vx v8, v16, a0, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i64> @llvm.riscv.vwsll.mask.nxv8i64.nxv8i32.i32(
+    <vscale x 8 x i64> %0,
+    <vscale x 8 x i32> %1,
+    i32 %2,
+    <vscale x 8 x i1> %3,
+    iXLen %4, iXLen 1)
+
+  ret <vscale x 8 x i64> %a
+}
+
+define <vscale x 1 x i16> @intrinsic_vwsll_vi_nxv1i16_nxv1i8_i8(<vscale x 1 x i8> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vwsll_vi_nxv1i16_nxv1i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, mf8, ta, ma
+; CHECK-NEXT:    vwsll.vi v9, v8, 1
+; CHECK-NEXT:    vmv1r.v v8, v9
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i16> @llvm.riscv.vwsll.nxv1i16.nxv1i8.i8(
+    <vscale x 1 x i16> undef,
+    <vscale x 1 x i8> %0,
+    i8 1,
+    iXLen %1)
+
+  ret <vscale x 1 x i16> %a
+}
+
+define <vscale x 1 x i16> @intrinsic_vwsll_mask_vi_nxv1i16_nxv1i8_i8(<vscale x 1 x i16> %0, <vscale x 1 x i8> %1, <vscale x 1 x i1> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vwsll_mask_vi_nxv1i16_nxv1i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, mf8, ta, mu
+; CHECK-NEXT:    vwsll.vi v8, v9, 1, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i16> @llvm.riscv.vwsll.mask.nxv1i16.nxv1i8.i8(
+    <vscale x 1 x i16> %0,
+    <vscale x 1 x i8> %1,
+    i8 1,
+    <vscale x 1 x i1> %2,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 1 x i16> %a
+}
+
+define <vscale x 2 x i16> @intrinsic_vwsll_vi_nxv2i16_nxv2i8_i8(<vscale x 2 x i8> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vwsll_vi_nxv2i16_nxv2i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, mf4, ta, ma
+; CHECK-NEXT:    vwsll.vi v9, v8, 1
+; CHECK-NEXT:    vmv1r.v v8, v9
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i16> @llvm.riscv.vwsll.nxv2i16.nxv2i8.i8(
+    <vscale x 2 x i16> undef,
+    <vscale x 2 x i8> %0,
+    i8 1,
+    iXLen %1)
+
+  ret <vscale x 2 x i16> %a
+}
+
+define <vscale x 2 x i16> @intrinsic_vwsll_mask_vi_nxv2i16_nxv2i8_i8(<vscale x 2 x i16> %0, <vscale x 2 x i8> %1, <vscale x 2 x i1> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vwsll_mask_vi_nxv2i16_nxv2i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, mf4, ta, mu
+; CHECK-NEXT:    vwsll.vi v8, v9, 1, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i16> @llvm.riscv.vwsll.mask.nxv2i16.nxv2i8.i8(
+    <vscale x 2 x i16> %0,
+    <vscale x 2 x i8> %1,
+    i8 1,
+    <vscale x 2 x i1> %2,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 2 x i16> %a
+}
+
+define <vscale x 4 x i16> @intrinsic_vwsll_vi_nxv4i16_nxv4i8_i8(<vscale x 4 x i8> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vwsll_vi_nxv4i16_nxv4i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, mf2, ta, ma
+; CHECK-NEXT:    vwsll.vi v9, v8, 1
+; CHECK-NEXT:    vmv1r.v v8, v9
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i16> @llvm.riscv.vwsll.nxv4i16.nxv4i8.i8(
+    <vscale x 4 x i16> undef,
+    <vscale x 4 x i8> %0,
+    i8 1,
+    iXLen %1)
+
+  ret <vscale x 4 x i16> %a
+}
+
+define <vscale x 4 x i16> @intrinsic_vwsll_mask_vi_nxv4i16_nxv4i8_i8(<vscale x 4 x i16> %0, <vscale x 4 x i8> %1, <vscale x 4 x i1> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vwsll_mask_vi_nxv4i16_nxv4i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, mf2, ta, mu
+; CHECK-NEXT:    vwsll.vi v8, v9, 1, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i16> @llvm.riscv.vwsll.mask.nxv4i16.nxv4i8.i8(
+    <vscale x 4 x i16> %0,
+    <vscale x 4 x i8> %1,
+    i8 1,
+    <vscale x 4 x i1> %2,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 4 x i16> %a
+}
+
+define <vscale x 8 x i16> @intrinsic_vwsll_vi_nxv8i16_nxv8i8_i8(<vscale x 8 x i8> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vwsll_vi_nxv8i16_nxv8i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, m1, ta, ma
+; CHECK-NEXT:    vwsll.vi v10, v8, 1
+; CHECK-NEXT:    vmv2r.v v8, v10
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i16> @llvm.riscv.vwsll.nxv8i16.nxv8i8.i8(
+    <vscale x 8 x i16> undef,
+    <vscale x 8 x i8> %0,
+    i8 1,
+    iXLen %1)
+
+  ret <vscale x 8 x i16> %a
+}
+
+define <vscale x 8 x i16> @intrinsic_vwsll_mask_vi_nxv8i16_nxv8i8_i8(<vscale x 8 x i16> %0, <vscale x 8 x i8> %1, <vscale x 8 x i1> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vwsll_mask_vi_nxv8i16_nxv8i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, m1, ta, mu
+; CHECK-NEXT:    vwsll.vi v8, v10, 1, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i16> @llvm.riscv.vwsll.mask.nxv8i16.nxv8i8.i8(
+    <vscale x 8 x i16> %0,
+    <vscale x 8 x i8> %1,
+    i8 1,
+    <vscale x 8 x i1> %2,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 8 x i16> %a
+}
+
+define <vscale x 16 x i16> @intrinsic_vwsll_vi_nxv16i16_nxv16i8_i8(<vscale x 16 x i8> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vwsll_vi_nxv16i16_nxv16i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, m2, ta, ma
+; CHECK-NEXT:    vwsll.vi v12, v8, 1
+; CHECK-NEXT:    vmv4r.v v8, v12
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 16 x i16> @llvm.riscv.vwsll.nxv16i16.nxv16i8.i8(
+    <vscale x 16 x i16> undef,
+    <vscale x 16 x i8> %0,
+    i8 1,
+    iXLen %1)
+
+  ret <vscale x 16 x i16> %a
+}
+
+define <vscale x 16 x i16> @intrinsic_vwsll_mask_vi_nxv16i16_nxv16i8_i8(<vscale x 16 x i16> %0, <vscale x 16 x i8> %1, <vscale x 16 x i1> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vwsll_mask_vi_nxv16i16_nxv16i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, m2, ta, mu
+; CHECK-NEXT:    vwsll.vi v8, v12, 1, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 16 x i16> @llvm.riscv.vwsll.mask.nxv16i16.nxv16i8.i8(
+    <vscale x 16 x i16> %0,
+    <vscale x 16 x i8> %1,
+    i8 1,
+    <vscale x 16 x i1> %2,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 16 x i16> %a
+}
+
+define <vscale x 32 x i16> @intrinsic_vwsll_vi_nxv32i16_nxv32i8_i8(<vscale x 32 x i8> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vwsll_vi_nxv32i16_nxv32i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, m4, ta, ma
+; CHECK-NEXT:    vwsll.vi v16, v8, 1
+; CHECK-NEXT:    vmv8r.v v8, v16
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 32 x i16> @llvm.riscv.vwsll.nxv32i16.nxv32i8.i8(
+    <vscale x 32 x i16> undef,
+    <vscale x 32 x i8> %0,
+    i8 1,
+    iXLen %1)
+
+  ret <vscale x 32 x i16> %a
+}
+
+define <vscale x 32 x i16> @intrinsic_vwsll_mask_vi_nxv32i16_nxv32i8_i8(<vscale x 32 x i16> %0, <vscale x 32 x i8> %1, <vscale x 32 x i1> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vwsll_mask_vi_nxv32i16_nxv32i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, m4, ta, mu
+; CHECK-NEXT:    vwsll.vi v8, v16, 1, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 32 x i16> @llvm.riscv.vwsll.mask.nxv32i16.nxv32i8.i8(
+    <vscale x 32 x i16> %0,
+    <vscale x 32 x i8> %1,
+    i8 1,
+    <vscale x 32 x i1> %2,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 32 x i16> %a
+}
+
+define <vscale x 1 x i32> @intrinsic_vwsll_vi_nxv1i32_nxv1i16_i16(<vscale x 1 x i16> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vwsll_vi_nxv1i32_nxv1i16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, mf4, ta, ma
+; CHECK-NEXT:    vwsll.vi v9, v8, 1
+; CHECK-NEXT:    vmv1r.v v8, v9
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i32> @llvm.riscv.vwsll.nxv1i32.nxv1i16.i16(
+    <vscale x 1 x i32> undef,
+    <vscale x 1 x i16> %0,
+    i16 1,
+    iXLen %1)
+
+  ret <vscale x 1 x i32> %a
+}
+
+define <vscale x 1 x i32> @intrinsic_vwsll_mask_vi_nxv1i32_nxv1i16_i16(<vscale x 1 x i32> %0, <vscale x 1 x i16> %1, <vscale x 1 x i1> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vwsll_mask_vi_nxv1i32_nxv1i16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, mf4, ta, mu
+; CHECK-NEXT:    vwsll.vi v8, v9, 1, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i32> @llvm.riscv.vwsll.mask.nxv1i32.nxv1i16.i16(
+    <vscale x 1 x i32> %0,
+    <vscale x 1 x i16> %1,
+    i16 1,
+    <vscale x 1 x i1> %2,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 1 x i32> %a
+}
+
+define <vscale x 2 x i32> @intrinsic_vwsll_vi_nxv2i32_nxv2i16_i16(<vscale x 2 x i16> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vwsll_vi_nxv2i32_nxv2i16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, mf2, ta, ma
+; CHECK-NEXT:    vwsll.vi v9, v8, 1
+; CHECK-NEXT:    vmv1r.v v8, v9
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i32> @llvm.riscv.vwsll.nxv2i32.nxv2i16.i16(
+    <vscale x 2 x i32> undef,
+    <vscale x 2 x i16> %0,
+    i16 1,
+    iXLen %1)
+
+  ret <vscale x 2 x i32> %a
+}
+
+define <vscale x 2 x i32> @intrinsic_vwsll_mask_vi_nxv2i32_nxv2i16_i16(<vscale x 2 x i32> %0, <vscale x 2 x i16> %1, <vscale x 2 x i1> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vwsll_mask_vi_nxv2i32_nxv2i16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, mf2, ta, mu
+; CHECK-NEXT:    vwsll.vi v8, v9, 1, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i32> @llvm.riscv.vwsll.mask.nxv2i32.nxv2i16.i16(
+    <vscale x 2 x i32> %0,
+    <vscale x 2 x i16> %1,
+    i16 1,
+    <vscale x 2 x i1> %2,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 2 x i32> %a
+}
+
+define <vscale x 4 x i32> @intrinsic_vwsll_vi_nxv4i32_nxv4i16_i16(<vscale x 4 x i16> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vwsll_vi_nxv4i32_nxv4i16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, m1, ta, ma
+; CHECK-NEXT:    vwsll.vi v10, v8, 1
+; CHECK-NEXT:    vmv2r.v v8, v10
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i32> @llvm.riscv.vwsll.nxv4i32.nxv4i16.i16(
+    <vscale x 4 x i32> undef,
+    <vscale x 4 x i16> %0,
+    i16 1,
+    iXLen %1)
+
+  ret <vscale x 4 x i32> %a
+}
+
+define <vscale x 4 x i32> @intrinsic_vwsll_mask_vi_nxv4i32_nxv4i16_i16(<vscale x 4 x i32> %0, <vscale x 4 x i16> %1, <vscale x 4 x i1> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vwsll_mask_vi_nxv4i32_nxv4i16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, m1, ta, mu
+; CHECK-NEXT:    vwsll.vi v8, v10, 1, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i32> @llvm.riscv.vwsll.mask.nxv4i32.nxv4i16.i16(
+    <vscale x 4 x i32> %0,
+    <vscale x 4 x i16> %1,
+    i16 1,
+    <vscale x 4 x i1> %2,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 4 x i32> %a
+}
+
+define <vscale x 8 x i32> @intrinsic_vwsll_vi_nxv8i32_nxv8i16_i16(<vscale x 8 x i16> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vwsll_vi_nxv8i32_nxv8i16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, m2, ta, ma
+; CHECK-NEXT:    vwsll.vi v12, v8, 1
+; CHECK-NEXT:    vmv4r.v v8, v12
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i32> @llvm.riscv.vwsll.nxv8i32.nxv8i16.i16(
+    <vscale x 8 x i32> undef,
+    <vscale x 8 x i16> %0,
+    i16 1,
+    iXLen %1)
+
+  ret <vscale x 8 x i32> %a
+}
+
+define <vscale x 8 x i32> @intrinsic_vwsll_mask_vi_nxv8i32_nxv8i16_i16(<vscale x 8 x i32> %0, <vscale x 8 x i16> %1, <vscale x 8 x i1> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vwsll_mask_vi_nxv8i32_nxv8i16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, m2, ta, mu
+; CHECK-NEXT:    vwsll.vi v8, v12, 1, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i32> @llvm.riscv.vwsll.mask.nxv8i32.nxv8i16.i16(
+    <vscale x 8 x i32> %0,
+    <vscale x 8 x i16> %1,
+    i16 1,
+    <vscale x 8 x i1> %2,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 8 x i32> %a
+}
+
+define <vscale x 16 x i32> @intrinsic_vwsll_vi_nxv16i32_nxv16i16_i16(<vscale x 16 x i16> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vwsll_vi_nxv16i32_nxv16i16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, m4, ta, ma
+; CHECK-NEXT:    vwsll.vi v16, v8, 1
+; CHECK-NEXT:    vmv8r.v v8, v16
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 16 x i32> @llvm.riscv.vwsll.nxv16i32.nxv16i16.i16(
+    <vscale x 16 x i32> undef,
+    <vscale x 16 x i16> %0,
+    i16 1,
+    iXLen %1)
+
+  ret <vscale x 16 x i32> %a
+}
+
+define <vscale x 16 x i32> @intrinsic_vwsll_mask_vi_nxv16i32_nxv16i16_i16(<vscale x 16 x i32> %0, <vscale x 16 x i16> %1, <vscale x 16 x i1> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vwsll_mask_vi_nxv16i32_nxv16i16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, m4, ta, mu
+; CHECK-NEXT:    vwsll.vi v8, v16, 1, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 16 x i32> @llvm.riscv.vwsll.mask.nxv16i32.nxv16i16.i16(
+    <vscale x 16 x i32> %0,
+    <vscale x 16 x i16> %1,
+    i16 1,
+    <vscale x 16 x i1> %2,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 16 x i32> %a
+}
+
+define <vscale x 1 x i64> @intrinsic_vwsll_vi_nxv1i64_nxv1i32(<vscale x 1 x i32> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vwsll_vi_nxv1i64_nxv1i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, mf2, ta, ma
+; CHECK-NEXT:    vwsll.vi v9, v8, 1
+; CHECK-NEXT:    vmv1r.v v8, v9
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i64> @llvm.riscv.vwsll.nxv1i64.nxv1i32.i32(
+    <vscale x 1 x i64> undef,
+    <vscale x 1 x i32> %0,
+    i32 1,
+    iXLen %1)
+
+  ret <vscale x 1 x i64> %a
+}
+
+define <vscale x 1 x i64> @intrinsic_vwsll_mask_vi_nxv1i64_nxv1i32(<vscale x 1 x i64> %0, <vscale x 1 x i32> %1, <vscale x 1 x i1> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vwsll_mask_vi_nxv1i64_nxv1i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, mf2, ta, mu
+; CHECK-NEXT:    vwsll.vi v8, v9, 1, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i64> @llvm.riscv.vwsll.mask.nxv1i64.nxv1i32.i32(
+    <vscale x 1 x i64> %0,
+    <vscale x 1 x i32> %1,
+    i32 1,
+    <vscale x 1 x i1> %2,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 1 x i64> %a
+}
+
+define <vscale x 2 x i64> @intrinsic_vwsll_vi_nxv2i64_nxv2i32(<vscale x 2 x i32> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vwsll_vi_nxv2i64_nxv2i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m1, ta, ma
+; CHECK-NEXT:    vwsll.vi v10, v8, 1
+; CHECK-NEXT:    vmv2r.v v8, v10
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i64> @llvm.riscv.vwsll.nxv2i64.nxv2i32.i32(
+    <vscale x 2 x i64> undef,
+    <vscale x 2 x i32> %0,
+    i32 1,
+    iXLen %1)
+
+  ret <vscale x 2 x i64> %a
+}
+
+define <vscale x 2 x i64> @intrinsic_vwsll_mask_vi_nxv2i64_nxv2i32(<vscale x 2 x i64> %0, <vscale x 2 x i32> %1, <vscale x 2 x i1> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vwsll_mask_vi_nxv2i64_nxv2i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m1, ta, mu
+; CHECK-NEXT:    vwsll.vi v8, v10, 1, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i64> @llvm.riscv.vwsll.mask.nxv2i64.nxv2i32.i32(
+    <vscale x 2 x i64> %0,
+    <vscale x 2 x i32> %1,
+    i32 1,
+    <vscale x 2 x i1> %2,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 2 x i64> %a
+}
+
+define <vscale x 4 x i64> @intrinsic_vwsll_vi_nxv4i64_nxv4i32(<vscale x 4 x i32> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vwsll_vi_nxv4i64_nxv4i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m2, ta, ma
+; CHECK-NEXT:    vwsll.vi v12, v8, 1
+; CHECK-NEXT:    vmv4r.v v8, v12
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i64> @llvm.riscv.vwsll.nxv4i64.nxv4i32.i32(
+    <vscale x 4 x i64> undef,
+    <vscale x 4 x i32> %0,
+    i32 1,
+    iXLen %1)
+
+  ret <vscale x 4 x i64> %a
+}
+
+define <vscale x 4 x i64> @intrinsic_vwsll_mask_vi_nxv4i64_nxv4i32(<vscale x 4 x i64> %0, <vscale x 4 x i32> %1, <vscale x 4 x i1> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vwsll_mask_vi_nxv4i64_nxv4i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m2, ta, mu
+; CHECK-NEXT:    vwsll.vi v8, v12, 1, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i64> @llvm.riscv.vwsll.mask.nxv4i64.nxv4i32.i32(
+    <vscale x 4 x i64> %0,
+    <vscale x 4 x i32> %1,
+    i32 1,
+    <vscale x 4 x i1> %2,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 4 x i64> %a
+}
+
+define <vscale x 8 x i64> @intrinsic_vwsll_vi_nxv8i64_nxv8i32(<vscale x 8 x i32> %0, iXLen %1) nounwind {
+; CHECK-LABEL: intrinsic_vwsll_vi_nxv8i64_nxv8i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m4, ta, ma
+; CHECK-NEXT:    vwsll.vi v16, v8, 1
+; CHECK-NEXT:    vmv8r.v v8, v16
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i64> @llvm.riscv.vwsll.nxv8i64.nxv8i32.i32(
+    <vscale x 8 x i64> undef,
+    <vscale x 8 x i32> %0,
+    i32 1,
+    iXLen %1)
+
+  ret <vscale x 8 x i64> %a
+}
+
+define <vscale x 8 x i64> @intrinsic_vwsll_mask_vi_nxv8i64_nxv8i32(<vscale x 8 x i64> %0, <vscale x 8 x i32> %1, <vscale x 8 x i1> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vwsll_mask_vi_nxv8i64_nxv8i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m4, ta, mu
+; CHECK-NEXT:    vwsll.vi v8, v16, 1, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i64> @llvm.riscv.vwsll.mask.nxv8i64.nxv8i32.i32(
+    <vscale x 8 x i64> %0,
+    <vscale x 8 x i32> %1,
+    i32 1,
+    <vscale x 8 x i1> %2,
+    iXLen %3, iXLen 1)
+
+  ret <vscale x 8 x i64> %a
+}