From bea661d9a52f9abb4fef7cf195092e912c165d34 Mon Sep 17 00:00:00 2001
From: ShihPo Hung <shihpo.hung@sifive.com>
Date: Mon, 18 Jan 2021 18:44:59 -0800
Subject: [PATCH] [RISCV] Add intrinsics for RVV 1.0 vrgatherei16

Reviewed By: craig.topper

Differential Revision: https://reviews.llvm.org/D95014
---
 llvm/include/llvm/IR/IntrinsicsRISCV.td       |    1 +
 .../Target/RISCV/RISCVInstrInfoVPseudos.td    |   53 +
 .../CodeGen/RISCV/rvv/vrgatherei16-rv32.ll    | 1272 +++++++++++++++
 .../CodeGen/RISCV/rvv/vrgatherei16-rv64.ll    | 1364 +++++++++++++++++
 4 files changed, 2690 insertions(+)
 create mode 100644 llvm/test/CodeGen/RISCV/rvv/vrgatherei16-rv32.ll
 create mode 100644 llvm/test/CodeGen/RISCV/rvv/vrgatherei16-rv64.ll

diff --git a/llvm/include/llvm/IR/IntrinsicsRISCV.td b/llvm/include/llvm/IR/IntrinsicsRISCV.td
index 659010399977..cda0c86f0048 100644
--- a/llvm/include/llvm/IR/IntrinsicsRISCV.td
+++ b/llvm/include/llvm/IR/IntrinsicsRISCV.td
@@ -885,6 +885,7 @@ let TargetPrefix = "riscv" in {
   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
index 4650c75b77fc..fd563f010cae 100644
--- a/llvm/lib/Target/RISCV/RISCVInstrInfoVPseudos.td
+++ b/llvm/lib/Target/RISCV/RISCVInstrInfoVPseudos.td
@@ -1266,11 +1266,40 @@ multiclass VPseudoBinary<VReg RetClass,
   }
 }
 
+multiclass VPseudoBinaryEmul<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 emulMX = octuple_to_str<octuple_emul>.ret;
+        defvar emul = !cast<LMULInfo>("V_" # emulMX);
+        defm _VV : VPseudoBinaryEmul<m.vrclass, m.vrclass, emul.vrclass, m, emul, Constraint>;
+      }
+    }
+  }
+}
+
 multiclass VPseudoBinaryV_VX<bit IsFloat, string Constraint = ""> {
   foreach m = MxList.m in
     defm !if(IsFloat, "_VF", "_VX") : VPseudoBinary<m.vrclass, m.vrclass,
@@ -2236,6 +2265,25 @@ multiclass VPatBinaryV_VV_INT<string intrinsic, string instruction,
   }
 }
 
+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);
+      defvar inst = instruction # "_VV_" # vti.LMul.MX # "_" # emul_str;
+      defm : VPatBinary<intrinsic, inst,
+                        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 {
@@ -3403,6 +3451,7 @@ let Predicates = [HasStdExtV, HasStdExtF] in {
 // 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
@@ -4081,11 +4130,15 @@ let Predicates = [HasStdExtV, HasStdExtF] in {
 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
index 000000000000..50dcdded0287
--- /dev/null
+++ b/llvm/test/CodeGen/RISCV/rvv/vrgatherei16-rv32.ll
@@ -0,0 +1,1272 @@
+; 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, v8, v9
+; CHECK-NEXT:    vmv1r.v v8, 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 v8, v9, v10, 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, v8, v9
+; CHECK-NEXT:    vmv1r.v v8, 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 v8, v9, v10, 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, v8, v9
+; CHECK-NEXT:    vmv1r.v v8, 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 v8, v9, v10, 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, v8, v10
+; CHECK-NEXT:    vmv1r.v v8, 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 v8, v9, v10, 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, v8, v12
+; CHECK-NEXT:    vmv2r.v v8, 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 v8, v10, v12, 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 a0, a0, e8,m4,ta,mu
+; CHECK-NEXT:    vrgatherei16.vv v28, v8, v16
+; CHECK-NEXT:    vmv4r.v v8, 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 a0, a0, e8,m4,tu,mu
+; CHECK-NEXT:    vrgatherei16.vv v8, v12, v16, 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, v8, v9
+; CHECK-NEXT:    vmv1r.v v8, 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 v8, v9, v10, 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, v8, v9
+; CHECK-NEXT:    vmv1r.v v8, 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 v8, v9, v10, 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, v8, v9
+; CHECK-NEXT:    vmv1r.v v8, 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 v8, v9, v10, 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, v8, v10
+; CHECK-NEXT:    vmv2r.v v8, 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 v8, v10, v12, 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, v8, v12
+; CHECK-NEXT:    vmv4r.v v8, 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 a0, a0, e16,m4,tu,mu
+; CHECK-NEXT:    vrgatherei16.vv v8, v12, v16, 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 a0, a0, e16,m8,ta,mu
+; CHECK-NEXT:    vrgatherei16.vv v24, v8, v16
+; CHECK-NEXT:    vmv8r.v v8, v24
+; 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 a2, zero, e16,m8,ta,mu
+; CHECK-NEXT:    vle16.v v24, (a0)
+; CHECK-NEXT:    vsetvli a0, a1, e16,m8,tu,mu
+; CHECK-NEXT:    vrgatherei16.vv v8, v16, v24, 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, v8, v9
+; CHECK-NEXT:    vmv1r.v v8, 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 v8, v9, v10, 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, v8, v10
+; CHECK-NEXT:    vmv2r.v v8, 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 v8, v10, v12, 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, v8, v12
+; CHECK-NEXT:    vmv4r.v v8, 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 a0, a0, e32,m4,tu,mu
+; CHECK-NEXT:    vrgatherei16.vv v8, v12, v16, 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 a0, a0, e32,m8,ta,mu
+; CHECK-NEXT:    vrgatherei16.vv v24, v8, v16
+; CHECK-NEXT:    vmv8r.v v8, v24
+; 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 a2, zero, e16,m4,ta,mu
+; CHECK-NEXT:    vle16.v v28, (a0)
+; CHECK-NEXT:    vsetvli a0, a1, e32,m8,tu,mu
+; CHECK-NEXT:    vrgatherei16.vv v8, v16, 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, v8, v9
+; CHECK-NEXT:    vmv1r.v v8, 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 v8, v9, v10, 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, v8, v9
+; CHECK-NEXT:    vmv1r.v v8, 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 v8, v9, v10, 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, v8, v9
+; CHECK-NEXT:    vmv1r.v v8, 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 v8, v9, v10, 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, v8, v10
+; CHECK-NEXT:    vmv2r.v v8, 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 v8, v10, v12, 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, v8, v12
+; CHECK-NEXT:    vmv4r.v v8, 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 a0, a0, e16,m4,tu,mu
+; CHECK-NEXT:    vrgatherei16.vv v8, v12, v16, 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 a0, a0, e16,m8,ta,mu
+; CHECK-NEXT:    vrgatherei16.vv v24, v8, v16
+; CHECK-NEXT:    vmv8r.v v8, v24
+; 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 a2, zero, e16,m8,ta,mu
+; CHECK-NEXT:    vle16.v v24, (a0)
+; CHECK-NEXT:    vsetvli a0, a1, e16,m8,tu,mu
+; CHECK-NEXT:    vrgatherei16.vv v8, v16, v24, 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, v8, v9
+; CHECK-NEXT:    vmv1r.v v8, 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 v8, v9, v10, 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, v8, v10
+; CHECK-NEXT:    vmv2r.v v8, 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 v8, v10, v12, 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, v8, v12
+; CHECK-NEXT:    vmv4r.v v8, 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 a0, a0, e32,m4,tu,mu
+; CHECK-NEXT:    vrgatherei16.vv v8, v12, v16, 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 a0, a0, e32,m8,ta,mu
+; CHECK-NEXT:    vrgatherei16.vv v24, v8, v16
+; CHECK-NEXT:    vmv8r.v v8, v24
+; 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 a2, zero, e16,m4,ta,mu
+; CHECK-NEXT:    vle16.v v28, (a0)
+; CHECK-NEXT:    vsetvli a0, a1, e32,m8,tu,mu
+; CHECK-NEXT:    vrgatherei16.vv v8, v16, 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, v8, v12
+; CHECK-NEXT:    vmv4r.v v8, 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 a0, a0, e64,m4,tu,mu
+; CHECK-NEXT:    vrgatherei16.vv v8, v12, v16, 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 a0, a0, e64,m8,ta,mu
+; CHECK-NEXT:    vrgatherei16.vv v24, v8, v16
+; CHECK-NEXT:    vmv8r.v v8, v24
+; 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 a2, zero, e16,m2,ta,mu
+; CHECK-NEXT:    vle16.v v26, (a0)
+; CHECK-NEXT:    vsetvli a0, a1, e64,m8,tu,mu
+; CHECK-NEXT:    vrgatherei16.vv v8, v16, 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
index 000000000000..db5e0efadfbb
--- /dev/null
+++ b/llvm/test/CodeGen/RISCV/rvv/vrgatherei16-rv64.ll
@@ -0,0 +1,1364 @@
+; 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, v8, v9
+; CHECK-NEXT:    vmv1r.v v8, 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 v8, v9, v10, 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, v8, v9
+; CHECK-NEXT:    vmv1r.v v8, 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 v8, v9, v10, 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, v8, v9
+; CHECK-NEXT:    vmv1r.v v8, 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 v8, v9, v10, 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, v8, v10
+; CHECK-NEXT:    vmv1r.v v8, 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 v8, v9, v10, 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, v8, v12
+; CHECK-NEXT:    vmv2r.v v8, 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 v8, v10, v12, 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 a0, a0, e8,m4,ta,mu
+; CHECK-NEXT:    vrgatherei16.vv v28, v8, v16
+; CHECK-NEXT:    vmv4r.v v8, 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 a0, a0, e8,m4,tu,mu
+; CHECK-NEXT:    vrgatherei16.vv v8, v12, v16, 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, v8, v9
+; CHECK-NEXT:    vmv1r.v v8, 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 v8, v9, v10, 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, v8, v9
+; CHECK-NEXT:    vmv1r.v v8, 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 v8, v9, v10, 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, v8, v9
+; CHECK-NEXT:    vmv1r.v v8, 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 v8, v9, v10, 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, v8, v10
+; CHECK-NEXT:    vmv2r.v v8, 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 v8, v10, v12, 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, v8, v12
+; CHECK-NEXT:    vmv4r.v v8, 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 a0, a0, e16,m4,tu,mu
+; CHECK-NEXT:    vrgatherei16.vv v8, v12, v16, 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 a0, a0, e16,m8,ta,mu
+; CHECK-NEXT:    vrgatherei16.vv v24, v8, v16
+; CHECK-NEXT:    vmv8r.v v8, v24
+; 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 a2, zero, e16,m8,ta,mu
+; CHECK-NEXT:    vle16.v v24, (a0)
+; CHECK-NEXT:    vsetvli a0, a1, e16,m8,tu,mu
+; CHECK-NEXT:    vrgatherei16.vv v8, v16, v24, 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, v8, v9
+; CHECK-NEXT:    vmv1r.v v8, 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 v8, v9, v10, 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, v8, v10
+; CHECK-NEXT:    vmv2r.v v8, 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 v8, v10, v12, 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, v8, v12
+; CHECK-NEXT:    vmv4r.v v8, 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 a0, a0, e32,m4,tu,mu
+; CHECK-NEXT:    vrgatherei16.vv v8, v12, v16, 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 a0, a0, e32,m8,ta,mu
+; CHECK-NEXT:    vrgatherei16.vv v24, v8, v16
+; CHECK-NEXT:    vmv8r.v v8, v24
+; 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 a2, zero, e16,m4,ta,mu
+; CHECK-NEXT:    vle16.v v28, (a0)
+; CHECK-NEXT:    vsetvli a0, a1, e32,m8,tu,mu
+; CHECK-NEXT:    vrgatherei16.vv v8, v16, 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, v8, v12
+; CHECK-NEXT:    vmv4r.v v8, 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 a0, a0, e64,m4,tu,mu
+; CHECK-NEXT:    vrgatherei16.vv v8, v12, v16, 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 a0, a0, e64,m8,ta,mu
+; CHECK-NEXT:    vrgatherei16.vv v24, v8, v16
+; CHECK-NEXT:    vmv8r.v v8, v24
+; 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 a2, zero, e16,m2,ta,mu
+; CHECK-NEXT:    vle16.v v26, (a0)
+; CHECK-NEXT:    vsetvli a0, a1, e64,m8,tu,mu
+; CHECK-NEXT:    vrgatherei16.vv v8, v16, 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, v8, v9
+; CHECK-NEXT:    vmv1r.v v8, 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 v8, v9, v10, 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, v8, v9
+; CHECK-NEXT:    vmv1r.v v8, 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 v8, v9, v10, 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, v8, v9
+; CHECK-NEXT:    vmv1r.v v8, 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 v8, v9, v10, 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, v8, v10
+; CHECK-NEXT:    vmv2r.v v8, 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 v8, v10, v12, 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, v8, v12
+; CHECK-NEXT:    vmv4r.v v8, 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 a0, a0, e16,m4,tu,mu
+; CHECK-NEXT:    vrgatherei16.vv v8, v12, v16, 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 a0, a0, e16,m8,ta,mu
+; CHECK-NEXT:    vrgatherei16.vv v24, v8, v16
+; CHECK-NEXT:    vmv8r.v v8, v24
+; 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 a2, zero, e16,m8,ta,mu
+; CHECK-NEXT:    vle16.v v24, (a0)
+; CHECK-NEXT:    vsetvli a0, a1, e16,m8,tu,mu
+; CHECK-NEXT:    vrgatherei16.vv v8, v16, v24, 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, v8, v9
+; CHECK-NEXT:    vmv1r.v v8, 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 v8, v9, v10, 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, v8, v10
+; CHECK-NEXT:    vmv2r.v v8, 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 v8, v10, v12, 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, v8, v12
+; CHECK-NEXT:    vmv4r.v v8, 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 a0, a0, e32,m4,tu,mu
+; CHECK-NEXT:    vrgatherei16.vv v8, v12, v16, 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 a0, a0, e32,m8,ta,mu
+; CHECK-NEXT:    vrgatherei16.vv v24, v8, v16
+; CHECK-NEXT:    vmv8r.v v8, v24
+; 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 a2, zero, e16,m4,ta,mu
+; CHECK-NEXT:    vle16.v v28, (a0)
+; CHECK-NEXT:    vsetvli a0, a1, e32,m8,tu,mu
+; CHECK-NEXT:    vrgatherei16.vv v8, v16, 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, v8, v12
+; CHECK-NEXT:    vmv4r.v v8, 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 a0, a0, e64,m4,tu,mu
+; CHECK-NEXT:    vrgatherei16.vv v8, v12, v16, 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 a0, a0, e64,m8,ta,mu
+; CHECK-NEXT:    vrgatherei16.vv v24, v8, v16
+; CHECK-NEXT:    vmv8r.v v8, v24
+; 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 a2, zero, e16,m2,ta,mu
+; CHECK-NEXT:    vle16.v v26, (a0)
+; CHECK-NEXT:    vsetvli a0, a1, e64,m8,tu,mu
+; CHECK-NEXT:    vrgatherei16.vv v8, v16, 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
+}