diff --git a/llvm/include/llvm/IR/IntrinsicsRISCV.td b/llvm/include/llvm/IR/IntrinsicsRISCV.td
--- a/llvm/include/llvm/IR/IntrinsicsRISCV.td
+++ b/llvm/include/llvm/IR/IntrinsicsRISCV.td
@@ -739,6 +739,7 @@
   defm vfslide1down : RISCVBinaryAAX;
 
   defm vrgather : RISCVBinaryAAX;
+  defm vrgatherei16 : RISCVBinaryAAX;
 
   def "int_riscv_vcompress" : RISCVBinaryAAAMask;
 
diff --git a/llvm/lib/Target/RISCV/RISCVInstrInfoVPseudos.td b/llvm/lib/Target/RISCV/RISCVInstrInfoVPseudos.td
--- a/llvm/lib/Target/RISCV/RISCVInstrInfoVPseudos.td
+++ b/llvm/lib/Target/RISCV/RISCVInstrInfoVPseudos.td
@@ -77,6 +77,27 @@
   int val = !if(!eq(num, 1), 0, !add(1, shift_amount<!srl(num, 1)>.val));
 }
 
+class octuple_from_str<string MX> {
+  int ret = !cond(!eq(MX, "MF8") : 1,
+                  !eq(MX, "MF4") : 2,
+                  !eq(MX, "MF2") : 4,
+                  !eq(MX, "M1") : 8,
+                  !eq(MX, "M2") : 16,
+                  !eq(MX, "M4") : 32,
+                  !eq(MX, "M8") : 64);
+}
+
+class octuple_to_str<int octuple> {
+  string ret = !if(!eq(octuple, 1), "MF8",
+                   !if(!eq(octuple, 2), "MF4",
+                   !if(!eq(octuple, 4), "MF2",
+                   !if(!eq(octuple, 8), "M1",
+                   !if(!eq(octuple, 16), "M2",
+                   !if(!eq(octuple, 32), "M4",
+                   !if(!eq(octuple, 64), "M8",
+                   "NoDef")))))));
+}
+
 // Output pattern for X0 used to represent VLMAX in the pseudo instructions.
 def VLMax : OutPatFrag<(ops), (XLenVT X0)>;
 
@@ -966,11 +987,40 @@
   }
 }
 
+multiclass VPseudoBinaryEEW<VReg RetClass,
+                            VReg Op1Class,
+                            DAGOperand Op2Class,
+                            LMULInfo lmul,
+                            LMULInfo emul,
+                            string Constraint = ""> {
+  let VLMul = lmul.value in {
+    def "_" # lmul.MX # "_" # emul.MX : VPseudoBinaryNoMask<RetClass, Op1Class, Op2Class,
+                                                            Constraint>;
+    def "_" # lmul.MX # "_" # emul.MX # "_MASK" : VPseudoBinaryMask<RetClass, Op1Class, Op2Class,
+                                                                    Constraint>;
+  }
+}
+
 multiclass VPseudoBinaryV_VV<string Constraint = ""> {
   foreach m = MxList.m in
     defm _VV : VPseudoBinary<m.vrclass, m.vrclass, m.vrclass, m, Constraint>;
 }
 
+multiclass VPseudoBinaryV_VV_EEW<int eew, string Constraint = ""> {
+  foreach m = MxList.m in {
+    foreach sew = EEWList in {
+      defvar octuple_lmul = octuple_from_str<m.MX>.ret;
+      // emul = lmul * eew / sew
+      defvar octuple_emul = !srl(!mul(octuple_lmul, eew), shift_amount<sew>.val);
+      if !and(!ge(octuple_emul, 1), !le(octuple_emul, 64)) then {
+        defvar emul_str = octuple_to_str<octuple_emul>.ret;
+        defvar emulInfo = !cast<LMULInfo>("V_" # emul_str);
+        defm _VV : VPseudoBinaryEEW<m.vrclass, m.vrclass, emulInfo.vrclass, m, emulInfo, Constraint>;
+      }
+    }
+  }
+}
+
 multiclass VPseudoBinaryV_VX<bit IsFloat, string Constraint = ""> {
   foreach m = MxList.m in
     defm !if(IsFloat, "_VF", "_VX") : VPseudoBinary<m.vrclass, m.vrclass,
@@ -1823,6 +1873,24 @@
   }
 }
 
+multiclass VPatBinaryV_VV_INT_EEW<string intrinsic, string instruction,
+                                  int eew, list<VTypeInfo> vtilist> {
+  foreach vti = vtilist in {
+    // emul = lmul * eew / sew
+    defvar vlmul = vti.LMul;
+    defvar octuple_lmul = octuple_from_str<vlmul.MX>.ret;
+    defvar octuple_emul = !srl(!mul(octuple_lmul, eew), shift_amount<vti.SEW>.val);
+    if !and(!ge(octuple_emul, 1), !le(octuple_emul, 64)) then {
+      defvar emul_str = octuple_to_str<octuple_emul>.ret;
+      defvar ivti = !cast<VTypeInfo>("VI" # eew # emul_str);
+      defm : VPatBinary<intrinsic, instruction # "_VV_" # vti.LMul.MX # "_" # emul_str,
+                           vti.Vector, vti.Vector, ivti.Vector, vti.Mask,
+                           vti.SEW, vti.RegClass,
+                           vti.RegClass, ivti.RegClass>;
+    }
+  }
+}
+
 multiclass VPatBinaryV_VX<string intrinsic, string instruction,
                           list<VTypeInfo> vtilist> {
   foreach vti = vtilist in {
@@ -2926,6 +2994,7 @@
 // 17.4. Vector Register Gather Instructions
 //===----------------------------------------------------------------------===//
 defm PseudoVRGATHER    : VPseudoBinaryV_VV_VX_VI<uimm5, "@earlyclobber $rd">;
+defm PseudoVRGATHEREI16 : VPseudoBinaryV_VV_EEW</* eew */ 16, "@earlyclobber $rd">;
 
 //===----------------------------------------------------------------------===//
 // 17.5. Vector Compress Instruction
@@ -3597,11 +3666,15 @@
 let Predicates = [HasStdExtV] in {
   defm "" : VPatBinaryV_VV_VX_VI_INT<"int_riscv_vrgather", "PseudoVRGATHER",
                                      AllIntegerVectors, uimm5>;
+  defm "" : VPatBinaryV_VV_INT_EEW<"int_riscv_vrgatherei16", "PseudoVRGATHEREI16",
+                                   /* eew */ 16, AllIntegerVectors>;
 } // Predicates = [HasStdExtV]
 
 let Predicates = [HasStdExtV, HasStdExtF] in {
   defm "" : VPatBinaryV_VV_VX_VI_INT<"int_riscv_vrgather", "PseudoVRGATHER",
                                      AllFloatVectors, uimm5>;
+  defm "" : VPatBinaryV_VV_INT_EEW<"int_riscv_vrgatherei16", "PseudoVRGATHEREI16",
+                                   /* eew */ 16, AllFloatVectors>;
 } // Predicates = [HasStdExtV, HasStdExtF]
 
 //===----------------------------------------------------------------------===//
diff --git a/llvm/test/CodeGen/RISCV/rvv/vrgatherei16-rv32.ll b/llvm/test/CodeGen/RISCV/rvv/vrgatherei16-rv32.ll
new file mode 100644
--- /dev/null
+++ b/llvm/test/CodeGen/RISCV/rvv/vrgatherei16-rv32.ll
@@ -0,0 +1,1304 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc -mtriple=riscv32 -mattr=+experimental-v,+d,+experimental-zfh -verify-machineinstrs \
+; RUN:   --riscv-no-aliases < %s | FileCheck %s
+declare <vscale x 1 x i8> @llvm.riscv.vrgatherei16.nxv1i8.nxv1i16(
+  <vscale x 1 x i8>,
+  <vscale x 1 x i16>,
+  i32);
+
+define <vscale x 1 x i8> @intrinsic_vrgatherei16_vv_nxv1i8_nxv1i8_nxv1i16(<vscale x 1 x i8> %0, <vscale x 1 x i16> %1, i32 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgatherei16_vv_nxv1i8_nxv1i8_nxv1i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e8,mf8,ta,mu
+; CHECK-NEXT:    vrgatherei16.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.vrgatherei16.nxv1i8.nxv1i16(
+    <vscale x 1 x i8> %0,
+    <vscale x 1 x i16> %1,
+    i32 %2)
+
+  ret <vscale x 1 x i8> %a
+}
+
+declare <vscale x 1 x i8> @llvm.riscv.vrgatherei16.mask.nxv1i8.nxv1i16(
+  <vscale x 1 x i8>,
+  <vscale x 1 x i8>,
+  <vscale x 1 x i16>,
+  <vscale x 1 x i1>,
+  i32);
+
+define <vscale x 1 x i8> @intrinsic_vrgatherei16_mask_vv_nxv1i8_nxv1i8_nxv1i16(<vscale x 1 x i8> %0, <vscale x 1 x i8> %1, <vscale x 1 x i16> %2, <vscale x 1 x i1> %3, i32 %4) nounwind {
+; CHECK-LABEL: intrinsic_vrgatherei16_mask_vv_nxv1i8_nxv1i8_nxv1i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e8,mf8,tu,mu
+; CHECK-NEXT:    vrgatherei16.vv v16, v17, v18, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 1 x i8> @llvm.riscv.vrgatherei16.mask.nxv1i8.nxv1i16(
+    <vscale x 1 x i8> %0,
+    <vscale x 1 x i8> %1,
+    <vscale x 1 x i16> %2,
+    <vscale x 1 x i1> %3,
+    i32 %4)
+
+  ret <vscale x 1 x i8> %a
+}
+
+declare <vscale x 2 x i8> @llvm.riscv.vrgatherei16.nxv2i8.nxv2i16(
+  <vscale x 2 x i8>,
+  <vscale x 2 x i16>,
+  i32);
+
+define <vscale x 2 x i8> @intrinsic_vrgatherei16_vv_nxv2i8_nxv2i8_nxv2i16(<vscale x 2 x i8> %0, <vscale x 2 x i16> %1, i32 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgatherei16_vv_nxv2i8_nxv2i8_nxv2i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e8,mf4,ta,mu
+; CHECK-NEXT:    vrgatherei16.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.vrgatherei16.nxv2i8.nxv2i16(
+    <vscale x 2 x i8> %0,
+    <vscale x 2 x i16> %1,
+    i32 %2)
+
+  ret <vscale x 2 x i8> %a
+}
+
+declare <vscale x 2 x i8> @llvm.riscv.vrgatherei16.mask.nxv2i8.nxv2i16(
+  <vscale x 2 x i8>,
+  <vscale x 2 x i8>,
+  <vscale x 2 x i16>,
+  <vscale x 2 x i1>,
+  i32);
+
+define <vscale x 2 x i8> @intrinsic_vrgatherei16_mask_vv_nxv2i8_nxv2i8_nxv2i16(<vscale x 2 x i8> %0, <vscale x 2 x i8> %1, <vscale x 2 x i16> %2, <vscale x 2 x i1> %3, i32 %4) nounwind {
+; CHECK-LABEL: intrinsic_vrgatherei16_mask_vv_nxv2i8_nxv2i8_nxv2i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e8,mf4,tu,mu
+; CHECK-NEXT:    vrgatherei16.vv v16, v17, v18, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 2 x i8> @llvm.riscv.vrgatherei16.mask.nxv2i8.nxv2i16(
+    <vscale x 2 x i8> %0,
+    <vscale x 2 x i8> %1,
+    <vscale x 2 x i16> %2,
+    <vscale x 2 x i1> %3,
+    i32 %4)
+
+  ret <vscale x 2 x i8> %a
+}
+
+declare <vscale x 4 x i8> @llvm.riscv.vrgatherei16.nxv4i8.nxv4i16(
+  <vscale x 4 x i8>,
+  <vscale x 4 x i16>,
+  i32);
+
+define <vscale x 4 x i8> @intrinsic_vrgatherei16_vv_nxv4i8_nxv4i8_nxv4i16(<vscale x 4 x i8> %0, <vscale x 4 x i16> %1, i32 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgatherei16_vv_nxv4i8_nxv4i8_nxv4i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e8,mf2,ta,mu
+; CHECK-NEXT:    vrgatherei16.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.vrgatherei16.nxv4i8.nxv4i16(
+    <vscale x 4 x i8> %0,
+    <vscale x 4 x i16> %1,
+    i32 %2)
+
+  ret <vscale x 4 x i8> %a
+}
+
+declare <vscale x 4 x i8> @llvm.riscv.vrgatherei16.mask.nxv4i8.nxv4i16(
+  <vscale x 4 x i8>,
+  <vscale x 4 x i8>,
+  <vscale x 4 x i16>,
+  <vscale x 4 x i1>,
+  i32);
+
+define <vscale x 4 x i8> @intrinsic_vrgatherei16_mask_vv_nxv4i8_nxv4i8_nxv4i16(<vscale x 4 x i8> %0, <vscale x 4 x i8> %1, <vscale x 4 x i16> %2, <vscale x 4 x i1> %3, i32 %4) nounwind {
+; CHECK-LABEL: intrinsic_vrgatherei16_mask_vv_nxv4i8_nxv4i8_nxv4i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e8,mf2,tu,mu
+; CHECK-NEXT:    vrgatherei16.vv v16, v17, v18, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 4 x i8> @llvm.riscv.vrgatherei16.mask.nxv4i8.nxv4i16(
+    <vscale x 4 x i8> %0,
+    <vscale x 4 x i8> %1,
+    <vscale x 4 x i16> %2,
+    <vscale x 4 x i1> %3,
+    i32 %4)
+
+  ret <vscale x 4 x i8> %a
+}
+
+declare <vscale x 8 x i8> @llvm.riscv.vrgatherei16.nxv8i8.nxv8i16(
+  <vscale x 8 x i8>,
+  <vscale x 8 x i16>,
+  i32);
+
+define <vscale x 8 x i8> @intrinsic_vrgatherei16_vv_nxv8i8_nxv8i8_nxv8i16(<vscale x 8 x i8> %0, <vscale x 8 x i16> %1, i32 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgatherei16_vv_nxv8i8_nxv8i8_nxv8i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e8,m1,ta,mu
+; CHECK-NEXT:    vrgatherei16.vv v25, v16, v18
+; CHECK-NEXT:    vmv1r.v v16, v25
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 8 x i8> @llvm.riscv.vrgatherei16.nxv8i8.nxv8i16(
+    <vscale x 8 x i8> %0,
+    <vscale x 8 x i16> %1,
+    i32 %2)
+
+  ret <vscale x 8 x i8> %a
+}
+
+declare <vscale x 8 x i8> @llvm.riscv.vrgatherei16.mask.nxv8i8.nxv8i16(
+  <vscale x 8 x i8>,
+  <vscale x 8 x i8>,
+  <vscale x 8 x i16>,
+  <vscale x 8 x i1>,
+  i32);
+
+define <vscale x 8 x i8> @intrinsic_vrgatherei16_mask_vv_nxv8i8_nxv8i8_nxv8i16(<vscale x 8 x i8> %0, <vscale x 8 x i8> %1, <vscale x 8 x i16> %2, <vscale x 8 x i1> %3, i32 %4) nounwind {
+; CHECK-LABEL: intrinsic_vrgatherei16_mask_vv_nxv8i8_nxv8i8_nxv8i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e8,m1,tu,mu
+; CHECK-NEXT:    vrgatherei16.vv v16, v17, v18, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 8 x i8> @llvm.riscv.vrgatherei16.mask.nxv8i8.nxv8i16(
+    <vscale x 8 x i8> %0,
+    <vscale x 8 x i8> %1,
+    <vscale x 8 x i16> %2,
+    <vscale x 8 x i1> %3,
+    i32 %4)
+
+  ret <vscale x 8 x i8> %a
+}
+
+declare <vscale x 16 x i8> @llvm.riscv.vrgatherei16.nxv16i8.nxv16i16(
+  <vscale x 16 x i8>,
+  <vscale x 16 x i16>,
+  i32);
+
+define <vscale x 16 x i8> @intrinsic_vrgatherei16_vv_nxv16i8_nxv16i8_nxv16i16(<vscale x 16 x i8> %0, <vscale x 16 x i16> %1, i32 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgatherei16_vv_nxv16i8_nxv16i8_nxv16i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e8,m2,ta,mu
+; CHECK-NEXT:    vrgatherei16.vv v26, v16, v20
+; CHECK-NEXT:    vmv2r.v v16, v26
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 16 x i8> @llvm.riscv.vrgatherei16.nxv16i8.nxv16i16(
+    <vscale x 16 x i8> %0,
+    <vscale x 16 x i16> %1,
+    i32 %2)
+
+  ret <vscale x 16 x i8> %a
+}
+
+declare <vscale x 16 x i8> @llvm.riscv.vrgatherei16.mask.nxv16i8.nxv16i16(
+  <vscale x 16 x i8>,
+  <vscale x 16 x i8>,
+  <vscale x 16 x i16>,
+  <vscale x 16 x i1>,
+  i32);
+
+define <vscale x 16 x i8> @intrinsic_vrgatherei16_mask_vv_nxv16i8_nxv16i8_nxv16i16(<vscale x 16 x i8> %0, <vscale x 16 x i8> %1, <vscale x 16 x i16> %2, <vscale x 16 x i1> %3, i32 %4) nounwind {
+; CHECK-LABEL: intrinsic_vrgatherei16_mask_vv_nxv16i8_nxv16i8_nxv16i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e8,m2,tu,mu
+; CHECK-NEXT:    vrgatherei16.vv v16, v18, v20, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 16 x i8> @llvm.riscv.vrgatherei16.mask.nxv16i8.nxv16i16(
+    <vscale x 16 x i8> %0,
+    <vscale x 16 x i8> %1,
+    <vscale x 16 x i16> %2,
+    <vscale x 16 x i1> %3,
+    i32 %4)
+
+  ret <vscale x 16 x i8> %a
+}
+
+declare <vscale x 32 x i8> @llvm.riscv.vrgatherei16.nxv32i8.nxv32i16(
+  <vscale x 32 x i8>,
+  <vscale x 32 x i16>,
+  i32);
+
+define <vscale x 32 x i8> @intrinsic_vrgatherei16_vv_nxv32i8_nxv32i8_nxv32i16(<vscale x 32 x i8> %0, <vscale x 32 x i16> %1, i32 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgatherei16_vv_nxv32i8_nxv32i8_nxv32i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a2, zero, e16,m8,ta,mu
+; CHECK-NEXT:    vle16.v v8, (a0)
+; CHECK-NEXT:    vsetvli a0, a1, e8,m4,ta,mu
+; CHECK-NEXT:    vrgatherei16.vv v28, v16, v8
+; CHECK-NEXT:    vmv4r.v v16, v28
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 32 x i8> @llvm.riscv.vrgatherei16.nxv32i8.nxv32i16(
+    <vscale x 32 x i8> %0,
+    <vscale x 32 x i16> %1,
+    i32 %2)
+
+  ret <vscale x 32 x i8> %a
+}
+
+declare <vscale x 32 x i8> @llvm.riscv.vrgatherei16.mask.nxv32i8.nxv32i16(
+  <vscale x 32 x i8>,
+  <vscale x 32 x i8>,
+  <vscale x 32 x i16>,
+  <vscale x 32 x i1>,
+  i32);
+
+define <vscale x 32 x i8> @intrinsic_vrgatherei16_mask_vv_nxv32i8_nxv32i8_nxv32i16(<vscale x 32 x i8> %0, <vscale x 32 x i8> %1, <vscale x 32 x i16> %2, <vscale x 32 x i1> %3, i32 %4) nounwind {
+; CHECK-LABEL: intrinsic_vrgatherei16_mask_vv_nxv32i8_nxv32i8_nxv32i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a2, zero, e16,m8,ta,mu
+; CHECK-NEXT:    vle16.v v8, (a0)
+; CHECK-NEXT:    vsetvli a0, a1, e8,m4,tu,mu
+; CHECK-NEXT:    vrgatherei16.vv v16, v20, v8, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 32 x i8> @llvm.riscv.vrgatherei16.mask.nxv32i8.nxv32i16(
+    <vscale x 32 x i8> %0,
+    <vscale x 32 x i8> %1,
+    <vscale x 32 x i16> %2,
+    <vscale x 32 x i1> %3,
+    i32 %4)
+
+  ret <vscale x 32 x i8> %a
+}
+
+declare <vscale x 1 x i16> @llvm.riscv.vrgatherei16.nxv1i16.nxv1i16(
+  <vscale x 1 x i16>,
+  <vscale x 1 x i16>,
+  i32);
+
+define <vscale x 1 x i16> @intrinsic_vrgatherei16_vv_nxv1i16_nxv1i16_nxv1i16(<vscale x 1 x i16> %0, <vscale x 1 x i16> %1, i32 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgatherei16_vv_nxv1i16_nxv1i16_nxv1i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e16,mf4,ta,mu
+; CHECK-NEXT:    vrgatherei16.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.vrgatherei16.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.vrgatherei16.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_vrgatherei16_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_vrgatherei16_mask_vv_nxv1i16_nxv1i16_nxv1i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e16,mf4,tu,mu
+; CHECK-NEXT:    vrgatherei16.vv v16, v17, v18, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 1 x i16> @llvm.riscv.vrgatherei16.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.vrgatherei16.nxv2i16.nxv2i16(
+  <vscale x 2 x i16>,
+  <vscale x 2 x i16>,
+  i32);
+
+define <vscale x 2 x i16> @intrinsic_vrgatherei16_vv_nxv2i16_nxv2i16_nxv2i16(<vscale x 2 x i16> %0, <vscale x 2 x i16> %1, i32 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgatherei16_vv_nxv2i16_nxv2i16_nxv2i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e16,mf2,ta,mu
+; CHECK-NEXT:    vrgatherei16.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.vrgatherei16.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.vrgatherei16.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_vrgatherei16_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_vrgatherei16_mask_vv_nxv2i16_nxv2i16_nxv2i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e16,mf2,tu,mu
+; CHECK-NEXT:    vrgatherei16.vv v16, v17, v18, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 2 x i16> @llvm.riscv.vrgatherei16.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.vrgatherei16.nxv4i16.nxv4i16(
+  <vscale x 4 x i16>,
+  <vscale x 4 x i16>,
+  i32);
+
+define <vscale x 4 x i16> @intrinsic_vrgatherei16_vv_nxv4i16_nxv4i16_nxv4i16(<vscale x 4 x i16> %0, <vscale x 4 x i16> %1, i32 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgatherei16_vv_nxv4i16_nxv4i16_nxv4i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e16,m1,ta,mu
+; CHECK-NEXT:    vrgatherei16.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.vrgatherei16.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.vrgatherei16.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_vrgatherei16_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_vrgatherei16_mask_vv_nxv4i16_nxv4i16_nxv4i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e16,m1,tu,mu
+; CHECK-NEXT:    vrgatherei16.vv v16, v17, v18, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 4 x i16> @llvm.riscv.vrgatherei16.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.vrgatherei16.nxv8i16.nxv8i16(
+  <vscale x 8 x i16>,
+  <vscale x 8 x i16>,
+  i32);
+
+define <vscale x 8 x i16> @intrinsic_vrgatherei16_vv_nxv8i16_nxv8i16_nxv8i16(<vscale x 8 x i16> %0, <vscale x 8 x i16> %1, i32 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgatherei16_vv_nxv8i16_nxv8i16_nxv8i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e16,m2,ta,mu
+; CHECK-NEXT:    vrgatherei16.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.vrgatherei16.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.vrgatherei16.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_vrgatherei16_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_vrgatherei16_mask_vv_nxv8i16_nxv8i16_nxv8i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e16,m2,tu,mu
+; CHECK-NEXT:    vrgatherei16.vv v16, v18, v20, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 8 x i16> @llvm.riscv.vrgatherei16.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.vrgatherei16.nxv16i16.nxv16i16(
+  <vscale x 16 x i16>,
+  <vscale x 16 x i16>,
+  i32);
+
+define <vscale x 16 x i16> @intrinsic_vrgatherei16_vv_nxv16i16_nxv16i16_nxv16i16(<vscale x 16 x i16> %0, <vscale x 16 x i16> %1, i32 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgatherei16_vv_nxv16i16_nxv16i16_nxv16i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e16,m4,ta,mu
+; CHECK-NEXT:    vrgatherei16.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.vrgatherei16.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.vrgatherei16.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_vrgatherei16_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_vrgatherei16_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,tu,mu
+; CHECK-NEXT:    vrgatherei16.vv v16, v20, v28, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 16 x i16> @llvm.riscv.vrgatherei16.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.vrgatherei16.nxv32i16.nxv32i16(
+  <vscale x 32 x i16>,
+  <vscale x 32 x i16>,
+  i32);
+
+define <vscale x 32 x i16> @intrinsic_vrgatherei16_vv_nxv32i16_nxv32i16_nxv32i16(<vscale x 32 x i16> %0, <vscale x 32 x i16> %1, i32 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgatherei16_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:    vrgatherei16.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.vrgatherei16.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.vrgatherei16.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_vrgatherei16_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_vrgatherei16_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,tu,mu
+; CHECK-NEXT:    vrgatherei16.vv v16, v24, v8, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 32 x i16> @llvm.riscv.vrgatherei16.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.vrgatherei16.nxv1i32.nxv1i16(
+  <vscale x 1 x i32>,
+  <vscale x 1 x i16>,
+  i32);
+
+define <vscale x 1 x i32> @intrinsic_vrgatherei16_vv_nxv1i32_nxv1i32_nxv1i16(<vscale x 1 x i32> %0, <vscale x 1 x i16> %1, i32 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgatherei16_vv_nxv1i32_nxv1i32_nxv1i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e32,mf2,ta,mu
+; CHECK-NEXT:    vrgatherei16.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.vrgatherei16.nxv1i32.nxv1i16(
+    <vscale x 1 x i32> %0,
+    <vscale x 1 x i16> %1,
+    i32 %2)
+
+  ret <vscale x 1 x i32> %a
+}
+
+declare <vscale x 1 x i32> @llvm.riscv.vrgatherei16.mask.nxv1i32.nxv1i16(
+  <vscale x 1 x i32>,
+  <vscale x 1 x i32>,
+  <vscale x 1 x i16>,
+  <vscale x 1 x i1>,
+  i32);
+
+define <vscale x 1 x i32> @intrinsic_vrgatherei16_mask_vv_nxv1i32_nxv1i32_nxv1i16(<vscale x 1 x i32> %0, <vscale x 1 x i32> %1, <vscale x 1 x i16> %2, <vscale x 1 x i1> %3, i32 %4) nounwind {
+; CHECK-LABEL: intrinsic_vrgatherei16_mask_vv_nxv1i32_nxv1i32_nxv1i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e32,mf2,tu,mu
+; CHECK-NEXT:    vrgatherei16.vv v16, v17, v18, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 1 x i32> @llvm.riscv.vrgatherei16.mask.nxv1i32.nxv1i16(
+    <vscale x 1 x i32> %0,
+    <vscale x 1 x i32> %1,
+    <vscale x 1 x i16> %2,
+    <vscale x 1 x i1> %3,
+    i32 %4)
+
+  ret <vscale x 1 x i32> %a
+}
+
+declare <vscale x 4 x i32> @llvm.riscv.vrgatherei16.nxv4i32.nxv4i16(
+  <vscale x 4 x i32>,
+  <vscale x 4 x i16>,
+  i32);
+
+define <vscale x 4 x i32> @intrinsic_vrgatherei16_vv_nxv4i32_nxv4i32_nxv4i16(<vscale x 4 x i32> %0, <vscale x 4 x i16> %1, i32 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgatherei16_vv_nxv4i32_nxv4i32_nxv4i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e32,m2,ta,mu
+; CHECK-NEXT:    vrgatherei16.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.vrgatherei16.nxv4i32.nxv4i16(
+    <vscale x 4 x i32> %0,
+    <vscale x 4 x i16> %1,
+    i32 %2)
+
+  ret <vscale x 4 x i32> %a
+}
+
+declare <vscale x 4 x i32> @llvm.riscv.vrgatherei16.mask.nxv4i32.nxv4i16(
+  <vscale x 4 x i32>,
+  <vscale x 4 x i32>,
+  <vscale x 4 x i16>,
+  <vscale x 4 x i1>,
+  i32);
+
+define <vscale x 4 x i32> @intrinsic_vrgatherei16_mask_vv_nxv4i32_nxv4i32_nxv4i16(<vscale x 4 x i32> %0, <vscale x 4 x i32> %1, <vscale x 4 x i16> %2, <vscale x 4 x i1> %3, i32 %4) nounwind {
+; CHECK-LABEL: intrinsic_vrgatherei16_mask_vv_nxv4i32_nxv4i32_nxv4i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e32,m2,tu,mu
+; CHECK-NEXT:    vrgatherei16.vv v16, v18, v20, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 4 x i32> @llvm.riscv.vrgatherei16.mask.nxv4i32.nxv4i16(
+    <vscale x 4 x i32> %0,
+    <vscale x 4 x i32> %1,
+    <vscale x 4 x i16> %2,
+    <vscale x 4 x i1> %3,
+    i32 %4)
+
+  ret <vscale x 4 x i32> %a
+}
+
+declare <vscale x 8 x i32> @llvm.riscv.vrgatherei16.nxv8i32.nxv8i16(
+  <vscale x 8 x i32>,
+  <vscale x 8 x i16>,
+  i32);
+
+define <vscale x 8 x i32> @intrinsic_vrgatherei16_vv_nxv8i32_nxv8i32_nxv8i16(<vscale x 8 x i32> %0, <vscale x 8 x i16> %1, i32 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgatherei16_vv_nxv8i32_nxv8i32_nxv8i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e32,m4,ta,mu
+; CHECK-NEXT:    vrgatherei16.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.vrgatherei16.nxv8i32.nxv8i16(
+    <vscale x 8 x i32> %0,
+    <vscale x 8 x i16> %1,
+    i32 %2)
+
+  ret <vscale x 8 x i32> %a
+}
+
+declare <vscale x 8 x i32> @llvm.riscv.vrgatherei16.mask.nxv8i32.nxv8i16(
+  <vscale x 8 x i32>,
+  <vscale x 8 x i32>,
+  <vscale x 8 x i16>,
+  <vscale x 8 x i1>,
+  i32);
+
+define <vscale x 8 x i32> @intrinsic_vrgatherei16_mask_vv_nxv8i32_nxv8i32_nxv8i16(<vscale x 8 x i32> %0, <vscale x 8 x i32> %1, <vscale x 8 x i16> %2, <vscale x 8 x i1> %3, i32 %4) nounwind {
+; CHECK-LABEL: intrinsic_vrgatherei16_mask_vv_nxv8i32_nxv8i32_nxv8i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a2, zero, e16,m2,ta,mu
+; CHECK-NEXT:    vle16.v v26, (a0)
+; CHECK-NEXT:    vsetvli a0, a1, e32,m4,tu,mu
+; CHECK-NEXT:    vrgatherei16.vv v16, v20, v26, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 8 x i32> @llvm.riscv.vrgatherei16.mask.nxv8i32.nxv8i16(
+    <vscale x 8 x i32> %0,
+    <vscale x 8 x i32> %1,
+    <vscale x 8 x i16> %2,
+    <vscale x 8 x i1> %3,
+    i32 %4)
+
+  ret <vscale x 8 x i32> %a
+}
+
+declare <vscale x 16 x i32> @llvm.riscv.vrgatherei16.nxv16i32.nxv16i16(
+  <vscale x 16 x i32>,
+  <vscale x 16 x i16>,
+  i32);
+
+define <vscale x 16 x i32> @intrinsic_vrgatherei16_vv_nxv16i32_nxv16i32_nxv16i16(<vscale x 16 x i32> %0, <vscale x 16 x i16> %1, i32 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgatherei16_vv_nxv16i32_nxv16i32_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, e32,m8,ta,mu
+; CHECK-NEXT:    vrgatherei16.vv v8, v16, v28
+; CHECK-NEXT:    vmv8r.v v16, v8
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 16 x i32> @llvm.riscv.vrgatherei16.nxv16i32.nxv16i16(
+    <vscale x 16 x i32> %0,
+    <vscale x 16 x i16> %1,
+    i32 %2)
+
+  ret <vscale x 16 x i32> %a
+}
+
+declare <vscale x 16 x i32> @llvm.riscv.vrgatherei16.mask.nxv16i32.nxv16i16(
+  <vscale x 16 x i32>,
+  <vscale x 16 x i32>,
+  <vscale x 16 x i16>,
+  <vscale x 16 x i1>,
+  i32);
+
+define <vscale x 16 x i32> @intrinsic_vrgatherei16_mask_vv_nxv16i32_nxv16i32_nxv16i16(<vscale x 16 x i32> %0, <vscale x 16 x i32> %1, <vscale x 16 x i16> %2, <vscale x 16 x i1> %3, i32 %4) nounwind {
+; CHECK-LABEL: intrinsic_vrgatherei16_mask_vv_nxv16i32_nxv16i32_nxv16i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a3, zero, e16,m4,ta,mu
+; CHECK-NEXT:    vle16.v v28, (a1)
+; CHECK-NEXT:    vsetvli a1, zero, e32,m8,ta,mu
+; CHECK-NEXT:    vle32.v v8, (a0)
+; CHECK-NEXT:    vsetvli a0, a2, e32,m8,tu,mu
+; CHECK-NEXT:    vrgatherei16.vv v16, v8, v28, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 16 x i32> @llvm.riscv.vrgatherei16.mask.nxv16i32.nxv16i16(
+    <vscale x 16 x i32> %0,
+    <vscale x 16 x i32> %1,
+    <vscale x 16 x i16> %2,
+    <vscale x 16 x i1> %3,
+    i32 %4)
+
+  ret <vscale x 16 x i32> %a
+}
+
+declare <vscale x 1 x half> @llvm.riscv.vrgatherei16.nxv1f16.nxv1i16(
+  <vscale x 1 x half>,
+  <vscale x 1 x i16>,
+  i32);
+
+define <vscale x 1 x half> @intrinsic_vrgatherei16_vv_nxv1f16_nxv1f16_nxv1i16(<vscale x 1 x half> %0, <vscale x 1 x i16> %1, i32 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgatherei16_vv_nxv1f16_nxv1f16_nxv1i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e16,mf4,ta,mu
+; CHECK-NEXT:    vrgatherei16.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.vrgatherei16.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.vrgatherei16.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_vrgatherei16_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_vrgatherei16_mask_vv_nxv1f16_nxv1f16_nxv1i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e16,mf4,tu,mu
+; CHECK-NEXT:    vrgatherei16.vv v16, v17, v18, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 1 x half> @llvm.riscv.vrgatherei16.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.vrgatherei16.nxv2f16.nxv2i16(
+  <vscale x 2 x half>,
+  <vscale x 2 x i16>,
+  i32);
+
+define <vscale x 2 x half> @intrinsic_vrgatherei16_vv_nxv2f16_nxv2f16_nxv2i16(<vscale x 2 x half> %0, <vscale x 2 x i16> %1, i32 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgatherei16_vv_nxv2f16_nxv2f16_nxv2i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e16,mf2,ta,mu
+; CHECK-NEXT:    vrgatherei16.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.vrgatherei16.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.vrgatherei16.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_vrgatherei16_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_vrgatherei16_mask_vv_nxv2f16_nxv2f16_nxv2i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e16,mf2,tu,mu
+; CHECK-NEXT:    vrgatherei16.vv v16, v17, v18, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 2 x half> @llvm.riscv.vrgatherei16.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.vrgatherei16.nxv4f16.nxv4i16(
+  <vscale x 4 x half>,
+  <vscale x 4 x i16>,
+  i32);
+
+define <vscale x 4 x half> @intrinsic_vrgatherei16_vv_nxv4f16_nxv4f16_nxv4i16(<vscale x 4 x half> %0, <vscale x 4 x i16> %1, i32 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgatherei16_vv_nxv4f16_nxv4f16_nxv4i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e16,m1,ta,mu
+; CHECK-NEXT:    vrgatherei16.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.vrgatherei16.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.vrgatherei16.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_vrgatherei16_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_vrgatherei16_mask_vv_nxv4f16_nxv4f16_nxv4i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e16,m1,tu,mu
+; CHECK-NEXT:    vrgatherei16.vv v16, v17, v18, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 4 x half> @llvm.riscv.vrgatherei16.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.vrgatherei16.nxv8f16.nxv8i16(
+  <vscale x 8 x half>,
+  <vscale x 8 x i16>,
+  i32);
+
+define <vscale x 8 x half> @intrinsic_vrgatherei16_vv_nxv8f16_nxv8f16_nxv8i16(<vscale x 8 x half> %0, <vscale x 8 x i16> %1, i32 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgatherei16_vv_nxv8f16_nxv8f16_nxv8i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e16,m2,ta,mu
+; CHECK-NEXT:    vrgatherei16.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.vrgatherei16.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.vrgatherei16.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_vrgatherei16_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_vrgatherei16_mask_vv_nxv8f16_nxv8f16_nxv8i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e16,m2,tu,mu
+; CHECK-NEXT:    vrgatherei16.vv v16, v18, v20, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 8 x half> @llvm.riscv.vrgatherei16.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.vrgatherei16.nxv16f16.nxv16i16(
+  <vscale x 16 x half>,
+  <vscale x 16 x i16>,
+  i32);
+
+define <vscale x 16 x half> @intrinsic_vrgatherei16_vv_nxv16f16_nxv16f16_nxv16i16(<vscale x 16 x half> %0, <vscale x 16 x i16> %1, i32 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgatherei16_vv_nxv16f16_nxv16f16_nxv16i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e16,m4,ta,mu
+; CHECK-NEXT:    vrgatherei16.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.vrgatherei16.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.vrgatherei16.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_vrgatherei16_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_vrgatherei16_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,tu,mu
+; CHECK-NEXT:    vrgatherei16.vv v16, v20, v28, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 16 x half> @llvm.riscv.vrgatherei16.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.vrgatherei16.nxv32f16.nxv32i16(
+  <vscale x 32 x half>,
+  <vscale x 32 x i16>,
+  i32);
+
+define <vscale x 32 x half> @intrinsic_vrgatherei16_vv_nxv32f16_nxv32f16_nxv32i16(<vscale x 32 x half> %0, <vscale x 32 x i16> %1, i32 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgatherei16_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:    vrgatherei16.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.vrgatherei16.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.vrgatherei16.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_vrgatherei16_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_vrgatherei16_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,tu,mu
+; CHECK-NEXT:    vrgatherei16.vv v16, v24, v8, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 32 x half> @llvm.riscv.vrgatherei16.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.vrgatherei16.nxv1f32.nxv1i16(
+  <vscale x 1 x float>,
+  <vscale x 1 x i16>,
+  i32);
+
+define <vscale x 1 x float> @intrinsic_vrgatherei16_vv_nxv1f32_nxv1f32_nxv1i16(<vscale x 1 x float> %0, <vscale x 1 x i16> %1, i32 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgatherei16_vv_nxv1f32_nxv1f32_nxv1i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e32,mf2,ta,mu
+; CHECK-NEXT:    vrgatherei16.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.vrgatherei16.nxv1f32.nxv1i16(
+    <vscale x 1 x float> %0,
+    <vscale x 1 x i16> %1,
+    i32 %2)
+
+  ret <vscale x 1 x float> %a
+}
+
+declare <vscale x 1 x float> @llvm.riscv.vrgatherei16.mask.nxv1f32.nxv1i16(
+  <vscale x 1 x float>,
+  <vscale x 1 x float>,
+  <vscale x 1 x i16>,
+  <vscale x 1 x i1>,
+  i32);
+
+define <vscale x 1 x float> @intrinsic_vrgatherei16_mask_vv_nxv1f32_nxv1f32_nxv1i16(<vscale x 1 x float> %0, <vscale x 1 x float> %1, <vscale x 1 x i16> %2, <vscale x 1 x i1> %3, i32 %4) nounwind {
+; CHECK-LABEL: intrinsic_vrgatherei16_mask_vv_nxv1f32_nxv1f32_nxv1i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e32,mf2,tu,mu
+; CHECK-NEXT:    vrgatherei16.vv v16, v17, v18, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 1 x float> @llvm.riscv.vrgatherei16.mask.nxv1f32.nxv1i16(
+    <vscale x 1 x float> %0,
+    <vscale x 1 x float> %1,
+    <vscale x 1 x i16> %2,
+    <vscale x 1 x i1> %3,
+    i32 %4)
+
+  ret <vscale x 1 x float> %a
+}
+
+declare <vscale x 4 x float> @llvm.riscv.vrgatherei16.nxv4f32.nxv4i16(
+  <vscale x 4 x float>,
+  <vscale x 4 x i16>,
+  i32);
+
+define <vscale x 4 x float> @intrinsic_vrgatherei16_vv_nxv4f32_nxv4f32_nxv4i16(<vscale x 4 x float> %0, <vscale x 4 x i16> %1, i32 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgatherei16_vv_nxv4f32_nxv4f32_nxv4i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e32,m2,ta,mu
+; CHECK-NEXT:    vrgatherei16.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.vrgatherei16.nxv4f32.nxv4i16(
+    <vscale x 4 x float> %0,
+    <vscale x 4 x i16> %1,
+    i32 %2)
+
+  ret <vscale x 4 x float> %a
+}
+
+declare <vscale x 4 x float> @llvm.riscv.vrgatherei16.mask.nxv4f32.nxv4i16(
+  <vscale x 4 x float>,
+  <vscale x 4 x float>,
+  <vscale x 4 x i16>,
+  <vscale x 4 x i1>,
+  i32);
+
+define <vscale x 4 x float> @intrinsic_vrgatherei16_mask_vv_nxv4f32_nxv4f32_nxv4i16(<vscale x 4 x float> %0, <vscale x 4 x float> %1, <vscale x 4 x i16> %2, <vscale x 4 x i1> %3, i32 %4) nounwind {
+; CHECK-LABEL: intrinsic_vrgatherei16_mask_vv_nxv4f32_nxv4f32_nxv4i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e32,m2,tu,mu
+; CHECK-NEXT:    vrgatherei16.vv v16, v18, v20, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 4 x float> @llvm.riscv.vrgatherei16.mask.nxv4f32.nxv4i16(
+    <vscale x 4 x float> %0,
+    <vscale x 4 x float> %1,
+    <vscale x 4 x i16> %2,
+    <vscale x 4 x i1> %3,
+    i32 %4)
+
+  ret <vscale x 4 x float> %a
+}
+
+declare <vscale x 8 x float> @llvm.riscv.vrgatherei16.nxv8f32.nxv8i16(
+  <vscale x 8 x float>,
+  <vscale x 8 x i16>,
+  i32);
+
+define <vscale x 8 x float> @intrinsic_vrgatherei16_vv_nxv8f32_nxv8f32_nxv8i16(<vscale x 8 x float> %0, <vscale x 8 x i16> %1, i32 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgatherei16_vv_nxv8f32_nxv8f32_nxv8i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e32,m4,ta,mu
+; CHECK-NEXT:    vrgatherei16.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.vrgatherei16.nxv8f32.nxv8i16(
+    <vscale x 8 x float> %0,
+    <vscale x 8 x i16> %1,
+    i32 %2)
+
+  ret <vscale x 8 x float> %a
+}
+
+declare <vscale x 8 x float> @llvm.riscv.vrgatherei16.mask.nxv8f32.nxv8i16(
+  <vscale x 8 x float>,
+  <vscale x 8 x float>,
+  <vscale x 8 x i16>,
+  <vscale x 8 x i1>,
+  i32);
+
+define <vscale x 8 x float> @intrinsic_vrgatherei16_mask_vv_nxv8f32_nxv8f32_nxv8i16(<vscale x 8 x float> %0, <vscale x 8 x float> %1, <vscale x 8 x i16> %2, <vscale x 8 x i1> %3, i32 %4) nounwind {
+; CHECK-LABEL: intrinsic_vrgatherei16_mask_vv_nxv8f32_nxv8f32_nxv8i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a2, zero, e16,m2,ta,mu
+; CHECK-NEXT:    vle16.v v26, (a0)
+; CHECK-NEXT:    vsetvli a0, a1, e32,m4,tu,mu
+; CHECK-NEXT:    vrgatherei16.vv v16, v20, v26, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 8 x float> @llvm.riscv.vrgatherei16.mask.nxv8f32.nxv8i16(
+    <vscale x 8 x float> %0,
+    <vscale x 8 x float> %1,
+    <vscale x 8 x i16> %2,
+    <vscale x 8 x i1> %3,
+    i32 %4)
+
+  ret <vscale x 8 x float> %a
+}
+
+declare <vscale x 16 x float> @llvm.riscv.vrgatherei16.nxv16f32.nxv16i16(
+  <vscale x 16 x float>,
+  <vscale x 16 x i16>,
+  i32);
+
+define <vscale x 16 x float> @intrinsic_vrgatherei16_vv_nxv16f32_nxv16f32_nxv16i16(<vscale x 16 x float> %0, <vscale x 16 x i16> %1, i32 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgatherei16_vv_nxv16f32_nxv16f32_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, e32,m8,ta,mu
+; CHECK-NEXT:    vrgatherei16.vv v8, v16, v28
+; CHECK-NEXT:    vmv8r.v v16, v8
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 16 x float> @llvm.riscv.vrgatherei16.nxv16f32.nxv16i16(
+    <vscale x 16 x float> %0,
+    <vscale x 16 x i16> %1,
+    i32 %2)
+
+  ret <vscale x 16 x float> %a
+}
+
+declare <vscale x 16 x float> @llvm.riscv.vrgatherei16.mask.nxv16f32.nxv16i16(
+  <vscale x 16 x float>,
+  <vscale x 16 x float>,
+  <vscale x 16 x i16>,
+  <vscale x 16 x i1>,
+  i32);
+
+define <vscale x 16 x float> @intrinsic_vrgatherei16_mask_vv_nxv16f32_nxv16f32_nxv16i16(<vscale x 16 x float> %0, <vscale x 16 x float> %1, <vscale x 16 x i16> %2, <vscale x 16 x i1> %3, i32 %4) nounwind {
+; CHECK-LABEL: intrinsic_vrgatherei16_mask_vv_nxv16f32_nxv16f32_nxv16i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a3, zero, e16,m4,ta,mu
+; CHECK-NEXT:    vle16.v v28, (a1)
+; CHECK-NEXT:    vsetvli a1, zero, e32,m8,ta,mu
+; CHECK-NEXT:    vle32.v v8, (a0)
+; CHECK-NEXT:    vsetvli a0, a2, e32,m8,tu,mu
+; CHECK-NEXT:    vrgatherei16.vv v16, v8, v28, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 16 x float> @llvm.riscv.vrgatherei16.mask.nxv16f32.nxv16i16(
+    <vscale x 16 x float> %0,
+    <vscale x 16 x float> %1,
+    <vscale x 16 x i16> %2,
+    <vscale x 16 x i1> %3,
+    i32 %4)
+
+  ret <vscale x 16 x float> %a
+}
+
+declare <vscale x 4 x double> @llvm.riscv.vrgatherei16.nxv4f64.nxv4i16(
+  <vscale x 4 x double>,
+  <vscale x 4 x i16>,
+  i32);
+
+define <vscale x 4 x double> @intrinsic_vrgatherei16_vv_nxv4f64_nxv4f64_nxv4i16(<vscale x 4 x double> %0, <vscale x 4 x i16> %1, i32 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgatherei16_vv_nxv4f64_nxv4f64_nxv4i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e64,m4,ta,mu
+; CHECK-NEXT:    vrgatherei16.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.vrgatherei16.nxv4f64.nxv4i16(
+    <vscale x 4 x double> %0,
+    <vscale x 4 x i16> %1,
+    i32 %2)
+
+  ret <vscale x 4 x double> %a
+}
+
+declare <vscale x 4 x double> @llvm.riscv.vrgatherei16.mask.nxv4f64.nxv4i16(
+  <vscale x 4 x double>,
+  <vscale x 4 x double>,
+  <vscale x 4 x i16>,
+  <vscale x 4 x i1>,
+  i32);
+
+define <vscale x 4 x double> @intrinsic_vrgatherei16_mask_vv_nxv4f64_nxv4f64_nxv4i16(<vscale x 4 x double> %0, <vscale x 4 x double> %1, <vscale x 4 x i16> %2, <vscale x 4 x i1> %3, i32 %4) nounwind {
+; CHECK-LABEL: intrinsic_vrgatherei16_mask_vv_nxv4f64_nxv4f64_nxv4i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a2, zero, e16,m1,ta,mu
+; CHECK-NEXT:    vle16.v v25, (a0)
+; CHECK-NEXT:    vsetvli a0, a1, e64,m4,tu,mu
+; CHECK-NEXT:    vrgatherei16.vv v16, v20, v25, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 4 x double> @llvm.riscv.vrgatherei16.mask.nxv4f64.nxv4i16(
+    <vscale x 4 x double> %0,
+    <vscale x 4 x double> %1,
+    <vscale x 4 x i16> %2,
+    <vscale x 4 x i1> %3,
+    i32 %4)
+
+  ret <vscale x 4 x double> %a
+}
+
+declare <vscale x 8 x double> @llvm.riscv.vrgatherei16.nxv8f64.nxv8i16(
+  <vscale x 8 x double>,
+  <vscale x 8 x i16>,
+  i32);
+
+define <vscale x 8 x double> @intrinsic_vrgatherei16_vv_nxv8f64_nxv8f64_nxv8i16(<vscale x 8 x double> %0, <vscale x 8 x i16> %1, i32 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgatherei16_vv_nxv8f64_nxv8f64_nxv8i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a2, zero, e16,m2,ta,mu
+; CHECK-NEXT:    vle16.v v26, (a0)
+; CHECK-NEXT:    vsetvli a0, a1, e64,m8,ta,mu
+; CHECK-NEXT:    vrgatherei16.vv v8, v16, v26
+; CHECK-NEXT:    vmv8r.v v16, v8
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 8 x double> @llvm.riscv.vrgatherei16.nxv8f64.nxv8i16(
+    <vscale x 8 x double> %0,
+    <vscale x 8 x i16> %1,
+    i32 %2)
+
+  ret <vscale x 8 x double> %a
+}
+
+declare <vscale x 8 x double> @llvm.riscv.vrgatherei16.mask.nxv8f64.nxv8i16(
+  <vscale x 8 x double>,
+  <vscale x 8 x double>,
+  <vscale x 8 x i16>,
+  <vscale x 8 x i1>,
+  i32);
+
+define <vscale x 8 x double> @intrinsic_vrgatherei16_mask_vv_nxv8f64_nxv8f64_nxv8i16(<vscale x 8 x double> %0, <vscale x 8 x double> %1, <vscale x 8 x i16> %2, <vscale x 8 x i1> %3, i32 %4) nounwind {
+; CHECK-LABEL: intrinsic_vrgatherei16_mask_vv_nxv8f64_nxv8f64_nxv8i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a3, zero, e16,m2,ta,mu
+; CHECK-NEXT:    vle16.v v26, (a1)
+; CHECK-NEXT:    vsetvli a1, zero, e64,m8,ta,mu
+; CHECK-NEXT:    vle64.v v8, (a0)
+; CHECK-NEXT:    vsetvli a0, a2, e64,m8,tu,mu
+; CHECK-NEXT:    vrgatherei16.vv v16, v8, v26, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 8 x double> @llvm.riscv.vrgatherei16.mask.nxv8f64.nxv8i16(
+    <vscale x 8 x double> %0,
+    <vscale x 8 x double> %1,
+    <vscale x 8 x i16> %2,
+    <vscale x 8 x i1> %3,
+    i32 %4)
+
+  ret <vscale x 8 x double> %a
+}
diff --git a/llvm/test/CodeGen/RISCV/rvv/vrgatherei16-rv64.ll b/llvm/test/CodeGen/RISCV/rvv/vrgatherei16-rv64.ll
new file mode 100644
--- /dev/null
+++ b/llvm/test/CodeGen/RISCV/rvv/vrgatherei16-rv64.ll
@@ -0,0 +1,1402 @@
+; 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.vrgatherei16.nxv1i8.nxv1i16(
+  <vscale x 1 x i8>,
+  <vscale x 1 x i16>,
+  i64);
+
+define <vscale x 1 x i8> @intrinsic_vrgatherei16_vv_nxv1i8_nxv1i8_nxv1i16(<vscale x 1 x i8> %0, <vscale x 1 x i16> %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgatherei16_vv_nxv1i8_nxv1i8_nxv1i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e8,mf8,ta,mu
+; CHECK-NEXT:    vrgatherei16.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.vrgatherei16.nxv1i8.nxv1i16(
+    <vscale x 1 x i8> %0,
+    <vscale x 1 x i16> %1,
+    i64 %2)
+
+  ret <vscale x 1 x i8> %a
+}
+
+declare <vscale x 1 x i8> @llvm.riscv.vrgatherei16.mask.nxv1i8.nxv1i16(
+  <vscale x 1 x i8>,
+  <vscale x 1 x i8>,
+  <vscale x 1 x i16>,
+  <vscale x 1 x i1>,
+  i64);
+
+define <vscale x 1 x i8> @intrinsic_vrgatherei16_mask_vv_nxv1i8_nxv1i8_nxv1i16(<vscale x 1 x i8> %0, <vscale x 1 x i8> %1, <vscale x 1 x i16> %2, <vscale x 1 x i1> %3, i64 %4) nounwind {
+; CHECK-LABEL: intrinsic_vrgatherei16_mask_vv_nxv1i8_nxv1i8_nxv1i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e8,mf8,tu,mu
+; CHECK-NEXT:    vrgatherei16.vv v16, v17, v18, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 1 x i8> @llvm.riscv.vrgatherei16.mask.nxv1i8.nxv1i16(
+    <vscale x 1 x i8> %0,
+    <vscale x 1 x i8> %1,
+    <vscale x 1 x i16> %2,
+    <vscale x 1 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 1 x i8> %a
+}
+
+declare <vscale x 2 x i8> @llvm.riscv.vrgatherei16.nxv2i8.nxv2i16(
+  <vscale x 2 x i8>,
+  <vscale x 2 x i16>,
+  i64);
+
+define <vscale x 2 x i8> @intrinsic_vrgatherei16_vv_nxv2i8_nxv2i8_nxv2i16(<vscale x 2 x i8> %0, <vscale x 2 x i16> %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgatherei16_vv_nxv2i8_nxv2i8_nxv2i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e8,mf4,ta,mu
+; CHECK-NEXT:    vrgatherei16.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.vrgatherei16.nxv2i8.nxv2i16(
+    <vscale x 2 x i8> %0,
+    <vscale x 2 x i16> %1,
+    i64 %2)
+
+  ret <vscale x 2 x i8> %a
+}
+
+declare <vscale x 2 x i8> @llvm.riscv.vrgatherei16.mask.nxv2i8.nxv2i16(
+  <vscale x 2 x i8>,
+  <vscale x 2 x i8>,
+  <vscale x 2 x i16>,
+  <vscale x 2 x i1>,
+  i64);
+
+define <vscale x 2 x i8> @intrinsic_vrgatherei16_mask_vv_nxv2i8_nxv2i8_nxv2i16(<vscale x 2 x i8> %0, <vscale x 2 x i8> %1, <vscale x 2 x i16> %2, <vscale x 2 x i1> %3, i64 %4) nounwind {
+; CHECK-LABEL: intrinsic_vrgatherei16_mask_vv_nxv2i8_nxv2i8_nxv2i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e8,mf4,tu,mu
+; CHECK-NEXT:    vrgatherei16.vv v16, v17, v18, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 2 x i8> @llvm.riscv.vrgatherei16.mask.nxv2i8.nxv2i16(
+    <vscale x 2 x i8> %0,
+    <vscale x 2 x i8> %1,
+    <vscale x 2 x i16> %2,
+    <vscale x 2 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 2 x i8> %a
+}
+
+declare <vscale x 4 x i8> @llvm.riscv.vrgatherei16.nxv4i8.nxv4i16(
+  <vscale x 4 x i8>,
+  <vscale x 4 x i16>,
+  i64);
+
+define <vscale x 4 x i8> @intrinsic_vrgatherei16_vv_nxv4i8_nxv4i8_nxv4i16(<vscale x 4 x i8> %0, <vscale x 4 x i16> %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgatherei16_vv_nxv4i8_nxv4i8_nxv4i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e8,mf2,ta,mu
+; CHECK-NEXT:    vrgatherei16.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.vrgatherei16.nxv4i8.nxv4i16(
+    <vscale x 4 x i8> %0,
+    <vscale x 4 x i16> %1,
+    i64 %2)
+
+  ret <vscale x 4 x i8> %a
+}
+
+declare <vscale x 4 x i8> @llvm.riscv.vrgatherei16.mask.nxv4i8.nxv4i16(
+  <vscale x 4 x i8>,
+  <vscale x 4 x i8>,
+  <vscale x 4 x i16>,
+  <vscale x 4 x i1>,
+  i64);
+
+define <vscale x 4 x i8> @intrinsic_vrgatherei16_mask_vv_nxv4i8_nxv4i8_nxv4i16(<vscale x 4 x i8> %0, <vscale x 4 x i8> %1, <vscale x 4 x i16> %2, <vscale x 4 x i1> %3, i64 %4) nounwind {
+; CHECK-LABEL: intrinsic_vrgatherei16_mask_vv_nxv4i8_nxv4i8_nxv4i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e8,mf2,tu,mu
+; CHECK-NEXT:    vrgatherei16.vv v16, v17, v18, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 4 x i8> @llvm.riscv.vrgatherei16.mask.nxv4i8.nxv4i16(
+    <vscale x 4 x i8> %0,
+    <vscale x 4 x i8> %1,
+    <vscale x 4 x i16> %2,
+    <vscale x 4 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 4 x i8> %a
+}
+
+declare <vscale x 8 x i8> @llvm.riscv.vrgatherei16.nxv8i8.nxv8i16(
+  <vscale x 8 x i8>,
+  <vscale x 8 x i16>,
+  i64);
+
+define <vscale x 8 x i8> @intrinsic_vrgatherei16_vv_nxv8i8_nxv8i8_nxv8i16(<vscale x 8 x i8> %0, <vscale x 8 x i16> %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgatherei16_vv_nxv8i8_nxv8i8_nxv8i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e8,m1,ta,mu
+; CHECK-NEXT:    vrgatherei16.vv v25, v16, v18
+; CHECK-NEXT:    vmv1r.v v16, v25
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 8 x i8> @llvm.riscv.vrgatherei16.nxv8i8.nxv8i16(
+    <vscale x 8 x i8> %0,
+    <vscale x 8 x i16> %1,
+    i64 %2)
+
+  ret <vscale x 8 x i8> %a
+}
+
+declare <vscale x 8 x i8> @llvm.riscv.vrgatherei16.mask.nxv8i8.nxv8i16(
+  <vscale x 8 x i8>,
+  <vscale x 8 x i8>,
+  <vscale x 8 x i16>,
+  <vscale x 8 x i1>,
+  i64);
+
+define <vscale x 8 x i8> @intrinsic_vrgatherei16_mask_vv_nxv8i8_nxv8i8_nxv8i16(<vscale x 8 x i8> %0, <vscale x 8 x i8> %1, <vscale x 8 x i16> %2, <vscale x 8 x i1> %3, i64 %4) nounwind {
+; CHECK-LABEL: intrinsic_vrgatherei16_mask_vv_nxv8i8_nxv8i8_nxv8i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e8,m1,tu,mu
+; CHECK-NEXT:    vrgatherei16.vv v16, v17, v18, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 8 x i8> @llvm.riscv.vrgatherei16.mask.nxv8i8.nxv8i16(
+    <vscale x 8 x i8> %0,
+    <vscale x 8 x i8> %1,
+    <vscale x 8 x i16> %2,
+    <vscale x 8 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 8 x i8> %a
+}
+
+declare <vscale x 16 x i8> @llvm.riscv.vrgatherei16.nxv16i8.nxv16i16(
+  <vscale x 16 x i8>,
+  <vscale x 16 x i16>,
+  i64);
+
+define <vscale x 16 x i8> @intrinsic_vrgatherei16_vv_nxv16i8_nxv16i8_nxv16i16(<vscale x 16 x i8> %0, <vscale x 16 x i16> %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgatherei16_vv_nxv16i8_nxv16i8_nxv16i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e8,m2,ta,mu
+; CHECK-NEXT:    vrgatherei16.vv v26, v16, v20
+; CHECK-NEXT:    vmv2r.v v16, v26
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 16 x i8> @llvm.riscv.vrgatherei16.nxv16i8.nxv16i16(
+    <vscale x 16 x i8> %0,
+    <vscale x 16 x i16> %1,
+    i64 %2)
+
+  ret <vscale x 16 x i8> %a
+}
+
+declare <vscale x 16 x i8> @llvm.riscv.vrgatherei16.mask.nxv16i8.nxv16i16(
+  <vscale x 16 x i8>,
+  <vscale x 16 x i8>,
+  <vscale x 16 x i16>,
+  <vscale x 16 x i1>,
+  i64);
+
+define <vscale x 16 x i8> @intrinsic_vrgatherei16_mask_vv_nxv16i8_nxv16i8_nxv16i16(<vscale x 16 x i8> %0, <vscale x 16 x i8> %1, <vscale x 16 x i16> %2, <vscale x 16 x i1> %3, i64 %4) nounwind {
+; CHECK-LABEL: intrinsic_vrgatherei16_mask_vv_nxv16i8_nxv16i8_nxv16i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e8,m2,tu,mu
+; CHECK-NEXT:    vrgatherei16.vv v16, v18, v20, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 16 x i8> @llvm.riscv.vrgatherei16.mask.nxv16i8.nxv16i16(
+    <vscale x 16 x i8> %0,
+    <vscale x 16 x i8> %1,
+    <vscale x 16 x i16> %2,
+    <vscale x 16 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 16 x i8> %a
+}
+
+declare <vscale x 32 x i8> @llvm.riscv.vrgatherei16.nxv32i8.nxv32i16(
+  <vscale x 32 x i8>,
+  <vscale x 32 x i16>,
+  i64);
+
+define <vscale x 32 x i8> @intrinsic_vrgatherei16_vv_nxv32i8_nxv32i8_nxv32i16(<vscale x 32 x i8> %0, <vscale x 32 x i16> %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgatherei16_vv_nxv32i8_nxv32i8_nxv32i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a2, zero, e16,m8,ta,mu
+; CHECK-NEXT:    vle16.v v8, (a0)
+; CHECK-NEXT:    vsetvli a0, a1, e8,m4,ta,mu
+; CHECK-NEXT:    vrgatherei16.vv v28, v16, v8
+; CHECK-NEXT:    vmv4r.v v16, v28
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 32 x i8> @llvm.riscv.vrgatherei16.nxv32i8.nxv32i16(
+    <vscale x 32 x i8> %0,
+    <vscale x 32 x i16> %1,
+    i64 %2)
+
+  ret <vscale x 32 x i8> %a
+}
+
+declare <vscale x 32 x i8> @llvm.riscv.vrgatherei16.mask.nxv32i8.nxv32i16(
+  <vscale x 32 x i8>,
+  <vscale x 32 x i8>,
+  <vscale x 32 x i16>,
+  <vscale x 32 x i1>,
+  i64);
+
+define <vscale x 32 x i8> @intrinsic_vrgatherei16_mask_vv_nxv32i8_nxv32i8_nxv32i16(<vscale x 32 x i8> %0, <vscale x 32 x i8> %1, <vscale x 32 x i16> %2, <vscale x 32 x i1> %3, i64 %4) nounwind {
+; CHECK-LABEL: intrinsic_vrgatherei16_mask_vv_nxv32i8_nxv32i8_nxv32i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a2, zero, e16,m8,ta,mu
+; CHECK-NEXT:    vle16.v v8, (a0)
+; CHECK-NEXT:    vsetvli a0, a1, e8,m4,tu,mu
+; CHECK-NEXT:    vrgatherei16.vv v16, v20, v8, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 32 x i8> @llvm.riscv.vrgatherei16.mask.nxv32i8.nxv32i16(
+    <vscale x 32 x i8> %0,
+    <vscale x 32 x i8> %1,
+    <vscale x 32 x i16> %2,
+    <vscale x 32 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 32 x i8> %a
+}
+
+declare <vscale x 1 x i16> @llvm.riscv.vrgatherei16.nxv1i16.nxv1i16(
+  <vscale x 1 x i16>,
+  <vscale x 1 x i16>,
+  i64);
+
+define <vscale x 1 x i16> @intrinsic_vrgatherei16_vv_nxv1i16_nxv1i16_nxv1i16(<vscale x 1 x i16> %0, <vscale x 1 x i16> %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgatherei16_vv_nxv1i16_nxv1i16_nxv1i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e16,mf4,ta,mu
+; CHECK-NEXT:    vrgatherei16.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.vrgatherei16.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.vrgatherei16.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_vrgatherei16_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_vrgatherei16_mask_vv_nxv1i16_nxv1i16_nxv1i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e16,mf4,tu,mu
+; CHECK-NEXT:    vrgatherei16.vv v16, v17, v18, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 1 x i16> @llvm.riscv.vrgatherei16.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.vrgatherei16.nxv2i16.nxv2i16(
+  <vscale x 2 x i16>,
+  <vscale x 2 x i16>,
+  i64);
+
+define <vscale x 2 x i16> @intrinsic_vrgatherei16_vv_nxv2i16_nxv2i16_nxv2i16(<vscale x 2 x i16> %0, <vscale x 2 x i16> %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgatherei16_vv_nxv2i16_nxv2i16_nxv2i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e16,mf2,ta,mu
+; CHECK-NEXT:    vrgatherei16.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.vrgatherei16.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.vrgatherei16.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_vrgatherei16_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_vrgatherei16_mask_vv_nxv2i16_nxv2i16_nxv2i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e16,mf2,tu,mu
+; CHECK-NEXT:    vrgatherei16.vv v16, v17, v18, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 2 x i16> @llvm.riscv.vrgatherei16.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.vrgatherei16.nxv4i16.nxv4i16(
+  <vscale x 4 x i16>,
+  <vscale x 4 x i16>,
+  i64);
+
+define <vscale x 4 x i16> @intrinsic_vrgatherei16_vv_nxv4i16_nxv4i16_nxv4i16(<vscale x 4 x i16> %0, <vscale x 4 x i16> %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgatherei16_vv_nxv4i16_nxv4i16_nxv4i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e16,m1,ta,mu
+; CHECK-NEXT:    vrgatherei16.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.vrgatherei16.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.vrgatherei16.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_vrgatherei16_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_vrgatherei16_mask_vv_nxv4i16_nxv4i16_nxv4i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e16,m1,tu,mu
+; CHECK-NEXT:    vrgatherei16.vv v16, v17, v18, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 4 x i16> @llvm.riscv.vrgatherei16.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.vrgatherei16.nxv8i16.nxv8i16(
+  <vscale x 8 x i16>,
+  <vscale x 8 x i16>,
+  i64);
+
+define <vscale x 8 x i16> @intrinsic_vrgatherei16_vv_nxv8i16_nxv8i16_nxv8i16(<vscale x 8 x i16> %0, <vscale x 8 x i16> %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgatherei16_vv_nxv8i16_nxv8i16_nxv8i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e16,m2,ta,mu
+; CHECK-NEXT:    vrgatherei16.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.vrgatherei16.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.vrgatherei16.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_vrgatherei16_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_vrgatherei16_mask_vv_nxv8i16_nxv8i16_nxv8i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e16,m2,tu,mu
+; CHECK-NEXT:    vrgatherei16.vv v16, v18, v20, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 8 x i16> @llvm.riscv.vrgatherei16.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.vrgatherei16.nxv16i16.nxv16i16(
+  <vscale x 16 x i16>,
+  <vscale x 16 x i16>,
+  i64);
+
+define <vscale x 16 x i16> @intrinsic_vrgatherei16_vv_nxv16i16_nxv16i16_nxv16i16(<vscale x 16 x i16> %0, <vscale x 16 x i16> %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgatherei16_vv_nxv16i16_nxv16i16_nxv16i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e16,m4,ta,mu
+; CHECK-NEXT:    vrgatherei16.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.vrgatherei16.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.vrgatherei16.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_vrgatherei16_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_vrgatherei16_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,tu,mu
+; CHECK-NEXT:    vrgatherei16.vv v16, v20, v28, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 16 x i16> @llvm.riscv.vrgatherei16.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.vrgatherei16.nxv32i16.nxv32i16(
+  <vscale x 32 x i16>,
+  <vscale x 32 x i16>,
+  i64);
+
+define <vscale x 32 x i16> @intrinsic_vrgatherei16_vv_nxv32i16_nxv32i16_nxv32i16(<vscale x 32 x i16> %0, <vscale x 32 x i16> %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgatherei16_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:    vrgatherei16.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.vrgatherei16.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.vrgatherei16.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_vrgatherei16_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_vrgatherei16_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,tu,mu
+; CHECK-NEXT:    vrgatherei16.vv v16, v24, v8, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 32 x i16> @llvm.riscv.vrgatherei16.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.vrgatherei16.nxv1i32.nxv1i16(
+  <vscale x 1 x i32>,
+  <vscale x 1 x i16>,
+  i64);
+
+define <vscale x 1 x i32> @intrinsic_vrgatherei16_vv_nxv1i32_nxv1i32_nxv1i16(<vscale x 1 x i32> %0, <vscale x 1 x i16> %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgatherei16_vv_nxv1i32_nxv1i32_nxv1i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e32,mf2,ta,mu
+; CHECK-NEXT:    vrgatherei16.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.vrgatherei16.nxv1i32.nxv1i16(
+    <vscale x 1 x i32> %0,
+    <vscale x 1 x i16> %1,
+    i64 %2)
+
+  ret <vscale x 1 x i32> %a
+}
+
+declare <vscale x 1 x i32> @llvm.riscv.vrgatherei16.mask.nxv1i32.nxv1i16(
+  <vscale x 1 x i32>,
+  <vscale x 1 x i32>,
+  <vscale x 1 x i16>,
+  <vscale x 1 x i1>,
+  i64);
+
+define <vscale x 1 x i32> @intrinsic_vrgatherei16_mask_vv_nxv1i32_nxv1i32_nxv1i16(<vscale x 1 x i32> %0, <vscale x 1 x i32> %1, <vscale x 1 x i16> %2, <vscale x 1 x i1> %3, i64 %4) nounwind {
+; CHECK-LABEL: intrinsic_vrgatherei16_mask_vv_nxv1i32_nxv1i32_nxv1i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e32,mf2,tu,mu
+; CHECK-NEXT:    vrgatherei16.vv v16, v17, v18, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 1 x i32> @llvm.riscv.vrgatherei16.mask.nxv1i32.nxv1i16(
+    <vscale x 1 x i32> %0,
+    <vscale x 1 x i32> %1,
+    <vscale x 1 x i16> %2,
+    <vscale x 1 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 1 x i32> %a
+}
+
+declare <vscale x 4 x i32> @llvm.riscv.vrgatherei16.nxv4i32.nxv4i16(
+  <vscale x 4 x i32>,
+  <vscale x 4 x i16>,
+  i64);
+
+define <vscale x 4 x i32> @intrinsic_vrgatherei16_vv_nxv4i32_nxv4i32_nxv4i16(<vscale x 4 x i32> %0, <vscale x 4 x i16> %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgatherei16_vv_nxv4i32_nxv4i32_nxv4i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e32,m2,ta,mu
+; CHECK-NEXT:    vrgatherei16.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.vrgatherei16.nxv4i32.nxv4i16(
+    <vscale x 4 x i32> %0,
+    <vscale x 4 x i16> %1,
+    i64 %2)
+
+  ret <vscale x 4 x i32> %a
+}
+
+declare <vscale x 4 x i32> @llvm.riscv.vrgatherei16.mask.nxv4i32.nxv4i16(
+  <vscale x 4 x i32>,
+  <vscale x 4 x i32>,
+  <vscale x 4 x i16>,
+  <vscale x 4 x i1>,
+  i64);
+
+define <vscale x 4 x i32> @intrinsic_vrgatherei16_mask_vv_nxv4i32_nxv4i32_nxv4i16(<vscale x 4 x i32> %0, <vscale x 4 x i32> %1, <vscale x 4 x i16> %2, <vscale x 4 x i1> %3, i64 %4) nounwind {
+; CHECK-LABEL: intrinsic_vrgatherei16_mask_vv_nxv4i32_nxv4i32_nxv4i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e32,m2,tu,mu
+; CHECK-NEXT:    vrgatherei16.vv v16, v18, v20, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 4 x i32> @llvm.riscv.vrgatherei16.mask.nxv4i32.nxv4i16(
+    <vscale x 4 x i32> %0,
+    <vscale x 4 x i32> %1,
+    <vscale x 4 x i16> %2,
+    <vscale x 4 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 4 x i32> %a
+}
+
+declare <vscale x 8 x i32> @llvm.riscv.vrgatherei16.nxv8i32.nxv8i16(
+  <vscale x 8 x i32>,
+  <vscale x 8 x i16>,
+  i64);
+
+define <vscale x 8 x i32> @intrinsic_vrgatherei16_vv_nxv8i32_nxv8i32_nxv8i16(<vscale x 8 x i32> %0, <vscale x 8 x i16> %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgatherei16_vv_nxv8i32_nxv8i32_nxv8i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e32,m4,ta,mu
+; CHECK-NEXT:    vrgatherei16.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.vrgatherei16.nxv8i32.nxv8i16(
+    <vscale x 8 x i32> %0,
+    <vscale x 8 x i16> %1,
+    i64 %2)
+
+  ret <vscale x 8 x i32> %a
+}
+
+declare <vscale x 8 x i32> @llvm.riscv.vrgatherei16.mask.nxv8i32.nxv8i16(
+  <vscale x 8 x i32>,
+  <vscale x 8 x i32>,
+  <vscale x 8 x i16>,
+  <vscale x 8 x i1>,
+  i64);
+
+define <vscale x 8 x i32> @intrinsic_vrgatherei16_mask_vv_nxv8i32_nxv8i32_nxv8i16(<vscale x 8 x i32> %0, <vscale x 8 x i32> %1, <vscale x 8 x i16> %2, <vscale x 8 x i1> %3, i64 %4) nounwind {
+; CHECK-LABEL: intrinsic_vrgatherei16_mask_vv_nxv8i32_nxv8i32_nxv8i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a2, zero, e16,m2,ta,mu
+; CHECK-NEXT:    vle16.v v26, (a0)
+; CHECK-NEXT:    vsetvli a0, a1, e32,m4,tu,mu
+; CHECK-NEXT:    vrgatherei16.vv v16, v20, v26, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 8 x i32> @llvm.riscv.vrgatherei16.mask.nxv8i32.nxv8i16(
+    <vscale x 8 x i32> %0,
+    <vscale x 8 x i32> %1,
+    <vscale x 8 x i16> %2,
+    <vscale x 8 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 8 x i32> %a
+}
+
+declare <vscale x 16 x i32> @llvm.riscv.vrgatherei16.nxv16i32.nxv16i16(
+  <vscale x 16 x i32>,
+  <vscale x 16 x i16>,
+  i64);
+
+define <vscale x 16 x i32> @intrinsic_vrgatherei16_vv_nxv16i32_nxv16i32_nxv16i16(<vscale x 16 x i32> %0, <vscale x 16 x i16> %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgatherei16_vv_nxv16i32_nxv16i32_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, e32,m8,ta,mu
+; CHECK-NEXT:    vrgatherei16.vv v8, v16, v28
+; CHECK-NEXT:    vmv8r.v v16, v8
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 16 x i32> @llvm.riscv.vrgatherei16.nxv16i32.nxv16i16(
+    <vscale x 16 x i32> %0,
+    <vscale x 16 x i16> %1,
+    i64 %2)
+
+  ret <vscale x 16 x i32> %a
+}
+
+declare <vscale x 16 x i32> @llvm.riscv.vrgatherei16.mask.nxv16i32.nxv16i16(
+  <vscale x 16 x i32>,
+  <vscale x 16 x i32>,
+  <vscale x 16 x i16>,
+  <vscale x 16 x i1>,
+  i64);
+
+define <vscale x 16 x i32> @intrinsic_vrgatherei16_mask_vv_nxv16i32_nxv16i32_nxv16i16(<vscale x 16 x i32> %0, <vscale x 16 x i32> %1, <vscale x 16 x i16> %2, <vscale x 16 x i1> %3, i64 %4) nounwind {
+; CHECK-LABEL: intrinsic_vrgatherei16_mask_vv_nxv16i32_nxv16i32_nxv16i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a3, zero, e16,m4,ta,mu
+; CHECK-NEXT:    vle16.v v28, (a1)
+; CHECK-NEXT:    vsetvli a1, zero, e32,m8,ta,mu
+; CHECK-NEXT:    vle32.v v8, (a0)
+; CHECK-NEXT:    vsetvli a0, a2, e32,m8,tu,mu
+; CHECK-NEXT:    vrgatherei16.vv v16, v8, v28, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 16 x i32> @llvm.riscv.vrgatherei16.mask.nxv16i32.nxv16i16(
+    <vscale x 16 x i32> %0,
+    <vscale x 16 x i32> %1,
+    <vscale x 16 x i16> %2,
+    <vscale x 16 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 16 x i32> %a
+}
+
+declare <vscale x 4 x i64> @llvm.riscv.vrgatherei16.nxv4i64.nxv4i16(
+  <vscale x 4 x i64>,
+  <vscale x 4 x i16>,
+  i64);
+
+define <vscale x 4 x i64> @intrinsic_vrgatherei16_vv_nxv4i64_nxv4i64_nxv4i16(<vscale x 4 x i64> %0, <vscale x 4 x i16> %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgatherei16_vv_nxv4i64_nxv4i64_nxv4i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e64,m4,ta,mu
+; CHECK-NEXT:    vrgatherei16.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.vrgatherei16.nxv4i64.nxv4i16(
+    <vscale x 4 x i64> %0,
+    <vscale x 4 x i16> %1,
+    i64 %2)
+
+  ret <vscale x 4 x i64> %a
+}
+
+declare <vscale x 4 x i64> @llvm.riscv.vrgatherei16.mask.nxv4i64.nxv4i16(
+  <vscale x 4 x i64>,
+  <vscale x 4 x i64>,
+  <vscale x 4 x i16>,
+  <vscale x 4 x i1>,
+  i64);
+
+define <vscale x 4 x i64> @intrinsic_vrgatherei16_mask_vv_nxv4i64_nxv4i64_nxv4i16(<vscale x 4 x i64> %0, <vscale x 4 x i64> %1, <vscale x 4 x i16> %2, <vscale x 4 x i1> %3, i64 %4) nounwind {
+; CHECK-LABEL: intrinsic_vrgatherei16_mask_vv_nxv4i64_nxv4i64_nxv4i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a2, zero, e16,m1,ta,mu
+; CHECK-NEXT:    vle16.v v25, (a0)
+; CHECK-NEXT:    vsetvli a0, a1, e64,m4,tu,mu
+; CHECK-NEXT:    vrgatherei16.vv v16, v20, v25, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 4 x i64> @llvm.riscv.vrgatherei16.mask.nxv4i64.nxv4i16(
+    <vscale x 4 x i64> %0,
+    <vscale x 4 x i64> %1,
+    <vscale x 4 x i16> %2,
+    <vscale x 4 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 4 x i64> %a
+}
+
+declare <vscale x 8 x i64> @llvm.riscv.vrgatherei16.nxv8i64.nxv8i16(
+  <vscale x 8 x i64>,
+  <vscale x 8 x i16>,
+  i64);
+
+define <vscale x 8 x i64> @intrinsic_vrgatherei16_vv_nxv8i64_nxv8i64_nxv8i16(<vscale x 8 x i64> %0, <vscale x 8 x i16> %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgatherei16_vv_nxv8i64_nxv8i64_nxv8i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a2, zero, e16,m2,ta,mu
+; CHECK-NEXT:    vle16.v v26, (a0)
+; CHECK-NEXT:    vsetvli a0, a1, e64,m8,ta,mu
+; CHECK-NEXT:    vrgatherei16.vv v8, v16, v26
+; CHECK-NEXT:    vmv8r.v v16, v8
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 8 x i64> @llvm.riscv.vrgatherei16.nxv8i64.nxv8i16(
+    <vscale x 8 x i64> %0,
+    <vscale x 8 x i16> %1,
+    i64 %2)
+
+  ret <vscale x 8 x i64> %a
+}
+
+declare <vscale x 8 x i64> @llvm.riscv.vrgatherei16.mask.nxv8i64.nxv8i16(
+  <vscale x 8 x i64>,
+  <vscale x 8 x i64>,
+  <vscale x 8 x i16>,
+  <vscale x 8 x i1>,
+  i64);
+
+define <vscale x 8 x i64> @intrinsic_vrgatherei16_mask_vv_nxv8i64_nxv8i64_nxv8i16(<vscale x 8 x i64> %0, <vscale x 8 x i64> %1, <vscale x 8 x i16> %2, <vscale x 8 x i1> %3, i64 %4) nounwind {
+; CHECK-LABEL: intrinsic_vrgatherei16_mask_vv_nxv8i64_nxv8i64_nxv8i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a3, zero, e16,m2,ta,mu
+; CHECK-NEXT:    vle16.v v26, (a1)
+; CHECK-NEXT:    vsetvli a1, zero, e64,m8,ta,mu
+; CHECK-NEXT:    vle64.v v8, (a0)
+; CHECK-NEXT:    vsetvli a0, a2, e64,m8,tu,mu
+; CHECK-NEXT:    vrgatherei16.vv v16, v8, v26, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 8 x i64> @llvm.riscv.vrgatherei16.mask.nxv8i64.nxv8i16(
+    <vscale x 8 x i64> %0,
+    <vscale x 8 x i64> %1,
+    <vscale x 8 x i16> %2,
+    <vscale x 8 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 8 x i64> %a
+}
+
+declare <vscale x 1 x half> @llvm.riscv.vrgatherei16.nxv1f16.nxv1i16(
+  <vscale x 1 x half>,
+  <vscale x 1 x i16>,
+  i64);
+
+define <vscale x 1 x half> @intrinsic_vrgatherei16_vv_nxv1f16_nxv1f16_nxv1i16(<vscale x 1 x half> %0, <vscale x 1 x i16> %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgatherei16_vv_nxv1f16_nxv1f16_nxv1i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e16,mf4,ta,mu
+; CHECK-NEXT:    vrgatherei16.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.vrgatherei16.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.vrgatherei16.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_vrgatherei16_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_vrgatherei16_mask_vv_nxv1f16_nxv1f16_nxv1i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e16,mf4,tu,mu
+; CHECK-NEXT:    vrgatherei16.vv v16, v17, v18, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 1 x half> @llvm.riscv.vrgatherei16.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.vrgatherei16.nxv2f16.nxv2i16(
+  <vscale x 2 x half>,
+  <vscale x 2 x i16>,
+  i64);
+
+define <vscale x 2 x half> @intrinsic_vrgatherei16_vv_nxv2f16_nxv2f16_nxv2i16(<vscale x 2 x half> %0, <vscale x 2 x i16> %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgatherei16_vv_nxv2f16_nxv2f16_nxv2i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e16,mf2,ta,mu
+; CHECK-NEXT:    vrgatherei16.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.vrgatherei16.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.vrgatherei16.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_vrgatherei16_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_vrgatherei16_mask_vv_nxv2f16_nxv2f16_nxv2i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e16,mf2,tu,mu
+; CHECK-NEXT:    vrgatherei16.vv v16, v17, v18, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 2 x half> @llvm.riscv.vrgatherei16.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.vrgatherei16.nxv4f16.nxv4i16(
+  <vscale x 4 x half>,
+  <vscale x 4 x i16>,
+  i64);
+
+define <vscale x 4 x half> @intrinsic_vrgatherei16_vv_nxv4f16_nxv4f16_nxv4i16(<vscale x 4 x half> %0, <vscale x 4 x i16> %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgatherei16_vv_nxv4f16_nxv4f16_nxv4i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e16,m1,ta,mu
+; CHECK-NEXT:    vrgatherei16.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.vrgatherei16.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.vrgatherei16.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_vrgatherei16_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_vrgatherei16_mask_vv_nxv4f16_nxv4f16_nxv4i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e16,m1,tu,mu
+; CHECK-NEXT:    vrgatherei16.vv v16, v17, v18, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 4 x half> @llvm.riscv.vrgatherei16.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.vrgatherei16.nxv8f16.nxv8i16(
+  <vscale x 8 x half>,
+  <vscale x 8 x i16>,
+  i64);
+
+define <vscale x 8 x half> @intrinsic_vrgatherei16_vv_nxv8f16_nxv8f16_nxv8i16(<vscale x 8 x half> %0, <vscale x 8 x i16> %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgatherei16_vv_nxv8f16_nxv8f16_nxv8i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e16,m2,ta,mu
+; CHECK-NEXT:    vrgatherei16.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.vrgatherei16.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.vrgatherei16.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_vrgatherei16_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_vrgatherei16_mask_vv_nxv8f16_nxv8f16_nxv8i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e16,m2,tu,mu
+; CHECK-NEXT:    vrgatherei16.vv v16, v18, v20, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 8 x half> @llvm.riscv.vrgatherei16.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.vrgatherei16.nxv16f16.nxv16i16(
+  <vscale x 16 x half>,
+  <vscale x 16 x i16>,
+  i64);
+
+define <vscale x 16 x half> @intrinsic_vrgatherei16_vv_nxv16f16_nxv16f16_nxv16i16(<vscale x 16 x half> %0, <vscale x 16 x i16> %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgatherei16_vv_nxv16f16_nxv16f16_nxv16i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e16,m4,ta,mu
+; CHECK-NEXT:    vrgatherei16.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.vrgatherei16.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.vrgatherei16.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_vrgatherei16_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_vrgatherei16_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,tu,mu
+; CHECK-NEXT:    vrgatherei16.vv v16, v20, v28, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 16 x half> @llvm.riscv.vrgatherei16.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.vrgatherei16.nxv32f16.nxv32i16(
+  <vscale x 32 x half>,
+  <vscale x 32 x i16>,
+  i64);
+
+define <vscale x 32 x half> @intrinsic_vrgatherei16_vv_nxv32f16_nxv32f16_nxv32i16(<vscale x 32 x half> %0, <vscale x 32 x i16> %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgatherei16_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:    vrgatherei16.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.vrgatherei16.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.vrgatherei16.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_vrgatherei16_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_vrgatherei16_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,tu,mu
+; CHECK-NEXT:    vrgatherei16.vv v16, v24, v8, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 32 x half> @llvm.riscv.vrgatherei16.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.vrgatherei16.nxv1f32.nxv1i16(
+  <vscale x 1 x float>,
+  <vscale x 1 x i16>,
+  i64);
+
+define <vscale x 1 x float> @intrinsic_vrgatherei16_vv_nxv1f32_nxv1f32_nxv1i16(<vscale x 1 x float> %0, <vscale x 1 x i16> %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgatherei16_vv_nxv1f32_nxv1f32_nxv1i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e32,mf2,ta,mu
+; CHECK-NEXT:    vrgatherei16.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.vrgatherei16.nxv1f32.nxv1i16(
+    <vscale x 1 x float> %0,
+    <vscale x 1 x i16> %1,
+    i64 %2)
+
+  ret <vscale x 1 x float> %a
+}
+
+declare <vscale x 1 x float> @llvm.riscv.vrgatherei16.mask.nxv1f32.nxv1i16(
+  <vscale x 1 x float>,
+  <vscale x 1 x float>,
+  <vscale x 1 x i16>,
+  <vscale x 1 x i1>,
+  i64);
+
+define <vscale x 1 x float> @intrinsic_vrgatherei16_mask_vv_nxv1f32_nxv1f32_nxv1i16(<vscale x 1 x float> %0, <vscale x 1 x float> %1, <vscale x 1 x i16> %2, <vscale x 1 x i1> %3, i64 %4) nounwind {
+; CHECK-LABEL: intrinsic_vrgatherei16_mask_vv_nxv1f32_nxv1f32_nxv1i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e32,mf2,tu,mu
+; CHECK-NEXT:    vrgatherei16.vv v16, v17, v18, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 1 x float> @llvm.riscv.vrgatherei16.mask.nxv1f32.nxv1i16(
+    <vscale x 1 x float> %0,
+    <vscale x 1 x float> %1,
+    <vscale x 1 x i16> %2,
+    <vscale x 1 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 1 x float> %a
+}
+
+declare <vscale x 4 x float> @llvm.riscv.vrgatherei16.nxv4f32.nxv4i16(
+  <vscale x 4 x float>,
+  <vscale x 4 x i16>,
+  i64);
+
+define <vscale x 4 x float> @intrinsic_vrgatherei16_vv_nxv4f32_nxv4f32_nxv4i16(<vscale x 4 x float> %0, <vscale x 4 x i16> %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgatherei16_vv_nxv4f32_nxv4f32_nxv4i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e32,m2,ta,mu
+; CHECK-NEXT:    vrgatherei16.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.vrgatherei16.nxv4f32.nxv4i16(
+    <vscale x 4 x float> %0,
+    <vscale x 4 x i16> %1,
+    i64 %2)
+
+  ret <vscale x 4 x float> %a
+}
+
+declare <vscale x 4 x float> @llvm.riscv.vrgatherei16.mask.nxv4f32.nxv4i16(
+  <vscale x 4 x float>,
+  <vscale x 4 x float>,
+  <vscale x 4 x i16>,
+  <vscale x 4 x i1>,
+  i64);
+
+define <vscale x 4 x float> @intrinsic_vrgatherei16_mask_vv_nxv4f32_nxv4f32_nxv4i16(<vscale x 4 x float> %0, <vscale x 4 x float> %1, <vscale x 4 x i16> %2, <vscale x 4 x i1> %3, i64 %4) nounwind {
+; CHECK-LABEL: intrinsic_vrgatherei16_mask_vv_nxv4f32_nxv4f32_nxv4i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e32,m2,tu,mu
+; CHECK-NEXT:    vrgatherei16.vv v16, v18, v20, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 4 x float> @llvm.riscv.vrgatherei16.mask.nxv4f32.nxv4i16(
+    <vscale x 4 x float> %0,
+    <vscale x 4 x float> %1,
+    <vscale x 4 x i16> %2,
+    <vscale x 4 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 4 x float> %a
+}
+
+declare <vscale x 8 x float> @llvm.riscv.vrgatherei16.nxv8f32.nxv8i16(
+  <vscale x 8 x float>,
+  <vscale x 8 x i16>,
+  i64);
+
+define <vscale x 8 x float> @intrinsic_vrgatherei16_vv_nxv8f32_nxv8f32_nxv8i16(<vscale x 8 x float> %0, <vscale x 8 x i16> %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgatherei16_vv_nxv8f32_nxv8f32_nxv8i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e32,m4,ta,mu
+; CHECK-NEXT:    vrgatherei16.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.vrgatherei16.nxv8f32.nxv8i16(
+    <vscale x 8 x float> %0,
+    <vscale x 8 x i16> %1,
+    i64 %2)
+
+  ret <vscale x 8 x float> %a
+}
+
+declare <vscale x 8 x float> @llvm.riscv.vrgatherei16.mask.nxv8f32.nxv8i16(
+  <vscale x 8 x float>,
+  <vscale x 8 x float>,
+  <vscale x 8 x i16>,
+  <vscale x 8 x i1>,
+  i64);
+
+define <vscale x 8 x float> @intrinsic_vrgatherei16_mask_vv_nxv8f32_nxv8f32_nxv8i16(<vscale x 8 x float> %0, <vscale x 8 x float> %1, <vscale x 8 x i16> %2, <vscale x 8 x i1> %3, i64 %4) nounwind {
+; CHECK-LABEL: intrinsic_vrgatherei16_mask_vv_nxv8f32_nxv8f32_nxv8i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a2, zero, e16,m2,ta,mu
+; CHECK-NEXT:    vle16.v v26, (a0)
+; CHECK-NEXT:    vsetvli a0, a1, e32,m4,tu,mu
+; CHECK-NEXT:    vrgatherei16.vv v16, v20, v26, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 8 x float> @llvm.riscv.vrgatherei16.mask.nxv8f32.nxv8i16(
+    <vscale x 8 x float> %0,
+    <vscale x 8 x float> %1,
+    <vscale x 8 x i16> %2,
+    <vscale x 8 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 8 x float> %a
+}
+
+declare <vscale x 16 x float> @llvm.riscv.vrgatherei16.nxv16f32.nxv16i16(
+  <vscale x 16 x float>,
+  <vscale x 16 x i16>,
+  i64);
+
+define <vscale x 16 x float> @intrinsic_vrgatherei16_vv_nxv16f32_nxv16f32_nxv16i16(<vscale x 16 x float> %0, <vscale x 16 x i16> %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgatherei16_vv_nxv16f32_nxv16f32_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, e32,m8,ta,mu
+; CHECK-NEXT:    vrgatherei16.vv v8, v16, v28
+; CHECK-NEXT:    vmv8r.v v16, v8
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 16 x float> @llvm.riscv.vrgatherei16.nxv16f32.nxv16i16(
+    <vscale x 16 x float> %0,
+    <vscale x 16 x i16> %1,
+    i64 %2)
+
+  ret <vscale x 16 x float> %a
+}
+
+declare <vscale x 16 x float> @llvm.riscv.vrgatherei16.mask.nxv16f32.nxv16i16(
+  <vscale x 16 x float>,
+  <vscale x 16 x float>,
+  <vscale x 16 x i16>,
+  <vscale x 16 x i1>,
+  i64);
+
+define <vscale x 16 x float> @intrinsic_vrgatherei16_mask_vv_nxv16f32_nxv16f32_nxv16i16(<vscale x 16 x float> %0, <vscale x 16 x float> %1, <vscale x 16 x i16> %2, <vscale x 16 x i1> %3, i64 %4) nounwind {
+; CHECK-LABEL: intrinsic_vrgatherei16_mask_vv_nxv16f32_nxv16f32_nxv16i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a3, zero, e16,m4,ta,mu
+; CHECK-NEXT:    vle16.v v28, (a1)
+; CHECK-NEXT:    vsetvli a1, zero, e32,m8,ta,mu
+; CHECK-NEXT:    vle32.v v8, (a0)
+; CHECK-NEXT:    vsetvli a0, a2, e32,m8,tu,mu
+; CHECK-NEXT:    vrgatherei16.vv v16, v8, v28, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 16 x float> @llvm.riscv.vrgatherei16.mask.nxv16f32.nxv16i16(
+    <vscale x 16 x float> %0,
+    <vscale x 16 x float> %1,
+    <vscale x 16 x i16> %2,
+    <vscale x 16 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 16 x float> %a
+}
+
+declare <vscale x 4 x double> @llvm.riscv.vrgatherei16.nxv4f64.nxv4i16(
+  <vscale x 4 x double>,
+  <vscale x 4 x i16>,
+  i64);
+
+define <vscale x 4 x double> @intrinsic_vrgatherei16_vv_nxv4f64_nxv4f64_nxv4i16(<vscale x 4 x double> %0, <vscale x 4 x i16> %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgatherei16_vv_nxv4f64_nxv4f64_nxv4i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a0, a0, e64,m4,ta,mu
+; CHECK-NEXT:    vrgatherei16.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.vrgatherei16.nxv4f64.nxv4i16(
+    <vscale x 4 x double> %0,
+    <vscale x 4 x i16> %1,
+    i64 %2)
+
+  ret <vscale x 4 x double> %a
+}
+
+declare <vscale x 4 x double> @llvm.riscv.vrgatherei16.mask.nxv4f64.nxv4i16(
+  <vscale x 4 x double>,
+  <vscale x 4 x double>,
+  <vscale x 4 x i16>,
+  <vscale x 4 x i1>,
+  i64);
+
+define <vscale x 4 x double> @intrinsic_vrgatherei16_mask_vv_nxv4f64_nxv4f64_nxv4i16(<vscale x 4 x double> %0, <vscale x 4 x double> %1, <vscale x 4 x i16> %2, <vscale x 4 x i1> %3, i64 %4) nounwind {
+; CHECK-LABEL: intrinsic_vrgatherei16_mask_vv_nxv4f64_nxv4f64_nxv4i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a2, zero, e16,m1,ta,mu
+; CHECK-NEXT:    vle16.v v25, (a0)
+; CHECK-NEXT:    vsetvli a0, a1, e64,m4,tu,mu
+; CHECK-NEXT:    vrgatherei16.vv v16, v20, v25, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 4 x double> @llvm.riscv.vrgatherei16.mask.nxv4f64.nxv4i16(
+    <vscale x 4 x double> %0,
+    <vscale x 4 x double> %1,
+    <vscale x 4 x i16> %2,
+    <vscale x 4 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 4 x double> %a
+}
+
+declare <vscale x 8 x double> @llvm.riscv.vrgatherei16.nxv8f64.nxv8i16(
+  <vscale x 8 x double>,
+  <vscale x 8 x i16>,
+  i64);
+
+define <vscale x 8 x double> @intrinsic_vrgatherei16_vv_nxv8f64_nxv8f64_nxv8i16(<vscale x 8 x double> %0, <vscale x 8 x i16> %1, i64 %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgatherei16_vv_nxv8f64_nxv8f64_nxv8i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a2, zero, e16,m2,ta,mu
+; CHECK-NEXT:    vle16.v v26, (a0)
+; CHECK-NEXT:    vsetvli a0, a1, e64,m8,ta,mu
+; CHECK-NEXT:    vrgatherei16.vv v8, v16, v26
+; CHECK-NEXT:    vmv8r.v v16, v8
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 8 x double> @llvm.riscv.vrgatherei16.nxv8f64.nxv8i16(
+    <vscale x 8 x double> %0,
+    <vscale x 8 x i16> %1,
+    i64 %2)
+
+  ret <vscale x 8 x double> %a
+}
+
+declare <vscale x 8 x double> @llvm.riscv.vrgatherei16.mask.nxv8f64.nxv8i16(
+  <vscale x 8 x double>,
+  <vscale x 8 x double>,
+  <vscale x 8 x i16>,
+  <vscale x 8 x i1>,
+  i64);
+
+define <vscale x 8 x double> @intrinsic_vrgatherei16_mask_vv_nxv8f64_nxv8f64_nxv8i16(<vscale x 8 x double> %0, <vscale x 8 x double> %1, <vscale x 8 x i16> %2, <vscale x 8 x i1> %3, i64 %4) nounwind {
+; CHECK-LABEL: intrinsic_vrgatherei16_mask_vv_nxv8f64_nxv8f64_nxv8i16:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vsetvli a3, zero, e16,m2,ta,mu
+; CHECK-NEXT:    vle16.v v26, (a1)
+; CHECK-NEXT:    vsetvli a1, zero, e64,m8,ta,mu
+; CHECK-NEXT:    vle64.v v8, (a0)
+; CHECK-NEXT:    vsetvli a0, a2, e64,m8,tu,mu
+; CHECK-NEXT:    vrgatherei16.vv v16, v8, v26, v0.t
+; CHECK-NEXT:    jalr zero, 0(ra)
+entry:
+  %a = call <vscale x 8 x double> @llvm.riscv.vrgatherei16.mask.nxv8f64.nxv8i16(
+    <vscale x 8 x double> %0,
+    <vscale x 8 x double> %1,
+    <vscale x 8 x i16> %2,
+    <vscale x 8 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 8 x double> %a
+}