[RISCV] Add intrinsics for vrgather instruction

[arcbbb]

Summary

This patch defines vrgather intrinsics and lower to V instructions.

We work with @rogfer01 from BSC to come out this patch.

Authored-by: Roger Ferrer Ibanez <[e-mail]>
Co-Authored-by: ShihPo Hung <[e-mail]>

[craig.topper]

LGTM

llvm/include/llvm/IR/IntrinsicsRISCV.td

let TargetPrefix = "riscv" in {
   defm vslideup : RISCVTernaryAAAX;
   defm vslidedown : RISCVTernaryAAAX;
 
   defm vslide1up : RISCVBinaryAAX;
   defm vslide1down : RISCVBinaryAAX;
   defm vfslide1up : RISCVBinaryAAX;
   defm vfslide1down : RISCVBinaryAAX;
 
+  defm vrgather : RISCVBinaryAAX;
+
   defm vaaddu : RISCVSaturatingBinaryAAX;
   defm vaadd : RISCVSaturatingBinaryAAX;
   defm vasubu : RISCVSaturatingBinaryAAX;
   defm vasub : RISCVSaturatingBinaryAAX;
 
   defm vsmul : RISCVSaturatingBinaryAAX;
 
   defm vssrl : RISCVSaturatingBinaryAAX;

llvm/lib/Target/RISCV/RISCVInstrInfoVPseudos.td

defset list<GroupVTypeInfo> GroupFloatVectors = {
       def VF64M4: GroupVTypeInfo<vfloat64m4_t, vfloat64m1_t, vbool16_t, 64,
                                   VRM4, V_M4, f64, FPR64>;
       def VF64M8: GroupVTypeInfo<vfloat64m8_t, vfloat64m1_t, vbool8_t,  64,
                                   VRM8, V_M8, f64, FPR64>;
     }
   }
 }
 
+// This functor is used to obtain the int vector type that has the same SEW and
+// multiplier as the input parameter type
+class GetIntVTypeInfo<VTypeInfo vti>
+{
+  // Equivalent integer vector type. Eg.
+  //   VI8M1 → VI8M1 (identity)
+  //   VF64M4 → VI64M4
+  VTypeInfo Vti = !cast<VTypeInfo>(!subst("VF", "VI", !cast<string>(vti)));
+}
+
 class VTypeInfoToWide<VTypeInfo vti, VTypeInfo wti>
 {
   VTypeInfo Vti = vti;
   VTypeInfo Wti = wti;
 }
 
 defset list<VTypeInfoToWide> AllWidenableIntVectors = {
   def : VTypeInfoToWide<VI8MF8,  VI16MF4>;
multiclass VPseudoBinary<VReg RetClass,
   let VLMul = MInfo.value in {
     def "_" # MInfo.MX : VPseudoBinaryNoMask<RetClass, Op1Class, Op2Class,
                                              Constraint>;
     def "_" # MInfo.MX # "_MASK" : VPseudoBinaryMask<RetClass, Op1Class, Op2Class,
                                                      Constraint>;
   }
 }
 
-multiclass VPseudoBinaryV_VV {
+multiclass VPseudoBinaryV_VV<string Constraint = ""> {
   foreach m = MxList.m in
-    defm _VV : VPseudoBinary<m.vrclass, m.vrclass, m.vrclass, m>;
+    defm _VV : VPseudoBinary<m.vrclass, m.vrclass, m.vrclass, m, Constraint>;
 }
 
 multiclass VPseudoBinaryV_VX<bit IsFloat, string Constraint = ""> {
   foreach m = MxList.m in
     defm !if(IsFloat, "_VF", "_VX") : VPseudoBinary<m.vrclass, m.vrclass,
                              !if(IsFloat, FPR32, GPR), m, Constraint>;
 }
 
-multiclass VPseudoBinaryV_VI<Operand ImmType = simm5> {
+multiclass VPseudoBinaryV_VI<Operand ImmType = simm5, string Constraint = ""> {
   foreach m = MxList.m in
-    defm _VI : VPseudoBinary<m.vrclass, m.vrclass, ImmType, m>;
+    defm _VI : VPseudoBinary<m.vrclass, m.vrclass, ImmType, m, Constraint>;
 }
 
 // We use earlyclobber here due to
 // * The destination EEW is smaller than the source EEW and the overlap is
 //   in the lowest-numbered part of the source register group is legal.
 //   Otherwise, it is illegal.
 // * The destination EEW is greater than the source EEW, the source EMUL is
 //   at least 1, and the overlap is in the highest-numbered part of the
defm !if(IsFloat, "_VF", "_VX") :
                     "@earlyclobber $rd">;
 }
 
 multiclass VPseudoBinaryM_VI {
   foreach m = MxList.m in
     defm _VI : VPseudoBinary<VR, m.vrclass, simm5, m, "@earlyclobber $rd">;
 }
 
-multiclass VPseudoBinaryV_VV_VX_VI<Operand ImmType = simm5> {
-  defm "" : VPseudoBinaryV_VV;
-  defm "" : VPseudoBinaryV_VX</*IsFloat=*/0>;
-  defm "" : VPseudoBinaryV_VI<ImmType>;
+multiclass VPseudoBinaryV_VV_VX_VI<Operand ImmType = simm5, string Constraint = ""> {
+  defm "" : VPseudoBinaryV_VV<Constraint>;
+  defm "" : VPseudoBinaryV_VX</*IsFloat=*/false, Constraint>;
+  defm "" : VPseudoBinaryV_VI<ImmType, Constraint>;
 }
 
 multiclass VPseudoBinaryV_VV_VX<bit IsFloat = 0> {
   defm "" : VPseudoBinaryV_VV;
   defm "" : VPseudoBinaryV_VX<IsFloat>;
 }
 
 multiclass VPseudoBinaryV_VX_VI<Operand ImmType = simm5> {
multiclass VPatBinaryV_VV<string intrinsic, string instruction,
                           list<VTypeInfo> vtilist> {
   foreach vti = vtilist in
     defm : VPatBinary<intrinsic, instruction, "VV",
                       vti.Vector, vti.Vector, vti.Vector, vti.Mask,
                       vti.SEW, vti.LMul, vti.RegClass,
                       vti.RegClass, vti.RegClass>;
 }
 
+multiclass VPatBinaryV_VV_INT<string intrinsic, string instruction,
+                          list<VTypeInfo> vtilist> {
+  foreach vti = vtilist in {
+    defvar ivti = GetIntVTypeInfo<vti>.Vti;
+    defm : VPatBinary<intrinsic, instruction, "VV",
+                      vti.Vector, vti.Vector, ivti.Vector, vti.Mask,
+                      vti.SEW, vti.LMul, vti.RegClass,
+                      vti.RegClass, vti.RegClass>;
+  }
+}
+
 multiclass VPatBinaryV_VX<string intrinsic, string instruction,
                           list<VTypeInfo> vtilist> {
   foreach vti = vtilist in
     defm : VPatBinary<intrinsic, instruction,
                       !if(!eq(vti.Scalar, XLenVT), "VX", "VF"),
                       vti.Vector, vti.Vector, vti.Scalar, vti.Mask,
                       vti.SEW, vti.LMul, vti.RegClass,
                       vti.RegClass, vti.ScalarRegClass>;
 }
 
+multiclass VPatBinaryV_VX_INT<string intrinsic, string instruction,
+                          list<VTypeInfo> vtilist> {
+  foreach vti = vtilist in
+    defm : VPatBinary<intrinsic, instruction, "VX",
+                      vti.Vector, vti.Vector, XLenVT, vti.Mask,
+                      vti.SEW, vti.LMul, vti.RegClass,
+                      vti.RegClass, GPR>;
+}
+
 multiclass VPatBinaryV_VI<string intrinsic, string instruction,
                           list<VTypeInfo> vtilist, Operand imm_type> {
   foreach vti = vtilist in
     defm : VPatBinary<intrinsic, instruction, "VI",
                       vti.Vector, vti.Vector, XLenVT, vti.Mask,
                       vti.SEW, vti.LMul, vti.RegClass,
                       vti.RegClass, imm_type>;
 }

 
 multiclass VPatBinaryM_VX_VI<string intrinsic, string instruction,
                              list<VTypeInfo> vtilist>
 {
   defm "" : VPatBinaryM_VX<intrinsic, instruction, vtilist>;
   defm "" : VPatBinaryM_VI<intrinsic, instruction, vtilist>;
 }
 
+multiclass VPatBinaryV_VV_VX_VI_INT<string intrinsic, string instruction,
+                                    list<VTypeInfo> vtilist, Operand ImmType = simm5>
+{
+  defm "" : VPatBinaryV_VV_INT<intrinsic, instruction, vtilist>;
+  defm "" : VPatBinaryV_VX_INT<intrinsic, instruction, vtilist>;
+  defm "" : VPatBinaryV_VI<intrinsic, instruction, vtilist, ImmType>;
+}
+
 multiclass VPatReductionV_VS<string intrinsic, string instruction, bit IsFloat = 0> {
   foreach vti = !if(IsFloat, NoGroupFloatVectors, NoGroupIntegerVectors) in
   {
     defvar vectorM1 = !cast<VTypeInfo>(!if(IsFloat, "VF", "VI") # vti.SEW # "M1");
     defm : VPatTernary<intrinsic, instruction, "VS",
                        vectorM1.Vector, vti.Vector,
                        vectorM1.Vector, vti.Mask,
                        vti.SEW, vti.LMul,

 } // Predicates = [HasStdExtV]
 
 let Predicates = [HasStdExtV, HasStdExtF] in {
   defm PseudoVFSLIDE1UP  : VPseudoBinaryV_VX</*IsFloat*/true, "@earlyclobber $rd">;
   defm PseudoVFSLIDE1DOWN : VPseudoBinaryV_VX</*IsFloat*/true>;
 } // Predicates = [HasStdExtV, HasStdExtF]
 
 //===----------------------------------------------------------------------===//
+// 17.4. Vector Register Gather Instructions
+//===----------------------------------------------------------------------===//
+defm PseudoVRGATHER    : VPseudoBinaryV_VV_VX_VI<uimm5, "@earlyclobber $rd">;
+
+//===----------------------------------------------------------------------===//
 // Patterns.
 //===----------------------------------------------------------------------===//
 let Predicates = [HasStdExtV] in {
 
 //===----------------------------------------------------------------------===//
 // 7. Vector Loads and Stores
 //===----------------------------------------------------------------------===//
 

 
 let Predicates = [HasStdExtV, HasStdExtF] in {
   defm "" : VPatTernaryV_VX_VI<"int_riscv_vslideup", "PseudoVSLIDEUP", AllFloatVectors, uimm5>;
   defm "" : VPatTernaryV_VX_VI<"int_riscv_vslidedown", "PseudoVSLIDEDOWN", AllFloatVectors, uimm5>;
   defm "" : VPatBinaryV_VX<"int_riscv_vfslide1up", "PseudoVFSLIDE1UP", AllFloatVectors>;
   defm "" : VPatBinaryV_VX<"int_riscv_vfslide1down", "PseudoVFSLIDE1DOWN", AllFloatVectors>;
 } // Predicates = [HasStdExtV, HasStdExtF]
 
+//===----------------------------------------------------------------------===//
+// 17.4. Vector Register Gather Instructions
+//===----------------------------------------------------------------------===//
+let Predicates = [HasStdExtV] in {
+  defm "" : VPatBinaryV_VV_VX_VI_INT<"int_riscv_vrgather", "PseudoVRGATHER",
+                                     AllIntegerVectors, uimm5>;
+} // Predicates = [HasStdExtV]
+
+let Predicates = [HasStdExtV, HasStdExtF] in {
+  defm "" : VPatBinaryV_VV_VX_VI_INT<"int_riscv_vrgather", "PseudoVRGATHER",
+                                     AllFloatVectors, uimm5>;
+} // Predicates = [HasStdExtV, HasStdExtF]
+
 // Include the non-intrinsic ISel patterns
 include "RISCVInstrInfoVSDPatterns.td"

llvm/test/CodeGen/RISCV/rvv/vrgather-rv32.ll

+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc -mtriple=riscv32 -mattr=+experimental-v,+f,+experimental-zfh -verify-machineinstrs \
+; RUN:   --riscv-no-aliases < %s | FileCheck %s
+declare <vscale x 1 x i8> @llvm.riscv.vrgather.nxv1i8.nxv1i8(
+  <vscale x 1 x i8>,
+  <vscale x 1 x i8>,
+  i32);
+
+define <vscale x 1 x i8> @intrinsic_vrgather_vv_nxv1i8_nxv1i8_nxv1i8(<vscale x 1 x i8> %0, <vscale x 1 x i8> %1, i32 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vv_nxv1i8_nxv1i8_nxv1i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e8,mf8,ta,mu
+; CHECK-NEXT:    vrgather.vv v25, v16, v17
+; CHECK-NEXT:    vmv1r.v v16, v25
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 1 x i8> @llvm.riscv.vrgather.nxv1i8.nxv1i8(
+    <vscale x 1 x i8> %0,
+    <vscale x 1 x i8> %1,
+    i32 %2)
+
+  ret <vscale x 1 x i8> %a
+}
+
+declare <vscale x 1 x i8> @llvm.riscv.vrgather.mask.nxv1i8.nxv1i8(
+  <vscale x 1 x i8>,
+  <vscale x 1 x i8>,
+  <vscale x 1 x i8>,
+  <vscale x 1 x i1>,
+  i32);
+
+define <vscale x 1 x i8> @intrinsic_vrgather_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, i32 %4) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vv_nxv1i8_nxv1i8_nxv1i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e8,mf8,ta,mu
+; CHECK-NEXT:    vrgather.vv v16, v17, v18, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 1 x i8> @llvm.riscv.vrgather.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,
+    i32 %4)
+
+  ret <vscale x 1 x i8> %a
+}
+
+declare <vscale x 2 x i8> @llvm.riscv.vrgather.nxv2i8.nxv2i8(
+  <vscale x 2 x i8>,
+  <vscale x 2 x i8>,
+  i32);
+
+define <vscale x 2 x i8> @intrinsic_vrgather_vv_nxv2i8_nxv2i8_nxv2i8(<vscale x 2 x i8> %0, <vscale x 2 x i8> %1, i32 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vv_nxv2i8_nxv2i8_nxv2i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e8,mf4,ta,mu
+; CHECK-NEXT:    vrgather.vv v25, v16, v17
+; CHECK-NEXT:    vmv1r.v v16, v25
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 2 x i8> @llvm.riscv.vrgather.nxv2i8.nxv2i8(
+    <vscale x 2 x i8> %0,
+    <vscale x 2 x i8> %1,
+    i32 %2)
+
+  ret <vscale x 2 x i8> %a
+}
+
+declare <vscale x 2 x i8> @llvm.riscv.vrgather.mask.nxv2i8.nxv2i8(
+  <vscale x 2 x i8>,
+  <vscale x 2 x i8>,
+  <vscale x 2 x i8>,
+  <vscale x 2 x i1>,
+  i32);
+
+define <vscale x 2 x i8> @intrinsic_vrgather_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, i32 %4) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vv_nxv2i8_nxv2i8_nxv2i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e8,mf4,ta,mu
+; CHECK-NEXT:    vrgather.vv v16, v17, v18, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 2 x i8> @llvm.riscv.vrgather.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,
+    i32 %4)
+
+  ret <vscale x 2 x i8> %a
+}
+
+declare <vscale x 4 x i8> @llvm.riscv.vrgather.nxv4i8.nxv4i8(
+  <vscale x 4 x i8>,
+  <vscale x 4 x i8>,
+  i32);
+
+define <vscale x 4 x i8> @intrinsic_vrgather_vv_nxv4i8_nxv4i8_nxv4i8(<vscale x 4 x i8> %0, <vscale x 4 x i8> %1, i32 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vv_nxv4i8_nxv4i8_nxv4i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e8,mf2,ta,mu
+; CHECK-NEXT:    vrgather.vv v25, v16, v17
+; CHECK-NEXT:    vmv1r.v v16, v25
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 4 x i8> @llvm.riscv.vrgather.nxv4i8.nxv4i8(
+    <vscale x 4 x i8> %0,
+    <vscale x 4 x i8> %1,
+    i32 %2)
+
+  ret <vscale x 4 x i8> %a
+}
+
+declare <vscale x 4 x i8> @llvm.riscv.vrgather.mask.nxv4i8.nxv4i8(
+  <vscale x 4 x i8>,
+  <vscale x 4 x i8>,
+  <vscale x 4 x i8>,
+  <vscale x 4 x i1>,
+  i32);
+
+define <vscale x 4 x i8> @intrinsic_vrgather_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, i32 %4) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vv_nxv4i8_nxv4i8_nxv4i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e8,mf2,ta,mu
+; CHECK-NEXT:    vrgather.vv v16, v17, v18, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 4 x i8> @llvm.riscv.vrgather.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,
+    i32 %4)
+
+  ret <vscale x 4 x i8> %a
+}
+
+declare <vscale x 8 x i8> @llvm.riscv.vrgather.nxv8i8.nxv8i8(
+  <vscale x 8 x i8>,
+  <vscale x 8 x i8>,
+  i32);
+
+define <vscale x 8 x i8> @intrinsic_vrgather_vv_nxv8i8_nxv8i8_nxv8i8(<vscale x 8 x i8> %0, <vscale x 8 x i8> %1, i32 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vv_nxv8i8_nxv8i8_nxv8i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e8,m1,ta,mu
+; CHECK-NEXT:    vrgather.vv v25, v16, v17
+; CHECK-NEXT:    vmv1r.v v16, v25
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 8 x i8> @llvm.riscv.vrgather.nxv8i8.nxv8i8(
+    <vscale x 8 x i8> %0,
+    <vscale x 8 x i8> %1,
+    i32 %2)
+
+  ret <vscale x 8 x i8> %a
+}
+
+declare <vscale x 8 x i8> @llvm.riscv.vrgather.mask.nxv8i8.nxv8i8(
+  <vscale x 8 x i8>,
+  <vscale x 8 x i8>,
+  <vscale x 8 x i8>,
+  <vscale x 8 x i1>,
+  i32);
+
+define <vscale x 8 x i8> @intrinsic_vrgather_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, i32 %4) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vv_nxv8i8_nxv8i8_nxv8i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e8,m1,ta,mu
+; CHECK-NEXT:    vrgather.vv v16, v17, v18, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 8 x i8> @llvm.riscv.vrgather.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,
+    i32 %4)
+
+  ret <vscale x 8 x i8> %a
+}
+
+declare <vscale x 16 x i8> @llvm.riscv.vrgather.nxv16i8.nxv16i8(
+  <vscale x 16 x i8>,
+  <vscale x 16 x i8>,
+  i32);
+
+define <vscale x 16 x i8> @intrinsic_vrgather_vv_nxv16i8_nxv16i8_nxv16i8(<vscale x 16 x i8> %0, <vscale x 16 x i8> %1, i32 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vv_nxv16i8_nxv16i8_nxv16i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e8,m2,ta,mu
+; CHECK-NEXT:    vrgather.vv v26, v16, v18
+; CHECK-NEXT:    vmv2r.v v16, v26
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 16 x i8> @llvm.riscv.vrgather.nxv16i8.nxv16i8(
+    <vscale x 16 x i8> %0,
+    <vscale x 16 x i8> %1,
+    i32 %2)
+
+  ret <vscale x 16 x i8> %a
+}
+
+declare <vscale x 16 x i8> @llvm.riscv.vrgather.mask.nxv16i8.nxv16i8(
+  <vscale x 16 x i8>,
+  <vscale x 16 x i8>,
+  <vscale x 16 x i8>,
+  <vscale x 16 x i1>,
+  i32);
+
+define <vscale x 16 x i8> @intrinsic_vrgather_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, i32 %4) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vv_nxv16i8_nxv16i8_nxv16i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e8,m2,ta,mu
+; CHECK-NEXT:    vrgather.vv v16, v18, v20, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 16 x i8> @llvm.riscv.vrgather.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,
+    i32 %4)
+
+  ret <vscale x 16 x i8> %a
+}
+
+declare <vscale x 32 x i8> @llvm.riscv.vrgather.nxv32i8.nxv32i8(
+  <vscale x 32 x i8>,
+  <vscale x 32 x i8>,
+  i32);
+
+define <vscale x 32 x i8> @intrinsic_vrgather_vv_nxv32i8_nxv32i8_nxv32i8(<vscale x 32 x i8> %0, <vscale x 32 x i8> %1, i32 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vv_nxv32i8_nxv32i8_nxv32i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e8,m4,ta,mu
+; CHECK-NEXT:    vrgather.vv v28, v16, v20
+; CHECK-NEXT:    vmv4r.v v16, v28
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 32 x i8> @llvm.riscv.vrgather.nxv32i8.nxv32i8(
+    <vscale x 32 x i8> %0,
+    <vscale x 32 x i8> %1,
+    i32 %2)
+
+  ret <vscale x 32 x i8> %a
+}
+
+declare <vscale x 32 x i8> @llvm.riscv.vrgather.mask.nxv32i8.nxv32i8(
+  <vscale x 32 x i8>,
+  <vscale x 32 x i8>,
+  <vscale x 32 x i8>,
+  <vscale x 32 x i1>,
+  i32);
+
+define <vscale x 32 x i8> @intrinsic_vrgather_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, i32 %4) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vv_nxv32i8_nxv32i8_nxv32i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a2, zero, e8,m4,ta,mu
+; CHECK-NEXT:    vle8.v v28, (a0)
+; CHECK-NEXT:    vsetvli a0, a1, e8,m4,ta,mu
+; CHECK-NEXT:    vrgather.vv v16, v20, v28, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 32 x i8> @llvm.riscv.vrgather.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,
+    i32 %4)
+
+  ret <vscale x 32 x i8> %a
+}
+
+declare <vscale x 64 x i8> @llvm.riscv.vrgather.nxv64i8.nxv64i8(
+  <vscale x 64 x i8>,
+  <vscale x 64 x i8>,
+  i32);
+
+define <vscale x 64 x i8> @intrinsic_vrgather_vv_nxv64i8_nxv64i8_nxv64i8(<vscale x 64 x i8> %0, <vscale x 64 x i8> %1, i32 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vv_nxv64i8_nxv64i8_nxv64i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a2, zero, e8,m8,ta,mu
+; CHECK-NEXT:    vle8.v v24, (a0)
+; CHECK-NEXT:    vsetvli a0, a1, e8,m8,ta,mu
+; CHECK-NEXT:    vrgather.vv v8, v16, v24
+; CHECK-NEXT:    vmv8r.v v16, v8
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 64 x i8> @llvm.riscv.vrgather.nxv64i8.nxv64i8(
+    <vscale x 64 x i8> %0,
+    <vscale x 64 x i8> %1,
+    i32 %2)
+
+  ret <vscale x 64 x i8> %a
+}
+
+declare <vscale x 64 x i8> @llvm.riscv.vrgather.mask.nxv64i8.nxv64i8(
+  <vscale x 64 x i8>,
+  <vscale x 64 x i8>,
+  <vscale x 64 x i8>,
+  <vscale x 64 x i1>,
+  i32);
+
+define <vscale x 64 x i8> @intrinsic_vrgather_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, i32 %4) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vv_nxv64i8_nxv64i8_nxv64i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a3, zero, e8,m8,ta,mu
+; CHECK-NEXT:    vle8.v v8, (a1)
+; CHECK-NEXT:    vle8.v v24, (a0)
+; CHECK-NEXT:    vsetvli a0, a2, e8,m8,ta,mu
+; CHECK-NEXT:    vrgather.vv v16, v24, v8, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 64 x i8> @llvm.riscv.vrgather.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,
+    i32 %4)
+
+  ret <vscale x 64 x i8> %a
+}
+
+declare <vscale x 1 x i16> @llvm.riscv.vrgather.nxv1i16.nxv1i16(
+  <vscale x 1 x i16>,
+  <vscale x 1 x i16>,
+  i32);
+
+define <vscale x 1 x i16> @intrinsic_vrgather_vv_nxv1i16_nxv1i16_nxv1i16(<vscale x 1 x i16> %0, <vscale x 1 x i16> %1, i32 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vv_nxv1i16_nxv1i16_nxv1i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e16,mf4,ta,mu
+; CHECK-NEXT:    vrgather.vv v25, v16, v17
+; CHECK-NEXT:    vmv1r.v v16, v25
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 1 x i16> @llvm.riscv.vrgather.nxv1i16.nxv1i16(
+    <vscale x 1 x i16> %0,
+    <vscale x 1 x i16> %1,
+    i32 %2)
+
+  ret <vscale x 1 x i16> %a
+}
+
+declare <vscale x 1 x i16> @llvm.riscv.vrgather.mask.nxv1i16.nxv1i16(
+  <vscale x 1 x i16>,
+  <vscale x 1 x i16>,
+  <vscale x 1 x i16>,
+  <vscale x 1 x i1>,
+  i32);
+
+define <vscale x 1 x i16> @intrinsic_vrgather_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, i32 %4) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vv_nxv1i16_nxv1i16_nxv1i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e16,mf4,ta,mu
+; CHECK-NEXT:    vrgather.vv v16, v17, v18, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 1 x i16> @llvm.riscv.vrgather.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,
+    i32 %4)
+
+  ret <vscale x 1 x i16> %a
+}
+
+declare <vscale x 2 x i16> @llvm.riscv.vrgather.nxv2i16.nxv2i16(
+  <vscale x 2 x i16>,
+  <vscale x 2 x i16>,
+  i32);
+
+define <vscale x 2 x i16> @intrinsic_vrgather_vv_nxv2i16_nxv2i16_nxv2i16(<vscale x 2 x i16> %0, <vscale x 2 x i16> %1, i32 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vv_nxv2i16_nxv2i16_nxv2i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e16,mf2,ta,mu
+; CHECK-NEXT:    vrgather.vv v25, v16, v17
+; CHECK-NEXT:    vmv1r.v v16, v25
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 2 x i16> @llvm.riscv.vrgather.nxv2i16.nxv2i16(
+    <vscale x 2 x i16> %0,
+    <vscale x 2 x i16> %1,
+    i32 %2)
+
+  ret <vscale x 2 x i16> %a
+}
+
+declare <vscale x 2 x i16> @llvm.riscv.vrgather.mask.nxv2i16.nxv2i16(
+  <vscale x 2 x i16>,
+  <vscale x 2 x i16>,
+  <vscale x 2 x i16>,
+  <vscale x 2 x i1>,
+  i32);
+
+define <vscale x 2 x i16> @intrinsic_vrgather_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, i32 %4) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vv_nxv2i16_nxv2i16_nxv2i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e16,mf2,ta,mu
+; CHECK-NEXT:    vrgather.vv v16, v17, v18, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 2 x i16> @llvm.riscv.vrgather.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,
+    i32 %4)
+
+  ret <vscale x 2 x i16> %a
+}
+
+declare <vscale x 4 x i16> @llvm.riscv.vrgather.nxv4i16.nxv4i16(
+  <vscale x 4 x i16>,
+  <vscale x 4 x i16>,
+  i32);
+
+define <vscale x 4 x i16> @intrinsic_vrgather_vv_nxv4i16_nxv4i16_nxv4i16(<vscale x 4 x i16> %0, <vscale x 4 x i16> %1, i32 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vv_nxv4i16_nxv4i16_nxv4i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e16,m1,ta,mu
+; CHECK-NEXT:    vrgather.vv v25, v16, v17
+; CHECK-NEXT:    vmv1r.v v16, v25
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 4 x i16> @llvm.riscv.vrgather.nxv4i16.nxv4i16(
+    <vscale x 4 x i16> %0,
+    <vscale x 4 x i16> %1,
+    i32 %2)
+
+  ret <vscale x 4 x i16> %a
+}
+
+declare <vscale x 4 x i16> @llvm.riscv.vrgather.mask.nxv4i16.nxv4i16(
+  <vscale x 4 x i16>,
+  <vscale x 4 x i16>,
+  <vscale x 4 x i16>,
+  <vscale x 4 x i1>,
+  i32);
+
+define <vscale x 4 x i16> @intrinsic_vrgather_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, i32 %4) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vv_nxv4i16_nxv4i16_nxv4i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e16,m1,ta,mu
+; CHECK-NEXT:    vrgather.vv v16, v17, v18, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 4 x i16> @llvm.riscv.vrgather.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,
+    i32 %4)
+
+  ret <vscale x 4 x i16> %a
+}
+
+declare <vscale x 8 x i16> @llvm.riscv.vrgather.nxv8i16.nxv8i16(
+  <vscale x 8 x i16>,
+  <vscale x 8 x i16>,
+  i32);
+
+define <vscale x 8 x i16> @intrinsic_vrgather_vv_nxv8i16_nxv8i16_nxv8i16(<vscale x 8 x i16> %0, <vscale x 8 x i16> %1, i32 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vv_nxv8i16_nxv8i16_nxv8i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e16,m2,ta,mu
+; CHECK-NEXT:    vrgather.vv v26, v16, v18
+; CHECK-NEXT:    vmv2r.v v16, v26
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 8 x i16> @llvm.riscv.vrgather.nxv8i16.nxv8i16(
+    <vscale x 8 x i16> %0,
+    <vscale x 8 x i16> %1,
+    i32 %2)
+
+  ret <vscale x 8 x i16> %a
+}
+
+declare <vscale x 8 x i16> @llvm.riscv.vrgather.mask.nxv8i16.nxv8i16(
+  <vscale x 8 x i16>,
+  <vscale x 8 x i16>,
+  <vscale x 8 x i16>,
+  <vscale x 8 x i1>,
+  i32);
+
+define <vscale x 8 x i16> @intrinsic_vrgather_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, i32 %4) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vv_nxv8i16_nxv8i16_nxv8i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e16,m2,ta,mu
+; CHECK-NEXT:    vrgather.vv v16, v18, v20, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 8 x i16> @llvm.riscv.vrgather.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,
+    i32 %4)
+
+  ret <vscale x 8 x i16> %a
+}
+
+declare <vscale x 16 x i16> @llvm.riscv.vrgather.nxv16i16.nxv16i16(
+  <vscale x 16 x i16>,
+  <vscale x 16 x i16>,
+  i32);
+
+define <vscale x 16 x i16> @intrinsic_vrgather_vv_nxv16i16_nxv16i16_nxv16i16(<vscale x 16 x i16> %0, <vscale x 16 x i16> %1, i32 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vv_nxv16i16_nxv16i16_nxv16i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e16,m4,ta,mu
+; CHECK-NEXT:    vrgather.vv v28, v16, v20
+; CHECK-NEXT:    vmv4r.v v16, v28
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 16 x i16> @llvm.riscv.vrgather.nxv16i16.nxv16i16(
+    <vscale x 16 x i16> %0,
+    <vscale x 16 x i16> %1,
+    i32 %2)
+
+  ret <vscale x 16 x i16> %a
+}
+
+declare <vscale x 16 x i16> @llvm.riscv.vrgather.mask.nxv16i16.nxv16i16(
+  <vscale x 16 x i16>,
+  <vscale x 16 x i16>,
+  <vscale x 16 x i16>,
+  <vscale x 16 x i1>,
+  i32);
+
+define <vscale x 16 x i16> @intrinsic_vrgather_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, i32 %4) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vv_nxv16i16_nxv16i16_nxv16i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a2, zero, e16,m4,ta,mu
+; CHECK-NEXT:    vle16.v v28, (a0)
+; CHECK-NEXT:    vsetvli a0, a1, e16,m4,ta,mu
+; CHECK-NEXT:    vrgather.vv v16, v20, v28, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 16 x i16> @llvm.riscv.vrgather.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,
+    i32 %4)
+
+  ret <vscale x 16 x i16> %a
+}
+
+declare <vscale x 32 x i16> @llvm.riscv.vrgather.nxv32i16.nxv32i16(
+  <vscale x 32 x i16>,
+  <vscale x 32 x i16>,
+  i32);
+
+define <vscale x 32 x i16> @intrinsic_vrgather_vv_nxv32i16_nxv32i16_nxv32i16(<vscale x 32 x i16> %0, <vscale x 32 x i16> %1, i32 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vv_nxv32i16_nxv32i16_nxv32i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a2, zero, e16,m8,ta,mu
+; CHECK-NEXT:    vle16.v v24, (a0)
+; CHECK-NEXT:    vsetvli a0, a1, e16,m8,ta,mu
+; CHECK-NEXT:    vrgather.vv v8, v16, v24
+; CHECK-NEXT:    vmv8r.v v16, v8
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 32 x i16> @llvm.riscv.vrgather.nxv32i16.nxv32i16(
+    <vscale x 32 x i16> %0,
+    <vscale x 32 x i16> %1,
+    i32 %2)
+
+  ret <vscale x 32 x i16> %a
+}
+
+declare <vscale x 32 x i16> @llvm.riscv.vrgather.mask.nxv32i16.nxv32i16(
+  <vscale x 32 x i16>,
+  <vscale x 32 x i16>,
+  <vscale x 32 x i16>,
+  <vscale x 32 x i1>,
+  i32);
+
+define <vscale x 32 x i16> @intrinsic_vrgather_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, i32 %4) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vv_nxv32i16_nxv32i16_nxv32i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a3, zero, e16,m8,ta,mu
+; CHECK-NEXT:    vle16.v v8, (a1)
+; CHECK-NEXT:    vle16.v v24, (a0)
+; CHECK-NEXT:    vsetvli a0, a2, e16,m8,ta,mu
+; CHECK-NEXT:    vrgather.vv v16, v24, v8, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 32 x i16> @llvm.riscv.vrgather.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,
+    i32 %4)
+
+  ret <vscale x 32 x i16> %a
+}
+
+declare <vscale x 1 x i32> @llvm.riscv.vrgather.nxv1i32.nxv1i32(
+  <vscale x 1 x i32>,
+  <vscale x 1 x i32>,
+  i32);
+
+define <vscale x 1 x i32> @intrinsic_vrgather_vv_nxv1i32_nxv1i32_nxv1i32(<vscale x 1 x i32> %0, <vscale x 1 x i32> %1, i32 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vv_nxv1i32_nxv1i32_nxv1i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e32,mf2,ta,mu
+; CHECK-NEXT:    vrgather.vv v25, v16, v17
+; CHECK-NEXT:    vmv1r.v v16, v25
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 1 x i32> @llvm.riscv.vrgather.nxv1i32.nxv1i32(
+    <vscale x 1 x i32> %0,
+    <vscale x 1 x i32> %1,
+    i32 %2)
+
+  ret <vscale x 1 x i32> %a
+}
+
+declare <vscale x 1 x i32> @llvm.riscv.vrgather.mask.nxv1i32.nxv1i32(
+  <vscale x 1 x i32>,
+  <vscale x 1 x i32>,
+  <vscale x 1 x i32>,
+  <vscale x 1 x i1>,
+  i32);
+
+define <vscale x 1 x i32> @intrinsic_vrgather_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, i32 %4) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vv_nxv1i32_nxv1i32_nxv1i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e32,mf2,ta,mu
+; CHECK-NEXT:    vrgather.vv v16, v17, v18, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 1 x i32> @llvm.riscv.vrgather.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,
+    i32 %4)
+
+  ret <vscale x 1 x i32> %a
+}
+
+declare <vscale x 2 x i32> @llvm.riscv.vrgather.nxv2i32.nxv2i32(
+  <vscale x 2 x i32>,
+  <vscale x 2 x i32>,
+  i32);
+
+define <vscale x 2 x i32> @intrinsic_vrgather_vv_nxv2i32_nxv2i32_nxv2i32(<vscale x 2 x i32> %0, <vscale x 2 x i32> %1, i32 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vv_nxv2i32_nxv2i32_nxv2i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e32,m1,ta,mu
+; CHECK-NEXT:    vrgather.vv v25, v16, v17
+; CHECK-NEXT:    vmv1r.v v16, v25
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 2 x i32> @llvm.riscv.vrgather.nxv2i32.nxv2i32(
+    <vscale x 2 x i32> %0,
+    <vscale x 2 x i32> %1,
+    i32 %2)
+
+  ret <vscale x 2 x i32> %a
+}
+
+declare <vscale x 2 x i32> @llvm.riscv.vrgather.mask.nxv2i32.nxv2i32(
+  <vscale x 2 x i32>,
+  <vscale x 2 x i32>,
+  <vscale x 2 x i32>,
+  <vscale x 2 x i1>,
+  i32);
+
+define <vscale x 2 x i32> @intrinsic_vrgather_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, i32 %4) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vv_nxv2i32_nxv2i32_nxv2i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e32,m1,ta,mu
+; CHECK-NEXT:    vrgather.vv v16, v17, v18, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 2 x i32> @llvm.riscv.vrgather.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,
+    i32 %4)
+
+  ret <vscale x 2 x i32> %a
+}
+
+declare <vscale x 4 x i32> @llvm.riscv.vrgather.nxv4i32.nxv4i32(
+  <vscale x 4 x i32>,
+  <vscale x 4 x i32>,
+  i32);
+
+define <vscale x 4 x i32> @intrinsic_vrgather_vv_nxv4i32_nxv4i32_nxv4i32(<vscale x 4 x i32> %0, <vscale x 4 x i32> %1, i32 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vv_nxv4i32_nxv4i32_nxv4i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e32,m2,ta,mu
+; CHECK-NEXT:    vrgather.vv v26, v16, v18
+; CHECK-NEXT:    vmv2r.v v16, v26
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 4 x i32> @llvm.riscv.vrgather.nxv4i32.nxv4i32(
+    <vscale x 4 x i32> %0,
+    <vscale x 4 x i32> %1,
+    i32 %2)
+
+  ret <vscale x 4 x i32> %a
+}
+
+declare <vscale x 4 x i32> @llvm.riscv.vrgather.mask.nxv4i32.nxv4i32(
+  <vscale x 4 x i32>,
+  <vscale x 4 x i32>,
+  <vscale x 4 x i32>,
+  <vscale x 4 x i1>,
+  i32);
+
+define <vscale x 4 x i32> @intrinsic_vrgather_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, i32 %4) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vv_nxv4i32_nxv4i32_nxv4i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e32,m2,ta,mu
+; CHECK-NEXT:    vrgather.vv v16, v18, v20, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 4 x i32> @llvm.riscv.vrgather.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,
+    i32 %4)
+
+  ret <vscale x 4 x i32> %a
+}
+
+declare <vscale x 8 x i32> @llvm.riscv.vrgather.nxv8i32.nxv8i32(
+  <vscale x 8 x i32>,
+  <vscale x 8 x i32>,
+  i32);
+
+define <vscale x 8 x i32> @intrinsic_vrgather_vv_nxv8i32_nxv8i32_nxv8i32(<vscale x 8 x i32> %0, <vscale x 8 x i32> %1, i32 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vv_nxv8i32_nxv8i32_nxv8i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e32,m4,ta,mu
+; CHECK-NEXT:    vrgather.vv v28, v16, v20
+; CHECK-NEXT:    vmv4r.v v16, v28
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 8 x i32> @llvm.riscv.vrgather.nxv8i32.nxv8i32(
+    <vscale x 8 x i32> %0,
+    <vscale x 8 x i32> %1,
+    i32 %2)
+
+  ret <vscale x 8 x i32> %a
+}
+
+declare <vscale x 8 x i32> @llvm.riscv.vrgather.mask.nxv8i32.nxv8i32(
+  <vscale x 8 x i32>,
+  <vscale x 8 x i32>,
+  <vscale x 8 x i32>,
+  <vscale x 8 x i1>,
+  i32);
+
+define <vscale x 8 x i32> @intrinsic_vrgather_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, i32 %4) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vv_nxv8i32_nxv8i32_nxv8i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a2, zero, e32,m4,ta,mu
+; CHECK-NEXT:    vle32.v v28, (a0)
+; CHECK-NEXT:    vsetvli a0, a1, e32,m4,ta,mu
+; CHECK-NEXT:    vrgather.vv v16, v20, v28, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 8 x i32> @llvm.riscv.vrgather.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,
+    i32 %4)
+
+  ret <vscale x 8 x i32> %a
+}
+
+declare <vscale x 16 x i32> @llvm.riscv.vrgather.nxv16i32.nxv16i32(
+  <vscale x 16 x i32>,
+  <vscale x 16 x i32>,
+  i32);
+
+define <vscale x 16 x i32> @intrinsic_vrgather_vv_nxv16i32_nxv16i32_nxv16i32(<vscale x 16 x i32> %0, <vscale x 16 x i32> %1, i32 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vv_nxv16i32_nxv16i32_nxv16i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a2, zero, e32,m8,ta,mu
+; CHECK-NEXT:    vle32.v v24, (a0)
+; CHECK-NEXT:    vsetvli a0, a1, e32,m8,ta,mu
+; CHECK-NEXT:    vrgather.vv v8, v16, v24
+; CHECK-NEXT:    vmv8r.v v16, v8
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 16 x i32> @llvm.riscv.vrgather.nxv16i32.nxv16i32(
+    <vscale x 16 x i32> %0,
+    <vscale x 16 x i32> %1,
+    i32 %2)
+
+  ret <vscale x 16 x i32> %a
+}
+
+declare <vscale x 16 x i32> @llvm.riscv.vrgather.mask.nxv16i32.nxv16i32(
+  <vscale x 16 x i32>,
+  <vscale x 16 x i32>,
+  <vscale x 16 x i32>,
+  <vscale x 16 x i1>,
+  i32);
+
+define <vscale x 16 x i32> @intrinsic_vrgather_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, i32 %4) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vv_nxv16i32_nxv16i32_nxv16i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a3, zero, e32,m8,ta,mu
+; CHECK-NEXT:    vle32.v v8, (a1)
+; CHECK-NEXT:    vle32.v v24, (a0)
+; CHECK-NEXT:    vsetvli a0, a2, e32,m8,ta,mu
+; CHECK-NEXT:    vrgather.vv v16, v24, v8, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 16 x i32> @llvm.riscv.vrgather.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,
+    i32 %4)
+
+  ret <vscale x 16 x i32> %a
+}
+
+declare <vscale x 1 x half> @llvm.riscv.vrgather.nxv1f16.nxv1i16(
+  <vscale x 1 x half>,
+  <vscale x 1 x i16>,
+  i32);
+
+define <vscale x 1 x half> @intrinsic_vrgather_vv_nxv1f16_nxv1f16_nxv1i16(<vscale x 1 x half> %0, <vscale x 1 x i16> %1, i32 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vv_nxv1f16_nxv1f16_nxv1i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e16,mf4,ta,mu
+; CHECK-NEXT:    vrgather.vv v25, v16, v17
+; CHECK-NEXT:    vmv1r.v v16, v25
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 1 x half> @llvm.riscv.vrgather.nxv1f16.nxv1i16(
+    <vscale x 1 x half> %0,
+    <vscale x 1 x i16> %1,
+    i32 %2)
+
+  ret <vscale x 1 x half> %a
+}
+
+declare <vscale x 1 x half> @llvm.riscv.vrgather.mask.nxv1f16.nxv1i16(
+  <vscale x 1 x half>,
+  <vscale x 1 x half>,
+  <vscale x 1 x i16>,
+  <vscale x 1 x i1>,
+  i32);
+
+define <vscale x 1 x half> @intrinsic_vrgather_mask_vv_nxv1f16_nxv1f16_nxv1i16(<vscale x 1 x half> %0, <vscale x 1 x half> %1, <vscale x 1 x i16> %2, <vscale x 1 x i1> %3, i32 %4) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vv_nxv1f16_nxv1f16_nxv1i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e16,mf4,ta,mu
+; CHECK-NEXT:    vrgather.vv v16, v17, v18, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 1 x half> @llvm.riscv.vrgather.mask.nxv1f16.nxv1i16(
+    <vscale x 1 x half> %0,
+    <vscale x 1 x half> %1,
+    <vscale x 1 x i16> %2,
+    <vscale x 1 x i1> %3,
+    i32 %4)
+
+  ret <vscale x 1 x half> %a
+}
+
+declare <vscale x 2 x half> @llvm.riscv.vrgather.nxv2f16.nxv2i16(
+  <vscale x 2 x half>,
+  <vscale x 2 x i16>,
+  i32);
+
+define <vscale x 2 x half> @intrinsic_vrgather_vv_nxv2f16_nxv2f16_nxv2i16(<vscale x 2 x half> %0, <vscale x 2 x i16> %1, i32 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vv_nxv2f16_nxv2f16_nxv2i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e16,mf2,ta,mu
+; CHECK-NEXT:    vrgather.vv v25, v16, v17
+; CHECK-NEXT:    vmv1r.v v16, v25
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 2 x half> @llvm.riscv.vrgather.nxv2f16.nxv2i16(
+    <vscale x 2 x half> %0,
+    <vscale x 2 x i16> %1,
+    i32 %2)
+
+  ret <vscale x 2 x half> %a
+}
+
+declare <vscale x 2 x half> @llvm.riscv.vrgather.mask.nxv2f16.nxv2i16(
+  <vscale x 2 x half>,
+  <vscale x 2 x half>,
+  <vscale x 2 x i16>,
+  <vscale x 2 x i1>,
+  i32);
+
+define <vscale x 2 x half> @intrinsic_vrgather_mask_vv_nxv2f16_nxv2f16_nxv2i16(<vscale x 2 x half> %0, <vscale x 2 x half> %1, <vscale x 2 x i16> %2, <vscale x 2 x i1> %3, i32 %4) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vv_nxv2f16_nxv2f16_nxv2i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e16,mf2,ta,mu
+; CHECK-NEXT:    vrgather.vv v16, v17, v18, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 2 x half> @llvm.riscv.vrgather.mask.nxv2f16.nxv2i16(
+    <vscale x 2 x half> %0,
+    <vscale x 2 x half> %1,
+    <vscale x 2 x i16> %2,
+    <vscale x 2 x i1> %3,
+    i32 %4)
+
+  ret <vscale x 2 x half> %a
+}
+
+declare <vscale x 4 x half> @llvm.riscv.vrgather.nxv4f16.nxv4i16(
+  <vscale x 4 x half>,
+  <vscale x 4 x i16>,
+  i32);
+
+define <vscale x 4 x half> @intrinsic_vrgather_vv_nxv4f16_nxv4f16_nxv4i16(<vscale x 4 x half> %0, <vscale x 4 x i16> %1, i32 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vv_nxv4f16_nxv4f16_nxv4i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e16,m1,ta,mu
+; CHECK-NEXT:    vrgather.vv v25, v16, v17
+; CHECK-NEXT:    vmv1r.v v16, v25
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 4 x half> @llvm.riscv.vrgather.nxv4f16.nxv4i16(
+    <vscale x 4 x half> %0,
+    <vscale x 4 x i16> %1,
+    i32 %2)
+
+  ret <vscale x 4 x half> %a
+}
+
+declare <vscale x 4 x half> @llvm.riscv.vrgather.mask.nxv4f16.nxv4i16(
+  <vscale x 4 x half>,
+  <vscale x 4 x half>,
+  <vscale x 4 x i16>,
+  <vscale x 4 x i1>,
+  i32);
+
+define <vscale x 4 x half> @intrinsic_vrgather_mask_vv_nxv4f16_nxv4f16_nxv4i16(<vscale x 4 x half> %0, <vscale x 4 x half> %1, <vscale x 4 x i16> %2, <vscale x 4 x i1> %3, i32 %4) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vv_nxv4f16_nxv4f16_nxv4i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e16,m1,ta,mu
+; CHECK-NEXT:    vrgather.vv v16, v17, v18, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 4 x half> @llvm.riscv.vrgather.mask.nxv4f16.nxv4i16(
+    <vscale x 4 x half> %0,
+    <vscale x 4 x half> %1,
+    <vscale x 4 x i16> %2,
+    <vscale x 4 x i1> %3,
+    i32 %4)
+
+  ret <vscale x 4 x half> %a
+}
+
+declare <vscale x 8 x half> @llvm.riscv.vrgather.nxv8f16.nxv8i16(
+  <vscale x 8 x half>,
+  <vscale x 8 x i16>,
+  i32);
+
+define <vscale x 8 x half> @intrinsic_vrgather_vv_nxv8f16_nxv8f16_nxv8i16(<vscale x 8 x half> %0, <vscale x 8 x i16> %1, i32 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vv_nxv8f16_nxv8f16_nxv8i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e16,m2,ta,mu
+; CHECK-NEXT:    vrgather.vv v26, v16, v18
+; CHECK-NEXT:    vmv2r.v v16, v26
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 8 x half> @llvm.riscv.vrgather.nxv8f16.nxv8i16(
+    <vscale x 8 x half> %0,
+    <vscale x 8 x i16> %1,
+    i32 %2)
+
+  ret <vscale x 8 x half> %a
+}
+
+declare <vscale x 8 x half> @llvm.riscv.vrgather.mask.nxv8f16.nxv8i16(
+  <vscale x 8 x half>,
+  <vscale x 8 x half>,
+  <vscale x 8 x i16>,
+  <vscale x 8 x i1>,
+  i32);
+
+define <vscale x 8 x half> @intrinsic_vrgather_mask_vv_nxv8f16_nxv8f16_nxv8i16(<vscale x 8 x half> %0, <vscale x 8 x half> %1, <vscale x 8 x i16> %2, <vscale x 8 x i1> %3, i32 %4) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vv_nxv8f16_nxv8f16_nxv8i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e16,m2,ta,mu
+; CHECK-NEXT:    vrgather.vv v16, v18, v20, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 8 x half> @llvm.riscv.vrgather.mask.nxv8f16.nxv8i16(
+    <vscale x 8 x half> %0,
+    <vscale x 8 x half> %1,
+    <vscale x 8 x i16> %2,
+    <vscale x 8 x i1> %3,
+    i32 %4)
+
+  ret <vscale x 8 x half> %a
+}
+
+declare <vscale x 16 x half> @llvm.riscv.vrgather.nxv16f16.nxv16i16(
+  <vscale x 16 x half>,
+  <vscale x 16 x i16>,
+  i32);
+
+define <vscale x 16 x half> @intrinsic_vrgather_vv_nxv16f16_nxv16f16_nxv16i16(<vscale x 16 x half> %0, <vscale x 16 x i16> %1, i32 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vv_nxv16f16_nxv16f16_nxv16i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e16,m4,ta,mu
+; CHECK-NEXT:    vrgather.vv v28, v16, v20
+; CHECK-NEXT:    vmv4r.v v16, v28
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 16 x half> @llvm.riscv.vrgather.nxv16f16.nxv16i16(
+    <vscale x 16 x half> %0,
+    <vscale x 16 x i16> %1,
+    i32 %2)
+
+  ret <vscale x 16 x half> %a
+}
+
+declare <vscale x 16 x half> @llvm.riscv.vrgather.mask.nxv16f16.nxv16i16(
+  <vscale x 16 x half>,
+  <vscale x 16 x half>,
+  <vscale x 16 x i16>,
+  <vscale x 16 x i1>,
+  i32);
+
+define <vscale x 16 x half> @intrinsic_vrgather_mask_vv_nxv16f16_nxv16f16_nxv16i16(<vscale x 16 x half> %0, <vscale x 16 x half> %1, <vscale x 16 x i16> %2, <vscale x 16 x i1> %3, i32 %4) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vv_nxv16f16_nxv16f16_nxv16i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a2, zero, e16,m4,ta,mu
+; CHECK-NEXT:    vle16.v v28, (a0)
+; CHECK-NEXT:    vsetvli a0, a1, e16,m4,ta,mu
+; CHECK-NEXT:    vrgather.vv v16, v20, v28, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 16 x half> @llvm.riscv.vrgather.mask.nxv16f16.nxv16i16(
+    <vscale x 16 x half> %0,
+    <vscale x 16 x half> %1,
+    <vscale x 16 x i16> %2,
+    <vscale x 16 x i1> %3,
+    i32 %4)
+
+  ret <vscale x 16 x half> %a
+}
+
+declare <vscale x 32 x half> @llvm.riscv.vrgather.nxv32f16.nxv32i16(
+  <vscale x 32 x half>,
+  <vscale x 32 x i16>,
+  i32);
+
+define <vscale x 32 x half> @intrinsic_vrgather_vv_nxv32f16_nxv32f16_nxv32i16(<vscale x 32 x half> %0, <vscale x 32 x i16> %1, i32 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vv_nxv32f16_nxv32f16_nxv32i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a2, zero, e16,m8,ta,mu
+; CHECK-NEXT:    vle16.v v24, (a0)
+; CHECK-NEXT:    vsetvli a0, a1, e16,m8,ta,mu
+; CHECK-NEXT:    vrgather.vv v8, v16, v24
+; CHECK-NEXT:    vmv8r.v v16, v8
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 32 x half> @llvm.riscv.vrgather.nxv32f16.nxv32i16(
+    <vscale x 32 x half> %0,
+    <vscale x 32 x i16> %1,
+    i32 %2)
+
+  ret <vscale x 32 x half> %a
+}
+
+declare <vscale x 32 x half> @llvm.riscv.vrgather.mask.nxv32f16.nxv32i16(
+  <vscale x 32 x half>,
+  <vscale x 32 x half>,
+  <vscale x 32 x i16>,
+  <vscale x 32 x i1>,
+  i32);
+
+define <vscale x 32 x half> @intrinsic_vrgather_mask_vv_nxv32f16_nxv32f16_nxv32i16(<vscale x 32 x half> %0, <vscale x 32 x half> %1, <vscale x 32 x i16> %2, <vscale x 32 x i1> %3, i32 %4) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vv_nxv32f16_nxv32f16_nxv32i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a3, zero, e16,m8,ta,mu
+; CHECK-NEXT:    vle16.v v8, (a1)
+; CHECK-NEXT:    vle16.v v24, (a0)
+; CHECK-NEXT:    vsetvli a0, a2, e16,m8,ta,mu
+; CHECK-NEXT:    vrgather.vv v16, v24, v8, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 32 x half> @llvm.riscv.vrgather.mask.nxv32f16.nxv32i16(
+    <vscale x 32 x half> %0,
+    <vscale x 32 x half> %1,
+    <vscale x 32 x i16> %2,
+    <vscale x 32 x i1> %3,
+    i32 %4)
+
+  ret <vscale x 32 x half> %a
+}
+
+declare <vscale x 1 x float> @llvm.riscv.vrgather.nxv1f32.nxv1i32(
+  <vscale x 1 x float>,
+  <vscale x 1 x i32>,
+  i32);
+
+define <vscale x 1 x float> @intrinsic_vrgather_vv_nxv1f32_nxv1f32_nxv1i32(<vscale x 1 x float> %0, <vscale x 1 x i32> %1, i32 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vv_nxv1f32_nxv1f32_nxv1i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e32,mf2,ta,mu
+; CHECK-NEXT:    vrgather.vv v25, v16, v17
+; CHECK-NEXT:    vmv1r.v v16, v25
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 1 x float> @llvm.riscv.vrgather.nxv1f32.nxv1i32(
+    <vscale x 1 x float> %0,
+    <vscale x 1 x i32> %1,
+    i32 %2)
+
+  ret <vscale x 1 x float> %a
+}
+
+declare <vscale x 1 x float> @llvm.riscv.vrgather.mask.nxv1f32.nxv1i32(
+  <vscale x 1 x float>,
+  <vscale x 1 x float>,
+  <vscale x 1 x i32>,
+  <vscale x 1 x i1>,
+  i32);
+
+define <vscale x 1 x float> @intrinsic_vrgather_mask_vv_nxv1f32_nxv1f32_nxv1i32(<vscale x 1 x float> %0, <vscale x 1 x float> %1, <vscale x 1 x i32> %2, <vscale x 1 x i1> %3, i32 %4) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vv_nxv1f32_nxv1f32_nxv1i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e32,mf2,ta,mu
+; CHECK-NEXT:    vrgather.vv v16, v17, v18, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 1 x float> @llvm.riscv.vrgather.mask.nxv1f32.nxv1i32(
+    <vscale x 1 x float> %0,
+    <vscale x 1 x float> %1,
+    <vscale x 1 x i32> %2,
+    <vscale x 1 x i1> %3,
+    i32 %4)
+
+  ret <vscale x 1 x float> %a
+}
+
+declare <vscale x 2 x float> @llvm.riscv.vrgather.nxv2f32.nxv2i32(
+  <vscale x 2 x float>,
+  <vscale x 2 x i32>,
+  i32);
+
+define <vscale x 2 x float> @intrinsic_vrgather_vv_nxv2f32_nxv2f32_nxv2i32(<vscale x 2 x float> %0, <vscale x 2 x i32> %1, i32 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vv_nxv2f32_nxv2f32_nxv2i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e32,m1,ta,mu
+; CHECK-NEXT:    vrgather.vv v25, v16, v17
+; CHECK-NEXT:    vmv1r.v v16, v25
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 2 x float> @llvm.riscv.vrgather.nxv2f32.nxv2i32(
+    <vscale x 2 x float> %0,
+    <vscale x 2 x i32> %1,
+    i32 %2)
+
+  ret <vscale x 2 x float> %a
+}
+
+declare <vscale x 2 x float> @llvm.riscv.vrgather.mask.nxv2f32.nxv2i32(
+  <vscale x 2 x float>,
+  <vscale x 2 x float>,
+  <vscale x 2 x i32>,
+  <vscale x 2 x i1>,
+  i32);
+
+define <vscale x 2 x float> @intrinsic_vrgather_mask_vv_nxv2f32_nxv2f32_nxv2i32(<vscale x 2 x float> %0, <vscale x 2 x float> %1, <vscale x 2 x i32> %2, <vscale x 2 x i1> %3, i32 %4) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vv_nxv2f32_nxv2f32_nxv2i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e32,m1,ta,mu
+; CHECK-NEXT:    vrgather.vv v16, v17, v18, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 2 x float> @llvm.riscv.vrgather.mask.nxv2f32.nxv2i32(
+    <vscale x 2 x float> %0,
+    <vscale x 2 x float> %1,
+    <vscale x 2 x i32> %2,
+    <vscale x 2 x i1> %3,
+    i32 %4)
+
+  ret <vscale x 2 x float> %a
+}
+
+declare <vscale x 4 x float> @llvm.riscv.vrgather.nxv4f32.nxv4i32(
+  <vscale x 4 x float>,
+  <vscale x 4 x i32>,
+  i32);
+
+define <vscale x 4 x float> @intrinsic_vrgather_vv_nxv4f32_nxv4f32_nxv4i32(<vscale x 4 x float> %0, <vscale x 4 x i32> %1, i32 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vv_nxv4f32_nxv4f32_nxv4i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e32,m2,ta,mu
+; CHECK-NEXT:    vrgather.vv v26, v16, v18
+; CHECK-NEXT:    vmv2r.v v16, v26
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 4 x float> @llvm.riscv.vrgather.nxv4f32.nxv4i32(
+    <vscale x 4 x float> %0,
+    <vscale x 4 x i32> %1,
+    i32 %2)
+
+  ret <vscale x 4 x float> %a
+}
+
+declare <vscale x 4 x float> @llvm.riscv.vrgather.mask.nxv4f32.nxv4i32(
+  <vscale x 4 x float>,
+  <vscale x 4 x float>,
+  <vscale x 4 x i32>,
+  <vscale x 4 x i1>,
+  i32);
+
+define <vscale x 4 x float> @intrinsic_vrgather_mask_vv_nxv4f32_nxv4f32_nxv4i32(<vscale x 4 x float> %0, <vscale x 4 x float> %1, <vscale x 4 x i32> %2, <vscale x 4 x i1> %3, i32 %4) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vv_nxv4f32_nxv4f32_nxv4i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e32,m2,ta,mu
+; CHECK-NEXT:    vrgather.vv v16, v18, v20, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 4 x float> @llvm.riscv.vrgather.mask.nxv4f32.nxv4i32(
+    <vscale x 4 x float> %0,
+    <vscale x 4 x float> %1,
+    <vscale x 4 x i32> %2,
+    <vscale x 4 x i1> %3,
+    i32 %4)
+
+  ret <vscale x 4 x float> %a
+}
+
+declare <vscale x 8 x float> @llvm.riscv.vrgather.nxv8f32.nxv8i32(
+  <vscale x 8 x float>,
+  <vscale x 8 x i32>,
+  i32);
+
+define <vscale x 8 x float> @intrinsic_vrgather_vv_nxv8f32_nxv8f32_nxv8i32(<vscale x 8 x float> %0, <vscale x 8 x i32> %1, i32 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vv_nxv8f32_nxv8f32_nxv8i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e32,m4,ta,mu
+; CHECK-NEXT:    vrgather.vv v28, v16, v20
+; CHECK-NEXT:    vmv4r.v v16, v28
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 8 x float> @llvm.riscv.vrgather.nxv8f32.nxv8i32(
+    <vscale x 8 x float> %0,
+    <vscale x 8 x i32> %1,
+    i32 %2)
+
+  ret <vscale x 8 x float> %a
+}
+
+declare <vscale x 8 x float> @llvm.riscv.vrgather.mask.nxv8f32.nxv8i32(
+  <vscale x 8 x float>,
+  <vscale x 8 x float>,
+  <vscale x 8 x i32>,
+  <vscale x 8 x i1>,
+  i32);
+
+define <vscale x 8 x float> @intrinsic_vrgather_mask_vv_nxv8f32_nxv8f32_nxv8i32(<vscale x 8 x float> %0, <vscale x 8 x float> %1, <vscale x 8 x i32> %2, <vscale x 8 x i1> %3, i32 %4) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vv_nxv8f32_nxv8f32_nxv8i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a2, zero, e32,m4,ta,mu
+; CHECK-NEXT:    vle32.v v28, (a0)
+; CHECK-NEXT:    vsetvli a0, a1, e32,m4,ta,mu
+; CHECK-NEXT:    vrgather.vv v16, v20, v28, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 8 x float> @llvm.riscv.vrgather.mask.nxv8f32.nxv8i32(
+    <vscale x 8 x float> %0,
+    <vscale x 8 x float> %1,
+    <vscale x 8 x i32> %2,
+    <vscale x 8 x i1> %3,
+    i32 %4)
+
+  ret <vscale x 8 x float> %a
+}
+
+declare <vscale x 16 x float> @llvm.riscv.vrgather.nxv16f32.nxv16i32(
+  <vscale x 16 x float>,
+  <vscale x 16 x i32>,
+  i32);
+
+define <vscale x 16 x float> @intrinsic_vrgather_vv_nxv16f32_nxv16f32_nxv16i32(<vscale x 16 x float> %0, <vscale x 16 x i32> %1, i32 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vv_nxv16f32_nxv16f32_nxv16i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a2, zero, e32,m8,ta,mu
+; CHECK-NEXT:    vle32.v v24, (a0)
+; CHECK-NEXT:    vsetvli a0, a1, e32,m8,ta,mu
+; CHECK-NEXT:    vrgather.vv v8, v16, v24
+; CHECK-NEXT:    vmv8r.v v16, v8
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 16 x float> @llvm.riscv.vrgather.nxv16f32.nxv16i32(
+    <vscale x 16 x float> %0,
+    <vscale x 16 x i32> %1,
+    i32 %2)
+
+  ret <vscale x 16 x float> %a
+}
+
+declare <vscale x 16 x float> @llvm.riscv.vrgather.mask.nxv16f32.nxv16i32(
+  <vscale x 16 x float>,
+  <vscale x 16 x float>,
+  <vscale x 16 x i32>,
+  <vscale x 16 x i1>,
+  i32);
+
+define <vscale x 16 x float> @intrinsic_vrgather_mask_vv_nxv16f32_nxv16f32_nxv16i32(<vscale x 16 x float> %0, <vscale x 16 x float> %1, <vscale x 16 x i32> %2, <vscale x 16 x i1> %3, i32 %4) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vv_nxv16f32_nxv16f32_nxv16i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a3, zero, e32,m8,ta,mu
+; CHECK-NEXT:    vle32.v v8, (a1)
+; CHECK-NEXT:    vle32.v v24, (a0)
+; CHECK-NEXT:    vsetvli a0, a2, e32,m8,ta,mu
+; CHECK-NEXT:    vrgather.vv v16, v24, v8, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 16 x float> @llvm.riscv.vrgather.mask.nxv16f32.nxv16i32(
+    <vscale x 16 x float> %0,
+    <vscale x 16 x float> %1,
+    <vscale x 16 x i32> %2,
+    <vscale x 16 x i1> %3,
+    i32 %4)
+
+  ret <vscale x 16 x float> %a
+}
+
+declare <vscale x 1 x i8> @llvm.riscv.vrgather.nxv1i8.i8(
+  <vscale x 1 x i8>,
+  i8,
+  i32);
+
+define <vscale x 1 x i8> @intrinsic_vrgather_vx_nxv1i8_nxv1i8_i8(<vscale x 1 x i8> %0, i8 %1, i32 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vx_nxv1i8_nxv1i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a1, a1, e8,mf8,ta,mu
+; CHECK-NEXT:    vrgather.vx v25, v16, a0
+; CHECK-NEXT:    vmv1r.v v16, v25
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 1 x i8> @llvm.riscv.vrgather.nxv1i8.i8(
+    <vscale x 1 x i8> %0,
+    i8 %1,
+    i32 %2)
+
+  ret <vscale x 1 x i8> %a
+}
+
+declare <vscale x 1 x i8> @llvm.riscv.vrgather.mask.nxv1i8.i8(
+  <vscale x 1 x i8>,
+  <vscale x 1 x i8>,
+  i8,
+  <vscale x 1 x i1>,
+  i32);
+
+define <vscale x 1 x i8> @intrinsic_vrgather_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, i32 %4) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vx_nxv1i8_nxv1i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a1, a1, e8,mf8,ta,mu
+; CHECK-NEXT:    vrgather.vx v16, v17, a0, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 1 x i8> @llvm.riscv.vrgather.mask.nxv1i8.i8(
+    <vscale x 1 x i8> %0,
+    <vscale x 1 x i8> %1,
+    i8 %2,
+    <vscale x 1 x i1> %3,
+    i32 %4)
+
+  ret <vscale x 1 x i8> %a
+}
+
+declare <vscale x 2 x i8> @llvm.riscv.vrgather.nxv2i8.i8(
+  <vscale x 2 x i8>,
+  i8,
+  i32);
+
+define <vscale x 2 x i8> @intrinsic_vrgather_vx_nxv2i8_nxv2i8_i8(<vscale x 2 x i8> %0, i8 %1, i32 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vx_nxv2i8_nxv2i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a1, a1, e8,mf4,ta,mu
+; CHECK-NEXT:    vrgather.vx v25, v16, a0
+; CHECK-NEXT:    vmv1r.v v16, v25
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 2 x i8> @llvm.riscv.vrgather.nxv2i8.i8(
+    <vscale x 2 x i8> %0,
+    i8 %1,
+    i32 %2)
+
+  ret <vscale x 2 x i8> %a
+}
+
+declare <vscale x 2 x i8> @llvm.riscv.vrgather.mask.nxv2i8.i8(
+  <vscale x 2 x i8>,
+  <vscale x 2 x i8>,
+  i8,
+  <vscale x 2 x i1>,
+  i32);
+
+define <vscale x 2 x i8> @intrinsic_vrgather_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, i32 %4) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vx_nxv2i8_nxv2i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a1, a1, e8,mf4,ta,mu
+; CHECK-NEXT:    vrgather.vx v16, v17, a0, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 2 x i8> @llvm.riscv.vrgather.mask.nxv2i8.i8(
+    <vscale x 2 x i8> %0,
+    <vscale x 2 x i8> %1,
+    i8 %2,
+    <vscale x 2 x i1> %3,
+    i32 %4)
+
+  ret <vscale x 2 x i8> %a
+}
+
+declare <vscale x 4 x i8> @llvm.riscv.vrgather.nxv4i8.i8(
+  <vscale x 4 x i8>,
+  i8,
+  i32);
+
+define <vscale x 4 x i8> @intrinsic_vrgather_vx_nxv4i8_nxv4i8_i8(<vscale x 4 x i8> %0, i8 %1, i32 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vx_nxv4i8_nxv4i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a1, a1, e8,mf2,ta,mu
+; CHECK-NEXT:    vrgather.vx v25, v16, a0
+; CHECK-NEXT:    vmv1r.v v16, v25
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 4 x i8> @llvm.riscv.vrgather.nxv4i8.i8(
+    <vscale x 4 x i8> %0,
+    i8 %1,
+    i32 %2)
+
+  ret <vscale x 4 x i8> %a
+}
+
+declare <vscale x 4 x i8> @llvm.riscv.vrgather.mask.nxv4i8.i8(
+  <vscale x 4 x i8>,
+  <vscale x 4 x i8>,
+  i8,
+  <vscale x 4 x i1>,
+  i32);
+
+define <vscale x 4 x i8> @intrinsic_vrgather_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, i32 %4) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vx_nxv4i8_nxv4i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a1, a1, e8,mf2,ta,mu
+; CHECK-NEXT:    vrgather.vx v16, v17, a0, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 4 x i8> @llvm.riscv.vrgather.mask.nxv4i8.i8(
+    <vscale x 4 x i8> %0,
+    <vscale x 4 x i8> %1,
+    i8 %2,
+    <vscale x 4 x i1> %3,
+    i32 %4)
+
+  ret <vscale x 4 x i8> %a
+}
+
+declare <vscale x 8 x i8> @llvm.riscv.vrgather.nxv8i8.i8(
+  <vscale x 8 x i8>,
+  i8,
+  i32);
+
+define <vscale x 8 x i8> @intrinsic_vrgather_vx_nxv8i8_nxv8i8_i8(<vscale x 8 x i8> %0, i8 %1, i32 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vx_nxv8i8_nxv8i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a1, a1, e8,m1,ta,mu
+; CHECK-NEXT:    vrgather.vx v25, v16, a0
+; CHECK-NEXT:    vmv1r.v v16, v25
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 8 x i8> @llvm.riscv.vrgather.nxv8i8.i8(
+    <vscale x 8 x i8> %0,
+    i8 %1,
+    i32 %2)
+
+  ret <vscale x 8 x i8> %a
+}
+
+declare <vscale x 8 x i8> @llvm.riscv.vrgather.mask.nxv8i8.i8(
+  <vscale x 8 x i8>,
+  <vscale x 8 x i8>,
+  i8,
+  <vscale x 8 x i1>,
+  i32);
+
+define <vscale x 8 x i8> @intrinsic_vrgather_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, i32 %4) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vx_nxv8i8_nxv8i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a1, a1, e8,m1,ta,mu
+; CHECK-NEXT:    vrgather.vx v16, v17, a0, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 8 x i8> @llvm.riscv.vrgather.mask.nxv8i8.i8(
+    <vscale x 8 x i8> %0,
+    <vscale x 8 x i8> %1,
+    i8 %2,
+    <vscale x 8 x i1> %3,
+    i32 %4)
+
+  ret <vscale x 8 x i8> %a
+}
+
+declare <vscale x 16 x i8> @llvm.riscv.vrgather.nxv16i8.i8(
+  <vscale x 16 x i8>,
+  i8,
+  i32);
+
+define <vscale x 16 x i8> @intrinsic_vrgather_vx_nxv16i8_nxv16i8_i8(<vscale x 16 x i8> %0, i8 %1, i32 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vx_nxv16i8_nxv16i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a1, a1, e8,m2,ta,mu
+; CHECK-NEXT:    vrgather.vx v26, v16, a0
+; CHECK-NEXT:    vmv2r.v v16, v26
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 16 x i8> @llvm.riscv.vrgather.nxv16i8.i8(
+    <vscale x 16 x i8> %0,
+    i8 %1,
+    i32 %2)
+
+  ret <vscale x 16 x i8> %a
+}
+
+declare <vscale x 16 x i8> @llvm.riscv.vrgather.mask.nxv16i8.i8(
+  <vscale x 16 x i8>,
+  <vscale x 16 x i8>,
+  i8,
+  <vscale x 16 x i1>,
+  i32);
+
+define <vscale x 16 x i8> @intrinsic_vrgather_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, i32 %4) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vx_nxv16i8_nxv16i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a1, a1, e8,m2,ta,mu
+; CHECK-NEXT:    vrgather.vx v16, v18, a0, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 16 x i8> @llvm.riscv.vrgather.mask.nxv16i8.i8(
+    <vscale x 16 x i8> %0,
+    <vscale x 16 x i8> %1,
+    i8 %2,
+    <vscale x 16 x i1> %3,
+    i32 %4)
+
+  ret <vscale x 16 x i8> %a
+}
+
+declare <vscale x 32 x i8> @llvm.riscv.vrgather.nxv32i8.i8(
+  <vscale x 32 x i8>,
+  i8,
+  i32);
+
+define <vscale x 32 x i8> @intrinsic_vrgather_vx_nxv32i8_nxv32i8_i8(<vscale x 32 x i8> %0, i8 %1, i32 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vx_nxv32i8_nxv32i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a1, a1, e8,m4,ta,mu
+; CHECK-NEXT:    vrgather.vx v28, v16, a0
+; CHECK-NEXT:    vmv4r.v v16, v28
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 32 x i8> @llvm.riscv.vrgather.nxv32i8.i8(
+    <vscale x 32 x i8> %0,
+    i8 %1,
+    i32 %2)
+
+  ret <vscale x 32 x i8> %a
+}
+
+declare <vscale x 32 x i8> @llvm.riscv.vrgather.mask.nxv32i8.i8(
+  <vscale x 32 x i8>,
+  <vscale x 32 x i8>,
+  i8,
+  <vscale x 32 x i1>,
+  i32);
+
+define <vscale x 32 x i8> @intrinsic_vrgather_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, i32 %4) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vx_nxv32i8_nxv32i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a1, a1, e8,m4,ta,mu
+; CHECK-NEXT:    vrgather.vx v16, v20, a0, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 32 x i8> @llvm.riscv.vrgather.mask.nxv32i8.i8(
+    <vscale x 32 x i8> %0,
+    <vscale x 32 x i8> %1,
+    i8 %2,
+    <vscale x 32 x i1> %3,
+    i32 %4)
+
+  ret <vscale x 32 x i8> %a
+}
+
+declare <vscale x 64 x i8> @llvm.riscv.vrgather.nxv64i8.i8(
+  <vscale x 64 x i8>,
+  i8,
+  i32);
+
+define <vscale x 64 x i8> @intrinsic_vrgather_vx_nxv64i8_nxv64i8_i8(<vscale x 64 x i8> %0, i8 %1, i32 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vx_nxv64i8_nxv64i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a1, a1, e8,m8,ta,mu
+; CHECK-NEXT:    vrgather.vx v8, v16, a0
+; CHECK-NEXT:    vmv8r.v v16, v8
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 64 x i8> @llvm.riscv.vrgather.nxv64i8.i8(
+    <vscale x 64 x i8> %0,
+    i8 %1,
+    i32 %2)
+
+  ret <vscale x 64 x i8> %a
+}
+
+declare <vscale x 64 x i8> @llvm.riscv.vrgather.mask.nxv64i8.i8(
+  <vscale x 64 x i8>,
+  <vscale x 64 x i8>,
+  i8,
+  <vscale x 64 x i1>,
+  i32);
+
+define <vscale x 64 x i8> @intrinsic_vrgather_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, i32 %4) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vx_nxv64i8_nxv64i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a3, zero, e8,m8,ta,mu
+; CHECK-NEXT:    vle8.v v8, (a0)
+; CHECK-NEXT:    vsetvli a0, a2, e8,m8,ta,mu
+; CHECK-NEXT:    vrgather.vx v16, v8, a1, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 64 x i8> @llvm.riscv.vrgather.mask.nxv64i8.i8(
+    <vscale x 64 x i8> %0,
+    <vscale x 64 x i8> %1,
+    i8 %2,
+    <vscale x 64 x i1> %3,
+    i32 %4)
+
+  ret <vscale x 64 x i8> %a
+}
+
+declare <vscale x 1 x i16> @llvm.riscv.vrgather.nxv1i16.i16(
+  <vscale x 1 x i16>,
+  i16,
+  i32);
+
+define <vscale x 1 x i16> @intrinsic_vrgather_vx_nxv1i16_nxv1i16_i16(<vscale x 1 x i16> %0, i16 %1, i32 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vx_nxv1i16_nxv1i16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a1, a1, e16,mf4,ta,mu
+; CHECK-NEXT:    vrgather.vx v25, v16, a0
+; CHECK-NEXT:    vmv1r.v v16, v25
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 1 x i16> @llvm.riscv.vrgather.nxv1i16.i16(
+    <vscale x 1 x i16> %0,
+    i16 %1,
+    i32 %2)
+
+  ret <vscale x 1 x i16> %a
+}
+
+declare <vscale x 1 x i16> @llvm.riscv.vrgather.mask.nxv1i16.i16(
+  <vscale x 1 x i16>,
+  <vscale x 1 x i16>,
+  i16,
+  <vscale x 1 x i1>,
+  i32);
+
+define <vscale x 1 x i16> @intrinsic_vrgather_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, i32 %4) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vx_nxv1i16_nxv1i16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a1, a1, e16,mf4,ta,mu
+; CHECK-NEXT:    vrgather.vx v16, v17, a0, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 1 x i16> @llvm.riscv.vrgather.mask.nxv1i16.i16(
+    <vscale x 1 x i16> %0,
+    <vscale x 1 x i16> %1,
+    i16 %2,
+    <vscale x 1 x i1> %3,
+    i32 %4)
+
+  ret <vscale x 1 x i16> %a
+}
+
+declare <vscale x 2 x i16> @llvm.riscv.vrgather.nxv2i16.i16(
+  <vscale x 2 x i16>,
+  i16,
+  i32);
+
+define <vscale x 2 x i16> @intrinsic_vrgather_vx_nxv2i16_nxv2i16_i16(<vscale x 2 x i16> %0, i16 %1, i32 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vx_nxv2i16_nxv2i16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a1, a1, e16,mf2,ta,mu
+; CHECK-NEXT:    vrgather.vx v25, v16, a0
+; CHECK-NEXT:    vmv1r.v v16, v25
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 2 x i16> @llvm.riscv.vrgather.nxv2i16.i16(
+    <vscale x 2 x i16> %0,
+    i16 %1,
+    i32 %2)
+
+  ret <vscale x 2 x i16> %a
+}
+
+declare <vscale x 2 x i16> @llvm.riscv.vrgather.mask.nxv2i16.i16(
+  <vscale x 2 x i16>,
+  <vscale x 2 x i16>,
+  i16,
+  <vscale x 2 x i1>,
+  i32);
+
+define <vscale x 2 x i16> @intrinsic_vrgather_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, i32 %4) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vx_nxv2i16_nxv2i16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a1, a1, e16,mf2,ta,mu
+; CHECK-NEXT:    vrgather.vx v16, v17, a0, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 2 x i16> @llvm.riscv.vrgather.mask.nxv2i16.i16(
+    <vscale x 2 x i16> %0,
+    <vscale x 2 x i16> %1,
+    i16 %2,
+    <vscale x 2 x i1> %3,
+    i32 %4)
+
+  ret <vscale x 2 x i16> %a
+}
+
+declare <vscale x 4 x i16> @llvm.riscv.vrgather.nxv4i16.i16(
+  <vscale x 4 x i16>,
+  i16,
+  i32);
+
+define <vscale x 4 x i16> @intrinsic_vrgather_vx_nxv4i16_nxv4i16_i16(<vscale x 4 x i16> %0, i16 %1, i32 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vx_nxv4i16_nxv4i16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a1, a1, e16,m1,ta,mu
+; CHECK-NEXT:    vrgather.vx v25, v16, a0
+; CHECK-NEXT:    vmv1r.v v16, v25
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 4 x i16> @llvm.riscv.vrgather.nxv4i16.i16(
+    <vscale x 4 x i16> %0,
+    i16 %1,
+    i32 %2)
+
+  ret <vscale x 4 x i16> %a
+}
+
+declare <vscale x 4 x i16> @llvm.riscv.vrgather.mask.nxv4i16.i16(
+  <vscale x 4 x i16>,
+  <vscale x 4 x i16>,
+  i16,
+  <vscale x 4 x i1>,
+  i32);
+
+define <vscale x 4 x i16> @intrinsic_vrgather_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, i32 %4) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vx_nxv4i16_nxv4i16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a1, a1, e16,m1,ta,mu
+; CHECK-NEXT:    vrgather.vx v16, v17, a0, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 4 x i16> @llvm.riscv.vrgather.mask.nxv4i16.i16(
+    <vscale x 4 x i16> %0,
+    <vscale x 4 x i16> %1,
+    i16 %2,
+    <vscale x 4 x i1> %3,
+    i32 %4)
+
+  ret <vscale x 4 x i16> %a
+}
+
+declare <vscale x 8 x i16> @llvm.riscv.vrgather.nxv8i16.i16(
+  <vscale x 8 x i16>,
+  i16,
+  i32);
+
+define <vscale x 8 x i16> @intrinsic_vrgather_vx_nxv8i16_nxv8i16_i16(<vscale x 8 x i16> %0, i16 %1, i32 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vx_nxv8i16_nxv8i16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a1, a1, e16,m2,ta,mu
+; CHECK-NEXT:    vrgather.vx v26, v16, a0
+; CHECK-NEXT:    vmv2r.v v16, v26
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 8 x i16> @llvm.riscv.vrgather.nxv8i16.i16(
+    <vscale x 8 x i16> %0,
+    i16 %1,
+    i32 %2)
+
+  ret <vscale x 8 x i16> %a
+}
+
+declare <vscale x 8 x i16> @llvm.riscv.vrgather.mask.nxv8i16.i16(
+  <vscale x 8 x i16>,
+  <vscale x 8 x i16>,
+  i16,
+  <vscale x 8 x i1>,
+  i32);
+
+define <vscale x 8 x i16> @intrinsic_vrgather_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, i32 %4) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vx_nxv8i16_nxv8i16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a1, a1, e16,m2,ta,mu
+; CHECK-NEXT:    vrgather.vx v16, v18, a0, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 8 x i16> @llvm.riscv.vrgather.mask.nxv8i16.i16(
+    <vscale x 8 x i16> %0,
+    <vscale x 8 x i16> %1,
+    i16 %2,
+    <vscale x 8 x i1> %3,
+    i32 %4)
+
+  ret <vscale x 8 x i16> %a
+}
+
+declare <vscale x 16 x i16> @llvm.riscv.vrgather.nxv16i16.i16(
+  <vscale x 16 x i16>,
+  i16,
+  i32);
+
+define <vscale x 16 x i16> @intrinsic_vrgather_vx_nxv16i16_nxv16i16_i16(<vscale x 16 x i16> %0, i16 %1, i32 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vx_nxv16i16_nxv16i16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a1, a1, e16,m4,ta,mu
+; CHECK-NEXT:    vrgather.vx v28, v16, a0
+; CHECK-NEXT:    vmv4r.v v16, v28
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 16 x i16> @llvm.riscv.vrgather.nxv16i16.i16(
+    <vscale x 16 x i16> %0,
+    i16 %1,
+    i32 %2)
+
+  ret <vscale x 16 x i16> %a
+}
+
+declare <vscale x 16 x i16> @llvm.riscv.vrgather.mask.nxv16i16.i16(
+  <vscale x 16 x i16>,
+  <vscale x 16 x i16>,
+  i16,
+  <vscale x 16 x i1>,
+  i32);
+
+define <vscale x 16 x i16> @intrinsic_vrgather_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, i32 %4) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vx_nxv16i16_nxv16i16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a1, a1, e16,m4,ta,mu
+; CHECK-NEXT:    vrgather.vx v16, v20, a0, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 16 x i16> @llvm.riscv.vrgather.mask.nxv16i16.i16(
+    <vscale x 16 x i16> %0,
+    <vscale x 16 x i16> %1,
+    i16 %2,
+    <vscale x 16 x i1> %3,
+    i32 %4)
+
+  ret <vscale x 16 x i16> %a
+}
+
+declare <vscale x 32 x i16> @llvm.riscv.vrgather.nxv32i16.i16(
+  <vscale x 32 x i16>,
+  i16,
+  i32);
+
+define <vscale x 32 x i16> @intrinsic_vrgather_vx_nxv32i16_nxv32i16_i16(<vscale x 32 x i16> %0, i16 %1, i32 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vx_nxv32i16_nxv32i16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a1, a1, e16,m8,ta,mu
+; CHECK-NEXT:    vrgather.vx v8, v16, a0
+; CHECK-NEXT:    vmv8r.v v16, v8
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 32 x i16> @llvm.riscv.vrgather.nxv32i16.i16(
+    <vscale x 32 x i16> %0,
+    i16 %1,
+    i32 %2)
+
+  ret <vscale x 32 x i16> %a
+}
+
+declare <vscale x 32 x i16> @llvm.riscv.vrgather.mask.nxv32i16.i16(
+  <vscale x 32 x i16>,
+  <vscale x 32 x i16>,
+  i16,
+  <vscale x 32 x i1>,
+  i32);
+
+define <vscale x 32 x i16> @intrinsic_vrgather_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, i32 %4) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vx_nxv32i16_nxv32i16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a3, zero, e16,m8,ta,mu
+; CHECK-NEXT:    vle16.v v8, (a0)
+; CHECK-NEXT:    vsetvli a0, a2, e16,m8,ta,mu
+; CHECK-NEXT:    vrgather.vx v16, v8, a1, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 32 x i16> @llvm.riscv.vrgather.mask.nxv32i16.i16(
+    <vscale x 32 x i16> %0,
+    <vscale x 32 x i16> %1,
+    i16 %2,
+    <vscale x 32 x i1> %3,
+    i32 %4)
+
+  ret <vscale x 32 x i16> %a
+}
+
+declare <vscale x 1 x i32> @llvm.riscv.vrgather.nxv1i32.i32(
+  <vscale x 1 x i32>,
+  i32,
+  i32);
+
+define <vscale x 1 x i32> @intrinsic_vrgather_vx_nxv1i32_nxv1i32_i32(<vscale x 1 x i32> %0, i32 %1, i32 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vx_nxv1i32_nxv1i32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a1, a1, e32,mf2,ta,mu
+; CHECK-NEXT:    vrgather.vx v25, v16, a0
+; CHECK-NEXT:    vmv1r.v v16, v25
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 1 x i32> @llvm.riscv.vrgather.nxv1i32.i32(
+    <vscale x 1 x i32> %0,
+    i32 %1,
+    i32 %2)
+
+  ret <vscale x 1 x i32> %a
+}
+
+declare <vscale x 1 x i32> @llvm.riscv.vrgather.mask.nxv1i32.i32(
+  <vscale x 1 x i32>,
+  <vscale x 1 x i32>,
+  i32,
+  <vscale x 1 x i1>,
+  i32);
+
+define <vscale x 1 x i32> @intrinsic_vrgather_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, i32 %4) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vx_nxv1i32_nxv1i32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a1, a1, e32,mf2,ta,mu
+; CHECK-NEXT:    vrgather.vx v16, v17, a0, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 1 x i32> @llvm.riscv.vrgather.mask.nxv1i32.i32(
+    <vscale x 1 x i32> %0,
+    <vscale x 1 x i32> %1,
+    i32 %2,
+    <vscale x 1 x i1> %3,
+    i32 %4)
+
+  ret <vscale x 1 x i32> %a
+}
+
+declare <vscale x 2 x i32> @llvm.riscv.vrgather.nxv2i32.i32(
+  <vscale x 2 x i32>,
+  i32,
+  i32);
+
+define <vscale x 2 x i32> @intrinsic_vrgather_vx_nxv2i32_nxv2i32_i32(<vscale x 2 x i32> %0, i32 %1, i32 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vx_nxv2i32_nxv2i32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a1, a1, e32,m1,ta,mu
+; CHECK-NEXT:    vrgather.vx v25, v16, a0
+; CHECK-NEXT:    vmv1r.v v16, v25
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 2 x i32> @llvm.riscv.vrgather.nxv2i32.i32(
+    <vscale x 2 x i32> %0,
+    i32 %1,
+    i32 %2)
+
+  ret <vscale x 2 x i32> %a
+}
+
+declare <vscale x 2 x i32> @llvm.riscv.vrgather.mask.nxv2i32.i32(
+  <vscale x 2 x i32>,
+  <vscale x 2 x i32>,
+  i32,
+  <vscale x 2 x i1>,
+  i32);
+
+define <vscale x 2 x i32> @intrinsic_vrgather_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, i32 %4) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vx_nxv2i32_nxv2i32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a1, a1, e32,m1,ta,mu
+; CHECK-NEXT:    vrgather.vx v16, v17, a0, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 2 x i32> @llvm.riscv.vrgather.mask.nxv2i32.i32(
+    <vscale x 2 x i32> %0,
+    <vscale x 2 x i32> %1,
+    i32 %2,
+    <vscale x 2 x i1> %3,
+    i32 %4)
+
+  ret <vscale x 2 x i32> %a
+}
+
+declare <vscale x 4 x i32> @llvm.riscv.vrgather.nxv4i32.i32(
+  <vscale x 4 x i32>,
+  i32,
+  i32);
+
+define <vscale x 4 x i32> @intrinsic_vrgather_vx_nxv4i32_nxv4i32_i32(<vscale x 4 x i32> %0, i32 %1, i32 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vx_nxv4i32_nxv4i32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a1, a1, e32,m2,ta,mu
+; CHECK-NEXT:    vrgather.vx v26, v16, a0
+; CHECK-NEXT:    vmv2r.v v16, v26
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 4 x i32> @llvm.riscv.vrgather.nxv4i32.i32(
+    <vscale x 4 x i32> %0,
+    i32 %1,
+    i32 %2)
+
+  ret <vscale x 4 x i32> %a
+}
+
+declare <vscale x 4 x i32> @llvm.riscv.vrgather.mask.nxv4i32.i32(
+  <vscale x 4 x i32>,
+  <vscale x 4 x i32>,
+  i32,
+  <vscale x 4 x i1>,
+  i32);
+
+define <vscale x 4 x i32> @intrinsic_vrgather_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, i32 %4) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vx_nxv4i32_nxv4i32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a1, a1, e32,m2,ta,mu
+; CHECK-NEXT:    vrgather.vx v16, v18, a0, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 4 x i32> @llvm.riscv.vrgather.mask.nxv4i32.i32(
+    <vscale x 4 x i32> %0,
+    <vscale x 4 x i32> %1,
+    i32 %2,
+    <vscale x 4 x i1> %3,
+    i32 %4)
+
+  ret <vscale x 4 x i32> %a
+}
+
+declare <vscale x 8 x i32> @llvm.riscv.vrgather.nxv8i32.i32(
+  <vscale x 8 x i32>,
+  i32,
+  i32);
+
+define <vscale x 8 x i32> @intrinsic_vrgather_vx_nxv8i32_nxv8i32_i32(<vscale x 8 x i32> %0, i32 %1, i32 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vx_nxv8i32_nxv8i32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a1, a1, e32,m4,ta,mu
+; CHECK-NEXT:    vrgather.vx v28, v16, a0
+; CHECK-NEXT:    vmv4r.v v16, v28
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 8 x i32> @llvm.riscv.vrgather.nxv8i32.i32(
+    <vscale x 8 x i32> %0,
+    i32 %1,
+    i32 %2)
+
+  ret <vscale x 8 x i32> %a
+}
+
+declare <vscale x 8 x i32> @llvm.riscv.vrgather.mask.nxv8i32.i32(
+  <vscale x 8 x i32>,
+  <vscale x 8 x i32>,
+  i32,
+  <vscale x 8 x i1>,
+  i32);
+
+define <vscale x 8 x i32> @intrinsic_vrgather_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, i32 %4) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vx_nxv8i32_nxv8i32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a1, a1, e32,m4,ta,mu
+; CHECK-NEXT:    vrgather.vx v16, v20, a0, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 8 x i32> @llvm.riscv.vrgather.mask.nxv8i32.i32(
+    <vscale x 8 x i32> %0,
+    <vscale x 8 x i32> %1,
+    i32 %2,
+    <vscale x 8 x i1> %3,
+    i32 %4)
+
+  ret <vscale x 8 x i32> %a
+}
+
+declare <vscale x 16 x i32> @llvm.riscv.vrgather.nxv16i32.i32(
+  <vscale x 16 x i32>,
+  i32,
+  i32);
+
+define <vscale x 16 x i32> @intrinsic_vrgather_vx_nxv16i32_nxv16i32_i32(<vscale x 16 x i32> %0, i32 %1, i32 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vx_nxv16i32_nxv16i32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a1, a1, e32,m8,ta,mu
+; CHECK-NEXT:    vrgather.vx v8, v16, a0
+; CHECK-NEXT:    vmv8r.v v16, v8
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 16 x i32> @llvm.riscv.vrgather.nxv16i32.i32(
+    <vscale x 16 x i32> %0,
+    i32 %1,
+    i32 %2)
+
+  ret <vscale x 16 x i32> %a
+}
+
+declare <vscale x 16 x i32> @llvm.riscv.vrgather.mask.nxv16i32.i32(
+  <vscale x 16 x i32>,
+  <vscale x 16 x i32>,
+  i32,
+  <vscale x 16 x i1>,
+  i32);
+
+define <vscale x 16 x i32> @intrinsic_vrgather_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, i32 %4) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vx_nxv16i32_nxv16i32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a3, zero, e32,m8,ta,mu
+; CHECK-NEXT:    vle32.v v8, (a0)
+; CHECK-NEXT:    vsetvli a0, a2, e32,m8,ta,mu
+; CHECK-NEXT:    vrgather.vx v16, v8, a1, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 16 x i32> @llvm.riscv.vrgather.mask.nxv16i32.i32(
+    <vscale x 16 x i32> %0,
+    <vscale x 16 x i32> %1,
+    i32 %2,
+    <vscale x 16 x i1> %3,
+    i32 %4)
+
+  ret <vscale x 16 x i32> %a
+}
+
+declare <vscale x 1 x half> @llvm.riscv.vrgather.nxv1f16.i16(
+  <vscale x 1 x half>,
+  i16,
+  i32);
+
+define <vscale x 1 x half> @intrinsic_vrgather_vx_nxv1f16_nxv1f16_i16(<vscale x 1 x half> %0, i16 %1, i32 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vx_nxv1f16_nxv1f16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a1, a1, e16,mf4,ta,mu
+; CHECK-NEXT:    vrgather.vx v25, v16, a0
+; CHECK-NEXT:    vmv1r.v v16, v25
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 1 x half> @llvm.riscv.vrgather.nxv1f16.i16(
+    <vscale x 1 x half> %0,
+    i16 %1,
+    i32 %2)
+
+  ret <vscale x 1 x half> %a
+}
+
+declare <vscale x 1 x half> @llvm.riscv.vrgather.mask.nxv1f16.i16(
+  <vscale x 1 x half>,
+  <vscale x 1 x half>,
+  i16,
+  <vscale x 1 x i1>,
+  i32);
+
+define <vscale x 1 x half> @intrinsic_vrgather_mask_vx_nxv1f16_nxv1f16_i16(<vscale x 1 x half> %0, <vscale x 1 x half> %1, i16 %2, <vscale x 1 x i1> %3, i32 %4) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vx_nxv1f16_nxv1f16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a1, a1, e16,mf4,ta,mu
+; CHECK-NEXT:    vrgather.vx v16, v17, a0, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 1 x half> @llvm.riscv.vrgather.mask.nxv1f16.i16(
+    <vscale x 1 x half> %0,
+    <vscale x 1 x half> %1,
+    i16 %2,
+    <vscale x 1 x i1> %3,
+    i32 %4)
+
+  ret <vscale x 1 x half> %a
+}
+
+declare <vscale x 2 x half> @llvm.riscv.vrgather.nxv2f16.i16(
+  <vscale x 2 x half>,
+  i16,
+  i32);
+
+define <vscale x 2 x half> @intrinsic_vrgather_vx_nxv2f16_nxv2f16_i16(<vscale x 2 x half> %0, i16 %1, i32 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vx_nxv2f16_nxv2f16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a1, a1, e16,mf2,ta,mu
+; CHECK-NEXT:    vrgather.vx v25, v16, a0
+; CHECK-NEXT:    vmv1r.v v16, v25
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 2 x half> @llvm.riscv.vrgather.nxv2f16.i16(
+    <vscale x 2 x half> %0,
+    i16 %1,
+    i32 %2)
+
+  ret <vscale x 2 x half> %a
+}
+
+declare <vscale x 2 x half> @llvm.riscv.vrgather.mask.nxv2f16.i16(
+  <vscale x 2 x half>,
+  <vscale x 2 x half>,
+  i16,
+  <vscale x 2 x i1>,
+  i32);
+
+define <vscale x 2 x half> @intrinsic_vrgather_mask_vx_nxv2f16_nxv2f16_i16(<vscale x 2 x half> %0, <vscale x 2 x half> %1, i16 %2, <vscale x 2 x i1> %3, i32 %4) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vx_nxv2f16_nxv2f16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a1, a1, e16,mf2,ta,mu
+; CHECK-NEXT:    vrgather.vx v16, v17, a0, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 2 x half> @llvm.riscv.vrgather.mask.nxv2f16.i16(
+    <vscale x 2 x half> %0,
+    <vscale x 2 x half> %1,
+    i16 %2,
+    <vscale x 2 x i1> %3,
+    i32 %4)
+
+  ret <vscale x 2 x half> %a
+}
+
+declare <vscale x 4 x half> @llvm.riscv.vrgather.nxv4f16.i16(
+  <vscale x 4 x half>,
+  i16,
+  i32);
+
+define <vscale x 4 x half> @intrinsic_vrgather_vx_nxv4f16_nxv4f16_i16(<vscale x 4 x half> %0, i16 %1, i32 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vx_nxv4f16_nxv4f16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a1, a1, e16,m1,ta,mu
+; CHECK-NEXT:    vrgather.vx v25, v16, a0
+; CHECK-NEXT:    vmv1r.v v16, v25
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 4 x half> @llvm.riscv.vrgather.nxv4f16.i16(
+    <vscale x 4 x half> %0,
+    i16 %1,
+    i32 %2)
+
+  ret <vscale x 4 x half> %a
+}
+
+declare <vscale x 4 x half> @llvm.riscv.vrgather.mask.nxv4f16.i16(
+  <vscale x 4 x half>,
+  <vscale x 4 x half>,
+  i16,
+  <vscale x 4 x i1>,
+  i32);
+
+define <vscale x 4 x half> @intrinsic_vrgather_mask_vx_nxv4f16_nxv4f16_i16(<vscale x 4 x half> %0, <vscale x 4 x half> %1, i16 %2, <vscale x 4 x i1> %3, i32 %4) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vx_nxv4f16_nxv4f16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a1, a1, e16,m1,ta,mu
+; CHECK-NEXT:    vrgather.vx v16, v17, a0, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 4 x half> @llvm.riscv.vrgather.mask.nxv4f16.i16(
+    <vscale x 4 x half> %0,
+    <vscale x 4 x half> %1,
+    i16 %2,
+    <vscale x 4 x i1> %3,
+    i32 %4)
+
+  ret <vscale x 4 x half> %a
+}
+
+declare <vscale x 8 x half> @llvm.riscv.vrgather.nxv8f16.i16(
+  <vscale x 8 x half>,
+  i16,
+  i32);
+
+define <vscale x 8 x half> @intrinsic_vrgather_vx_nxv8f16_nxv8f16_i16(<vscale x 8 x half> %0, i16 %1, i32 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vx_nxv8f16_nxv8f16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a1, a1, e16,m2,ta,mu
+; CHECK-NEXT:    vrgather.vx v26, v16, a0
+; CHECK-NEXT:    vmv2r.v v16, v26
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 8 x half> @llvm.riscv.vrgather.nxv8f16.i16(
+    <vscale x 8 x half> %0,
+    i16 %1,
+    i32 %2)
+
+  ret <vscale x 8 x half> %a
+}
+
+declare <vscale x 8 x half> @llvm.riscv.vrgather.mask.nxv8f16.i16(
+  <vscale x 8 x half>,
+  <vscale x 8 x half>,
+  i16,
+  <vscale x 8 x i1>,
+  i32);
+
+define <vscale x 8 x half> @intrinsic_vrgather_mask_vx_nxv8f16_nxv8f16_i16(<vscale x 8 x half> %0, <vscale x 8 x half> %1, i16 %2, <vscale x 8 x i1> %3, i32 %4) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vx_nxv8f16_nxv8f16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a1, a1, e16,m2,ta,mu
+; CHECK-NEXT:    vrgather.vx v16, v18, a0, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 8 x half> @llvm.riscv.vrgather.mask.nxv8f16.i16(
+    <vscale x 8 x half> %0,
+    <vscale x 8 x half> %1,
+    i16 %2,
+    <vscale x 8 x i1> %3,
+    i32 %4)
+
+  ret <vscale x 8 x half> %a
+}
+
+declare <vscale x 16 x half> @llvm.riscv.vrgather.nxv16f16.i16(
+  <vscale x 16 x half>,
+  i16,
+  i32);
+
+define <vscale x 16 x half> @intrinsic_vrgather_vx_nxv16f16_nxv16f16_i16(<vscale x 16 x half> %0, i16 %1, i32 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vx_nxv16f16_nxv16f16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a1, a1, e16,m4,ta,mu
+; CHECK-NEXT:    vrgather.vx v28, v16, a0
+; CHECK-NEXT:    vmv4r.v v16, v28
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 16 x half> @llvm.riscv.vrgather.nxv16f16.i16(
+    <vscale x 16 x half> %0,
+    i16 %1,
+    i32 %2)
+
+  ret <vscale x 16 x half> %a
+}
+
+declare <vscale x 16 x half> @llvm.riscv.vrgather.mask.nxv16f16.i16(
+  <vscale x 16 x half>,
+  <vscale x 16 x half>,
+  i16,
+  <vscale x 16 x i1>,
+  i32);
+
+define <vscale x 16 x half> @intrinsic_vrgather_mask_vx_nxv16f16_nxv16f16_i16(<vscale x 16 x half> %0, <vscale x 16 x half> %1, i16 %2, <vscale x 16 x i1> %3, i32 %4) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vx_nxv16f16_nxv16f16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a1, a1, e16,m4,ta,mu
+; CHECK-NEXT:    vrgather.vx v16, v20, a0, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 16 x half> @llvm.riscv.vrgather.mask.nxv16f16.i16(
+    <vscale x 16 x half> %0,
+    <vscale x 16 x half> %1,
+    i16 %2,
+    <vscale x 16 x i1> %3,
+    i32 %4)
+
+  ret <vscale x 16 x half> %a
+}
+
+declare <vscale x 32 x half> @llvm.riscv.vrgather.nxv32f16.i16(
+  <vscale x 32 x half>,
+  i16,
+  i32);
+
+define <vscale x 32 x half> @intrinsic_vrgather_vx_nxv32f16_nxv32f16_i16(<vscale x 32 x half> %0, i16 %1, i32 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vx_nxv32f16_nxv32f16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a1, a1, e16,m8,ta,mu
+; CHECK-NEXT:    vrgather.vx v8, v16, a0
+; CHECK-NEXT:    vmv8r.v v16, v8
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 32 x half> @llvm.riscv.vrgather.nxv32f16.i16(
+    <vscale x 32 x half> %0,
+    i16 %1,
+    i32 %2)
+
+  ret <vscale x 32 x half> %a
+}
+
+declare <vscale x 32 x half> @llvm.riscv.vrgather.mask.nxv32f16.i16(
+  <vscale x 32 x half>,
+  <vscale x 32 x half>,
+  i16,
+  <vscale x 32 x i1>,
+  i32);
+
+define <vscale x 32 x half> @intrinsic_vrgather_mask_vx_nxv32f16_nxv32f16_i16(<vscale x 32 x half> %0, <vscale x 32 x half> %1, i16 %2, <vscale x 32 x i1> %3, i32 %4) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vx_nxv32f16_nxv32f16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a3, zero, e16,m8,ta,mu
+; CHECK-NEXT:    vle16.v v8, (a0)
+; CHECK-NEXT:    vsetvli a0, a2, e16,m8,ta,mu
+; CHECK-NEXT:    vrgather.vx v16, v8, a1, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 32 x half> @llvm.riscv.vrgather.mask.nxv32f16.i16(
+    <vscale x 32 x half> %0,
+    <vscale x 32 x half> %1,
+    i16 %2,
+    <vscale x 32 x i1> %3,
+    i32 %4)
+
+  ret <vscale x 32 x half> %a
+}
+
+declare <vscale x 1 x float> @llvm.riscv.vrgather.nxv1f32.i32(
+  <vscale x 1 x float>,
+  i32,
+  i32);
+
+define <vscale x 1 x float> @intrinsic_vrgather_vx_nxv1f32_nxv1f32_i32(<vscale x 1 x float> %0, i32 %1, i32 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vx_nxv1f32_nxv1f32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a1, a1, e32,mf2,ta,mu
+; CHECK-NEXT:    vrgather.vx v25, v16, a0
+; CHECK-NEXT:    vmv1r.v v16, v25
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 1 x float> @llvm.riscv.vrgather.nxv1f32.i32(
+    <vscale x 1 x float> %0,
+    i32 %1,
+    i32 %2)
+
+  ret <vscale x 1 x float> %a
+}
+
+declare <vscale x 1 x float> @llvm.riscv.vrgather.mask.nxv1f32.i32(
+  <vscale x 1 x float>,
+  <vscale x 1 x float>,
+  i32,
+  <vscale x 1 x i1>,
+  i32);
+
+define <vscale x 1 x float> @intrinsic_vrgather_mask_vx_nxv1f32_nxv1f32_i32(<vscale x 1 x float> %0, <vscale x 1 x float> %1, i32 %2, <vscale x 1 x i1> %3, i32 %4) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vx_nxv1f32_nxv1f32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a1, a1, e32,mf2,ta,mu
+; CHECK-NEXT:    vrgather.vx v16, v17, a0, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 1 x float> @llvm.riscv.vrgather.mask.nxv1f32.i32(
+    <vscale x 1 x float> %0,
+    <vscale x 1 x float> %1,
+    i32 %2,
+    <vscale x 1 x i1> %3,
+    i32 %4)
+
+  ret <vscale x 1 x float> %a
+}
+
+declare <vscale x 2 x float> @llvm.riscv.vrgather.nxv2f32.i32(
+  <vscale x 2 x float>,
+  i32,
+  i32);
+
+define <vscale x 2 x float> @intrinsic_vrgather_vx_nxv2f32_nxv2f32_i32(<vscale x 2 x float> %0, i32 %1, i32 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vx_nxv2f32_nxv2f32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a1, a1, e32,m1,ta,mu
+; CHECK-NEXT:    vrgather.vx v25, v16, a0
+; CHECK-NEXT:    vmv1r.v v16, v25
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 2 x float> @llvm.riscv.vrgather.nxv2f32.i32(
+    <vscale x 2 x float> %0,
+    i32 %1,
+    i32 %2)
+
+  ret <vscale x 2 x float> %a
+}
+
+declare <vscale x 2 x float> @llvm.riscv.vrgather.mask.nxv2f32.i32(
+  <vscale x 2 x float>,
+  <vscale x 2 x float>,
+  i32,
+  <vscale x 2 x i1>,
+  i32);
+
+define <vscale x 2 x float> @intrinsic_vrgather_mask_vx_nxv2f32_nxv2f32_i32(<vscale x 2 x float> %0, <vscale x 2 x float> %1, i32 %2, <vscale x 2 x i1> %3, i32 %4) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vx_nxv2f32_nxv2f32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a1, a1, e32,m1,ta,mu
+; CHECK-NEXT:    vrgather.vx v16, v17, a0, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 2 x float> @llvm.riscv.vrgather.mask.nxv2f32.i32(
+    <vscale x 2 x float> %0,
+    <vscale x 2 x float> %1,
+    i32 %2,
+    <vscale x 2 x i1> %3,
+    i32 %4)
+
+  ret <vscale x 2 x float> %a
+}
+
+declare <vscale x 4 x float> @llvm.riscv.vrgather.nxv4f32.i32(
+  <vscale x 4 x float>,
+  i32,
+  i32);
+
+define <vscale x 4 x float> @intrinsic_vrgather_vx_nxv4f32_nxv4f32_i32(<vscale x 4 x float> %0, i32 %1, i32 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vx_nxv4f32_nxv4f32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a1, a1, e32,m2,ta,mu
+; CHECK-NEXT:    vrgather.vx v26, v16, a0
+; CHECK-NEXT:    vmv2r.v v16, v26
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 4 x float> @llvm.riscv.vrgather.nxv4f32.i32(
+    <vscale x 4 x float> %0,
+    i32 %1,
+    i32 %2)
+
+  ret <vscale x 4 x float> %a
+}
+
+declare <vscale x 4 x float> @llvm.riscv.vrgather.mask.nxv4f32.i32(
+  <vscale x 4 x float>,
+  <vscale x 4 x float>,
+  i32,
+  <vscale x 4 x i1>,
+  i32);
+
+define <vscale x 4 x float> @intrinsic_vrgather_mask_vx_nxv4f32_nxv4f32_i32(<vscale x 4 x float> %0, <vscale x 4 x float> %1, i32 %2, <vscale x 4 x i1> %3, i32 %4) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vx_nxv4f32_nxv4f32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a1, a1, e32,m2,ta,mu
+; CHECK-NEXT:    vrgather.vx v16, v18, a0, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 4 x float> @llvm.riscv.vrgather.mask.nxv4f32.i32(
+    <vscale x 4 x float> %0,
+    <vscale x 4 x float> %1,
+    i32 %2,
+    <vscale x 4 x i1> %3,
+    i32 %4)
+
+  ret <vscale x 4 x float> %a
+}
+
+declare <vscale x 8 x float> @llvm.riscv.vrgather.nxv8f32.i32(
+  <vscale x 8 x float>,
+  i32,
+  i32);
+
+define <vscale x 8 x float> @intrinsic_vrgather_vx_nxv8f32_nxv8f32_i32(<vscale x 8 x float> %0, i32 %1, i32 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vx_nxv8f32_nxv8f32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a1, a1, e32,m4,ta,mu
+; CHECK-NEXT:    vrgather.vx v28, v16, a0
+; CHECK-NEXT:    vmv4r.v v16, v28
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 8 x float> @llvm.riscv.vrgather.nxv8f32.i32(
+    <vscale x 8 x float> %0,
+    i32 %1,
+    i32 %2)
+
+  ret <vscale x 8 x float> %a
+}
+
+declare <vscale x 8 x float> @llvm.riscv.vrgather.mask.nxv8f32.i32(
+  <vscale x 8 x float>,
+  <vscale x 8 x float>,
+  i32,
+  <vscale x 8 x i1>,
+  i32);
+
+define <vscale x 8 x float> @intrinsic_vrgather_mask_vx_nxv8f32_nxv8f32_i32(<vscale x 8 x float> %0, <vscale x 8 x float> %1, i32 %2, <vscale x 8 x i1> %3, i32 %4) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vx_nxv8f32_nxv8f32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a1, a1, e32,m4,ta,mu
+; CHECK-NEXT:    vrgather.vx v16, v20, a0, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 8 x float> @llvm.riscv.vrgather.mask.nxv8f32.i32(
+    <vscale x 8 x float> %0,
+    <vscale x 8 x float> %1,
+    i32 %2,
+    <vscale x 8 x i1> %3,
+    i32 %4)
+
+  ret <vscale x 8 x float> %a
+}
+
+declare <vscale x 16 x float> @llvm.riscv.vrgather.nxv16f32.i32(
+  <vscale x 16 x float>,
+  i32,
+  i32);
+
+define <vscale x 16 x float> @intrinsic_vrgather_vx_nxv16f32_nxv16f32_i32(<vscale x 16 x float> %0, i32 %1, i32 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vx_nxv16f32_nxv16f32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a1, a1, e32,m8,ta,mu
+; CHECK-NEXT:    vrgather.vx v8, v16, a0
+; CHECK-NEXT:    vmv8r.v v16, v8
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 16 x float> @llvm.riscv.vrgather.nxv16f32.i32(
+    <vscale x 16 x float> %0,
+    i32 %1,
+    i32 %2)
+
+  ret <vscale x 16 x float> %a
+}
+
+declare <vscale x 16 x float> @llvm.riscv.vrgather.mask.nxv16f32.i32(
+  <vscale x 16 x float>,
+  <vscale x 16 x float>,
+  i32,
+  <vscale x 16 x i1>,
+  i32);
+
+define <vscale x 16 x float> @intrinsic_vrgather_mask_vx_nxv16f32_nxv16f32_i32(<vscale x 16 x float> %0, <vscale x 16 x float> %1, i32 %2, <vscale x 16 x i1> %3, i32 %4) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vx_nxv16f32_nxv16f32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a3, zero, e32,m8,ta,mu
+; CHECK-NEXT:    vle32.v v8, (a0)
+; CHECK-NEXT:    vsetvli a0, a2, e32,m8,ta,mu
+; CHECK-NEXT:    vrgather.vx v16, v8, a1, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 16 x float> @llvm.riscv.vrgather.mask.nxv16f32.i32(
+    <vscale x 16 x float> %0,
+    <vscale x 16 x float> %1,
+    i32 %2,
+    <vscale x 16 x i1> %3,
+    i32 %4)
+
+  ret <vscale x 16 x float> %a
+}
+
+define <vscale x 1 x i8> @intrinsic_vrgather_vi_nxv1i8_nxv1i8_i8(<vscale x 1 x i8> %0, i32 %1) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vi_nxv1i8_nxv1i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e8,mf8,ta,mu
+; CHECK-NEXT:    vrgather.vi v25, v16, 9
+; CHECK-NEXT:    vmv1r.v v16, v25
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 1 x i8> @llvm.riscv.vrgather.nxv1i8.i8(
+    <vscale x 1 x i8> %0,
+    i8 9,
+    i32 %1)
+
+  ret <vscale x 1 x i8> %a
+}
+
+define <vscale x 1 x i8> @intrinsic_vrgather_mask_vi_nxv1i8_nxv1i8_i8(<vscale x 1 x i8> %0, <vscale x 1 x i8> %1, <vscale x 1 x i1> %2, i32 %3) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vi_nxv1i8_nxv1i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e8,mf8,ta,mu
+; CHECK-NEXT:    vrgather.vi v16, v17, 9, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 1 x i8> @llvm.riscv.vrgather.mask.nxv1i8.i8(
+    <vscale x 1 x i8> %0,
+    <vscale x 1 x i8> %1,
+    i8 9,
+    <vscale x 1 x i1> %2,
+    i32 %3)
+
+  ret <vscale x 1 x i8> %a
+}
+
+define <vscale x 2 x i8> @intrinsic_vrgather_vi_nxv2i8_nxv2i8_i8(<vscale x 2 x i8> %0, i32 %1) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vi_nxv2i8_nxv2i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e8,mf4,ta,mu
+; CHECK-NEXT:    vrgather.vi v25, v16, 9
+; CHECK-NEXT:    vmv1r.v v16, v25
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 2 x i8> @llvm.riscv.vrgather.nxv2i8.i8(
+    <vscale x 2 x i8> %0,
+    i8 9,
+    i32 %1)
+
+  ret <vscale x 2 x i8> %a
+}
+
+define <vscale x 2 x i8> @intrinsic_vrgather_mask_vi_nxv2i8_nxv2i8_i8(<vscale x 2 x i8> %0, <vscale x 2 x i8> %1, <vscale x 2 x i1> %2, i32 %3) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vi_nxv2i8_nxv2i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e8,mf4,ta,mu
+; CHECK-NEXT:    vrgather.vi v16, v17, 9, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 2 x i8> @llvm.riscv.vrgather.mask.nxv2i8.i8(
+    <vscale x 2 x i8> %0,
+    <vscale x 2 x i8> %1,
+    i8 9,
+    <vscale x 2 x i1> %2,
+    i32 %3)
+
+  ret <vscale x 2 x i8> %a
+}
+
+define <vscale x 4 x i8> @intrinsic_vrgather_vi_nxv4i8_nxv4i8_i8(<vscale x 4 x i8> %0, i32 %1) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vi_nxv4i8_nxv4i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e8,mf2,ta,mu
+; CHECK-NEXT:    vrgather.vi v25, v16, 9
+; CHECK-NEXT:    vmv1r.v v16, v25
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 4 x i8> @llvm.riscv.vrgather.nxv4i8.i8(
+    <vscale x 4 x i8> %0,
+    i8 9,
+    i32 %1)
+
+  ret <vscale x 4 x i8> %a
+}
+
+define <vscale x 4 x i8> @intrinsic_vrgather_mask_vi_nxv4i8_nxv4i8_i8(<vscale x 4 x i8> %0, <vscale x 4 x i8> %1, <vscale x 4 x i1> %2, i32 %3) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vi_nxv4i8_nxv4i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e8,mf2,ta,mu
+; CHECK-NEXT:    vrgather.vi v16, v17, 9, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 4 x i8> @llvm.riscv.vrgather.mask.nxv4i8.i8(
+    <vscale x 4 x i8> %0,
+    <vscale x 4 x i8> %1,
+    i8 9,
+    <vscale x 4 x i1> %2,
+    i32 %3)
+
+  ret <vscale x 4 x i8> %a
+}
+
+define <vscale x 8 x i8> @intrinsic_vrgather_vi_nxv8i8_nxv8i8_i8(<vscale x 8 x i8> %0, i32 %1) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vi_nxv8i8_nxv8i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e8,m1,ta,mu
+; CHECK-NEXT:    vrgather.vi v25, v16, 9
+; CHECK-NEXT:    vmv1r.v v16, v25
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 8 x i8> @llvm.riscv.vrgather.nxv8i8.i8(
+    <vscale x 8 x i8> %0,
+    i8 9,
+    i32 %1)
+
+  ret <vscale x 8 x i8> %a
+}
+
+define <vscale x 8 x i8> @intrinsic_vrgather_mask_vi_nxv8i8_nxv8i8_i8(<vscale x 8 x i8> %0, <vscale x 8 x i8> %1, <vscale x 8 x i1> %2, i32 %3) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vi_nxv8i8_nxv8i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e8,m1,ta,mu
+; CHECK-NEXT:    vrgather.vi v16, v17, 9, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 8 x i8> @llvm.riscv.vrgather.mask.nxv8i8.i8(
+    <vscale x 8 x i8> %0,
+    <vscale x 8 x i8> %1,
+    i8 9,
+    <vscale x 8 x i1> %2,
+    i32 %3)
+
+  ret <vscale x 8 x i8> %a
+}
+
+define <vscale x 16 x i8> @intrinsic_vrgather_vi_nxv16i8_nxv16i8_i8(<vscale x 16 x i8> %0, i32 %1) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vi_nxv16i8_nxv16i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e8,m2,ta,mu
+; CHECK-NEXT:    vrgather.vi v26, v16, 9
+; CHECK-NEXT:    vmv2r.v v16, v26
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 16 x i8> @llvm.riscv.vrgather.nxv16i8.i8(
+    <vscale x 16 x i8> %0,
+    i8 9,
+    i32 %1)
+
+  ret <vscale x 16 x i8> %a
+}
+
+define <vscale x 16 x i8> @intrinsic_vrgather_mask_vi_nxv16i8_nxv16i8_i8(<vscale x 16 x i8> %0, <vscale x 16 x i8> %1, <vscale x 16 x i1> %2, i32 %3) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vi_nxv16i8_nxv16i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e8,m2,ta,mu
+; CHECK-NEXT:    vrgather.vi v16, v18, 9, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 16 x i8> @llvm.riscv.vrgather.mask.nxv16i8.i8(
+    <vscale x 16 x i8> %0,
+    <vscale x 16 x i8> %1,
+    i8 9,
+    <vscale x 16 x i1> %2,
+    i32 %3)
+
+  ret <vscale x 16 x i8> %a
+}
+
+define <vscale x 32 x i8> @intrinsic_vrgather_vi_nxv32i8_nxv32i8_i8(<vscale x 32 x i8> %0, i32 %1) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vi_nxv32i8_nxv32i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e8,m4,ta,mu
+; CHECK-NEXT:    vrgather.vi v28, v16, 9
+; CHECK-NEXT:    vmv4r.v v16, v28
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 32 x i8> @llvm.riscv.vrgather.nxv32i8.i8(
+    <vscale x 32 x i8> %0,
+    i8 9,
+    i32 %1)
+
+  ret <vscale x 32 x i8> %a
+}
+
+define <vscale x 32 x i8> @intrinsic_vrgather_mask_vi_nxv32i8_nxv32i8_i8(<vscale x 32 x i8> %0, <vscale x 32 x i8> %1, <vscale x 32 x i1> %2, i32 %3) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vi_nxv32i8_nxv32i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e8,m4,ta,mu
+; CHECK-NEXT:    vrgather.vi v16, v20, 9, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 32 x i8> @llvm.riscv.vrgather.mask.nxv32i8.i8(
+    <vscale x 32 x i8> %0,
+    <vscale x 32 x i8> %1,
+    i8 9,
+    <vscale x 32 x i1> %2,
+    i32 %3)
+
+  ret <vscale x 32 x i8> %a
+}
+
+define <vscale x 64 x i8> @intrinsic_vrgather_vi_nxv64i8_nxv64i8_i8(<vscale x 64 x i8> %0, i32 %1) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vi_nxv64i8_nxv64i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e8,m8,ta,mu
+; CHECK-NEXT:    vrgather.vi v8, v16, 9
+; CHECK-NEXT:    vmv8r.v v16, v8
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 64 x i8> @llvm.riscv.vrgather.nxv64i8.i8(
+    <vscale x 64 x i8> %0,
+    i8 9,
+    i32 %1)
+
+  ret <vscale x 64 x i8> %a
+}
+
+define <vscale x 64 x i8> @intrinsic_vrgather_mask_vi_nxv64i8_nxv64i8_i8(<vscale x 64 x i8> %0, <vscale x 64 x i8> %1, <vscale x 64 x i1> %2, i32 %3) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vi_nxv64i8_nxv64i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a2, zero, e8,m8,ta,mu
+; CHECK-NEXT:    vle8.v v8, (a0)
+; CHECK-NEXT:    vsetvli a0, a1, e8,m8,ta,mu
+; CHECK-NEXT:    vrgather.vi v16, v8, 9, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 64 x i8> @llvm.riscv.vrgather.mask.nxv64i8.i8(
+    <vscale x 64 x i8> %0,
+    <vscale x 64 x i8> %1,
+    i8 9,
+    <vscale x 64 x i1> %2,
+    i32 %3)
+
+  ret <vscale x 64 x i8> %a
+}
+
+define <vscale x 1 x i16> @intrinsic_vrgather_vi_nxv1i16_nxv1i16_i16(<vscale x 1 x i16> %0, i32 %1) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vi_nxv1i16_nxv1i16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e16,mf4,ta,mu
+; CHECK-NEXT:    vrgather.vi v25, v16, 9
+; CHECK-NEXT:    vmv1r.v v16, v25
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 1 x i16> @llvm.riscv.vrgather.nxv1i16.i16(
+    <vscale x 1 x i16> %0,
+    i16 9,
+    i32 %1)
+
+  ret <vscale x 1 x i16> %a
+}
+
+define <vscale x 1 x i16> @intrinsic_vrgather_mask_vi_nxv1i16_nxv1i16_i16(<vscale x 1 x i16> %0, <vscale x 1 x i16> %1, <vscale x 1 x i1> %2, i32 %3) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vi_nxv1i16_nxv1i16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e16,mf4,ta,mu
+; CHECK-NEXT:    vrgather.vi v16, v17, 9, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 1 x i16> @llvm.riscv.vrgather.mask.nxv1i16.i16(
+    <vscale x 1 x i16> %0,
+    <vscale x 1 x i16> %1,
+    i16 9,
+    <vscale x 1 x i1> %2,
+    i32 %3)
+
+  ret <vscale x 1 x i16> %a
+}
+
+define <vscale x 2 x i16> @intrinsic_vrgather_vi_nxv2i16_nxv2i16_i16(<vscale x 2 x i16> %0, i32 %1) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vi_nxv2i16_nxv2i16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e16,mf2,ta,mu
+; CHECK-NEXT:    vrgather.vi v25, v16, 9
+; CHECK-NEXT:    vmv1r.v v16, v25
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 2 x i16> @llvm.riscv.vrgather.nxv2i16.i16(
+    <vscale x 2 x i16> %0,
+    i16 9,
+    i32 %1)
+
+  ret <vscale x 2 x i16> %a
+}
+
+define <vscale x 2 x i16> @intrinsic_vrgather_mask_vi_nxv2i16_nxv2i16_i16(<vscale x 2 x i16> %0, <vscale x 2 x i16> %1, <vscale x 2 x i1> %2, i32 %3) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vi_nxv2i16_nxv2i16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e16,mf2,ta,mu
+; CHECK-NEXT:    vrgather.vi v16, v17, 9, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 2 x i16> @llvm.riscv.vrgather.mask.nxv2i16.i16(
+    <vscale x 2 x i16> %0,
+    <vscale x 2 x i16> %1,
+    i16 9,
+    <vscale x 2 x i1> %2,
+    i32 %3)
+
+  ret <vscale x 2 x i16> %a
+}
+
+define <vscale x 4 x i16> @intrinsic_vrgather_vi_nxv4i16_nxv4i16_i16(<vscale x 4 x i16> %0, i32 %1) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vi_nxv4i16_nxv4i16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e16,m1,ta,mu
+; CHECK-NEXT:    vrgather.vi v25, v16, 9
+; CHECK-NEXT:    vmv1r.v v16, v25
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 4 x i16> @llvm.riscv.vrgather.nxv4i16.i16(
+    <vscale x 4 x i16> %0,
+    i16 9,
+    i32 %1)
+
+  ret <vscale x 4 x i16> %a
+}
+
+define <vscale x 4 x i16> @intrinsic_vrgather_mask_vi_nxv4i16_nxv4i16_i16(<vscale x 4 x i16> %0, <vscale x 4 x i16> %1, <vscale x 4 x i1> %2, i32 %3) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vi_nxv4i16_nxv4i16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e16,m1,ta,mu
+; CHECK-NEXT:    vrgather.vi v16, v17, 9, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 4 x i16> @llvm.riscv.vrgather.mask.nxv4i16.i16(
+    <vscale x 4 x i16> %0,
+    <vscale x 4 x i16> %1,
+    i16 9,
+    <vscale x 4 x i1> %2,
+    i32 %3)
+
+  ret <vscale x 4 x i16> %a
+}
+
+define <vscale x 8 x i16> @intrinsic_vrgather_vi_nxv8i16_nxv8i16_i16(<vscale x 8 x i16> %0, i32 %1) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vi_nxv8i16_nxv8i16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e16,m2,ta,mu
+; CHECK-NEXT:    vrgather.vi v26, v16, 9
+; CHECK-NEXT:    vmv2r.v v16, v26
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 8 x i16> @llvm.riscv.vrgather.nxv8i16.i16(
+    <vscale x 8 x i16> %0,
+    i16 9,
+    i32 %1)
+
+  ret <vscale x 8 x i16> %a
+}
+
+define <vscale x 8 x i16> @intrinsic_vrgather_mask_vi_nxv8i16_nxv8i16_i16(<vscale x 8 x i16> %0, <vscale x 8 x i16> %1, <vscale x 8 x i1> %2, i32 %3) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vi_nxv8i16_nxv8i16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e16,m2,ta,mu
+; CHECK-NEXT:    vrgather.vi v16, v18, 9, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 8 x i16> @llvm.riscv.vrgather.mask.nxv8i16.i16(
+    <vscale x 8 x i16> %0,
+    <vscale x 8 x i16> %1,
+    i16 9,
+    <vscale x 8 x i1> %2,
+    i32 %3)
+
+  ret <vscale x 8 x i16> %a
+}
+
+define <vscale x 16 x i16> @intrinsic_vrgather_vi_nxv16i16_nxv16i16_i16(<vscale x 16 x i16> %0, i32 %1) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vi_nxv16i16_nxv16i16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e16,m4,ta,mu
+; CHECK-NEXT:    vrgather.vi v28, v16, 9
+; CHECK-NEXT:    vmv4r.v v16, v28
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 16 x i16> @llvm.riscv.vrgather.nxv16i16.i16(
+    <vscale x 16 x i16> %0,
+    i16 9,
+    i32 %1)
+
+  ret <vscale x 16 x i16> %a
+}
+
+define <vscale x 16 x i16> @intrinsic_vrgather_mask_vi_nxv16i16_nxv16i16_i16(<vscale x 16 x i16> %0, <vscale x 16 x i16> %1, <vscale x 16 x i1> %2, i32 %3) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vi_nxv16i16_nxv16i16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e16,m4,ta,mu
+; CHECK-NEXT:    vrgather.vi v16, v20, 9, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 16 x i16> @llvm.riscv.vrgather.mask.nxv16i16.i16(
+    <vscale x 16 x i16> %0,
+    <vscale x 16 x i16> %1,
+    i16 9,
+    <vscale x 16 x i1> %2,
+    i32 %3)
+
+  ret <vscale x 16 x i16> %a
+}
+
+define <vscale x 32 x i16> @intrinsic_vrgather_vi_nxv32i16_nxv32i16_i16(<vscale x 32 x i16> %0, i32 %1) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vi_nxv32i16_nxv32i16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e16,m8,ta,mu
+; CHECK-NEXT:    vrgather.vi v8, v16, 9
+; CHECK-NEXT:    vmv8r.v v16, v8
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 32 x i16> @llvm.riscv.vrgather.nxv32i16.i16(
+    <vscale x 32 x i16> %0,
+    i16 9,
+    i32 %1)
+
+  ret <vscale x 32 x i16> %a
+}
+
+define <vscale x 32 x i16> @intrinsic_vrgather_mask_vi_nxv32i16_nxv32i16_i16(<vscale x 32 x i16> %0, <vscale x 32 x i16> %1, <vscale x 32 x i1> %2, i32 %3) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vi_nxv32i16_nxv32i16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a2, zero, e16,m8,ta,mu
+; CHECK-NEXT:    vle16.v v8, (a0)
+; CHECK-NEXT:    vsetvli a0, a1, e16,m8,ta,mu
+; CHECK-NEXT:    vrgather.vi v16, v8, 9, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 32 x i16> @llvm.riscv.vrgather.mask.nxv32i16.i16(
+    <vscale x 32 x i16> %0,
+    <vscale x 32 x i16> %1,
+    i16 9,
+    <vscale x 32 x i1> %2,
+    i32 %3)
+
+  ret <vscale x 32 x i16> %a
+}
+
+define <vscale x 1 x i32> @intrinsic_vrgather_vi_nxv1i32_nxv1i32_i32(<vscale x 1 x i32> %0, i32 %1) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vi_nxv1i32_nxv1i32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e32,mf2,ta,mu
+; CHECK-NEXT:    vrgather.vi v25, v16, 9
+; CHECK-NEXT:    vmv1r.v v16, v25
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 1 x i32> @llvm.riscv.vrgather.nxv1i32.i32(
+    <vscale x 1 x i32> %0,
+    i32 9,
+    i32 %1)
+
+  ret <vscale x 1 x i32> %a
+}
+
+define <vscale x 1 x i32> @intrinsic_vrgather_mask_vi_nxv1i32_nxv1i32_i32(<vscale x 1 x i32> %0, <vscale x 1 x i32> %1, <vscale x 1 x i1> %2, i32 %3) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vi_nxv1i32_nxv1i32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e32,mf2,ta,mu
+; CHECK-NEXT:    vrgather.vi v16, v17, 9, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 1 x i32> @llvm.riscv.vrgather.mask.nxv1i32.i32(
+    <vscale x 1 x i32> %0,
+    <vscale x 1 x i32> %1,
+    i32 9,
+    <vscale x 1 x i1> %2,
+    i32 %3)
+
+  ret <vscale x 1 x i32> %a
+}
+
+define <vscale x 2 x i32> @intrinsic_vrgather_vi_nxv2i32_nxv2i32_i32(<vscale x 2 x i32> %0, i32 %1) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vi_nxv2i32_nxv2i32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e32,m1,ta,mu
+; CHECK-NEXT:    vrgather.vi v25, v16, 9
+; CHECK-NEXT:    vmv1r.v v16, v25
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 2 x i32> @llvm.riscv.vrgather.nxv2i32.i32(
+    <vscale x 2 x i32> %0,
+    i32 9,
+    i32 %1)
+
+  ret <vscale x 2 x i32> %a
+}
+
+define <vscale x 2 x i32> @intrinsic_vrgather_mask_vi_nxv2i32_nxv2i32_i32(<vscale x 2 x i32> %0, <vscale x 2 x i32> %1, <vscale x 2 x i1> %2, i32 %3) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vi_nxv2i32_nxv2i32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e32,m1,ta,mu
+; CHECK-NEXT:    vrgather.vi v16, v17, 9, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 2 x i32> @llvm.riscv.vrgather.mask.nxv2i32.i32(
+    <vscale x 2 x i32> %0,
+    <vscale x 2 x i32> %1,
+    i32 9,
+    <vscale x 2 x i1> %2,
+    i32 %3)
+
+  ret <vscale x 2 x i32> %a
+}
+
+define <vscale x 4 x i32> @intrinsic_vrgather_vi_nxv4i32_nxv4i32_i32(<vscale x 4 x i32> %0, i32 %1) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vi_nxv4i32_nxv4i32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e32,m2,ta,mu
+; CHECK-NEXT:    vrgather.vi v26, v16, 9
+; CHECK-NEXT:    vmv2r.v v16, v26
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 4 x i32> @llvm.riscv.vrgather.nxv4i32.i32(
+    <vscale x 4 x i32> %0,
+    i32 9,
+    i32 %1)
+
+  ret <vscale x 4 x i32> %a
+}
+
+define <vscale x 4 x i32> @intrinsic_vrgather_mask_vi_nxv4i32_nxv4i32_i32(<vscale x 4 x i32> %0, <vscale x 4 x i32> %1, <vscale x 4 x i1> %2, i32 %3) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vi_nxv4i32_nxv4i32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e32,m2,ta,mu
+; CHECK-NEXT:    vrgather.vi v16, v18, 9, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 4 x i32> @llvm.riscv.vrgather.mask.nxv4i32.i32(
+    <vscale x 4 x i32> %0,
+    <vscale x 4 x i32> %1,
+    i32 9,
+    <vscale x 4 x i1> %2,
+    i32 %3)
+
+  ret <vscale x 4 x i32> %a
+}
+
+define <vscale x 8 x i32> @intrinsic_vrgather_vi_nxv8i32_nxv8i32_i32(<vscale x 8 x i32> %0, i32 %1) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vi_nxv8i32_nxv8i32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e32,m4,ta,mu
+; CHECK-NEXT:    vrgather.vi v28, v16, 9
+; CHECK-NEXT:    vmv4r.v v16, v28
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 8 x i32> @llvm.riscv.vrgather.nxv8i32.i32(
+    <vscale x 8 x i32> %0,
+    i32 9,
+    i32 %1)
+
+  ret <vscale x 8 x i32> %a
+}
+
+define <vscale x 8 x i32> @intrinsic_vrgather_mask_vi_nxv8i32_nxv8i32_i32(<vscale x 8 x i32> %0, <vscale x 8 x i32> %1, <vscale x 8 x i1> %2, i32 %3) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vi_nxv8i32_nxv8i32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e32,m4,ta,mu
+; CHECK-NEXT:    vrgather.vi v16, v20, 9, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 8 x i32> @llvm.riscv.vrgather.mask.nxv8i32.i32(
+    <vscale x 8 x i32> %0,
+    <vscale x 8 x i32> %1,
+    i32 9,
+    <vscale x 8 x i1> %2,
+    i32 %3)
+
+  ret <vscale x 8 x i32> %a
+}
+
+define <vscale x 16 x i32> @intrinsic_vrgather_vi_nxv16i32_nxv16i32_i32(<vscale x 16 x i32> %0, i32 %1) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vi_nxv16i32_nxv16i32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e32,m8,ta,mu
+; CHECK-NEXT:    vrgather.vi v8, v16, 9
+; CHECK-NEXT:    vmv8r.v v16, v8
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 16 x i32> @llvm.riscv.vrgather.nxv16i32.i32(
+    <vscale x 16 x i32> %0,
+    i32 9,
+    i32 %1)
+
+  ret <vscale x 16 x i32> %a
+}
+
+define <vscale x 16 x i32> @intrinsic_vrgather_mask_vi_nxv16i32_nxv16i32_i32(<vscale x 16 x i32> %0, <vscale x 16 x i32> %1, <vscale x 16 x i1> %2, i32 %3) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vi_nxv16i32_nxv16i32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a2, zero, e32,m8,ta,mu
+; CHECK-NEXT:    vle32.v v8, (a0)
+; CHECK-NEXT:    vsetvli a0, a1, e32,m8,ta,mu
+; CHECK-NEXT:    vrgather.vi v16, v8, 9, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 16 x i32> @llvm.riscv.vrgather.mask.nxv16i32.i32(
+    <vscale x 16 x i32> %0,
+    <vscale x 16 x i32> %1,
+    i32 9,
+    <vscale x 16 x i1> %2,
+    i32 %3)
+
+  ret <vscale x 16 x i32> %a
+}
+
+define <vscale x 1 x half> @intrinsic_vrgather_vi_nxv1f16_nxv1f16_i16(<vscale x 1 x half> %0, i32 %1) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vi_nxv1f16_nxv1f16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e16,mf4,ta,mu
+; CHECK-NEXT:    vrgather.vi v25, v16, 9
+; CHECK-NEXT:    vmv1r.v v16, v25
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 1 x half> @llvm.riscv.vrgather.nxv1f16.i16(
+    <vscale x 1 x half> %0,
+    i16 9,
+    i32 %1)
+
+  ret <vscale x 1 x half> %a
+}
+
+define <vscale x 1 x half> @intrinsic_vrgather_mask_vi_nxv1f16_nxv1f16_i16(<vscale x 1 x half> %0, <vscale x 1 x half> %1, <vscale x 1 x i1> %2, i32 %3) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vi_nxv1f16_nxv1f16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e16,mf4,ta,mu
+; CHECK-NEXT:    vrgather.vi v16, v17, 9, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 1 x half> @llvm.riscv.vrgather.mask.nxv1f16.i16(
+    <vscale x 1 x half> %0,
+    <vscale x 1 x half> %1,
+    i16 9,
+    <vscale x 1 x i1> %2,
+    i32 %3)
+
+  ret <vscale x 1 x half> %a
+}
+
+define <vscale x 2 x half> @intrinsic_vrgather_vi_nxv2f16_nxv2f16_i16(<vscale x 2 x half> %0, i32 %1) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vi_nxv2f16_nxv2f16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e16,mf2,ta,mu
+; CHECK-NEXT:    vrgather.vi v25, v16, 9
+; CHECK-NEXT:    vmv1r.v v16, v25
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 2 x half> @llvm.riscv.vrgather.nxv2f16.i16(
+    <vscale x 2 x half> %0,
+    i16 9,
+    i32 %1)
+
+  ret <vscale x 2 x half> %a
+}
+
+define <vscale x 2 x half> @intrinsic_vrgather_mask_vi_nxv2f16_nxv2f16_i16(<vscale x 2 x half> %0, <vscale x 2 x half> %1, <vscale x 2 x i1> %2, i32 %3) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vi_nxv2f16_nxv2f16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e16,mf2,ta,mu
+; CHECK-NEXT:    vrgather.vi v16, v17, 9, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 2 x half> @llvm.riscv.vrgather.mask.nxv2f16.i16(
+    <vscale x 2 x half> %0,
+    <vscale x 2 x half> %1,
+    i16 9,
+    <vscale x 2 x i1> %2,
+    i32 %3)
+
+  ret <vscale x 2 x half> %a
+}
+
+define <vscale x 4 x half> @intrinsic_vrgather_vi_nxv4f16_nxv4f16_i16(<vscale x 4 x half> %0, i32 %1) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vi_nxv4f16_nxv4f16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e16,m1,ta,mu
+; CHECK-NEXT:    vrgather.vi v25, v16, 9
+; CHECK-NEXT:    vmv1r.v v16, v25
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 4 x half> @llvm.riscv.vrgather.nxv4f16.i16(
+    <vscale x 4 x half> %0,
+    i16 9,
+    i32 %1)
+
+  ret <vscale x 4 x half> %a
+}
+
+define <vscale x 4 x half> @intrinsic_vrgather_mask_vi_nxv4f16_nxv4f16_i16(<vscale x 4 x half> %0, <vscale x 4 x half> %1, <vscale x 4 x i1> %2, i32 %3) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vi_nxv4f16_nxv4f16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e16,m1,ta,mu
+; CHECK-NEXT:    vrgather.vi v16, v17, 9, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 4 x half> @llvm.riscv.vrgather.mask.nxv4f16.i16(
+    <vscale x 4 x half> %0,
+    <vscale x 4 x half> %1,
+    i16 9,
+    <vscale x 4 x i1> %2,
+    i32 %3)
+
+  ret <vscale x 4 x half> %a
+}
+
+define <vscale x 8 x half> @intrinsic_vrgather_vi_nxv8f16_nxv8f16_i16(<vscale x 8 x half> %0, i32 %1) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vi_nxv8f16_nxv8f16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e16,m2,ta,mu
+; CHECK-NEXT:    vrgather.vi v26, v16, 9
+; CHECK-NEXT:    vmv2r.v v16, v26
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 8 x half> @llvm.riscv.vrgather.nxv8f16.i16(
+    <vscale x 8 x half> %0,
+    i16 9,
+    i32 %1)
+
+  ret <vscale x 8 x half> %a
+}
+
+define <vscale x 8 x half> @intrinsic_vrgather_mask_vi_nxv8f16_nxv8f16_i16(<vscale x 8 x half> %0, <vscale x 8 x half> %1, <vscale x 8 x i1> %2, i32 %3) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vi_nxv8f16_nxv8f16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e16,m2,ta,mu
+; CHECK-NEXT:    vrgather.vi v16, v18, 9, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 8 x half> @llvm.riscv.vrgather.mask.nxv8f16.i16(
+    <vscale x 8 x half> %0,
+    <vscale x 8 x half> %1,
+    i16 9,
+    <vscale x 8 x i1> %2,
+    i32 %3)
+
+  ret <vscale x 8 x half> %a
+}
+
+define <vscale x 16 x half> @intrinsic_vrgather_vi_nxv16f16_nxv16f16_i16(<vscale x 16 x half> %0, i32 %1) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vi_nxv16f16_nxv16f16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e16,m4,ta,mu
+; CHECK-NEXT:    vrgather.vi v28, v16, 9
+; CHECK-NEXT:    vmv4r.v v16, v28
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 16 x half> @llvm.riscv.vrgather.nxv16f16.i16(
+    <vscale x 16 x half> %0,
+    i16 9,
+    i32 %1)
+
+  ret <vscale x 16 x half> %a
+}
+
+define <vscale x 16 x half> @intrinsic_vrgather_mask_vi_nxv16f16_nxv16f16_i16(<vscale x 16 x half> %0, <vscale x 16 x half> %1, <vscale x 16 x i1> %2, i32 %3) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vi_nxv16f16_nxv16f16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e16,m4,ta,mu
+; CHECK-NEXT:    vrgather.vi v16, v20, 9, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 16 x half> @llvm.riscv.vrgather.mask.nxv16f16.i16(
+    <vscale x 16 x half> %0,
+    <vscale x 16 x half> %1,
+    i16 9,
+    <vscale x 16 x i1> %2,
+    i32 %3)
+
+  ret <vscale x 16 x half> %a
+}
+
+define <vscale x 32 x half> @intrinsic_vrgather_vi_nxv32f16_nxv32f16_i16(<vscale x 32 x half> %0, i32 %1) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vi_nxv32f16_nxv32f16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e16,m8,ta,mu
+; CHECK-NEXT:    vrgather.vi v8, v16, 9
+; CHECK-NEXT:    vmv8r.v v16, v8
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 32 x half> @llvm.riscv.vrgather.nxv32f16.i16(
+    <vscale x 32 x half> %0,
+    i16 9,
+    i32 %1)
+
+  ret <vscale x 32 x half> %a
+}
+
+define <vscale x 32 x half> @intrinsic_vrgather_mask_vi_nxv32f16_nxv32f16_i16(<vscale x 32 x half> %0, <vscale x 32 x half> %1, <vscale x 32 x i1> %2, i32 %3) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vi_nxv32f16_nxv32f16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a2, zero, e16,m8,ta,mu
+; CHECK-NEXT:    vle16.v v8, (a0)
+; CHECK-NEXT:    vsetvli a0, a1, e16,m8,ta,mu
+; CHECK-NEXT:    vrgather.vi v16, v8, 9, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 32 x half> @llvm.riscv.vrgather.mask.nxv32f16.i16(
+    <vscale x 32 x half> %0,
+    <vscale x 32 x half> %1,
+    i16 9,
+    <vscale x 32 x i1> %2,
+    i32 %3)
+
+  ret <vscale x 32 x half> %a
+}
+
+define <vscale x 1 x float> @intrinsic_vrgather_vi_nxv1f32_nxv1f32_i32(<vscale x 1 x float> %0, i32 %1) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vi_nxv1f32_nxv1f32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e32,mf2,ta,mu
+; CHECK-NEXT:    vrgather.vi v25, v16, 9
+; CHECK-NEXT:    vmv1r.v v16, v25
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 1 x float> @llvm.riscv.vrgather.nxv1f32.i32(
+    <vscale x 1 x float> %0,
+    i32 9,
+    i32 %1)
+
+  ret <vscale x 1 x float> %a
+}
+
+define <vscale x 1 x float> @intrinsic_vrgather_mask_vi_nxv1f32_nxv1f32_i32(<vscale x 1 x float> %0, <vscale x 1 x float> %1, <vscale x 1 x i1> %2, i32 %3) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vi_nxv1f32_nxv1f32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e32,mf2,ta,mu
+; CHECK-NEXT:    vrgather.vi v16, v17, 9, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 1 x float> @llvm.riscv.vrgather.mask.nxv1f32.i32(
+    <vscale x 1 x float> %0,
+    <vscale x 1 x float> %1,
+    i32 9,
+    <vscale x 1 x i1> %2,
+    i32 %3)
+
+  ret <vscale x 1 x float> %a
+}
+
+define <vscale x 2 x float> @intrinsic_vrgather_vi_nxv2f32_nxv2f32_i32(<vscale x 2 x float> %0, i32 %1) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vi_nxv2f32_nxv2f32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e32,m1,ta,mu
+; CHECK-NEXT:    vrgather.vi v25, v16, 9
+; CHECK-NEXT:    vmv1r.v v16, v25
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 2 x float> @llvm.riscv.vrgather.nxv2f32.i32(
+    <vscale x 2 x float> %0,
+    i32 9,
+    i32 %1)
+
+  ret <vscale x 2 x float> %a
+}
+
+define <vscale x 2 x float> @intrinsic_vrgather_mask_vi_nxv2f32_nxv2f32_i32(<vscale x 2 x float> %0, <vscale x 2 x float> %1, <vscale x 2 x i1> %2, i32 %3) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vi_nxv2f32_nxv2f32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e32,m1,ta,mu
+; CHECK-NEXT:    vrgather.vi v16, v17, 9, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 2 x float> @llvm.riscv.vrgather.mask.nxv2f32.i32(
+    <vscale x 2 x float> %0,
+    <vscale x 2 x float> %1,
+    i32 9,
+    <vscale x 2 x i1> %2,
+    i32 %3)
+
+  ret <vscale x 2 x float> %a
+}
+
+define <vscale x 4 x float> @intrinsic_vrgather_vi_nxv4f32_nxv4f32_i32(<vscale x 4 x float> %0, i32 %1) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vi_nxv4f32_nxv4f32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e32,m2,ta,mu
+; CHECK-NEXT:    vrgather.vi v26, v16, 9
+; CHECK-NEXT:    vmv2r.v v16, v26
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 4 x float> @llvm.riscv.vrgather.nxv4f32.i32(
+    <vscale x 4 x float> %0,
+    i32 9,
+    i32 %1)
+
+  ret <vscale x 4 x float> %a
+}
+
+define <vscale x 4 x float> @intrinsic_vrgather_mask_vi_nxv4f32_nxv4f32_i32(<vscale x 4 x float> %0, <vscale x 4 x float> %1, <vscale x 4 x i1> %2, i32 %3) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vi_nxv4f32_nxv4f32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e32,m2,ta,mu
+; CHECK-NEXT:    vrgather.vi v16, v18, 9, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 4 x float> @llvm.riscv.vrgather.mask.nxv4f32.i32(
+    <vscale x 4 x float> %0,
+    <vscale x 4 x float> %1,
+    i32 9,
+    <vscale x 4 x i1> %2,
+    i32 %3)
+
+  ret <vscale x 4 x float> %a
+}
+
+define <vscale x 8 x float> @intrinsic_vrgather_vi_nxv8f32_nxv8f32_i32(<vscale x 8 x float> %0, i32 %1) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vi_nxv8f32_nxv8f32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e32,m4,ta,mu
+; CHECK-NEXT:    vrgather.vi v28, v16, 9
+; CHECK-NEXT:    vmv4r.v v16, v28
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 8 x float> @llvm.riscv.vrgather.nxv8f32.i32(
+    <vscale x 8 x float> %0,
+    i32 9,
+    i32 %1)
+
+  ret <vscale x 8 x float> %a
+}
+
+define <vscale x 8 x float> @intrinsic_vrgather_mask_vi_nxv8f32_nxv8f32_i32(<vscale x 8 x float> %0, <vscale x 8 x float> %1, <vscale x 8 x i1> %2, i32 %3) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vi_nxv8f32_nxv8f32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e32,m4,ta,mu
+; CHECK-NEXT:    vrgather.vi v16, v20, 9, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 8 x float> @llvm.riscv.vrgather.mask.nxv8f32.i32(
+    <vscale x 8 x float> %0,
+    <vscale x 8 x float> %1,
+    i32 9,
+    <vscale x 8 x i1> %2,
+    i32 %3)
+
+  ret <vscale x 8 x float> %a
+}
+
+define <vscale x 16 x float> @intrinsic_vrgather_vi_nxv16f32_nxv16f32_i32(<vscale x 16 x float> %0, i32 %1) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vi_nxv16f32_nxv16f32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e32,m8,ta,mu
+; CHECK-NEXT:    vrgather.vi v8, v16, 9
+; CHECK-NEXT:    vmv8r.v v16, v8
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 16 x float> @llvm.riscv.vrgather.nxv16f32.i32(
+    <vscale x 16 x float> %0,
+    i32 9,
+    i32 %1)
+
+  ret <vscale x 16 x float> %a
+}
+
+define <vscale x 16 x float> @intrinsic_vrgather_mask_vi_nxv16f32_nxv16f32_i32(<vscale x 16 x float> %0, <vscale x 16 x float> %1, <vscale x 16 x i1> %2, i32 %3) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vi_nxv16f32_nxv16f32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a2, zero, e32,m8,ta,mu
+; CHECK-NEXT:    vle32.v v8, (a0)
+; CHECK-NEXT:    vsetvli a0, a1, e32,m8,ta,mu
+; CHECK-NEXT:    vrgather.vi v16, v8, 9, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 16 x float> @llvm.riscv.vrgather.mask.nxv16f32.i32(
+    <vscale x 16 x float> %0,
+    <vscale x 16 x float> %1,
+    i32 9,
+    <vscale x 16 x i1> %2,
+    i32 %3)
+
+  ret <vscale x 16 x float> %a
+}

llvm/test/CodeGen/RISCV/rvv/vrgather-rv64.ll

+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc -mtriple=riscv64 -mattr=+experimental-v,+d,+experimental-zfh -verify-machineinstrs \
+; RUN:   --riscv-no-aliases < %s | FileCheck %s
+declare <vscale x 1 x i8> @llvm.riscv.vrgather.nxv1i8.nxv1i8(
+  <vscale x 1 x i8>,
+  <vscale x 1 x i8>,
+  i64);
+
+define <vscale x 1 x i8> @intrinsic_vrgather_vv_nxv1i8_nxv1i8_nxv1i8(<vscale x 1 x i8> %0, <vscale x 1 x i8> %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vv_nxv1i8_nxv1i8_nxv1i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e8,mf8,ta,mu
+; CHECK-NEXT:    vrgather.vv v25, v16, v17
+; CHECK-NEXT:    vmv1r.v v16, v25
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 1 x i8> @llvm.riscv.vrgather.nxv1i8.nxv1i8(
+    <vscale x 1 x i8> %0,
+    <vscale x 1 x i8> %1,
+    i64 %2)
+
+  ret <vscale x 1 x i8> %a
+}
+
+declare <vscale x 1 x i8> @llvm.riscv.vrgather.mask.nxv1i8.nxv1i8(
+  <vscale x 1 x i8>,
+  <vscale x 1 x i8>,
+  <vscale x 1 x i8>,
+  <vscale x 1 x i1>,
+  i64);
+
+define <vscale x 1 x i8> @intrinsic_vrgather_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_vrgather_mask_vv_nxv1i8_nxv1i8_nxv1i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e8,mf8,ta,mu
+; CHECK-NEXT:    vrgather.vv v16, v17, v18, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 1 x i8> @llvm.riscv.vrgather.mask.nxv1i8.nxv1i8(
+    <vscale x 1 x i8> %0,
+    <vscale x 1 x i8> %1,
+    <vscale x 1 x i8> %2,
+    <vscale x 1 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 1 x i8> %a
+}
+
+declare <vscale x 2 x i8> @llvm.riscv.vrgather.nxv2i8.nxv2i8(
+  <vscale x 2 x i8>,
+  <vscale x 2 x i8>,
+  i64);
+
+define <vscale x 2 x i8> @intrinsic_vrgather_vv_nxv2i8_nxv2i8_nxv2i8(<vscale x 2 x i8> %0, <vscale x 2 x i8> %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vv_nxv2i8_nxv2i8_nxv2i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e8,mf4,ta,mu
+; CHECK-NEXT:    vrgather.vv v25, v16, v17
+; CHECK-NEXT:    vmv1r.v v16, v25
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 2 x i8> @llvm.riscv.vrgather.nxv2i8.nxv2i8(
+    <vscale x 2 x i8> %0,
+    <vscale x 2 x i8> %1,
+    i64 %2)
+
+  ret <vscale x 2 x i8> %a
+}
+
+declare <vscale x 2 x i8> @llvm.riscv.vrgather.mask.nxv2i8.nxv2i8(
+  <vscale x 2 x i8>,
+  <vscale x 2 x i8>,
+  <vscale x 2 x i8>,
+  <vscale x 2 x i1>,
+  i64);
+
+define <vscale x 2 x i8> @intrinsic_vrgather_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_vrgather_mask_vv_nxv2i8_nxv2i8_nxv2i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e8,mf4,ta,mu
+; CHECK-NEXT:    vrgather.vv v16, v17, v18, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 2 x i8> @llvm.riscv.vrgather.mask.nxv2i8.nxv2i8(
+    <vscale x 2 x i8> %0,
+    <vscale x 2 x i8> %1,
+    <vscale x 2 x i8> %2,
+    <vscale x 2 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 2 x i8> %a
+}
+
+declare <vscale x 4 x i8> @llvm.riscv.vrgather.nxv4i8.nxv4i8(
+  <vscale x 4 x i8>,
+  <vscale x 4 x i8>,
+  i64);
+
+define <vscale x 4 x i8> @intrinsic_vrgather_vv_nxv4i8_nxv4i8_nxv4i8(<vscale x 4 x i8> %0, <vscale x 4 x i8> %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vv_nxv4i8_nxv4i8_nxv4i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e8,mf2,ta,mu
+; CHECK-NEXT:    vrgather.vv v25, v16, v17
+; CHECK-NEXT:    vmv1r.v v16, v25
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 4 x i8> @llvm.riscv.vrgather.nxv4i8.nxv4i8(
+    <vscale x 4 x i8> %0,
+    <vscale x 4 x i8> %1,
+    i64 %2)
+
+  ret <vscale x 4 x i8> %a
+}
+
+declare <vscale x 4 x i8> @llvm.riscv.vrgather.mask.nxv4i8.nxv4i8(
+  <vscale x 4 x i8>,
+  <vscale x 4 x i8>,
+  <vscale x 4 x i8>,
+  <vscale x 4 x i1>,
+  i64);
+
+define <vscale x 4 x i8> @intrinsic_vrgather_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_vrgather_mask_vv_nxv4i8_nxv4i8_nxv4i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e8,mf2,ta,mu
+; CHECK-NEXT:    vrgather.vv v16, v17, v18, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 4 x i8> @llvm.riscv.vrgather.mask.nxv4i8.nxv4i8(
+    <vscale x 4 x i8> %0,
+    <vscale x 4 x i8> %1,
+    <vscale x 4 x i8> %2,
+    <vscale x 4 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 4 x i8> %a
+}
+
+declare <vscale x 8 x i8> @llvm.riscv.vrgather.nxv8i8.nxv8i8(
+  <vscale x 8 x i8>,
+  <vscale x 8 x i8>,
+  i64);
+
+define <vscale x 8 x i8> @intrinsic_vrgather_vv_nxv8i8_nxv8i8_nxv8i8(<vscale x 8 x i8> %0, <vscale x 8 x i8> %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vv_nxv8i8_nxv8i8_nxv8i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e8,m1,ta,mu
+; CHECK-NEXT:    vrgather.vv v25, v16, v17
+; CHECK-NEXT:    vmv1r.v v16, v25
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 8 x i8> @llvm.riscv.vrgather.nxv8i8.nxv8i8(
+    <vscale x 8 x i8> %0,
+    <vscale x 8 x i8> %1,
+    i64 %2)
+
+  ret <vscale x 8 x i8> %a
+}
+
+declare <vscale x 8 x i8> @llvm.riscv.vrgather.mask.nxv8i8.nxv8i8(
+  <vscale x 8 x i8>,
+  <vscale x 8 x i8>,
+  <vscale x 8 x i8>,
+  <vscale x 8 x i1>,
+  i64);
+
+define <vscale x 8 x i8> @intrinsic_vrgather_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_vrgather_mask_vv_nxv8i8_nxv8i8_nxv8i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e8,m1,ta,mu
+; CHECK-NEXT:    vrgather.vv v16, v17, v18, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 8 x i8> @llvm.riscv.vrgather.mask.nxv8i8.nxv8i8(
+    <vscale x 8 x i8> %0,
+    <vscale x 8 x i8> %1,
+    <vscale x 8 x i8> %2,
+    <vscale x 8 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 8 x i8> %a
+}
+
+declare <vscale x 16 x i8> @llvm.riscv.vrgather.nxv16i8.nxv16i8(
+  <vscale x 16 x i8>,
+  <vscale x 16 x i8>,
+  i64);
+
+define <vscale x 16 x i8> @intrinsic_vrgather_vv_nxv16i8_nxv16i8_nxv16i8(<vscale x 16 x i8> %0, <vscale x 16 x i8> %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vv_nxv16i8_nxv16i8_nxv16i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e8,m2,ta,mu
+; CHECK-NEXT:    vrgather.vv v26, v16, v18
+; CHECK-NEXT:    vmv2r.v v16, v26
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 16 x i8> @llvm.riscv.vrgather.nxv16i8.nxv16i8(
+    <vscale x 16 x i8> %0,
+    <vscale x 16 x i8> %1,
+    i64 %2)
+
+  ret <vscale x 16 x i8> %a
+}
+
+declare <vscale x 16 x i8> @llvm.riscv.vrgather.mask.nxv16i8.nxv16i8(
+  <vscale x 16 x i8>,
+  <vscale x 16 x i8>,
+  <vscale x 16 x i8>,
+  <vscale x 16 x i1>,
+  i64);
+
+define <vscale x 16 x i8> @intrinsic_vrgather_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_vrgather_mask_vv_nxv16i8_nxv16i8_nxv16i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e8,m2,ta,mu
+; CHECK-NEXT:    vrgather.vv v16, v18, v20, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 16 x i8> @llvm.riscv.vrgather.mask.nxv16i8.nxv16i8(
+    <vscale x 16 x i8> %0,
+    <vscale x 16 x i8> %1,
+    <vscale x 16 x i8> %2,
+    <vscale x 16 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 16 x i8> %a
+}
+
+declare <vscale x 32 x i8> @llvm.riscv.vrgather.nxv32i8.nxv32i8(
+  <vscale x 32 x i8>,
+  <vscale x 32 x i8>,
+  i64);
+
+define <vscale x 32 x i8> @intrinsic_vrgather_vv_nxv32i8_nxv32i8_nxv32i8(<vscale x 32 x i8> %0, <vscale x 32 x i8> %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vv_nxv32i8_nxv32i8_nxv32i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e8,m4,ta,mu
+; CHECK-NEXT:    vrgather.vv v28, v16, v20
+; CHECK-NEXT:    vmv4r.v v16, v28
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 32 x i8> @llvm.riscv.vrgather.nxv32i8.nxv32i8(
+    <vscale x 32 x i8> %0,
+    <vscale x 32 x i8> %1,
+    i64 %2)
+
+  ret <vscale x 32 x i8> %a
+}
+
+declare <vscale x 32 x i8> @llvm.riscv.vrgather.mask.nxv32i8.nxv32i8(
+  <vscale x 32 x i8>,
+  <vscale x 32 x i8>,
+  <vscale x 32 x i8>,
+  <vscale x 32 x i1>,
+  i64);
+
+define <vscale x 32 x i8> @intrinsic_vrgather_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_vrgather_mask_vv_nxv32i8_nxv32i8_nxv32i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a2, zero, e8,m4,ta,mu
+; CHECK-NEXT:    vle8.v v28, (a0)
+; CHECK-NEXT:    vsetvli a0, a1, e8,m4,ta,mu
+; CHECK-NEXT:    vrgather.vv v16, v20, v28, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 32 x i8> @llvm.riscv.vrgather.mask.nxv32i8.nxv32i8(
+    <vscale x 32 x i8> %0,
+    <vscale x 32 x i8> %1,
+    <vscale x 32 x i8> %2,
+    <vscale x 32 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 32 x i8> %a
+}
+
+declare <vscale x 64 x i8> @llvm.riscv.vrgather.nxv64i8.nxv64i8(
+  <vscale x 64 x i8>,
+  <vscale x 64 x i8>,
+  i64);
+
+define <vscale x 64 x i8> @intrinsic_vrgather_vv_nxv64i8_nxv64i8_nxv64i8(<vscale x 64 x i8> %0, <vscale x 64 x i8> %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vv_nxv64i8_nxv64i8_nxv64i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a2, zero, e8,m8,ta,mu
+; CHECK-NEXT:    vle8.v v24, (a0)
+; CHECK-NEXT:    vsetvli a0, a1, e8,m8,ta,mu
+; CHECK-NEXT:    vrgather.vv v8, v16, v24
+; CHECK-NEXT:    vmv8r.v v16, v8
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 64 x i8> @llvm.riscv.vrgather.nxv64i8.nxv64i8(
+    <vscale x 64 x i8> %0,
+    <vscale x 64 x i8> %1,
+    i64 %2)
+
+  ret <vscale x 64 x i8> %a
+}
+
+declare <vscale x 64 x i8> @llvm.riscv.vrgather.mask.nxv64i8.nxv64i8(
+  <vscale x 64 x i8>,
+  <vscale x 64 x i8>,
+  <vscale x 64 x i8>,
+  <vscale x 64 x i1>,
+  i64);
+
+define <vscale x 64 x i8> @intrinsic_vrgather_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_vrgather_mask_vv_nxv64i8_nxv64i8_nxv64i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a3, zero, e8,m8,ta,mu
+; CHECK-NEXT:    vle8.v v8, (a1)
+; CHECK-NEXT:    vle8.v v24, (a0)
+; CHECK-NEXT:    vsetvli a0, a2, e8,m8,ta,mu
+; CHECK-NEXT:    vrgather.vv v16, v24, v8, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 64 x i8> @llvm.riscv.vrgather.mask.nxv64i8.nxv64i8(
+    <vscale x 64 x i8> %0,
+    <vscale x 64 x i8> %1,
+    <vscale x 64 x i8> %2,
+    <vscale x 64 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 64 x i8> %a
+}
+
+declare <vscale x 1 x i16> @llvm.riscv.vrgather.nxv1i16.nxv1i16(
+  <vscale x 1 x i16>,
+  <vscale x 1 x i16>,
+  i64);
+
+define <vscale x 1 x i16> @intrinsic_vrgather_vv_nxv1i16_nxv1i16_nxv1i16(<vscale x 1 x i16> %0, <vscale x 1 x i16> %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vv_nxv1i16_nxv1i16_nxv1i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e16,mf4,ta,mu
+; CHECK-NEXT:    vrgather.vv v25, v16, v17
+; CHECK-NEXT:    vmv1r.v v16, v25
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 1 x i16> @llvm.riscv.vrgather.nxv1i16.nxv1i16(
+    <vscale x 1 x i16> %0,
+    <vscale x 1 x i16> %1,
+    i64 %2)
+
+  ret <vscale x 1 x i16> %a
+}
+
+declare <vscale x 1 x i16> @llvm.riscv.vrgather.mask.nxv1i16.nxv1i16(
+  <vscale x 1 x i16>,
+  <vscale x 1 x i16>,
+  <vscale x 1 x i16>,
+  <vscale x 1 x i1>,
+  i64);
+
+define <vscale x 1 x i16> @intrinsic_vrgather_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_vrgather_mask_vv_nxv1i16_nxv1i16_nxv1i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e16,mf4,ta,mu
+; CHECK-NEXT:    vrgather.vv v16, v17, v18, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 1 x i16> @llvm.riscv.vrgather.mask.nxv1i16.nxv1i16(
+    <vscale x 1 x i16> %0,
+    <vscale x 1 x i16> %1,
+    <vscale x 1 x i16> %2,
+    <vscale x 1 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 1 x i16> %a
+}
+
+declare <vscale x 2 x i16> @llvm.riscv.vrgather.nxv2i16.nxv2i16(
+  <vscale x 2 x i16>,
+  <vscale x 2 x i16>,
+  i64);
+
+define <vscale x 2 x i16> @intrinsic_vrgather_vv_nxv2i16_nxv2i16_nxv2i16(<vscale x 2 x i16> %0, <vscale x 2 x i16> %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vv_nxv2i16_nxv2i16_nxv2i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e16,mf2,ta,mu
+; CHECK-NEXT:    vrgather.vv v25, v16, v17
+; CHECK-NEXT:    vmv1r.v v16, v25
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 2 x i16> @llvm.riscv.vrgather.nxv2i16.nxv2i16(
+    <vscale x 2 x i16> %0,
+    <vscale x 2 x i16> %1,
+    i64 %2)
+
+  ret <vscale x 2 x i16> %a
+}
+
+declare <vscale x 2 x i16> @llvm.riscv.vrgather.mask.nxv2i16.nxv2i16(
+  <vscale x 2 x i16>,
+  <vscale x 2 x i16>,
+  <vscale x 2 x i16>,
+  <vscale x 2 x i1>,
+  i64);
+
+define <vscale x 2 x i16> @intrinsic_vrgather_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_vrgather_mask_vv_nxv2i16_nxv2i16_nxv2i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e16,mf2,ta,mu
+; CHECK-NEXT:    vrgather.vv v16, v17, v18, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 2 x i16> @llvm.riscv.vrgather.mask.nxv2i16.nxv2i16(
+    <vscale x 2 x i16> %0,
+    <vscale x 2 x i16> %1,
+    <vscale x 2 x i16> %2,
+    <vscale x 2 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 2 x i16> %a
+}
+
+declare <vscale x 4 x i16> @llvm.riscv.vrgather.nxv4i16.nxv4i16(
+  <vscale x 4 x i16>,
+  <vscale x 4 x i16>,
+  i64);
+
+define <vscale x 4 x i16> @intrinsic_vrgather_vv_nxv4i16_nxv4i16_nxv4i16(<vscale x 4 x i16> %0, <vscale x 4 x i16> %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vv_nxv4i16_nxv4i16_nxv4i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e16,m1,ta,mu
+; CHECK-NEXT:    vrgather.vv v25, v16, v17
+; CHECK-NEXT:    vmv1r.v v16, v25
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 4 x i16> @llvm.riscv.vrgather.nxv4i16.nxv4i16(
+    <vscale x 4 x i16> %0,
+    <vscale x 4 x i16> %1,
+    i64 %2)
+
+  ret <vscale x 4 x i16> %a
+}
+
+declare <vscale x 4 x i16> @llvm.riscv.vrgather.mask.nxv4i16.nxv4i16(
+  <vscale x 4 x i16>,
+  <vscale x 4 x i16>,
+  <vscale x 4 x i16>,
+  <vscale x 4 x i1>,
+  i64);
+
+define <vscale x 4 x i16> @intrinsic_vrgather_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_vrgather_mask_vv_nxv4i16_nxv4i16_nxv4i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e16,m1,ta,mu
+; CHECK-NEXT:    vrgather.vv v16, v17, v18, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 4 x i16> @llvm.riscv.vrgather.mask.nxv4i16.nxv4i16(
+    <vscale x 4 x i16> %0,
+    <vscale x 4 x i16> %1,
+    <vscale x 4 x i16> %2,
+    <vscale x 4 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 4 x i16> %a
+}
+
+declare <vscale x 8 x i16> @llvm.riscv.vrgather.nxv8i16.nxv8i16(
+  <vscale x 8 x i16>,
+  <vscale x 8 x i16>,
+  i64);
+
+define <vscale x 8 x i16> @intrinsic_vrgather_vv_nxv8i16_nxv8i16_nxv8i16(<vscale x 8 x i16> %0, <vscale x 8 x i16> %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vv_nxv8i16_nxv8i16_nxv8i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e16,m2,ta,mu
+; CHECK-NEXT:    vrgather.vv v26, v16, v18
+; CHECK-NEXT:    vmv2r.v v16, v26
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 8 x i16> @llvm.riscv.vrgather.nxv8i16.nxv8i16(
+    <vscale x 8 x i16> %0,
+    <vscale x 8 x i16> %1,
+    i64 %2)
+
+  ret <vscale x 8 x i16> %a
+}
+
+declare <vscale x 8 x i16> @llvm.riscv.vrgather.mask.nxv8i16.nxv8i16(
+  <vscale x 8 x i16>,
+  <vscale x 8 x i16>,
+  <vscale x 8 x i16>,
+  <vscale x 8 x i1>,
+  i64);
+
+define <vscale x 8 x i16> @intrinsic_vrgather_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_vrgather_mask_vv_nxv8i16_nxv8i16_nxv8i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e16,m2,ta,mu
+; CHECK-NEXT:    vrgather.vv v16, v18, v20, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 8 x i16> @llvm.riscv.vrgather.mask.nxv8i16.nxv8i16(
+    <vscale x 8 x i16> %0,
+    <vscale x 8 x i16> %1,
+    <vscale x 8 x i16> %2,
+    <vscale x 8 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 8 x i16> %a
+}
+
+declare <vscale x 16 x i16> @llvm.riscv.vrgather.nxv16i16.nxv16i16(
+  <vscale x 16 x i16>,
+  <vscale x 16 x i16>,
+  i64);
+
+define <vscale x 16 x i16> @intrinsic_vrgather_vv_nxv16i16_nxv16i16_nxv16i16(<vscale x 16 x i16> %0, <vscale x 16 x i16> %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vv_nxv16i16_nxv16i16_nxv16i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e16,m4,ta,mu
+; CHECK-NEXT:    vrgather.vv v28, v16, v20
+; CHECK-NEXT:    vmv4r.v v16, v28
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 16 x i16> @llvm.riscv.vrgather.nxv16i16.nxv16i16(
+    <vscale x 16 x i16> %0,
+    <vscale x 16 x i16> %1,
+    i64 %2)
+
+  ret <vscale x 16 x i16> %a
+}
+
+declare <vscale x 16 x i16> @llvm.riscv.vrgather.mask.nxv16i16.nxv16i16(
+  <vscale x 16 x i16>,
+  <vscale x 16 x i16>,
+  <vscale x 16 x i16>,
+  <vscale x 16 x i1>,
+  i64);
+
+define <vscale x 16 x i16> @intrinsic_vrgather_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_vrgather_mask_vv_nxv16i16_nxv16i16_nxv16i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a2, zero, e16,m4,ta,mu
+; CHECK-NEXT:    vle16.v v28, (a0)
+; CHECK-NEXT:    vsetvli a0, a1, e16,m4,ta,mu
+; CHECK-NEXT:    vrgather.vv v16, v20, v28, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 16 x i16> @llvm.riscv.vrgather.mask.nxv16i16.nxv16i16(
+    <vscale x 16 x i16> %0,
+    <vscale x 16 x i16> %1,
+    <vscale x 16 x i16> %2,
+    <vscale x 16 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 16 x i16> %a
+}
+
+declare <vscale x 32 x i16> @llvm.riscv.vrgather.nxv32i16.nxv32i16(
+  <vscale x 32 x i16>,
+  <vscale x 32 x i16>,
+  i64);
+
+define <vscale x 32 x i16> @intrinsic_vrgather_vv_nxv32i16_nxv32i16_nxv32i16(<vscale x 32 x i16> %0, <vscale x 32 x i16> %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vv_nxv32i16_nxv32i16_nxv32i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a2, zero, e16,m8,ta,mu
+; CHECK-NEXT:    vle16.v v24, (a0)
+; CHECK-NEXT:    vsetvli a0, a1, e16,m8,ta,mu
+; CHECK-NEXT:    vrgather.vv v8, v16, v24
+; CHECK-NEXT:    vmv8r.v v16, v8
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 32 x i16> @llvm.riscv.vrgather.nxv32i16.nxv32i16(
+    <vscale x 32 x i16> %0,
+    <vscale x 32 x i16> %1,
+    i64 %2)
+
+  ret <vscale x 32 x i16> %a
+}
+
+declare <vscale x 32 x i16> @llvm.riscv.vrgather.mask.nxv32i16.nxv32i16(
+  <vscale x 32 x i16>,
+  <vscale x 32 x i16>,
+  <vscale x 32 x i16>,
+  <vscale x 32 x i1>,
+  i64);
+
+define <vscale x 32 x i16> @intrinsic_vrgather_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_vrgather_mask_vv_nxv32i16_nxv32i16_nxv32i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a3, zero, e16,m8,ta,mu
+; CHECK-NEXT:    vle16.v v8, (a1)
+; CHECK-NEXT:    vle16.v v24, (a0)
+; CHECK-NEXT:    vsetvli a0, a2, e16,m8,ta,mu
+; CHECK-NEXT:    vrgather.vv v16, v24, v8, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 32 x i16> @llvm.riscv.vrgather.mask.nxv32i16.nxv32i16(
+    <vscale x 32 x i16> %0,
+    <vscale x 32 x i16> %1,
+    <vscale x 32 x i16> %2,
+    <vscale x 32 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 32 x i16> %a
+}
+
+declare <vscale x 1 x i32> @llvm.riscv.vrgather.nxv1i32.nxv1i32(
+  <vscale x 1 x i32>,
+  <vscale x 1 x i32>,
+  i64);
+
+define <vscale x 1 x i32> @intrinsic_vrgather_vv_nxv1i32_nxv1i32_nxv1i32(<vscale x 1 x i32> %0, <vscale x 1 x i32> %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vv_nxv1i32_nxv1i32_nxv1i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e32,mf2,ta,mu
+; CHECK-NEXT:    vrgather.vv v25, v16, v17
+; CHECK-NEXT:    vmv1r.v v16, v25
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 1 x i32> @llvm.riscv.vrgather.nxv1i32.nxv1i32(
+    <vscale x 1 x i32> %0,
+    <vscale x 1 x i32> %1,
+    i64 %2)
+
+  ret <vscale x 1 x i32> %a
+}
+
+declare <vscale x 1 x i32> @llvm.riscv.vrgather.mask.nxv1i32.nxv1i32(
+  <vscale x 1 x i32>,
+  <vscale x 1 x i32>,
+  <vscale x 1 x i32>,
+  <vscale x 1 x i1>,
+  i64);
+
+define <vscale x 1 x i32> @intrinsic_vrgather_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_vrgather_mask_vv_nxv1i32_nxv1i32_nxv1i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e32,mf2,ta,mu
+; CHECK-NEXT:    vrgather.vv v16, v17, v18, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 1 x i32> @llvm.riscv.vrgather.mask.nxv1i32.nxv1i32(
+    <vscale x 1 x i32> %0,
+    <vscale x 1 x i32> %1,
+    <vscale x 1 x i32> %2,
+    <vscale x 1 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 1 x i32> %a
+}
+
+declare <vscale x 2 x i32> @llvm.riscv.vrgather.nxv2i32.nxv2i32(
+  <vscale x 2 x i32>,
+  <vscale x 2 x i32>,
+  i64);
+
+define <vscale x 2 x i32> @intrinsic_vrgather_vv_nxv2i32_nxv2i32_nxv2i32(<vscale x 2 x i32> %0, <vscale x 2 x i32> %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vv_nxv2i32_nxv2i32_nxv2i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e32,m1,ta,mu
+; CHECK-NEXT:    vrgather.vv v25, v16, v17
+; CHECK-NEXT:    vmv1r.v v16, v25
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 2 x i32> @llvm.riscv.vrgather.nxv2i32.nxv2i32(
+    <vscale x 2 x i32> %0,
+    <vscale x 2 x i32> %1,
+    i64 %2)
+
+  ret <vscale x 2 x i32> %a
+}
+
+declare <vscale x 2 x i32> @llvm.riscv.vrgather.mask.nxv2i32.nxv2i32(
+  <vscale x 2 x i32>,
+  <vscale x 2 x i32>,
+  <vscale x 2 x i32>,
+  <vscale x 2 x i1>,
+  i64);
+
+define <vscale x 2 x i32> @intrinsic_vrgather_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_vrgather_mask_vv_nxv2i32_nxv2i32_nxv2i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e32,m1,ta,mu
+; CHECK-NEXT:    vrgather.vv v16, v17, v18, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 2 x i32> @llvm.riscv.vrgather.mask.nxv2i32.nxv2i32(
+    <vscale x 2 x i32> %0,
+    <vscale x 2 x i32> %1,
+    <vscale x 2 x i32> %2,
+    <vscale x 2 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 2 x i32> %a
+}
+
+declare <vscale x 4 x i32> @llvm.riscv.vrgather.nxv4i32.nxv4i32(
+  <vscale x 4 x i32>,
+  <vscale x 4 x i32>,
+  i64);
+
+define <vscale x 4 x i32> @intrinsic_vrgather_vv_nxv4i32_nxv4i32_nxv4i32(<vscale x 4 x i32> %0, <vscale x 4 x i32> %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vv_nxv4i32_nxv4i32_nxv4i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e32,m2,ta,mu
+; CHECK-NEXT:    vrgather.vv v26, v16, v18
+; CHECK-NEXT:    vmv2r.v v16, v26
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 4 x i32> @llvm.riscv.vrgather.nxv4i32.nxv4i32(
+    <vscale x 4 x i32> %0,
+    <vscale x 4 x i32> %1,
+    i64 %2)
+
+  ret <vscale x 4 x i32> %a
+}
+
+declare <vscale x 4 x i32> @llvm.riscv.vrgather.mask.nxv4i32.nxv4i32(
+  <vscale x 4 x i32>,
+  <vscale x 4 x i32>,
+  <vscale x 4 x i32>,
+  <vscale x 4 x i1>,
+  i64);
+
+define <vscale x 4 x i32> @intrinsic_vrgather_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_vrgather_mask_vv_nxv4i32_nxv4i32_nxv4i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e32,m2,ta,mu
+; CHECK-NEXT:    vrgather.vv v16, v18, v20, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 4 x i32> @llvm.riscv.vrgather.mask.nxv4i32.nxv4i32(
+    <vscale x 4 x i32> %0,
+    <vscale x 4 x i32> %1,
+    <vscale x 4 x i32> %2,
+    <vscale x 4 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 4 x i32> %a
+}
+
+declare <vscale x 8 x i32> @llvm.riscv.vrgather.nxv8i32.nxv8i32(
+  <vscale x 8 x i32>,
+  <vscale x 8 x i32>,
+  i64);
+
+define <vscale x 8 x i32> @intrinsic_vrgather_vv_nxv8i32_nxv8i32_nxv8i32(<vscale x 8 x i32> %0, <vscale x 8 x i32> %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vv_nxv8i32_nxv8i32_nxv8i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e32,m4,ta,mu
+; CHECK-NEXT:    vrgather.vv v28, v16, v20
+; CHECK-NEXT:    vmv4r.v v16, v28
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 8 x i32> @llvm.riscv.vrgather.nxv8i32.nxv8i32(
+    <vscale x 8 x i32> %0,
+    <vscale x 8 x i32> %1,
+    i64 %2)
+
+  ret <vscale x 8 x i32> %a
+}
+
+declare <vscale x 8 x i32> @llvm.riscv.vrgather.mask.nxv8i32.nxv8i32(
+  <vscale x 8 x i32>,
+  <vscale x 8 x i32>,
+  <vscale x 8 x i32>,
+  <vscale x 8 x i1>,
+  i64);
+
+define <vscale x 8 x i32> @intrinsic_vrgather_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_vrgather_mask_vv_nxv8i32_nxv8i32_nxv8i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a2, zero, e32,m4,ta,mu
+; CHECK-NEXT:    vle32.v v28, (a0)
+; CHECK-NEXT:    vsetvli a0, a1, e32,m4,ta,mu
+; CHECK-NEXT:    vrgather.vv v16, v20, v28, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 8 x i32> @llvm.riscv.vrgather.mask.nxv8i32.nxv8i32(
+    <vscale x 8 x i32> %0,
+    <vscale x 8 x i32> %1,
+    <vscale x 8 x i32> %2,
+    <vscale x 8 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 8 x i32> %a
+}
+
+declare <vscale x 16 x i32> @llvm.riscv.vrgather.nxv16i32.nxv16i32(
+  <vscale x 16 x i32>,
+  <vscale x 16 x i32>,
+  i64);
+
+define <vscale x 16 x i32> @intrinsic_vrgather_vv_nxv16i32_nxv16i32_nxv16i32(<vscale x 16 x i32> %0, <vscale x 16 x i32> %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vv_nxv16i32_nxv16i32_nxv16i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a2, zero, e32,m8,ta,mu
+; CHECK-NEXT:    vle32.v v24, (a0)
+; CHECK-NEXT:    vsetvli a0, a1, e32,m8,ta,mu
+; CHECK-NEXT:    vrgather.vv v8, v16, v24
+; CHECK-NEXT:    vmv8r.v v16, v8
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 16 x i32> @llvm.riscv.vrgather.nxv16i32.nxv16i32(
+    <vscale x 16 x i32> %0,
+    <vscale x 16 x i32> %1,
+    i64 %2)
+
+  ret <vscale x 16 x i32> %a
+}
+
+declare <vscale x 16 x i32> @llvm.riscv.vrgather.mask.nxv16i32.nxv16i32(
+  <vscale x 16 x i32>,
+  <vscale x 16 x i32>,
+  <vscale x 16 x i32>,
+  <vscale x 16 x i1>,
+  i64);
+
+define <vscale x 16 x i32> @intrinsic_vrgather_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_vrgather_mask_vv_nxv16i32_nxv16i32_nxv16i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a3, zero, e32,m8,ta,mu
+; CHECK-NEXT:    vle32.v v8, (a1)
+; CHECK-NEXT:    vle32.v v24, (a0)
+; CHECK-NEXT:    vsetvli a0, a2, e32,m8,ta,mu
+; CHECK-NEXT:    vrgather.vv v16, v24, v8, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 16 x i32> @llvm.riscv.vrgather.mask.nxv16i32.nxv16i32(
+    <vscale x 16 x i32> %0,
+    <vscale x 16 x i32> %1,
+    <vscale x 16 x i32> %2,
+    <vscale x 16 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 16 x i32> %a
+}
+
+declare <vscale x 1 x i64> @llvm.riscv.vrgather.nxv1i64.nxv1i64(
+  <vscale x 1 x i64>,
+  <vscale x 1 x i64>,
+  i64);
+
+define <vscale x 1 x i64> @intrinsic_vrgather_vv_nxv1i64_nxv1i64_nxv1i64(<vscale x 1 x i64> %0, <vscale x 1 x i64> %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vv_nxv1i64_nxv1i64_nxv1i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e64,m1,ta,mu
+; CHECK-NEXT:    vrgather.vv v25, v16, v17
+; CHECK-NEXT:    vmv1r.v v16, v25
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 1 x i64> @llvm.riscv.vrgather.nxv1i64.nxv1i64(
+    <vscale x 1 x i64> %0,
+    <vscale x 1 x i64> %1,
+    i64 %2)
+
+  ret <vscale x 1 x i64> %a
+}
+
+declare <vscale x 1 x i64> @llvm.riscv.vrgather.mask.nxv1i64.nxv1i64(
+  <vscale x 1 x i64>,
+  <vscale x 1 x i64>,
+  <vscale x 1 x i64>,
+  <vscale x 1 x i1>,
+  i64);
+
+define <vscale x 1 x i64> @intrinsic_vrgather_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_vrgather_mask_vv_nxv1i64_nxv1i64_nxv1i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e64,m1,ta,mu
+; CHECK-NEXT:    vrgather.vv v16, v17, v18, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 1 x i64> @llvm.riscv.vrgather.mask.nxv1i64.nxv1i64(
+    <vscale x 1 x i64> %0,
+    <vscale x 1 x i64> %1,
+    <vscale x 1 x i64> %2,
+    <vscale x 1 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 1 x i64> %a
+}
+
+declare <vscale x 2 x i64> @llvm.riscv.vrgather.nxv2i64.nxv2i64(
+  <vscale x 2 x i64>,
+  <vscale x 2 x i64>,
+  i64);
+
+define <vscale x 2 x i64> @intrinsic_vrgather_vv_nxv2i64_nxv2i64_nxv2i64(<vscale x 2 x i64> %0, <vscale x 2 x i64> %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vv_nxv2i64_nxv2i64_nxv2i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e64,m2,ta,mu
+; CHECK-NEXT:    vrgather.vv v26, v16, v18
+; CHECK-NEXT:    vmv2r.v v16, v26
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 2 x i64> @llvm.riscv.vrgather.nxv2i64.nxv2i64(
+    <vscale x 2 x i64> %0,
+    <vscale x 2 x i64> %1,
+    i64 %2)
+
+  ret <vscale x 2 x i64> %a
+}
+
+declare <vscale x 2 x i64> @llvm.riscv.vrgather.mask.nxv2i64.nxv2i64(
+  <vscale x 2 x i64>,
+  <vscale x 2 x i64>,
+  <vscale x 2 x i64>,
+  <vscale x 2 x i1>,
+  i64);
+
+define <vscale x 2 x i64> @intrinsic_vrgather_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_vrgather_mask_vv_nxv2i64_nxv2i64_nxv2i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e64,m2,ta,mu
+; CHECK-NEXT:    vrgather.vv v16, v18, v20, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 2 x i64> @llvm.riscv.vrgather.mask.nxv2i64.nxv2i64(
+    <vscale x 2 x i64> %0,
+    <vscale x 2 x i64> %1,
+    <vscale x 2 x i64> %2,
+    <vscale x 2 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 2 x i64> %a
+}
+
+declare <vscale x 4 x i64> @llvm.riscv.vrgather.nxv4i64.nxv4i64(
+  <vscale x 4 x i64>,
+  <vscale x 4 x i64>,
+  i64);
+
+define <vscale x 4 x i64> @intrinsic_vrgather_vv_nxv4i64_nxv4i64_nxv4i64(<vscale x 4 x i64> %0, <vscale x 4 x i64> %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vv_nxv4i64_nxv4i64_nxv4i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e64,m4,ta,mu
+; CHECK-NEXT:    vrgather.vv v28, v16, v20
+; CHECK-NEXT:    vmv4r.v v16, v28
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 4 x i64> @llvm.riscv.vrgather.nxv4i64.nxv4i64(
+    <vscale x 4 x i64> %0,
+    <vscale x 4 x i64> %1,
+    i64 %2)
+
+  ret <vscale x 4 x i64> %a
+}
+
+declare <vscale x 4 x i64> @llvm.riscv.vrgather.mask.nxv4i64.nxv4i64(
+  <vscale x 4 x i64>,
+  <vscale x 4 x i64>,
+  <vscale x 4 x i64>,
+  <vscale x 4 x i1>,
+  i64);
+
+define <vscale x 4 x i64> @intrinsic_vrgather_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_vrgather_mask_vv_nxv4i64_nxv4i64_nxv4i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a2, zero, e64,m4,ta,mu
+; CHECK-NEXT:    vle64.v v28, (a0)
+; CHECK-NEXT:    vsetvli a0, a1, e64,m4,ta,mu
+; CHECK-NEXT:    vrgather.vv v16, v20, v28, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 4 x i64> @llvm.riscv.vrgather.mask.nxv4i64.nxv4i64(
+    <vscale x 4 x i64> %0,
+    <vscale x 4 x i64> %1,
+    <vscale x 4 x i64> %2,
+    <vscale x 4 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 4 x i64> %a
+}
+
+declare <vscale x 8 x i64> @llvm.riscv.vrgather.nxv8i64.nxv8i64(
+  <vscale x 8 x i64>,
+  <vscale x 8 x i64>,
+  i64);
+
+define <vscale x 8 x i64> @intrinsic_vrgather_vv_nxv8i64_nxv8i64_nxv8i64(<vscale x 8 x i64> %0, <vscale x 8 x i64> %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vv_nxv8i64_nxv8i64_nxv8i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a2, zero, e64,m8,ta,mu
+; CHECK-NEXT:    vle64.v v24, (a0)
+; CHECK-NEXT:    vsetvli a0, a1, e64,m8,ta,mu
+; CHECK-NEXT:    vrgather.vv v8, v16, v24
+; CHECK-NEXT:    vmv8r.v v16, v8
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 8 x i64> @llvm.riscv.vrgather.nxv8i64.nxv8i64(
+    <vscale x 8 x i64> %0,
+    <vscale x 8 x i64> %1,
+    i64 %2)
+
+  ret <vscale x 8 x i64> %a
+}
+
+declare <vscale x 8 x i64> @llvm.riscv.vrgather.mask.nxv8i64.nxv8i64(
+  <vscale x 8 x i64>,
+  <vscale x 8 x i64>,
+  <vscale x 8 x i64>,
+  <vscale x 8 x i1>,
+  i64);
+
+define <vscale x 8 x i64> @intrinsic_vrgather_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_vrgather_mask_vv_nxv8i64_nxv8i64_nxv8i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a3, zero, e64,m8,ta,mu
+; CHECK-NEXT:    vle64.v v8, (a1)
+; CHECK-NEXT:    vle64.v v24, (a0)
+; CHECK-NEXT:    vsetvli a0, a2, e64,m8,ta,mu
+; CHECK-NEXT:    vrgather.vv v16, v24, v8, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 8 x i64> @llvm.riscv.vrgather.mask.nxv8i64.nxv8i64(
+    <vscale x 8 x i64> %0,
+    <vscale x 8 x i64> %1,
+    <vscale x 8 x i64> %2,
+    <vscale x 8 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 8 x i64> %a
+}
+
+declare <vscale x 1 x half> @llvm.riscv.vrgather.nxv1f16.nxv1i16(
+  <vscale x 1 x half>,
+  <vscale x 1 x i16>,
+  i64);
+
+define <vscale x 1 x half> @intrinsic_vrgather_vv_nxv1f16_nxv1f16_nxv1i16(<vscale x 1 x half> %0, <vscale x 1 x i16> %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vv_nxv1f16_nxv1f16_nxv1i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e16,mf4,ta,mu
+; CHECK-NEXT:    vrgather.vv v25, v16, v17
+; CHECK-NEXT:    vmv1r.v v16, v25
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 1 x half> @llvm.riscv.vrgather.nxv1f16.nxv1i16(
+    <vscale x 1 x half> %0,
+    <vscale x 1 x i16> %1,
+    i64 %2)
+
+  ret <vscale x 1 x half> %a
+}
+
+declare <vscale x 1 x half> @llvm.riscv.vrgather.mask.nxv1f16.nxv1i16(
+  <vscale x 1 x half>,
+  <vscale x 1 x half>,
+  <vscale x 1 x i16>,
+  <vscale x 1 x i1>,
+  i64);
+
+define <vscale x 1 x half> @intrinsic_vrgather_mask_vv_nxv1f16_nxv1f16_nxv1i16(<vscale x 1 x half> %0, <vscale x 1 x half> %1, <vscale x 1 x i16> %2, <vscale x 1 x i1> %3, i64 %4) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vv_nxv1f16_nxv1f16_nxv1i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e16,mf4,ta,mu
+; CHECK-NEXT:    vrgather.vv v16, v17, v18, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 1 x half> @llvm.riscv.vrgather.mask.nxv1f16.nxv1i16(
+    <vscale x 1 x half> %0,
+    <vscale x 1 x half> %1,
+    <vscale x 1 x i16> %2,
+    <vscale x 1 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 1 x half> %a
+}
+
+declare <vscale x 2 x half> @llvm.riscv.vrgather.nxv2f16.nxv2i16(
+  <vscale x 2 x half>,
+  <vscale x 2 x i16>,
+  i64);
+
+define <vscale x 2 x half> @intrinsic_vrgather_vv_nxv2f16_nxv2f16_nxv2i16(<vscale x 2 x half> %0, <vscale x 2 x i16> %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vv_nxv2f16_nxv2f16_nxv2i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e16,mf2,ta,mu
+; CHECK-NEXT:    vrgather.vv v25, v16, v17
+; CHECK-NEXT:    vmv1r.v v16, v25
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 2 x half> @llvm.riscv.vrgather.nxv2f16.nxv2i16(
+    <vscale x 2 x half> %0,
+    <vscale x 2 x i16> %1,
+    i64 %2)
+
+  ret <vscale x 2 x half> %a
+}
+
+declare <vscale x 2 x half> @llvm.riscv.vrgather.mask.nxv2f16.nxv2i16(
+  <vscale x 2 x half>,
+  <vscale x 2 x half>,
+  <vscale x 2 x i16>,
+  <vscale x 2 x i1>,
+  i64);
+
+define <vscale x 2 x half> @intrinsic_vrgather_mask_vv_nxv2f16_nxv2f16_nxv2i16(<vscale x 2 x half> %0, <vscale x 2 x half> %1, <vscale x 2 x i16> %2, <vscale x 2 x i1> %3, i64 %4) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vv_nxv2f16_nxv2f16_nxv2i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e16,mf2,ta,mu
+; CHECK-NEXT:    vrgather.vv v16, v17, v18, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 2 x half> @llvm.riscv.vrgather.mask.nxv2f16.nxv2i16(
+    <vscale x 2 x half> %0,
+    <vscale x 2 x half> %1,
+    <vscale x 2 x i16> %2,
+    <vscale x 2 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 2 x half> %a
+}
+
+declare <vscale x 4 x half> @llvm.riscv.vrgather.nxv4f16.nxv4i16(
+  <vscale x 4 x half>,
+  <vscale x 4 x i16>,
+  i64);
+
+define <vscale x 4 x half> @intrinsic_vrgather_vv_nxv4f16_nxv4f16_nxv4i16(<vscale x 4 x half> %0, <vscale x 4 x i16> %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vv_nxv4f16_nxv4f16_nxv4i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e16,m1,ta,mu
+; CHECK-NEXT:    vrgather.vv v25, v16, v17
+; CHECK-NEXT:    vmv1r.v v16, v25
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 4 x half> @llvm.riscv.vrgather.nxv4f16.nxv4i16(
+    <vscale x 4 x half> %0,
+    <vscale x 4 x i16> %1,
+    i64 %2)
+
+  ret <vscale x 4 x half> %a
+}
+
+declare <vscale x 4 x half> @llvm.riscv.vrgather.mask.nxv4f16.nxv4i16(
+  <vscale x 4 x half>,
+  <vscale x 4 x half>,
+  <vscale x 4 x i16>,
+  <vscale x 4 x i1>,
+  i64);
+
+define <vscale x 4 x half> @intrinsic_vrgather_mask_vv_nxv4f16_nxv4f16_nxv4i16(<vscale x 4 x half> %0, <vscale x 4 x half> %1, <vscale x 4 x i16> %2, <vscale x 4 x i1> %3, i64 %4) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vv_nxv4f16_nxv4f16_nxv4i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e16,m1,ta,mu
+; CHECK-NEXT:    vrgather.vv v16, v17, v18, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 4 x half> @llvm.riscv.vrgather.mask.nxv4f16.nxv4i16(
+    <vscale x 4 x half> %0,
+    <vscale x 4 x half> %1,
+    <vscale x 4 x i16> %2,
+    <vscale x 4 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 4 x half> %a
+}
+
+declare <vscale x 8 x half> @llvm.riscv.vrgather.nxv8f16.nxv8i16(
+  <vscale x 8 x half>,
+  <vscale x 8 x i16>,
+  i64);
+
+define <vscale x 8 x half> @intrinsic_vrgather_vv_nxv8f16_nxv8f16_nxv8i16(<vscale x 8 x half> %0, <vscale x 8 x i16> %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vv_nxv8f16_nxv8f16_nxv8i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e16,m2,ta,mu
+; CHECK-NEXT:    vrgather.vv v26, v16, v18
+; CHECK-NEXT:    vmv2r.v v16, v26
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 8 x half> @llvm.riscv.vrgather.nxv8f16.nxv8i16(
+    <vscale x 8 x half> %0,
+    <vscale x 8 x i16> %1,
+    i64 %2)
+
+  ret <vscale x 8 x half> %a
+}
+
+declare <vscale x 8 x half> @llvm.riscv.vrgather.mask.nxv8f16.nxv8i16(
+  <vscale x 8 x half>,
+  <vscale x 8 x half>,
+  <vscale x 8 x i16>,
+  <vscale x 8 x i1>,
+  i64);
+
+define <vscale x 8 x half> @intrinsic_vrgather_mask_vv_nxv8f16_nxv8f16_nxv8i16(<vscale x 8 x half> %0, <vscale x 8 x half> %1, <vscale x 8 x i16> %2, <vscale x 8 x i1> %3, i64 %4) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vv_nxv8f16_nxv8f16_nxv8i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e16,m2,ta,mu
+; CHECK-NEXT:    vrgather.vv v16, v18, v20, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 8 x half> @llvm.riscv.vrgather.mask.nxv8f16.nxv8i16(
+    <vscale x 8 x half> %0,
+    <vscale x 8 x half> %1,
+    <vscale x 8 x i16> %2,
+    <vscale x 8 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 8 x half> %a
+}
+
+declare <vscale x 16 x half> @llvm.riscv.vrgather.nxv16f16.nxv16i16(
+  <vscale x 16 x half>,
+  <vscale x 16 x i16>,
+  i64);
+
+define <vscale x 16 x half> @intrinsic_vrgather_vv_nxv16f16_nxv16f16_nxv16i16(<vscale x 16 x half> %0, <vscale x 16 x i16> %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vv_nxv16f16_nxv16f16_nxv16i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e16,m4,ta,mu
+; CHECK-NEXT:    vrgather.vv v28, v16, v20
+; CHECK-NEXT:    vmv4r.v v16, v28
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 16 x half> @llvm.riscv.vrgather.nxv16f16.nxv16i16(
+    <vscale x 16 x half> %0,
+    <vscale x 16 x i16> %1,
+    i64 %2)
+
+  ret <vscale x 16 x half> %a
+}
+
+declare <vscale x 16 x half> @llvm.riscv.vrgather.mask.nxv16f16.nxv16i16(
+  <vscale x 16 x half>,
+  <vscale x 16 x half>,
+  <vscale x 16 x i16>,
+  <vscale x 16 x i1>,
+  i64);
+
+define <vscale x 16 x half> @intrinsic_vrgather_mask_vv_nxv16f16_nxv16f16_nxv16i16(<vscale x 16 x half> %0, <vscale x 16 x half> %1, <vscale x 16 x i16> %2, <vscale x 16 x i1> %3, i64 %4) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vv_nxv16f16_nxv16f16_nxv16i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a2, zero, e16,m4,ta,mu
+; CHECK-NEXT:    vle16.v v28, (a0)
+; CHECK-NEXT:    vsetvli a0, a1, e16,m4,ta,mu
+; CHECK-NEXT:    vrgather.vv v16, v20, v28, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 16 x half> @llvm.riscv.vrgather.mask.nxv16f16.nxv16i16(
+    <vscale x 16 x half> %0,
+    <vscale x 16 x half> %1,
+    <vscale x 16 x i16> %2,
+    <vscale x 16 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 16 x half> %a
+}
+
+declare <vscale x 32 x half> @llvm.riscv.vrgather.nxv32f16.nxv32i16(
+  <vscale x 32 x half>,
+  <vscale x 32 x i16>,
+  i64);
+
+define <vscale x 32 x half> @intrinsic_vrgather_vv_nxv32f16_nxv32f16_nxv32i16(<vscale x 32 x half> %0, <vscale x 32 x i16> %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vv_nxv32f16_nxv32f16_nxv32i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a2, zero, e16,m8,ta,mu
+; CHECK-NEXT:    vle16.v v24, (a0)
+; CHECK-NEXT:    vsetvli a0, a1, e16,m8,ta,mu
+; CHECK-NEXT:    vrgather.vv v8, v16, v24
+; CHECK-NEXT:    vmv8r.v v16, v8
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 32 x half> @llvm.riscv.vrgather.nxv32f16.nxv32i16(
+    <vscale x 32 x half> %0,
+    <vscale x 32 x i16> %1,
+    i64 %2)
+
+  ret <vscale x 32 x half> %a
+}
+
+declare <vscale x 32 x half> @llvm.riscv.vrgather.mask.nxv32f16.nxv32i16(
+  <vscale x 32 x half>,
+  <vscale x 32 x half>,
+  <vscale x 32 x i16>,
+  <vscale x 32 x i1>,
+  i64);
+
+define <vscale x 32 x half> @intrinsic_vrgather_mask_vv_nxv32f16_nxv32f16_nxv32i16(<vscale x 32 x half> %0, <vscale x 32 x half> %1, <vscale x 32 x i16> %2, <vscale x 32 x i1> %3, i64 %4) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vv_nxv32f16_nxv32f16_nxv32i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a3, zero, e16,m8,ta,mu
+; CHECK-NEXT:    vle16.v v8, (a1)
+; CHECK-NEXT:    vle16.v v24, (a0)
+; CHECK-NEXT:    vsetvli a0, a2, e16,m8,ta,mu
+; CHECK-NEXT:    vrgather.vv v16, v24, v8, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 32 x half> @llvm.riscv.vrgather.mask.nxv32f16.nxv32i16(
+    <vscale x 32 x half> %0,
+    <vscale x 32 x half> %1,
+    <vscale x 32 x i16> %2,
+    <vscale x 32 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 32 x half> %a
+}
+
+declare <vscale x 1 x float> @llvm.riscv.vrgather.nxv1f32.nxv1i32(
+  <vscale x 1 x float>,
+  <vscale x 1 x i32>,
+  i64);
+
+define <vscale x 1 x float> @intrinsic_vrgather_vv_nxv1f32_nxv1f32_nxv1i32(<vscale x 1 x float> %0, <vscale x 1 x i32> %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vv_nxv1f32_nxv1f32_nxv1i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e32,mf2,ta,mu
+; CHECK-NEXT:    vrgather.vv v25, v16, v17
+; CHECK-NEXT:    vmv1r.v v16, v25
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 1 x float> @llvm.riscv.vrgather.nxv1f32.nxv1i32(
+    <vscale x 1 x float> %0,
+    <vscale x 1 x i32> %1,
+    i64 %2)
+
+  ret <vscale x 1 x float> %a
+}
+
+declare <vscale x 1 x float> @llvm.riscv.vrgather.mask.nxv1f32.nxv1i32(
+  <vscale x 1 x float>,
+  <vscale x 1 x float>,
+  <vscale x 1 x i32>,
+  <vscale x 1 x i1>,
+  i64);
+
+define <vscale x 1 x float> @intrinsic_vrgather_mask_vv_nxv1f32_nxv1f32_nxv1i32(<vscale x 1 x float> %0, <vscale x 1 x float> %1, <vscale x 1 x i32> %2, <vscale x 1 x i1> %3, i64 %4) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vv_nxv1f32_nxv1f32_nxv1i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e32,mf2,ta,mu
+; CHECK-NEXT:    vrgather.vv v16, v17, v18, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 1 x float> @llvm.riscv.vrgather.mask.nxv1f32.nxv1i32(
+    <vscale x 1 x float> %0,
+    <vscale x 1 x float> %1,
+    <vscale x 1 x i32> %2,
+    <vscale x 1 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 1 x float> %a
+}
+
+declare <vscale x 2 x float> @llvm.riscv.vrgather.nxv2f32.nxv2i32(
+  <vscale x 2 x float>,
+  <vscale x 2 x i32>,
+  i64);
+
+define <vscale x 2 x float> @intrinsic_vrgather_vv_nxv2f32_nxv2f32_nxv2i32(<vscale x 2 x float> %0, <vscale x 2 x i32> %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vv_nxv2f32_nxv2f32_nxv2i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e32,m1,ta,mu
+; CHECK-NEXT:    vrgather.vv v25, v16, v17
+; CHECK-NEXT:    vmv1r.v v16, v25
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 2 x float> @llvm.riscv.vrgather.nxv2f32.nxv2i32(
+    <vscale x 2 x float> %0,
+    <vscale x 2 x i32> %1,
+    i64 %2)
+
+  ret <vscale x 2 x float> %a
+}
+
+declare <vscale x 2 x float> @llvm.riscv.vrgather.mask.nxv2f32.nxv2i32(
+  <vscale x 2 x float>,
+  <vscale x 2 x float>,
+  <vscale x 2 x i32>,
+  <vscale x 2 x i1>,
+  i64);
+
+define <vscale x 2 x float> @intrinsic_vrgather_mask_vv_nxv2f32_nxv2f32_nxv2i32(<vscale x 2 x float> %0, <vscale x 2 x float> %1, <vscale x 2 x i32> %2, <vscale x 2 x i1> %3, i64 %4) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vv_nxv2f32_nxv2f32_nxv2i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e32,m1,ta,mu
+; CHECK-NEXT:    vrgather.vv v16, v17, v18, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 2 x float> @llvm.riscv.vrgather.mask.nxv2f32.nxv2i32(
+    <vscale x 2 x float> %0,
+    <vscale x 2 x float> %1,
+    <vscale x 2 x i32> %2,
+    <vscale x 2 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 2 x float> %a
+}
+
+declare <vscale x 4 x float> @llvm.riscv.vrgather.nxv4f32.nxv4i32(
+  <vscale x 4 x float>,
+  <vscale x 4 x i32>,
+  i64);
+
+define <vscale x 4 x float> @intrinsic_vrgather_vv_nxv4f32_nxv4f32_nxv4i32(<vscale x 4 x float> %0, <vscale x 4 x i32> %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vv_nxv4f32_nxv4f32_nxv4i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e32,m2,ta,mu
+; CHECK-NEXT:    vrgather.vv v26, v16, v18
+; CHECK-NEXT:    vmv2r.v v16, v26
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 4 x float> @llvm.riscv.vrgather.nxv4f32.nxv4i32(
+    <vscale x 4 x float> %0,
+    <vscale x 4 x i32> %1,
+    i64 %2)
+
+  ret <vscale x 4 x float> %a
+}
+
+declare <vscale x 4 x float> @llvm.riscv.vrgather.mask.nxv4f32.nxv4i32(
+  <vscale x 4 x float>,
+  <vscale x 4 x float>,
+  <vscale x 4 x i32>,
+  <vscale x 4 x i1>,
+  i64);
+
+define <vscale x 4 x float> @intrinsic_vrgather_mask_vv_nxv4f32_nxv4f32_nxv4i32(<vscale x 4 x float> %0, <vscale x 4 x float> %1, <vscale x 4 x i32> %2, <vscale x 4 x i1> %3, i64 %4) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vv_nxv4f32_nxv4f32_nxv4i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e32,m2,ta,mu
+; CHECK-NEXT:    vrgather.vv v16, v18, v20, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 4 x float> @llvm.riscv.vrgather.mask.nxv4f32.nxv4i32(
+    <vscale x 4 x float> %0,
+    <vscale x 4 x float> %1,
+    <vscale x 4 x i32> %2,
+    <vscale x 4 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 4 x float> %a
+}
+
+declare <vscale x 8 x float> @llvm.riscv.vrgather.nxv8f32.nxv8i32(
+  <vscale x 8 x float>,
+  <vscale x 8 x i32>,
+  i64);
+
+define <vscale x 8 x float> @intrinsic_vrgather_vv_nxv8f32_nxv8f32_nxv8i32(<vscale x 8 x float> %0, <vscale x 8 x i32> %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vv_nxv8f32_nxv8f32_nxv8i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e32,m4,ta,mu
+; CHECK-NEXT:    vrgather.vv v28, v16, v20
+; CHECK-NEXT:    vmv4r.v v16, v28
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 8 x float> @llvm.riscv.vrgather.nxv8f32.nxv8i32(
+    <vscale x 8 x float> %0,
+    <vscale x 8 x i32> %1,
+    i64 %2)
+
+  ret <vscale x 8 x float> %a
+}
+
+declare <vscale x 8 x float> @llvm.riscv.vrgather.mask.nxv8f32.nxv8i32(
+  <vscale x 8 x float>,
+  <vscale x 8 x float>,
+  <vscale x 8 x i32>,
+  <vscale x 8 x i1>,
+  i64);
+
+define <vscale x 8 x float> @intrinsic_vrgather_mask_vv_nxv8f32_nxv8f32_nxv8i32(<vscale x 8 x float> %0, <vscale x 8 x float> %1, <vscale x 8 x i32> %2, <vscale x 8 x i1> %3, i64 %4) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vv_nxv8f32_nxv8f32_nxv8i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a2, zero, e32,m4,ta,mu
+; CHECK-NEXT:    vle32.v v28, (a0)
+; CHECK-NEXT:    vsetvli a0, a1, e32,m4,ta,mu
+; CHECK-NEXT:    vrgather.vv v16, v20, v28, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 8 x float> @llvm.riscv.vrgather.mask.nxv8f32.nxv8i32(
+    <vscale x 8 x float> %0,
+    <vscale x 8 x float> %1,
+    <vscale x 8 x i32> %2,
+    <vscale x 8 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 8 x float> %a
+}
+
+declare <vscale x 16 x float> @llvm.riscv.vrgather.nxv16f32.nxv16i32(
+  <vscale x 16 x float>,
+  <vscale x 16 x i32>,
+  i64);
+
+define <vscale x 16 x float> @intrinsic_vrgather_vv_nxv16f32_nxv16f32_nxv16i32(<vscale x 16 x float> %0, <vscale x 16 x i32> %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vv_nxv16f32_nxv16f32_nxv16i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a2, zero, e32,m8,ta,mu
+; CHECK-NEXT:    vle32.v v24, (a0)
+; CHECK-NEXT:    vsetvli a0, a1, e32,m8,ta,mu
+; CHECK-NEXT:    vrgather.vv v8, v16, v24
+; CHECK-NEXT:    vmv8r.v v16, v8
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 16 x float> @llvm.riscv.vrgather.nxv16f32.nxv16i32(
+    <vscale x 16 x float> %0,
+    <vscale x 16 x i32> %1,
+    i64 %2)
+
+  ret <vscale x 16 x float> %a
+}
+
+declare <vscale x 16 x float> @llvm.riscv.vrgather.mask.nxv16f32.nxv16i32(
+  <vscale x 16 x float>,
+  <vscale x 16 x float>,
+  <vscale x 16 x i32>,
+  <vscale x 16 x i1>,
+  i64);
+
+define <vscale x 16 x float> @intrinsic_vrgather_mask_vv_nxv16f32_nxv16f32_nxv16i32(<vscale x 16 x float> %0, <vscale x 16 x float> %1, <vscale x 16 x i32> %2, <vscale x 16 x i1> %3, i64 %4) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vv_nxv16f32_nxv16f32_nxv16i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a3, zero, e32,m8,ta,mu
+; CHECK-NEXT:    vle32.v v8, (a1)
+; CHECK-NEXT:    vle32.v v24, (a0)
+; CHECK-NEXT:    vsetvli a0, a2, e32,m8,ta,mu
+; CHECK-NEXT:    vrgather.vv v16, v24, v8, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 16 x float> @llvm.riscv.vrgather.mask.nxv16f32.nxv16i32(
+    <vscale x 16 x float> %0,
+    <vscale x 16 x float> %1,
+    <vscale x 16 x i32> %2,
+    <vscale x 16 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 16 x float> %a
+}
+
+declare <vscale x 1 x double> @llvm.riscv.vrgather.nxv1f64.nxv1i64(
+  <vscale x 1 x double>,
+  <vscale x 1 x i64>,
+  i64);
+
+define <vscale x 1 x double> @intrinsic_vrgather_vv_nxv1f64_nxv1f64_nxv1i64(<vscale x 1 x double> %0, <vscale x 1 x i64> %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vv_nxv1f64_nxv1f64_nxv1i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e64,m1,ta,mu
+; CHECK-NEXT:    vrgather.vv v25, v16, v17
+; CHECK-NEXT:    vmv1r.v v16, v25
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 1 x double> @llvm.riscv.vrgather.nxv1f64.nxv1i64(
+    <vscale x 1 x double> %0,
+    <vscale x 1 x i64> %1,
+    i64 %2)
+
+  ret <vscale x 1 x double> %a
+}
+
+declare <vscale x 1 x double> @llvm.riscv.vrgather.mask.nxv1f64.nxv1i64(
+  <vscale x 1 x double>,
+  <vscale x 1 x double>,
+  <vscale x 1 x i64>,
+  <vscale x 1 x i1>,
+  i64);
+
+define <vscale x 1 x double> @intrinsic_vrgather_mask_vv_nxv1f64_nxv1f64_nxv1i64(<vscale x 1 x double> %0, <vscale x 1 x double> %1, <vscale x 1 x i64> %2, <vscale x 1 x i1> %3, i64 %4) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vv_nxv1f64_nxv1f64_nxv1i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e64,m1,ta,mu
+; CHECK-NEXT:    vrgather.vv v16, v17, v18, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 1 x double> @llvm.riscv.vrgather.mask.nxv1f64.nxv1i64(
+    <vscale x 1 x double> %0,
+    <vscale x 1 x double> %1,
+    <vscale x 1 x i64> %2,
+    <vscale x 1 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 1 x double> %a
+}
+
+declare <vscale x 2 x double> @llvm.riscv.vrgather.nxv2f64.nxv2i64(
+  <vscale x 2 x double>,
+  <vscale x 2 x i64>,
+  i64);
+
+define <vscale x 2 x double> @intrinsic_vrgather_vv_nxv2f64_nxv2f64_nxv2i64(<vscale x 2 x double> %0, <vscale x 2 x i64> %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vv_nxv2f64_nxv2f64_nxv2i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e64,m2,ta,mu
+; CHECK-NEXT:    vrgather.vv v26, v16, v18
+; CHECK-NEXT:    vmv2r.v v16, v26
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 2 x double> @llvm.riscv.vrgather.nxv2f64.nxv2i64(
+    <vscale x 2 x double> %0,
+    <vscale x 2 x i64> %1,
+    i64 %2)
+
+  ret <vscale x 2 x double> %a
+}
+
+declare <vscale x 2 x double> @llvm.riscv.vrgather.mask.nxv2f64.nxv2i64(
+  <vscale x 2 x double>,
+  <vscale x 2 x double>,
+  <vscale x 2 x i64>,
+  <vscale x 2 x i1>,
+  i64);
+
+define <vscale x 2 x double> @intrinsic_vrgather_mask_vv_nxv2f64_nxv2f64_nxv2i64(<vscale x 2 x double> %0, <vscale x 2 x double> %1, <vscale x 2 x i64> %2, <vscale x 2 x i1> %3, i64 %4) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vv_nxv2f64_nxv2f64_nxv2i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e64,m2,ta,mu
+; CHECK-NEXT:    vrgather.vv v16, v18, v20, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 2 x double> @llvm.riscv.vrgather.mask.nxv2f64.nxv2i64(
+    <vscale x 2 x double> %0,
+    <vscale x 2 x double> %1,
+    <vscale x 2 x i64> %2,
+    <vscale x 2 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 2 x double> %a
+}
+
+declare <vscale x 4 x double> @llvm.riscv.vrgather.nxv4f64.nxv4i64(
+  <vscale x 4 x double>,
+  <vscale x 4 x i64>,
+  i64);
+
+define <vscale x 4 x double> @intrinsic_vrgather_vv_nxv4f64_nxv4f64_nxv4i64(<vscale x 4 x double> %0, <vscale x 4 x i64> %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vv_nxv4f64_nxv4f64_nxv4i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e64,m4,ta,mu
+; CHECK-NEXT:    vrgather.vv v28, v16, v20
+; CHECK-NEXT:    vmv4r.v v16, v28
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 4 x double> @llvm.riscv.vrgather.nxv4f64.nxv4i64(
+    <vscale x 4 x double> %0,
+    <vscale x 4 x i64> %1,
+    i64 %2)
+
+  ret <vscale x 4 x double> %a
+}
+
+declare <vscale x 4 x double> @llvm.riscv.vrgather.mask.nxv4f64.nxv4i64(
+  <vscale x 4 x double>,
+  <vscale x 4 x double>,
+  <vscale x 4 x i64>,
+  <vscale x 4 x i1>,
+  i64);
+
+define <vscale x 4 x double> @intrinsic_vrgather_mask_vv_nxv4f64_nxv4f64_nxv4i64(<vscale x 4 x double> %0, <vscale x 4 x double> %1, <vscale x 4 x i64> %2, <vscale x 4 x i1> %3, i64 %4) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vv_nxv4f64_nxv4f64_nxv4i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a2, zero, e64,m4,ta,mu
+; CHECK-NEXT:    vle64.v v28, (a0)
+; CHECK-NEXT:    vsetvli a0, a1, e64,m4,ta,mu
+; CHECK-NEXT:    vrgather.vv v16, v20, v28, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 4 x double> @llvm.riscv.vrgather.mask.nxv4f64.nxv4i64(
+    <vscale x 4 x double> %0,
+    <vscale x 4 x double> %1,
+    <vscale x 4 x i64> %2,
+    <vscale x 4 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 4 x double> %a
+}
+
+declare <vscale x 8 x double> @llvm.riscv.vrgather.nxv8f64.nxv8i64(
+  <vscale x 8 x double>,
+  <vscale x 8 x i64>,
+  i64);
+
+define <vscale x 8 x double> @intrinsic_vrgather_vv_nxv8f64_nxv8f64_nxv8i64(<vscale x 8 x double> %0, <vscale x 8 x i64> %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vv_nxv8f64_nxv8f64_nxv8i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a2, zero, e64,m8,ta,mu
+; CHECK-NEXT:    vle64.v v24, (a0)
+; CHECK-NEXT:    vsetvli a0, a1, e64,m8,ta,mu
+; CHECK-NEXT:    vrgather.vv v8, v16, v24
+; CHECK-NEXT:    vmv8r.v v16, v8
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 8 x double> @llvm.riscv.vrgather.nxv8f64.nxv8i64(
+    <vscale x 8 x double> %0,
+    <vscale x 8 x i64> %1,
+    i64 %2)
+
+  ret <vscale x 8 x double> %a
+}
+
+declare <vscale x 8 x double> @llvm.riscv.vrgather.mask.nxv8f64.nxv8i64(
+  <vscale x 8 x double>,
+  <vscale x 8 x double>,
+  <vscale x 8 x i64>,
+  <vscale x 8 x i1>,
+  i64);
+
+define <vscale x 8 x double> @intrinsic_vrgather_mask_vv_nxv8f64_nxv8f64_nxv8i64(<vscale x 8 x double> %0, <vscale x 8 x double> %1, <vscale x 8 x i64> %2, <vscale x 8 x i1> %3, i64 %4) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vv_nxv8f64_nxv8f64_nxv8i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a3, zero, e64,m8,ta,mu
+; CHECK-NEXT:    vle64.v v8, (a1)
+; CHECK-NEXT:    vle64.v v24, (a0)
+; CHECK-NEXT:    vsetvli a0, a2, e64,m8,ta,mu
+; CHECK-NEXT:    vrgather.vv v16, v24, v8, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 8 x double> @llvm.riscv.vrgather.mask.nxv8f64.nxv8i64(
+    <vscale x 8 x double> %0,
+    <vscale x 8 x double> %1,
+    <vscale x 8 x i64> %2,
+    <vscale x 8 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 8 x double> %a
+}
+
+declare <vscale x 1 x i8> @llvm.riscv.vrgather.nxv1i8.i8(
+  <vscale x 1 x i8>,
+  i8,
+  i64);
+
+define <vscale x 1 x i8> @intrinsic_vrgather_vx_nxv1i8_nxv1i8_i8(<vscale x 1 x i8> %0, i8 %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vx_nxv1i8_nxv1i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a1, a1, e8,mf8,ta,mu
+; CHECK-NEXT:    vrgather.vx v25, v16, a0
+; CHECK-NEXT:    vmv1r.v v16, v25
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 1 x i8> @llvm.riscv.vrgather.nxv1i8.i8(
+    <vscale x 1 x i8> %0,
+    i8 %1,
+    i64 %2)
+
+  ret <vscale x 1 x i8> %a
+}
+
+declare <vscale x 1 x i8> @llvm.riscv.vrgather.mask.nxv1i8.i8(
+  <vscale x 1 x i8>,
+  <vscale x 1 x i8>,
+  i8,
+  <vscale x 1 x i1>,
+  i64);
+
+define <vscale x 1 x i8> @intrinsic_vrgather_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_vrgather_mask_vx_nxv1i8_nxv1i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a1, a1, e8,mf8,ta,mu
+; CHECK-NEXT:    vrgather.vx v16, v17, a0, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 1 x i8> @llvm.riscv.vrgather.mask.nxv1i8.i8(
+    <vscale x 1 x i8> %0,
+    <vscale x 1 x i8> %1,
+    i8 %2,
+    <vscale x 1 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 1 x i8> %a
+}
+
+declare <vscale x 2 x i8> @llvm.riscv.vrgather.nxv2i8.i8(
+  <vscale x 2 x i8>,
+  i8,
+  i64);
+
+define <vscale x 2 x i8> @intrinsic_vrgather_vx_nxv2i8_nxv2i8_i8(<vscale x 2 x i8> %0, i8 %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vx_nxv2i8_nxv2i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a1, a1, e8,mf4,ta,mu
+; CHECK-NEXT:    vrgather.vx v25, v16, a0
+; CHECK-NEXT:    vmv1r.v v16, v25
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 2 x i8> @llvm.riscv.vrgather.nxv2i8.i8(
+    <vscale x 2 x i8> %0,
+    i8 %1,
+    i64 %2)
+
+  ret <vscale x 2 x i8> %a
+}
+
+declare <vscale x 2 x i8> @llvm.riscv.vrgather.mask.nxv2i8.i8(
+  <vscale x 2 x i8>,
+  <vscale x 2 x i8>,
+  i8,
+  <vscale x 2 x i1>,
+  i64);
+
+define <vscale x 2 x i8> @intrinsic_vrgather_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_vrgather_mask_vx_nxv2i8_nxv2i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a1, a1, e8,mf4,ta,mu
+; CHECK-NEXT:    vrgather.vx v16, v17, a0, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 2 x i8> @llvm.riscv.vrgather.mask.nxv2i8.i8(
+    <vscale x 2 x i8> %0,
+    <vscale x 2 x i8> %1,
+    i8 %2,
+    <vscale x 2 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 2 x i8> %a
+}
+
+declare <vscale x 4 x i8> @llvm.riscv.vrgather.nxv4i8.i8(
+  <vscale x 4 x i8>,
+  i8,
+  i64);
+
+define <vscale x 4 x i8> @intrinsic_vrgather_vx_nxv4i8_nxv4i8_i8(<vscale x 4 x i8> %0, i8 %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vx_nxv4i8_nxv4i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a1, a1, e8,mf2,ta,mu
+; CHECK-NEXT:    vrgather.vx v25, v16, a0
+; CHECK-NEXT:    vmv1r.v v16, v25
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 4 x i8> @llvm.riscv.vrgather.nxv4i8.i8(
+    <vscale x 4 x i8> %0,
+    i8 %1,
+    i64 %2)
+
+  ret <vscale x 4 x i8> %a
+}
+
+declare <vscale x 4 x i8> @llvm.riscv.vrgather.mask.nxv4i8.i8(
+  <vscale x 4 x i8>,
+  <vscale x 4 x i8>,
+  i8,
+  <vscale x 4 x i1>,
+  i64);
+
+define <vscale x 4 x i8> @intrinsic_vrgather_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_vrgather_mask_vx_nxv4i8_nxv4i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a1, a1, e8,mf2,ta,mu
+; CHECK-NEXT:    vrgather.vx v16, v17, a0, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 4 x i8> @llvm.riscv.vrgather.mask.nxv4i8.i8(
+    <vscale x 4 x i8> %0,
+    <vscale x 4 x i8> %1,
+    i8 %2,
+    <vscale x 4 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 4 x i8> %a
+}
+
+declare <vscale x 8 x i8> @llvm.riscv.vrgather.nxv8i8.i8(
+  <vscale x 8 x i8>,
+  i8,
+  i64);
+
+define <vscale x 8 x i8> @intrinsic_vrgather_vx_nxv8i8_nxv8i8_i8(<vscale x 8 x i8> %0, i8 %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vx_nxv8i8_nxv8i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a1, a1, e8,m1,ta,mu
+; CHECK-NEXT:    vrgather.vx v25, v16, a0
+; CHECK-NEXT:    vmv1r.v v16, v25
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 8 x i8> @llvm.riscv.vrgather.nxv8i8.i8(
+    <vscale x 8 x i8> %0,
+    i8 %1,
+    i64 %2)
+
+  ret <vscale x 8 x i8> %a
+}
+
+declare <vscale x 8 x i8> @llvm.riscv.vrgather.mask.nxv8i8.i8(
+  <vscale x 8 x i8>,
+  <vscale x 8 x i8>,
+  i8,
+  <vscale x 8 x i1>,
+  i64);
+
+define <vscale x 8 x i8> @intrinsic_vrgather_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_vrgather_mask_vx_nxv8i8_nxv8i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a1, a1, e8,m1,ta,mu
+; CHECK-NEXT:    vrgather.vx v16, v17, a0, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 8 x i8> @llvm.riscv.vrgather.mask.nxv8i8.i8(
+    <vscale x 8 x i8> %0,
+    <vscale x 8 x i8> %1,
+    i8 %2,
+    <vscale x 8 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 8 x i8> %a
+}
+
+declare <vscale x 16 x i8> @llvm.riscv.vrgather.nxv16i8.i8(
+  <vscale x 16 x i8>,
+  i8,
+  i64);
+
+define <vscale x 16 x i8> @intrinsic_vrgather_vx_nxv16i8_nxv16i8_i8(<vscale x 16 x i8> %0, i8 %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vx_nxv16i8_nxv16i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a1, a1, e8,m2,ta,mu
+; CHECK-NEXT:    vrgather.vx v26, v16, a0
+; CHECK-NEXT:    vmv2r.v v16, v26
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 16 x i8> @llvm.riscv.vrgather.nxv16i8.i8(
+    <vscale x 16 x i8> %0,
+    i8 %1,
+    i64 %2)
+
+  ret <vscale x 16 x i8> %a
+}
+
+declare <vscale x 16 x i8> @llvm.riscv.vrgather.mask.nxv16i8.i8(
+  <vscale x 16 x i8>,
+  <vscale x 16 x i8>,
+  i8,
+  <vscale x 16 x i1>,
+  i64);
+
+define <vscale x 16 x i8> @intrinsic_vrgather_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_vrgather_mask_vx_nxv16i8_nxv16i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a1, a1, e8,m2,ta,mu
+; CHECK-NEXT:    vrgather.vx v16, v18, a0, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 16 x i8> @llvm.riscv.vrgather.mask.nxv16i8.i8(
+    <vscale x 16 x i8> %0,
+    <vscale x 16 x i8> %1,
+    i8 %2,
+    <vscale x 16 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 16 x i8> %a
+}
+
+declare <vscale x 32 x i8> @llvm.riscv.vrgather.nxv32i8.i8(
+  <vscale x 32 x i8>,
+  i8,
+  i64);
+
+define <vscale x 32 x i8> @intrinsic_vrgather_vx_nxv32i8_nxv32i8_i8(<vscale x 32 x i8> %0, i8 %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vx_nxv32i8_nxv32i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a1, a1, e8,m4,ta,mu
+; CHECK-NEXT:    vrgather.vx v28, v16, a0
+; CHECK-NEXT:    vmv4r.v v16, v28
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 32 x i8> @llvm.riscv.vrgather.nxv32i8.i8(
+    <vscale x 32 x i8> %0,
+    i8 %1,
+    i64 %2)
+
+  ret <vscale x 32 x i8> %a
+}
+
+declare <vscale x 32 x i8> @llvm.riscv.vrgather.mask.nxv32i8.i8(
+  <vscale x 32 x i8>,
+  <vscale x 32 x i8>,
+  i8,
+  <vscale x 32 x i1>,
+  i64);
+
+define <vscale x 32 x i8> @intrinsic_vrgather_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_vrgather_mask_vx_nxv32i8_nxv32i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a1, a1, e8,m4,ta,mu
+; CHECK-NEXT:    vrgather.vx v16, v20, a0, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 32 x i8> @llvm.riscv.vrgather.mask.nxv32i8.i8(
+    <vscale x 32 x i8> %0,
+    <vscale x 32 x i8> %1,
+    i8 %2,
+    <vscale x 32 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 32 x i8> %a
+}
+
+declare <vscale x 64 x i8> @llvm.riscv.vrgather.nxv64i8.i8(
+  <vscale x 64 x i8>,
+  i8,
+  i64);
+
+define <vscale x 64 x i8> @intrinsic_vrgather_vx_nxv64i8_nxv64i8_i8(<vscale x 64 x i8> %0, i8 %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vx_nxv64i8_nxv64i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a1, a1, e8,m8,ta,mu
+; CHECK-NEXT:    vrgather.vx v8, v16, a0
+; CHECK-NEXT:    vmv8r.v v16, v8
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 64 x i8> @llvm.riscv.vrgather.nxv64i8.i8(
+    <vscale x 64 x i8> %0,
+    i8 %1,
+    i64 %2)
+
+  ret <vscale x 64 x i8> %a
+}
+
+declare <vscale x 64 x i8> @llvm.riscv.vrgather.mask.nxv64i8.i8(
+  <vscale x 64 x i8>,
+  <vscale x 64 x i8>,
+  i8,
+  <vscale x 64 x i1>,
+  i64);
+
+define <vscale x 64 x i8> @intrinsic_vrgather_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_vrgather_mask_vx_nxv64i8_nxv64i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a3, zero, e8,m8,ta,mu
+; CHECK-NEXT:    vle8.v v8, (a0)
+; CHECK-NEXT:    vsetvli a0, a2, e8,m8,ta,mu
+; CHECK-NEXT:    vrgather.vx v16, v8, a1, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 64 x i8> @llvm.riscv.vrgather.mask.nxv64i8.i8(
+    <vscale x 64 x i8> %0,
+    <vscale x 64 x i8> %1,
+    i8 %2,
+    <vscale x 64 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 64 x i8> %a
+}
+
+declare <vscale x 1 x i16> @llvm.riscv.vrgather.nxv1i16.i16(
+  <vscale x 1 x i16>,
+  i16,
+  i64);
+
+define <vscale x 1 x i16> @intrinsic_vrgather_vx_nxv1i16_nxv1i16_i16(<vscale x 1 x i16> %0, i16 %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vx_nxv1i16_nxv1i16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a1, a1, e16,mf4,ta,mu
+; CHECK-NEXT:    vrgather.vx v25, v16, a0
+; CHECK-NEXT:    vmv1r.v v16, v25
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 1 x i16> @llvm.riscv.vrgather.nxv1i16.i16(
+    <vscale x 1 x i16> %0,
+    i16 %1,
+    i64 %2)
+
+  ret <vscale x 1 x i16> %a
+}
+
+declare <vscale x 1 x i16> @llvm.riscv.vrgather.mask.nxv1i16.i16(
+  <vscale x 1 x i16>,
+  <vscale x 1 x i16>,
+  i16,
+  <vscale x 1 x i1>,
+  i64);
+
+define <vscale x 1 x i16> @intrinsic_vrgather_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_vrgather_mask_vx_nxv1i16_nxv1i16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a1, a1, e16,mf4,ta,mu
+; CHECK-NEXT:    vrgather.vx v16, v17, a0, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 1 x i16> @llvm.riscv.vrgather.mask.nxv1i16.i16(
+    <vscale x 1 x i16> %0,
+    <vscale x 1 x i16> %1,
+    i16 %2,
+    <vscale x 1 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 1 x i16> %a
+}
+
+declare <vscale x 2 x i16> @llvm.riscv.vrgather.nxv2i16.i16(
+  <vscale x 2 x i16>,
+  i16,
+  i64);
+
+define <vscale x 2 x i16> @intrinsic_vrgather_vx_nxv2i16_nxv2i16_i16(<vscale x 2 x i16> %0, i16 %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vx_nxv2i16_nxv2i16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a1, a1, e16,mf2,ta,mu
+; CHECK-NEXT:    vrgather.vx v25, v16, a0
+; CHECK-NEXT:    vmv1r.v v16, v25
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 2 x i16> @llvm.riscv.vrgather.nxv2i16.i16(
+    <vscale x 2 x i16> %0,
+    i16 %1,
+    i64 %2)
+
+  ret <vscale x 2 x i16> %a
+}
+
+declare <vscale x 2 x i16> @llvm.riscv.vrgather.mask.nxv2i16.i16(
+  <vscale x 2 x i16>,
+  <vscale x 2 x i16>,
+  i16,
+  <vscale x 2 x i1>,
+  i64);
+
+define <vscale x 2 x i16> @intrinsic_vrgather_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_vrgather_mask_vx_nxv2i16_nxv2i16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a1, a1, e16,mf2,ta,mu
+; CHECK-NEXT:    vrgather.vx v16, v17, a0, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 2 x i16> @llvm.riscv.vrgather.mask.nxv2i16.i16(
+    <vscale x 2 x i16> %0,
+    <vscale x 2 x i16> %1,
+    i16 %2,
+    <vscale x 2 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 2 x i16> %a
+}
+
+declare <vscale x 4 x i16> @llvm.riscv.vrgather.nxv4i16.i16(
+  <vscale x 4 x i16>,
+  i16,
+  i64);
+
+define <vscale x 4 x i16> @intrinsic_vrgather_vx_nxv4i16_nxv4i16_i16(<vscale x 4 x i16> %0, i16 %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vx_nxv4i16_nxv4i16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a1, a1, e16,m1,ta,mu
+; CHECK-NEXT:    vrgather.vx v25, v16, a0
+; CHECK-NEXT:    vmv1r.v v16, v25
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 4 x i16> @llvm.riscv.vrgather.nxv4i16.i16(
+    <vscale x 4 x i16> %0,
+    i16 %1,
+    i64 %2)
+
+  ret <vscale x 4 x i16> %a
+}
+
+declare <vscale x 4 x i16> @llvm.riscv.vrgather.mask.nxv4i16.i16(
+  <vscale x 4 x i16>,
+  <vscale x 4 x i16>,
+  i16,
+  <vscale x 4 x i1>,
+  i64);
+
+define <vscale x 4 x i16> @intrinsic_vrgather_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_vrgather_mask_vx_nxv4i16_nxv4i16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a1, a1, e16,m1,ta,mu
+; CHECK-NEXT:    vrgather.vx v16, v17, a0, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 4 x i16> @llvm.riscv.vrgather.mask.nxv4i16.i16(
+    <vscale x 4 x i16> %0,
+    <vscale x 4 x i16> %1,
+    i16 %2,
+    <vscale x 4 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 4 x i16> %a
+}
+
+declare <vscale x 8 x i16> @llvm.riscv.vrgather.nxv8i16.i16(
+  <vscale x 8 x i16>,
+  i16,
+  i64);
+
+define <vscale x 8 x i16> @intrinsic_vrgather_vx_nxv8i16_nxv8i16_i16(<vscale x 8 x i16> %0, i16 %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vx_nxv8i16_nxv8i16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a1, a1, e16,m2,ta,mu
+; CHECK-NEXT:    vrgather.vx v26, v16, a0
+; CHECK-NEXT:    vmv2r.v v16, v26
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 8 x i16> @llvm.riscv.vrgather.nxv8i16.i16(
+    <vscale x 8 x i16> %0,
+    i16 %1,
+    i64 %2)
+
+  ret <vscale x 8 x i16> %a
+}
+
+declare <vscale x 8 x i16> @llvm.riscv.vrgather.mask.nxv8i16.i16(
+  <vscale x 8 x i16>,
+  <vscale x 8 x i16>,
+  i16,
+  <vscale x 8 x i1>,
+  i64);
+
+define <vscale x 8 x i16> @intrinsic_vrgather_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_vrgather_mask_vx_nxv8i16_nxv8i16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a1, a1, e16,m2,ta,mu
+; CHECK-NEXT:    vrgather.vx v16, v18, a0, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 8 x i16> @llvm.riscv.vrgather.mask.nxv8i16.i16(
+    <vscale x 8 x i16> %0,
+    <vscale x 8 x i16> %1,
+    i16 %2,
+    <vscale x 8 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 8 x i16> %a
+}
+
+declare <vscale x 16 x i16> @llvm.riscv.vrgather.nxv16i16.i16(
+  <vscale x 16 x i16>,
+  i16,
+  i64);
+
+define <vscale x 16 x i16> @intrinsic_vrgather_vx_nxv16i16_nxv16i16_i16(<vscale x 16 x i16> %0, i16 %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vx_nxv16i16_nxv16i16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a1, a1, e16,m4,ta,mu
+; CHECK-NEXT:    vrgather.vx v28, v16, a0
+; CHECK-NEXT:    vmv4r.v v16, v28
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 16 x i16> @llvm.riscv.vrgather.nxv16i16.i16(
+    <vscale x 16 x i16> %0,
+    i16 %1,
+    i64 %2)
+
+  ret <vscale x 16 x i16> %a
+}
+
+declare <vscale x 16 x i16> @llvm.riscv.vrgather.mask.nxv16i16.i16(
+  <vscale x 16 x i16>,
+  <vscale x 16 x i16>,
+  i16,
+  <vscale x 16 x i1>,
+  i64);
+
+define <vscale x 16 x i16> @intrinsic_vrgather_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_vrgather_mask_vx_nxv16i16_nxv16i16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a1, a1, e16,m4,ta,mu
+; CHECK-NEXT:    vrgather.vx v16, v20, a0, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 16 x i16> @llvm.riscv.vrgather.mask.nxv16i16.i16(
+    <vscale x 16 x i16> %0,
+    <vscale x 16 x i16> %1,
+    i16 %2,
+    <vscale x 16 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 16 x i16> %a
+}
+
+declare <vscale x 32 x i16> @llvm.riscv.vrgather.nxv32i16.i16(
+  <vscale x 32 x i16>,
+  i16,
+  i64);
+
+define <vscale x 32 x i16> @intrinsic_vrgather_vx_nxv32i16_nxv32i16_i16(<vscale x 32 x i16> %0, i16 %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vx_nxv32i16_nxv32i16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a1, a1, e16,m8,ta,mu
+; CHECK-NEXT:    vrgather.vx v8, v16, a0
+; CHECK-NEXT:    vmv8r.v v16, v8
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 32 x i16> @llvm.riscv.vrgather.nxv32i16.i16(
+    <vscale x 32 x i16> %0,
+    i16 %1,
+    i64 %2)
+
+  ret <vscale x 32 x i16> %a
+}
+
+declare <vscale x 32 x i16> @llvm.riscv.vrgather.mask.nxv32i16.i16(
+  <vscale x 32 x i16>,
+  <vscale x 32 x i16>,
+  i16,
+  <vscale x 32 x i1>,
+  i64);
+
+define <vscale x 32 x i16> @intrinsic_vrgather_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_vrgather_mask_vx_nxv32i16_nxv32i16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a3, zero, e16,m8,ta,mu
+; CHECK-NEXT:    vle16.v v8, (a0)
+; CHECK-NEXT:    vsetvli a0, a2, e16,m8,ta,mu
+; CHECK-NEXT:    vrgather.vx v16, v8, a1, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 32 x i16> @llvm.riscv.vrgather.mask.nxv32i16.i16(
+    <vscale x 32 x i16> %0,
+    <vscale x 32 x i16> %1,
+    i16 %2,
+    <vscale x 32 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 32 x i16> %a
+}
+
+declare <vscale x 1 x i32> @llvm.riscv.vrgather.nxv1i32.i32(
+  <vscale x 1 x i32>,
+  i32,
+  i64);
+
+define <vscale x 1 x i32> @intrinsic_vrgather_vx_nxv1i32_nxv1i32_i32(<vscale x 1 x i32> %0, i32 %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vx_nxv1i32_nxv1i32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a1, a1, e32,mf2,ta,mu
+; CHECK-NEXT:    vrgather.vx v25, v16, a0
+; CHECK-NEXT:    vmv1r.v v16, v25
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 1 x i32> @llvm.riscv.vrgather.nxv1i32.i32(
+    <vscale x 1 x i32> %0,
+    i32 %1,
+    i64 %2)
+
+  ret <vscale x 1 x i32> %a
+}
+
+declare <vscale x 1 x i32> @llvm.riscv.vrgather.mask.nxv1i32.i32(
+  <vscale x 1 x i32>,
+  <vscale x 1 x i32>,
+  i32,
+  <vscale x 1 x i1>,
+  i64);
+
+define <vscale x 1 x i32> @intrinsic_vrgather_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_vrgather_mask_vx_nxv1i32_nxv1i32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a1, a1, e32,mf2,ta,mu
+; CHECK-NEXT:    vrgather.vx v16, v17, a0, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 1 x i32> @llvm.riscv.vrgather.mask.nxv1i32.i32(
+    <vscale x 1 x i32> %0,
+    <vscale x 1 x i32> %1,
+    i32 %2,
+    <vscale x 1 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 1 x i32> %a
+}
+
+declare <vscale x 2 x i32> @llvm.riscv.vrgather.nxv2i32.i32(
+  <vscale x 2 x i32>,
+  i32,
+  i64);
+
+define <vscale x 2 x i32> @intrinsic_vrgather_vx_nxv2i32_nxv2i32_i32(<vscale x 2 x i32> %0, i32 %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vx_nxv2i32_nxv2i32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a1, a1, e32,m1,ta,mu
+; CHECK-NEXT:    vrgather.vx v25, v16, a0
+; CHECK-NEXT:    vmv1r.v v16, v25
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 2 x i32> @llvm.riscv.vrgather.nxv2i32.i32(
+    <vscale x 2 x i32> %0,
+    i32 %1,
+    i64 %2)
+
+  ret <vscale x 2 x i32> %a
+}
+
+declare <vscale x 2 x i32> @llvm.riscv.vrgather.mask.nxv2i32.i32(
+  <vscale x 2 x i32>,
+  <vscale x 2 x i32>,
+  i32,
+  <vscale x 2 x i1>,
+  i64);
+
+define <vscale x 2 x i32> @intrinsic_vrgather_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_vrgather_mask_vx_nxv2i32_nxv2i32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a1, a1, e32,m1,ta,mu
+; CHECK-NEXT:    vrgather.vx v16, v17, a0, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 2 x i32> @llvm.riscv.vrgather.mask.nxv2i32.i32(
+    <vscale x 2 x i32> %0,
+    <vscale x 2 x i32> %1,
+    i32 %2,
+    <vscale x 2 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 2 x i32> %a
+}
+
+declare <vscale x 4 x i32> @llvm.riscv.vrgather.nxv4i32.i32(
+  <vscale x 4 x i32>,
+  i32,
+  i64);
+
+define <vscale x 4 x i32> @intrinsic_vrgather_vx_nxv4i32_nxv4i32_i32(<vscale x 4 x i32> %0, i32 %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vx_nxv4i32_nxv4i32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a1, a1, e32,m2,ta,mu
+; CHECK-NEXT:    vrgather.vx v26, v16, a0
+; CHECK-NEXT:    vmv2r.v v16, v26
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 4 x i32> @llvm.riscv.vrgather.nxv4i32.i32(
+    <vscale x 4 x i32> %0,
+    i32 %1,
+    i64 %2)
+
+  ret <vscale x 4 x i32> %a
+}
+
+declare <vscale x 4 x i32> @llvm.riscv.vrgather.mask.nxv4i32.i32(
+  <vscale x 4 x i32>,
+  <vscale x 4 x i32>,
+  i32,
+  <vscale x 4 x i1>,
+  i64);
+
+define <vscale x 4 x i32> @intrinsic_vrgather_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_vrgather_mask_vx_nxv4i32_nxv4i32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a1, a1, e32,m2,ta,mu
+; CHECK-NEXT:    vrgather.vx v16, v18, a0, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 4 x i32> @llvm.riscv.vrgather.mask.nxv4i32.i32(
+    <vscale x 4 x i32> %0,
+    <vscale x 4 x i32> %1,
+    i32 %2,
+    <vscale x 4 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 4 x i32> %a
+}
+
+declare <vscale x 8 x i32> @llvm.riscv.vrgather.nxv8i32.i32(
+  <vscale x 8 x i32>,
+  i32,
+  i64);
+
+define <vscale x 8 x i32> @intrinsic_vrgather_vx_nxv8i32_nxv8i32_i32(<vscale x 8 x i32> %0, i32 %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vx_nxv8i32_nxv8i32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a1, a1, e32,m4,ta,mu
+; CHECK-NEXT:    vrgather.vx v28, v16, a0
+; CHECK-NEXT:    vmv4r.v v16, v28
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 8 x i32> @llvm.riscv.vrgather.nxv8i32.i32(
+    <vscale x 8 x i32> %0,
+    i32 %1,
+    i64 %2)
+
+  ret <vscale x 8 x i32> %a
+}
+
+declare <vscale x 8 x i32> @llvm.riscv.vrgather.mask.nxv8i32.i32(
+  <vscale x 8 x i32>,
+  <vscale x 8 x i32>,
+  i32,
+  <vscale x 8 x i1>,
+  i64);
+
+define <vscale x 8 x i32> @intrinsic_vrgather_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_vrgather_mask_vx_nxv8i32_nxv8i32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a1, a1, e32,m4,ta,mu
+; CHECK-NEXT:    vrgather.vx v16, v20, a0, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 8 x i32> @llvm.riscv.vrgather.mask.nxv8i32.i32(
+    <vscale x 8 x i32> %0,
+    <vscale x 8 x i32> %1,
+    i32 %2,
+    <vscale x 8 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 8 x i32> %a
+}
+
+declare <vscale x 16 x i32> @llvm.riscv.vrgather.nxv16i32.i32(
+  <vscale x 16 x i32>,
+  i32,
+  i64);
+
+define <vscale x 16 x i32> @intrinsic_vrgather_vx_nxv16i32_nxv16i32_i32(<vscale x 16 x i32> %0, i32 %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vx_nxv16i32_nxv16i32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a1, a1, e32,m8,ta,mu
+; CHECK-NEXT:    vrgather.vx v8, v16, a0
+; CHECK-NEXT:    vmv8r.v v16, v8
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 16 x i32> @llvm.riscv.vrgather.nxv16i32.i32(
+    <vscale x 16 x i32> %0,
+    i32 %1,
+    i64 %2)
+
+  ret <vscale x 16 x i32> %a
+}
+
+declare <vscale x 16 x i32> @llvm.riscv.vrgather.mask.nxv16i32.i32(
+  <vscale x 16 x i32>,
+  <vscale x 16 x i32>,
+  i32,
+  <vscale x 16 x i1>,
+  i64);
+
+define <vscale x 16 x i32> @intrinsic_vrgather_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_vrgather_mask_vx_nxv16i32_nxv16i32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a3, zero, e32,m8,ta,mu
+; CHECK-NEXT:    vle32.v v8, (a0)
+; CHECK-NEXT:    vsetvli a0, a2, e32,m8,ta,mu
+; CHECK-NEXT:    vrgather.vx v16, v8, a1, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 16 x i32> @llvm.riscv.vrgather.mask.nxv16i32.i32(
+    <vscale x 16 x i32> %0,
+    <vscale x 16 x i32> %1,
+    i32 %2,
+    <vscale x 16 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 16 x i32> %a
+}
+
+declare <vscale x 1 x i64> @llvm.riscv.vrgather.nxv1i64.i64(
+  <vscale x 1 x i64>,
+  i64,
+  i64);
+
+define <vscale x 1 x i64> @intrinsic_vrgather_vx_nxv1i64_nxv1i64_i64(<vscale x 1 x i64> %0, i64 %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vx_nxv1i64_nxv1i64_i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a1, a1, e64,m1,ta,mu
+; CHECK-NEXT:    vrgather.vx v25, v16, a0
+; CHECK-NEXT:    vmv1r.v v16, v25
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 1 x i64> @llvm.riscv.vrgather.nxv1i64.i64(
+    <vscale x 1 x i64> %0,
+    i64 %1,
+    i64 %2)
+
+  ret <vscale x 1 x i64> %a
+}
+
+declare <vscale x 1 x i64> @llvm.riscv.vrgather.mask.nxv1i64.i64(
+  <vscale x 1 x i64>,
+  <vscale x 1 x i64>,
+  i64,
+  <vscale x 1 x i1>,
+  i64);
+
+define <vscale x 1 x i64> @intrinsic_vrgather_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_vrgather_mask_vx_nxv1i64_nxv1i64_i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a1, a1, e64,m1,ta,mu
+; CHECK-NEXT:    vrgather.vx v16, v17, a0, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 1 x i64> @llvm.riscv.vrgather.mask.nxv1i64.i64(
+    <vscale x 1 x i64> %0,
+    <vscale x 1 x i64> %1,
+    i64 %2,
+    <vscale x 1 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 1 x i64> %a
+}
+
+declare <vscale x 2 x i64> @llvm.riscv.vrgather.nxv2i64.i64(
+  <vscale x 2 x i64>,
+  i64,
+  i64);
+
+define <vscale x 2 x i64> @intrinsic_vrgather_vx_nxv2i64_nxv2i64_i64(<vscale x 2 x i64> %0, i64 %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vx_nxv2i64_nxv2i64_i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a1, a1, e64,m2,ta,mu
+; CHECK-NEXT:    vrgather.vx v26, v16, a0
+; CHECK-NEXT:    vmv2r.v v16, v26
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 2 x i64> @llvm.riscv.vrgather.nxv2i64.i64(
+    <vscale x 2 x i64> %0,
+    i64 %1,
+    i64 %2)
+
+  ret <vscale x 2 x i64> %a
+}
+
+declare <vscale x 2 x i64> @llvm.riscv.vrgather.mask.nxv2i64.i64(
+  <vscale x 2 x i64>,
+  <vscale x 2 x i64>,
+  i64,
+  <vscale x 2 x i1>,
+  i64);
+
+define <vscale x 2 x i64> @intrinsic_vrgather_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_vrgather_mask_vx_nxv2i64_nxv2i64_i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a1, a1, e64,m2,ta,mu
+; CHECK-NEXT:    vrgather.vx v16, v18, a0, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 2 x i64> @llvm.riscv.vrgather.mask.nxv2i64.i64(
+    <vscale x 2 x i64> %0,
+    <vscale x 2 x i64> %1,
+    i64 %2,
+    <vscale x 2 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 2 x i64> %a
+}
+
+declare <vscale x 4 x i64> @llvm.riscv.vrgather.nxv4i64.i64(
+  <vscale x 4 x i64>,
+  i64,
+  i64);
+
+define <vscale x 4 x i64> @intrinsic_vrgather_vx_nxv4i64_nxv4i64_i64(<vscale x 4 x i64> %0, i64 %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vx_nxv4i64_nxv4i64_i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a1, a1, e64,m4,ta,mu
+; CHECK-NEXT:    vrgather.vx v28, v16, a0
+; CHECK-NEXT:    vmv4r.v v16, v28
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 4 x i64> @llvm.riscv.vrgather.nxv4i64.i64(
+    <vscale x 4 x i64> %0,
+    i64 %1,
+    i64 %2)
+
+  ret <vscale x 4 x i64> %a
+}
+
+declare <vscale x 4 x i64> @llvm.riscv.vrgather.mask.nxv4i64.i64(
+  <vscale x 4 x i64>,
+  <vscale x 4 x i64>,
+  i64,
+  <vscale x 4 x i1>,
+  i64);
+
+define <vscale x 4 x i64> @intrinsic_vrgather_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_vrgather_mask_vx_nxv4i64_nxv4i64_i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a1, a1, e64,m4,ta,mu
+; CHECK-NEXT:    vrgather.vx v16, v20, a0, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 4 x i64> @llvm.riscv.vrgather.mask.nxv4i64.i64(
+    <vscale x 4 x i64> %0,
+    <vscale x 4 x i64> %1,
+    i64 %2,
+    <vscale x 4 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 4 x i64> %a
+}
+
+declare <vscale x 8 x i64> @llvm.riscv.vrgather.nxv8i64.i64(
+  <vscale x 8 x i64>,
+  i64,
+  i64);
+
+define <vscale x 8 x i64> @intrinsic_vrgather_vx_nxv8i64_nxv8i64_i64(<vscale x 8 x i64> %0, i64 %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vx_nxv8i64_nxv8i64_i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a1, a1, e64,m8,ta,mu
+; CHECK-NEXT:    vrgather.vx v8, v16, a0
+; CHECK-NEXT:    vmv8r.v v16, v8
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 8 x i64> @llvm.riscv.vrgather.nxv8i64.i64(
+    <vscale x 8 x i64> %0,
+    i64 %1,
+    i64 %2)
+
+  ret <vscale x 8 x i64> %a
+}
+
+declare <vscale x 8 x i64> @llvm.riscv.vrgather.mask.nxv8i64.i64(
+  <vscale x 8 x i64>,
+  <vscale x 8 x i64>,
+  i64,
+  <vscale x 8 x i1>,
+  i64);
+
+define <vscale x 8 x i64> @intrinsic_vrgather_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_vrgather_mask_vx_nxv8i64_nxv8i64_i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a3, zero, e64,m8,ta,mu
+; CHECK-NEXT:    vle64.v v8, (a0)
+; CHECK-NEXT:    vsetvli a0, a2, e64,m8,ta,mu
+; CHECK-NEXT:    vrgather.vx v16, v8, a1, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 8 x i64> @llvm.riscv.vrgather.mask.nxv8i64.i64(
+    <vscale x 8 x i64> %0,
+    <vscale x 8 x i64> %1,
+    i64 %2,
+    <vscale x 8 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 8 x i64> %a
+}
+
+declare <vscale x 1 x half> @llvm.riscv.vrgather.nxv1f16.i16(
+  <vscale x 1 x half>,
+  i16,
+  i64);
+
+define <vscale x 1 x half> @intrinsic_vrgather_vx_nxv1f16_nxv1f16_i16(<vscale x 1 x half> %0, i16 %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vx_nxv1f16_nxv1f16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a1, a1, e16,mf4,ta,mu
+; CHECK-NEXT:    vrgather.vx v25, v16, a0
+; CHECK-NEXT:    vmv1r.v v16, v25
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 1 x half> @llvm.riscv.vrgather.nxv1f16.i16(
+    <vscale x 1 x half> %0,
+    i16 %1,
+    i64 %2)
+
+  ret <vscale x 1 x half> %a
+}
+
+declare <vscale x 1 x half> @llvm.riscv.vrgather.mask.nxv1f16.i16(
+  <vscale x 1 x half>,
+  <vscale x 1 x half>,
+  i16,
+  <vscale x 1 x i1>,
+  i64);
+
+define <vscale x 1 x half> @intrinsic_vrgather_mask_vx_nxv1f16_nxv1f16_i16(<vscale x 1 x half> %0, <vscale x 1 x half> %1, i16 %2, <vscale x 1 x i1> %3, i64 %4) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vx_nxv1f16_nxv1f16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a1, a1, e16,mf4,ta,mu
+; CHECK-NEXT:    vrgather.vx v16, v17, a0, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 1 x half> @llvm.riscv.vrgather.mask.nxv1f16.i16(
+    <vscale x 1 x half> %0,
+    <vscale x 1 x half> %1,
+    i16 %2,
+    <vscale x 1 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 1 x half> %a
+}
+
+declare <vscale x 2 x half> @llvm.riscv.vrgather.nxv2f16.i16(
+  <vscale x 2 x half>,
+  i16,
+  i64);
+
+define <vscale x 2 x half> @intrinsic_vrgather_vx_nxv2f16_nxv2f16_i16(<vscale x 2 x half> %0, i16 %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vx_nxv2f16_nxv2f16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a1, a1, e16,mf2,ta,mu
+; CHECK-NEXT:    vrgather.vx v25, v16, a0
+; CHECK-NEXT:    vmv1r.v v16, v25
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 2 x half> @llvm.riscv.vrgather.nxv2f16.i16(
+    <vscale x 2 x half> %0,
+    i16 %1,
+    i64 %2)
+
+  ret <vscale x 2 x half> %a
+}
+
+declare <vscale x 2 x half> @llvm.riscv.vrgather.mask.nxv2f16.i16(
+  <vscale x 2 x half>,
+  <vscale x 2 x half>,
+  i16,
+  <vscale x 2 x i1>,
+  i64);
+
+define <vscale x 2 x half> @intrinsic_vrgather_mask_vx_nxv2f16_nxv2f16_i16(<vscale x 2 x half> %0, <vscale x 2 x half> %1, i16 %2, <vscale x 2 x i1> %3, i64 %4) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vx_nxv2f16_nxv2f16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a1, a1, e16,mf2,ta,mu
+; CHECK-NEXT:    vrgather.vx v16, v17, a0, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 2 x half> @llvm.riscv.vrgather.mask.nxv2f16.i16(
+    <vscale x 2 x half> %0,
+    <vscale x 2 x half> %1,
+    i16 %2,
+    <vscale x 2 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 2 x half> %a
+}
+
+declare <vscale x 4 x half> @llvm.riscv.vrgather.nxv4f16.i16(
+  <vscale x 4 x half>,
+  i16,
+  i64);
+
+define <vscale x 4 x half> @intrinsic_vrgather_vx_nxv4f16_nxv4f16_i16(<vscale x 4 x half> %0, i16 %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vx_nxv4f16_nxv4f16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a1, a1, e16,m1,ta,mu
+; CHECK-NEXT:    vrgather.vx v25, v16, a0
+; CHECK-NEXT:    vmv1r.v v16, v25
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 4 x half> @llvm.riscv.vrgather.nxv4f16.i16(
+    <vscale x 4 x half> %0,
+    i16 %1,
+    i64 %2)
+
+  ret <vscale x 4 x half> %a
+}
+
+declare <vscale x 4 x half> @llvm.riscv.vrgather.mask.nxv4f16.i16(
+  <vscale x 4 x half>,
+  <vscale x 4 x half>,
+  i16,
+  <vscale x 4 x i1>,
+  i64);
+
+define <vscale x 4 x half> @intrinsic_vrgather_mask_vx_nxv4f16_nxv4f16_i16(<vscale x 4 x half> %0, <vscale x 4 x half> %1, i16 %2, <vscale x 4 x i1> %3, i64 %4) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vx_nxv4f16_nxv4f16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a1, a1, e16,m1,ta,mu
+; CHECK-NEXT:    vrgather.vx v16, v17, a0, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 4 x half> @llvm.riscv.vrgather.mask.nxv4f16.i16(
+    <vscale x 4 x half> %0,
+    <vscale x 4 x half> %1,
+    i16 %2,
+    <vscale x 4 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 4 x half> %a
+}
+
+declare <vscale x 8 x half> @llvm.riscv.vrgather.nxv8f16.i16(
+  <vscale x 8 x half>,
+  i16,
+  i64);
+
+define <vscale x 8 x half> @intrinsic_vrgather_vx_nxv8f16_nxv8f16_i16(<vscale x 8 x half> %0, i16 %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vx_nxv8f16_nxv8f16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a1, a1, e16,m2,ta,mu
+; CHECK-NEXT:    vrgather.vx v26, v16, a0
+; CHECK-NEXT:    vmv2r.v v16, v26
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 8 x half> @llvm.riscv.vrgather.nxv8f16.i16(
+    <vscale x 8 x half> %0,
+    i16 %1,
+    i64 %2)
+
+  ret <vscale x 8 x half> %a
+}
+
+declare <vscale x 8 x half> @llvm.riscv.vrgather.mask.nxv8f16.i16(
+  <vscale x 8 x half>,
+  <vscale x 8 x half>,
+  i16,
+  <vscale x 8 x i1>,
+  i64);
+
+define <vscale x 8 x half> @intrinsic_vrgather_mask_vx_nxv8f16_nxv8f16_i16(<vscale x 8 x half> %0, <vscale x 8 x half> %1, i16 %2, <vscale x 8 x i1> %3, i64 %4) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vx_nxv8f16_nxv8f16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a1, a1, e16,m2,ta,mu
+; CHECK-NEXT:    vrgather.vx v16, v18, a0, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 8 x half> @llvm.riscv.vrgather.mask.nxv8f16.i16(
+    <vscale x 8 x half> %0,
+    <vscale x 8 x half> %1,
+    i16 %2,
+    <vscale x 8 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 8 x half> %a
+}
+
+declare <vscale x 16 x half> @llvm.riscv.vrgather.nxv16f16.i16(
+  <vscale x 16 x half>,
+  i16,
+  i64);
+
+define <vscale x 16 x half> @intrinsic_vrgather_vx_nxv16f16_nxv16f16_i16(<vscale x 16 x half> %0, i16 %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vx_nxv16f16_nxv16f16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a1, a1, e16,m4,ta,mu
+; CHECK-NEXT:    vrgather.vx v28, v16, a0
+; CHECK-NEXT:    vmv4r.v v16, v28
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 16 x half> @llvm.riscv.vrgather.nxv16f16.i16(
+    <vscale x 16 x half> %0,
+    i16 %1,
+    i64 %2)
+
+  ret <vscale x 16 x half> %a
+}
+
+declare <vscale x 16 x half> @llvm.riscv.vrgather.mask.nxv16f16.i16(
+  <vscale x 16 x half>,
+  <vscale x 16 x half>,
+  i16,
+  <vscale x 16 x i1>,
+  i64);
+
+define <vscale x 16 x half> @intrinsic_vrgather_mask_vx_nxv16f16_nxv16f16_i16(<vscale x 16 x half> %0, <vscale x 16 x half> %1, i16 %2, <vscale x 16 x i1> %3, i64 %4) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vx_nxv16f16_nxv16f16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a1, a1, e16,m4,ta,mu
+; CHECK-NEXT:    vrgather.vx v16, v20, a0, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 16 x half> @llvm.riscv.vrgather.mask.nxv16f16.i16(
+    <vscale x 16 x half> %0,
+    <vscale x 16 x half> %1,
+    i16 %2,
+    <vscale x 16 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 16 x half> %a
+}
+
+declare <vscale x 32 x half> @llvm.riscv.vrgather.nxv32f16.i16(
+  <vscale x 32 x half>,
+  i16,
+  i64);
+
+define <vscale x 32 x half> @intrinsic_vrgather_vx_nxv32f16_nxv32f16_i16(<vscale x 32 x half> %0, i16 %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vx_nxv32f16_nxv32f16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a1, a1, e16,m8,ta,mu
+; CHECK-NEXT:    vrgather.vx v8, v16, a0
+; CHECK-NEXT:    vmv8r.v v16, v8
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 32 x half> @llvm.riscv.vrgather.nxv32f16.i16(
+    <vscale x 32 x half> %0,
+    i16 %1,
+    i64 %2)
+
+  ret <vscale x 32 x half> %a
+}
+
+declare <vscale x 32 x half> @llvm.riscv.vrgather.mask.nxv32f16.i16(
+  <vscale x 32 x half>,
+  <vscale x 32 x half>,
+  i16,
+  <vscale x 32 x i1>,
+  i64);
+
+define <vscale x 32 x half> @intrinsic_vrgather_mask_vx_nxv32f16_nxv32f16_i16(<vscale x 32 x half> %0, <vscale x 32 x half> %1, i16 %2, <vscale x 32 x i1> %3, i64 %4) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vx_nxv32f16_nxv32f16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a3, zero, e16,m8,ta,mu
+; CHECK-NEXT:    vle16.v v8, (a0)
+; CHECK-NEXT:    vsetvli a0, a2, e16,m8,ta,mu
+; CHECK-NEXT:    vrgather.vx v16, v8, a1, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 32 x half> @llvm.riscv.vrgather.mask.nxv32f16.i16(
+    <vscale x 32 x half> %0,
+    <vscale x 32 x half> %1,
+    i16 %2,
+    <vscale x 32 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 32 x half> %a
+}
+
+declare <vscale x 1 x float> @llvm.riscv.vrgather.nxv1f32.i32(
+  <vscale x 1 x float>,
+  i32,
+  i64);
+
+define <vscale x 1 x float> @intrinsic_vrgather_vx_nxv1f32_nxv1f32_i32(<vscale x 1 x float> %0, i32 %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vx_nxv1f32_nxv1f32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a1, a1, e32,mf2,ta,mu
+; CHECK-NEXT:    vrgather.vx v25, v16, a0
+; CHECK-NEXT:    vmv1r.v v16, v25
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 1 x float> @llvm.riscv.vrgather.nxv1f32.i32(
+    <vscale x 1 x float> %0,
+    i32 %1,
+    i64 %2)
+
+  ret <vscale x 1 x float> %a
+}
+
+declare <vscale x 1 x float> @llvm.riscv.vrgather.mask.nxv1f32.i32(
+  <vscale x 1 x float>,
+  <vscale x 1 x float>,
+  i32,
+  <vscale x 1 x i1>,
+  i64);
+
+define <vscale x 1 x float> @intrinsic_vrgather_mask_vx_nxv1f32_nxv1f32_i32(<vscale x 1 x float> %0, <vscale x 1 x float> %1, i32 %2, <vscale x 1 x i1> %3, i64 %4) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vx_nxv1f32_nxv1f32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a1, a1, e32,mf2,ta,mu
+; CHECK-NEXT:    vrgather.vx v16, v17, a0, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 1 x float> @llvm.riscv.vrgather.mask.nxv1f32.i32(
+    <vscale x 1 x float> %0,
+    <vscale x 1 x float> %1,
+    i32 %2,
+    <vscale x 1 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 1 x float> %a
+}
+
+declare <vscale x 2 x float> @llvm.riscv.vrgather.nxv2f32.i32(
+  <vscale x 2 x float>,
+  i32,
+  i64);
+
+define <vscale x 2 x float> @intrinsic_vrgather_vx_nxv2f32_nxv2f32_i32(<vscale x 2 x float> %0, i32 %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vx_nxv2f32_nxv2f32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a1, a1, e32,m1,ta,mu
+; CHECK-NEXT:    vrgather.vx v25, v16, a0
+; CHECK-NEXT:    vmv1r.v v16, v25
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 2 x float> @llvm.riscv.vrgather.nxv2f32.i32(
+    <vscale x 2 x float> %0,
+    i32 %1,
+    i64 %2)
+
+  ret <vscale x 2 x float> %a
+}
+
+declare <vscale x 2 x float> @llvm.riscv.vrgather.mask.nxv2f32.i32(
+  <vscale x 2 x float>,
+  <vscale x 2 x float>,
+  i32,
+  <vscale x 2 x i1>,
+  i64);
+
+define <vscale x 2 x float> @intrinsic_vrgather_mask_vx_nxv2f32_nxv2f32_i32(<vscale x 2 x float> %0, <vscale x 2 x float> %1, i32 %2, <vscale x 2 x i1> %3, i64 %4) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vx_nxv2f32_nxv2f32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a1, a1, e32,m1,ta,mu
+; CHECK-NEXT:    vrgather.vx v16, v17, a0, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 2 x float> @llvm.riscv.vrgather.mask.nxv2f32.i32(
+    <vscale x 2 x float> %0,
+    <vscale x 2 x float> %1,
+    i32 %2,
+    <vscale x 2 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 2 x float> %a
+}
+
+declare <vscale x 4 x float> @llvm.riscv.vrgather.nxv4f32.i32(
+  <vscale x 4 x float>,
+  i32,
+  i64);
+
+define <vscale x 4 x float> @intrinsic_vrgather_vx_nxv4f32_nxv4f32_i32(<vscale x 4 x float> %0, i32 %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vx_nxv4f32_nxv4f32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a1, a1, e32,m2,ta,mu
+; CHECK-NEXT:    vrgather.vx v26, v16, a0
+; CHECK-NEXT:    vmv2r.v v16, v26
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 4 x float> @llvm.riscv.vrgather.nxv4f32.i32(
+    <vscale x 4 x float> %0,
+    i32 %1,
+    i64 %2)
+
+  ret <vscale x 4 x float> %a
+}
+
+declare <vscale x 4 x float> @llvm.riscv.vrgather.mask.nxv4f32.i32(
+  <vscale x 4 x float>,
+  <vscale x 4 x float>,
+  i32,
+  <vscale x 4 x i1>,
+  i64);
+
+define <vscale x 4 x float> @intrinsic_vrgather_mask_vx_nxv4f32_nxv4f32_i32(<vscale x 4 x float> %0, <vscale x 4 x float> %1, i32 %2, <vscale x 4 x i1> %3, i64 %4) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vx_nxv4f32_nxv4f32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a1, a1, e32,m2,ta,mu
+; CHECK-NEXT:    vrgather.vx v16, v18, a0, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 4 x float> @llvm.riscv.vrgather.mask.nxv4f32.i32(
+    <vscale x 4 x float> %0,
+    <vscale x 4 x float> %1,
+    i32 %2,
+    <vscale x 4 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 4 x float> %a
+}
+
+declare <vscale x 8 x float> @llvm.riscv.vrgather.nxv8f32.i32(
+  <vscale x 8 x float>,
+  i32,
+  i64);
+
+define <vscale x 8 x float> @intrinsic_vrgather_vx_nxv8f32_nxv8f32_i32(<vscale x 8 x float> %0, i32 %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vx_nxv8f32_nxv8f32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a1, a1, e32,m4,ta,mu
+; CHECK-NEXT:    vrgather.vx v28, v16, a0
+; CHECK-NEXT:    vmv4r.v v16, v28
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 8 x float> @llvm.riscv.vrgather.nxv8f32.i32(
+    <vscale x 8 x float> %0,
+    i32 %1,
+    i64 %2)
+
+  ret <vscale x 8 x float> %a
+}
+
+declare <vscale x 8 x float> @llvm.riscv.vrgather.mask.nxv8f32.i32(
+  <vscale x 8 x float>,
+  <vscale x 8 x float>,
+  i32,
+  <vscale x 8 x i1>,
+  i64);
+
+define <vscale x 8 x float> @intrinsic_vrgather_mask_vx_nxv8f32_nxv8f32_i32(<vscale x 8 x float> %0, <vscale x 8 x float> %1, i32 %2, <vscale x 8 x i1> %3, i64 %4) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vx_nxv8f32_nxv8f32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a1, a1, e32,m4,ta,mu
+; CHECK-NEXT:    vrgather.vx v16, v20, a0, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 8 x float> @llvm.riscv.vrgather.mask.nxv8f32.i32(
+    <vscale x 8 x float> %0,
+    <vscale x 8 x float> %1,
+    i32 %2,
+    <vscale x 8 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 8 x float> %a
+}
+
+declare <vscale x 16 x float> @llvm.riscv.vrgather.nxv16f32.i32(
+  <vscale x 16 x float>,
+  i32,
+  i64);
+
+define <vscale x 16 x float> @intrinsic_vrgather_vx_nxv16f32_nxv16f32_i32(<vscale x 16 x float> %0, i32 %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vx_nxv16f32_nxv16f32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a1, a1, e32,m8,ta,mu
+; CHECK-NEXT:    vrgather.vx v8, v16, a0
+; CHECK-NEXT:    vmv8r.v v16, v8
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 16 x float> @llvm.riscv.vrgather.nxv16f32.i32(
+    <vscale x 16 x float> %0,
+    i32 %1,
+    i64 %2)
+
+  ret <vscale x 16 x float> %a
+}
+
+declare <vscale x 16 x float> @llvm.riscv.vrgather.mask.nxv16f32.i32(
+  <vscale x 16 x float>,
+  <vscale x 16 x float>,
+  i32,
+  <vscale x 16 x i1>,
+  i64);
+
+define <vscale x 16 x float> @intrinsic_vrgather_mask_vx_nxv16f32_nxv16f32_i32(<vscale x 16 x float> %0, <vscale x 16 x float> %1, i32 %2, <vscale x 16 x i1> %3, i64 %4) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vx_nxv16f32_nxv16f32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a3, zero, e32,m8,ta,mu
+; CHECK-NEXT:    vle32.v v8, (a0)
+; CHECK-NEXT:    vsetvli a0, a2, e32,m8,ta,mu
+; CHECK-NEXT:    vrgather.vx v16, v8, a1, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 16 x float> @llvm.riscv.vrgather.mask.nxv16f32.i32(
+    <vscale x 16 x float> %0,
+    <vscale x 16 x float> %1,
+    i32 %2,
+    <vscale x 16 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 16 x float> %a
+}
+
+declare <vscale x 1 x double> @llvm.riscv.vrgather.nxv1f64.i64(
+  <vscale x 1 x double>,
+  i64,
+  i64);
+
+define <vscale x 1 x double> @intrinsic_vrgather_vx_nxv1f64_nxv1f64_i64(<vscale x 1 x double> %0, i64 %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vx_nxv1f64_nxv1f64_i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a1, a1, e64,m1,ta,mu
+; CHECK-NEXT:    vrgather.vx v25, v16, a0
+; CHECK-NEXT:    vmv1r.v v16, v25
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 1 x double> @llvm.riscv.vrgather.nxv1f64.i64(
+    <vscale x 1 x double> %0,
+    i64 %1,
+    i64 %2)
+
+  ret <vscale x 1 x double> %a
+}
+
+declare <vscale x 1 x double> @llvm.riscv.vrgather.mask.nxv1f64.i64(
+  <vscale x 1 x double>,
+  <vscale x 1 x double>,
+  i64,
+  <vscale x 1 x i1>,
+  i64);
+
+define <vscale x 1 x double> @intrinsic_vrgather_mask_vx_nxv1f64_nxv1f64_i64(<vscale x 1 x double> %0, <vscale x 1 x double> %1, i64 %2, <vscale x 1 x i1> %3, i64 %4) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vx_nxv1f64_nxv1f64_i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a1, a1, e64,m1,ta,mu
+; CHECK-NEXT:    vrgather.vx v16, v17, a0, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 1 x double> @llvm.riscv.vrgather.mask.nxv1f64.i64(
+    <vscale x 1 x double> %0,
+    <vscale x 1 x double> %1,
+    i64 %2,
+    <vscale x 1 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 1 x double> %a
+}
+
+declare <vscale x 2 x double> @llvm.riscv.vrgather.nxv2f64.i64(
+  <vscale x 2 x double>,
+  i64,
+  i64);
+
+define <vscale x 2 x double> @intrinsic_vrgather_vx_nxv2f64_nxv2f64_i64(<vscale x 2 x double> %0, i64 %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vx_nxv2f64_nxv2f64_i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a1, a1, e64,m2,ta,mu
+; CHECK-NEXT:    vrgather.vx v26, v16, a0
+; CHECK-NEXT:    vmv2r.v v16, v26
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 2 x double> @llvm.riscv.vrgather.nxv2f64.i64(
+    <vscale x 2 x double> %0,
+    i64 %1,
+    i64 %2)
+
+  ret <vscale x 2 x double> %a
+}
+
+declare <vscale x 2 x double> @llvm.riscv.vrgather.mask.nxv2f64.i64(
+  <vscale x 2 x double>,
+  <vscale x 2 x double>,
+  i64,
+  <vscale x 2 x i1>,
+  i64);
+
+define <vscale x 2 x double> @intrinsic_vrgather_mask_vx_nxv2f64_nxv2f64_i64(<vscale x 2 x double> %0, <vscale x 2 x double> %1, i64 %2, <vscale x 2 x i1> %3, i64 %4) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vx_nxv2f64_nxv2f64_i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a1, a1, e64,m2,ta,mu
+; CHECK-NEXT:    vrgather.vx v16, v18, a0, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 2 x double> @llvm.riscv.vrgather.mask.nxv2f64.i64(
+    <vscale x 2 x double> %0,
+    <vscale x 2 x double> %1,
+    i64 %2,
+    <vscale x 2 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 2 x double> %a
+}
+
+declare <vscale x 4 x double> @llvm.riscv.vrgather.nxv4f64.i64(
+  <vscale x 4 x double>,
+  i64,
+  i64);
+
+define <vscale x 4 x double> @intrinsic_vrgather_vx_nxv4f64_nxv4f64_i64(<vscale x 4 x double> %0, i64 %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vx_nxv4f64_nxv4f64_i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a1, a1, e64,m4,ta,mu
+; CHECK-NEXT:    vrgather.vx v28, v16, a0
+; CHECK-NEXT:    vmv4r.v v16, v28
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 4 x double> @llvm.riscv.vrgather.nxv4f64.i64(
+    <vscale x 4 x double> %0,
+    i64 %1,
+    i64 %2)
+
+  ret <vscale x 4 x double> %a
+}
+
+declare <vscale x 4 x double> @llvm.riscv.vrgather.mask.nxv4f64.i64(
+  <vscale x 4 x double>,
+  <vscale x 4 x double>,
+  i64,
+  <vscale x 4 x i1>,
+  i64);
+
+define <vscale x 4 x double> @intrinsic_vrgather_mask_vx_nxv4f64_nxv4f64_i64(<vscale x 4 x double> %0, <vscale x 4 x double> %1, i64 %2, <vscale x 4 x i1> %3, i64 %4) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vx_nxv4f64_nxv4f64_i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a1, a1, e64,m4,ta,mu
+; CHECK-NEXT:    vrgather.vx v16, v20, a0, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 4 x double> @llvm.riscv.vrgather.mask.nxv4f64.i64(
+    <vscale x 4 x double> %0,
+    <vscale x 4 x double> %1,
+    i64 %2,
+    <vscale x 4 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 4 x double> %a
+}
+
+declare <vscale x 8 x double> @llvm.riscv.vrgather.nxv8f64.i64(
+  <vscale x 8 x double>,
+  i64,
+  i64);
+
+define <vscale x 8 x double> @intrinsic_vrgather_vx_nxv8f64_nxv8f64_i64(<vscale x 8 x double> %0, i64 %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vx_nxv8f64_nxv8f64_i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a1, a1, e64,m8,ta,mu
+; CHECK-NEXT:    vrgather.vx v8, v16, a0
+; CHECK-NEXT:    vmv8r.v v16, v8
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 8 x double> @llvm.riscv.vrgather.nxv8f64.i64(
+    <vscale x 8 x double> %0,
+    i64 %1,
+    i64 %2)
+
+  ret <vscale x 8 x double> %a
+}
+
+declare <vscale x 8 x double> @llvm.riscv.vrgather.mask.nxv8f64.i64(
+  <vscale x 8 x double>,
+  <vscale x 8 x double>,
+  i64,
+  <vscale x 8 x i1>,
+  i64);
+
+define <vscale x 8 x double> @intrinsic_vrgather_mask_vx_nxv8f64_nxv8f64_i64(<vscale x 8 x double> %0, <vscale x 8 x double> %1, i64 %2, <vscale x 8 x i1> %3, i64 %4) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vx_nxv8f64_nxv8f64_i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a3, zero, e64,m8,ta,mu
+; CHECK-NEXT:    vle64.v v8, (a0)
+; CHECK-NEXT:    vsetvli a0, a2, e64,m8,ta,mu
+; CHECK-NEXT:    vrgather.vx v16, v8, a1, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 8 x double> @llvm.riscv.vrgather.mask.nxv8f64.i64(
+    <vscale x 8 x double> %0,
+    <vscale x 8 x double> %1,
+    i64 %2,
+    <vscale x 8 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 8 x double> %a
+}
+
+define <vscale x 1 x i8> @intrinsic_vrgather_vi_nxv1i8_nxv1i8_i8(<vscale x 1 x i8> %0, i64 %1) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vi_nxv1i8_nxv1i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e8,mf8,ta,mu
+; CHECK-NEXT:    vrgather.vi v25, v16, 9
+; CHECK-NEXT:    vmv1r.v v16, v25
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 1 x i8> @llvm.riscv.vrgather.nxv1i8.i8(
+    <vscale x 1 x i8> %0,
+    i8 9,
+    i64 %1)
+
+  ret <vscale x 1 x i8> %a
+}
+
+define <vscale x 1 x i8> @intrinsic_vrgather_mask_vi_nxv1i8_nxv1i8_i8(<vscale x 1 x i8> %0, <vscale x 1 x i8> %1, <vscale x 1 x i1> %2, i64 %3) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vi_nxv1i8_nxv1i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e8,mf8,ta,mu
+; CHECK-NEXT:    vrgather.vi v16, v17, 9, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 1 x i8> @llvm.riscv.vrgather.mask.nxv1i8.i8(
+    <vscale x 1 x i8> %0,
+    <vscale x 1 x i8> %1,
+    i8 9,
+    <vscale x 1 x i1> %2,
+    i64 %3)
+
+  ret <vscale x 1 x i8> %a
+}
+
+define <vscale x 2 x i8> @intrinsic_vrgather_vi_nxv2i8_nxv2i8_i8(<vscale x 2 x i8> %0, i64 %1) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vi_nxv2i8_nxv2i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e8,mf4,ta,mu
+; CHECK-NEXT:    vrgather.vi v25, v16, 9
+; CHECK-NEXT:    vmv1r.v v16, v25
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 2 x i8> @llvm.riscv.vrgather.nxv2i8.i8(
+    <vscale x 2 x i8> %0,
+    i8 9,
+    i64 %1)
+
+  ret <vscale x 2 x i8> %a
+}
+
+define <vscale x 2 x i8> @intrinsic_vrgather_mask_vi_nxv2i8_nxv2i8_i8(<vscale x 2 x i8> %0, <vscale x 2 x i8> %1, <vscale x 2 x i1> %2, i64 %3) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vi_nxv2i8_nxv2i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e8,mf4,ta,mu
+; CHECK-NEXT:    vrgather.vi v16, v17, 9, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 2 x i8> @llvm.riscv.vrgather.mask.nxv2i8.i8(
+    <vscale x 2 x i8> %0,
+    <vscale x 2 x i8> %1,
+    i8 9,
+    <vscale x 2 x i1> %2,
+    i64 %3)
+
+  ret <vscale x 2 x i8> %a
+}
+
+define <vscale x 4 x i8> @intrinsic_vrgather_vi_nxv4i8_nxv4i8_i8(<vscale x 4 x i8> %0, i64 %1) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vi_nxv4i8_nxv4i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e8,mf2,ta,mu
+; CHECK-NEXT:    vrgather.vi v25, v16, 9
+; CHECK-NEXT:    vmv1r.v v16, v25
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 4 x i8> @llvm.riscv.vrgather.nxv4i8.i8(
+    <vscale x 4 x i8> %0,
+    i8 9,
+    i64 %1)
+
+  ret <vscale x 4 x i8> %a
+}
+
+define <vscale x 4 x i8> @intrinsic_vrgather_mask_vi_nxv4i8_nxv4i8_i8(<vscale x 4 x i8> %0, <vscale x 4 x i8> %1, <vscale x 4 x i1> %2, i64 %3) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vi_nxv4i8_nxv4i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e8,mf2,ta,mu
+; CHECK-NEXT:    vrgather.vi v16, v17, 9, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 4 x i8> @llvm.riscv.vrgather.mask.nxv4i8.i8(
+    <vscale x 4 x i8> %0,
+    <vscale x 4 x i8> %1,
+    i8 9,
+    <vscale x 4 x i1> %2,
+    i64 %3)
+
+  ret <vscale x 4 x i8> %a
+}
+
+define <vscale x 8 x i8> @intrinsic_vrgather_vi_nxv8i8_nxv8i8_i8(<vscale x 8 x i8> %0, i64 %1) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vi_nxv8i8_nxv8i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e8,m1,ta,mu
+; CHECK-NEXT:    vrgather.vi v25, v16, 9
+; CHECK-NEXT:    vmv1r.v v16, v25
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 8 x i8> @llvm.riscv.vrgather.nxv8i8.i8(
+    <vscale x 8 x i8> %0,
+    i8 9,
+    i64 %1)
+
+  ret <vscale x 8 x i8> %a
+}
+
+define <vscale x 8 x i8> @intrinsic_vrgather_mask_vi_nxv8i8_nxv8i8_i8(<vscale x 8 x i8> %0, <vscale x 8 x i8> %1, <vscale x 8 x i1> %2, i64 %3) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vi_nxv8i8_nxv8i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e8,m1,ta,mu
+; CHECK-NEXT:    vrgather.vi v16, v17, 9, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 8 x i8> @llvm.riscv.vrgather.mask.nxv8i8.i8(
+    <vscale x 8 x i8> %0,
+    <vscale x 8 x i8> %1,
+    i8 9,
+    <vscale x 8 x i1> %2,
+    i64 %3)
+
+  ret <vscale x 8 x i8> %a
+}
+
+define <vscale x 16 x i8> @intrinsic_vrgather_vi_nxv16i8_nxv16i8_i8(<vscale x 16 x i8> %0, i64 %1) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vi_nxv16i8_nxv16i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e8,m2,ta,mu
+; CHECK-NEXT:    vrgather.vi v26, v16, 9
+; CHECK-NEXT:    vmv2r.v v16, v26
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 16 x i8> @llvm.riscv.vrgather.nxv16i8.i8(
+    <vscale x 16 x i8> %0,
+    i8 9,
+    i64 %1)
+
+  ret <vscale x 16 x i8> %a
+}
+
+define <vscale x 16 x i8> @intrinsic_vrgather_mask_vi_nxv16i8_nxv16i8_i8(<vscale x 16 x i8> %0, <vscale x 16 x i8> %1, <vscale x 16 x i1> %2, i64 %3) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vi_nxv16i8_nxv16i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e8,m2,ta,mu
+; CHECK-NEXT:    vrgather.vi v16, v18, 9, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 16 x i8> @llvm.riscv.vrgather.mask.nxv16i8.i8(
+    <vscale x 16 x i8> %0,
+    <vscale x 16 x i8> %1,
+    i8 9,
+    <vscale x 16 x i1> %2,
+    i64 %3)
+
+  ret <vscale x 16 x i8> %a
+}
+
+define <vscale x 32 x i8> @intrinsic_vrgather_vi_nxv32i8_nxv32i8_i8(<vscale x 32 x i8> %0, i64 %1) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vi_nxv32i8_nxv32i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e8,m4,ta,mu
+; CHECK-NEXT:    vrgather.vi v28, v16, 9
+; CHECK-NEXT:    vmv4r.v v16, v28
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 32 x i8> @llvm.riscv.vrgather.nxv32i8.i8(
+    <vscale x 32 x i8> %0,
+    i8 9,
+    i64 %1)
+
+  ret <vscale x 32 x i8> %a
+}
+
+define <vscale x 32 x i8> @intrinsic_vrgather_mask_vi_nxv32i8_nxv32i8_i8(<vscale x 32 x i8> %0, <vscale x 32 x i8> %1, <vscale x 32 x i1> %2, i64 %3) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vi_nxv32i8_nxv32i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e8,m4,ta,mu
+; CHECK-NEXT:    vrgather.vi v16, v20, 9, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 32 x i8> @llvm.riscv.vrgather.mask.nxv32i8.i8(
+    <vscale x 32 x i8> %0,
+    <vscale x 32 x i8> %1,
+    i8 9,
+    <vscale x 32 x i1> %2,
+    i64 %3)
+
+  ret <vscale x 32 x i8> %a
+}
+
+define <vscale x 64 x i8> @intrinsic_vrgather_vi_nxv64i8_nxv64i8_i8(<vscale x 64 x i8> %0, i64 %1) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vi_nxv64i8_nxv64i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e8,m8,ta,mu
+; CHECK-NEXT:    vrgather.vi v8, v16, 9
+; CHECK-NEXT:    vmv8r.v v16, v8
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 64 x i8> @llvm.riscv.vrgather.nxv64i8.i8(
+    <vscale x 64 x i8> %0,
+    i8 9,
+    i64 %1)
+
+  ret <vscale x 64 x i8> %a
+}
+
+define <vscale x 64 x i8> @intrinsic_vrgather_mask_vi_nxv64i8_nxv64i8_i8(<vscale x 64 x i8> %0, <vscale x 64 x i8> %1, <vscale x 64 x i1> %2, i64 %3) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vi_nxv64i8_nxv64i8_i8:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a2, zero, e8,m8,ta,mu
+; CHECK-NEXT:    vle8.v v8, (a0)
+; CHECK-NEXT:    vsetvli a0, a1, e8,m8,ta,mu
+; CHECK-NEXT:    vrgather.vi v16, v8, 9, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 64 x i8> @llvm.riscv.vrgather.mask.nxv64i8.i8(
+    <vscale x 64 x i8> %0,
+    <vscale x 64 x i8> %1,
+    i8 9,
+    <vscale x 64 x i1> %2,
+    i64 %3)
+
+  ret <vscale x 64 x i8> %a
+}
+
+define <vscale x 1 x i16> @intrinsic_vrgather_vi_nxv1i16_nxv1i16_i16(<vscale x 1 x i16> %0, i64 %1) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vi_nxv1i16_nxv1i16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e16,mf4,ta,mu
+; CHECK-NEXT:    vrgather.vi v25, v16, 9
+; CHECK-NEXT:    vmv1r.v v16, v25
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 1 x i16> @llvm.riscv.vrgather.nxv1i16.i16(
+    <vscale x 1 x i16> %0,
+    i16 9,
+    i64 %1)
+
+  ret <vscale x 1 x i16> %a
+}
+
+define <vscale x 1 x i16> @intrinsic_vrgather_mask_vi_nxv1i16_nxv1i16_i16(<vscale x 1 x i16> %0, <vscale x 1 x i16> %1, <vscale x 1 x i1> %2, i64 %3) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vi_nxv1i16_nxv1i16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e16,mf4,ta,mu
+; CHECK-NEXT:    vrgather.vi v16, v17, 9, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 1 x i16> @llvm.riscv.vrgather.mask.nxv1i16.i16(
+    <vscale x 1 x i16> %0,
+    <vscale x 1 x i16> %1,
+    i16 9,
+    <vscale x 1 x i1> %2,
+    i64 %3)
+
+  ret <vscale x 1 x i16> %a
+}
+
+define <vscale x 2 x i16> @intrinsic_vrgather_vi_nxv2i16_nxv2i16_i16(<vscale x 2 x i16> %0, i64 %1) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vi_nxv2i16_nxv2i16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e16,mf2,ta,mu
+; CHECK-NEXT:    vrgather.vi v25, v16, 9
+; CHECK-NEXT:    vmv1r.v v16, v25
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 2 x i16> @llvm.riscv.vrgather.nxv2i16.i16(
+    <vscale x 2 x i16> %0,
+    i16 9,
+    i64 %1)
+
+  ret <vscale x 2 x i16> %a
+}
+
+define <vscale x 2 x i16> @intrinsic_vrgather_mask_vi_nxv2i16_nxv2i16_i16(<vscale x 2 x i16> %0, <vscale x 2 x i16> %1, <vscale x 2 x i1> %2, i64 %3) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vi_nxv2i16_nxv2i16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e16,mf2,ta,mu
+; CHECK-NEXT:    vrgather.vi v16, v17, 9, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 2 x i16> @llvm.riscv.vrgather.mask.nxv2i16.i16(
+    <vscale x 2 x i16> %0,
+    <vscale x 2 x i16> %1,
+    i16 9,
+    <vscale x 2 x i1> %2,
+    i64 %3)
+
+  ret <vscale x 2 x i16> %a
+}
+
+define <vscale x 4 x i16> @intrinsic_vrgather_vi_nxv4i16_nxv4i16_i16(<vscale x 4 x i16> %0, i64 %1) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vi_nxv4i16_nxv4i16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e16,m1,ta,mu
+; CHECK-NEXT:    vrgather.vi v25, v16, 9
+; CHECK-NEXT:    vmv1r.v v16, v25
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 4 x i16> @llvm.riscv.vrgather.nxv4i16.i16(
+    <vscale x 4 x i16> %0,
+    i16 9,
+    i64 %1)
+
+  ret <vscale x 4 x i16> %a
+}
+
+define <vscale x 4 x i16> @intrinsic_vrgather_mask_vi_nxv4i16_nxv4i16_i16(<vscale x 4 x i16> %0, <vscale x 4 x i16> %1, <vscale x 4 x i1> %2, i64 %3) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vi_nxv4i16_nxv4i16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e16,m1,ta,mu
+; CHECK-NEXT:    vrgather.vi v16, v17, 9, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 4 x i16> @llvm.riscv.vrgather.mask.nxv4i16.i16(
+    <vscale x 4 x i16> %0,
+    <vscale x 4 x i16> %1,
+    i16 9,
+    <vscale x 4 x i1> %2,
+    i64 %3)
+
+  ret <vscale x 4 x i16> %a
+}
+
+define <vscale x 8 x i16> @intrinsic_vrgather_vi_nxv8i16_nxv8i16_i16(<vscale x 8 x i16> %0, i64 %1) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vi_nxv8i16_nxv8i16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e16,m2,ta,mu
+; CHECK-NEXT:    vrgather.vi v26, v16, 9
+; CHECK-NEXT:    vmv2r.v v16, v26
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 8 x i16> @llvm.riscv.vrgather.nxv8i16.i16(
+    <vscale x 8 x i16> %0,
+    i16 9,
+    i64 %1)
+
+  ret <vscale x 8 x i16> %a
+}
+
+define <vscale x 8 x i16> @intrinsic_vrgather_mask_vi_nxv8i16_nxv8i16_i16(<vscale x 8 x i16> %0, <vscale x 8 x i16> %1, <vscale x 8 x i1> %2, i64 %3) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vi_nxv8i16_nxv8i16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e16,m2,ta,mu
+; CHECK-NEXT:    vrgather.vi v16, v18, 9, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 8 x i16> @llvm.riscv.vrgather.mask.nxv8i16.i16(
+    <vscale x 8 x i16> %0,
+    <vscale x 8 x i16> %1,
+    i16 9,
+    <vscale x 8 x i1> %2,
+    i64 %3)
+
+  ret <vscale x 8 x i16> %a
+}
+
+define <vscale x 16 x i16> @intrinsic_vrgather_vi_nxv16i16_nxv16i16_i16(<vscale x 16 x i16> %0, i64 %1) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vi_nxv16i16_nxv16i16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e16,m4,ta,mu
+; CHECK-NEXT:    vrgather.vi v28, v16, 9
+; CHECK-NEXT:    vmv4r.v v16, v28
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 16 x i16> @llvm.riscv.vrgather.nxv16i16.i16(
+    <vscale x 16 x i16> %0,
+    i16 9,
+    i64 %1)
+
+  ret <vscale x 16 x i16> %a
+}
+
+define <vscale x 16 x i16> @intrinsic_vrgather_mask_vi_nxv16i16_nxv16i16_i16(<vscale x 16 x i16> %0, <vscale x 16 x i16> %1, <vscale x 16 x i1> %2, i64 %3) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vi_nxv16i16_nxv16i16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e16,m4,ta,mu
+; CHECK-NEXT:    vrgather.vi v16, v20, 9, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 16 x i16> @llvm.riscv.vrgather.mask.nxv16i16.i16(
+    <vscale x 16 x i16> %0,
+    <vscale x 16 x i16> %1,
+    i16 9,
+    <vscale x 16 x i1> %2,
+    i64 %3)
+
+  ret <vscale x 16 x i16> %a
+}
+
+define <vscale x 32 x i16> @intrinsic_vrgather_vi_nxv32i16_nxv32i16_i16(<vscale x 32 x i16> %0, i64 %1) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vi_nxv32i16_nxv32i16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e16,m8,ta,mu
+; CHECK-NEXT:    vrgather.vi v8, v16, 9
+; CHECK-NEXT:    vmv8r.v v16, v8
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 32 x i16> @llvm.riscv.vrgather.nxv32i16.i16(
+    <vscale x 32 x i16> %0,
+    i16 9,
+    i64 %1)
+
+  ret <vscale x 32 x i16> %a
+}
+
+define <vscale x 32 x i16> @intrinsic_vrgather_mask_vi_nxv32i16_nxv32i16_i16(<vscale x 32 x i16> %0, <vscale x 32 x i16> %1, <vscale x 32 x i1> %2, i64 %3) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vi_nxv32i16_nxv32i16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a2, zero, e16,m8,ta,mu
+; CHECK-NEXT:    vle16.v v8, (a0)
+; CHECK-NEXT:    vsetvli a0, a1, e16,m8,ta,mu
+; CHECK-NEXT:    vrgather.vi v16, v8, 9, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 32 x i16> @llvm.riscv.vrgather.mask.nxv32i16.i16(
+    <vscale x 32 x i16> %0,
+    <vscale x 32 x i16> %1,
+    i16 9,
+    <vscale x 32 x i1> %2,
+    i64 %3)
+
+  ret <vscale x 32 x i16> %a
+}
+
+define <vscale x 1 x i32> @intrinsic_vrgather_vi_nxv1i32_nxv1i32_i32(<vscale x 1 x i32> %0, i64 %1) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vi_nxv1i32_nxv1i32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e32,mf2,ta,mu
+; CHECK-NEXT:    vrgather.vi v25, v16, 9
+; CHECK-NEXT:    vmv1r.v v16, v25
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 1 x i32> @llvm.riscv.vrgather.nxv1i32.i32(
+    <vscale x 1 x i32> %0,
+    i32 9,
+    i64 %1)
+
+  ret <vscale x 1 x i32> %a
+}
+
+define <vscale x 1 x i32> @intrinsic_vrgather_mask_vi_nxv1i32_nxv1i32_i32(<vscale x 1 x i32> %0, <vscale x 1 x i32> %1, <vscale x 1 x i1> %2, i64 %3) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vi_nxv1i32_nxv1i32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e32,mf2,ta,mu
+; CHECK-NEXT:    vrgather.vi v16, v17, 9, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 1 x i32> @llvm.riscv.vrgather.mask.nxv1i32.i32(
+    <vscale x 1 x i32> %0,
+    <vscale x 1 x i32> %1,
+    i32 9,
+    <vscale x 1 x i1> %2,
+    i64 %3)
+
+  ret <vscale x 1 x i32> %a
+}
+
+define <vscale x 2 x i32> @intrinsic_vrgather_vi_nxv2i32_nxv2i32_i32(<vscale x 2 x i32> %0, i64 %1) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vi_nxv2i32_nxv2i32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e32,m1,ta,mu
+; CHECK-NEXT:    vrgather.vi v25, v16, 9
+; CHECK-NEXT:    vmv1r.v v16, v25
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 2 x i32> @llvm.riscv.vrgather.nxv2i32.i32(
+    <vscale x 2 x i32> %0,
+    i32 9,
+    i64 %1)
+
+  ret <vscale x 2 x i32> %a
+}
+
+define <vscale x 2 x i32> @intrinsic_vrgather_mask_vi_nxv2i32_nxv2i32_i32(<vscale x 2 x i32> %0, <vscale x 2 x i32> %1, <vscale x 2 x i1> %2, i64 %3) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vi_nxv2i32_nxv2i32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e32,m1,ta,mu
+; CHECK-NEXT:    vrgather.vi v16, v17, 9, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 2 x i32> @llvm.riscv.vrgather.mask.nxv2i32.i32(
+    <vscale x 2 x i32> %0,
+    <vscale x 2 x i32> %1,
+    i32 9,
+    <vscale x 2 x i1> %2,
+    i64 %3)
+
+  ret <vscale x 2 x i32> %a
+}
+
+define <vscale x 4 x i32> @intrinsic_vrgather_vi_nxv4i32_nxv4i32_i32(<vscale x 4 x i32> %0, i64 %1) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vi_nxv4i32_nxv4i32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e32,m2,ta,mu
+; CHECK-NEXT:    vrgather.vi v26, v16, 9
+; CHECK-NEXT:    vmv2r.v v16, v26
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 4 x i32> @llvm.riscv.vrgather.nxv4i32.i32(
+    <vscale x 4 x i32> %0,
+    i32 9,
+    i64 %1)
+
+  ret <vscale x 4 x i32> %a
+}
+
+define <vscale x 4 x i32> @intrinsic_vrgather_mask_vi_nxv4i32_nxv4i32_i32(<vscale x 4 x i32> %0, <vscale x 4 x i32> %1, <vscale x 4 x i1> %2, i64 %3) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vi_nxv4i32_nxv4i32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e32,m2,ta,mu
+; CHECK-NEXT:    vrgather.vi v16, v18, 9, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 4 x i32> @llvm.riscv.vrgather.mask.nxv4i32.i32(
+    <vscale x 4 x i32> %0,
+    <vscale x 4 x i32> %1,
+    i32 9,
+    <vscale x 4 x i1> %2,
+    i64 %3)
+
+  ret <vscale x 4 x i32> %a
+}
+
+define <vscale x 8 x i32> @intrinsic_vrgather_vi_nxv8i32_nxv8i32_i32(<vscale x 8 x i32> %0, i64 %1) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vi_nxv8i32_nxv8i32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e32,m4,ta,mu
+; CHECK-NEXT:    vrgather.vi v28, v16, 9
+; CHECK-NEXT:    vmv4r.v v16, v28
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 8 x i32> @llvm.riscv.vrgather.nxv8i32.i32(
+    <vscale x 8 x i32> %0,
+    i32 9,
+    i64 %1)
+
+  ret <vscale x 8 x i32> %a
+}
+
+define <vscale x 8 x i32> @intrinsic_vrgather_mask_vi_nxv8i32_nxv8i32_i32(<vscale x 8 x i32> %0, <vscale x 8 x i32> %1, <vscale x 8 x i1> %2, i64 %3) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vi_nxv8i32_nxv8i32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e32,m4,ta,mu
+; CHECK-NEXT:    vrgather.vi v16, v20, 9, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 8 x i32> @llvm.riscv.vrgather.mask.nxv8i32.i32(
+    <vscale x 8 x i32> %0,
+    <vscale x 8 x i32> %1,
+    i32 9,
+    <vscale x 8 x i1> %2,
+    i64 %3)
+
+  ret <vscale x 8 x i32> %a
+}
+
+define <vscale x 16 x i32> @intrinsic_vrgather_vi_nxv16i32_nxv16i32_i32(<vscale x 16 x i32> %0, i64 %1) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vi_nxv16i32_nxv16i32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e32,m8,ta,mu
+; CHECK-NEXT:    vrgather.vi v8, v16, 9
+; CHECK-NEXT:    vmv8r.v v16, v8
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 16 x i32> @llvm.riscv.vrgather.nxv16i32.i32(
+    <vscale x 16 x i32> %0,
+    i32 9,
+    i64 %1)
+
+  ret <vscale x 16 x i32> %a
+}
+
+define <vscale x 16 x i32> @intrinsic_vrgather_mask_vi_nxv16i32_nxv16i32_i32(<vscale x 16 x i32> %0, <vscale x 16 x i32> %1, <vscale x 16 x i1> %2, i64 %3) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vi_nxv16i32_nxv16i32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a2, zero, e32,m8,ta,mu
+; CHECK-NEXT:    vle32.v v8, (a0)
+; CHECK-NEXT:    vsetvli a0, a1, e32,m8,ta,mu
+; CHECK-NEXT:    vrgather.vi v16, v8, 9, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 16 x i32> @llvm.riscv.vrgather.mask.nxv16i32.i32(
+    <vscale x 16 x i32> %0,
+    <vscale x 16 x i32> %1,
+    i32 9,
+    <vscale x 16 x i1> %2,
+    i64 %3)
+
+  ret <vscale x 16 x i32> %a
+}
+
+define <vscale x 1 x i64> @intrinsic_vrgather_vi_nxv1i64_nxv1i64_i64(<vscale x 1 x i64> %0, i64 %1) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vi_nxv1i64_nxv1i64_i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e64,m1,ta,mu
+; CHECK-NEXT:    vrgather.vi v25, v16, 9
+; CHECK-NEXT:    vmv1r.v v16, v25
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 1 x i64> @llvm.riscv.vrgather.nxv1i64.i64(
+    <vscale x 1 x i64> %0,
+    i64 9,
+    i64 %1)
+
+  ret <vscale x 1 x i64> %a
+}
+
+define <vscale x 1 x i64> @intrinsic_vrgather_mask_vi_nxv1i64_nxv1i64_i64(<vscale x 1 x i64> %0, <vscale x 1 x i64> %1, <vscale x 1 x i1> %2, i64 %3) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vi_nxv1i64_nxv1i64_i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e64,m1,ta,mu
+; CHECK-NEXT:    vrgather.vi v16, v17, 9, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 1 x i64> @llvm.riscv.vrgather.mask.nxv1i64.i64(
+    <vscale x 1 x i64> %0,
+    <vscale x 1 x i64> %1,
+    i64 9,
+    <vscale x 1 x i1> %2,
+    i64 %3)
+
+  ret <vscale x 1 x i64> %a
+}
+
+define <vscale x 2 x i64> @intrinsic_vrgather_vi_nxv2i64_nxv2i64_i64(<vscale x 2 x i64> %0, i64 %1) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vi_nxv2i64_nxv2i64_i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e64,m2,ta,mu
+; CHECK-NEXT:    vrgather.vi v26, v16, 9
+; CHECK-NEXT:    vmv2r.v v16, v26
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 2 x i64> @llvm.riscv.vrgather.nxv2i64.i64(
+    <vscale x 2 x i64> %0,
+    i64 9,
+    i64 %1)
+
+  ret <vscale x 2 x i64> %a
+}
+
+define <vscale x 2 x i64> @intrinsic_vrgather_mask_vi_nxv2i64_nxv2i64_i64(<vscale x 2 x i64> %0, <vscale x 2 x i64> %1, <vscale x 2 x i1> %2, i64 %3) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vi_nxv2i64_nxv2i64_i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e64,m2,ta,mu
+; CHECK-NEXT:    vrgather.vi v16, v18, 9, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 2 x i64> @llvm.riscv.vrgather.mask.nxv2i64.i64(
+    <vscale x 2 x i64> %0,
+    <vscale x 2 x i64> %1,
+    i64 9,
+    <vscale x 2 x i1> %2,
+    i64 %3)
+
+  ret <vscale x 2 x i64> %a
+}
+
+define <vscale x 4 x i64> @intrinsic_vrgather_vi_nxv4i64_nxv4i64_i64(<vscale x 4 x i64> %0, i64 %1) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vi_nxv4i64_nxv4i64_i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e64,m4,ta,mu
+; CHECK-NEXT:    vrgather.vi v28, v16, 9
+; CHECK-NEXT:    vmv4r.v v16, v28
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 4 x i64> @llvm.riscv.vrgather.nxv4i64.i64(
+    <vscale x 4 x i64> %0,
+    i64 9,
+    i64 %1)
+
+  ret <vscale x 4 x i64> %a
+}
+
+define <vscale x 4 x i64> @intrinsic_vrgather_mask_vi_nxv4i64_nxv4i64_i64(<vscale x 4 x i64> %0, <vscale x 4 x i64> %1, <vscale x 4 x i1> %2, i64 %3) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vi_nxv4i64_nxv4i64_i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e64,m4,ta,mu
+; CHECK-NEXT:    vrgather.vi v16, v20, 9, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 4 x i64> @llvm.riscv.vrgather.mask.nxv4i64.i64(
+    <vscale x 4 x i64> %0,
+    <vscale x 4 x i64> %1,
+    i64 9,
+    <vscale x 4 x i1> %2,
+    i64 %3)
+
+  ret <vscale x 4 x i64> %a
+}
+
+define <vscale x 8 x i64> @intrinsic_vrgather_vi_nxv8i64_nxv8i64_i64(<vscale x 8 x i64> %0, i64 %1) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vi_nxv8i64_nxv8i64_i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e64,m8,ta,mu
+; CHECK-NEXT:    vrgather.vi v8, v16, 9
+; CHECK-NEXT:    vmv8r.v v16, v8
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 8 x i64> @llvm.riscv.vrgather.nxv8i64.i64(
+    <vscale x 8 x i64> %0,
+    i64 9,
+    i64 %1)
+
+  ret <vscale x 8 x i64> %a
+}
+
+define <vscale x 8 x i64> @intrinsic_vrgather_mask_vi_nxv8i64_nxv8i64_i64(<vscale x 8 x i64> %0, <vscale x 8 x i64> %1, <vscale x 8 x i1> %2, i64 %3) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vi_nxv8i64_nxv8i64_i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a2, zero, e64,m8,ta,mu
+; CHECK-NEXT:    vle64.v v8, (a0)
+; CHECK-NEXT:    vsetvli a0, a1, e64,m8,ta,mu
+; CHECK-NEXT:    vrgather.vi v16, v8, 9, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 8 x i64> @llvm.riscv.vrgather.mask.nxv8i64.i64(
+    <vscale x 8 x i64> %0,
+    <vscale x 8 x i64> %1,
+    i64 9,
+    <vscale x 8 x i1> %2,
+    i64 %3)
+
+  ret <vscale x 8 x i64> %a
+}
+
+define <vscale x 1 x half> @intrinsic_vrgather_vi_nxv1f16_nxv1f16_i16(<vscale x 1 x half> %0, i64 %1) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vi_nxv1f16_nxv1f16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e16,mf4,ta,mu
+; CHECK-NEXT:    vrgather.vi v25, v16, 9
+; CHECK-NEXT:    vmv1r.v v16, v25
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 1 x half> @llvm.riscv.vrgather.nxv1f16.i16(
+    <vscale x 1 x half> %0,
+    i16 9,
+    i64 %1)
+
+  ret <vscale x 1 x half> %a
+}
+
+define <vscale x 1 x half> @intrinsic_vrgather_mask_vi_nxv1f16_nxv1f16_i16(<vscale x 1 x half> %0, <vscale x 1 x half> %1, <vscale x 1 x i1> %2, i64 %3) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vi_nxv1f16_nxv1f16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e16,mf4,ta,mu
+; CHECK-NEXT:    vrgather.vi v16, v17, 9, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 1 x half> @llvm.riscv.vrgather.mask.nxv1f16.i16(
+    <vscale x 1 x half> %0,
+    <vscale x 1 x half> %1,
+    i16 9,
+    <vscale x 1 x i1> %2,
+    i64 %3)
+
+  ret <vscale x 1 x half> %a
+}
+
+define <vscale x 2 x half> @intrinsic_vrgather_vi_nxv2f16_nxv2f16_i16(<vscale x 2 x half> %0, i64 %1) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vi_nxv2f16_nxv2f16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e16,mf2,ta,mu
+; CHECK-NEXT:    vrgather.vi v25, v16, 9
+; CHECK-NEXT:    vmv1r.v v16, v25
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 2 x half> @llvm.riscv.vrgather.nxv2f16.i16(
+    <vscale x 2 x half> %0,
+    i16 9,
+    i64 %1)
+
+  ret <vscale x 2 x half> %a
+}
+
+define <vscale x 2 x half> @intrinsic_vrgather_mask_vi_nxv2f16_nxv2f16_i16(<vscale x 2 x half> %0, <vscale x 2 x half> %1, <vscale x 2 x i1> %2, i64 %3) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vi_nxv2f16_nxv2f16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e16,mf2,ta,mu
+; CHECK-NEXT:    vrgather.vi v16, v17, 9, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 2 x half> @llvm.riscv.vrgather.mask.nxv2f16.i16(
+    <vscale x 2 x half> %0,
+    <vscale x 2 x half> %1,
+    i16 9,
+    <vscale x 2 x i1> %2,
+    i64 %3)
+
+  ret <vscale x 2 x half> %a
+}
+
+define <vscale x 4 x half> @intrinsic_vrgather_vi_nxv4f16_nxv4f16_i16(<vscale x 4 x half> %0, i64 %1) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vi_nxv4f16_nxv4f16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e16,m1,ta,mu
+; CHECK-NEXT:    vrgather.vi v25, v16, 9
+; CHECK-NEXT:    vmv1r.v v16, v25
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 4 x half> @llvm.riscv.vrgather.nxv4f16.i16(
+    <vscale x 4 x half> %0,
+    i16 9,
+    i64 %1)
+
+  ret <vscale x 4 x half> %a
+}
+
+define <vscale x 4 x half> @intrinsic_vrgather_mask_vi_nxv4f16_nxv4f16_i16(<vscale x 4 x half> %0, <vscale x 4 x half> %1, <vscale x 4 x i1> %2, i64 %3) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vi_nxv4f16_nxv4f16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e16,m1,ta,mu
+; CHECK-NEXT:    vrgather.vi v16, v17, 9, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 4 x half> @llvm.riscv.vrgather.mask.nxv4f16.i16(
+    <vscale x 4 x half> %0,
+    <vscale x 4 x half> %1,
+    i16 9,
+    <vscale x 4 x i1> %2,
+    i64 %3)
+
+  ret <vscale x 4 x half> %a
+}
+
+define <vscale x 8 x half> @intrinsic_vrgather_vi_nxv8f16_nxv8f16_i16(<vscale x 8 x half> %0, i64 %1) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vi_nxv8f16_nxv8f16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e16,m2,ta,mu
+; CHECK-NEXT:    vrgather.vi v26, v16, 9
+; CHECK-NEXT:    vmv2r.v v16, v26
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 8 x half> @llvm.riscv.vrgather.nxv8f16.i16(
+    <vscale x 8 x half> %0,
+    i16 9,
+    i64 %1)
+
+  ret <vscale x 8 x half> %a
+}
+
+define <vscale x 8 x half> @intrinsic_vrgather_mask_vi_nxv8f16_nxv8f16_i16(<vscale x 8 x half> %0, <vscale x 8 x half> %1, <vscale x 8 x i1> %2, i64 %3) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vi_nxv8f16_nxv8f16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e16,m2,ta,mu
+; CHECK-NEXT:    vrgather.vi v16, v18, 9, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 8 x half> @llvm.riscv.vrgather.mask.nxv8f16.i16(
+    <vscale x 8 x half> %0,
+    <vscale x 8 x half> %1,
+    i16 9,
+    <vscale x 8 x i1> %2,
+    i64 %3)
+
+  ret <vscale x 8 x half> %a
+}
+
+define <vscale x 16 x half> @intrinsic_vrgather_vi_nxv16f16_nxv16f16_i16(<vscale x 16 x half> %0, i64 %1) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vi_nxv16f16_nxv16f16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e16,m4,ta,mu
+; CHECK-NEXT:    vrgather.vi v28, v16, 9
+; CHECK-NEXT:    vmv4r.v v16, v28
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 16 x half> @llvm.riscv.vrgather.nxv16f16.i16(
+    <vscale x 16 x half> %0,
+    i16 9,
+    i64 %1)
+
+  ret <vscale x 16 x half> %a
+}
+
+define <vscale x 16 x half> @intrinsic_vrgather_mask_vi_nxv16f16_nxv16f16_i16(<vscale x 16 x half> %0, <vscale x 16 x half> %1, <vscale x 16 x i1> %2, i64 %3) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vi_nxv16f16_nxv16f16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e16,m4,ta,mu
+; CHECK-NEXT:    vrgather.vi v16, v20, 9, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 16 x half> @llvm.riscv.vrgather.mask.nxv16f16.i16(
+    <vscale x 16 x half> %0,
+    <vscale x 16 x half> %1,
+    i16 9,
+    <vscale x 16 x i1> %2,
+    i64 %3)
+
+  ret <vscale x 16 x half> %a
+}
+
+define <vscale x 32 x half> @intrinsic_vrgather_vi_nxv32f16_nxv32f16_i16(<vscale x 32 x half> %0, i64 %1) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vi_nxv32f16_nxv32f16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e16,m8,ta,mu
+; CHECK-NEXT:    vrgather.vi v8, v16, 9
+; CHECK-NEXT:    vmv8r.v v16, v8
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 32 x half> @llvm.riscv.vrgather.nxv32f16.i16(
+    <vscale x 32 x half> %0,
+    i16 9,
+    i64 %1)
+
+  ret <vscale x 32 x half> %a
+}
+
+define <vscale x 32 x half> @intrinsic_vrgather_mask_vi_nxv32f16_nxv32f16_i16(<vscale x 32 x half> %0, <vscale x 32 x half> %1, <vscale x 32 x i1> %2, i64 %3) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vi_nxv32f16_nxv32f16_i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a2, zero, e16,m8,ta,mu
+; CHECK-NEXT:    vle16.v v8, (a0)
+; CHECK-NEXT:    vsetvli a0, a1, e16,m8,ta,mu
+; CHECK-NEXT:    vrgather.vi v16, v8, 9, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 32 x half> @llvm.riscv.vrgather.mask.nxv32f16.i16(
+    <vscale x 32 x half> %0,
+    <vscale x 32 x half> %1,
+    i16 9,
+    <vscale x 32 x i1> %2,
+    i64 %3)
+
+  ret <vscale x 32 x half> %a
+}
+
+define <vscale x 1 x float> @intrinsic_vrgather_vi_nxv1f32_nxv1f32_i32(<vscale x 1 x float> %0, i64 %1) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vi_nxv1f32_nxv1f32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e32,mf2,ta,mu
+; CHECK-NEXT:    vrgather.vi v25, v16, 9
+; CHECK-NEXT:    vmv1r.v v16, v25
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 1 x float> @llvm.riscv.vrgather.nxv1f32.i32(
+    <vscale x 1 x float> %0,
+    i32 9,
+    i64 %1)
+
+  ret <vscale x 1 x float> %a
+}
+
+define <vscale x 1 x float> @intrinsic_vrgather_mask_vi_nxv1f32_nxv1f32_i32(<vscale x 1 x float> %0, <vscale x 1 x float> %1, <vscale x 1 x i1> %2, i64 %3) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vi_nxv1f32_nxv1f32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e32,mf2,ta,mu
+; CHECK-NEXT:    vrgather.vi v16, v17, 9, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 1 x float> @llvm.riscv.vrgather.mask.nxv1f32.i32(
+    <vscale x 1 x float> %0,
+    <vscale x 1 x float> %1,
+    i32 9,
+    <vscale x 1 x i1> %2,
+    i64 %3)
+
+  ret <vscale x 1 x float> %a
+}
+
+define <vscale x 2 x float> @intrinsic_vrgather_vi_nxv2f32_nxv2f32_i32(<vscale x 2 x float> %0, i64 %1) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vi_nxv2f32_nxv2f32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e32,m1,ta,mu
+; CHECK-NEXT:    vrgather.vi v25, v16, 9
+; CHECK-NEXT:    vmv1r.v v16, v25
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 2 x float> @llvm.riscv.vrgather.nxv2f32.i32(
+    <vscale x 2 x float> %0,
+    i32 9,
+    i64 %1)
+
+  ret <vscale x 2 x float> %a
+}
+
+define <vscale x 2 x float> @intrinsic_vrgather_mask_vi_nxv2f32_nxv2f32_i32(<vscale x 2 x float> %0, <vscale x 2 x float> %1, <vscale x 2 x i1> %2, i64 %3) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vi_nxv2f32_nxv2f32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e32,m1,ta,mu
+; CHECK-NEXT:    vrgather.vi v16, v17, 9, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 2 x float> @llvm.riscv.vrgather.mask.nxv2f32.i32(
+    <vscale x 2 x float> %0,
+    <vscale x 2 x float> %1,
+    i32 9,
+    <vscale x 2 x i1> %2,
+    i64 %3)
+
+  ret <vscale x 2 x float> %a
+}
+
+define <vscale x 4 x float> @intrinsic_vrgather_vi_nxv4f32_nxv4f32_i32(<vscale x 4 x float> %0, i64 %1) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vi_nxv4f32_nxv4f32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e32,m2,ta,mu
+; CHECK-NEXT:    vrgather.vi v26, v16, 9
+; CHECK-NEXT:    vmv2r.v v16, v26
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 4 x float> @llvm.riscv.vrgather.nxv4f32.i32(
+    <vscale x 4 x float> %0,
+    i32 9,
+    i64 %1)
+
+  ret <vscale x 4 x float> %a
+}
+
+define <vscale x 4 x float> @intrinsic_vrgather_mask_vi_nxv4f32_nxv4f32_i32(<vscale x 4 x float> %0, <vscale x 4 x float> %1, <vscale x 4 x i1> %2, i64 %3) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vi_nxv4f32_nxv4f32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e32,m2,ta,mu
+; CHECK-NEXT:    vrgather.vi v16, v18, 9, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 4 x float> @llvm.riscv.vrgather.mask.nxv4f32.i32(
+    <vscale x 4 x float> %0,
+    <vscale x 4 x float> %1,
+    i32 9,
+    <vscale x 4 x i1> %2,
+    i64 %3)
+
+  ret <vscale x 4 x float> %a
+}
+
+define <vscale x 8 x float> @intrinsic_vrgather_vi_nxv8f32_nxv8f32_i32(<vscale x 8 x float> %0, i64 %1) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vi_nxv8f32_nxv8f32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e32,m4,ta,mu
+; CHECK-NEXT:    vrgather.vi v28, v16, 9
+; CHECK-NEXT:    vmv4r.v v16, v28
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 8 x float> @llvm.riscv.vrgather.nxv8f32.i32(
+    <vscale x 8 x float> %0,
+    i32 9,
+    i64 %1)
+
+  ret <vscale x 8 x float> %a
+}
+
+define <vscale x 8 x float> @intrinsic_vrgather_mask_vi_nxv8f32_nxv8f32_i32(<vscale x 8 x float> %0, <vscale x 8 x float> %1, <vscale x 8 x i1> %2, i64 %3) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vi_nxv8f32_nxv8f32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e32,m4,ta,mu
+; CHECK-NEXT:    vrgather.vi v16, v20, 9, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 8 x float> @llvm.riscv.vrgather.mask.nxv8f32.i32(
+    <vscale x 8 x float> %0,
+    <vscale x 8 x float> %1,
+    i32 9,
+    <vscale x 8 x i1> %2,
+    i64 %3)
+
+  ret <vscale x 8 x float> %a
+}
+
+define <vscale x 16 x float> @intrinsic_vrgather_vi_nxv16f32_nxv16f32_i32(<vscale x 16 x float> %0, i64 %1) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vi_nxv16f32_nxv16f32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e32,m8,ta,mu
+; CHECK-NEXT:    vrgather.vi v8, v16, 9
+; CHECK-NEXT:    vmv8r.v v16, v8
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 16 x float> @llvm.riscv.vrgather.nxv16f32.i32(
+    <vscale x 16 x float> %0,
+    i32 9,
+    i64 %1)
+
+  ret <vscale x 16 x float> %a
+}
+
+define <vscale x 16 x float> @intrinsic_vrgather_mask_vi_nxv16f32_nxv16f32_i32(<vscale x 16 x float> %0, <vscale x 16 x float> %1, <vscale x 16 x i1> %2, i64 %3) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vi_nxv16f32_nxv16f32_i32:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a2, zero, e32,m8,ta,mu
+; CHECK-NEXT:    vle32.v v8, (a0)
+; CHECK-NEXT:    vsetvli a0, a1, e32,m8,ta,mu
+; CHECK-NEXT:    vrgather.vi v16, v8, 9, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 16 x float> @llvm.riscv.vrgather.mask.nxv16f32.i32(
+    <vscale x 16 x float> %0,
+    <vscale x 16 x float> %1,
+    i32 9,
+    <vscale x 16 x i1> %2,
+    i64 %3)
+
+  ret <vscale x 16 x float> %a
+}
+
+define <vscale x 1 x double> @intrinsic_vrgather_vi_nxv1f64_nxv1f64_i64(<vscale x 1 x double> %0, i64 %1) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vi_nxv1f64_nxv1f64_i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e64,m1,ta,mu
+; CHECK-NEXT:    vrgather.vi v25, v16, 9
+; CHECK-NEXT:    vmv1r.v v16, v25
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 1 x double> @llvm.riscv.vrgather.nxv1f64.i64(
+    <vscale x 1 x double> %0,
+    i64 9,
+    i64 %1)
+
+  ret <vscale x 1 x double> %a
+}
+
+define <vscale x 1 x double> @intrinsic_vrgather_mask_vi_nxv1f64_nxv1f64_i64(<vscale x 1 x double> %0, <vscale x 1 x double> %1, <vscale x 1 x i1> %2, i64 %3) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vi_nxv1f64_nxv1f64_i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e64,m1,ta,mu
+; CHECK-NEXT:    vrgather.vi v16, v17, 9, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 1 x double> @llvm.riscv.vrgather.mask.nxv1f64.i64(
+    <vscale x 1 x double> %0,
+    <vscale x 1 x double> %1,
+    i64 9,
+    <vscale x 1 x i1> %2,
+    i64 %3)
+
+  ret <vscale x 1 x double> %a
+}
+
+define <vscale x 2 x double> @intrinsic_vrgather_vi_nxv2f64_nxv2f64_i64(<vscale x 2 x double> %0, i64 %1) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vi_nxv2f64_nxv2f64_i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e64,m2,ta,mu
+; CHECK-NEXT:    vrgather.vi v26, v16, 9
+; CHECK-NEXT:    vmv2r.v v16, v26
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 2 x double> @llvm.riscv.vrgather.nxv2f64.i64(
+    <vscale x 2 x double> %0,
+    i64 9,
+    i64 %1)
+
+  ret <vscale x 2 x double> %a
+}
+
+define <vscale x 2 x double> @intrinsic_vrgather_mask_vi_nxv2f64_nxv2f64_i64(<vscale x 2 x double> %0, <vscale x 2 x double> %1, <vscale x 2 x i1> %2, i64 %3) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vi_nxv2f64_nxv2f64_i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e64,m2,ta,mu
+; CHECK-NEXT:    vrgather.vi v16, v18, 9, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 2 x double> @llvm.riscv.vrgather.mask.nxv2f64.i64(
+    <vscale x 2 x double> %0,
+    <vscale x 2 x double> %1,
+    i64 9,
+    <vscale x 2 x i1> %2,
+    i64 %3)
+
+  ret <vscale x 2 x double> %a
+}
+
+define <vscale x 4 x double> @intrinsic_vrgather_vi_nxv4f64_nxv4f64_i64(<vscale x 4 x double> %0, i64 %1) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vi_nxv4f64_nxv4f64_i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e64,m4,ta,mu
+; CHECK-NEXT:    vrgather.vi v28, v16, 9
+; CHECK-NEXT:    vmv4r.v v16, v28
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 4 x double> @llvm.riscv.vrgather.nxv4f64.i64(
+    <vscale x 4 x double> %0,
+    i64 9,
+    i64 %1)
+
+  ret <vscale x 4 x double> %a
+}
+
+define <vscale x 4 x double> @intrinsic_vrgather_mask_vi_nxv4f64_nxv4f64_i64(<vscale x 4 x double> %0, <vscale x 4 x double> %1, <vscale x 4 x i1> %2, i64 %3) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vi_nxv4f64_nxv4f64_i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e64,m4,ta,mu
+; CHECK-NEXT:    vrgather.vi v16, v20, 9, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 4 x double> @llvm.riscv.vrgather.mask.nxv4f64.i64(
+    <vscale x 4 x double> %0,
+    <vscale x 4 x double> %1,
+    i64 9,
+    <vscale x 4 x i1> %2,
+    i64 %3)
+
+  ret <vscale x 4 x double> %a
+}
+
+define <vscale x 8 x double> @intrinsic_vrgather_vi_nxv8f64_nxv8f64_i64(<vscale x 8 x double> %0, i64 %1) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_vi_nxv8f64_nxv8f64_i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e64,m8,ta,mu
+; CHECK-NEXT:    vrgather.vi v8, v16, 9
+; CHECK-NEXT:    vmv8r.v v16, v8
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 8 x double> @llvm.riscv.vrgather.nxv8f64.i64(
+    <vscale x 8 x double> %0,
+    i64 9,
+    i64 %1)
+
+  ret <vscale x 8 x double> %a
+}
+
+define <vscale x 8 x double> @intrinsic_vrgather_mask_vi_nxv8f64_nxv8f64_i64(<vscale x 8 x double> %0, <vscale x 8 x double> %1, <vscale x 8 x i1> %2, i64 %3) nounwind {
+; CHECK-LABEL: intrinsic_vrgather_mask_vi_nxv8f64_nxv8f64_i64:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a2, zero, e64,m8,ta,mu
+; CHECK-NEXT:    vle64.v v8, (a0)
+; CHECK-NEXT:    vsetvli a0, a1, e64,m8,ta,mu
+; CHECK-NEXT:    vrgather.vi v16, v8, 9, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 8 x double> @llvm.riscv.vrgather.mask.nxv8f64.i64(
+    <vscale x 8 x double> %0,
+    <vscale x 8 x double> %1,
+    i64 9,
+    <vscale x 8 x i1> %2,
+    i64 %3)
+
+  ret <vscale x 8 x double> %a
+}