[VP][RISCV] Add vp.ctpop and RISC-V support.

[fakepaper56]

Summary

The patch also adds expandVPCTPOP in TargetLowering to expand VP_CTPOP nodes.

[craig.topper]

LGTM

llvm/docs/LangRef.rst

 intrinsic returns an i32 value that has the four bytes of the input i32
 swapped, so that if the input bytes are numbered 0, 1, 2, 3 then the
 returned i32 will have its bytes in 3, 2, 1, 0 order. The
 ``llvm.bswap.i48``, ``llvm.bswap.i64`` and other intrinsics extend this
 concept to additional even-byte lengths (6 bytes, 8 bytes and more,
 respectively). The vector intrinsics, such as ``llvm.bswap.v4i32``,
 operate on a per-element basis and the element order is not affected.
 
+.. _int_ctpop:
+
 '``llvm.ctpop.*``' Intrinsic
 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
 
 Syntax:
 """""""
 
 This is an overloaded intrinsic. You can use llvm.ctpop on any integer
 bit width, or on any vector with integer elements. Not all targets
.. code-block:: llvm
 
       %r = call <4 x i32> @llvm.vp.bswap.v4i32(<4 x i32> %a, <4 x i1> %mask, i32 %evl)
       ;; For all lanes below %evl, %r is lane-wise equivalent to %also.r
 
       %t = call <4 x i32> @llvm.bswap.v4i32(<4 x i32> %a)
       %also.r = select <4 x i1> %mask, <4 x i32> %t, <4 x i32> poison
 
 
+.. _int_vp_ctpop:
+
+'``llvm.vp.ctpop.*``' Intrinsics
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+Syntax:
+"""""""
+This is an overloaded intrinsic.
+
+::
+
+      declare <16 x i32>  @llvm.vp.ctpop.v16i32 (<16 x i32> <op>, <16 x i1> <mask>, i32 <vector_length>)
+      declare <vscale x 4 x i32>  @llvm.vp.ctpop.nxv4i32 (<vscale x 4 x i32> <op>, <vscale x 4 x i1> <mask>, i32 <vector_length>)
+      declare <256 x i64>  @llvm.vp.ctpop.v256i64 (<256 x i64> <op>, <256 x i1> <mask>, i32 <vector_length>)
+
+Overview:
+"""""""""
+
+Predicated ctpop of a vector of integers.
+
+
+Arguments:
+""""""""""
+
+The first operand and the result have the same vector of integer type. The
+second operand is the vector mask and has the same number of elements as the
+result vector type. The third operand is the explicit vector length of the
+operation.
+
+Semantics:
+""""""""""
+
+The '``llvm.vp.ctpop``' intrinsic performs ctpop (:ref:`ctpop <int_ctpop>`) of the first operand on each
+enabled lane.  The result on disabled lanes is a :ref:`poison value <poisonvalues>`.
+
+Examples:
+"""""""""
+
+.. code-block:: llvm
+
+      %r = call <4 x i32> @llvm.vp.ctpop.v4i32(<4 x i32> %a, <4 x i1> %mask, i32 %evl)
+      ;; For all lanes below %evl, %r is lane-wise equivalent to %also.r
+
+      %t = call <4 x i32> @llvm.ctpop.v4i32(<4 x i32> %a)
+      %also.r = select <4 x i1> %mask, <4 x i32> %t, <4 x i32> poison
+
+
 .. _int_vp_fshl:
 
 '``llvm.vp.fshl.*``' Intrinsics
 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
 
 Syntax:
 """""""
 This is an overloaded intrinsic.

llvm/include/llvm/CodeGen/TargetLowering.h

SDValue expandIS_FPCLASS(EVT ResultVT, SDValue Op, unsigned Test,
                            SelectionDAG &DAG) const;
 
   /// Expand CTPOP nodes. Expands vector/scalar CTPOP nodes,
   /// vector nodes can only succeed if all operations are legal/custom.
   /// \param N Node to expand
   /// \returns The expansion result or SDValue() if it fails.
   SDValue expandCTPOP(SDNode *N, SelectionDAG &DAG) const;
 
+  /// Expand VP_CTPOP nodes.
+  /// \returns The expansion result or SDValue() if it fails.
+  SDValue expandVPCTPOP(SDNode *N, SelectionDAG &DAG) const;
+
   /// Expand CTLZ/CTLZ_ZERO_UNDEF nodes. Expands vector/scalar CTLZ nodes,
   /// vector nodes can only succeed if all operations are legal/custom.
   /// \param N Node to expand
   /// \returns The expansion result or SDValue() if it fails.
   SDValue expandCTLZ(SDNode *N, SelectionDAG &DAG) const;
 
   /// Expand CTTZ via Table Lookup.
   /// \param N Node to expand

llvm/include/llvm/IR/Intrinsics.td

let IntrProperties = [IntrNoMem, IntrNoSync, IntrWillReturn] in {
   def int_vp_bswap : DefaultAttrsIntrinsic<[ llvm_anyvector_ty ],
                              [ LLVMMatchType<0>,
                                LLVMScalarOrSameVectorWidth<0, llvm_i1_ty>,
                                llvm_i32_ty]>;
   def int_vp_bitreverse : DefaultAttrsIntrinsic<[ llvm_anyvector_ty ],
                              [ LLVMMatchType<0>,
                                LLVMScalarOrSameVectorWidth<0, llvm_i1_ty>,
                                llvm_i32_ty]>;
+  def int_vp_ctpop : DefaultAttrsIntrinsic<[ llvm_anyvector_ty ],
+                             [ LLVMMatchType<0>,
+                               LLVMScalarOrSameVectorWidth<0, llvm_i1_ty>,
+                               llvm_i32_ty]>;
   def int_vp_fshl : DefaultAttrsIntrinsic<[ llvm_anyvector_ty ],
                              [ LLVMMatchType<0>,
                                LLVMMatchType<0>,
                                LLVMMatchType<0>,
                                LLVMScalarOrSameVectorWidth<0, llvm_i1_ty>,
                                llvm_i32_ty]>;
   def int_vp_fshr : DefaultAttrsIntrinsic<[ llvm_anyvector_ty ],
                              [ LLVMMatchType<0>,

llvm/include/llvm/IR/VPIntrinsics.def

 // llvm.vp.bswap(x,mask,vlen)
 BEGIN_REGISTER_VP(vp_bswap, 1, 2, VP_BSWAP, -1)
 END_REGISTER_VP(vp_bswap, VP_BSWAP)
 
 // llvm.vp.bitreverse(x,mask,vlen)
 BEGIN_REGISTER_VP(vp_bitreverse, 1, 2, VP_BITREVERSE, -1)
 END_REGISTER_VP(vp_bitreverse, VP_BITREVERSE)
 
+// llvm.vp.ctpop(x,mask,vlen)
+BEGIN_REGISTER_VP(vp_ctpop, 1, 2, VP_CTPOP, -1)
+END_REGISTER_VP(vp_ctpop, VP_CTPOP)
+
 // llvm.vp.fshl(x,y,z,mask,vlen)
 BEGIN_REGISTER_VP(vp_fshl, 3, 4, VP_FSHL, -1)
 END_REGISTER_VP(vp_fshl, VP_FSHL)
 
 // llvm.vp.fshr(x,y,z,mask,vlen)
 BEGIN_REGISTER_VP(vp_fshr, 3, 4, VP_FSHR, -1)
 END_REGISTER_VP(vp_fshr, VP_FSHR)
 ///// } Integer Arithmetic

llvm/lib/CodeGen/SelectionDAG/LegalizeVectorOps.cpp

case ISD::VP_BITREVERSE:
     }
     break;
   case ISD::CTPOP:
     if (SDValue Expanded = TLI.expandCTPOP(Node, DAG)) {
       Results.push_back(Expanded);
       return;
     }
     break;
+  case ISD::VP_CTPOP:
+    if (SDValue Expanded = TLI.expandVPCTPOP(Node, DAG)) {
+      Results.push_back(Expanded);
+      return;
+    }
+    break;
   case ISD::CTLZ:
   case ISD::CTLZ_ZERO_UNDEF:
     if (SDValue Expanded = TLI.expandCTLZ(Node, DAG)) {
       Results.push_back(Expanded);
       return;
     }
     break;
   case ISD::CTTZ:

llvm/lib/CodeGen/SelectionDAG/LegalizeVectorTypes.cpp

#endif
   case ISD::VP_BITREVERSE:
   case ISD::BSWAP:
   case ISD::VP_BSWAP:
   case ISD::CTLZ:
   case ISD::CTTZ:
   case ISD::CTLZ_ZERO_UNDEF:
   case ISD::CTTZ_ZERO_UNDEF:
   case ISD::CTPOP:
+  case ISD::VP_CTPOP:
   case ISD::FABS: case ISD::VP_FABS:
   case ISD::FCEIL:
   case ISD::VP_FCEIL:
   case ISD::FCOS:
   case ISD::FEXP:
   case ISD::FEXP2:
   case ISD::FFLOOR:
   case ISD::VP_FFLOOR:
#include "llvm/IR/ConstrainedOps.def"
   case ISD::ABS:
   case ISD::BITREVERSE:
   case ISD::VP_BITREVERSE:
   case ISD::BSWAP:
   case ISD::VP_BSWAP:
   case ISD::CTLZ:
   case ISD::CTLZ_ZERO_UNDEF:
   case ISD::CTPOP:
+  case ISD::VP_CTPOP:
   case ISD::CTTZ:
   case ISD::CTTZ_ZERO_UNDEF:
   case ISD::FNEG: case ISD::VP_FNEG:
   case ISD::VP_FABS:
   case ISD::VP_SQRT:
   case ISD::VP_FCEIL:
   case ISD::VP_FFLOOR:
   case ISD::VP_FRINT:

llvm/lib/CodeGen/SelectionDAG/TargetLowering.cpp

SDValue TargetLowering::expandCTPOP(SDNode *Node, SelectionDAG &DAG) const {
   // v = (v * 0x01010101...) >> (Len - 8)
   SDValue Mask01 =
       DAG.getConstant(APInt::getSplat(Len, APInt(8, 0x01)), dl, VT);
   return DAG.getNode(ISD::SRL, dl, VT,
                      DAG.getNode(ISD::MUL, dl, VT, Op, Mask01),
                      DAG.getConstant(Len - 8, dl, ShVT));
 }
 
+SDValue TargetLowering::expandVPCTPOP(SDNode *Node, SelectionDAG &DAG) const {
+  SDLoc dl(Node);
+  EVT VT = Node->getValueType(0);
+  EVT ShVT = getShiftAmountTy(VT, DAG.getDataLayout());
+  SDValue Op = Node->getOperand(0);
+  SDValue Mask = Node->getOperand(1);
+  SDValue VL = Node->getOperand(2);
+  unsigned Len = VT.getScalarSizeInBits();
+  assert(VT.isInteger() && "VP_CTPOP not implemented for this type.");
+
+  // TODO: Add support for irregular type lengths.
+  if (!(Len <= 128 && Len % 8 == 0))
+    return SDValue();
+
+  // This is same algorithm of expandCTPOP from
+  // http://graphics.stanford.edu/~seander/bithacks.html#CountBitsSetParallel
+  SDValue Mask55 =
+      DAG.getConstant(APInt::getSplat(Len, APInt(8, 0x55)), dl, VT);
+  SDValue Mask33 =
+      DAG.getConstant(APInt::getSplat(Len, APInt(8, 0x33)), dl, VT);
+  SDValue Mask0F =
+      DAG.getConstant(APInt::getSplat(Len, APInt(8, 0x0F)), dl, VT);
+
+  SDValue Tmp1, Tmp2, Tmp3, Tmp4, Tmp5;
+
+  // v = v - ((v >> 1) & 0x55555555...)
+  Tmp1 = DAG.getNode(ISD::VP_AND, dl, VT,
+                     DAG.getNode(ISD::VP_LSHR, dl, VT, Op,
+                                 DAG.getConstant(1, dl, ShVT), Mask, VL),
+                     Mask55, Mask, VL);
+  Op = DAG.getNode(ISD::VP_SUB, dl, VT, Op, Tmp1, Mask, VL);
+
+  // v = (v & 0x33333333...) + ((v >> 2) & 0x33333333...)
+  Tmp2 = DAG.getNode(ISD::VP_AND, dl, VT, Op, Mask33, Mask, VL);
+  Tmp3 = DAG.getNode(ISD::VP_AND, dl, VT,
+                     DAG.getNode(ISD::VP_LSHR, dl, VT, Op,
+                                 DAG.getConstant(2, dl, ShVT), Mask, VL),
+                     Mask33, Mask, VL);
+  Op = DAG.getNode(ISD::VP_ADD, dl, VT, Tmp2, Tmp3, Mask, VL);
+
+  // v = (v + (v >> 4)) & 0x0F0F0F0F...
+  Tmp4 = DAG.getNode(ISD::VP_LSHR, dl, VT, Op, DAG.getConstant(4, dl, ShVT),
+                     Mask, VL),
+  Tmp5 = DAG.getNode(ISD::VP_ADD, dl, VT, Op, Tmp4, Mask, VL);
+  Op = DAG.getNode(ISD::VP_AND, dl, VT, Tmp5, Mask0F, Mask, VL);
+
+  if (Len <= 8)
+    return Op;
+
+  // v = (v * 0x01010101...) >> (Len - 8)
+  SDValue Mask01 =
+      DAG.getConstant(APInt::getSplat(Len, APInt(8, 0x01)), dl, VT);
+  return DAG.getNode(ISD::VP_LSHR, dl, VT,
+                     DAG.getNode(ISD::VP_MUL, dl, VT, Op, Mask01, Mask, VL),
+                     DAG.getConstant(Len - 8, dl, ShVT), Mask, VL);
+}
+
 SDValue TargetLowering::expandCTLZ(SDNode *Node, SelectionDAG &DAG) const {
   SDLoc dl(Node);
   EVT VT = Node->getValueType(0);
   EVT ShVT = getShiftAmountTy(VT, DAG.getDataLayout());
   SDValue Op = Node->getOperand(0);
   unsigned NumBitsPerElt = VT.getScalarSizeInBits();
 
   // If the non-ZERO_UNDEF version is supported we can use that instead.

llvm/lib/Target/RISCV/RISCVISelLowering.cpp

for (MVT VT : IntVecVTs) {
 
       setOperationAction({ISD::ROTL, ISD::ROTR}, VT, Expand);
 
       setOperationAction({ISD::CTTZ, ISD::CTLZ, ISD::CTPOP}, VT, Expand);
 
       setOperationAction(ISD::BSWAP, VT, Expand);
       setOperationAction({ISD::VP_BSWAP, ISD::VP_BITREVERSE}, VT, Expand);
       setOperationAction({ISD::VP_FSHL, ISD::VP_FSHR}, VT, Expand);
+      setOperationAction(ISD::VP_CTPOP, VT, Expand);
 
       // Custom-lower extensions and truncations from/to mask types.
       setOperationAction({ISD::ANY_EXTEND, ISD::SIGN_EXTEND, ISD::ZERO_EXTEND},
                          VT, Custom);
 
       // RVV has native int->float & float->int conversions where the
       // element type sizes are within one power-of-two of each other. Any
       // wider distances between type sizes have to be lowered as sequences

llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp

static const CostTblEntry VectorIntrinsicCostTable[]{
     {Intrinsic::ctpop, MVT::v2i64, 21},
     {Intrinsic::ctpop, MVT::v4i64, 21},
     {Intrinsic::ctpop, MVT::v8i64, 21},
     {Intrinsic::ctpop, MVT::v16i64, 21},
     {Intrinsic::ctpop, MVT::nxv1i64, 21},
     {Intrinsic::ctpop, MVT::nxv2i64, 21},
     {Intrinsic::ctpop, MVT::nxv4i64, 21},
     {Intrinsic::ctpop, MVT::nxv8i64, 21},
+    {Intrinsic::vp_ctpop, MVT::v2i8, 12},
+    {Intrinsic::vp_ctpop, MVT::v4i8, 12},
+    {Intrinsic::vp_ctpop, MVT::v8i8, 12},
+    {Intrinsic::vp_ctpop, MVT::v16i8, 12},
+    {Intrinsic::vp_ctpop, MVT::nxv1i8, 12},
+    {Intrinsic::vp_ctpop, MVT::nxv2i8, 12},
+    {Intrinsic::vp_ctpop, MVT::nxv4i8, 12},
+    {Intrinsic::vp_ctpop, MVT::nxv8i8, 12},
+    {Intrinsic::vp_ctpop, MVT::nxv16i8, 12},
+    {Intrinsic::vp_ctpop, MVT::v2i16, 19},
+    {Intrinsic::vp_ctpop, MVT::v4i16, 19},
+    {Intrinsic::vp_ctpop, MVT::v8i16, 19},
+    {Intrinsic::vp_ctpop, MVT::v16i16, 19},
+    {Intrinsic::vp_ctpop, MVT::nxv1i16, 19},
+    {Intrinsic::vp_ctpop, MVT::nxv2i16, 19},
+    {Intrinsic::vp_ctpop, MVT::nxv4i16, 19},
+    {Intrinsic::vp_ctpop, MVT::nxv8i16, 19},
+    {Intrinsic::vp_ctpop, MVT::nxv16i16, 19},
+    {Intrinsic::vp_ctpop, MVT::v2i32, 20},
+    {Intrinsic::vp_ctpop, MVT::v4i32, 20},
+    {Intrinsic::vp_ctpop, MVT::v8i32, 20},
+    {Intrinsic::vp_ctpop, MVT::v16i32, 20},
+    {Intrinsic::vp_ctpop, MVT::nxv1i32, 20},
+    {Intrinsic::vp_ctpop, MVT::nxv2i32, 20},
+    {Intrinsic::vp_ctpop, MVT::nxv4i32, 20},
+    {Intrinsic::vp_ctpop, MVT::nxv8i32, 20},
+    {Intrinsic::vp_ctpop, MVT::nxv16i32, 20},
+    {Intrinsic::vp_ctpop, MVT::v2i64, 21},
+    {Intrinsic::vp_ctpop, MVT::v4i64, 21},
+    {Intrinsic::vp_ctpop, MVT::v8i64, 21},
+    {Intrinsic::vp_ctpop, MVT::v16i64, 21},
+    {Intrinsic::vp_ctpop, MVT::nxv1i64, 21},
+    {Intrinsic::vp_ctpop, MVT::nxv2i64, 21},
+    {Intrinsic::vp_ctpop, MVT::nxv4i64, 21},
+    {Intrinsic::vp_ctpop, MVT::nxv8i64, 21},
 };
 
 static unsigned getISDForVPIntrinsicID(Intrinsic::ID ID) {
   switch (ID) {
 #define HELPER_MAP_VPID_TO_VPSD(VPID, VPSD)                                    \
   case Intrinsic::VPID:                                                        \
     return ISD::VPSD;
 #include "llvm/IR/VPIntrinsics.def"

llvm/test/Analysis/CostModel/RISCV/int-bit-manip.ll

;
   call <vscale x 1 x i64> @llvm.vp.bswap.nvx1i64(<vscale x 1 x i64> undef, <vscale x 1 x i1> undef, i32 undef)
   call <vscale x 2 x i64> @llvm.vp.bswap.nvx2i64(<vscale x 2 x i64> undef, <vscale x 2 x i1> undef, i32 undef)
   call <vscale x 4 x i64> @llvm.vp.bswap.nvx4i64(<vscale x 4 x i64> undef, <vscale x 4 x i1> undef, i32 undef)
   call <vscale x 8 x i64> @llvm.vp.bswap.nvx8i64(<vscale x 8 x i64> undef, <vscale x 8 x i1> undef, i32 undef)
   call <vscale x 16 x i64> @llvm.vp.bswap.nvx16i64(<vscale x 16 x i64> undef, <vscale x 16 x i1> undef, i32 undef)
   ret void
 }
 
+define void @vp_ctpop() {
+; CHECK-LABEL: 'vp_ctpop'
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %1 = call <2 x i16> @llvm.vp.ctpop.v2i16(<2 x i16> undef, <2 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %2 = call <4 x i16> @llvm.vp.ctpop.v4i16(<4 x i16> undef, <4 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %3 = call <8 x i16> @llvm.vp.ctpop.v8i16(<8 x i16> undef, <8 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %4 = call <16 x i16> @llvm.vp.ctpop.v16i16(<16 x i16> undef, <16 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %5 = call <vscale x 1 x i16> @llvm.vp.ctpop.nxv1i16(<vscale x 1 x i16> undef, <vscale x 1 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %6 = call <vscale x 2 x i16> @llvm.vp.ctpop.nxv2i16(<vscale x 2 x i16> undef, <vscale x 2 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %7 = call <vscale x 4 x i16> @llvm.vp.ctpop.nxv4i16(<vscale x 4 x i16> undef, <vscale x 4 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %8 = call <vscale x 8 x i16> @llvm.vp.ctpop.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %9 = call <vscale x 16 x i16> @llvm.vp.ctpop.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %10 = call <2 x i16> @llvm.vp.ctpop.v2i16(<2 x i16> undef, <2 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %11 = call <4 x i16> @llvm.vp.ctpop.v4i16(<4 x i16> undef, <4 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %12 = call <8 x i16> @llvm.vp.ctpop.v8i16(<8 x i16> undef, <8 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %13 = call <16 x i16> @llvm.vp.ctpop.v16i16(<16 x i16> undef, <16 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %14 = call <vscale x 1 x i16> @llvm.vp.ctpop.nxv1i16(<vscale x 1 x i16> undef, <vscale x 1 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %15 = call <vscale x 2 x i16> @llvm.vp.ctpop.nxv2i16(<vscale x 2 x i16> undef, <vscale x 2 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %16 = call <vscale x 4 x i16> @llvm.vp.ctpop.nxv4i16(<vscale x 4 x i16> undef, <vscale x 4 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %17 = call <vscale x 8 x i16> @llvm.vp.ctpop.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %18 = call <vscale x 16 x i16> @llvm.vp.ctpop.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %19 = call <2 x i32> @llvm.vp.ctpop.v2i32(<2 x i32> undef, <2 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %20 = call <4 x i32> @llvm.vp.ctpop.v4i32(<4 x i32> undef, <4 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %21 = call <8 x i32> @llvm.vp.ctpop.v8i32(<8 x i32> undef, <8 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %22 = call <16 x i32> @llvm.vp.ctpop.v16i32(<16 x i32> undef, <16 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %23 = call <vscale x 1 x i32> @llvm.vp.ctpop.nxv1i32(<vscale x 1 x i32> undef, <vscale x 1 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %24 = call <vscale x 2 x i32> @llvm.vp.ctpop.nxv2i32(<vscale x 2 x i32> undef, <vscale x 2 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %25 = call <vscale x 4 x i32> @llvm.vp.ctpop.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %26 = call <vscale x 8 x i32> @llvm.vp.ctpop.nxv8i32(<vscale x 8 x i32> undef, <vscale x 8 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %27 = call <vscale x 16 x i32> @llvm.vp.ctpop.nxv16i32(<vscale x 16 x i32> undef, <vscale x 16 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %28 = call <2 x i64> @llvm.vp.ctpop.v2i64(<2 x i64> undef, <2 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %29 = call <4 x i64> @llvm.vp.ctpop.v4i64(<4 x i64> undef, <4 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %30 = call <8 x i64> @llvm.vp.ctpop.v8i64(<8 x i64> undef, <8 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %31 = call <16 x i64> @llvm.vp.ctpop.v16i64(<16 x i64> undef, <16 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %32 = call <vscale x 1 x i64> @llvm.vp.ctpop.nxv1i64(<vscale x 1 x i64> undef, <vscale x 1 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %33 = call <vscale x 2 x i64> @llvm.vp.ctpop.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %34 = call <vscale x 4 x i64> @llvm.vp.ctpop.nxv4i64(<vscale x 4 x i64> undef, <vscale x 4 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %35 = call <vscale x 8 x i64> @llvm.vp.ctpop.nxv8i64(<vscale x 8 x i64> undef, <vscale x 8 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 42 for instruction: %36 = call <vscale x 16 x i64> @llvm.vp.ctpop.nxv16i64(<vscale x 16 x i64> undef, <vscale x 16 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret void
+;
+  call <2 x i16> @llvm.vp.ctpop.v2i16(<2 x i16> undef, <2 x i1> undef, i32 undef)
+  call <4 x i16> @llvm.vp.ctpop.v4i16(<4 x i16> undef, <4 x i1> undef, i32 undef)
+  call <8 x i16> @llvm.vp.ctpop.v8i16(<8 x i16> undef, <8 x i1> undef, i32 undef)
+  call <16 x i16> @llvm.vp.ctpop.v16i16(<16 x i16> undef, <16 x i1> undef, i32 undef)
+  call <vscale x 1 x i16> @llvm.vp.ctpop.nvx1i16(<vscale x 1 x i16> undef, <vscale x 1 x i1> undef, i32 undef)
+  call <vscale x 2 x i16> @llvm.vp.ctpop.nvx2i16(<vscale x 2 x i16> undef, <vscale x 2 x i1> undef, i32 undef)
+  call <vscale x 4 x i16> @llvm.vp.ctpop.nvx4i16(<vscale x 4 x i16> undef, <vscale x 4 x i1> undef, i32 undef)
+  call <vscale x 8 x i16> @llvm.vp.ctpop.nvx8i16(<vscale x 8 x i16> undef, <vscale x 8 x i1> undef, i32 undef)
+  call <vscale x 16 x i16> @llvm.vp.ctpop.nvx16i16(<vscale x 16 x i16> undef, <vscale x 16 x i1> undef, i32 undef)
+  call <2 x i16> @llvm.vp.ctpop.v2i16(<2 x i16> undef, <2 x i1> undef, i32 undef)
+  call <4 x i16> @llvm.vp.ctpop.v4i16(<4 x i16> undef, <4 x i1> undef, i32 undef)
+  call <8 x i16> @llvm.vp.ctpop.v8i16(<8 x i16> undef, <8 x i1> undef, i32 undef)
+  call <16 x i16> @llvm.vp.ctpop.v16i16(<16 x i16> undef, <16 x i1> undef, i32 undef)
+  call <vscale x 1 x i16> @llvm.vp.ctpop.nvx1i16(<vscale x 1 x i16> undef, <vscale x 1 x i1> undef, i32 undef)
+  call <vscale x 2 x i16> @llvm.vp.ctpop.nvx2i16(<vscale x 2 x i16> undef, <vscale x 2 x i1> undef, i32 undef)
+  call <vscale x 4 x i16> @llvm.vp.ctpop.nvx4i16(<vscale x 4 x i16> undef, <vscale x 4 x i1> undef, i32 undef)
+  call <vscale x 8 x i16> @llvm.vp.ctpop.nvx8i16(<vscale x 8 x i16> undef, <vscale x 8 x i1> undef, i32 undef)
+  call <vscale x 16 x i16> @llvm.vp.ctpop.nvx16i16(<vscale x 16 x i16> undef, <vscale x 16 x i1> undef, i32 undef)
+  call <2 x i32> @llvm.vp.ctpop.v2i32(<2 x i32> undef, <2 x i1> undef, i32 undef)
+  call <4 x i32> @llvm.vp.ctpop.v4i32(<4 x i32> undef, <4 x i1> undef, i32 undef)
+  call <8 x i32> @llvm.vp.ctpop.v8i32(<8 x i32> undef, <8 x i1> undef, i32 undef)
+  call <16 x i32> @llvm.vp.ctpop.v16i32(<16 x i32> undef, <16 x i1> undef, i32 undef)
+  call <vscale x 1 x i32> @llvm.vp.ctpop.nvx1i32(<vscale x 1 x i32> undef, <vscale x 1 x i1> undef, i32 undef)
+  call <vscale x 2 x i32> @llvm.vp.ctpop.nvx2i32(<vscale x 2 x i32> undef, <vscale x 2 x i1> undef, i32 undef)
+  call <vscale x 4 x i32> @llvm.vp.ctpop.nvx4i32(<vscale x 4 x i32> undef, <vscale x 4 x i1> undef, i32 undef)
+  call <vscale x 8 x i32> @llvm.vp.ctpop.nvx8i32(<vscale x 8 x i32> undef, <vscale x 8 x i1> undef, i32 undef)
+  call <vscale x 16 x i32> @llvm.vp.ctpop.nvx16i32(<vscale x 16 x i32> undef, <vscale x 16 x i1> undef, i32 undef)
+  call <2 x i64> @llvm.vp.ctpop.v2i64(<2 x i64> undef, <2 x i1> undef, i32 undef)
+  call <4 x i64> @llvm.vp.ctpop.v4i64(<4 x i64> undef, <4 x i1> undef, i32 undef)
+  call <8 x i64> @llvm.vp.ctpop.v8i64(<8 x i64> undef, <8 x i1> undef, i32 undef)
+  call <16 x i64> @llvm.vp.ctpop.v16i64(<16 x i64> undef, <16 x i1> undef, i32 undef)
+  call <vscale x 1 x i64> @llvm.vp.ctpop.nvx1i64(<vscale x 1 x i64> undef, <vscale x 1 x i1> undef, i32 undef)
+  call <vscale x 2 x i64> @llvm.vp.ctpop.nvx2i64(<vscale x 2 x i64> undef, <vscale x 2 x i1> undef, i32 undef)
+  call <vscale x 4 x i64> @llvm.vp.ctpop.nvx4i64(<vscale x 4 x i64> undef, <vscale x 4 x i1> undef, i32 undef)
+  call <vscale x 8 x i64> @llvm.vp.ctpop.nvx8i64(<vscale x 8 x i64> undef, <vscale x 8 x i1> undef, i32 undef)
+  call <vscale x 16 x i64> @llvm.vp.ctpop.nvx16i64(<vscale x 16 x i64> undef, <vscale x 16 x i1> undef, i32 undef)
+  ret void
+}
+
 declare i16 @llvm.bswap.i16(i16)
 declare <2 x i16> @llvm.bswap.v2i16(<2 x i16>)
 declare <4 x i16> @llvm.bswap.v4i16(<4 x i16>)
 declare <8 x i16> @llvm.bswap.v8i16(<8 x i16>)
 declare <16 x i16> @llvm.bswap.v16i16(<16 x i16>)
 declare <vscale x 1 x i16> @llvm.bswap.nvx1i16(<vscale x 1 x i16>)
 declare <vscale x 2 x i16> @llvm.bswap.nvx2i16(<vscale x 2 x i16>)
 declare <vscale x 4 x i16> @llvm.bswap.nvx4i16(<vscale x 4 x i16>)

 declare <4 x i64> @llvm.vp.bswap.v4i64(<4 x i64>, <4 x i1>, i32)
 declare <8 x i64> @llvm.vp.bswap.v8i64(<8 x i64>, <8 x i1>, i32)
 declare <16 x i64> @llvm.vp.bswap.v16i64(<16 x i64>, <16 x i1>, i32)
 declare <vscale x 1 x i64> @llvm.vp.bswap.nvx1i64(<vscale x 1 x i64>, <vscale x 1 x i1>, i32)
 declare <vscale x 2 x i64> @llvm.vp.bswap.nvx2i64(<vscale x 2 x i64>, <vscale x 2 x i1>, i32)
 declare <vscale x 4 x i64> @llvm.vp.bswap.nvx4i64(<vscale x 4 x i64>, <vscale x 4 x i1>, i32)
 declare <vscale x 8 x i64> @llvm.vp.bswap.nvx8i64(<vscale x 8 x i64>, <vscale x 8 x i1>, i32)
 declare <vscale x 16 x i64> @llvm.vp.bswap.nvx16i64(<vscale x 16 x i64>, <vscale x 16 x i1>, i32)
+
+declare <2 x i8> @llvm.vp.ctpop.v2i8(<2 x i8>, <2 x i1>, i32)
+declare <4 x i8> @llvm.vp.ctpop.v4i8(<4 x i8>, <4 x i1>, i32)
+declare <8 x i8> @llvm.vp.ctpop.v8i8(<8 x i8>, <8 x i1>, i32)
+declare <16 x i8> @llvm.vp.ctpop.v16i8(<16 x i8>, <16 x i1>, i32)
+declare <vscale x 1 x i8> @llvm.vp.ctpop.nvx1i8(<vscale x 1 x i8>, <vscale x 1 x i1>, i32)
+declare <vscale x 2 x i8> @llvm.vp.ctpop.nvx2i8(<vscale x 2 x i8>, <vscale x 2 x i1>, i32)
+declare <vscale x 4 x i8> @llvm.vp.ctpop.nvx4i8(<vscale x 4 x i8>, <vscale x 4 x i1>, i32)
+declare <vscale x 8 x i8> @llvm.vp.ctpop.nvx8i8(<vscale x 8 x i8>, <vscale x 8 x i1>, i32)
+declare <vscale x 16 x i8> @llvm.vp.ctpop.nvx16i8(<vscale x 16 x i8>, <vscale x 16 x i1>, i32)
+declare <2 x i16> @llvm.vp.ctpop.v2i16(<2 x i16>, <2 x i1>, i32)
+declare <4 x i16> @llvm.vp.ctpop.v4i16(<4 x i16>, <4 x i1>, i32)
+declare <8 x i16> @llvm.vp.ctpop.v8i16(<8 x i16>, <8 x i1>, i32)
+declare <16 x i16> @llvm.vp.ctpop.v16i16(<16 x i16>, <16 x i1>, i32)
+declare <vscale x 1 x i16> @llvm.vp.ctpop.nvx1i16(<vscale x 1 x i16>, <vscale x 1 x i1>, i32)
+declare <vscale x 2 x i16> @llvm.vp.ctpop.nvx2i16(<vscale x 2 x i16>, <vscale x 2 x i1>, i32)
+declare <vscale x 4 x i16> @llvm.vp.ctpop.nvx4i16(<vscale x 4 x i16>, <vscale x 4 x i1>, i32)
+declare <vscale x 8 x i16> @llvm.vp.ctpop.nvx8i16(<vscale x 8 x i16>, <vscale x 8 x i1>, i32)
+declare <vscale x 16 x i16> @llvm.vp.ctpop.nvx16i16(<vscale x 16 x i16>, <vscale x 16 x i1>, i32)
+declare <2 x i32> @llvm.vp.ctpop.v2i32(<2 x i32>, <2 x i1>, i32)
+declare <4 x i32> @llvm.vp.ctpop.v4i32(<4 x i32>, <4 x i1>, i32)
+declare <8 x i32> @llvm.vp.ctpop.v8i32(<8 x i32>, <8 x i1>, i32)
+declare <16 x i32> @llvm.vp.ctpop.v16i32(<16 x i32>, <16 x i1>, i32)
+declare <vscale x 1 x i32> @llvm.vp.ctpop.nvx1i32(<vscale x 1 x i32>, <vscale x 1 x i1>, i32)
+declare <vscale x 2 x i32> @llvm.vp.ctpop.nvx2i32(<vscale x 2 x i32>, <vscale x 2 x i1>, i32)
+declare <vscale x 4 x i32> @llvm.vp.ctpop.nvx4i32(<vscale x 4 x i32>, <vscale x 4 x i1>, i32)
+declare <vscale x 8 x i32> @llvm.vp.ctpop.nvx8i32(<vscale x 8 x i32>, <vscale x 8 x i1>, i32)
+declare <vscale x 16 x i32> @llvm.vp.ctpop.nvx16i32(<vscale x 16 x i32>, <vscale x 16 x i1>, i32)
+declare <2 x i64> @llvm.vp.ctpop.v2i64(<2 x i64>, <2 x i1>, i32)
+declare <4 x i64> @llvm.vp.ctpop.v4i64(<4 x i64>, <4 x i1>, i32)
+declare <8 x i64> @llvm.vp.ctpop.v8i64(<8 x i64>, <8 x i1>, i32)
+declare <16 x i64> @llvm.vp.ctpop.v16i64(<16 x i64>, <16 x i1>, i32)
+declare <vscale x 1 x i64> @llvm.vp.ctpop.nvx1i64(<vscale x 1 x i64>, <vscale x 1 x i1>, i32)
+declare <vscale x 2 x i64> @llvm.vp.ctpop.nvx2i64(<vscale x 2 x i64>, <vscale x 2 x i1>, i32)
+declare <vscale x 4 x i64> @llvm.vp.ctpop.nvx4i64(<vscale x 4 x i64>, <vscale x 4 x i1>, i32)
+declare <vscale x 8 x i64> @llvm.vp.ctpop.nvx8i64(<vscale x 8 x i64>, <vscale x 8 x i1>, i32)
+declare <vscale x 16 x i64> @llvm.vp.ctpop.nvx16i64(<vscale x 16 x i64>, <vscale x 16 x i1>, i32)

llvm/test/CodeGen/RISCV/rvv/ctpop-vp.ll

+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc -mtriple=riscv32 -mattr=+d,+zfh,+experimental-zvfh,+v,+m -target-abi=ilp32d \
+; RUN:     -verify-machineinstrs < %s | FileCheck %s --check-prefixes=CHECK,RV32
+; RUN: llc -mtriple=riscv64 -mattr=+d,+zfh,+experimental-zvfh,+v,+m -target-abi=lp64d \
+; RUN:     -verify-machineinstrs < %s | FileCheck %s --check-prefixes=CHECK,RV64
+
+declare <vscale x 1 x i8> @llvm.vp.ctpop.nxv1i8(<vscale x 1 x i8>, <vscale x 1 x i1>, i32)
+
+define <vscale x 1 x i8> @vp_ctpop_nxv1i8(<vscale x 1 x i8> %va, <vscale x 1 x i1> %m, i32 zeroext %evl) {
+; CHECK-LABEL: vp_ctpop_nxv1i8:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli zero, a0, e8, mf8, ta, ma
+; CHECK-NEXT:    vsrl.vi v9, v8, 1, v0.t
+; CHECK-NEXT:    li a0, 85
+; CHECK-NEXT:    vand.vx v9, v9, a0, v0.t
+; CHECK-NEXT:    vsub.vv v8, v8, v9, v0.t
+; CHECK-NEXT:    li a0, 51
+; CHECK-NEXT:    vand.vx v9, v8, a0, v0.t
+; CHECK-NEXT:    vsrl.vi v8, v8, 2, v0.t
+; CHECK-NEXT:    vand.vx v8, v8, a0, v0.t
+; CHECK-NEXT:    vadd.vv v8, v9, v8, v0.t
+; CHECK-NEXT:    vsrl.vi v9, v8, 4, v0.t
+; CHECK-NEXT:    vadd.vv v8, v8, v9, v0.t
+; CHECK-NEXT:    vand.vi v8, v8, 15, v0.t
+; CHECK-NEXT:    ret
+  %v = call <vscale x 1 x i8> @llvm.vp.ctpop.nxv1i8(<vscale x 1 x i8> %va, <vscale x 1 x i1> %m, i32 %evl)
+  ret <vscale x 1 x i8> %v
+}
+
+define <vscale x 1 x i8> @vp_ctpop_nxv1i8_unmasked(<vscale x 1 x i8> %va, i32 zeroext %evl) {
+; CHECK-LABEL: vp_ctpop_nxv1i8_unmasked:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli zero, a0, e8, mf8, ta, ma
+; CHECK-NEXT:    vsrl.vi v9, v8, 1
+; CHECK-NEXT:    li a0, 85
+; CHECK-NEXT:    vand.vx v9, v9, a0
+; CHECK-NEXT:    vsub.vv v8, v8, v9
+; CHECK-NEXT:    li a0, 51
+; CHECK-NEXT:    vand.vx v9, v8, a0
+; CHECK-NEXT:    vsrl.vi v8, v8, 2
+; CHECK-NEXT:    vand.vx v8, v8, a0
+; CHECK-NEXT:    vadd.vv v8, v9, v8
+; CHECK-NEXT:    vsrl.vi v9, v8, 4
+; CHECK-NEXT:    vadd.vv v8, v8, v9
+; CHECK-NEXT:    vand.vi v8, v8, 15
+; CHECK-NEXT:    ret
+  %head = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
+  %m = shufflevector <vscale x 1 x i1> %head, <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
+  %v = call <vscale x 1 x i8> @llvm.vp.ctpop.nxv1i8(<vscale x 1 x i8> %va, <vscale x 1 x i1> %m, i32 %evl)
+  ret <vscale x 1 x i8> %v
+}
+
+declare <vscale x 2 x i8> @llvm.vp.ctpop.nxv2i8(<vscale x 2 x i8>, <vscale x 2 x i1>, i32)
+
+define <vscale x 2 x i8> @vp_ctpop_nxv2i8(<vscale x 2 x i8> %va, <vscale x 2 x i1> %m, i32 zeroext %evl) {
+; CHECK-LABEL: vp_ctpop_nxv2i8:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli zero, a0, e8, mf4, ta, ma
+; CHECK-NEXT:    vsrl.vi v9, v8, 1, v0.t
+; CHECK-NEXT:    li a0, 85
+; CHECK-NEXT:    vand.vx v9, v9, a0, v0.t
+; CHECK-NEXT:    vsub.vv v8, v8, v9, v0.t
+; CHECK-NEXT:    li a0, 51
+; CHECK-NEXT:    vand.vx v9, v8, a0, v0.t
+; CHECK-NEXT:    vsrl.vi v8, v8, 2, v0.t
+; CHECK-NEXT:    vand.vx v8, v8, a0, v0.t
+; CHECK-NEXT:    vadd.vv v8, v9, v8, v0.t
+; CHECK-NEXT:    vsrl.vi v9, v8, 4, v0.t
+; CHECK-NEXT:    vadd.vv v8, v8, v9, v0.t
+; CHECK-NEXT:    vand.vi v8, v8, 15, v0.t
+; CHECK-NEXT:    ret
+  %v = call <vscale x 2 x i8> @llvm.vp.ctpop.nxv2i8(<vscale x 2 x i8> %va, <vscale x 2 x i1> %m, i32 %evl)
+  ret <vscale x 2 x i8> %v
+}
+
+define <vscale x 2 x i8> @vp_ctpop_nxv2i8_unmasked(<vscale x 2 x i8> %va, i32 zeroext %evl) {
+; CHECK-LABEL: vp_ctpop_nxv2i8_unmasked:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli zero, a0, e8, mf4, ta, ma
+; CHECK-NEXT:    vsrl.vi v9, v8, 1
+; CHECK-NEXT:    li a0, 85
+; CHECK-NEXT:    vand.vx v9, v9, a0
+; CHECK-NEXT:    vsub.vv v8, v8, v9
+; CHECK-NEXT:    li a0, 51
+; CHECK-NEXT:    vand.vx v9, v8, a0
+; CHECK-NEXT:    vsrl.vi v8, v8, 2
+; CHECK-NEXT:    vand.vx v8, v8, a0
+; CHECK-NEXT:    vadd.vv v8, v9, v8
+; CHECK-NEXT:    vsrl.vi v9, v8, 4
+; CHECK-NEXT:    vadd.vv v8, v8, v9
+; CHECK-NEXT:    vand.vi v8, v8, 15
+; CHECK-NEXT:    ret
+  %head = insertelement <vscale x 2 x i1> poison, i1 true, i32 0
+  %m = shufflevector <vscale x 2 x i1> %head, <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer
+  %v = call <vscale x 2 x i8> @llvm.vp.ctpop.nxv2i8(<vscale x 2 x i8> %va, <vscale x 2 x i1> %m, i32 %evl)
+  ret <vscale x 2 x i8> %v
+}
+
+declare <vscale x 4 x i8> @llvm.vp.ctpop.nxv4i8(<vscale x 4 x i8>, <vscale x 4 x i1>, i32)
+
+define <vscale x 4 x i8> @vp_ctpop_nxv4i8(<vscale x 4 x i8> %va, <vscale x 4 x i1> %m, i32 zeroext %evl) {
+; CHECK-LABEL: vp_ctpop_nxv4i8:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli zero, a0, e8, mf2, ta, ma
+; CHECK-NEXT:    vsrl.vi v9, v8, 1, v0.t
+; CHECK-NEXT:    li a0, 85
+; CHECK-NEXT:    vand.vx v9, v9, a0, v0.t
+; CHECK-NEXT:    vsub.vv v8, v8, v9, v0.t
+; CHECK-NEXT:    li a0, 51
+; CHECK-NEXT:    vand.vx v9, v8, a0, v0.t
+; CHECK-NEXT:    vsrl.vi v8, v8, 2, v0.t
+; CHECK-NEXT:    vand.vx v8, v8, a0, v0.t
+; CHECK-NEXT:    vadd.vv v8, v9, v8, v0.t
+; CHECK-NEXT:    vsrl.vi v9, v8, 4, v0.t
+; CHECK-NEXT:    vadd.vv v8, v8, v9, v0.t
+; CHECK-NEXT:    vand.vi v8, v8, 15, v0.t
+; CHECK-NEXT:    ret
+  %v = call <vscale x 4 x i8> @llvm.vp.ctpop.nxv4i8(<vscale x 4 x i8> %va, <vscale x 4 x i1> %m, i32 %evl)
+  ret <vscale x 4 x i8> %v
+}
+
+define <vscale x 4 x i8> @vp_ctpop_nxv4i8_unmasked(<vscale x 4 x i8> %va, i32 zeroext %evl) {
+; CHECK-LABEL: vp_ctpop_nxv4i8_unmasked:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli zero, a0, e8, mf2, ta, ma
+; CHECK-NEXT:    vsrl.vi v9, v8, 1
+; CHECK-NEXT:    li a0, 85
+; CHECK-NEXT:    vand.vx v9, v9, a0
+; CHECK-NEXT:    vsub.vv v8, v8, v9
+; CHECK-NEXT:    li a0, 51
+; CHECK-NEXT:    vand.vx v9, v8, a0
+; CHECK-NEXT:    vsrl.vi v8, v8, 2
+; CHECK-NEXT:    vand.vx v8, v8, a0
+; CHECK-NEXT:    vadd.vv v8, v9, v8
+; CHECK-NEXT:    vsrl.vi v9, v8, 4
+; CHECK-NEXT:    vadd.vv v8, v8, v9
+; CHECK-NEXT:    vand.vi v8, v8, 15
+; CHECK-NEXT:    ret
+  %head = insertelement <vscale x 4 x i1> poison, i1 true, i32 0
+  %m = shufflevector <vscale x 4 x i1> %head, <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer
+  %v = call <vscale x 4 x i8> @llvm.vp.ctpop.nxv4i8(<vscale x 4 x i8> %va, <vscale x 4 x i1> %m, i32 %evl)
+  ret <vscale x 4 x i8> %v
+}
+
+declare <vscale x 8 x i8> @llvm.vp.ctpop.nxv8i8(<vscale x 8 x i8>, <vscale x 8 x i1>, i32)
+
+define <vscale x 8 x i8> @vp_ctpop_nxv8i8(<vscale x 8 x i8> %va, <vscale x 8 x i1> %m, i32 zeroext %evl) {
+; CHECK-LABEL: vp_ctpop_nxv8i8:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli zero, a0, e8, m1, ta, ma
+; CHECK-NEXT:    vsrl.vi v9, v8, 1, v0.t
+; CHECK-NEXT:    li a0, 85
+; CHECK-NEXT:    vand.vx v9, v9, a0, v0.t
+; CHECK-NEXT:    vsub.vv v8, v8, v9, v0.t
+; CHECK-NEXT:    li a0, 51
+; CHECK-NEXT:    vand.vx v9, v8, a0, v0.t
+; CHECK-NEXT:    vsrl.vi v8, v8, 2, v0.t
+; CHECK-NEXT:    vand.vx v8, v8, a0, v0.t
+; CHECK-NEXT:    vadd.vv v8, v9, v8, v0.t
+; CHECK-NEXT:    vsrl.vi v9, v8, 4, v0.t
+; CHECK-NEXT:    vadd.vv v8, v8, v9, v0.t
+; CHECK-NEXT:    vand.vi v8, v8, 15, v0.t
+; CHECK-NEXT:    ret
+  %v = call <vscale x 8 x i8> @llvm.vp.ctpop.nxv8i8(<vscale x 8 x i8> %va, <vscale x 8 x i1> %m, i32 %evl)
+  ret <vscale x 8 x i8> %v
+}
+
+define <vscale x 8 x i8> @vp_ctpop_nxv8i8_unmasked(<vscale x 8 x i8> %va, i32 zeroext %evl) {
+; CHECK-LABEL: vp_ctpop_nxv8i8_unmasked:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli zero, a0, e8, m1, ta, ma
+; CHECK-NEXT:    vsrl.vi v9, v8, 1
+; CHECK-NEXT:    li a0, 85
+; CHECK-NEXT:    vand.vx v9, v9, a0
+; CHECK-NEXT:    vsub.vv v8, v8, v9
+; CHECK-NEXT:    li a0, 51
+; CHECK-NEXT:    vand.vx v9, v8, a0
+; CHECK-NEXT:    vsrl.vi v8, v8, 2
+; CHECK-NEXT:    vand.vx v8, v8, a0
+; CHECK-NEXT:    vadd.vv v8, v9, v8
+; CHECK-NEXT:    vsrl.vi v9, v8, 4
+; CHECK-NEXT:    vadd.vv v8, v8, v9
+; CHECK-NEXT:    vand.vi v8, v8, 15
+; CHECK-NEXT:    ret
+  %head = insertelement <vscale x 8 x i1> poison, i1 true, i32 0
+  %m = shufflevector <vscale x 8 x i1> %head, <vscale x 8 x i1> poison, <vscale x 8 x i32> zeroinitializer
+  %v = call <vscale x 8 x i8> @llvm.vp.ctpop.nxv8i8(<vscale x 8 x i8> %va, <vscale x 8 x i1> %m, i32 %evl)
+  ret <vscale x 8 x i8> %v
+}
+
+declare <vscale x 16 x i8> @llvm.vp.ctpop.nxv16i8(<vscale x 16 x i8>, <vscale x 16 x i1>, i32)
+
+define <vscale x 16 x i8> @vp_ctpop_nxv16i8(<vscale x 16 x i8> %va, <vscale x 16 x i1> %m, i32 zeroext %evl) {
+; CHECK-LABEL: vp_ctpop_nxv16i8:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli zero, a0, e8, m2, ta, ma
+; CHECK-NEXT:    vsrl.vi v10, v8, 1, v0.t
+; CHECK-NEXT:    li a0, 85
+; CHECK-NEXT:    vand.vx v10, v10, a0, v0.t
+; CHECK-NEXT:    vsub.vv v8, v8, v10, v0.t
+; CHECK-NEXT:    li a0, 51
+; CHECK-NEXT:    vand.vx v10, v8, a0, v0.t
+; CHECK-NEXT:    vsrl.vi v8, v8, 2, v0.t
+; CHECK-NEXT:    vand.vx v8, v8, a0, v0.t
+; CHECK-NEXT:    vadd.vv v8, v10, v8, v0.t
+; CHECK-NEXT:    vsrl.vi v10, v8, 4, v0.t
+; CHECK-NEXT:    vadd.vv v8, v8, v10, v0.t
+; CHECK-NEXT:    vand.vi v8, v8, 15, v0.t
+; CHECK-NEXT:    ret
+  %v = call <vscale x 16 x i8> @llvm.vp.ctpop.nxv16i8(<vscale x 16 x i8> %va, <vscale x 16 x i1> %m, i32 %evl)
+  ret <vscale x 16 x i8> %v
+}
+
+define <vscale x 16 x i8> @vp_ctpop_nxv16i8_unmasked(<vscale x 16 x i8> %va, i32 zeroext %evl) {
+; CHECK-LABEL: vp_ctpop_nxv16i8_unmasked:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli zero, a0, e8, m2, ta, ma
+; CHECK-NEXT:    vsrl.vi v10, v8, 1
+; CHECK-NEXT:    li a0, 85
+; CHECK-NEXT:    vand.vx v10, v10, a0
+; CHECK-NEXT:    vsub.vv v8, v8, v10
+; CHECK-NEXT:    li a0, 51
+; CHECK-NEXT:    vand.vx v10, v8, a0
+; CHECK-NEXT:    vsrl.vi v8, v8, 2
+; CHECK-NEXT:    vand.vx v8, v8, a0
+; CHECK-NEXT:    vadd.vv v8, v10, v8
+; CHECK-NEXT:    vsrl.vi v10, v8, 4
+; CHECK-NEXT:    vadd.vv v8, v8, v10
+; CHECK-NEXT:    vand.vi v8, v8, 15
+; CHECK-NEXT:    ret
+  %head = insertelement <vscale x 16 x i1> poison, i1 true, i32 0
+  %m = shufflevector <vscale x 16 x i1> %head, <vscale x 16 x i1> poison, <vscale x 16 x i32> zeroinitializer
+  %v = call <vscale x 16 x i8> @llvm.vp.ctpop.nxv16i8(<vscale x 16 x i8> %va, <vscale x 16 x i1> %m, i32 %evl)
+  ret <vscale x 16 x i8> %v
+}
+
+declare <vscale x 32 x i8> @llvm.vp.ctpop.nxv32i8(<vscale x 32 x i8>, <vscale x 32 x i1>, i32)
+
+define <vscale x 32 x i8> @vp_ctpop_nxv32i8(<vscale x 32 x i8> %va, <vscale x 32 x i1> %m, i32 zeroext %evl) {
+; CHECK-LABEL: vp_ctpop_nxv32i8:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli zero, a0, e8, m4, ta, ma
+; CHECK-NEXT:    vsrl.vi v12, v8, 1, v0.t
+; CHECK-NEXT:    li a0, 85
+; CHECK-NEXT:    vand.vx v12, v12, a0, v0.t
+; CHECK-NEXT:    vsub.vv v8, v8, v12, v0.t
+; CHECK-NEXT:    li a0, 51
+; CHECK-NEXT:    vand.vx v12, v8, a0, v0.t
+; CHECK-NEXT:    vsrl.vi v8, v8, 2, v0.t
+; CHECK-NEXT:    vand.vx v8, v8, a0, v0.t
+; CHECK-NEXT:    vadd.vv v8, v12, v8, v0.t
+; CHECK-NEXT:    vsrl.vi v12, v8, 4, v0.t
+; CHECK-NEXT:    vadd.vv v8, v8, v12, v0.t
+; CHECK-NEXT:    vand.vi v8, v8, 15, v0.t
+; CHECK-NEXT:    ret
+  %v = call <vscale x 32 x i8> @llvm.vp.ctpop.nxv32i8(<vscale x 32 x i8> %va, <vscale x 32 x i1> %m, i32 %evl)
+  ret <vscale x 32 x i8> %v
+}
+
+define <vscale x 32 x i8> @vp_ctpop_nxv32i8_unmasked(<vscale x 32 x i8> %va, i32 zeroext %evl) {
+; CHECK-LABEL: vp_ctpop_nxv32i8_unmasked:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli zero, a0, e8, m4, ta, ma
+; CHECK-NEXT:    vsrl.vi v12, v8, 1
+; CHECK-NEXT:    li a0, 85
+; CHECK-NEXT:    vand.vx v12, v12, a0
+; CHECK-NEXT:    vsub.vv v8, v8, v12
+; CHECK-NEXT:    li a0, 51
+; CHECK-NEXT:    vand.vx v12, v8, a0
+; CHECK-NEXT:    vsrl.vi v8, v8, 2
+; CHECK-NEXT:    vand.vx v8, v8, a0
+; CHECK-NEXT:    vadd.vv v8, v12, v8
+; CHECK-NEXT:    vsrl.vi v12, v8, 4
+; CHECK-NEXT:    vadd.vv v8, v8, v12
+; CHECK-NEXT:    vand.vi v8, v8, 15
+; CHECK-NEXT:    ret
+  %head = insertelement <vscale x 32 x i1> poison, i1 true, i32 0
+  %m = shufflevector <vscale x 32 x i1> %head, <vscale x 32 x i1> poison, <vscale x 32 x i32> zeroinitializer
+  %v = call <vscale x 32 x i8> @llvm.vp.ctpop.nxv32i8(<vscale x 32 x i8> %va, <vscale x 32 x i1> %m, i32 %evl)
+  ret <vscale x 32 x i8> %v
+}
+
+declare <vscale x 64 x i8> @llvm.vp.ctpop.nxv64i8(<vscale x 64 x i8>, <vscale x 64 x i1>, i32)
+
+define <vscale x 64 x i8> @vp_ctpop_nxv64i8(<vscale x 64 x i8> %va, <vscale x 64 x i1> %m, i32 zeroext %evl) {
+; CHECK-LABEL: vp_ctpop_nxv64i8:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli zero, a0, e8, m8, ta, ma
+; CHECK-NEXT:    vsrl.vi v16, v8, 1, v0.t
+; CHECK-NEXT:    li a0, 85
+; CHECK-NEXT:    vand.vx v16, v16, a0, v0.t
+; CHECK-NEXT:    vsub.vv v8, v8, v16, v0.t
+; CHECK-NEXT:    li a0, 51
+; CHECK-NEXT:    vand.vx v16, v8, a0, v0.t
+; CHECK-NEXT:    vsrl.vi v8, v8, 2, v0.t
+; CHECK-NEXT:    vand.vx v8, v8, a0, v0.t
+; CHECK-NEXT:    vadd.vv v8, v16, v8, v0.t
+; CHECK-NEXT:    vsrl.vi v16, v8, 4, v0.t
+; CHECK-NEXT:    vadd.vv v8, v8, v16, v0.t
+; CHECK-NEXT:    vand.vi v8, v8, 15, v0.t
+; CHECK-NEXT:    ret
+  %v = call <vscale x 64 x i8> @llvm.vp.ctpop.nxv64i8(<vscale x 64 x i8> %va, <vscale x 64 x i1> %m, i32 %evl)
+  ret <vscale x 64 x i8> %v
+}
+
+define <vscale x 64 x i8> @vp_ctpop_nxv64i8_unmasked(<vscale x 64 x i8> %va, i32 zeroext %evl) {
+; CHECK-LABEL: vp_ctpop_nxv64i8_unmasked:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli zero, a0, e8, m8, ta, ma
+; CHECK-NEXT:    vsrl.vi v16, v8, 1
+; CHECK-NEXT:    li a0, 85
+; CHECK-NEXT:    vand.vx v16, v16, a0
+; CHECK-NEXT:    vsub.vv v8, v8, v16
+; CHECK-NEXT:    li a0, 51
+; CHECK-NEXT:    vand.vx v16, v8, a0
+; CHECK-NEXT:    vsrl.vi v8, v8, 2
+; CHECK-NEXT:    vand.vx v8, v8, a0
+; CHECK-NEXT:    vadd.vv v8, v16, v8
+; CHECK-NEXT:    vsrl.vi v16, v8, 4
+; CHECK-NEXT:    vadd.vv v8, v8, v16
+; CHECK-NEXT:    vand.vi v8, v8, 15
+; CHECK-NEXT:    ret
+  %head = insertelement <vscale x 64 x i1> poison, i1 true, i32 0
+  %m = shufflevector <vscale x 64 x i1> %head, <vscale x 64 x i1> poison, <vscale x 64 x i32> zeroinitializer
+  %v = call <vscale x 64 x i8> @llvm.vp.ctpop.nxv64i8(<vscale x 64 x i8> %va, <vscale x 64 x i1> %m, i32 %evl)
+  ret <vscale x 64 x i8> %v
+}
+
+declare <vscale x 1 x i16> @llvm.vp.ctpop.nxv1i16(<vscale x 1 x i16>, <vscale x 1 x i1>, i32)
+
+define <vscale x 1 x i16> @vp_ctpop_nxv1i16(<vscale x 1 x i16> %va, <vscale x 1 x i1> %m, i32 zeroext %evl) {
+; RV32-LABEL: vp_ctpop_nxv1i16:
+; RV32:       # %bb.0:
+; RV32-NEXT:    vsetvli zero, a0, e16, mf4, ta, ma
+; RV32-NEXT:    vsrl.vi v9, v8, 1, v0.t
+; RV32-NEXT:    lui a0, 5
+; RV32-NEXT:    addi a0, a0, 1365
+; RV32-NEXT:    vand.vx v9, v9, a0, v0.t
+; RV32-NEXT:    vsub.vv v8, v8, v9, v0.t
+; RV32-NEXT:    lui a0, 3
+; RV32-NEXT:    addi a0, a0, 819
+; RV32-NEXT:    vand.vx v9, v8, a0, v0.t
+; RV32-NEXT:    vsrl.vi v8, v8, 2, v0.t
+; RV32-NEXT:    vand.vx v8, v8, a0, v0.t
+; RV32-NEXT:    vadd.vv v8, v9, v8, v0.t
+; RV32-NEXT:    vsrl.vi v9, v8, 4, v0.t
+; RV32-NEXT:    vadd.vv v8, v8, v9, v0.t
+; RV32-NEXT:    lui a0, 1
+; RV32-NEXT:    addi a0, a0, -241
+; RV32-NEXT:    vand.vx v8, v8, a0, v0.t
+; RV32-NEXT:    li a0, 257
+; RV32-NEXT:    vmul.vx v8, v8, a0, v0.t
+; RV32-NEXT:    vsrl.vi v8, v8, 8, v0.t
+; RV32-NEXT:    ret
+;
+; RV64-LABEL: vp_ctpop_nxv1i16:
+; RV64:       # %bb.0:
+; RV64-NEXT:    vsetvli zero, a0, e16, mf4, ta, ma
+; RV64-NEXT:    vsrl.vi v9, v8, 1, v0.t
+; RV64-NEXT:    lui a0, 5
+; RV64-NEXT:    addiw a0, a0, 1365
+; RV64-NEXT:    vand.vx v9, v9, a0, v0.t
+; RV64-NEXT:    vsub.vv v8, v8, v9, v0.t
+; RV64-NEXT:    lui a0, 3
+; RV64-NEXT:    addiw a0, a0, 819
+; RV64-NEXT:    vand.vx v9, v8, a0, v0.t
+; RV64-NEXT:    vsrl.vi v8, v8, 2, v0.t
+; RV64-NEXT:    vand.vx v8, v8, a0, v0.t
+; RV64-NEXT:    vadd.vv v8, v9, v8, v0.t
+; RV64-NEXT:    vsrl.vi v9, v8, 4, v0.t
+; RV64-NEXT:    vadd.vv v8, v8, v9, v0.t
+; RV64-NEXT:    lui a0, 1
+; RV64-NEXT:    addiw a0, a0, -241
+; RV64-NEXT:    vand.vx v8, v8, a0, v0.t
+; RV64-NEXT:    li a0, 257
+; RV64-NEXT:    vmul.vx v8, v8, a0, v0.t
+; RV64-NEXT:    vsrl.vi v8, v8, 8, v0.t
+; RV64-NEXT:    ret
+  %v = call <vscale x 1 x i16> @llvm.vp.ctpop.nxv1i16(<vscale x 1 x i16> %va, <vscale x 1 x i1> %m, i32 %evl)
+  ret <vscale x 1 x i16> %v
+}
+
+define <vscale x 1 x i16> @vp_ctpop_nxv1i16_unmasked(<vscale x 1 x i16> %va, i32 zeroext %evl) {
+; RV32-LABEL: vp_ctpop_nxv1i16_unmasked:
+; RV32:       # %bb.0:
+; RV32-NEXT:    vsetvli zero, a0, e16, mf4, ta, ma
+; RV32-NEXT:    vsrl.vi v9, v8, 1
+; RV32-NEXT:    lui a0, 5
+; RV32-NEXT:    addi a0, a0, 1365
+; RV32-NEXT:    vand.vx v9, v9, a0
+; RV32-NEXT:    vsub.vv v8, v8, v9
+; RV32-NEXT:    lui a0, 3
+; RV32-NEXT:    addi a0, a0, 819
+; RV32-NEXT:    vand.vx v9, v8, a0
+; RV32-NEXT:    vsrl.vi v8, v8, 2
+; RV32-NEXT:    vand.vx v8, v8, a0
+; RV32-NEXT:    vadd.vv v8, v9, v8
+; RV32-NEXT:    vsrl.vi v9, v8, 4
+; RV32-NEXT:    vadd.vv v8, v8, v9
+; RV32-NEXT:    lui a0, 1
+; RV32-NEXT:    addi a0, a0, -241
+; RV32-NEXT:    vand.vx v8, v8, a0
+; RV32-NEXT:    li a0, 257
+; RV32-NEXT:    vmul.vx v8, v8, a0
+; RV32-NEXT:    vsrl.vi v8, v8, 8
+; RV32-NEXT:    ret
+;
+; RV64-LABEL: vp_ctpop_nxv1i16_unmasked:
+; RV64:       # %bb.0:
+; RV64-NEXT:    vsetvli zero, a0, e16, mf4, ta, ma
+; RV64-NEXT:    vsrl.vi v9, v8, 1
+; RV64-NEXT:    lui a0, 5
+; RV64-NEXT:    addiw a0, a0, 1365
+; RV64-NEXT:    vand.vx v9, v9, a0
+; RV64-NEXT:    vsub.vv v8, v8, v9
+; RV64-NEXT:    lui a0, 3
+; RV64-NEXT:    addiw a0, a0, 819
+; RV64-NEXT:    vand.vx v9, v8, a0
+; RV64-NEXT:    vsrl.vi v8, v8, 2
+; RV64-NEXT:    vand.vx v8, v8, a0
+; RV64-NEXT:    vadd.vv v8, v9, v8
+; RV64-NEXT:    vsrl.vi v9, v8, 4
+; RV64-NEXT:    vadd.vv v8, v8, v9
+; RV64-NEXT:    lui a0, 1
+; RV64-NEXT:    addiw a0, a0, -241
+; RV64-NEXT:    vand.vx v8, v8, a0
+; RV64-NEXT:    li a0, 257
+; RV64-NEXT:    vmul.vx v8, v8, a0
+; RV64-NEXT:    vsrl.vi v8, v8, 8
+; RV64-NEXT:    ret
+  %head = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
+  %m = shufflevector <vscale x 1 x i1> %head, <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
+  %v = call <vscale x 1 x i16> @llvm.vp.ctpop.nxv1i16(<vscale x 1 x i16> %va, <vscale x 1 x i1> %m, i32 %evl)
+  ret <vscale x 1 x i16> %v
+}
+
+declare <vscale x 2 x i16> @llvm.vp.ctpop.nxv2i16(<vscale x 2 x i16>, <vscale x 2 x i1>, i32)
+
+define <vscale x 2 x i16> @vp_ctpop_nxv2i16(<vscale x 2 x i16> %va, <vscale x 2 x i1> %m, i32 zeroext %evl) {
+; RV32-LABEL: vp_ctpop_nxv2i16:
+; RV32:       # %bb.0:
+; RV32-NEXT:    vsetvli zero, a0, e16, mf2, ta, ma
+; RV32-NEXT:    vsrl.vi v9, v8, 1, v0.t
+; RV32-NEXT:    lui a0, 5
+; RV32-NEXT:    addi a0, a0, 1365
+; RV32-NEXT:    vand.vx v9, v9, a0, v0.t
+; RV32-NEXT:    vsub.vv v8, v8, v9, v0.t
+; RV32-NEXT:    lui a0, 3
+; RV32-NEXT:    addi a0, a0, 819
+; RV32-NEXT:    vand.vx v9, v8, a0, v0.t
+; RV32-NEXT:    vsrl.vi v8, v8, 2, v0.t
+; RV32-NEXT:    vand.vx v8, v8, a0, v0.t
+; RV32-NEXT:    vadd.vv v8, v9, v8, v0.t
+; RV32-NEXT:    vsrl.vi v9, v8, 4, v0.t
+; RV32-NEXT:    vadd.vv v8, v8, v9, v0.t
+; RV32-NEXT:    lui a0, 1
+; RV32-NEXT:    addi a0, a0, -241
+; RV32-NEXT:    vand.vx v8, v8, a0, v0.t
+; RV32-NEXT:    li a0, 257
+; RV32-NEXT:    vmul.vx v8, v8, a0, v0.t
+; RV32-NEXT:    vsrl.vi v8, v8, 8, v0.t
+; RV32-NEXT:    ret
+;
+; RV64-LABEL: vp_ctpop_nxv2i16:
+; RV64:       # %bb.0:
+; RV64-NEXT:    vsetvli zero, a0, e16, mf2, ta, ma
+; RV64-NEXT:    vsrl.vi v9, v8, 1, v0.t
+; RV64-NEXT:    lui a0, 5
+; RV64-NEXT:    addiw a0, a0, 1365
+; RV64-NEXT:    vand.vx v9, v9, a0, v0.t
+; RV64-NEXT:    vsub.vv v8, v8, v9, v0.t
+; RV64-NEXT:    lui a0, 3
+; RV64-NEXT:    addiw a0, a0, 819
+; RV64-NEXT:    vand.vx v9, v8, a0, v0.t
+; RV64-NEXT:    vsrl.vi v8, v8, 2, v0.t
+; RV64-NEXT:    vand.vx v8, v8, a0, v0.t
+; RV64-NEXT:    vadd.vv v8, v9, v8, v0.t
+; RV64-NEXT:    vsrl.vi v9, v8, 4, v0.t
+; RV64-NEXT:    vadd.vv v8, v8, v9, v0.t
+; RV64-NEXT:    lui a0, 1
+; RV64-NEXT:    addiw a0, a0, -241
+; RV64-NEXT:    vand.vx v8, v8, a0, v0.t
+; RV64-NEXT:    li a0, 257
+; RV64-NEXT:    vmul.vx v8, v8, a0, v0.t
+; RV64-NEXT:    vsrl.vi v8, v8, 8, v0.t
+; RV64-NEXT:    ret
+  %v = call <vscale x 2 x i16> @llvm.vp.ctpop.nxv2i16(<vscale x 2 x i16> %va, <vscale x 2 x i1> %m, i32 %evl)
+  ret <vscale x 2 x i16> %v
+}
+
+define <vscale x 2 x i16> @vp_ctpop_nxv2i16_unmasked(<vscale x 2 x i16> %va, i32 zeroext %evl) {
+; RV32-LABEL: vp_ctpop_nxv2i16_unmasked:
+; RV32:       # %bb.0:
+; RV32-NEXT:    vsetvli zero, a0, e16, mf2, ta, ma
+; RV32-NEXT:    vsrl.vi v9, v8, 1
+; RV32-NEXT:    lui a0, 5
+; RV32-NEXT:    addi a0, a0, 1365
+; RV32-NEXT:    vand.vx v9, v9, a0
+; RV32-NEXT:    vsub.vv v8, v8, v9
+; RV32-NEXT:    lui a0, 3
+; RV32-NEXT:    addi a0, a0, 819
+; RV32-NEXT:    vand.vx v9, v8, a0
+; RV32-NEXT:    vsrl.vi v8, v8, 2
+; RV32-NEXT:    vand.vx v8, v8, a0
+; RV32-NEXT:    vadd.vv v8, v9, v8
+; RV32-NEXT:    vsrl.vi v9, v8, 4
+; RV32-NEXT:    vadd.vv v8, v8, v9
+; RV32-NEXT:    lui a0, 1
+; RV32-NEXT:    addi a0, a0, -241
+; RV32-NEXT:    vand.vx v8, v8, a0
+; RV32-NEXT:    li a0, 257
+; RV32-NEXT:    vmul.vx v8, v8, a0
+; RV32-NEXT:    vsrl.vi v8, v8, 8
+; RV32-NEXT:    ret
+;
+; RV64-LABEL: vp_ctpop_nxv2i16_unmasked:
+; RV64:       # %bb.0:
+; RV64-NEXT:    vsetvli zero, a0, e16, mf2, ta, ma
+; RV64-NEXT:    vsrl.vi v9, v8, 1
+; RV64-NEXT:    lui a0, 5
+; RV64-NEXT:    addiw a0, a0, 1365
+; RV64-NEXT:    vand.vx v9, v9, a0
+; RV64-NEXT:    vsub.vv v8, v8, v9
+; RV64-NEXT:    lui a0, 3
+; RV64-NEXT:    addiw a0, a0, 819
+; RV64-NEXT:    vand.vx v9, v8, a0
+; RV64-NEXT:    vsrl.vi v8, v8, 2
+; RV64-NEXT:    vand.vx v8, v8, a0
+; RV64-NEXT:    vadd.vv v8, v9, v8
+; RV64-NEXT:    vsrl.vi v9, v8, 4
+; RV64-NEXT:    vadd.vv v8, v8, v9
+; RV64-NEXT:    lui a0, 1
+; RV64-NEXT:    addiw a0, a0, -241
+; RV64-NEXT:    vand.vx v8, v8, a0
+; RV64-NEXT:    li a0, 257
+; RV64-NEXT:    vmul.vx v8, v8, a0
+; RV64-NEXT:    vsrl.vi v8, v8, 8
+; RV64-NEXT:    ret
+  %head = insertelement <vscale x 2 x i1> poison, i1 true, i32 0
+  %m = shufflevector <vscale x 2 x i1> %head, <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer
+  %v = call <vscale x 2 x i16> @llvm.vp.ctpop.nxv2i16(<vscale x 2 x i16> %va, <vscale x 2 x i1> %m, i32 %evl)
+  ret <vscale x 2 x i16> %v
+}
+
+declare <vscale x 4 x i16> @llvm.vp.ctpop.nxv4i16(<vscale x 4 x i16>, <vscale x 4 x i1>, i32)
+
+define <vscale x 4 x i16> @vp_ctpop_nxv4i16(<vscale x 4 x i16> %va, <vscale x 4 x i1> %m, i32 zeroext %evl) {
+; RV32-LABEL: vp_ctpop_nxv4i16:
+; RV32:       # %bb.0:
+; RV32-NEXT:    vsetvli zero, a0, e16, m1, ta, ma
+; RV32-NEXT:    vsrl.vi v9, v8, 1, v0.t
+; RV32-NEXT:    lui a0, 5
+; RV32-NEXT:    addi a0, a0, 1365
+; RV32-NEXT:    vand.vx v9, v9, a0, v0.t
+; RV32-NEXT:    vsub.vv v8, v8, v9, v0.t
+; RV32-NEXT:    lui a0, 3
+; RV32-NEXT:    addi a0, a0, 819
+; RV32-NEXT:    vand.vx v9, v8, a0, v0.t
+; RV32-NEXT:    vsrl.vi v8, v8, 2, v0.t
+; RV32-NEXT:    vand.vx v8, v8, a0, v0.t
+; RV32-NEXT:    vadd.vv v8, v9, v8, v0.t
+; RV32-NEXT:    vsrl.vi v9, v8, 4, v0.t
+; RV32-NEXT:    vadd.vv v8, v8, v9, v0.t
+; RV32-NEXT:    lui a0, 1
+; RV32-NEXT:    addi a0, a0, -241
+; RV32-NEXT:    vand.vx v8, v8, a0, v0.t
+; RV32-NEXT:    li a0, 257
+; RV32-NEXT:    vmul.vx v8, v8, a0, v0.t
+; RV32-NEXT:    vsrl.vi v8, v8, 8, v0.t
+; RV32-NEXT:    ret
+;
+; RV64-LABEL: vp_ctpop_nxv4i16:
+; RV64:       # %bb.0:
+; RV64-NEXT:    vsetvli zero, a0, e16, m1, ta, ma
+; RV64-NEXT:    vsrl.vi v9, v8, 1, v0.t
+; RV64-NEXT:    lui a0, 5
+; RV64-NEXT:    addiw a0, a0, 1365
+; RV64-NEXT:    vand.vx v9, v9, a0, v0.t
+; RV64-NEXT:    vsub.vv v8, v8, v9, v0.t
+; RV64-NEXT:    lui a0, 3
+; RV64-NEXT:    addiw a0, a0, 819
+; RV64-NEXT:    vand.vx v9, v8, a0, v0.t
+; RV64-NEXT:    vsrl.vi v8, v8, 2, v0.t
+; RV64-NEXT:    vand.vx v8, v8, a0, v0.t
+; RV64-NEXT:    vadd.vv v8, v9, v8, v0.t
+; RV64-NEXT:    vsrl.vi v9, v8, 4, v0.t
+; RV64-NEXT:    vadd.vv v8, v8, v9, v0.t
+; RV64-NEXT:    lui a0, 1
+; RV64-NEXT:    addiw a0, a0, -241
+; RV64-NEXT:    vand.vx v8, v8, a0, v0.t
+; RV64-NEXT:    li a0, 257
+; RV64-NEXT:    vmul.vx v8, v8, a0, v0.t
+; RV64-NEXT:    vsrl.vi v8, v8, 8, v0.t
+; RV64-NEXT:    ret
+  %v = call <vscale x 4 x i16> @llvm.vp.ctpop.nxv4i16(<vscale x 4 x i16> %va, <vscale x 4 x i1> %m, i32 %evl)
+  ret <vscale x 4 x i16> %v
+}
+
+define <vscale x 4 x i16> @vp_ctpop_nxv4i16_unmasked(<vscale x 4 x i16> %va, i32 zeroext %evl) {
+; RV32-LABEL: vp_ctpop_nxv4i16_unmasked:
+; RV32:       # %bb.0:
+; RV32-NEXT:    vsetvli zero, a0, e16, m1, ta, ma
+; RV32-NEXT:    vsrl.vi v9, v8, 1
+; RV32-NEXT:    lui a0, 5
+; RV32-NEXT:    addi a0, a0, 1365
+; RV32-NEXT:    vand.vx v9, v9, a0
+; RV32-NEXT:    vsub.vv v8, v8, v9
+; RV32-NEXT:    lui a0, 3
+; RV32-NEXT:    addi a0, a0, 819
+; RV32-NEXT:    vand.vx v9, v8, a0
+; RV32-NEXT:    vsrl.vi v8, v8, 2
+; RV32-NEXT:    vand.vx v8, v8, a0
+; RV32-NEXT:    vadd.vv v8, v9, v8
+; RV32-NEXT:    vsrl.vi v9, v8, 4
+; RV32-NEXT:    vadd.vv v8, v8, v9
+; RV32-NEXT:    lui a0, 1
+; RV32-NEXT:    addi a0, a0, -241
+; RV32-NEXT:    vand.vx v8, v8, a0
+; RV32-NEXT:    li a0, 257
+; RV32-NEXT:    vmul.vx v8, v8, a0
+; RV32-NEXT:    vsrl.vi v8, v8, 8
+; RV32-NEXT:    ret
+;
+; RV64-LABEL: vp_ctpop_nxv4i16_unmasked:
+; RV64:       # %bb.0:
+; RV64-NEXT:    vsetvli zero, a0, e16, m1, ta, ma
+; RV64-NEXT:    vsrl.vi v9, v8, 1
+; RV64-NEXT:    lui a0, 5
+; RV64-NEXT:    addiw a0, a0, 1365
+; RV64-NEXT:    vand.vx v9, v9, a0
+; RV64-NEXT:    vsub.vv v8, v8, v9
+; RV64-NEXT:    lui a0, 3
+; RV64-NEXT:    addiw a0, a0, 819
+; RV64-NEXT:    vand.vx v9, v8, a0
+; RV64-NEXT:    vsrl.vi v8, v8, 2
+; RV64-NEXT:    vand.vx v8, v8, a0
+; RV64-NEXT:    vadd.vv v8, v9, v8
+; RV64-NEXT:    vsrl.vi v9, v8, 4
+; RV64-NEXT:    vadd.vv v8, v8, v9
+; RV64-NEXT:    lui a0, 1
+; RV64-NEXT:    addiw a0, a0, -241
+; RV64-NEXT:    vand.vx v8, v8, a0
+; RV64-NEXT:    li a0, 257
+; RV64-NEXT:    vmul.vx v8, v8, a0
+; RV64-NEXT:    vsrl.vi v8, v8, 8
+; RV64-NEXT:    ret
+  %head = insertelement <vscale x 4 x i1> poison, i1 true, i32 0
+  %m = shufflevector <vscale x 4 x i1> %head, <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer
+  %v = call <vscale x 4 x i16> @llvm.vp.ctpop.nxv4i16(<vscale x 4 x i16> %va, <vscale x 4 x i1> %m, i32 %evl)
+  ret <vscale x 4 x i16> %v
+}
+
+declare <vscale x 8 x i16> @llvm.vp.ctpop.nxv8i16(<vscale x 8 x i16>, <vscale x 8 x i1>, i32)
+
+define <vscale x 8 x i16> @vp_ctpop_nxv8i16(<vscale x 8 x i16> %va, <vscale x 8 x i1> %m, i32 zeroext %evl) {
+; RV32-LABEL: vp_ctpop_nxv8i16:
+; RV32:       # %bb.0:
+; RV32-NEXT:    vsetvli zero, a0, e16, m2, ta, ma
+; RV32-NEXT:    vsrl.vi v10, v8, 1, v0.t
+; RV32-NEXT:    lui a0, 5
+; RV32-NEXT:    addi a0, a0, 1365
+; RV32-NEXT:    vand.vx v10, v10, a0, v0.t
+; RV32-NEXT:    vsub.vv v8, v8, v10, v0.t
+; RV32-NEXT:    lui a0, 3
+; RV32-NEXT:    addi a0, a0, 819
+; RV32-NEXT:    vand.vx v10, v8, a0, v0.t
+; RV32-NEXT:    vsrl.vi v8, v8, 2, v0.t
+; RV32-NEXT:    vand.vx v8, v8, a0, v0.t
+; RV32-NEXT:    vadd.vv v8, v10, v8, v0.t
+; RV32-NEXT:    vsrl.vi v10, v8, 4, v0.t
+; RV32-NEXT:    vadd.vv v8, v8, v10, v0.t
+; RV32-NEXT:    lui a0, 1
+; RV32-NEXT:    addi a0, a0, -241
+; RV32-NEXT:    vand.vx v8, v8, a0, v0.t
+; RV32-NEXT:    li a0, 257
+; RV32-NEXT:    vmul.vx v8, v8, a0, v0.t
+; RV32-NEXT:    vsrl.vi v8, v8, 8, v0.t
+; RV32-NEXT:    ret
+;
+; RV64-LABEL: vp_ctpop_nxv8i16:
+; RV64:       # %bb.0:
+; RV64-NEXT:    vsetvli zero, a0, e16, m2, ta, ma
+; RV64-NEXT:    vsrl.vi v10, v8, 1, v0.t
+; RV64-NEXT:    lui a0, 5
+; RV64-NEXT:    addiw a0, a0, 1365
+; RV64-NEXT:    vand.vx v10, v10, a0, v0.t
+; RV64-NEXT:    vsub.vv v8, v8, v10, v0.t
+; RV64-NEXT:    lui a0, 3
+; RV64-NEXT:    addiw a0, a0, 819
+; RV64-NEXT:    vand.vx v10, v8, a0, v0.t
+; RV64-NEXT:    vsrl.vi v8, v8, 2, v0.t
+; RV64-NEXT:    vand.vx v8, v8, a0, v0.t
+; RV64-NEXT:    vadd.vv v8, v10, v8, v0.t
+; RV64-NEXT:    vsrl.vi v10, v8, 4, v0.t
+; RV64-NEXT:    vadd.vv v8, v8, v10, v0.t
+; RV64-NEXT:    lui a0, 1
+; RV64-NEXT:    addiw a0, a0, -241
+; RV64-NEXT:    vand.vx v8, v8, a0, v0.t
+; RV64-NEXT:    li a0, 257
+; RV64-NEXT:    vmul.vx v8, v8, a0, v0.t
+; RV64-NEXT:    vsrl.vi v8, v8, 8, v0.t
+; RV64-NEXT:    ret
+  %v = call <vscale x 8 x i16> @llvm.vp.ctpop.nxv8i16(<vscale x 8 x i16> %va, <vscale x 8 x i1> %m, i32 %evl)
+  ret <vscale x 8 x i16> %v
+}
+
+define <vscale x 8 x i16> @vp_ctpop_nxv8i16_unmasked(<vscale x 8 x i16> %va, i32 zeroext %evl) {
+; RV32-LABEL: vp_ctpop_nxv8i16_unmasked:
+; RV32:       # %bb.0:
+; RV32-NEXT:    vsetvli zero, a0, e16, m2, ta, ma
+; RV32-NEXT:    vsrl.vi v10, v8, 1
+; RV32-NEXT:    lui a0, 5
+; RV32-NEXT:    addi a0, a0, 1365
+; RV32-NEXT:    vand.vx v10, v10, a0
+; RV32-NEXT:    vsub.vv v8, v8, v10
+; RV32-NEXT:    lui a0, 3
+; RV32-NEXT:    addi a0, a0, 819
+; RV32-NEXT:    vand.vx v10, v8, a0
+; RV32-NEXT:    vsrl.vi v8, v8, 2
+; RV32-NEXT:    vand.vx v8, v8, a0
+; RV32-NEXT:    vadd.vv v8, v10, v8
+; RV32-NEXT:    vsrl.vi v10, v8, 4
+; RV32-NEXT:    vadd.vv v8, v8, v10
+; RV32-NEXT:    lui a0, 1
+; RV32-NEXT:    addi a0, a0, -241
+; RV32-NEXT:    vand.vx v8, v8, a0
+; RV32-NEXT:    li a0, 257
+; RV32-NEXT:    vmul.vx v8, v8, a0
+; RV32-NEXT:    vsrl.vi v8, v8, 8
+; RV32-NEXT:    ret
+;
+; RV64-LABEL: vp_ctpop_nxv8i16_unmasked:
+; RV64:       # %bb.0:
+; RV64-NEXT:    vsetvli zero, a0, e16, m2, ta, ma
+; RV64-NEXT:    vsrl.vi v10, v8, 1
+; RV64-NEXT:    lui a0, 5
+; RV64-NEXT:    addiw a0, a0, 1365
+; RV64-NEXT:    vand.vx v10, v10, a0
+; RV64-NEXT:    vsub.vv v8, v8, v10
+; RV64-NEXT:    lui a0, 3
+; RV64-NEXT:    addiw a0, a0, 819
+; RV64-NEXT:    vand.vx v10, v8, a0
+; RV64-NEXT:    vsrl.vi v8, v8, 2
+; RV64-NEXT:    vand.vx v8, v8, a0
+; RV64-NEXT:    vadd.vv v8, v10, v8
+; RV64-NEXT:    vsrl.vi v10, v8, 4
+; RV64-NEXT:    vadd.vv v8, v8, v10
+; RV64-NEXT:    lui a0, 1
+; RV64-NEXT:    addiw a0, a0, -241
+; RV64-NEXT:    vand.vx v8, v8, a0
+; RV64-NEXT:    li a0, 257
+; RV64-NEXT:    vmul.vx v8, v8, a0
+; RV64-NEXT:    vsrl.vi v8, v8, 8
+; RV64-NEXT:    ret
+  %head = insertelement <vscale x 8 x i1> poison, i1 true, i32 0
+  %m = shufflevector <vscale x 8 x i1> %head, <vscale x 8 x i1> poison, <vscale x 8 x i32> zeroinitializer
+  %v = call <vscale x 8 x i16> @llvm.vp.ctpop.nxv8i16(<vscale x 8 x i16> %va, <vscale x 8 x i1> %m, i32 %evl)
+  ret <vscale x 8 x i16> %v
+}
+
+declare <vscale x 16 x i16> @llvm.vp.ctpop.nxv16i16(<vscale x 16 x i16>, <vscale x 16 x i1>, i32)
+
+define <vscale x 16 x i16> @vp_ctpop_nxv16i16(<vscale x 16 x i16> %va, <vscale x 16 x i1> %m, i32 zeroext %evl) {
+; RV32-LABEL: vp_ctpop_nxv16i16:
+; RV32:       # %bb.0:
+; RV32-NEXT:    vsetvli zero, a0, e16, m4, ta, ma
+; RV32-NEXT:    vsrl.vi v12, v8, 1, v0.t
+; RV32-NEXT:    lui a0, 5
+; RV32-NEXT:    addi a0, a0, 1365
+; RV32-NEXT:    vand.vx v12, v12, a0, v0.t
+; RV32-NEXT:    vsub.vv v8, v8, v12, v0.t
+; RV32-NEXT:    lui a0, 3
+; RV32-NEXT:    addi a0, a0, 819
+; RV32-NEXT:    vand.vx v12, v8, a0, v0.t
+; RV32-NEXT:    vsrl.vi v8, v8, 2, v0.t
+; RV32-NEXT:    vand.vx v8, v8, a0, v0.t
+; RV32-NEXT:    vadd.vv v8, v12, v8, v0.t
+; RV32-NEXT:    vsrl.vi v12, v8, 4, v0.t
+; RV32-NEXT:    vadd.vv v8, v8, v12, v0.t
+; RV32-NEXT:    lui a0, 1
+; RV32-NEXT:    addi a0, a0, -241
+; RV32-NEXT:    vand.vx v8, v8, a0, v0.t
+; RV32-NEXT:    li a0, 257
+; RV32-NEXT:    vmul.vx v8, v8, a0, v0.t
+; RV32-NEXT:    vsrl.vi v8, v8, 8, v0.t
+; RV32-NEXT:    ret
+;
+; RV64-LABEL: vp_ctpop_nxv16i16:
+; RV64:       # %bb.0:
+; RV64-NEXT:    vsetvli zero, a0, e16, m4, ta, ma
+; RV64-NEXT:    vsrl.vi v12, v8, 1, v0.t
+; RV64-NEXT:    lui a0, 5
+; RV64-NEXT:    addiw a0, a0, 1365
+; RV64-NEXT:    vand.vx v12, v12, a0, v0.t
+; RV64-NEXT:    vsub.vv v8, v8, v12, v0.t
+; RV64-NEXT:    lui a0, 3
+; RV64-NEXT:    addiw a0, a0, 819
+; RV64-NEXT:    vand.vx v12, v8, a0, v0.t
+; RV64-NEXT:    vsrl.vi v8, v8, 2, v0.t
+; RV64-NEXT:    vand.vx v8, v8, a0, v0.t
+; RV64-NEXT:    vadd.vv v8, v12, v8, v0.t
+; RV64-NEXT:    vsrl.vi v12, v8, 4, v0.t
+; RV64-NEXT:    vadd.vv v8, v8, v12, v0.t
+; RV64-NEXT:    lui a0, 1
+; RV64-NEXT:    addiw a0, a0, -241
+; RV64-NEXT:    vand.vx v8, v8, a0, v0.t
+; RV64-NEXT:    li a0, 257
+; RV64-NEXT:    vmul.vx v8, v8, a0, v0.t
+; RV64-NEXT:    vsrl.vi v8, v8, 8, v0.t
+; RV64-NEXT:    ret
+  %v = call <vscale x 16 x i16> @llvm.vp.ctpop.nxv16i16(<vscale x 16 x i16> %va, <vscale x 16 x i1> %m, i32 %evl)
+  ret <vscale x 16 x i16> %v
+}
+
+define <vscale x 16 x i16> @vp_ctpop_nxv16i16_unmasked(<vscale x 16 x i16> %va, i32 zeroext %evl) {
+; RV32-LABEL: vp_ctpop_nxv16i16_unmasked:
+; RV32:       # %bb.0:
+; RV32-NEXT:    vsetvli zero, a0, e16, m4, ta, ma
+; RV32-NEXT:    vsrl.vi v12, v8, 1
+; RV32-NEXT:    lui a0, 5
+; RV32-NEXT:    addi a0, a0, 1365
+; RV32-NEXT:    vand.vx v12, v12, a0
+; RV32-NEXT:    vsub.vv v8, v8, v12
+; RV32-NEXT:    lui a0, 3
+; RV32-NEXT:    addi a0, a0, 819
+; RV32-NEXT:    vand.vx v12, v8, a0
+; RV32-NEXT:    vsrl.vi v8, v8, 2
+; RV32-NEXT:    vand.vx v8, v8, a0
+; RV32-NEXT:    vadd.vv v8, v12, v8
+; RV32-NEXT:    vsrl.vi v12, v8, 4
+; RV32-NEXT:    vadd.vv v8, v8, v12
+; RV32-NEXT:    lui a0, 1
+; RV32-NEXT:    addi a0, a0, -241
+; RV32-NEXT:    vand.vx v8, v8, a0
+; RV32-NEXT:    li a0, 257
+; RV32-NEXT:    vmul.vx v8, v8, a0
+; RV32-NEXT:    vsrl.vi v8, v8, 8
+; RV32-NEXT:    ret
+;
+; RV64-LABEL: vp_ctpop_nxv16i16_unmasked:
+; RV64:       # %bb.0:
+; RV64-NEXT:    vsetvli zero, a0, e16, m4, ta, ma
+; RV64-NEXT:    vsrl.vi v12, v8, 1
+; RV64-NEXT:    lui a0, 5
+; RV64-NEXT:    addiw a0, a0, 1365
+; RV64-NEXT:    vand.vx v12, v12, a0
+; RV64-NEXT:    vsub.vv v8, v8, v12
+; RV64-NEXT:    lui a0, 3
+; RV64-NEXT:    addiw a0, a0, 819
+; RV64-NEXT:    vand.vx v12, v8, a0
+; RV64-NEXT:    vsrl.vi v8, v8, 2
+; RV64-NEXT:    vand.vx v8, v8, a0
+; RV64-NEXT:    vadd.vv v8, v12, v8
+; RV64-NEXT:    vsrl.vi v12, v8, 4
+; RV64-NEXT:    vadd.vv v8, v8, v12
+; RV64-NEXT:    lui a0, 1
+; RV64-NEXT:    addiw a0, a0, -241
+; RV64-NEXT:    vand.vx v8, v8, a0
+; RV64-NEXT:    li a0, 257
+; RV64-NEXT:    vmul.vx v8, v8, a0
+; RV64-NEXT:    vsrl.vi v8, v8, 8
+; RV64-NEXT:    ret
+  %head = insertelement <vscale x 16 x i1> poison, i1 true, i32 0
+  %m = shufflevector <vscale x 16 x i1> %head, <vscale x 16 x i1> poison, <vscale x 16 x i32> zeroinitializer
+  %v = call <vscale x 16 x i16> @llvm.vp.ctpop.nxv16i16(<vscale x 16 x i16> %va, <vscale x 16 x i1> %m, i32 %evl)
+  ret <vscale x 16 x i16> %v
+}
+
+declare <vscale x 32 x i16> @llvm.vp.ctpop.nxv32i16(<vscale x 32 x i16>, <vscale x 32 x i1>, i32)
+
+define <vscale x 32 x i16> @vp_ctpop_nxv32i16(<vscale x 32 x i16> %va, <vscale x 32 x i1> %m, i32 zeroext %evl) {
+; RV32-LABEL: vp_ctpop_nxv32i16:
+; RV32:       # %bb.0:
+; RV32-NEXT:    vsetvli zero, a0, e16, m8, ta, ma
+; RV32-NEXT:    vsrl.vi v16, v8, 1, v0.t
+; RV32-NEXT:    lui a0, 5
+; RV32-NEXT:    addi a0, a0, 1365
+; RV32-NEXT:    vand.vx v16, v16, a0, v0.t
+; RV32-NEXT:    vsub.vv v8, v8, v16, v0.t
+; RV32-NEXT:    lui a0, 3
+; RV32-NEXT:    addi a0, a0, 819
+; RV32-NEXT:    vand.vx v16, v8, a0, v0.t
+; RV32-NEXT:    vsrl.vi v8, v8, 2, v0.t
+; RV32-NEXT:    vand.vx v8, v8, a0, v0.t
+; RV32-NEXT:    vadd.vv v8, v16, v8, v0.t
+; RV32-NEXT:    vsrl.vi v16, v8, 4, v0.t
+; RV32-NEXT:    vadd.vv v8, v8, v16, v0.t
+; RV32-NEXT:    lui a0, 1
+; RV32-NEXT:    addi a0, a0, -241
+; RV32-NEXT:    vand.vx v8, v8, a0, v0.t
+; RV32-NEXT:    li a0, 257
+; RV32-NEXT:    vmul.vx v8, v8, a0, v0.t
+; RV32-NEXT:    vsrl.vi v8, v8, 8, v0.t
+; RV32-NEXT:    ret
+;
+; RV64-LABEL: vp_ctpop_nxv32i16:
+; RV64:       # %bb.0:
+; RV64-NEXT:    vsetvli zero, a0, e16, m8, ta, ma
+; RV64-NEXT:    vsrl.vi v16, v8, 1, v0.t
+; RV64-NEXT:    lui a0, 5
+; RV64-NEXT:    addiw a0, a0, 1365
+; RV64-NEXT:    vand.vx v16, v16, a0, v0.t
+; RV64-NEXT:    vsub.vv v8, v8, v16, v0.t
+; RV64-NEXT:    lui a0, 3
+; RV64-NEXT:    addiw a0, a0, 819
+; RV64-NEXT:    vand.vx v16, v8, a0, v0.t
+; RV64-NEXT:    vsrl.vi v8, v8, 2, v0.t
+; RV64-NEXT:    vand.vx v8, v8, a0, v0.t
+; RV64-NEXT:    vadd.vv v8, v16, v8, v0.t
+; RV64-NEXT:    vsrl.vi v16, v8, 4, v0.t
+; RV64-NEXT:    vadd.vv v8, v8, v16, v0.t
+; RV64-NEXT:    lui a0, 1
+; RV64-NEXT:    addiw a0, a0, -241
+; RV64-NEXT:    vand.vx v8, v8, a0, v0.t
+; RV64-NEXT:    li a0, 257
+; RV64-NEXT:    vmul.vx v8, v8, a0, v0.t
+; RV64-NEXT:    vsrl.vi v8, v8, 8, v0.t
+; RV64-NEXT:    ret
+  %v = call <vscale x 32 x i16> @llvm.vp.ctpop.nxv32i16(<vscale x 32 x i16> %va, <vscale x 32 x i1> %m, i32 %evl)
+  ret <vscale x 32 x i16> %v
+}
+
+define <vscale x 32 x i16> @vp_ctpop_nxv32i16_unmasked(<vscale x 32 x i16> %va, i32 zeroext %evl) {
+; RV32-LABEL: vp_ctpop_nxv32i16_unmasked:
+; RV32:       # %bb.0:
+; RV32-NEXT:    vsetvli zero, a0, e16, m8, ta, ma
+; RV32-NEXT:    vsrl.vi v16, v8, 1
+; RV32-NEXT:    lui a0, 5
+; RV32-NEXT:    addi a0, a0, 1365
+; RV32-NEXT:    vand.vx v16, v16, a0
+; RV32-NEXT:    vsub.vv v8, v8, v16
+; RV32-NEXT:    lui a0, 3
+; RV32-NEXT:    addi a0, a0, 819
+; RV32-NEXT:    vand.vx v16, v8, a0
+; RV32-NEXT:    vsrl.vi v8, v8, 2
+; RV32-NEXT:    vand.vx v8, v8, a0
+; RV32-NEXT:    vadd.vv v8, v16, v8
+; RV32-NEXT:    vsrl.vi v16, v8, 4
+; RV32-NEXT:    vadd.vv v8, v8, v16
+; RV32-NEXT:    lui a0, 1
+; RV32-NEXT:    addi a0, a0, -241
+; RV32-NEXT:    vand.vx v8, v8, a0
+; RV32-NEXT:    li a0, 257
+; RV32-NEXT:    vmul.vx v8, v8, a0
+; RV32-NEXT:    vsrl.vi v8, v8, 8
+; RV32-NEXT:    ret
+;
+; RV64-LABEL: vp_ctpop_nxv32i16_unmasked:
+; RV64:       # %bb.0:
+; RV64-NEXT:    vsetvli zero, a0, e16, m8, ta, ma
+; RV64-NEXT:    vsrl.vi v16, v8, 1
+; RV64-NEXT:    lui a0, 5
+; RV64-NEXT:    addiw a0, a0, 1365
+; RV64-NEXT:    vand.vx v16, v16, a0
+; RV64-NEXT:    vsub.vv v8, v8, v16
+; RV64-NEXT:    lui a0, 3
+; RV64-NEXT:    addiw a0, a0, 819
+; RV64-NEXT:    vand.vx v16, v8, a0
+; RV64-NEXT:    vsrl.vi v8, v8, 2
+; RV64-NEXT:    vand.vx v8, v8, a0
+; RV64-NEXT:    vadd.vv v8, v16, v8
+; RV64-NEXT:    vsrl.vi v16, v8, 4
+; RV64-NEXT:    vadd.vv v8, v8, v16
+; RV64-NEXT:    lui a0, 1
+; RV64-NEXT:    addiw a0, a0, -241
+; RV64-NEXT:    vand.vx v8, v8, a0
+; RV64-NEXT:    li a0, 257
+; RV64-NEXT:    vmul.vx v8, v8, a0
+; RV64-NEXT:    vsrl.vi v8, v8, 8
+; RV64-NEXT:    ret
+  %head = insertelement <vscale x 32 x i1> poison, i1 true, i32 0
+  %m = shufflevector <vscale x 32 x i1> %head, <vscale x 32 x i1> poison, <vscale x 32 x i32> zeroinitializer
+  %v = call <vscale x 32 x i16> @llvm.vp.ctpop.nxv32i16(<vscale x 32 x i16> %va, <vscale x 32 x i1> %m, i32 %evl)
+  ret <vscale x 32 x i16> %v
+}
+
+declare <vscale x 1 x i32> @llvm.vp.ctpop.nxv1i32(<vscale x 1 x i32>, <vscale x 1 x i1>, i32)
+
+define <vscale x 1 x i32> @vp_ctpop_nxv1i32(<vscale x 1 x i32> %va, <vscale x 1 x i1> %m, i32 zeroext %evl) {
+; RV32-LABEL: vp_ctpop_nxv1i32:
+; RV32:       # %bb.0:
+; RV32-NEXT:    vsetvli zero, a0, e32, mf2, ta, ma
+; RV32-NEXT:    vsrl.vi v9, v8, 1, v0.t
+; RV32-NEXT:    lui a0, 349525
+; RV32-NEXT:    addi a0, a0, 1365
+; RV32-NEXT:    vand.vx v9, v9, a0, v0.t
+; RV32-NEXT:    vsub.vv v8, v8, v9, v0.t
+; RV32-NEXT:    lui a0, 209715
+; RV32-NEXT:    addi a0, a0, 819
+; RV32-NEXT:    vand.vx v9, v8, a0, v0.t
+; RV32-NEXT:    vsrl.vi v8, v8, 2, v0.t
+; RV32-NEXT:    vand.vx v8, v8, a0, v0.t
+; RV32-NEXT:    vadd.vv v8, v9, v8, v0.t
+; RV32-NEXT:    vsrl.vi v9, v8, 4, v0.t
+; RV32-NEXT:    vadd.vv v8, v8, v9, v0.t
+; RV32-NEXT:    lui a0, 61681
+; RV32-NEXT:    addi a0, a0, -241
+; RV32-NEXT:    vand.vx v8, v8, a0, v0.t
+; RV32-NEXT:    lui a0, 4112
+; RV32-NEXT:    addi a0, a0, 257
+; RV32-NEXT:    vmul.vx v8, v8, a0, v0.t
+; RV32-NEXT:    vsrl.vi v8, v8, 24, v0.t
+; RV32-NEXT:    ret
+;
+; RV64-LABEL: vp_ctpop_nxv1i32:
+; RV64:       # %bb.0:
+; RV64-NEXT:    vsetvli zero, a0, e32, mf2, ta, ma
+; RV64-NEXT:    vsrl.vi v9, v8, 1, v0.t
+; RV64-NEXT:    lui a0, 349525
+; RV64-NEXT:    addiw a0, a0, 1365
+; RV64-NEXT:    vand.vx v9, v9, a0, v0.t
+; RV64-NEXT:    vsub.vv v8, v8, v9, v0.t
+; RV64-NEXT:    lui a0, 209715
+; RV64-NEXT:    addiw a0, a0, 819
+; RV64-NEXT:    vand.vx v9, v8, a0, v0.t
+; RV64-NEXT:    vsrl.vi v8, v8, 2, v0.t
+; RV64-NEXT:    vand.vx v8, v8, a0, v0.t
+; RV64-NEXT:    vadd.vv v8, v9, v8, v0.t
+; RV64-NEXT:    vsrl.vi v9, v8, 4, v0.t
+; RV64-NEXT:    vadd.vv v8, v8, v9, v0.t
+; RV64-NEXT:    lui a0, 61681
+; RV64-NEXT:    addiw a0, a0, -241
+; RV64-NEXT:    vand.vx v8, v8, a0, v0.t
+; RV64-NEXT:    lui a0, 4112
+; RV64-NEXT:    addiw a0, a0, 257
+; RV64-NEXT:    vmul.vx v8, v8, a0, v0.t
+; RV64-NEXT:    vsrl.vi v8, v8, 24, v0.t
+; RV64-NEXT:    ret
+  %v = call <vscale x 1 x i32> @llvm.vp.ctpop.nxv1i32(<vscale x 1 x i32> %va, <vscale x 1 x i1> %m, i32 %evl)
+  ret <vscale x 1 x i32> %v
+}
+
+define <vscale x 1 x i32> @vp_ctpop_nxv1i32_unmasked(<vscale x 1 x i32> %va, i32 zeroext %evl) {
+; RV32-LABEL: vp_ctpop_nxv1i32_unmasked:
+; RV32:       # %bb.0:
+; RV32-NEXT:    vsetvli zero, a0, e32, mf2, ta, ma
+; RV32-NEXT:    vsrl.vi v9, v8, 1
+; RV32-NEXT:    lui a0, 349525
+; RV32-NEXT:    addi a0, a0, 1365
+; RV32-NEXT:    vand.vx v9, v9, a0
+; RV32-NEXT:    vsub.vv v8, v8, v9
+; RV32-NEXT:    lui a0, 209715
+; RV32-NEXT:    addi a0, a0, 819
+; RV32-NEXT:    vand.vx v9, v8, a0
+; RV32-NEXT:    vsrl.vi v8, v8, 2
+; RV32-NEXT:    vand.vx v8, v8, a0
+; RV32-NEXT:    vadd.vv v8, v9, v8
+; RV32-NEXT:    vsrl.vi v9, v8, 4
+; RV32-NEXT:    vadd.vv v8, v8, v9
+; RV32-NEXT:    lui a0, 61681
+; RV32-NEXT:    addi a0, a0, -241
+; RV32-NEXT:    vand.vx v8, v8, a0
+; RV32-NEXT:    lui a0, 4112
+; RV32-NEXT:    addi a0, a0, 257
+; RV32-NEXT:    vmul.vx v8, v8, a0
+; RV32-NEXT:    vsrl.vi v8, v8, 24
+; RV32-NEXT:    ret
+;
+; RV64-LABEL: vp_ctpop_nxv1i32_unmasked:
+; RV64:       # %bb.0:
+; RV64-NEXT:    vsetvli zero, a0, e32, mf2, ta, ma
+; RV64-NEXT:    vsrl.vi v9, v8, 1
+; RV64-NEXT:    lui a0, 349525
+; RV64-NEXT:    addiw a0, a0, 1365
+; RV64-NEXT:    vand.vx v9, v9, a0
+; RV64-NEXT:    vsub.vv v8, v8, v9
+; RV64-NEXT:    lui a0, 209715
+; RV64-NEXT:    addiw a0, a0, 819
+; RV64-NEXT:    vand.vx v9, v8, a0
+; RV64-NEXT:    vsrl.vi v8, v8, 2
+; RV64-NEXT:    vand.vx v8, v8, a0
+; RV64-NEXT:    vadd.vv v8, v9, v8
+; RV64-NEXT:    vsrl.vi v9, v8, 4
+; RV64-NEXT:    vadd.vv v8, v8, v9
+; RV64-NEXT:    lui a0, 61681
+; RV64-NEXT:    addiw a0, a0, -241
+; RV64-NEXT:    vand.vx v8, v8, a0
+; RV64-NEXT:    lui a0, 4112
+; RV64-NEXT:    addiw a0, a0, 257
+; RV64-NEXT:    vmul.vx v8, v8, a0
+; RV64-NEXT:    vsrl.vi v8, v8, 24
+; RV64-NEXT:    ret
+  %head = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
+  %m = shufflevector <vscale x 1 x i1> %head, <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
+  %v = call <vscale x 1 x i32> @llvm.vp.ctpop.nxv1i32(<vscale x 1 x i32> %va, <vscale x 1 x i1> %m, i32 %evl)
+  ret <vscale x 1 x i32> %v
+}
+
+declare <vscale x 2 x i32> @llvm.vp.ctpop.nxv2i32(<vscale x 2 x i32>, <vscale x 2 x i1>, i32)
+
+define <vscale x 2 x i32> @vp_ctpop_nxv2i32(<vscale x 2 x i32> %va, <vscale x 2 x i1> %m, i32 zeroext %evl) {
+; RV32-LABEL: vp_ctpop_nxv2i32:
+; RV32:       # %bb.0:
+; RV32-NEXT:    vsetvli zero, a0, e32, m1, ta, ma
+; RV32-NEXT:    vsrl.vi v9, v8, 1, v0.t
+; RV32-NEXT:    lui a0, 349525
+; RV32-NEXT:    addi a0, a0, 1365
+; RV32-NEXT:    vand.vx v9, v9, a0, v0.t
+; RV32-NEXT:    vsub.vv v8, v8, v9, v0.t
+; RV32-NEXT:    lui a0, 209715
+; RV32-NEXT:    addi a0, a0, 819
+; RV32-NEXT:    vand.vx v9, v8, a0, v0.t
+; RV32-NEXT:    vsrl.vi v8, v8, 2, v0.t
+; RV32-NEXT:    vand.vx v8, v8, a0, v0.t
+; RV32-NEXT:    vadd.vv v8, v9, v8, v0.t
+; RV32-NEXT:    vsrl.vi v9, v8, 4, v0.t
+; RV32-NEXT:    vadd.vv v8, v8, v9, v0.t
+; RV32-NEXT:    lui a0, 61681
+; RV32-NEXT:    addi a0, a0, -241
+; RV32-NEXT:    vand.vx v8, v8, a0, v0.t
+; RV32-NEXT:    lui a0, 4112
+; RV32-NEXT:    addi a0, a0, 257
+; RV32-NEXT:    vmul.vx v8, v8, a0, v0.t
+; RV32-NEXT:    vsrl.vi v8, v8, 24, v0.t
+; RV32-NEXT:    ret
+;
+; RV64-LABEL: vp_ctpop_nxv2i32:
+; RV64:       # %bb.0:
+; RV64-NEXT:    vsetvli zero, a0, e32, m1, ta, ma
+; RV64-NEXT:    vsrl.vi v9, v8, 1, v0.t
+; RV64-NEXT:    lui a0, 349525
+; RV64-NEXT:    addiw a0, a0, 1365
+; RV64-NEXT:    vand.vx v9, v9, a0, v0.t
+; RV64-NEXT:    vsub.vv v8, v8, v9, v0.t
+; RV64-NEXT:    lui a0, 209715
+; RV64-NEXT:    addiw a0, a0, 819
+; RV64-NEXT:    vand.vx v9, v8, a0, v0.t
+; RV64-NEXT:    vsrl.vi v8, v8, 2, v0.t
+; RV64-NEXT:    vand.vx v8, v8, a0, v0.t
+; RV64-NEXT:    vadd.vv v8, v9, v8, v0.t
+; RV64-NEXT:    vsrl.vi v9, v8, 4, v0.t
+; RV64-NEXT:    vadd.vv v8, v8, v9, v0.t
+; RV64-NEXT:    lui a0, 61681
+; RV64-NEXT:    addiw a0, a0, -241
+; RV64-NEXT:    vand.vx v8, v8, a0, v0.t
+; RV64-NEXT:    lui a0, 4112
+; RV64-NEXT:    addiw a0, a0, 257
+; RV64-NEXT:    vmul.vx v8, v8, a0, v0.t
+; RV64-NEXT:    vsrl.vi v8, v8, 24, v0.t
+; RV64-NEXT:    ret
+  %v = call <vscale x 2 x i32> @llvm.vp.ctpop.nxv2i32(<vscale x 2 x i32> %va, <vscale x 2 x i1> %m, i32 %evl)
+  ret <vscale x 2 x i32> %v
+}
+
+define <vscale x 2 x i32> @vp_ctpop_nxv2i32_unmasked(<vscale x 2 x i32> %va, i32 zeroext %evl) {
+; RV32-LABEL: vp_ctpop_nxv2i32_unmasked:
+; RV32:       # %bb.0:
+; RV32-NEXT:    vsetvli zero, a0, e32, m1, ta, ma
+; RV32-NEXT:    vsrl.vi v9, v8, 1
+; RV32-NEXT:    lui a0, 349525
+; RV32-NEXT:    addi a0, a0, 1365
+; RV32-NEXT:    vand.vx v9, v9, a0
+; RV32-NEXT:    vsub.vv v8, v8, v9
+; RV32-NEXT:    lui a0, 209715
+; RV32-NEXT:    addi a0, a0, 819
+; RV32-NEXT:    vand.vx v9, v8, a0
+; RV32-NEXT:    vsrl.vi v8, v8, 2
+; RV32-NEXT:    vand.vx v8, v8, a0
+; RV32-NEXT:    vadd.vv v8, v9, v8
+; RV32-NEXT:    vsrl.vi v9, v8, 4
+; RV32-NEXT:    vadd.vv v8, v8, v9
+; RV32-NEXT:    lui a0, 61681
+; RV32-NEXT:    addi a0, a0, -241
+; RV32-NEXT:    vand.vx v8, v8, a0
+; RV32-NEXT:    lui a0, 4112
+; RV32-NEXT:    addi a0, a0, 257
+; RV32-NEXT:    vmul.vx v8, v8, a0
+; RV32-NEXT:    vsrl.vi v8, v8, 24
+; RV32-NEXT:    ret
+;
+; RV64-LABEL: vp_ctpop_nxv2i32_unmasked:
+; RV64:       # %bb.0:
+; RV64-NEXT:    vsetvli zero, a0, e32, m1, ta, ma
+; RV64-NEXT:    vsrl.vi v9, v8, 1
+; RV64-NEXT:    lui a0, 349525
+; RV64-NEXT:    addiw a0, a0, 1365
+; RV64-NEXT:    vand.vx v9, v9, a0
+; RV64-NEXT:    vsub.vv v8, v8, v9
+; RV64-NEXT:    lui a0, 209715
+; RV64-NEXT:    addiw a0, a0, 819
+; RV64-NEXT:    vand.vx v9, v8, a0
+; RV64-NEXT:    vsrl.vi v8, v8, 2
+; RV64-NEXT:    vand.vx v8, v8, a0
+; RV64-NEXT:    vadd.vv v8, v9, v8
+; RV64-NEXT:    vsrl.vi v9, v8, 4
+; RV64-NEXT:    vadd.vv v8, v8, v9
+; RV64-NEXT:    lui a0, 61681
+; RV64-NEXT:    addiw a0, a0, -241
+; RV64-NEXT:    vand.vx v8, v8, a0
+; RV64-NEXT:    lui a0, 4112
+; RV64-NEXT:    addiw a0, a0, 257
+; RV64-NEXT:    vmul.vx v8, v8, a0
+; RV64-NEXT:    vsrl.vi v8, v8, 24
+; RV64-NEXT:    ret
+  %head = insertelement <vscale x 2 x i1> poison, i1 true, i32 0
+  %m = shufflevector <vscale x 2 x i1> %head, <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer
+  %v = call <vscale x 2 x i32> @llvm.vp.ctpop.nxv2i32(<vscale x 2 x i32> %va, <vscale x 2 x i1> %m, i32 %evl)
+  ret <vscale x 2 x i32> %v
+}
+
+declare <vscale x 4 x i32> @llvm.vp.ctpop.nxv4i32(<vscale x 4 x i32>, <vscale x 4 x i1>, i32)
+
+define <vscale x 4 x i32> @vp_ctpop_nxv4i32(<vscale x 4 x i32> %va, <vscale x 4 x i1> %m, i32 zeroext %evl) {
+; RV32-LABEL: vp_ctpop_nxv4i32:
+; RV32:       # %bb.0:
+; RV32-NEXT:    vsetvli zero, a0, e32, m2, ta, ma
+; RV32-NEXT:    vsrl.vi v10, v8, 1, v0.t
+; RV32-NEXT:    lui a0, 349525
+; RV32-NEXT:    addi a0, a0, 1365
+; RV32-NEXT:    vand.vx v10, v10, a0, v0.t
+; RV32-NEXT:    vsub.vv v8, v8, v10, v0.t
+; RV32-NEXT:    lui a0, 209715
+; RV32-NEXT:    addi a0, a0, 819
+; RV32-NEXT:    vand.vx v10, v8, a0, v0.t
+; RV32-NEXT:    vsrl.vi v8, v8, 2, v0.t
+; RV32-NEXT:    vand.vx v8, v8, a0, v0.t
+; RV32-NEXT:    vadd.vv v8, v10, v8, v0.t
+; RV32-NEXT:    vsrl.vi v10, v8, 4, v0.t
+; RV32-NEXT:    vadd.vv v8, v8, v10, v0.t
+; RV32-NEXT:    lui a0, 61681
+; RV32-NEXT:    addi a0, a0, -241
+; RV32-NEXT:    vand.vx v8, v8, a0, v0.t
+; RV32-NEXT:    lui a0, 4112
+; RV32-NEXT:    addi a0, a0, 257
+; RV32-NEXT:    vmul.vx v8, v8, a0, v0.t
+; RV32-NEXT:    vsrl.vi v8, v8, 24, v0.t
+; RV32-NEXT:    ret
+;
+; RV64-LABEL: vp_ctpop_nxv4i32:
+; RV64:       # %bb.0:
+; RV64-NEXT:    vsetvli zero, a0, e32, m2, ta, ma
+; RV64-NEXT:    vsrl.vi v10, v8, 1, v0.t
+; RV64-NEXT:    lui a0, 349525
+; RV64-NEXT:    addiw a0, a0, 1365
+; RV64-NEXT:    vand.vx v10, v10, a0, v0.t
+; RV64-NEXT:    vsub.vv v8, v8, v10, v0.t
+; RV64-NEXT:    lui a0, 209715
+; RV64-NEXT:    addiw a0, a0, 819
+; RV64-NEXT:    vand.vx v10, v8, a0, v0.t
+; RV64-NEXT:    vsrl.vi v8, v8, 2, v0.t
+; RV64-NEXT:    vand.vx v8, v8, a0, v0.t
+; RV64-NEXT:    vadd.vv v8, v10, v8, v0.t
+; RV64-NEXT:    vsrl.vi v10, v8, 4, v0.t
+; RV64-NEXT:    vadd.vv v8, v8, v10, v0.t
+; RV64-NEXT:    lui a0, 61681
+; RV64-NEXT:    addiw a0, a0, -241
+; RV64-NEXT:    vand.vx v8, v8, a0, v0.t
+; RV64-NEXT:    lui a0, 4112
+; RV64-NEXT:    addiw a0, a0, 257
+; RV64-NEXT:    vmul.vx v8, v8, a0, v0.t
+; RV64-NEXT:    vsrl.vi v8, v8, 24, v0.t
+; RV64-NEXT:    ret
+  %v = call <vscale x 4 x i32> @llvm.vp.ctpop.nxv4i32(<vscale x 4 x i32> %va, <vscale x 4 x i1> %m, i32 %evl)
+  ret <vscale x 4 x i32> %v
+}
+
+define <vscale x 4 x i32> @vp_ctpop_nxv4i32_unmasked(<vscale x 4 x i32> %va, i32 zeroext %evl) {
+; RV32-LABEL: vp_ctpop_nxv4i32_unmasked:
+; RV32:       # %bb.0:
+; RV32-NEXT:    vsetvli zero, a0, e32, m2, ta, ma
+; RV32-NEXT:    vsrl.vi v10, v8, 1
+; RV32-NEXT:    lui a0, 349525
+; RV32-NEXT:    addi a0, a0, 1365
+; RV32-NEXT:    vand.vx v10, v10, a0
+; RV32-NEXT:    vsub.vv v8, v8, v10
+; RV32-NEXT:    lui a0, 209715
+; RV32-NEXT:    addi a0, a0, 819
+; RV32-NEXT:    vand.vx v10, v8, a0
+; RV32-NEXT:    vsrl.vi v8, v8, 2
+; RV32-NEXT:    vand.vx v8, v8, a0
+; RV32-NEXT:    vadd.vv v8, v10, v8
+; RV32-NEXT:    vsrl.vi v10, v8, 4
+; RV32-NEXT:    vadd.vv v8, v8, v10
+; RV32-NEXT:    lui a0, 61681
+; RV32-NEXT:    addi a0, a0, -241
+; RV32-NEXT:    vand.vx v8, v8, a0
+; RV32-NEXT:    lui a0, 4112
+; RV32-NEXT:    addi a0, a0, 257
+; RV32-NEXT:    vmul.vx v8, v8, a0
+; RV32-NEXT:    vsrl.vi v8, v8, 24
+; RV32-NEXT:    ret
+;
+; RV64-LABEL: vp_ctpop_nxv4i32_unmasked:
+; RV64:       # %bb.0:
+; RV64-NEXT:    vsetvli zero, a0, e32, m2, ta, ma
+; RV64-NEXT:    vsrl.vi v10, v8, 1
+; RV64-NEXT:    lui a0, 349525
+; RV64-NEXT:    addiw a0, a0, 1365
+; RV64-NEXT:    vand.vx v10, v10, a0
+; RV64-NEXT:    vsub.vv v8, v8, v10
+; RV64-NEXT:    lui a0, 209715
+; RV64-NEXT:    addiw a0, a0, 819
+; RV64-NEXT:    vand.vx v10, v8, a0
+; RV64-NEXT:    vsrl.vi v8, v8, 2
+; RV64-NEXT:    vand.vx v8, v8, a0
+; RV64-NEXT:    vadd.vv v8, v10, v8
+; RV64-NEXT:    vsrl.vi v10, v8, 4
+; RV64-NEXT:    vadd.vv v8, v8, v10
+; RV64-NEXT:    lui a0, 61681
+; RV64-NEXT:    addiw a0, a0, -241
+; RV64-NEXT:    vand.vx v8, v8, a0
+; RV64-NEXT:    lui a0, 4112
+; RV64-NEXT:    addiw a0, a0, 257
+; RV64-NEXT:    vmul.vx v8, v8, a0
+; RV64-NEXT:    vsrl.vi v8, v8, 24
+; RV64-NEXT:    ret
+  %head = insertelement <vscale x 4 x i1> poison, i1 true, i32 0
+  %m = shufflevector <vscale x 4 x i1> %head, <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer
+  %v = call <vscale x 4 x i32> @llvm.vp.ctpop.nxv4i32(<vscale x 4 x i32> %va, <vscale x 4 x i1> %m, i32 %evl)
+  ret <vscale x 4 x i32> %v
+}
+
+declare <vscale x 8 x i32> @llvm.vp.ctpop.nxv8i32(<vscale x 8 x i32>, <vscale x 8 x i1>, i32)
+
+define <vscale x 8 x i32> @vp_ctpop_nxv8i32(<vscale x 8 x i32> %va, <vscale x 8 x i1> %m, i32 zeroext %evl) {
+; RV32-LABEL: vp_ctpop_nxv8i32:
+; RV32:       # %bb.0:
+; RV32-NEXT:    vsetvli zero, a0, e32, m4, ta, ma
+; RV32-NEXT:    vsrl.vi v12, v8, 1, v0.t
+; RV32-NEXT:    lui a0, 349525
+; RV32-NEXT:    addi a0, a0, 1365
+; RV32-NEXT:    vand.vx v12, v12, a0, v0.t
+; RV32-NEXT:    vsub.vv v8, v8, v12, v0.t
+; RV32-NEXT:    lui a0, 209715
+; RV32-NEXT:    addi a0, a0, 819
+; RV32-NEXT:    vand.vx v12, v8, a0, v0.t
+; RV32-NEXT:    vsrl.vi v8, v8, 2, v0.t
+; RV32-NEXT:    vand.vx v8, v8, a0, v0.t
+; RV32-NEXT:    vadd.vv v8, v12, v8, v0.t
+; RV32-NEXT:    vsrl.vi v12, v8, 4, v0.t
+; RV32-NEXT:    vadd.vv v8, v8, v12, v0.t
+; RV32-NEXT:    lui a0, 61681
+; RV32-NEXT:    addi a0, a0, -241
+; RV32-NEXT:    vand.vx v8, v8, a0, v0.t
+; RV32-NEXT:    lui a0, 4112
+; RV32-NEXT:    addi a0, a0, 257
+; RV32-NEXT:    vmul.vx v8, v8, a0, v0.t
+; RV32-NEXT:    vsrl.vi v8, v8, 24, v0.t
+; RV32-NEXT:    ret
+;
+; RV64-LABEL: vp_ctpop_nxv8i32:
+; RV64:       # %bb.0:
+; RV64-NEXT:    vsetvli zero, a0, e32, m4, ta, ma
+; RV64-NEXT:    vsrl.vi v12, v8, 1, v0.t
+; RV64-NEXT:    lui a0, 349525
+; RV64-NEXT:    addiw a0, a0, 1365
+; RV64-NEXT:    vand.vx v12, v12, a0, v0.t
+; RV64-NEXT:    vsub.vv v8, v8, v12, v0.t
+; RV64-NEXT:    lui a0, 209715
+; RV64-NEXT:    addiw a0, a0, 819
+; RV64-NEXT:    vand.vx v12, v8, a0, v0.t
+; RV64-NEXT:    vsrl.vi v8, v8, 2, v0.t
+; RV64-NEXT:    vand.vx v8, v8, a0, v0.t
+; RV64-NEXT:    vadd.vv v8, v12, v8, v0.t
+; RV64-NEXT:    vsrl.vi v12, v8, 4, v0.t
+; RV64-NEXT:    vadd.vv v8, v8, v12, v0.t
+; RV64-NEXT:    lui a0, 61681
+; RV64-NEXT:    addiw a0, a0, -241
+; RV64-NEXT:    vand.vx v8, v8, a0, v0.t
+; RV64-NEXT:    lui a0, 4112
+; RV64-NEXT:    addiw a0, a0, 257
+; RV64-NEXT:    vmul.vx v8, v8, a0, v0.t
+; RV64-NEXT:    vsrl.vi v8, v8, 24, v0.t
+; RV64-NEXT:    ret
+  %v = call <vscale x 8 x i32> @llvm.vp.ctpop.nxv8i32(<vscale x 8 x i32> %va, <vscale x 8 x i1> %m, i32 %evl)
+  ret <vscale x 8 x i32> %v
+}
+
+define <vscale x 8 x i32> @vp_ctpop_nxv8i32_unmasked(<vscale x 8 x i32> %va, i32 zeroext %evl) {
+; RV32-LABEL: vp_ctpop_nxv8i32_unmasked:
+; RV32:       # %bb.0:
+; RV32-NEXT:    vsetvli zero, a0, e32, m4, ta, ma
+; RV32-NEXT:    vsrl.vi v12, v8, 1
+; RV32-NEXT:    lui a0, 349525
+; RV32-NEXT:    addi a0, a0, 1365
+; RV32-NEXT:    vand.vx v12, v12, a0
+; RV32-NEXT:    vsub.vv v8, v8, v12
+; RV32-NEXT:    lui a0, 209715
+; RV32-NEXT:    addi a0, a0, 819
+; RV32-NEXT:    vand.vx v12, v8, a0
+; RV32-NEXT:    vsrl.vi v8, v8, 2
+; RV32-NEXT:    vand.vx v8, v8, a0
+; RV32-NEXT:    vadd.vv v8, v12, v8
+; RV32-NEXT:    vsrl.vi v12, v8, 4
+; RV32-NEXT:    vadd.vv v8, v8, v12
+; RV32-NEXT:    lui a0, 61681
+; RV32-NEXT:    addi a0, a0, -241
+; RV32-NEXT:    vand.vx v8, v8, a0
+; RV32-NEXT:    lui a0, 4112
+; RV32-NEXT:    addi a0, a0, 257
+; RV32-NEXT:    vmul.vx v8, v8, a0
+; RV32-NEXT:    vsrl.vi v8, v8, 24
+; RV32-NEXT:    ret
+;
+; RV64-LABEL: vp_ctpop_nxv8i32_unmasked:
+; RV64:       # %bb.0:
+; RV64-NEXT:    vsetvli zero, a0, e32, m4, ta, ma
+; RV64-NEXT:    vsrl.vi v12, v8, 1
+; RV64-NEXT:    lui a0, 349525
+; RV64-NEXT:    addiw a0, a0, 1365
+; RV64-NEXT:    vand.vx v12, v12, a0
+; RV64-NEXT:    vsub.vv v8, v8, v12
+; RV64-NEXT:    lui a0, 209715
+; RV64-NEXT:    addiw a0, a0, 819
+; RV64-NEXT:    vand.vx v12, v8, a0
+; RV64-NEXT:    vsrl.vi v8, v8, 2
+; RV64-NEXT:    vand.vx v8, v8, a0
+; RV64-NEXT:    vadd.vv v8, v12, v8
+; RV64-NEXT:    vsrl.vi v12, v8, 4
+; RV64-NEXT:    vadd.vv v8, v8, v12
+; RV64-NEXT:    lui a0, 61681
+; RV64-NEXT:    addiw a0, a0, -241
+; RV64-NEXT:    vand.vx v8, v8, a0
+; RV64-NEXT:    lui a0, 4112
+; RV64-NEXT:    addiw a0, a0, 257
+; RV64-NEXT:    vmul.vx v8, v8, a0
+; RV64-NEXT:    vsrl.vi v8, v8, 24
+; RV64-NEXT:    ret
+  %head = insertelement <vscale x 8 x i1> poison, i1 true, i32 0
+  %m = shufflevector <vscale x 8 x i1> %head, <vscale x 8 x i1> poison, <vscale x 8 x i32> zeroinitializer
+  %v = call <vscale x 8 x i32> @llvm.vp.ctpop.nxv8i32(<vscale x 8 x i32> %va, <vscale x 8 x i1> %m, i32 %evl)
+  ret <vscale x 8 x i32> %v
+}
+
+declare <vscale x 16 x i32> @llvm.vp.ctpop.nxv16i32(<vscale x 16 x i32>, <vscale x 16 x i1>, i32)
+
+define <vscale x 16 x i32> @vp_ctpop_nxv16i32(<vscale x 16 x i32> %va, <vscale x 16 x i1> %m, i32 zeroext %evl) {
+; RV32-LABEL: vp_ctpop_nxv16i32:
+; RV32:       # %bb.0:
+; RV32-NEXT:    vsetvli zero, a0, e32, m8, ta, ma
+; RV32-NEXT:    vsrl.vi v16, v8, 1, v0.t
+; RV32-NEXT:    lui a0, 349525
+; RV32-NEXT:    addi a0, a0, 1365
+; RV32-NEXT:    vand.vx v16, v16, a0, v0.t
+; RV32-NEXT:    vsub.vv v8, v8, v16, v0.t
+; RV32-NEXT:    lui a0, 209715
+; RV32-NEXT:    addi a0, a0, 819
+; RV32-NEXT:    vand.vx v16, v8, a0, v0.t
+; RV32-NEXT:    vsrl.vi v8, v8, 2, v0.t
+; RV32-NEXT:    vand.vx v8, v8, a0, v0.t
+; RV32-NEXT:    vadd.vv v8, v16, v8, v0.t
+; RV32-NEXT:    vsrl.vi v16, v8, 4, v0.t
+; RV32-NEXT:    vadd.vv v8, v8, v16, v0.t
+; RV32-NEXT:    lui a0, 61681
+; RV32-NEXT:    addi a0, a0, -241
+; RV32-NEXT:    vand.vx v8, v8, a0, v0.t
+; RV32-NEXT:    lui a0, 4112
+; RV32-NEXT:    addi a0, a0, 257
+; RV32-NEXT:    vmul.vx v8, v8, a0, v0.t
+; RV32-NEXT:    vsrl.vi v8, v8, 24, v0.t
+; RV32-NEXT:    ret
+;
+; RV64-LABEL: vp_ctpop_nxv16i32:
+; RV64:       # %bb.0:
+; RV64-NEXT:    vsetvli zero, a0, e32, m8, ta, ma
+; RV64-NEXT:    vsrl.vi v16, v8, 1, v0.t
+; RV64-NEXT:    lui a0, 349525
+; RV64-NEXT:    addiw a0, a0, 1365
+; RV64-NEXT:    vand.vx v16, v16, a0, v0.t
+; RV64-NEXT:    vsub.vv v8, v8, v16, v0.t
+; RV64-NEXT:    lui a0, 209715
+; RV64-NEXT:    addiw a0, a0, 819
+; RV64-NEXT:    vand.vx v16, v8, a0, v0.t
+; RV64-NEXT:    vsrl.vi v8, v8, 2, v0.t
+; RV64-NEXT:    vand.vx v8, v8, a0, v0.t
+; RV64-NEXT:    vadd.vv v8, v16, v8, v0.t
+; RV64-NEXT:    vsrl.vi v16, v8, 4, v0.t
+; RV64-NEXT:    vadd.vv v8, v8, v16, v0.t
+; RV64-NEXT:    lui a0, 61681
+; RV64-NEXT:    addiw a0, a0, -241
+; RV64-NEXT:    vand.vx v8, v8, a0, v0.t
+; RV64-NEXT:    lui a0, 4112
+; RV64-NEXT:    addiw a0, a0, 257
+; RV64-NEXT:    vmul.vx v8, v8, a0, v0.t
+; RV64-NEXT:    vsrl.vi v8, v8, 24, v0.t
+; RV64-NEXT:    ret
+  %v = call <vscale x 16 x i32> @llvm.vp.ctpop.nxv16i32(<vscale x 16 x i32> %va, <vscale x 16 x i1> %m, i32 %evl)
+  ret <vscale x 16 x i32> %v
+}
+
+define <vscale x 16 x i32> @vp_ctpop_nxv16i32_unmasked(<vscale x 16 x i32> %va, i32 zeroext %evl) {
+; RV32-LABEL: vp_ctpop_nxv16i32_unmasked:
+; RV32:       # %bb.0:
+; RV32-NEXT:    vsetvli zero, a0, e32, m8, ta, ma
+; RV32-NEXT:    vsrl.vi v16, v8, 1
+; RV32-NEXT:    lui a0, 349525
+; RV32-NEXT:    addi a0, a0, 1365
+; RV32-NEXT:    vand.vx v16, v16, a0
+; RV32-NEXT:    vsub.vv v8, v8, v16
+; RV32-NEXT:    lui a0, 209715
+; RV32-NEXT:    addi a0, a0, 819
+; RV32-NEXT:    vand.vx v16, v8, a0
+; RV32-NEXT:    vsrl.vi v8, v8, 2
+; RV32-NEXT:    vand.vx v8, v8, a0
+; RV32-NEXT:    vadd.vv v8, v16, v8
+; RV32-NEXT:    vsrl.vi v16, v8, 4
+; RV32-NEXT:    vadd.vv v8, v8, v16
+; RV32-NEXT:    lui a0, 61681
+; RV32-NEXT:    addi a0, a0, -241
+; RV32-NEXT:    vand.vx v8, v8, a0
+; RV32-NEXT:    lui a0, 4112
+; RV32-NEXT:    addi a0, a0, 257
+; RV32-NEXT:    vmul.vx v8, v8, a0
+; RV32-NEXT:    vsrl.vi v8, v8, 24
+; RV32-NEXT:    ret
+;
+; RV64-LABEL: vp_ctpop_nxv16i32_unmasked:
+; RV64:       # %bb.0:
+; RV64-NEXT:    vsetvli zero, a0, e32, m8, ta, ma
+; RV64-NEXT:    vsrl.vi v16, v8, 1
+; RV64-NEXT:    lui a0, 349525
+; RV64-NEXT:    addiw a0, a0, 1365
+; RV64-NEXT:    vand.vx v16, v16, a0
+; RV64-NEXT:    vsub.vv v8, v8, v16
+; RV64-NEXT:    lui a0, 209715
+; RV64-NEXT:    addiw a0, a0, 819
+; RV64-NEXT:    vand.vx v16, v8, a0
+; RV64-NEXT:    vsrl.vi v8, v8, 2
+; RV64-NEXT:    vand.vx v8, v8, a0
+; RV64-NEXT:    vadd.vv v8, v16, v8
+; RV64-NEXT:    vsrl.vi v16, v8, 4
+; RV64-NEXT:    vadd.vv v8, v8, v16
+; RV64-NEXT:    lui a0, 61681
+; RV64-NEXT:    addiw a0, a0, -241
+; RV64-NEXT:    vand.vx v8, v8, a0
+; RV64-NEXT:    lui a0, 4112
+; RV64-NEXT:    addiw a0, a0, 257
+; RV64-NEXT:    vmul.vx v8, v8, a0
+; RV64-NEXT:    vsrl.vi v8, v8, 24
+; RV64-NEXT:    ret
+  %head = insertelement <vscale x 16 x i1> poison, i1 true, i32 0
+  %m = shufflevector <vscale x 16 x i1> %head, <vscale x 16 x i1> poison, <vscale x 16 x i32> zeroinitializer
+  %v = call <vscale x 16 x i32> @llvm.vp.ctpop.nxv16i32(<vscale x 16 x i32> %va, <vscale x 16 x i1> %m, i32 %evl)
+  ret <vscale x 16 x i32> %v
+}
+
+declare <vscale x 1 x i64> @llvm.vp.ctpop.nxv1i64(<vscale x 1 x i64>, <vscale x 1 x i1>, i32)
+
+define <vscale x 1 x i64> @vp_ctpop_nxv1i64(<vscale x 1 x i64> %va, <vscale x 1 x i1> %m, i32 zeroext %evl) {
+; RV32-LABEL: vp_ctpop_nxv1i64:
+; RV32:       # %bb.0:
+; RV32-NEXT:    addi sp, sp, -16
+; RV32-NEXT:    .cfi_def_cfa_offset 16
+; RV32-NEXT:    lui a1, 349525
+; RV32-NEXT:    addi a1, a1, 1365
+; RV32-NEXT:    sw a1, 12(sp)
+; RV32-NEXT:    sw a1, 8(sp)
+; RV32-NEXT:    lui a1, 209715
+; RV32-NEXT:    addi a1, a1, 819
+; RV32-NEXT:    sw a1, 12(sp)
+; RV32-NEXT:    sw a1, 8(sp)
+; RV32-NEXT:    lui a1, 61681
+; RV32-NEXT:    addi a1, a1, -241
+; RV32-NEXT:    sw a1, 12(sp)
+; RV32-NEXT:    sw a1, 8(sp)
+; RV32-NEXT:    lui a1, 4112
+; RV32-NEXT:    addi a1, a1, 257
+; RV32-NEXT:    sw a1, 12(sp)
+; RV32-NEXT:    sw a1, 8(sp)
+; RV32-NEXT:    vsetvli zero, a0, e64, m1, ta, ma
+; RV32-NEXT:    vsrl.vi v9, v8, 1, v0.t
+; RV32-NEXT:    addi a1, sp, 8
+; RV32-NEXT:    vsetvli a2, zero, e64, m1, ta, ma
+; RV32-NEXT:    vlse64.v v10, (a1), zero
+; RV32-NEXT:    vsetvli zero, a0, e64, m1, ta, ma
+; RV32-NEXT:    vand.vv v9, v9, v10, v0.t
+; RV32-NEXT:    vsub.vv v8, v8, v9, v0.t
+; RV32-NEXT:    vsetvli a2, zero, e64, m1, ta, ma
+; RV32-NEXT:    vlse64.v v9, (a1), zero
+; RV32-NEXT:    vsetvli zero, a0, e64, m1, ta, ma
+; RV32-NEXT:    vand.vv v10, v8, v9, v0.t
+; RV32-NEXT:    vsrl.vi v8, v8, 2, v0.t
+; RV32-NEXT:    vand.vv v8, v8, v9, v0.t
+; RV32-NEXT:    vadd.vv v8, v10, v8, v0.t
+; RV32-NEXT:    vsrl.vi v9, v8, 4, v0.t
+; RV32-NEXT:    vadd.vv v8, v8, v9, v0.t
+; RV32-NEXT:    vsetvli a2, zero, e64, m1, ta, ma
+; RV32-NEXT:    vlse64.v v9, (a1), zero
+; RV32-NEXT:    vsetvli zero, a0, e64, m1, ta, ma
+; RV32-NEXT:    vand.vv v8, v8, v9, v0.t
+; RV32-NEXT:    vsetvli a2, zero, e64, m1, ta, ma
+; RV32-NEXT:    vlse64.v v9, (a1), zero
+; RV32-NEXT:    vsetvli zero, a0, e64, m1, ta, ma
+; RV32-NEXT:    vmul.vv v8, v8, v9, v0.t
+; RV32-NEXT:    li a0, 56
+; RV32-NEXT:    vsrl.vx v8, v8, a0, v0.t
+; RV32-NEXT:    addi sp, sp, 16
+; RV32-NEXT:    ret
+;
+; RV64-LABEL: vp_ctpop_nxv1i64:
+; RV64:       # %bb.0:
+; RV64-NEXT:    vsetvli zero, a0, e64, m1, ta, ma
+; RV64-NEXT:    lui a0, %hi(.LCPI36_0)
+; RV64-NEXT:    ld a0, %lo(.LCPI36_0)(a0)
+; RV64-NEXT:    lui a1, %hi(.LCPI36_1)
+; RV64-NEXT:    ld a1, %lo(.LCPI36_1)(a1)
+; RV64-NEXT:    vsrl.vi v9, v8, 1, v0.t
+; RV64-NEXT:    vand.vx v9, v9, a0, v0.t
+; RV64-NEXT:    vsub.vv v8, v8, v9, v0.t
+; RV64-NEXT:    vand.vx v9, v8, a1, v0.t
+; RV64-NEXT:    vsrl.vi v8, v8, 2, v0.t
+; RV64-NEXT:    vand.vx v8, v8, a1, v0.t
+; RV64-NEXT:    vadd.vv v8, v9, v8, v0.t
+; RV64-NEXT:    lui a0, %hi(.LCPI36_2)
+; RV64-NEXT:    ld a0, %lo(.LCPI36_2)(a0)
+; RV64-NEXT:    lui a1, %hi(.LCPI36_3)
+; RV64-NEXT:    ld a1, %lo(.LCPI36_3)(a1)
+; RV64-NEXT:    vsrl.vi v9, v8, 4, v0.t
+; RV64-NEXT:    vadd.vv v8, v8, v9, v0.t
+; RV64-NEXT:    vand.vx v8, v8, a0, v0.t
+; RV64-NEXT:    vmul.vx v8, v8, a1, v0.t
+; RV64-NEXT:    li a0, 56
+; RV64-NEXT:    vsrl.vx v8, v8, a0, v0.t
+; RV64-NEXT:    ret
+  %v = call <vscale x 1 x i64> @llvm.vp.ctpop.nxv1i64(<vscale x 1 x i64> %va, <vscale x 1 x i1> %m, i32 %evl)
+  ret <vscale x 1 x i64> %v
+}
+
+define <vscale x 1 x i64> @vp_ctpop_nxv1i64_unmasked(<vscale x 1 x i64> %va, i32 zeroext %evl) {
+; RV32-LABEL: vp_ctpop_nxv1i64_unmasked:
+; RV32:       # %bb.0:
+; RV32-NEXT:    addi sp, sp, -16
+; RV32-NEXT:    .cfi_def_cfa_offset 16
+; RV32-NEXT:    lui a1, 349525
+; RV32-NEXT:    addi a1, a1, 1365
+; RV32-NEXT:    sw a1, 12(sp)
+; RV32-NEXT:    sw a1, 8(sp)
+; RV32-NEXT:    lui a1, 209715
+; RV32-NEXT:    addi a1, a1, 819
+; RV32-NEXT:    sw a1, 12(sp)
+; RV32-NEXT:    sw a1, 8(sp)
+; RV32-NEXT:    lui a1, 61681
+; RV32-NEXT:    addi a1, a1, -241
+; RV32-NEXT:    sw a1, 12(sp)
+; RV32-NEXT:    sw a1, 8(sp)
+; RV32-NEXT:    lui a1, 4112
+; RV32-NEXT:    addi a1, a1, 257
+; RV32-NEXT:    sw a1, 12(sp)
+; RV32-NEXT:    sw a1, 8(sp)
+; RV32-NEXT:    vsetvli zero, a0, e64, m1, ta, ma
+; RV32-NEXT:    vsrl.vi v9, v8, 1
+; RV32-NEXT:    addi a1, sp, 8
+; RV32-NEXT:    vsetvli a2, zero, e64, m1, ta, ma
+; RV32-NEXT:    vlse64.v v10, (a1), zero
+; RV32-NEXT:    vsetvli zero, a0, e64, m1, ta, ma
+; RV32-NEXT:    vand.vv v9, v9, v10
+; RV32-NEXT:    vsub.vv v8, v8, v9
+; RV32-NEXT:    vsetvli a2, zero, e64, m1, ta, ma
+; RV32-NEXT:    vlse64.v v9, (a1), zero
+; RV32-NEXT:    vsetvli zero, a0, e64, m1, ta, ma
+; RV32-NEXT:    vand.vv v10, v8, v9
+; RV32-NEXT:    vsrl.vi v8, v8, 2
+; RV32-NEXT:    vand.vv v8, v8, v9
+; RV32-NEXT:    vadd.vv v8, v10, v8
+; RV32-NEXT:    vsrl.vi v9, v8, 4
+; RV32-NEXT:    vadd.vv v8, v8, v9
+; RV32-NEXT:    vsetvli a2, zero, e64, m1, ta, ma
+; RV32-NEXT:    vlse64.v v9, (a1), zero
+; RV32-NEXT:    vsetvli zero, a0, e64, m1, ta, ma
+; RV32-NEXT:    vand.vv v8, v8, v9
+; RV32-NEXT:    vsetvli a2, zero, e64, m1, ta, ma
+; RV32-NEXT:    vlse64.v v9, (a1), zero
+; RV32-NEXT:    vsetvli zero, a0, e64, m1, ta, ma
+; RV32-NEXT:    vmul.vv v8, v8, v9
+; RV32-NEXT:    li a0, 56
+; RV32-NEXT:    vsrl.vx v8, v8, a0
+; RV32-NEXT:    addi sp, sp, 16
+; RV32-NEXT:    ret
+;
+; RV64-LABEL: vp_ctpop_nxv1i64_unmasked:
+; RV64:       # %bb.0:
+; RV64-NEXT:    vsetvli zero, a0, e64, m1, ta, ma
+; RV64-NEXT:    lui a0, %hi(.LCPI37_0)
+; RV64-NEXT:    ld a0, %lo(.LCPI37_0)(a0)
+; RV64-NEXT:    lui a1, %hi(.LCPI37_1)
+; RV64-NEXT:    ld a1, %lo(.LCPI37_1)(a1)
+; RV64-NEXT:    vsrl.vi v9, v8, 1
+; RV64-NEXT:    vand.vx v9, v9, a0
+; RV64-NEXT:    vsub.vv v8, v8, v9
+; RV64-NEXT:    vand.vx v9, v8, a1
+; RV64-NEXT:    vsrl.vi v8, v8, 2
+; RV64-NEXT:    vand.vx v8, v8, a1
+; RV64-NEXT:    vadd.vv v8, v9, v8
+; RV64-NEXT:    lui a0, %hi(.LCPI37_2)
+; RV64-NEXT:    ld a0, %lo(.LCPI37_2)(a0)
+; RV64-NEXT:    lui a1, %hi(.LCPI37_3)
+; RV64-NEXT:    ld a1, %lo(.LCPI37_3)(a1)
+; RV64-NEXT:    vsrl.vi v9, v8, 4
+; RV64-NEXT:    vadd.vv v8, v8, v9
+; RV64-NEXT:    vand.vx v8, v8, a0
+; RV64-NEXT:    vmul.vx v8, v8, a1
+; RV64-NEXT:    li a0, 56
+; RV64-NEXT:    vsrl.vx v8, v8, a0
+; RV64-NEXT:    ret
+  %head = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
+  %m = shufflevector <vscale x 1 x i1> %head, <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
+  %v = call <vscale x 1 x i64> @llvm.vp.ctpop.nxv1i64(<vscale x 1 x i64> %va, <vscale x 1 x i1> %m, i32 %evl)
+  ret <vscale x 1 x i64> %v
+}
+
+declare <vscale x 2 x i64> @llvm.vp.ctpop.nxv2i64(<vscale x 2 x i64>, <vscale x 2 x i1>, i32)
+
+define <vscale x 2 x i64> @vp_ctpop_nxv2i64(<vscale x 2 x i64> %va, <vscale x 2 x i1> %m, i32 zeroext %evl) {
+; RV32-LABEL: vp_ctpop_nxv2i64:
+; RV32:       # %bb.0:
+; RV32-NEXT:    addi sp, sp, -16
+; RV32-NEXT:    .cfi_def_cfa_offset 16
+; RV32-NEXT:    lui a1, 349525
+; RV32-NEXT:    addi a1, a1, 1365
+; RV32-NEXT:    sw a1, 12(sp)
+; RV32-NEXT:    sw a1, 8(sp)
+; RV32-NEXT:    lui a1, 209715
+; RV32-NEXT:    addi a1, a1, 819
+; RV32-NEXT:    sw a1, 12(sp)
+; RV32-NEXT:    sw a1, 8(sp)
+; RV32-NEXT:    lui a1, 61681
+; RV32-NEXT:    addi a1, a1, -241
+; RV32-NEXT:    sw a1, 12(sp)
+; RV32-NEXT:    sw a1, 8(sp)
+; RV32-NEXT:    lui a1, 4112
+; RV32-NEXT:    addi a1, a1, 257
+; RV32-NEXT:    sw a1, 12(sp)
+; RV32-NEXT:    sw a1, 8(sp)
+; RV32-NEXT:    vsetvli zero, a0, e64, m2, ta, ma
+; RV32-NEXT:    vsrl.vi v10, v8, 1, v0.t
+; RV32-NEXT:    addi a1, sp, 8
+; RV32-NEXT:    vsetvli a2, zero, e64, m2, ta, ma
+; RV32-NEXT:    vlse64.v v12, (a1), zero
+; RV32-NEXT:    vsetvli zero, a0, e64, m2, ta, ma
+; RV32-NEXT:    vand.vv v10, v10, v12, v0.t
+; RV32-NEXT:    vsub.vv v8, v8, v10, v0.t
+; RV32-NEXT:    vsetvli a2, zero, e64, m2, ta, ma
+; RV32-NEXT:    vlse64.v v10, (a1), zero
+; RV32-NEXT:    vsetvli zero, a0, e64, m2, ta, ma
+; RV32-NEXT:    vand.vv v12, v8, v10, v0.t
+; RV32-NEXT:    vsrl.vi v8, v8, 2, v0.t
+; RV32-NEXT:    vand.vv v8, v8, v10, v0.t
+; RV32-NEXT:    vadd.vv v8, v12, v8, v0.t
+; RV32-NEXT:    vsrl.vi v10, v8, 4, v0.t
+; RV32-NEXT:    vadd.vv v8, v8, v10, v0.t
+; RV32-NEXT:    vsetvli a2, zero, e64, m2, ta, ma
+; RV32-NEXT:    vlse64.v v10, (a1), zero
+; RV32-NEXT:    vsetvli zero, a0, e64, m2, ta, ma
+; RV32-NEXT:    vand.vv v8, v8, v10, v0.t
+; RV32-NEXT:    vsetvli a2, zero, e64, m2, ta, ma
+; RV32-NEXT:    vlse64.v v10, (a1), zero
+; RV32-NEXT:    vsetvli zero, a0, e64, m2, ta, ma
+; RV32-NEXT:    vmul.vv v8, v8, v10, v0.t
+; RV32-NEXT:    li a0, 56
+; RV32-NEXT:    vsrl.vx v8, v8, a0, v0.t
+; RV32-NEXT:    addi sp, sp, 16
+; RV32-NEXT:    ret
+;
+; RV64-LABEL: vp_ctpop_nxv2i64:
+; RV64:       # %bb.0:
+; RV64-NEXT:    vsetvli zero, a0, e64, m2, ta, ma
+; RV64-NEXT:    lui a0, %hi(.LCPI38_0)
+; RV64-NEXT:    ld a0, %lo(.LCPI38_0)(a0)
+; RV64-NEXT:    lui a1, %hi(.LCPI38_1)
+; RV64-NEXT:    ld a1, %lo(.LCPI38_1)(a1)
+; RV64-NEXT:    vsrl.vi v10, v8, 1, v0.t
+; RV64-NEXT:    vand.vx v10, v10, a0, v0.t
+; RV64-NEXT:    vsub.vv v8, v8, v10, v0.t
+; RV64-NEXT:    vand.vx v10, v8, a1, v0.t
+; RV64-NEXT:    vsrl.vi v8, v8, 2, v0.t
+; RV64-NEXT:    vand.vx v8, v8, a1, v0.t
+; RV64-NEXT:    vadd.vv v8, v10, v8, v0.t
+; RV64-NEXT:    lui a0, %hi(.LCPI38_2)
+; RV64-NEXT:    ld a0, %lo(.LCPI38_2)(a0)
+; RV64-NEXT:    lui a1, %hi(.LCPI38_3)
+; RV64-NEXT:    ld a1, %lo(.LCPI38_3)(a1)
+; RV64-NEXT:    vsrl.vi v10, v8, 4, v0.t
+; RV64-NEXT:    vadd.vv v8, v8, v10, v0.t
+; RV64-NEXT:    vand.vx v8, v8, a0, v0.t
+; RV64-NEXT:    vmul.vx v8, v8, a1, v0.t
+; RV64-NEXT:    li a0, 56
+; RV64-NEXT:    vsrl.vx v8, v8, a0, v0.t
+; RV64-NEXT:    ret
+  %v = call <vscale x 2 x i64> @llvm.vp.ctpop.nxv2i64(<vscale x 2 x i64> %va, <vscale x 2 x i1> %m, i32 %evl)
+  ret <vscale x 2 x i64> %v
+}
+
+define <vscale x 2 x i64> @vp_ctpop_nxv2i64_unmasked(<vscale x 2 x i64> %va, i32 zeroext %evl) {
+; RV32-LABEL: vp_ctpop_nxv2i64_unmasked:
+; RV32:       # %bb.0:
+; RV32-NEXT:    addi sp, sp, -16
+; RV32-NEXT:    .cfi_def_cfa_offset 16
+; RV32-NEXT:    lui a1, 349525
+; RV32-NEXT:    addi a1, a1, 1365
+; RV32-NEXT:    sw a1, 12(sp)
+; RV32-NEXT:    sw a1, 8(sp)
+; RV32-NEXT:    lui a1, 209715
+; RV32-NEXT:    addi a1, a1, 819
+; RV32-NEXT:    sw a1, 12(sp)
+; RV32-NEXT:    sw a1, 8(sp)
+; RV32-NEXT:    lui a1, 61681
+; RV32-NEXT:    addi a1, a1, -241
+; RV32-NEXT:    sw a1, 12(sp)
+; RV32-NEXT:    sw a1, 8(sp)
+; RV32-NEXT:    lui a1, 4112
+; RV32-NEXT:    addi a1, a1, 257
+; RV32-NEXT:    sw a1, 12(sp)
+; RV32-NEXT:    sw a1, 8(sp)
+; RV32-NEXT:    vsetvli zero, a0, e64, m2, ta, ma
+; RV32-NEXT:    vsrl.vi v10, v8, 1
+; RV32-NEXT:    addi a1, sp, 8
+; RV32-NEXT:    vsetvli a2, zero, e64, m2, ta, ma
+; RV32-NEXT:    vlse64.v v12, (a1), zero
+; RV32-NEXT:    vsetvli zero, a0, e64, m2, ta, ma
+; RV32-NEXT:    vand.vv v10, v10, v12
+; RV32-NEXT:    vsub.vv v8, v8, v10
+; RV32-NEXT:    vsetvli a2, zero, e64, m2, ta, ma
+; RV32-NEXT:    vlse64.v v10, (a1), zero
+; RV32-NEXT:    vsetvli zero, a0, e64, m2, ta, ma
+; RV32-NEXT:    vand.vv v12, v8, v10
+; RV32-NEXT:    vsrl.vi v8, v8, 2
+; RV32-NEXT:    vand.vv v8, v8, v10
+; RV32-NEXT:    vadd.vv v8, v12, v8
+; RV32-NEXT:    vsrl.vi v10, v8, 4
+; RV32-NEXT:    vadd.vv v8, v8, v10
+; RV32-NEXT:    vsetvli a2, zero, e64, m2, ta, ma
+; RV32-NEXT:    vlse64.v v10, (a1), zero
+; RV32-NEXT:    vsetvli zero, a0, e64, m2, ta, ma
+; RV32-NEXT:    vand.vv v8, v8, v10
+; RV32-NEXT:    vsetvli a2, zero, e64, m2, ta, ma
+; RV32-NEXT:    vlse64.v v10, (a1), zero
+; RV32-NEXT:    vsetvli zero, a0, e64, m2, ta, ma
+; RV32-NEXT:    vmul.vv v8, v8, v10
+; RV32-NEXT:    li a0, 56
+; RV32-NEXT:    vsrl.vx v8, v8, a0
+; RV32-NEXT:    addi sp, sp, 16
+; RV32-NEXT:    ret
+;
+; RV64-LABEL: vp_ctpop_nxv2i64_unmasked:
+; RV64:       # %bb.0:
+; RV64-NEXT:    vsetvli zero, a0, e64, m2, ta, ma
+; RV64-NEXT:    lui a0, %hi(.LCPI39_0)
+; RV64-NEXT:    ld a0, %lo(.LCPI39_0)(a0)
+; RV64-NEXT:    lui a1, %hi(.LCPI39_1)
+; RV64-NEXT:    ld a1, %lo(.LCPI39_1)(a1)
+; RV64-NEXT:    vsrl.vi v10, v8, 1
+; RV64-NEXT:    vand.vx v10, v10, a0
+; RV64-NEXT:    vsub.vv v8, v8, v10
+; RV64-NEXT:    vand.vx v10, v8, a1
+; RV64-NEXT:    vsrl.vi v8, v8, 2
+; RV64-NEXT:    vand.vx v8, v8, a1
+; RV64-NEXT:    vadd.vv v8, v10, v8
+; RV64-NEXT:    lui a0, %hi(.LCPI39_2)
+; RV64-NEXT:    ld a0, %lo(.LCPI39_2)(a0)
+; RV64-NEXT:    lui a1, %hi(.LCPI39_3)
+; RV64-NEXT:    ld a1, %lo(.LCPI39_3)(a1)
+; RV64-NEXT:    vsrl.vi v10, v8, 4
+; RV64-NEXT:    vadd.vv v8, v8, v10
+; RV64-NEXT:    vand.vx v8, v8, a0
+; RV64-NEXT:    vmul.vx v8, v8, a1
+; RV64-NEXT:    li a0, 56
+; RV64-NEXT:    vsrl.vx v8, v8, a0
+; RV64-NEXT:    ret
+  %head = insertelement <vscale x 2 x i1> poison, i1 true, i32 0
+  %m = shufflevector <vscale x 2 x i1> %head, <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer
+  %v = call <vscale x 2 x i64> @llvm.vp.ctpop.nxv2i64(<vscale x 2 x i64> %va, <vscale x 2 x i1> %m, i32 %evl)
+  ret <vscale x 2 x i64> %v
+}
+
+declare <vscale x 4 x i64> @llvm.vp.ctpop.nxv4i64(<vscale x 4 x i64>, <vscale x 4 x i1>, i32)
+
+define <vscale x 4 x i64> @vp_ctpop_nxv4i64(<vscale x 4 x i64> %va, <vscale x 4 x i1> %m, i32 zeroext %evl) {
+; RV32-LABEL: vp_ctpop_nxv4i64:
+; RV32:       # %bb.0:
+; RV32-NEXT:    addi sp, sp, -16
+; RV32-NEXT:    .cfi_def_cfa_offset 16
+; RV32-NEXT:    lui a1, 349525
+; RV32-NEXT:    addi a1, a1, 1365
+; RV32-NEXT:    sw a1, 12(sp)
+; RV32-NEXT:    sw a1, 8(sp)
+; RV32-NEXT:    lui a1, 209715
+; RV32-NEXT:    addi a1, a1, 819
+; RV32-NEXT:    sw a1, 12(sp)
+; RV32-NEXT:    sw a1, 8(sp)
+; RV32-NEXT:    lui a1, 61681
+; RV32-NEXT:    addi a1, a1, -241
+; RV32-NEXT:    sw a1, 12(sp)
+; RV32-NEXT:    sw a1, 8(sp)
+; RV32-NEXT:    lui a1, 4112
+; RV32-NEXT:    addi a1, a1, 257
+; RV32-NEXT:    sw a1, 12(sp)
+; RV32-NEXT:    sw a1, 8(sp)
+; RV32-NEXT:    vsetvli zero, a0, e64, m4, ta, ma
+; RV32-NEXT:    vsrl.vi v12, v8, 1, v0.t
+; RV32-NEXT:    addi a1, sp, 8
+; RV32-NEXT:    vsetvli a2, zero, e64, m4, ta, ma
+; RV32-NEXT:    vlse64.v v16, (a1), zero
+; RV32-NEXT:    vsetvli zero, a0, e64, m4, ta, ma
+; RV32-NEXT:    vand.vv v12, v12, v16, v0.t
+; RV32-NEXT:    vsub.vv v8, v8, v12, v0.t
+; RV32-NEXT:    vsetvli a2, zero, e64, m4, ta, ma
+; RV32-NEXT:    vlse64.v v12, (a1), zero
+; RV32-NEXT:    vsetvli zero, a0, e64, m4, ta, ma
+; RV32-NEXT:    vand.vv v16, v8, v12, v0.t
+; RV32-NEXT:    vsrl.vi v8, v8, 2, v0.t
+; RV32-NEXT:    vand.vv v8, v8, v12, v0.t
+; RV32-NEXT:    vadd.vv v8, v16, v8, v0.t
+; RV32-NEXT:    vsrl.vi v12, v8, 4, v0.t
+; RV32-NEXT:    vadd.vv v8, v8, v12, v0.t
+; RV32-NEXT:    vsetvli a2, zero, e64, m4, ta, ma
+; RV32-NEXT:    vlse64.v v12, (a1), zero
+; RV32-NEXT:    vsetvli zero, a0, e64, m4, ta, ma
+; RV32-NEXT:    vand.vv v8, v8, v12, v0.t
+; RV32-NEXT:    vsetvli a2, zero, e64, m4, ta, ma
+; RV32-NEXT:    vlse64.v v12, (a1), zero
+; RV32-NEXT:    vsetvli zero, a0, e64, m4, ta, ma
+; RV32-NEXT:    vmul.vv v8, v8, v12, v0.t
+; RV32-NEXT:    li a0, 56
+; RV32-NEXT:    vsrl.vx v8, v8, a0, v0.t
+; RV32-NEXT:    addi sp, sp, 16
+; RV32-NEXT:    ret
+;
+; RV64-LABEL: vp_ctpop_nxv4i64:
+; RV64:       # %bb.0:
+; RV64-NEXT:    vsetvli zero, a0, e64, m4, ta, ma
+; RV64-NEXT:    lui a0, %hi(.LCPI40_0)
+; RV64-NEXT:    ld a0, %lo(.LCPI40_0)(a0)
+; RV64-NEXT:    lui a1, %hi(.LCPI40_1)
+; RV64-NEXT:    ld a1, %lo(.LCPI40_1)(a1)
+; RV64-NEXT:    vsrl.vi v12, v8, 1, v0.t
+; RV64-NEXT:    vand.vx v12, v12, a0, v0.t
+; RV64-NEXT:    vsub.vv v8, v8, v12, v0.t
+; RV64-NEXT:    vand.vx v12, v8, a1, v0.t
+; RV64-NEXT:    vsrl.vi v8, v8, 2, v0.t
+; RV64-NEXT:    vand.vx v8, v8, a1, v0.t
+; RV64-NEXT:    vadd.vv v8, v12, v8, v0.t
+; RV64-NEXT:    lui a0, %hi(.LCPI40_2)
+; RV64-NEXT:    ld a0, %lo(.LCPI40_2)(a0)
+; RV64-NEXT:    lui a1, %hi(.LCPI40_3)
+; RV64-NEXT:    ld a1, %lo(.LCPI40_3)(a1)
+; RV64-NEXT:    vsrl.vi v12, v8, 4, v0.t
+; RV64-NEXT:    vadd.vv v8, v8, v12, v0.t
+; RV64-NEXT:    vand.vx v8, v8, a0, v0.t
+; RV64-NEXT:    vmul.vx v8, v8, a1, v0.t
+; RV64-NEXT:    li a0, 56
+; RV64-NEXT:    vsrl.vx v8, v8, a0, v0.t
+; RV64-NEXT:    ret
+  %v = call <vscale x 4 x i64> @llvm.vp.ctpop.nxv4i64(<vscale x 4 x i64> %va, <vscale x 4 x i1> %m, i32 %evl)
+  ret <vscale x 4 x i64> %v
+}
+
+define <vscale x 4 x i64> @vp_ctpop_nxv4i64_unmasked(<vscale x 4 x i64> %va, i32 zeroext %evl) {
+; RV32-LABEL: vp_ctpop_nxv4i64_unmasked:
+; RV32:       # %bb.0:
+; RV32-NEXT:    addi sp, sp, -16
+; RV32-NEXT:    .cfi_def_cfa_offset 16
+; RV32-NEXT:    lui a1, 349525
+; RV32-NEXT:    addi a1, a1, 1365
+; RV32-NEXT:    sw a1, 12(sp)
+; RV32-NEXT:    sw a1, 8(sp)
+; RV32-NEXT:    lui a1, 209715
+; RV32-NEXT:    addi a1, a1, 819
+; RV32-NEXT:    sw a1, 12(sp)
+; RV32-NEXT:    sw a1, 8(sp)
+; RV32-NEXT:    lui a1, 61681
+; RV32-NEXT:    addi a1, a1, -241
+; RV32-NEXT:    sw a1, 12(sp)
+; RV32-NEXT:    sw a1, 8(sp)
+; RV32-NEXT:    lui a1, 4112
+; RV32-NEXT:    addi a1, a1, 257
+; RV32-NEXT:    sw a1, 12(sp)
+; RV32-NEXT:    sw a1, 8(sp)
+; RV32-NEXT:    vsetvli zero, a0, e64, m4, ta, ma
+; RV32-NEXT:    vsrl.vi v12, v8, 1
+; RV32-NEXT:    addi a1, sp, 8
+; RV32-NEXT:    vsetvli a2, zero, e64, m4, ta, ma
+; RV32-NEXT:    vlse64.v v16, (a1), zero
+; RV32-NEXT:    vsetvli zero, a0, e64, m4, ta, ma
+; RV32-NEXT:    vand.vv v12, v12, v16
+; RV32-NEXT:    vsub.vv v8, v8, v12
+; RV32-NEXT:    vsetvli a2, zero, e64, m4, ta, ma
+; RV32-NEXT:    vlse64.v v12, (a1), zero
+; RV32-NEXT:    vsetvli zero, a0, e64, m4, ta, ma
+; RV32-NEXT:    vand.vv v16, v8, v12
+; RV32-NEXT:    vsrl.vi v8, v8, 2
+; RV32-NEXT:    vand.vv v8, v8, v12
+; RV32-NEXT:    vadd.vv v8, v16, v8
+; RV32-NEXT:    vsrl.vi v12, v8, 4
+; RV32-NEXT:    vadd.vv v8, v8, v12
+; RV32-NEXT:    vsetvli a2, zero, e64, m4, ta, ma
+; RV32-NEXT:    vlse64.v v12, (a1), zero
+; RV32-NEXT:    vsetvli zero, a0, e64, m4, ta, ma
+; RV32-NEXT:    vand.vv v8, v8, v12
+; RV32-NEXT:    vsetvli a2, zero, e64, m4, ta, ma
+; RV32-NEXT:    vlse64.v v12, (a1), zero
+; RV32-NEXT:    vsetvli zero, a0, e64, m4, ta, ma
+; RV32-NEXT:    vmul.vv v8, v8, v12
+; RV32-NEXT:    li a0, 56
+; RV32-NEXT:    vsrl.vx v8, v8, a0
+; RV32-NEXT:    addi sp, sp, 16
+; RV32-NEXT:    ret
+;
+; RV64-LABEL: vp_ctpop_nxv4i64_unmasked:
+; RV64:       # %bb.0:
+; RV64-NEXT:    vsetvli zero, a0, e64, m4, ta, ma
+; RV64-NEXT:    lui a0, %hi(.LCPI41_0)
+; RV64-NEXT:    ld a0, %lo(.LCPI41_0)(a0)
+; RV64-NEXT:    lui a1, %hi(.LCPI41_1)
+; RV64-NEXT:    ld a1, %lo(.LCPI41_1)(a1)
+; RV64-NEXT:    vsrl.vi v12, v8, 1
+; RV64-NEXT:    vand.vx v12, v12, a0
+; RV64-NEXT:    vsub.vv v8, v8, v12
+; RV64-NEXT:    vand.vx v12, v8, a1
+; RV64-NEXT:    vsrl.vi v8, v8, 2
+; RV64-NEXT:    vand.vx v8, v8, a1
+; RV64-NEXT:    vadd.vv v8, v12, v8
+; RV64-NEXT:    lui a0, %hi(.LCPI41_2)
+; RV64-NEXT:    ld a0, %lo(.LCPI41_2)(a0)
+; RV64-NEXT:    lui a1, %hi(.LCPI41_3)
+; RV64-NEXT:    ld a1, %lo(.LCPI41_3)(a1)
+; RV64-NEXT:    vsrl.vi v12, v8, 4
+; RV64-NEXT:    vadd.vv v8, v8, v12
+; RV64-NEXT:    vand.vx v8, v8, a0
+; RV64-NEXT:    vmul.vx v8, v8, a1
+; RV64-NEXT:    li a0, 56
+; RV64-NEXT:    vsrl.vx v8, v8, a0
+; RV64-NEXT:    ret
+  %head = insertelement <vscale x 4 x i1> poison, i1 true, i32 0
+  %m = shufflevector <vscale x 4 x i1> %head, <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer
+  %v = call <vscale x 4 x i64> @llvm.vp.ctpop.nxv4i64(<vscale x 4 x i64> %va, <vscale x 4 x i1> %m, i32 %evl)
+  ret <vscale x 4 x i64> %v
+}
+
+declare <vscale x 7 x i64> @llvm.vp.ctpop.nxv7i64(<vscale x 7 x i64>, <vscale x 7 x i1>, i32)
+
+define <vscale x 7 x i64> @vp_ctpop_nxv7i64(<vscale x 7 x i64> %va, <vscale x 7 x i1> %m, i32 zeroext %evl) {
+; RV32-LABEL: vp_ctpop_nxv7i64:
+; RV32:       # %bb.0:
+; RV32-NEXT:    addi sp, sp, -16
+; RV32-NEXT:    .cfi_def_cfa_offset 16
+; RV32-NEXT:    lui a1, 349525
+; RV32-NEXT:    addi a1, a1, 1365
+; RV32-NEXT:    sw a1, 12(sp)
+; RV32-NEXT:    sw a1, 8(sp)
+; RV32-NEXT:    lui a1, 209715
+; RV32-NEXT:    addi a1, a1, 819
+; RV32-NEXT:    sw a1, 12(sp)
+; RV32-NEXT:    sw a1, 8(sp)
+; RV32-NEXT:    lui a1, 61681
+; RV32-NEXT:    addi a1, a1, -241
+; RV32-NEXT:    sw a1, 12(sp)
+; RV32-NEXT:    sw a1, 8(sp)
+; RV32-NEXT:    lui a1, 4112
+; RV32-NEXT:    addi a1, a1, 257
+; RV32-NEXT:    sw a1, 12(sp)
+; RV32-NEXT:    sw a1, 8(sp)
+; RV32-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
+; RV32-NEXT:    vsrl.vi v16, v8, 1, v0.t
+; RV32-NEXT:    addi a1, sp, 8
+; RV32-NEXT:    vsetvli a2, zero, e64, m8, ta, ma
+; RV32-NEXT:    vlse64.v v24, (a1), zero
+; RV32-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
+; RV32-NEXT:    vand.vv v16, v16, v24, v0.t
+; RV32-NEXT:    vsub.vv v8, v8, v16, v0.t
+; RV32-NEXT:    vsetvli a2, zero, e64, m8, ta, ma
+; RV32-NEXT:    vlse64.v v16, (a1), zero
+; RV32-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
+; RV32-NEXT:    vand.vv v24, v8, v16, v0.t
+; RV32-NEXT:    vsrl.vi v8, v8, 2, v0.t
+; RV32-NEXT:    vand.vv v8, v8, v16, v0.t
+; RV32-NEXT:    vadd.vv v8, v24, v8, v0.t
+; RV32-NEXT:    vsrl.vi v16, v8, 4, v0.t
+; RV32-NEXT:    vadd.vv v8, v8, v16, v0.t
+; RV32-NEXT:    vsetvli a2, zero, e64, m8, ta, ma
+; RV32-NEXT:    vlse64.v v16, (a1), zero
+; RV32-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
+; RV32-NEXT:    vand.vv v8, v8, v16, v0.t
+; RV32-NEXT:    vsetvli a2, zero, e64, m8, ta, ma
+; RV32-NEXT:    vlse64.v v16, (a1), zero
+; RV32-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
+; RV32-NEXT:    vmul.vv v8, v8, v16, v0.t
+; RV32-NEXT:    li a0, 56
+; RV32-NEXT:    vsrl.vx v8, v8, a0, v0.t
+; RV32-NEXT:    addi sp, sp, 16
+; RV32-NEXT:    ret
+;
+; RV64-LABEL: vp_ctpop_nxv7i64:
+; RV64:       # %bb.0:
+; RV64-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
+; RV64-NEXT:    lui a0, %hi(.LCPI42_0)
+; RV64-NEXT:    ld a0, %lo(.LCPI42_0)(a0)
+; RV64-NEXT:    lui a1, %hi(.LCPI42_1)
+; RV64-NEXT:    ld a1, %lo(.LCPI42_1)(a1)
+; RV64-NEXT:    vsrl.vi v16, v8, 1, v0.t
+; RV64-NEXT:    vand.vx v16, v16, a0, v0.t
+; RV64-NEXT:    vsub.vv v8, v8, v16, v0.t
+; RV64-NEXT:    vand.vx v16, v8, a1, v0.t
+; RV64-NEXT:    vsrl.vi v8, v8, 2, v0.t
+; RV64-NEXT:    vand.vx v8, v8, a1, v0.t
+; RV64-NEXT:    vadd.vv v8, v16, v8, v0.t
+; RV64-NEXT:    lui a0, %hi(.LCPI42_2)
+; RV64-NEXT:    ld a0, %lo(.LCPI42_2)(a0)
+; RV64-NEXT:    lui a1, %hi(.LCPI42_3)
+; RV64-NEXT:    ld a1, %lo(.LCPI42_3)(a1)
+; RV64-NEXT:    vsrl.vi v16, v8, 4, v0.t
+; RV64-NEXT:    vadd.vv v8, v8, v16, v0.t
+; RV64-NEXT:    vand.vx v8, v8, a0, v0.t
+; RV64-NEXT:    vmul.vx v8, v8, a1, v0.t
+; RV64-NEXT:    li a0, 56
+; RV64-NEXT:    vsrl.vx v8, v8, a0, v0.t
+; RV64-NEXT:    ret
+  %v = call <vscale x 7 x i64> @llvm.vp.ctpop.nxv7i64(<vscale x 7 x i64> %va, <vscale x 7 x i1> %m, i32 %evl)
+  ret <vscale x 7 x i64> %v
+}
+
+define <vscale x 7 x i64> @vp_ctpop_nxv7i64_unmasked(<vscale x 7 x i64> %va, i32 zeroext %evl) {
+; RV32-LABEL: vp_ctpop_nxv7i64_unmasked:
+; RV32:       # %bb.0:
+; RV32-NEXT:    addi sp, sp, -16
+; RV32-NEXT:    .cfi_def_cfa_offset 16
+; RV32-NEXT:    lui a1, 349525
+; RV32-NEXT:    addi a1, a1, 1365
+; RV32-NEXT:    sw a1, 12(sp)
+; RV32-NEXT:    sw a1, 8(sp)
+; RV32-NEXT:    lui a1, 209715
+; RV32-NEXT:    addi a1, a1, 819
+; RV32-NEXT:    sw a1, 12(sp)
+; RV32-NEXT:    sw a1, 8(sp)
+; RV32-NEXT:    lui a1, 61681
+; RV32-NEXT:    addi a1, a1, -241
+; RV32-NEXT:    sw a1, 12(sp)
+; RV32-NEXT:    sw a1, 8(sp)
+; RV32-NEXT:    lui a1, 4112
+; RV32-NEXT:    addi a1, a1, 257
+; RV32-NEXT:    sw a1, 12(sp)
+; RV32-NEXT:    sw a1, 8(sp)
+; RV32-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
+; RV32-NEXT:    vsrl.vi v16, v8, 1
+; RV32-NEXT:    addi a1, sp, 8
+; RV32-NEXT:    vsetvli a2, zero, e64, m8, ta, ma
+; RV32-NEXT:    vlse64.v v24, (a1), zero
+; RV32-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
+; RV32-NEXT:    vand.vv v16, v16, v24
+; RV32-NEXT:    vsub.vv v8, v8, v16
+; RV32-NEXT:    vsetvli a2, zero, e64, m8, ta, ma
+; RV32-NEXT:    vlse64.v v16, (a1), zero
+; RV32-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
+; RV32-NEXT:    vand.vv v24, v8, v16
+; RV32-NEXT:    vsrl.vi v8, v8, 2
+; RV32-NEXT:    vand.vv v8, v8, v16
+; RV32-NEXT:    vadd.vv v8, v24, v8
+; RV32-NEXT:    vsrl.vi v16, v8, 4
+; RV32-NEXT:    vadd.vv v8, v8, v16
+; RV32-NEXT:    vsetvli a2, zero, e64, m8, ta, ma
+; RV32-NEXT:    vlse64.v v16, (a1), zero
+; RV32-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
+; RV32-NEXT:    vand.vv v8, v8, v16
+; RV32-NEXT:    vsetvli a2, zero, e64, m8, ta, ma
+; RV32-NEXT:    vlse64.v v16, (a1), zero
+; RV32-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
+; RV32-NEXT:    vmul.vv v8, v8, v16
+; RV32-NEXT:    li a0, 56
+; RV32-NEXT:    vsrl.vx v8, v8, a0
+; RV32-NEXT:    addi sp, sp, 16
+; RV32-NEXT:    ret
+;
+; RV64-LABEL: vp_ctpop_nxv7i64_unmasked:
+; RV64:       # %bb.0:
+; RV64-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
+; RV64-NEXT:    lui a0, %hi(.LCPI43_0)
+; RV64-NEXT:    ld a0, %lo(.LCPI43_0)(a0)
+; RV64-NEXT:    lui a1, %hi(.LCPI43_1)
+; RV64-NEXT:    ld a1, %lo(.LCPI43_1)(a1)
+; RV64-NEXT:    vsrl.vi v16, v8, 1
+; RV64-NEXT:    vand.vx v16, v16, a0
+; RV64-NEXT:    vsub.vv v8, v8, v16
+; RV64-NEXT:    vand.vx v16, v8, a1
+; RV64-NEXT:    vsrl.vi v8, v8, 2
+; RV64-NEXT:    vand.vx v8, v8, a1
+; RV64-NEXT:    vadd.vv v8, v16, v8
+; RV64-NEXT:    lui a0, %hi(.LCPI43_2)
+; RV64-NEXT:    ld a0, %lo(.LCPI43_2)(a0)
+; RV64-NEXT:    lui a1, %hi(.LCPI43_3)
+; RV64-NEXT:    ld a1, %lo(.LCPI43_3)(a1)
+; RV64-NEXT:    vsrl.vi v16, v8, 4
+; RV64-NEXT:    vadd.vv v8, v8, v16
+; RV64-NEXT:    vand.vx v8, v8, a0
+; RV64-NEXT:    vmul.vx v8, v8, a1
+; RV64-NEXT:    li a0, 56
+; RV64-NEXT:    vsrl.vx v8, v8, a0
+; RV64-NEXT:    ret
+  %head = insertelement <vscale x 7 x i1> poison, i1 true, i32 0
+  %m = shufflevector <vscale x 7 x i1> %head, <vscale x 7 x i1> poison, <vscale x 7 x i32> zeroinitializer
+  %v = call <vscale x 7 x i64> @llvm.vp.ctpop.nxv7i64(<vscale x 7 x i64> %va, <vscale x 7 x i1> %m, i32 %evl)
+  ret <vscale x 7 x i64> %v
+}
+
+declare <vscale x 8 x i64> @llvm.vp.ctpop.nxv8i64(<vscale x 8 x i64>, <vscale x 8 x i1>, i32)
+
+define <vscale x 8 x i64> @vp_ctpop_nxv8i64(<vscale x 8 x i64> %va, <vscale x 8 x i1> %m, i32 zeroext %evl) {
+; RV32-LABEL: vp_ctpop_nxv8i64:
+; RV32:       # %bb.0:
+; RV32-NEXT:    addi sp, sp, -16
+; RV32-NEXT:    .cfi_def_cfa_offset 16
+; RV32-NEXT:    lui a1, 349525
+; RV32-NEXT:    addi a1, a1, 1365
+; RV32-NEXT:    sw a1, 12(sp)
+; RV32-NEXT:    sw a1, 8(sp)
+; RV32-NEXT:    lui a1, 209715
+; RV32-NEXT:    addi a1, a1, 819
+; RV32-NEXT:    sw a1, 12(sp)
+; RV32-NEXT:    sw a1, 8(sp)
+; RV32-NEXT:    lui a1, 61681
+; RV32-NEXT:    addi a1, a1, -241
+; RV32-NEXT:    sw a1, 12(sp)
+; RV32-NEXT:    sw a1, 8(sp)
+; RV32-NEXT:    lui a1, 4112
+; RV32-NEXT:    addi a1, a1, 257
+; RV32-NEXT:    sw a1, 12(sp)
+; RV32-NEXT:    sw a1, 8(sp)
+; RV32-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
+; RV32-NEXT:    vsrl.vi v16, v8, 1, v0.t
+; RV32-NEXT:    addi a1, sp, 8
+; RV32-NEXT:    vsetvli a2, zero, e64, m8, ta, ma
+; RV32-NEXT:    vlse64.v v24, (a1), zero
+; RV32-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
+; RV32-NEXT:    vand.vv v16, v16, v24, v0.t
+; RV32-NEXT:    vsub.vv v8, v8, v16, v0.t
+; RV32-NEXT:    vsetvli a2, zero, e64, m8, ta, ma
+; RV32-NEXT:    vlse64.v v16, (a1), zero
+; RV32-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
+; RV32-NEXT:    vand.vv v24, v8, v16, v0.t
+; RV32-NEXT:    vsrl.vi v8, v8, 2, v0.t
+; RV32-NEXT:    vand.vv v8, v8, v16, v0.t
+; RV32-NEXT:    vadd.vv v8, v24, v8, v0.t
+; RV32-NEXT:    vsrl.vi v16, v8, 4, v0.t
+; RV32-NEXT:    vadd.vv v8, v8, v16, v0.t
+; RV32-NEXT:    vsetvli a2, zero, e64, m8, ta, ma
+; RV32-NEXT:    vlse64.v v16, (a1), zero
+; RV32-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
+; RV32-NEXT:    vand.vv v8, v8, v16, v0.t
+; RV32-NEXT:    vsetvli a2, zero, e64, m8, ta, ma
+; RV32-NEXT:    vlse64.v v16, (a1), zero
+; RV32-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
+; RV32-NEXT:    vmul.vv v8, v8, v16, v0.t
+; RV32-NEXT:    li a0, 56
+; RV32-NEXT:    vsrl.vx v8, v8, a0, v0.t
+; RV32-NEXT:    addi sp, sp, 16
+; RV32-NEXT:    ret
+;
+; RV64-LABEL: vp_ctpop_nxv8i64:
+; RV64:       # %bb.0:
+; RV64-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
+; RV64-NEXT:    lui a0, %hi(.LCPI44_0)
+; RV64-NEXT:    ld a0, %lo(.LCPI44_0)(a0)
+; RV64-NEXT:    lui a1, %hi(.LCPI44_1)
+; RV64-NEXT:    ld a1, %lo(.LCPI44_1)(a1)
+; RV64-NEXT:    vsrl.vi v16, v8, 1, v0.t
+; RV64-NEXT:    vand.vx v16, v16, a0, v0.t
+; RV64-NEXT:    vsub.vv v8, v8, v16, v0.t
+; RV64-NEXT:    vand.vx v16, v8, a1, v0.t
+; RV64-NEXT:    vsrl.vi v8, v8, 2, v0.t
+; RV64-NEXT:    vand.vx v8, v8, a1, v0.t
+; RV64-NEXT:    vadd.vv v8, v16, v8, v0.t
+; RV64-NEXT:    lui a0, %hi(.LCPI44_2)
+; RV64-NEXT:    ld a0, %lo(.LCPI44_2)(a0)
+; RV64-NEXT:    lui a1, %hi(.LCPI44_3)
+; RV64-NEXT:    ld a1, %lo(.LCPI44_3)(a1)
+; RV64-NEXT:    vsrl.vi v16, v8, 4, v0.t
+; RV64-NEXT:    vadd.vv v8, v8, v16, v0.t
+; RV64-NEXT:    vand.vx v8, v8, a0, v0.t
+; RV64-NEXT:    vmul.vx v8, v8, a1, v0.t
+; RV64-NEXT:    li a0, 56
+; RV64-NEXT:    vsrl.vx v8, v8, a0, v0.t
+; RV64-NEXT:    ret
+  %v = call <vscale x 8 x i64> @llvm.vp.ctpop.nxv8i64(<vscale x 8 x i64> %va, <vscale x 8 x i1> %m, i32 %evl)
+  ret <vscale x 8 x i64> %v
+}
+
+define <vscale x 8 x i64> @vp_ctpop_nxv8i64_unmasked(<vscale x 8 x i64> %va, i32 zeroext %evl) {
+; RV32-LABEL: vp_ctpop_nxv8i64_unmasked:
+; RV32:       # %bb.0:
+; RV32-NEXT:    addi sp, sp, -16
+; RV32-NEXT:    .cfi_def_cfa_offset 16
+; RV32-NEXT:    lui a1, 349525
+; RV32-NEXT:    addi a1, a1, 1365
+; RV32-NEXT:    sw a1, 12(sp)
+; RV32-NEXT:    sw a1, 8(sp)
+; RV32-NEXT:    lui a1, 209715
+; RV32-NEXT:    addi a1, a1, 819
+; RV32-NEXT:    sw a1, 12(sp)
+; RV32-NEXT:    sw a1, 8(sp)
+; RV32-NEXT:    lui a1, 61681
+; RV32-NEXT:    addi a1, a1, -241
+; RV32-NEXT:    sw a1, 12(sp)
+; RV32-NEXT:    sw a1, 8(sp)
+; RV32-NEXT:    lui a1, 4112
+; RV32-NEXT:    addi a1, a1, 257
+; RV32-NEXT:    sw a1, 12(sp)
+; RV32-NEXT:    sw a1, 8(sp)
+; RV32-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
+; RV32-NEXT:    vsrl.vi v16, v8, 1
+; RV32-NEXT:    addi a1, sp, 8
+; RV32-NEXT:    vsetvli a2, zero, e64, m8, ta, ma
+; RV32-NEXT:    vlse64.v v24, (a1), zero
+; RV32-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
+; RV32-NEXT:    vand.vv v16, v16, v24
+; RV32-NEXT:    vsub.vv v8, v8, v16
+; RV32-NEXT:    vsetvli a2, zero, e64, m8, ta, ma
+; RV32-NEXT:    vlse64.v v16, (a1), zero
+; RV32-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
+; RV32-NEXT:    vand.vv v24, v8, v16
+; RV32-NEXT:    vsrl.vi v8, v8, 2
+; RV32-NEXT:    vand.vv v8, v8, v16
+; RV32-NEXT:    vadd.vv v8, v24, v8
+; RV32-NEXT:    vsrl.vi v16, v8, 4
+; RV32-NEXT:    vadd.vv v8, v8, v16
+; RV32-NEXT:    vsetvli a2, zero, e64, m8, ta, ma
+; RV32-NEXT:    vlse64.v v16, (a1), zero
+; RV32-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
+; RV32-NEXT:    vand.vv v8, v8, v16
+; RV32-NEXT:    vsetvli a2, zero, e64, m8, ta, ma
+; RV32-NEXT:    vlse64.v v16, (a1), zero
+; RV32-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
+; RV32-NEXT:    vmul.vv v8, v8, v16
+; RV32-NEXT:    li a0, 56
+; RV32-NEXT:    vsrl.vx v8, v8, a0
+; RV32-NEXT:    addi sp, sp, 16
+; RV32-NEXT:    ret
+;
+; RV64-LABEL: vp_ctpop_nxv8i64_unmasked:
+; RV64:       # %bb.0:
+; RV64-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
+; RV64-NEXT:    lui a0, %hi(.LCPI45_0)
+; RV64-NEXT:    ld a0, %lo(.LCPI45_0)(a0)
+; RV64-NEXT:    lui a1, %hi(.LCPI45_1)
+; RV64-NEXT:    ld a1, %lo(.LCPI45_1)(a1)
+; RV64-NEXT:    vsrl.vi v16, v8, 1
+; RV64-NEXT:    vand.vx v16, v16, a0
+; RV64-NEXT:    vsub.vv v8, v8, v16
+; RV64-NEXT:    vand.vx v16, v8, a1
+; RV64-NEXT:    vsrl.vi v8, v8, 2
+; RV64-NEXT:    vand.vx v8, v8, a1
+; RV64-NEXT:    vadd.vv v8, v16, v8
+; RV64-NEXT:    lui a0, %hi(.LCPI45_2)
+; RV64-NEXT:    ld a0, %lo(.LCPI45_2)(a0)
+; RV64-NEXT:    lui a1, %hi(.LCPI45_3)
+; RV64-NEXT:    ld a1, %lo(.LCPI45_3)(a1)
+; RV64-NEXT:    vsrl.vi v16, v8, 4
+; RV64-NEXT:    vadd.vv v8, v8, v16
+; RV64-NEXT:    vand.vx v8, v8, a0
+; RV64-NEXT:    vmul.vx v8, v8, a1
+; RV64-NEXT:    li a0, 56
+; RV64-NEXT:    vsrl.vx v8, v8, a0
+; RV64-NEXT:    ret
+  %head = insertelement <vscale x 8 x i1> poison, i1 true, i32 0
+  %m = shufflevector <vscale x 8 x i1> %head, <vscale x 8 x i1> poison, <vscale x 8 x i32> zeroinitializer
+  %v = call <vscale x 8 x i64> @llvm.vp.ctpop.nxv8i64(<vscale x 8 x i64> %va, <vscale x 8 x i1> %m, i32 %evl)
+  ret <vscale x 8 x i64> %v
+}
+
+declare <vscale x 16 x i64> @llvm.vp.ctpop.nxv16i64(<vscale x 16 x i64>, <vscale x 16 x i1>, i32)
+
+define <vscale x 16 x i64> @vp_ctpop_nxv16i64(<vscale x 16 x i64> %va, <vscale x 16 x i1> %m, i32 zeroext %evl) {
+; RV32-LABEL: vp_ctpop_nxv16i64:
+; RV32:       # %bb.0:
+; RV32-NEXT:    addi sp, sp, -16
+; RV32-NEXT:    .cfi_def_cfa_offset 16
+; RV32-NEXT:    csrr a1, vlenb
+; RV32-NEXT:    li a2, 48
+; RV32-NEXT:    mul a1, a1, a2
+; RV32-NEXT:    sub sp, sp, a1
+; RV32-NEXT:    .cfi_escape 0x0f, 0x0d, 0x72, 0x00, 0x11, 0x10, 0x22, 0x11, 0x30, 0x92, 0xa2, 0x38, 0x00, 0x1e, 0x22 # sp + 16 + 48 * vlenb
+; RV32-NEXT:    vmv1r.v v1, v0
+; RV32-NEXT:    csrr a1, vlenb
+; RV32-NEXT:    li a2, 40
+; RV32-NEXT:    mul a1, a1, a2
+; RV32-NEXT:    add a1, sp, a1
+; RV32-NEXT:    addi a1, a1, 16
+; RV32-NEXT:    vs8r.v v16, (a1) # Unknown-size Folded Spill
+; RV32-NEXT:    csrr a1, vlenb
+; RV32-NEXT:    srli a2, a1, 3
+; RV32-NEXT:    vsetvli a3, zero, e8, mf4, ta, ma
+; RV32-NEXT:    vslidedown.vx v0, v0, a2
+; RV32-NEXT:    lui a2, 349525
+; RV32-NEXT:    addi a2, a2, 1365
+; RV32-NEXT:    sw a2, 12(sp)
+; RV32-NEXT:    sw a2, 8(sp)
+; RV32-NEXT:    lui a2, 209715
+; RV32-NEXT:    addi a2, a2, 819
+; RV32-NEXT:    sw a2, 12(sp)
+; RV32-NEXT:    sw a2, 8(sp)
+; RV32-NEXT:    lui a2, 61681
+; RV32-NEXT:    addi a2, a2, -241
+; RV32-NEXT:    sw a2, 12(sp)
+; RV32-NEXT:    sw a2, 8(sp)
+; RV32-NEXT:    lui a2, 4112
+; RV32-NEXT:    addi a2, a2, 257
+; RV32-NEXT:    sw a2, 12(sp)
+; RV32-NEXT:    sw a2, 8(sp)
+; RV32-NEXT:    sub a2, a0, a1
+; RV32-NEXT:    sltu a3, a0, a2
+; RV32-NEXT:    addi a3, a3, -1
+; RV32-NEXT:    and a2, a3, a2
+; RV32-NEXT:    vsetvli zero, a2, e64, m8, ta, ma
+; RV32-NEXT:    vsrl.vi v24, v16, 1, v0.t
+; RV32-NEXT:    addi a3, sp, 8
+; RV32-NEXT:    vsetvli a4, zero, e64, m8, ta, ma
+; RV32-NEXT:    vlse64.v v16, (a3), zero
+; RV32-NEXT:    vsetvli zero, a2, e64, m8, ta, ma
+; RV32-NEXT:    csrr a4, vlenb
+; RV32-NEXT:    slli a4, a4, 5
+; RV32-NEXT:    add a4, sp, a4
+; RV32-NEXT:    addi a4, a4, 16
+; RV32-NEXT:    vs8r.v v16, (a4) # Unknown-size Folded Spill
+; RV32-NEXT:    vand.vv v24, v24, v16, v0.t
+; RV32-NEXT:    csrr a4, vlenb
+; RV32-NEXT:    li a5, 40
+; RV32-NEXT:    mul a4, a4, a5
+; RV32-NEXT:    add a4, sp, a4
+; RV32-NEXT:    addi a4, a4, 16
+; RV32-NEXT:    vl8r.v v16, (a4) # Unknown-size Folded Reload
+; RV32-NEXT:    vsub.vv v16, v16, v24, v0.t
+; RV32-NEXT:    csrr a4, vlenb
+; RV32-NEXT:    li a5, 40
+; RV32-NEXT:    mul a4, a4, a5
+; RV32-NEXT:    add a4, sp, a4
+; RV32-NEXT:    addi a4, a4, 16
+; RV32-NEXT:    vs8r.v v16, (a4) # Unknown-size Folded Spill
+; RV32-NEXT:    vsetvli a4, zero, e64, m8, ta, ma
+; RV32-NEXT:    vlse64.v v16, (a3), zero
+; RV32-NEXT:    vsetvli zero, a2, e64, m8, ta, ma
+; RV32-NEXT:    csrr a4, vlenb
+; RV32-NEXT:    li a5, 40
+; RV32-NEXT:    mul a4, a4, a5
+; RV32-NEXT:    add a4, sp, a4
+; RV32-NEXT:    addi a4, a4, 16
+; RV32-NEXT:    vl8r.v v24, (a4) # Unknown-size Folded Reload
+; RV32-NEXT:    vand.vv v24, v24, v16, v0.t
+; RV32-NEXT:    csrr a4, vlenb
+; RV32-NEXT:    li a5, 24
+; RV32-NEXT:    mul a4, a4, a5
+; RV32-NEXT:    add a4, sp, a4
+; RV32-NEXT:    addi a4, a4, 16
+; RV32-NEXT:    vs8r.v v24, (a4) # Unknown-size Folded Spill
+; RV32-NEXT:    csrr a4, vlenb
+; RV32-NEXT:    li a5, 40
+; RV32-NEXT:    mul a4, a4, a5
+; RV32-NEXT:    add a4, sp, a4
+; RV32-NEXT:    addi a4, a4, 16
+; RV32-NEXT:    vl8r.v v24, (a4) # Unknown-size Folded Reload
+; RV32-NEXT:    vsrl.vi v24, v24, 2, v0.t
+; RV32-NEXT:    csrr a4, vlenb
+; RV32-NEXT:    li a5, 40
+; RV32-NEXT:    mul a4, a4, a5
+; RV32-NEXT:    add a4, sp, a4
+; RV32-NEXT:    addi a4, a4, 16
+; RV32-NEXT:    vs8r.v v16, (a4) # Unknown-size Folded Spill
+; RV32-NEXT:    vand.vv v16, v24, v16, v0.t
+; RV32-NEXT:    csrr a4, vlenb
+; RV32-NEXT:    li a5, 24
+; RV32-NEXT:    mul a4, a4, a5
+; RV32-NEXT:    add a4, sp, a4
+; RV32-NEXT:    addi a4, a4, 16
+; RV32-NEXT:    vl8r.v v24, (a4) # Unknown-size Folded Reload
+; RV32-NEXT:    vadd.vv v16, v24, v16, v0.t
+; RV32-NEXT:    vsrl.vi v24, v16, 4, v0.t
+; RV32-NEXT:    vadd.vv v24, v16, v24, v0.t
+; RV32-NEXT:    vsetvli a4, zero, e64, m8, ta, ma
+; RV32-NEXT:    vlse64.v v16, (a3), zero
+; RV32-NEXT:    vsetvli zero, a2, e64, m8, ta, ma
+; RV32-NEXT:    csrr a4, vlenb
+; RV32-NEXT:    li a5, 24
+; RV32-NEXT:    mul a4, a4, a5
+; RV32-NEXT:    add a4, sp, a4
+; RV32-NEXT:    addi a4, a4, 16
+; RV32-NEXT:    vs8r.v v16, (a4) # Unknown-size Folded Spill
+; RV32-NEXT:    vand.vv v24, v24, v16, v0.t
+; RV32-NEXT:    vsetvli a4, zero, e64, m8, ta, ma
+; RV32-NEXT:    vlse64.v v16, (a3), zero
+; RV32-NEXT:    addi a3, sp, 16
+; RV32-NEXT:    vs8r.v v8, (a3) # Unknown-size Folded Spill
+; RV32-NEXT:    vsetvli zero, a2, e64, m8, ta, ma
+; RV32-NEXT:    csrr a2, vlenb
+; RV32-NEXT:    slli a2, a2, 4
+; RV32-NEXT:    add a2, sp, a2
+; RV32-NEXT:    addi a2, a2, 16
+; RV32-NEXT:    vs8r.v v16, (a2) # Unknown-size Folded Spill
+; RV32-NEXT:    vmul.vv v16, v24, v16, v0.t
+; RV32-NEXT:    li a2, 56
+; RV32-NEXT:    vsrl.vx v8, v16, a2, v0.t
+; RV32-NEXT:    csrr a3, vlenb
+; RV32-NEXT:    slli a3, a3, 3
+; RV32-NEXT:    add a3, sp, a3
+; RV32-NEXT:    addi a3, a3, 16
+; RV32-NEXT:    vs8r.v v8, (a3) # Unknown-size Folded Spill
+; RV32-NEXT:    bltu a0, a1, .LBB46_2
+; RV32-NEXT:  # %bb.1:
+; RV32-NEXT:    mv a0, a1
+; RV32-NEXT:  .LBB46_2:
+; RV32-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
+; RV32-NEXT:    vmv1r.v v0, v1
+; RV32-NEXT:    addi a0, sp, 16
+; RV32-NEXT:    vl8r.v v8, (a0) # Unknown-size Folded Reload
+; RV32-NEXT:    vsrl.vi v24, v8, 1, v0.t
+; RV32-NEXT:    csrr a0, vlenb
+; RV32-NEXT:    slli a0, a0, 5
+; RV32-NEXT:    add a0, sp, a0
+; RV32-NEXT:    addi a0, a0, 16
+; RV32-NEXT:    vl8r.v v16, (a0) # Unknown-size Folded Reload
+; RV32-NEXT:    vand.vv v16, v24, v16, v0.t
+; RV32-NEXT:    vsub.vv v8, v8, v16, v0.t
+; RV32-NEXT:    csrr a0, vlenb
+; RV32-NEXT:    li a1, 40
+; RV32-NEXT:    mul a0, a0, a1
+; RV32-NEXT:    add a0, sp, a0
+; RV32-NEXT:    addi a0, a0, 16
+; RV32-NEXT:    vl8r.v v16, (a0) # Unknown-size Folded Reload
+; RV32-NEXT:    vand.vv v24, v8, v16, v0.t
+; RV32-NEXT:    vsrl.vi v8, v8, 2, v0.t
+; RV32-NEXT:    vand.vv v8, v8, v16, v0.t
+; RV32-NEXT:    vadd.vv v8, v24, v8, v0.t
+; RV32-NEXT:    vsrl.vi v16, v8, 4, v0.t
+; RV32-NEXT:    vadd.vv v8, v8, v16, v0.t
+; RV32-NEXT:    csrr a0, vlenb
+; RV32-NEXT:    li a1, 24
+; RV32-NEXT:    mul a0, a0, a1
+; RV32-NEXT:    add a0, sp, a0
+; RV32-NEXT:    addi a0, a0, 16
+; RV32-NEXT:    vl8r.v v16, (a0) # Unknown-size Folded Reload
+; RV32-NEXT:    vand.vv v8, v8, v16, v0.t
+; RV32-NEXT:    csrr a0, vlenb
+; RV32-NEXT:    slli a0, a0, 4
+; RV32-NEXT:    add a0, sp, a0
+; RV32-NEXT:    addi a0, a0, 16
+; RV32-NEXT:    vl8r.v v16, (a0) # Unknown-size Folded Reload
+; RV32-NEXT:    vmul.vv v8, v8, v16, v0.t
+; RV32-NEXT:    vsrl.vx v8, v8, a2, v0.t
+; RV32-NEXT:    csrr a0, vlenb
+; RV32-NEXT:    slli a0, a0, 3
+; RV32-NEXT:    add a0, sp, a0
+; RV32-NEXT:    addi a0, a0, 16
+; RV32-NEXT:    vl8r.v v16, (a0) # Unknown-size Folded Reload
+; RV32-NEXT:    csrr a0, vlenb
+; RV32-NEXT:    li a1, 48
+; RV32-NEXT:    mul a0, a0, a1
+; RV32-NEXT:    add sp, sp, a0
+; RV32-NEXT:    addi sp, sp, 16
+; RV32-NEXT:    ret
+;
+; RV64-LABEL: vp_ctpop_nxv16i64:
+; RV64:       # %bb.0:
+; RV64-NEXT:    addi sp, sp, -16
+; RV64-NEXT:    .cfi_def_cfa_offset 16
+; RV64-NEXT:    csrr a1, vlenb
+; RV64-NEXT:    slli a1, a1, 4
+; RV64-NEXT:    sub sp, sp, a1
+; RV64-NEXT:    .cfi_escape 0x0f, 0x0d, 0x72, 0x00, 0x11, 0x10, 0x22, 0x11, 0x10, 0x92, 0xa2, 0x38, 0x00, 0x1e, 0x22 # sp + 16 + 16 * vlenb
+; RV64-NEXT:    vmv1r.v v24, v0
+; RV64-NEXT:    csrr a1, vlenb
+; RV64-NEXT:    slli a1, a1, 3
+; RV64-NEXT:    add a1, sp, a1
+; RV64-NEXT:    addi a1, a1, 16
+; RV64-NEXT:    vs8r.v v8, (a1) # Unknown-size Folded Spill
+; RV64-NEXT:    csrr a1, vlenb
+; RV64-NEXT:    srli a2, a1, 3
+; RV64-NEXT:    vsetvli a3, zero, e8, mf4, ta, ma
+; RV64-NEXT:    vslidedown.vx v0, v0, a2
+; RV64-NEXT:    sub a2, a0, a1
+; RV64-NEXT:    sltu a3, a0, a2
+; RV64-NEXT:    addi a3, a3, -1
+; RV64-NEXT:    and a2, a3, a2
+; RV64-NEXT:    vsetvli zero, a2, e64, m8, ta, ma
+; RV64-NEXT:    lui a2, %hi(.LCPI46_0)
+; RV64-NEXT:    ld a3, %lo(.LCPI46_0)(a2)
+; RV64-NEXT:    lui a2, %hi(.LCPI46_1)
+; RV64-NEXT:    ld a2, %lo(.LCPI46_1)(a2)
+; RV64-NEXT:    vsrl.vi v8, v16, 1, v0.t
+; RV64-NEXT:    vand.vx v8, v8, a3, v0.t
+; RV64-NEXT:    vsub.vv v8, v16, v8, v0.t
+; RV64-NEXT:    vand.vx v16, v8, a2, v0.t
+; RV64-NEXT:    vsrl.vi v8, v8, 2, v0.t
+; RV64-NEXT:    vand.vx v8, v8, a2, v0.t
+; RV64-NEXT:    vadd.vv v16, v16, v8, v0.t
+; RV64-NEXT:    lui a4, %hi(.LCPI46_2)
+; RV64-NEXT:    ld a4, %lo(.LCPI46_2)(a4)
+; RV64-NEXT:    lui a5, %hi(.LCPI46_3)
+; RV64-NEXT:    ld a5, %lo(.LCPI46_3)(a5)
+; RV64-NEXT:    vsrl.vi v8, v16, 4, v0.t
+; RV64-NEXT:    vadd.vv v8, v16, v8, v0.t
+; RV64-NEXT:    vand.vx v8, v8, a4, v0.t
+; RV64-NEXT:    vmul.vx v8, v8, a5, v0.t
+; RV64-NEXT:    li a6, 56
+; RV64-NEXT:    vsrl.vx v8, v8, a6, v0.t
+; RV64-NEXT:    addi a7, sp, 16
+; RV64-NEXT:    vs8r.v v8, (a7) # Unknown-size Folded Spill
+; RV64-NEXT:    bltu a0, a1, .LBB46_2
+; RV64-NEXT:  # %bb.1:
+; RV64-NEXT:    mv a0, a1
+; RV64-NEXT:  .LBB46_2:
+; RV64-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
+; RV64-NEXT:    vmv1r.v v0, v24
+; RV64-NEXT:    csrr a0, vlenb
+; RV64-NEXT:    slli a0, a0, 3
+; RV64-NEXT:    add a0, sp, a0
+; RV64-NEXT:    addi a0, a0, 16
+; RV64-NEXT:    vl8r.v v16, (a0) # Unknown-size Folded Reload
+; RV64-NEXT:    vsrl.vi v8, v16, 1, v0.t
+; RV64-NEXT:    vand.vx v8, v8, a3, v0.t
+; RV64-NEXT:    vsub.vv v8, v16, v8, v0.t
+; RV64-NEXT:    vand.vx v16, v8, a2, v0.t
+; RV64-NEXT:    vsrl.vi v8, v8, 2, v0.t
+; RV64-NEXT:    vand.vx v8, v8, a2, v0.t
+; RV64-NEXT:    vadd.vv v8, v16, v8, v0.t
+; RV64-NEXT:    vsrl.vi v16, v8, 4, v0.t
+; RV64-NEXT:    vadd.vv v8, v8, v16, v0.t
+; RV64-NEXT:    vand.vx v8, v8, a4, v0.t
+; RV64-NEXT:    vmul.vx v8, v8, a5, v0.t
+; RV64-NEXT:    vsrl.vx v8, v8, a6, v0.t
+; RV64-NEXT:    addi a0, sp, 16
+; RV64-NEXT:    vl8r.v v16, (a0) # Unknown-size Folded Reload
+; RV64-NEXT:    csrr a0, vlenb
+; RV64-NEXT:    slli a0, a0, 4
+; RV64-NEXT:    add sp, sp, a0
+; RV64-NEXT:    addi sp, sp, 16
+; RV64-NEXT:    ret
+  %v = call <vscale x 16 x i64> @llvm.vp.ctpop.nxv16i64(<vscale x 16 x i64> %va, <vscale x 16 x i1> %m, i32 %evl)
+  ret <vscale x 16 x i64> %v
+}
+
+define <vscale x 16 x i64> @vp_ctpop_nxv16i64_unmasked(<vscale x 16 x i64> %va, i32 zeroext %evl) {
+; RV32-LABEL: vp_ctpop_nxv16i64_unmasked:
+; RV32:       # %bb.0:
+; RV32-NEXT:    addi sp, sp, -16
+; RV32-NEXT:    .cfi_def_cfa_offset 16
+; RV32-NEXT:    csrr a1, vlenb
+; RV32-NEXT:    slli a1, a1, 5
+; RV32-NEXT:    sub sp, sp, a1
+; RV32-NEXT:    .cfi_escape 0x0f, 0x0d, 0x72, 0x00, 0x11, 0x10, 0x22, 0x11, 0x20, 0x92, 0xa2, 0x38, 0x00, 0x1e, 0x22 # sp + 16 + 32 * vlenb
+; RV32-NEXT:    lui a1, 349525
+; RV32-NEXT:    addi a1, a1, 1365
+; RV32-NEXT:    sw a1, 12(sp)
+; RV32-NEXT:    sw a1, 8(sp)
+; RV32-NEXT:    lui a1, 209715
+; RV32-NEXT:    addi a1, a1, 819
+; RV32-NEXT:    sw a1, 12(sp)
+; RV32-NEXT:    sw a1, 8(sp)
+; RV32-NEXT:    lui a1, 61681
+; RV32-NEXT:    addi a1, a1, -241
+; RV32-NEXT:    sw a1, 12(sp)
+; RV32-NEXT:    sw a1, 8(sp)
+; RV32-NEXT:    lui a1, 4112
+; RV32-NEXT:    addi a1, a1, 257
+; RV32-NEXT:    sw a1, 12(sp)
+; RV32-NEXT:    sw a1, 8(sp)
+; RV32-NEXT:    csrr a1, vlenb
+; RV32-NEXT:    sub a2, a0, a1
+; RV32-NEXT:    sltu a3, a0, a2
+; RV32-NEXT:    addi a3, a3, -1
+; RV32-NEXT:    and a2, a3, a2
+; RV32-NEXT:    vsetvli zero, a2, e64, m8, ta, ma
+; RV32-NEXT:    vsrl.vi v24, v16, 1
+; RV32-NEXT:    addi a3, sp, 8
+; RV32-NEXT:    vsetvli a4, zero, e64, m8, ta, ma
+; RV32-NEXT:    vlse64.v v0, (a3), zero
+; RV32-NEXT:    vsetvli zero, a2, e64, m8, ta, ma
+; RV32-NEXT:    csrr a4, vlenb
+; RV32-NEXT:    li a5, 24
+; RV32-NEXT:    mul a4, a4, a5
+; RV32-NEXT:    add a4, sp, a4
+; RV32-NEXT:    addi a4, a4, 16
+; RV32-NEXT:    vs8r.v v0, (a4) # Unknown-size Folded Spill
+; RV32-NEXT:    vand.vv v24, v24, v0
+; RV32-NEXT:    vsub.vv v16, v16, v24
+; RV32-NEXT:    vsetvli a4, zero, e64, m8, ta, ma
+; RV32-NEXT:    vlse64.v v0, (a3), zero
+; RV32-NEXT:    vsetvli zero, a2, e64, m8, ta, ma
+; RV32-NEXT:    vand.vv v24, v16, v0
+; RV32-NEXT:    vsrl.vi v16, v16, 2
+; RV32-NEXT:    vand.vv v16, v16, v0
+; RV32-NEXT:    vadd.vv v16, v24, v16
+; RV32-NEXT:    vsrl.vi v24, v16, 4
+; RV32-NEXT:    vadd.vv v24, v16, v24
+; RV32-NEXT:    vsetvli a4, zero, e64, m8, ta, ma
+; RV32-NEXT:    vlse64.v v16, (a3), zero
+; RV32-NEXT:    vsetvli zero, a2, e64, m8, ta, ma
+; RV32-NEXT:    csrr a4, vlenb
+; RV32-NEXT:    slli a4, a4, 4
+; RV32-NEXT:    add a4, sp, a4
+; RV32-NEXT:    addi a4, a4, 16
+; RV32-NEXT:    vs8r.v v16, (a4) # Unknown-size Folded Spill
+; RV32-NEXT:    vand.vv v16, v24, v16
+; RV32-NEXT:    vsetvli a4, zero, e64, m8, ta, ma
+; RV32-NEXT:    vlse64.v v24, (a3), zero
+; RV32-NEXT:    vsetvli zero, a2, e64, m8, ta, ma
+; RV32-NEXT:    csrr a2, vlenb
+; RV32-NEXT:    slli a2, a2, 3
+; RV32-NEXT:    add a2, sp, a2
+; RV32-NEXT:    addi a2, a2, 16
+; RV32-NEXT:    vs8r.v v24, (a2) # Unknown-size Folded Spill
+; RV32-NEXT:    vmul.vv v16, v16, v24
+; RV32-NEXT:    li a2, 56
+; RV32-NEXT:    vsrl.vx v16, v16, a2
+; RV32-NEXT:    addi a3, sp, 16
+; RV32-NEXT:    vs8r.v v16, (a3) # Unknown-size Folded Spill
+; RV32-NEXT:    bltu a0, a1, .LBB47_2
+; RV32-NEXT:  # %bb.1:
+; RV32-NEXT:    mv a0, a1
+; RV32-NEXT:  .LBB47_2:
+; RV32-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
+; RV32-NEXT:    vsrl.vi v16, v8, 1
+; RV32-NEXT:    csrr a0, vlenb
+; RV32-NEXT:    li a1, 24
+; RV32-NEXT:    mul a0, a0, a1
+; RV32-NEXT:    add a0, sp, a0
+; RV32-NEXT:    addi a0, a0, 16
+; RV32-NEXT:    vl8r.v v24, (a0) # Unknown-size Folded Reload
+; RV32-NEXT:    vand.vv v16, v16, v24
+; RV32-NEXT:    vsub.vv v8, v8, v16
+; RV32-NEXT:    vand.vv v16, v8, v0
+; RV32-NEXT:    vsrl.vi v8, v8, 2
+; RV32-NEXT:    vand.vv v8, v8, v0
+; RV32-NEXT:    vadd.vv v8, v16, v8
+; RV32-NEXT:    vsrl.vi v16, v8, 4
+; RV32-NEXT:    vadd.vv v8, v8, v16
+; RV32-NEXT:    csrr a0, vlenb
+; RV32-NEXT:    slli a0, a0, 4
+; RV32-NEXT:    add a0, sp, a0
+; RV32-NEXT:    addi a0, a0, 16
+; RV32-NEXT:    vl8r.v v16, (a0) # Unknown-size Folded Reload
+; RV32-NEXT:    vand.vv v8, v8, v16
+; RV32-NEXT:    csrr a0, vlenb
+; RV32-NEXT:    slli a0, a0, 3
+; RV32-NEXT:    add a0, sp, a0
+; RV32-NEXT:    addi a0, a0, 16
+; RV32-NEXT:    vl8r.v v16, (a0) # Unknown-size Folded Reload
+; RV32-NEXT:    vmul.vv v8, v8, v16
+; RV32-NEXT:    vsrl.vx v8, v8, a2
+; RV32-NEXT:    addi a0, sp, 16
+; RV32-NEXT:    vl8r.v v16, (a0) # Unknown-size Folded Reload
+; RV32-NEXT:    csrr a0, vlenb
+; RV32-NEXT:    slli a0, a0, 5
+; RV32-NEXT:    add sp, sp, a0
+; RV32-NEXT:    addi sp, sp, 16
+; RV32-NEXT:    ret
+;
+; RV64-LABEL: vp_ctpop_nxv16i64_unmasked:
+; RV64:       # %bb.0:
+; RV64-NEXT:    csrr a1, vlenb
+; RV64-NEXT:    sub a2, a0, a1
+; RV64-NEXT:    sltu a3, a0, a2
+; RV64-NEXT:    addi a3, a3, -1
+; RV64-NEXT:    and a2, a3, a2
+; RV64-NEXT:    vsetvli zero, a2, e64, m8, ta, ma
+; RV64-NEXT:    lui a2, %hi(.LCPI47_0)
+; RV64-NEXT:    ld a2, %lo(.LCPI47_0)(a2)
+; RV64-NEXT:    lui a3, %hi(.LCPI47_1)
+; RV64-NEXT:    ld a3, %lo(.LCPI47_1)(a3)
+; RV64-NEXT:    vsrl.vi v24, v16, 1
+; RV64-NEXT:    vand.vx v24, v24, a2
+; RV64-NEXT:    vsub.vv v16, v16, v24
+; RV64-NEXT:    vand.vx v24, v16, a3
+; RV64-NEXT:    vsrl.vi v16, v16, 2
+; RV64-NEXT:    vand.vx v16, v16, a3
+; RV64-NEXT:    vadd.vv v16, v24, v16
+; RV64-NEXT:    lui a4, %hi(.LCPI47_2)
+; RV64-NEXT:    ld a4, %lo(.LCPI47_2)(a4)
+; RV64-NEXT:    lui a5, %hi(.LCPI47_3)
+; RV64-NEXT:    ld a5, %lo(.LCPI47_3)(a5)
+; RV64-NEXT:    vsrl.vi v24, v16, 4
+; RV64-NEXT:    vadd.vv v16, v16, v24
+; RV64-NEXT:    vand.vx v16, v16, a4
+; RV64-NEXT:    vmul.vx v16, v16, a5
+; RV64-NEXT:    li a6, 56
+; RV64-NEXT:    vsrl.vx v16, v16, a6
+; RV64-NEXT:    bltu a0, a1, .LBB47_2
+; RV64-NEXT:  # %bb.1:
+; RV64-NEXT:    mv a0, a1
+; RV64-NEXT:  .LBB47_2:
+; RV64-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
+; RV64-NEXT:    vsrl.vi v24, v8, 1
+; RV64-NEXT:    vand.vx v24, v24, a2
+; RV64-NEXT:    vsub.vv v8, v8, v24
+; RV64-NEXT:    vand.vx v24, v8, a3
+; RV64-NEXT:    vsrl.vi v8, v8, 2
+; RV64-NEXT:    vand.vx v8, v8, a3
+; RV64-NEXT:    vadd.vv v8, v24, v8
+; RV64-NEXT:    vsrl.vi v24, v8, 4
+; RV64-NEXT:    vadd.vv v8, v8, v24
+; RV64-NEXT:    vand.vx v8, v8, a4
+; RV64-NEXT:    vmul.vx v8, v8, a5
+; RV64-NEXT:    vsrl.vx v8, v8, a6
+; RV64-NEXT:    ret
+  %head = insertelement <vscale x 16 x i1> poison, i1 true, i32 0
+  %m = shufflevector <vscale x 16 x i1> %head, <vscale x 16 x i1> poison, <vscale x 16 x i32> zeroinitializer
+  %v = call <vscale x 16 x i64> @llvm.vp.ctpop.nxv16i64(<vscale x 16 x i64> %va, <vscale x 16 x i1> %m, i32 %evl)
+  ret <vscale x 16 x i64> %v
+}

llvm/test/CodeGen/RISCV/rvv/fixed-vectors-ctpop-vp.ll

+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc -mtriple=riscv32 -mattr=+d,+zfh,+experimental-zvfh,+v,+m -target-abi=ilp32d -riscv-v-vector-bits-min=128 \
+; RUN:   -verify-machineinstrs < %s | FileCheck %s --check-prefixes=CHECK,RV32
+; RUN: llc -mtriple=riscv64 -mattr=+d,+zfh,+experimental-zvfh,+v,+m -target-abi=lp64d -riscv-v-vector-bits-min=128 \
+; RUN:   -verify-machineinstrs < %s | FileCheck %s --check-prefixes=CHECK,RV64
+
+declare <2 x i8> @llvm.vp.ctpop.v2i8(<2 x i8>, <2 x i1>, i32)
+
+define <2 x i8> @vp_ctpop_v2i8(<2 x i8> %va, <2 x i1> %m, i32 zeroext %evl) {
+; CHECK-LABEL: vp_ctpop_v2i8:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli zero, a0, e8, mf8, ta, ma
+; CHECK-NEXT:    vsrl.vi v9, v8, 1, v0.t
+; CHECK-NEXT:    li a0, 85
+; CHECK-NEXT:    vand.vx v9, v9, a0, v0.t
+; CHECK-NEXT:    vsub.vv v8, v8, v9, v0.t
+; CHECK-NEXT:    li a0, 51
+; CHECK-NEXT:    vand.vx v9, v8, a0, v0.t
+; CHECK-NEXT:    vsrl.vi v8, v8, 2, v0.t
+; CHECK-NEXT:    vand.vx v8, v8, a0, v0.t
+; CHECK-NEXT:    vadd.vv v8, v9, v8, v0.t
+; CHECK-NEXT:    vsrl.vi v9, v8, 4, v0.t
+; CHECK-NEXT:    vadd.vv v8, v8, v9, v0.t
+; CHECK-NEXT:    vand.vi v8, v8, 15, v0.t
+; CHECK-NEXT:    ret
+  %v = call <2 x i8> @llvm.vp.ctpop.v2i8(<2 x i8> %va, <2 x i1> %m, i32 %evl)
+  ret <2 x i8> %v
+}
+
+define <2 x i8> @vp_ctpop_v2i8_unmasked(<2 x i8> %va, i32 zeroext %evl) {
+; CHECK-LABEL: vp_ctpop_v2i8_unmasked:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli zero, a0, e8, mf8, ta, ma
+; CHECK-NEXT:    vsrl.vi v9, v8, 1
+; CHECK-NEXT:    li a0, 85
+; CHECK-NEXT:    vand.vx v9, v9, a0
+; CHECK-NEXT:    vsub.vv v8, v8, v9
+; CHECK-NEXT:    li a0, 51
+; CHECK-NEXT:    vand.vx v9, v8, a0
+; CHECK-NEXT:    vsrl.vi v8, v8, 2
+; CHECK-NEXT:    vand.vx v8, v8, a0
+; CHECK-NEXT:    vadd.vv v8, v9, v8
+; CHECK-NEXT:    vsrl.vi v9, v8, 4
+; CHECK-NEXT:    vadd.vv v8, v8, v9
+; CHECK-NEXT:    vand.vi v8, v8, 15
+; CHECK-NEXT:    ret
+  %head = insertelement <2 x i1> poison, i1 true, i32 0
+  %m = shufflevector <2 x i1> %head, <2 x i1> poison, <2 x i32> zeroinitializer
+  %v = call <2 x i8> @llvm.vp.ctpop.v2i8(<2 x i8> %va, <2 x i1> %m, i32 %evl)
+  ret <2 x i8> %v
+}
+
+declare <4 x i8> @llvm.vp.ctpop.v4i8(<4 x i8>, <4 x i1>, i32)
+
+define <4 x i8> @vp_ctpop_v4i8(<4 x i8> %va, <4 x i1> %m, i32 zeroext %evl) {
+; CHECK-LABEL: vp_ctpop_v4i8:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli zero, a0, e8, mf4, ta, ma
+; CHECK-NEXT:    vsrl.vi v9, v8, 1, v0.t
+; CHECK-NEXT:    li a0, 85
+; CHECK-NEXT:    vand.vx v9, v9, a0, v0.t
+; CHECK-NEXT:    vsub.vv v8, v8, v9, v0.t
+; CHECK-NEXT:    li a0, 51
+; CHECK-NEXT:    vand.vx v9, v8, a0, v0.t
+; CHECK-NEXT:    vsrl.vi v8, v8, 2, v0.t
+; CHECK-NEXT:    vand.vx v8, v8, a0, v0.t
+; CHECK-NEXT:    vadd.vv v8, v9, v8, v0.t
+; CHECK-NEXT:    vsrl.vi v9, v8, 4, v0.t
+; CHECK-NEXT:    vadd.vv v8, v8, v9, v0.t
+; CHECK-NEXT:    vand.vi v8, v8, 15, v0.t
+; CHECK-NEXT:    ret
+  %v = call <4 x i8> @llvm.vp.ctpop.v4i8(<4 x i8> %va, <4 x i1> %m, i32 %evl)
+  ret <4 x i8> %v
+}
+
+define <4 x i8> @vp_ctpop_v4i8_unmasked(<4 x i8> %va, i32 zeroext %evl) {
+; CHECK-LABEL: vp_ctpop_v4i8_unmasked:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli zero, a0, e8, mf4, ta, ma
+; CHECK-NEXT:    vsrl.vi v9, v8, 1
+; CHECK-NEXT:    li a0, 85
+; CHECK-NEXT:    vand.vx v9, v9, a0
+; CHECK-NEXT:    vsub.vv v8, v8, v9
+; CHECK-NEXT:    li a0, 51
+; CHECK-NEXT:    vand.vx v9, v8, a0
+; CHECK-NEXT:    vsrl.vi v8, v8, 2
+; CHECK-NEXT:    vand.vx v8, v8, a0
+; CHECK-NEXT:    vadd.vv v8, v9, v8
+; CHECK-NEXT:    vsrl.vi v9, v8, 4
+; CHECK-NEXT:    vadd.vv v8, v8, v9
+; CHECK-NEXT:    vand.vi v8, v8, 15
+; CHECK-NEXT:    ret
+  %head = insertelement <4 x i1> poison, i1 true, i32 0
+  %m = shufflevector <4 x i1> %head, <4 x i1> poison, <4 x i32> zeroinitializer
+  %v = call <4 x i8> @llvm.vp.ctpop.v4i8(<4 x i8> %va, <4 x i1> %m, i32 %evl)
+  ret <4 x i8> %v
+}
+
+declare <8 x i8> @llvm.vp.ctpop.v8i8(<8 x i8>, <8 x i1>, i32)
+
+define <8 x i8> @vp_ctpop_v8i8(<8 x i8> %va, <8 x i1> %m, i32 zeroext %evl) {
+; CHECK-LABEL: vp_ctpop_v8i8:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli zero, a0, e8, mf2, ta, ma
+; CHECK-NEXT:    vsrl.vi v9, v8, 1, v0.t
+; CHECK-NEXT:    li a0, 85
+; CHECK-NEXT:    vand.vx v9, v9, a0, v0.t
+; CHECK-NEXT:    vsub.vv v8, v8, v9, v0.t
+; CHECK-NEXT:    li a0, 51
+; CHECK-NEXT:    vand.vx v9, v8, a0, v0.t
+; CHECK-NEXT:    vsrl.vi v8, v8, 2, v0.t
+; CHECK-NEXT:    vand.vx v8, v8, a0, v0.t
+; CHECK-NEXT:    vadd.vv v8, v9, v8, v0.t
+; CHECK-NEXT:    vsrl.vi v9, v8, 4, v0.t
+; CHECK-NEXT:    vadd.vv v8, v8, v9, v0.t
+; CHECK-NEXT:    vand.vi v8, v8, 15, v0.t
+; CHECK-NEXT:    ret
+  %v = call <8 x i8> @llvm.vp.ctpop.v8i8(<8 x i8> %va, <8 x i1> %m, i32 %evl)
+  ret <8 x i8> %v
+}
+
+define <8 x i8> @vp_ctpop_v8i8_unmasked(<8 x i8> %va, i32 zeroext %evl) {
+; CHECK-LABEL: vp_ctpop_v8i8_unmasked:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli zero, a0, e8, mf2, ta, ma
+; CHECK-NEXT:    vsrl.vi v9, v8, 1
+; CHECK-NEXT:    li a0, 85
+; CHECK-NEXT:    vand.vx v9, v9, a0
+; CHECK-NEXT:    vsub.vv v8, v8, v9
+; CHECK-NEXT:    li a0, 51
+; CHECK-NEXT:    vand.vx v9, v8, a0
+; CHECK-NEXT:    vsrl.vi v8, v8, 2
+; CHECK-NEXT:    vand.vx v8, v8, a0
+; CHECK-NEXT:    vadd.vv v8, v9, v8
+; CHECK-NEXT:    vsrl.vi v9, v8, 4
+; CHECK-NEXT:    vadd.vv v8, v8, v9
+; CHECK-NEXT:    vand.vi v8, v8, 15
+; CHECK-NEXT:    ret
+  %head = insertelement <8 x i1> poison, i1 true, i32 0
+  %m = shufflevector <8 x i1> %head, <8 x i1> poison, <8 x i32> zeroinitializer
+  %v = call <8 x i8> @llvm.vp.ctpop.v8i8(<8 x i8> %va, <8 x i1> %m, i32 %evl)
+  ret <8 x i8> %v
+}
+
+declare <16 x i8> @llvm.vp.ctpop.v16i8(<16 x i8>, <16 x i1>, i32)
+
+define <16 x i8> @vp_ctpop_v16i8(<16 x i8> %va, <16 x i1> %m, i32 zeroext %evl) {
+; CHECK-LABEL: vp_ctpop_v16i8:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli zero, a0, e8, m1, ta, ma
+; CHECK-NEXT:    vsrl.vi v9, v8, 1, v0.t
+; CHECK-NEXT:    li a0, 85
+; CHECK-NEXT:    vand.vx v9, v9, a0, v0.t
+; CHECK-NEXT:    vsub.vv v8, v8, v9, v0.t
+; CHECK-NEXT:    li a0, 51
+; CHECK-NEXT:    vand.vx v9, v8, a0, v0.t
+; CHECK-NEXT:    vsrl.vi v8, v8, 2, v0.t
+; CHECK-NEXT:    vand.vx v8, v8, a0, v0.t
+; CHECK-NEXT:    vadd.vv v8, v9, v8, v0.t
+; CHECK-NEXT:    vsrl.vi v9, v8, 4, v0.t
+; CHECK-NEXT:    vadd.vv v8, v8, v9, v0.t
+; CHECK-NEXT:    vand.vi v8, v8, 15, v0.t
+; CHECK-NEXT:    ret
+  %v = call <16 x i8> @llvm.vp.ctpop.v16i8(<16 x i8> %va, <16 x i1> %m, i32 %evl)
+  ret <16 x i8> %v
+}
+
+define <16 x i8> @vp_ctpop_v16i8_unmasked(<16 x i8> %va, i32 zeroext %evl) {
+; CHECK-LABEL: vp_ctpop_v16i8_unmasked:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli zero, a0, e8, m1, ta, ma
+; CHECK-NEXT:    vsrl.vi v9, v8, 1
+; CHECK-NEXT:    li a0, 85
+; CHECK-NEXT:    vand.vx v9, v9, a0
+; CHECK-NEXT:    vsub.vv v8, v8, v9
+; CHECK-NEXT:    li a0, 51
+; CHECK-NEXT:    vand.vx v9, v8, a0
+; CHECK-NEXT:    vsrl.vi v8, v8, 2
+; CHECK-NEXT:    vand.vx v8, v8, a0
+; CHECK-NEXT:    vadd.vv v8, v9, v8
+; CHECK-NEXT:    vsrl.vi v9, v8, 4
+; CHECK-NEXT:    vadd.vv v8, v8, v9
+; CHECK-NEXT:    vand.vi v8, v8, 15
+; CHECK-NEXT:    ret
+  %head = insertelement <16 x i1> poison, i1 true, i32 0
+  %m = shufflevector <16 x i1> %head, <16 x i1> poison, <16 x i32> zeroinitializer
+  %v = call <16 x i8> @llvm.vp.ctpop.v16i8(<16 x i8> %va, <16 x i1> %m, i32 %evl)
+  ret <16 x i8> %v
+}
+
+declare <2 x i16> @llvm.vp.ctpop.v2i16(<2 x i16>, <2 x i1>, i32)
+
+define <2 x i16> @vp_ctpop_v2i16(<2 x i16> %va, <2 x i1> %m, i32 zeroext %evl) {
+; RV32-LABEL: vp_ctpop_v2i16:
+; RV32:       # %bb.0:
+; RV32-NEXT:    vsetvli zero, a0, e16, mf4, ta, ma
+; RV32-NEXT:    vsrl.vi v9, v8, 1, v0.t
+; RV32-NEXT:    lui a0, 5
+; RV32-NEXT:    addi a0, a0, 1365
+; RV32-NEXT:    vand.vx v9, v9, a0, v0.t
+; RV32-NEXT:    vsub.vv v8, v8, v9, v0.t
+; RV32-NEXT:    lui a0, 3
+; RV32-NEXT:    addi a0, a0, 819
+; RV32-NEXT:    vand.vx v9, v8, a0, v0.t
+; RV32-NEXT:    vsrl.vi v8, v8, 2, v0.t
+; RV32-NEXT:    vand.vx v8, v8, a0, v0.t
+; RV32-NEXT:    vadd.vv v8, v9, v8, v0.t
+; RV32-NEXT:    vsrl.vi v9, v8, 4, v0.t
+; RV32-NEXT:    vadd.vv v8, v8, v9, v0.t
+; RV32-NEXT:    lui a0, 1
+; RV32-NEXT:    addi a0, a0, -241
+; RV32-NEXT:    vand.vx v8, v8, a0, v0.t
+; RV32-NEXT:    li a0, 257
+; RV32-NEXT:    vmul.vx v8, v8, a0, v0.t
+; RV32-NEXT:    vsrl.vi v8, v8, 8, v0.t
+; RV32-NEXT:    ret
+;
+; RV64-LABEL: vp_ctpop_v2i16:
+; RV64:       # %bb.0:
+; RV64-NEXT:    vsetvli zero, a0, e16, mf4, ta, ma
+; RV64-NEXT:    vsrl.vi v9, v8, 1, v0.t
+; RV64-NEXT:    lui a0, 5
+; RV64-NEXT:    addiw a0, a0, 1365
+; RV64-NEXT:    vand.vx v9, v9, a0, v0.t
+; RV64-NEXT:    vsub.vv v8, v8, v9, v0.t
+; RV64-NEXT:    lui a0, 3
+; RV64-NEXT:    addiw a0, a0, 819
+; RV64-NEXT:    vand.vx v9, v8, a0, v0.t
+; RV64-NEXT:    vsrl.vi v8, v8, 2, v0.t
+; RV64-NEXT:    vand.vx v8, v8, a0, v0.t
+; RV64-NEXT:    vadd.vv v8, v9, v8, v0.t
+; RV64-NEXT:    vsrl.vi v9, v8, 4, v0.t
+; RV64-NEXT:    vadd.vv v8, v8, v9, v0.t
+; RV64-NEXT:    lui a0, 1
+; RV64-NEXT:    addiw a0, a0, -241
+; RV64-NEXT:    vand.vx v8, v8, a0, v0.t
+; RV64-NEXT:    li a0, 257
+; RV64-NEXT:    vmul.vx v8, v8, a0, v0.t
+; RV64-NEXT:    vsrl.vi v8, v8, 8, v0.t
+; RV64-NEXT:    ret
+  %v = call <2 x i16> @llvm.vp.ctpop.v2i16(<2 x i16> %va, <2 x i1> %m, i32 %evl)
+  ret <2 x i16> %v
+}
+
+define <2 x i16> @vp_ctpop_v2i16_unmasked(<2 x i16> %va, i32 zeroext %evl) {
+; RV32-LABEL: vp_ctpop_v2i16_unmasked:
+; RV32:       # %bb.0:
+; RV32-NEXT:    vsetvli zero, a0, e16, mf4, ta, ma
+; RV32-NEXT:    vsrl.vi v9, v8, 1
+; RV32-NEXT:    lui a0, 5
+; RV32-NEXT:    addi a0, a0, 1365
+; RV32-NEXT:    vand.vx v9, v9, a0
+; RV32-NEXT:    vsub.vv v8, v8, v9
+; RV32-NEXT:    lui a0, 3
+; RV32-NEXT:    addi a0, a0, 819
+; RV32-NEXT:    vand.vx v9, v8, a0
+; RV32-NEXT:    vsrl.vi v8, v8, 2
+; RV32-NEXT:    vand.vx v8, v8, a0
+; RV32-NEXT:    vadd.vv v8, v9, v8
+; RV32-NEXT:    vsrl.vi v9, v8, 4
+; RV32-NEXT:    vadd.vv v8, v8, v9
+; RV32-NEXT:    lui a0, 1
+; RV32-NEXT:    addi a0, a0, -241
+; RV32-NEXT:    vand.vx v8, v8, a0
+; RV32-NEXT:    li a0, 257
+; RV32-NEXT:    vmul.vx v8, v8, a0
+; RV32-NEXT:    vsrl.vi v8, v8, 8
+; RV32-NEXT:    ret
+;
+; RV64-LABEL: vp_ctpop_v2i16_unmasked:
+; RV64:       # %bb.0:
+; RV64-NEXT:    vsetvli zero, a0, e16, mf4, ta, ma
+; RV64-NEXT:    vsrl.vi v9, v8, 1
+; RV64-NEXT:    lui a0, 5
+; RV64-NEXT:    addiw a0, a0, 1365
+; RV64-NEXT:    vand.vx v9, v9, a0
+; RV64-NEXT:    vsub.vv v8, v8, v9
+; RV64-NEXT:    lui a0, 3
+; RV64-NEXT:    addiw a0, a0, 819
+; RV64-NEXT:    vand.vx v9, v8, a0
+; RV64-NEXT:    vsrl.vi v8, v8, 2
+; RV64-NEXT:    vand.vx v8, v8, a0
+; RV64-NEXT:    vadd.vv v8, v9, v8
+; RV64-NEXT:    vsrl.vi v9, v8, 4
+; RV64-NEXT:    vadd.vv v8, v8, v9
+; RV64-NEXT:    lui a0, 1
+; RV64-NEXT:    addiw a0, a0, -241
+; RV64-NEXT:    vand.vx v8, v8, a0
+; RV64-NEXT:    li a0, 257
+; RV64-NEXT:    vmul.vx v8, v8, a0
+; RV64-NEXT:    vsrl.vi v8, v8, 8
+; RV64-NEXT:    ret
+  %head = insertelement <2 x i1> poison, i1 true, i32 0
+  %m = shufflevector <2 x i1> %head, <2 x i1> poison, <2 x i32> zeroinitializer
+  %v = call <2 x i16> @llvm.vp.ctpop.v2i16(<2 x i16> %va, <2 x i1> %m, i32 %evl)
+  ret <2 x i16> %v
+}
+
+declare <4 x i16> @llvm.vp.ctpop.v4i16(<4 x i16>, <4 x i1>, i32)
+
+define <4 x i16> @vp_ctpop_v4i16(<4 x i16> %va, <4 x i1> %m, i32 zeroext %evl) {
+; RV32-LABEL: vp_ctpop_v4i16:
+; RV32:       # %bb.0:
+; RV32-NEXT:    vsetvli zero, a0, e16, mf2, ta, ma
+; RV32-NEXT:    vsrl.vi v9, v8, 1, v0.t
+; RV32-NEXT:    lui a0, 5
+; RV32-NEXT:    addi a0, a0, 1365
+; RV32-NEXT:    vand.vx v9, v9, a0, v0.t
+; RV32-NEXT:    vsub.vv v8, v8, v9, v0.t
+; RV32-NEXT:    lui a0, 3
+; RV32-NEXT:    addi a0, a0, 819
+; RV32-NEXT:    vand.vx v9, v8, a0, v0.t
+; RV32-NEXT:    vsrl.vi v8, v8, 2, v0.t
+; RV32-NEXT:    vand.vx v8, v8, a0, v0.t
+; RV32-NEXT:    vadd.vv v8, v9, v8, v0.t
+; RV32-NEXT:    vsrl.vi v9, v8, 4, v0.t
+; RV32-NEXT:    vadd.vv v8, v8, v9, v0.t
+; RV32-NEXT:    lui a0, 1
+; RV32-NEXT:    addi a0, a0, -241
+; RV32-NEXT:    vand.vx v8, v8, a0, v0.t
+; RV32-NEXT:    li a0, 257
+; RV32-NEXT:    vmul.vx v8, v8, a0, v0.t
+; RV32-NEXT:    vsrl.vi v8, v8, 8, v0.t
+; RV32-NEXT:    ret
+;
+; RV64-LABEL: vp_ctpop_v4i16:
+; RV64:       # %bb.0:
+; RV64-NEXT:    vsetvli zero, a0, e16, mf2, ta, ma
+; RV64-NEXT:    vsrl.vi v9, v8, 1, v0.t
+; RV64-NEXT:    lui a0, 5
+; RV64-NEXT:    addiw a0, a0, 1365
+; RV64-NEXT:    vand.vx v9, v9, a0, v0.t
+; RV64-NEXT:    vsub.vv v8, v8, v9, v0.t
+; RV64-NEXT:    lui a0, 3
+; RV64-NEXT:    addiw a0, a0, 819
+; RV64-NEXT:    vand.vx v9, v8, a0, v0.t
+; RV64-NEXT:    vsrl.vi v8, v8, 2, v0.t
+; RV64-NEXT:    vand.vx v8, v8, a0, v0.t
+; RV64-NEXT:    vadd.vv v8, v9, v8, v0.t
+; RV64-NEXT:    vsrl.vi v9, v8, 4, v0.t
+; RV64-NEXT:    vadd.vv v8, v8, v9, v0.t
+; RV64-NEXT:    lui a0, 1
+; RV64-NEXT:    addiw a0, a0, -241
+; RV64-NEXT:    vand.vx v8, v8, a0, v0.t
+; RV64-NEXT:    li a0, 257
+; RV64-NEXT:    vmul.vx v8, v8, a0, v0.t
+; RV64-NEXT:    vsrl.vi v8, v8, 8, v0.t
+; RV64-NEXT:    ret
+  %v = call <4 x i16> @llvm.vp.ctpop.v4i16(<4 x i16> %va, <4 x i1> %m, i32 %evl)
+  ret <4 x i16> %v
+}
+
+define <4 x i16> @vp_ctpop_v4i16_unmasked(<4 x i16> %va, i32 zeroext %evl) {
+; RV32-LABEL: vp_ctpop_v4i16_unmasked:
+; RV32:       # %bb.0:
+; RV32-NEXT:    vsetvli zero, a0, e16, mf2, ta, ma
+; RV32-NEXT:    vsrl.vi v9, v8, 1
+; RV32-NEXT:    lui a0, 5
+; RV32-NEXT:    addi a0, a0, 1365
+; RV32-NEXT:    vand.vx v9, v9, a0
+; RV32-NEXT:    vsub.vv v8, v8, v9
+; RV32-NEXT:    lui a0, 3
+; RV32-NEXT:    addi a0, a0, 819
+; RV32-NEXT:    vand.vx v9, v8, a0
+; RV32-NEXT:    vsrl.vi v8, v8, 2
+; RV32-NEXT:    vand.vx v8, v8, a0
+; RV32-NEXT:    vadd.vv v8, v9, v8
+; RV32-NEXT:    vsrl.vi v9, v8, 4
+; RV32-NEXT:    vadd.vv v8, v8, v9
+; RV32-NEXT:    lui a0, 1
+; RV32-NEXT:    addi a0, a0, -241
+; RV32-NEXT:    vand.vx v8, v8, a0
+; RV32-NEXT:    li a0, 257
+; RV32-NEXT:    vmul.vx v8, v8, a0
+; RV32-NEXT:    vsrl.vi v8, v8, 8
+; RV32-NEXT:    ret
+;
+; RV64-LABEL: vp_ctpop_v4i16_unmasked:
+; RV64:       # %bb.0:
+; RV64-NEXT:    vsetvli zero, a0, e16, mf2, ta, ma
+; RV64-NEXT:    vsrl.vi v9, v8, 1
+; RV64-NEXT:    lui a0, 5
+; RV64-NEXT:    addiw a0, a0, 1365
+; RV64-NEXT:    vand.vx v9, v9, a0
+; RV64-NEXT:    vsub.vv v8, v8, v9
+; RV64-NEXT:    lui a0, 3
+; RV64-NEXT:    addiw a0, a0, 819
+; RV64-NEXT:    vand.vx v9, v8, a0
+; RV64-NEXT:    vsrl.vi v8, v8, 2
+; RV64-NEXT:    vand.vx v8, v8, a0
+; RV64-NEXT:    vadd.vv v8, v9, v8
+; RV64-NEXT:    vsrl.vi v9, v8, 4
+; RV64-NEXT:    vadd.vv v8, v8, v9
+; RV64-NEXT:    lui a0, 1
+; RV64-NEXT:    addiw a0, a0, -241
+; RV64-NEXT:    vand.vx v8, v8, a0
+; RV64-NEXT:    li a0, 257
+; RV64-NEXT:    vmul.vx v8, v8, a0
+; RV64-NEXT:    vsrl.vi v8, v8, 8
+; RV64-NEXT:    ret
+  %head = insertelement <4 x i1> poison, i1 true, i32 0
+  %m = shufflevector <4 x i1> %head, <4 x i1> poison, <4 x i32> zeroinitializer
+  %v = call <4 x i16> @llvm.vp.ctpop.v4i16(<4 x i16> %va, <4 x i1> %m, i32 %evl)
+  ret <4 x i16> %v
+}
+
+declare <8 x i16> @llvm.vp.ctpop.v8i16(<8 x i16>, <8 x i1>, i32)
+
+define <8 x i16> @vp_ctpop_v8i16(<8 x i16> %va, <8 x i1> %m, i32 zeroext %evl) {
+; RV32-LABEL: vp_ctpop_v8i16:
+; RV32:       # %bb.0:
+; RV32-NEXT:    vsetvli zero, a0, e16, m1, ta, ma
+; RV32-NEXT:    vsrl.vi v9, v8, 1, v0.t
+; RV32-NEXT:    lui a0, 5
+; RV32-NEXT:    addi a0, a0, 1365
+; RV32-NEXT:    vand.vx v9, v9, a0, v0.t
+; RV32-NEXT:    vsub.vv v8, v8, v9, v0.t
+; RV32-NEXT:    lui a0, 3
+; RV32-NEXT:    addi a0, a0, 819
+; RV32-NEXT:    vand.vx v9, v8, a0, v0.t
+; RV32-NEXT:    vsrl.vi v8, v8, 2, v0.t
+; RV32-NEXT:    vand.vx v8, v8, a0, v0.t
+; RV32-NEXT:    vadd.vv v8, v9, v8, v0.t
+; RV32-NEXT:    vsrl.vi v9, v8, 4, v0.t
+; RV32-NEXT:    vadd.vv v8, v8, v9, v0.t
+; RV32-NEXT:    lui a0, 1
+; RV32-NEXT:    addi a0, a0, -241
+; RV32-NEXT:    vand.vx v8, v8, a0, v0.t
+; RV32-NEXT:    li a0, 257
+; RV32-NEXT:    vmul.vx v8, v8, a0, v0.t
+; RV32-NEXT:    vsrl.vi v8, v8, 8, v0.t
+; RV32-NEXT:    ret
+;
+; RV64-LABEL: vp_ctpop_v8i16:
+; RV64:       # %bb.0:
+; RV64-NEXT:    vsetvli zero, a0, e16, m1, ta, ma
+; RV64-NEXT:    vsrl.vi v9, v8, 1, v0.t
+; RV64-NEXT:    lui a0, 5
+; RV64-NEXT:    addiw a0, a0, 1365
+; RV64-NEXT:    vand.vx v9, v9, a0, v0.t
+; RV64-NEXT:    vsub.vv v8, v8, v9, v0.t
+; RV64-NEXT:    lui a0, 3
+; RV64-NEXT:    addiw a0, a0, 819
+; RV64-NEXT:    vand.vx v9, v8, a0, v0.t
+; RV64-NEXT:    vsrl.vi v8, v8, 2, v0.t
+; RV64-NEXT:    vand.vx v8, v8, a0, v0.t
+; RV64-NEXT:    vadd.vv v8, v9, v8, v0.t
+; RV64-NEXT:    vsrl.vi v9, v8, 4, v0.t
+; RV64-NEXT:    vadd.vv v8, v8, v9, v0.t
+; RV64-NEXT:    lui a0, 1
+; RV64-NEXT:    addiw a0, a0, -241
+; RV64-NEXT:    vand.vx v8, v8, a0, v0.t
+; RV64-NEXT:    li a0, 257
+; RV64-NEXT:    vmul.vx v8, v8, a0, v0.t
+; RV64-NEXT:    vsrl.vi v8, v8, 8, v0.t
+; RV64-NEXT:    ret
+  %v = call <8 x i16> @llvm.vp.ctpop.v8i16(<8 x i16> %va, <8 x i1> %m, i32 %evl)
+  ret <8 x i16> %v
+}
+
+define <8 x i16> @vp_ctpop_v8i16_unmasked(<8 x i16> %va, i32 zeroext %evl) {
+; RV32-LABEL: vp_ctpop_v8i16_unmasked:
+; RV32:       # %bb.0:
+; RV32-NEXT:    vsetvli zero, a0, e16, m1, ta, ma
+; RV32-NEXT:    vsrl.vi v9, v8, 1
+; RV32-NEXT:    lui a0, 5
+; RV32-NEXT:    addi a0, a0, 1365
+; RV32-NEXT:    vand.vx v9, v9, a0
+; RV32-NEXT:    vsub.vv v8, v8, v9
+; RV32-NEXT:    lui a0, 3
+; RV32-NEXT:    addi a0, a0, 819
+; RV32-NEXT:    vand.vx v9, v8, a0
+; RV32-NEXT:    vsrl.vi v8, v8, 2
+; RV32-NEXT:    vand.vx v8, v8, a0
+; RV32-NEXT:    vadd.vv v8, v9, v8
+; RV32-NEXT:    vsrl.vi v9, v8, 4
+; RV32-NEXT:    vadd.vv v8, v8, v9
+; RV32-NEXT:    lui a0, 1
+; RV32-NEXT:    addi a0, a0, -241
+; RV32-NEXT:    vand.vx v8, v8, a0
+; RV32-NEXT:    li a0, 257
+; RV32-NEXT:    vmul.vx v8, v8, a0
+; RV32-NEXT:    vsrl.vi v8, v8, 8
+; RV32-NEXT:    ret
+;
+; RV64-LABEL: vp_ctpop_v8i16_unmasked:
+; RV64:       # %bb.0:
+; RV64-NEXT:    vsetvli zero, a0, e16, m1, ta, ma
+; RV64-NEXT:    vsrl.vi v9, v8, 1
+; RV64-NEXT:    lui a0, 5
+; RV64-NEXT:    addiw a0, a0, 1365
+; RV64-NEXT:    vand.vx v9, v9, a0
+; RV64-NEXT:    vsub.vv v8, v8, v9
+; RV64-NEXT:    lui a0, 3
+; RV64-NEXT:    addiw a0, a0, 819
+; RV64-NEXT:    vand.vx v9, v8, a0
+; RV64-NEXT:    vsrl.vi v8, v8, 2
+; RV64-NEXT:    vand.vx v8, v8, a0
+; RV64-NEXT:    vadd.vv v8, v9, v8
+; RV64-NEXT:    vsrl.vi v9, v8, 4
+; RV64-NEXT:    vadd.vv v8, v8, v9
+; RV64-NEXT:    lui a0, 1
+; RV64-NEXT:    addiw a0, a0, -241
+; RV64-NEXT:    vand.vx v8, v8, a0
+; RV64-NEXT:    li a0, 257
+; RV64-NEXT:    vmul.vx v8, v8, a0
+; RV64-NEXT:    vsrl.vi v8, v8, 8
+; RV64-NEXT:    ret
+  %head = insertelement <8 x i1> poison, i1 true, i32 0
+  %m = shufflevector <8 x i1> %head, <8 x i1> poison, <8 x i32> zeroinitializer
+  %v = call <8 x i16> @llvm.vp.ctpop.v8i16(<8 x i16> %va, <8 x i1> %m, i32 %evl)
+  ret <8 x i16> %v
+}
+
+declare <16 x i16> @llvm.vp.ctpop.v16i16(<16 x i16>, <16 x i1>, i32)
+
+define <16 x i16> @vp_ctpop_v16i16(<16 x i16> %va, <16 x i1> %m, i32 zeroext %evl) {
+; RV32-LABEL: vp_ctpop_v16i16:
+; RV32:       # %bb.0:
+; RV32-NEXT:    vsetvli zero, a0, e16, m2, ta, ma
+; RV32-NEXT:    vsrl.vi v10, v8, 1, v0.t
+; RV32-NEXT:    lui a0, 5
+; RV32-NEXT:    addi a0, a0, 1365
+; RV32-NEXT:    vand.vx v10, v10, a0, v0.t
+; RV32-NEXT:    vsub.vv v8, v8, v10, v0.t
+; RV32-NEXT:    lui a0, 3
+; RV32-NEXT:    addi a0, a0, 819
+; RV32-NEXT:    vand.vx v10, v8, a0, v0.t
+; RV32-NEXT:    vsrl.vi v8, v8, 2, v0.t
+; RV32-NEXT:    vand.vx v8, v8, a0, v0.t
+; RV32-NEXT:    vadd.vv v8, v10, v8, v0.t
+; RV32-NEXT:    vsrl.vi v10, v8, 4, v0.t
+; RV32-NEXT:    vadd.vv v8, v8, v10, v0.t
+; RV32-NEXT:    lui a0, 1
+; RV32-NEXT:    addi a0, a0, -241
+; RV32-NEXT:    vand.vx v8, v8, a0, v0.t
+; RV32-NEXT:    li a0, 257
+; RV32-NEXT:    vmul.vx v8, v8, a0, v0.t
+; RV32-NEXT:    vsrl.vi v8, v8, 8, v0.t
+; RV32-NEXT:    ret
+;
+; RV64-LABEL: vp_ctpop_v16i16:
+; RV64:       # %bb.0:
+; RV64-NEXT:    vsetvli zero, a0, e16, m2, ta, ma
+; RV64-NEXT:    vsrl.vi v10, v8, 1, v0.t
+; RV64-NEXT:    lui a0, 5
+; RV64-NEXT:    addiw a0, a0, 1365
+; RV64-NEXT:    vand.vx v10, v10, a0, v0.t
+; RV64-NEXT:    vsub.vv v8, v8, v10, v0.t
+; RV64-NEXT:    lui a0, 3
+; RV64-NEXT:    addiw a0, a0, 819
+; RV64-NEXT:    vand.vx v10, v8, a0, v0.t
+; RV64-NEXT:    vsrl.vi v8, v8, 2, v0.t
+; RV64-NEXT:    vand.vx v8, v8, a0, v0.t
+; RV64-NEXT:    vadd.vv v8, v10, v8, v0.t
+; RV64-NEXT:    vsrl.vi v10, v8, 4, v0.t
+; RV64-NEXT:    vadd.vv v8, v8, v10, v0.t
+; RV64-NEXT:    lui a0, 1
+; RV64-NEXT:    addiw a0, a0, -241
+; RV64-NEXT:    vand.vx v8, v8, a0, v0.t
+; RV64-NEXT:    li a0, 257
+; RV64-NEXT:    vmul.vx v8, v8, a0, v0.t
+; RV64-NEXT:    vsrl.vi v8, v8, 8, v0.t
+; RV64-NEXT:    ret
+  %v = call <16 x i16> @llvm.vp.ctpop.v16i16(<16 x i16> %va, <16 x i1> %m, i32 %evl)
+  ret <16 x i16> %v
+}
+
+define <16 x i16> @vp_ctpop_v16i16_unmasked(<16 x i16> %va, i32 zeroext %evl) {
+; RV32-LABEL: vp_ctpop_v16i16_unmasked:
+; RV32:       # %bb.0:
+; RV32-NEXT:    vsetvli zero, a0, e16, m2, ta, ma
+; RV32-NEXT:    vsrl.vi v10, v8, 1
+; RV32-NEXT:    lui a0, 5
+; RV32-NEXT:    addi a0, a0, 1365
+; RV32-NEXT:    vand.vx v10, v10, a0
+; RV32-NEXT:    vsub.vv v8, v8, v10
+; RV32-NEXT:    lui a0, 3
+; RV32-NEXT:    addi a0, a0, 819
+; RV32-NEXT:    vand.vx v10, v8, a0
+; RV32-NEXT:    vsrl.vi v8, v8, 2
+; RV32-NEXT:    vand.vx v8, v8, a0
+; RV32-NEXT:    vadd.vv v8, v10, v8
+; RV32-NEXT:    vsrl.vi v10, v8, 4
+; RV32-NEXT:    vadd.vv v8, v8, v10
+; RV32-NEXT:    lui a0, 1
+; RV32-NEXT:    addi a0, a0, -241
+; RV32-NEXT:    vand.vx v8, v8, a0
+; RV32-NEXT:    li a0, 257
+; RV32-NEXT:    vmul.vx v8, v8, a0
+; RV32-NEXT:    vsrl.vi v8, v8, 8
+; RV32-NEXT:    ret
+;
+; RV64-LABEL: vp_ctpop_v16i16_unmasked:
+; RV64:       # %bb.0:
+; RV64-NEXT:    vsetvli zero, a0, e16, m2, ta, ma
+; RV64-NEXT:    vsrl.vi v10, v8, 1
+; RV64-NEXT:    lui a0, 5
+; RV64-NEXT:    addiw a0, a0, 1365
+; RV64-NEXT:    vand.vx v10, v10, a0
+; RV64-NEXT:    vsub.vv v8, v8, v10
+; RV64-NEXT:    lui a0, 3
+; RV64-NEXT:    addiw a0, a0, 819
+; RV64-NEXT:    vand.vx v10, v8, a0
+; RV64-NEXT:    vsrl.vi v8, v8, 2
+; RV64-NEXT:    vand.vx v8, v8, a0
+; RV64-NEXT:    vadd.vv v8, v10, v8
+; RV64-NEXT:    vsrl.vi v10, v8, 4
+; RV64-NEXT:    vadd.vv v8, v8, v10
+; RV64-NEXT:    lui a0, 1
+; RV64-NEXT:    addiw a0, a0, -241
+; RV64-NEXT:    vand.vx v8, v8, a0
+; RV64-NEXT:    li a0, 257
+; RV64-NEXT:    vmul.vx v8, v8, a0
+; RV64-NEXT:    vsrl.vi v8, v8, 8
+; RV64-NEXT:    ret
+  %head = insertelement <16 x i1> poison, i1 true, i32 0
+  %m = shufflevector <16 x i1> %head, <16 x i1> poison, <16 x i32> zeroinitializer
+  %v = call <16 x i16> @llvm.vp.ctpop.v16i16(<16 x i16> %va, <16 x i1> %m, i32 %evl)
+  ret <16 x i16> %v
+}
+
+declare <2 x i32> @llvm.vp.ctpop.v2i32(<2 x i32>, <2 x i1>, i32)
+
+define <2 x i32> @vp_ctpop_v2i32(<2 x i32> %va, <2 x i1> %m, i32 zeroext %evl) {
+; RV32-LABEL: vp_ctpop_v2i32:
+; RV32:       # %bb.0:
+; RV32-NEXT:    vsetvli zero, a0, e32, mf2, ta, ma
+; RV32-NEXT:    vsrl.vi v9, v8, 1, v0.t
+; RV32-NEXT:    lui a0, 349525
+; RV32-NEXT:    addi a0, a0, 1365
+; RV32-NEXT:    vand.vx v9, v9, a0, v0.t
+; RV32-NEXT:    vsub.vv v8, v8, v9, v0.t
+; RV32-NEXT:    lui a0, 209715
+; RV32-NEXT:    addi a0, a0, 819
+; RV32-NEXT:    vand.vx v9, v8, a0, v0.t
+; RV32-NEXT:    vsrl.vi v8, v8, 2, v0.t
+; RV32-NEXT:    vand.vx v8, v8, a0, v0.t
+; RV32-NEXT:    vadd.vv v8, v9, v8, v0.t
+; RV32-NEXT:    vsrl.vi v9, v8, 4, v0.t
+; RV32-NEXT:    vadd.vv v8, v8, v9, v0.t
+; RV32-NEXT:    lui a0, 61681
+; RV32-NEXT:    addi a0, a0, -241
+; RV32-NEXT:    vand.vx v8, v8, a0, v0.t
+; RV32-NEXT:    lui a0, 4112
+; RV32-NEXT:    addi a0, a0, 257
+; RV32-NEXT:    vmul.vx v8, v8, a0, v0.t
+; RV32-NEXT:    vsrl.vi v8, v8, 24, v0.t
+; RV32-NEXT:    ret
+;
+; RV64-LABEL: vp_ctpop_v2i32:
+; RV64:       # %bb.0:
+; RV64-NEXT:    vsetvli zero, a0, e32, mf2, ta, ma
+; RV64-NEXT:    vsrl.vi v9, v8, 1, v0.t
+; RV64-NEXT:    lui a0, 349525
+; RV64-NEXT:    addiw a0, a0, 1365
+; RV64-NEXT:    vand.vx v9, v9, a0, v0.t
+; RV64-NEXT:    vsub.vv v8, v8, v9, v0.t
+; RV64-NEXT:    lui a0, 209715
+; RV64-NEXT:    addiw a0, a0, 819
+; RV64-NEXT:    vand.vx v9, v8, a0, v0.t
+; RV64-NEXT:    vsrl.vi v8, v8, 2, v0.t
+; RV64-NEXT:    vand.vx v8, v8, a0, v0.t
+; RV64-NEXT:    vadd.vv v8, v9, v8, v0.t
+; RV64-NEXT:    vsrl.vi v9, v8, 4, v0.t
+; RV64-NEXT:    vadd.vv v8, v8, v9, v0.t
+; RV64-NEXT:    lui a0, 61681
+; RV64-NEXT:    addiw a0, a0, -241
+; RV64-NEXT:    vand.vx v8, v8, a0, v0.t
+; RV64-NEXT:    lui a0, 4112
+; RV64-NEXT:    addiw a0, a0, 257
+; RV64-NEXT:    vmul.vx v8, v8, a0, v0.t
+; RV64-NEXT:    vsrl.vi v8, v8, 24, v0.t
+; RV64-NEXT:    ret
+  %v = call <2 x i32> @llvm.vp.ctpop.v2i32(<2 x i32> %va, <2 x i1> %m, i32 %evl)
+  ret <2 x i32> %v
+}
+
+define <2 x i32> @vp_ctpop_v2i32_unmasked(<2 x i32> %va, i32 zeroext %evl) {
+; RV32-LABEL: vp_ctpop_v2i32_unmasked:
+; RV32:       # %bb.0:
+; RV32-NEXT:    vsetvli zero, a0, e32, mf2, ta, ma
+; RV32-NEXT:    vsrl.vi v9, v8, 1
+; RV32-NEXT:    lui a0, 349525
+; RV32-NEXT:    addi a0, a0, 1365
+; RV32-NEXT:    vand.vx v9, v9, a0
+; RV32-NEXT:    vsub.vv v8, v8, v9
+; RV32-NEXT:    lui a0, 209715
+; RV32-NEXT:    addi a0, a0, 819
+; RV32-NEXT:    vand.vx v9, v8, a0
+; RV32-NEXT:    vsrl.vi v8, v8, 2
+; RV32-NEXT:    vand.vx v8, v8, a0
+; RV32-NEXT:    vadd.vv v8, v9, v8
+; RV32-NEXT:    vsrl.vi v9, v8, 4
+; RV32-NEXT:    vadd.vv v8, v8, v9
+; RV32-NEXT:    lui a0, 61681
+; RV32-NEXT:    addi a0, a0, -241
+; RV32-NEXT:    vand.vx v8, v8, a0
+; RV32-NEXT:    lui a0, 4112
+; RV32-NEXT:    addi a0, a0, 257
+; RV32-NEXT:    vmul.vx v8, v8, a0
+; RV32-NEXT:    vsrl.vi v8, v8, 24
+; RV32-NEXT:    ret
+;
+; RV64-LABEL: vp_ctpop_v2i32_unmasked:
+; RV64:       # %bb.0:
+; RV64-NEXT:    vsetvli zero, a0, e32, mf2, ta, ma
+; RV64-NEXT:    vsrl.vi v9, v8, 1
+; RV64-NEXT:    lui a0, 349525
+; RV64-NEXT:    addiw a0, a0, 1365
+; RV64-NEXT:    vand.vx v9, v9, a0
+; RV64-NEXT:    vsub.vv v8, v8, v9
+; RV64-NEXT:    lui a0, 209715
+; RV64-NEXT:    addiw a0, a0, 819
+; RV64-NEXT:    vand.vx v9, v8, a0
+; RV64-NEXT:    vsrl.vi v8, v8, 2
+; RV64-NEXT:    vand.vx v8, v8, a0
+; RV64-NEXT:    vadd.vv v8, v9, v8
+; RV64-NEXT:    vsrl.vi v9, v8, 4
+; RV64-NEXT:    vadd.vv v8, v8, v9
+; RV64-NEXT:    lui a0, 61681
+; RV64-NEXT:    addiw a0, a0, -241
+; RV64-NEXT:    vand.vx v8, v8, a0
+; RV64-NEXT:    lui a0, 4112
+; RV64-NEXT:    addiw a0, a0, 257
+; RV64-NEXT:    vmul.vx v8, v8, a0
+; RV64-NEXT:    vsrl.vi v8, v8, 24
+; RV64-NEXT:    ret
+  %head = insertelement <2 x i1> poison, i1 true, i32 0
+  %m = shufflevector <2 x i1> %head, <2 x i1> poison, <2 x i32> zeroinitializer
+  %v = call <2 x i32> @llvm.vp.ctpop.v2i32(<2 x i32> %va, <2 x i1> %m, i32 %evl)
+  ret <2 x i32> %v
+}
+
+declare <4 x i32> @llvm.vp.ctpop.v4i32(<4 x i32>, <4 x i1>, i32)
+
+define <4 x i32> @vp_ctpop_v4i32(<4 x i32> %va, <4 x i1> %m, i32 zeroext %evl) {
+; RV32-LABEL: vp_ctpop_v4i32:
+; RV32:       # %bb.0:
+; RV32-NEXT:    vsetvli zero, a0, e32, m1, ta, ma
+; RV32-NEXT:    vsrl.vi v9, v8, 1, v0.t
+; RV32-NEXT:    lui a0, 349525
+; RV32-NEXT:    addi a0, a0, 1365
+; RV32-NEXT:    vand.vx v9, v9, a0, v0.t
+; RV32-NEXT:    vsub.vv v8, v8, v9, v0.t
+; RV32-NEXT:    lui a0, 209715
+; RV32-NEXT:    addi a0, a0, 819
+; RV32-NEXT:    vand.vx v9, v8, a0, v0.t
+; RV32-NEXT:    vsrl.vi v8, v8, 2, v0.t
+; RV32-NEXT:    vand.vx v8, v8, a0, v0.t
+; RV32-NEXT:    vadd.vv v8, v9, v8, v0.t
+; RV32-NEXT:    vsrl.vi v9, v8, 4, v0.t
+; RV32-NEXT:    vadd.vv v8, v8, v9, v0.t
+; RV32-NEXT:    lui a0, 61681
+; RV32-NEXT:    addi a0, a0, -241
+; RV32-NEXT:    vand.vx v8, v8, a0, v0.t
+; RV32-NEXT:    lui a0, 4112
+; RV32-NEXT:    addi a0, a0, 257
+; RV32-NEXT:    vmul.vx v8, v8, a0, v0.t
+; RV32-NEXT:    vsrl.vi v8, v8, 24, v0.t
+; RV32-NEXT:    ret
+;
+; RV64-LABEL: vp_ctpop_v4i32:
+; RV64:       # %bb.0:
+; RV64-NEXT:    vsetvli zero, a0, e32, m1, ta, ma
+; RV64-NEXT:    vsrl.vi v9, v8, 1, v0.t
+; RV64-NEXT:    lui a0, 349525
+; RV64-NEXT:    addiw a0, a0, 1365
+; RV64-NEXT:    vand.vx v9, v9, a0, v0.t
+; RV64-NEXT:    vsub.vv v8, v8, v9, v0.t
+; RV64-NEXT:    lui a0, 209715
+; RV64-NEXT:    addiw a0, a0, 819
+; RV64-NEXT:    vand.vx v9, v8, a0, v0.t
+; RV64-NEXT:    vsrl.vi v8, v8, 2, v0.t
+; RV64-NEXT:    vand.vx v8, v8, a0, v0.t
+; RV64-NEXT:    vadd.vv v8, v9, v8, v0.t
+; RV64-NEXT:    vsrl.vi v9, v8, 4, v0.t
+; RV64-NEXT:    vadd.vv v8, v8, v9, v0.t
+; RV64-NEXT:    lui a0, 61681
+; RV64-NEXT:    addiw a0, a0, -241
+; RV64-NEXT:    vand.vx v8, v8, a0, v0.t
+; RV64-NEXT:    lui a0, 4112
+; RV64-NEXT:    addiw a0, a0, 257
+; RV64-NEXT:    vmul.vx v8, v8, a0, v0.t
+; RV64-NEXT:    vsrl.vi v8, v8, 24, v0.t
+; RV64-NEXT:    ret
+  %v = call <4 x i32> @llvm.vp.ctpop.v4i32(<4 x i32> %va, <4 x i1> %m, i32 %evl)
+  ret <4 x i32> %v
+}
+
+define <4 x i32> @vp_ctpop_v4i32_unmasked(<4 x i32> %va, i32 zeroext %evl) {
+; RV32-LABEL: vp_ctpop_v4i32_unmasked:
+; RV32:       # %bb.0:
+; RV32-NEXT:    vsetvli zero, a0, e32, m1, ta, ma
+; RV32-NEXT:    vsrl.vi v9, v8, 1
+; RV32-NEXT:    lui a0, 349525
+; RV32-NEXT:    addi a0, a0, 1365
+; RV32-NEXT:    vand.vx v9, v9, a0
+; RV32-NEXT:    vsub.vv v8, v8, v9
+; RV32-NEXT:    lui a0, 209715
+; RV32-NEXT:    addi a0, a0, 819
+; RV32-NEXT:    vand.vx v9, v8, a0
+; RV32-NEXT:    vsrl.vi v8, v8, 2
+; RV32-NEXT:    vand.vx v8, v8, a0
+; RV32-NEXT:    vadd.vv v8, v9, v8
+; RV32-NEXT:    vsrl.vi v9, v8, 4
+; RV32-NEXT:    vadd.vv v8, v8, v9
+; RV32-NEXT:    lui a0, 61681
+; RV32-NEXT:    addi a0, a0, -241
+; RV32-NEXT:    vand.vx v8, v8, a0
+; RV32-NEXT:    lui a0, 4112
+; RV32-NEXT:    addi a0, a0, 257
+; RV32-NEXT:    vmul.vx v8, v8, a0
+; RV32-NEXT:    vsrl.vi v8, v8, 24
+; RV32-NEXT:    ret
+;
+; RV64-LABEL: vp_ctpop_v4i32_unmasked:
+; RV64:       # %bb.0:
+; RV64-NEXT:    vsetvli zero, a0, e32, m1, ta, ma
+; RV64-NEXT:    vsrl.vi v9, v8, 1
+; RV64-NEXT:    lui a0, 349525
+; RV64-NEXT:    addiw a0, a0, 1365
+; RV64-NEXT:    vand.vx v9, v9, a0
+; RV64-NEXT:    vsub.vv v8, v8, v9
+; RV64-NEXT:    lui a0, 209715
+; RV64-NEXT:    addiw a0, a0, 819
+; RV64-NEXT:    vand.vx v9, v8, a0
+; RV64-NEXT:    vsrl.vi v8, v8, 2
+; RV64-NEXT:    vand.vx v8, v8, a0
+; RV64-NEXT:    vadd.vv v8, v9, v8
+; RV64-NEXT:    vsrl.vi v9, v8, 4
+; RV64-NEXT:    vadd.vv v8, v8, v9
+; RV64-NEXT:    lui a0, 61681
+; RV64-NEXT:    addiw a0, a0, -241
+; RV64-NEXT:    vand.vx v8, v8, a0
+; RV64-NEXT:    lui a0, 4112
+; RV64-NEXT:    addiw a0, a0, 257
+; RV64-NEXT:    vmul.vx v8, v8, a0
+; RV64-NEXT:    vsrl.vi v8, v8, 24
+; RV64-NEXT:    ret
+  %head = insertelement <4 x i1> poison, i1 true, i32 0
+  %m = shufflevector <4 x i1> %head, <4 x i1> poison, <4 x i32> zeroinitializer
+  %v = call <4 x i32> @llvm.vp.ctpop.v4i32(<4 x i32> %va, <4 x i1> %m, i32 %evl)
+  ret <4 x i32> %v
+}
+
+declare <8 x i32> @llvm.vp.ctpop.v8i32(<8 x i32>, <8 x i1>, i32)
+
+define <8 x i32> @vp_ctpop_v8i32(<8 x i32> %va, <8 x i1> %m, i32 zeroext %evl) {
+; RV32-LABEL: vp_ctpop_v8i32:
+; RV32:       # %bb.0:
+; RV32-NEXT:    vsetvli zero, a0, e32, m2, ta, ma
+; RV32-NEXT:    vsrl.vi v10, v8, 1, v0.t
+; RV32-NEXT:    lui a0, 349525
+; RV32-NEXT:    addi a0, a0, 1365
+; RV32-NEXT:    vand.vx v10, v10, a0, v0.t
+; RV32-NEXT:    vsub.vv v8, v8, v10, v0.t
+; RV32-NEXT:    lui a0, 209715
+; RV32-NEXT:    addi a0, a0, 819
+; RV32-NEXT:    vand.vx v10, v8, a0, v0.t
+; RV32-NEXT:    vsrl.vi v8, v8, 2, v0.t
+; RV32-NEXT:    vand.vx v8, v8, a0, v0.t
+; RV32-NEXT:    vadd.vv v8, v10, v8, v0.t
+; RV32-NEXT:    vsrl.vi v10, v8, 4, v0.t
+; RV32-NEXT:    vadd.vv v8, v8, v10, v0.t
+; RV32-NEXT:    lui a0, 61681
+; RV32-NEXT:    addi a0, a0, -241
+; RV32-NEXT:    vand.vx v8, v8, a0, v0.t
+; RV32-NEXT:    lui a0, 4112
+; RV32-NEXT:    addi a0, a0, 257
+; RV32-NEXT:    vmul.vx v8, v8, a0, v0.t
+; RV32-NEXT:    vsrl.vi v8, v8, 24, v0.t
+; RV32-NEXT:    ret
+;
+; RV64-LABEL: vp_ctpop_v8i32:
+; RV64:       # %bb.0:
+; RV64-NEXT:    vsetvli zero, a0, e32, m2, ta, ma
+; RV64-NEXT:    vsrl.vi v10, v8, 1, v0.t
+; RV64-NEXT:    lui a0, 349525
+; RV64-NEXT:    addiw a0, a0, 1365
+; RV64-NEXT:    vand.vx v10, v10, a0, v0.t
+; RV64-NEXT:    vsub.vv v8, v8, v10, v0.t
+; RV64-NEXT:    lui a0, 209715
+; RV64-NEXT:    addiw a0, a0, 819
+; RV64-NEXT:    vand.vx v10, v8, a0, v0.t
+; RV64-NEXT:    vsrl.vi v8, v8, 2, v0.t
+; RV64-NEXT:    vand.vx v8, v8, a0, v0.t
+; RV64-NEXT:    vadd.vv v8, v10, v8, v0.t
+; RV64-NEXT:    vsrl.vi v10, v8, 4, v0.t
+; RV64-NEXT:    vadd.vv v8, v8, v10, v0.t
+; RV64-NEXT:    lui a0, 61681
+; RV64-NEXT:    addiw a0, a0, -241
+; RV64-NEXT:    vand.vx v8, v8, a0, v0.t
+; RV64-NEXT:    lui a0, 4112
+; RV64-NEXT:    addiw a0, a0, 257
+; RV64-NEXT:    vmul.vx v8, v8, a0, v0.t
+; RV64-NEXT:    vsrl.vi v8, v8, 24, v0.t
+; RV64-NEXT:    ret
+  %v = call <8 x i32> @llvm.vp.ctpop.v8i32(<8 x i32> %va, <8 x i1> %m, i32 %evl)
+  ret <8 x i32> %v
+}
+
+define <8 x i32> @vp_ctpop_v8i32_unmasked(<8 x i32> %va, i32 zeroext %evl) {
+; RV32-LABEL: vp_ctpop_v8i32_unmasked:
+; RV32:       # %bb.0:
+; RV32-NEXT:    vsetvli zero, a0, e32, m2, ta, ma
+; RV32-NEXT:    vsrl.vi v10, v8, 1
+; RV32-NEXT:    lui a0, 349525
+; RV32-NEXT:    addi a0, a0, 1365
+; RV32-NEXT:    vand.vx v10, v10, a0
+; RV32-NEXT:    vsub.vv v8, v8, v10
+; RV32-NEXT:    lui a0, 209715
+; RV32-NEXT:    addi a0, a0, 819
+; RV32-NEXT:    vand.vx v10, v8, a0
+; RV32-NEXT:    vsrl.vi v8, v8, 2
+; RV32-NEXT:    vand.vx v8, v8, a0
+; RV32-NEXT:    vadd.vv v8, v10, v8
+; RV32-NEXT:    vsrl.vi v10, v8, 4
+; RV32-NEXT:    vadd.vv v8, v8, v10
+; RV32-NEXT:    lui a0, 61681
+; RV32-NEXT:    addi a0, a0, -241
+; RV32-NEXT:    vand.vx v8, v8, a0
+; RV32-NEXT:    lui a0, 4112
+; RV32-NEXT:    addi a0, a0, 257
+; RV32-NEXT:    vmul.vx v8, v8, a0
+; RV32-NEXT:    vsrl.vi v8, v8, 24
+; RV32-NEXT:    ret
+;
+; RV64-LABEL: vp_ctpop_v8i32_unmasked:
+; RV64:       # %bb.0:
+; RV64-NEXT:    vsetvli zero, a0, e32, m2, ta, ma
+; RV64-NEXT:    vsrl.vi v10, v8, 1
+; RV64-NEXT:    lui a0, 349525
+; RV64-NEXT:    addiw a0, a0, 1365
+; RV64-NEXT:    vand.vx v10, v10, a0
+; RV64-NEXT:    vsub.vv v8, v8, v10
+; RV64-NEXT:    lui a0, 209715
+; RV64-NEXT:    addiw a0, a0, 819
+; RV64-NEXT:    vand.vx v10, v8, a0
+; RV64-NEXT:    vsrl.vi v8, v8, 2
+; RV64-NEXT:    vand.vx v8, v8, a0
+; RV64-NEXT:    vadd.vv v8, v10, v8
+; RV64-NEXT:    vsrl.vi v10, v8, 4
+; RV64-NEXT:    vadd.vv v8, v8, v10
+; RV64-NEXT:    lui a0, 61681
+; RV64-NEXT:    addiw a0, a0, -241
+; RV64-NEXT:    vand.vx v8, v8, a0
+; RV64-NEXT:    lui a0, 4112
+; RV64-NEXT:    addiw a0, a0, 257
+; RV64-NEXT:    vmul.vx v8, v8, a0
+; RV64-NEXT:    vsrl.vi v8, v8, 24
+; RV64-NEXT:    ret
+  %head = insertelement <8 x i1> poison, i1 true, i32 0
+  %m = shufflevector <8 x i1> %head, <8 x i1> poison, <8 x i32> zeroinitializer
+  %v = call <8 x i32> @llvm.vp.ctpop.v8i32(<8 x i32> %va, <8 x i1> %m, i32 %evl)
+  ret <8 x i32> %v
+}
+
+declare <16 x i32> @llvm.vp.ctpop.v16i32(<16 x i32>, <16 x i1>, i32)
+
+define <16 x i32> @vp_ctpop_v16i32(<16 x i32> %va, <16 x i1> %m, i32 zeroext %evl) {
+; RV32-LABEL: vp_ctpop_v16i32:
+; RV32:       # %bb.0:
+; RV32-NEXT:    vsetvli zero, a0, e32, m4, ta, ma
+; RV32-NEXT:    vsrl.vi v12, v8, 1, v0.t
+; RV32-NEXT:    lui a0, 349525
+; RV32-NEXT:    addi a0, a0, 1365
+; RV32-NEXT:    vand.vx v12, v12, a0, v0.t
+; RV32-NEXT:    vsub.vv v8, v8, v12, v0.t
+; RV32-NEXT:    lui a0, 209715
+; RV32-NEXT:    addi a0, a0, 819
+; RV32-NEXT:    vand.vx v12, v8, a0, v0.t
+; RV32-NEXT:    vsrl.vi v8, v8, 2, v0.t
+; RV32-NEXT:    vand.vx v8, v8, a0, v0.t
+; RV32-NEXT:    vadd.vv v8, v12, v8, v0.t
+; RV32-NEXT:    vsrl.vi v12, v8, 4, v0.t
+; RV32-NEXT:    vadd.vv v8, v8, v12, v0.t
+; RV32-NEXT:    lui a0, 61681
+; RV32-NEXT:    addi a0, a0, -241
+; RV32-NEXT:    vand.vx v8, v8, a0, v0.t
+; RV32-NEXT:    lui a0, 4112
+; RV32-NEXT:    addi a0, a0, 257
+; RV32-NEXT:    vmul.vx v8, v8, a0, v0.t
+; RV32-NEXT:    vsrl.vi v8, v8, 24, v0.t
+; RV32-NEXT:    ret
+;
+; RV64-LABEL: vp_ctpop_v16i32:
+; RV64:       # %bb.0:
+; RV64-NEXT:    vsetvli zero, a0, e32, m4, ta, ma
+; RV64-NEXT:    vsrl.vi v12, v8, 1, v0.t
+; RV64-NEXT:    lui a0, 349525
+; RV64-NEXT:    addiw a0, a0, 1365
+; RV64-NEXT:    vand.vx v12, v12, a0, v0.t
+; RV64-NEXT:    vsub.vv v8, v8, v12, v0.t
+; RV64-NEXT:    lui a0, 209715
+; RV64-NEXT:    addiw a0, a0, 819
+; RV64-NEXT:    vand.vx v12, v8, a0, v0.t
+; RV64-NEXT:    vsrl.vi v8, v8, 2, v0.t
+; RV64-NEXT:    vand.vx v8, v8, a0, v0.t
+; RV64-NEXT:    vadd.vv v8, v12, v8, v0.t
+; RV64-NEXT:    vsrl.vi v12, v8, 4, v0.t
+; RV64-NEXT:    vadd.vv v8, v8, v12, v0.t
+; RV64-NEXT:    lui a0, 61681
+; RV64-NEXT:    addiw a0, a0, -241
+; RV64-NEXT:    vand.vx v8, v8, a0, v0.t
+; RV64-NEXT:    lui a0, 4112
+; RV64-NEXT:    addiw a0, a0, 257
+; RV64-NEXT:    vmul.vx v8, v8, a0, v0.t
+; RV64-NEXT:    vsrl.vi v8, v8, 24, v0.t
+; RV64-NEXT:    ret
+  %v = call <16 x i32> @llvm.vp.ctpop.v16i32(<16 x i32> %va, <16 x i1> %m, i32 %evl)
+  ret <16 x i32> %v
+}
+
+define <16 x i32> @vp_ctpop_v16i32_unmasked(<16 x i32> %va, i32 zeroext %evl) {
+; RV32-LABEL: vp_ctpop_v16i32_unmasked:
+; RV32:       # %bb.0:
+; RV32-NEXT:    vsetvli zero, a0, e32, m4, ta, ma
+; RV32-NEXT:    vsrl.vi v12, v8, 1
+; RV32-NEXT:    lui a0, 349525
+; RV32-NEXT:    addi a0, a0, 1365
+; RV32-NEXT:    vand.vx v12, v12, a0
+; RV32-NEXT:    vsub.vv v8, v8, v12
+; RV32-NEXT:    lui a0, 209715
+; RV32-NEXT:    addi a0, a0, 819
+; RV32-NEXT:    vand.vx v12, v8, a0
+; RV32-NEXT:    vsrl.vi v8, v8, 2
+; RV32-NEXT:    vand.vx v8, v8, a0
+; RV32-NEXT:    vadd.vv v8, v12, v8
+; RV32-NEXT:    vsrl.vi v12, v8, 4
+; RV32-NEXT:    vadd.vv v8, v8, v12
+; RV32-NEXT:    lui a0, 61681
+; RV32-NEXT:    addi a0, a0, -241
+; RV32-NEXT:    vand.vx v8, v8, a0
+; RV32-NEXT:    lui a0, 4112
+; RV32-NEXT:    addi a0, a0, 257
+; RV32-NEXT:    vmul.vx v8, v8, a0
+; RV32-NEXT:    vsrl.vi v8, v8, 24
+; RV32-NEXT:    ret
+;
+; RV64-LABEL: vp_ctpop_v16i32_unmasked:
+; RV64:       # %bb.0:
+; RV64-NEXT:    vsetvli zero, a0, e32, m4, ta, ma
+; RV64-NEXT:    vsrl.vi v12, v8, 1
+; RV64-NEXT:    lui a0, 349525
+; RV64-NEXT:    addiw a0, a0, 1365
+; RV64-NEXT:    vand.vx v12, v12, a0
+; RV64-NEXT:    vsub.vv v8, v8, v12
+; RV64-NEXT:    lui a0, 209715
+; RV64-NEXT:    addiw a0, a0, 819
+; RV64-NEXT:    vand.vx v12, v8, a0
+; RV64-NEXT:    vsrl.vi v8, v8, 2
+; RV64-NEXT:    vand.vx v8, v8, a0
+; RV64-NEXT:    vadd.vv v8, v12, v8
+; RV64-NEXT:    vsrl.vi v12, v8, 4
+; RV64-NEXT:    vadd.vv v8, v8, v12
+; RV64-NEXT:    lui a0, 61681
+; RV64-NEXT:    addiw a0, a0, -241
+; RV64-NEXT:    vand.vx v8, v8, a0
+; RV64-NEXT:    lui a0, 4112
+; RV64-NEXT:    addiw a0, a0, 257
+; RV64-NEXT:    vmul.vx v8, v8, a0
+; RV64-NEXT:    vsrl.vi v8, v8, 24
+; RV64-NEXT:    ret
+  %head = insertelement <16 x i1> poison, i1 true, i32 0
+  %m = shufflevector <16 x i1> %head, <16 x i1> poison, <16 x i32> zeroinitializer
+  %v = call <16 x i32> @llvm.vp.ctpop.v16i32(<16 x i32> %va, <16 x i1> %m, i32 %evl)
+  ret <16 x i32> %v
+}
+
+declare <2 x i64> @llvm.vp.ctpop.v2i64(<2 x i64>, <2 x i1>, i32)
+
+define <2 x i64> @vp_ctpop_v2i64(<2 x i64> %va, <2 x i1> %m, i32 zeroext %evl) {
+; RV32-LABEL: vp_ctpop_v2i64:
+; RV32:       # %bb.0:
+; RV32-NEXT:    vsetvli zero, a0, e64, m1, ta, ma
+; RV32-NEXT:    vsrl.vi v9, v8, 1, v0.t
+; RV32-NEXT:    lui a1, 349525
+; RV32-NEXT:    addi a1, a1, 1365
+; RV32-NEXT:    vsetivli zero, 4, e32, m1, ta, ma
+; RV32-NEXT:    vmv.v.x v10, a1
+; RV32-NEXT:    vsetvli zero, a0, e64, m1, ta, ma
+; RV32-NEXT:    vand.vv v9, v9, v10, v0.t
+; RV32-NEXT:    vsub.vv v8, v8, v9, v0.t
+; RV32-NEXT:    lui a1, 209715
+; RV32-NEXT:    addi a1, a1, 819
+; RV32-NEXT:    vsetivli zero, 4, e32, m1, ta, ma
+; RV32-NEXT:    vmv.v.x v9, a1
+; RV32-NEXT:    vsetvli zero, a0, e64, m1, ta, ma
+; RV32-NEXT:    vand.vv v10, v8, v9, v0.t
+; RV32-NEXT:    vsrl.vi v8, v8, 2, v0.t
+; RV32-NEXT:    vand.vv v8, v8, v9, v0.t
+; RV32-NEXT:    vadd.vv v8, v10, v8, v0.t
+; RV32-NEXT:    vsrl.vi v9, v8, 4, v0.t
+; RV32-NEXT:    vadd.vv v8, v8, v9, v0.t
+; RV32-NEXT:    lui a1, 61681
+; RV32-NEXT:    addi a1, a1, -241
+; RV32-NEXT:    vsetivli zero, 4, e32, m1, ta, ma
+; RV32-NEXT:    vmv.v.x v9, a1
+; RV32-NEXT:    vsetvli zero, a0, e64, m1, ta, ma
+; RV32-NEXT:    vand.vv v8, v8, v9, v0.t
+; RV32-NEXT:    lui a1, 4112
+; RV32-NEXT:    addi a1, a1, 257
+; RV32-NEXT:    vsetivli zero, 4, e32, m1, ta, ma
+; RV32-NEXT:    vmv.v.x v9, a1
+; RV32-NEXT:    vsetvli zero, a0, e64, m1, ta, ma
+; RV32-NEXT:    vmul.vv v8, v8, v9, v0.t
+; RV32-NEXT:    li a0, 56
+; RV32-NEXT:    vsrl.vx v8, v8, a0, v0.t
+; RV32-NEXT:    ret
+;
+; RV64-LABEL: vp_ctpop_v2i64:
+; RV64:       # %bb.0:
+; RV64-NEXT:    vsetvli zero, a0, e64, m1, ta, ma
+; RV64-NEXT:    lui a0, %hi(.LCPI24_0)
+; RV64-NEXT:    ld a0, %lo(.LCPI24_0)(a0)
+; RV64-NEXT:    lui a1, %hi(.LCPI24_1)
+; RV64-NEXT:    ld a1, %lo(.LCPI24_1)(a1)
+; RV64-NEXT:    vsrl.vi v9, v8, 1, v0.t
+; RV64-NEXT:    vand.vx v9, v9, a0, v0.t
+; RV64-NEXT:    vsub.vv v8, v8, v9, v0.t
+; RV64-NEXT:    vand.vx v9, v8, a1, v0.t
+; RV64-NEXT:    vsrl.vi v8, v8, 2, v0.t
+; RV64-NEXT:    vand.vx v8, v8, a1, v0.t
+; RV64-NEXT:    vadd.vv v8, v9, v8, v0.t
+; RV64-NEXT:    lui a0, %hi(.LCPI24_2)
+; RV64-NEXT:    ld a0, %lo(.LCPI24_2)(a0)
+; RV64-NEXT:    lui a1, %hi(.LCPI24_3)
+; RV64-NEXT:    ld a1, %lo(.LCPI24_3)(a1)
+; RV64-NEXT:    vsrl.vi v9, v8, 4, v0.t
+; RV64-NEXT:    vadd.vv v8, v8, v9, v0.t
+; RV64-NEXT:    vand.vx v8, v8, a0, v0.t
+; RV64-NEXT:    vmul.vx v8, v8, a1, v0.t
+; RV64-NEXT:    li a0, 56
+; RV64-NEXT:    vsrl.vx v8, v8, a0, v0.t
+; RV64-NEXT:    ret
+  %v = call <2 x i64> @llvm.vp.ctpop.v2i64(<2 x i64> %va, <2 x i1> %m, i32 %evl)
+  ret <2 x i64> %v
+}
+
+define <2 x i64> @vp_ctpop_v2i64_unmasked(<2 x i64> %va, i32 zeroext %evl) {
+; RV32-LABEL: vp_ctpop_v2i64_unmasked:
+; RV32:       # %bb.0:
+; RV32-NEXT:    vsetvli zero, a0, e64, m1, ta, ma
+; RV32-NEXT:    vsrl.vi v9, v8, 1
+; RV32-NEXT:    lui a1, 349525
+; RV32-NEXT:    addi a1, a1, 1365
+; RV32-NEXT:    vsetivli zero, 4, e32, m1, ta, ma
+; RV32-NEXT:    vmv.v.x v10, a1
+; RV32-NEXT:    vsetvli zero, a0, e64, m1, ta, ma
+; RV32-NEXT:    vand.vv v9, v9, v10
+; RV32-NEXT:    vsub.vv v8, v8, v9
+; RV32-NEXT:    lui a1, 209715
+; RV32-NEXT:    addi a1, a1, 819
+; RV32-NEXT:    vsetivli zero, 4, e32, m1, ta, ma
+; RV32-NEXT:    vmv.v.x v9, a1
+; RV32-NEXT:    vsetvli zero, a0, e64, m1, ta, ma
+; RV32-NEXT:    vand.vv v10, v8, v9
+; RV32-NEXT:    vsrl.vi v8, v8, 2
+; RV32-NEXT:    vand.vv v8, v8, v9
+; RV32-NEXT:    vadd.vv v8, v10, v8
+; RV32-NEXT:    vsrl.vi v9, v8, 4
+; RV32-NEXT:    vadd.vv v8, v8, v9
+; RV32-NEXT:    lui a1, 61681
+; RV32-NEXT:    addi a1, a1, -241
+; RV32-NEXT:    vsetivli zero, 4, e32, m1, ta, ma
+; RV32-NEXT:    vmv.v.x v9, a1
+; RV32-NEXT:    vsetvli zero, a0, e64, m1, ta, ma
+; RV32-NEXT:    vand.vv v8, v8, v9
+; RV32-NEXT:    lui a1, 4112
+; RV32-NEXT:    addi a1, a1, 257
+; RV32-NEXT:    vsetivli zero, 4, e32, m1, ta, ma
+; RV32-NEXT:    vmv.v.x v9, a1
+; RV32-NEXT:    vsetvli zero, a0, e64, m1, ta, ma
+; RV32-NEXT:    vmul.vv v8, v8, v9
+; RV32-NEXT:    li a0, 56
+; RV32-NEXT:    vsrl.vx v8, v8, a0
+; RV32-NEXT:    ret
+;
+; RV64-LABEL: vp_ctpop_v2i64_unmasked:
+; RV64:       # %bb.0:
+; RV64-NEXT:    vsetvli zero, a0, e64, m1, ta, ma
+; RV64-NEXT:    lui a0, %hi(.LCPI25_0)
+; RV64-NEXT:    ld a0, %lo(.LCPI25_0)(a0)
+; RV64-NEXT:    lui a1, %hi(.LCPI25_1)
+; RV64-NEXT:    ld a1, %lo(.LCPI25_1)(a1)
+; RV64-NEXT:    vsrl.vi v9, v8, 1
+; RV64-NEXT:    vand.vx v9, v9, a0
+; RV64-NEXT:    vsub.vv v8, v8, v9
+; RV64-NEXT:    vand.vx v9, v8, a1
+; RV64-NEXT:    vsrl.vi v8, v8, 2
+; RV64-NEXT:    vand.vx v8, v8, a1
+; RV64-NEXT:    vadd.vv v8, v9, v8
+; RV64-NEXT:    lui a0, %hi(.LCPI25_2)
+; RV64-NEXT:    ld a0, %lo(.LCPI25_2)(a0)
+; RV64-NEXT:    lui a1, %hi(.LCPI25_3)
+; RV64-NEXT:    ld a1, %lo(.LCPI25_3)(a1)
+; RV64-NEXT:    vsrl.vi v9, v8, 4
+; RV64-NEXT:    vadd.vv v8, v8, v9
+; RV64-NEXT:    vand.vx v8, v8, a0
+; RV64-NEXT:    vmul.vx v8, v8, a1
+; RV64-NEXT:    li a0, 56
+; RV64-NEXT:    vsrl.vx v8, v8, a0
+; RV64-NEXT:    ret
+  %head = insertelement <2 x i1> poison, i1 true, i32 0
+  %m = shufflevector <2 x i1> %head, <2 x i1> poison, <2 x i32> zeroinitializer
+  %v = call <2 x i64> @llvm.vp.ctpop.v2i64(<2 x i64> %va, <2 x i1> %m, i32 %evl)
+  ret <2 x i64> %v
+}
+
+declare <4 x i64> @llvm.vp.ctpop.v4i64(<4 x i64>, <4 x i1>, i32)
+
+define <4 x i64> @vp_ctpop_v4i64(<4 x i64> %va, <4 x i1> %m, i32 zeroext %evl) {
+; RV32-LABEL: vp_ctpop_v4i64:
+; RV32:       # %bb.0:
+; RV32-NEXT:    vsetvli zero, a0, e64, m2, ta, ma
+; RV32-NEXT:    vsrl.vi v10, v8, 1, v0.t
+; RV32-NEXT:    lui a1, 349525
+; RV32-NEXT:    addi a1, a1, 1365
+; RV32-NEXT:    vsetivli zero, 8, e32, m2, ta, ma
+; RV32-NEXT:    vmv.v.x v12, a1
+; RV32-NEXT:    vsetvli zero, a0, e64, m2, ta, ma
+; RV32-NEXT:    vand.vv v10, v10, v12, v0.t
+; RV32-NEXT:    vsub.vv v8, v8, v10, v0.t
+; RV32-NEXT:    lui a1, 209715
+; RV32-NEXT:    addi a1, a1, 819
+; RV32-NEXT:    vsetivli zero, 8, e32, m2, ta, ma
+; RV32-NEXT:    vmv.v.x v10, a1
+; RV32-NEXT:    vsetvli zero, a0, e64, m2, ta, ma
+; RV32-NEXT:    vand.vv v12, v8, v10, v0.t
+; RV32-NEXT:    vsrl.vi v8, v8, 2, v0.t
+; RV32-NEXT:    vand.vv v8, v8, v10, v0.t
+; RV32-NEXT:    vadd.vv v8, v12, v8, v0.t
+; RV32-NEXT:    vsrl.vi v10, v8, 4, v0.t
+; RV32-NEXT:    vadd.vv v8, v8, v10, v0.t
+; RV32-NEXT:    lui a1, 61681
+; RV32-NEXT:    addi a1, a1, -241
+; RV32-NEXT:    vsetivli zero, 8, e32, m2, ta, ma
+; RV32-NEXT:    vmv.v.x v10, a1
+; RV32-NEXT:    vsetvli zero, a0, e64, m2, ta, ma
+; RV32-NEXT:    vand.vv v8, v8, v10, v0.t
+; RV32-NEXT:    lui a1, 4112
+; RV32-NEXT:    addi a1, a1, 257
+; RV32-NEXT:    vsetivli zero, 8, e32, m2, ta, ma
+; RV32-NEXT:    vmv.v.x v10, a1
+; RV32-NEXT:    vsetvli zero, a0, e64, m2, ta, ma
+; RV32-NEXT:    vmul.vv v8, v8, v10, v0.t
+; RV32-NEXT:    li a0, 56
+; RV32-NEXT:    vsrl.vx v8, v8, a0, v0.t
+; RV32-NEXT:    ret
+;
+; RV64-LABEL: vp_ctpop_v4i64:
+; RV64:       # %bb.0:
+; RV64-NEXT:    vsetvli zero, a0, e64, m2, ta, ma
+; RV64-NEXT:    lui a0, %hi(.LCPI26_0)
+; RV64-NEXT:    ld a0, %lo(.LCPI26_0)(a0)
+; RV64-NEXT:    lui a1, %hi(.LCPI26_1)
+; RV64-NEXT:    ld a1, %lo(.LCPI26_1)(a1)
+; RV64-NEXT:    vsrl.vi v10, v8, 1, v0.t
+; RV64-NEXT:    vand.vx v10, v10, a0, v0.t
+; RV64-NEXT:    vsub.vv v8, v8, v10, v0.t
+; RV64-NEXT:    vand.vx v10, v8, a1, v0.t
+; RV64-NEXT:    vsrl.vi v8, v8, 2, v0.t
+; RV64-NEXT:    vand.vx v8, v8, a1, v0.t
+; RV64-NEXT:    vadd.vv v8, v10, v8, v0.t
+; RV64-NEXT:    lui a0, %hi(.LCPI26_2)
+; RV64-NEXT:    ld a0, %lo(.LCPI26_2)(a0)
+; RV64-NEXT:    lui a1, %hi(.LCPI26_3)
+; RV64-NEXT:    ld a1, %lo(.LCPI26_3)(a1)
+; RV64-NEXT:    vsrl.vi v10, v8, 4, v0.t
+; RV64-NEXT:    vadd.vv v8, v8, v10, v0.t
+; RV64-NEXT:    vand.vx v8, v8, a0, v0.t
+; RV64-NEXT:    vmul.vx v8, v8, a1, v0.t
+; RV64-NEXT:    li a0, 56
+; RV64-NEXT:    vsrl.vx v8, v8, a0, v0.t
+; RV64-NEXT:    ret
+  %v = call <4 x i64> @llvm.vp.ctpop.v4i64(<4 x i64> %va, <4 x i1> %m, i32 %evl)
+  ret <4 x i64> %v
+}
+
+define <4 x i64> @vp_ctpop_v4i64_unmasked(<4 x i64> %va, i32 zeroext %evl) {
+; RV32-LABEL: vp_ctpop_v4i64_unmasked:
+; RV32:       # %bb.0:
+; RV32-NEXT:    vsetvli zero, a0, e64, m2, ta, ma
+; RV32-NEXT:    vsrl.vi v10, v8, 1
+; RV32-NEXT:    lui a1, 349525
+; RV32-NEXT:    addi a1, a1, 1365
+; RV32-NEXT:    vsetivli zero, 8, e32, m2, ta, ma
+; RV32-NEXT:    vmv.v.x v12, a1
+; RV32-NEXT:    vsetvli zero, a0, e64, m2, ta, ma
+; RV32-NEXT:    vand.vv v10, v10, v12
+; RV32-NEXT:    vsub.vv v8, v8, v10
+; RV32-NEXT:    lui a1, 209715
+; RV32-NEXT:    addi a1, a1, 819
+; RV32-NEXT:    vsetivli zero, 8, e32, m2, ta, ma
+; RV32-NEXT:    vmv.v.x v10, a1
+; RV32-NEXT:    vsetvli zero, a0, e64, m2, ta, ma
+; RV32-NEXT:    vand.vv v12, v8, v10
+; RV32-NEXT:    vsrl.vi v8, v8, 2
+; RV32-NEXT:    vand.vv v8, v8, v10
+; RV32-NEXT:    vadd.vv v8, v12, v8
+; RV32-NEXT:    vsrl.vi v10, v8, 4
+; RV32-NEXT:    vadd.vv v8, v8, v10
+; RV32-NEXT:    lui a1, 61681
+; RV32-NEXT:    addi a1, a1, -241
+; RV32-NEXT:    vsetivli zero, 8, e32, m2, ta, ma
+; RV32-NEXT:    vmv.v.x v10, a1
+; RV32-NEXT:    vsetvli zero, a0, e64, m2, ta, ma
+; RV32-NEXT:    vand.vv v8, v8, v10
+; RV32-NEXT:    lui a1, 4112
+; RV32-NEXT:    addi a1, a1, 257
+; RV32-NEXT:    vsetivli zero, 8, e32, m2, ta, ma
+; RV32-NEXT:    vmv.v.x v10, a1
+; RV32-NEXT:    vsetvli zero, a0, e64, m2, ta, ma
+; RV32-NEXT:    vmul.vv v8, v8, v10
+; RV32-NEXT:    li a0, 56
+; RV32-NEXT:    vsrl.vx v8, v8, a0
+; RV32-NEXT:    ret
+;
+; RV64-LABEL: vp_ctpop_v4i64_unmasked:
+; RV64:       # %bb.0:
+; RV64-NEXT:    vsetvli zero, a0, e64, m2, ta, ma
+; RV64-NEXT:    lui a0, %hi(.LCPI27_0)
+; RV64-NEXT:    ld a0, %lo(.LCPI27_0)(a0)
+; RV64-NEXT:    lui a1, %hi(.LCPI27_1)
+; RV64-NEXT:    ld a1, %lo(.LCPI27_1)(a1)
+; RV64-NEXT:    vsrl.vi v10, v8, 1
+; RV64-NEXT:    vand.vx v10, v10, a0
+; RV64-NEXT:    vsub.vv v8, v8, v10
+; RV64-NEXT:    vand.vx v10, v8, a1
+; RV64-NEXT:    vsrl.vi v8, v8, 2
+; RV64-NEXT:    vand.vx v8, v8, a1
+; RV64-NEXT:    vadd.vv v8, v10, v8
+; RV64-NEXT:    lui a0, %hi(.LCPI27_2)
+; RV64-NEXT:    ld a0, %lo(.LCPI27_2)(a0)
+; RV64-NEXT:    lui a1, %hi(.LCPI27_3)
+; RV64-NEXT:    ld a1, %lo(.LCPI27_3)(a1)
+; RV64-NEXT:    vsrl.vi v10, v8, 4
+; RV64-NEXT:    vadd.vv v8, v8, v10
+; RV64-NEXT:    vand.vx v8, v8, a0
+; RV64-NEXT:    vmul.vx v8, v8, a1
+; RV64-NEXT:    li a0, 56
+; RV64-NEXT:    vsrl.vx v8, v8, a0
+; RV64-NEXT:    ret
+  %head = insertelement <4 x i1> poison, i1 true, i32 0
+  %m = shufflevector <4 x i1> %head, <4 x i1> poison, <4 x i32> zeroinitializer
+  %v = call <4 x i64> @llvm.vp.ctpop.v4i64(<4 x i64> %va, <4 x i1> %m, i32 %evl)
+  ret <4 x i64> %v
+}
+
+declare <8 x i64> @llvm.vp.ctpop.v8i64(<8 x i64>, <8 x i1>, i32)
+
+define <8 x i64> @vp_ctpop_v8i64(<8 x i64> %va, <8 x i1> %m, i32 zeroext %evl) {
+; RV32-LABEL: vp_ctpop_v8i64:
+; RV32:       # %bb.0:
+; RV32-NEXT:    vsetvli zero, a0, e64, m4, ta, ma
+; RV32-NEXT:    vsrl.vi v12, v8, 1, v0.t
+; RV32-NEXT:    lui a1, 349525
+; RV32-NEXT:    addi a1, a1, 1365
+; RV32-NEXT:    vsetivli zero, 16, e32, m4, ta, ma
+; RV32-NEXT:    vmv.v.x v16, a1
+; RV32-NEXT:    vsetvli zero, a0, e64, m4, ta, ma
+; RV32-NEXT:    vand.vv v12, v12, v16, v0.t
+; RV32-NEXT:    vsub.vv v8, v8, v12, v0.t
+; RV32-NEXT:    lui a1, 209715
+; RV32-NEXT:    addi a1, a1, 819
+; RV32-NEXT:    vsetivli zero, 16, e32, m4, ta, ma
+; RV32-NEXT:    vmv.v.x v12, a1
+; RV32-NEXT:    vsetvli zero, a0, e64, m4, ta, ma
+; RV32-NEXT:    vand.vv v16, v8, v12, v0.t
+; RV32-NEXT:    vsrl.vi v8, v8, 2, v0.t
+; RV32-NEXT:    vand.vv v8, v8, v12, v0.t
+; RV32-NEXT:    vadd.vv v8, v16, v8, v0.t
+; RV32-NEXT:    vsrl.vi v12, v8, 4, v0.t
+; RV32-NEXT:    vadd.vv v8, v8, v12, v0.t
+; RV32-NEXT:    lui a1, 61681
+; RV32-NEXT:    addi a1, a1, -241
+; RV32-NEXT:    vsetivli zero, 16, e32, m4, ta, ma
+; RV32-NEXT:    vmv.v.x v12, a1
+; RV32-NEXT:    vsetvli zero, a0, e64, m4, ta, ma
+; RV32-NEXT:    vand.vv v8, v8, v12, v0.t
+; RV32-NEXT:    lui a1, 4112
+; RV32-NEXT:    addi a1, a1, 257
+; RV32-NEXT:    vsetivli zero, 16, e32, m4, ta, ma
+; RV32-NEXT:    vmv.v.x v12, a1
+; RV32-NEXT:    vsetvli zero, a0, e64, m4, ta, ma
+; RV32-NEXT:    vmul.vv v8, v8, v12, v0.t
+; RV32-NEXT:    li a0, 56
+; RV32-NEXT:    vsrl.vx v8, v8, a0, v0.t
+; RV32-NEXT:    ret
+;
+; RV64-LABEL: vp_ctpop_v8i64:
+; RV64:       # %bb.0:
+; RV64-NEXT:    vsetvli zero, a0, e64, m4, ta, ma
+; RV64-NEXT:    lui a0, %hi(.LCPI28_0)
+; RV64-NEXT:    ld a0, %lo(.LCPI28_0)(a0)
+; RV64-NEXT:    lui a1, %hi(.LCPI28_1)
+; RV64-NEXT:    ld a1, %lo(.LCPI28_1)(a1)
+; RV64-NEXT:    vsrl.vi v12, v8, 1, v0.t
+; RV64-NEXT:    vand.vx v12, v12, a0, v0.t
+; RV64-NEXT:    vsub.vv v8, v8, v12, v0.t
+; RV64-NEXT:    vand.vx v12, v8, a1, v0.t
+; RV64-NEXT:    vsrl.vi v8, v8, 2, v0.t
+; RV64-NEXT:    vand.vx v8, v8, a1, v0.t
+; RV64-NEXT:    vadd.vv v8, v12, v8, v0.t
+; RV64-NEXT:    lui a0, %hi(.LCPI28_2)
+; RV64-NEXT:    ld a0, %lo(.LCPI28_2)(a0)
+; RV64-NEXT:    lui a1, %hi(.LCPI28_3)
+; RV64-NEXT:    ld a1, %lo(.LCPI28_3)(a1)
+; RV64-NEXT:    vsrl.vi v12, v8, 4, v0.t
+; RV64-NEXT:    vadd.vv v8, v8, v12, v0.t
+; RV64-NEXT:    vand.vx v8, v8, a0, v0.t
+; RV64-NEXT:    vmul.vx v8, v8, a1, v0.t
+; RV64-NEXT:    li a0, 56
+; RV64-NEXT:    vsrl.vx v8, v8, a0, v0.t
+; RV64-NEXT:    ret
+  %v = call <8 x i64> @llvm.vp.ctpop.v8i64(<8 x i64> %va, <8 x i1> %m, i32 %evl)
+  ret <8 x i64> %v
+}
+
+define <8 x i64> @vp_ctpop_v8i64_unmasked(<8 x i64> %va, i32 zeroext %evl) {
+; RV32-LABEL: vp_ctpop_v8i64_unmasked:
+; RV32:       # %bb.0:
+; RV32-NEXT:    vsetvli zero, a0, e64, m4, ta, ma
+; RV32-NEXT:    vsrl.vi v12, v8, 1
+; RV32-NEXT:    lui a1, 349525
+; RV32-NEXT:    addi a1, a1, 1365
+; RV32-NEXT:    vsetivli zero, 16, e32, m4, ta, ma
+; RV32-NEXT:    vmv.v.x v16, a1
+; RV32-NEXT:    vsetvli zero, a0, e64, m4, ta, ma
+; RV32-NEXT:    vand.vv v12, v12, v16
+; RV32-NEXT:    vsub.vv v8, v8, v12
+; RV32-NEXT:    lui a1, 209715
+; RV32-NEXT:    addi a1, a1, 819
+; RV32-NEXT:    vsetivli zero, 16, e32, m4, ta, ma
+; RV32-NEXT:    vmv.v.x v12, a1
+; RV32-NEXT:    vsetvli zero, a0, e64, m4, ta, ma
+; RV32-NEXT:    vand.vv v16, v8, v12
+; RV32-NEXT:    vsrl.vi v8, v8, 2
+; RV32-NEXT:    vand.vv v8, v8, v12
+; RV32-NEXT:    vadd.vv v8, v16, v8
+; RV32-NEXT:    vsrl.vi v12, v8, 4
+; RV32-NEXT:    vadd.vv v8, v8, v12
+; RV32-NEXT:    lui a1, 61681
+; RV32-NEXT:    addi a1, a1, -241
+; RV32-NEXT:    vsetivli zero, 16, e32, m4, ta, ma
+; RV32-NEXT:    vmv.v.x v12, a1
+; RV32-NEXT:    vsetvli zero, a0, e64, m4, ta, ma
+; RV32-NEXT:    vand.vv v8, v8, v12
+; RV32-NEXT:    lui a1, 4112
+; RV32-NEXT:    addi a1, a1, 257
+; RV32-NEXT:    vsetivli zero, 16, e32, m4, ta, ma
+; RV32-NEXT:    vmv.v.x v12, a1
+; RV32-NEXT:    vsetvli zero, a0, e64, m4, ta, ma
+; RV32-NEXT:    vmul.vv v8, v8, v12
+; RV32-NEXT:    li a0, 56
+; RV32-NEXT:    vsrl.vx v8, v8, a0
+; RV32-NEXT:    ret
+;
+; RV64-LABEL: vp_ctpop_v8i64_unmasked:
+; RV64:       # %bb.0:
+; RV64-NEXT:    vsetvli zero, a0, e64, m4, ta, ma
+; RV64-NEXT:    lui a0, %hi(.LCPI29_0)
+; RV64-NEXT:    ld a0, %lo(.LCPI29_0)(a0)
+; RV64-NEXT:    lui a1, %hi(.LCPI29_1)
+; RV64-NEXT:    ld a1, %lo(.LCPI29_1)(a1)
+; RV64-NEXT:    vsrl.vi v12, v8, 1
+; RV64-NEXT:    vand.vx v12, v12, a0
+; RV64-NEXT:    vsub.vv v8, v8, v12
+; RV64-NEXT:    vand.vx v12, v8, a1
+; RV64-NEXT:    vsrl.vi v8, v8, 2
+; RV64-NEXT:    vand.vx v8, v8, a1
+; RV64-NEXT:    vadd.vv v8, v12, v8
+; RV64-NEXT:    lui a0, %hi(.LCPI29_2)
+; RV64-NEXT:    ld a0, %lo(.LCPI29_2)(a0)
+; RV64-NEXT:    lui a1, %hi(.LCPI29_3)
+; RV64-NEXT:    ld a1, %lo(.LCPI29_3)(a1)
+; RV64-NEXT:    vsrl.vi v12, v8, 4
+; RV64-NEXT:    vadd.vv v8, v8, v12
+; RV64-NEXT:    vand.vx v8, v8, a0
+; RV64-NEXT:    vmul.vx v8, v8, a1
+; RV64-NEXT:    li a0, 56
+; RV64-NEXT:    vsrl.vx v8, v8, a0
+; RV64-NEXT:    ret
+  %head = insertelement <8 x i1> poison, i1 true, i32 0
+  %m = shufflevector <8 x i1> %head, <8 x i1> poison, <8 x i32> zeroinitializer
+  %v = call <8 x i64> @llvm.vp.ctpop.v8i64(<8 x i64> %va, <8 x i1> %m, i32 %evl)
+  ret <8 x i64> %v
+}
+
+declare <15 x i64> @llvm.vp.ctpop.v15i64(<15 x i64>, <15 x i1>, i32)
+
+define <15 x i64> @vp_ctpop_v15i64(<15 x i64> %va, <15 x i1> %m, i32 zeroext %evl) {
+; RV32-LABEL: vp_ctpop_v15i64:
+; RV32:       # %bb.0:
+; RV32-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
+; RV32-NEXT:    vsrl.vi v16, v8, 1, v0.t
+; RV32-NEXT:    lui a1, 349525
+; RV32-NEXT:    addi a1, a1, 1365
+; RV32-NEXT:    li a2, 32
+; RV32-NEXT:    vsetvli zero, a2, e32, m8, ta, ma
+; RV32-NEXT:    vmv.v.x v24, a1
+; RV32-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
+; RV32-NEXT:    vand.vv v16, v16, v24, v0.t
+; RV32-NEXT:    vsub.vv v8, v8, v16, v0.t
+; RV32-NEXT:    lui a1, 209715
+; RV32-NEXT:    addi a1, a1, 819
+; RV32-NEXT:    vsetvli zero, a2, e32, m8, ta, ma
+; RV32-NEXT:    vmv.v.x v16, a1
+; RV32-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
+; RV32-NEXT:    vand.vv v24, v8, v16, v0.t
+; RV32-NEXT:    vsrl.vi v8, v8, 2, v0.t
+; RV32-NEXT:    vand.vv v8, v8, v16, v0.t
+; RV32-NEXT:    vadd.vv v8, v24, v8, v0.t
+; RV32-NEXT:    vsrl.vi v16, v8, 4, v0.t
+; RV32-NEXT:    vadd.vv v8, v8, v16, v0.t
+; RV32-NEXT:    lui a1, 61681
+; RV32-NEXT:    addi a1, a1, -241
+; RV32-NEXT:    vsetvli zero, a2, e32, m8, ta, ma
+; RV32-NEXT:    vmv.v.x v16, a1
+; RV32-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
+; RV32-NEXT:    vand.vv v8, v8, v16, v0.t
+; RV32-NEXT:    lui a1, 4112
+; RV32-NEXT:    addi a1, a1, 257
+; RV32-NEXT:    vsetvli zero, a2, e32, m8, ta, ma
+; RV32-NEXT:    vmv.v.x v16, a1
+; RV32-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
+; RV32-NEXT:    vmul.vv v8, v8, v16, v0.t
+; RV32-NEXT:    li a0, 56
+; RV32-NEXT:    vsrl.vx v8, v8, a0, v0.t
+; RV32-NEXT:    ret
+;
+; RV64-LABEL: vp_ctpop_v15i64:
+; RV64:       # %bb.0:
+; RV64-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
+; RV64-NEXT:    lui a0, %hi(.LCPI30_0)
+; RV64-NEXT:    ld a0, %lo(.LCPI30_0)(a0)
+; RV64-NEXT:    lui a1, %hi(.LCPI30_1)
+; RV64-NEXT:    ld a1, %lo(.LCPI30_1)(a1)
+; RV64-NEXT:    vsrl.vi v16, v8, 1, v0.t
+; RV64-NEXT:    vand.vx v16, v16, a0, v0.t
+; RV64-NEXT:    vsub.vv v8, v8, v16, v0.t
+; RV64-NEXT:    vand.vx v16, v8, a1, v0.t
+; RV64-NEXT:    vsrl.vi v8, v8, 2, v0.t
+; RV64-NEXT:    vand.vx v8, v8, a1, v0.t
+; RV64-NEXT:    vadd.vv v8, v16, v8, v0.t
+; RV64-NEXT:    lui a0, %hi(.LCPI30_2)
+; RV64-NEXT:    ld a0, %lo(.LCPI30_2)(a0)
+; RV64-NEXT:    lui a1, %hi(.LCPI30_3)
+; RV64-NEXT:    ld a1, %lo(.LCPI30_3)(a1)
+; RV64-NEXT:    vsrl.vi v16, v8, 4, v0.t
+; RV64-NEXT:    vadd.vv v8, v8, v16, v0.t
+; RV64-NEXT:    vand.vx v8, v8, a0, v0.t
+; RV64-NEXT:    vmul.vx v8, v8, a1, v0.t
+; RV64-NEXT:    li a0, 56
+; RV64-NEXT:    vsrl.vx v8, v8, a0, v0.t
+; RV64-NEXT:    ret
+  %v = call <15 x i64> @llvm.vp.ctpop.v15i64(<15 x i64> %va, <15 x i1> %m, i32 %evl)
+  ret <15 x i64> %v
+}
+
+define <15 x i64> @vp_ctpop_v15i64_unmasked(<15 x i64> %va, i32 zeroext %evl) {
+; RV32-LABEL: vp_ctpop_v15i64_unmasked:
+; RV32:       # %bb.0:
+; RV32-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
+; RV32-NEXT:    vsrl.vi v16, v8, 1
+; RV32-NEXT:    lui a1, 349525
+; RV32-NEXT:    addi a1, a1, 1365
+; RV32-NEXT:    li a2, 32
+; RV32-NEXT:    vsetvli zero, a2, e32, m8, ta, ma
+; RV32-NEXT:    vmv.v.x v24, a1
+; RV32-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
+; RV32-NEXT:    vand.vv v16, v16, v24
+; RV32-NEXT:    vsub.vv v8, v8, v16
+; RV32-NEXT:    lui a1, 209715
+; RV32-NEXT:    addi a1, a1, 819
+; RV32-NEXT:    vsetvli zero, a2, e32, m8, ta, ma
+; RV32-NEXT:    vmv.v.x v16, a1
+; RV32-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
+; RV32-NEXT:    vand.vv v24, v8, v16
+; RV32-NEXT:    vsrl.vi v8, v8, 2
+; RV32-NEXT:    vand.vv v8, v8, v16
+; RV32-NEXT:    vadd.vv v8, v24, v8
+; RV32-NEXT:    vsrl.vi v16, v8, 4
+; RV32-NEXT:    vadd.vv v8, v8, v16
+; RV32-NEXT:    lui a1, 61681
+; RV32-NEXT:    addi a1, a1, -241
+; RV32-NEXT:    vsetvli zero, a2, e32, m8, ta, ma
+; RV32-NEXT:    vmv.v.x v16, a1
+; RV32-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
+; RV32-NEXT:    vand.vv v8, v8, v16
+; RV32-NEXT:    lui a1, 4112
+; RV32-NEXT:    addi a1, a1, 257
+; RV32-NEXT:    vsetvli zero, a2, e32, m8, ta, ma
+; RV32-NEXT:    vmv.v.x v16, a1
+; RV32-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
+; RV32-NEXT:    vmul.vv v8, v8, v16
+; RV32-NEXT:    li a0, 56
+; RV32-NEXT:    vsrl.vx v8, v8, a0
+; RV32-NEXT:    ret
+;
+; RV64-LABEL: vp_ctpop_v15i64_unmasked:
+; RV64:       # %bb.0:
+; RV64-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
+; RV64-NEXT:    lui a0, %hi(.LCPI31_0)
+; RV64-NEXT:    ld a0, %lo(.LCPI31_0)(a0)
+; RV64-NEXT:    lui a1, %hi(.LCPI31_1)
+; RV64-NEXT:    ld a1, %lo(.LCPI31_1)(a1)
+; RV64-NEXT:    vsrl.vi v16, v8, 1
+; RV64-NEXT:    vand.vx v16, v16, a0
+; RV64-NEXT:    vsub.vv v8, v8, v16
+; RV64-NEXT:    vand.vx v16, v8, a1
+; RV64-NEXT:    vsrl.vi v8, v8, 2
+; RV64-NEXT:    vand.vx v8, v8, a1
+; RV64-NEXT:    vadd.vv v8, v16, v8
+; RV64-NEXT:    lui a0, %hi(.LCPI31_2)
+; RV64-NEXT:    ld a0, %lo(.LCPI31_2)(a0)
+; RV64-NEXT:    lui a1, %hi(.LCPI31_3)
+; RV64-NEXT:    ld a1, %lo(.LCPI31_3)(a1)
+; RV64-NEXT:    vsrl.vi v16, v8, 4
+; RV64-NEXT:    vadd.vv v8, v8, v16
+; RV64-NEXT:    vand.vx v8, v8, a0
+; RV64-NEXT:    vmul.vx v8, v8, a1
+; RV64-NEXT:    li a0, 56
+; RV64-NEXT:    vsrl.vx v8, v8, a0
+; RV64-NEXT:    ret
+  %head = insertelement <15 x i1> poison, i1 true, i32 0
+  %m = shufflevector <15 x i1> %head, <15 x i1> poison, <15 x i32> zeroinitializer
+  %v = call <15 x i64> @llvm.vp.ctpop.v15i64(<15 x i64> %va, <15 x i1> %m, i32 %evl)
+  ret <15 x i64> %v
+}
+
+declare <16 x i64> @llvm.vp.ctpop.v16i64(<16 x i64>, <16 x i1>, i32)
+
+define <16 x i64> @vp_ctpop_v16i64(<16 x i64> %va, <16 x i1> %m, i32 zeroext %evl) {
+; RV32-LABEL: vp_ctpop_v16i64:
+; RV32:       # %bb.0:
+; RV32-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
+; RV32-NEXT:    vsrl.vi v16, v8, 1, v0.t
+; RV32-NEXT:    lui a1, 349525
+; RV32-NEXT:    addi a1, a1, 1365
+; RV32-NEXT:    li a2, 32
+; RV32-NEXT:    vsetvli zero, a2, e32, m8, ta, ma
+; RV32-NEXT:    vmv.v.x v24, a1
+; RV32-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
+; RV32-NEXT:    vand.vv v16, v16, v24, v0.t
+; RV32-NEXT:    vsub.vv v8, v8, v16, v0.t
+; RV32-NEXT:    lui a1, 209715
+; RV32-NEXT:    addi a1, a1, 819
+; RV32-NEXT:    vsetvli zero, a2, e32, m8, ta, ma
+; RV32-NEXT:    vmv.v.x v16, a1
+; RV32-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
+; RV32-NEXT:    vand.vv v24, v8, v16, v0.t
+; RV32-NEXT:    vsrl.vi v8, v8, 2, v0.t
+; RV32-NEXT:    vand.vv v8, v8, v16, v0.t
+; RV32-NEXT:    vadd.vv v8, v24, v8, v0.t
+; RV32-NEXT:    vsrl.vi v16, v8, 4, v0.t
+; RV32-NEXT:    vadd.vv v8, v8, v16, v0.t
+; RV32-NEXT:    lui a1, 61681
+; RV32-NEXT:    addi a1, a1, -241
+; RV32-NEXT:    vsetvli zero, a2, e32, m8, ta, ma
+; RV32-NEXT:    vmv.v.x v16, a1
+; RV32-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
+; RV32-NEXT:    vand.vv v8, v8, v16, v0.t
+; RV32-NEXT:    lui a1, 4112
+; RV32-NEXT:    addi a1, a1, 257
+; RV32-NEXT:    vsetvli zero, a2, e32, m8, ta, ma
+; RV32-NEXT:    vmv.v.x v16, a1
+; RV32-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
+; RV32-NEXT:    vmul.vv v8, v8, v16, v0.t
+; RV32-NEXT:    li a0, 56
+; RV32-NEXT:    vsrl.vx v8, v8, a0, v0.t
+; RV32-NEXT:    ret
+;
+; RV64-LABEL: vp_ctpop_v16i64:
+; RV64:       # %bb.0:
+; RV64-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
+; RV64-NEXT:    lui a0, %hi(.LCPI32_0)
+; RV64-NEXT:    ld a0, %lo(.LCPI32_0)(a0)
+; RV64-NEXT:    lui a1, %hi(.LCPI32_1)
+; RV64-NEXT:    ld a1, %lo(.LCPI32_1)(a1)
+; RV64-NEXT:    vsrl.vi v16, v8, 1, v0.t
+; RV64-NEXT:    vand.vx v16, v16, a0, v0.t
+; RV64-NEXT:    vsub.vv v8, v8, v16, v0.t
+; RV64-NEXT:    vand.vx v16, v8, a1, v0.t
+; RV64-NEXT:    vsrl.vi v8, v8, 2, v0.t
+; RV64-NEXT:    vand.vx v8, v8, a1, v0.t
+; RV64-NEXT:    vadd.vv v8, v16, v8, v0.t
+; RV64-NEXT:    lui a0, %hi(.LCPI32_2)
+; RV64-NEXT:    ld a0, %lo(.LCPI32_2)(a0)
+; RV64-NEXT:    lui a1, %hi(.LCPI32_3)
+; RV64-NEXT:    ld a1, %lo(.LCPI32_3)(a1)
+; RV64-NEXT:    vsrl.vi v16, v8, 4, v0.t
+; RV64-NEXT:    vadd.vv v8, v8, v16, v0.t
+; RV64-NEXT:    vand.vx v8, v8, a0, v0.t
+; RV64-NEXT:    vmul.vx v8, v8, a1, v0.t
+; RV64-NEXT:    li a0, 56
+; RV64-NEXT:    vsrl.vx v8, v8, a0, v0.t
+; RV64-NEXT:    ret
+  %v = call <16 x i64> @llvm.vp.ctpop.v16i64(<16 x i64> %va, <16 x i1> %m, i32 %evl)
+  ret <16 x i64> %v
+}
+
+define <16 x i64> @vp_ctpop_v16i64_unmasked(<16 x i64> %va, i32 zeroext %evl) {
+; RV32-LABEL: vp_ctpop_v16i64_unmasked:
+; RV32:       # %bb.0:
+; RV32-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
+; RV32-NEXT:    vsrl.vi v16, v8, 1
+; RV32-NEXT:    lui a1, 349525
+; RV32-NEXT:    addi a1, a1, 1365
+; RV32-NEXT:    li a2, 32
+; RV32-NEXT:    vsetvli zero, a2, e32, m8, ta, ma
+; RV32-NEXT:    vmv.v.x v24, a1
+; RV32-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
+; RV32-NEXT:    vand.vv v16, v16, v24
+; RV32-NEXT:    vsub.vv v8, v8, v16
+; RV32-NEXT:    lui a1, 209715
+; RV32-NEXT:    addi a1, a1, 819
+; RV32-NEXT:    vsetvli zero, a2, e32, m8, ta, ma
+; RV32-NEXT:    vmv.v.x v16, a1
+; RV32-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
+; RV32-NEXT:    vand.vv v24, v8, v16
+; RV32-NEXT:    vsrl.vi v8, v8, 2
+; RV32-NEXT:    vand.vv v8, v8, v16
+; RV32-NEXT:    vadd.vv v8, v24, v8
+; RV32-NEXT:    vsrl.vi v16, v8, 4
+; RV32-NEXT:    vadd.vv v8, v8, v16
+; RV32-NEXT:    lui a1, 61681
+; RV32-NEXT:    addi a1, a1, -241
+; RV32-NEXT:    vsetvli zero, a2, e32, m8, ta, ma
+; RV32-NEXT:    vmv.v.x v16, a1
+; RV32-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
+; RV32-NEXT:    vand.vv v8, v8, v16
+; RV32-NEXT:    lui a1, 4112
+; RV32-NEXT:    addi a1, a1, 257
+; RV32-NEXT:    vsetvli zero, a2, e32, m8, ta, ma
+; RV32-NEXT:    vmv.v.x v16, a1
+; RV32-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
+; RV32-NEXT:    vmul.vv v8, v8, v16
+; RV32-NEXT:    li a0, 56
+; RV32-NEXT:    vsrl.vx v8, v8, a0
+; RV32-NEXT:    ret
+;
+; RV64-LABEL: vp_ctpop_v16i64_unmasked:
+; RV64:       # %bb.0:
+; RV64-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
+; RV64-NEXT:    lui a0, %hi(.LCPI33_0)
+; RV64-NEXT:    ld a0, %lo(.LCPI33_0)(a0)
+; RV64-NEXT:    lui a1, %hi(.LCPI33_1)
+; RV64-NEXT:    ld a1, %lo(.LCPI33_1)(a1)
+; RV64-NEXT:    vsrl.vi v16, v8, 1
+; RV64-NEXT:    vand.vx v16, v16, a0
+; RV64-NEXT:    vsub.vv v8, v8, v16
+; RV64-NEXT:    vand.vx v16, v8, a1
+; RV64-NEXT:    vsrl.vi v8, v8, 2
+; RV64-NEXT:    vand.vx v8, v8, a1
+; RV64-NEXT:    vadd.vv v8, v16, v8
+; RV64-NEXT:    lui a0, %hi(.LCPI33_2)
+; RV64-NEXT:    ld a0, %lo(.LCPI33_2)(a0)
+; RV64-NEXT:    lui a1, %hi(.LCPI33_3)
+; RV64-NEXT:    ld a1, %lo(.LCPI33_3)(a1)
+; RV64-NEXT:    vsrl.vi v16, v8, 4
+; RV64-NEXT:    vadd.vv v8, v8, v16
+; RV64-NEXT:    vand.vx v8, v8, a0
+; RV64-NEXT:    vmul.vx v8, v8, a1
+; RV64-NEXT:    li a0, 56
+; RV64-NEXT:    vsrl.vx v8, v8, a0
+; RV64-NEXT:    ret
+  %head = insertelement <16 x i1> poison, i1 true, i32 0
+  %m = shufflevector <16 x i1> %head, <16 x i1> poison, <16 x i32> zeroinitializer
+  %v = call <16 x i64> @llvm.vp.ctpop.v16i64(<16 x i64> %va, <16 x i1> %m, i32 %evl)
+  ret <16 x i64> %v
+}
+
+declare <32 x i64> @llvm.vp.ctpop.v32i64(<32 x i64>, <32 x i1>, i32)
+
+define <32 x i64> @vp_ctpop_v32i64(<32 x i64> %va, <32 x i1> %m, i32 zeroext %evl) {
+; RV32-LABEL: vp_ctpop_v32i64:
+; RV32:       # %bb.0:
+; RV32-NEXT:    addi sp, sp, -16
+; RV32-NEXT:    .cfi_def_cfa_offset 16
+; RV32-NEXT:    csrr a1, vlenb
+; RV32-NEXT:    li a2, 56
+; RV32-NEXT:    mul a1, a1, a2
+; RV32-NEXT:    sub sp, sp, a1
+; RV32-NEXT:    .cfi_escape 0x0f, 0x0d, 0x72, 0x00, 0x11, 0x10, 0x22, 0x11, 0x38, 0x92, 0xa2, 0x38, 0x00, 0x1e, 0x22 # sp + 16 + 56 * vlenb
+; RV32-NEXT:    csrr a1, vlenb
+; RV32-NEXT:    li a2, 48
+; RV32-NEXT:    mul a1, a1, a2
+; RV32-NEXT:    add a1, sp, a1
+; RV32-NEXT:    addi a1, a1, 16
+; RV32-NEXT:    vs8r.v v16, (a1) # Unknown-size Folded Spill
+; RV32-NEXT:    vsetivli zero, 2, e8, mf4, ta, ma
+; RV32-NEXT:    li a2, 16
+; RV32-NEXT:    vslidedown.vi v24, v0, 2
+; RV32-NEXT:    mv a1, a0
+; RV32-NEXT:    bltu a0, a2, .LBB34_2
+; RV32-NEXT:  # %bb.1:
+; RV32-NEXT:    li a1, 16
+; RV32-NEXT:  .LBB34_2:
+; RV32-NEXT:    vsetvli zero, a1, e64, m8, ta, ma
+; RV32-NEXT:    vsrl.vi v16, v8, 1, v0.t
+; RV32-NEXT:    lui a2, 349525
+; RV32-NEXT:    addi a2, a2, 1365
+; RV32-NEXT:    li a3, 32
+; RV32-NEXT:    vsetvli zero, a3, e32, m8, ta, ma
+; RV32-NEXT:    csrr a4, vlenb
+; RV32-NEXT:    li a5, 40
+; RV32-NEXT:    mul a4, a4, a5
+; RV32-NEXT:    add a4, sp, a4
+; RV32-NEXT:    addi a4, a4, 16
+; RV32-NEXT:    vs8r.v v8, (a4) # Unknown-size Folded Spill
+; RV32-NEXT:    vmv.v.x v8, a2
+; RV32-NEXT:    csrr a2, vlenb
+; RV32-NEXT:    li a4, 24
+; RV32-NEXT:    mul a2, a2, a4
+; RV32-NEXT:    add a2, sp, a2
+; RV32-NEXT:    addi a2, a2, 16
+; RV32-NEXT:    vs8r.v v8, (a2) # Unknown-size Folded Spill
+; RV32-NEXT:    vsetvli zero, a1, e64, m8, ta, ma
+; RV32-NEXT:    vand.vv v16, v16, v8, v0.t
+; RV32-NEXT:    csrr a2, vlenb
+; RV32-NEXT:    li a4, 40
+; RV32-NEXT:    mul a2, a2, a4
+; RV32-NEXT:    add a2, sp, a2
+; RV32-NEXT:    addi a2, a2, 16
+; RV32-NEXT:    vl8r.v v8, (a2) # Unknown-size Folded Reload
+; RV32-NEXT:    vsub.vv v8, v8, v16, v0.t
+; RV32-NEXT:    csrr a2, vlenb
+; RV32-NEXT:    slli a2, a2, 5
+; RV32-NEXT:    add a2, sp, a2
+; RV32-NEXT:    addi a2, a2, 16
+; RV32-NEXT:    vs8r.v v8, (a2) # Unknown-size Folded Spill
+; RV32-NEXT:    lui a2, 209715
+; RV32-NEXT:    addi a2, a2, 819
+; RV32-NEXT:    vsetvli zero, a3, e32, m8, ta, ma
+; RV32-NEXT:    vmv.v.x v8, a2
+; RV32-NEXT:    csrr a2, vlenb
+; RV32-NEXT:    li a4, 40
+; RV32-NEXT:    mul a2, a2, a4
+; RV32-NEXT:    add a2, sp, a2
+; RV32-NEXT:    addi a2, a2, 16
+; RV32-NEXT:    vs8r.v v8, (a2) # Unknown-size Folded Spill
+; RV32-NEXT:    vsetvli zero, a1, e64, m8, ta, ma
+; RV32-NEXT:    csrr a2, vlenb
+; RV32-NEXT:    slli a2, a2, 5
+; RV32-NEXT:    add a2, sp, a2
+; RV32-NEXT:    addi a2, a2, 16
+; RV32-NEXT:    vl8r.v v16, (a2) # Unknown-size Folded Reload
+; RV32-NEXT:    vand.vv v16, v16, v8, v0.t
+; RV32-NEXT:    csrr a2, vlenb
+; RV32-NEXT:    slli a2, a2, 4
+; RV32-NEXT:    add a2, sp, a2
+; RV32-NEXT:    addi a2, a2, 16
+; RV32-NEXT:    vs8r.v v16, (a2) # Unknown-size Folded Spill
+; RV32-NEXT:    csrr a2, vlenb
+; RV32-NEXT:    slli a2, a2, 5
+; RV32-NEXT:    add a2, sp, a2
+; RV32-NEXT:    addi a2, a2, 16
+; RV32-NEXT:    vl8r.v v16, (a2) # Unknown-size Folded Reload
+; RV32-NEXT:    vsrl.vi v16, v16, 2, v0.t
+; RV32-NEXT:    vand.vv v16, v16, v8, v0.t
+; RV32-NEXT:    csrr a2, vlenb
+; RV32-NEXT:    slli a2, a2, 4
+; RV32-NEXT:    add a2, sp, a2
+; RV32-NEXT:    addi a2, a2, 16
+; RV32-NEXT:    vl8r.v v8, (a2) # Unknown-size Folded Reload
+; RV32-NEXT:    vadd.vv v16, v8, v16, v0.t
+; RV32-NEXT:    vsrl.vi v8, v16, 4, v0.t
+; RV32-NEXT:    vadd.vv v16, v16, v8, v0.t
+; RV32-NEXT:    lui a2, 61681
+; RV32-NEXT:    addi a2, a2, -241
+; RV32-NEXT:    vsetvli zero, a3, e32, m8, ta, ma
+; RV32-NEXT:    vmv.v.x v8, a2
+; RV32-NEXT:    csrr a2, vlenb
+; RV32-NEXT:    slli a2, a2, 5
+; RV32-NEXT:    add a2, sp, a2
+; RV32-NEXT:    addi a2, a2, 16
+; RV32-NEXT:    vs8r.v v8, (a2) # Unknown-size Folded Spill
+; RV32-NEXT:    vsetvli zero, a1, e64, m8, ta, ma
+; RV32-NEXT:    vand.vv v8, v16, v8, v0.t
+; RV32-NEXT:    lui a2, 4112
+; RV32-NEXT:    addi a2, a2, 257
+; RV32-NEXT:    vsetvli zero, a3, e32, m8, ta, ma
+; RV32-NEXT:    vmv.v.x v16, a2
+; RV32-NEXT:    csrr a2, vlenb
+; RV32-NEXT:    slli a2, a2, 3
+; RV32-NEXT:    add a2, sp, a2
+; RV32-NEXT:    addi a2, a2, 16
+; RV32-NEXT:    vs8r.v v16, (a2) # Unknown-size Folded Spill
+; RV32-NEXT:    vsetvli zero, a1, e64, m8, ta, ma
+; RV32-NEXT:    vmul.vv v8, v8, v16, v0.t
+; RV32-NEXT:    li a1, 56
+; RV32-NEXT:    vsrl.vx v8, v8, a1, v0.t
+; RV32-NEXT:    csrr a2, vlenb
+; RV32-NEXT:    slli a2, a2, 4
+; RV32-NEXT:    add a2, sp, a2
+; RV32-NEXT:    addi a2, a2, 16
+; RV32-NEXT:    vs8r.v v8, (a2) # Unknown-size Folded Spill
+; RV32-NEXT:    addi a2, a0, -16
+; RV32-NEXT:    sltu a0, a0, a2
+; RV32-NEXT:    addi a0, a0, -1
+; RV32-NEXT:    and a0, a0, a2
+; RV32-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
+; RV32-NEXT:    vmv1r.v v0, v24
+; RV32-NEXT:    csrr a0, vlenb
+; RV32-NEXT:    li a2, 48
+; RV32-NEXT:    mul a0, a0, a2
+; RV32-NEXT:    add a0, sp, a0
+; RV32-NEXT:    addi a0, a0, 16
+; RV32-NEXT:    vl8r.v v8, (a0) # Unknown-size Folded Reload
+; RV32-NEXT:    vsrl.vi v8, v8, 1, v0.t
+; RV32-NEXT:    addi a0, sp, 16
+; RV32-NEXT:    vs8r.v v8, (a0) # Unknown-size Folded Spill
+; RV32-NEXT:    csrr a0, vlenb
+; RV32-NEXT:    li a2, 24
+; RV32-NEXT:    mul a0, a0, a2
+; RV32-NEXT:    add a0, sp, a0
+; RV32-NEXT:    addi a0, a0, 16
+; RV32-NEXT:    vl8r.v v8, (a0) # Unknown-size Folded Reload
+; RV32-NEXT:    addi a0, sp, 16
+; RV32-NEXT:    vl8r.v v16, (a0) # Unknown-size Folded Reload
+; RV32-NEXT:    vand.vv v8, v16, v8, v0.t
+; RV32-NEXT:    csrr a0, vlenb
+; RV32-NEXT:    li a2, 48
+; RV32-NEXT:    mul a0, a0, a2
+; RV32-NEXT:    add a0, sp, a0
+; RV32-NEXT:    addi a0, a0, 16
+; RV32-NEXT:    vl8r.v v16, (a0) # Unknown-size Folded Reload
+; RV32-NEXT:    vsub.vv v8, v16, v8, v0.t
+; RV32-NEXT:    csrr a0, vlenb
+; RV32-NEXT:    li a2, 40
+; RV32-NEXT:    mul a0, a0, a2
+; RV32-NEXT:    add a0, sp, a0
+; RV32-NEXT:    addi a0, a0, 16
+; RV32-NEXT:    vl8r.v v16, (a0) # Unknown-size Folded Reload
+; RV32-NEXT:    vand.vv v16, v8, v16, v0.t
+; RV32-NEXT:    csrr a0, vlenb
+; RV32-NEXT:    li a2, 48
+; RV32-NEXT:    mul a0, a0, a2
+; RV32-NEXT:    add a0, sp, a0
+; RV32-NEXT:    addi a0, a0, 16
+; RV32-NEXT:    vs8r.v v16, (a0) # Unknown-size Folded Spill
+; RV32-NEXT:    vsrl.vi v8, v8, 2, v0.t
+; RV32-NEXT:    csrr a0, vlenb
+; RV32-NEXT:    li a2, 40
+; RV32-NEXT:    mul a0, a0, a2
+; RV32-NEXT:    add a0, sp, a0
+; RV32-NEXT:    addi a0, a0, 16
+; RV32-NEXT:    vl8r.v v16, (a0) # Unknown-size Folded Reload
+; RV32-NEXT:    vand.vv v8, v8, v16, v0.t
+; RV32-NEXT:    csrr a0, vlenb
+; RV32-NEXT:    li a2, 48
+; RV32-NEXT:    mul a0, a0, a2
+; RV32-NEXT:    add a0, sp, a0
+; RV32-NEXT:    addi a0, a0, 16
+; RV32-NEXT:    vl8r.v v16, (a0) # Unknown-size Folded Reload
+; RV32-NEXT:    vadd.vv v8, v16, v8, v0.t
+; RV32-NEXT:    vsrl.vi v16, v8, 4, v0.t
+; RV32-NEXT:    vadd.vv v8, v8, v16, v0.t
+; RV32-NEXT:    csrr a0, vlenb
+; RV32-NEXT:    slli a0, a0, 5
+; RV32-NEXT:    add a0, sp, a0
+; RV32-NEXT:    addi a0, a0, 16
+; RV32-NEXT:    vl8r.v v16, (a0) # Unknown-size Folded Reload
+; RV32-NEXT:    vand.vv v8, v8, v16, v0.t
+; RV32-NEXT:    csrr a0, vlenb
+; RV32-NEXT:    slli a0, a0, 3
+; RV32-NEXT:    add a0, sp, a0
+; RV32-NEXT:    addi a0, a0, 16
+; RV32-NEXT:    vl8r.v v16, (a0) # Unknown-size Folded Reload
+; RV32-NEXT:    vmul.vv v8, v8, v16, v0.t
+; RV32-NEXT:    vsrl.vx v16, v8, a1, v0.t
+; RV32-NEXT:    csrr a0, vlenb
+; RV32-NEXT:    slli a0, a0, 4
+; RV32-NEXT:    add a0, sp, a0
+; RV32-NEXT:    addi a0, a0, 16
+; RV32-NEXT:    vl8r.v v8, (a0) # Unknown-size Folded Reload
+; RV32-NEXT:    csrr a0, vlenb
+; RV32-NEXT:    li a1, 56
+; RV32-NEXT:    mul a0, a0, a1
+; RV32-NEXT:    add sp, sp, a0
+; RV32-NEXT:    addi sp, sp, 16
+; RV32-NEXT:    ret
+;
+; RV64-LABEL: vp_ctpop_v32i64:
+; RV64:       # %bb.0:
+; RV64-NEXT:    addi sp, sp, -16
+; RV64-NEXT:    .cfi_def_cfa_offset 16
+; RV64-NEXT:    csrr a1, vlenb
+; RV64-NEXT:    slli a1, a1, 4
+; RV64-NEXT:    sub sp, sp, a1
+; RV64-NEXT:    .cfi_escape 0x0f, 0x0d, 0x72, 0x00, 0x11, 0x10, 0x22, 0x11, 0x10, 0x92, 0xa2, 0x38, 0x00, 0x1e, 0x22 # sp + 16 + 16 * vlenb
+; RV64-NEXT:    csrr a1, vlenb
+; RV64-NEXT:    slli a1, a1, 3
+; RV64-NEXT:    add a1, sp, a1
+; RV64-NEXT:    addi a1, a1, 16
+; RV64-NEXT:    vs8r.v v16, (a1) # Unknown-size Folded Spill
+; RV64-NEXT:    vsetivli zero, 2, e8, mf4, ta, ma
+; RV64-NEXT:    li a2, 16
+; RV64-NEXT:    vslidedown.vi v24, v0, 2
+; RV64-NEXT:    mv a1, a0
+; RV64-NEXT:    bltu a0, a2, .LBB34_2
+; RV64-NEXT:  # %bb.1:
+; RV64-NEXT:    li a1, 16
+; RV64-NEXT:  .LBB34_2:
+; RV64-NEXT:    vsetvli zero, a1, e64, m8, ta, ma
+; RV64-NEXT:    lui a1, %hi(.LCPI34_0)
+; RV64-NEXT:    ld a1, %lo(.LCPI34_0)(a1)
+; RV64-NEXT:    lui a2, %hi(.LCPI34_1)
+; RV64-NEXT:    ld a2, %lo(.LCPI34_1)(a2)
+; RV64-NEXT:    vsrl.vi v16, v8, 1, v0.t
+; RV64-NEXT:    vand.vx v16, v16, a1, v0.t
+; RV64-NEXT:    vsub.vv v8, v8, v16, v0.t
+; RV64-NEXT:    vand.vx v16, v8, a2, v0.t
+; RV64-NEXT:    vsrl.vi v8, v8, 2, v0.t
+; RV64-NEXT:    vand.vx v8, v8, a2, v0.t
+; RV64-NEXT:    vadd.vv v8, v16, v8, v0.t
+; RV64-NEXT:    lui a3, %hi(.LCPI34_2)
+; RV64-NEXT:    ld a3, %lo(.LCPI34_2)(a3)
+; RV64-NEXT:    lui a4, %hi(.LCPI34_3)
+; RV64-NEXT:    ld a4, %lo(.LCPI34_3)(a4)
+; RV64-NEXT:    vsrl.vi v16, v8, 4, v0.t
+; RV64-NEXT:    vadd.vv v8, v8, v16, v0.t
+; RV64-NEXT:    vand.vx v8, v8, a3, v0.t
+; RV64-NEXT:    vmul.vx v8, v8, a4, v0.t
+; RV64-NEXT:    li a5, 56
+; RV64-NEXT:    vsrl.vx v8, v8, a5, v0.t
+; RV64-NEXT:    addi a6, sp, 16
+; RV64-NEXT:    vs8r.v v8, (a6) # Unknown-size Folded Spill
+; RV64-NEXT:    addi a6, a0, -16
+; RV64-NEXT:    sltu a0, a0, a6
+; RV64-NEXT:    addi a0, a0, -1
+; RV64-NEXT:    and a0, a0, a6
+; RV64-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
+; RV64-NEXT:    vmv1r.v v0, v24
+; RV64-NEXT:    csrr a0, vlenb
+; RV64-NEXT:    slli a0, a0, 3
+; RV64-NEXT:    add a0, sp, a0
+; RV64-NEXT:    addi a0, a0, 16
+; RV64-NEXT:    vl8r.v v8, (a0) # Unknown-size Folded Reload
+; RV64-NEXT:    vsrl.vi v16, v8, 1, v0.t
+; RV64-NEXT:    vand.vx v16, v16, a1, v0.t
+; RV64-NEXT:    vsub.vv v16, v8, v16, v0.t
+; RV64-NEXT:    vand.vx v8, v16, a2, v0.t
+; RV64-NEXT:    vsrl.vi v16, v16, 2, v0.t
+; RV64-NEXT:    vand.vx v16, v16, a2, v0.t
+; RV64-NEXT:    vadd.vv v8, v8, v16, v0.t
+; RV64-NEXT:    vsrl.vi v16, v8, 4, v0.t
+; RV64-NEXT:    vadd.vv v8, v8, v16, v0.t
+; RV64-NEXT:    vand.vx v8, v8, a3, v0.t
+; RV64-NEXT:    vmul.vx v8, v8, a4, v0.t
+; RV64-NEXT:    vsrl.vx v16, v8, a5, v0.t
+; RV64-NEXT:    addi a0, sp, 16
+; RV64-NEXT:    vl8r.v v8, (a0) # Unknown-size Folded Reload
+; RV64-NEXT:    csrr a0, vlenb
+; RV64-NEXT:    slli a0, a0, 4
+; RV64-NEXT:    add sp, sp, a0
+; RV64-NEXT:    addi sp, sp, 16
+; RV64-NEXT:    ret
+  %v = call <32 x i64> @llvm.vp.ctpop.v32i64(<32 x i64> %va, <32 x i1> %m, i32 %evl)
+  ret <32 x i64> %v
+}
+
+define <32 x i64> @vp_ctpop_v32i64_unmasked(<32 x i64> %va, i32 zeroext %evl) {
+; RV32-LABEL: vp_ctpop_v32i64_unmasked:
+; RV32:       # %bb.0:
+; RV32-NEXT:    addi sp, sp, -16
+; RV32-NEXT:    .cfi_def_cfa_offset 16
+; RV32-NEXT:    csrr a1, vlenb
+; RV32-NEXT:    li a2, 40
+; RV32-NEXT:    mul a1, a1, a2
+; RV32-NEXT:    sub sp, sp, a1
+; RV32-NEXT:    .cfi_escape 0x0f, 0x0d, 0x72, 0x00, 0x11, 0x10, 0x22, 0x11, 0x28, 0x92, 0xa2, 0x38, 0x00, 0x1e, 0x22 # sp + 16 + 40 * vlenb
+; RV32-NEXT:    li a2, 16
+; RV32-NEXT:    csrr a1, vlenb
+; RV32-NEXT:    slli a1, a1, 5
+; RV32-NEXT:    add a1, sp, a1
+; RV32-NEXT:    addi a1, a1, 16
+; RV32-NEXT:    vs8r.v v16, (a1) # Unknown-size Folded Spill
+; RV32-NEXT:    mv a1, a0
+; RV32-NEXT:    bltu a0, a2, .LBB35_2
+; RV32-NEXT:  # %bb.1:
+; RV32-NEXT:    li a1, 16
+; RV32-NEXT:  .LBB35_2:
+; RV32-NEXT:    vsetvli zero, a1, e64, m8, ta, ma
+; RV32-NEXT:    vsrl.vi v16, v8, 1
+; RV32-NEXT:    lui a2, 349525
+; RV32-NEXT:    addi a2, a2, 1365
+; RV32-NEXT:    li a3, 32
+; RV32-NEXT:    vsetvli zero, a3, e32, m8, ta, ma
+; RV32-NEXT:    vmv.v.x v24, a2
+; RV32-NEXT:    csrr a2, vlenb
+; RV32-NEXT:    li a4, 24
+; RV32-NEXT:    mul a2, a2, a4
+; RV32-NEXT:    add a2, sp, a2
+; RV32-NEXT:    addi a2, a2, 16
+; RV32-NEXT:    vs8r.v v24, (a2) # Unknown-size Folded Spill
+; RV32-NEXT:    vsetvli zero, a1, e64, m8, ta, ma
+; RV32-NEXT:    vand.vv v16, v16, v24
+; RV32-NEXT:    vsub.vv v8, v8, v16
+; RV32-NEXT:    lui a2, 209715
+; RV32-NEXT:    addi a2, a2, 819
+; RV32-NEXT:    vsetvli zero, a3, e32, m8, ta, ma
+; RV32-NEXT:    vmv.v.x v0, a2
+; RV32-NEXT:    vsetvli zero, a1, e64, m8, ta, ma
+; RV32-NEXT:    vand.vv v16, v8, v0
+; RV32-NEXT:    vsrl.vi v8, v8, 2
+; RV32-NEXT:    vand.vv v8, v8, v0
+; RV32-NEXT:    vadd.vv v8, v16, v8
+; RV32-NEXT:    vsrl.vi v16, v8, 4
+; RV32-NEXT:    vadd.vv v8, v8, v16
+; RV32-NEXT:    lui a2, 61681
+; RV32-NEXT:    addi a2, a2, -241
+; RV32-NEXT:    vsetvli zero, a3, e32, m8, ta, ma
+; RV32-NEXT:    vmv.v.x v16, a2
+; RV32-NEXT:    csrr a2, vlenb
+; RV32-NEXT:    slli a2, a2, 4
+; RV32-NEXT:    add a2, sp, a2
+; RV32-NEXT:    addi a2, a2, 16
+; RV32-NEXT:    vs8r.v v16, (a2) # Unknown-size Folded Spill
+; RV32-NEXT:    vsetvli zero, a1, e64, m8, ta, ma
+; RV32-NEXT:    vand.vv v24, v8, v16
+; RV32-NEXT:    lui a2, 4112
+; RV32-NEXT:    addi a2, a2, 257
+; RV32-NEXT:    vsetvli zero, a3, e32, m8, ta, ma
+; RV32-NEXT:    vmv.v.x v8, a2
+; RV32-NEXT:    addi a2, sp, 16
+; RV32-NEXT:    vs8r.v v8, (a2) # Unknown-size Folded Spill
+; RV32-NEXT:    vsetvli zero, a1, e64, m8, ta, ma
+; RV32-NEXT:    vmul.vv v24, v24, v8
+; RV32-NEXT:    li a1, 56
+; RV32-NEXT:    vsrl.vx v8, v24, a1
+; RV32-NEXT:    csrr a2, vlenb
+; RV32-NEXT:    slli a2, a2, 3
+; RV32-NEXT:    add a2, sp, a2
+; RV32-NEXT:    addi a2, a2, 16
+; RV32-NEXT:    vs8r.v v8, (a2) # Unknown-size Folded Spill
+; RV32-NEXT:    addi a2, a0, -16
+; RV32-NEXT:    sltu a0, a0, a2
+; RV32-NEXT:    addi a0, a0, -1
+; RV32-NEXT:    and a0, a0, a2
+; RV32-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
+; RV32-NEXT:    csrr a0, vlenb
+; RV32-NEXT:    slli a0, a0, 5
+; RV32-NEXT:    add a0, sp, a0
+; RV32-NEXT:    addi a0, a0, 16
+; RV32-NEXT:    vl8r.v v8, (a0) # Unknown-size Folded Reload
+; RV32-NEXT:    vsrl.vi v24, v8, 1
+; RV32-NEXT:    csrr a0, vlenb
+; RV32-NEXT:    li a2, 24
+; RV32-NEXT:    mul a0, a0, a2
+; RV32-NEXT:    add a0, sp, a0
+; RV32-NEXT:    addi a0, a0, 16
+; RV32-NEXT:    vl8r.v v16, (a0) # Unknown-size Folded Reload
+; RV32-NEXT:    vand.vv v24, v24, v16
+; RV32-NEXT:    vsub.vv v24, v8, v24
+; RV32-NEXT:    vand.vv v8, v24, v0
+; RV32-NEXT:    vsrl.vi v24, v24, 2
+; RV32-NEXT:    vand.vv v24, v24, v0
+; RV32-NEXT:    vadd.vv v8, v8, v24
+; RV32-NEXT:    vsrl.vi v24, v8, 4
+; RV32-NEXT:    vadd.vv v8, v8, v24
+; RV32-NEXT:    csrr a0, vlenb
+; RV32-NEXT:    slli a0, a0, 4
+; RV32-NEXT:    add a0, sp, a0
+; RV32-NEXT:    addi a0, a0, 16
+; RV32-NEXT:    vl8r.v v16, (a0) # Unknown-size Folded Reload
+; RV32-NEXT:    vand.vv v8, v8, v16
+; RV32-NEXT:    addi a0, sp, 16
+; RV32-NEXT:    vl8r.v v16, (a0) # Unknown-size Folded Reload
+; RV32-NEXT:    vmul.vv v8, v8, v16
+; RV32-NEXT:    vsrl.vx v16, v8, a1
+; RV32-NEXT:    csrr a0, vlenb
+; RV32-NEXT:    slli a0, a0, 3
+; RV32-NEXT:    add a0, sp, a0
+; RV32-NEXT:    addi a0, a0, 16
+; RV32-NEXT:    vl8r.v v8, (a0) # Unknown-size Folded Reload
+; RV32-NEXT:    csrr a0, vlenb
+; RV32-NEXT:    li a1, 40
+; RV32-NEXT:    mul a0, a0, a1
+; RV32-NEXT:    add sp, sp, a0
+; RV32-NEXT:    addi sp, sp, 16
+; RV32-NEXT:    ret
+;
+; RV64-LABEL: vp_ctpop_v32i64_unmasked:
+; RV64:       # %bb.0:
+; RV64-NEXT:    li a2, 16
+; RV64-NEXT:    mv a1, a0
+; RV64-NEXT:    bltu a0, a2, .LBB35_2
+; RV64-NEXT:  # %bb.1:
+; RV64-NEXT:    li a1, 16
+; RV64-NEXT:  .LBB35_2:
+; RV64-NEXT:    vsetvli zero, a1, e64, m8, ta, ma
+; RV64-NEXT:    lui a1, %hi(.LCPI35_0)
+; RV64-NEXT:    ld a1, %lo(.LCPI35_0)(a1)
+; RV64-NEXT:    lui a2, %hi(.LCPI35_1)
+; RV64-NEXT:    ld a2, %lo(.LCPI35_1)(a2)
+; RV64-NEXT:    vsrl.vi v24, v8, 1
+; RV64-NEXT:    vand.vx v24, v24, a1
+; RV64-NEXT:    vsub.vv v8, v8, v24
+; RV64-NEXT:    vand.vx v24, v8, a2
+; RV64-NEXT:    vsrl.vi v8, v8, 2
+; RV64-NEXT:    vand.vx v8, v8, a2
+; RV64-NEXT:    vadd.vv v8, v24, v8
+; RV64-NEXT:    lui a3, %hi(.LCPI35_2)
+; RV64-NEXT:    ld a3, %lo(.LCPI35_2)(a3)
+; RV64-NEXT:    lui a4, %hi(.LCPI35_3)
+; RV64-NEXT:    ld a4, %lo(.LCPI35_3)(a4)
+; RV64-NEXT:    vsrl.vi v24, v8, 4
+; RV64-NEXT:    vadd.vv v8, v8, v24
+; RV64-NEXT:    vand.vx v8, v8, a3
+; RV64-NEXT:    vmul.vx v8, v8, a4
+; RV64-NEXT:    li a5, 56
+; RV64-NEXT:    vsrl.vx v8, v8, a5
+; RV64-NEXT:    addi a6, a0, -16
+; RV64-NEXT:    sltu a0, a0, a6
+; RV64-NEXT:    addi a0, a0, -1
+; RV64-NEXT:    and a0, a0, a6
+; RV64-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
+; RV64-NEXT:    vsrl.vi v24, v16, 1
+; RV64-NEXT:    vand.vx v24, v24, a1
+; RV64-NEXT:    vsub.vv v16, v16, v24
+; RV64-NEXT:    vand.vx v24, v16, a2
+; RV64-NEXT:    vsrl.vi v16, v16, 2
+; RV64-NEXT:    vand.vx v16, v16, a2
+; RV64-NEXT:    vadd.vv v16, v24, v16
+; RV64-NEXT:    vsrl.vi v24, v16, 4
+; RV64-NEXT:    vadd.vv v16, v16, v24
+; RV64-NEXT:    vand.vx v16, v16, a3
+; RV64-NEXT:    vmul.vx v16, v16, a4
+; RV64-NEXT:    vsrl.vx v16, v16, a5
+; RV64-NEXT:    ret
+  %head = insertelement <32 x i1> poison, i1 true, i32 0
+  %m = shufflevector <32 x i1> %head, <32 x i1> poison, <32 x i32> zeroinitializer
+  %v = call <32 x i64> @llvm.vp.ctpop.v32i64(<32 x i64> %va, <32 x i1> %m, i32 %evl)
+  ret <32 x i64> %v
+}

llvm/unittests/IR/VPIntrinsicTest.cpp

Str << " declare <8 x i1> @llvm.vp.fcmp.v8f32"
         << "(<8 x float>, <8 x float>, metadata, <8 x i1>, i32) ";
     Str << " declare <8 x i1> @llvm.vp.icmp.v8i16"
         << "(<8 x i16>, <8 x i16>, metadata, <8 x i1>, i32) ";
 
     Str << " declare <8 x i16> @llvm.vp.bitreverse.v8i16"
         << "(<8 x i16>, <8 x i1>, i32) ";
     Str << " declare <8 x i16> @llvm.vp.bswap.v8i16"
         << "(<8 x i16>, <8 x i1>, i32) ";
+    Str << " declare <8 x i16> @llvm.vp.ctpop.v8i16"
+        << "(<8 x i16>, <8 x i1>, i32) ";
     Str << " declare <8 x i16> @llvm.vp.fshl.v8i16"
         << "(<8 x i16>, <8 x i16>, <8 x i16>, <8 x i1>, i32) ";
     Str << " declare <8 x i16> @llvm.vp.fshr.v8i16"
         << "(<8 x i16>, <8 x i16>, <8 x i16>, <8 x i1>, i32) ";
 
     return parseAssemblyString(Str.str(), Err, C);
   }
 };