diff --git a/llvm/include/llvm/IR/IntrinsicsRISCV.td b/llvm/include/llvm/IR/IntrinsicsRISCV.td
--- a/llvm/include/llvm/IR/IntrinsicsRISCV.td
+++ b/llvm/include/llvm/IR/IntrinsicsRISCV.td
@@ -604,6 +604,17 @@
   }
   // For Saturating binary operations.
   // The destination vector type is the same as first source vector.
+  // Input: (passthru, vector_in, vector_in/scalar_in, vl, vxrm)
+  class RISCVSaturatingBinaryRMAAXNoMask
+        : Intrinsic<[llvm_anyvector_ty],
+                    [LLVMMatchType<0>, LLVMMatchType<0>, llvm_any_ty,
+                     llvm_anyint_ty, LLVMMatchType<2>],
+                    [ImmArg<ArgIndex<4>>, IntrNoMem]>, RISCVVIntrinsic {
+    let SplatOperand = 2;
+    let VLOperand = 3;
+  }
+  // For Saturating binary operations.
+  // The destination vector type is the same as first source vector.
   // Input: (passthru, vector_in, vector_in/scalar_in, vl)
   class RISCVSaturatingBinaryAAXNoMask
         : Intrinsic<[llvm_anyvector_ty],
@@ -625,6 +636,18 @@
     let SplatOperand = 2;
     let VLOperand = 4;
   }
+  // For Saturating binary operations with mask.
+  // The destination vector type is the same as first source vector.
+  // Input: (maskedoff, vector_in, vector_in/scalar_in, mask, vl, policy, vxrm)
+  class RISCVSaturatingBinaryRMAAXMask
+        : Intrinsic<[llvm_anyvector_ty],
+                    [LLVMMatchType<0>, LLVMMatchType<0>, llvm_any_ty,
+                     LLVMScalarOrSameVectorWidth<0, llvm_i1_ty>, llvm_anyint_ty,
+                     LLVMMatchType<2>, LLVMMatchType<2>],
+                    [ImmArg<ArgIndex<5>>, ImmArg<ArgIndex<6>>, IntrNoMem]>, RISCVVIntrinsic {
+    let SplatOperand = 2;
+    let VLOperand = 4;
+  }
   // For Saturating binary operations.
   // The destination vector type is the same as first source vector.
   // The second source operand matches the destination type or is an XLen scalar.
@@ -1087,6 +1110,10 @@
   multiclass RISCVBinaryMaskOut {
     def "int_riscv_" # NAME : RISCVBinaryMOut;
   }
+  multiclass RISCVSaturatingBinaryRMAAX {
+    def "int_riscv_" # NAME : RISCVSaturatingBinaryRMAAXNoMask;
+    def "int_riscv_" # NAME # "_mask" : RISCVSaturatingBinaryRMAAXMask;
+  }
   multiclass RISCVSaturatingBinaryAAX {
     def "int_riscv_" # NAME : RISCVSaturatingBinaryAAXNoMask;
     def "int_riscv_" # NAME # "_mask" : RISCVSaturatingBinaryAAXMask;
@@ -1372,6 +1399,7 @@
 
   defm vaaddu : RISCVSaturatingBinaryAAX;
   defm vaadd : RISCVSaturatingBinaryAAX;
+  defm vaadd_rm : RISCVSaturatingBinaryRMAAX;
   defm vasubu : RISCVSaturatingBinaryAAX;
   defm vasub : RISCVSaturatingBinaryAAX;
 
diff --git a/llvm/lib/Target/RISCV/CMakeLists.txt b/llvm/lib/Target/RISCV/CMakeLists.txt
--- a/llvm/lib/Target/RISCV/CMakeLists.txt
+++ b/llvm/lib/Target/RISCV/CMakeLists.txt
@@ -26,6 +26,7 @@
   RISCVFrameLowering.cpp
   RISCVGatherScatterLowering.cpp
   RISCVInsertVSETVLI.cpp
+  RISCVVXRMRegister.cpp
   RISCVInstrInfo.cpp
   RISCVInstructionSelector.cpp
   RISCVISelDAGToDAG.cpp
diff --git a/llvm/lib/Target/RISCV/MCTargetDesc/RISCVBaseInfo.h b/llvm/lib/Target/RISCV/MCTargetDesc/RISCVBaseInfo.h
--- a/llvm/lib/Target/RISCV/MCTargetDesc/RISCVBaseInfo.h
+++ b/llvm/lib/Target/RISCV/MCTargetDesc/RISCVBaseInfo.h
@@ -88,6 +88,9 @@
   // Pseudos.
   IsRVVWideningReductionShift = HasVecPolicyOpShift + 1,
   IsRVVWideningReductionMask = 1 << IsRVVWideningReductionShift,
+
+  HasRoundModeOpShift = IsRVVWideningReductionShift + 1,
+  HasRoundModeOpMask = 1 << HasRoundModeOpShift,
 };
 
 // Match with the definitions in RISCVInstrFormatsV.td
@@ -156,7 +159,9 @@
 static inline bool isRVVWideningReduction(uint64_t TSFlags) {
   return TSFlags & IsRVVWideningReductionMask;
 }
-
+static inline bool hasRoundModeOp(uint64_t TSFlags) {
+  return TSFlags & HasRoundModeOpMask;
+}
 // RISC-V Specific Machine Operand Flags
 enum {
   MO_None = 0,
@@ -268,6 +273,17 @@
 }
 } // namespace RISCVFPRndMode
 
+namespace RISCVVXRndMode {
+enum RoundingMode {
+  RNU = 0,
+  RNE = 1,
+  RDN = 2,
+  ROD = 3,
+  DYN = 4,
+};
+
+} // namespace RISCVVXRndMode
+
 namespace RISCVSysReg {
 struct SysReg {
   const char *Name;
diff --git a/llvm/lib/Target/RISCV/RISCV.h b/llvm/lib/Target/RISCV/RISCV.h
--- a/llvm/lib/Target/RISCV/RISCV.h
+++ b/llvm/lib/Target/RISCV/RISCV.h
@@ -55,6 +55,9 @@
 FunctionPass *createRISCVInsertVSETVLIPass();
 void initializeRISCVInsertVSETVLIPass(PassRegistry &);
 
+FunctionPass *createRISCVVXRMRegisterPass();
+void initializeRISCVVXRMRegisterPass(PassRegistry &);
+
 FunctionPass *createRISCVRedundantCopyEliminationPass();
 void initializeRISCVRedundantCopyEliminationPass(PassRegistry &);
 
diff --git a/llvm/lib/Target/RISCV/RISCVInstrFormats.td b/llvm/lib/Target/RISCV/RISCVInstrFormats.td
--- a/llvm/lib/Target/RISCV/RISCVInstrFormats.td
+++ b/llvm/lib/Target/RISCV/RISCVInstrFormats.td
@@ -197,6 +197,9 @@
 
   bit IsRVVWideningReduction = 0;
   let TSFlags{17} =  IsRVVWideningReduction;
+
+  bit HasRoundModeOp = 0;
+  let TSFlags{18} =  HasRoundModeOp;
 }
 
 // Pseudo instructions
diff --git a/llvm/lib/Target/RISCV/RISCVInstrInfo.td b/llvm/lib/Target/RISCV/RISCVInstrInfo.td
--- a/llvm/lib/Target/RISCV/RISCVInstrInfo.td
+++ b/llvm/lib/Target/RISCV/RISCVInstrInfo.td
@@ -1389,6 +1389,11 @@
 def WriteFRM : WriteSysReg<SysRegFRM, [FRM]>;
 def WriteFRMImm : WriteSysRegImm<SysRegFRM, [FRM]>;
 
+def ReadVXRM : ReadSysReg<SysRegVXRM, [VXRM]>;
+def WriteVXRM : WriteSysReg<SysRegVXRM, [VXRM]>;
+def WriteVXRMImm : WriteSysRegImm<SysRegVXRM, [VXRM]>;
+def SwapVXRMImm : SwapSysRegImm<SysRegVXRM, [VXRM]>;
+
 let hasSideEffects = true in {
 def ReadFFLAGS : ReadSysReg<SysRegFFLAGS, [FFLAGS]>;
 def WriteFFLAGS : WriteSysReg<SysRegFFLAGS, [FFLAGS]>;
diff --git a/llvm/lib/Target/RISCV/RISCVInstrInfoVPseudos.td b/llvm/lib/Target/RISCV/RISCVInstrInfoVPseudos.td
--- a/llvm/lib/Target/RISCV/RISCVInstrInfoVPseudos.td
+++ b/llvm/lib/Target/RISCV/RISCVInstrInfoVPseudos.td
@@ -42,6 +42,7 @@
 
 defvar TAIL_UNDISTURBED = 0;
 defvar TAIL_AGNOSTIC = 1;
+defvar VXRM_DYN = 4;
 
 //===----------------------------------------------------------------------===//
 // Utilities.
@@ -1747,6 +1748,29 @@
   }
 }
 
+multiclass VPseudoBinaryRM<VReg RetClass,
+                           VReg Op1Class,
+                           DAGOperand Op2Class,
+                           LMULInfo MInfo,
+                           string Constraint = ""> {
+  let VLMul = MInfo.value, HasRoundModeOp = 1 in {
+    let InOperandList = (ins Op1Class:$rs2, Op2Class:$rs1,
+                             ixlenimm:$rm, AVL:$vl, ixlenimm:$sew) in
+    def "_" # MInfo.MX : VPseudoBinaryNoMask<RetClass, Op1Class, Op2Class,
+                                             Constraint>;
+    let InOperandList = (ins RetClass:$merge, Op1Class:$rs2, Op2Class:$rs1,
+                             ixlenimm:$rm, AVL:$vl, ixlenimm:$sew) in
+    def "_" # MInfo.MX # "_TU" : VPseudoBinaryNoMaskTU<RetClass, Op1Class, Op2Class,
+                                                       Constraint>;
+    let InOperandList = (ins GetVRegNoV0<RetClass>.R:$merge,
+                             Op1Class:$rs2, Op2Class:$rs1,
+                             VMaskOp:$vm, ixlenimm:$rm, AVL:$vl, ixlenimm:$sew, ixlenimm:$policy) in
+    def "_" # MInfo.MX # "_MASK" : VPseudoBinaryMaskPolicy<RetClass, Op1Class, Op2Class,
+                                                           Constraint>,
+                                   RISCVMaskedPseudo</*MaskOpIdx*/ 3>;
+  }
+}
+
 multiclass VPseudoBinaryM<VReg RetClass,
                           VReg Op1Class,
                           DAGOperand Op2Class,
@@ -1796,6 +1820,11 @@
     defm _VV : VPseudoBinary<m.vrclass, m.vrclass, m.vrclass, m, Constraint>;
 }
 
+multiclass VPseudoBinaryRM_V_VV<string Constraint = ""> {
+  foreach m = MxList in
+    defm _VV : VPseudoBinaryRM<m.vrclass, m.vrclass, m.vrclass, m, Constraint>;
+}
+
 // Similar to VPseudoBinaryV_VV, but uses MxListF.
 multiclass VPseudoBinaryFV_VV<string Constraint = ""> {
   foreach m = MxListF in
@@ -1823,6 +1852,11 @@
     defm "_VX" : VPseudoBinary<m.vrclass, m.vrclass, GPR, m, Constraint>;
 }
 
+multiclass VPseudoBinaryRM_V_VX<string Constraint = ""> {
+  foreach m = MxList in
+    defm "_VX" : VPseudoBinaryRM<m.vrclass, m.vrclass, GPR, m, Constraint>;
+}
+
 multiclass VPseudoVSLD1_VX<string Constraint = ""> {
   foreach m = MxList in
     defm "_VX" : VPseudoBinary<m.vrclass, m.vrclass, GPR, m, Constraint>,
@@ -2232,6 +2266,13 @@
             Sched<[WriteVAALUX, ReadVAALUV, ReadVAALUX, ReadVMask]>;
 }
 
+multiclass VPseudoVAALU_RM_VV_VX {
+  defm "" : VPseudoBinaryRM_V_VV,
+            Sched<[WriteVAALUV, ReadVAALUV, ReadVAALUV, ReadVMask]>;
+  defm "" : VPseudoBinaryRM_V_VX,
+            Sched<[WriteVAALUX, ReadVAALUV, ReadVAALUX, ReadVMask]>;
+}
+
 multiclass VPseudoVMINMAX_VV_VX {
   defm "" : VPseudoBinaryV_VV,
             Sched<[WriteVICmpV, ReadVICmpV, ReadVICmpV, ReadVMask]>;
@@ -3001,6 +3042,35 @@
                    (op2_type op2_kind:$rs2),
                    GPR:$vl, sew)>;
 
+multiclass VPatBinaryRMNoMaskTA<string intrinsic_name,
+                                string inst,
+                                ValueType result_type,
+                                ValueType op1_type,
+                                ValueType op2_type,
+                                int sew,
+                                VReg op1_reg_class,
+                                DAGOperand op2_kind> {
+  def : Pat<(result_type (!cast<Intrinsic>(intrinsic_name)
+                   (result_type (undef)),
+                   (op1_type op1_reg_class:$rs1),
+                   (op2_type op2_kind:$rs2),
+                   VLOpFrag)),
+            (!cast<Instruction>(inst)
+                   (op1_type op1_reg_class:$rs1),
+                   (op2_type op2_kind:$rs2),
+                   (XLenVT VXRM_DYN), GPR:$vl, sew)>;
+  def : Pat<(result_type (!cast<Intrinsic>(intrinsic_name # "_rm")
+                   (result_type (undef)),
+                   (op1_type op1_reg_class:$rs1),
+                   (op2_type op2_kind:$rs2),
+                   VLOpFrag,
+                   (XLenVT timm:$round))),
+            (!cast<Instruction>(inst)
+                   (op1_type op1_reg_class:$rs1),
+                   (op2_type op2_kind:$rs2),
+                   (XLenVT timm:$round), GPR:$vl, sew)>;
+}
+
 class VPatBinaryNoMaskTU<string intrinsic_name,
                          string inst,
                          ValueType result_type,
@@ -3021,6 +3091,38 @@
                    (op2_type op2_kind:$rs2),
                    GPR:$vl, sew)>;
 
+multiclass VPatBinaryRMNoMaskTU<string intrinsic_name,
+                                string inst,
+                                ValueType result_type,
+                                ValueType op1_type,
+                                ValueType op2_type,
+                                int sew,
+                                VReg result_reg_class,
+                                VReg op1_reg_class,
+                                DAGOperand op2_kind> {
+  def : Pat<(result_type (!cast<Intrinsic>(intrinsic_name)
+                   (result_type result_reg_class:$merge),
+                   (op1_type op1_reg_class:$rs1),
+                   (op2_type op2_kind:$rs2),
+                   VLOpFrag)),
+            (!cast<Instruction>(inst#"_TU")
+                   (result_type result_reg_class:$merge),
+                   (op1_type op1_reg_class:$rs1),
+                   (op2_type op2_kind:$rs2),
+                   (XLenVT VXRM_DYN), GPR:$vl, sew)>;
+  def : Pat<(result_type (!cast<Intrinsic>(intrinsic_name # "_rm")
+                   (result_type result_reg_class:$merge),
+                   (op1_type op1_reg_class:$rs1),
+                   (op2_type op2_kind:$rs2),
+                   VLOpFrag,
+                   (XLenVT timm:$round))),
+            (!cast<Instruction>(inst#"_TU")
+                   (result_type result_reg_class:$merge),
+                   (op1_type op1_reg_class:$rs1),
+                   (op2_type op2_kind:$rs2),
+                   (XLenVT timm:$round), GPR:$vl, sew)>;
+}
+
 // Same as above but source operands are swapped.
 class VPatBinaryNoMaskSwapped<string intrinsic_name,
                               string inst,
@@ -3083,6 +3185,40 @@
                    (op2_type op2_kind:$rs2),
                    (mask_type V0), GPR:$vl, sew, (XLenVT timm:$policy))>;
 
+multiclass VPatBinaryRMMaskTA<string intrinsic_name,
+                         string inst,
+                         ValueType result_type,
+                         ValueType op1_type,
+                         ValueType op2_type,
+                         ValueType mask_type,
+                         int sew,
+                         VReg result_reg_class,
+                         VReg op1_reg_class,
+                         DAGOperand op2_kind> {
+  def : Pat<(result_type (!cast<Intrinsic>(intrinsic_name#"_mask")
+                   (result_type result_reg_class:$merge),
+                   (op1_type op1_reg_class:$rs1),
+                   (op2_type op2_kind:$rs2),
+                   (mask_type V0),
+                   VLOpFrag, (XLenVT timm:$policy))),
+            (!cast<Instruction>(inst#"_MASK")
+                   (result_type result_reg_class:$merge),
+                   (op1_type op1_reg_class:$rs1),
+                   (op2_type op2_kind:$rs2),
+                   (mask_type V0), (XLenVT VXRM_DYN), GPR:$vl, sew, (XLenVT timm:$policy))>;
+  def : Pat<(result_type (!cast<Intrinsic>(intrinsic_name#"_rm_mask")
+                   (result_type result_reg_class:$merge),
+                   (op1_type op1_reg_class:$rs1),
+                   (op2_type op2_kind:$rs2),
+                   (mask_type V0),
+                   VLOpFrag, (XLenVT timm:$policy), (XLenVT timm:$round))),
+            (!cast<Instruction>(inst#"_MASK")
+                   (result_type result_reg_class:$merge),
+                   (op1_type op1_reg_class:$rs1),
+                   (op2_type op2_kind:$rs2),
+                   (mask_type V0), (XLenVT timm:$round), GPR:$vl, sew, (XLenVT timm:$policy))>;
+}
+
 // Same as above but source operands are swapped.
 class VPatBinaryMaskSwapped<string intrinsic_name,
                             string inst,
@@ -3401,6 +3537,26 @@
                          op2_kind>;
 }
 
+multiclass VPatBinaryRMTA<string intrinsic,
+                          string inst,
+                          ValueType result_type,
+                          ValueType op1_type,
+                          ValueType op2_type,
+                          ValueType mask_type,
+                          int sew,
+                          VReg result_reg_class,
+                          VReg op1_reg_class,
+                          DAGOperand op2_kind>
+{
+  defm : VPatBinaryRMNoMaskTA<intrinsic, inst, result_type, op1_type, op2_type,
+                              sew, op1_reg_class, op2_kind>;
+  defm : VPatBinaryRMNoMaskTU<intrinsic, inst, result_type, op1_type, op2_type,
+                              sew, result_reg_class, op1_reg_class, op2_kind>;
+  defm : VPatBinaryRMMaskTA<intrinsic, inst, result_type, op1_type, op2_type,
+                            mask_type, sew, result_reg_class, op1_reg_class,
+                            op2_kind>;
+}
+
 multiclass VPatBinarySwapped<string intrinsic,
                       string inst,
                       ValueType result_type,
@@ -3527,6 +3683,15 @@
                         vti.RegClass, vti.RegClass>;
 }
 
+multiclass VPatBinary_RM_V_VV<string intrinsic, string instruction,
+                              list<VTypeInfo> vtilist> {
+  foreach vti = vtilist in
+    defm : VPatBinaryRMTA<intrinsic, instruction # "_VV_" # vti.LMul.MX,
+                        vti.Vector, vti.Vector, vti.Vector,vti.Mask,
+                        vti.Log2SEW, vti.RegClass,
+                        vti.RegClass, vti.RegClass>;
+}
+
 multiclass VPatBinaryV_VV_INT<string intrinsic, string instruction,
                           list<VTypeInfo> vtilist> {
   foreach vti = vtilist in {
@@ -3568,6 +3733,17 @@
   }
 }
 
+multiclass VPatBinary_RM_V_VX<string intrinsic, string instruction,
+                              list<VTypeInfo> vtilist> {
+  foreach vti = vtilist in {
+    defvar kind = "V"#vti.ScalarSuffix;
+    defm : VPatBinaryRMTA<intrinsic, instruction#"_"#kind#"_"#vti.LMul.MX,
+                          vti.Vector, vti.Vector, vti.Scalar, vti.Mask,
+                          vti.Log2SEW, vti.RegClass,
+                          vti.RegClass, vti.ScalarRegClass>;
+  }
+}
+
 multiclass VPatBinaryV_VX_INT<string intrinsic, string instruction,
                           list<VTypeInfo> vtilist> {
   foreach vti = vtilist in
@@ -3833,6 +4009,11 @@
     : VPatBinaryV_VV<intrinsic, instruction, vtilist>,
       VPatBinaryV_VX<intrinsic, instruction, vtilist>;
 
+multiclass VPatBinaryRM_V_VV_VX<string intrinsic, string instruction,
+                             list<VTypeInfo> vtilist>
+    : VPatBinary_RM_V_VV<intrinsic, instruction, vtilist>,
+      VPatBinary_RM_V_VX<intrinsic, instruction, vtilist>;
+
 multiclass VPatBinaryV_VX_VI<string intrinsic, string instruction,
                              list<VTypeInfo> vtilist>
     : VPatBinaryV_VX<intrinsic, instruction, vtilist>,
@@ -4536,7 +4717,7 @@
 //===----------------------------------------------------------------------===//
 let Uses = [VXRM], hasSideEffects = 1 in {
   defm PseudoVAADDU : VPseudoVAALU_VV_VX;
-  defm PseudoVAADD  : VPseudoVAALU_VV_VX;
+  defm PseudoVAADD  : VPseudoVAALU_RM_VV_VX;
   defm PseudoVASUBU : VPseudoVAALU_VV_VX;
   defm PseudoVASUB  : VPseudoVAALU_VV_VX;
 }
@@ -5141,7 +5322,7 @@
 // 13.2. Vector Single-Width Averaging Add and Subtract
 //===----------------------------------------------------------------------===//
 defm : VPatBinaryV_VV_VX<"int_riscv_vaaddu", "PseudoVAADDU", AllIntegerVectors>;
-defm : VPatBinaryV_VV_VX<"int_riscv_vaadd", "PseudoVAADD", AllIntegerVectors>;
+defm : VPatBinaryRM_V_VV_VX<"int_riscv_vaadd", "PseudoVAADD", AllIntegerVectors>;
 defm : VPatBinaryV_VV_VX<"int_riscv_vasubu", "PseudoVASUBU", AllIntegerVectors>;
 defm : VPatBinaryV_VV_VX<"int_riscv_vasub", "PseudoVASUB", AllIntegerVectors>;
 
diff --git a/llvm/lib/Target/RISCV/RISCVMCInstLower.cpp b/llvm/lib/Target/RISCV/RISCVMCInstLower.cpp
--- a/llvm/lib/Target/RISCV/RISCVMCInstLower.cpp
+++ b/llvm/lib/Target/RISCV/RISCVMCInstLower.cpp
@@ -155,6 +155,8 @@
     --NumOps;
   if (RISCVII::hasVLOp(TSFlags))
     --NumOps;
+  if (RISCVII::hasRoundModeOp(TSFlags))
+    --NumOps;
   if (RISCVII::hasSEWOp(TSFlags))
     --NumOps;
 
diff --git a/llvm/lib/Target/RISCV/RISCVSystemOperands.td b/llvm/lib/Target/RISCV/RISCVSystemOperands.td
--- a/llvm/lib/Target/RISCV/RISCVSystemOperands.td
+++ b/llvm/lib/Target/RISCV/RISCVSystemOperands.td
@@ -350,7 +350,7 @@
 //===----------------------------------------------------------------------===//
 def : SysReg<"vstart", 0x008>;
 def : SysReg<"vxsat", 0x009>;
-def : SysReg<"vxrm", 0x00A>;
+def SysRegVXRM : SysReg<"vxrm", 0x00A>;
 def : SysReg<"vcsr", 0x00F>;
 def : SysReg<"vl", 0xC20>;
 def : SysReg<"vtype", 0xC21>;
diff --git a/llvm/lib/Target/RISCV/RISCVTargetMachine.cpp b/llvm/lib/Target/RISCV/RISCVTargetMachine.cpp
--- a/llvm/lib/Target/RISCV/RISCVTargetMachine.cpp
+++ b/llvm/lib/Target/RISCV/RISCVTargetMachine.cpp
@@ -47,6 +47,7 @@
   initializeRISCVSExtWRemovalPass(*PR);
   initializeRISCVExpandPseudoPass(*PR);
   initializeRISCVInsertVSETVLIPass(*PR);
+  initializeRISCVVXRMRegisterPass(*PR);
 }
 
 static StringRef computeDataLayout(const Triple &TT) {
@@ -213,6 +214,7 @@
   if (TM->getOptLevel() != CodeGenOpt::None)
     addPass(createRISCVMergeBaseOffsetOptPass());
   addPass(createRISCVInsertVSETVLIPass());
+  addPass(createRISCVVXRMRegisterPass());
 }
 
 void RISCVPassConfig::addPostRegAlloc() {
diff --git a/llvm/lib/Target/RISCV/RISCVVXRMRegister.cpp b/llvm/lib/Target/RISCV/RISCVVXRMRegister.cpp
new file mode 100644
--- /dev/null
+++ b/llvm/lib/Target/RISCV/RISCVVXRMRegister.cpp
@@ -0,0 +1,172 @@
+//===- RISCVVXRMRegister.cpp - Insert WriteVXRM instructions
+//---------------===//
+//
+// 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 implements a function pass that inserts SwapVXRM/WriteVXRM
+// instructions where needed.
+//
+// The pass consists of a single pass over each basici block looking for VXRM
+// usage that requires a WriteVXRM to be inserted.
+//
+// Since ABI doesn't specify if VXRM is required to be preserved by calls for
+// the moment, to be defensive in current state we always keep the incoming VXRM
+// value from predecessors and calls and use it when the RoundModeOperand is
+// specified as RISCVVXRndMode::DYN.
+//
+// This can be enhanced later if the ABI specify it is volatile across calls.
+//
+// TODO: Future enhancements to this pass will take into account VXRM from
+// predecessors.
+//
+//===----------------------------------------------------------------------===//
+
+#include "RISCV.h"
+#include "RISCVSubtarget.h"
+#include "llvm/CodeGen/MachineFunctionPass.h"
+using namespace llvm;
+
+#define DEBUG_TYPE "riscv-insert-writevxrm"
+#define RISCV_INSERT_WRITEVXRM_NAME "RISCV Insert required VXRM values"
+namespace {
+
+class RISCVVXRMRegister : public MachineFunctionPass {
+  const TargetInstrInfo *TII;
+  MachineRegisterInfo *MRI;
+
+public:
+  static char ID;
+
+  RISCVVXRMRegister() : MachineFunctionPass(ID) {
+    initializeRISCVVXRMRegisterPass(*PassRegistry::getPassRegistry());
+  }
+  bool runOnMachineFunction(MachineFunction &MF) override;
+
+  void getAnalysisUsage(AnalysisUsage &AU) const override {
+    AU.setPreservesCFG();
+    MachineFunctionPass::getAnalysisUsage(AU);
+  }
+
+  StringRef getPassName() const override { return RISCV_INSERT_WRITEVXRM_NAME; }
+
+private:
+  bool emitWriteVXRM(MachineBasicBlock &MBB);
+  bool hasVXRMInfo(const MachineInstr &MI, unsigned &VXRMInfo) const;
+};
+
+} // end anonymous namespace
+
+char RISCVVXRMRegister::ID = 0;
+
+INITIALIZE_PASS(RISCVVXRMRegister, DEBUG_TYPE, RISCV_INSERT_WRITEVXRM_NAME,
+                false, false)
+
+bool RISCVVXRMRegister::hasVXRMInfo(const MachineInstr &MI,
+                                    unsigned &NewInfo) const {
+  uint64_t TSFlags = MI.getDesc().TSFlags;
+  bool HasRoundModeOp = RISCVII::hasRoundModeOp(TSFlags);
+
+  if (HasRoundModeOp) {
+    unsigned NumOperands = MI.getNumExplicitOperands();
+    bool HasPolicy = RISCVII::hasVecPolicyOp(TSFlags);
+    if (HasPolicy)
+      --NumOperands;
+    const MachineOperand &RoundModeOp = MI.getOperand(NumOperands - 3);
+
+    NewInfo = RoundModeOp.getImm() & 0x7;
+  }
+  return HasRoundModeOp;
+}
+
+bool RISCVVXRMRegister::emitWriteVXRM(MachineBasicBlock &MBB) {
+  bool MadeChange = false;
+
+  // To be defensive we keep the incoming VXRM value when round mode is changed
+  // from RISCVVXRndMode::DYN
+  Register SavedVXRMReg = 0;
+
+  // For now predecessor state is unknown, we use RISCVVXRndMode::DYN to
+  // represent the incoming VXRM value
+  unsigned CurVXRMImm = RISCVVXRndMode::DYN;
+  for (MachineInstr &MI : MBB) {
+    if (!MI.readsRegister(RISCV::VXRM) && !MI.isCall() && !MI.isInlineAsm())
+      continue;
+
+    unsigned NewVXRMImm;
+    if (hasVXRMInfo(MI, NewVXRMImm)) {
+      if (NewVXRMImm == CurVXRMImm)
+        continue;
+
+      // If the current mode doesn't meet the requirement, we need to insert
+      // WriteVXRM
+
+      if (CurVXRMImm == RISCVVXRndMode::DYN) {
+        assert(SavedVXRMReg == 0);
+        SavedVXRMReg = MRI->createVirtualRegister(&RISCV::GPRRegClass);
+        BuildMI(MBB, MI, MI.getDebugLoc(), TII->get(RISCV::SwapVXRMImm),
+                SavedVXRMReg)
+            .addImm(NewVXRMImm);
+        CurVXRMImm = NewVXRMImm;
+        MadeChange = true;
+        continue;
+      } else if (NewVXRMImm != RISCVVXRndMode::DYN) {
+        BuildMI(MBB, MI, MI.getDebugLoc(), TII->get(RISCV::WriteVXRMImm))
+            .addImm(NewVXRMImm);
+        CurVXRMImm = NewVXRMImm;
+        continue;
+      }
+    }
+
+    if (CurVXRMImm == RISCVVXRndMode::DYN)
+      continue;
+
+    // Here handles Calls, Terminator, InlineAsm, and all ops
+    // which depend on saved VXRM
+
+    assert(SavedVXRMReg);
+    BuildMI(MBB, MI, MI.getDebugLoc(), TII->get(RISCV::WriteVXRM))
+        .addReg(SavedVXRMReg);
+
+    SavedVXRMReg = 0;
+    CurVXRMImm = RISCVVXRndMode::DYN;
+  }
+
+  // Restore VXRM to previous saved value before leaving the block
+  if (SavedVXRMReg) {
+    MachineInstr &MI = MBB.back();
+    if (MI.isTerminator()) {
+      BuildMI(MBB, MI, MI.getDebugLoc(), TII->get(RISCV::WriteVXRM))
+          .addReg(SavedVXRMReg);
+    } else {
+      BuildMI(&MBB, MBB.back().getDebugLoc(), TII->get(RISCV::WriteVXRM))
+          .addReg(SavedVXRMReg);
+    }
+  }
+
+  return MadeChange;
+}
+
+bool RISCVVXRMRegister::runOnMachineFunction(MachineFunction &MF) {
+  // Skip if the vector extension is not enabled.
+  const RISCVSubtarget &ST = MF.getSubtarget<RISCVSubtarget>();
+  if (!ST.hasVInstructions())
+    return false;
+
+  TII = ST.getInstrInfo();
+  MRI = &MF.getRegInfo();
+
+  bool Changed = false;
+
+  for (MachineBasicBlock &MBB : MF)
+    Changed |= emitWriteVXRM(MBB);
+
+  return Changed;
+}
+
+FunctionPass *llvm::createRISCVVXRMRegisterPass() {
+  return new RISCVVXRMRegister();
+}
diff --git a/llvm/test/CodeGen/RISCV/rvv/roundmode-insert.ll b/llvm/test/CodeGen/RISCV/rvv/roundmode-insert.ll
new file mode 100644
--- /dev/null
+++ b/llvm/test/CodeGen/RISCV/rvv/roundmode-insert.ll
@@ -0,0 +1,37 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc -mtriple=riscv64 -mattr=+v -verify-machineinstrs < %s | FileCheck %s
+
+declare <vscale x 1 x i8> @llvm.riscv.vaadd.rm.nxv1i8.nxv1i8(
+  <vscale x 1 x i8>,
+  <vscale x 1 x i8>,
+  <vscale x 1 x i8>,
+  i64,
+  i64);
+
+; test1(A, B, C, vl) = ((A + B) / 2 + C + 1) / 2
+define <vscale x 1 x i8> @test1(<vscale x 1 x i8> %0, <vscale x 1 x i8> %1, <vscale x 1 x i8> %2, i64 %3) nounwind {
+; CHECK-LABEL: test1:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, mf8, ta, mu
+; CHECK-NEXT:    csrrwi a0, vxrm, 2
+; CHECK-NEXT:    vaadd.vv v8, v8, v9
+; CHECK-NEXT:    csrwi vxrm, 0
+; CHECK-NEXT:    vaadd.vv v8, v8, v10
+; CHECK-NEXT:    csrw vxrm, a0
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i8> @llvm.riscv.vaadd.rm.nxv1i8.nxv1i8(
+    <vscale x 1 x i8> undef,
+    <vscale x 1 x i8> %0,
+    <vscale x 1 x i8> %1,
+    i64 %3,
+    i64 2)
+  %res = call <vscale x 1 x i8> @llvm.riscv.vaadd.rm.nxv1i8.nxv1i8(
+    <vscale x 1 x i8> undef,
+    <vscale x 1 x i8> %a,
+    <vscale x 1 x i8> %2,
+    i64 %3,
+    i64 0)
+
+  ret <vscale x 1 x i8> %res
+}
diff --git a/llvm/test/CodeGen/RISCV/rvv/roundmode-insert.mir b/llvm/test/CodeGen/RISCV/rvv/roundmode-insert.mir
new file mode 100644
--- /dev/null
+++ b/llvm/test/CodeGen/RISCV/rvv/roundmode-insert.mir
@@ -0,0 +1,95 @@
+# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
+# RUN: llc %s -o - -mtriple=riscv64 -mattr=+v -run-pass=riscv-insert-writevxrm | FileCheck %s
+---
+name:  vaadd
+tracksRegLiveness: true
+body: |
+  bb.0.entry:
+    liveins: $v8, $v9, $x10
+
+    ; CHECK-LABEL: name: vaadd
+    ; CHECK: liveins: $v8, $v9, $x10
+    ; CHECK-NEXT: {{  $}}
+    ; CHECK-NEXT: [[COPY:%[0-9]+]]:vr = COPY $v8
+    ; CHECK-NEXT: [[COPY1:%[0-9]+]]:vr = COPY $v9
+    ; CHECK-NEXT: [[COPY2:%[0-9]+]]:gprnox0 = COPY $x10
+    ; CHECK-NEXT: dead $x0 = PseudoVSETVLI [[COPY2]], 69, implicit-def $vl, implicit-def $vtype
+    ; CHECK-NEXT: [[SwapVXRMImm:%[0-9]+]]:gpr = SwapVXRMImm 2, implicit-def $vxrm, implicit $vxrm
+    ; CHECK-NEXT: [[PseudoVAADD_VV_MF8_:%[0-9]+]]:vr = PseudoVAADD_VV_MF8 [[COPY]], [[COPY1]], 2, $noreg, 3, implicit $vxrm, implicit $vl, implicit $vtype
+    ; CHECK-NEXT: $v8 = COPY [[PseudoVAADD_VV_MF8_]]
+    ; CHECK-NEXT: WriteVXRM [[SwapVXRMImm]], implicit-def $vxrm
+    ; CHECK-NEXT: PseudoRET implicit $v8
+    %0:vr = COPY $v8
+    %1:vr = COPY $v9
+    %2:gprnox0 = COPY $x10
+    dead $x0 = PseudoVSETVLI %2:gprnox0, 69, implicit-def $vl, implicit-def $vtype
+    %3:vr = PseudoVAADD_VV_MF8 %0:vr, %1:vr, 2, $noreg, 3, implicit $vxrm, implicit $vl, implicit $vtype
+    $v8 = COPY %3:vr
+    PseudoRET implicit $v8
+...
+---
+name: vaadd_inlineasm
+tracksRegLiveness: true
+body: |
+  bb.0.entry:
+    liveins: $v8, $v9, $v10, $x10
+    ; CHECK-LABEL: name: vaadd_inlineasm
+    ; CHECK: liveins: $v8, $v9, $v10, $x10
+    ; CHECK-NEXT: {{  $}}
+    ; CHECK-NEXT: [[COPY:%[0-9]+]]:gprnox0 = COPY $x10
+    ; CHECK-NEXT: [[COPY1:%[0-9]+]]:vr = COPY $v10
+    ; CHECK-NEXT: [[COPY2:%[0-9]+]]:vr = COPY $v9
+    ; CHECK-NEXT: [[COPY3:%[0-9]+]]:vr = COPY $v8
+    ; CHECK-NEXT: dead $x0 = PseudoVSETVLI [[COPY]], 69, implicit-def $vl, implicit-def $vtype
+    ; CHECK-NEXT: [[SwapVXRMImm:%[0-9]+]]:gpr = SwapVXRMImm 2, implicit-def $vxrm, implicit $vxrm
+    ; CHECK-NEXT: [[PseudoVAADD_VV_MF8_:%[0-9]+]]:vr = PseudoVAADD_VV_MF8 [[COPY3]], [[COPY2]], 2, $noreg, 3, implicit $vxrm, implicit $vl, implicit $vtype
+    ; CHECK-NEXT: WriteVXRM [[SwapVXRMImm]], implicit-def $vxrm
+    ; CHECK-NEXT: INLINEASM &"", 1 /* sideeffect attdialect */
+    ; CHECK-NEXT: [[SwapVXRMImm1:%[0-9]+]]:gpr = SwapVXRMImm 0, implicit-def $vxrm, implicit $vxrm
+    ; CHECK-NEXT: [[PseudoVAADD_VV_MF8_1:%[0-9]+]]:vr = PseudoVAADD_VV_MF8 killed [[PseudoVAADD_VV_MF8_]], [[COPY1]], 0, $noreg, 3, implicit $vxrm, implicit $vl, implicit $vtype
+    ; CHECK-NEXT: $v8 = COPY [[PseudoVAADD_VV_MF8_1]]
+    ; CHECK-NEXT: WriteVXRM [[SwapVXRMImm1]], implicit-def $vxrm
+    ; CHECK-NEXT: PseudoRET implicit $v8
+    %3:gprnox0 = COPY $x10
+    %2:vr = COPY $v10
+    %1:vr = COPY $v9
+    %0:vr = COPY $v8
+    dead $x0 = PseudoVSETVLI %3:gprnox0, 69, implicit-def $vl, implicit-def $vtype
+    %4:vr = PseudoVAADD_VV_MF8 %0:vr, %1:vr, 2, $noreg, 3, implicit $vxrm, implicit $vl, implicit $vtype
+    INLINEASM &"", 1 /* sideeffect attdialect */
+    %5:vr = PseudoVAADD_VV_MF8 killed %4:vr, %2:vr, 0, $noreg, 3, implicit $vxrm, implicit $vl, implicit $vtype
+    $v8 = COPY %5:vr
+    PseudoRET implicit $v8
+...
+---
+name:  fallthrough_basicblock
+tracksRegLiveness: true
+body:     |
+  ; CHECK-LABEL: name: fallthrough_basicblock
+  ; CHECK: bb.0.entry:
+  ; CHECK-NEXT:   successors: %bb.1(0x80000000)
+  ; CHECK-NEXT:   liveins: $v8, $v9, $x10
+  ; CHECK-NEXT: {{  $}}
+  ; CHECK-NEXT:   [[COPY:%[0-9]+]]:vr = COPY $v8
+  ; CHECK-NEXT:   [[COPY1:%[0-9]+]]:vr = COPY $v9
+  ; CHECK-NEXT:   [[COPY2:%[0-9]+]]:gprnox0 = COPY $x10
+  ; CHECK-NEXT:   dead $x0 = PseudoVSETVLI [[COPY2]], 69, implicit-def $vl, implicit-def $vtype
+  ; CHECK-NEXT:   [[SwapVXRMImm:%[0-9]+]]:gpr = SwapVXRMImm 2, implicit-def $vxrm, implicit $vxrm
+  ; CHECK-NEXT:   [[PseudoVAADD_VV_MF8_:%[0-9]+]]:vr = PseudoVAADD_VV_MF8 [[COPY]], [[COPY1]], 2, $noreg, 3, implicit $vxrm, implicit $vl, implicit $vtype
+  ; CHECK-NEXT:   WriteVXRM [[SwapVXRMImm]], implicit-def $vxrm
+  ; CHECK-NEXT: {{  $}}
+  ; CHECK-NEXT: bb.1:
+  ; CHECK-NEXT:   $v8 = COPY [[PseudoVAADD_VV_MF8_]]
+  ; CHECK-NEXT:   PseudoRET implicit $v8
+  bb.0.entry:
+    liveins: $v8, $v9, $x10
+
+    %0:vr = COPY $v8
+    %1:vr = COPY $v9
+    %2:gprnox0 = COPY $x10
+    dead $x0 = PseudoVSETVLI %2:gprnox0, 69, implicit-def $vl, implicit-def $vtype
+    %3:vr = PseudoVAADD_VV_MF8 %0:vr, %1:vr, 2, $noreg, 3, implicit $vxrm, implicit $vl, implicit $vtype
+  bb.1:
+    $v8 = COPY %3:vr
+    PseudoRET implicit $v8
+...
diff --git a/llvm/test/CodeGen/RISCV/rvv/vaadd-rm-rv64.ll b/llvm/test/CodeGen/RISCV/rvv/vaadd-rm-rv64.ll
new file mode 100644
--- /dev/null
+++ b/llvm/test/CodeGen/RISCV/rvv/vaadd-rm-rv64.ll
@@ -0,0 +1,2250 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc -mtriple=riscv64 -mattr=+v -verify-machineinstrs \
+; RUN:   < %s | FileCheck %s
+declare <vscale x 1 x i8> @llvm.riscv.vaadd.rm.nxv1i8.nxv1i8(
+  <vscale x 1 x i8>,
+  <vscale x 1 x i8>,
+  <vscale x 1 x i8>,
+  i64,
+  i64);
+
+define <vscale x 1 x i8> @intrinsic_vaadd_vv_nxv1i8_nxv1i8_nxv1i8(<vscale x 1 x i8> %0, <vscale x 1 x i8> %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vaadd_vv_nxv1i8_nxv1i8_nxv1i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, mf8, ta, mu
+; CHECK-NEXT:    vaadd.vv v8, v8, v9
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i8> @llvm.riscv.vaadd.rm.nxv1i8.nxv1i8(
+    <vscale x 1 x i8> undef,
+    <vscale x 1 x i8> %0,
+    <vscale x 1 x i8> %1,
+    i64 %2,
+    i64 4)
+
+  ret <vscale x 1 x i8> %a
+}
+
+declare <vscale x 1 x i8> @llvm.riscv.vaadd.rm.mask.nxv1i8.nxv1i8(
+  <vscale x 1 x i8>,
+  <vscale x 1 x i8>,
+  <vscale x 1 x i8>,
+  <vscale x 1 x i1>,
+  i64,
+  i64,
+  i64);
+
+define <vscale x 1 x i8> @intrinsic_vaadd_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 {
+; CHECK-LABEL: intrinsic_vaadd_mask_vv_nxv1i8_nxv1i8_nxv1i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, mf8, ta, mu
+; CHECK-NEXT:    vaadd.vv v8, v9, v10, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i8> @llvm.riscv.vaadd.rm.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, i64 1,
+    i64 4)
+
+  ret <vscale x 1 x i8> %a
+}
+
+declare <vscale x 2 x i8> @llvm.riscv.vaadd.rm.nxv2i8.nxv2i8(
+  <vscale x 2 x i8>,
+  <vscale x 2 x i8>,
+  <vscale x 2 x i8>,
+  i64,
+  i64);
+
+define <vscale x 2 x i8> @intrinsic_vaadd_vv_nxv2i8_nxv2i8_nxv2i8(<vscale x 2 x i8> %0, <vscale x 2 x i8> %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vaadd_vv_nxv2i8_nxv2i8_nxv2i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, mf4, ta, mu
+; CHECK-NEXT:    vaadd.vv v8, v8, v9
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i8> @llvm.riscv.vaadd.rm.nxv2i8.nxv2i8(
+    <vscale x 2 x i8> undef,
+    <vscale x 2 x i8> %0,
+    <vscale x 2 x i8> %1,
+    i64 %2,
+    i64 4)
+
+  ret <vscale x 2 x i8> %a
+}
+
+declare <vscale x 2 x i8> @llvm.riscv.vaadd.rm.mask.nxv2i8.nxv2i8(
+  <vscale x 2 x i8>,
+  <vscale x 2 x i8>,
+  <vscale x 2 x i8>,
+  <vscale x 2 x i1>,
+  i64,
+  i64,
+  i64);
+
+define <vscale x 2 x i8> @intrinsic_vaadd_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 {
+; CHECK-LABEL: intrinsic_vaadd_mask_vv_nxv2i8_nxv2i8_nxv2i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, mf4, ta, mu
+; CHECK-NEXT:    vaadd.vv v8, v9, v10, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i8> @llvm.riscv.vaadd.rm.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, i64 1,
+    i64 4)
+
+  ret <vscale x 2 x i8> %a
+}
+
+declare <vscale x 4 x i8> @llvm.riscv.vaadd.rm.nxv4i8.nxv4i8(
+  <vscale x 4 x i8>,
+  <vscale x 4 x i8>,
+  <vscale x 4 x i8>,
+  i64,
+  i64);
+
+define <vscale x 4 x i8> @intrinsic_vaadd_vv_nxv4i8_nxv4i8_nxv4i8(<vscale x 4 x i8> %0, <vscale x 4 x i8> %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vaadd_vv_nxv4i8_nxv4i8_nxv4i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, mf2, ta, mu
+; CHECK-NEXT:    vaadd.vv v8, v8, v9
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i8> @llvm.riscv.vaadd.rm.nxv4i8.nxv4i8(
+    <vscale x 4 x i8> undef,
+    <vscale x 4 x i8> %0,
+    <vscale x 4 x i8> %1,
+    i64 %2,
+    i64 4)
+
+  ret <vscale x 4 x i8> %a
+}
+
+declare <vscale x 4 x i8> @llvm.riscv.vaadd.rm.mask.nxv4i8.nxv4i8(
+  <vscale x 4 x i8>,
+  <vscale x 4 x i8>,
+  <vscale x 4 x i8>,
+  <vscale x 4 x i1>,
+  i64,
+  i64,
+  i64);
+
+define <vscale x 4 x i8> @intrinsic_vaadd_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 {
+; CHECK-LABEL: intrinsic_vaadd_mask_vv_nxv4i8_nxv4i8_nxv4i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, mf2, ta, mu
+; CHECK-NEXT:    vaadd.vv v8, v9, v10, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i8> @llvm.riscv.vaadd.rm.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, i64 1,
+    i64 4)
+
+  ret <vscale x 4 x i8> %a
+}
+
+declare <vscale x 8 x i8> @llvm.riscv.vaadd.rm.nxv8i8.nxv8i8(
+  <vscale x 8 x i8>,
+  <vscale x 8 x i8>,
+  <vscale x 8 x i8>,
+  i64,
+  i64);
+
+define <vscale x 8 x i8> @intrinsic_vaadd_vv_nxv8i8_nxv8i8_nxv8i8(<vscale x 8 x i8> %0, <vscale x 8 x i8> %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vaadd_vv_nxv8i8_nxv8i8_nxv8i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, m1, ta, mu
+; CHECK-NEXT:    vaadd.vv v8, v8, v9
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i8> @llvm.riscv.vaadd.rm.nxv8i8.nxv8i8(
+    <vscale x 8 x i8> undef,
+    <vscale x 8 x i8> %0,
+    <vscale x 8 x i8> %1,
+    i64 %2,
+    i64 4)
+
+  ret <vscale x 8 x i8> %a
+}
+
+declare <vscale x 8 x i8> @llvm.riscv.vaadd.rm.mask.nxv8i8.nxv8i8(
+  <vscale x 8 x i8>,
+  <vscale x 8 x i8>,
+  <vscale x 8 x i8>,
+  <vscale x 8 x i1>,
+  i64,
+  i64,
+  i64);
+
+define <vscale x 8 x i8> @intrinsic_vaadd_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 {
+; CHECK-LABEL: intrinsic_vaadd_mask_vv_nxv8i8_nxv8i8_nxv8i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, m1, ta, mu
+; CHECK-NEXT:    vaadd.vv v8, v9, v10, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i8> @llvm.riscv.vaadd.rm.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, i64 1,
+    i64 4)
+
+  ret <vscale x 8 x i8> %a
+}
+
+declare <vscale x 16 x i8> @llvm.riscv.vaadd.rm.nxv16i8.nxv16i8(
+  <vscale x 16 x i8>,
+  <vscale x 16 x i8>,
+  <vscale x 16 x i8>,
+  i64,
+  i64);
+
+define <vscale x 16 x i8> @intrinsic_vaadd_vv_nxv16i8_nxv16i8_nxv16i8(<vscale x 16 x i8> %0, <vscale x 16 x i8> %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vaadd_vv_nxv16i8_nxv16i8_nxv16i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, m2, ta, mu
+; CHECK-NEXT:    vaadd.vv v8, v8, v10
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 16 x i8> @llvm.riscv.vaadd.rm.nxv16i8.nxv16i8(
+    <vscale x 16 x i8> undef,
+    <vscale x 16 x i8> %0,
+    <vscale x 16 x i8> %1,
+    i64 %2,
+    i64 4)
+
+  ret <vscale x 16 x i8> %a
+}
+
+declare <vscale x 16 x i8> @llvm.riscv.vaadd.rm.mask.nxv16i8.nxv16i8(
+  <vscale x 16 x i8>,
+  <vscale x 16 x i8>,
+  <vscale x 16 x i8>,
+  <vscale x 16 x i1>,
+  i64,
+  i64,
+  i64);
+
+define <vscale x 16 x i8> @intrinsic_vaadd_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 {
+; CHECK-LABEL: intrinsic_vaadd_mask_vv_nxv16i8_nxv16i8_nxv16i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, m2, ta, mu
+; CHECK-NEXT:    vaadd.vv v8, v10, v12, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 16 x i8> @llvm.riscv.vaadd.rm.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, i64 1,
+    i64 4)
+
+  ret <vscale x 16 x i8> %a
+}
+
+declare <vscale x 32 x i8> @llvm.riscv.vaadd.rm.nxv32i8.nxv32i8(
+  <vscale x 32 x i8>,
+  <vscale x 32 x i8>,
+  <vscale x 32 x i8>,
+  i64,
+  i64);
+
+define <vscale x 32 x i8> @intrinsic_vaadd_vv_nxv32i8_nxv32i8_nxv32i8(<vscale x 32 x i8> %0, <vscale x 32 x i8> %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vaadd_vv_nxv32i8_nxv32i8_nxv32i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, m4, ta, mu
+; CHECK-NEXT:    vaadd.vv v8, v8, v12
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 32 x i8> @llvm.riscv.vaadd.rm.nxv32i8.nxv32i8(
+    <vscale x 32 x i8> undef,
+    <vscale x 32 x i8> %0,
+    <vscale x 32 x i8> %1,
+    i64 %2,
+    i64 4)
+
+  ret <vscale x 32 x i8> %a
+}
+
+declare <vscale x 32 x i8> @llvm.riscv.vaadd.rm.mask.nxv32i8.nxv32i8(
+  <vscale x 32 x i8>,
+  <vscale x 32 x i8>,
+  <vscale x 32 x i8>,
+  <vscale x 32 x i1>,
+  i64,
+  i64,
+  i64);
+
+define <vscale x 32 x i8> @intrinsic_vaadd_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 {
+; CHECK-LABEL: intrinsic_vaadd_mask_vv_nxv32i8_nxv32i8_nxv32i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, m4, ta, mu
+; CHECK-NEXT:    vaadd.vv v8, v12, v16, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 32 x i8> @llvm.riscv.vaadd.rm.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, i64 1,
+    i64 4)
+
+  ret <vscale x 32 x i8> %a
+}
+
+declare <vscale x 64 x i8> @llvm.riscv.vaadd.rm.nxv64i8.nxv64i8(
+  <vscale x 64 x i8>,
+  <vscale x 64 x i8>,
+  <vscale x 64 x i8>,
+  i64,
+  i64);
+
+define <vscale x 64 x i8> @intrinsic_vaadd_vv_nxv64i8_nxv64i8_nxv64i8(<vscale x 64 x i8> %0, <vscale x 64 x i8> %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vaadd_vv_nxv64i8_nxv64i8_nxv64i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e8, m8, ta, mu
+; CHECK-NEXT:    vaadd.vv v8, v8, v16
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 64 x i8> @llvm.riscv.vaadd.rm.nxv64i8.nxv64i8(
+    <vscale x 64 x i8> undef,
+    <vscale x 64 x i8> %0,
+    <vscale x 64 x i8> %1,
+    i64 %2,
+    i64 4)
+
+  ret <vscale x 64 x i8> %a
+}
+
+declare <vscale x 64 x i8> @llvm.riscv.vaadd.rm.mask.nxv64i8.nxv64i8(
+  <vscale x 64 x i8>,
+  <vscale x 64 x i8>,
+  <vscale x 64 x i8>,
+  <vscale x 64 x i1>,
+  i64,
+  i64,
+  i64);
+
+define <vscale x 64 x i8> @intrinsic_vaadd_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 {
+; CHECK-LABEL: intrinsic_vaadd_mask_vv_nxv64i8_nxv64i8_nxv64i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vl8r.v v24, (a0)
+; CHECK-NEXT:    vsetvli zero, a1, e8, m8, ta, mu
+; CHECK-NEXT:    vaadd.vv v8, v16, v24, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 64 x i8> @llvm.riscv.vaadd.rm.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, i64 1,
+    i64 4)
+
+  ret <vscale x 64 x i8> %a
+}
+
+declare <vscale x 1 x i16> @llvm.riscv.vaadd.rm.nxv1i16.nxv1i16(
+  <vscale x 1 x i16>,
+  <vscale x 1 x i16>,
+  <vscale x 1 x i16>,
+  i64,
+  i64);
+
+define <vscale x 1 x i16> @intrinsic_vaadd_vv_nxv1i16_nxv1i16_nxv1i16(<vscale x 1 x i16> %0, <vscale x 1 x i16> %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vaadd_vv_nxv1i16_nxv1i16_nxv1i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, mf4, ta, mu
+; CHECK-NEXT:    vaadd.vv v8, v8, v9
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i16> @llvm.riscv.vaadd.rm.nxv1i16.nxv1i16(
+    <vscale x 1 x i16> undef,
+    <vscale x 1 x i16> %0,
+    <vscale x 1 x i16> %1,
+    i64 %2,
+    i64 4)
+
+  ret <vscale x 1 x i16> %a
+}
+
+declare <vscale x 1 x i16> @llvm.riscv.vaadd.rm.mask.nxv1i16.nxv1i16(
+  <vscale x 1 x i16>,
+  <vscale x 1 x i16>,
+  <vscale x 1 x i16>,
+  <vscale x 1 x i1>,
+  i64,
+  i64,
+  i64);
+
+define <vscale x 1 x i16> @intrinsic_vaadd_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 {
+; CHECK-LABEL: intrinsic_vaadd_mask_vv_nxv1i16_nxv1i16_nxv1i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, mf4, ta, mu
+; CHECK-NEXT:    vaadd.vv v8, v9, v10, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i16> @llvm.riscv.vaadd.rm.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, i64 1,
+    i64 4)
+
+  ret <vscale x 1 x i16> %a
+}
+
+declare <vscale x 2 x i16> @llvm.riscv.vaadd.rm.nxv2i16.nxv2i16(
+  <vscale x 2 x i16>,
+  <vscale x 2 x i16>,
+  <vscale x 2 x i16>,
+  i64,
+  i64);
+
+define <vscale x 2 x i16> @intrinsic_vaadd_vv_nxv2i16_nxv2i16_nxv2i16(<vscale x 2 x i16> %0, <vscale x 2 x i16> %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vaadd_vv_nxv2i16_nxv2i16_nxv2i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, mf2, ta, mu
+; CHECK-NEXT:    vaadd.vv v8, v8, v9
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i16> @llvm.riscv.vaadd.rm.nxv2i16.nxv2i16(
+    <vscale x 2 x i16> undef,
+    <vscale x 2 x i16> %0,
+    <vscale x 2 x i16> %1,
+    i64 %2,
+    i64 4)
+
+  ret <vscale x 2 x i16> %a
+}
+
+declare <vscale x 2 x i16> @llvm.riscv.vaadd.rm.mask.nxv2i16.nxv2i16(
+  <vscale x 2 x i16>,
+  <vscale x 2 x i16>,
+  <vscale x 2 x i16>,
+  <vscale x 2 x i1>,
+  i64,
+  i64,
+  i64);
+
+define <vscale x 2 x i16> @intrinsic_vaadd_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 {
+; CHECK-LABEL: intrinsic_vaadd_mask_vv_nxv2i16_nxv2i16_nxv2i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, mf2, ta, mu
+; CHECK-NEXT:    vaadd.vv v8, v9, v10, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i16> @llvm.riscv.vaadd.rm.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, i64 1,
+    i64 4)
+
+  ret <vscale x 2 x i16> %a
+}
+
+declare <vscale x 4 x i16> @llvm.riscv.vaadd.rm.nxv4i16.nxv4i16(
+  <vscale x 4 x i16>,
+  <vscale x 4 x i16>,
+  <vscale x 4 x i16>,
+  i64,
+  i64);
+
+define <vscale x 4 x i16> @intrinsic_vaadd_vv_nxv4i16_nxv4i16_nxv4i16(<vscale x 4 x i16> %0, <vscale x 4 x i16> %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vaadd_vv_nxv4i16_nxv4i16_nxv4i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, m1, ta, mu
+; CHECK-NEXT:    vaadd.vv v8, v8, v9
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i16> @llvm.riscv.vaadd.rm.nxv4i16.nxv4i16(
+    <vscale x 4 x i16> undef,
+    <vscale x 4 x i16> %0,
+    <vscale x 4 x i16> %1,
+    i64 %2,
+    i64 4)
+
+  ret <vscale x 4 x i16> %a
+}
+
+declare <vscale x 4 x i16> @llvm.riscv.vaadd.rm.mask.nxv4i16.nxv4i16(
+  <vscale x 4 x i16>,
+  <vscale x 4 x i16>,
+  <vscale x 4 x i16>,
+  <vscale x 4 x i1>,
+  i64,
+  i64,
+  i64);
+
+define <vscale x 4 x i16> @intrinsic_vaadd_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 {
+; CHECK-LABEL: intrinsic_vaadd_mask_vv_nxv4i16_nxv4i16_nxv4i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, m1, ta, mu
+; CHECK-NEXT:    vaadd.vv v8, v9, v10, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i16> @llvm.riscv.vaadd.rm.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, i64 1,
+    i64 4)
+
+  ret <vscale x 4 x i16> %a
+}
+
+declare <vscale x 8 x i16> @llvm.riscv.vaadd.rm.nxv8i16.nxv8i16(
+  <vscale x 8 x i16>,
+  <vscale x 8 x i16>,
+  <vscale x 8 x i16>,
+  i64,
+  i64);
+
+define <vscale x 8 x i16> @intrinsic_vaadd_vv_nxv8i16_nxv8i16_nxv8i16(<vscale x 8 x i16> %0, <vscale x 8 x i16> %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vaadd_vv_nxv8i16_nxv8i16_nxv8i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, m2, ta, mu
+; CHECK-NEXT:    vaadd.vv v8, v8, v10
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i16> @llvm.riscv.vaadd.rm.nxv8i16.nxv8i16(
+    <vscale x 8 x i16> undef,
+    <vscale x 8 x i16> %0,
+    <vscale x 8 x i16> %1,
+    i64 %2,
+    i64 4)
+
+  ret <vscale x 8 x i16> %a
+}
+
+declare <vscale x 8 x i16> @llvm.riscv.vaadd.rm.mask.nxv8i16.nxv8i16(
+  <vscale x 8 x i16>,
+  <vscale x 8 x i16>,
+  <vscale x 8 x i16>,
+  <vscale x 8 x i1>,
+  i64,
+  i64,
+  i64);
+
+define <vscale x 8 x i16> @intrinsic_vaadd_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 {
+; CHECK-LABEL: intrinsic_vaadd_mask_vv_nxv8i16_nxv8i16_nxv8i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, m2, ta, mu
+; CHECK-NEXT:    vaadd.vv v8, v10, v12, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i16> @llvm.riscv.vaadd.rm.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, i64 1,
+    i64 4)
+
+  ret <vscale x 8 x i16> %a
+}
+
+declare <vscale x 16 x i16> @llvm.riscv.vaadd.rm.nxv16i16.nxv16i16(
+  <vscale x 16 x i16>,
+  <vscale x 16 x i16>,
+  <vscale x 16 x i16>,
+  i64,
+  i64);
+
+define <vscale x 16 x i16> @intrinsic_vaadd_vv_nxv16i16_nxv16i16_nxv16i16(<vscale x 16 x i16> %0, <vscale x 16 x i16> %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vaadd_vv_nxv16i16_nxv16i16_nxv16i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, m4, ta, mu
+; CHECK-NEXT:    vaadd.vv v8, v8, v12
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 16 x i16> @llvm.riscv.vaadd.rm.nxv16i16.nxv16i16(
+    <vscale x 16 x i16> undef,
+    <vscale x 16 x i16> %0,
+    <vscale x 16 x i16> %1,
+    i64 %2,
+    i64 4)
+
+  ret <vscale x 16 x i16> %a
+}
+
+declare <vscale x 16 x i16> @llvm.riscv.vaadd.rm.mask.nxv16i16.nxv16i16(
+  <vscale x 16 x i16>,
+  <vscale x 16 x i16>,
+  <vscale x 16 x i16>,
+  <vscale x 16 x i1>,
+  i64,
+  i64,
+  i64);
+
+define <vscale x 16 x i16> @intrinsic_vaadd_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 {
+; CHECK-LABEL: intrinsic_vaadd_mask_vv_nxv16i16_nxv16i16_nxv16i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, m4, ta, mu
+; CHECK-NEXT:    vaadd.vv v8, v12, v16, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 16 x i16> @llvm.riscv.vaadd.rm.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, i64 1,
+    i64 4)
+
+  ret <vscale x 16 x i16> %a
+}
+
+declare <vscale x 32 x i16> @llvm.riscv.vaadd.rm.nxv32i16.nxv32i16(
+  <vscale x 32 x i16>,
+  <vscale x 32 x i16>,
+  <vscale x 32 x i16>,
+  i64,
+  i64);
+
+define <vscale x 32 x i16> @intrinsic_vaadd_vv_nxv32i16_nxv32i16_nxv32i16(<vscale x 32 x i16> %0, <vscale x 32 x i16> %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vaadd_vv_nxv32i16_nxv32i16_nxv32i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e16, m8, ta, mu
+; CHECK-NEXT:    vaadd.vv v8, v8, v16
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 32 x i16> @llvm.riscv.vaadd.rm.nxv32i16.nxv32i16(
+    <vscale x 32 x i16> undef,
+    <vscale x 32 x i16> %0,
+    <vscale x 32 x i16> %1,
+    i64 %2,
+    i64 4)
+
+  ret <vscale x 32 x i16> %a
+}
+
+declare <vscale x 32 x i16> @llvm.riscv.vaadd.rm.mask.nxv32i16.nxv32i16(
+  <vscale x 32 x i16>,
+  <vscale x 32 x i16>,
+  <vscale x 32 x i16>,
+  <vscale x 32 x i1>,
+  i64,
+  i64,
+  i64);
+
+define <vscale x 32 x i16> @intrinsic_vaadd_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 {
+; CHECK-LABEL: intrinsic_vaadd_mask_vv_nxv32i16_nxv32i16_nxv32i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vl8re16.v v24, (a0)
+; CHECK-NEXT:    vsetvli zero, a1, e16, m8, ta, mu
+; CHECK-NEXT:    vaadd.vv v8, v16, v24, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 32 x i16> @llvm.riscv.vaadd.rm.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, i64 1,
+    i64 4)
+
+  ret <vscale x 32 x i16> %a
+}
+
+declare <vscale x 1 x i32> @llvm.riscv.vaadd.rm.nxv1i32.nxv1i32(
+  <vscale x 1 x i32>,
+  <vscale x 1 x i32>,
+  <vscale x 1 x i32>,
+  i64,
+  i64);
+
+define <vscale x 1 x i32> @intrinsic_vaadd_vv_nxv1i32_nxv1i32_nxv1i32(<vscale x 1 x i32> %0, <vscale x 1 x i32> %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vaadd_vv_nxv1i32_nxv1i32_nxv1i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, mf2, ta, mu
+; CHECK-NEXT:    vaadd.vv v8, v8, v9
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i32> @llvm.riscv.vaadd.rm.nxv1i32.nxv1i32(
+    <vscale x 1 x i32> undef,
+    <vscale x 1 x i32> %0,
+    <vscale x 1 x i32> %1,
+    i64 %2,
+    i64 4)
+
+  ret <vscale x 1 x i32> %a
+}
+
+declare <vscale x 1 x i32> @llvm.riscv.vaadd.rm.mask.nxv1i32.nxv1i32(
+  <vscale x 1 x i32>,
+  <vscale x 1 x i32>,
+  <vscale x 1 x i32>,
+  <vscale x 1 x i1>,
+  i64,
+  i64,
+  i64);
+
+define <vscale x 1 x i32> @intrinsic_vaadd_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 {
+; CHECK-LABEL: intrinsic_vaadd_mask_vv_nxv1i32_nxv1i32_nxv1i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, mf2, ta, mu
+; CHECK-NEXT:    vaadd.vv v8, v9, v10, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i32> @llvm.riscv.vaadd.rm.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, i64 1,
+    i64 4)
+
+  ret <vscale x 1 x i32> %a
+}
+
+declare <vscale x 2 x i32> @llvm.riscv.vaadd.rm.nxv2i32.nxv2i32(
+  <vscale x 2 x i32>,
+  <vscale x 2 x i32>,
+  <vscale x 2 x i32>,
+  i64,
+  i64);
+
+define <vscale x 2 x i32> @intrinsic_vaadd_vv_nxv2i32_nxv2i32_nxv2i32(<vscale x 2 x i32> %0, <vscale x 2 x i32> %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vaadd_vv_nxv2i32_nxv2i32_nxv2i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m1, ta, mu
+; CHECK-NEXT:    vaadd.vv v8, v8, v9
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i32> @llvm.riscv.vaadd.rm.nxv2i32.nxv2i32(
+    <vscale x 2 x i32> undef,
+    <vscale x 2 x i32> %0,
+    <vscale x 2 x i32> %1,
+    i64 %2,
+    i64 4)
+
+  ret <vscale x 2 x i32> %a
+}
+
+declare <vscale x 2 x i32> @llvm.riscv.vaadd.rm.mask.nxv2i32.nxv2i32(
+  <vscale x 2 x i32>,
+  <vscale x 2 x i32>,
+  <vscale x 2 x i32>,
+  <vscale x 2 x i1>,
+  i64,
+  i64,
+  i64);
+
+define <vscale x 2 x i32> @intrinsic_vaadd_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 {
+; CHECK-LABEL: intrinsic_vaadd_mask_vv_nxv2i32_nxv2i32_nxv2i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m1, ta, mu
+; CHECK-NEXT:    vaadd.vv v8, v9, v10, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i32> @llvm.riscv.vaadd.rm.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, i64 1,
+    i64 4)
+
+  ret <vscale x 2 x i32> %a
+}
+
+declare <vscale x 4 x i32> @llvm.riscv.vaadd.rm.nxv4i32.nxv4i32(
+  <vscale x 4 x i32>,
+  <vscale x 4 x i32>,
+  <vscale x 4 x i32>,
+  i64,
+  i64);
+
+define <vscale x 4 x i32> @intrinsic_vaadd_vv_nxv4i32_nxv4i32_nxv4i32(<vscale x 4 x i32> %0, <vscale x 4 x i32> %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vaadd_vv_nxv4i32_nxv4i32_nxv4i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m2, ta, mu
+; CHECK-NEXT:    vaadd.vv v8, v8, v10
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i32> @llvm.riscv.vaadd.rm.nxv4i32.nxv4i32(
+    <vscale x 4 x i32> undef,
+    <vscale x 4 x i32> %0,
+    <vscale x 4 x i32> %1,
+    i64 %2,
+    i64 4)
+
+  ret <vscale x 4 x i32> %a
+}
+
+declare <vscale x 4 x i32> @llvm.riscv.vaadd.rm.mask.nxv4i32.nxv4i32(
+  <vscale x 4 x i32>,
+  <vscale x 4 x i32>,
+  <vscale x 4 x i32>,
+  <vscale x 4 x i1>,
+  i64,
+  i64,
+  i64);
+
+define <vscale x 4 x i32> @intrinsic_vaadd_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 {
+; CHECK-LABEL: intrinsic_vaadd_mask_vv_nxv4i32_nxv4i32_nxv4i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m2, ta, mu
+; CHECK-NEXT:    vaadd.vv v8, v10, v12, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i32> @llvm.riscv.vaadd.rm.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, i64 1,
+    i64 4)
+
+  ret <vscale x 4 x i32> %a
+}
+
+declare <vscale x 8 x i32> @llvm.riscv.vaadd.rm.nxv8i32.nxv8i32(
+  <vscale x 8 x i32>,
+  <vscale x 8 x i32>,
+  <vscale x 8 x i32>,
+  i64,
+  i64);
+
+define <vscale x 8 x i32> @intrinsic_vaadd_vv_nxv8i32_nxv8i32_nxv8i32(<vscale x 8 x i32> %0, <vscale x 8 x i32> %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vaadd_vv_nxv8i32_nxv8i32_nxv8i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m4, ta, mu
+; CHECK-NEXT:    vaadd.vv v8, v8, v12
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i32> @llvm.riscv.vaadd.rm.nxv8i32.nxv8i32(
+    <vscale x 8 x i32> undef,
+    <vscale x 8 x i32> %0,
+    <vscale x 8 x i32> %1,
+    i64 %2,
+    i64 4)
+
+  ret <vscale x 8 x i32> %a
+}
+
+declare <vscale x 8 x i32> @llvm.riscv.vaadd.rm.mask.nxv8i32.nxv8i32(
+  <vscale x 8 x i32>,
+  <vscale x 8 x i32>,
+  <vscale x 8 x i32>,
+  <vscale x 8 x i1>,
+  i64,
+  i64,
+  i64);
+
+define <vscale x 8 x i32> @intrinsic_vaadd_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 {
+; CHECK-LABEL: intrinsic_vaadd_mask_vv_nxv8i32_nxv8i32_nxv8i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m4, ta, mu
+; CHECK-NEXT:    vaadd.vv v8, v12, v16, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i32> @llvm.riscv.vaadd.rm.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, i64 1,
+    i64 4)
+
+  ret <vscale x 8 x i32> %a
+}
+
+declare <vscale x 16 x i32> @llvm.riscv.vaadd.rm.nxv16i32.nxv16i32(
+  <vscale x 16 x i32>,
+  <vscale x 16 x i32>,
+  <vscale x 16 x i32>,
+  i64,
+  i64);
+
+define <vscale x 16 x i32> @intrinsic_vaadd_vv_nxv16i32_nxv16i32_nxv16i32(<vscale x 16 x i32> %0, <vscale x 16 x i32> %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vaadd_vv_nxv16i32_nxv16i32_nxv16i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e32, m8, ta, mu
+; CHECK-NEXT:    vaadd.vv v8, v8, v16
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 16 x i32> @llvm.riscv.vaadd.rm.nxv16i32.nxv16i32(
+    <vscale x 16 x i32> undef,
+    <vscale x 16 x i32> %0,
+    <vscale x 16 x i32> %1,
+    i64 %2,
+    i64 4)
+
+  ret <vscale x 16 x i32> %a
+}
+
+declare <vscale x 16 x i32> @llvm.riscv.vaadd.rm.mask.nxv16i32.nxv16i32(
+  <vscale x 16 x i32>,
+  <vscale x 16 x i32>,
+  <vscale x 16 x i32>,
+  <vscale x 16 x i1>,
+  i64,
+  i64,
+  i64);
+
+define <vscale x 16 x i32> @intrinsic_vaadd_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 {
+; CHECK-LABEL: intrinsic_vaadd_mask_vv_nxv16i32_nxv16i32_nxv16i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vl8re32.v v24, (a0)
+; CHECK-NEXT:    vsetvli zero, a1, e32, m8, ta, mu
+; CHECK-NEXT:    vaadd.vv v8, v16, v24, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 16 x i32> @llvm.riscv.vaadd.rm.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, i64 1,
+    i64 4)
+
+  ret <vscale x 16 x i32> %a
+}
+
+declare <vscale x 1 x i64> @llvm.riscv.vaadd.rm.nxv1i64.nxv1i64(
+  <vscale x 1 x i64>,
+  <vscale x 1 x i64>,
+  <vscale x 1 x i64>,
+  i64,
+  i64);
+
+define <vscale x 1 x i64> @intrinsic_vaadd_vv_nxv1i64_nxv1i64_nxv1i64(<vscale x 1 x i64> %0, <vscale x 1 x i64> %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vaadd_vv_nxv1i64_nxv1i64_nxv1i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e64, m1, ta, mu
+; CHECK-NEXT:    vaadd.vv v8, v8, v9
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i64> @llvm.riscv.vaadd.rm.nxv1i64.nxv1i64(
+    <vscale x 1 x i64> undef,
+    <vscale x 1 x i64> %0,
+    <vscale x 1 x i64> %1,
+    i64 %2,
+    i64 4)
+
+  ret <vscale x 1 x i64> %a
+}
+
+declare <vscale x 1 x i64> @llvm.riscv.vaadd.rm.mask.nxv1i64.nxv1i64(
+  <vscale x 1 x i64>,
+  <vscale x 1 x i64>,
+  <vscale x 1 x i64>,
+  <vscale x 1 x i1>,
+  i64,
+  i64,
+  i64);
+
+define <vscale x 1 x i64> @intrinsic_vaadd_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 {
+; CHECK-LABEL: intrinsic_vaadd_mask_vv_nxv1i64_nxv1i64_nxv1i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e64, m1, ta, mu
+; CHECK-NEXT:    vaadd.vv v8, v9, v10, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i64> @llvm.riscv.vaadd.rm.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, i64 1,
+    i64 4)
+
+  ret <vscale x 1 x i64> %a
+}
+
+declare <vscale x 2 x i64> @llvm.riscv.vaadd.rm.nxv2i64.nxv2i64(
+  <vscale x 2 x i64>,
+  <vscale x 2 x i64>,
+  <vscale x 2 x i64>,
+  i64,
+  i64);
+
+define <vscale x 2 x i64> @intrinsic_vaadd_vv_nxv2i64_nxv2i64_nxv2i64(<vscale x 2 x i64> %0, <vscale x 2 x i64> %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vaadd_vv_nxv2i64_nxv2i64_nxv2i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e64, m2, ta, mu
+; CHECK-NEXT:    vaadd.vv v8, v8, v10
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i64> @llvm.riscv.vaadd.rm.nxv2i64.nxv2i64(
+    <vscale x 2 x i64> undef,
+    <vscale x 2 x i64> %0,
+    <vscale x 2 x i64> %1,
+    i64 %2,
+    i64 4)
+
+  ret <vscale x 2 x i64> %a
+}
+
+declare <vscale x 2 x i64> @llvm.riscv.vaadd.rm.mask.nxv2i64.nxv2i64(
+  <vscale x 2 x i64>,
+  <vscale x 2 x i64>,
+  <vscale x 2 x i64>,
+  <vscale x 2 x i1>,
+  i64,
+  i64,
+  i64);
+
+define <vscale x 2 x i64> @intrinsic_vaadd_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 {
+; CHECK-LABEL: intrinsic_vaadd_mask_vv_nxv2i64_nxv2i64_nxv2i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e64, m2, ta, mu
+; CHECK-NEXT:    vaadd.vv v8, v10, v12, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i64> @llvm.riscv.vaadd.rm.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, i64 1,
+    i64 4)
+
+  ret <vscale x 2 x i64> %a
+}
+
+declare <vscale x 4 x i64> @llvm.riscv.vaadd.rm.nxv4i64.nxv4i64(
+  <vscale x 4 x i64>,
+  <vscale x 4 x i64>,
+  <vscale x 4 x i64>,
+  i64,
+  i64);
+
+define <vscale x 4 x i64> @intrinsic_vaadd_vv_nxv4i64_nxv4i64_nxv4i64(<vscale x 4 x i64> %0, <vscale x 4 x i64> %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vaadd_vv_nxv4i64_nxv4i64_nxv4i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e64, m4, ta, mu
+; CHECK-NEXT:    vaadd.vv v8, v8, v12
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i64> @llvm.riscv.vaadd.rm.nxv4i64.nxv4i64(
+    <vscale x 4 x i64> undef,
+    <vscale x 4 x i64> %0,
+    <vscale x 4 x i64> %1,
+    i64 %2,
+    i64 4)
+
+  ret <vscale x 4 x i64> %a
+}
+
+declare <vscale x 4 x i64> @llvm.riscv.vaadd.rm.mask.nxv4i64.nxv4i64(
+  <vscale x 4 x i64>,
+  <vscale x 4 x i64>,
+  <vscale x 4 x i64>,
+  <vscale x 4 x i1>,
+  i64,
+  i64,
+  i64);
+
+define <vscale x 4 x i64> @intrinsic_vaadd_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 {
+; CHECK-LABEL: intrinsic_vaadd_mask_vv_nxv4i64_nxv4i64_nxv4i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e64, m4, ta, mu
+; CHECK-NEXT:    vaadd.vv v8, v12, v16, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i64> @llvm.riscv.vaadd.rm.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, i64 1,
+    i64 4)
+
+  ret <vscale x 4 x i64> %a
+}
+
+declare <vscale x 8 x i64> @llvm.riscv.vaadd.rm.nxv8i64.nxv8i64(
+  <vscale x 8 x i64>,
+  <vscale x 8 x i64>,
+  <vscale x 8 x i64>,
+  i64,
+  i64);
+
+define <vscale x 8 x i64> @intrinsic_vaadd_vv_nxv8i64_nxv8i64_nxv8i64(<vscale x 8 x i64> %0, <vscale x 8 x i64> %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vaadd_vv_nxv8i64_nxv8i64_nxv8i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, mu
+; CHECK-NEXT:    vaadd.vv v8, v8, v16
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i64> @llvm.riscv.vaadd.rm.nxv8i64.nxv8i64(
+    <vscale x 8 x i64> undef,
+    <vscale x 8 x i64> %0,
+    <vscale x 8 x i64> %1,
+    i64 %2,
+    i64 4)
+
+  ret <vscale x 8 x i64> %a
+}
+
+declare <vscale x 8 x i64> @llvm.riscv.vaadd.rm.mask.nxv8i64.nxv8i64(
+  <vscale x 8 x i64>,
+  <vscale x 8 x i64>,
+  <vscale x 8 x i64>,
+  <vscale x 8 x i1>,
+  i64,
+  i64,
+  i64);
+
+define <vscale x 8 x i64> @intrinsic_vaadd_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 {
+; CHECK-LABEL: intrinsic_vaadd_mask_vv_nxv8i64_nxv8i64_nxv8i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vl8re64.v v24, (a0)
+; CHECK-NEXT:    vsetvli zero, a1, e64, m8, ta, mu
+; CHECK-NEXT:    vaadd.vv v8, v16, v24, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i64> @llvm.riscv.vaadd.rm.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, i64 1,
+    i64 4)
+
+  ret <vscale x 8 x i64> %a
+}
+
+declare <vscale x 1 x i8> @llvm.riscv.vaadd.rm.nxv1i8.i8(
+  <vscale x 1 x i8>,
+  <vscale x 1 x i8>,
+  i8,
+  i64,
+  i64);
+
+define <vscale x 1 x i8> @intrinsic_vaadd_vx_nxv1i8_nxv1i8_i8(<vscale x 1 x i8> %0, i8 %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vaadd_vx_nxv1i8_nxv1i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e8, mf8, ta, mu
+; CHECK-NEXT:    vaadd.vx v8, v8, a0
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i8> @llvm.riscv.vaadd.rm.nxv1i8.i8(
+    <vscale x 1 x i8> undef,
+    <vscale x 1 x i8> %0,
+    i8 %1,
+    i64 %2,
+    i64 4)
+
+  ret <vscale x 1 x i8> %a
+}
+
+declare <vscale x 1 x i8> @llvm.riscv.vaadd.rm.mask.nxv1i8.i8(
+  <vscale x 1 x i8>,
+  <vscale x 1 x i8>,
+  i8,
+  <vscale x 1 x i1>,
+  i64,
+  i64,
+  i64);
+
+define <vscale x 1 x i8> @intrinsic_vaadd_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 {
+; CHECK-LABEL: intrinsic_vaadd_mask_vx_nxv1i8_nxv1i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e8, mf8, ta, mu
+; CHECK-NEXT:    vaadd.vx v8, v9, a0, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i8> @llvm.riscv.vaadd.rm.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, i64 1,
+    i64 4)
+
+  ret <vscale x 1 x i8> %a
+}
+
+declare <vscale x 2 x i8> @llvm.riscv.vaadd.rm.nxv2i8.i8(
+  <vscale x 2 x i8>,
+  <vscale x 2 x i8>,
+  i8,
+  i64,
+  i64);
+
+define <vscale x 2 x i8> @intrinsic_vaadd_vx_nxv2i8_nxv2i8_i8(<vscale x 2 x i8> %0, i8 %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vaadd_vx_nxv2i8_nxv2i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e8, mf4, ta, mu
+; CHECK-NEXT:    vaadd.vx v8, v8, a0
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i8> @llvm.riscv.vaadd.rm.nxv2i8.i8(
+    <vscale x 2 x i8> undef,
+    <vscale x 2 x i8> %0,
+    i8 %1,
+    i64 %2,
+    i64 4)
+
+  ret <vscale x 2 x i8> %a
+}
+
+declare <vscale x 2 x i8> @llvm.riscv.vaadd.rm.mask.nxv2i8.i8(
+  <vscale x 2 x i8>,
+  <vscale x 2 x i8>,
+  i8,
+  <vscale x 2 x i1>,
+  i64,
+  i64,
+  i64);
+
+define <vscale x 2 x i8> @intrinsic_vaadd_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 {
+; CHECK-LABEL: intrinsic_vaadd_mask_vx_nxv2i8_nxv2i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e8, mf4, ta, mu
+; CHECK-NEXT:    vaadd.vx v8, v9, a0, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i8> @llvm.riscv.vaadd.rm.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, i64 1,
+    i64 4)
+
+  ret <vscale x 2 x i8> %a
+}
+
+declare <vscale x 4 x i8> @llvm.riscv.vaadd.rm.nxv4i8.i8(
+  <vscale x 4 x i8>,
+  <vscale x 4 x i8>,
+  i8,
+  i64,
+  i64);
+
+define <vscale x 4 x i8> @intrinsic_vaadd_vx_nxv4i8_nxv4i8_i8(<vscale x 4 x i8> %0, i8 %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vaadd_vx_nxv4i8_nxv4i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e8, mf2, ta, mu
+; CHECK-NEXT:    vaadd.vx v8, v8, a0
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i8> @llvm.riscv.vaadd.rm.nxv4i8.i8(
+    <vscale x 4 x i8> undef,
+    <vscale x 4 x i8> %0,
+    i8 %1,
+    i64 %2,
+    i64 4)
+
+  ret <vscale x 4 x i8> %a
+}
+
+declare <vscale x 4 x i8> @llvm.riscv.vaadd.rm.mask.nxv4i8.i8(
+  <vscale x 4 x i8>,
+  <vscale x 4 x i8>,
+  i8,
+  <vscale x 4 x i1>,
+  i64,
+  i64,
+  i64);
+
+define <vscale x 4 x i8> @intrinsic_vaadd_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 {
+; CHECK-LABEL: intrinsic_vaadd_mask_vx_nxv4i8_nxv4i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e8, mf2, ta, mu
+; CHECK-NEXT:    vaadd.vx v8, v9, a0, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i8> @llvm.riscv.vaadd.rm.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, i64 1,
+    i64 4)
+
+  ret <vscale x 4 x i8> %a
+}
+
+declare <vscale x 8 x i8> @llvm.riscv.vaadd.rm.nxv8i8.i8(
+  <vscale x 8 x i8>,
+  <vscale x 8 x i8>,
+  i8,
+  i64,
+  i64);
+
+define <vscale x 8 x i8> @intrinsic_vaadd_vx_nxv8i8_nxv8i8_i8(<vscale x 8 x i8> %0, i8 %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vaadd_vx_nxv8i8_nxv8i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e8, m1, ta, mu
+; CHECK-NEXT:    vaadd.vx v8, v8, a0
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i8> @llvm.riscv.vaadd.rm.nxv8i8.i8(
+    <vscale x 8 x i8> undef,
+    <vscale x 8 x i8> %0,
+    i8 %1,
+    i64 %2,
+    i64 4)
+
+  ret <vscale x 8 x i8> %a
+}
+
+declare <vscale x 8 x i8> @llvm.riscv.vaadd.rm.mask.nxv8i8.i8(
+  <vscale x 8 x i8>,
+  <vscale x 8 x i8>,
+  i8,
+  <vscale x 8 x i1>,
+  i64,
+  i64,
+  i64);
+
+define <vscale x 8 x i8> @intrinsic_vaadd_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 {
+; CHECK-LABEL: intrinsic_vaadd_mask_vx_nxv8i8_nxv8i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e8, m1, ta, mu
+; CHECK-NEXT:    vaadd.vx v8, v9, a0, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i8> @llvm.riscv.vaadd.rm.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, i64 1,
+    i64 4)
+
+  ret <vscale x 8 x i8> %a
+}
+
+declare <vscale x 16 x i8> @llvm.riscv.vaadd.rm.nxv16i8.i8(
+  <vscale x 16 x i8>,
+  <vscale x 16 x i8>,
+  i8,
+  i64,
+  i64);
+
+define <vscale x 16 x i8> @intrinsic_vaadd_vx_nxv16i8_nxv16i8_i8(<vscale x 16 x i8> %0, i8 %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vaadd_vx_nxv16i8_nxv16i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e8, m2, ta, mu
+; CHECK-NEXT:    vaadd.vx v8, v8, a0
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 16 x i8> @llvm.riscv.vaadd.rm.nxv16i8.i8(
+    <vscale x 16 x i8> undef,
+    <vscale x 16 x i8> %0,
+    i8 %1,
+    i64 %2,
+    i64 4)
+
+  ret <vscale x 16 x i8> %a
+}
+
+declare <vscale x 16 x i8> @llvm.riscv.vaadd.rm.mask.nxv16i8.i8(
+  <vscale x 16 x i8>,
+  <vscale x 16 x i8>,
+  i8,
+  <vscale x 16 x i1>,
+  i64,
+  i64,
+  i64);
+
+define <vscale x 16 x i8> @intrinsic_vaadd_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 {
+; CHECK-LABEL: intrinsic_vaadd_mask_vx_nxv16i8_nxv16i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e8, m2, ta, mu
+; CHECK-NEXT:    vaadd.vx v8, v10, a0, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 16 x i8> @llvm.riscv.vaadd.rm.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, i64 1,
+    i64 4)
+
+  ret <vscale x 16 x i8> %a
+}
+
+declare <vscale x 32 x i8> @llvm.riscv.vaadd.rm.nxv32i8.i8(
+  <vscale x 32 x i8>,
+  <vscale x 32 x i8>,
+  i8,
+  i64,
+  i64);
+
+define <vscale x 32 x i8> @intrinsic_vaadd_vx_nxv32i8_nxv32i8_i8(<vscale x 32 x i8> %0, i8 %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vaadd_vx_nxv32i8_nxv32i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e8, m4, ta, mu
+; CHECK-NEXT:    vaadd.vx v8, v8, a0
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 32 x i8> @llvm.riscv.vaadd.rm.nxv32i8.i8(
+    <vscale x 32 x i8> undef,
+    <vscale x 32 x i8> %0,
+    i8 %1,
+    i64 %2,
+    i64 4)
+
+  ret <vscale x 32 x i8> %a
+}
+
+declare <vscale x 32 x i8> @llvm.riscv.vaadd.rm.mask.nxv32i8.i8(
+  <vscale x 32 x i8>,
+  <vscale x 32 x i8>,
+  i8,
+  <vscale x 32 x i1>,
+  i64,
+  i64,
+  i64);
+
+define <vscale x 32 x i8> @intrinsic_vaadd_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 {
+; CHECK-LABEL: intrinsic_vaadd_mask_vx_nxv32i8_nxv32i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e8, m4, ta, mu
+; CHECK-NEXT:    vaadd.vx v8, v12, a0, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 32 x i8> @llvm.riscv.vaadd.rm.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, i64 1,
+    i64 4)
+
+  ret <vscale x 32 x i8> %a
+}
+
+declare <vscale x 64 x i8> @llvm.riscv.vaadd.rm.nxv64i8.i8(
+  <vscale x 64 x i8>,
+  <vscale x 64 x i8>,
+  i8,
+  i64,
+  i64);
+
+define <vscale x 64 x i8> @intrinsic_vaadd_vx_nxv64i8_nxv64i8_i8(<vscale x 64 x i8> %0, i8 %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vaadd_vx_nxv64i8_nxv64i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e8, m8, ta, mu
+; CHECK-NEXT:    vaadd.vx v8, v8, a0
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 64 x i8> @llvm.riscv.vaadd.rm.nxv64i8.i8(
+    <vscale x 64 x i8> undef,
+    <vscale x 64 x i8> %0,
+    i8 %1,
+    i64 %2,
+    i64 4)
+
+  ret <vscale x 64 x i8> %a
+}
+
+declare <vscale x 64 x i8> @llvm.riscv.vaadd.rm.mask.nxv64i8.i8(
+  <vscale x 64 x i8>,
+  <vscale x 64 x i8>,
+  i8,
+  <vscale x 64 x i1>,
+  i64,
+  i64,
+  i64);
+
+define <vscale x 64 x i8> @intrinsic_vaadd_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 {
+; CHECK-LABEL: intrinsic_vaadd_mask_vx_nxv64i8_nxv64i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e8, m8, ta, mu
+; CHECK-NEXT:    vaadd.vx v8, v16, a0, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 64 x i8> @llvm.riscv.vaadd.rm.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, i64 1,
+    i64 4)
+
+  ret <vscale x 64 x i8> %a
+}
+
+declare <vscale x 1 x i16> @llvm.riscv.vaadd.rm.nxv1i16.i16(
+  <vscale x 1 x i16>,
+  <vscale x 1 x i16>,
+  i16,
+  i64,
+  i64);
+
+define <vscale x 1 x i16> @intrinsic_vaadd_vx_nxv1i16_nxv1i16_i16(<vscale x 1 x i16> %0, i16 %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vaadd_vx_nxv1i16_nxv1i16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e16, mf4, ta, mu
+; CHECK-NEXT:    vaadd.vx v8, v8, a0
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i16> @llvm.riscv.vaadd.rm.nxv1i16.i16(
+    <vscale x 1 x i16> undef,
+    <vscale x 1 x i16> %0,
+    i16 %1,
+    i64 %2,
+    i64 4)
+
+  ret <vscale x 1 x i16> %a
+}
+
+declare <vscale x 1 x i16> @llvm.riscv.vaadd.rm.mask.nxv1i16.i16(
+  <vscale x 1 x i16>,
+  <vscale x 1 x i16>,
+  i16,
+  <vscale x 1 x i1>,
+  i64,
+  i64,
+  i64);
+
+define <vscale x 1 x i16> @intrinsic_vaadd_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 {
+; CHECK-LABEL: intrinsic_vaadd_mask_vx_nxv1i16_nxv1i16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e16, mf4, ta, mu
+; CHECK-NEXT:    vaadd.vx v8, v9, a0, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i16> @llvm.riscv.vaadd.rm.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, i64 1,
+    i64 4)
+
+  ret <vscale x 1 x i16> %a
+}
+
+declare <vscale x 2 x i16> @llvm.riscv.vaadd.rm.nxv2i16.i16(
+  <vscale x 2 x i16>,
+  <vscale x 2 x i16>,
+  i16,
+  i64,
+  i64);
+
+define <vscale x 2 x i16> @intrinsic_vaadd_vx_nxv2i16_nxv2i16_i16(<vscale x 2 x i16> %0, i16 %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vaadd_vx_nxv2i16_nxv2i16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e16, mf2, ta, mu
+; CHECK-NEXT:    vaadd.vx v8, v8, a0
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i16> @llvm.riscv.vaadd.rm.nxv2i16.i16(
+    <vscale x 2 x i16> undef,
+    <vscale x 2 x i16> %0,
+    i16 %1,
+    i64 %2,
+    i64 4)
+
+  ret <vscale x 2 x i16> %a
+}
+
+declare <vscale x 2 x i16> @llvm.riscv.vaadd.rm.mask.nxv2i16.i16(
+  <vscale x 2 x i16>,
+  <vscale x 2 x i16>,
+  i16,
+  <vscale x 2 x i1>,
+  i64,
+  i64,
+  i64);
+
+define <vscale x 2 x i16> @intrinsic_vaadd_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 {
+; CHECK-LABEL: intrinsic_vaadd_mask_vx_nxv2i16_nxv2i16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e16, mf2, ta, mu
+; CHECK-NEXT:    vaadd.vx v8, v9, a0, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i16> @llvm.riscv.vaadd.rm.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, i64 1,
+    i64 4)
+
+  ret <vscale x 2 x i16> %a
+}
+
+declare <vscale x 4 x i16> @llvm.riscv.vaadd.rm.nxv4i16.i16(
+  <vscale x 4 x i16>,
+  <vscale x 4 x i16>,
+  i16,
+  i64,
+  i64);
+
+define <vscale x 4 x i16> @intrinsic_vaadd_vx_nxv4i16_nxv4i16_i16(<vscale x 4 x i16> %0, i16 %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vaadd_vx_nxv4i16_nxv4i16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e16, m1, ta, mu
+; CHECK-NEXT:    vaadd.vx v8, v8, a0
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i16> @llvm.riscv.vaadd.rm.nxv4i16.i16(
+    <vscale x 4 x i16> undef,
+    <vscale x 4 x i16> %0,
+    i16 %1,
+    i64 %2,
+    i64 4)
+
+  ret <vscale x 4 x i16> %a
+}
+
+declare <vscale x 4 x i16> @llvm.riscv.vaadd.rm.mask.nxv4i16.i16(
+  <vscale x 4 x i16>,
+  <vscale x 4 x i16>,
+  i16,
+  <vscale x 4 x i1>,
+  i64,
+  i64,
+  i64);
+
+define <vscale x 4 x i16> @intrinsic_vaadd_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 {
+; CHECK-LABEL: intrinsic_vaadd_mask_vx_nxv4i16_nxv4i16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e16, m1, ta, mu
+; CHECK-NEXT:    vaadd.vx v8, v9, a0, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i16> @llvm.riscv.vaadd.rm.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, i64 1,
+    i64 4)
+
+  ret <vscale x 4 x i16> %a
+}
+
+declare <vscale x 8 x i16> @llvm.riscv.vaadd.rm.nxv8i16.i16(
+  <vscale x 8 x i16>,
+  <vscale x 8 x i16>,
+  i16,
+  i64,
+  i64);
+
+define <vscale x 8 x i16> @intrinsic_vaadd_vx_nxv8i16_nxv8i16_i16(<vscale x 8 x i16> %0, i16 %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vaadd_vx_nxv8i16_nxv8i16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e16, m2, ta, mu
+; CHECK-NEXT:    vaadd.vx v8, v8, a0
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i16> @llvm.riscv.vaadd.rm.nxv8i16.i16(
+    <vscale x 8 x i16> undef,
+    <vscale x 8 x i16> %0,
+    i16 %1,
+    i64 %2,
+    i64 4)
+
+  ret <vscale x 8 x i16> %a
+}
+
+declare <vscale x 8 x i16> @llvm.riscv.vaadd.rm.mask.nxv8i16.i16(
+  <vscale x 8 x i16>,
+  <vscale x 8 x i16>,
+  i16,
+  <vscale x 8 x i1>,
+  i64,
+  i64,
+  i64);
+
+define <vscale x 8 x i16> @intrinsic_vaadd_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 {
+; CHECK-LABEL: intrinsic_vaadd_mask_vx_nxv8i16_nxv8i16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e16, m2, ta, mu
+; CHECK-NEXT:    vaadd.vx v8, v10, a0, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i16> @llvm.riscv.vaadd.rm.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, i64 1,
+    i64 4)
+
+  ret <vscale x 8 x i16> %a
+}
+
+declare <vscale x 16 x i16> @llvm.riscv.vaadd.rm.nxv16i16.i16(
+  <vscale x 16 x i16>,
+  <vscale x 16 x i16>,
+  i16,
+  i64,
+  i64);
+
+define <vscale x 16 x i16> @intrinsic_vaadd_vx_nxv16i16_nxv16i16_i16(<vscale x 16 x i16> %0, i16 %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vaadd_vx_nxv16i16_nxv16i16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e16, m4, ta, mu
+; CHECK-NEXT:    vaadd.vx v8, v8, a0
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 16 x i16> @llvm.riscv.vaadd.rm.nxv16i16.i16(
+    <vscale x 16 x i16> undef,
+    <vscale x 16 x i16> %0,
+    i16 %1,
+    i64 %2,
+    i64 4)
+
+  ret <vscale x 16 x i16> %a
+}
+
+declare <vscale x 16 x i16> @llvm.riscv.vaadd.rm.mask.nxv16i16.i16(
+  <vscale x 16 x i16>,
+  <vscale x 16 x i16>,
+  i16,
+  <vscale x 16 x i1>,
+  i64,
+  i64,
+  i64);
+
+define <vscale x 16 x i16> @intrinsic_vaadd_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 {
+; CHECK-LABEL: intrinsic_vaadd_mask_vx_nxv16i16_nxv16i16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e16, m4, ta, mu
+; CHECK-NEXT:    vaadd.vx v8, v12, a0, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 16 x i16> @llvm.riscv.vaadd.rm.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, i64 1,
+    i64 4)
+
+  ret <vscale x 16 x i16> %a
+}
+
+declare <vscale x 32 x i16> @llvm.riscv.vaadd.rm.nxv32i16.i16(
+  <vscale x 32 x i16>,
+  <vscale x 32 x i16>,
+  i16,
+  i64,
+  i64);
+
+define <vscale x 32 x i16> @intrinsic_vaadd_vx_nxv32i16_nxv32i16_i16(<vscale x 32 x i16> %0, i16 %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vaadd_vx_nxv32i16_nxv32i16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e16, m8, ta, mu
+; CHECK-NEXT:    vaadd.vx v8, v8, a0
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 32 x i16> @llvm.riscv.vaadd.rm.nxv32i16.i16(
+    <vscale x 32 x i16> undef,
+    <vscale x 32 x i16> %0,
+    i16 %1,
+    i64 %2,
+    i64 4)
+
+  ret <vscale x 32 x i16> %a
+}
+
+declare <vscale x 32 x i16> @llvm.riscv.vaadd.rm.mask.nxv32i16.i16(
+  <vscale x 32 x i16>,
+  <vscale x 32 x i16>,
+  i16,
+  <vscale x 32 x i1>,
+  i64,
+  i64,
+  i64);
+
+define <vscale x 32 x i16> @intrinsic_vaadd_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 {
+; CHECK-LABEL: intrinsic_vaadd_mask_vx_nxv32i16_nxv32i16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e16, m8, ta, mu
+; CHECK-NEXT:    vaadd.vx v8, v16, a0, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 32 x i16> @llvm.riscv.vaadd.rm.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, i64 1,
+    i64 4)
+
+  ret <vscale x 32 x i16> %a
+}
+
+declare <vscale x 1 x i32> @llvm.riscv.vaadd.rm.nxv1i32.i32(
+  <vscale x 1 x i32>,
+  <vscale x 1 x i32>,
+  i32,
+  i64,
+  i64);
+
+define <vscale x 1 x i32> @intrinsic_vaadd_vx_nxv1i32_nxv1i32_i32(<vscale x 1 x i32> %0, i32 %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vaadd_vx_nxv1i32_nxv1i32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e32, mf2, ta, mu
+; CHECK-NEXT:    vaadd.vx v8, v8, a0
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i32> @llvm.riscv.vaadd.rm.nxv1i32.i32(
+    <vscale x 1 x i32> undef,
+    <vscale x 1 x i32> %0,
+    i32 %1,
+    i64 %2,
+    i64 4)
+
+  ret <vscale x 1 x i32> %a
+}
+
+declare <vscale x 1 x i32> @llvm.riscv.vaadd.rm.mask.nxv1i32.i32(
+  <vscale x 1 x i32>,
+  <vscale x 1 x i32>,
+  i32,
+  <vscale x 1 x i1>,
+  i64,
+  i64,
+  i64);
+
+define <vscale x 1 x i32> @intrinsic_vaadd_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 {
+; CHECK-LABEL: intrinsic_vaadd_mask_vx_nxv1i32_nxv1i32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e32, mf2, ta, mu
+; CHECK-NEXT:    vaadd.vx v8, v9, a0, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i32> @llvm.riscv.vaadd.rm.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, i64 1,
+    i64 4)
+
+  ret <vscale x 1 x i32> %a
+}
+
+declare <vscale x 2 x i32> @llvm.riscv.vaadd.rm.nxv2i32.i32(
+  <vscale x 2 x i32>,
+  <vscale x 2 x i32>,
+  i32,
+  i64,
+  i64);
+
+define <vscale x 2 x i32> @intrinsic_vaadd_vx_nxv2i32_nxv2i32_i32(<vscale x 2 x i32> %0, i32 %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vaadd_vx_nxv2i32_nxv2i32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e32, m1, ta, mu
+; CHECK-NEXT:    vaadd.vx v8, v8, a0
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i32> @llvm.riscv.vaadd.rm.nxv2i32.i32(
+    <vscale x 2 x i32> undef,
+    <vscale x 2 x i32> %0,
+    i32 %1,
+    i64 %2,
+    i64 4)
+
+  ret <vscale x 2 x i32> %a
+}
+
+declare <vscale x 2 x i32> @llvm.riscv.vaadd.rm.mask.nxv2i32.i32(
+  <vscale x 2 x i32>,
+  <vscale x 2 x i32>,
+  i32,
+  <vscale x 2 x i1>,
+  i64,
+  i64,
+  i64);
+
+define <vscale x 2 x i32> @intrinsic_vaadd_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 {
+; CHECK-LABEL: intrinsic_vaadd_mask_vx_nxv2i32_nxv2i32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e32, m1, ta, mu
+; CHECK-NEXT:    vaadd.vx v8, v9, a0, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i32> @llvm.riscv.vaadd.rm.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, i64 1,
+    i64 4)
+
+  ret <vscale x 2 x i32> %a
+}
+
+declare <vscale x 4 x i32> @llvm.riscv.vaadd.rm.nxv4i32.i32(
+  <vscale x 4 x i32>,
+  <vscale x 4 x i32>,
+  i32,
+  i64,
+  i64);
+
+define <vscale x 4 x i32> @intrinsic_vaadd_vx_nxv4i32_nxv4i32_i32(<vscale x 4 x i32> %0, i32 %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vaadd_vx_nxv4i32_nxv4i32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e32, m2, ta, mu
+; CHECK-NEXT:    vaadd.vx v8, v8, a0
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i32> @llvm.riscv.vaadd.rm.nxv4i32.i32(
+    <vscale x 4 x i32> undef,
+    <vscale x 4 x i32> %0,
+    i32 %1,
+    i64 %2,
+    i64 4)
+
+  ret <vscale x 4 x i32> %a
+}
+
+declare <vscale x 4 x i32> @llvm.riscv.vaadd.rm.mask.nxv4i32.i32(
+  <vscale x 4 x i32>,
+  <vscale x 4 x i32>,
+  i32,
+  <vscale x 4 x i1>,
+  i64,
+  i64,
+  i64);
+
+define <vscale x 4 x i32> @intrinsic_vaadd_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 {
+; CHECK-LABEL: intrinsic_vaadd_mask_vx_nxv4i32_nxv4i32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e32, m2, ta, mu
+; CHECK-NEXT:    vaadd.vx v8, v10, a0, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i32> @llvm.riscv.vaadd.rm.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, i64 1,
+    i64 4)
+
+  ret <vscale x 4 x i32> %a
+}
+
+declare <vscale x 8 x i32> @llvm.riscv.vaadd.rm.nxv8i32.i32(
+  <vscale x 8 x i32>,
+  <vscale x 8 x i32>,
+  i32,
+  i64,
+  i64);
+
+define <vscale x 8 x i32> @intrinsic_vaadd_vx_nxv8i32_nxv8i32_i32(<vscale x 8 x i32> %0, i32 %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vaadd_vx_nxv8i32_nxv8i32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e32, m4, ta, mu
+; CHECK-NEXT:    vaadd.vx v8, v8, a0
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i32> @llvm.riscv.vaadd.rm.nxv8i32.i32(
+    <vscale x 8 x i32> undef,
+    <vscale x 8 x i32> %0,
+    i32 %1,
+    i64 %2,
+    i64 4)
+
+  ret <vscale x 8 x i32> %a
+}
+
+declare <vscale x 8 x i32> @llvm.riscv.vaadd.rm.mask.nxv8i32.i32(
+  <vscale x 8 x i32>,
+  <vscale x 8 x i32>,
+  i32,
+  <vscale x 8 x i1>,
+  i64,
+  i64,
+  i64);
+
+define <vscale x 8 x i32> @intrinsic_vaadd_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 {
+; CHECK-LABEL: intrinsic_vaadd_mask_vx_nxv8i32_nxv8i32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e32, m4, ta, mu
+; CHECK-NEXT:    vaadd.vx v8, v12, a0, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i32> @llvm.riscv.vaadd.rm.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, i64 1,
+    i64 4)
+
+  ret <vscale x 8 x i32> %a
+}
+
+declare <vscale x 16 x i32> @llvm.riscv.vaadd.rm.nxv16i32.i32(
+  <vscale x 16 x i32>,
+  <vscale x 16 x i32>,
+  i32,
+  i64,
+  i64);
+
+define <vscale x 16 x i32> @intrinsic_vaadd_vx_nxv16i32_nxv16i32_i32(<vscale x 16 x i32> %0, i32 %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vaadd_vx_nxv16i32_nxv16i32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e32, m8, ta, mu
+; CHECK-NEXT:    vaadd.vx v8, v8, a0
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 16 x i32> @llvm.riscv.vaadd.rm.nxv16i32.i32(
+    <vscale x 16 x i32> undef,
+    <vscale x 16 x i32> %0,
+    i32 %1,
+    i64 %2,
+    i64 4)
+
+  ret <vscale x 16 x i32> %a
+}
+
+declare <vscale x 16 x i32> @llvm.riscv.vaadd.rm.mask.nxv16i32.i32(
+  <vscale x 16 x i32>,
+  <vscale x 16 x i32>,
+  i32,
+  <vscale x 16 x i1>,
+  i64,
+  i64,
+  i64);
+
+define <vscale x 16 x i32> @intrinsic_vaadd_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 {
+; CHECK-LABEL: intrinsic_vaadd_mask_vx_nxv16i32_nxv16i32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e32, m8, ta, mu
+; CHECK-NEXT:    vaadd.vx v8, v16, a0, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 16 x i32> @llvm.riscv.vaadd.rm.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, i64 1,
+    i64 4)
+
+  ret <vscale x 16 x i32> %a
+}
+
+declare <vscale x 1 x i64> @llvm.riscv.vaadd.rm.nxv1i64.i64(
+  <vscale x 1 x i64>,
+  <vscale x 1 x i64>,
+  i64,
+  i64,
+  i64);
+
+define <vscale x 1 x i64> @intrinsic_vaadd_vx_nxv1i64_nxv1i64_i64(<vscale x 1 x i64> %0, i64 %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vaadd_vx_nxv1i64_nxv1i64_i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e64, m1, ta, mu
+; CHECK-NEXT:    vaadd.vx v8, v8, a0
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i64> @llvm.riscv.vaadd.rm.nxv1i64.i64(
+    <vscale x 1 x i64> undef,
+    <vscale x 1 x i64> %0,
+    i64 %1,
+    i64 %2,
+    i64 4)
+
+  ret <vscale x 1 x i64> %a
+}
+
+declare <vscale x 1 x i64> @llvm.riscv.vaadd.rm.mask.nxv1i64.i64(
+  <vscale x 1 x i64>,
+  <vscale x 1 x i64>,
+  i64,
+  <vscale x 1 x i1>,
+  i64,
+  i64,
+  i64);
+
+define <vscale x 1 x i64> @intrinsic_vaadd_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 {
+; CHECK-LABEL: intrinsic_vaadd_mask_vx_nxv1i64_nxv1i64_i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e64, m1, ta, mu
+; CHECK-NEXT:    vaadd.vx v8, v9, a0, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i64> @llvm.riscv.vaadd.rm.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, i64 1,
+    i64 4)
+
+  ret <vscale x 1 x i64> %a
+}
+
+declare <vscale x 2 x i64> @llvm.riscv.vaadd.rm.nxv2i64.i64(
+  <vscale x 2 x i64>,
+  <vscale x 2 x i64>,
+  i64,
+  i64,
+  i64);
+
+define <vscale x 2 x i64> @intrinsic_vaadd_vx_nxv2i64_nxv2i64_i64(<vscale x 2 x i64> %0, i64 %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vaadd_vx_nxv2i64_nxv2i64_i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e64, m2, ta, mu
+; CHECK-NEXT:    vaadd.vx v8, v8, a0
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i64> @llvm.riscv.vaadd.rm.nxv2i64.i64(
+    <vscale x 2 x i64> undef,
+    <vscale x 2 x i64> %0,
+    i64 %1,
+    i64 %2,
+    i64 4)
+
+  ret <vscale x 2 x i64> %a
+}
+
+declare <vscale x 2 x i64> @llvm.riscv.vaadd.rm.mask.nxv2i64.i64(
+  <vscale x 2 x i64>,
+  <vscale x 2 x i64>,
+  i64,
+  <vscale x 2 x i1>,
+  i64,
+  i64,
+  i64);
+
+define <vscale x 2 x i64> @intrinsic_vaadd_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 {
+; CHECK-LABEL: intrinsic_vaadd_mask_vx_nxv2i64_nxv2i64_i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e64, m2, ta, mu
+; CHECK-NEXT:    vaadd.vx v8, v10, a0, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 2 x i64> @llvm.riscv.vaadd.rm.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, i64 1,
+    i64 4)
+
+  ret <vscale x 2 x i64> %a
+}
+
+declare <vscale x 4 x i64> @llvm.riscv.vaadd.rm.nxv4i64.i64(
+  <vscale x 4 x i64>,
+  <vscale x 4 x i64>,
+  i64,
+  i64,
+  i64);
+
+define <vscale x 4 x i64> @intrinsic_vaadd_vx_nxv4i64_nxv4i64_i64(<vscale x 4 x i64> %0, i64 %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vaadd_vx_nxv4i64_nxv4i64_i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e64, m4, ta, mu
+; CHECK-NEXT:    vaadd.vx v8, v8, a0
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i64> @llvm.riscv.vaadd.rm.nxv4i64.i64(
+    <vscale x 4 x i64> undef,
+    <vscale x 4 x i64> %0,
+    i64 %1,
+    i64 %2,
+    i64 4)
+
+  ret <vscale x 4 x i64> %a
+}
+
+declare <vscale x 4 x i64> @llvm.riscv.vaadd.rm.mask.nxv4i64.i64(
+  <vscale x 4 x i64>,
+  <vscale x 4 x i64>,
+  i64,
+  <vscale x 4 x i1>,
+  i64,
+  i64,
+  i64);
+
+define <vscale x 4 x i64> @intrinsic_vaadd_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 {
+; CHECK-LABEL: intrinsic_vaadd_mask_vx_nxv4i64_nxv4i64_i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e64, m4, ta, mu
+; CHECK-NEXT:    vaadd.vx v8, v12, a0, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 4 x i64> @llvm.riscv.vaadd.rm.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, i64 1,
+    i64 4)
+
+  ret <vscale x 4 x i64> %a
+}
+
+declare <vscale x 8 x i64> @llvm.riscv.vaadd.rm.nxv8i64.i64(
+  <vscale x 8 x i64>,
+  <vscale x 8 x i64>,
+  i64,
+  i64,
+  i64);
+
+define <vscale x 8 x i64> @intrinsic_vaadd_vx_nxv8i64_nxv8i64_i64(<vscale x 8 x i64> %0, i64 %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vaadd_vx_nxv8i64_nxv8i64_i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e64, m8, ta, mu
+; CHECK-NEXT:    vaadd.vx v8, v8, a0
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i64> @llvm.riscv.vaadd.rm.nxv8i64.i64(
+    <vscale x 8 x i64> undef,
+    <vscale x 8 x i64> %0,
+    i64 %1,
+    i64 %2,
+    i64 4)
+
+  ret <vscale x 8 x i64> %a
+}
+
+declare <vscale x 8 x i64> @llvm.riscv.vaadd.rm.mask.nxv8i64.i64(
+  <vscale x 8 x i64>,
+  <vscale x 8 x i64>,
+  i64,
+  <vscale x 8 x i1>,
+  i64,
+  i64,
+  i64);
+
+define <vscale x 8 x i64> @intrinsic_vaadd_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 {
+; CHECK-LABEL: intrinsic_vaadd_mask_vx_nxv8i64_nxv8i64_i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli zero, a1, e64, m8, ta, mu
+; CHECK-NEXT:    vaadd.vx v8, v16, a0, v0.t
+; CHECK-NEXT:    ret
+entry:
+  %a = call <vscale x 8 x i64> @llvm.riscv.vaadd.rm.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, i64 1,
+    i64 4)
+
+  ret <vscale x 8 x i64> %a
+}