; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=riscv32 -mattr=+v,+m -target-abi=ilp32d \
; RUN:     -verify-machineinstrs < %s | FileCheck %s --check-prefixes=CHECK,RV32
; RUN: llc -mtriple=riscv64 -mattr=+v,+m -target-abi=lp64d \
; RUN:     -verify-machineinstrs < %s | FileCheck %s --check-prefixes=CHECK,RV64
; RUN: llc -mtriple=riscv32 -mattr=+v,+zvbb,+m -target-abi=ilp32d \
; RUN:     -verify-machineinstrs < %s | FileCheck %s --check-prefixes=CHECK-ZVBB
; RUN: llc -mtriple=riscv64 -mattr=+v,+zvbb,+m -target-abi=lp64d \
; RUN:     -verify-machineinstrs < %s | FileCheck %s --check-prefixes=CHECK-ZVBB

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:    li a0, 51
; CHECK-NEXT:    vsub.vv v8, v8, v9, v0.t
; 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
;
; CHECK-ZVBB-LABEL: vp_ctpop_nxv1i8:
; CHECK-ZVBB:       # %bb.0:
; CHECK-ZVBB-NEXT:    vsetvli zero, a0, e8, mf8, ta, ma
; CHECK-ZVBB-NEXT:    vcpop.v v8, v8, v0.t
; CHECK-ZVBB-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:    li a0, 51
; CHECK-NEXT:    vsub.vv v8, v8, v9
; 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
;
; CHECK-ZVBB-LABEL: vp_ctpop_nxv1i8_unmasked:
; CHECK-ZVBB:       # %bb.0:
; CHECK-ZVBB-NEXT:    vsetvli zero, a0, e8, mf8, ta, ma
; CHECK-ZVBB-NEXT:    vcpop.v v8, v8
; CHECK-ZVBB-NEXT:    ret
  %v = call <vscale x 1 x i8> @llvm.vp.ctpop.nxv1i8(<vscale x 1 x i8> %va, <vscale x 1 x i1> splat (i1 true), 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:    li a0, 51
; CHECK-NEXT:    vsub.vv v8, v8, v9, v0.t
; 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
;
; CHECK-ZVBB-LABEL: vp_ctpop_nxv2i8:
; CHECK-ZVBB:       # %bb.0:
; CHECK-ZVBB-NEXT:    vsetvli zero, a0, e8, mf4, ta, ma
; CHECK-ZVBB-NEXT:    vcpop.v v8, v8, v0.t
; CHECK-ZVBB-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:    li a0, 51
; CHECK-NEXT:    vsub.vv v8, v8, v9
; 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
;
; CHECK-ZVBB-LABEL: vp_ctpop_nxv2i8_unmasked:
; CHECK-ZVBB:       # %bb.0:
; CHECK-ZVBB-NEXT:    vsetvli zero, a0, e8, mf4, ta, ma
; CHECK-ZVBB-NEXT:    vcpop.v v8, v8
; CHECK-ZVBB-NEXT:    ret
  %v = call <vscale x 2 x i8> @llvm.vp.ctpop.nxv2i8(<vscale x 2 x i8> %va, <vscale x 2 x i1> splat (i1 true), 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:    li a0, 51
; CHECK-NEXT:    vsub.vv v8, v8, v9, v0.t
; 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
;
; CHECK-ZVBB-LABEL: vp_ctpop_nxv4i8:
; CHECK-ZVBB:       # %bb.0:
; CHECK-ZVBB-NEXT:    vsetvli zero, a0, e8, mf2, ta, ma
; CHECK-ZVBB-NEXT:    vcpop.v v8, v8, v0.t
; CHECK-ZVBB-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:    li a0, 51
; CHECK-NEXT:    vsub.vv v8, v8, v9
; 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
;
; CHECK-ZVBB-LABEL: vp_ctpop_nxv4i8_unmasked:
; CHECK-ZVBB:       # %bb.0:
; CHECK-ZVBB-NEXT:    vsetvli zero, a0, e8, mf2, ta, ma
; CHECK-ZVBB-NEXT:    vcpop.v v8, v8
; CHECK-ZVBB-NEXT:    ret
  %v = call <vscale x 4 x i8> @llvm.vp.ctpop.nxv4i8(<vscale x 4 x i8> %va, <vscale x 4 x i1> splat (i1 true), 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:    li a0, 51
; CHECK-NEXT:    vsub.vv v8, v8, v9, v0.t
; 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
;
; CHECK-ZVBB-LABEL: vp_ctpop_nxv8i8:
; CHECK-ZVBB:       # %bb.0:
; CHECK-ZVBB-NEXT:    vsetvli zero, a0, e8, m1, ta, ma
; CHECK-ZVBB-NEXT:    vcpop.v v8, v8, v0.t
; CHECK-ZVBB-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:    li a0, 51
; CHECK-NEXT:    vsub.vv v8, v8, v9
; 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
;
; CHECK-ZVBB-LABEL: vp_ctpop_nxv8i8_unmasked:
; CHECK-ZVBB:       # %bb.0:
; CHECK-ZVBB-NEXT:    vsetvli zero, a0, e8, m1, ta, ma
; CHECK-ZVBB-NEXT:    vcpop.v v8, v8
; CHECK-ZVBB-NEXT:    ret
  %v = call <vscale x 8 x i8> @llvm.vp.ctpop.nxv8i8(<vscale x 8 x i8> %va, <vscale x 8 x i1> splat (i1 true), 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:    li a0, 51
; CHECK-NEXT:    vsub.vv v8, v8, v10, v0.t
; 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
;
; CHECK-ZVBB-LABEL: vp_ctpop_nxv16i8:
; CHECK-ZVBB:       # %bb.0:
; CHECK-ZVBB-NEXT:    vsetvli zero, a0, e8, m2, ta, ma
; CHECK-ZVBB-NEXT:    vcpop.v v8, v8, v0.t
; CHECK-ZVBB-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:    li a0, 51
; CHECK-NEXT:    vsub.vv v8, v8, v10
; 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
;
; CHECK-ZVBB-LABEL: vp_ctpop_nxv16i8_unmasked:
; CHECK-ZVBB:       # %bb.0:
; CHECK-ZVBB-NEXT:    vsetvli zero, a0, e8, m2, ta, ma
; CHECK-ZVBB-NEXT:    vcpop.v v8, v8
; CHECK-ZVBB-NEXT:    ret
  %v = call <vscale x 16 x i8> @llvm.vp.ctpop.nxv16i8(<vscale x 16 x i8> %va, <vscale x 16 x i1> splat (i1 true), 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:    li a0, 51
; CHECK-NEXT:    vsub.vv v8, v8, v12, v0.t
; 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
;
; CHECK-ZVBB-LABEL: vp_ctpop_nxv32i8:
; CHECK-ZVBB:       # %bb.0:
; CHECK-ZVBB-NEXT:    vsetvli zero, a0, e8, m4, ta, ma
; CHECK-ZVBB-NEXT:    vcpop.v v8, v8, v0.t
; CHECK-ZVBB-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:    li a0, 51
; CHECK-NEXT:    vsub.vv v8, v8, v12
; 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
;
; CHECK-ZVBB-LABEL: vp_ctpop_nxv32i8_unmasked:
; CHECK-ZVBB:       # %bb.0:
; CHECK-ZVBB-NEXT:    vsetvli zero, a0, e8, m4, ta, ma
; CHECK-ZVBB-NEXT:    vcpop.v v8, v8
; CHECK-ZVBB-NEXT:    ret
  %v = call <vscale x 32 x i8> @llvm.vp.ctpop.nxv32i8(<vscale x 32 x i8> %va, <vscale x 32 x i1> splat (i1 true), 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:    li a0, 51
; CHECK-NEXT:    vsub.vv v8, v8, v16, v0.t
; 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
;
; CHECK-ZVBB-LABEL: vp_ctpop_nxv64i8:
; CHECK-ZVBB:       # %bb.0:
; CHECK-ZVBB-NEXT:    vsetvli zero, a0, e8, m8, ta, ma
; CHECK-ZVBB-NEXT:    vcpop.v v8, v8, v0.t
; CHECK-ZVBB-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:    li a0, 51
; CHECK-NEXT:    vsub.vv v8, v8, v16
; 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
;
; CHECK-ZVBB-LABEL: vp_ctpop_nxv64i8_unmasked:
; CHECK-ZVBB:       # %bb.0:
; CHECK-ZVBB-NEXT:    vsetvli zero, a0, e8, m8, ta, ma
; CHECK-ZVBB-NEXT:    vcpop.v v8, v8
; CHECK-ZVBB-NEXT:    ret
  %v = call <vscale x 64 x i8> @llvm.vp.ctpop.nxv64i8(<vscale x 64 x i8> %va, <vscale x 64 x i1> splat (i1 true), 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) {
; CHECK-LABEL: vp_ctpop_nxv1i16:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a0, e16, mf4, ta, ma
; CHECK-NEXT:    vsrl.vi v9, v8, 1, v0.t
; CHECK-NEXT:    lui a0, 5
; CHECK-NEXT:    addi a0, a0, 1365
; CHECK-NEXT:    vand.vx v9, v9, a0, v0.t
; CHECK-NEXT:    lui a0, 3
; CHECK-NEXT:    addi a0, a0, 819
; CHECK-NEXT:    vsub.vv v8, v8, v9, v0.t
; 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:    lui a0, 1
; CHECK-NEXT:    addi a0, a0, -241
; 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.vx v8, v8, a0, v0.t
; CHECK-NEXT:    li a0, 257
; CHECK-NEXT:    vmul.vx v8, v8, a0, v0.t
; CHECK-NEXT:    vsrl.vi v8, v8, 8, v0.t
; CHECK-NEXT:    ret
;
; CHECK-ZVBB-LABEL: vp_ctpop_nxv1i16:
; CHECK-ZVBB:       # %bb.0:
; CHECK-ZVBB-NEXT:    vsetvli zero, a0, e16, mf4, ta, ma
; CHECK-ZVBB-NEXT:    vcpop.v v8, v8, v0.t
; CHECK-ZVBB-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) {
; CHECK-LABEL: vp_ctpop_nxv1i16_unmasked:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a0, e16, mf4, ta, ma
; CHECK-NEXT:    vsrl.vi v9, v8, 1
; CHECK-NEXT:    lui a0, 5
; CHECK-NEXT:    addi a0, a0, 1365
; CHECK-NEXT:    vand.vx v9, v9, a0
; CHECK-NEXT:    lui a0, 3
; CHECK-NEXT:    addi a0, a0, 819
; CHECK-NEXT:    vsub.vv v8, v8, v9
; CHECK-NEXT:    vand.vx v9, v8, a0
; CHECK-NEXT:    vsrl.vi v8, v8, 2
; CHECK-NEXT:    vand.vx v8, v8, a0
; CHECK-NEXT:    lui a0, 1
; CHECK-NEXT:    addi a0, a0, -241
; CHECK-NEXT:    vadd.vv v8, v9, v8
; CHECK-NEXT:    vsrl.vi v9, v8, 4
; CHECK-NEXT:    vadd.vv v8, v8, v9
; CHECK-NEXT:    vand.vx v8, v8, a0
; CHECK-NEXT:    li a0, 257
; CHECK-NEXT:    vmul.vx v8, v8, a0
; CHECK-NEXT:    vsrl.vi v8, v8, 8
; CHECK-NEXT:    ret
;
; CHECK-ZVBB-LABEL: vp_ctpop_nxv1i16_unmasked:
; CHECK-ZVBB:       # %bb.0:
; CHECK-ZVBB-NEXT:    vsetvli zero, a0, e16, mf4, ta, ma
; CHECK-ZVBB-NEXT:    vcpop.v v8, v8
; CHECK-ZVBB-NEXT:    ret
  %v = call <vscale x 1 x i16> @llvm.vp.ctpop.nxv1i16(<vscale x 1 x i16> %va, <vscale x 1 x i1> splat (i1 true), 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) {
; CHECK-LABEL: vp_ctpop_nxv2i16:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a0, e16, mf2, ta, ma
; CHECK-NEXT:    vsrl.vi v9, v8, 1, v0.t
; CHECK-NEXT:    lui a0, 5
; CHECK-NEXT:    addi a0, a0, 1365
; CHECK-NEXT:    vand.vx v9, v9, a0, v0.t
; CHECK-NEXT:    lui a0, 3
; CHECK-NEXT:    addi a0, a0, 819
; CHECK-NEXT:    vsub.vv v8, v8, v9, v0.t
; 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:    lui a0, 1
; CHECK-NEXT:    addi a0, a0, -241
; 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.vx v8, v8, a0, v0.t
; CHECK-NEXT:    li a0, 257
; CHECK-NEXT:    vmul.vx v8, v8, a0, v0.t
; CHECK-NEXT:    vsrl.vi v8, v8, 8, v0.t
; CHECK-NEXT:    ret
;
; CHECK-ZVBB-LABEL: vp_ctpop_nxv2i16:
; CHECK-ZVBB:       # %bb.0:
; CHECK-ZVBB-NEXT:    vsetvli zero, a0, e16, mf2, ta, ma
; CHECK-ZVBB-NEXT:    vcpop.v v8, v8, v0.t
; CHECK-ZVBB-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) {
; CHECK-LABEL: vp_ctpop_nxv2i16_unmasked:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a0, e16, mf2, ta, ma
; CHECK-NEXT:    vsrl.vi v9, v8, 1
; CHECK-NEXT:    lui a0, 5
; CHECK-NEXT:    addi a0, a0, 1365
; CHECK-NEXT:    vand.vx v9, v9, a0
; CHECK-NEXT:    lui a0, 3
; CHECK-NEXT:    addi a0, a0, 819
; CHECK-NEXT:    vsub.vv v8, v8, v9
; CHECK-NEXT:    vand.vx v9, v8, a0
; CHECK-NEXT:    vsrl.vi v8, v8, 2
; CHECK-NEXT:    vand.vx v8, v8, a0
; CHECK-NEXT:    lui a0, 1
; CHECK-NEXT:    addi a0, a0, -241
; CHECK-NEXT:    vadd.vv v8, v9, v8
; CHECK-NEXT:    vsrl.vi v9, v8, 4
; CHECK-NEXT:    vadd.vv v8, v8, v9
; CHECK-NEXT:    vand.vx v8, v8, a0
; CHECK-NEXT:    li a0, 257
; CHECK-NEXT:    vmul.vx v8, v8, a0
; CHECK-NEXT:    vsrl.vi v8, v8, 8
; CHECK-NEXT:    ret
;
; CHECK-ZVBB-LABEL: vp_ctpop_nxv2i16_unmasked:
; CHECK-ZVBB:       # %bb.0:
; CHECK-ZVBB-NEXT:    vsetvli zero, a0, e16, mf2, ta, ma
; CHECK-ZVBB-NEXT:    vcpop.v v8, v8
; CHECK-ZVBB-NEXT:    ret
  %v = call <vscale x 2 x i16> @llvm.vp.ctpop.nxv2i16(<vscale x 2 x i16> %va, <vscale x 2 x i1> splat (i1 true), 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) {
; CHECK-LABEL: vp_ctpop_nxv4i16:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a0, e16, m1, ta, ma
; CHECK-NEXT:    vsrl.vi v9, v8, 1, v0.t
; CHECK-NEXT:    lui a0, 5
; CHECK-NEXT:    addi a0, a0, 1365
; CHECK-NEXT:    vand.vx v9, v9, a0, v0.t
; CHECK-NEXT:    lui a0, 3
; CHECK-NEXT:    addi a0, a0, 819
; CHECK-NEXT:    vsub.vv v8, v8, v9, v0.t
; 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:    lui a0, 1
; CHECK-NEXT:    addi a0, a0, -241
; 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.vx v8, v8, a0, v0.t
; CHECK-NEXT:    li a0, 257
; CHECK-NEXT:    vmul.vx v8, v8, a0, v0.t
; CHECK-NEXT:    vsrl.vi v8, v8, 8, v0.t
; CHECK-NEXT:    ret
;
; CHECK-ZVBB-LABEL: vp_ctpop_nxv4i16:
; CHECK-ZVBB:       # %bb.0:
; CHECK-ZVBB-NEXT:    vsetvli zero, a0, e16, m1, ta, ma
; CHECK-ZVBB-NEXT:    vcpop.v v8, v8, v0.t
; CHECK-ZVBB-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) {
; CHECK-LABEL: vp_ctpop_nxv4i16_unmasked:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a0, e16, m1, ta, ma
; CHECK-NEXT:    vsrl.vi v9, v8, 1
; CHECK-NEXT:    lui a0, 5
; CHECK-NEXT:    addi a0, a0, 1365
; CHECK-NEXT:    vand.vx v9, v9, a0
; CHECK-NEXT:    lui a0, 3
; CHECK-NEXT:    addi a0, a0, 819
; CHECK-NEXT:    vsub.vv v8, v8, v9
; CHECK-NEXT:    vand.vx v9, v8, a0
; CHECK-NEXT:    vsrl.vi v8, v8, 2
; CHECK-NEXT:    vand.vx v8, v8, a0
; CHECK-NEXT:    lui a0, 1
; CHECK-NEXT:    addi a0, a0, -241
; CHECK-NEXT:    vadd.vv v8, v9, v8
; CHECK-NEXT:    vsrl.vi v9, v8, 4
; CHECK-NEXT:    vadd.vv v8, v8, v9
; CHECK-NEXT:    vand.vx v8, v8, a0
; CHECK-NEXT:    li a0, 257
; CHECK-NEXT:    vmul.vx v8, v8, a0
; CHECK-NEXT:    vsrl.vi v8, v8, 8
; CHECK-NEXT:    ret
;
; CHECK-ZVBB-LABEL: vp_ctpop_nxv4i16_unmasked:
; CHECK-ZVBB:       # %bb.0:
; CHECK-ZVBB-NEXT:    vsetvli zero, a0, e16, m1, ta, ma
; CHECK-ZVBB-NEXT:    vcpop.v v8, v8
; CHECK-ZVBB-NEXT:    ret
  %v = call <vscale x 4 x i16> @llvm.vp.ctpop.nxv4i16(<vscale x 4 x i16> %va, <vscale x 4 x i1> splat (i1 true), 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) {
; CHECK-LABEL: vp_ctpop_nxv8i16:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a0, e16, m2, ta, ma
; CHECK-NEXT:    vsrl.vi v10, v8, 1, v0.t
; CHECK-NEXT:    lui a0, 5
; CHECK-NEXT:    addi a0, a0, 1365
; CHECK-NEXT:    vand.vx v10, v10, a0, v0.t
; CHECK-NEXT:    lui a0, 3
; CHECK-NEXT:    addi a0, a0, 819
; CHECK-NEXT:    vsub.vv v8, v8, v10, v0.t
; 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:    lui a0, 1
; CHECK-NEXT:    addi a0, a0, -241
; 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.vx v8, v8, a0, v0.t
; CHECK-NEXT:    li a0, 257
; CHECK-NEXT:    vmul.vx v8, v8, a0, v0.t
; CHECK-NEXT:    vsrl.vi v8, v8, 8, v0.t
; CHECK-NEXT:    ret
;
; CHECK-ZVBB-LABEL: vp_ctpop_nxv8i16:
; CHECK-ZVBB:       # %bb.0:
; CHECK-ZVBB-NEXT:    vsetvli zero, a0, e16, m2, ta, ma
; CHECK-ZVBB-NEXT:    vcpop.v v8, v8, v0.t
; CHECK-ZVBB-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) {
; CHECK-LABEL: vp_ctpop_nxv8i16_unmasked:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a0, e16, m2, ta, ma
; CHECK-NEXT:    vsrl.vi v10, v8, 1
; CHECK-NEXT:    lui a0, 5
; CHECK-NEXT:    addi a0, a0, 1365
; CHECK-NEXT:    vand.vx v10, v10, a0
; CHECK-NEXT:    lui a0, 3
; CHECK-NEXT:    addi a0, a0, 819
; CHECK-NEXT:    vsub.vv v8, v8, v10
; CHECK-NEXT:    vand.vx v10, v8, a0
; CHECK-NEXT:    vsrl.vi v8, v8, 2
; CHECK-NEXT:    vand.vx v8, v8, a0
; CHECK-NEXT:    lui a0, 1
; CHECK-NEXT:    addi a0, a0, -241
; CHECK-NEXT:    vadd.vv v8, v10, v8
; CHECK-NEXT:    vsrl.vi v10, v8, 4
; CHECK-NEXT:    vadd.vv v8, v8, v10
; CHECK-NEXT:    vand.vx v8, v8, a0
; CHECK-NEXT:    li a0, 257
; CHECK-NEXT:    vmul.vx v8, v8, a0
; CHECK-NEXT:    vsrl.vi v8, v8, 8
; CHECK-NEXT:    ret
;
; CHECK-ZVBB-LABEL: vp_ctpop_nxv8i16_unmasked:
; CHECK-ZVBB:       # %bb.0:
; CHECK-ZVBB-NEXT:    vsetvli zero, a0, e16, m2, ta, ma
; CHECK-ZVBB-NEXT:    vcpop.v v8, v8
; CHECK-ZVBB-NEXT:    ret
  %v = call <vscale x 8 x i16> @llvm.vp.ctpop.nxv8i16(<vscale x 8 x i16> %va, <vscale x 8 x i1> splat (i1 true), 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) {
; CHECK-LABEL: vp_ctpop_nxv16i16:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a0, e16, m4, ta, ma
; CHECK-NEXT:    vsrl.vi v12, v8, 1, v0.t
; CHECK-NEXT:    lui a0, 5
; CHECK-NEXT:    addi a0, a0, 1365
; CHECK-NEXT:    vand.vx v12, v12, a0, v0.t
; CHECK-NEXT:    lui a0, 3
; CHECK-NEXT:    addi a0, a0, 819
; CHECK-NEXT:    vsub.vv v8, v8, v12, v0.t
; 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:    lui a0, 1
; CHECK-NEXT:    addi a0, a0, -241
; 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.vx v8, v8, a0, v0.t
; CHECK-NEXT:    li a0, 257
; CHECK-NEXT:    vmul.vx v8, v8, a0, v0.t
; CHECK-NEXT:    vsrl.vi v8, v8, 8, v0.t
; CHECK-NEXT:    ret
;
; CHECK-ZVBB-LABEL: vp_ctpop_nxv16i16:
; CHECK-ZVBB:       # %bb.0:
; CHECK-ZVBB-NEXT:    vsetvli zero, a0, e16, m4, ta, ma
; CHECK-ZVBB-NEXT:    vcpop.v v8, v8, v0.t
; CHECK-ZVBB-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) {
; CHECK-LABEL: vp_ctpop_nxv16i16_unmasked:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a0, e16, m4, ta, ma
; CHECK-NEXT:    vsrl.vi v12, v8, 1
; CHECK-NEXT:    lui a0, 5
; CHECK-NEXT:    addi a0, a0, 1365
; CHECK-NEXT:    vand.vx v12, v12, a0
; CHECK-NEXT:    lui a0, 3
; CHECK-NEXT:    addi a0, a0, 819
; CHECK-NEXT:    vsub.vv v8, v8, v12
; CHECK-NEXT:    vand.vx v12, v8, a0
; CHECK-NEXT:    vsrl.vi v8, v8, 2
; CHECK-NEXT:    vand.vx v8, v8, a0
; CHECK-NEXT:    lui a0, 1
; CHECK-NEXT:    addi a0, a0, -241
; CHECK-NEXT:    vadd.vv v8, v12, v8
; CHECK-NEXT:    vsrl.vi v12, v8, 4
; CHECK-NEXT:    vadd.vv v8, v8, v12
; CHECK-NEXT:    vand.vx v8, v8, a0
; CHECK-NEXT:    li a0, 257
; CHECK-NEXT:    vmul.vx v8, v8, a0
; CHECK-NEXT:    vsrl.vi v8, v8, 8
; CHECK-NEXT:    ret
;
; CHECK-ZVBB-LABEL: vp_ctpop_nxv16i16_unmasked:
; CHECK-ZVBB:       # %bb.0:
; CHECK-ZVBB-NEXT:    vsetvli zero, a0, e16, m4, ta, ma
; CHECK-ZVBB-NEXT:    vcpop.v v8, v8
; CHECK-ZVBB-NEXT:    ret
  %v = call <vscale x 16 x i16> @llvm.vp.ctpop.nxv16i16(<vscale x 16 x i16> %va, <vscale x 16 x i1> splat (i1 true), 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) {
; CHECK-LABEL: vp_ctpop_nxv32i16:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a0, e16, m8, ta, ma
; CHECK-NEXT:    vsrl.vi v16, v8, 1, v0.t
; CHECK-NEXT:    lui a0, 5
; CHECK-NEXT:    addi a0, a0, 1365
; CHECK-NEXT:    vand.vx v16, v16, a0, v0.t
; CHECK-NEXT:    lui a0, 3
; CHECK-NEXT:    addi a0, a0, 819
; CHECK-NEXT:    vsub.vv v16, v8, v16, v0.t
; CHECK-NEXT:    vand.vx v8, v16, a0, v0.t
; CHECK-NEXT:    vsrl.vi v16, v16, 2, v0.t
; CHECK-NEXT:    vand.vx v16, v16, a0, v0.t
; CHECK-NEXT:    lui a0, 1
; CHECK-NEXT:    addi a0, a0, -241
; CHECK-NEXT:    vadd.vv v8, v8, v16, v0.t
; CHECK-NEXT:    vsrl.vi v16, v8, 4, v0.t
; CHECK-NEXT:    vadd.vv v8, v8, v16, v0.t
; CHECK-NEXT:    vand.vx v8, v8, a0, v0.t
; CHECK-NEXT:    li a0, 257
; CHECK-NEXT:    vmul.vx v8, v8, a0, v0.t
; CHECK-NEXT:    vsrl.vi v8, v8, 8, v0.t
; CHECK-NEXT:    ret
;
; CHECK-ZVBB-LABEL: vp_ctpop_nxv32i16:
; CHECK-ZVBB:       # %bb.0:
; CHECK-ZVBB-NEXT:    vsetvli zero, a0, e16, m8, ta, ma
; CHECK-ZVBB-NEXT:    vcpop.v v8, v8, v0.t
; CHECK-ZVBB-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) {
; CHECK-LABEL: vp_ctpop_nxv32i16_unmasked:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a0, e16, m8, ta, ma
; CHECK-NEXT:    vsrl.vi v16, v8, 1
; CHECK-NEXT:    lui a0, 5
; CHECK-NEXT:    addi a0, a0, 1365
; CHECK-NEXT:    vand.vx v16, v16, a0
; CHECK-NEXT:    lui a0, 3
; CHECK-NEXT:    addi a0, a0, 819
; CHECK-NEXT:    vsub.vv v8, v8, v16
; CHECK-NEXT:    vand.vx v16, v8, a0
; CHECK-NEXT:    vsrl.vi v8, v8, 2
; CHECK-NEXT:    vand.vx v8, v8, a0
; CHECK-NEXT:    lui a0, 1
; CHECK-NEXT:    addi a0, a0, -241
; CHECK-NEXT:    vadd.vv v8, v16, v8
; CHECK-NEXT:    vsrl.vi v16, v8, 4
; CHECK-NEXT:    vadd.vv v8, v8, v16
; CHECK-NEXT:    vand.vx v8, v8, a0
; CHECK-NEXT:    li a0, 257
; CHECK-NEXT:    vmul.vx v8, v8, a0
; CHECK-NEXT:    vsrl.vi v8, v8, 8
; CHECK-NEXT:    ret
;
; CHECK-ZVBB-LABEL: vp_ctpop_nxv32i16_unmasked:
; CHECK-ZVBB:       # %bb.0:
; CHECK-ZVBB-NEXT:    vsetvli zero, a0, e16, m8, ta, ma
; CHECK-ZVBB-NEXT:    vcpop.v v8, v8
; CHECK-ZVBB-NEXT:    ret
  %v = call <vscale x 32 x i16> @llvm.vp.ctpop.nxv32i16(<vscale x 32 x i16> %va, <vscale x 32 x i1> splat (i1 true), 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) {
; CHECK-LABEL: vp_ctpop_nxv1i32:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a0, e32, mf2, ta, ma
; CHECK-NEXT:    vsrl.vi v9, v8, 1, v0.t
; CHECK-NEXT:    lui a0, 349525
; CHECK-NEXT:    addi a0, a0, 1365
; CHECK-NEXT:    vand.vx v9, v9, a0, v0.t
; CHECK-NEXT:    lui a0, 209715
; CHECK-NEXT:    addi a0, a0, 819
; CHECK-NEXT:    vsub.vv v8, v8, v9, v0.t
; 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:    lui a0, 61681
; CHECK-NEXT:    addi a0, a0, -241
; 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.vx v8, v8, a0, v0.t
; CHECK-NEXT:    lui a0, 4112
; CHECK-NEXT:    addi a0, a0, 257
; CHECK-NEXT:    vmul.vx v8, v8, a0, v0.t
; CHECK-NEXT:    vsrl.vi v8, v8, 24, v0.t
; CHECK-NEXT:    ret
;
; CHECK-ZVBB-LABEL: vp_ctpop_nxv1i32:
; CHECK-ZVBB:       # %bb.0:
; CHECK-ZVBB-NEXT:    vsetvli zero, a0, e32, mf2, ta, ma
; CHECK-ZVBB-NEXT:    vcpop.v v8, v8, v0.t
; CHECK-ZVBB-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) {
; CHECK-LABEL: vp_ctpop_nxv1i32_unmasked:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a0, e32, mf2, ta, ma
; CHECK-NEXT:    vsrl.vi v9, v8, 1
; CHECK-NEXT:    lui a0, 349525
; CHECK-NEXT:    addi a0, a0, 1365
; CHECK-NEXT:    vand.vx v9, v9, a0
; CHECK-NEXT:    lui a0, 209715
; CHECK-NEXT:    addi a0, a0, 819
; CHECK-NEXT:    vsub.vv v8, v8, v9
; CHECK-NEXT:    vand.vx v9, v8, a0
; CHECK-NEXT:    vsrl.vi v8, v8, 2
; CHECK-NEXT:    vand.vx v8, v8, a0
; CHECK-NEXT:    lui a0, 61681
; CHECK-NEXT:    addi a0, a0, -241
; CHECK-NEXT:    vadd.vv v8, v9, v8
; CHECK-NEXT:    vsrl.vi v9, v8, 4
; CHECK-NEXT:    vadd.vv v8, v8, v9
; CHECK-NEXT:    vand.vx v8, v8, a0
; CHECK-NEXT:    lui a0, 4112
; CHECK-NEXT:    addi a0, a0, 257
; CHECK-NEXT:    vmul.vx v8, v8, a0
; CHECK-NEXT:    vsrl.vi v8, v8, 24
; CHECK-NEXT:    ret
;
; CHECK-ZVBB-LABEL: vp_ctpop_nxv1i32_unmasked:
; CHECK-ZVBB:       # %bb.0:
; CHECK-ZVBB-NEXT:    vsetvli zero, a0, e32, mf2, ta, ma
; CHECK-ZVBB-NEXT:    vcpop.v v8, v8
; CHECK-ZVBB-NEXT:    ret
  %v = call <vscale x 1 x i32> @llvm.vp.ctpop.nxv1i32(<vscale x 1 x i32> %va, <vscale x 1 x i1> splat (i1 true), 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) {
; CHECK-LABEL: vp_ctpop_nxv2i32:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a0, e32, m1, ta, ma
; CHECK-NEXT:    vsrl.vi v9, v8, 1, v0.t
; CHECK-NEXT:    lui a0, 349525
; CHECK-NEXT:    addi a0, a0, 1365
; CHECK-NEXT:    vand.vx v9, v9, a0, v0.t
; CHECK-NEXT:    lui a0, 209715
; CHECK-NEXT:    addi a0, a0, 819
; CHECK-NEXT:    vsub.vv v8, v8, v9, v0.t
; 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:    lui a0, 61681
; CHECK-NEXT:    addi a0, a0, -241
; 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.vx v8, v8, a0, v0.t
; CHECK-NEXT:    lui a0, 4112
; CHECK-NEXT:    addi a0, a0, 257
; CHECK-NEXT:    vmul.vx v8, v8, a0, v0.t
; CHECK-NEXT:    vsrl.vi v8, v8, 24, v0.t
; CHECK-NEXT:    ret
;
; CHECK-ZVBB-LABEL: vp_ctpop_nxv2i32:
; CHECK-ZVBB:       # %bb.0:
; CHECK-ZVBB-NEXT:    vsetvli zero, a0, e32, m1, ta, ma
; CHECK-ZVBB-NEXT:    vcpop.v v8, v8, v0.t
; CHECK-ZVBB-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) {
; CHECK-LABEL: vp_ctpop_nxv2i32_unmasked:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a0, e32, m1, ta, ma
; CHECK-NEXT:    vsrl.vi v9, v8, 1
; CHECK-NEXT:    lui a0, 349525
; CHECK-NEXT:    addi a0, a0, 1365
; CHECK-NEXT:    vand.vx v9, v9, a0
; CHECK-NEXT:    lui a0, 209715
; CHECK-NEXT:    addi a0, a0, 819
; CHECK-NEXT:    vsub.vv v8, v8, v9
; CHECK-NEXT:    vand.vx v9, v8, a0
; CHECK-NEXT:    vsrl.vi v8, v8, 2
; CHECK-NEXT:    vand.vx v8, v8, a0
; CHECK-NEXT:    lui a0, 61681
; CHECK-NEXT:    addi a0, a0, -241
; CHECK-NEXT:    vadd.vv v8, v9, v8
; CHECK-NEXT:    vsrl.vi v9, v8, 4
; CHECK-NEXT:    vadd.vv v8, v8, v9
; CHECK-NEXT:    vand.vx v8, v8, a0
; CHECK-NEXT:    lui a0, 4112
; CHECK-NEXT:    addi a0, a0, 257
; CHECK-NEXT:    vmul.vx v8, v8, a0
; CHECK-NEXT:    vsrl.vi v8, v8, 24
; CHECK-NEXT:    ret
;
; CHECK-ZVBB-LABEL: vp_ctpop_nxv2i32_unmasked:
; CHECK-ZVBB:       # %bb.0:
; CHECK-ZVBB-NEXT:    vsetvli zero, a0, e32, m1, ta, ma
; CHECK-ZVBB-NEXT:    vcpop.v v8, v8
; CHECK-ZVBB-NEXT:    ret
  %v = call <vscale x 2 x i32> @llvm.vp.ctpop.nxv2i32(<vscale x 2 x i32> %va, <vscale x 2 x i1> splat (i1 true), 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) {
; CHECK-LABEL: vp_ctpop_nxv4i32:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a0, e32, m2, ta, ma
; CHECK-NEXT:    vsrl.vi v10, v8, 1, v0.t
; CHECK-NEXT:    lui a0, 349525
; CHECK-NEXT:    addi a0, a0, 1365
; CHECK-NEXT:    vand.vx v10, v10, a0, v0.t
; CHECK-NEXT:    lui a0, 209715
; CHECK-NEXT:    addi a0, a0, 819
; CHECK-NEXT:    vsub.vv v8, v8, v10, v0.t
; 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:    lui a0, 61681
; CHECK-NEXT:    addi a0, a0, -241
; 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.vx v8, v8, a0, v0.t
; CHECK-NEXT:    lui a0, 4112
; CHECK-NEXT:    addi a0, a0, 257
; CHECK-NEXT:    vmul.vx v8, v8, a0, v0.t
; CHECK-NEXT:    vsrl.vi v8, v8, 24, v0.t
; CHECK-NEXT:    ret
;
; CHECK-ZVBB-LABEL: vp_ctpop_nxv4i32:
; CHECK-ZVBB:       # %bb.0:
; CHECK-ZVBB-NEXT:    vsetvli zero, a0, e32, m2, ta, ma
; CHECK-ZVBB-NEXT:    vcpop.v v8, v8, v0.t
; CHECK-ZVBB-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) {
; CHECK-LABEL: vp_ctpop_nxv4i32_unmasked:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a0, e32, m2, ta, ma
; CHECK-NEXT:    vsrl.vi v10, v8, 1
; CHECK-NEXT:    lui a0, 349525
; CHECK-NEXT:    addi a0, a0, 1365
; CHECK-NEXT:    vand.vx v10, v10, a0
; CHECK-NEXT:    lui a0, 209715
; CHECK-NEXT:    addi a0, a0, 819
; CHECK-NEXT:    vsub.vv v8, v8, v10
; CHECK-NEXT:    vand.vx v10, v8, a0
; CHECK-NEXT:    vsrl.vi v8, v8, 2
; CHECK-NEXT:    vand.vx v8, v8, a0
; CHECK-NEXT:    lui a0, 61681
; CHECK-NEXT:    addi a0, a0, -241
; CHECK-NEXT:    vadd.vv v8, v10, v8
; CHECK-NEXT:    vsrl.vi v10, v8, 4
; CHECK-NEXT:    vadd.vv v8, v8, v10
; CHECK-NEXT:    vand.vx v8, v8, a0
; CHECK-NEXT:    lui a0, 4112
; CHECK-NEXT:    addi a0, a0, 257
; CHECK-NEXT:    vmul.vx v8, v8, a0
; CHECK-NEXT:    vsrl.vi v8, v8, 24
; CHECK-NEXT:    ret
;
; CHECK-ZVBB-LABEL: vp_ctpop_nxv4i32_unmasked:
; CHECK-ZVBB:       # %bb.0:
; CHECK-ZVBB-NEXT:    vsetvli zero, a0, e32, m2, ta, ma
; CHECK-ZVBB-NEXT:    vcpop.v v8, v8
; CHECK-ZVBB-NEXT:    ret
  %v = call <vscale x 4 x i32> @llvm.vp.ctpop.nxv4i32(<vscale x 4 x i32> %va, <vscale x 4 x i1> splat (i1 true), 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) {
; CHECK-LABEL: vp_ctpop_nxv8i32:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a0, e32, m4, ta, ma
; CHECK-NEXT:    vsrl.vi v12, v8, 1, v0.t
; CHECK-NEXT:    lui a0, 349525
; CHECK-NEXT:    addi a0, a0, 1365
; CHECK-NEXT:    vand.vx v12, v12, a0, v0.t
; CHECK-NEXT:    lui a0, 209715
; CHECK-NEXT:    addi a0, a0, 819
; CHECK-NEXT:    vsub.vv v8, v8, v12, v0.t
; 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:    lui a0, 61681
; CHECK-NEXT:    addi a0, a0, -241
; 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.vx v8, v8, a0, v0.t
; CHECK-NEXT:    lui a0, 4112
; CHECK-NEXT:    addi a0, a0, 257
; CHECK-NEXT:    vmul.vx v8, v8, a0, v0.t
; CHECK-NEXT:    vsrl.vi v8, v8, 24, v0.t
; CHECK-NEXT:    ret
;
; CHECK-ZVBB-LABEL: vp_ctpop_nxv8i32:
; CHECK-ZVBB:       # %bb.0:
; CHECK-ZVBB-NEXT:    vsetvli zero, a0, e32, m4, ta, ma
; CHECK-ZVBB-NEXT:    vcpop.v v8, v8, v0.t
; CHECK-ZVBB-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) {
; CHECK-LABEL: vp_ctpop_nxv8i32_unmasked:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a0, e32, m4, ta, ma
; CHECK-NEXT:    vsrl.vi v12, v8, 1
; CHECK-NEXT:    lui a0, 349525
; CHECK-NEXT:    addi a0, a0, 1365
; CHECK-NEXT:    vand.vx v12, v12, a0
; CHECK-NEXT:    lui a0, 209715
; CHECK-NEXT:    addi a0, a0, 819
; CHECK-NEXT:    vsub.vv v8, v8, v12
; CHECK-NEXT:    vand.vx v12, v8, a0
; CHECK-NEXT:    vsrl.vi v8, v8, 2
; CHECK-NEXT:    vand.vx v8, v8, a0
; CHECK-NEXT:    lui a0, 61681
; CHECK-NEXT:    addi a0, a0, -241
; CHECK-NEXT:    vadd.vv v8, v12, v8
; CHECK-NEXT:    vsrl.vi v12, v8, 4
; CHECK-NEXT:    vadd.vv v8, v8, v12
; CHECK-NEXT:    vand.vx v8, v8, a0
; CHECK-NEXT:    lui a0, 4112
; CHECK-NEXT:    addi a0, a0, 257
; CHECK-NEXT:    vmul.vx v8, v8, a0
; CHECK-NEXT:    vsrl.vi v8, v8, 24
; CHECK-NEXT:    ret
;
; CHECK-ZVBB-LABEL: vp_ctpop_nxv8i32_unmasked:
; CHECK-ZVBB:       # %bb.0:
; CHECK-ZVBB-NEXT:    vsetvli zero, a0, e32, m4, ta, ma
; CHECK-ZVBB-NEXT:    vcpop.v v8, v8
; CHECK-ZVBB-NEXT:    ret
  %v = call <vscale x 8 x i32> @llvm.vp.ctpop.nxv8i32(<vscale x 8 x i32> %va, <vscale x 8 x i1> splat (i1 true), 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) {
; CHECK-LABEL: vp_ctpop_nxv16i32:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a0, e32, m8, ta, ma
; CHECK-NEXT:    vsrl.vi v16, v8, 1, v0.t
; CHECK-NEXT:    lui a0, 349525
; CHECK-NEXT:    addi a0, a0, 1365
; CHECK-NEXT:    vand.vx v16, v16, a0, v0.t
; CHECK-NEXT:    lui a0, 209715
; CHECK-NEXT:    addi a0, a0, 819
; CHECK-NEXT:    vsub.vv v16, v8, v16, v0.t
; CHECK-NEXT:    vand.vx v8, v16, a0, v0.t
; CHECK-NEXT:    vsrl.vi v16, v16, 2, v0.t
; CHECK-NEXT:    vand.vx v16, v16, a0, v0.t
; CHECK-NEXT:    lui a0, 61681
; CHECK-NEXT:    addi a0, a0, -241
; CHECK-NEXT:    vadd.vv v8, v8, v16, v0.t
; CHECK-NEXT:    vsrl.vi v16, v8, 4, v0.t
; CHECK-NEXT:    vadd.vv v8, v8, v16, v0.t
; CHECK-NEXT:    vand.vx v8, v8, a0, v0.t
; CHECK-NEXT:    lui a0, 4112
; CHECK-NEXT:    addi a0, a0, 257
; CHECK-NEXT:    vmul.vx v8, v8, a0, v0.t
; CHECK-NEXT:    vsrl.vi v8, v8, 24, v0.t
; CHECK-NEXT:    ret
;
; CHECK-ZVBB-LABEL: vp_ctpop_nxv16i32:
; CHECK-ZVBB:       # %bb.0:
; CHECK-ZVBB-NEXT:    vsetvli zero, a0, e32, m8, ta, ma
; CHECK-ZVBB-NEXT:    vcpop.v v8, v8, v0.t
; CHECK-ZVBB-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) {
; CHECK-LABEL: vp_ctpop_nxv16i32_unmasked:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a0, e32, m8, ta, ma
; CHECK-NEXT:    vsrl.vi v16, v8, 1
; CHECK-NEXT:    lui a0, 349525
; CHECK-NEXT:    addi a0, a0, 1365
; CHECK-NEXT:    vand.vx v16, v16, a0
; CHECK-NEXT:    lui a0, 209715
; CHECK-NEXT:    addi a0, a0, 819
; CHECK-NEXT:    vsub.vv v8, v8, v16
; CHECK-NEXT:    vand.vx v16, v8, a0
; CHECK-NEXT:    vsrl.vi v8, v8, 2
; CHECK-NEXT:    vand.vx v8, v8, a0
; CHECK-NEXT:    lui a0, 61681
; CHECK-NEXT:    addi a0, a0, -241
; CHECK-NEXT:    vadd.vv v8, v16, v8
; CHECK-NEXT:    vsrl.vi v16, v8, 4
; CHECK-NEXT:    vadd.vv v8, v8, v16
; CHECK-NEXT:    vand.vx v8, v8, a0
; CHECK-NEXT:    lui a0, 4112
; CHECK-NEXT:    addi a0, a0, 257
; CHECK-NEXT:    vmul.vx v8, v8, a0
; CHECK-NEXT:    vsrl.vi v8, v8, 24
; CHECK-NEXT:    ret
;
; CHECK-ZVBB-LABEL: vp_ctpop_nxv16i32_unmasked:
; CHECK-ZVBB:       # %bb.0:
; CHECK-ZVBB-NEXT:    vsetvli zero, a0, e32, m8, ta, ma
; CHECK-ZVBB-NEXT:    vcpop.v v8, v8
; CHECK-ZVBB-NEXT:    ret
  %v = call <vscale x 16 x i32> @llvm.vp.ctpop.nxv16i32(<vscale x 16 x i32> %va, <vscale x 16 x i1> splat (i1 true), 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:    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:    vsetvli a2, zero, e32, m1, ta, ma
; RV32-NEXT:    vmv.v.x v10, a1
; RV32-NEXT:    lui a1, 209715
; RV32-NEXT:    addi a1, a1, 819
; RV32-NEXT:    vsetvli zero, a0, e64, m1, ta, ma
; RV32-NEXT:    vand.vv v9, v9, v10, v0.t
; RV32-NEXT:    vsetvli a2, zero, e32, m1, ta, ma
; RV32-NEXT:    vmv.v.x v10, a1
; RV32-NEXT:    lui a1, 61681
; RV32-NEXT:    addi a1, a1, -241
; RV32-NEXT:    vsetvli zero, a0, e64, m1, ta, ma
; RV32-NEXT:    vsub.vv v8, v8, v9, v0.t
; RV32-NEXT:    vand.vv v9, v8, v10, v0.t
; RV32-NEXT:    vsrl.vi v8, v8, 2, v0.t
; RV32-NEXT:    vand.vv v8, v8, v10, v0.t
; RV32-NEXT:    vsetvli a2, zero, e32, m1, ta, ma
; RV32-NEXT:    vmv.v.x v10, a1
; RV32-NEXT:    lui a1, 4112
; RV32-NEXT:    addi a1, a1, 257
; RV32-NEXT:    vsetvli zero, a0, e64, m1, ta, ma
; 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:    vsetvli a2, zero, e32, m1, ta, ma
; RV32-NEXT:    vmv.v.x v9, a1
; RV32-NEXT:    li a1, 56
; RV32-NEXT:    vsetvli zero, a0, e64, m1, ta, ma
; RV32-NEXT:    vand.vv v8, v8, v10, v0.t
; RV32-NEXT:    vmul.vv v8, v8, v9, v0.t
; RV32-NEXT:    vsrl.vx v8, v8, a1, v0.t
; RV32-NEXT:    ret
;
; RV64-LABEL: vp_ctpop_nxv1i64:
; RV64:       # %bb.0:
; RV64-NEXT:    lui a1, 349525
; RV64-NEXT:    lui a2, 209715
; RV64-NEXT:    lui a3, 61681
; RV64-NEXT:    lui a4, 4112
; RV64-NEXT:    addi a1, a1, 1365
; RV64-NEXT:    addi a2, a2, 819
; RV64-NEXT:    addi a3, a3, -241
; RV64-NEXT:    addi a4, a4, 257
; RV64-NEXT:    slli a5, a1, 32
; RV64-NEXT:    add a1, a1, a5
; RV64-NEXT:    slli a5, a2, 32
; RV64-NEXT:    add a2, a2, a5
; RV64-NEXT:    slli a5, a3, 32
; RV64-NEXT:    add a3, a3, a5
; RV64-NEXT:    slli a5, a4, 32
; RV64-NEXT:    add a4, a4, a5
; RV64-NEXT:    vsetvli zero, a0, e64, m1, ta, ma
; RV64-NEXT:    vsrl.vi v9, v8, 1, v0.t
; RV64-NEXT:    vand.vx v9, v9, a1, v0.t
; RV64-NEXT:    vsub.vv v8, v8, v9, v0.t
; RV64-NEXT:    vand.vx v9, 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, v9, v8, v0.t
; RV64-NEXT:    vsrl.vi v9, v8, 4, v0.t
; RV64-NEXT:    vadd.vv v8, v8, v9, v0.t
; RV64-NEXT:    vand.vx v8, v8, a3, v0.t
; RV64-NEXT:    li a0, 56
; RV64-NEXT:    vmul.vx v8, v8, a4, v0.t
; RV64-NEXT:    vsrl.vx v8, v8, a0, v0.t
; RV64-NEXT:    ret
;
; CHECK-ZVBB-LABEL: vp_ctpop_nxv1i64:
; CHECK-ZVBB:       # %bb.0:
; CHECK-ZVBB-NEXT:    vsetvli zero, a0, e64, m1, ta, ma
; CHECK-ZVBB-NEXT:    vcpop.v v8, v8, v0.t
; CHECK-ZVBB-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:    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:    vsetvli a2, zero, e32, m1, ta, ma
; RV32-NEXT:    vmv.v.x v10, a1
; RV32-NEXT:    lui a1, 209715
; RV32-NEXT:    addi a1, a1, 819
; RV32-NEXT:    vsetvli zero, a0, e64, m1, ta, ma
; RV32-NEXT:    vand.vv v9, v9, v10
; RV32-NEXT:    vsetvli a2, zero, e32, m1, ta, ma
; RV32-NEXT:    vmv.v.x v10, a1
; RV32-NEXT:    lui a1, 61681
; RV32-NEXT:    addi a1, a1, -241
; RV32-NEXT:    vsetvli zero, a0, e64, m1, ta, ma
; RV32-NEXT:    vsub.vv v8, v8, v9
; RV32-NEXT:    vand.vv v9, v8, v10
; RV32-NEXT:    vsrl.vi v8, v8, 2
; RV32-NEXT:    vand.vv v8, v8, v10
; RV32-NEXT:    vsetvli a2, zero, e32, m1, ta, ma
; RV32-NEXT:    vmv.v.x v10, a1
; RV32-NEXT:    lui a1, 4112
; RV32-NEXT:    addi a1, a1, 257
; RV32-NEXT:    vsetvli zero, a0, e64, m1, ta, ma
; RV32-NEXT:    vadd.vv v8, v9, v8
; RV32-NEXT:    vsrl.vi v9, v8, 4
; RV32-NEXT:    vadd.vv v8, v8, v9
; RV32-NEXT:    vsetvli a2, zero, 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, v10
; 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_nxv1i64_unmasked:
; RV64:       # %bb.0:
; RV64-NEXT:    lui a1, 349525
; RV64-NEXT:    lui a2, 209715
; RV64-NEXT:    lui a3, 61681
; RV64-NEXT:    lui a4, 4112
; RV64-NEXT:    addi a1, a1, 1365
; RV64-NEXT:    addi a2, a2, 819
; RV64-NEXT:    addi a3, a3, -241
; RV64-NEXT:    addi a4, a4, 257
; RV64-NEXT:    slli a5, a1, 32
; RV64-NEXT:    add a1, a1, a5
; RV64-NEXT:    slli a5, a2, 32
; RV64-NEXT:    add a2, a2, a5
; RV64-NEXT:    slli a5, a3, 32
; RV64-NEXT:    add a3, a3, a5
; RV64-NEXT:    slli a5, a4, 32
; RV64-NEXT:    add a4, a4, a5
; RV64-NEXT:    vsetvli zero, a0, e64, m1, ta, ma
; RV64-NEXT:    vsrl.vi v9, v8, 1
; RV64-NEXT:    vand.vx v9, v9, a1
; RV64-NEXT:    vsub.vv v8, v8, v9
; RV64-NEXT:    vand.vx v9, v8, a2
; RV64-NEXT:    vsrl.vi v8, v8, 2
; RV64-NEXT:    vand.vx v8, v8, a2
; RV64-NEXT:    vadd.vv v8, v9, v8
; RV64-NEXT:    vsrl.vi v9, v8, 4
; RV64-NEXT:    vadd.vv v8, v8, v9
; RV64-NEXT:    vand.vx v8, v8, a3
; RV64-NEXT:    vmul.vx v8, v8, a4
; RV64-NEXT:    li a0, 56
; RV64-NEXT:    vsrl.vx v8, v8, a0
; RV64-NEXT:    ret
;
; CHECK-ZVBB-LABEL: vp_ctpop_nxv1i64_unmasked:
; CHECK-ZVBB:       # %bb.0:
; CHECK-ZVBB-NEXT:    vsetvli zero, a0, e64, m1, ta, ma
; CHECK-ZVBB-NEXT:    vcpop.v v8, v8
; CHECK-ZVBB-NEXT:    ret
  %v = call <vscale x 1 x i64> @llvm.vp.ctpop.nxv1i64(<vscale x 1 x i64> %va, <vscale x 1 x i1> splat (i1 true), 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:    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:    vsetvli a2, zero, e32, m2, ta, ma
; RV32-NEXT:    vmv.v.x v12, a1
; RV32-NEXT:    lui a1, 209715
; RV32-NEXT:    addi a1, a1, 819
; RV32-NEXT:    vsetvli zero, a0, e64, m2, ta, ma
; RV32-NEXT:    vand.vv v10, v10, v12, v0.t
; RV32-NEXT:    vsetvli a2, zero, e32, m2, ta, ma
; RV32-NEXT:    vmv.v.x v12, a1
; RV32-NEXT:    lui a1, 61681
; RV32-NEXT:    addi a1, a1, -241
; RV32-NEXT:    vsetvli zero, a0, e64, m2, ta, ma
; RV32-NEXT:    vsub.vv v8, v8, v10, v0.t
; RV32-NEXT:    vand.vv v10, v8, v12, v0.t
; RV32-NEXT:    vsrl.vi v8, v8, 2, v0.t
; RV32-NEXT:    vand.vv v8, v8, v12, v0.t
; RV32-NEXT:    vsetvli a2, zero, e32, m2, ta, ma
; RV32-NEXT:    vmv.v.x v12, a1
; RV32-NEXT:    lui a1, 4112
; RV32-NEXT:    addi a1, a1, 257
; RV32-NEXT:    vsetvli zero, a0, e64, m2, ta, ma
; 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:    vsetvli a2, zero, e32, m2, ta, ma
; RV32-NEXT:    vmv.v.x v10, a1
; RV32-NEXT:    li a1, 56
; RV32-NEXT:    vsetvli zero, a0, e64, m2, ta, ma
; RV32-NEXT:    vand.vv v8, v8, v12, v0.t
; RV32-NEXT:    vmul.vv v8, v8, v10, v0.t
; RV32-NEXT:    vsrl.vx v8, v8, a1, v0.t
; RV32-NEXT:    ret
;
; RV64-LABEL: vp_ctpop_nxv2i64:
; RV64:       # %bb.0:
; RV64-NEXT:    lui a1, 349525
; RV64-NEXT:    lui a2, 209715
; RV64-NEXT:    lui a3, 61681
; RV64-NEXT:    lui a4, 4112
; RV64-NEXT:    addi a1, a1, 1365
; RV64-NEXT:    addi a2, a2, 819
; RV64-NEXT:    addi a3, a3, -241
; RV64-NEXT:    addi a4, a4, 257
; RV64-NEXT:    slli a5, a1, 32
; RV64-NEXT:    add a1, a1, a5
; RV64-NEXT:    slli a5, a2, 32
; RV64-NEXT:    add a2, a2, a5
; RV64-NEXT:    slli a5, a3, 32
; RV64-NEXT:    add a3, a3, a5
; RV64-NEXT:    slli a5, a4, 32
; RV64-NEXT:    add a4, a4, a5
; RV64-NEXT:    vsetvli zero, a0, e64, m2, ta, ma
; RV64-NEXT:    vsrl.vi v10, v8, 1, v0.t
; RV64-NEXT:    vand.vx v10, v10, a1, v0.t
; RV64-NEXT:    vsub.vv v8, v8, v10, v0.t
; RV64-NEXT:    vand.vx v10, 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, v10, v8, v0.t
; RV64-NEXT:    vsrl.vi v10, v8, 4, v0.t
; RV64-NEXT:    vadd.vv v8, v8, v10, v0.t
; RV64-NEXT:    vand.vx v8, v8, a3, v0.t
; RV64-NEXT:    li a0, 56
; RV64-NEXT:    vmul.vx v8, v8, a4, v0.t
; RV64-NEXT:    vsrl.vx v8, v8, a0, v0.t
; RV64-NEXT:    ret
;
; CHECK-ZVBB-LABEL: vp_ctpop_nxv2i64:
; CHECK-ZVBB:       # %bb.0:
; CHECK-ZVBB-NEXT:    vsetvli zero, a0, e64, m2, ta, ma
; CHECK-ZVBB-NEXT:    vcpop.v v8, v8, v0.t
; CHECK-ZVBB-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:    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:    vsetvli a2, zero, e32, m2, ta, ma
; RV32-NEXT:    vmv.v.x v12, a1
; RV32-NEXT:    lui a1, 209715
; RV32-NEXT:    addi a1, a1, 819
; RV32-NEXT:    vsetvli zero, a0, e64, m2, ta, ma
; RV32-NEXT:    vand.vv v10, v10, v12
; RV32-NEXT:    vsetvli a2, zero, e32, m2, ta, ma
; RV32-NEXT:    vmv.v.x v12, a1
; RV32-NEXT:    lui a1, 61681
; RV32-NEXT:    addi a1, a1, -241
; RV32-NEXT:    vsetvli zero, a0, e64, m2, ta, ma
; RV32-NEXT:    vsub.vv v8, v8, v10
; RV32-NEXT:    vand.vv v10, v8, v12
; RV32-NEXT:    vsrl.vi v8, v8, 2
; RV32-NEXT:    vand.vv v8, v8, v12
; RV32-NEXT:    vsetvli a2, zero, e32, m2, ta, ma
; RV32-NEXT:    vmv.v.x v12, a1
; RV32-NEXT:    lui a1, 4112
; RV32-NEXT:    addi a1, a1, 257
; RV32-NEXT:    vsetvli zero, a0, e64, m2, ta, ma
; RV32-NEXT:    vadd.vv v8, v10, v8
; RV32-NEXT:    vsrl.vi v10, v8, 4
; RV32-NEXT:    vadd.vv v8, v8, v10
; RV32-NEXT:    vsetvli a2, zero, 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, v12
; 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_nxv2i64_unmasked:
; RV64:       # %bb.0:
; RV64-NEXT:    lui a1, 349525
; RV64-NEXT:    lui a2, 209715
; RV64-NEXT:    lui a3, 61681
; RV64-NEXT:    lui a4, 4112
; RV64-NEXT:    addi a1, a1, 1365
; RV64-NEXT:    addi a2, a2, 819
; RV64-NEXT:    addi a3, a3, -241
; RV64-NEXT:    addi a4, a4, 257
; RV64-NEXT:    slli a5, a1, 32
; RV64-NEXT:    add a1, a1, a5
; RV64-NEXT:    slli a5, a2, 32
; RV64-NEXT:    add a2, a2, a5
; RV64-NEXT:    slli a5, a3, 32
; RV64-NEXT:    add a3, a3, a5
; RV64-NEXT:    slli a5, a4, 32
; RV64-NEXT:    add a4, a4, a5
; RV64-NEXT:    vsetvli zero, a0, e64, m2, ta, ma
; RV64-NEXT:    vsrl.vi v10, v8, 1
; RV64-NEXT:    vand.vx v10, v10, a1
; RV64-NEXT:    vsub.vv v8, v8, v10
; RV64-NEXT:    vand.vx v10, v8, a2
; RV64-NEXT:    vsrl.vi v8, v8, 2
; RV64-NEXT:    vand.vx v8, v8, a2
; RV64-NEXT:    vadd.vv v8, v10, v8
; RV64-NEXT:    vsrl.vi v10, v8, 4
; RV64-NEXT:    vadd.vv v8, v8, v10
; RV64-NEXT:    vand.vx v8, v8, a3
; RV64-NEXT:    vmul.vx v8, v8, a4
; RV64-NEXT:    li a0, 56
; RV64-NEXT:    vsrl.vx v8, v8, a0
; RV64-NEXT:    ret
;
; CHECK-ZVBB-LABEL: vp_ctpop_nxv2i64_unmasked:
; CHECK-ZVBB:       # %bb.0:
; CHECK-ZVBB-NEXT:    vsetvli zero, a0, e64, m2, ta, ma
; CHECK-ZVBB-NEXT:    vcpop.v v8, v8
; CHECK-ZVBB-NEXT:    ret
  %v = call <vscale x 2 x i64> @llvm.vp.ctpop.nxv2i64(<vscale x 2 x i64> %va, <vscale x 2 x i1> splat (i1 true), 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:    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:    vsetvli a2, zero, e32, m4, ta, ma
; RV32-NEXT:    vmv.v.x v16, a1
; RV32-NEXT:    lui a1, 209715
; RV32-NEXT:    addi a1, a1, 819
; RV32-NEXT:    vsetvli zero, a0, e64, m4, ta, ma
; RV32-NEXT:    vand.vv v16, v12, v16, v0.t
; RV32-NEXT:    vsetvli a2, zero, e32, m4, ta, ma
; RV32-NEXT:    vmv.v.x v12, a1
; RV32-NEXT:    lui a1, 61681
; RV32-NEXT:    addi a1, a1, -241
; RV32-NEXT:    vsetvli zero, a0, e64, m4, ta, ma
; RV32-NEXT:    vsub.vv v8, v8, v16, v0.t
; 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:    vsetvli a2, zero, e32, m4, ta, ma
; RV32-NEXT:    vmv.v.x v12, a1
; RV32-NEXT:    lui a1, 4112
; RV32-NEXT:    addi a1, a1, 257
; RV32-NEXT:    vsetvli zero, a0, e64, m4, ta, ma
; 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:    vsetvli a2, zero, e32, m4, ta, ma
; RV32-NEXT:    vmv.v.x v16, a1
; RV32-NEXT:    li a1, 56
; RV32-NEXT:    vsetvli zero, a0, e64, m4, ta, ma
; RV32-NEXT:    vand.vv v8, v8, v12, v0.t
; RV32-NEXT:    vmul.vv v8, v8, v16, v0.t
; RV32-NEXT:    vsrl.vx v8, v8, a1, v0.t
; RV32-NEXT:    ret
;
; RV64-LABEL: vp_ctpop_nxv4i64:
; RV64:       # %bb.0:
; RV64-NEXT:    lui a1, 349525
; RV64-NEXT:    lui a2, 209715
; RV64-NEXT:    lui a3, 61681
; RV64-NEXT:    lui a4, 4112
; RV64-NEXT:    addi a1, a1, 1365
; RV64-NEXT:    addi a2, a2, 819
; RV64-NEXT:    addi a3, a3, -241
; RV64-NEXT:    addi a4, a4, 257
; RV64-NEXT:    slli a5, a1, 32
; RV64-NEXT:    add a1, a1, a5
; RV64-NEXT:    slli a5, a2, 32
; RV64-NEXT:    add a2, a2, a5
; RV64-NEXT:    slli a5, a3, 32
; RV64-NEXT:    add a3, a3, a5
; RV64-NEXT:    slli a5, a4, 32
; RV64-NEXT:    add a4, a4, a5
; RV64-NEXT:    vsetvli zero, a0, e64, m4, ta, ma
; RV64-NEXT:    vsrl.vi v12, v8, 1, v0.t
; RV64-NEXT:    vand.vx v12, v12, a1, v0.t
; RV64-NEXT:    vsub.vv v8, v8, v12, v0.t
; RV64-NEXT:    vand.vx v12, 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, v12, v8, v0.t
; RV64-NEXT:    vsrl.vi v12, v8, 4, v0.t
; RV64-NEXT:    vadd.vv v8, v8, v12, v0.t
; RV64-NEXT:    vand.vx v8, v8, a3, v0.t
; RV64-NEXT:    li a0, 56
; RV64-NEXT:    vmul.vx v8, v8, a4, v0.t
; RV64-NEXT:    vsrl.vx v8, v8, a0, v0.t
; RV64-NEXT:    ret
;
; CHECK-ZVBB-LABEL: vp_ctpop_nxv4i64:
; CHECK-ZVBB:       # %bb.0:
; CHECK-ZVBB-NEXT:    vsetvli zero, a0, e64, m4, ta, ma
; CHECK-ZVBB-NEXT:    vcpop.v v8, v8, v0.t
; CHECK-ZVBB-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:    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:    vsetvli a2, zero, e32, m4, ta, ma
; RV32-NEXT:    vmv.v.x v16, a1
; RV32-NEXT:    lui a1, 209715
; RV32-NEXT:    addi a1, a1, 819
; RV32-NEXT:    vsetvli zero, a0, e64, m4, ta, ma
; RV32-NEXT:    vand.vv v12, v12, v16
; RV32-NEXT:    vsetvli a2, zero, e32, m4, ta, ma
; RV32-NEXT:    vmv.v.x v16, a1
; RV32-NEXT:    lui a1, 61681
; RV32-NEXT:    addi a1, a1, -241
; RV32-NEXT:    vsetvli zero, a0, e64, m4, ta, ma
; RV32-NEXT:    vsub.vv v8, v8, v12
; RV32-NEXT:    vand.vv v12, v8, v16
; RV32-NEXT:    vsrl.vi v8, v8, 2
; RV32-NEXT:    vand.vv v8, v8, v16
; RV32-NEXT:    vsetvli a2, zero, e32, m4, ta, ma
; RV32-NEXT:    vmv.v.x v16, a1
; RV32-NEXT:    lui a1, 4112
; RV32-NEXT:    addi a1, a1, 257
; RV32-NEXT:    vsetvli zero, a0, e64, m4, ta, ma
; RV32-NEXT:    vadd.vv v8, v12, v8
; RV32-NEXT:    vsrl.vi v12, v8, 4
; RV32-NEXT:    vadd.vv v8, v8, v12
; RV32-NEXT:    vsetvli a2, zero, 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, v16
; 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_nxv4i64_unmasked:
; RV64:       # %bb.0:
; RV64-NEXT:    lui a1, 349525
; RV64-NEXT:    lui a2, 209715
; RV64-NEXT:    lui a3, 61681
; RV64-NEXT:    lui a4, 4112
; RV64-NEXT:    addi a1, a1, 1365
; RV64-NEXT:    addi a2, a2, 819
; RV64-NEXT:    addi a3, a3, -241
; RV64-NEXT:    addi a4, a4, 257
; RV64-NEXT:    slli a5, a1, 32
; RV64-NEXT:    add a1, a1, a5
; RV64-NEXT:    slli a5, a2, 32
; RV64-NEXT:    add a2, a2, a5
; RV64-NEXT:    slli a5, a3, 32
; RV64-NEXT:    add a3, a3, a5
; RV64-NEXT:    slli a5, a4, 32
; RV64-NEXT:    add a4, a4, a5
; RV64-NEXT:    vsetvli zero, a0, e64, m4, ta, ma
; RV64-NEXT:    vsrl.vi v12, v8, 1
; RV64-NEXT:    vand.vx v12, v12, a1
; RV64-NEXT:    vsub.vv v8, v8, v12
; RV64-NEXT:    vand.vx v12, v8, a2
; RV64-NEXT:    vsrl.vi v8, v8, 2
; RV64-NEXT:    vand.vx v8, v8, a2
; RV64-NEXT:    vadd.vv v8, v12, v8
; RV64-NEXT:    vsrl.vi v12, v8, 4
; RV64-NEXT:    vadd.vv v8, v8, v12
; RV64-NEXT:    vand.vx v8, v8, a3
; RV64-NEXT:    vmul.vx v8, v8, a4
; RV64-NEXT:    li a0, 56
; RV64-NEXT:    vsrl.vx v8, v8, a0
; RV64-NEXT:    ret
;
; CHECK-ZVBB-LABEL: vp_ctpop_nxv4i64_unmasked:
; CHECK-ZVBB:       # %bb.0:
; CHECK-ZVBB-NEXT:    vsetvli zero, a0, e64, m4, ta, ma
; CHECK-ZVBB-NEXT:    vcpop.v v8, v8
; CHECK-ZVBB-NEXT:    ret
  %v = call <vscale x 4 x i64> @llvm.vp.ctpop.nxv4i64(<vscale x 4 x i64> %va, <vscale x 4 x i1> splat (i1 true), 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:    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:    vsetvli a2, zero, e32, m8, ta, ma
; RV32-NEXT:    vmv.v.x v24, a1
; RV32-NEXT:    lui a1, 209715
; RV32-NEXT:    addi a1, a1, 819
; RV32-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
; RV32-NEXT:    vand.vv v24, v16, v24, v0.t
; RV32-NEXT:    vsetvli a2, zero, e32, m8, ta, ma
; RV32-NEXT:    vmv.v.x v16, a1
; RV32-NEXT:    lui a1, 61681
; RV32-NEXT:    addi a1, a1, -241
; RV32-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
; RV32-NEXT:    vsub.vv v8, v8, v24, v0.t
; RV32-NEXT:    vand.vv v24, v8, v16, v0.t
; RV32-NEXT:    vsrl.vi v8, v8, 2, v0.t
; RV32-NEXT:    vand.vv v16, v8, v16, v0.t
; RV32-NEXT:    vsetvli a2, zero, e32, m8, ta, ma
; RV32-NEXT:    vmv.v.x v8, a1
; RV32-NEXT:    lui a1, 4112
; RV32-NEXT:    addi a1, a1, 257
; RV32-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
; RV32-NEXT:    vadd.vv v16, v24, v16, v0.t
; RV32-NEXT:    vsrl.vi v24, v16, 4, v0.t
; RV32-NEXT:    vadd.vv v16, v16, v24, v0.t
; RV32-NEXT:    vsetvli a2, zero, e32, m8, ta, ma
; RV32-NEXT:    vmv.v.x v24, a1
; RV32-NEXT:    li a1, 56
; RV32-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
; RV32-NEXT:    vand.vv v8, v16, v8, v0.t
; RV32-NEXT:    vmul.vv v8, v8, v24, v0.t
; RV32-NEXT:    vsrl.vx v8, v8, a1, v0.t
; RV32-NEXT:    ret
;
; RV64-LABEL: vp_ctpop_nxv7i64:
; RV64:       # %bb.0:
; RV64-NEXT:    lui a1, 349525
; RV64-NEXT:    lui a2, 209715
; RV64-NEXT:    lui a3, 61681
; RV64-NEXT:    lui a4, 4112
; RV64-NEXT:    addi a1, a1, 1365
; RV64-NEXT:    addi a2, a2, 819
; RV64-NEXT:    addi a3, a3, -241
; RV64-NEXT:    addi a4, a4, 257
; RV64-NEXT:    slli a5, a1, 32
; RV64-NEXT:    add a1, a1, a5
; RV64-NEXT:    slli a5, a2, 32
; RV64-NEXT:    add a2, a2, a5
; RV64-NEXT:    slli a5, a3, 32
; RV64-NEXT:    add a3, a3, a5
; RV64-NEXT:    slli a5, a4, 32
; RV64-NEXT:    add a4, a4, a5
; RV64-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
; 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:    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:    li a0, 56
; RV64-NEXT:    vmul.vx v8, v8, a4, v0.t
; RV64-NEXT:    vsrl.vx v8, v8, a0, v0.t
; RV64-NEXT:    ret
;
; CHECK-ZVBB-LABEL: vp_ctpop_nxv7i64:
; CHECK-ZVBB:       # %bb.0:
; CHECK-ZVBB-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
; CHECK-ZVBB-NEXT:    vcpop.v v8, v8, v0.t
; CHECK-ZVBB-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:    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:    vsetvli a2, zero, e32, m8, ta, ma
; RV32-NEXT:    vmv.v.x v24, a1
; RV32-NEXT:    lui a1, 209715
; RV32-NEXT:    addi a1, a1, 819
; RV32-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
; RV32-NEXT:    vand.vv v24, v16, v24
; RV32-NEXT:    vsetvli a2, zero, e32, m8, ta, ma
; RV32-NEXT:    vmv.v.x v16, a1
; RV32-NEXT:    lui a1, 61681
; RV32-NEXT:    addi a1, a1, -241
; RV32-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
; RV32-NEXT:    vsub.vv v8, v8, v24
; RV32-NEXT:    vand.vv v24, v8, v16
; RV32-NEXT:    vsrl.vi v8, v8, 2
; RV32-NEXT:    vand.vv v8, v8, v16
; RV32-NEXT:    vsetvli a2, zero, e32, m8, ta, ma
; RV32-NEXT:    vmv.v.x v16, a1
; RV32-NEXT:    lui a1, 4112
; RV32-NEXT:    addi a1, a1, 257
; RV32-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
; RV32-NEXT:    vadd.vv v8, v24, v8
; RV32-NEXT:    vsrl.vi v24, v8, 4
; RV32-NEXT:    vadd.vv v8, v8, v24
; RV32-NEXT:    vsetvli a2, zero, e32, m8, ta, ma
; RV32-NEXT:    vmv.v.x v24, a1
; RV32-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
; RV32-NEXT:    vand.vv v8, v8, v16
; RV32-NEXT:    vmul.vv v8, v8, v24
; RV32-NEXT:    li a0, 56
; RV32-NEXT:    vsrl.vx v8, v8, a0
; RV32-NEXT:    ret
;
; RV64-LABEL: vp_ctpop_nxv7i64_unmasked:
; RV64:       # %bb.0:
; RV64-NEXT:    lui a1, 349525
; RV64-NEXT:    lui a2, 209715
; RV64-NEXT:    lui a3, 61681
; RV64-NEXT:    lui a4, 4112
; RV64-NEXT:    addi a1, a1, 1365
; RV64-NEXT:    addi a2, a2, 819
; RV64-NEXT:    addi a3, a3, -241
; RV64-NEXT:    addi a4, a4, 257
; RV64-NEXT:    slli a5, a1, 32
; RV64-NEXT:    add a1, a1, a5
; RV64-NEXT:    slli a5, a2, 32
; RV64-NEXT:    add a2, a2, a5
; RV64-NEXT:    slli a5, a3, 32
; RV64-NEXT:    add a3, a3, a5
; RV64-NEXT:    slli a5, a4, 32
; RV64-NEXT:    add a4, a4, a5
; RV64-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
; RV64-NEXT:    vsrl.vi v16, v8, 1
; RV64-NEXT:    vand.vx v16, v16, a1
; RV64-NEXT:    vsub.vv v8, v8, v16
; RV64-NEXT:    vand.vx v16, v8, a2
; RV64-NEXT:    vsrl.vi v8, v8, 2
; RV64-NEXT:    vand.vx v8, v8, a2
; RV64-NEXT:    vadd.vv v8, v16, v8
; RV64-NEXT:    vsrl.vi v16, v8, 4
; RV64-NEXT:    vadd.vv v8, v8, v16
; RV64-NEXT:    vand.vx v8, v8, a3
; RV64-NEXT:    vmul.vx v8, v8, a4
; RV64-NEXT:    li a0, 56
; RV64-NEXT:    vsrl.vx v8, v8, a0
; RV64-NEXT:    ret
;
; CHECK-ZVBB-LABEL: vp_ctpop_nxv7i64_unmasked:
; CHECK-ZVBB:       # %bb.0:
; CHECK-ZVBB-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
; CHECK-ZVBB-NEXT:    vcpop.v v8, v8
; CHECK-ZVBB-NEXT:    ret
  %v = call <vscale x 7 x i64> @llvm.vp.ctpop.nxv7i64(<vscale x 7 x i64> %va, <vscale x 7 x i1> splat (i1 true), 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:    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:    vsetvli a2, zero, e32, m8, ta, ma
; RV32-NEXT:    vmv.v.x v24, a1
; RV32-NEXT:    lui a1, 209715
; RV32-NEXT:    addi a1, a1, 819
; RV32-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
; RV32-NEXT:    vand.vv v24, v16, v24, v0.t
; RV32-NEXT:    vsetvli a2, zero, e32, m8, ta, ma
; RV32-NEXT:    vmv.v.x v16, a1
; RV32-NEXT:    lui a1, 61681
; RV32-NEXT:    addi a1, a1, -241
; RV32-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
; RV32-NEXT:    vsub.vv v8, v8, v24, v0.t
; RV32-NEXT:    vand.vv v24, v8, v16, v0.t
; RV32-NEXT:    vsrl.vi v8, v8, 2, v0.t
; RV32-NEXT:    vand.vv v16, v8, v16, v0.t
; RV32-NEXT:    vsetvli a2, zero, e32, m8, ta, ma
; RV32-NEXT:    vmv.v.x v8, a1
; RV32-NEXT:    lui a1, 4112
; RV32-NEXT:    addi a1, a1, 257
; RV32-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
; RV32-NEXT:    vadd.vv v16, v24, v16, v0.t
; RV32-NEXT:    vsrl.vi v24, v16, 4, v0.t
; RV32-NEXT:    vadd.vv v16, v16, v24, v0.t
; RV32-NEXT:    vsetvli a2, zero, e32, m8, ta, ma
; RV32-NEXT:    vmv.v.x v24, a1
; RV32-NEXT:    li a1, 56
; RV32-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
; RV32-NEXT:    vand.vv v8, v16, v8, v0.t
; RV32-NEXT:    vmul.vv v8, v8, v24, v0.t
; RV32-NEXT:    vsrl.vx v8, v8, a1, v0.t
; RV32-NEXT:    ret
;
; RV64-LABEL: vp_ctpop_nxv8i64:
; RV64:       # %bb.0:
; RV64-NEXT:    lui a1, 349525
; RV64-NEXT:    lui a2, 209715
; RV64-NEXT:    lui a3, 61681
; RV64-NEXT:    lui a4, 4112
; RV64-NEXT:    addi a1, a1, 1365
; RV64-NEXT:    addi a2, a2, 819
; RV64-NEXT:    addi a3, a3, -241
; RV64-NEXT:    addi a4, a4, 257
; RV64-NEXT:    slli a5, a1, 32
; RV64-NEXT:    add a1, a1, a5
; RV64-NEXT:    slli a5, a2, 32
; RV64-NEXT:    add a2, a2, a5
; RV64-NEXT:    slli a5, a3, 32
; RV64-NEXT:    add a3, a3, a5
; RV64-NEXT:    slli a5, a4, 32
; RV64-NEXT:    add a4, a4, a5
; RV64-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
; 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:    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:    li a0, 56
; RV64-NEXT:    vmul.vx v8, v8, a4, v0.t
; RV64-NEXT:    vsrl.vx v8, v8, a0, v0.t
; RV64-NEXT:    ret
;
; CHECK-ZVBB-LABEL: vp_ctpop_nxv8i64:
; CHECK-ZVBB:       # %bb.0:
; CHECK-ZVBB-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
; CHECK-ZVBB-NEXT:    vcpop.v v8, v8, v0.t
; CHECK-ZVBB-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:    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:    vsetvli a2, zero, e32, m8, ta, ma
; RV32-NEXT:    vmv.v.x v24, a1
; RV32-NEXT:    lui a1, 209715
; RV32-NEXT:    addi a1, a1, 819
; RV32-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
; RV32-NEXT:    vand.vv v24, v16, v24
; RV32-NEXT:    vsetvli a2, zero, e32, m8, ta, ma
; RV32-NEXT:    vmv.v.x v16, a1
; RV32-NEXT:    lui a1, 61681
; RV32-NEXT:    addi a1, a1, -241
; RV32-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
; RV32-NEXT:    vsub.vv v8, v8, v24
; RV32-NEXT:    vand.vv v24, v8, v16
; RV32-NEXT:    vsrl.vi v8, v8, 2
; RV32-NEXT:    vand.vv v8, v8, v16
; RV32-NEXT:    vsetvli a2, zero, e32, m8, ta, ma
; RV32-NEXT:    vmv.v.x v16, a1
; RV32-NEXT:    lui a1, 4112
; RV32-NEXT:    addi a1, a1, 257
; RV32-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
; RV32-NEXT:    vadd.vv v8, v24, v8
; RV32-NEXT:    vsrl.vi v24, v8, 4
; RV32-NEXT:    vadd.vv v8, v8, v24
; RV32-NEXT:    vsetvli a2, zero, e32, m8, ta, ma
; RV32-NEXT:    vmv.v.x v24, a1
; RV32-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
; RV32-NEXT:    vand.vv v8, v8, v16
; RV32-NEXT:    vmul.vv v8, v8, v24
; RV32-NEXT:    li a0, 56
; RV32-NEXT:    vsrl.vx v8, v8, a0
; RV32-NEXT:    ret
;
; RV64-LABEL: vp_ctpop_nxv8i64_unmasked:
; RV64:       # %bb.0:
; RV64-NEXT:    lui a1, 349525
; RV64-NEXT:    lui a2, 209715
; RV64-NEXT:    lui a3, 61681
; RV64-NEXT:    lui a4, 4112
; RV64-NEXT:    addi a1, a1, 1365
; RV64-NEXT:    addi a2, a2, 819
; RV64-NEXT:    addi a3, a3, -241
; RV64-NEXT:    addi a4, a4, 257
; RV64-NEXT:    slli a5, a1, 32
; RV64-NEXT:    add a1, a1, a5
; RV64-NEXT:    slli a5, a2, 32
; RV64-NEXT:    add a2, a2, a5
; RV64-NEXT:    slli a5, a3, 32
; RV64-NEXT:    add a3, a3, a5
; RV64-NEXT:    slli a5, a4, 32
; RV64-NEXT:    add a4, a4, a5
; RV64-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
; RV64-NEXT:    vsrl.vi v16, v8, 1
; RV64-NEXT:    vand.vx v16, v16, a1
; RV64-NEXT:    vsub.vv v8, v8, v16
; RV64-NEXT:    vand.vx v16, v8, a2
; RV64-NEXT:    vsrl.vi v8, v8, 2
; RV64-NEXT:    vand.vx v8, v8, a2
; RV64-NEXT:    vadd.vv v8, v16, v8
; RV64-NEXT:    vsrl.vi v16, v8, 4
; RV64-NEXT:    vadd.vv v8, v8, v16
; RV64-NEXT:    vand.vx v8, v8, a3
; RV64-NEXT:    vmul.vx v8, v8, a4
; RV64-NEXT:    li a0, 56
; RV64-NEXT:    vsrl.vx v8, v8, a0
; RV64-NEXT:    ret
;
; CHECK-ZVBB-LABEL: vp_ctpop_nxv8i64_unmasked:
; CHECK-ZVBB:       # %bb.0:
; CHECK-ZVBB-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
; CHECK-ZVBB-NEXT:    vcpop.v v8, v8
; CHECK-ZVBB-NEXT:    ret
  %v = call <vscale x 8 x i64> @llvm.vp.ctpop.nxv8i64(<vscale x 8 x i64> %va, <vscale x 8 x i1> splat (i1 true), 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:    vsetvli a1, zero, e8, mf4, ta, ma
; RV32-NEXT:    vmv1r.v v7, v0
; 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 v8, (a1) # vscale x 64-byte Folded Spill
; RV32-NEXT:    csrr a1, vlenb
; RV32-NEXT:    lui a2, 349525
; RV32-NEXT:    srli a3, a1, 3
; RV32-NEXT:    vslidedown.vx v0, v0, a3
; RV32-NEXT:    sub a3, a0, a1
; RV32-NEXT:    addi a2, a2, 1365
; RV32-NEXT:    vsetvli a4, zero, e32, m8, ta, ma
; RV32-NEXT:    vmv.v.x v8, a2
; RV32-NEXT:    sltu a2, a0, a3
; RV32-NEXT:    addi a2, a2, -1
; RV32-NEXT:    and a2, a2, a3
; RV32-NEXT:    vsetvli zero, a2, e64, m8, ta, ma
; RV32-NEXT:    vsrl.vi v24, v16, 1, v0.t
; RV32-NEXT:    csrr a3, vlenb
; RV32-NEXT:    li a4, 40
; RV32-NEXT:    mul a3, a3, a4
; RV32-NEXT:    add a3, sp, a3
; RV32-NEXT:    addi a3, a3, 16
; RV32-NEXT:    vs8r.v v8, (a3) # vscale x 64-byte Folded Spill
; RV32-NEXT:    vand.vv v24, v24, v8, v0.t
; RV32-NEXT:    vsub.vv v16, v16, v24, v0.t
; RV32-NEXT:    lui a3, 209715
; RV32-NEXT:    addi a3, a3, 819
; RV32-NEXT:    vsetvli a4, zero, e32, m8, ta, ma
; RV32-NEXT:    vmv.v.x v8, a3
; RV32-NEXT:    vsetvli zero, a2, e64, m8, ta, ma
; RV32-NEXT:    vand.vv v24, v16, v8, v0.t
; RV32-NEXT:    vsrl.vi v16, v16, 2, v0.t
; RV32-NEXT:    csrr a3, vlenb
; RV32-NEXT:    li a4, 24
; RV32-NEXT:    mul a3, a3, a4
; RV32-NEXT:    add a3, sp, a3
; RV32-NEXT:    addi a3, a3, 16
; RV32-NEXT:    vs8r.v v8, (a3) # vscale x 64-byte Folded Spill
; RV32-NEXT:    vand.vv v16, v16, v8, v0.t
; RV32-NEXT:    vadd.vv v16, v24, v16, v0.t
; RV32-NEXT:    vsrl.vi v24, v16, 4, v0.t
; RV32-NEXT:    vadd.vv v16, v16, v24, v0.t
; RV32-NEXT:    lui a3, 61681
; RV32-NEXT:    addi a3, a3, -241
; RV32-NEXT:    vsetvli a4, zero, e32, m8, ta, ma
; RV32-NEXT:    vmv.v.x v8, a3
; RV32-NEXT:    csrr a3, vlenb
; RV32-NEXT:    slli a3, a3, 4
; RV32-NEXT:    add a3, sp, a3
; RV32-NEXT:    addi a3, a3, 16
; RV32-NEXT:    vs8r.v v8, (a3) # vscale x 64-byte Folded Spill
; RV32-NEXT:    vsetvli zero, a2, e64, m8, ta, ma
; RV32-NEXT:    vand.vv v16, v16, v8, v0.t
; RV32-NEXT:    lui a3, 4112
; RV32-NEXT:    addi a3, a3, 257
; RV32-NEXT:    vsetvli a4, zero, e32, m8, ta, ma
; RV32-NEXT:    vmv.v.x v8, a3
; 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) # vscale x 64-byte Folded Spill
; RV32-NEXT:    vsetvli zero, a2, e64, m8, ta, ma
; RV32-NEXT:    vmul.vv v16, v16, v8, v0.t
; RV32-NEXT:    li a2, 56
; RV32-NEXT:    vsrl.vx v8, v16, a2, v0.t
; RV32-NEXT:    addi a3, sp, 16
; RV32-NEXT:    vs8r.v v8, (a3) # vscale x 64-byte Folded Spill
; RV32-NEXT:    bltu a0, a1, .LBB46_2
; RV32-NEXT:  # %bb.1:
; RV32-NEXT:    mv a0, a1
; RV32-NEXT:  .LBB46_2:
; RV32-NEXT:    vmv1r.v v0, v7
; RV32-NEXT:    slli a1, a1, 5
; RV32-NEXT:    add a1, sp, a1
; RV32-NEXT:    addi a1, a1, 16
; RV32-NEXT:    vl8r.v v8, (a1) # vscale x 64-byte Folded Reload
; RV32-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
; RV32-NEXT:    vsrl.vi v16, v8, 1, 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 v24, (a0) # vscale x 64-byte Folded Reload
; RV32-NEXT:    vand.vv v24, v16, v24, v0.t
; RV32-NEXT:    vsub.vv v24, v8, v24, 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) # vscale x 64-byte Folded Reload
; RV32-NEXT:    vand.vv v8, v24, v16, v0.t
; RV32-NEXT:    vsrl.vi v24, v24, 2, v0.t
; RV32-NEXT:    vand.vv v24, v24, v16, v0.t
; RV32-NEXT:    vadd.vv v8, v8, v24, v0.t
; RV32-NEXT:    vsrl.vi v24, v8, 4, v0.t
; RV32-NEXT:    vadd.vv v8, v8, v24, 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) # vscale x 64-byte 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) # vscale x 64-byte Folded Reload
; RV32-NEXT:    vmul.vv v8, v8, v16, v0.t
; RV32-NEXT:    vsrl.vx v8, v8, a2, v0.t
; RV32-NEXT:    addi a0, sp, 16
; RV32-NEXT:    vl8r.v v16, (a0) # vscale x 64-byte 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:    .cfi_def_cfa sp, 16
; RV32-NEXT:    addi sp, sp, 16
; RV32-NEXT:    .cfi_def_cfa_offset 0
; RV32-NEXT:    ret
;
; RV64-LABEL: vp_ctpop_nxv16i64:
; RV64:       # %bb.0:
; RV64-NEXT:    csrr a1, vlenb
; RV64-NEXT:    srli a2, a1, 3
; RV64-NEXT:    vsetvli a3, zero, e8, mf4, ta, ma
; RV64-NEXT:    vslidedown.vx v7, v0, a2
; RV64-NEXT:    mv a2, a0
; RV64-NEXT:    bltu a0, a1, .LBB46_2
; RV64-NEXT:  # %bb.1:
; RV64-NEXT:    mv a2, a1
; RV64-NEXT:  .LBB46_2:
; RV64-NEXT:    vsetvli zero, a2, e64, m8, ta, ma
; RV64-NEXT:    vsrl.vi v24, v8, 1, v0.t
; RV64-NEXT:    lui a2, 349525
; RV64-NEXT:    lui a3, 209715
; RV64-NEXT:    lui a4, 61681
; RV64-NEXT:    lui a5, 4112
; RV64-NEXT:    addi a2, a2, 1365
; RV64-NEXT:    addi a3, a3, 819
; RV64-NEXT:    addi a4, a4, -241
; RV64-NEXT:    addi a5, a5, 257
; RV64-NEXT:    slli a6, a2, 32
; RV64-NEXT:    add a2, a2, a6
; RV64-NEXT:    slli a6, a3, 32
; RV64-NEXT:    add a3, a3, a6
; RV64-NEXT:    slli a6, a4, 32
; RV64-NEXT:    add a4, a4, a6
; RV64-NEXT:    slli a6, a5, 32
; RV64-NEXT:    add a5, a5, a6
; RV64-NEXT:    li a6, 56
; RV64-NEXT:    sub a1, a0, a1
; RV64-NEXT:    sltu a0, a0, a1
; RV64-NEXT:    addi a0, a0, -1
; RV64-NEXT:    and a0, a0, a1
; RV64-NEXT:    vand.vx v24, v24, a2, v0.t
; RV64-NEXT:    vsub.vv v8, v8, v24, v0.t
; RV64-NEXT:    vand.vx v24, v8, a3, v0.t
; RV64-NEXT:    vsrl.vi v8, v8, 2, v0.t
; RV64-NEXT:    vand.vx v8, v8, a3, v0.t
; RV64-NEXT:    vadd.vv v8, v24, v8, v0.t
; RV64-NEXT:    vsrl.vi v24, v8, 4, v0.t
; RV64-NEXT:    vadd.vv v8, v8, v24, 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:    vmv1r.v v0, v7
; RV64-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
; RV64-NEXT:    vsrl.vi v24, v16, 1, v0.t
; RV64-NEXT:    vand.vx v24, v24, a2, v0.t
; RV64-NEXT:    vsub.vv v16, v16, v24, v0.t
; RV64-NEXT:    vand.vx v24, v16, a3, v0.t
; RV64-NEXT:    vsrl.vi v16, v16, 2, v0.t
; RV64-NEXT:    vand.vx v16, v16, a3, v0.t
; RV64-NEXT:    vadd.vv v16, v24, v16, v0.t
; RV64-NEXT:    vsrl.vi v24, v16, 4, v0.t
; RV64-NEXT:    vadd.vv v16, v16, v24, v0.t
; RV64-NEXT:    vand.vx v16, v16, a4, v0.t
; RV64-NEXT:    vmul.vx v16, v16, a5, v0.t
; RV64-NEXT:    vsrl.vx v16, v16, a6, v0.t
; RV64-NEXT:    ret
;
; CHECK-ZVBB-LABEL: vp_ctpop_nxv16i64:
; CHECK-ZVBB:       # %bb.0:
; CHECK-ZVBB-NEXT:    vsetvli a1, zero, e8, mf4, ta, ma
; CHECK-ZVBB-NEXT:    vmv1r.v v24, v0
; CHECK-ZVBB-NEXT:    csrr a1, vlenb
; CHECK-ZVBB-NEXT:    srli a2, a1, 3
; CHECK-ZVBB-NEXT:    sub a3, a0, a1
; CHECK-ZVBB-NEXT:    vslidedown.vx v0, v0, a2
; CHECK-ZVBB-NEXT:    sltu a2, a0, a3
; CHECK-ZVBB-NEXT:    addi a2, a2, -1
; CHECK-ZVBB-NEXT:    and a2, a2, a3
; CHECK-ZVBB-NEXT:    vsetvli zero, a2, e64, m8, ta, ma
; CHECK-ZVBB-NEXT:    vcpop.v v16, v16, v0.t
; CHECK-ZVBB-NEXT:    bltu a0, a1, .LBB46_2
; CHECK-ZVBB-NEXT:  # %bb.1:
; CHECK-ZVBB-NEXT:    mv a0, a1
; CHECK-ZVBB-NEXT:  .LBB46_2:
; CHECK-ZVBB-NEXT:    vmv1r.v v0, v24
; CHECK-ZVBB-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
; CHECK-ZVBB-NEXT:    vcpop.v v8, v8, v0.t
; CHECK-ZVBB-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:    csrr a1, vlenb
; RV32-NEXT:    lui a2, 349525
; RV32-NEXT:    lui a3, 209715
; RV32-NEXT:    sub a4, a0, a1
; RV32-NEXT:    addi a2, a2, 1365
; RV32-NEXT:    addi a3, a3, 819
; RV32-NEXT:    vsetvli a5, zero, e32, m8, ta, ma
; RV32-NEXT:    vmv.v.x v0, a2
; RV32-NEXT:    sltu a2, a0, a4
; RV32-NEXT:    addi a2, a2, -1
; RV32-NEXT:    and a2, a2, a4
; RV32-NEXT:    vsetvli zero, a2, e64, m8, ta, ma
; RV32-NEXT:    vsrl.vi v24, v16, 1
; 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) # vscale x 64-byte Folded Spill
; RV32-NEXT:    vand.vv v24, v24, v0
; RV32-NEXT:    vsub.vv v16, v16, v24
; RV32-NEXT:    vsetvli a4, zero, e32, m8, ta, ma
; RV32-NEXT:    vmv.v.x v0, a3
; 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:    csrr a3, vlenb
; RV32-NEXT:    slli a3, a3, 4
; RV32-NEXT:    add a3, sp, a3
; RV32-NEXT:    addi a3, a3, 16
; RV32-NEXT:    vs8r.v v0, (a3) # vscale x 64-byte Folded Spill
; 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 v16, v16, v24
; RV32-NEXT:    lui a3, 61681
; RV32-NEXT:    lui a4, 4112
; RV32-NEXT:    addi a3, a3, -241
; RV32-NEXT:    addi a4, a4, 257
; RV32-NEXT:    vsetvli a5, zero, e32, m8, ta, ma
; RV32-NEXT:    vmv.v.x v24, a3
; 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 v24, (a3) # vscale x 64-byte Folded Spill
; RV32-NEXT:    vsetvli zero, a2, e64, m8, ta, ma
; RV32-NEXT:    vand.vv v16, v16, v24
; RV32-NEXT:    vsetvli a3, zero, e32, m8, ta, ma
; RV32-NEXT:    vmv.v.x v24, a4
; RV32-NEXT:    addi a3, sp, 16
; RV32-NEXT:    vs8r.v v24, (a3) # vscale x 64-byte Folded Spill
; RV32-NEXT:    vsetvli zero, a2, e64, m8, ta, ma
; RV32-NEXT:    vmul.vv v16, v16, v24
; RV32-NEXT:    li a2, 56
; RV32-NEXT:    vsrl.vx v16, v16, a2
; 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 v24, 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 v0, (a0) # vscale x 64-byte Folded Reload
; RV32-NEXT:    vand.vv v24, v24, v0
; RV32-NEXT:    vsub.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 v0, (a0) # vscale x 64-byte Folded Reload
; RV32-NEXT:    vand.vv v24, v8, v0
; RV32-NEXT:    vsrl.vi v8, v8, 2
; RV32-NEXT:    vand.vv v8, v8, v0
; RV32-NEXT:    vadd.vv v8, v24, v8
; RV32-NEXT:    vsrl.vi v24, v8, 4
; RV32-NEXT:    vadd.vv v8, v8, v24
; 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 v24, (a0) # vscale x 64-byte Folded Reload
; RV32-NEXT:    vand.vv v8, v8, v24
; RV32-NEXT:    addi a0, sp, 16
; RV32-NEXT:    vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
; RV32-NEXT:    vmul.vv v8, v8, v24
; RV32-NEXT:    vsrl.vx v8, v8, a2
; RV32-NEXT:    csrr a0, vlenb
; RV32-NEXT:    slli a0, a0, 5
; RV32-NEXT:    add sp, sp, a0
; RV32-NEXT:    .cfi_def_cfa sp, 16
; RV32-NEXT:    addi sp, sp, 16
; RV32-NEXT:    .cfi_def_cfa_offset 0
; RV32-NEXT:    ret
;
; RV64-LABEL: vp_ctpop_nxv16i64_unmasked:
; RV64:       # %bb.0:
; RV64-NEXT:    csrr a2, vlenb
; RV64-NEXT:    mv a1, a0
; RV64-NEXT:    bltu a0, a2, .LBB47_2
; RV64-NEXT:  # %bb.1:
; RV64-NEXT:    mv a1, a2
; RV64-NEXT:  .LBB47_2:
; RV64-NEXT:    vsetvli zero, a1, e64, m8, ta, ma
; RV64-NEXT:    vsrl.vi v24, v8, 1
; RV64-NEXT:    lui a3, 349525
; RV64-NEXT:    lui a4, 209715
; RV64-NEXT:    lui a5, 61681
; RV64-NEXT:    lui a6, 4112
; RV64-NEXT:    addi a3, a3, 1365
; RV64-NEXT:    addi a4, a4, 819
; RV64-NEXT:    addi a5, a5, -241
; RV64-NEXT:    addi a6, a6, 257
; RV64-NEXT:    slli a7, a3, 32
; RV64-NEXT:    add a3, a3, a7
; RV64-NEXT:    slli a7, a4, 32
; RV64-NEXT:    add a4, a4, a7
; RV64-NEXT:    slli a7, a5, 32
; RV64-NEXT:    add a5, a5, a7
; RV64-NEXT:    slli a7, a6, 32
; RV64-NEXT:    add a6, a6, a7
; RV64-NEXT:    li a7, 56
; RV64-NEXT:    sub a2, a0, a2
; RV64-NEXT:    sltu a0, a0, a2
; RV64-NEXT:    addi a0, a0, -1
; RV64-NEXT:    and a0, a0, a2
; RV64-NEXT:    vand.vx v24, v24, a3
; RV64-NEXT:    vsub.vv v8, v8, v24
; RV64-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
; RV64-NEXT:    vsrl.vi v24, v16, 1
; RV64-NEXT:    vand.vx v24, v24, a3
; RV64-NEXT:    vsub.vv v16, v16, v24
; RV64-NEXT:    vsetvli zero, a1, e64, m8, ta, ma
; RV64-NEXT:    vand.vx v24, v8, a4
; RV64-NEXT:    vsrl.vi v8, v8, 2
; RV64-NEXT:    vand.vx v8, v8, a4
; RV64-NEXT:    vadd.vv v8, v24, v8
; RV64-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
; RV64-NEXT:    vand.vx v24, v16, a4
; RV64-NEXT:    vsrl.vi v16, v16, 2
; RV64-NEXT:    vand.vx v16, v16, a4
; RV64-NEXT:    vadd.vv v16, v24, v16
; RV64-NEXT:    vsetvli zero, a1, e64, m8, ta, ma
; RV64-NEXT:    vsrl.vi v24, v8, 4
; RV64-NEXT:    vadd.vv v8, v8, v24
; RV64-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
; RV64-NEXT:    vsrl.vi v24, v16, 4
; RV64-NEXT:    vsetvli zero, a1, e64, m8, ta, ma
; RV64-NEXT:    vand.vx v8, v8, a5
; RV64-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
; RV64-NEXT:    vadd.vv v16, v16, v24
; RV64-NEXT:    vsetvli zero, a1, e64, m8, ta, ma
; RV64-NEXT:    vmul.vx v8, v8, a6
; RV64-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
; RV64-NEXT:    vand.vx v16, v16, a5
; RV64-NEXT:    vsetvli zero, a1, e64, m8, ta, ma
; RV64-NEXT:    vsrl.vx v8, v8, a7
; RV64-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
; RV64-NEXT:    vmul.vx v16, v16, a6
; RV64-NEXT:    vsrl.vx v16, v16, a7
; RV64-NEXT:    ret
;
; CHECK-ZVBB-LABEL: vp_ctpop_nxv16i64_unmasked:
; CHECK-ZVBB:       # %bb.0:
; CHECK-ZVBB-NEXT:    csrr a1, vlenb
; CHECK-ZVBB-NEXT:    sub a2, a0, a1
; CHECK-ZVBB-NEXT:    sltu a3, a0, a2
; CHECK-ZVBB-NEXT:    addi a3, a3, -1
; CHECK-ZVBB-NEXT:    and a2, a3, a2
; CHECK-ZVBB-NEXT:    vsetvli zero, a2, e64, m8, ta, ma
; CHECK-ZVBB-NEXT:    vcpop.v v16, v16
; CHECK-ZVBB-NEXT:    bltu a0, a1, .LBB47_2
; CHECK-ZVBB-NEXT:  # %bb.1:
; CHECK-ZVBB-NEXT:    mv a0, a1
; CHECK-ZVBB-NEXT:  .LBB47_2:
; CHECK-ZVBB-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
; CHECK-ZVBB-NEXT:    vcpop.v v8, v8
; CHECK-ZVBB-NEXT:    ret
  %v = call <vscale x 16 x i64> @llvm.vp.ctpop.nxv16i64(<vscale x 16 x i64> %va, <vscale x 16 x i1> splat (i1 true), i32 %evl)
  ret <vscale x 16 x i64> %v
}

; Test promotion.
declare <vscale x 1 x i9> @llvm.vp.ctpop.nxv1i9(<vscale x 1 x i9>, <vscale x 1 x i1>, i32)

define <vscale x 1 x i9> @vp_ctpop_nxv1i9(<vscale x 1 x i9> %va, <vscale x 1 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vp_ctpop_nxv1i9:
; CHECK:       # %bb.0:
; CHECK-NEXT:    li a1, 511
; CHECK-NEXT:    vsetvli zero, a0, e16, mf4, ta, ma
; CHECK-NEXT:    vand.vx v8, v8, a1, v0.t
; CHECK-NEXT:    lui a0, 5
; CHECK-NEXT:    addi a0, a0, 1365
; CHECK-NEXT:    vsrl.vi v9, v8, 1, v0.t
; CHECK-NEXT:    vand.vx v9, v9, a0, v0.t
; CHECK-NEXT:    lui a0, 3
; CHECK-NEXT:    addi a0, a0, 819
; CHECK-NEXT:    vsub.vv v8, v8, v9, v0.t
; 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:    lui a0, 1
; CHECK-NEXT:    addi a0, a0, -241
; 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.vx v8, v8, a0, v0.t
; CHECK-NEXT:    li a0, 257
; CHECK-NEXT:    vmul.vx v8, v8, a0, v0.t
; CHECK-NEXT:    vsrl.vi v8, v8, 8, v0.t
; CHECK-NEXT:    ret
;
; CHECK-ZVBB-LABEL: vp_ctpop_nxv1i9:
; CHECK-ZVBB:       # %bb.0:
; CHECK-ZVBB-NEXT:    li a1, 511
; CHECK-ZVBB-NEXT:    vsetvli zero, a0, e16, mf4, ta, ma
; CHECK-ZVBB-NEXT:    vand.vx v8, v8, a1, v0.t
; CHECK-ZVBB-NEXT:    vcpop.v v8, v8, v0.t
; CHECK-ZVBB-NEXT:    ret
  %v = call <vscale x 1 x i9> @llvm.vp.ctpop.nxv1i9(<vscale x 1 x i9> %va, <vscale x 1 x i1> %m, i32 %evl)
  ret <vscale x 1 x i9> %v
}