diff --git a/llvm/lib/Target/RISCV/GISel/RISCVInstructionSelector.cpp b/llvm/lib/Target/RISCV/GISel/RISCVInstructionSelector.cpp
index 4f2e633c1c524..c252875f05dca 100644
--- a/llvm/lib/Target/RISCV/GISel/RISCVInstructionSelector.cpp
+++ b/llvm/lib/Target/RISCV/GISel/RISCVInstructionSelector.cpp
@@ -100,7 +100,7 @@ class RISCVInstructionSelector : public InstructionSelector {
   bool selectIntrinsicWithSideEffects(MachineInstr &I,
                                       MachineIRBuilder &MIB) const;
   bool selectExtractSubvector(MachineInstr &MI, MachineIRBuilder &MIB) const;
-
+  bool selectInsertSubVector(MachineInstr &I, MachineIRBuilder &MIB) const;
   ComplexRendererFns selectShiftMask(MachineOperand &Root,
                                      unsigned ShiftWidth) const;
   ComplexRendererFns selectShiftMaskXLen(MachineOperand &Root) const {
@@ -1007,6 +1007,66 @@ bool RISCVInstructionSelector::selectExtractSubvector(
   return true;
 }
 
+bool RISCVInstructionSelector::selectInsertSubVector(
+    MachineInstr &MI, MachineIRBuilder &MIB) const {
+  assert(MI.getOpcode() == TargetOpcode::G_INSERT_SUBVECTOR);
+
+  Register DstReg = MI.getOperand(0).getReg();
+  Register VecReg = MI.getOperand(1).getReg();
+  Register SubVecReg = MI.getOperand(2).getReg();
+
+  LLT VecTy = MRI->getType(VecReg);
+  LLT SubVecTy = MRI->getType(SubVecReg);
+
+  MVT VecMVT = getMVTForLLT(VecTy);
+  MVT SubVecMVT = getMVTForLLT(SubVecTy);
+
+  unsigned Idx = static_cast<unsigned>(MI.getOperand(3).getImm());
+
+  unsigned SubRegIdx;
+  std::tie(SubRegIdx, Idx) =
+      RISCVTargetLowering::decomposeSubvectorInsertExtractToSubRegs(
+          VecMVT, SubVecMVT, Idx, &TRI);
+
+  // If the Idx hasn't been completely eliminated then this is a subvector
+  // insert which doesn't naturally align to a vector register. These must
+  // be handled using instructions to manipulate the vector registers.
+  if (Idx != 0)
+    return false;
+
+  RISCVVType::VLMUL SubVecLMUL = RISCVTargetLowering::getLMUL(SubVecMVT);
+  [[maybe_unused]] bool IsSubVecPartReg =
+      SubVecLMUL == RISCVVType::VLMUL::LMUL_F2 ||
+      SubVecLMUL == RISCVVType::VLMUL::LMUL_F4 ||
+      SubVecLMUL == RISCVVType::VLMUL::LMUL_F8;
+
+  // Constrain dst
+  unsigned DstRegClassID = RISCVTargetLowering::getRegClassIDForVecVT(VecMVT);
+  const TargetRegisterClass *DstRC = TRI.getRegClass(DstRegClassID);
+  if (!RBI.constrainGenericRegister(DstReg, *DstRC, *MRI))
+    return false;
+
+  // If we haven't set a SubRegIdx, then we must be going between
+  // equally-sized LMUL groups (e.g. VR -> VR). This can be done as a copy.
+  if (SubRegIdx == RISCV::NoSubRegister) {
+    assert(RISCVTargetLowering::getRegClassIDForVecVT(SubVecMVT) ==
+               DstRegClassID &&
+           "Unexpected subvector insert");
+    MIB.buildInstr(TargetOpcode::COPY, {DstReg}, {}).addReg(SubVecReg);
+    MI.eraseFromParent();
+    return true;
+  }
+
+  // Use INSERT_SUBREG to insert the subvector into the vector at the
+  // appropriate subregister index.
+  auto Ins =
+      MIB.buildInstr(TargetOpcode::INSERT_SUBREG, {DstReg}, {VecReg, SubVecReg})
+          .addImm(SubRegIdx);
+
+  MI.eraseFromParent();
+  return constrainSelectedInstRegOperands(*Ins, TII, TRI, RBI);
+}
+
 bool RISCVInstructionSelector::select(MachineInstr &MI) {
   MachineIRBuilder MIB(MI);
 
@@ -1281,6 +1341,8 @@ bool RISCVInstructionSelector::select(MachineInstr &MI) {
     return selectIntrinsicWithSideEffects(MI, MIB);
   case TargetOpcode::G_EXTRACT_SUBVECTOR:
     return selectExtractSubvector(MI, MIB);
+  case TargetOpcode::G_INSERT_SUBVECTOR:
+    return selectInsertSubVector(MI, MIB);
   default:
     return false;
   }
diff --git a/llvm/lib/Target/RISCV/RISCVISelLowering.cpp b/llvm/lib/Target/RISCV/RISCVISelLowering.cpp
index 7cbb9c0da4874..f56922828cb41 100644
--- a/llvm/lib/Target/RISCV/RISCVISelLowering.cpp
+++ b/llvm/lib/Target/RISCV/RISCVISelLowering.cpp
@@ -25587,7 +25587,8 @@ bool RISCVTargetLowering::fallBackToDAGISel(const Instruction &Inst) const {
 
       return false;
     }
-    if (II->getIntrinsicID() == Intrinsic::vector_extract)
+    if (II->getIntrinsicID() == Intrinsic::vector_extract ||
+        II->getIntrinsicID() == Intrinsic::vector_insert)
       return false;
   }
 
diff --git a/llvm/test/CodeGen/RISCV/GlobalISel/rvv/insert-subvector.ll b/llvm/test/CodeGen/RISCV/GlobalISel/rvv/insert-subvector.ll
new file mode 100644
index 0000000000000..571e3bd25d1b0
--- /dev/null
+++ b/llvm/test/CodeGen/RISCV/GlobalISel/rvv/insert-subvector.ll
@@ -0,0 +1,411 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc -mtriple=riscv32 -global-isel -mattr=+m,+d,+zvfh,+v,+zvfbfmin -verify-machineinstrs < %s | FileCheck %s
+; RUN: llc -mtriple=riscv64 -global-isel -mattr=+m,+d,+zvfh,+v,+zvfbfmin -verify-machineinstrs < %s | FileCheck %s
+
+define <vscale x 8 x i32> @insert_nxv8i32_nxv4i32_0(<vscale x 8 x i32> %vec, <vscale x 4 x i32> %subvec) {
+; CHECK-LABEL: insert_nxv8i32_nxv4i32_0:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 1, e8, m1, ta, ma
+; CHECK-NEXT:    vmv2r.v v8, v12
+; CHECK-NEXT:    ret
+  %v = call <vscale x 8 x i32> @llvm.vector.insert.nxv4i32.nxv8i32(<vscale x 8 x i32> %vec, <vscale x 4 x i32> %subvec, i64 0)
+  ret <vscale x 8 x i32> %v
+}
+
+define <vscale x 8 x i32> @insert_nxv8i32_nxv4i32_4(<vscale x 8 x i32> %vec, <vscale x 4 x i32> %subvec) {
+; CHECK-LABEL: insert_nxv8i32_nxv4i32_4:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 1, e8, m1, ta, ma
+; CHECK-NEXT:    vmv2r.v v10, v12
+; CHECK-NEXT:    ret
+  %v = call <vscale x 8 x i32> @llvm.vector.insert.nxv4i32.nxv8i32(<vscale x 8 x i32> %vec, <vscale x 4 x i32> %subvec, i64 4)
+  ret <vscale x 8 x i32> %v
+}
+
+define <vscale x 8 x i32> @insert_nxv8i32_nxv2i32_0(<vscale x 8 x i32> %vec, <vscale x 2 x i32> %subvec) {
+; CHECK-LABEL: insert_nxv8i32_nxv2i32_0:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 1, e8, m1, ta, ma
+; CHECK-NEXT:    vmv1r.v v8, v12
+; CHECK-NEXT:    ret
+  %v = call <vscale x 8 x i32> @llvm.vector.insert.nxv2i32.nxv8i32(<vscale x 8 x i32> %vec, <vscale x 2 x i32> %subvec, i64 0)
+  ret <vscale x 8 x i32> %v
+}
+
+define <vscale x 8 x i32> @insert_nxv8i32_nxv2i32_2(<vscale x 8 x i32> %vec, <vscale x 2 x i32> %subvec) {
+; CHECK-LABEL: insert_nxv8i32_nxv2i32_2:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 1, e8, m1, ta, ma
+; CHECK-NEXT:    vmv1r.v v9, v12
+; CHECK-NEXT:    ret
+  %v = call <vscale x 8 x i32> @llvm.vector.insert.nxv2i32.nxv8i32(<vscale x 8 x i32> %vec, <vscale x 2 x i32> %subvec, i64 2)
+  ret <vscale x 8 x i32> %v
+}
+
+define <vscale x 8 x i32> @insert_nxv8i32_nxv2i32_4(<vscale x 8 x i32> %vec, <vscale x 2 x i32> %subvec) {
+; CHECK-LABEL: insert_nxv8i32_nxv2i32_4:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 1, e8, m1, ta, ma
+; CHECK-NEXT:    vmv1r.v v10, v12
+; CHECK-NEXT:    ret
+  %v = call <vscale x 8 x i32> @llvm.vector.insert.nxv2i32.nxv8i32(<vscale x 8 x i32> %vec, <vscale x 2 x i32> %subvec, i64 4)
+  ret <vscale x 8 x i32> %v
+}
+
+define <vscale x 8 x i32> @insert_nxv8i32_nxv2i32_6(<vscale x 8 x i32> %vec, <vscale x 2 x i32> %subvec) {
+; CHECK-LABEL: insert_nxv8i32_nxv2i32_6:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 1, e8, m1, ta, ma
+; CHECK-NEXT:    vmv1r.v v11, v12
+; CHECK-NEXT:    ret
+  %v = call <vscale x 8 x i32> @llvm.vector.insert.nxv2i32.nxv8i32(<vscale x 8 x i32> %vec, <vscale x 2 x i32> %subvec, i64 6)
+  ret <vscale x 8 x i32> %v
+}
+
+define <vscale x 4 x i8> @insert_nxv1i8_nxv4i8_0(<vscale x 4 x i8> %vec, <vscale x 1 x i8> %subvec) {
+; CHECK-LABEL: insert_nxv1i8_nxv4i8_0:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    csrr a0, vlenb
+; CHECK-NEXT:    srli a0, a0, 3
+; CHECK-NEXT:    vsetvli zero, a0, e8, mf2, tu, ma
+; CHECK-NEXT:    vmv.v.v v8, v9
+; CHECK-NEXT:    ret
+  %v = call <vscale x 4 x i8> @llvm.vector.insert.nxv1i8.nxv4i8(<vscale x 4 x i8> %vec, <vscale x 1 x i8> %subvec, i64 0)
+  ret <vscale x 4 x i8> %v
+}
+
+define <vscale x 4 x i8> @insert_nxv1i8_nxv4i8_3(<vscale x 4 x i8> %vec, <vscale x 1 x i8> %subvec) {
+; CHECK-LABEL: insert_nxv1i8_nxv4i8_3:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    csrr a0, vlenb
+; CHECK-NEXT:    li a1, 3
+; CHECK-NEXT:    srli a0, a0, 3
+; CHECK-NEXT:    mul a1, a0, a1
+; CHECK-NEXT:    add a0, a1, a0
+; CHECK-NEXT:    vsetvli zero, a0, e8, mf2, ta, ma
+; CHECK-NEXT:    vslideup.vx v8, v9, a1
+; CHECK-NEXT:    ret
+  %v = call <vscale x 4 x i8> @llvm.vector.insert.nxv1i8.nxv4i8(<vscale x 4 x i8> %vec, <vscale x 1 x i8> %subvec, i64 3)
+  ret <vscale x 4 x i8> %v
+}
+
+define <vscale x 16 x i32> @insert_nxv16i32_nxv8i32_0(<vscale x 16 x i32> %vec, <vscale x 8 x i32> %subvec) {
+; CHECK-LABEL: insert_nxv16i32_nxv8i32_0:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 1, e8, m1, ta, ma
+; CHECK-NEXT:    vmv4r.v v8, v16
+; CHECK-NEXT:    ret
+  %v = call <vscale x 16 x i32> @llvm.vector.insert.nxv8i32.nxv16i32(<vscale x 16 x i32> %vec, <vscale x 8 x i32> %subvec, i64 0)
+  ret <vscale x 16 x i32> %v
+}
+
+define <vscale x 16 x i32> @insert_nxv16i32_nxv8i32_8(<vscale x 16 x i32> %vec, <vscale x 8 x i32> %subvec) {
+; CHECK-LABEL: insert_nxv16i32_nxv8i32_8:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 1, e8, m1, ta, ma
+; CHECK-NEXT:    vmv4r.v v12, v16
+; CHECK-NEXT:    ret
+  %v = call <vscale x 16 x i32> @llvm.vector.insert.nxv8i32.nxv16i32(<vscale x 16 x i32> %vec, <vscale x 8 x i32> %subvec, i64 8)
+  ret <vscale x 16 x i32> %v
+}
+
+define <vscale x 16 x i32> @insert_nxv16i32_nxv4i32_0(<vscale x 16 x i32> %vec, <vscale x 4 x i32> %subvec) {
+; CHECK-LABEL: insert_nxv16i32_nxv4i32_0:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 1, e8, m1, ta, ma
+; CHECK-NEXT:    vmv2r.v v8, v16
+; CHECK-NEXT:    ret
+  %v = call <vscale x 16 x i32> @llvm.vector.insert.nxv4i32.nxv16i32(<vscale x 16 x i32> %vec, <vscale x 4 x i32> %subvec, i64 0)
+  ret <vscale x 16 x i32> %v
+}
+
+define <vscale x 16 x i32> @insert_nxv16i32_nxv4i32_4(<vscale x 16 x i32> %vec, <vscale x 4 x i32> %subvec) {
+; CHECK-LABEL: insert_nxv16i32_nxv4i32_4:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 1, e8, m1, ta, ma
+; CHECK-NEXT:    vmv2r.v v10, v16
+; CHECK-NEXT:    ret
+  %v = call <vscale x 16 x i32> @llvm.vector.insert.nxv4i32.nxv16i32(<vscale x 16 x i32> %vec, <vscale x 4 x i32> %subvec, i64 4)
+  ret <vscale x 16 x i32> %v
+}
+
+define <vscale x 16 x i32> @insert_nxv16i32_nxv4i32_8(<vscale x 16 x i32> %vec, <vscale x 4 x i32> %subvec) {
+; CHECK-LABEL: insert_nxv16i32_nxv4i32_8:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 1, e8, m1, ta, ma
+; CHECK-NEXT:    vmv2r.v v12, v16
+; CHECK-NEXT:    ret
+  %v = call <vscale x 16 x i32> @llvm.vector.insert.nxv4i32.nxv16i32(<vscale x 16 x i32> %vec, <vscale x 4 x i32> %subvec, i64 8)
+  ret <vscale x 16 x i32> %v
+}
+
+define <vscale x 16 x i32> @insert_nxv16i32_nxv4i32_12(<vscale x 16 x i32> %vec, <vscale x 4 x i32> %subvec) {
+; CHECK-LABEL: insert_nxv16i32_nxv4i32_12:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 1, e8, m1, ta, ma
+; CHECK-NEXT:    vmv2r.v v14, v16
+; CHECK-NEXT:    ret
+  %v = call <vscale x 16 x i32> @llvm.vector.insert.nxv4i32.nxv16i32(<vscale x 16 x i32> %vec, <vscale x 4 x i32> %subvec, i64 12)
+  ret <vscale x 16 x i32> %v
+}
+
+define <vscale x 16 x i32> @insert_nxv16i32_nxv2i32_0(<vscale x 16 x i32> %vec, <vscale x 2 x i32> %subvec) {
+; CHECK-LABEL: insert_nxv16i32_nxv2i32_0:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 1, e8, m1, ta, ma
+; CHECK-NEXT:    vmv1r.v v8, v16
+; CHECK-NEXT:    ret
+  %v = call <vscale x 16 x i32> @llvm.vector.insert.nxv2i32.nxv16i32(<vscale x 16 x i32> %vec, <vscale x 2 x i32> %subvec, i64 0)
+  ret <vscale x 16 x i32> %v
+}
+
+define <vscale x 16 x i32> @insert_nxv16i32_nxv2i32_2(<vscale x 16 x i32> %vec, <vscale x 2 x i32> %subvec) {
+; CHECK-LABEL: insert_nxv16i32_nxv2i32_2:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 1, e8, m1, ta, ma
+; CHECK-NEXT:    vmv1r.v v9, v16
+; CHECK-NEXT:    ret
+  %v = call <vscale x 16 x i32> @llvm.vector.insert.nxv2i32.nxv16i32(<vscale x 16 x i32> %vec, <vscale x 2 x i32> %subvec, i64 2)
+  ret <vscale x 16 x i32> %v
+}
+
+define <vscale x 16 x i32> @insert_nxv16i32_nxv2i32_4(<vscale x 16 x i32> %vec, <vscale x 2 x i32> %subvec) {
+; CHECK-LABEL: insert_nxv16i32_nxv2i32_4:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 1, e8, m1, ta, ma
+; CHECK-NEXT:    vmv1r.v v10, v16
+; CHECK-NEXT:    ret
+  %v = call <vscale x 16 x i32> @llvm.vector.insert.nxv2i32.nxv16i32(<vscale x 16 x i32> %vec, <vscale x 2 x i32> %subvec, i64 4)
+  ret <vscale x 16 x i32> %v
+}
+
+define <vscale x 16 x i32> @insert_nxv16i32_nxv2i32_6(<vscale x 16 x i32> %vec, <vscale x 2 x i32> %subvec) {
+; CHECK-LABEL: insert_nxv16i32_nxv2i32_6:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 1, e8, m1, ta, ma
+; CHECK-NEXT:    vmv1r.v v11, v16
+; CHECK-NEXT:    ret
+  %v = call <vscale x 16 x i32> @llvm.vector.insert.nxv2i32.nxv16i32(<vscale x 16 x i32> %vec, <vscale x 2 x i32> %subvec, i64 6)
+  ret <vscale x 16 x i32> %v
+}
+
+define <vscale x 16 x i32> @insert_nxv16i32_nxv2i32_8(<vscale x 16 x i32> %vec, <vscale x 2 x i32> %subvec) {
+; CHECK-LABEL: insert_nxv16i32_nxv2i32_8:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 1, e8, m1, ta, ma
+; CHECK-NEXT:    vmv1r.v v12, v16
+; CHECK-NEXT:    ret
+  %v = call <vscale x 16 x i32> @llvm.vector.insert.nxv2i32.nxv16i32(<vscale x 16 x i32> %vec, <vscale x 2 x i32> %subvec, i64 8)
+  ret <vscale x 16 x i32> %v
+}
+
+define <vscale x 16 x i32> @insert_nxv16i32_nxv2i32_10(<vscale x 16 x i32> %vec, <vscale x 2 x i32> %subvec) {
+; CHECK-LABEL: insert_nxv16i32_nxv2i32_10:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 1, e8, m1, ta, ma
+; CHECK-NEXT:    vmv1r.v v13, v16
+; CHECK-NEXT:    ret
+  %v = call <vscale x 16 x i32> @llvm.vector.insert.nxv2i32.nxv16i32(<vscale x 16 x i32> %vec, <vscale x 2 x i32> %subvec, i64 10)
+  ret <vscale x 16 x i32> %v
+}
+
+define <vscale x 16 x i32> @insert_nxv16i32_nxv2i32_12(<vscale x 16 x i32> %vec, <vscale x 2 x i32> %subvec) {
+; CHECK-LABEL: insert_nxv16i32_nxv2i32_12:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 1, e8, m1, ta, ma
+; CHECK-NEXT:    vmv1r.v v14, v16
+; CHECK-NEXT:    ret
+  %v = call <vscale x 16 x i32> @llvm.vector.insert.nxv2i32.nxv16i32(<vscale x 16 x i32> %vec, <vscale x 2 x i32> %subvec, i64 12)
+  ret <vscale x 16 x i32> %v
+}
+
+define <vscale x 16 x i32> @insert_nxv16i32_nxv2i32_14(<vscale x 16 x i32> %vec, <vscale x 2 x i32> %subvec) {
+; CHECK-LABEL: insert_nxv16i32_nxv2i32_14:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 1, e8, m1, ta, ma
+; CHECK-NEXT:    vmv1r.v v15, v16
+; CHECK-NEXT:    ret
+  %v = call <vscale x 16 x i32> @llvm.vector.insert.nxv2i32.nxv16i32(<vscale x 16 x i32> %vec, <vscale x 2 x i32> %subvec, i64 14)
+  ret <vscale x 16 x i32> %v
+}
+
+define <vscale x 16 x i32> @insert_nxv16i32_nxv1i32_0(<vscale x 16 x i32> %vec, <vscale x 1 x i32> %subvec) {
+; CHECK-LABEL: insert_nxv16i32_nxv1i32_0:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    csrr a0, vlenb
+; CHECK-NEXT:    srli a0, a0, 3
+; CHECK-NEXT:    vsetvli zero, a0, e32, m1, tu, ma
+; CHECK-NEXT:    vmv.v.v v8, v16
+; CHECK-NEXT:    ret
+  %v = call <vscale x 16 x i32> @llvm.vector.insert.nxv1i32.nxv16i32(<vscale x 16 x i32> %vec, <vscale x 1 x i32> %subvec, i64 0)
+  ret <vscale x 16 x i32> %v
+}
+
+define <vscale x 16 x i32> @insert_nxv16i32_nxv1i32_1(<vscale x 16 x i32> %vec, <vscale x 1 x i32> %subvec) {
+; CHECK-LABEL: insert_nxv16i32_nxv1i32_1:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    csrr a0, vlenb
+; CHECK-NEXT:    srli a0, a0, 3
+; CHECK-NEXT:    add a1, a0, a0
+; CHECK-NEXT:    vsetvli zero, a1, e32, m1, ta, ma
+; CHECK-NEXT:    vslideup.vx v8, v16, a0
+; CHECK-NEXT:    ret
+  %v = call <vscale x 16 x i32> @llvm.vector.insert.nxv1i32.nxv16i32(<vscale x 16 x i32> %vec, <vscale x 1 x i32> %subvec, i64 1)
+  ret <vscale x 16 x i32> %v
+}
+
+define <vscale x 16 x i32> @insert_nxv16i32_nxv1i32_6(<vscale x 16 x i32> %vec, <vscale x 1 x i32> %subvec) {
+; CHECK-LABEL: insert_nxv16i32_nxv1i32_6:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    csrr a0, vlenb
+; CHECK-NEXT:    srli a0, a0, 3
+; CHECK-NEXT:    vsetvli zero, a0, e32, m1, tu, ma
+; CHECK-NEXT:    vmv.v.v v11, v16
+; CHECK-NEXT:    ret
+  %v = call <vscale x 16 x i32> @llvm.vector.insert.nxv1i32.nxv16i32(<vscale x 16 x i32> %vec, <vscale x 1 x i32> %subvec, i64 6)
+  ret <vscale x 16 x i32> %v
+}
+
+define <vscale x 16 x i8> @insert_nxv16i8_nxv1i8_0(<vscale x 16 x i8> %vec, <vscale x 1 x i8> %subvec) {
+; CHECK-LABEL: insert_nxv16i8_nxv1i8_0:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    csrr a0, vlenb
+; CHECK-NEXT:    srli a0, a0, 3
+; CHECK-NEXT:    vsetvli zero, a0, e8, m1, tu, ma
+; CHECK-NEXT:    vmv.v.v v8, v10
+; CHECK-NEXT:    ret
+  %v = call <vscale x 16 x i8> @llvm.vector.insert.nxv1i8.nxv16i8(<vscale x 16 x i8> %vec, <vscale x 1 x i8> %subvec, i64 0)
+  ret <vscale x 16 x i8> %v
+}
+
+define <vscale x 16 x i8> @insert_nxv16i8_nxv1i8_1(<vscale x 16 x i8> %vec, <vscale x 1 x i8> %subvec) {
+; CHECK-LABEL: insert_nxv16i8_nxv1i8_1:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    csrr a0, vlenb
+; CHECK-NEXT:    srli a0, a0, 3
+; CHECK-NEXT:    add a1, a0, a0
+; CHECK-NEXT:    vsetvli zero, a1, e8, m1, tu, ma
+; CHECK-NEXT:    vslideup.vx v8, v10, a0
+; CHECK-NEXT:    ret
+  %v = call <vscale x 16 x i8> @llvm.vector.insert.nxv1i8.nxv16i8(<vscale x 16 x i8> %vec, <vscale x 1 x i8> %subvec, i64 1)
+  ret <vscale x 16 x i8> %v
+}
+
+define <vscale x 16 x i8> @insert_nxv16i8_nxv1i8_2(<vscale x 16 x i8> %vec, <vscale x 1 x i8> %subvec) {
+; CHECK-LABEL: insert_nxv16i8_nxv1i8_2:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    csrr a0, vlenb
+; CHECK-NEXT:    srli a1, a0, 3
+; CHECK-NEXT:    srli a0, a0, 2
+; CHECK-NEXT:    add a1, a0, a1
+; CHECK-NEXT:    vsetvli zero, a1, e8, m1, tu, ma
+; CHECK-NEXT:    vslideup.vx v8, v10, a0
+; CHECK-NEXT:    ret
+  %v = call <vscale x 16 x i8> @llvm.vector.insert.nxv1i8.nxv16i8(<vscale x 16 x i8> %vec, <vscale x 1 x i8> %subvec, i64 2)
+  ret <vscale x 16 x i8> %v
+}
+
+define <vscale x 16 x i8> @insert_nxv16i8_nxv1i8_3(<vscale x 16 x i8> %vec, <vscale x 1 x i8> %subvec) {
+; CHECK-LABEL: insert_nxv16i8_nxv1i8_3:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    csrr a0, vlenb
+; CHECK-NEXT:    li a1, 3
+; CHECK-NEXT:    srli a0, a0, 3
+; CHECK-NEXT:    mul a1, a0, a1
+; CHECK-NEXT:    add a0, a1, a0
+; CHECK-NEXT:    vsetvli zero, a0, e8, m1, tu, ma
+; CHECK-NEXT:    vslideup.vx v8, v10, a1
+; CHECK-NEXT:    ret
+  %v = call <vscale x 16 x i8> @llvm.vector.insert.nxv1i8.nxv16i8(<vscale x 16 x i8> %vec, <vscale x 1 x i8> %subvec, i64 3)
+  ret <vscale x 16 x i8> %v
+}
+
+define <vscale x 16 x i8> @insert_nxv16i8_nxv1i8_7(<vscale x 16 x i8> %vec, <vscale x 1 x i8> %subvec) {
+; CHECK-LABEL: insert_nxv16i8_nxv1i8_7:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    csrr a0, vlenb
+; CHECK-NEXT:    srli a0, a0, 3
+; CHECK-NEXT:    li a1, 7
+; CHECK-NEXT:    mul a1, a0, a1
+; CHECK-NEXT:    add a0, a1, a0
+; CHECK-NEXT:    vsetvli zero, a0, e8, m1, ta, ma
+; CHECK-NEXT:    vslideup.vx v8, v10, a1
+; CHECK-NEXT:    ret
+  %v = call <vscale x 16 x i8> @llvm.vector.insert.nxv1i8.nxv16i8(<vscale x 16 x i8> %vec, <vscale x 1 x i8> %subvec, i64 7)
+  ret <vscale x 16 x i8> %v
+}
+
+define <vscale x 16 x i8> @insert_nxv16i8_nxv1i8_15(<vscale x 16 x i8> %vec, <vscale x 1 x i8> %subvec) {
+; CHECK-LABEL: insert_nxv16i8_nxv1i8_15:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    csrr a0, vlenb
+; CHECK-NEXT:    srli a0, a0, 3
+; CHECK-NEXT:    li a1, 7
+; CHECK-NEXT:    mul a1, a0, a1
+; CHECK-NEXT:    add a0, a1, a0
+; CHECK-NEXT:    vsetvli zero, a0, e8, m1, ta, ma
+; CHECK-NEXT:    vslideup.vx v9, v10, a1
+; CHECK-NEXT:    ret
+  %v = call <vscale x 16 x i8> @llvm.vector.insert.nxv1i8.nxv16i8(<vscale x 16 x i8> %vec, <vscale x 1 x i8> %subvec, i64 15)
+  ret <vscale x 16 x i8> %v
+}
+
+define <vscale x 32 x half> @insert_nxv32f16_nxv2f16_0(<vscale x 32 x half> %vec, <vscale x 2 x half> %subvec) {
+; CHECK-LABEL: insert_nxv32f16_nxv2f16_0:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    csrr a0, vlenb
+; CHECK-NEXT:    srli a0, a0, 2
+; CHECK-NEXT:    vsetvli zero, a0, e16, m1, tu, ma
+; CHECK-NEXT:    vmv.v.v v8, v16
+; CHECK-NEXT:    ret
+  %v = call <vscale x 32 x half> @llvm.vector.insert.nxv2f16.nxv32f16(<vscale x 32 x half> %vec, <vscale x 2 x half> %subvec, i64 0)
+  ret <vscale x 32 x half> %v
+}
+
+define <vscale x 32 x half> @insert_nxv32f16_nxv2f16_2(<vscale x 32 x half> %vec, <vscale x 2 x half> %subvec) {
+; CHECK-LABEL: insert_nxv32f16_nxv2f16_2:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    csrr a0, vlenb
+; CHECK-NEXT:    srli a0, a0, 2
+; CHECK-NEXT:    add a1, a0, a0
+; CHECK-NEXT:    vsetvli zero, a1, e16, m1, ta, ma
+; CHECK-NEXT:    vslideup.vx v8, v16, a0
+; CHECK-NEXT:    ret
+  %v = call <vscale x 32 x half> @llvm.vector.insert.nxv2f16.nxv32f16(<vscale x 32 x half> %vec, <vscale x 2 x half> %subvec, i64 2)
+  ret <vscale x 32 x half> %v
+}
+
+define <vscale x 32 x half> @insert_nxv32f16_nxv2f16_26(<vscale x 32 x half> %vec, <vscale x 2 x half> %subvec) {
+; CHECK-LABEL: insert_nxv32f16_nxv2f16_26:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    csrr a0, vlenb
+; CHECK-NEXT:    srli a0, a0, 2
+; CHECK-NEXT:    add a1, a0, a0
+; CHECK-NEXT:    vsetvli zero, a1, e16, m1, ta, ma
+; CHECK-NEXT:    vslideup.vx v14, v16, a0
+; CHECK-NEXT:    ret
+  %v = call <vscale x 32 x half> @llvm.vector.insert.nxv2f16.nxv32f16(<vscale x 32 x half> %vec, <vscale x 2 x half> %subvec, i64 26)
+  ret <vscale x 32 x half> %v
+}
+
+define <vscale x 32 x half> @insert_nxv32f16_undef_nxv1f16_0(<vscale x 1 x half> %subvec) {
+; CHECK-LABEL: insert_nxv32f16_undef_nxv1f16_0:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    ret
+  %v = call <vscale x 32 x half> @llvm.vector.insert.nxv1f16.nxv32f16(<vscale x 32 x half> poison, <vscale x 1 x half> %subvec, i64 0)
+  ret <vscale x 32 x half> %v
+}
+
+define <vscale x 32 x half> @insert_nxv32f16_undef_nxv1f16_26(<vscale x 1 x half> %subvec) {
+; CHECK-LABEL: insert_nxv32f16_undef_nxv1f16_26:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    csrr a0, vlenb
+; CHECK-NEXT:    srli a1, a0, 3
+; CHECK-NEXT:    srli a0, a0, 2
+; CHECK-NEXT:    add a1, a0, a1
+; CHECK-NEXT:    vsetvli zero, a1, e16, m1, ta, ma
+; CHECK-NEXT:    vslideup.vx v14, v8, a0
+; CHECK-NEXT:    ret
+  %v = call <vscale x 32 x half> @llvm.vector.insert.nxv1f16.nxv32f16(<vscale x 32 x half> poison, <vscale x 1 x half> %subvec, i64 26)
+  ret <vscale x 32 x half> %v
+}