[RISCV] Define vadd/vsub/vrsub intrinsics and lower to V instructions.

[HsiangKai]

Summary

Demonstrate how to model RISC-V V intrinsics and lower them to V instructions.

The CodeGen strategy is designed by @rogfer01 from BSC.

[frasercrmck]

llvm/lib/Target/RISCV/RISCVInstrInfoVPseudos.td

17

Documenting this and why it's necessary (X0 != ADD X0, 0 for vsetvli) would be good

78

Documenting this helper class would be helpful

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

3

Having +m,+f,+d,+a,+c all seem unnecessary here

7

The formatting of this IR function declaration looks a little weird to me - is this the usual style?

19

It would be good to have a test without undef inputs.

[HsiangKai]

Add more test cases and extend scalar operand to the legal type.

[HsiangKai]

Address @frasercrmck's comments.

[HsiangKai]

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

7

It is generated by our internal test generator.

[kito-cheng]

llvm/lib/Target/RISCV/RISCVISelLowering.cpp

2296

I would suggest add a new assert here, the assertion message seems not fit for the extra checking.

[HsiangKai]

• Remove unnecessary swap function in this patch. Add it if we need it afterward.
• Address @kito-cheng's comments.

[rogfer01]

llvm/lib/Target/RISCV/RISCVISelLowering.cpp

2067

Thanks a lot for the patch @HsiangKai !

I would add a comment here, to avoid confusion, stating that this is an interim calling convention and it may be changed in the future.

[HsiangKai]

Address @rogfer01's comments.

[craig.topper]

llvm/include/llvm/IR/IntrinsicsRISCV.td

26

The comment block above this is about atomics which should stay with the atomic intrinsics. Can we start a new section for vectors after closing the "let TargetPrefix = "riscv" in {" portion for atomics. Same as what I did in D92973.

73

The vl parameter is going to need to be llvm_anyint_ty to support RV32

llvm/lib/Target/RISCV/RISCVISelLowering.cpp

2121

Can you pass TLI by reference since its never null? Just need to change the callers to pass *this instead of this

llvm/lib/Target/RISCV/RISCVInstrInfoVPseudos.td

70

Why do we need to do this? The vector instructions for that use a FPR64 or FPR32 should only be supported when the scalar type is supported. Why can't we use the proper register class directly?

llvm/lib/Target/RISCV/Utils/RISCVBaseInfo.cpp

17

This feels like a library layering violation. This file belongs to the MC layer and shouldn't be pulling in files in the IR directory.

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

19

Agreed. Can we just avoid undef inputs in all tests?

[craig.topper]

llvm/lib/Target/RISCV/RISCVISelLowering.cpp

2256

Will RC ever be a subclass? Can we just check RC == &RISCV::VRRegClass?

2392

Would getRegClassFor work for the scalar case too?

llvm/lib/Target/RISCV/RISCVInstrInfoVPseudos.td

24

Put this inside the if since its only needed if we create nodes.

26

This can be simplified slightly to

auto *C = dyn_cast<ConstantSDNode(N);
if (C && C->isNullValue()

Then you don't need two levels of indentation

[jrtc27]

llvm/lib/Target/RISCV/RISCVInstrInfoVPseudos.td

26

I forget whether C++17 is allowed; if so you can do

if (auto *C = dyn_cast<ConstantSDNode>(N); C->isNullValue())

to get the benefits both of reduced scope and of reduced indentation.

[craig.topper]

llvm/lib/Target/RISCV/RISCVInstrInfoVPseudos.td

70

Answering my own question. SEW is part of the pseudo operands. So we don't have separate pseudos for FPR16/FPR32/FPR64. That's why we have this

I'm not completely sure about extracting FPR64 values to FPR32 when we really care about the full 64-bit value. Inserting FPR16 to FPR32 seems more ok. How many instructions does this affect?

[craig.topper]

llvm/lib/Target/RISCV/RISCVISelLowering.cpp

1017

Use SmallVector with the expected number of operands.

1022

MVT::i64 here should be Subtarget->XLenVT() I think.

[craig.topper]

llvm/lib/Target/RISCV/RISCVInstrInfoVPseudos.td

26

I think we're only allowed to use C++14.

[HsiangKai]

Combine D93048 into this patch.

[evandro]

llvm/lib/Target/RISCV/RISCVInstrInfoVPseudos.td

20

s/~0/VLMAX/

21

"Keep current vl, just change vtype"

28

Subtarget->XLenVT() instead of MVT::i64, here and below, yes?

[HsiangKai]

llvm/lib/Target/RISCV/RISCVInstrInfoVPseudos.td

70

@rogfer01, could you help to give a more detail explanation here, thanks.

[HsiangKai]

The destination vector register group for a masked vector instruction cannot overlap the source mask register (v0), unless the destination vector register is being written with a mask value (e.g., comparisons) or the scalar result of a reduction.

[HsiangKai]

Rebase on master.

[HsiangKai]

Update test cases.

[HsiangKai]

Gather the class attributes.

[HsiangKai]

Encode the destination type into pattern classes.

[HsiangKai]

Refine the class name in IntrinsicsRISCV.td.

[HsiangKai]

clang format.

[HsiangKai]

Avoid a library layering violation.

[craig.topper]

llvm/lib/Target/RISCV/RISCVISelLowering.cpp

337

Is MVT::i1 needed here? The custom lowering only checks i8/i16/i32.

Should we only have i32 as custom with RV64?

2387

Pass by reference?

llvm/lib/Target/RISCV/RISCVInstrInfo.cpp

142

lowerest->lowest

144

This will fail for VMV1R_V won't it?

146

I'm not sure I'm comfortable with losing the tracking of the full register write before all machine IR passes run. Can we have a Pseudo instructions for VMV2/4/8_V with the right register classes and let RISCVMCInstLower.cpp expand them?

[craig.topper]

llvm/lib/Target/RISCV/RISCVInstrInfoVPseudos.td

223

It's weird that we have a multiclass and a class both named VPseudoBinary. It works because they are considered difference namespaces by tablegen. But it makes the file hard to navigate for a human.

[evandro]

llvm/lib/Target/RISCV/RISCVISelLowering.cpp

337

Good question...

[HsiangKai]

llvm/lib/Target/RISCV/RISCVISelLowering.cpp

337

MVT::i1 is not needed. We need i8/i16. In vadd.vx, the SEW of scalar argument may be 8 or 16.

[HsiangKai]

Address @craig.topper's comments. I will create pseudo instructions for vector register move later.

[HsiangKai]

Define pseudo instructions for vector whole register move.

[craig.topper]

This looks good to me other than that one comment.

llvm/lib/Target/RISCV/RISCVInstrInfo.cpp

101

Comment needs to be updated to mention vectors

[evandro]

LGTM, but, please, see if any of the lint notices can be addressed before committing.

[evandro]

RV32 tests are also needed, please.

[HsiangKai]

Address @craig.topper and @evandro's comments.

[craig.topper]

LGTM

llvm/include/llvm/IR/IntrinsicsRISCV.td

 // they require). We carefully instantiate only specific versions of these for
 // specific integer widths, rather than using `llvm_anyint_ty`.
 //
 // In fact, as these intrinsics take `llvm_anyptr_ty`, the given names are the
 // canonical names, and the intrinsics used in the code will have a name
 // suffixed with the pointer type they are specialised for (denoted `<p>` in the
 // names below), in order to avoid type conflicts.
 
 let TargetPrefix = "riscv" in {
 
   // T @llvm.<name>.T.<p>(any*, T, T, T imm);
   class MaskedAtomicRMWFourArg<LLVMType itype>
       : Intrinsic<[itype], [llvm_anyptr_ty, itype, itype, itype],
                   [IntrArgMemOnly, NoCapture<ArgIndex<0>>, ImmArg<ArgIndex<3>>]>;
   // T @llvm.<name>.T.<p>(any*, T, T, T, T imm);
   class MaskedAtomicRMWFiveArg<LLVMType itype>
       : Intrinsic<[itype], [llvm_anyptr_ty, itype, itype, itype, itype],
let TargetPrefix = "riscv" in {
   // Unsigned min and max don't need the extra operand.
   defm int_riscv_masked_atomicrmw_umax : MaskedAtomicRMWFourArgIntrinsics;
   defm int_riscv_masked_atomicrmw_umin : MaskedAtomicRMWFourArgIntrinsics;
 
   // @llvm.riscv.masked.cmpxchg.{i32,i64}.<p>(...)
   defm int_riscv_masked_cmpxchg : MaskedAtomicRMWFiveArgIntrinsics;
 
 } // TargetPrefix = "riscv"
+
+//===----------------------------------------------------------------------===//
+// Vectors
+
+class RISCVVIntrinsic {
+  // These intrinsics may accept illegal integer values in their llvm_any_ty
+  // operand, so they have to be extended. If set to zero then the intrinsic
+  // does not have any operand that must be extended.
+  Intrinsic IntrinsicID = !cast<Intrinsic>(NAME);
+  bits<4> ExtendOperand = 0;
+}
+
+let TargetPrefix = "riscv" in {
+  // For (vector, vector) and (vector, scalar) binary arithmetic.
+  // Input: (vector_in, vector_in/scalar_in, vl)
+  class RVVBinaryCommon
+        : Intrinsic<[llvm_anyvector_ty],
+                    [LLVMMatchType<0>, llvm_any_ty, llvm_anyint_ty],
+                    [IntrNoMem]>, RISCVVIntrinsic {
+    let ExtendOperand = 2;
+  }
+  // For (vector, vector) and (vector, scalar) bianry arithmetic with mask.
+  // Input: (maskedoff, vector_in, vector_in/scalar_in, mask, vl)
+  class RVVBinaryCommonMask
+       : Intrinsic<[llvm_anyvector_ty],
+                   [LLVMMatchType<0>, LLVMMatchType<0>, llvm_any_ty,
+                    llvm_anyvector_ty, llvm_anyint_ty],
+                   [IntrNoMem]>, RISCVVIntrinsic {
+    let ExtendOperand = 3;
+  }
+
+  multiclass riscv_binary {
+    def "int_riscv_" # NAME : RVVBinaryCommon;
+    def "int_riscv_" # NAME # "_mask" : RVVBinaryCommonMask;
+  }
+
+  defm vadd : riscv_binary;
+  defm vsub : riscv_binary;
+  defm vrsub : riscv_binary;
+} // TargetPrefix = "riscv"

llvm/lib/Target/RISCV/RISCVISelLowering.h

 
 class RISCVTargetLowering : public TargetLowering {
   const RISCVSubtarget &Subtarget;
 
 public:
   explicit RISCVTargetLowering(const TargetMachine &TM,
                                const RISCVSubtarget &STI);
 
+  const RISCVSubtarget &getSubtarget() const { return Subtarget; }
+
   bool getTgtMemIntrinsic(IntrinsicInfo &Info, const CallInst &I,
                           MachineFunction &MF,
                           unsigned Intrinsic) const override;
   bool isLegalAddressingMode(const DataLayout &DL, const AddrMode &AM, Type *Ty,
                              unsigned AS,
                              Instruction *I = nullptr) const override;
   bool isLegalICmpImmediate(int64_t Imm) const override;
   bool isLegalAddImmediate(int64_t Imm) const override;

llvm/lib/Target/RISCV/RISCVISelLowering.cpp

if (Subtarget.hasStdExtA()) {
     setMaxAtomicSizeInBitsSupported(Subtarget.getXLen());
     setMinCmpXchgSizeInBits(32);
   } else {
     setMaxAtomicSizeInBitsSupported(0);
   }
 
   setBooleanContents(ZeroOrOneBooleanContent);
 
-  if (Subtarget.hasStdExtV())
+  if (Subtarget.hasStdExtV()) {
     setBooleanVectorContents(ZeroOrOneBooleanContent);
+    // RVV intrinsics may have illegal operands.
+    for (auto VT : {MVT::i1, MVT::i8, MVT::i16, MVT::i32})
+      setOperationAction(ISD::INTRINSIC_WO_CHAIN, VT, Custom);
+  }
 
   // Function alignments.
   const Align FunctionAlignment(Subtarget.hasStdExtC() ? 2 : 4);
   setMinFunctionAlignment(FunctionAlignment);
   setPrefFunctionAlignment(FunctionAlignment);
 
   // Effectively disable jump table generation.
   setMinimumJumpTableEntries(INT_MAX);
SDValue RISCVTargetLowering::lowerShiftRightParts(SDValue Op, SelectionDAG &DAG,
   SDValue Parts[2] = {Lo, Hi};
   return DAG.getMergeValues(Parts, DL);
 }
 
 SDValue RISCVTargetLowering::LowerINTRINSIC_WO_CHAIN(SDValue Op,
                                                      SelectionDAG &DAG) const {
   unsigned IntNo = cast<ConstantSDNode>(Op.getOperand(0))->getZExtValue();
   SDLoc DL(Op);
+
+  if (Subtarget.hasStdExtV()) {
+    // Some RVV intrinsics may claim that they want an integer operand to be
+    // extended.
+    if (const RISCVVIntrinsicsTable::RISCVVIntrinsicInfo *II =
+            RISCVVIntrinsicsTable::getRISCVVIntrinsicInfo(IntNo)) {
+      if (II->ExtendedOperand) {
+        assert(II->ExtendedOperand < Op.getNumOperands());
+        SmallVector<SDValue, 8> Operands(Op->op_begin(), Op->op_end());
+        SDValue &ScalarOp = Operands[II->ExtendedOperand];
+        if (ScalarOp.getValueType() == MVT::i8 ||
+            ScalarOp.getValueType() == MVT::i16 ||
+            ScalarOp.getValueType() == MVT::i32) {
+          ScalarOp =
+              DAG.getNode(ISD::ANY_EXTEND, DL, Subtarget.getXLenVT(), ScalarOp);
+          return DAG.getNode(ISD::INTRINSIC_WO_CHAIN, DL, Op.getValueType(),
+                             Operands);
+        }
+      }
+    }
+  }
+
   switch (IntNo) {
   default:
     return SDValue();    // Don't custom lower most intrinsics.
   case Intrinsic::thread_pointer: {
     EVT PtrVT = getPointerTy(DAG.getDataLayout());
     return DAG.getRegister(RISCV::X4, PtrVT);
   }
   }

 static const MCPhysReg ArgFPR32s[] = {
   RISCV::F10_F, RISCV::F11_F, RISCV::F12_F, RISCV::F13_F,
   RISCV::F14_F, RISCV::F15_F, RISCV::F16_F, RISCV::F17_F
 };
 static const MCPhysReg ArgFPR64s[] = {
   RISCV::F10_D, RISCV::F11_D, RISCV::F12_D, RISCV::F13_D,
   RISCV::F14_D, RISCV::F15_D, RISCV::F16_D, RISCV::F17_D
 };
+// This is an interim calling convention and it may be changed in the future.
+static const MCPhysReg ArgVRs[] = {
+  RISCV::V16, RISCV::V17, RISCV::V18, RISCV::V19, RISCV::V20,
+  RISCV::V21, RISCV::V22, RISCV::V23
+};
+static const MCPhysReg ArgVRM2s[] = {
+  RISCV::V16M2, RISCV::V18M2, RISCV::V20M2, RISCV::V22M2
+};
+static const MCPhysReg ArgVRM4s[] = {RISCV::V16M4, RISCV::V20M4};
+static const MCPhysReg ArgVRM8s[] = {RISCV::V16M8};
 
 // Pass a 2*XLEN argument that has been split into two XLEN values through
 // registers or the stack as necessary.
 static bool CC_RISCVAssign2XLen(unsigned XLen, CCState &State, CCValAssign VA1,
                                 ISD::ArgFlagsTy ArgFlags1, unsigned ValNo2,
                                 MVT ValVT2, MVT LocVT2,
                                 ISD::ArgFlagsTy ArgFlags2) {
   unsigned XLenInBytes = XLen / 8;
static bool CC_RISCVAssign2XLen(unsigned XLen, CCState &State, CCValAssign VA1,
 
   return false;
 }
 
 // Implements the RISC-V calling convention. Returns true upon failure.
 static bool CC_RISCV(const DataLayout &DL, RISCVABI::ABI ABI, unsigned ValNo,
                      MVT ValVT, MVT LocVT, CCValAssign::LocInfo LocInfo,
                      ISD::ArgFlagsTy ArgFlags, CCState &State, bool IsFixed,
-                     bool IsRet, Type *OrigTy) {
+                     bool IsRet, Type *OrigTy, const RISCVTargetLowering &TLI) {
   unsigned XLen = DL.getLargestLegalIntTypeSizeInBits();
   assert(XLen == 32 || XLen == 64);
   MVT XLenVT = XLen == 32 ? MVT::i32 : MVT::i64;
 
   // Any return value split in to more than two values can't be returned
   // directly.
   if (IsRet && ValNo > 1)
     return true;
static bool CC_RISCV(const DataLayout &DL, RISCVABI::ABI ABI, unsigned ValNo,
   // Allocate to a register if possible, or else a stack slot.
   Register Reg;
   if (ValVT == MVT::f16 && !UseGPRForF16_F32)
     Reg = State.AllocateReg(ArgFPR16s);
   else if (ValVT == MVT::f32 && !UseGPRForF16_F32)
     Reg = State.AllocateReg(ArgFPR32s);
   else if (ValVT == MVT::f64 && !UseGPRForF64)
     Reg = State.AllocateReg(ArgFPR64s);
-  else
+  else if (ValVT.isScalableVector()) {
+    const TargetRegisterClass *RC = TLI.getRegClassFor(ValVT);
+    if (RC == &RISCV::VRRegClass) {
+      Reg = State.AllocateReg(ArgVRs);
+    } else if (RC == &RISCV::VRM2RegClass) {
+      Reg = State.AllocateReg(ArgVRM2s);
+    } else if (RC == &RISCV::VRM4RegClass) {
+      Reg = State.AllocateReg(ArgVRM4s);
+    } else if (RC == &RISCV::VRM8RegClass) {
+      Reg = State.AllocateReg(ArgVRM8s);
+    } else {
+      llvm_unreachable("Unhandled class register for ValueType");
+    }
+    if (!Reg) {
+      LocInfo = CCValAssign::Indirect;
+      // Try using a GPR to pass the address
+      Reg = State.AllocateReg(ArgGPRs);
+      LocVT = XLenVT;
+    }
+  } else
     Reg = State.AllocateReg(ArgGPRs);
   unsigned StackOffset =
       Reg ? 0 : State.AllocateStack(XLen / 8, Align(XLen / 8));
 
   // If we reach this point and PendingLocs is non-empty, we must be at the
   // end of a split argument that must be passed indirectly.
   if (!PendingLocs.empty()) {
     assert(ArgFlags.isSplitEnd() && "Expected ArgFlags.isSplitEnd()");
     assert(PendingLocs.size() > 2 && "Unexpected PendingLocs.size()");
 
     for (auto &It : PendingLocs) {
       if (Reg)
         It.convertToReg(Reg);
       else
         It.convertToMem(StackOffset);
       State.addLoc(It);
     }
     PendingLocs.clear();
     PendingArgFlags.clear();
     return false;
   }
 
-  assert((!UseGPRForF16_F32 || !UseGPRForF64 || LocVT == XLenVT) &&
-         "Expected an XLenVT at this stage");
+  assert((!UseGPRForF16_F32 || !UseGPRForF64 || LocVT == XLenVT ||
+          (TLI.getSubtarget().hasStdExtV() && ValVT.isScalableVector())) &&
+         "Expected an XLenVT or scalable vector types at this stage");
 
   if (Reg) {
     State.addLoc(CCValAssign::getReg(ValNo, ValVT, Reg, LocVT, LocInfo));
     return false;
   }
 
   // When a floating-point value is passed on the stack, no bit-conversion is
   // needed.
for (unsigned i = 0; i != NumArgs; ++i) {
     Type *ArgTy = nullptr;
     if (IsRet)
       ArgTy = FType->getReturnType();
     else if (Ins[i].isOrigArg())
       ArgTy = FType->getParamType(Ins[i].getOrigArgIndex());
 
     RISCVABI::ABI ABI = MF.getSubtarget<RISCVSubtarget>().getTargetABI();
     if (CC_RISCV(MF.getDataLayout(), ABI, i, ArgVT, ArgVT, CCValAssign::Full,
-                 ArgFlags, CCInfo, /*IsFixed=*/true, IsRet, ArgTy)) {
+                 ArgFlags, CCInfo, /*IsFixed=*/true, IsRet, ArgTy, *this)) {
       LLVM_DEBUG(dbgs() << "InputArg #" << i << " has unhandled type "
                         << EVT(ArgVT).getEVTString() << '\n');
       llvm_unreachable(nullptr);
     }
   }
 }
 
 void RISCVTargetLowering::analyzeOutputArgs(
     MachineFunction &MF, CCState &CCInfo,
     const SmallVectorImpl<ISD::OutputArg> &Outs, bool IsRet,
     CallLoweringInfo *CLI) const {
   unsigned NumArgs = Outs.size();
 
   for (unsigned i = 0; i != NumArgs; i++) {
     MVT ArgVT = Outs[i].VT;
     ISD::ArgFlagsTy ArgFlags = Outs[i].Flags;
     Type *OrigTy = CLI ? CLI->getArgs()[Outs[i].OrigArgIndex].Ty : nullptr;
 
     RISCVABI::ABI ABI = MF.getSubtarget<RISCVSubtarget>().getTargetABI();
     if (CC_RISCV(MF.getDataLayout(), ABI, i, ArgVT, ArgVT, CCValAssign::Full,
-                 ArgFlags, CCInfo, Outs[i].IsFixed, IsRet, OrigTy)) {
+                 ArgFlags, CCInfo, Outs[i].IsFixed, IsRet, OrigTy, *this)) {
       LLVM_DEBUG(dbgs() << "OutputArg #" << i << " has unhandled type "
                         << EVT(ArgVT).getEVTString() << "\n");
       llvm_unreachable(nullptr);
     }
   }
 }
 
 // Convert Val to a ValVT. Should not be called for CCValAssign::Indirect
case CCValAssign::BCvt:
     break;
   }
   return Val;
 }
 
 // The caller is responsible for loading the full value if the argument is
 // passed with CCValAssign::Indirect.
 static SDValue unpackFromRegLoc(SelectionDAG &DAG, SDValue Chain,
-                                const CCValAssign &VA, const SDLoc &DL) {
+                                const CCValAssign &VA, const SDLoc &DL,
+                                const RISCVTargetLowering *TLI) {
   MachineFunction &MF = DAG.getMachineFunction();
   MachineRegisterInfo &RegInfo = MF.getRegInfo();
   EVT LocVT = VA.getLocVT();
   SDValue Val;
-  const TargetRegisterClass *RC;
-
-  switch (LocVT.getSimpleVT().SimpleTy) {
-  default:
-    llvm_unreachable("Unexpected register type");
-  case MVT::i32:
-  case MVT::i64:
-    RC = &RISCV::GPRRegClass;
-    break;
-  case MVT::f16:
-    RC = &RISCV::FPR16RegClass;
-    break;
-  case MVT::f32:
-    RC = &RISCV::FPR32RegClass;
-    break;
-  case MVT::f64:
-    RC = &RISCV::FPR64RegClass;
-    break;
-  }
-
+  const TargetRegisterClass *RC = TLI->getRegClassFor(LocVT.getSimpleVT());
   Register VReg = RegInfo.createVirtualRegister(RC);
   RegInfo.addLiveIn(VA.getLocReg(), VReg);
   Val = DAG.getCopyFromReg(Chain, DL, VReg, LocVT);
 
   if (VA.getLocInfo() == CCValAssign::Indirect)
     return Val;
 
   return convertLocVTToValVT(DAG, Val, VA, DL);
SDValue RISCVTargetLowering::LowerFormalArguments(
   for (unsigned i = 0, e = ArgLocs.size(); i != e; ++i) {
     CCValAssign &VA = ArgLocs[i];
     SDValue ArgValue;
     // Passing f64 on RV32D with a soft float ABI must be handled as a special
     // case.
     if (VA.getLocVT() == MVT::i32 && VA.getValVT() == MVT::f64)
       ArgValue = unpackF64OnRV32DSoftABI(DAG, Chain, VA, DL);
     else if (VA.isRegLoc())
-      ArgValue = unpackFromRegLoc(DAG, Chain, VA, DL);
+      ArgValue = unpackFromRegLoc(DAG, Chain, VA, DL, this);
     else
       ArgValue = unpackFromMemLoc(DAG, Chain, VA, DL);
 
     if (VA.getLocInfo() == CCValAssign::Indirect) {
       // If the original argument was split and passed by reference (e.g. i128
       // on RV32), we need to load all parts of it here (using the same
       // address).
       InVals.push_back(DAG.getLoad(VA.getValVT(), DL, Chain, ArgValue,
bool RISCVTargetLowering::CanLowerReturn(
     const SmallVectorImpl<ISD::OutputArg> &Outs, LLVMContext &Context) const {
   SmallVector<CCValAssign, 16> RVLocs;
   CCState CCInfo(CallConv, IsVarArg, MF, RVLocs, Context);
   for (unsigned i = 0, e = Outs.size(); i != e; ++i) {
     MVT VT = Outs[i].VT;
     ISD::ArgFlagsTy ArgFlags = Outs[i].Flags;
     RISCVABI::ABI ABI = MF.getSubtarget<RISCVSubtarget>().getTargetABI();
     if (CC_RISCV(MF.getDataLayout(), ABI, i, VT, VT, CCValAssign::Full,
-                 ArgFlags, CCInfo, /*IsFixed=*/true, /*IsRet=*/true, nullptr))
+                 ArgFlags, CCInfo, /*IsFixed=*/true, /*IsRet=*/true, nullptr,
+                 *this))
       return false;
   }
   return true;
 }
 
 SDValue
 RISCVTargetLowering::LowerReturn(SDValue Chain, CallingConv::ID CallConv,
                                  bool IsVarArg,

llvm/lib/Target/RISCV/RISCVInstrInfo.cpp

void RISCVInstrInfo::copyPhysReg(MachineBasicBlock &MBB,
                                  MCRegister SrcReg, bool KillSrc) const {
   if (RISCV::GPRRegClass.contains(DstReg, SrcReg)) {
     BuildMI(MBB, MBBI, DL, get(RISCV::ADDI), DstReg)
         .addReg(SrcReg, getKillRegState(KillSrc))
         .addImm(0);
     return;
   }
 
   // FPR->FPR copies
   unsigned Opc;
+  bool IsScalableVector = false;
   if (RISCV::FPR16RegClass.contains(DstReg, SrcReg))
     Opc = RISCV::FSGNJ_H;
   else if (RISCV::FPR32RegClass.contains(DstReg, SrcReg))
     Opc = RISCV::FSGNJ_S;
   else if (RISCV::FPR64RegClass.contains(DstReg, SrcReg))
     Opc = RISCV::FSGNJ_D;
-  else
+  else if (RISCV::VRRegClass.contains(DstReg, SrcReg)) {
+    Opc = RISCV::VMV1R_V;
+    IsScalableVector = true;
+  } else if (RISCV::VRM2RegClass.contains(DstReg, SrcReg)) {
+    Opc = RISCV::VMV2R_V;
+    IsScalableVector = true;
+  } else if (RISCV::VRM4RegClass.contains(DstReg, SrcReg)) {
+    Opc = RISCV::VMV4R_V;
+    IsScalableVector = true;
+  } else if (RISCV::VRM8RegClass.contains(DstReg, SrcReg)) {
+    Opc = RISCV::VMV8R_V;
+    IsScalableVector = true;
+  } else
     llvm_unreachable("Impossible reg-to-reg copy");
 
+  if (IsScalableVector) {
+    MachineFunction *MF = MBB.getParent();
+    const TargetRegisterInfo *RI = MF->getSubtarget().getRegisterInfo();
+    // Regardless LMUL = 1, 2, 4 or 8, the register is represented using the
+    // lowerest number of the register group. In V instruction definition, we
+    // only model the instructions using VR for LMUL = 1.
+    SrcReg = RI->getSubReg(SrcReg, RISCV::sub_vrm2);
+    DstReg = RI->getSubReg(DstReg, RISCV::sub_vrm2);
+    BuildMI(MBB, MBBI, DL, get(Opc), DstReg)
+      .addReg(SrcReg, getKillRegState(KillSrc));
+  } else
     BuildMI(MBB, MBBI, DL, get(Opc), DstReg)
       .addReg(SrcReg, getKillRegState(KillSrc))
       .addReg(SrcReg, getKillRegState(KillSrc));
 }
 
 void RISCVInstrInfo::storeRegToStackSlot(MachineBasicBlock &MBB,
                                          MachineBasicBlock::iterator I,
                                          Register SrcReg, bool IsKill, int FI,
                                          const TargetRegisterClass *RC,
                                          const TargetRegisterInfo *TRI) const {
   DebugLoc DL;
   if (I != MBB.end())
     DL = I->getDebugLoc();
 
   MachineFunction *MF = MBB.getParent();
   const MachineFrameInfo &MFI = MF->getFrameInfo();
   MachineMemOperand *MMO = MF->getMachineMemOperand(
       MachinePointerInfo::getFixedStack(*MF, FI), MachineMemOperand::MOStore,
       MFI.getObjectSize(FI), MFI.getObjectAlign(FI));

llvm/lib/Target/RISCV/RISCVInstrInfoVPseudos.td

 //===-- RISCVInstrInfoVPseudos.td - RISC-V 'V' Pseudos -----*- tablegen -*-===//
 //
 // Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
 // See https://llvm.org/LICENSE.txt for license information.
 // SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 //
 //===----------------------------------------------------------------------===//
 ///
 /// This file contains the required infrastructure to support code generation
 /// for the standard 'V' (Vector) extension, version 0.9.  This version is still
 /// experimental as the 'V' extension hasn't been ratified yet.
 ///
 /// This file is included from RISCVInstrInfoV.td
 ///
 //===----------------------------------------------------------------------===//
 
+// X0 has special meaning for vsetvl/vsetvli.
+//  rd | rs1 |   AVL value | Effect on vl
+//--------------------------------------------------------------
+// !X0 |  X0 |       VLMAX | Set vl to VLMAX
+//  X0 |  X0 | Value in vl | Keep current vl, just change vtype.
+def NoX0 : SDNodeXForm<undef,
+[{
+  auto *C = dyn_cast<ConstantSDNode>(N);
+  if (C && C->isNullValue()) {
+    SDLoc DL(N);
+    return SDValue(CurDAG->getMachineNode(RISCV::ADDI, DL, Subtarget->getXLenVT(),
+                   CurDAG->getRegister(RISCV::X0, Subtarget->getXLenVT()),
+                   CurDAG->getTargetConstant(0, DL, Subtarget->getXLenVT())), 0);
+  }
+  return SDValue(N, 0);
+}]>;
+
 //===----------------------------------------------------------------------===//
 // Utilities.
 //===----------------------------------------------------------------------===//
 
 // This class describes information associated to the LMUL.
 class LMULInfo<int lmul, VReg regclass, string mx> {
   bits<3> value = lmul; // This is encoded as the vlmul field of vtype.
   VReg vrclass = regclass;

 }
 
 // Output pattern for X0 used to represent VLMAX in the pseudo instructions.
 def VLMax : OutPatFrag<(ops), (XLenVT X0)>;
 
 // List of EEW.
 defvar EEWList = [8, 16, 32, 64];
 
+// We only model FPR32 for V instructions in RISCVInstrInfoV.td.
+// FP16/FP32/FP64 registers are alias each other. Convert FPR16 and FPR64
+// to FPR32 for V instructions is enough.
+class ToFPR32<ValueType type, DAGOperand operand, string name> {
+  dag ret = !cond(!eq(!cast<string>(operand), !cast<string>(FPR64)):
+                      (EXTRACT_SUBREG !dag(type, [FPR64], [name]), sub_32),
+                  !eq(!cast<string>(operand), !cast<string>(FPR16)):
+                      (SUBREG_TO_REG (i16 -1), !dag(type, [FPR16], [name]), sub_16),
+                  !eq(1, 1):
+                      !dag(type, [operand], [name]));
+}
+
 //===----------------------------------------------------------------------===//
 // Vector register and vector group type information.
 //===----------------------------------------------------------------------===//
 
 class VTypeInfo<ValueType Vec, ValueType Mas, int Sew, VReg Reg, LMULInfo M>
 {
   ValueType Vector = Vec;
   ValueType Mask = Mas;
def RISCVVPseudosTable : GenericTable {
   let FilterClass = "RISCVVPseudo";
   let CppTypeName = "PseudoInfo";
   let Fields = [ "Pseudo", "BaseInstr", "VLIndex", "SEWIndex", "MergeOpIndex",
                  "VLMul" ];
   let PrimaryKey = [ "Pseudo" ];
   let PrimaryKeyName = "getPseudoInfo";
 }
 
+def RISCVVIntrinsicsTable : GenericTable {
+  let FilterClass = "RISCVVIntrinsic";
+  let CppTypeName = "RISCVVIntrinsicInfo";
+  let Fields = ["IntrinsicID", "ExtendOperand"];
+  let PrimaryKey = ["IntrinsicID"];
+  let PrimaryKeyName = "getRISCVVIntrinsicInfo";
+}
+
 //===----------------------------------------------------------------------===//
 // Helpers to define the different pseudo instructions.
 //===----------------------------------------------------------------------===//
 
 class PseudoToVInst<string PseudoInst> {
   string VInst = !subst("_M8", "",
                  !subst("_M4", "",
                  !subst("_M2", "",
                  !subst("_M1", "",
                  !subst("_MF2", "",
                  !subst("_MF4", "",
                  !subst("_MF8", "",
                  !subst("_MASK", "",
                  !subst("Pseudo", "", PseudoInst)))))))));
 }
 
+// The destination vector register group for a masked vector instruction cannot
+// overlap the source mask register (v0), unless the destination vector register
+// is being written with a mask value (e.g., comparisons) or the scalar result
+// of a reduction.
+class GetVRegNoV0<VReg VRegClass> {
+  VReg R = !cond(!eq(VRegClass, VR) : VRNoV0,
+                 !eq(VRegClass, VRM2) : VRM2NoV0,
+                 !eq(VRegClass, VRM4) : VRM4NoV0,
+                 !eq(VRegClass, VRM8) : VRM8NoV0,
+                 !eq(1, 1) : VRegClass);
+}
+
 class VPseudoBinary<VReg RetClass,
                     VReg Op1Class,
                     DAGOperand Op2Class> :
         Pseudo<(outs RetClass:$rd),
                (ins Op1Class:$rs2, Op2Class:$rs1, GPR:$vl, ixlenimm:$sew), []>,
         RISCVVPseudo {
   let Uses = [VL, VTYPE];
   let VLIndex = 3;
   let SEWIndex = 4;
   let MergeOpIndex = -1;
   let BaseInstr = !cast<Instruction>(PseudoToVInst<NAME>.VInst);
 }
 
 class VPseudoBinaryMask<VReg RetClass,
                         VReg Op1Class,
                         DAGOperand Op2Class> :
-        Pseudo<(outs RetClass:$rd),
-                (ins RetClass:$merge,
+        Pseudo<(outs GetVRegNoV0<RetClass>.R:$rd),
+                (ins GetVRegNoV0<RetClass>.R:$merge,
                      Op1Class:$rs2, Op2Class:$rs1,
                      VMaskOp:$vm, GPR:$vl, ixlenimm:$sew), []>,
         RISCVVPseudo {
   let Constraints = "$rd = $merge";
   let Uses = [VL, VTYPE];
   let VLIndex = 5;
   let SEWIndex = 6;
   let MergeOpIndex = 1;
   let BaseInstr = !cast<Instruction>(PseudoToVInst<NAME>.VInst);
 }
 
 multiclass VPseudoBinary<VReg RetClass,
                          VReg Op1Class,
                          DAGOperand Op2Class,
                          LMULInfo MInfo> {
   def "_" # MInfo.MX : VPseudoBinary<RetClass, Op1Class, Op2Class>;
   def "_" # MInfo.MX # "_MASK" : VPseudoBinaryMask<RetClass, Op1Class, Op2Class>;
 }
 
 multiclass VPseudoBinaryV_VV {
   let mayLoad = 0, mayStore = 0, hasSideEffects = 0, usesCustomInserter = 1 in
   foreach m = MxList.m in
   {
     let VLMul = m.value in
multiclass VPseudoBinaryV_VI<Operand ImmType = simm5> {
   let mayLoad = 0, mayStore = 0, hasSideEffects = 0, usesCustomInserter = 1 in
   foreach m = MxList.m in
   {
     let VLMul = m.value in
     defm _VI : VPseudoBinary<m.vrclass, m.vrclass, ImmType, m>;
   }
 }
 
-multiclass VPseudoBinary_VV_VX_VI<Operand ImmType = simm5> {
+multiclass VPseudoBinaryV_VV_VX_VI<Operand ImmType = simm5> {
+  defm "" : VPseudoBinaryV_VV;
+  defm "" : VPseudoBinaryV_VX;
+  defm "" : VPseudoBinaryV_VI<ImmType>;
+}
+
+multiclass VPseudoBinaryV_VV_VX {
   defm "" : VPseudoBinaryV_VV;
   defm "" : VPseudoBinaryV_VX;
+}
+
+multiclass VPseudoBinaryV_VX_VI<Operand ImmType = simm5> {
+  defm "" : VPseudoBinaryV_VX;
   defm "" : VPseudoBinaryV_VI<ImmType>;
 }
 
 //===----------------------------------------------------------------------===//
 // Helpers to define the different patterns.
 //===----------------------------------------------------------------------===//
-
-multiclass pat_vop_binary<SDNode vop,
-                          string instruction_name,
-                          ValueType result_type,
-                          ValueType op_type,
-                          ValueType mask_type,
-                          int sew,
-                          LMULInfo vlmul,
-                          VReg RetClass,
-                          VReg op_reg_class,
-                          bit swap = 0>
-{
-  defvar instruction = !cast<Instruction>(instruction_name#"_VV_"# vlmul.MX);
-  def : Pat<(result_type (vop
-                          (op_type op_reg_class:$rs1),
-                          (op_type op_reg_class:$rs2))),
-            (instruction op_reg_class:$rs1,
-                         op_reg_class:$rs2,
-                         VLMax, sew)>;
-}
+class VPatBinarySDNode<SDNode vop,
+                       VReg op_reg_class> :
+    Pat<(result_type (vop
+                     (!cast<Instruction>(instruction_name#"_VV_"# vlmul.MX)
+                     op_reg_class:$rs1,
 
-multiclass pat_vop_binary_common<SDNode vop,
-                                 string instruction_name,
-                                 list<VTypeInfo> vtilist>
+multiclass VPatBinarySDNode<SDNode vop, string instruction_name>
 {
-  foreach vti = vtilist in
-  defm : pat_vop_binary<vop, instruction_name,
+  foreach vti = AllIntegerVectors in
+    def : VPatBinarySDNode<vop, instruction_name,
                            vti.Vector, vti.Vector, vti.Mask, vti.SEW,
                            vti.LMul, vti.RegClass, vti.RegClass>;
 }
 
+class VPatBinary<string intrinsic_name,
+                 string inst,
+                 string kind,
+                 ValueType result_type,
+                 ValueType op1_type,
+                 ValueType op2_type,
+                 ValueType mask_type,
+                 int sew,
+                 LMULInfo vlmul,
+                 VReg result_reg_class,
+                 VReg op1_reg_class,
+                 DAGOperand op2_kind> :
+  Pat<(result_type (!cast<Intrinsic>(intrinsic_name)
+                   (op1_type op1_reg_class:$rs1),
+                   (op2_type op2_kind:$rs2),
+                   (i64 GPR:$vl))),
+                   (!cast<Instruction>(inst#"_"#kind#"_"#vlmul.MX)
+                   (op1_type op1_reg_class:$rs1),
+                   ToFPR32<op2_type, op2_kind, "rs2">.ret,
+                   (NoX0 GPR:$vl), sew)>;
+
+class VPatBinaryMask<string intrinsic_name,
+                     string inst,
+                     string kind,
+                     ValueType result_type,
+                     ValueType op1_type,
+                     ValueType op2_type,
+                     ValueType mask_type,
+                     int sew,
+                     LMULInfo vlmul,
+                     VReg result_reg_class,
+                     VReg op1_reg_class,
+                     DAGOperand op2_kind> :
+  Pat<(result_type (!cast<Intrinsic>(intrinsic_name#"_mask")
+                   (result_type result_reg_class:$merge),
+                   (op1_type op1_reg_class:$rs1),
+                   (op2_type op2_kind:$rs2),
+                   (mask_type V0),
+                   (i64 GPR:$vl))),
+                   (!cast<Instruction>(inst#"_"#kind#"_"#vlmul.MX#"_MASK")
+                   (result_type result_reg_class:$merge),
+                   (op1_type op1_reg_class:$rs1),
+                   ToFPR32<op2_type, op2_kind, "rs2">.ret,
+                   (mask_type V0), (NoX0 GPR:$vl), sew)>;
+
+multiclass VPatBinary<string intrinsic,
+                      string inst,
+                      string kind,
+                      ValueType result_type,
+                      ValueType op1_type,
+                      ValueType op2_type,
+                      ValueType mask_type,
+                      int sew,
+                      LMULInfo vlmul,
+                      VReg result_reg_class,
+                      VReg op1_reg_class,
+                      DAGOperand op2_kind>
+{
+  def : VPatBinary<intrinsic, inst, kind, result_type, op1_type, op2_type,
+                   mask_type, sew, vlmul, result_reg_class, op1_reg_class,
+                   op2_kind>;
+  def : VPatBinaryMask<intrinsic, inst, kind, result_type, op1_type, op2_type,
+                       mask_type, sew, vlmul, result_reg_class, op1_reg_class,
+                       op2_kind>;
+}
+
+multiclass VPatBinaryV_VV<string intrinsic, string instruction> {
+  foreach vti = AllIntegerVectors in
+    defm : VPatBinary<intrinsic, instruction, "VV",
+                      vti.Vector, vti.Vector, vti.Vector, vti.Mask,
+                      vti.SEW, vti.LMul, vti.RegClass,
+                      vti.RegClass, vti.RegClass>;
+}
+
+multiclass VPatBinaryV_VX<string intrinsic, string instruction> {
+  foreach vti = AllIntegerVectors in
+    defm : VPatBinary<intrinsic, instruction, "VX",
+                      vti.Vector, vti.Vector, XLenVT, vti.Mask,
+                      vti.SEW, vti.LMul, vti.RegClass,
+                      vti.RegClass, GPR>;
+}
+
+multiclass VPatBinaryV_VI<string intrinsic, string instruction, Operand imm_type> {
+  foreach vti = AllIntegerVectors in
+    defm : VPatBinary<intrinsic, instruction, "VI",
+                      vti.Vector, vti.Vector, XLenVT, vti.Mask,
+                      vti.SEW, vti.LMul, vti.RegClass,
+                      vti.RegClass, imm_type>;
+}
+
+multiclass VPatBinary_VV_VX_VI<string intrinsic,
+                               string instruction,
+                               Operand imm_type = simm5>
+{
+  defm "" : VPatBinaryV_VV<intrinsic, instruction>;
+  defm "" : VPatBinaryV_VX<intrinsic, instruction>;
+  defm "" : VPatBinaryV_VI<intrinsic, instruction, imm_type>;
+}
+
+multiclass VPatBinary_VV_VX<string intrinsic,
+                            string instruction>
+{
+  defm "" : VPatBinaryV_VV<intrinsic, instruction>;
+  defm "" : VPatBinaryV_VX<intrinsic, instruction>;
+}
+
+multiclass VPatBinary_VX_VI<string intrinsic,
+                            string instruction,
+                            Operand imm_type = simm5>
+{
+  defm "" : VPatBinaryV_VX<intrinsic, instruction>;
+  defm "" : VPatBinaryV_VI<intrinsic, instruction, imm_type>;
+}
+
 //===----------------------------------------------------------------------===//
 // Pseudo instructions and patterns.
 //===----------------------------------------------------------------------===//
 
 let Predicates = [HasStdExtV] in {
 
 //===----------------------------------------------------------------------===//
 // 6. Configuration-Setting Instructions

 // 12. Vector Integer Arithmetic Instructions
 //===----------------------------------------------------------------------===//
 
 //===----------------------------------------------------------------------===//
 // 12.1. Vector Single-Width Integer Add and Subtract
 //===----------------------------------------------------------------------===//
 
 // Pseudo instructions.
-defm PseudoVADD        : VPseudoBinary_VV_VX_VI;
+defm PseudoVADD        : VPseudoBinaryV_VV_VX_VI;
+defm PseudoVSUB        : VPseudoBinaryV_VV_VX;
+defm PseudoVRSUB       : VPseudoBinaryV_VX_VI;
+
+//===----------------------------------------------------------------------===//
+// Patterns.
+//===----------------------------------------------------------------------===//
 
 // Whole-register vector patterns.
-defm "" : pat_vop_binary_common<add, "PseudoVADD", AllIntegerVectors>;
+defm "" : VPatBinarySDNode<add, "PseudoVADD">;
+
+defm "" : VPatBinary_VV_VX_VI<"int_riscv_vadd", "PseudoVADD">;
+defm "" : VPatBinary_VV_VX<"int_riscv_vsub", "PseudoVSUB">;
+defm "" : VPatBinary_VX_VI<"int_riscv_vrsub", "PseudoVRSUB">;
 
 } // Predicates = [HasStdExtV]

llvm/lib/Target/RISCV/RISCVRegisterInfo.td

def VRNoV0 : VReg<[vint8mf2_t, vint8mf4_t, vint8mf8_t,
                     (sequence "V%u", 8, 24),
                     (sequence "V%u", 1, 7)), 1>;
 
 def VRM2 : VReg<[vint8m2_t, vint16m2_t, vint32m2_t, vint64m2_t,
                  vfloat32m2_t, vfloat64m2_t],
              (add V26M2, V28M2, V30M2, V8M2, V10M2, V12M2, V14M2, V16M2,
                   V18M2, V20M2, V22M2, V24M2, V0M2, V2M2, V4M2, V6M2), 2>;
 
+def VRM2NoV0 : VReg<[vint8m2_t, vint16m2_t, vint32m2_t, vint64m2_t,
+                     vfloat32m2_t, vfloat64m2_t],
+                 (add V26M2, V28M2, V30M2, V8M2, V10M2, V12M2, V14M2, V16M2,
+                      V18M2, V20M2, V22M2, V24M2, V2M2, V4M2, V6M2), 2>;
+
 def VRM4 : VReg<[vint8m4_t, vint16m4_t, vint32m4_t, vint64m4_t,
                  vfloat32m4_t, vfloat64m4_t],
              (add V28M4, V8M4, V12M4, V16M4, V20M4, V24M4, V0M4, V4M4), 4>;
 
+def VRM4NoV0 : VReg<[vint8m4_t, vint16m4_t, vint32m4_t, vint64m4_t,
+                     vfloat32m4_t, vfloat64m4_t],
+                 (add V28M4, V8M4, V12M4, V16M4, V20M4, V24M4, V4M4), 4>;
+
 def VRM8 : VReg<[vint8m8_t, vint16m8_t, vint32m8_t, vint64m8_t,
                  vfloat32m8_t, vfloat64m8_t],
              (add V8M8, V16M8, V24M8, V0M8), 8>;
 
+def VRM8NoV0 : VReg<[vint8m8_t, vint16m8_t, vint32m8_t, vint64m8_t,
+                     vfloat32m8_t, vfloat64m8_t],
+                 (add V8M8, V16M8, V24M8), 8>;
+
 defvar VMaskVTs = [vbool64_t, vbool32_t, vbool16_t, vbool8_t,
                    vbool4_t, vbool2_t, vbool1_t];
 
 def VMV0 : RegisterClass<"RISCV", VMaskVTs, 64, (add V0)> {
   let Size = 64;
 }

llvm/lib/Target/RISCV/Utils/RISCVBaseInfo.h

 
 using namespace RISCV;
 
 #define GET_RISCVVPseudosTable_DECL
 #include "RISCVGenSearchableTables.inc"
 
 } // end namespace RISCVVPseudosTable
 
+namespace RISCVVIntrinsicsTable {
+
+struct RISCVVIntrinsicInfo {
+  unsigned int IntrinsicID;
+  unsigned int ExtendedOperand;
+};
+
+using namespace RISCV;
+
+#define GET_RISCVVIntrinsicsTable_DECL
+#include "RISCVGenSearchableTables.inc"
+
+} // end namespace RISCVVIntrinsicsTable
+
 } // namespace llvm
 
 #endif

llvm/lib/Target/RISCV/Utils/RISCVBaseInfo.cpp

 //===-- RISCVBaseInfo.cpp - Top level definitions for RISCV MC ------------===//
 //
 // Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
 // See https://llvm.org/LICENSE.txt for license information.
 // SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 //
 //===----------------------------------------------------------------------===//
 //
 // This file contains small standalone enum definitions for the RISCV target
 // useful for the compiler back-end and the MC libraries.
 //
 //===----------------------------------------------------------------------===//
 
 #include "RISCVBaseInfo.h"
 #include "llvm/ADT/ArrayRef.h"
 #include "llvm/ADT/Triple.h"
+#include "llvm/IR/IntrinsicsRISCV.h"
 #include "llvm/Support/raw_ostream.h"
 
 namespace llvm {
 namespace RISCVSysReg {
 #define GET_SysRegsList_IMPL
 #include "RISCVGenSearchableTables.inc"
 } // namespace RISCVSysReg
 

 
 void validate(const Triple &TT, const FeatureBitset &FeatureBits) {
   if (TT.isArch64Bit() && FeatureBits[RISCV::FeatureRV32E])
     report_fatal_error("RV32E can't be enabled for an RV64 target");
 }
 
 } // namespace RISCVFeatures
 
+namespace RISCVVIntrinsicsTable {
+
+#define GET_RISCVVIntrinsicsTable_IMPL
+#include "RISCVGenSearchableTables.inc"
+
+} // namespace RISCVVIntrinsicsTable
+
 namespace RISCVVPseudosTable {
 
 #define GET_RISCVVPseudosTable_IMPL
 #include "RISCVGenSearchableTables.inc"
 
 } // namespace RISCVVPseudosTable
 
 } // namespace llvm

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

+; RUN: llc -mtriple=riscv64 -mattr=+experimental-v -verify-machineinstrs \
+; RUN:   --riscv-no-aliases < %s | FileCheck %s
+declare <vscale x 1 x i8> @llvm.riscv.vadd.nxv1i8.nxv1i8(
+  <vscale x 1 x i8>,
+  <vscale x 1 x i8>,
+  i64);
+
+define <vscale x 1 x i8> @intrinsic_vadd_vv_nxv1i8_nxv1i8_nxv1i8(<vscale x 1 x i8> %0, <vscale x 1 x i8> %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_vv_nxv1i8_nxv1i8_nxv1i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,mf8,tu,mu
+; CHECK:       vadd.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
+  %a = call <vscale x 1 x i8> @llvm.riscv.vadd.nxv1i8.nxv1i8(
+    <vscale x 1 x i8> %0,
+    <vscale x 1 x i8> %1,
+    i64 %2)
+
+  ret <vscale x 1 x i8> %a
+}
+
+declare <vscale x 1 x i8> @llvm.riscv.vadd.mask.nxv1i8.nxv1i8(
+  <vscale x 1 x i8>,
+  <vscale x 1 x i8>,
+  <vscale x 1 x i8>,
+  <vscale x 1 x i1>,
+  i64);
+
+define <vscale x 1 x i8> @intrinsic_vadd_mask_vv_nxv1i8_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, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_mask_vv_nxv1i8_nxv1i8_nxv1i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,mf8,tu,mu
+; CHECK:       vadd.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}, v0.t
+  %a = call <vscale x 1 x i8> @llvm.riscv.vadd.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,
+    i64 %4)
+
+  ret <vscale x 1 x i8> %a
+}
+
+declare <vscale x 2 x i8> @llvm.riscv.vadd.nxv2i8.nxv2i8(
+  <vscale x 2 x i8>,
+  <vscale x 2 x i8>,
+  i64);
+
+define <vscale x 2 x i8> @intrinsic_vadd_vv_nxv2i8_nxv2i8_nxv2i8(<vscale x 2 x i8> %0, <vscale x 2 x i8> %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_vv_nxv2i8_nxv2i8_nxv2i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,mf4,tu,mu
+; CHECK:       vadd.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
+  %a = call <vscale x 2 x i8> @llvm.riscv.vadd.nxv2i8.nxv2i8(
+    <vscale x 2 x i8> %0,
+    <vscale x 2 x i8> %1,
+    i64 %2)
+
+  ret <vscale x 2 x i8> %a
+}
+
+declare <vscale x 2 x i8> @llvm.riscv.vadd.mask.nxv2i8.nxv2i8(
+  <vscale x 2 x i8>,
+  <vscale x 2 x i8>,
+  <vscale x 2 x i8>,
+  <vscale x 2 x i1>,
+  i64);
+
+define <vscale x 2 x i8> @intrinsic_vadd_mask_vv_nxv2i8_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, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_mask_vv_nxv2i8_nxv2i8_nxv2i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,mf4,tu,mu
+; CHECK:       vadd.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}, v0.t
+  %a = call <vscale x 2 x i8> @llvm.riscv.vadd.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,
+    i64 %4)
+
+  ret <vscale x 2 x i8> %a
+}
+
+declare <vscale x 4 x i8> @llvm.riscv.vadd.nxv4i8.nxv4i8(
+  <vscale x 4 x i8>,
+  <vscale x 4 x i8>,
+  i64);
+
+define <vscale x 4 x i8> @intrinsic_vadd_vv_nxv4i8_nxv4i8_nxv4i8(<vscale x 4 x i8> %0, <vscale x 4 x i8> %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_vv_nxv4i8_nxv4i8_nxv4i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,mf2,tu,mu
+; CHECK:       vadd.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
+  %a = call <vscale x 4 x i8> @llvm.riscv.vadd.nxv4i8.nxv4i8(
+    <vscale x 4 x i8> %0,
+    <vscale x 4 x i8> %1,
+    i64 %2)
+
+  ret <vscale x 4 x i8> %a
+}
+
+declare <vscale x 4 x i8> @llvm.riscv.vadd.mask.nxv4i8.nxv4i8(
+  <vscale x 4 x i8>,
+  <vscale x 4 x i8>,
+  <vscale x 4 x i8>,
+  <vscale x 4 x i1>,
+  i64);
+
+define <vscale x 4 x i8> @intrinsic_vadd_mask_vv_nxv4i8_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, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_mask_vv_nxv4i8_nxv4i8_nxv4i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,mf2,tu,mu
+; CHECK:       vadd.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}, v0.t
+  %a = call <vscale x 4 x i8> @llvm.riscv.vadd.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,
+    i64 %4)
+
+  ret <vscale x 4 x i8> %a
+}
+
+declare <vscale x 8 x i8> @llvm.riscv.vadd.nxv8i8.nxv8i8(
+  <vscale x 8 x i8>,
+  <vscale x 8 x i8>,
+  i64);
+
+define <vscale x 8 x i8> @intrinsic_vadd_vv_nxv8i8_nxv8i8_nxv8i8(<vscale x 8 x i8> %0, <vscale x 8 x i8> %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_vv_nxv8i8_nxv8i8_nxv8i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,m1,tu,mu
+; CHECK:       vadd.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
+  %a = call <vscale x 8 x i8> @llvm.riscv.vadd.nxv8i8.nxv8i8(
+    <vscale x 8 x i8> %0,
+    <vscale x 8 x i8> %1,
+    i64 %2)
+
+  ret <vscale x 8 x i8> %a
+}
+
+declare <vscale x 8 x i8> @llvm.riscv.vadd.mask.nxv8i8.nxv8i8(
+  <vscale x 8 x i8>,
+  <vscale x 8 x i8>,
+  <vscale x 8 x i8>,
+  <vscale x 8 x i1>,
+  i64);
+
+define <vscale x 8 x i8> @intrinsic_vadd_mask_vv_nxv8i8_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, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_mask_vv_nxv8i8_nxv8i8_nxv8i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,m1,tu,mu
+; CHECK:       vadd.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}, v0.t
+  %a = call <vscale x 8 x i8> @llvm.riscv.vadd.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,
+    i64 %4)
+
+  ret <vscale x 8 x i8> %a
+}
+
+declare <vscale x 16 x i8> @llvm.riscv.vadd.nxv16i8.nxv16i8(
+  <vscale x 16 x i8>,
+  <vscale x 16 x i8>,
+  i64);
+
+define <vscale x 16 x i8> @intrinsic_vadd_vv_nxv16i8_nxv16i8_nxv16i8(<vscale x 16 x i8> %0, <vscale x 16 x i8> %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_vv_nxv16i8_nxv16i8_nxv16i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,m2,tu,mu
+; CHECK:       vadd.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
+  %a = call <vscale x 16 x i8> @llvm.riscv.vadd.nxv16i8.nxv16i8(
+    <vscale x 16 x i8> %0,
+    <vscale x 16 x i8> %1,
+    i64 %2)
+
+  ret <vscale x 16 x i8> %a
+}
+
+declare <vscale x 16 x i8> @llvm.riscv.vadd.mask.nxv16i8.nxv16i8(
+  <vscale x 16 x i8>,
+  <vscale x 16 x i8>,
+  <vscale x 16 x i8>,
+  <vscale x 16 x i1>,
+  i64);
+
+define <vscale x 16 x i8> @intrinsic_vadd_mask_vv_nxv16i8_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, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_mask_vv_nxv16i8_nxv16i8_nxv16i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,m2,tu,mu
+; CHECK:       vadd.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}, v0.t
+  %a = call <vscale x 16 x i8> @llvm.riscv.vadd.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,
+    i64 %4)
+
+  ret <vscale x 16 x i8> %a
+}
+
+declare <vscale x 32 x i8> @llvm.riscv.vadd.nxv32i8.nxv32i8(
+  <vscale x 32 x i8>,
+  <vscale x 32 x i8>,
+  i64);
+
+define <vscale x 32 x i8> @intrinsic_vadd_vv_nxv32i8_nxv32i8_nxv32i8(<vscale x 32 x i8> %0, <vscale x 32 x i8> %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_vv_nxv32i8_nxv32i8_nxv32i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,m4,tu,mu
+; CHECK:       vadd.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
+  %a = call <vscale x 32 x i8> @llvm.riscv.vadd.nxv32i8.nxv32i8(
+    <vscale x 32 x i8> %0,
+    <vscale x 32 x i8> %1,
+    i64 %2)
+
+  ret <vscale x 32 x i8> %a
+}
+
+declare <vscale x 32 x i8> @llvm.riscv.vadd.mask.nxv32i8.nxv32i8(
+  <vscale x 32 x i8>,
+  <vscale x 32 x i8>,
+  <vscale x 32 x i8>,
+  <vscale x 32 x i1>,
+  i64);
+
+define <vscale x 32 x i8> @intrinsic_vadd_mask_vv_nxv32i8_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, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_mask_vv_nxv32i8_nxv32i8_nxv32i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,m4,tu,mu
+; CHECK:       vadd.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}, v0.t
+  %a = call <vscale x 32 x i8> @llvm.riscv.vadd.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,
+    i64 %4)
+
+  ret <vscale x 32 x i8> %a
+}
+
+declare <vscale x 64 x i8> @llvm.riscv.vadd.nxv64i8.nxv64i8(
+  <vscale x 64 x i8>,
+  <vscale x 64 x i8>,
+  i64);
+
+define <vscale x 64 x i8> @intrinsic_vadd_vv_nxv64i8_nxv64i8_nxv64i8(<vscale x 64 x i8> %0, <vscale x 64 x i8> %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_vv_nxv64i8_nxv64i8_nxv64i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,m8,tu,mu
+; CHECK:       vadd.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
+  %a = call <vscale x 64 x i8> @llvm.riscv.vadd.nxv64i8.nxv64i8(
+    <vscale x 64 x i8> %0,
+    <vscale x 64 x i8> %1,
+    i64 %2)
+
+  ret <vscale x 64 x i8> %a
+}
+
+declare <vscale x 64 x i8> @llvm.riscv.vadd.mask.nxv64i8.nxv64i8(
+  <vscale x 64 x i8>,
+  <vscale x 64 x i8>,
+  <vscale x 64 x i8>,
+  <vscale x 64 x i1>,
+  i64);
+
+define <vscale x 64 x i8> @intrinsic_vadd_mask_vv_nxv64i8_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, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_mask_vv_nxv64i8_nxv64i8_nxv64i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,m8,tu,mu
+; CHECK:       vadd.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}, v0.t
+  %a = call <vscale x 64 x i8> @llvm.riscv.vadd.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,
+    i64 %4)
+
+  ret <vscale x 64 x i8> %a
+}
+
+declare <vscale x 1 x i16> @llvm.riscv.vadd.nxv1i16.nxv1i16(
+  <vscale x 1 x i16>,
+  <vscale x 1 x i16>,
+  i64);
+
+define <vscale x 1 x i16> @intrinsic_vadd_vv_nxv1i16_nxv1i16_nxv1i16(<vscale x 1 x i16> %0, <vscale x 1 x i16> %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_vv_nxv1i16_nxv1i16_nxv1i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,mf4,tu,mu
+; CHECK:       vadd.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
+  %a = call <vscale x 1 x i16> @llvm.riscv.vadd.nxv1i16.nxv1i16(
+    <vscale x 1 x i16> %0,
+    <vscale x 1 x i16> %1,
+    i64 %2)
+
+  ret <vscale x 1 x i16> %a
+}
+
+declare <vscale x 1 x i16> @llvm.riscv.vadd.mask.nxv1i16.nxv1i16(
+  <vscale x 1 x i16>,
+  <vscale x 1 x i16>,
+  <vscale x 1 x i16>,
+  <vscale x 1 x i1>,
+  i64);
+
+define <vscale x 1 x i16> @intrinsic_vadd_mask_vv_nxv1i16_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, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_mask_vv_nxv1i16_nxv1i16_nxv1i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,mf4,tu,mu
+; CHECK:       vadd.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}, v0.t
+  %a = call <vscale x 1 x i16> @llvm.riscv.vadd.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,
+    i64 %4)
+
+  ret <vscale x 1 x i16> %a
+}
+
+declare <vscale x 2 x i16> @llvm.riscv.vadd.nxv2i16.nxv2i16(
+  <vscale x 2 x i16>,
+  <vscale x 2 x i16>,
+  i64);
+
+define <vscale x 2 x i16> @intrinsic_vadd_vv_nxv2i16_nxv2i16_nxv2i16(<vscale x 2 x i16> %0, <vscale x 2 x i16> %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_vv_nxv2i16_nxv2i16_nxv2i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,mf2,tu,mu
+; CHECK:       vadd.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
+  %a = call <vscale x 2 x i16> @llvm.riscv.vadd.nxv2i16.nxv2i16(
+    <vscale x 2 x i16> %0,
+    <vscale x 2 x i16> %1,
+    i64 %2)
+
+  ret <vscale x 2 x i16> %a
+}
+
+declare <vscale x 2 x i16> @llvm.riscv.vadd.mask.nxv2i16.nxv2i16(
+  <vscale x 2 x i16>,
+  <vscale x 2 x i16>,
+  <vscale x 2 x i16>,
+  <vscale x 2 x i1>,
+  i64);
+
+define <vscale x 2 x i16> @intrinsic_vadd_mask_vv_nxv2i16_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, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_mask_vv_nxv2i16_nxv2i16_nxv2i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,mf2,tu,mu
+; CHECK:       vadd.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}, v0.t
+  %a = call <vscale x 2 x i16> @llvm.riscv.vadd.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,
+    i64 %4)
+
+  ret <vscale x 2 x i16> %a
+}
+
+declare <vscale x 4 x i16> @llvm.riscv.vadd.nxv4i16.nxv4i16(
+  <vscale x 4 x i16>,
+  <vscale x 4 x i16>,
+  i64);
+
+define <vscale x 4 x i16> @intrinsic_vadd_vv_nxv4i16_nxv4i16_nxv4i16(<vscale x 4 x i16> %0, <vscale x 4 x i16> %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_vv_nxv4i16_nxv4i16_nxv4i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,m1,tu,mu
+; CHECK:       vadd.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
+  %a = call <vscale x 4 x i16> @llvm.riscv.vadd.nxv4i16.nxv4i16(
+    <vscale x 4 x i16> %0,
+    <vscale x 4 x i16> %1,
+    i64 %2)
+
+  ret <vscale x 4 x i16> %a
+}
+
+declare <vscale x 4 x i16> @llvm.riscv.vadd.mask.nxv4i16.nxv4i16(
+  <vscale x 4 x i16>,
+  <vscale x 4 x i16>,
+  <vscale x 4 x i16>,
+  <vscale x 4 x i1>,
+  i64);
+
+define <vscale x 4 x i16> @intrinsic_vadd_mask_vv_nxv4i16_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, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_mask_vv_nxv4i16_nxv4i16_nxv4i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,m1,tu,mu
+; CHECK:       vadd.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}, v0.t
+  %a = call <vscale x 4 x i16> @llvm.riscv.vadd.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,
+    i64 %4)
+
+  ret <vscale x 4 x i16> %a
+}
+
+declare <vscale x 8 x i16> @llvm.riscv.vadd.nxv8i16.nxv8i16(
+  <vscale x 8 x i16>,
+  <vscale x 8 x i16>,
+  i64);
+
+define <vscale x 8 x i16> @intrinsic_vadd_vv_nxv8i16_nxv8i16_nxv8i16(<vscale x 8 x i16> %0, <vscale x 8 x i16> %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_vv_nxv8i16_nxv8i16_nxv8i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,m2,tu,mu
+; CHECK:       vadd.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
+  %a = call <vscale x 8 x i16> @llvm.riscv.vadd.nxv8i16.nxv8i16(
+    <vscale x 8 x i16> %0,
+    <vscale x 8 x i16> %1,
+    i64 %2)
+
+  ret <vscale x 8 x i16> %a
+}
+
+declare <vscale x 8 x i16> @llvm.riscv.vadd.mask.nxv8i16.nxv8i16(
+  <vscale x 8 x i16>,
+  <vscale x 8 x i16>,
+  <vscale x 8 x i16>,
+  <vscale x 8 x i1>,
+  i64);
+
+define <vscale x 8 x i16> @intrinsic_vadd_mask_vv_nxv8i16_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, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_mask_vv_nxv8i16_nxv8i16_nxv8i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,m2,tu,mu
+; CHECK:       vadd.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}, v0.t
+  %a = call <vscale x 8 x i16> @llvm.riscv.vadd.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,
+    i64 %4)
+
+  ret <vscale x 8 x i16> %a
+}
+
+declare <vscale x 16 x i16> @llvm.riscv.vadd.nxv16i16.nxv16i16(
+  <vscale x 16 x i16>,
+  <vscale x 16 x i16>,
+  i64);
+
+define <vscale x 16 x i16> @intrinsic_vadd_vv_nxv16i16_nxv16i16_nxv16i16(<vscale x 16 x i16> %0, <vscale x 16 x i16> %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_vv_nxv16i16_nxv16i16_nxv16i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,m4,tu,mu
+; CHECK:       vadd.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
+  %a = call <vscale x 16 x i16> @llvm.riscv.vadd.nxv16i16.nxv16i16(
+    <vscale x 16 x i16> %0,
+    <vscale x 16 x i16> %1,
+    i64 %2)
+
+  ret <vscale x 16 x i16> %a
+}
+
+declare <vscale x 16 x i16> @llvm.riscv.vadd.mask.nxv16i16.nxv16i16(
+  <vscale x 16 x i16>,
+  <vscale x 16 x i16>,
+  <vscale x 16 x i16>,
+  <vscale x 16 x i1>,
+  i64);
+
+define <vscale x 16 x i16> @intrinsic_vadd_mask_vv_nxv16i16_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, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_mask_vv_nxv16i16_nxv16i16_nxv16i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,m4,tu,mu
+; CHECK:       vadd.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}, v0.t
+  %a = call <vscale x 16 x i16> @llvm.riscv.vadd.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,
+    i64 %4)
+
+  ret <vscale x 16 x i16> %a
+}
+
+declare <vscale x 32 x i16> @llvm.riscv.vadd.nxv32i16.nxv32i16(
+  <vscale x 32 x i16>,
+  <vscale x 32 x i16>,
+  i64);
+
+define <vscale x 32 x i16> @intrinsic_vadd_vv_nxv32i16_nxv32i16_nxv32i16(<vscale x 32 x i16> %0, <vscale x 32 x i16> %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_vv_nxv32i16_nxv32i16_nxv32i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,m8,tu,mu
+; CHECK:       vadd.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
+  %a = call <vscale x 32 x i16> @llvm.riscv.vadd.nxv32i16.nxv32i16(
+    <vscale x 32 x i16> %0,
+    <vscale x 32 x i16> %1,
+    i64 %2)
+
+  ret <vscale x 32 x i16> %a
+}
+
+declare <vscale x 32 x i16> @llvm.riscv.vadd.mask.nxv32i16.nxv32i16(
+  <vscale x 32 x i16>,
+  <vscale x 32 x i16>,
+  <vscale x 32 x i16>,
+  <vscale x 32 x i1>,
+  i64);
+
+define <vscale x 32 x i16> @intrinsic_vadd_mask_vv_nxv32i16_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, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_mask_vv_nxv32i16_nxv32i16_nxv32i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,m8,tu,mu
+; CHECK:       vadd.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}, v0.t
+  %a = call <vscale x 32 x i16> @llvm.riscv.vadd.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,
+    i64 %4)
+
+  ret <vscale x 32 x i16> %a
+}
+
+declare <vscale x 1 x i32> @llvm.riscv.vadd.nxv1i32.nxv1i32(
+  <vscale x 1 x i32>,
+  <vscale x 1 x i32>,
+  i64);
+
+define <vscale x 1 x i32> @intrinsic_vadd_vv_nxv1i32_nxv1i32_nxv1i32(<vscale x 1 x i32> %0, <vscale x 1 x i32> %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_vv_nxv1i32_nxv1i32_nxv1i32
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e32,mf2,tu,mu
+; CHECK:       vadd.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
+  %a = call <vscale x 1 x i32> @llvm.riscv.vadd.nxv1i32.nxv1i32(
+    <vscale x 1 x i32> %0,
+    <vscale x 1 x i32> %1,
+    i64 %2)
+
+  ret <vscale x 1 x i32> %a
+}
+
+declare <vscale x 1 x i32> @llvm.riscv.vadd.mask.nxv1i32.nxv1i32(
+  <vscale x 1 x i32>,
+  <vscale x 1 x i32>,
+  <vscale x 1 x i32>,
+  <vscale x 1 x i1>,
+  i64);
+
+define <vscale x 1 x i32> @intrinsic_vadd_mask_vv_nxv1i32_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, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_mask_vv_nxv1i32_nxv1i32_nxv1i32
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e32,mf2,tu,mu
+; CHECK:       vadd.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}, v0.t
+  %a = call <vscale x 1 x i32> @llvm.riscv.vadd.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,
+    i64 %4)
+
+  ret <vscale x 1 x i32> %a
+}
+
+declare <vscale x 2 x i32> @llvm.riscv.vadd.nxv2i32.nxv2i32(
+  <vscale x 2 x i32>,
+  <vscale x 2 x i32>,
+  i64);
+
+define <vscale x 2 x i32> @intrinsic_vadd_vv_nxv2i32_nxv2i32_nxv2i32(<vscale x 2 x i32> %0, <vscale x 2 x i32> %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_vv_nxv2i32_nxv2i32_nxv2i32
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e32,m1,tu,mu
+; CHECK:       vadd.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
+  %a = call <vscale x 2 x i32> @llvm.riscv.vadd.nxv2i32.nxv2i32(
+    <vscale x 2 x i32> %0,
+    <vscale x 2 x i32> %1,
+    i64 %2)
+
+  ret <vscale x 2 x i32> %a
+}
+
+declare <vscale x 2 x i32> @llvm.riscv.vadd.mask.nxv2i32.nxv2i32(
+  <vscale x 2 x i32>,
+  <vscale x 2 x i32>,
+  <vscale x 2 x i32>,
+  <vscale x 2 x i1>,
+  i64);
+
+define <vscale x 2 x i32> @intrinsic_vadd_mask_vv_nxv2i32_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, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_mask_vv_nxv2i32_nxv2i32_nxv2i32
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e32,m1,tu,mu
+; CHECK:       vadd.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}, v0.t
+  %a = call <vscale x 2 x i32> @llvm.riscv.vadd.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,
+    i64 %4)
+
+  ret <vscale x 2 x i32> %a
+}
+
+declare <vscale x 4 x i32> @llvm.riscv.vadd.nxv4i32.nxv4i32(
+  <vscale x 4 x i32>,
+  <vscale x 4 x i32>,
+  i64);
+
+define <vscale x 4 x i32> @intrinsic_vadd_vv_nxv4i32_nxv4i32_nxv4i32(<vscale x 4 x i32> %0, <vscale x 4 x i32> %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_vv_nxv4i32_nxv4i32_nxv4i32
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e32,m2,tu,mu
+; CHECK:       vadd.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
+  %a = call <vscale x 4 x i32> @llvm.riscv.vadd.nxv4i32.nxv4i32(
+    <vscale x 4 x i32> %0,
+    <vscale x 4 x i32> %1,
+    i64 %2)
+
+  ret <vscale x 4 x i32> %a
+}
+
+declare <vscale x 4 x i32> @llvm.riscv.vadd.mask.nxv4i32.nxv4i32(
+  <vscale x 4 x i32>,
+  <vscale x 4 x i32>,
+  <vscale x 4 x i32>,
+  <vscale x 4 x i1>,
+  i64);
+
+define <vscale x 4 x i32> @intrinsic_vadd_mask_vv_nxv4i32_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, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_mask_vv_nxv4i32_nxv4i32_nxv4i32
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e32,m2,tu,mu
+; CHECK:       vadd.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}, v0.t
+  %a = call <vscale x 4 x i32> @llvm.riscv.vadd.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,
+    i64 %4)
+
+  ret <vscale x 4 x i32> %a
+}
+
+declare <vscale x 8 x i32> @llvm.riscv.vadd.nxv8i32.nxv8i32(
+  <vscale x 8 x i32>,
+  <vscale x 8 x i32>,
+  i64);
+
+define <vscale x 8 x i32> @intrinsic_vadd_vv_nxv8i32_nxv8i32_nxv8i32(<vscale x 8 x i32> %0, <vscale x 8 x i32> %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_vv_nxv8i32_nxv8i32_nxv8i32
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e32,m4,tu,mu
+; CHECK:       vadd.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
+  %a = call <vscale x 8 x i32> @llvm.riscv.vadd.nxv8i32.nxv8i32(
+    <vscale x 8 x i32> %0,
+    <vscale x 8 x i32> %1,
+    i64 %2)
+
+  ret <vscale x 8 x i32> %a
+}
+
+declare <vscale x 8 x i32> @llvm.riscv.vadd.mask.nxv8i32.nxv8i32(
+  <vscale x 8 x i32>,
+  <vscale x 8 x i32>,
+  <vscale x 8 x i32>,
+  <vscale x 8 x i1>,
+  i64);
+
+define <vscale x 8 x i32> @intrinsic_vadd_mask_vv_nxv8i32_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, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_mask_vv_nxv8i32_nxv8i32_nxv8i32
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e32,m4,tu,mu
+; CHECK:       vadd.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}, v0.t
+  %a = call <vscale x 8 x i32> @llvm.riscv.vadd.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,
+    i64 %4)
+
+  ret <vscale x 8 x i32> %a
+}
+
+declare <vscale x 16 x i32> @llvm.riscv.vadd.nxv16i32.nxv16i32(
+  <vscale x 16 x i32>,
+  <vscale x 16 x i32>,
+  i64);
+
+define <vscale x 16 x i32> @intrinsic_vadd_vv_nxv16i32_nxv16i32_nxv16i32(<vscale x 16 x i32> %0, <vscale x 16 x i32> %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_vv_nxv16i32_nxv16i32_nxv16i32
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e32,m8,tu,mu
+; CHECK:       vadd.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
+  %a = call <vscale x 16 x i32> @llvm.riscv.vadd.nxv16i32.nxv16i32(
+    <vscale x 16 x i32> %0,
+    <vscale x 16 x i32> %1,
+    i64 %2)
+
+  ret <vscale x 16 x i32> %a
+}
+
+declare <vscale x 16 x i32> @llvm.riscv.vadd.mask.nxv16i32.nxv16i32(
+  <vscale x 16 x i32>,
+  <vscale x 16 x i32>,
+  <vscale x 16 x i32>,
+  <vscale x 16 x i1>,
+  i64);
+
+define <vscale x 16 x i32> @intrinsic_vadd_mask_vv_nxv16i32_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, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_mask_vv_nxv16i32_nxv16i32_nxv16i32
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e32,m8,tu,mu
+; CHECK:       vadd.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}, v0.t
+  %a = call <vscale x 16 x i32> @llvm.riscv.vadd.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,
+    i64 %4)
+
+  ret <vscale x 16 x i32> %a
+}
+
+declare <vscale x 1 x i64> @llvm.riscv.vadd.nxv1i64.nxv1i64(
+  <vscale x 1 x i64>,
+  <vscale x 1 x i64>,
+  i64);
+
+define <vscale x 1 x i64> @intrinsic_vadd_vv_nxv1i64_nxv1i64_nxv1i64(<vscale x 1 x i64> %0, <vscale x 1 x i64> %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_vv_nxv1i64_nxv1i64_nxv1i64
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e64,m1,tu,mu
+; CHECK:       vadd.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
+  %a = call <vscale x 1 x i64> @llvm.riscv.vadd.nxv1i64.nxv1i64(
+    <vscale x 1 x i64> %0,
+    <vscale x 1 x i64> %1,
+    i64 %2)
+
+  ret <vscale x 1 x i64> %a
+}
+
+declare <vscale x 1 x i64> @llvm.riscv.vadd.mask.nxv1i64.nxv1i64(
+  <vscale x 1 x i64>,
+  <vscale x 1 x i64>,
+  <vscale x 1 x i64>,
+  <vscale x 1 x i1>,
+  i64);
+
+define <vscale x 1 x i64> @intrinsic_vadd_mask_vv_nxv1i64_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, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_mask_vv_nxv1i64_nxv1i64_nxv1i64
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e64,m1,tu,mu
+; CHECK:       vadd.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}, v0.t
+  %a = call <vscale x 1 x i64> @llvm.riscv.vadd.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,
+    i64 %4)
+
+  ret <vscale x 1 x i64> %a
+}
+
+declare <vscale x 2 x i64> @llvm.riscv.vadd.nxv2i64.nxv2i64(
+  <vscale x 2 x i64>,
+  <vscale x 2 x i64>,
+  i64);
+
+define <vscale x 2 x i64> @intrinsic_vadd_vv_nxv2i64_nxv2i64_nxv2i64(<vscale x 2 x i64> %0, <vscale x 2 x i64> %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_vv_nxv2i64_nxv2i64_nxv2i64
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e64,m2,tu,mu
+; CHECK:       vadd.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
+  %a = call <vscale x 2 x i64> @llvm.riscv.vadd.nxv2i64.nxv2i64(
+    <vscale x 2 x i64> %0,
+    <vscale x 2 x i64> %1,
+    i64 %2)
+
+  ret <vscale x 2 x i64> %a
+}
+
+declare <vscale x 2 x i64> @llvm.riscv.vadd.mask.nxv2i64.nxv2i64(
+  <vscale x 2 x i64>,
+  <vscale x 2 x i64>,
+  <vscale x 2 x i64>,
+  <vscale x 2 x i1>,
+  i64);
+
+define <vscale x 2 x i64> @intrinsic_vadd_mask_vv_nxv2i64_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, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_mask_vv_nxv2i64_nxv2i64_nxv2i64
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e64,m2,tu,mu
+; CHECK:       vadd.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}, v0.t
+  %a = call <vscale x 2 x i64> @llvm.riscv.vadd.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,
+    i64 %4)
+
+  ret <vscale x 2 x i64> %a
+}
+
+declare <vscale x 4 x i64> @llvm.riscv.vadd.nxv4i64.nxv4i64(
+  <vscale x 4 x i64>,
+  <vscale x 4 x i64>,
+  i64);
+
+define <vscale x 4 x i64> @intrinsic_vadd_vv_nxv4i64_nxv4i64_nxv4i64(<vscale x 4 x i64> %0, <vscale x 4 x i64> %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_vv_nxv4i64_nxv4i64_nxv4i64
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e64,m4,tu,mu
+; CHECK:       vadd.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
+  %a = call <vscale x 4 x i64> @llvm.riscv.vadd.nxv4i64.nxv4i64(
+    <vscale x 4 x i64> %0,
+    <vscale x 4 x i64> %1,
+    i64 %2)
+
+  ret <vscale x 4 x i64> %a
+}
+
+declare <vscale x 4 x i64> @llvm.riscv.vadd.mask.nxv4i64.nxv4i64(
+  <vscale x 4 x i64>,
+  <vscale x 4 x i64>,
+  <vscale x 4 x i64>,
+  <vscale x 4 x i1>,
+  i64);
+
+define <vscale x 4 x i64> @intrinsic_vadd_mask_vv_nxv4i64_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, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_mask_vv_nxv4i64_nxv4i64_nxv4i64
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e64,m4,tu,mu
+; CHECK:       vadd.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}, v0.t
+  %a = call <vscale x 4 x i64> @llvm.riscv.vadd.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,
+    i64 %4)
+
+  ret <vscale x 4 x i64> %a
+}
+
+declare <vscale x 8 x i64> @llvm.riscv.vadd.nxv8i64.nxv8i64(
+  <vscale x 8 x i64>,
+  <vscale x 8 x i64>,
+  i64);
+
+define <vscale x 8 x i64> @intrinsic_vadd_vv_nxv8i64_nxv8i64_nxv8i64(<vscale x 8 x i64> %0, <vscale x 8 x i64> %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_vv_nxv8i64_nxv8i64_nxv8i64
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e64,m8,tu,mu
+; CHECK:       vadd.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
+  %a = call <vscale x 8 x i64> @llvm.riscv.vadd.nxv8i64.nxv8i64(
+    <vscale x 8 x i64> %0,
+    <vscale x 8 x i64> %1,
+    i64 %2)
+
+  ret <vscale x 8 x i64> %a
+}
+
+declare <vscale x 8 x i64> @llvm.riscv.vadd.mask.nxv8i64.nxv8i64(
+  <vscale x 8 x i64>,
+  <vscale x 8 x i64>,
+  <vscale x 8 x i64>,
+  <vscale x 8 x i1>,
+  i64);
+
+define <vscale x 8 x i64> @intrinsic_vadd_mask_vv_nxv8i64_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, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_mask_vv_nxv8i64_nxv8i64_nxv8i64
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e64,m8,tu,mu
+; CHECK:       vadd.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}, v0.t
+  %a = call <vscale x 8 x i64> @llvm.riscv.vadd.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,
+    i64 %4)
+
+  ret <vscale x 8 x i64> %a
+}
+
+declare <vscale x 1 x i8> @llvm.riscv.vadd.nxv1i8.i8(
+  <vscale x 1 x i8>,
+  i8,
+  i64);
+
+define <vscale x 1 x i8> @intrinsic_vadd_vx_nxv1i8_nxv1i8_i8(<vscale x 1 x i8> %0, i8 %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_vx_nxv1i8_nxv1i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,mf8,tu,mu
+; CHECK:       vadd.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 1 x i8> @llvm.riscv.vadd.nxv1i8.i8(
+    <vscale x 1 x i8> %0,
+    i8 %1,
+    i64 %2)
+
+  ret <vscale x 1 x i8> %a
+}
+
+declare <vscale x 1 x i8> @llvm.riscv.vadd.mask.nxv1i8.i8(
+  <vscale x 1 x i8>,
+  <vscale x 1 x i8>,
+  i8,
+  <vscale x 1 x i1>,
+  i64);
+
+define <vscale x 1 x i8> @intrinsic_vadd_mask_vx_nxv1i8_nxv1i8_i8(<vscale x 1 x i8> %0, <vscale x 1 x i8> %1, i8 %2, <vscale x 1 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_mask_vx_nxv1i8_nxv1i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,mf8,tu,mu
+; CHECK:       vadd.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 1 x i8> @llvm.riscv.vadd.mask.nxv1i8.i8(
+    <vscale x 1 x i8> %0,
+    <vscale x 1 x i8> %1,
+    i8 %2,
+    <vscale x 1 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 1 x i8> %a
+}
+
+declare <vscale x 2 x i8> @llvm.riscv.vadd.nxv2i8.i8(
+  <vscale x 2 x i8>,
+  i8,
+  i64);
+
+define <vscale x 2 x i8> @intrinsic_vadd_vx_nxv2i8_nxv2i8_i8(<vscale x 2 x i8> %0, i8 %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_vx_nxv2i8_nxv2i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,mf4,tu,mu
+; CHECK:       vadd.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 2 x i8> @llvm.riscv.vadd.nxv2i8.i8(
+    <vscale x 2 x i8> %0,
+    i8 %1,
+    i64 %2)
+
+  ret <vscale x 2 x i8> %a
+}
+
+declare <vscale x 2 x i8> @llvm.riscv.vadd.mask.nxv2i8.i8(
+  <vscale x 2 x i8>,
+  <vscale x 2 x i8>,
+  i8,
+  <vscale x 2 x i1>,
+  i64);
+
+define <vscale x 2 x i8> @intrinsic_vadd_mask_vx_nxv2i8_nxv2i8_i8(<vscale x 2 x i8> %0, <vscale x 2 x i8> %1, i8 %2, <vscale x 2 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_mask_vx_nxv2i8_nxv2i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,mf4,tu,mu
+; CHECK:       vadd.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 2 x i8> @llvm.riscv.vadd.mask.nxv2i8.i8(
+    <vscale x 2 x i8> %0,
+    <vscale x 2 x i8> %1,
+    i8 %2,
+    <vscale x 2 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 2 x i8> %a
+}
+
+declare <vscale x 4 x i8> @llvm.riscv.vadd.nxv4i8.i8(
+  <vscale x 4 x i8>,
+  i8,
+  i64);
+
+define <vscale x 4 x i8> @intrinsic_vadd_vx_nxv4i8_nxv4i8_i8(<vscale x 4 x i8> %0, i8 %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_vx_nxv4i8_nxv4i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,mf2,tu,mu
+; CHECK:       vadd.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 4 x i8> @llvm.riscv.vadd.nxv4i8.i8(
+    <vscale x 4 x i8> %0,
+    i8 %1,
+    i64 %2)
+
+  ret <vscale x 4 x i8> %a
+}
+
+declare <vscale x 4 x i8> @llvm.riscv.vadd.mask.nxv4i8.i8(
+  <vscale x 4 x i8>,
+  <vscale x 4 x i8>,
+  i8,
+  <vscale x 4 x i1>,
+  i64);
+
+define <vscale x 4 x i8> @intrinsic_vadd_mask_vx_nxv4i8_nxv4i8_i8(<vscale x 4 x i8> %0, <vscale x 4 x i8> %1, i8 %2, <vscale x 4 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_mask_vx_nxv4i8_nxv4i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,mf2,tu,mu
+; CHECK:       vadd.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 4 x i8> @llvm.riscv.vadd.mask.nxv4i8.i8(
+    <vscale x 4 x i8> %0,
+    <vscale x 4 x i8> %1,
+    i8 %2,
+    <vscale x 4 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 4 x i8> %a
+}
+
+declare <vscale x 8 x i8> @llvm.riscv.vadd.nxv8i8.i8(
+  <vscale x 8 x i8>,
+  i8,
+  i64);
+
+define <vscale x 8 x i8> @intrinsic_vadd_vx_nxv8i8_nxv8i8_i8(<vscale x 8 x i8> %0, i8 %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_vx_nxv8i8_nxv8i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,m1,tu,mu
+; CHECK:       vadd.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 8 x i8> @llvm.riscv.vadd.nxv8i8.i8(
+    <vscale x 8 x i8> %0,
+    i8 %1,
+    i64 %2)
+
+  ret <vscale x 8 x i8> %a
+}
+
+declare <vscale x 8 x i8> @llvm.riscv.vadd.mask.nxv8i8.i8(
+  <vscale x 8 x i8>,
+  <vscale x 8 x i8>,
+  i8,
+  <vscale x 8 x i1>,
+  i64);
+
+define <vscale x 8 x i8> @intrinsic_vadd_mask_vx_nxv8i8_nxv8i8_i8(<vscale x 8 x i8> %0, <vscale x 8 x i8> %1, i8 %2, <vscale x 8 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_mask_vx_nxv8i8_nxv8i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,m1,tu,mu
+; CHECK:       vadd.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 8 x i8> @llvm.riscv.vadd.mask.nxv8i8.i8(
+    <vscale x 8 x i8> %0,
+    <vscale x 8 x i8> %1,
+    i8 %2,
+    <vscale x 8 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 8 x i8> %a
+}
+
+declare <vscale x 16 x i8> @llvm.riscv.vadd.nxv16i8.i8(
+  <vscale x 16 x i8>,
+  i8,
+  i64);
+
+define <vscale x 16 x i8> @intrinsic_vadd_vx_nxv16i8_nxv16i8_i8(<vscale x 16 x i8> %0, i8 %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_vx_nxv16i8_nxv16i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,m2,tu,mu
+; CHECK:       vadd.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 16 x i8> @llvm.riscv.vadd.nxv16i8.i8(
+    <vscale x 16 x i8> %0,
+    i8 %1,
+    i64 %2)
+
+  ret <vscale x 16 x i8> %a
+}
+
+declare <vscale x 16 x i8> @llvm.riscv.vadd.mask.nxv16i8.i8(
+  <vscale x 16 x i8>,
+  <vscale x 16 x i8>,
+  i8,
+  <vscale x 16 x i1>,
+  i64);
+
+define <vscale x 16 x i8> @intrinsic_vadd_mask_vx_nxv16i8_nxv16i8_i8(<vscale x 16 x i8> %0, <vscale x 16 x i8> %1, i8 %2, <vscale x 16 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_mask_vx_nxv16i8_nxv16i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,m2,tu,mu
+; CHECK:       vadd.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 16 x i8> @llvm.riscv.vadd.mask.nxv16i8.i8(
+    <vscale x 16 x i8> %0,
+    <vscale x 16 x i8> %1,
+    i8 %2,
+    <vscale x 16 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 16 x i8> %a
+}
+
+declare <vscale x 32 x i8> @llvm.riscv.vadd.nxv32i8.i8(
+  <vscale x 32 x i8>,
+  i8,
+  i64);
+
+define <vscale x 32 x i8> @intrinsic_vadd_vx_nxv32i8_nxv32i8_i8(<vscale x 32 x i8> %0, i8 %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_vx_nxv32i8_nxv32i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,m4,tu,mu
+; CHECK:       vadd.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 32 x i8> @llvm.riscv.vadd.nxv32i8.i8(
+    <vscale x 32 x i8> %0,
+    i8 %1,
+    i64 %2)
+
+  ret <vscale x 32 x i8> %a
+}
+
+declare <vscale x 32 x i8> @llvm.riscv.vadd.mask.nxv32i8.i8(
+  <vscale x 32 x i8>,
+  <vscale x 32 x i8>,
+  i8,
+  <vscale x 32 x i1>,
+  i64);
+
+define <vscale x 32 x i8> @intrinsic_vadd_mask_vx_nxv32i8_nxv32i8_i8(<vscale x 32 x i8> %0, <vscale x 32 x i8> %1, i8 %2, <vscale x 32 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_mask_vx_nxv32i8_nxv32i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,m4,tu,mu
+; CHECK:       vadd.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 32 x i8> @llvm.riscv.vadd.mask.nxv32i8.i8(
+    <vscale x 32 x i8> %0,
+    <vscale x 32 x i8> %1,
+    i8 %2,
+    <vscale x 32 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 32 x i8> %a
+}
+
+declare <vscale x 64 x i8> @llvm.riscv.vadd.nxv64i8.i8(
+  <vscale x 64 x i8>,
+  i8,
+  i64);
+
+define <vscale x 64 x i8> @intrinsic_vadd_vx_nxv64i8_nxv64i8_i8(<vscale x 64 x i8> %0, i8 %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_vx_nxv64i8_nxv64i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,m8,tu,mu
+; CHECK:       vadd.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 64 x i8> @llvm.riscv.vadd.nxv64i8.i8(
+    <vscale x 64 x i8> %0,
+    i8 %1,
+    i64 %2)
+
+  ret <vscale x 64 x i8> %a
+}
+
+declare <vscale x 64 x i8> @llvm.riscv.vadd.mask.nxv64i8.i8(
+  <vscale x 64 x i8>,
+  <vscale x 64 x i8>,
+  i8,
+  <vscale x 64 x i1>,
+  i64);
+
+define <vscale x 64 x i8> @intrinsic_vadd_mask_vx_nxv64i8_nxv64i8_i8(<vscale x 64 x i8> %0, <vscale x 64 x i8> %1, i8 %2, <vscale x 64 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_mask_vx_nxv64i8_nxv64i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,m8,tu,mu
+; CHECK:       vadd.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 64 x i8> @llvm.riscv.vadd.mask.nxv64i8.i8(
+    <vscale x 64 x i8> %0,
+    <vscale x 64 x i8> %1,
+    i8 %2,
+    <vscale x 64 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 64 x i8> %a
+}
+
+declare <vscale x 1 x i16> @llvm.riscv.vadd.nxv1i16.i16(
+  <vscale x 1 x i16>,
+  i16,
+  i64);
+
+define <vscale x 1 x i16> @intrinsic_vadd_vx_nxv1i16_nxv1i16_i16(<vscale x 1 x i16> %0, i16 %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_vx_nxv1i16_nxv1i16_i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,mf4,tu,mu
+; CHECK:       vadd.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 1 x i16> @llvm.riscv.vadd.nxv1i16.i16(
+    <vscale x 1 x i16> %0,
+    i16 %1,
+    i64 %2)
+
+  ret <vscale x 1 x i16> %a
+}
+
+declare <vscale x 1 x i16> @llvm.riscv.vadd.mask.nxv1i16.i16(
+  <vscale x 1 x i16>,
+  <vscale x 1 x i16>,
+  i16,
+  <vscale x 1 x i1>,
+  i64);
+
+define <vscale x 1 x i16> @intrinsic_vadd_mask_vx_nxv1i16_nxv1i16_i16(<vscale x 1 x i16> %0, <vscale x 1 x i16> %1, i16 %2, <vscale x 1 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_mask_vx_nxv1i16_nxv1i16_i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,mf4,tu,mu
+; CHECK:       vadd.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 1 x i16> @llvm.riscv.vadd.mask.nxv1i16.i16(
+    <vscale x 1 x i16> %0,
+    <vscale x 1 x i16> %1,
+    i16 %2,
+    <vscale x 1 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 1 x i16> %a
+}
+
+declare <vscale x 2 x i16> @llvm.riscv.vadd.nxv2i16.i16(
+  <vscale x 2 x i16>,
+  i16,
+  i64);
+
+define <vscale x 2 x i16> @intrinsic_vadd_vx_nxv2i16_nxv2i16_i16(<vscale x 2 x i16> %0, i16 %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_vx_nxv2i16_nxv2i16_i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,mf2,tu,mu
+; CHECK:       vadd.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 2 x i16> @llvm.riscv.vadd.nxv2i16.i16(
+    <vscale x 2 x i16> %0,
+    i16 %1,
+    i64 %2)
+
+  ret <vscale x 2 x i16> %a
+}
+
+declare <vscale x 2 x i16> @llvm.riscv.vadd.mask.nxv2i16.i16(
+  <vscale x 2 x i16>,
+  <vscale x 2 x i16>,
+  i16,
+  <vscale x 2 x i1>,
+  i64);
+
+define <vscale x 2 x i16> @intrinsic_vadd_mask_vx_nxv2i16_nxv2i16_i16(<vscale x 2 x i16> %0, <vscale x 2 x i16> %1, i16 %2, <vscale x 2 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_mask_vx_nxv2i16_nxv2i16_i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,mf2,tu,mu
+; CHECK:       vadd.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 2 x i16> @llvm.riscv.vadd.mask.nxv2i16.i16(
+    <vscale x 2 x i16> %0,
+    <vscale x 2 x i16> %1,
+    i16 %2,
+    <vscale x 2 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 2 x i16> %a
+}
+
+declare <vscale x 4 x i16> @llvm.riscv.vadd.nxv4i16.i16(
+  <vscale x 4 x i16>,
+  i16,
+  i64);
+
+define <vscale x 4 x i16> @intrinsic_vadd_vx_nxv4i16_nxv4i16_i16(<vscale x 4 x i16> %0, i16 %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_vx_nxv4i16_nxv4i16_i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,m1,tu,mu
+; CHECK:       vadd.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 4 x i16> @llvm.riscv.vadd.nxv4i16.i16(
+    <vscale x 4 x i16> %0,
+    i16 %1,
+    i64 %2)
+
+  ret <vscale x 4 x i16> %a
+}
+
+declare <vscale x 4 x i16> @llvm.riscv.vadd.mask.nxv4i16.i16(
+  <vscale x 4 x i16>,
+  <vscale x 4 x i16>,
+  i16,
+  <vscale x 4 x i1>,
+  i64);
+
+define <vscale x 4 x i16> @intrinsic_vadd_mask_vx_nxv4i16_nxv4i16_i16(<vscale x 4 x i16> %0, <vscale x 4 x i16> %1, i16 %2, <vscale x 4 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_mask_vx_nxv4i16_nxv4i16_i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,m1,tu,mu
+; CHECK:       vadd.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 4 x i16> @llvm.riscv.vadd.mask.nxv4i16.i16(
+    <vscale x 4 x i16> %0,
+    <vscale x 4 x i16> %1,
+    i16 %2,
+    <vscale x 4 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 4 x i16> %a
+}
+
+declare <vscale x 8 x i16> @llvm.riscv.vadd.nxv8i16.i16(
+  <vscale x 8 x i16>,
+  i16,
+  i64);
+
+define <vscale x 8 x i16> @intrinsic_vadd_vx_nxv8i16_nxv8i16_i16(<vscale x 8 x i16> %0, i16 %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_vx_nxv8i16_nxv8i16_i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,m2,tu,mu
+; CHECK:       vadd.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 8 x i16> @llvm.riscv.vadd.nxv8i16.i16(
+    <vscale x 8 x i16> %0,
+    i16 %1,
+    i64 %2)
+
+  ret <vscale x 8 x i16> %a
+}
+
+declare <vscale x 8 x i16> @llvm.riscv.vadd.mask.nxv8i16.i16(
+  <vscale x 8 x i16>,
+  <vscale x 8 x i16>,
+  i16,
+  <vscale x 8 x i1>,
+  i64);
+
+define <vscale x 8 x i16> @intrinsic_vadd_mask_vx_nxv8i16_nxv8i16_i16(<vscale x 8 x i16> %0, <vscale x 8 x i16> %1, i16 %2, <vscale x 8 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_mask_vx_nxv8i16_nxv8i16_i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,m2,tu,mu
+; CHECK:       vadd.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 8 x i16> @llvm.riscv.vadd.mask.nxv8i16.i16(
+    <vscale x 8 x i16> %0,
+    <vscale x 8 x i16> %1,
+    i16 %2,
+    <vscale x 8 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 8 x i16> %a
+}
+
+declare <vscale x 16 x i16> @llvm.riscv.vadd.nxv16i16.i16(
+  <vscale x 16 x i16>,
+  i16,
+  i64);
+
+define <vscale x 16 x i16> @intrinsic_vadd_vx_nxv16i16_nxv16i16_i16(<vscale x 16 x i16> %0, i16 %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_vx_nxv16i16_nxv16i16_i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,m4,tu,mu
+; CHECK:       vadd.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 16 x i16> @llvm.riscv.vadd.nxv16i16.i16(
+    <vscale x 16 x i16> %0,
+    i16 %1,
+    i64 %2)
+
+  ret <vscale x 16 x i16> %a
+}
+
+declare <vscale x 16 x i16> @llvm.riscv.vadd.mask.nxv16i16.i16(
+  <vscale x 16 x i16>,
+  <vscale x 16 x i16>,
+  i16,
+  <vscale x 16 x i1>,
+  i64);
+
+define <vscale x 16 x i16> @intrinsic_vadd_mask_vx_nxv16i16_nxv16i16_i16(<vscale x 16 x i16> %0, <vscale x 16 x i16> %1, i16 %2, <vscale x 16 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_mask_vx_nxv16i16_nxv16i16_i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,m4,tu,mu
+; CHECK:       vadd.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 16 x i16> @llvm.riscv.vadd.mask.nxv16i16.i16(
+    <vscale x 16 x i16> %0,
+    <vscale x 16 x i16> %1,
+    i16 %2,
+    <vscale x 16 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 16 x i16> %a
+}
+
+declare <vscale x 32 x i16> @llvm.riscv.vadd.nxv32i16.i16(
+  <vscale x 32 x i16>,
+  i16,
+  i64);
+
+define <vscale x 32 x i16> @intrinsic_vadd_vx_nxv32i16_nxv32i16_i16(<vscale x 32 x i16> %0, i16 %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_vx_nxv32i16_nxv32i16_i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,m8,tu,mu
+; CHECK:       vadd.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 32 x i16> @llvm.riscv.vadd.nxv32i16.i16(
+    <vscale x 32 x i16> %0,
+    i16 %1,
+    i64 %2)
+
+  ret <vscale x 32 x i16> %a
+}
+
+declare <vscale x 32 x i16> @llvm.riscv.vadd.mask.nxv32i16.i16(
+  <vscale x 32 x i16>,
+  <vscale x 32 x i16>,
+  i16,
+  <vscale x 32 x i1>,
+  i64);
+
+define <vscale x 32 x i16> @intrinsic_vadd_mask_vx_nxv32i16_nxv32i16_i16(<vscale x 32 x i16> %0, <vscale x 32 x i16> %1, i16 %2, <vscale x 32 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_mask_vx_nxv32i16_nxv32i16_i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,m8,tu,mu
+; CHECK:       vadd.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 32 x i16> @llvm.riscv.vadd.mask.nxv32i16.i16(
+    <vscale x 32 x i16> %0,
+    <vscale x 32 x i16> %1,
+    i16 %2,
+    <vscale x 32 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 32 x i16> %a
+}
+
+declare <vscale x 1 x i32> @llvm.riscv.vadd.nxv1i32.i32(
+  <vscale x 1 x i32>,
+  i32,
+  i64);
+
+define <vscale x 1 x i32> @intrinsic_vadd_vx_nxv1i32_nxv1i32_i32(<vscale x 1 x i32> %0, i32 %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_vx_nxv1i32_nxv1i32_i32
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e32,mf2,tu,mu
+; CHECK:       vadd.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 1 x i32> @llvm.riscv.vadd.nxv1i32.i32(
+    <vscale x 1 x i32> %0,
+    i32 %1,
+    i64 %2)
+
+  ret <vscale x 1 x i32> %a
+}
+
+declare <vscale x 1 x i32> @llvm.riscv.vadd.mask.nxv1i32.i32(
+  <vscale x 1 x i32>,
+  <vscale x 1 x i32>,
+  i32,
+  <vscale x 1 x i1>,
+  i64);
+
+define <vscale x 1 x i32> @intrinsic_vadd_mask_vx_nxv1i32_nxv1i32_i32(<vscale x 1 x i32> %0, <vscale x 1 x i32> %1, i32 %2, <vscale x 1 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_mask_vx_nxv1i32_nxv1i32_i32
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e32,mf2,tu,mu
+; CHECK:       vadd.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 1 x i32> @llvm.riscv.vadd.mask.nxv1i32.i32(
+    <vscale x 1 x i32> %0,
+    <vscale x 1 x i32> %1,
+    i32 %2,
+    <vscale x 1 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 1 x i32> %a
+}
+
+declare <vscale x 2 x i32> @llvm.riscv.vadd.nxv2i32.i32(
+  <vscale x 2 x i32>,
+  i32,
+  i64);
+
+define <vscale x 2 x i32> @intrinsic_vadd_vx_nxv2i32_nxv2i32_i32(<vscale x 2 x i32> %0, i32 %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_vx_nxv2i32_nxv2i32_i32
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e32,m1,tu,mu
+; CHECK:       vadd.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 2 x i32> @llvm.riscv.vadd.nxv2i32.i32(
+    <vscale x 2 x i32> %0,
+    i32 %1,
+    i64 %2)
+
+  ret <vscale x 2 x i32> %a
+}
+
+declare <vscale x 2 x i32> @llvm.riscv.vadd.mask.nxv2i32.i32(
+  <vscale x 2 x i32>,
+  <vscale x 2 x i32>,
+  i32,
+  <vscale x 2 x i1>,
+  i64);
+
+define <vscale x 2 x i32> @intrinsic_vadd_mask_vx_nxv2i32_nxv2i32_i32(<vscale x 2 x i32> %0, <vscale x 2 x i32> %1, i32 %2, <vscale x 2 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_mask_vx_nxv2i32_nxv2i32_i32
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e32,m1,tu,mu
+; CHECK:       vadd.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 2 x i32> @llvm.riscv.vadd.mask.nxv2i32.i32(
+    <vscale x 2 x i32> %0,
+    <vscale x 2 x i32> %1,
+    i32 %2,
+    <vscale x 2 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 2 x i32> %a
+}
+
+declare <vscale x 4 x i32> @llvm.riscv.vadd.nxv4i32.i32(
+  <vscale x 4 x i32>,
+  i32,
+  i64);
+
+define <vscale x 4 x i32> @intrinsic_vadd_vx_nxv4i32_nxv4i32_i32(<vscale x 4 x i32> %0, i32 %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_vx_nxv4i32_nxv4i32_i32
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e32,m2,tu,mu
+; CHECK:       vadd.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 4 x i32> @llvm.riscv.vadd.nxv4i32.i32(
+    <vscale x 4 x i32> %0,
+    i32 %1,
+    i64 %2)
+
+  ret <vscale x 4 x i32> %a
+}
+
+declare <vscale x 4 x i32> @llvm.riscv.vadd.mask.nxv4i32.i32(
+  <vscale x 4 x i32>,
+  <vscale x 4 x i32>,
+  i32,
+  <vscale x 4 x i1>,
+  i64);
+
+define <vscale x 4 x i32> @intrinsic_vadd_mask_vx_nxv4i32_nxv4i32_i32(<vscale x 4 x i32> %0, <vscale x 4 x i32> %1, i32 %2, <vscale x 4 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_mask_vx_nxv4i32_nxv4i32_i32
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e32,m2,tu,mu
+; CHECK:       vadd.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 4 x i32> @llvm.riscv.vadd.mask.nxv4i32.i32(
+    <vscale x 4 x i32> %0,
+    <vscale x 4 x i32> %1,
+    i32 %2,
+    <vscale x 4 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 4 x i32> %a
+}
+
+declare <vscale x 8 x i32> @llvm.riscv.vadd.nxv8i32.i32(
+  <vscale x 8 x i32>,
+  i32,
+  i64);
+
+define <vscale x 8 x i32> @intrinsic_vadd_vx_nxv8i32_nxv8i32_i32(<vscale x 8 x i32> %0, i32 %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_vx_nxv8i32_nxv8i32_i32
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e32,m4,tu,mu
+; CHECK:       vadd.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 8 x i32> @llvm.riscv.vadd.nxv8i32.i32(
+    <vscale x 8 x i32> %0,
+    i32 %1,
+    i64 %2)
+
+  ret <vscale x 8 x i32> %a
+}
+
+declare <vscale x 8 x i32> @llvm.riscv.vadd.mask.nxv8i32.i32(
+  <vscale x 8 x i32>,
+  <vscale x 8 x i32>,
+  i32,
+  <vscale x 8 x i1>,
+  i64);
+
+define <vscale x 8 x i32> @intrinsic_vadd_mask_vx_nxv8i32_nxv8i32_i32(<vscale x 8 x i32> %0, <vscale x 8 x i32> %1, i32 %2, <vscale x 8 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_mask_vx_nxv8i32_nxv8i32_i32
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e32,m4,tu,mu
+; CHECK:       vadd.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 8 x i32> @llvm.riscv.vadd.mask.nxv8i32.i32(
+    <vscale x 8 x i32> %0,
+    <vscale x 8 x i32> %1,
+    i32 %2,
+    <vscale x 8 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 8 x i32> %a
+}
+
+declare <vscale x 16 x i32> @llvm.riscv.vadd.nxv16i32.i32(
+  <vscale x 16 x i32>,
+  i32,
+  i64);
+
+define <vscale x 16 x i32> @intrinsic_vadd_vx_nxv16i32_nxv16i32_i32(<vscale x 16 x i32> %0, i32 %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_vx_nxv16i32_nxv16i32_i32
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e32,m8,tu,mu
+; CHECK:       vadd.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 16 x i32> @llvm.riscv.vadd.nxv16i32.i32(
+    <vscale x 16 x i32> %0,
+    i32 %1,
+    i64 %2)
+
+  ret <vscale x 16 x i32> %a
+}
+
+declare <vscale x 16 x i32> @llvm.riscv.vadd.mask.nxv16i32.i32(
+  <vscale x 16 x i32>,
+  <vscale x 16 x i32>,
+  i32,
+  <vscale x 16 x i1>,
+  i64);
+
+define <vscale x 16 x i32> @intrinsic_vadd_mask_vx_nxv16i32_nxv16i32_i32(<vscale x 16 x i32> %0, <vscale x 16 x i32> %1, i32 %2, <vscale x 16 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_mask_vx_nxv16i32_nxv16i32_i32
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e32,m8,tu,mu
+; CHECK:       vadd.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 16 x i32> @llvm.riscv.vadd.mask.nxv16i32.i32(
+    <vscale x 16 x i32> %0,
+    <vscale x 16 x i32> %1,
+    i32 %2,
+    <vscale x 16 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 16 x i32> %a
+}
+
+declare <vscale x 1 x i64> @llvm.riscv.vadd.nxv1i64.i64(
+  <vscale x 1 x i64>,
+  i64,
+  i64);
+
+define <vscale x 1 x i64> @intrinsic_vadd_vx_nxv1i64_nxv1i64_i64(<vscale x 1 x i64> %0, i64 %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_vx_nxv1i64_nxv1i64_i64
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e64,m1,tu,mu
+; CHECK:       vadd.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 1 x i64> @llvm.riscv.vadd.nxv1i64.i64(
+    <vscale x 1 x i64> %0,
+    i64 %1,
+    i64 %2)
+
+  ret <vscale x 1 x i64> %a
+}
+
+declare <vscale x 1 x i64> @llvm.riscv.vadd.mask.nxv1i64.i64(
+  <vscale x 1 x i64>,
+  <vscale x 1 x i64>,
+  i64,
+  <vscale x 1 x i1>,
+  i64);
+
+define <vscale x 1 x i64> @intrinsic_vadd_mask_vx_nxv1i64_nxv1i64_i64(<vscale x 1 x i64> %0, <vscale x 1 x i64> %1, i64 %2, <vscale x 1 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_mask_vx_nxv1i64_nxv1i64_i64
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e64,m1,tu,mu
+; CHECK:       vadd.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 1 x i64> @llvm.riscv.vadd.mask.nxv1i64.i64(
+    <vscale x 1 x i64> %0,
+    <vscale x 1 x i64> %1,
+    i64 %2,
+    <vscale x 1 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 1 x i64> %a
+}
+
+declare <vscale x 2 x i64> @llvm.riscv.vadd.nxv2i64.i64(
+  <vscale x 2 x i64>,
+  i64,
+  i64);
+
+define <vscale x 2 x i64> @intrinsic_vadd_vx_nxv2i64_nxv2i64_i64(<vscale x 2 x i64> %0, i64 %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_vx_nxv2i64_nxv2i64_i64
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e64,m2,tu,mu
+; CHECK:       vadd.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 2 x i64> @llvm.riscv.vadd.nxv2i64.i64(
+    <vscale x 2 x i64> %0,
+    i64 %1,
+    i64 %2)
+
+  ret <vscale x 2 x i64> %a
+}
+
+declare <vscale x 2 x i64> @llvm.riscv.vadd.mask.nxv2i64.i64(
+  <vscale x 2 x i64>,
+  <vscale x 2 x i64>,
+  i64,
+  <vscale x 2 x i1>,
+  i64);
+
+define <vscale x 2 x i64> @intrinsic_vadd_mask_vx_nxv2i64_nxv2i64_i64(<vscale x 2 x i64> %0, <vscale x 2 x i64> %1, i64 %2, <vscale x 2 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_mask_vx_nxv2i64_nxv2i64_i64
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e64,m2,tu,mu
+; CHECK:       vadd.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 2 x i64> @llvm.riscv.vadd.mask.nxv2i64.i64(
+    <vscale x 2 x i64> %0,
+    <vscale x 2 x i64> %1,
+    i64 %2,
+    <vscale x 2 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 2 x i64> %a
+}
+
+declare <vscale x 4 x i64> @llvm.riscv.vadd.nxv4i64.i64(
+  <vscale x 4 x i64>,
+  i64,
+  i64);
+
+define <vscale x 4 x i64> @intrinsic_vadd_vx_nxv4i64_nxv4i64_i64(<vscale x 4 x i64> %0, i64 %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_vx_nxv4i64_nxv4i64_i64
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e64,m4,tu,mu
+; CHECK:       vadd.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 4 x i64> @llvm.riscv.vadd.nxv4i64.i64(
+    <vscale x 4 x i64> %0,
+    i64 %1,
+    i64 %2)
+
+  ret <vscale x 4 x i64> %a
+}
+
+declare <vscale x 4 x i64> @llvm.riscv.vadd.mask.nxv4i64.i64(
+  <vscale x 4 x i64>,
+  <vscale x 4 x i64>,
+  i64,
+  <vscale x 4 x i1>,
+  i64);
+
+define <vscale x 4 x i64> @intrinsic_vadd_mask_vx_nxv4i64_nxv4i64_i64(<vscale x 4 x i64> %0, <vscale x 4 x i64> %1, i64 %2, <vscale x 4 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_mask_vx_nxv4i64_nxv4i64_i64
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e64,m4,tu,mu
+; CHECK:       vadd.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 4 x i64> @llvm.riscv.vadd.mask.nxv4i64.i64(
+    <vscale x 4 x i64> %0,
+    <vscale x 4 x i64> %1,
+    i64 %2,
+    <vscale x 4 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 4 x i64> %a
+}
+
+declare <vscale x 8 x i64> @llvm.riscv.vadd.nxv8i64.i64(
+  <vscale x 8 x i64>,
+  i64,
+  i64);
+
+define <vscale x 8 x i64> @intrinsic_vadd_vx_nxv8i64_nxv8i64_i64(<vscale x 8 x i64> %0, i64 %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_vx_nxv8i64_nxv8i64_i64
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e64,m8,tu,mu
+; CHECK:       vadd.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 8 x i64> @llvm.riscv.vadd.nxv8i64.i64(
+    <vscale x 8 x i64> %0,
+    i64 %1,
+    i64 %2)
+
+  ret <vscale x 8 x i64> %a
+}
+
+declare <vscale x 8 x i64> @llvm.riscv.vadd.mask.nxv8i64.i64(
+  <vscale x 8 x i64>,
+  <vscale x 8 x i64>,
+  i64,
+  <vscale x 8 x i1>,
+  i64);
+
+define <vscale x 8 x i64> @intrinsic_vadd_mask_vx_nxv8i64_nxv8i64_i64(<vscale x 8 x i64> %0, <vscale x 8 x i64> %1, i64 %2, <vscale x 8 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_mask_vx_nxv8i64_nxv8i64_i64
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e64,m8,tu,mu
+; CHECK:       vadd.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 8 x i64> @llvm.riscv.vadd.mask.nxv8i64.i64(
+    <vscale x 8 x i64> %0,
+    <vscale x 8 x i64> %1,
+    i64 %2,
+    <vscale x 8 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 8 x i64> %a
+}
+
+define <vscale x 1 x i8> @intrinsic_vadd_vi_nxv1i8_nxv1i8_i8(<vscale x 1 x i8> %0, i64 %1) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_vi_nxv1i8_nxv1i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,mf8,tu,mu
+; CHECK:       vadd.vi {{v[0-9]+}}, {{v[0-9]+}}, 9
+  %a = call <vscale x 1 x i8> @llvm.riscv.vadd.nxv1i8.i8(
+    <vscale x 1 x i8> %0,
+    i8 9,
+    i64 %1)
+
+  ret <vscale x 1 x i8> %a
+}
+
+define <vscale x 1 x i8> @intrinsic_vadd_mask_vi_nxv1i8_nxv1i8_i8(<vscale x 1 x i8> %0, <vscale x 1 x i8> %1, <vscale x 1 x i1> %2, i64 %3) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_mask_vi_nxv1i8_nxv1i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,mf8,tu,mu
+; CHECK:       vadd.vi {{v[0-9]+}}, {{v[0-9]+}}, 9, v0.t
+  %a = call <vscale x 1 x i8> @llvm.riscv.vadd.mask.nxv1i8.i8(
+    <vscale x 1 x i8> %0,
+    <vscale x 1 x i8> %1,
+    i8 9,
+    <vscale x 1 x i1> %2,
+    i64 %3)
+
+  ret <vscale x 1 x i8> %a
+}
+
+define <vscale x 2 x i8> @intrinsic_vadd_vi_nxv2i8_nxv2i8_i8(<vscale x 2 x i8> %0, i64 %1) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_vi_nxv2i8_nxv2i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,mf4,tu,mu
+; CHECK:       vadd.vi {{v[0-9]+}}, {{v[0-9]+}}, 9
+  %a = call <vscale x 2 x i8> @llvm.riscv.vadd.nxv2i8.i8(
+    <vscale x 2 x i8> %0,
+    i8 9,
+    i64 %1)
+
+  ret <vscale x 2 x i8> %a
+}
+
+define <vscale x 2 x i8> @intrinsic_vadd_mask_vi_nxv2i8_nxv2i8_i8(<vscale x 2 x i8> %0, <vscale x 2 x i8> %1, <vscale x 2 x i1> %2, i64 %3) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_mask_vi_nxv2i8_nxv2i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,mf4,tu,mu
+; CHECK:       vadd.vi {{v[0-9]+}}, {{v[0-9]+}}, 9, v0.t
+  %a = call <vscale x 2 x i8> @llvm.riscv.vadd.mask.nxv2i8.i8(
+    <vscale x 2 x i8> %0,
+    <vscale x 2 x i8> %1,
+    i8 9,
+    <vscale x 2 x i1> %2,
+    i64 %3)
+
+  ret <vscale x 2 x i8> %a
+}
+
+define <vscale x 4 x i8> @intrinsic_vadd_vi_nxv4i8_nxv4i8_i8(<vscale x 4 x i8> %0, i64 %1) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_vi_nxv4i8_nxv4i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,mf2,tu,mu
+; CHECK:       vadd.vi {{v[0-9]+}}, {{v[0-9]+}}, 9
+  %a = call <vscale x 4 x i8> @llvm.riscv.vadd.nxv4i8.i8(
+    <vscale x 4 x i8> %0,
+    i8 9,
+    i64 %1)
+
+  ret <vscale x 4 x i8> %a
+}
+
+define <vscale x 4 x i8> @intrinsic_vadd_mask_vi_nxv4i8_nxv4i8_i8(<vscale x 4 x i8> %0, <vscale x 4 x i8> %1, <vscale x 4 x i1> %2, i64 %3) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_mask_vi_nxv4i8_nxv4i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,mf2,tu,mu
+; CHECK:       vadd.vi {{v[0-9]+}}, {{v[0-9]+}}, 9, v0.t
+  %a = call <vscale x 4 x i8> @llvm.riscv.vadd.mask.nxv4i8.i8(
+    <vscale x 4 x i8> %0,
+    <vscale x 4 x i8> %1,
+    i8 9,
+    <vscale x 4 x i1> %2,
+    i64 %3)
+
+  ret <vscale x 4 x i8> %a
+}
+
+define <vscale x 8 x i8> @intrinsic_vadd_vi_nxv8i8_nxv8i8_i8(<vscale x 8 x i8> %0, i64 %1) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_vi_nxv8i8_nxv8i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,m1,tu,mu
+; CHECK:       vadd.vi {{v[0-9]+}}, {{v[0-9]+}}, 9
+  %a = call <vscale x 8 x i8> @llvm.riscv.vadd.nxv8i8.i8(
+    <vscale x 8 x i8> %0,
+    i8 9,
+    i64 %1)
+
+  ret <vscale x 8 x i8> %a
+}
+
+define <vscale x 8 x i8> @intrinsic_vadd_mask_vi_nxv8i8_nxv8i8_i8(<vscale x 8 x i8> %0, <vscale x 8 x i8> %1, <vscale x 8 x i1> %2, i64 %3) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_mask_vi_nxv8i8_nxv8i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,m1,tu,mu
+; CHECK:       vadd.vi {{v[0-9]+}}, {{v[0-9]+}}, 9, v0.t
+  %a = call <vscale x 8 x i8> @llvm.riscv.vadd.mask.nxv8i8.i8(
+    <vscale x 8 x i8> %0,
+    <vscale x 8 x i8> %1,
+    i8 9,
+    <vscale x 8 x i1> %2,
+    i64 %3)
+
+  ret <vscale x 8 x i8> %a
+}
+
+define <vscale x 16 x i8> @intrinsic_vadd_vi_nxv16i8_nxv16i8_i8(<vscale x 16 x i8> %0, i64 %1) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_vi_nxv16i8_nxv16i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,m2,tu,mu
+; CHECK:       vadd.vi {{v[0-9]+}}, {{v[0-9]+}}, 9
+  %a = call <vscale x 16 x i8> @llvm.riscv.vadd.nxv16i8.i8(
+    <vscale x 16 x i8> %0,
+    i8 9,
+    i64 %1)
+
+  ret <vscale x 16 x i8> %a
+}
+
+define <vscale x 16 x i8> @intrinsic_vadd_mask_vi_nxv16i8_nxv16i8_i8(<vscale x 16 x i8> %0, <vscale x 16 x i8> %1, <vscale x 16 x i1> %2, i64 %3) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_mask_vi_nxv16i8_nxv16i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,m2,tu,mu
+; CHECK:       vadd.vi {{v[0-9]+}}, {{v[0-9]+}}, 9, v0.t
+  %a = call <vscale x 16 x i8> @llvm.riscv.vadd.mask.nxv16i8.i8(
+    <vscale x 16 x i8> %0,
+    <vscale x 16 x i8> %1,
+    i8 9,
+    <vscale x 16 x i1> %2,
+    i64 %3)
+
+  ret <vscale x 16 x i8> %a
+}
+
+define <vscale x 32 x i8> @intrinsic_vadd_vi_nxv32i8_nxv32i8_i8(<vscale x 32 x i8> %0, i64 %1) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_vi_nxv32i8_nxv32i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,m4,tu,mu
+; CHECK:       vadd.vi {{v[0-9]+}}, {{v[0-9]+}}, 9
+  %a = call <vscale x 32 x i8> @llvm.riscv.vadd.nxv32i8.i8(
+    <vscale x 32 x i8> %0,
+    i8 9,
+    i64 %1)
+
+  ret <vscale x 32 x i8> %a
+}
+
+define <vscale x 32 x i8> @intrinsic_vadd_mask_vi_nxv32i8_nxv32i8_i8(<vscale x 32 x i8> %0, <vscale x 32 x i8> %1, <vscale x 32 x i1> %2, i64 %3) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_mask_vi_nxv32i8_nxv32i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,m4,tu,mu
+; CHECK:       vadd.vi {{v[0-9]+}}, {{v[0-9]+}}, 9, v0.t
+  %a = call <vscale x 32 x i8> @llvm.riscv.vadd.mask.nxv32i8.i8(
+    <vscale x 32 x i8> %0,
+    <vscale x 32 x i8> %1,
+    i8 9,
+    <vscale x 32 x i1> %2,
+    i64 %3)
+
+  ret <vscale x 32 x i8> %a
+}
+
+define <vscale x 64 x i8> @intrinsic_vadd_vi_nxv64i8_nxv64i8_i8(<vscale x 64 x i8> %0, i64 %1) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_vi_nxv64i8_nxv64i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,m8,tu,mu
+; CHECK:       vadd.vi {{v[0-9]+}}, {{v[0-9]+}}, 9
+  %a = call <vscale x 64 x i8> @llvm.riscv.vadd.nxv64i8.i8(
+    <vscale x 64 x i8> %0,
+    i8 9,
+    i64 %1)
+
+  ret <vscale x 64 x i8> %a
+}
+
+define <vscale x 64 x i8> @intrinsic_vadd_mask_vi_nxv64i8_nxv64i8_i8(<vscale x 64 x i8> %0, <vscale x 64 x i8> %1, <vscale x 64 x i1> %2, i64 %3) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_mask_vi_nxv64i8_nxv64i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,m8,tu,mu
+; CHECK:       vadd.vi {{v[0-9]+}}, {{v[0-9]+}}, 9, v0.t
+  %a = call <vscale x 64 x i8> @llvm.riscv.vadd.mask.nxv64i8.i8(
+    <vscale x 64 x i8> %0,
+    <vscale x 64 x i8> %1,
+    i8 9,
+    <vscale x 64 x i1> %2,
+    i64 %3)
+
+  ret <vscale x 64 x i8> %a
+}
+
+define <vscale x 1 x i16> @intrinsic_vadd_vi_nxv1i16_nxv1i16_i16(<vscale x 1 x i16> %0, i64 %1) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_vi_nxv1i16_nxv1i16_i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,mf4,tu,mu
+; CHECK:       vadd.vi {{v[0-9]+}}, {{v[0-9]+}}, 9
+  %a = call <vscale x 1 x i16> @llvm.riscv.vadd.nxv1i16.i16(
+    <vscale x 1 x i16> %0,
+    i16 9,
+    i64 %1)
+
+  ret <vscale x 1 x i16> %a
+}
+
+define <vscale x 1 x i16> @intrinsic_vadd_mask_vi_nxv1i16_nxv1i16_i16(<vscale x 1 x i16> %0, <vscale x 1 x i16> %1, <vscale x 1 x i1> %2, i64 %3) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_mask_vi_nxv1i16_nxv1i16_i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,mf4,tu,mu
+; CHECK:       vadd.vi {{v[0-9]+}}, {{v[0-9]+}}, 9, v0.t
+  %a = call <vscale x 1 x i16> @llvm.riscv.vadd.mask.nxv1i16.i16(
+    <vscale x 1 x i16> %0,
+    <vscale x 1 x i16> %1,
+    i16 9,
+    <vscale x 1 x i1> %2,
+    i64 %3)
+
+  ret <vscale x 1 x i16> %a
+}
+
+define <vscale x 2 x i16> @intrinsic_vadd_vi_nxv2i16_nxv2i16_i16(<vscale x 2 x i16> %0, i64 %1) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_vi_nxv2i16_nxv2i16_i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,mf2,tu,mu
+; CHECK:       vadd.vi {{v[0-9]+}}, {{v[0-9]+}}, 9
+  %a = call <vscale x 2 x i16> @llvm.riscv.vadd.nxv2i16.i16(
+    <vscale x 2 x i16> %0,
+    i16 9,
+    i64 %1)
+
+  ret <vscale x 2 x i16> %a
+}
+
+define <vscale x 2 x i16> @intrinsic_vadd_mask_vi_nxv2i16_nxv2i16_i16(<vscale x 2 x i16> %0, <vscale x 2 x i16> %1, <vscale x 2 x i1> %2, i64 %3) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_mask_vi_nxv2i16_nxv2i16_i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,mf2,tu,mu
+; CHECK:       vadd.vi {{v[0-9]+}}, {{v[0-9]+}}, 9, v0.t
+  %a = call <vscale x 2 x i16> @llvm.riscv.vadd.mask.nxv2i16.i16(
+    <vscale x 2 x i16> %0,
+    <vscale x 2 x i16> %1,
+    i16 9,
+    <vscale x 2 x i1> %2,
+    i64 %3)
+
+  ret <vscale x 2 x i16> %a
+}
+
+define <vscale x 4 x i16> @intrinsic_vadd_vi_nxv4i16_nxv4i16_i16(<vscale x 4 x i16> %0, i64 %1) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_vi_nxv4i16_nxv4i16_i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,m1,tu,mu
+; CHECK:       vadd.vi {{v[0-9]+}}, {{v[0-9]+}}, 9
+  %a = call <vscale x 4 x i16> @llvm.riscv.vadd.nxv4i16.i16(
+    <vscale x 4 x i16> %0,
+    i16 9,
+    i64 %1)
+
+  ret <vscale x 4 x i16> %a
+}
+
+define <vscale x 4 x i16> @intrinsic_vadd_mask_vi_nxv4i16_nxv4i16_i16(<vscale x 4 x i16> %0, <vscale x 4 x i16> %1, <vscale x 4 x i1> %2, i64 %3) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_mask_vi_nxv4i16_nxv4i16_i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,m1,tu,mu
+; CHECK:       vadd.vi {{v[0-9]+}}, {{v[0-9]+}}, 9, v0.t
+  %a = call <vscale x 4 x i16> @llvm.riscv.vadd.mask.nxv4i16.i16(
+    <vscale x 4 x i16> %0,
+    <vscale x 4 x i16> %1,
+    i16 9,
+    <vscale x 4 x i1> %2,
+    i64 %3)
+
+  ret <vscale x 4 x i16> %a
+}
+
+define <vscale x 8 x i16> @intrinsic_vadd_vi_nxv8i16_nxv8i16_i16(<vscale x 8 x i16> %0, i64 %1) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_vi_nxv8i16_nxv8i16_i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,m2,tu,mu
+; CHECK:       vadd.vi {{v[0-9]+}}, {{v[0-9]+}}, 9
+  %a = call <vscale x 8 x i16> @llvm.riscv.vadd.nxv8i16.i16(
+    <vscale x 8 x i16> %0,
+    i16 9,
+    i64 %1)
+
+  ret <vscale x 8 x i16> %a
+}
+
+define <vscale x 8 x i16> @intrinsic_vadd_mask_vi_nxv8i16_nxv8i16_i16(<vscale x 8 x i16> %0, <vscale x 8 x i16> %1, <vscale x 8 x i1> %2, i64 %3) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_mask_vi_nxv8i16_nxv8i16_i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,m2,tu,mu
+; CHECK:       vadd.vi {{v[0-9]+}}, {{v[0-9]+}}, 9, v0.t
+  %a = call <vscale x 8 x i16> @llvm.riscv.vadd.mask.nxv8i16.i16(
+    <vscale x 8 x i16> %0,
+    <vscale x 8 x i16> %1,
+    i16 9,
+    <vscale x 8 x i1> %2,
+    i64 %3)
+
+  ret <vscale x 8 x i16> %a
+}
+
+define <vscale x 16 x i16> @intrinsic_vadd_vi_nxv16i16_nxv16i16_i16(<vscale x 16 x i16> %0, i64 %1) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_vi_nxv16i16_nxv16i16_i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,m4,tu,mu
+; CHECK:       vadd.vi {{v[0-9]+}}, {{v[0-9]+}}, 9
+  %a = call <vscale x 16 x i16> @llvm.riscv.vadd.nxv16i16.i16(
+    <vscale x 16 x i16> %0,
+    i16 9,
+    i64 %1)
+
+  ret <vscale x 16 x i16> %a
+}
+
+define <vscale x 16 x i16> @intrinsic_vadd_mask_vi_nxv16i16_nxv16i16_i16(<vscale x 16 x i16> %0, <vscale x 16 x i16> %1, <vscale x 16 x i1> %2, i64 %3) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_mask_vi_nxv16i16_nxv16i16_i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,m4,tu,mu
+; CHECK:       vadd.vi {{v[0-9]+}}, {{v[0-9]+}}, 9, v0.t
+  %a = call <vscale x 16 x i16> @llvm.riscv.vadd.mask.nxv16i16.i16(
+    <vscale x 16 x i16> %0,
+    <vscale x 16 x i16> %1,
+    i16 9,
+    <vscale x 16 x i1> %2,
+    i64 %3)
+
+  ret <vscale x 16 x i16> %a
+}
+
+define <vscale x 32 x i16> @intrinsic_vadd_vi_nxv32i16_nxv32i16_i16(<vscale x 32 x i16> %0, i64 %1) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_vi_nxv32i16_nxv32i16_i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,m8,tu,mu
+; CHECK:       vadd.vi {{v[0-9]+}}, {{v[0-9]+}}, 9
+  %a = call <vscale x 32 x i16> @llvm.riscv.vadd.nxv32i16.i16(
+    <vscale x 32 x i16> %0,
+    i16 9,
+    i64 %1)
+
+  ret <vscale x 32 x i16> %a
+}
+
+define <vscale x 32 x i16> @intrinsic_vadd_mask_vi_nxv32i16_nxv32i16_i16(<vscale x 32 x i16> %0, <vscale x 32 x i16> %1, <vscale x 32 x i1> %2, i64 %3) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_mask_vi_nxv32i16_nxv32i16_i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,m8,tu,mu
+; CHECK:       vadd.vi {{v[0-9]+}}, {{v[0-9]+}}, 9, v0.t
+  %a = call <vscale x 32 x i16> @llvm.riscv.vadd.mask.nxv32i16.i16(
+    <vscale x 32 x i16> %0,
+    <vscale x 32 x i16> %1,
+    i16 9,
+    <vscale x 32 x i1> %2,
+    i64 %3)
+
+  ret <vscale x 32 x i16> %a
+}
+
+define <vscale x 1 x i32> @intrinsic_vadd_vi_nxv1i32_nxv1i32_i32(<vscale x 1 x i32> %0, i64 %1) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_vi_nxv1i32_nxv1i32_i32
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e32,mf2,tu,mu
+; CHECK:       vadd.vi {{v[0-9]+}}, {{v[0-9]+}}, 9
+  %a = call <vscale x 1 x i32> @llvm.riscv.vadd.nxv1i32.i32(
+    <vscale x 1 x i32> %0,
+    i32 9,
+    i64 %1)
+
+  ret <vscale x 1 x i32> %a
+}
+
+define <vscale x 1 x i32> @intrinsic_vadd_mask_vi_nxv1i32_nxv1i32_i32(<vscale x 1 x i32> %0, <vscale x 1 x i32> %1, <vscale x 1 x i1> %2, i64 %3) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_mask_vi_nxv1i32_nxv1i32_i32
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e32,mf2,tu,mu
+; CHECK:       vadd.vi {{v[0-9]+}}, {{v[0-9]+}}, 9, v0.t
+  %a = call <vscale x 1 x i32> @llvm.riscv.vadd.mask.nxv1i32.i32(
+    <vscale x 1 x i32> %0,
+    <vscale x 1 x i32> %1,
+    i32 9,
+    <vscale x 1 x i1> %2,
+    i64 %3)
+
+  ret <vscale x 1 x i32> %a
+}
+
+define <vscale x 2 x i32> @intrinsic_vadd_vi_nxv2i32_nxv2i32_i32(<vscale x 2 x i32> %0, i64 %1) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_vi_nxv2i32_nxv2i32_i32
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e32,m1,tu,mu
+; CHECK:       vadd.vi {{v[0-9]+}}, {{v[0-9]+}}, 9
+  %a = call <vscale x 2 x i32> @llvm.riscv.vadd.nxv2i32.i32(
+    <vscale x 2 x i32> %0,
+    i32 9,
+    i64 %1)
+
+  ret <vscale x 2 x i32> %a
+}
+
+define <vscale x 2 x i32> @intrinsic_vadd_mask_vi_nxv2i32_nxv2i32_i32(<vscale x 2 x i32> %0, <vscale x 2 x i32> %1, <vscale x 2 x i1> %2, i64 %3) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_mask_vi_nxv2i32_nxv2i32_i32
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e32,m1,tu,mu
+; CHECK:       vadd.vi {{v[0-9]+}}, {{v[0-9]+}}, 9, v0.t
+  %a = call <vscale x 2 x i32> @llvm.riscv.vadd.mask.nxv2i32.i32(
+    <vscale x 2 x i32> %0,
+    <vscale x 2 x i32> %1,
+    i32 9,
+    <vscale x 2 x i1> %2,
+    i64 %3)
+
+  ret <vscale x 2 x i32> %a
+}
+
+define <vscale x 4 x i32> @intrinsic_vadd_vi_nxv4i32_nxv4i32_i32(<vscale x 4 x i32> %0, i64 %1) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_vi_nxv4i32_nxv4i32_i32
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e32,m2,tu,mu
+; CHECK:       vadd.vi {{v[0-9]+}}, {{v[0-9]+}}, 9
+  %a = call <vscale x 4 x i32> @llvm.riscv.vadd.nxv4i32.i32(
+    <vscale x 4 x i32> %0,
+    i32 9,
+    i64 %1)
+
+  ret <vscale x 4 x i32> %a
+}
+
+define <vscale x 4 x i32> @intrinsic_vadd_mask_vi_nxv4i32_nxv4i32_i32(<vscale x 4 x i32> %0, <vscale x 4 x i32> %1, <vscale x 4 x i1> %2, i64 %3) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_mask_vi_nxv4i32_nxv4i32_i32
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e32,m2,tu,mu
+; CHECK:       vadd.vi {{v[0-9]+}}, {{v[0-9]+}}, 9, v0.t
+  %a = call <vscale x 4 x i32> @llvm.riscv.vadd.mask.nxv4i32.i32(
+    <vscale x 4 x i32> %0,
+    <vscale x 4 x i32> %1,
+    i32 9,
+    <vscale x 4 x i1> %2,
+    i64 %3)
+
+  ret <vscale x 4 x i32> %a
+}
+
+define <vscale x 8 x i32> @intrinsic_vadd_vi_nxv8i32_nxv8i32_i32(<vscale x 8 x i32> %0, i64 %1) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_vi_nxv8i32_nxv8i32_i32
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e32,m4,tu,mu
+; CHECK:       vadd.vi {{v[0-9]+}}, {{v[0-9]+}}, 9
+  %a = call <vscale x 8 x i32> @llvm.riscv.vadd.nxv8i32.i32(
+    <vscale x 8 x i32> %0,
+    i32 9,
+    i64 %1)
+
+  ret <vscale x 8 x i32> %a
+}
+
+define <vscale x 8 x i32> @intrinsic_vadd_mask_vi_nxv8i32_nxv8i32_i32(<vscale x 8 x i32> %0, <vscale x 8 x i32> %1, <vscale x 8 x i1> %2, i64 %3) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_mask_vi_nxv8i32_nxv8i32_i32
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e32,m4,tu,mu
+; CHECK:       vadd.vi {{v[0-9]+}}, {{v[0-9]+}}, 9, v0.t
+  %a = call <vscale x 8 x i32> @llvm.riscv.vadd.mask.nxv8i32.i32(
+    <vscale x 8 x i32> %0,
+    <vscale x 8 x i32> %1,
+    i32 9,
+    <vscale x 8 x i1> %2,
+    i64 %3)
+
+  ret <vscale x 8 x i32> %a
+}
+
+define <vscale x 16 x i32> @intrinsic_vadd_vi_nxv16i32_nxv16i32_i32(<vscale x 16 x i32> %0, i64 %1) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_vi_nxv16i32_nxv16i32_i32
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e32,m8,tu,mu
+; CHECK:       vadd.vi {{v[0-9]+}}, {{v[0-9]+}}, 9
+  %a = call <vscale x 16 x i32> @llvm.riscv.vadd.nxv16i32.i32(
+    <vscale x 16 x i32> %0,
+    i32 9,
+    i64 %1)
+
+  ret <vscale x 16 x i32> %a
+}
+
+define <vscale x 16 x i32> @intrinsic_vadd_mask_vi_nxv16i32_nxv16i32_i32(<vscale x 16 x i32> %0, <vscale x 16 x i32> %1, <vscale x 16 x i1> %2, i64 %3) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_mask_vi_nxv16i32_nxv16i32_i32
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e32,m8,tu,mu
+; CHECK:       vadd.vi {{v[0-9]+}}, {{v[0-9]+}}, 9, v0.t
+  %a = call <vscale x 16 x i32> @llvm.riscv.vadd.mask.nxv16i32.i32(
+    <vscale x 16 x i32> %0,
+    <vscale x 16 x i32> %1,
+    i32 9,
+    <vscale x 16 x i1> %2,
+    i64 %3)
+
+  ret <vscale x 16 x i32> %a
+}
+
+define <vscale x 1 x i64> @intrinsic_vadd_vi_nxv1i64_nxv1i64_i64(<vscale x 1 x i64> %0, i64 %1) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_vi_nxv1i64_nxv1i64_i64
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e64,m1,tu,mu
+; CHECK:       vadd.vi {{v[0-9]+}}, {{v[0-9]+}}, 9
+  %a = call <vscale x 1 x i64> @llvm.riscv.vadd.nxv1i64.i64(
+    <vscale x 1 x i64> %0,
+    i64 9,
+    i64 %1)
+
+  ret <vscale x 1 x i64> %a
+}
+
+define <vscale x 1 x i64> @intrinsic_vadd_mask_vi_nxv1i64_nxv1i64_i64(<vscale x 1 x i64> %0, <vscale x 1 x i64> %1, <vscale x 1 x i1> %2, i64 %3) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_mask_vi_nxv1i64_nxv1i64_i64
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e64,m1,tu,mu
+; CHECK:       vadd.vi {{v[0-9]+}}, {{v[0-9]+}}, 9, v0.t
+  %a = call <vscale x 1 x i64> @llvm.riscv.vadd.mask.nxv1i64.i64(
+    <vscale x 1 x i64> %0,
+    <vscale x 1 x i64> %1,
+    i64 9,
+    <vscale x 1 x i1> %2,
+    i64 %3)
+
+  ret <vscale x 1 x i64> %a
+}
+
+define <vscale x 2 x i64> @intrinsic_vadd_vi_nxv2i64_nxv2i64_i64(<vscale x 2 x i64> %0, i64 %1) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_vi_nxv2i64_nxv2i64_i64
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e64,m2,tu,mu
+; CHECK:       vadd.vi {{v[0-9]+}}, {{v[0-9]+}}, 9
+  %a = call <vscale x 2 x i64> @llvm.riscv.vadd.nxv2i64.i64(
+    <vscale x 2 x i64> %0,
+    i64 9,
+    i64 %1)
+
+  ret <vscale x 2 x i64> %a
+}
+
+define <vscale x 2 x i64> @intrinsic_vadd_mask_vi_nxv2i64_nxv2i64_i64(<vscale x 2 x i64> %0, <vscale x 2 x i64> %1, <vscale x 2 x i1> %2, i64 %3) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_mask_vi_nxv2i64_nxv2i64_i64
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e64,m2,tu,mu
+; CHECK:       vadd.vi {{v[0-9]+}}, {{v[0-9]+}}, 9, v0.t
+  %a = call <vscale x 2 x i64> @llvm.riscv.vadd.mask.nxv2i64.i64(
+    <vscale x 2 x i64> %0,
+    <vscale x 2 x i64> %1,
+    i64 9,
+    <vscale x 2 x i1> %2,
+    i64 %3)
+
+  ret <vscale x 2 x i64> %a
+}
+
+define <vscale x 4 x i64> @intrinsic_vadd_vi_nxv4i64_nxv4i64_i64(<vscale x 4 x i64> %0, i64 %1) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_vi_nxv4i64_nxv4i64_i64
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e64,m4,tu,mu
+; CHECK:       vadd.vi {{v[0-9]+}}, {{v[0-9]+}}, 9
+  %a = call <vscale x 4 x i64> @llvm.riscv.vadd.nxv4i64.i64(
+    <vscale x 4 x i64> %0,
+    i64 9,
+    i64 %1)
+
+  ret <vscale x 4 x i64> %a
+}
+
+define <vscale x 4 x i64> @intrinsic_vadd_mask_vi_nxv4i64_nxv4i64_i64(<vscale x 4 x i64> %0, <vscale x 4 x i64> %1, <vscale x 4 x i1> %2, i64 %3) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_mask_vi_nxv4i64_nxv4i64_i64
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e64,m4,tu,mu
+; CHECK:       vadd.vi {{v[0-9]+}}, {{v[0-9]+}}, 9, v0.t
+  %a = call <vscale x 4 x i64> @llvm.riscv.vadd.mask.nxv4i64.i64(
+    <vscale x 4 x i64> %0,
+    <vscale x 4 x i64> %1,
+    i64 9,
+    <vscale x 4 x i1> %2,
+    i64 %3)
+
+  ret <vscale x 4 x i64> %a
+}
+
+define <vscale x 8 x i64> @intrinsic_vadd_vi_nxv8i64_nxv8i64_i64(<vscale x 8 x i64> %0, i64 %1) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_vi_nxv8i64_nxv8i64_i64
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e64,m8,tu,mu
+; CHECK:       vadd.vi {{v[0-9]+}}, {{v[0-9]+}}, 9
+  %a = call <vscale x 8 x i64> @llvm.riscv.vadd.nxv8i64.i64(
+    <vscale x 8 x i64> %0,
+    i64 9,
+    i64 %1)
+
+  ret <vscale x 8 x i64> %a
+}
+
+define <vscale x 8 x i64> @intrinsic_vadd_mask_vi_nxv8i64_nxv8i64_i64(<vscale x 8 x i64> %0, <vscale x 8 x i64> %1, <vscale x 8 x i1> %2, i64 %3) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vadd_mask_vi_nxv8i64_nxv8i64_i64
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e64,m8,tu,mu
+; CHECK:       vadd.vi {{v[0-9]+}}, {{v[0-9]+}}, 9, v0.t
+  %a = call <vscale x 8 x i64> @llvm.riscv.vadd.mask.nxv8i64.i64(
+    <vscale x 8 x i64> %0,
+    <vscale x 8 x i64> %1,
+    i64 9,
+    <vscale x 8 x i1> %2,
+    i64 %3)
+
+  ret <vscale x 8 x i64> %a
+}

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

+; RUN: llc -mtriple=riscv64 -mattr=+experimental-v -verify-machineinstrs \
+; RUN:   --riscv-no-aliases < %s | FileCheck %s
+declare <vscale x 1 x i8> @llvm.riscv.vrsub.nxv1i8.i8(
+  <vscale x 1 x i8>,
+  i8,
+  i64);
+
+define <vscale x 1 x i8> @intrinsic_vrsub_vx_nxv1i8_nxv1i8_i8(<vscale x 1 x i8> %0, i8 %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vrsub_vx_nxv1i8_nxv1i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,mf8,tu,mu
+; CHECK:       vrsub.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 1 x i8> @llvm.riscv.vrsub.nxv1i8.i8(
+    <vscale x 1 x i8> %0,
+    i8 %1,
+    i64 %2)
+
+  ret <vscale x 1 x i8> %a
+}
+
+declare <vscale x 1 x i8> @llvm.riscv.vrsub.mask.nxv1i8.i8(
+  <vscale x 1 x i8>,
+  <vscale x 1 x i8>,
+  i8,
+  <vscale x 1 x i1>,
+  i64);
+
+define <vscale x 1 x i8> @intrinsic_vrsub_mask_vx_nxv1i8_nxv1i8_i8(<vscale x 1 x i8> %0, <vscale x 1 x i8> %1, i8 %2, <vscale x 1 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vrsub_mask_vx_nxv1i8_nxv1i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,mf8,tu,mu
+; CHECK:       vrsub.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 1 x i8> @llvm.riscv.vrsub.mask.nxv1i8.i8(
+    <vscale x 1 x i8> %0,
+    <vscale x 1 x i8> %1,
+    i8 %2,
+    <vscale x 1 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 1 x i8> %a
+}
+
+declare <vscale x 2 x i8> @llvm.riscv.vrsub.nxv2i8.i8(
+  <vscale x 2 x i8>,
+  i8,
+  i64);
+
+define <vscale x 2 x i8> @intrinsic_vrsub_vx_nxv2i8_nxv2i8_i8(<vscale x 2 x i8> %0, i8 %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vrsub_vx_nxv2i8_nxv2i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,mf4,tu,mu
+; CHECK:       vrsub.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 2 x i8> @llvm.riscv.vrsub.nxv2i8.i8(
+    <vscale x 2 x i8> %0,
+    i8 %1,
+    i64 %2)
+
+  ret <vscale x 2 x i8> %a
+}
+
+declare <vscale x 2 x i8> @llvm.riscv.vrsub.mask.nxv2i8.i8(
+  <vscale x 2 x i8>,
+  <vscale x 2 x i8>,
+  i8,
+  <vscale x 2 x i1>,
+  i64);
+
+define <vscale x 2 x i8> @intrinsic_vrsub_mask_vx_nxv2i8_nxv2i8_i8(<vscale x 2 x i8> %0, <vscale x 2 x i8> %1, i8 %2, <vscale x 2 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vrsub_mask_vx_nxv2i8_nxv2i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,mf4,tu,mu
+; CHECK:       vrsub.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 2 x i8> @llvm.riscv.vrsub.mask.nxv2i8.i8(
+    <vscale x 2 x i8> %0,
+    <vscale x 2 x i8> %1,
+    i8 %2,
+    <vscale x 2 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 2 x i8> %a
+}
+
+declare <vscale x 4 x i8> @llvm.riscv.vrsub.nxv4i8.i8(
+  <vscale x 4 x i8>,
+  i8,
+  i64);
+
+define <vscale x 4 x i8> @intrinsic_vrsub_vx_nxv4i8_nxv4i8_i8(<vscale x 4 x i8> %0, i8 %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vrsub_vx_nxv4i8_nxv4i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,mf2,tu,mu
+; CHECK:       vrsub.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 4 x i8> @llvm.riscv.vrsub.nxv4i8.i8(
+    <vscale x 4 x i8> %0,
+    i8 %1,
+    i64 %2)
+
+  ret <vscale x 4 x i8> %a
+}
+
+declare <vscale x 4 x i8> @llvm.riscv.vrsub.mask.nxv4i8.i8(
+  <vscale x 4 x i8>,
+  <vscale x 4 x i8>,
+  i8,
+  <vscale x 4 x i1>,
+  i64);
+
+define <vscale x 4 x i8> @intrinsic_vrsub_mask_vx_nxv4i8_nxv4i8_i8(<vscale x 4 x i8> %0, <vscale x 4 x i8> %1, i8 %2, <vscale x 4 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vrsub_mask_vx_nxv4i8_nxv4i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,mf2,tu,mu
+; CHECK:       vrsub.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 4 x i8> @llvm.riscv.vrsub.mask.nxv4i8.i8(
+    <vscale x 4 x i8> %0,
+    <vscale x 4 x i8> %1,
+    i8 %2,
+    <vscale x 4 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 4 x i8> %a
+}
+
+declare <vscale x 8 x i8> @llvm.riscv.vrsub.nxv8i8.i8(
+  <vscale x 8 x i8>,
+  i8,
+  i64);
+
+define <vscale x 8 x i8> @intrinsic_vrsub_vx_nxv8i8_nxv8i8_i8(<vscale x 8 x i8> %0, i8 %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vrsub_vx_nxv8i8_nxv8i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,m1,tu,mu
+; CHECK:       vrsub.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 8 x i8> @llvm.riscv.vrsub.nxv8i8.i8(
+    <vscale x 8 x i8> %0,
+    i8 %1,
+    i64 %2)
+
+  ret <vscale x 8 x i8> %a
+}
+
+declare <vscale x 8 x i8> @llvm.riscv.vrsub.mask.nxv8i8.i8(
+  <vscale x 8 x i8>,
+  <vscale x 8 x i8>,
+  i8,
+  <vscale x 8 x i1>,
+  i64);
+
+define <vscale x 8 x i8> @intrinsic_vrsub_mask_vx_nxv8i8_nxv8i8_i8(<vscale x 8 x i8> %0, <vscale x 8 x i8> %1, i8 %2, <vscale x 8 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vrsub_mask_vx_nxv8i8_nxv8i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,m1,tu,mu
+; CHECK:       vrsub.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 8 x i8> @llvm.riscv.vrsub.mask.nxv8i8.i8(
+    <vscale x 8 x i8> %0,
+    <vscale x 8 x i8> %1,
+    i8 %2,
+    <vscale x 8 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 8 x i8> %a
+}
+
+declare <vscale x 16 x i8> @llvm.riscv.vrsub.nxv16i8.i8(
+  <vscale x 16 x i8>,
+  i8,
+  i64);
+
+define <vscale x 16 x i8> @intrinsic_vrsub_vx_nxv16i8_nxv16i8_i8(<vscale x 16 x i8> %0, i8 %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vrsub_vx_nxv16i8_nxv16i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,m2,tu,mu
+; CHECK:       vrsub.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 16 x i8> @llvm.riscv.vrsub.nxv16i8.i8(
+    <vscale x 16 x i8> %0,
+    i8 %1,
+    i64 %2)
+
+  ret <vscale x 16 x i8> %a
+}
+
+declare <vscale x 16 x i8> @llvm.riscv.vrsub.mask.nxv16i8.i8(
+  <vscale x 16 x i8>,
+  <vscale x 16 x i8>,
+  i8,
+  <vscale x 16 x i1>,
+  i64);
+
+define <vscale x 16 x i8> @intrinsic_vrsub_mask_vx_nxv16i8_nxv16i8_i8(<vscale x 16 x i8> %0, <vscale x 16 x i8> %1, i8 %2, <vscale x 16 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vrsub_mask_vx_nxv16i8_nxv16i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,m2,tu,mu
+; CHECK:       vrsub.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 16 x i8> @llvm.riscv.vrsub.mask.nxv16i8.i8(
+    <vscale x 16 x i8> %0,
+    <vscale x 16 x i8> %1,
+    i8 %2,
+    <vscale x 16 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 16 x i8> %a
+}
+
+declare <vscale x 32 x i8> @llvm.riscv.vrsub.nxv32i8.i8(
+  <vscale x 32 x i8>,
+  i8,
+  i64);
+
+define <vscale x 32 x i8> @intrinsic_vrsub_vx_nxv32i8_nxv32i8_i8(<vscale x 32 x i8> %0, i8 %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vrsub_vx_nxv32i8_nxv32i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,m4,tu,mu
+; CHECK:       vrsub.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 32 x i8> @llvm.riscv.vrsub.nxv32i8.i8(
+    <vscale x 32 x i8> %0,
+    i8 %1,
+    i64 %2)
+
+  ret <vscale x 32 x i8> %a
+}
+
+declare <vscale x 32 x i8> @llvm.riscv.vrsub.mask.nxv32i8.i8(
+  <vscale x 32 x i8>,
+  <vscale x 32 x i8>,
+  i8,
+  <vscale x 32 x i1>,
+  i64);
+
+define <vscale x 32 x i8> @intrinsic_vrsub_mask_vx_nxv32i8_nxv32i8_i8(<vscale x 32 x i8> %0, <vscale x 32 x i8> %1, i8 %2, <vscale x 32 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vrsub_mask_vx_nxv32i8_nxv32i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,m4,tu,mu
+; CHECK:       vrsub.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 32 x i8> @llvm.riscv.vrsub.mask.nxv32i8.i8(
+    <vscale x 32 x i8> %0,
+    <vscale x 32 x i8> %1,
+    i8 %2,
+    <vscale x 32 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 32 x i8> %a
+}
+
+declare <vscale x 64 x i8> @llvm.riscv.vrsub.nxv64i8.i8(
+  <vscale x 64 x i8>,
+  i8,
+  i64);
+
+define <vscale x 64 x i8> @intrinsic_vrsub_vx_nxv64i8_nxv64i8_i8(<vscale x 64 x i8> %0, i8 %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vrsub_vx_nxv64i8_nxv64i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,m8,tu,mu
+; CHECK:       vrsub.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 64 x i8> @llvm.riscv.vrsub.nxv64i8.i8(
+    <vscale x 64 x i8> %0,
+    i8 %1,
+    i64 %2)
+
+  ret <vscale x 64 x i8> %a
+}
+
+declare <vscale x 64 x i8> @llvm.riscv.vrsub.mask.nxv64i8.i8(
+  <vscale x 64 x i8>,
+  <vscale x 64 x i8>,
+  i8,
+  <vscale x 64 x i1>,
+  i64);
+
+define <vscale x 64 x i8> @intrinsic_vrsub_mask_vx_nxv64i8_nxv64i8_i8(<vscale x 64 x i8> %0, <vscale x 64 x i8> %1, i8 %2, <vscale x 64 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vrsub_mask_vx_nxv64i8_nxv64i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,m8,tu,mu
+; CHECK:       vrsub.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 64 x i8> @llvm.riscv.vrsub.mask.nxv64i8.i8(
+    <vscale x 64 x i8> %0,
+    <vscale x 64 x i8> %1,
+    i8 %2,
+    <vscale x 64 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 64 x i8> %a
+}
+
+declare <vscale x 1 x i16> @llvm.riscv.vrsub.nxv1i16.i16(
+  <vscale x 1 x i16>,
+  i16,
+  i64);
+
+define <vscale x 1 x i16> @intrinsic_vrsub_vx_nxv1i16_nxv1i16_i16(<vscale x 1 x i16> %0, i16 %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vrsub_vx_nxv1i16_nxv1i16_i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,mf4,tu,mu
+; CHECK:       vrsub.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 1 x i16> @llvm.riscv.vrsub.nxv1i16.i16(
+    <vscale x 1 x i16> %0,
+    i16 %1,
+    i64 %2)
+
+  ret <vscale x 1 x i16> %a
+}
+
+declare <vscale x 1 x i16> @llvm.riscv.vrsub.mask.nxv1i16.i16(
+  <vscale x 1 x i16>,
+  <vscale x 1 x i16>,
+  i16,
+  <vscale x 1 x i1>,
+  i64);
+
+define <vscale x 1 x i16> @intrinsic_vrsub_mask_vx_nxv1i16_nxv1i16_i16(<vscale x 1 x i16> %0, <vscale x 1 x i16> %1, i16 %2, <vscale x 1 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vrsub_mask_vx_nxv1i16_nxv1i16_i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,mf4,tu,mu
+; CHECK:       vrsub.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 1 x i16> @llvm.riscv.vrsub.mask.nxv1i16.i16(
+    <vscale x 1 x i16> %0,
+    <vscale x 1 x i16> %1,
+    i16 %2,
+    <vscale x 1 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 1 x i16> %a
+}
+
+declare <vscale x 2 x i16> @llvm.riscv.vrsub.nxv2i16.i16(
+  <vscale x 2 x i16>,
+  i16,
+  i64);
+
+define <vscale x 2 x i16> @intrinsic_vrsub_vx_nxv2i16_nxv2i16_i16(<vscale x 2 x i16> %0, i16 %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vrsub_vx_nxv2i16_nxv2i16_i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,mf2,tu,mu
+; CHECK:       vrsub.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 2 x i16> @llvm.riscv.vrsub.nxv2i16.i16(
+    <vscale x 2 x i16> %0,
+    i16 %1,
+    i64 %2)
+
+  ret <vscale x 2 x i16> %a
+}
+
+declare <vscale x 2 x i16> @llvm.riscv.vrsub.mask.nxv2i16.i16(
+  <vscale x 2 x i16>,
+  <vscale x 2 x i16>,
+  i16,
+  <vscale x 2 x i1>,
+  i64);
+
+define <vscale x 2 x i16> @intrinsic_vrsub_mask_vx_nxv2i16_nxv2i16_i16(<vscale x 2 x i16> %0, <vscale x 2 x i16> %1, i16 %2, <vscale x 2 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vrsub_mask_vx_nxv2i16_nxv2i16_i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,mf2,tu,mu
+; CHECK:       vrsub.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 2 x i16> @llvm.riscv.vrsub.mask.nxv2i16.i16(
+    <vscale x 2 x i16> %0,
+    <vscale x 2 x i16> %1,
+    i16 %2,
+    <vscale x 2 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 2 x i16> %a
+}
+
+declare <vscale x 4 x i16> @llvm.riscv.vrsub.nxv4i16.i16(
+  <vscale x 4 x i16>,
+  i16,
+  i64);
+
+define <vscale x 4 x i16> @intrinsic_vrsub_vx_nxv4i16_nxv4i16_i16(<vscale x 4 x i16> %0, i16 %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vrsub_vx_nxv4i16_nxv4i16_i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,m1,tu,mu
+; CHECK:       vrsub.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 4 x i16> @llvm.riscv.vrsub.nxv4i16.i16(
+    <vscale x 4 x i16> %0,
+    i16 %1,
+    i64 %2)
+
+  ret <vscale x 4 x i16> %a
+}
+
+declare <vscale x 4 x i16> @llvm.riscv.vrsub.mask.nxv4i16.i16(
+  <vscale x 4 x i16>,
+  <vscale x 4 x i16>,
+  i16,
+  <vscale x 4 x i1>,
+  i64);
+
+define <vscale x 4 x i16> @intrinsic_vrsub_mask_vx_nxv4i16_nxv4i16_i16(<vscale x 4 x i16> %0, <vscale x 4 x i16> %1, i16 %2, <vscale x 4 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vrsub_mask_vx_nxv4i16_nxv4i16_i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,m1,tu,mu
+; CHECK:       vrsub.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 4 x i16> @llvm.riscv.vrsub.mask.nxv4i16.i16(
+    <vscale x 4 x i16> %0,
+    <vscale x 4 x i16> %1,
+    i16 %2,
+    <vscale x 4 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 4 x i16> %a
+}
+
+declare <vscale x 8 x i16> @llvm.riscv.vrsub.nxv8i16.i16(
+  <vscale x 8 x i16>,
+  i16,
+  i64);
+
+define <vscale x 8 x i16> @intrinsic_vrsub_vx_nxv8i16_nxv8i16_i16(<vscale x 8 x i16> %0, i16 %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vrsub_vx_nxv8i16_nxv8i16_i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,m2,tu,mu
+; CHECK:       vrsub.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 8 x i16> @llvm.riscv.vrsub.nxv8i16.i16(
+    <vscale x 8 x i16> %0,
+    i16 %1,
+    i64 %2)
+
+  ret <vscale x 8 x i16> %a
+}
+
+declare <vscale x 8 x i16> @llvm.riscv.vrsub.mask.nxv8i16.i16(
+  <vscale x 8 x i16>,
+  <vscale x 8 x i16>,
+  i16,
+  <vscale x 8 x i1>,
+  i64);
+
+define <vscale x 8 x i16> @intrinsic_vrsub_mask_vx_nxv8i16_nxv8i16_i16(<vscale x 8 x i16> %0, <vscale x 8 x i16> %1, i16 %2, <vscale x 8 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vrsub_mask_vx_nxv8i16_nxv8i16_i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,m2,tu,mu
+; CHECK:       vrsub.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 8 x i16> @llvm.riscv.vrsub.mask.nxv8i16.i16(
+    <vscale x 8 x i16> %0,
+    <vscale x 8 x i16> %1,
+    i16 %2,
+    <vscale x 8 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 8 x i16> %a
+}
+
+declare <vscale x 16 x i16> @llvm.riscv.vrsub.nxv16i16.i16(
+  <vscale x 16 x i16>,
+  i16,
+  i64);
+
+define <vscale x 16 x i16> @intrinsic_vrsub_vx_nxv16i16_nxv16i16_i16(<vscale x 16 x i16> %0, i16 %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vrsub_vx_nxv16i16_nxv16i16_i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,m4,tu,mu
+; CHECK:       vrsub.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 16 x i16> @llvm.riscv.vrsub.nxv16i16.i16(
+    <vscale x 16 x i16> %0,
+    i16 %1,
+    i64 %2)
+
+  ret <vscale x 16 x i16> %a
+}
+
+declare <vscale x 16 x i16> @llvm.riscv.vrsub.mask.nxv16i16.i16(
+  <vscale x 16 x i16>,
+  <vscale x 16 x i16>,
+  i16,
+  <vscale x 16 x i1>,
+  i64);
+
+define <vscale x 16 x i16> @intrinsic_vrsub_mask_vx_nxv16i16_nxv16i16_i16(<vscale x 16 x i16> %0, <vscale x 16 x i16> %1, i16 %2, <vscale x 16 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vrsub_mask_vx_nxv16i16_nxv16i16_i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,m4,tu,mu
+; CHECK:       vrsub.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 16 x i16> @llvm.riscv.vrsub.mask.nxv16i16.i16(
+    <vscale x 16 x i16> %0,
+    <vscale x 16 x i16> %1,
+    i16 %2,
+    <vscale x 16 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 16 x i16> %a
+}
+
+declare <vscale x 32 x i16> @llvm.riscv.vrsub.nxv32i16.i16(
+  <vscale x 32 x i16>,
+  i16,
+  i64);
+
+define <vscale x 32 x i16> @intrinsic_vrsub_vx_nxv32i16_nxv32i16_i16(<vscale x 32 x i16> %0, i16 %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vrsub_vx_nxv32i16_nxv32i16_i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,m8,tu,mu
+; CHECK:       vrsub.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 32 x i16> @llvm.riscv.vrsub.nxv32i16.i16(
+    <vscale x 32 x i16> %0,
+    i16 %1,
+    i64 %2)
+
+  ret <vscale x 32 x i16> %a
+}
+
+declare <vscale x 32 x i16> @llvm.riscv.vrsub.mask.nxv32i16.i16(
+  <vscale x 32 x i16>,
+  <vscale x 32 x i16>,
+  i16,
+  <vscale x 32 x i1>,
+  i64);
+
+define <vscale x 32 x i16> @intrinsic_vrsub_mask_vx_nxv32i16_nxv32i16_i16(<vscale x 32 x i16> %0, <vscale x 32 x i16> %1, i16 %2, <vscale x 32 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vrsub_mask_vx_nxv32i16_nxv32i16_i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,m8,tu,mu
+; CHECK:       vrsub.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 32 x i16> @llvm.riscv.vrsub.mask.nxv32i16.i16(
+    <vscale x 32 x i16> %0,
+    <vscale x 32 x i16> %1,
+    i16 %2,
+    <vscale x 32 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 32 x i16> %a
+}
+
+declare <vscale x 1 x i32> @llvm.riscv.vrsub.nxv1i32.i32(
+  <vscale x 1 x i32>,
+  i32,
+  i64);
+
+define <vscale x 1 x i32> @intrinsic_vrsub_vx_nxv1i32_nxv1i32_i32(<vscale x 1 x i32> %0, i32 %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vrsub_vx_nxv1i32_nxv1i32_i32
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e32,mf2,tu,mu
+; CHECK:       vrsub.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 1 x i32> @llvm.riscv.vrsub.nxv1i32.i32(
+    <vscale x 1 x i32> %0,
+    i32 %1,
+    i64 %2)
+
+  ret <vscale x 1 x i32> %a
+}
+
+declare <vscale x 1 x i32> @llvm.riscv.vrsub.mask.nxv1i32.i32(
+  <vscale x 1 x i32>,
+  <vscale x 1 x i32>,
+  i32,
+  <vscale x 1 x i1>,
+  i64);
+
+define <vscale x 1 x i32> @intrinsic_vrsub_mask_vx_nxv1i32_nxv1i32_i32(<vscale x 1 x i32> %0, <vscale x 1 x i32> %1, i32 %2, <vscale x 1 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vrsub_mask_vx_nxv1i32_nxv1i32_i32
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e32,mf2,tu,mu
+; CHECK:       vrsub.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 1 x i32> @llvm.riscv.vrsub.mask.nxv1i32.i32(
+    <vscale x 1 x i32> %0,
+    <vscale x 1 x i32> %1,
+    i32 %2,
+    <vscale x 1 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 1 x i32> %a
+}
+
+declare <vscale x 2 x i32> @llvm.riscv.vrsub.nxv2i32.i32(
+  <vscale x 2 x i32>,
+  i32,
+  i64);
+
+define <vscale x 2 x i32> @intrinsic_vrsub_vx_nxv2i32_nxv2i32_i32(<vscale x 2 x i32> %0, i32 %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vrsub_vx_nxv2i32_nxv2i32_i32
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e32,m1,tu,mu
+; CHECK:       vrsub.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 2 x i32> @llvm.riscv.vrsub.nxv2i32.i32(
+    <vscale x 2 x i32> %0,
+    i32 %1,
+    i64 %2)
+
+  ret <vscale x 2 x i32> %a
+}
+
+declare <vscale x 2 x i32> @llvm.riscv.vrsub.mask.nxv2i32.i32(
+  <vscale x 2 x i32>,
+  <vscale x 2 x i32>,
+  i32,
+  <vscale x 2 x i1>,
+  i64);
+
+define <vscale x 2 x i32> @intrinsic_vrsub_mask_vx_nxv2i32_nxv2i32_i32(<vscale x 2 x i32> %0, <vscale x 2 x i32> %1, i32 %2, <vscale x 2 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vrsub_mask_vx_nxv2i32_nxv2i32_i32
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e32,m1,tu,mu
+; CHECK:       vrsub.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 2 x i32> @llvm.riscv.vrsub.mask.nxv2i32.i32(
+    <vscale x 2 x i32> %0,
+    <vscale x 2 x i32> %1,
+    i32 %2,
+    <vscale x 2 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 2 x i32> %a
+}
+
+declare <vscale x 4 x i32> @llvm.riscv.vrsub.nxv4i32.i32(
+  <vscale x 4 x i32>,
+  i32,
+  i64);
+
+define <vscale x 4 x i32> @intrinsic_vrsub_vx_nxv4i32_nxv4i32_i32(<vscale x 4 x i32> %0, i32 %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vrsub_vx_nxv4i32_nxv4i32_i32
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e32,m2,tu,mu
+; CHECK:       vrsub.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 4 x i32> @llvm.riscv.vrsub.nxv4i32.i32(
+    <vscale x 4 x i32> %0,
+    i32 %1,
+    i64 %2)
+
+  ret <vscale x 4 x i32> %a
+}
+
+declare <vscale x 4 x i32> @llvm.riscv.vrsub.mask.nxv4i32.i32(
+  <vscale x 4 x i32>,
+  <vscale x 4 x i32>,
+  i32,
+  <vscale x 4 x i1>,
+  i64);
+
+define <vscale x 4 x i32> @intrinsic_vrsub_mask_vx_nxv4i32_nxv4i32_i32(<vscale x 4 x i32> %0, <vscale x 4 x i32> %1, i32 %2, <vscale x 4 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vrsub_mask_vx_nxv4i32_nxv4i32_i32
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e32,m2,tu,mu
+; CHECK:       vrsub.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 4 x i32> @llvm.riscv.vrsub.mask.nxv4i32.i32(
+    <vscale x 4 x i32> %0,
+    <vscale x 4 x i32> %1,
+    i32 %2,
+    <vscale x 4 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 4 x i32> %a
+}
+
+declare <vscale x 8 x i32> @llvm.riscv.vrsub.nxv8i32.i32(
+  <vscale x 8 x i32>,
+  i32,
+  i64);
+
+define <vscale x 8 x i32> @intrinsic_vrsub_vx_nxv8i32_nxv8i32_i32(<vscale x 8 x i32> %0, i32 %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vrsub_vx_nxv8i32_nxv8i32_i32
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e32,m4,tu,mu
+; CHECK:       vrsub.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 8 x i32> @llvm.riscv.vrsub.nxv8i32.i32(
+    <vscale x 8 x i32> %0,
+    i32 %1,
+    i64 %2)
+
+  ret <vscale x 8 x i32> %a
+}
+
+declare <vscale x 8 x i32> @llvm.riscv.vrsub.mask.nxv8i32.i32(
+  <vscale x 8 x i32>,
+  <vscale x 8 x i32>,
+  i32,
+  <vscale x 8 x i1>,
+  i64);
+
+define <vscale x 8 x i32> @intrinsic_vrsub_mask_vx_nxv8i32_nxv8i32_i32(<vscale x 8 x i32> %0, <vscale x 8 x i32> %1, i32 %2, <vscale x 8 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vrsub_mask_vx_nxv8i32_nxv8i32_i32
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e32,m4,tu,mu
+; CHECK:       vrsub.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 8 x i32> @llvm.riscv.vrsub.mask.nxv8i32.i32(
+    <vscale x 8 x i32> %0,
+    <vscale x 8 x i32> %1,
+    i32 %2,
+    <vscale x 8 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 8 x i32> %a
+}
+
+declare <vscale x 16 x i32> @llvm.riscv.vrsub.nxv16i32.i32(
+  <vscale x 16 x i32>,
+  i32,
+  i64);
+
+define <vscale x 16 x i32> @intrinsic_vrsub_vx_nxv16i32_nxv16i32_i32(<vscale x 16 x i32> %0, i32 %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vrsub_vx_nxv16i32_nxv16i32_i32
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e32,m8,tu,mu
+; CHECK:       vrsub.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 16 x i32> @llvm.riscv.vrsub.nxv16i32.i32(
+    <vscale x 16 x i32> %0,
+    i32 %1,
+    i64 %2)
+
+  ret <vscale x 16 x i32> %a
+}
+
+declare <vscale x 16 x i32> @llvm.riscv.vrsub.mask.nxv16i32.i32(
+  <vscale x 16 x i32>,
+  <vscale x 16 x i32>,
+  i32,
+  <vscale x 16 x i1>,
+  i64);
+
+define <vscale x 16 x i32> @intrinsic_vrsub_mask_vx_nxv16i32_nxv16i32_i32(<vscale x 16 x i32> %0, <vscale x 16 x i32> %1, i32 %2, <vscale x 16 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vrsub_mask_vx_nxv16i32_nxv16i32_i32
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e32,m8,tu,mu
+; CHECK:       vrsub.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 16 x i32> @llvm.riscv.vrsub.mask.nxv16i32.i32(
+    <vscale x 16 x i32> %0,
+    <vscale x 16 x i32> %1,
+    i32 %2,
+    <vscale x 16 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 16 x i32> %a
+}
+
+declare <vscale x 1 x i64> @llvm.riscv.vrsub.nxv1i64.i64(
+  <vscale x 1 x i64>,
+  i64,
+  i64);
+
+define <vscale x 1 x i64> @intrinsic_vrsub_vx_nxv1i64_nxv1i64_i64(<vscale x 1 x i64> %0, i64 %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vrsub_vx_nxv1i64_nxv1i64_i64
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e64,m1,tu,mu
+; CHECK:       vrsub.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 1 x i64> @llvm.riscv.vrsub.nxv1i64.i64(
+    <vscale x 1 x i64> %0,
+    i64 %1,
+    i64 %2)
+
+  ret <vscale x 1 x i64> %a
+}
+
+declare <vscale x 1 x i64> @llvm.riscv.vrsub.mask.nxv1i64.i64(
+  <vscale x 1 x i64>,
+  <vscale x 1 x i64>,
+  i64,
+  <vscale x 1 x i1>,
+  i64);
+
+define <vscale x 1 x i64> @intrinsic_vrsub_mask_vx_nxv1i64_nxv1i64_i64(<vscale x 1 x i64> %0, <vscale x 1 x i64> %1, i64 %2, <vscale x 1 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vrsub_mask_vx_nxv1i64_nxv1i64_i64
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e64,m1,tu,mu
+; CHECK:       vrsub.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 1 x i64> @llvm.riscv.vrsub.mask.nxv1i64.i64(
+    <vscale x 1 x i64> %0,
+    <vscale x 1 x i64> %1,
+    i64 %2,
+    <vscale x 1 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 1 x i64> %a
+}
+
+declare <vscale x 2 x i64> @llvm.riscv.vrsub.nxv2i64.i64(
+  <vscale x 2 x i64>,
+  i64,
+  i64);
+
+define <vscale x 2 x i64> @intrinsic_vrsub_vx_nxv2i64_nxv2i64_i64(<vscale x 2 x i64> %0, i64 %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vrsub_vx_nxv2i64_nxv2i64_i64
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e64,m2,tu,mu
+; CHECK:       vrsub.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 2 x i64> @llvm.riscv.vrsub.nxv2i64.i64(
+    <vscale x 2 x i64> %0,
+    i64 %1,
+    i64 %2)
+
+  ret <vscale x 2 x i64> %a
+}
+
+declare <vscale x 2 x i64> @llvm.riscv.vrsub.mask.nxv2i64.i64(
+  <vscale x 2 x i64>,
+  <vscale x 2 x i64>,
+  i64,
+  <vscale x 2 x i1>,
+  i64);
+
+define <vscale x 2 x i64> @intrinsic_vrsub_mask_vx_nxv2i64_nxv2i64_i64(<vscale x 2 x i64> %0, <vscale x 2 x i64> %1, i64 %2, <vscale x 2 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vrsub_mask_vx_nxv2i64_nxv2i64_i64
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e64,m2,tu,mu
+; CHECK:       vrsub.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 2 x i64> @llvm.riscv.vrsub.mask.nxv2i64.i64(
+    <vscale x 2 x i64> %0,
+    <vscale x 2 x i64> %1,
+    i64 %2,
+    <vscale x 2 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 2 x i64> %a
+}
+
+declare <vscale x 4 x i64> @llvm.riscv.vrsub.nxv4i64.i64(
+  <vscale x 4 x i64>,
+  i64,
+  i64);
+
+define <vscale x 4 x i64> @intrinsic_vrsub_vx_nxv4i64_nxv4i64_i64(<vscale x 4 x i64> %0, i64 %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vrsub_vx_nxv4i64_nxv4i64_i64
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e64,m4,tu,mu
+; CHECK:       vrsub.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 4 x i64> @llvm.riscv.vrsub.nxv4i64.i64(
+    <vscale x 4 x i64> %0,
+    i64 %1,
+    i64 %2)
+
+  ret <vscale x 4 x i64> %a
+}
+
+declare <vscale x 4 x i64> @llvm.riscv.vrsub.mask.nxv4i64.i64(
+  <vscale x 4 x i64>,
+  <vscale x 4 x i64>,
+  i64,
+  <vscale x 4 x i1>,
+  i64);
+
+define <vscale x 4 x i64> @intrinsic_vrsub_mask_vx_nxv4i64_nxv4i64_i64(<vscale x 4 x i64> %0, <vscale x 4 x i64> %1, i64 %2, <vscale x 4 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vrsub_mask_vx_nxv4i64_nxv4i64_i64
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e64,m4,tu,mu
+; CHECK:       vrsub.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 4 x i64> @llvm.riscv.vrsub.mask.nxv4i64.i64(
+    <vscale x 4 x i64> %0,
+    <vscale x 4 x i64> %1,
+    i64 %2,
+    <vscale x 4 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 4 x i64> %a
+}
+
+declare <vscale x 8 x i64> @llvm.riscv.vrsub.nxv8i64.i64(
+  <vscale x 8 x i64>,
+  i64,
+  i64);
+
+define <vscale x 8 x i64> @intrinsic_vrsub_vx_nxv8i64_nxv8i64_i64(<vscale x 8 x i64> %0, i64 %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vrsub_vx_nxv8i64_nxv8i64_i64
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e64,m8,tu,mu
+; CHECK:       vrsub.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 8 x i64> @llvm.riscv.vrsub.nxv8i64.i64(
+    <vscale x 8 x i64> %0,
+    i64 %1,
+    i64 %2)
+
+  ret <vscale x 8 x i64> %a
+}
+
+declare <vscale x 8 x i64> @llvm.riscv.vrsub.mask.nxv8i64.i64(
+  <vscale x 8 x i64>,
+  <vscale x 8 x i64>,
+  i64,
+  <vscale x 8 x i1>,
+  i64);
+
+define <vscale x 8 x i64> @intrinsic_vrsub_mask_vx_nxv8i64_nxv8i64_i64(<vscale x 8 x i64> %0, <vscale x 8 x i64> %1, i64 %2, <vscale x 8 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vrsub_mask_vx_nxv8i64_nxv8i64_i64
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e64,m8,tu,mu
+; CHECK:       vrsub.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 8 x i64> @llvm.riscv.vrsub.mask.nxv8i64.i64(
+    <vscale x 8 x i64> %0,
+    <vscale x 8 x i64> %1,
+    i64 %2,
+    <vscale x 8 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 8 x i64> %a
+}
+
+define <vscale x 1 x i8> @intrinsic_vrsub_vi_nxv1i8_nxv1i8_i8(<vscale x 1 x i8> %0, i64 %1) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vrsub_vi_nxv1i8_nxv1i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,mf8,tu,mu
+; CHECK:       vrsub.vi {{v[0-9]+}}, {{v[0-9]+}}, 9
+  %a = call <vscale x 1 x i8> @llvm.riscv.vrsub.nxv1i8.i8(
+    <vscale x 1 x i8> %0,
+    i8 9,
+    i64 %1)
+
+  ret <vscale x 1 x i8> %a
+}
+
+define <vscale x 1 x i8> @intrinsic_vrsub_mask_vi_nxv1i8_nxv1i8_i8(<vscale x 1 x i8> %0, <vscale x 1 x i8> %1, <vscale x 1 x i1> %2, i64 %3) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vrsub_mask_vi_nxv1i8_nxv1i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,mf8,tu,mu
+; CHECK:       vrsub.vi {{v[0-9]+}}, {{v[0-9]+}}, 9, v0.t
+  %a = call <vscale x 1 x i8> @llvm.riscv.vrsub.mask.nxv1i8.i8(
+    <vscale x 1 x i8> %0,
+    <vscale x 1 x i8> %1,
+    i8 9,
+    <vscale x 1 x i1> %2,
+    i64 %3)
+
+  ret <vscale x 1 x i8> %a
+}
+
+define <vscale x 2 x i8> @intrinsic_vrsub_vi_nxv2i8_nxv2i8_i8(<vscale x 2 x i8> %0, i64 %1) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vrsub_vi_nxv2i8_nxv2i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,mf4,tu,mu
+; CHECK:       vrsub.vi {{v[0-9]+}}, {{v[0-9]+}}, 9
+  %a = call <vscale x 2 x i8> @llvm.riscv.vrsub.nxv2i8.i8(
+    <vscale x 2 x i8> %0,
+    i8 9,
+    i64 %1)
+
+  ret <vscale x 2 x i8> %a
+}
+
+define <vscale x 2 x i8> @intrinsic_vrsub_mask_vi_nxv2i8_nxv2i8_i8(<vscale x 2 x i8> %0, <vscale x 2 x i8> %1, <vscale x 2 x i1> %2, i64 %3) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vrsub_mask_vi_nxv2i8_nxv2i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,mf4,tu,mu
+; CHECK:       vrsub.vi {{v[0-9]+}}, {{v[0-9]+}}, 9, v0.t
+  %a = call <vscale x 2 x i8> @llvm.riscv.vrsub.mask.nxv2i8.i8(
+    <vscale x 2 x i8> %0,
+    <vscale x 2 x i8> %1,
+    i8 9,
+    <vscale x 2 x i1> %2,
+    i64 %3)
+
+  ret <vscale x 2 x i8> %a
+}
+
+define <vscale x 4 x i8> @intrinsic_vrsub_vi_nxv4i8_nxv4i8_i8(<vscale x 4 x i8> %0, i64 %1) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vrsub_vi_nxv4i8_nxv4i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,mf2,tu,mu
+; CHECK:       vrsub.vi {{v[0-9]+}}, {{v[0-9]+}}, 9
+  %a = call <vscale x 4 x i8> @llvm.riscv.vrsub.nxv4i8.i8(
+    <vscale x 4 x i8> %0,
+    i8 9,
+    i64 %1)
+
+  ret <vscale x 4 x i8> %a
+}
+
+define <vscale x 4 x i8> @intrinsic_vrsub_mask_vi_nxv4i8_nxv4i8_i8(<vscale x 4 x i8> %0, <vscale x 4 x i8> %1, <vscale x 4 x i1> %2, i64 %3) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vrsub_mask_vi_nxv4i8_nxv4i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,mf2,tu,mu
+; CHECK:       vrsub.vi {{v[0-9]+}}, {{v[0-9]+}}, 9, v0.t
+  %a = call <vscale x 4 x i8> @llvm.riscv.vrsub.mask.nxv4i8.i8(
+    <vscale x 4 x i8> %0,
+    <vscale x 4 x i8> %1,
+    i8 9,
+    <vscale x 4 x i1> %2,
+    i64 %3)
+
+  ret <vscale x 4 x i8> %a
+}
+
+define <vscale x 8 x i8> @intrinsic_vrsub_vi_nxv8i8_nxv8i8_i8(<vscale x 8 x i8> %0, i64 %1) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vrsub_vi_nxv8i8_nxv8i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,m1,tu,mu
+; CHECK:       vrsub.vi {{v[0-9]+}}, {{v[0-9]+}}, 9
+  %a = call <vscale x 8 x i8> @llvm.riscv.vrsub.nxv8i8.i8(
+    <vscale x 8 x i8> %0,
+    i8 9,
+    i64 %1)
+
+  ret <vscale x 8 x i8> %a
+}
+
+define <vscale x 8 x i8> @intrinsic_vrsub_mask_vi_nxv8i8_nxv8i8_i8(<vscale x 8 x i8> %0, <vscale x 8 x i8> %1, <vscale x 8 x i1> %2, i64 %3) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vrsub_mask_vi_nxv8i8_nxv8i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,m1,tu,mu
+; CHECK:       vrsub.vi {{v[0-9]+}}, {{v[0-9]+}}, 9, v0.t
+  %a = call <vscale x 8 x i8> @llvm.riscv.vrsub.mask.nxv8i8.i8(
+    <vscale x 8 x i8> %0,
+    <vscale x 8 x i8> %1,
+    i8 9,
+    <vscale x 8 x i1> %2,
+    i64 %3)
+
+  ret <vscale x 8 x i8> %a
+}
+
+define <vscale x 16 x i8> @intrinsic_vrsub_vi_nxv16i8_nxv16i8_i8(<vscale x 16 x i8> %0, i64 %1) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vrsub_vi_nxv16i8_nxv16i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,m2,tu,mu
+; CHECK:       vrsub.vi {{v[0-9]+}}, {{v[0-9]+}}, 9
+  %a = call <vscale x 16 x i8> @llvm.riscv.vrsub.nxv16i8.i8(
+    <vscale x 16 x i8> %0,
+    i8 9,
+    i64 %1)
+
+  ret <vscale x 16 x i8> %a
+}
+
+define <vscale x 16 x i8> @intrinsic_vrsub_mask_vi_nxv16i8_nxv16i8_i8(<vscale x 16 x i8> %0, <vscale x 16 x i8> %1, <vscale x 16 x i1> %2, i64 %3) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vrsub_mask_vi_nxv16i8_nxv16i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,m2,tu,mu
+; CHECK:       vrsub.vi {{v[0-9]+}}, {{v[0-9]+}}, 9, v0.t
+  %a = call <vscale x 16 x i8> @llvm.riscv.vrsub.mask.nxv16i8.i8(
+    <vscale x 16 x i8> %0,
+    <vscale x 16 x i8> %1,
+    i8 9,
+    <vscale x 16 x i1> %2,
+    i64 %3)
+
+  ret <vscale x 16 x i8> %a
+}
+
+define <vscale x 32 x i8> @intrinsic_vrsub_vi_nxv32i8_nxv32i8_i8(<vscale x 32 x i8> %0, i64 %1) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vrsub_vi_nxv32i8_nxv32i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,m4,tu,mu
+; CHECK:       vrsub.vi {{v[0-9]+}}, {{v[0-9]+}}, 9
+  %a = call <vscale x 32 x i8> @llvm.riscv.vrsub.nxv32i8.i8(
+    <vscale x 32 x i8> %0,
+    i8 9,
+    i64 %1)
+
+  ret <vscale x 32 x i8> %a
+}
+
+define <vscale x 32 x i8> @intrinsic_vrsub_mask_vi_nxv32i8_nxv32i8_i8(<vscale x 32 x i8> %0, <vscale x 32 x i8> %1, <vscale x 32 x i1> %2, i64 %3) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vrsub_mask_vi_nxv32i8_nxv32i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,m4,tu,mu
+; CHECK:       vrsub.vi {{v[0-9]+}}, {{v[0-9]+}}, 9, v0.t
+  %a = call <vscale x 32 x i8> @llvm.riscv.vrsub.mask.nxv32i8.i8(
+    <vscale x 32 x i8> %0,
+    <vscale x 32 x i8> %1,
+    i8 9,
+    <vscale x 32 x i1> %2,
+    i64 %3)
+
+  ret <vscale x 32 x i8> %a
+}
+
+define <vscale x 64 x i8> @intrinsic_vrsub_vi_nxv64i8_nxv64i8_i8(<vscale x 64 x i8> %0, i64 %1) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vrsub_vi_nxv64i8_nxv64i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,m8,tu,mu
+; CHECK:       vrsub.vi {{v[0-9]+}}, {{v[0-9]+}}, 9
+  %a = call <vscale x 64 x i8> @llvm.riscv.vrsub.nxv64i8.i8(
+    <vscale x 64 x i8> %0,
+    i8 9,
+    i64 %1)
+
+  ret <vscale x 64 x i8> %a
+}
+
+define <vscale x 64 x i8> @intrinsic_vrsub_mask_vi_nxv64i8_nxv64i8_i8(<vscale x 64 x i8> %0, <vscale x 64 x i8> %1, <vscale x 64 x i1> %2, i64 %3) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vrsub_mask_vi_nxv64i8_nxv64i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,m8,tu,mu
+; CHECK:       vrsub.vi {{v[0-9]+}}, {{v[0-9]+}}, 9, v0.t
+  %a = call <vscale x 64 x i8> @llvm.riscv.vrsub.mask.nxv64i8.i8(
+    <vscale x 64 x i8> %0,
+    <vscale x 64 x i8> %1,
+    i8 9,
+    <vscale x 64 x i1> %2,
+    i64 %3)
+
+  ret <vscale x 64 x i8> %a
+}
+
+define <vscale x 1 x i16> @intrinsic_vrsub_vi_nxv1i16_nxv1i16_i16(<vscale x 1 x i16> %0, i64 %1) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vrsub_vi_nxv1i16_nxv1i16_i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,mf4,tu,mu
+; CHECK:       vrsub.vi {{v[0-9]+}}, {{v[0-9]+}}, 9
+  %a = call <vscale x 1 x i16> @llvm.riscv.vrsub.nxv1i16.i16(
+    <vscale x 1 x i16> %0,
+    i16 9,
+    i64 %1)
+
+  ret <vscale x 1 x i16> %a
+}
+
+define <vscale x 1 x i16> @intrinsic_vrsub_mask_vi_nxv1i16_nxv1i16_i16(<vscale x 1 x i16> %0, <vscale x 1 x i16> %1, <vscale x 1 x i1> %2, i64 %3) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vrsub_mask_vi_nxv1i16_nxv1i16_i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,mf4,tu,mu
+; CHECK:       vrsub.vi {{v[0-9]+}}, {{v[0-9]+}}, 9, v0.t
+  %a = call <vscale x 1 x i16> @llvm.riscv.vrsub.mask.nxv1i16.i16(
+    <vscale x 1 x i16> %0,
+    <vscale x 1 x i16> %1,
+    i16 9,
+    <vscale x 1 x i1> %2,
+    i64 %3)
+
+  ret <vscale x 1 x i16> %a
+}
+
+define <vscale x 2 x i16> @intrinsic_vrsub_vi_nxv2i16_nxv2i16_i16(<vscale x 2 x i16> %0, i64 %1) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vrsub_vi_nxv2i16_nxv2i16_i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,mf2,tu,mu
+; CHECK:       vrsub.vi {{v[0-9]+}}, {{v[0-9]+}}, 9
+  %a = call <vscale x 2 x i16> @llvm.riscv.vrsub.nxv2i16.i16(
+    <vscale x 2 x i16> %0,
+    i16 9,
+    i64 %1)
+
+  ret <vscale x 2 x i16> %a
+}
+
+define <vscale x 2 x i16> @intrinsic_vrsub_mask_vi_nxv2i16_nxv2i16_i16(<vscale x 2 x i16> %0, <vscale x 2 x i16> %1, <vscale x 2 x i1> %2, i64 %3) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vrsub_mask_vi_nxv2i16_nxv2i16_i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,mf2,tu,mu
+; CHECK:       vrsub.vi {{v[0-9]+}}, {{v[0-9]+}}, 9, v0.t
+  %a = call <vscale x 2 x i16> @llvm.riscv.vrsub.mask.nxv2i16.i16(
+    <vscale x 2 x i16> %0,
+    <vscale x 2 x i16> %1,
+    i16 9,
+    <vscale x 2 x i1> %2,
+    i64 %3)
+
+  ret <vscale x 2 x i16> %a
+}
+
+define <vscale x 4 x i16> @intrinsic_vrsub_vi_nxv4i16_nxv4i16_i16(<vscale x 4 x i16> %0, i64 %1) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vrsub_vi_nxv4i16_nxv4i16_i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,m1,tu,mu
+; CHECK:       vrsub.vi {{v[0-9]+}}, {{v[0-9]+}}, 9
+  %a = call <vscale x 4 x i16> @llvm.riscv.vrsub.nxv4i16.i16(
+    <vscale x 4 x i16> %0,
+    i16 9,
+    i64 %1)
+
+  ret <vscale x 4 x i16> %a
+}
+
+define <vscale x 4 x i16> @intrinsic_vrsub_mask_vi_nxv4i16_nxv4i16_i16(<vscale x 4 x i16> %0, <vscale x 4 x i16> %1, <vscale x 4 x i1> %2, i64 %3) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vrsub_mask_vi_nxv4i16_nxv4i16_i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,m1,tu,mu
+; CHECK:       vrsub.vi {{v[0-9]+}}, {{v[0-9]+}}, 9, v0.t
+  %a = call <vscale x 4 x i16> @llvm.riscv.vrsub.mask.nxv4i16.i16(
+    <vscale x 4 x i16> %0,
+    <vscale x 4 x i16> %1,
+    i16 9,
+    <vscale x 4 x i1> %2,
+    i64 %3)
+
+  ret <vscale x 4 x i16> %a
+}
+
+define <vscale x 8 x i16> @intrinsic_vrsub_vi_nxv8i16_nxv8i16_i16(<vscale x 8 x i16> %0, i64 %1) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vrsub_vi_nxv8i16_nxv8i16_i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,m2,tu,mu
+; CHECK:       vrsub.vi {{v[0-9]+}}, {{v[0-9]+}}, 9
+  %a = call <vscale x 8 x i16> @llvm.riscv.vrsub.nxv8i16.i16(
+    <vscale x 8 x i16> %0,
+    i16 9,
+    i64 %1)
+
+  ret <vscale x 8 x i16> %a
+}
+
+define <vscale x 8 x i16> @intrinsic_vrsub_mask_vi_nxv8i16_nxv8i16_i16(<vscale x 8 x i16> %0, <vscale x 8 x i16> %1, <vscale x 8 x i1> %2, i64 %3) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vrsub_mask_vi_nxv8i16_nxv8i16_i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,m2,tu,mu
+; CHECK:       vrsub.vi {{v[0-9]+}}, {{v[0-9]+}}, 9, v0.t
+  %a = call <vscale x 8 x i16> @llvm.riscv.vrsub.mask.nxv8i16.i16(
+    <vscale x 8 x i16> %0,
+    <vscale x 8 x i16> %1,
+    i16 9,
+    <vscale x 8 x i1> %2,
+    i64 %3)
+
+  ret <vscale x 8 x i16> %a
+}
+
+define <vscale x 16 x i16> @intrinsic_vrsub_vi_nxv16i16_nxv16i16_i16(<vscale x 16 x i16> %0, i64 %1) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vrsub_vi_nxv16i16_nxv16i16_i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,m4,tu,mu
+; CHECK:       vrsub.vi {{v[0-9]+}}, {{v[0-9]+}}, 9
+  %a = call <vscale x 16 x i16> @llvm.riscv.vrsub.nxv16i16.i16(
+    <vscale x 16 x i16> %0,
+    i16 9,
+    i64 %1)
+
+  ret <vscale x 16 x i16> %a
+}
+
+define <vscale x 16 x i16> @intrinsic_vrsub_mask_vi_nxv16i16_nxv16i16_i16(<vscale x 16 x i16> %0, <vscale x 16 x i16> %1, <vscale x 16 x i1> %2, i64 %3) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vrsub_mask_vi_nxv16i16_nxv16i16_i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,m4,tu,mu
+; CHECK:       vrsub.vi {{v[0-9]+}}, {{v[0-9]+}}, 9, v0.t
+  %a = call <vscale x 16 x i16> @llvm.riscv.vrsub.mask.nxv16i16.i16(
+    <vscale x 16 x i16> %0,
+    <vscale x 16 x i16> %1,
+    i16 9,
+    <vscale x 16 x i1> %2,
+    i64 %3)
+
+  ret <vscale x 16 x i16> %a
+}
+
+define <vscale x 32 x i16> @intrinsic_vrsub_vi_nxv32i16_nxv32i16_i16(<vscale x 32 x i16> %0, i64 %1) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vrsub_vi_nxv32i16_nxv32i16_i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,m8,tu,mu
+; CHECK:       vrsub.vi {{v[0-9]+}}, {{v[0-9]+}}, 9
+  %a = call <vscale x 32 x i16> @llvm.riscv.vrsub.nxv32i16.i16(
+    <vscale x 32 x i16> %0,
+    i16 9,
+    i64 %1)
+
+  ret <vscale x 32 x i16> %a
+}
+
+define <vscale x 32 x i16> @intrinsic_vrsub_mask_vi_nxv32i16_nxv32i16_i16(<vscale x 32 x i16> %0, <vscale x 32 x i16> %1, <vscale x 32 x i1> %2, i64 %3) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vrsub_mask_vi_nxv32i16_nxv32i16_i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,m8,tu,mu
+; CHECK:       vrsub.vi {{v[0-9]+}}, {{v[0-9]+}}, 9, v0.t
+  %a = call <vscale x 32 x i16> @llvm.riscv.vrsub.mask.nxv32i16.i16(
+    <vscale x 32 x i16> %0,
+    <vscale x 32 x i16> %1,
+    i16 9,
+    <vscale x 32 x i1> %2,
+    i64 %3)
+
+  ret <vscale x 32 x i16> %a
+}
+
+define <vscale x 1 x i32> @intrinsic_vrsub_vi_nxv1i32_nxv1i32_i32(<vscale x 1 x i32> %0, i64 %1) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vrsub_vi_nxv1i32_nxv1i32_i32
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e32,mf2,tu,mu
+; CHECK:       vrsub.vi {{v[0-9]+}}, {{v[0-9]+}}, 9
+  %a = call <vscale x 1 x i32> @llvm.riscv.vrsub.nxv1i32.i32(
+    <vscale x 1 x i32> %0,
+    i32 9,
+    i64 %1)
+
+  ret <vscale x 1 x i32> %a
+}
+
+define <vscale x 1 x i32> @intrinsic_vrsub_mask_vi_nxv1i32_nxv1i32_i32(<vscale x 1 x i32> %0, <vscale x 1 x i32> %1, <vscale x 1 x i1> %2, i64 %3) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vrsub_mask_vi_nxv1i32_nxv1i32_i32
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e32,mf2,tu,mu
+; CHECK:       vrsub.vi {{v[0-9]+}}, {{v[0-9]+}}, 9, v0.t
+  %a = call <vscale x 1 x i32> @llvm.riscv.vrsub.mask.nxv1i32.i32(
+    <vscale x 1 x i32> %0,
+    <vscale x 1 x i32> %1,
+    i32 9,
+    <vscale x 1 x i1> %2,
+    i64 %3)
+
+  ret <vscale x 1 x i32> %a
+}
+
+define <vscale x 2 x i32> @intrinsic_vrsub_vi_nxv2i32_nxv2i32_i32(<vscale x 2 x i32> %0, i64 %1) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vrsub_vi_nxv2i32_nxv2i32_i32
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e32,m1,tu,mu
+; CHECK:       vrsub.vi {{v[0-9]+}}, {{v[0-9]+}}, 9
+  %a = call <vscale x 2 x i32> @llvm.riscv.vrsub.nxv2i32.i32(
+    <vscale x 2 x i32> %0,
+    i32 9,
+    i64 %1)
+
+  ret <vscale x 2 x i32> %a
+}
+
+define <vscale x 2 x i32> @intrinsic_vrsub_mask_vi_nxv2i32_nxv2i32_i32(<vscale x 2 x i32> %0, <vscale x 2 x i32> %1, <vscale x 2 x i1> %2, i64 %3) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vrsub_mask_vi_nxv2i32_nxv2i32_i32
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e32,m1,tu,mu
+; CHECK:       vrsub.vi {{v[0-9]+}}, {{v[0-9]+}}, 9, v0.t
+  %a = call <vscale x 2 x i32> @llvm.riscv.vrsub.mask.nxv2i32.i32(
+    <vscale x 2 x i32> %0,
+    <vscale x 2 x i32> %1,
+    i32 9,
+    <vscale x 2 x i1> %2,
+    i64 %3)
+
+  ret <vscale x 2 x i32> %a
+}
+
+define <vscale x 4 x i32> @intrinsic_vrsub_vi_nxv4i32_nxv4i32_i32(<vscale x 4 x i32> %0, i64 %1) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vrsub_vi_nxv4i32_nxv4i32_i32
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e32,m2,tu,mu
+; CHECK:       vrsub.vi {{v[0-9]+}}, {{v[0-9]+}}, 9
+  %a = call <vscale x 4 x i32> @llvm.riscv.vrsub.nxv4i32.i32(
+    <vscale x 4 x i32> %0,
+    i32 9,
+    i64 %1)
+
+  ret <vscale x 4 x i32> %a
+}
+
+define <vscale x 4 x i32> @intrinsic_vrsub_mask_vi_nxv4i32_nxv4i32_i32(<vscale x 4 x i32> %0, <vscale x 4 x i32> %1, <vscale x 4 x i1> %2, i64 %3) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vrsub_mask_vi_nxv4i32_nxv4i32_i32
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e32,m2,tu,mu
+; CHECK:       vrsub.vi {{v[0-9]+}}, {{v[0-9]+}}, 9, v0.t
+  %a = call <vscale x 4 x i32> @llvm.riscv.vrsub.mask.nxv4i32.i32(
+    <vscale x 4 x i32> %0,
+    <vscale x 4 x i32> %1,
+    i32 9,
+    <vscale x 4 x i1> %2,
+    i64 %3)
+
+  ret <vscale x 4 x i32> %a
+}
+
+define <vscale x 8 x i32> @intrinsic_vrsub_vi_nxv8i32_nxv8i32_i32(<vscale x 8 x i32> %0, i64 %1) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vrsub_vi_nxv8i32_nxv8i32_i32
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e32,m4,tu,mu
+; CHECK:       vrsub.vi {{v[0-9]+}}, {{v[0-9]+}}, 9
+  %a = call <vscale x 8 x i32> @llvm.riscv.vrsub.nxv8i32.i32(
+    <vscale x 8 x i32> %0,
+    i32 9,
+    i64 %1)
+
+  ret <vscale x 8 x i32> %a
+}
+
+define <vscale x 8 x i32> @intrinsic_vrsub_mask_vi_nxv8i32_nxv8i32_i32(<vscale x 8 x i32> %0, <vscale x 8 x i32> %1, <vscale x 8 x i1> %2, i64 %3) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vrsub_mask_vi_nxv8i32_nxv8i32_i32
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e32,m4,tu,mu
+; CHECK:       vrsub.vi {{v[0-9]+}}, {{v[0-9]+}}, 9, v0.t
+  %a = call <vscale x 8 x i32> @llvm.riscv.vrsub.mask.nxv8i32.i32(
+    <vscale x 8 x i32> %0,
+    <vscale x 8 x i32> %1,
+    i32 9,
+    <vscale x 8 x i1> %2,
+    i64 %3)
+
+  ret <vscale x 8 x i32> %a
+}
+
+define <vscale x 16 x i32> @intrinsic_vrsub_vi_nxv16i32_nxv16i32_i32(<vscale x 16 x i32> %0, i64 %1) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vrsub_vi_nxv16i32_nxv16i32_i32
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e32,m8,tu,mu
+; CHECK:       vrsub.vi {{v[0-9]+}}, {{v[0-9]+}}, 9
+  %a = call <vscale x 16 x i32> @llvm.riscv.vrsub.nxv16i32.i32(
+    <vscale x 16 x i32> %0,
+    i32 9,
+    i64 %1)
+
+  ret <vscale x 16 x i32> %a
+}
+
+define <vscale x 16 x i32> @intrinsic_vrsub_mask_vi_nxv16i32_nxv16i32_i32(<vscale x 16 x i32> %0, <vscale x 16 x i32> %1, <vscale x 16 x i1> %2, i64 %3) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vrsub_mask_vi_nxv16i32_nxv16i32_i32
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e32,m8,tu,mu
+; CHECK:       vrsub.vi {{v[0-9]+}}, {{v[0-9]+}}, 9, v0.t
+  %a = call <vscale x 16 x i32> @llvm.riscv.vrsub.mask.nxv16i32.i32(
+    <vscale x 16 x i32> %0,
+    <vscale x 16 x i32> %1,
+    i32 9,
+    <vscale x 16 x i1> %2,
+    i64 %3)
+
+  ret <vscale x 16 x i32> %a
+}
+
+define <vscale x 1 x i64> @intrinsic_vrsub_vi_nxv1i64_nxv1i64_i64(<vscale x 1 x i64> %0, i64 %1) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vrsub_vi_nxv1i64_nxv1i64_i64
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e64,m1,tu,mu
+; CHECK:       vrsub.vi {{v[0-9]+}}, {{v[0-9]+}}, 9
+  %a = call <vscale x 1 x i64> @llvm.riscv.vrsub.nxv1i64.i64(
+    <vscale x 1 x i64> %0,
+    i64 9,
+    i64 %1)
+
+  ret <vscale x 1 x i64> %a
+}
+
+define <vscale x 1 x i64> @intrinsic_vrsub_mask_vi_nxv1i64_nxv1i64_i64(<vscale x 1 x i64> %0, <vscale x 1 x i64> %1, <vscale x 1 x i1> %2, i64 %3) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vrsub_mask_vi_nxv1i64_nxv1i64_i64
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e64,m1,tu,mu
+; CHECK:       vrsub.vi {{v[0-9]+}}, {{v[0-9]+}}, 9, v0.t
+  %a = call <vscale x 1 x i64> @llvm.riscv.vrsub.mask.nxv1i64.i64(
+    <vscale x 1 x i64> %0,
+    <vscale x 1 x i64> %1,
+    i64 9,
+    <vscale x 1 x i1> %2,
+    i64 %3)
+
+  ret <vscale x 1 x i64> %a
+}
+
+define <vscale x 2 x i64> @intrinsic_vrsub_vi_nxv2i64_nxv2i64_i64(<vscale x 2 x i64> %0, i64 %1) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vrsub_vi_nxv2i64_nxv2i64_i64
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e64,m2,tu,mu
+; CHECK:       vrsub.vi {{v[0-9]+}}, {{v[0-9]+}}, 9
+  %a = call <vscale x 2 x i64> @llvm.riscv.vrsub.nxv2i64.i64(
+    <vscale x 2 x i64> %0,
+    i64 9,
+    i64 %1)
+
+  ret <vscale x 2 x i64> %a
+}
+
+define <vscale x 2 x i64> @intrinsic_vrsub_mask_vi_nxv2i64_nxv2i64_i64(<vscale x 2 x i64> %0, <vscale x 2 x i64> %1, <vscale x 2 x i1> %2, i64 %3) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vrsub_mask_vi_nxv2i64_nxv2i64_i64
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e64,m2,tu,mu
+; CHECK:       vrsub.vi {{v[0-9]+}}, {{v[0-9]+}}, 9, v0.t
+  %a = call <vscale x 2 x i64> @llvm.riscv.vrsub.mask.nxv2i64.i64(
+    <vscale x 2 x i64> %0,
+    <vscale x 2 x i64> %1,
+    i64 9,
+    <vscale x 2 x i1> %2,
+    i64 %3)
+
+  ret <vscale x 2 x i64> %a
+}
+
+define <vscale x 4 x i64> @intrinsic_vrsub_vi_nxv4i64_nxv4i64_i64(<vscale x 4 x i64> %0, i64 %1) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vrsub_vi_nxv4i64_nxv4i64_i64
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e64,m4,tu,mu
+; CHECK:       vrsub.vi {{v[0-9]+}}, {{v[0-9]+}}, 9
+  %a = call <vscale x 4 x i64> @llvm.riscv.vrsub.nxv4i64.i64(
+    <vscale x 4 x i64> %0,
+    i64 9,
+    i64 %1)
+
+  ret <vscale x 4 x i64> %a
+}
+
+define <vscale x 4 x i64> @intrinsic_vrsub_mask_vi_nxv4i64_nxv4i64_i64(<vscale x 4 x i64> %0, <vscale x 4 x i64> %1, <vscale x 4 x i1> %2, i64 %3) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vrsub_mask_vi_nxv4i64_nxv4i64_i64
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e64,m4,tu,mu
+; CHECK:       vrsub.vi {{v[0-9]+}}, {{v[0-9]+}}, 9, v0.t
+  %a = call <vscale x 4 x i64> @llvm.riscv.vrsub.mask.nxv4i64.i64(
+    <vscale x 4 x i64> %0,
+    <vscale x 4 x i64> %1,
+    i64 9,
+    <vscale x 4 x i1> %2,
+    i64 %3)
+
+  ret <vscale x 4 x i64> %a
+}
+
+define <vscale x 8 x i64> @intrinsic_vrsub_vi_nxv8i64_nxv8i64_i64(<vscale x 8 x i64> %0, i64 %1) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vrsub_vi_nxv8i64_nxv8i64_i64
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e64,m8,tu,mu
+; CHECK:       vrsub.vi {{v[0-9]+}}, {{v[0-9]+}}, 9
+  %a = call <vscale x 8 x i64> @llvm.riscv.vrsub.nxv8i64.i64(
+    <vscale x 8 x i64> %0,
+    i64 9,
+    i64 %1)
+
+  ret <vscale x 8 x i64> %a
+}
+
+define <vscale x 8 x i64> @intrinsic_vrsub_mask_vi_nxv8i64_nxv8i64_i64(<vscale x 8 x i64> %0, <vscale x 8 x i64> %1, <vscale x 8 x i1> %2, i64 %3) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vrsub_mask_vi_nxv8i64_nxv8i64_i64
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e64,m8,tu,mu
+; CHECK:       vrsub.vi {{v[0-9]+}}, {{v[0-9]+}}, 9, v0.t
+  %a = call <vscale x 8 x i64> @llvm.riscv.vrsub.mask.nxv8i64.i64(
+    <vscale x 8 x i64> %0,
+    <vscale x 8 x i64> %1,
+    i64 9,
+    <vscale x 8 x i1> %2,
+    i64 %3)
+
+  ret <vscale x 8 x i64> %a
+}

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

+; RUN: llc -mtriple=riscv64 -mattr=+experimental-v -verify-machineinstrs \
+; RUN:   --riscv-no-aliases < %s | FileCheck %s
+declare <vscale x 1 x i8> @llvm.riscv.vsub.nxv1i8.nxv1i8(
+  <vscale x 1 x i8>,
+  <vscale x 1 x i8>,
+  i64);
+
+define <vscale x 1 x i8> @intrinsic_vsub_vv_nxv1i8_nxv1i8_nxv1i8(<vscale x 1 x i8> %0, <vscale x 1 x i8> %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vsub_vv_nxv1i8_nxv1i8_nxv1i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,mf8,tu,mu
+; CHECK:       vsub.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
+  %a = call <vscale x 1 x i8> @llvm.riscv.vsub.nxv1i8.nxv1i8(
+    <vscale x 1 x i8> %0,
+    <vscale x 1 x i8> %1,
+    i64 %2)
+
+  ret <vscale x 1 x i8> %a
+}
+
+declare <vscale x 1 x i8> @llvm.riscv.vsub.mask.nxv1i8.nxv1i8(
+  <vscale x 1 x i8>,
+  <vscale x 1 x i8>,
+  <vscale x 1 x i8>,
+  <vscale x 1 x i1>,
+  i64);
+
+define <vscale x 1 x i8> @intrinsic_vsub_mask_vv_nxv1i8_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, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vsub_mask_vv_nxv1i8_nxv1i8_nxv1i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,mf8,tu,mu
+; CHECK:       vsub.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}, v0.t
+  %a = call <vscale x 1 x i8> @llvm.riscv.vsub.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,
+    i64 %4)
+
+  ret <vscale x 1 x i8> %a
+}
+
+declare <vscale x 2 x i8> @llvm.riscv.vsub.nxv2i8.nxv2i8(
+  <vscale x 2 x i8>,
+  <vscale x 2 x i8>,
+  i64);
+
+define <vscale x 2 x i8> @intrinsic_vsub_vv_nxv2i8_nxv2i8_nxv2i8(<vscale x 2 x i8> %0, <vscale x 2 x i8> %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vsub_vv_nxv2i8_nxv2i8_nxv2i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,mf4,tu,mu
+; CHECK:       vsub.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
+  %a = call <vscale x 2 x i8> @llvm.riscv.vsub.nxv2i8.nxv2i8(
+    <vscale x 2 x i8> %0,
+    <vscale x 2 x i8> %1,
+    i64 %2)
+
+  ret <vscale x 2 x i8> %a
+}
+
+declare <vscale x 2 x i8> @llvm.riscv.vsub.mask.nxv2i8.nxv2i8(
+  <vscale x 2 x i8>,
+  <vscale x 2 x i8>,
+  <vscale x 2 x i8>,
+  <vscale x 2 x i1>,
+  i64);
+
+define <vscale x 2 x i8> @intrinsic_vsub_mask_vv_nxv2i8_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, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vsub_mask_vv_nxv2i8_nxv2i8_nxv2i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,mf4,tu,mu
+; CHECK:       vsub.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}, v0.t
+  %a = call <vscale x 2 x i8> @llvm.riscv.vsub.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,
+    i64 %4)
+
+  ret <vscale x 2 x i8> %a
+}
+
+declare <vscale x 4 x i8> @llvm.riscv.vsub.nxv4i8.nxv4i8(
+  <vscale x 4 x i8>,
+  <vscale x 4 x i8>,
+  i64);
+
+define <vscale x 4 x i8> @intrinsic_vsub_vv_nxv4i8_nxv4i8_nxv4i8(<vscale x 4 x i8> %0, <vscale x 4 x i8> %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vsub_vv_nxv4i8_nxv4i8_nxv4i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,mf2,tu,mu
+; CHECK:       vsub.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
+  %a = call <vscale x 4 x i8> @llvm.riscv.vsub.nxv4i8.nxv4i8(
+    <vscale x 4 x i8> %0,
+    <vscale x 4 x i8> %1,
+    i64 %2)
+
+  ret <vscale x 4 x i8> %a
+}
+
+declare <vscale x 4 x i8> @llvm.riscv.vsub.mask.nxv4i8.nxv4i8(
+  <vscale x 4 x i8>,
+  <vscale x 4 x i8>,
+  <vscale x 4 x i8>,
+  <vscale x 4 x i1>,
+  i64);
+
+define <vscale x 4 x i8> @intrinsic_vsub_mask_vv_nxv4i8_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, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vsub_mask_vv_nxv4i8_nxv4i8_nxv4i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,mf2,tu,mu
+; CHECK:       vsub.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}, v0.t
+  %a = call <vscale x 4 x i8> @llvm.riscv.vsub.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,
+    i64 %4)
+
+  ret <vscale x 4 x i8> %a
+}
+
+declare <vscale x 8 x i8> @llvm.riscv.vsub.nxv8i8.nxv8i8(
+  <vscale x 8 x i8>,
+  <vscale x 8 x i8>,
+  i64);
+
+define <vscale x 8 x i8> @intrinsic_vsub_vv_nxv8i8_nxv8i8_nxv8i8(<vscale x 8 x i8> %0, <vscale x 8 x i8> %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vsub_vv_nxv8i8_nxv8i8_nxv8i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,m1,tu,mu
+; CHECK:       vsub.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
+  %a = call <vscale x 8 x i8> @llvm.riscv.vsub.nxv8i8.nxv8i8(
+    <vscale x 8 x i8> %0,
+    <vscale x 8 x i8> %1,
+    i64 %2)
+
+  ret <vscale x 8 x i8> %a
+}
+
+declare <vscale x 8 x i8> @llvm.riscv.vsub.mask.nxv8i8.nxv8i8(
+  <vscale x 8 x i8>,
+  <vscale x 8 x i8>,
+  <vscale x 8 x i8>,
+  <vscale x 8 x i1>,
+  i64);
+
+define <vscale x 8 x i8> @intrinsic_vsub_mask_vv_nxv8i8_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, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vsub_mask_vv_nxv8i8_nxv8i8_nxv8i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,m1,tu,mu
+; CHECK:       vsub.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}, v0.t
+  %a = call <vscale x 8 x i8> @llvm.riscv.vsub.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,
+    i64 %4)
+
+  ret <vscale x 8 x i8> %a
+}
+
+declare <vscale x 16 x i8> @llvm.riscv.vsub.nxv16i8.nxv16i8(
+  <vscale x 16 x i8>,
+  <vscale x 16 x i8>,
+  i64);
+
+define <vscale x 16 x i8> @intrinsic_vsub_vv_nxv16i8_nxv16i8_nxv16i8(<vscale x 16 x i8> %0, <vscale x 16 x i8> %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vsub_vv_nxv16i8_nxv16i8_nxv16i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,m2,tu,mu
+; CHECK:       vsub.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
+  %a = call <vscale x 16 x i8> @llvm.riscv.vsub.nxv16i8.nxv16i8(
+    <vscale x 16 x i8> %0,
+    <vscale x 16 x i8> %1,
+    i64 %2)
+
+  ret <vscale x 16 x i8> %a
+}
+
+declare <vscale x 16 x i8> @llvm.riscv.vsub.mask.nxv16i8.nxv16i8(
+  <vscale x 16 x i8>,
+  <vscale x 16 x i8>,
+  <vscale x 16 x i8>,
+  <vscale x 16 x i1>,
+  i64);
+
+define <vscale x 16 x i8> @intrinsic_vsub_mask_vv_nxv16i8_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, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vsub_mask_vv_nxv16i8_nxv16i8_nxv16i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,m2,tu,mu
+; CHECK:       vsub.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}, v0.t
+  %a = call <vscale x 16 x i8> @llvm.riscv.vsub.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,
+    i64 %4)
+
+  ret <vscale x 16 x i8> %a
+}
+
+declare <vscale x 32 x i8> @llvm.riscv.vsub.nxv32i8.nxv32i8(
+  <vscale x 32 x i8>,
+  <vscale x 32 x i8>,
+  i64);
+
+define <vscale x 32 x i8> @intrinsic_vsub_vv_nxv32i8_nxv32i8_nxv32i8(<vscale x 32 x i8> %0, <vscale x 32 x i8> %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vsub_vv_nxv32i8_nxv32i8_nxv32i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,m4,tu,mu
+; CHECK:       vsub.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
+  %a = call <vscale x 32 x i8> @llvm.riscv.vsub.nxv32i8.nxv32i8(
+    <vscale x 32 x i8> %0,
+    <vscale x 32 x i8> %1,
+    i64 %2)
+
+  ret <vscale x 32 x i8> %a
+}
+
+declare <vscale x 32 x i8> @llvm.riscv.vsub.mask.nxv32i8.nxv32i8(
+  <vscale x 32 x i8>,
+  <vscale x 32 x i8>,
+  <vscale x 32 x i8>,
+  <vscale x 32 x i1>,
+  i64);
+
+define <vscale x 32 x i8> @intrinsic_vsub_mask_vv_nxv32i8_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, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vsub_mask_vv_nxv32i8_nxv32i8_nxv32i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,m4,tu,mu
+; CHECK:       vsub.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}, v0.t
+  %a = call <vscale x 32 x i8> @llvm.riscv.vsub.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,
+    i64 %4)
+
+  ret <vscale x 32 x i8> %a
+}
+
+declare <vscale x 64 x i8> @llvm.riscv.vsub.nxv64i8.nxv64i8(
+  <vscale x 64 x i8>,
+  <vscale x 64 x i8>,
+  i64);
+
+define <vscale x 64 x i8> @intrinsic_vsub_vv_nxv64i8_nxv64i8_nxv64i8(<vscale x 64 x i8> %0, <vscale x 64 x i8> %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vsub_vv_nxv64i8_nxv64i8_nxv64i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,m8,tu,mu
+; CHECK:       vsub.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
+  %a = call <vscale x 64 x i8> @llvm.riscv.vsub.nxv64i8.nxv64i8(
+    <vscale x 64 x i8> %0,
+    <vscale x 64 x i8> %1,
+    i64 %2)
+
+  ret <vscale x 64 x i8> %a
+}
+
+declare <vscale x 64 x i8> @llvm.riscv.vsub.mask.nxv64i8.nxv64i8(
+  <vscale x 64 x i8>,
+  <vscale x 64 x i8>,
+  <vscale x 64 x i8>,
+  <vscale x 64 x i1>,
+  i64);
+
+define <vscale x 64 x i8> @intrinsic_vsub_mask_vv_nxv64i8_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, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vsub_mask_vv_nxv64i8_nxv64i8_nxv64i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,m8,tu,mu
+; CHECK:       vsub.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}, v0.t
+  %a = call <vscale x 64 x i8> @llvm.riscv.vsub.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,
+    i64 %4)
+
+  ret <vscale x 64 x i8> %a
+}
+
+declare <vscale x 1 x i16> @llvm.riscv.vsub.nxv1i16.nxv1i16(
+  <vscale x 1 x i16>,
+  <vscale x 1 x i16>,
+  i64);
+
+define <vscale x 1 x i16> @intrinsic_vsub_vv_nxv1i16_nxv1i16_nxv1i16(<vscale x 1 x i16> %0, <vscale x 1 x i16> %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vsub_vv_nxv1i16_nxv1i16_nxv1i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,mf4,tu,mu
+; CHECK:       vsub.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
+  %a = call <vscale x 1 x i16> @llvm.riscv.vsub.nxv1i16.nxv1i16(
+    <vscale x 1 x i16> %0,
+    <vscale x 1 x i16> %1,
+    i64 %2)
+
+  ret <vscale x 1 x i16> %a
+}
+
+declare <vscale x 1 x i16> @llvm.riscv.vsub.mask.nxv1i16.nxv1i16(
+  <vscale x 1 x i16>,
+  <vscale x 1 x i16>,
+  <vscale x 1 x i16>,
+  <vscale x 1 x i1>,
+  i64);
+
+define <vscale x 1 x i16> @intrinsic_vsub_mask_vv_nxv1i16_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, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vsub_mask_vv_nxv1i16_nxv1i16_nxv1i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,mf4,tu,mu
+; CHECK:       vsub.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}, v0.t
+  %a = call <vscale x 1 x i16> @llvm.riscv.vsub.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,
+    i64 %4)
+
+  ret <vscale x 1 x i16> %a
+}
+
+declare <vscale x 2 x i16> @llvm.riscv.vsub.nxv2i16.nxv2i16(
+  <vscale x 2 x i16>,
+  <vscale x 2 x i16>,
+  i64);
+
+define <vscale x 2 x i16> @intrinsic_vsub_vv_nxv2i16_nxv2i16_nxv2i16(<vscale x 2 x i16> %0, <vscale x 2 x i16> %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vsub_vv_nxv2i16_nxv2i16_nxv2i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,mf2,tu,mu
+; CHECK:       vsub.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
+  %a = call <vscale x 2 x i16> @llvm.riscv.vsub.nxv2i16.nxv2i16(
+    <vscale x 2 x i16> %0,
+    <vscale x 2 x i16> %1,
+    i64 %2)
+
+  ret <vscale x 2 x i16> %a
+}
+
+declare <vscale x 2 x i16> @llvm.riscv.vsub.mask.nxv2i16.nxv2i16(
+  <vscale x 2 x i16>,
+  <vscale x 2 x i16>,
+  <vscale x 2 x i16>,
+  <vscale x 2 x i1>,
+  i64);
+
+define <vscale x 2 x i16> @intrinsic_vsub_mask_vv_nxv2i16_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, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vsub_mask_vv_nxv2i16_nxv2i16_nxv2i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,mf2,tu,mu
+; CHECK:       vsub.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}, v0.t
+  %a = call <vscale x 2 x i16> @llvm.riscv.vsub.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,
+    i64 %4)
+
+  ret <vscale x 2 x i16> %a
+}
+
+declare <vscale x 4 x i16> @llvm.riscv.vsub.nxv4i16.nxv4i16(
+  <vscale x 4 x i16>,
+  <vscale x 4 x i16>,
+  i64);
+
+define <vscale x 4 x i16> @intrinsic_vsub_vv_nxv4i16_nxv4i16_nxv4i16(<vscale x 4 x i16> %0, <vscale x 4 x i16> %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vsub_vv_nxv4i16_nxv4i16_nxv4i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,m1,tu,mu
+; CHECK:       vsub.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
+  %a = call <vscale x 4 x i16> @llvm.riscv.vsub.nxv4i16.nxv4i16(
+    <vscale x 4 x i16> %0,
+    <vscale x 4 x i16> %1,
+    i64 %2)
+
+  ret <vscale x 4 x i16> %a
+}
+
+declare <vscale x 4 x i16> @llvm.riscv.vsub.mask.nxv4i16.nxv4i16(
+  <vscale x 4 x i16>,
+  <vscale x 4 x i16>,
+  <vscale x 4 x i16>,
+  <vscale x 4 x i1>,
+  i64);
+
+define <vscale x 4 x i16> @intrinsic_vsub_mask_vv_nxv4i16_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, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vsub_mask_vv_nxv4i16_nxv4i16_nxv4i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,m1,tu,mu
+; CHECK:       vsub.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}, v0.t
+  %a = call <vscale x 4 x i16> @llvm.riscv.vsub.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,
+    i64 %4)
+
+  ret <vscale x 4 x i16> %a
+}
+
+declare <vscale x 8 x i16> @llvm.riscv.vsub.nxv8i16.nxv8i16(
+  <vscale x 8 x i16>,
+  <vscale x 8 x i16>,
+  i64);
+
+define <vscale x 8 x i16> @intrinsic_vsub_vv_nxv8i16_nxv8i16_nxv8i16(<vscale x 8 x i16> %0, <vscale x 8 x i16> %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vsub_vv_nxv8i16_nxv8i16_nxv8i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,m2,tu,mu
+; CHECK:       vsub.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
+  %a = call <vscale x 8 x i16> @llvm.riscv.vsub.nxv8i16.nxv8i16(
+    <vscale x 8 x i16> %0,
+    <vscale x 8 x i16> %1,
+    i64 %2)
+
+  ret <vscale x 8 x i16> %a
+}
+
+declare <vscale x 8 x i16> @llvm.riscv.vsub.mask.nxv8i16.nxv8i16(
+  <vscale x 8 x i16>,
+  <vscale x 8 x i16>,
+  <vscale x 8 x i16>,
+  <vscale x 8 x i1>,
+  i64);
+
+define <vscale x 8 x i16> @intrinsic_vsub_mask_vv_nxv8i16_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, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vsub_mask_vv_nxv8i16_nxv8i16_nxv8i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,m2,tu,mu
+; CHECK:       vsub.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}, v0.t
+  %a = call <vscale x 8 x i16> @llvm.riscv.vsub.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,
+    i64 %4)
+
+  ret <vscale x 8 x i16> %a
+}
+
+declare <vscale x 16 x i16> @llvm.riscv.vsub.nxv16i16.nxv16i16(
+  <vscale x 16 x i16>,
+  <vscale x 16 x i16>,
+  i64);
+
+define <vscale x 16 x i16> @intrinsic_vsub_vv_nxv16i16_nxv16i16_nxv16i16(<vscale x 16 x i16> %0, <vscale x 16 x i16> %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vsub_vv_nxv16i16_nxv16i16_nxv16i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,m4,tu,mu
+; CHECK:       vsub.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
+  %a = call <vscale x 16 x i16> @llvm.riscv.vsub.nxv16i16.nxv16i16(
+    <vscale x 16 x i16> %0,
+    <vscale x 16 x i16> %1,
+    i64 %2)
+
+  ret <vscale x 16 x i16> %a
+}
+
+declare <vscale x 16 x i16> @llvm.riscv.vsub.mask.nxv16i16.nxv16i16(
+  <vscale x 16 x i16>,
+  <vscale x 16 x i16>,
+  <vscale x 16 x i16>,
+  <vscale x 16 x i1>,
+  i64);
+
+define <vscale x 16 x i16> @intrinsic_vsub_mask_vv_nxv16i16_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, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vsub_mask_vv_nxv16i16_nxv16i16_nxv16i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,m4,tu,mu
+; CHECK:       vsub.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}, v0.t
+  %a = call <vscale x 16 x i16> @llvm.riscv.vsub.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,
+    i64 %4)
+
+  ret <vscale x 16 x i16> %a
+}
+
+declare <vscale x 32 x i16> @llvm.riscv.vsub.nxv32i16.nxv32i16(
+  <vscale x 32 x i16>,
+  <vscale x 32 x i16>,
+  i64);
+
+define <vscale x 32 x i16> @intrinsic_vsub_vv_nxv32i16_nxv32i16_nxv32i16(<vscale x 32 x i16> %0, <vscale x 32 x i16> %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vsub_vv_nxv32i16_nxv32i16_nxv32i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,m8,tu,mu
+; CHECK:       vsub.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
+  %a = call <vscale x 32 x i16> @llvm.riscv.vsub.nxv32i16.nxv32i16(
+    <vscale x 32 x i16> %0,
+    <vscale x 32 x i16> %1,
+    i64 %2)
+
+  ret <vscale x 32 x i16> %a
+}
+
+declare <vscale x 32 x i16> @llvm.riscv.vsub.mask.nxv32i16.nxv32i16(
+  <vscale x 32 x i16>,
+  <vscale x 32 x i16>,
+  <vscale x 32 x i16>,
+  <vscale x 32 x i1>,
+  i64);
+
+define <vscale x 32 x i16> @intrinsic_vsub_mask_vv_nxv32i16_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, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vsub_mask_vv_nxv32i16_nxv32i16_nxv32i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,m8,tu,mu
+; CHECK:       vsub.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}, v0.t
+  %a = call <vscale x 32 x i16> @llvm.riscv.vsub.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,
+    i64 %4)
+
+  ret <vscale x 32 x i16> %a
+}
+
+declare <vscale x 1 x i32> @llvm.riscv.vsub.nxv1i32.nxv1i32(
+  <vscale x 1 x i32>,
+  <vscale x 1 x i32>,
+  i64);
+
+define <vscale x 1 x i32> @intrinsic_vsub_vv_nxv1i32_nxv1i32_nxv1i32(<vscale x 1 x i32> %0, <vscale x 1 x i32> %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vsub_vv_nxv1i32_nxv1i32_nxv1i32
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e32,mf2,tu,mu
+; CHECK:       vsub.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
+  %a = call <vscale x 1 x i32> @llvm.riscv.vsub.nxv1i32.nxv1i32(
+    <vscale x 1 x i32> %0,
+    <vscale x 1 x i32> %1,
+    i64 %2)
+
+  ret <vscale x 1 x i32> %a
+}
+
+declare <vscale x 1 x i32> @llvm.riscv.vsub.mask.nxv1i32.nxv1i32(
+  <vscale x 1 x i32>,
+  <vscale x 1 x i32>,
+  <vscale x 1 x i32>,
+  <vscale x 1 x i1>,
+  i64);
+
+define <vscale x 1 x i32> @intrinsic_vsub_mask_vv_nxv1i32_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, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vsub_mask_vv_nxv1i32_nxv1i32_nxv1i32
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e32,mf2,tu,mu
+; CHECK:       vsub.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}, v0.t
+  %a = call <vscale x 1 x i32> @llvm.riscv.vsub.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,
+    i64 %4)
+
+  ret <vscale x 1 x i32> %a
+}
+
+declare <vscale x 2 x i32> @llvm.riscv.vsub.nxv2i32.nxv2i32(
+  <vscale x 2 x i32>,
+  <vscale x 2 x i32>,
+  i64);
+
+define <vscale x 2 x i32> @intrinsic_vsub_vv_nxv2i32_nxv2i32_nxv2i32(<vscale x 2 x i32> %0, <vscale x 2 x i32> %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vsub_vv_nxv2i32_nxv2i32_nxv2i32
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e32,m1,tu,mu
+; CHECK:       vsub.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
+  %a = call <vscale x 2 x i32> @llvm.riscv.vsub.nxv2i32.nxv2i32(
+    <vscale x 2 x i32> %0,
+    <vscale x 2 x i32> %1,
+    i64 %2)
+
+  ret <vscale x 2 x i32> %a
+}
+
+declare <vscale x 2 x i32> @llvm.riscv.vsub.mask.nxv2i32.nxv2i32(
+  <vscale x 2 x i32>,
+  <vscale x 2 x i32>,
+  <vscale x 2 x i32>,
+  <vscale x 2 x i1>,
+  i64);
+
+define <vscale x 2 x i32> @intrinsic_vsub_mask_vv_nxv2i32_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, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vsub_mask_vv_nxv2i32_nxv2i32_nxv2i32
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e32,m1,tu,mu
+; CHECK:       vsub.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}, v0.t
+  %a = call <vscale x 2 x i32> @llvm.riscv.vsub.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,
+    i64 %4)
+
+  ret <vscale x 2 x i32> %a
+}
+
+declare <vscale x 4 x i32> @llvm.riscv.vsub.nxv4i32.nxv4i32(
+  <vscale x 4 x i32>,
+  <vscale x 4 x i32>,
+  i64);
+
+define <vscale x 4 x i32> @intrinsic_vsub_vv_nxv4i32_nxv4i32_nxv4i32(<vscale x 4 x i32> %0, <vscale x 4 x i32> %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vsub_vv_nxv4i32_nxv4i32_nxv4i32
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e32,m2,tu,mu
+; CHECK:       vsub.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
+  %a = call <vscale x 4 x i32> @llvm.riscv.vsub.nxv4i32.nxv4i32(
+    <vscale x 4 x i32> %0,
+    <vscale x 4 x i32> %1,
+    i64 %2)
+
+  ret <vscale x 4 x i32> %a
+}
+
+declare <vscale x 4 x i32> @llvm.riscv.vsub.mask.nxv4i32.nxv4i32(
+  <vscale x 4 x i32>,
+  <vscale x 4 x i32>,
+  <vscale x 4 x i32>,
+  <vscale x 4 x i1>,
+  i64);
+
+define <vscale x 4 x i32> @intrinsic_vsub_mask_vv_nxv4i32_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, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vsub_mask_vv_nxv4i32_nxv4i32_nxv4i32
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e32,m2,tu,mu
+; CHECK:       vsub.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}, v0.t
+  %a = call <vscale x 4 x i32> @llvm.riscv.vsub.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,
+    i64 %4)
+
+  ret <vscale x 4 x i32> %a
+}
+
+declare <vscale x 8 x i32> @llvm.riscv.vsub.nxv8i32.nxv8i32(
+  <vscale x 8 x i32>,
+  <vscale x 8 x i32>,
+  i64);
+
+define <vscale x 8 x i32> @intrinsic_vsub_vv_nxv8i32_nxv8i32_nxv8i32(<vscale x 8 x i32> %0, <vscale x 8 x i32> %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vsub_vv_nxv8i32_nxv8i32_nxv8i32
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e32,m4,tu,mu
+; CHECK:       vsub.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
+  %a = call <vscale x 8 x i32> @llvm.riscv.vsub.nxv8i32.nxv8i32(
+    <vscale x 8 x i32> %0,
+    <vscale x 8 x i32> %1,
+    i64 %2)
+
+  ret <vscale x 8 x i32> %a
+}
+
+declare <vscale x 8 x i32> @llvm.riscv.vsub.mask.nxv8i32.nxv8i32(
+  <vscale x 8 x i32>,
+  <vscale x 8 x i32>,
+  <vscale x 8 x i32>,
+  <vscale x 8 x i1>,
+  i64);
+
+define <vscale x 8 x i32> @intrinsic_vsub_mask_vv_nxv8i32_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, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vsub_mask_vv_nxv8i32_nxv8i32_nxv8i32
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e32,m4,tu,mu
+; CHECK:       vsub.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}, v0.t
+  %a = call <vscale x 8 x i32> @llvm.riscv.vsub.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,
+    i64 %4)
+
+  ret <vscale x 8 x i32> %a
+}
+
+declare <vscale x 16 x i32> @llvm.riscv.vsub.nxv16i32.nxv16i32(
+  <vscale x 16 x i32>,
+  <vscale x 16 x i32>,
+  i64);
+
+define <vscale x 16 x i32> @intrinsic_vsub_vv_nxv16i32_nxv16i32_nxv16i32(<vscale x 16 x i32> %0, <vscale x 16 x i32> %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vsub_vv_nxv16i32_nxv16i32_nxv16i32
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e32,m8,tu,mu
+; CHECK:       vsub.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
+  %a = call <vscale x 16 x i32> @llvm.riscv.vsub.nxv16i32.nxv16i32(
+    <vscale x 16 x i32> %0,
+    <vscale x 16 x i32> %1,
+    i64 %2)
+
+  ret <vscale x 16 x i32> %a
+}
+
+declare <vscale x 16 x i32> @llvm.riscv.vsub.mask.nxv16i32.nxv16i32(
+  <vscale x 16 x i32>,
+  <vscale x 16 x i32>,
+  <vscale x 16 x i32>,
+  <vscale x 16 x i1>,
+  i64);
+
+define <vscale x 16 x i32> @intrinsic_vsub_mask_vv_nxv16i32_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, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vsub_mask_vv_nxv16i32_nxv16i32_nxv16i32
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e32,m8,tu,mu
+; CHECK:       vsub.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}, v0.t
+  %a = call <vscale x 16 x i32> @llvm.riscv.vsub.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,
+    i64 %4)
+
+  ret <vscale x 16 x i32> %a
+}
+
+declare <vscale x 1 x i64> @llvm.riscv.vsub.nxv1i64.nxv1i64(
+  <vscale x 1 x i64>,
+  <vscale x 1 x i64>,
+  i64);
+
+define <vscale x 1 x i64> @intrinsic_vsub_vv_nxv1i64_nxv1i64_nxv1i64(<vscale x 1 x i64> %0, <vscale x 1 x i64> %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vsub_vv_nxv1i64_nxv1i64_nxv1i64
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e64,m1,tu,mu
+; CHECK:       vsub.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
+  %a = call <vscale x 1 x i64> @llvm.riscv.vsub.nxv1i64.nxv1i64(
+    <vscale x 1 x i64> %0,
+    <vscale x 1 x i64> %1,
+    i64 %2)
+
+  ret <vscale x 1 x i64> %a
+}
+
+declare <vscale x 1 x i64> @llvm.riscv.vsub.mask.nxv1i64.nxv1i64(
+  <vscale x 1 x i64>,
+  <vscale x 1 x i64>,
+  <vscale x 1 x i64>,
+  <vscale x 1 x i1>,
+  i64);
+
+define <vscale x 1 x i64> @intrinsic_vsub_mask_vv_nxv1i64_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, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vsub_mask_vv_nxv1i64_nxv1i64_nxv1i64
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e64,m1,tu,mu
+; CHECK:       vsub.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}, v0.t
+  %a = call <vscale x 1 x i64> @llvm.riscv.vsub.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,
+    i64 %4)
+
+  ret <vscale x 1 x i64> %a
+}
+
+declare <vscale x 2 x i64> @llvm.riscv.vsub.nxv2i64.nxv2i64(
+  <vscale x 2 x i64>,
+  <vscale x 2 x i64>,
+  i64);
+
+define <vscale x 2 x i64> @intrinsic_vsub_vv_nxv2i64_nxv2i64_nxv2i64(<vscale x 2 x i64> %0, <vscale x 2 x i64> %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vsub_vv_nxv2i64_nxv2i64_nxv2i64
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e64,m2,tu,mu
+; CHECK:       vsub.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
+  %a = call <vscale x 2 x i64> @llvm.riscv.vsub.nxv2i64.nxv2i64(
+    <vscale x 2 x i64> %0,
+    <vscale x 2 x i64> %1,
+    i64 %2)
+
+  ret <vscale x 2 x i64> %a
+}
+
+declare <vscale x 2 x i64> @llvm.riscv.vsub.mask.nxv2i64.nxv2i64(
+  <vscale x 2 x i64>,
+  <vscale x 2 x i64>,
+  <vscale x 2 x i64>,
+  <vscale x 2 x i1>,
+  i64);
+
+define <vscale x 2 x i64> @intrinsic_vsub_mask_vv_nxv2i64_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, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vsub_mask_vv_nxv2i64_nxv2i64_nxv2i64
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e64,m2,tu,mu
+; CHECK:       vsub.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}, v0.t
+  %a = call <vscale x 2 x i64> @llvm.riscv.vsub.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,
+    i64 %4)
+
+  ret <vscale x 2 x i64> %a
+}
+
+declare <vscale x 4 x i64> @llvm.riscv.vsub.nxv4i64.nxv4i64(
+  <vscale x 4 x i64>,
+  <vscale x 4 x i64>,
+  i64);
+
+define <vscale x 4 x i64> @intrinsic_vsub_vv_nxv4i64_nxv4i64_nxv4i64(<vscale x 4 x i64> %0, <vscale x 4 x i64> %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vsub_vv_nxv4i64_nxv4i64_nxv4i64
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e64,m4,tu,mu
+; CHECK:       vsub.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
+  %a = call <vscale x 4 x i64> @llvm.riscv.vsub.nxv4i64.nxv4i64(
+    <vscale x 4 x i64> %0,
+    <vscale x 4 x i64> %1,
+    i64 %2)
+
+  ret <vscale x 4 x i64> %a
+}
+
+declare <vscale x 4 x i64> @llvm.riscv.vsub.mask.nxv4i64.nxv4i64(
+  <vscale x 4 x i64>,
+  <vscale x 4 x i64>,
+  <vscale x 4 x i64>,
+  <vscale x 4 x i1>,
+  i64);
+
+define <vscale x 4 x i64> @intrinsic_vsub_mask_vv_nxv4i64_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, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vsub_mask_vv_nxv4i64_nxv4i64_nxv4i64
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e64,m4,tu,mu
+; CHECK:       vsub.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}, v0.t
+  %a = call <vscale x 4 x i64> @llvm.riscv.vsub.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,
+    i64 %4)
+
+  ret <vscale x 4 x i64> %a
+}
+
+declare <vscale x 8 x i64> @llvm.riscv.vsub.nxv8i64.nxv8i64(
+  <vscale x 8 x i64>,
+  <vscale x 8 x i64>,
+  i64);
+
+define <vscale x 8 x i64> @intrinsic_vsub_vv_nxv8i64_nxv8i64_nxv8i64(<vscale x 8 x i64> %0, <vscale x 8 x i64> %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vsub_vv_nxv8i64_nxv8i64_nxv8i64
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e64,m8,tu,mu
+; CHECK:       vsub.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
+  %a = call <vscale x 8 x i64> @llvm.riscv.vsub.nxv8i64.nxv8i64(
+    <vscale x 8 x i64> %0,
+    <vscale x 8 x i64> %1,
+    i64 %2)
+
+  ret <vscale x 8 x i64> %a
+}
+
+declare <vscale x 8 x i64> @llvm.riscv.vsub.mask.nxv8i64.nxv8i64(
+  <vscale x 8 x i64>,
+  <vscale x 8 x i64>,
+  <vscale x 8 x i64>,
+  <vscale x 8 x i1>,
+  i64);
+
+define <vscale x 8 x i64> @intrinsic_vsub_mask_vv_nxv8i64_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, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vsub_mask_vv_nxv8i64_nxv8i64_nxv8i64
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e64,m8,tu,mu
+; CHECK:       vsub.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}, v0.t
+  %a = call <vscale x 8 x i64> @llvm.riscv.vsub.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,
+    i64 %4)
+
+  ret <vscale x 8 x i64> %a
+}
+
+declare <vscale x 1 x i8> @llvm.riscv.vsub.nxv1i8.i8(
+  <vscale x 1 x i8>,
+  i8,
+  i64);
+
+define <vscale x 1 x i8> @intrinsic_vsub_vx_nxv1i8_nxv1i8_i8(<vscale x 1 x i8> %0, i8 %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vsub_vx_nxv1i8_nxv1i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,mf8,tu,mu
+; CHECK:       vsub.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 1 x i8> @llvm.riscv.vsub.nxv1i8.i8(
+    <vscale x 1 x i8> %0,
+    i8 %1,
+    i64 %2)
+
+  ret <vscale x 1 x i8> %a
+}
+
+declare <vscale x 1 x i8> @llvm.riscv.vsub.mask.nxv1i8.i8(
+  <vscale x 1 x i8>,
+  <vscale x 1 x i8>,
+  i8,
+  <vscale x 1 x i1>,
+  i64);
+
+define <vscale x 1 x i8> @intrinsic_vsub_mask_vx_nxv1i8_nxv1i8_i8(<vscale x 1 x i8> %0, <vscale x 1 x i8> %1, i8 %2, <vscale x 1 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vsub_mask_vx_nxv1i8_nxv1i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,mf8,tu,mu
+; CHECK:       vsub.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 1 x i8> @llvm.riscv.vsub.mask.nxv1i8.i8(
+    <vscale x 1 x i8> %0,
+    <vscale x 1 x i8> %1,
+    i8 %2,
+    <vscale x 1 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 1 x i8> %a
+}
+
+declare <vscale x 2 x i8> @llvm.riscv.vsub.nxv2i8.i8(
+  <vscale x 2 x i8>,
+  i8,
+  i64);
+
+define <vscale x 2 x i8> @intrinsic_vsub_vx_nxv2i8_nxv2i8_i8(<vscale x 2 x i8> %0, i8 %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vsub_vx_nxv2i8_nxv2i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,mf4,tu,mu
+; CHECK:       vsub.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 2 x i8> @llvm.riscv.vsub.nxv2i8.i8(
+    <vscale x 2 x i8> %0,
+    i8 %1,
+    i64 %2)
+
+  ret <vscale x 2 x i8> %a
+}
+
+declare <vscale x 2 x i8> @llvm.riscv.vsub.mask.nxv2i8.i8(
+  <vscale x 2 x i8>,
+  <vscale x 2 x i8>,
+  i8,
+  <vscale x 2 x i1>,
+  i64);
+
+define <vscale x 2 x i8> @intrinsic_vsub_mask_vx_nxv2i8_nxv2i8_i8(<vscale x 2 x i8> %0, <vscale x 2 x i8> %1, i8 %2, <vscale x 2 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vsub_mask_vx_nxv2i8_nxv2i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,mf4,tu,mu
+; CHECK:       vsub.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 2 x i8> @llvm.riscv.vsub.mask.nxv2i8.i8(
+    <vscale x 2 x i8> %0,
+    <vscale x 2 x i8> %1,
+    i8 %2,
+    <vscale x 2 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 2 x i8> %a
+}
+
+declare <vscale x 4 x i8> @llvm.riscv.vsub.nxv4i8.i8(
+  <vscale x 4 x i8>,
+  i8,
+  i64);
+
+define <vscale x 4 x i8> @intrinsic_vsub_vx_nxv4i8_nxv4i8_i8(<vscale x 4 x i8> %0, i8 %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vsub_vx_nxv4i8_nxv4i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,mf2,tu,mu
+; CHECK:       vsub.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 4 x i8> @llvm.riscv.vsub.nxv4i8.i8(
+    <vscale x 4 x i8> %0,
+    i8 %1,
+    i64 %2)
+
+  ret <vscale x 4 x i8> %a
+}
+
+declare <vscale x 4 x i8> @llvm.riscv.vsub.mask.nxv4i8.i8(
+  <vscale x 4 x i8>,
+  <vscale x 4 x i8>,
+  i8,
+  <vscale x 4 x i1>,
+  i64);
+
+define <vscale x 4 x i8> @intrinsic_vsub_mask_vx_nxv4i8_nxv4i8_i8(<vscale x 4 x i8> %0, <vscale x 4 x i8> %1, i8 %2, <vscale x 4 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vsub_mask_vx_nxv4i8_nxv4i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,mf2,tu,mu
+; CHECK:       vsub.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 4 x i8> @llvm.riscv.vsub.mask.nxv4i8.i8(
+    <vscale x 4 x i8> %0,
+    <vscale x 4 x i8> %1,
+    i8 %2,
+    <vscale x 4 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 4 x i8> %a
+}
+
+declare <vscale x 8 x i8> @llvm.riscv.vsub.nxv8i8.i8(
+  <vscale x 8 x i8>,
+  i8,
+  i64);
+
+define <vscale x 8 x i8> @intrinsic_vsub_vx_nxv8i8_nxv8i8_i8(<vscale x 8 x i8> %0, i8 %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vsub_vx_nxv8i8_nxv8i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,m1,tu,mu
+; CHECK:       vsub.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 8 x i8> @llvm.riscv.vsub.nxv8i8.i8(
+    <vscale x 8 x i8> %0,
+    i8 %1,
+    i64 %2)
+
+  ret <vscale x 8 x i8> %a
+}
+
+declare <vscale x 8 x i8> @llvm.riscv.vsub.mask.nxv8i8.i8(
+  <vscale x 8 x i8>,
+  <vscale x 8 x i8>,
+  i8,
+  <vscale x 8 x i1>,
+  i64);
+
+define <vscale x 8 x i8> @intrinsic_vsub_mask_vx_nxv8i8_nxv8i8_i8(<vscale x 8 x i8> %0, <vscale x 8 x i8> %1, i8 %2, <vscale x 8 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vsub_mask_vx_nxv8i8_nxv8i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,m1,tu,mu
+; CHECK:       vsub.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 8 x i8> @llvm.riscv.vsub.mask.nxv8i8.i8(
+    <vscale x 8 x i8> %0,
+    <vscale x 8 x i8> %1,
+    i8 %2,
+    <vscale x 8 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 8 x i8> %a
+}
+
+declare <vscale x 16 x i8> @llvm.riscv.vsub.nxv16i8.i8(
+  <vscale x 16 x i8>,
+  i8,
+  i64);
+
+define <vscale x 16 x i8> @intrinsic_vsub_vx_nxv16i8_nxv16i8_i8(<vscale x 16 x i8> %0, i8 %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vsub_vx_nxv16i8_nxv16i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,m2,tu,mu
+; CHECK:       vsub.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 16 x i8> @llvm.riscv.vsub.nxv16i8.i8(
+    <vscale x 16 x i8> %0,
+    i8 %1,
+    i64 %2)
+
+  ret <vscale x 16 x i8> %a
+}
+
+declare <vscale x 16 x i8> @llvm.riscv.vsub.mask.nxv16i8.i8(
+  <vscale x 16 x i8>,
+  <vscale x 16 x i8>,
+  i8,
+  <vscale x 16 x i1>,
+  i64);
+
+define <vscale x 16 x i8> @intrinsic_vsub_mask_vx_nxv16i8_nxv16i8_i8(<vscale x 16 x i8> %0, <vscale x 16 x i8> %1, i8 %2, <vscale x 16 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vsub_mask_vx_nxv16i8_nxv16i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,m2,tu,mu
+; CHECK:       vsub.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 16 x i8> @llvm.riscv.vsub.mask.nxv16i8.i8(
+    <vscale x 16 x i8> %0,
+    <vscale x 16 x i8> %1,
+    i8 %2,
+    <vscale x 16 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 16 x i8> %a
+}
+
+declare <vscale x 32 x i8> @llvm.riscv.vsub.nxv32i8.i8(
+  <vscale x 32 x i8>,
+  i8,
+  i64);
+
+define <vscale x 32 x i8> @intrinsic_vsub_vx_nxv32i8_nxv32i8_i8(<vscale x 32 x i8> %0, i8 %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vsub_vx_nxv32i8_nxv32i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,m4,tu,mu
+; CHECK:       vsub.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 32 x i8> @llvm.riscv.vsub.nxv32i8.i8(
+    <vscale x 32 x i8> %0,
+    i8 %1,
+    i64 %2)
+
+  ret <vscale x 32 x i8> %a
+}
+
+declare <vscale x 32 x i8> @llvm.riscv.vsub.mask.nxv32i8.i8(
+  <vscale x 32 x i8>,
+  <vscale x 32 x i8>,
+  i8,
+  <vscale x 32 x i1>,
+  i64);
+
+define <vscale x 32 x i8> @intrinsic_vsub_mask_vx_nxv32i8_nxv32i8_i8(<vscale x 32 x i8> %0, <vscale x 32 x i8> %1, i8 %2, <vscale x 32 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vsub_mask_vx_nxv32i8_nxv32i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,m4,tu,mu
+; CHECK:       vsub.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 32 x i8> @llvm.riscv.vsub.mask.nxv32i8.i8(
+    <vscale x 32 x i8> %0,
+    <vscale x 32 x i8> %1,
+    i8 %2,
+    <vscale x 32 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 32 x i8> %a
+}
+
+declare <vscale x 64 x i8> @llvm.riscv.vsub.nxv64i8.i8(
+  <vscale x 64 x i8>,
+  i8,
+  i64);
+
+define <vscale x 64 x i8> @intrinsic_vsub_vx_nxv64i8_nxv64i8_i8(<vscale x 64 x i8> %0, i8 %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vsub_vx_nxv64i8_nxv64i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,m8,tu,mu
+; CHECK:       vsub.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 64 x i8> @llvm.riscv.vsub.nxv64i8.i8(
+    <vscale x 64 x i8> %0,
+    i8 %1,
+    i64 %2)
+
+  ret <vscale x 64 x i8> %a
+}
+
+declare <vscale x 64 x i8> @llvm.riscv.vsub.mask.nxv64i8.i8(
+  <vscale x 64 x i8>,
+  <vscale x 64 x i8>,
+  i8,
+  <vscale x 64 x i1>,
+  i64);
+
+define <vscale x 64 x i8> @intrinsic_vsub_mask_vx_nxv64i8_nxv64i8_i8(<vscale x 64 x i8> %0, <vscale x 64 x i8> %1, i8 %2, <vscale x 64 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vsub_mask_vx_nxv64i8_nxv64i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,m8,tu,mu
+; CHECK:       vsub.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 64 x i8> @llvm.riscv.vsub.mask.nxv64i8.i8(
+    <vscale x 64 x i8> %0,
+    <vscale x 64 x i8> %1,
+    i8 %2,
+    <vscale x 64 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 64 x i8> %a
+}
+
+declare <vscale x 1 x i16> @llvm.riscv.vsub.nxv1i16.i16(
+  <vscale x 1 x i16>,
+  i16,
+  i64);
+
+define <vscale x 1 x i16> @intrinsic_vsub_vx_nxv1i16_nxv1i16_i16(<vscale x 1 x i16> %0, i16 %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vsub_vx_nxv1i16_nxv1i16_i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,mf4,tu,mu
+; CHECK:       vsub.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 1 x i16> @llvm.riscv.vsub.nxv1i16.i16(
+    <vscale x 1 x i16> %0,
+    i16 %1,
+    i64 %2)
+
+  ret <vscale x 1 x i16> %a
+}
+
+declare <vscale x 1 x i16> @llvm.riscv.vsub.mask.nxv1i16.i16(
+  <vscale x 1 x i16>,
+  <vscale x 1 x i16>,
+  i16,
+  <vscale x 1 x i1>,
+  i64);
+
+define <vscale x 1 x i16> @intrinsic_vsub_mask_vx_nxv1i16_nxv1i16_i16(<vscale x 1 x i16> %0, <vscale x 1 x i16> %1, i16 %2, <vscale x 1 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vsub_mask_vx_nxv1i16_nxv1i16_i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,mf4,tu,mu
+; CHECK:       vsub.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 1 x i16> @llvm.riscv.vsub.mask.nxv1i16.i16(
+    <vscale x 1 x i16> %0,
+    <vscale x 1 x i16> %1,
+    i16 %2,
+    <vscale x 1 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 1 x i16> %a
+}
+
+declare <vscale x 2 x i16> @llvm.riscv.vsub.nxv2i16.i16(
+  <vscale x 2 x i16>,
+  i16,
+  i64);
+
+define <vscale x 2 x i16> @intrinsic_vsub_vx_nxv2i16_nxv2i16_i16(<vscale x 2 x i16> %0, i16 %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vsub_vx_nxv2i16_nxv2i16_i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,mf2,tu,mu
+; CHECK:       vsub.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 2 x i16> @llvm.riscv.vsub.nxv2i16.i16(
+    <vscale x 2 x i16> %0,
+    i16 %1,
+    i64 %2)
+
+  ret <vscale x 2 x i16> %a
+}
+
+declare <vscale x 2 x i16> @llvm.riscv.vsub.mask.nxv2i16.i16(
+  <vscale x 2 x i16>,
+  <vscale x 2 x i16>,
+  i16,
+  <vscale x 2 x i1>,
+  i64);
+
+define <vscale x 2 x i16> @intrinsic_vsub_mask_vx_nxv2i16_nxv2i16_i16(<vscale x 2 x i16> %0, <vscale x 2 x i16> %1, i16 %2, <vscale x 2 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vsub_mask_vx_nxv2i16_nxv2i16_i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,mf2,tu,mu
+; CHECK:       vsub.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 2 x i16> @llvm.riscv.vsub.mask.nxv2i16.i16(
+    <vscale x 2 x i16> %0,
+    <vscale x 2 x i16> %1,
+    i16 %2,
+    <vscale x 2 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 2 x i16> %a
+}
+
+declare <vscale x 4 x i16> @llvm.riscv.vsub.nxv4i16.i16(
+  <vscale x 4 x i16>,
+  i16,
+  i64);
+
+define <vscale x 4 x i16> @intrinsic_vsub_vx_nxv4i16_nxv4i16_i16(<vscale x 4 x i16> %0, i16 %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vsub_vx_nxv4i16_nxv4i16_i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,m1,tu,mu
+; CHECK:       vsub.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 4 x i16> @llvm.riscv.vsub.nxv4i16.i16(
+    <vscale x 4 x i16> %0,
+    i16 %1,
+    i64 %2)
+
+  ret <vscale x 4 x i16> %a
+}
+
+declare <vscale x 4 x i16> @llvm.riscv.vsub.mask.nxv4i16.i16(
+  <vscale x 4 x i16>,
+  <vscale x 4 x i16>,
+  i16,
+  <vscale x 4 x i1>,
+  i64);
+
+define <vscale x 4 x i16> @intrinsic_vsub_mask_vx_nxv4i16_nxv4i16_i16(<vscale x 4 x i16> %0, <vscale x 4 x i16> %1, i16 %2, <vscale x 4 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vsub_mask_vx_nxv4i16_nxv4i16_i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,m1,tu,mu
+; CHECK:       vsub.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 4 x i16> @llvm.riscv.vsub.mask.nxv4i16.i16(
+    <vscale x 4 x i16> %0,
+    <vscale x 4 x i16> %1,
+    i16 %2,
+    <vscale x 4 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 4 x i16> %a
+}
+
+declare <vscale x 8 x i16> @llvm.riscv.vsub.nxv8i16.i16(
+  <vscale x 8 x i16>,
+  i16,
+  i64);
+
+define <vscale x 8 x i16> @intrinsic_vsub_vx_nxv8i16_nxv8i16_i16(<vscale x 8 x i16> %0, i16 %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vsub_vx_nxv8i16_nxv8i16_i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,m2,tu,mu
+; CHECK:       vsub.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 8 x i16> @llvm.riscv.vsub.nxv8i16.i16(
+    <vscale x 8 x i16> %0,
+    i16 %1,
+    i64 %2)
+
+  ret <vscale x 8 x i16> %a
+}
+
+declare <vscale x 8 x i16> @llvm.riscv.vsub.mask.nxv8i16.i16(
+  <vscale x 8 x i16>,
+  <vscale x 8 x i16>,
+  i16,
+  <vscale x 8 x i1>,
+  i64);
+
+define <vscale x 8 x i16> @intrinsic_vsub_mask_vx_nxv8i16_nxv8i16_i16(<vscale x 8 x i16> %0, <vscale x 8 x i16> %1, i16 %2, <vscale x 8 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vsub_mask_vx_nxv8i16_nxv8i16_i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,m2,tu,mu
+; CHECK:       vsub.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 8 x i16> @llvm.riscv.vsub.mask.nxv8i16.i16(
+    <vscale x 8 x i16> %0,
+    <vscale x 8 x i16> %1,
+    i16 %2,
+    <vscale x 8 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 8 x i16> %a
+}
+
+declare <vscale x 16 x i16> @llvm.riscv.vsub.nxv16i16.i16(
+  <vscale x 16 x i16>,
+  i16,
+  i64);
+
+define <vscale x 16 x i16> @intrinsic_vsub_vx_nxv16i16_nxv16i16_i16(<vscale x 16 x i16> %0, i16 %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vsub_vx_nxv16i16_nxv16i16_i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,m4,tu,mu
+; CHECK:       vsub.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 16 x i16> @llvm.riscv.vsub.nxv16i16.i16(
+    <vscale x 16 x i16> %0,
+    i16 %1,
+    i64 %2)
+
+  ret <vscale x 16 x i16> %a
+}
+
+declare <vscale x 16 x i16> @llvm.riscv.vsub.mask.nxv16i16.i16(
+  <vscale x 16 x i16>,
+  <vscale x 16 x i16>,
+  i16,
+  <vscale x 16 x i1>,
+  i64);
+
+define <vscale x 16 x i16> @intrinsic_vsub_mask_vx_nxv16i16_nxv16i16_i16(<vscale x 16 x i16> %0, <vscale x 16 x i16> %1, i16 %2, <vscale x 16 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vsub_mask_vx_nxv16i16_nxv16i16_i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,m4,tu,mu
+; CHECK:       vsub.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 16 x i16> @llvm.riscv.vsub.mask.nxv16i16.i16(
+    <vscale x 16 x i16> %0,
+    <vscale x 16 x i16> %1,
+    i16 %2,
+    <vscale x 16 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 16 x i16> %a
+}
+
+declare <vscale x 32 x i16> @llvm.riscv.vsub.nxv32i16.i16(
+  <vscale x 32 x i16>,
+  i16,
+  i64);
+
+define <vscale x 32 x i16> @intrinsic_vsub_vx_nxv32i16_nxv32i16_i16(<vscale x 32 x i16> %0, i16 %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vsub_vx_nxv32i16_nxv32i16_i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,m8,tu,mu
+; CHECK:       vsub.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 32 x i16> @llvm.riscv.vsub.nxv32i16.i16(
+    <vscale x 32 x i16> %0,
+    i16 %1,
+    i64 %2)
+
+  ret <vscale x 32 x i16> %a
+}
+
+declare <vscale x 32 x i16> @llvm.riscv.vsub.mask.nxv32i16.i16(
+  <vscale x 32 x i16>,
+  <vscale x 32 x i16>,
+  i16,
+  <vscale x 32 x i1>,
+  i64);
+
+define <vscale x 32 x i16> @intrinsic_vsub_mask_vx_nxv32i16_nxv32i16_i16(<vscale x 32 x i16> %0, <vscale x 32 x i16> %1, i16 %2, <vscale x 32 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vsub_mask_vx_nxv32i16_nxv32i16_i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,m8,tu,mu
+; CHECK:       vsub.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 32 x i16> @llvm.riscv.vsub.mask.nxv32i16.i16(
+    <vscale x 32 x i16> %0,
+    <vscale x 32 x i16> %1,
+    i16 %2,
+    <vscale x 32 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 32 x i16> %a
+}
+
+declare <vscale x 1 x i32> @llvm.riscv.vsub.nxv1i32.i32(
+  <vscale x 1 x i32>,
+  i32,
+  i64);
+
+define <vscale x 1 x i32> @intrinsic_vsub_vx_nxv1i32_nxv1i32_i32(<vscale x 1 x i32> %0, i32 %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vsub_vx_nxv1i32_nxv1i32_i32
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e32,mf2,tu,mu
+; CHECK:       vsub.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 1 x i32> @llvm.riscv.vsub.nxv1i32.i32(
+    <vscale x 1 x i32> %0,
+    i32 %1,
+    i64 %2)
+
+  ret <vscale x 1 x i32> %a
+}
+
+declare <vscale x 1 x i32> @llvm.riscv.vsub.mask.nxv1i32.i32(
+  <vscale x 1 x i32>,
+  <vscale x 1 x i32>,
+  i32,
+  <vscale x 1 x i1>,
+  i64);
+
+define <vscale x 1 x i32> @intrinsic_vsub_mask_vx_nxv1i32_nxv1i32_i32(<vscale x 1 x i32> %0, <vscale x 1 x i32> %1, i32 %2, <vscale x 1 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vsub_mask_vx_nxv1i32_nxv1i32_i32
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e32,mf2,tu,mu
+; CHECK:       vsub.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 1 x i32> @llvm.riscv.vsub.mask.nxv1i32.i32(
+    <vscale x 1 x i32> %0,
+    <vscale x 1 x i32> %1,
+    i32 %2,
+    <vscale x 1 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 1 x i32> %a
+}
+
+declare <vscale x 2 x i32> @llvm.riscv.vsub.nxv2i32.i32(
+  <vscale x 2 x i32>,
+  i32,
+  i64);
+
+define <vscale x 2 x i32> @intrinsic_vsub_vx_nxv2i32_nxv2i32_i32(<vscale x 2 x i32> %0, i32 %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vsub_vx_nxv2i32_nxv2i32_i32
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e32,m1,tu,mu
+; CHECK:       vsub.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 2 x i32> @llvm.riscv.vsub.nxv2i32.i32(
+    <vscale x 2 x i32> %0,
+    i32 %1,
+    i64 %2)
+
+  ret <vscale x 2 x i32> %a
+}
+
+declare <vscale x 2 x i32> @llvm.riscv.vsub.mask.nxv2i32.i32(
+  <vscale x 2 x i32>,
+  <vscale x 2 x i32>,
+  i32,
+  <vscale x 2 x i1>,
+  i64);
+
+define <vscale x 2 x i32> @intrinsic_vsub_mask_vx_nxv2i32_nxv2i32_i32(<vscale x 2 x i32> %0, <vscale x 2 x i32> %1, i32 %2, <vscale x 2 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vsub_mask_vx_nxv2i32_nxv2i32_i32
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e32,m1,tu,mu
+; CHECK:       vsub.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 2 x i32> @llvm.riscv.vsub.mask.nxv2i32.i32(
+    <vscale x 2 x i32> %0,
+    <vscale x 2 x i32> %1,
+    i32 %2,
+    <vscale x 2 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 2 x i32> %a
+}
+
+declare <vscale x 4 x i32> @llvm.riscv.vsub.nxv4i32.i32(
+  <vscale x 4 x i32>,
+  i32,
+  i64);
+
+define <vscale x 4 x i32> @intrinsic_vsub_vx_nxv4i32_nxv4i32_i32(<vscale x 4 x i32> %0, i32 %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vsub_vx_nxv4i32_nxv4i32_i32
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e32,m2,tu,mu
+; CHECK:       vsub.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 4 x i32> @llvm.riscv.vsub.nxv4i32.i32(
+    <vscale x 4 x i32> %0,
+    i32 %1,
+    i64 %2)
+
+  ret <vscale x 4 x i32> %a
+}
+
+declare <vscale x 4 x i32> @llvm.riscv.vsub.mask.nxv4i32.i32(
+  <vscale x 4 x i32>,
+  <vscale x 4 x i32>,
+  i32,
+  <vscale x 4 x i1>,
+  i64);
+
+define <vscale x 4 x i32> @intrinsic_vsub_mask_vx_nxv4i32_nxv4i32_i32(<vscale x 4 x i32> %0, <vscale x 4 x i32> %1, i32 %2, <vscale x 4 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vsub_mask_vx_nxv4i32_nxv4i32_i32
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e32,m2,tu,mu
+; CHECK:       vsub.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 4 x i32> @llvm.riscv.vsub.mask.nxv4i32.i32(
+    <vscale x 4 x i32> %0,
+    <vscale x 4 x i32> %1,
+    i32 %2,
+    <vscale x 4 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 4 x i32> %a
+}
+
+declare <vscale x 8 x i32> @llvm.riscv.vsub.nxv8i32.i32(
+  <vscale x 8 x i32>,
+  i32,
+  i64);
+
+define <vscale x 8 x i32> @intrinsic_vsub_vx_nxv8i32_nxv8i32_i32(<vscale x 8 x i32> %0, i32 %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vsub_vx_nxv8i32_nxv8i32_i32
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e32,m4,tu,mu
+; CHECK:       vsub.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 8 x i32> @llvm.riscv.vsub.nxv8i32.i32(
+    <vscale x 8 x i32> %0,
+    i32 %1,
+    i64 %2)
+
+  ret <vscale x 8 x i32> %a
+}
+
+declare <vscale x 8 x i32> @llvm.riscv.vsub.mask.nxv8i32.i32(
+  <vscale x 8 x i32>,
+  <vscale x 8 x i32>,
+  i32,
+  <vscale x 8 x i1>,
+  i64);
+
+define <vscale x 8 x i32> @intrinsic_vsub_mask_vx_nxv8i32_nxv8i32_i32(<vscale x 8 x i32> %0, <vscale x 8 x i32> %1, i32 %2, <vscale x 8 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vsub_mask_vx_nxv8i32_nxv8i32_i32
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e32,m4,tu,mu
+; CHECK:       vsub.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 8 x i32> @llvm.riscv.vsub.mask.nxv8i32.i32(
+    <vscale x 8 x i32> %0,
+    <vscale x 8 x i32> %1,
+    i32 %2,
+    <vscale x 8 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 8 x i32> %a
+}
+
+declare <vscale x 16 x i32> @llvm.riscv.vsub.nxv16i32.i32(
+  <vscale x 16 x i32>,
+  i32,
+  i64);
+
+define <vscale x 16 x i32> @intrinsic_vsub_vx_nxv16i32_nxv16i32_i32(<vscale x 16 x i32> %0, i32 %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vsub_vx_nxv16i32_nxv16i32_i32
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e32,m8,tu,mu
+; CHECK:       vsub.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 16 x i32> @llvm.riscv.vsub.nxv16i32.i32(
+    <vscale x 16 x i32> %0,
+    i32 %1,
+    i64 %2)
+
+  ret <vscale x 16 x i32> %a
+}
+
+declare <vscale x 16 x i32> @llvm.riscv.vsub.mask.nxv16i32.i32(
+  <vscale x 16 x i32>,
+  <vscale x 16 x i32>,
+  i32,
+  <vscale x 16 x i1>,
+  i64);
+
+define <vscale x 16 x i32> @intrinsic_vsub_mask_vx_nxv16i32_nxv16i32_i32(<vscale x 16 x i32> %0, <vscale x 16 x i32> %1, i32 %2, <vscale x 16 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vsub_mask_vx_nxv16i32_nxv16i32_i32
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e32,m8,tu,mu
+; CHECK:       vsub.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 16 x i32> @llvm.riscv.vsub.mask.nxv16i32.i32(
+    <vscale x 16 x i32> %0,
+    <vscale x 16 x i32> %1,
+    i32 %2,
+    <vscale x 16 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 16 x i32> %a
+}
+
+declare <vscale x 1 x i64> @llvm.riscv.vsub.nxv1i64.i64(
+  <vscale x 1 x i64>,
+  i64,
+  i64);
+
+define <vscale x 1 x i64> @intrinsic_vsub_vx_nxv1i64_nxv1i64_i64(<vscale x 1 x i64> %0, i64 %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vsub_vx_nxv1i64_nxv1i64_i64
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e64,m1,tu,mu
+; CHECK:       vsub.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 1 x i64> @llvm.riscv.vsub.nxv1i64.i64(
+    <vscale x 1 x i64> %0,
+    i64 %1,
+    i64 %2)
+
+  ret <vscale x 1 x i64> %a
+}
+
+declare <vscale x 1 x i64> @llvm.riscv.vsub.mask.nxv1i64.i64(
+  <vscale x 1 x i64>,
+  <vscale x 1 x i64>,
+  i64,
+  <vscale x 1 x i1>,
+  i64);
+
+define <vscale x 1 x i64> @intrinsic_vsub_mask_vx_nxv1i64_nxv1i64_i64(<vscale x 1 x i64> %0, <vscale x 1 x i64> %1, i64 %2, <vscale x 1 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vsub_mask_vx_nxv1i64_nxv1i64_i64
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e64,m1,tu,mu
+; CHECK:       vsub.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 1 x i64> @llvm.riscv.vsub.mask.nxv1i64.i64(
+    <vscale x 1 x i64> %0,
+    <vscale x 1 x i64> %1,
+    i64 %2,
+    <vscale x 1 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 1 x i64> %a
+}
+
+declare <vscale x 2 x i64> @llvm.riscv.vsub.nxv2i64.i64(
+  <vscale x 2 x i64>,
+  i64,
+  i64);
+
+define <vscale x 2 x i64> @intrinsic_vsub_vx_nxv2i64_nxv2i64_i64(<vscale x 2 x i64> %0, i64 %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vsub_vx_nxv2i64_nxv2i64_i64
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e64,m2,tu,mu
+; CHECK:       vsub.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 2 x i64> @llvm.riscv.vsub.nxv2i64.i64(
+    <vscale x 2 x i64> %0,
+    i64 %1,
+    i64 %2)
+
+  ret <vscale x 2 x i64> %a
+}
+
+declare <vscale x 2 x i64> @llvm.riscv.vsub.mask.nxv2i64.i64(
+  <vscale x 2 x i64>,
+  <vscale x 2 x i64>,
+  i64,
+  <vscale x 2 x i1>,
+  i64);
+
+define <vscale x 2 x i64> @intrinsic_vsub_mask_vx_nxv2i64_nxv2i64_i64(<vscale x 2 x i64> %0, <vscale x 2 x i64> %1, i64 %2, <vscale x 2 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vsub_mask_vx_nxv2i64_nxv2i64_i64
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e64,m2,tu,mu
+; CHECK:       vsub.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 2 x i64> @llvm.riscv.vsub.mask.nxv2i64.i64(
+    <vscale x 2 x i64> %0,
+    <vscale x 2 x i64> %1,
+    i64 %2,
+    <vscale x 2 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 2 x i64> %a
+}
+
+declare <vscale x 4 x i64> @llvm.riscv.vsub.nxv4i64.i64(
+  <vscale x 4 x i64>,
+  i64,
+  i64);
+
+define <vscale x 4 x i64> @intrinsic_vsub_vx_nxv4i64_nxv4i64_i64(<vscale x 4 x i64> %0, i64 %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vsub_vx_nxv4i64_nxv4i64_i64
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e64,m4,tu,mu
+; CHECK:       vsub.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 4 x i64> @llvm.riscv.vsub.nxv4i64.i64(
+    <vscale x 4 x i64> %0,
+    i64 %1,
+    i64 %2)
+
+  ret <vscale x 4 x i64> %a
+}
+
+declare <vscale x 4 x i64> @llvm.riscv.vsub.mask.nxv4i64.i64(
+  <vscale x 4 x i64>,
+  <vscale x 4 x i64>,
+  i64,
+  <vscale x 4 x i1>,
+  i64);
+
+define <vscale x 4 x i64> @intrinsic_vsub_mask_vx_nxv4i64_nxv4i64_i64(<vscale x 4 x i64> %0, <vscale x 4 x i64> %1, i64 %2, <vscale x 4 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vsub_mask_vx_nxv4i64_nxv4i64_i64
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e64,m4,tu,mu
+; CHECK:       vsub.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 4 x i64> @llvm.riscv.vsub.mask.nxv4i64.i64(
+    <vscale x 4 x i64> %0,
+    <vscale x 4 x i64> %1,
+    i64 %2,
+    <vscale x 4 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 4 x i64> %a
+}
+
+declare <vscale x 8 x i64> @llvm.riscv.vsub.nxv8i64.i64(
+  <vscale x 8 x i64>,
+  i64,
+  i64);
+
+define <vscale x 8 x i64> @intrinsic_vsub_vx_nxv8i64_nxv8i64_i64(<vscale x 8 x i64> %0, i64 %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vsub_vx_nxv8i64_nxv8i64_i64
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e64,m8,tu,mu
+; CHECK:       vsub.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 8 x i64> @llvm.riscv.vsub.nxv8i64.i64(
+    <vscale x 8 x i64> %0,
+    i64 %1,
+    i64 %2)
+
+  ret <vscale x 8 x i64> %a
+}
+
+declare <vscale x 8 x i64> @llvm.riscv.vsub.mask.nxv8i64.i64(
+  <vscale x 8 x i64>,
+  <vscale x 8 x i64>,
+  i64,
+  <vscale x 8 x i1>,
+  i64);
+
+define <vscale x 8 x i64> @intrinsic_vsub_mask_vx_nxv8i64_nxv8i64_i64(<vscale x 8 x i64> %0, <vscale x 8 x i64> %1, i64 %2, <vscale x 8 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vsub_mask_vx_nxv8i64_nxv8i64_i64
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e64,m8,tu,mu
+; CHECK:       vsub.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 8 x i64> @llvm.riscv.vsub.mask.nxv8i64.i64(
+    <vscale x 8 x i64> %0,
+    <vscale x 8 x i64> %1,
+    i64 %2,
+    <vscale x 8 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 8 x i64> %a
+}