; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=riscv64 -mattr=+m,+v -verify-machineinstrs < %s | FileCheck %s

define <vscale x 1 x i64> @test_vp_reverse_nxv1i64_masked(<vscale x 1 x i64> %src, <vscale x 1 x i1> %mask, i32 zeroext %evl) {
; CHECK-LABEL: test_vp_reverse_nxv1i64_masked:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a0, e64, m1, ta, ma
; CHECK-NEXT:    vid.v v9, v0.t
; CHECK-NEXT:    addi a0, a0, -1
; CHECK-NEXT:    vrsub.vx v10, v9, a0, v0.t
; CHECK-NEXT:    vrgather.vv v9, v8, v10, v0.t
; CHECK-NEXT:    vmv.v.v v8, v9
; CHECK-NEXT:    ret
  %dst = call <vscale x 1 x i64> @llvm.experimental.vp.reverse.nxv1i64(<vscale x 1 x i64> %src, <vscale x 1 x i1> %mask, i32 %evl)
  ret <vscale x 1 x i64> %dst
}

define <vscale x 1 x i64> @test_vp_reverse_nxv1i64(<vscale x 1 x i64> %src, i32 zeroext %evl) {
; CHECK-LABEL: test_vp_reverse_nxv1i64:
; CHECK:       # %bb.0:
; CHECK-NEXT:    addi a1, a0, -1
; CHECK-NEXT:    vsetvli zero, a0, e64, m1, ta, ma
; CHECK-NEXT:    vid.v v9
; CHECK-NEXT:    vrsub.vx v10, v9, a1
; CHECK-NEXT:    vrgather.vv v9, v8, v10
; CHECK-NEXT:    vmv.v.v v8, v9
; CHECK-NEXT:    ret
  %head = insertelement <vscale x 1 x i1> undef, i1 1, i32 0
  %allones = shufflevector <vscale x 1 x i1> %head, <vscale x 1 x i1> undef, <vscale x 1 x i32> zeroinitializer

  %dst = call <vscale x 1 x i64> @llvm.experimental.vp.reverse.nxv1i64(<vscale x 1 x i64> %src, <vscale x 1 x i1> %allones, i32 %evl)
  ret <vscale x 1 x i64> %dst
}

define <vscale x 2 x i32> @test_vp_reverse_nxv2i32_masked(<vscale x 2 x i32> %src, <vscale x 2 x i1> %mask, i32 zeroext %evl) {
; CHECK-LABEL: test_vp_reverse_nxv2i32_masked:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a0, e32, m1, ta, ma
; CHECK-NEXT:    vid.v v9, v0.t
; CHECK-NEXT:    addi a0, a0, -1
; CHECK-NEXT:    vrsub.vx v10, v9, a0, v0.t
; CHECK-NEXT:    vrgather.vv v9, v8, v10, v0.t
; CHECK-NEXT:    vmv.v.v v8, v9
; CHECK-NEXT:    ret
  %dst = call <vscale x 2 x i32> @llvm.experimental.vp.reverse.nxv2i32(<vscale x 2 x i32> %src, <vscale x 2 x i1> %mask, i32 %evl)
  ret <vscale x 2 x i32> %dst
}

define <vscale x 2 x i32> @test_vp_reverse_nxv2i32(<vscale x 2 x i32> %src, i32 zeroext %evl) {
; CHECK-LABEL: test_vp_reverse_nxv2i32:
; CHECK:       # %bb.0:
; CHECK-NEXT:    addi a1, a0, -1
; CHECK-NEXT:    vsetvli zero, a0, e32, m1, ta, ma
; CHECK-NEXT:    vid.v v9
; CHECK-NEXT:    vrsub.vx v10, v9, a1
; CHECK-NEXT:    vrgather.vv v9, v8, v10
; CHECK-NEXT:    vmv.v.v v8, v9
; CHECK-NEXT:    ret
  %head = insertelement <vscale x 2 x i1> undef, i1 1, i32 0
  %allones = shufflevector <vscale x 2 x i1> %head, <vscale x 2 x i1> undef, <vscale x 2 x i32> zeroinitializer

  %dst = call <vscale x 2 x i32> @llvm.experimental.vp.reverse.nxv2i32(<vscale x 2 x i32> %src, <vscale x 2 x i1> %allones, i32 %evl)
  ret <vscale x 2 x i32> %dst
}

define <vscale x 4 x i16> @test_vp_reverse_nxv4i16_masked(<vscale x 4 x i16> %src, <vscale x 4 x i1> %mask, i32 zeroext %evl) {
; CHECK-LABEL: test_vp_reverse_nxv4i16_masked:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a0, e16, m1, ta, ma
; CHECK-NEXT:    vid.v v9, v0.t
; CHECK-NEXT:    addi a0, a0, -1
; CHECK-NEXT:    vrsub.vx v10, v9, a0, v0.t
; CHECK-NEXT:    vrgather.vv v9, v8, v10, v0.t
; CHECK-NEXT:    vmv.v.v v8, v9
; CHECK-NEXT:    ret
  %dst = call <vscale x 4 x i16> @llvm.experimental.vp.reverse.nxv4i16(<vscale x 4 x i16> %src, <vscale x 4 x i1> %mask, i32 %evl)
  ret <vscale x 4 x i16> %dst
}

define <vscale x 4 x i16> @test_vp_reverse_nxv4i16(<vscale x 4 x i16> %src, i32 zeroext %evl) {
; CHECK-LABEL: test_vp_reverse_nxv4i16:
; CHECK:       # %bb.0:
; CHECK-NEXT:    addi a1, a0, -1
; CHECK-NEXT:    vsetvli zero, a0, e16, m1, ta, ma
; CHECK-NEXT:    vid.v v9
; CHECK-NEXT:    vrsub.vx v10, v9, a1
; CHECK-NEXT:    vrgather.vv v9, v8, v10
; CHECK-NEXT:    vmv.v.v v8, v9
; CHECK-NEXT:    ret
  %head = insertelement <vscale x 4 x i1> undef, i1 1, i32 0
  %allones = shufflevector <vscale x 4 x i1> %head, <vscale x 4 x i1> undef, <vscale x 4 x i32> zeroinitializer

  %dst = call <vscale x 4 x i16> @llvm.experimental.vp.reverse.nxv4i16(<vscale x 4 x i16> %src, <vscale x 4 x i1> %allones, i32 %evl)
  ret <vscale x 4 x i16> %dst
}

define <vscale x 8 x i8> @test_vp_reverse_nxv8i8_masked(<vscale x 8 x i8> %src, <vscale x 8 x i1> %mask, i32 zeroext %evl) {
; CHECK-LABEL: test_vp_reverse_nxv8i8_masked:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a0, e16, m2, ta, ma
; CHECK-NEXT:    vid.v v10, v0.t
; CHECK-NEXT:    addi a0, a0, -1
; CHECK-NEXT:    vrsub.vx v10, v10, a0, v0.t
; CHECK-NEXT:    vsetvli zero, zero, e8, m1, ta, ma
; CHECK-NEXT:    vrgatherei16.vv v9, v8, v10, v0.t
; CHECK-NEXT:    vmv.v.v v8, v9
; CHECK-NEXT:    ret
  %dst = call <vscale x 8 x i8> @llvm.experimental.vp.reverse.nxv8i8(<vscale x 8 x i8> %src, <vscale x 8 x i1> %mask, i32 %evl)
  ret <vscale x 8 x i8> %dst
}

define <vscale x 8 x i8> @test_vp_reverse_nxv8i8(<vscale x 8 x i8> %src, i32 zeroext %evl) {
; CHECK-LABEL: test_vp_reverse_nxv8i8:
; CHECK:       # %bb.0:
; CHECK-NEXT:    addi a1, a0, -1
; CHECK-NEXT:    vsetvli zero, a0, e16, m2, ta, ma
; CHECK-NEXT:    vid.v v10
; CHECK-NEXT:    vrsub.vx v10, v10, a1
; CHECK-NEXT:    vsetvli zero, zero, e8, m1, ta, ma
; CHECK-NEXT:    vrgatherei16.vv v9, v8, v10
; CHECK-NEXT:    vmv.v.v v8, v9
; CHECK-NEXT:    ret
  %head = insertelement <vscale x 8 x i1> undef, i1 1, i32 0
  %allones = shufflevector <vscale x 8 x i1> %head, <vscale x 8 x i1> undef, <vscale x 8 x i32> zeroinitializer

  %dst = call <vscale x 8 x i8> @llvm.experimental.vp.reverse.nxv8i8(<vscale x 8 x i8> %src, <vscale x 8 x i1> %allones, i32 %evl)
  ret <vscale x 8 x i8> %dst
}

define <vscale x 2 x i64> @test_vp_reverse_nxv2i64_masked(<vscale x 2 x i64> %src, <vscale x 2 x i1> %mask, i32 zeroext %evl) {
; CHECK-LABEL: test_vp_reverse_nxv2i64_masked:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a0, e64, m2, ta, ma
; CHECK-NEXT:    vid.v v10, v0.t
; CHECK-NEXT:    addi a0, a0, -1
; CHECK-NEXT:    vrsub.vx v12, v10, a0, v0.t
; CHECK-NEXT:    vrgather.vv v10, v8, v12, v0.t
; CHECK-NEXT:    vmv.v.v v8, v10
; CHECK-NEXT:    ret
  %dst = call <vscale x 2 x i64> @llvm.experimental.vp.reverse.nxv2i64(<vscale x 2 x i64> %src, <vscale x 2 x i1> %mask, i32 %evl)
  ret <vscale x 2 x i64> %dst
}

define <vscale x 2 x i64> @test_vp_reverse_nxv2i64(<vscale x 2 x i64> %src, i32 zeroext %evl) {
; CHECK-LABEL: test_vp_reverse_nxv2i64:
; CHECK:       # %bb.0:
; CHECK-NEXT:    addi a1, a0, -1
; CHECK-NEXT:    vsetvli zero, a0, e64, m2, ta, ma
; CHECK-NEXT:    vid.v v10
; CHECK-NEXT:    vrsub.vx v12, v10, a1
; CHECK-NEXT:    vrgather.vv v10, v8, v12
; CHECK-NEXT:    vmv.v.v v8, v10
; CHECK-NEXT:    ret
  %head = insertelement <vscale x 2 x i1> undef, i1 1, i32 0
  %allones = shufflevector <vscale x 2 x i1> %head, <vscale x 2 x i1> undef, <vscale x 2 x i32> zeroinitializer

  %dst = call <vscale x 2 x i64> @llvm.experimental.vp.reverse.nxv2i64(<vscale x 2 x i64> %src, <vscale x 2 x i1> %allones, i32 %evl)
  ret <vscale x 2 x i64> %dst
}

define <vscale x 4 x i32> @test_vp_reverse_nxv4i32_masked(<vscale x 4 x i32> %src, <vscale x 4 x i1> %mask, i32 zeroext %evl) {
; CHECK-LABEL: test_vp_reverse_nxv4i32_masked:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a0, e32, m2, ta, ma
; CHECK-NEXT:    vid.v v10, v0.t
; CHECK-NEXT:    addi a0, a0, -1
; CHECK-NEXT:    vrsub.vx v12, v10, a0, v0.t
; CHECK-NEXT:    vrgather.vv v10, v8, v12, v0.t
; CHECK-NEXT:    vmv.v.v v8, v10
; CHECK-NEXT:    ret
  %dst = call <vscale x 4 x i32> @llvm.experimental.vp.reverse.nxv4i32(<vscale x 4 x i32> %src, <vscale x 4 x i1> %mask, i32 %evl)
  ret <vscale x 4 x i32> %dst
}

define <vscale x 4 x i32> @test_vp_reverse_nxv4i32(<vscale x 4 x i32> %src, i32 zeroext %evl) {
; CHECK-LABEL: test_vp_reverse_nxv4i32:
; CHECK:       # %bb.0:
; CHECK-NEXT:    addi a1, a0, -1
; CHECK-NEXT:    vsetvli zero, a0, e32, m2, ta, ma
; CHECK-NEXT:    vid.v v10
; CHECK-NEXT:    vrsub.vx v12, v10, a1
; CHECK-NEXT:    vrgather.vv v10, v8, v12
; CHECK-NEXT:    vmv.v.v v8, v10
; CHECK-NEXT:    ret
  %head = insertelement <vscale x 4 x i1> undef, i1 1, i32 0
  %allones = shufflevector <vscale x 4 x i1> %head, <vscale x 4 x i1> undef, <vscale x 4 x i32> zeroinitializer

  %dst = call <vscale x 4 x i32> @llvm.experimental.vp.reverse.nxv4i32(<vscale x 4 x i32> %src, <vscale x 4 x i1> %allones, i32 %evl)
  ret <vscale x 4 x i32> %dst
}

define <vscale x 8 x i16> @test_vp_reverse_nxv8i16_masked(<vscale x 8 x i16> %src, <vscale x 8 x i1> %mask, i32 zeroext %evl) {
; CHECK-LABEL: test_vp_reverse_nxv8i16_masked:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a0, e16, m2, ta, ma
; CHECK-NEXT:    vid.v v10, v0.t
; CHECK-NEXT:    addi a0, a0, -1
; CHECK-NEXT:    vrsub.vx v12, v10, a0, v0.t
; CHECK-NEXT:    vrgather.vv v10, v8, v12, v0.t
; CHECK-NEXT:    vmv.v.v v8, v10
; CHECK-NEXT:    ret
  %dst = call <vscale x 8 x i16> @llvm.experimental.vp.reverse.nxv8i16(<vscale x 8 x i16> %src, <vscale x 8 x i1> %mask, i32 %evl)
  ret <vscale x 8 x i16> %dst
}

define <vscale x 8 x i16> @test_vp_reverse_nxv8i16(<vscale x 8 x i16> %src, i32 zeroext %evl) {
; CHECK-LABEL: test_vp_reverse_nxv8i16:
; CHECK:       # %bb.0:
; CHECK-NEXT:    addi a1, a0, -1
; CHECK-NEXT:    vsetvli zero, a0, e16, m2, ta, ma
; CHECK-NEXT:    vid.v v10
; CHECK-NEXT:    vrsub.vx v12, v10, a1
; CHECK-NEXT:    vrgather.vv v10, v8, v12
; CHECK-NEXT:    vmv.v.v v8, v10
; CHECK-NEXT:    ret
  %head = insertelement <vscale x 8 x i1> undef, i1 1, i32 0
  %allones = shufflevector <vscale x 8 x i1> %head, <vscale x 8 x i1> undef, <vscale x 8 x i32> zeroinitializer

  %dst = call <vscale x 8 x i16> @llvm.experimental.vp.reverse.nxv8i16(<vscale x 8 x i16> %src, <vscale x 8 x i1> %allones, i32 %evl)
  ret <vscale x 8 x i16> %dst
}

define <vscale x 16 x i8> @test_vp_reverse_nxv16i8_masked(<vscale x 16 x i8> %src, <vscale x 16 x i1> %mask, i32 zeroext %evl) {
; CHECK-LABEL: test_vp_reverse_nxv16i8_masked:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a0, e16, m4, ta, ma
; CHECK-NEXT:    vid.v v12, v0.t
; CHECK-NEXT:    addi a0, a0, -1
; CHECK-NEXT:    vrsub.vx v12, v12, a0, v0.t
; CHECK-NEXT:    vsetvli zero, zero, e8, m2, ta, ma
; CHECK-NEXT:    vrgatherei16.vv v10, v8, v12, v0.t
; CHECK-NEXT:    vmv.v.v v8, v10
; CHECK-NEXT:    ret
  %dst = call <vscale x 16 x i8> @llvm.experimental.vp.reverse.nxv16i8(<vscale x 16 x i8> %src, <vscale x 16 x i1> %mask, i32 %evl)
  ret <vscale x 16 x i8> %dst
}

define <vscale x 16 x i8> @test_vp_reverse_nxv16i8(<vscale x 16 x i8> %src, i32 zeroext %evl) {
; CHECK-LABEL: test_vp_reverse_nxv16i8:
; CHECK:       # %bb.0:
; CHECK-NEXT:    addi a1, a0, -1
; CHECK-NEXT:    vsetvli zero, a0, e16, m4, ta, ma
; CHECK-NEXT:    vid.v v12
; CHECK-NEXT:    vrsub.vx v12, v12, a1
; CHECK-NEXT:    vsetvli zero, zero, e8, m2, ta, ma
; CHECK-NEXT:    vrgatherei16.vv v10, v8, v12
; CHECK-NEXT:    vmv.v.v v8, v10
; CHECK-NEXT:    ret
  %head = insertelement <vscale x 16 x i1> undef, i1 1, i32 0
  %allones = shufflevector <vscale x 16 x i1> %head, <vscale x 16 x i1> undef, <vscale x 16 x i32> zeroinitializer

  %dst = call <vscale x 16 x i8> @llvm.experimental.vp.reverse.nxv16i8(<vscale x 16 x i8> %src, <vscale x 16 x i1> %allones, i32 %evl)
  ret <vscale x 16 x i8> %dst
}

define <vscale x 4 x i64> @test_vp_reverse_nxv4i64_masked(<vscale x 4 x i64> %src, <vscale x 4 x i1> %mask, i32 zeroext %evl) {
; CHECK-LABEL: test_vp_reverse_nxv4i64_masked:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a0, e64, m4, ta, ma
; CHECK-NEXT:    vid.v v12, v0.t
; CHECK-NEXT:    addi a0, a0, -1
; CHECK-NEXT:    vrsub.vx v16, v12, a0, v0.t
; CHECK-NEXT:    vrgather.vv v12, v8, v16, v0.t
; CHECK-NEXT:    vmv.v.v v8, v12
; CHECK-NEXT:    ret
  %dst = call <vscale x 4 x i64> @llvm.experimental.vp.reverse.nxv4i64(<vscale x 4 x i64> %src, <vscale x 4 x i1> %mask, i32 %evl)
  ret <vscale x 4 x i64> %dst
}

define <vscale x 4 x i64> @test_vp_reverse_nxv4i64(<vscale x 4 x i64> %src, i32 zeroext %evl) {
; CHECK-LABEL: test_vp_reverse_nxv4i64:
; CHECK:       # %bb.0:
; CHECK-NEXT:    addi a1, a0, -1
; CHECK-NEXT:    vsetvli zero, a0, e64, m4, ta, ma
; CHECK-NEXT:    vid.v v12
; CHECK-NEXT:    vrsub.vx v16, v12, a1
; CHECK-NEXT:    vrgather.vv v12, v8, v16
; CHECK-NEXT:    vmv.v.v v8, v12
; CHECK-NEXT:    ret
  %head = insertelement <vscale x 4 x i1> undef, i1 1, i32 0
  %allones = shufflevector <vscale x 4 x i1> %head, <vscale x 4 x i1> undef, <vscale x 4 x i32> zeroinitializer

  %dst = call <vscale x 4 x i64> @llvm.experimental.vp.reverse.nxv4i64(<vscale x 4 x i64> %src, <vscale x 4 x i1> %allones, i32 %evl)
  ret <vscale x 4 x i64> %dst
}

define <vscale x 8 x i32> @test_vp_reverse_nxv8i32_masked(<vscale x 8 x i32> %src, <vscale x 8 x i1> %mask, i32 zeroext %evl) {
; CHECK-LABEL: test_vp_reverse_nxv8i32_masked:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a0, e32, m4, ta, ma
; CHECK-NEXT:    vid.v v12, v0.t
; CHECK-NEXT:    addi a0, a0, -1
; CHECK-NEXT:    vrsub.vx v16, v12, a0, v0.t
; CHECK-NEXT:    vrgather.vv v12, v8, v16, v0.t
; CHECK-NEXT:    vmv.v.v v8, v12
; CHECK-NEXT:    ret
  %dst = call <vscale x 8 x i32> @llvm.experimental.vp.reverse.nxv8i32(<vscale x 8 x i32> %src, <vscale x 8 x i1> %mask, i32 %evl)
  ret <vscale x 8 x i32> %dst
}

define <vscale x 8 x i32> @test_vp_reverse_nxv8i32(<vscale x 8 x i32> %src, i32 zeroext %evl) {
; CHECK-LABEL: test_vp_reverse_nxv8i32:
; CHECK:       # %bb.0:
; CHECK-NEXT:    addi a1, a0, -1
; CHECK-NEXT:    vsetvli zero, a0, e32, m4, ta, ma
; CHECK-NEXT:    vid.v v12
; CHECK-NEXT:    vrsub.vx v16, v12, a1
; CHECK-NEXT:    vrgather.vv v12, v8, v16
; CHECK-NEXT:    vmv.v.v v8, v12
; CHECK-NEXT:    ret
  %head = insertelement <vscale x 8 x i1> undef, i1 1, i32 0
  %allones = shufflevector <vscale x 8 x i1> %head, <vscale x 8 x i1> undef, <vscale x 8 x i32> zeroinitializer

  %dst = call <vscale x 8 x i32> @llvm.experimental.vp.reverse.nxv8i32(<vscale x 8 x i32> %src, <vscale x 8 x i1> %allones, i32 %evl)
  ret <vscale x 8 x i32> %dst
}

define <vscale x 16 x i16> @test_vp_reverse_nxv16i16_masked(<vscale x 16 x i16> %src, <vscale x 16 x i1> %mask, i32 zeroext %evl) {
; CHECK-LABEL: test_vp_reverse_nxv16i16_masked:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a0, e16, m4, ta, ma
; CHECK-NEXT:    vid.v v12, v0.t
; CHECK-NEXT:    addi a0, a0, -1
; CHECK-NEXT:    vrsub.vx v16, v12, a0, v0.t
; CHECK-NEXT:    vrgather.vv v12, v8, v16, v0.t
; CHECK-NEXT:    vmv.v.v v8, v12
; CHECK-NEXT:    ret
  %dst = call <vscale x 16 x i16> @llvm.experimental.vp.reverse.nxv16i16(<vscale x 16 x i16> %src, <vscale x 16 x i1> %mask, i32 %evl)
  ret <vscale x 16 x i16> %dst
}

define <vscale x 16 x i16> @test_vp_reverse_nxv16i16(<vscale x 16 x i16> %src, i32 zeroext %evl) {
; CHECK-LABEL: test_vp_reverse_nxv16i16:
; CHECK:       # %bb.0:
; CHECK-NEXT:    addi a1, a0, -1
; CHECK-NEXT:    vsetvli zero, a0, e16, m4, ta, ma
; CHECK-NEXT:    vid.v v12
; CHECK-NEXT:    vrsub.vx v16, v12, a1
; CHECK-NEXT:    vrgather.vv v12, v8, v16
; CHECK-NEXT:    vmv.v.v v8, v12
; CHECK-NEXT:    ret
  %head = insertelement <vscale x 16 x i1> undef, i1 1, i32 0
  %allones = shufflevector <vscale x 16 x i1> %head, <vscale x 16 x i1> undef, <vscale x 16 x i32> zeroinitializer

  %dst = call <vscale x 16 x i16> @llvm.experimental.vp.reverse.nxv16i16(<vscale x 16 x i16> %src, <vscale x 16 x i1> %allones, i32 %evl)
  ret <vscale x 16 x i16> %dst
}

define <vscale x 32 x i8> @test_vp_reverse_nxv32i8_masked(<vscale x 32 x i8> %src, <vscale x 32 x i1> %mask, i32 zeroext %evl) {
; CHECK-LABEL: test_vp_reverse_nxv32i8_masked:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a0, e16, m8, ta, ma
; CHECK-NEXT:    vid.v v16, v0.t
; CHECK-NEXT:    addi a0, a0, -1
; CHECK-NEXT:    vrsub.vx v16, v16, a0, v0.t
; CHECK-NEXT:    vsetvli zero, zero, e8, m4, ta, ma
; CHECK-NEXT:    vrgatherei16.vv v12, v8, v16, v0.t
; CHECK-NEXT:    vmv.v.v v8, v12
; CHECK-NEXT:    ret
  %dst = call <vscale x 32 x i8> @llvm.experimental.vp.reverse.nxv32i8(<vscale x 32 x i8> %src, <vscale x 32 x i1> %mask, i32 %evl)
  ret <vscale x 32 x i8> %dst
}

define <vscale x 32 x i8> @test_vp_reverse_nxv32i8(<vscale x 32 x i8> %src, i32 zeroext %evl) {
; CHECK-LABEL: test_vp_reverse_nxv32i8:
; CHECK:       # %bb.0:
; CHECK-NEXT:    addi a1, a0, -1
; CHECK-NEXT:    vsetvli zero, a0, e16, m8, ta, ma
; CHECK-NEXT:    vid.v v16
; CHECK-NEXT:    vrsub.vx v16, v16, a1
; CHECK-NEXT:    vsetvli zero, zero, e8, m4, ta, ma
; CHECK-NEXT:    vrgatherei16.vv v12, v8, v16
; CHECK-NEXT:    vmv.v.v v8, v12
; CHECK-NEXT:    ret
  %head = insertelement <vscale x 32 x i1> undef, i1 1, i32 0
  %allones = shufflevector <vscale x 32 x i1> %head, <vscale x 32 x i1> undef, <vscale x 32 x i32> zeroinitializer

  %dst = call <vscale x 32 x i8> @llvm.experimental.vp.reverse.nxv32i8(<vscale x 32 x i8> %src, <vscale x 32 x i1> %allones, i32 %evl)
  ret <vscale x 32 x i8> %dst
}

define <vscale x 8 x i64> @test_vp_reverse_nxv8i64_masked(<vscale x 8 x i64> %src, <vscale x 8 x i1> %mask, i32 zeroext %evl) {
; CHECK-LABEL: test_vp_reverse_nxv8i64_masked:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
; CHECK-NEXT:    vid.v v16, v0.t
; CHECK-NEXT:    addi a0, a0, -1
; CHECK-NEXT:    vrsub.vx v24, v16, a0, v0.t
; CHECK-NEXT:    vrgather.vv v16, v8, v24, v0.t
; CHECK-NEXT:    vmv.v.v v8, v16
; CHECK-NEXT:    ret
  %dst = call <vscale x 8 x i64> @llvm.experimental.vp.reverse.nxv8i64(<vscale x 8 x i64> %src, <vscale x 8 x i1> %mask, i32 %evl)
  ret <vscale x 8 x i64> %dst
}

define <vscale x 8 x i64> @test_vp_reverse_nxv8i64(<vscale x 8 x i64> %src, i32 zeroext %evl) {
; CHECK-LABEL: test_vp_reverse_nxv8i64:
; CHECK:       # %bb.0:
; CHECK-NEXT:    addi a1, a0, -1
; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
; CHECK-NEXT:    vid.v v16
; CHECK-NEXT:    vrsub.vx v24, v16, a1
; CHECK-NEXT:    vrgather.vv v16, v8, v24
; CHECK-NEXT:    vmv.v.v v8, v16
; CHECK-NEXT:    ret
  %head = insertelement <vscale x 8 x i1> undef, i1 1, i32 0
  %allones = shufflevector <vscale x 8 x i1> %head, <vscale x 8 x i1> undef, <vscale x 8 x i32> zeroinitializer

  %dst = call <vscale x 8 x i64> @llvm.experimental.vp.reverse.nxv8i64(<vscale x 8 x i64> %src, <vscale x 8 x i1> %allones, i32 %evl)
  ret <vscale x 8 x i64> %dst
}

define <vscale x 16 x i32> @test_vp_reverse_nxv16i32_masked(<vscale x 16 x i32> %src, <vscale x 16 x i1> %mask, i32 zeroext %evl) {
; CHECK-LABEL: test_vp_reverse_nxv16i32_masked:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a0, e32, m8, ta, ma
; CHECK-NEXT:    vid.v v16, v0.t
; CHECK-NEXT:    addi a0, a0, -1
; CHECK-NEXT:    vrsub.vx v24, v16, a0, v0.t
; CHECK-NEXT:    vrgather.vv v16, v8, v24, v0.t
; CHECK-NEXT:    vmv.v.v v8, v16
; CHECK-NEXT:    ret
  %dst = call <vscale x 16 x i32> @llvm.experimental.vp.reverse.nxv16i32(<vscale x 16 x i32> %src, <vscale x 16 x i1> %mask, i32 %evl)
  ret <vscale x 16 x i32> %dst
}

define <vscale x 16 x i32> @test_vp_reverse_nxv16i32(<vscale x 16 x i32> %src, i32 zeroext %evl) {
; CHECK-LABEL: test_vp_reverse_nxv16i32:
; CHECK:       # %bb.0:
; CHECK-NEXT:    addi a1, a0, -1
; CHECK-NEXT:    vsetvli zero, a0, e32, m8, ta, ma
; CHECK-NEXT:    vid.v v16
; CHECK-NEXT:    vrsub.vx v24, v16, a1
; CHECK-NEXT:    vrgather.vv v16, v8, v24
; CHECK-NEXT:    vmv.v.v v8, v16
; CHECK-NEXT:    ret
  %head = insertelement <vscale x 16 x i1> undef, i1 1, i32 0
  %allones = shufflevector <vscale x 16 x i1> %head, <vscale x 16 x i1> undef, <vscale x 16 x i32> zeroinitializer

  %dst = call <vscale x 16 x i32> @llvm.experimental.vp.reverse.nxv16i32(<vscale x 16 x i32> %src, <vscale x 16 x i1> %allones, i32 %evl)
  ret <vscale x 16 x i32> %dst
}

define <vscale x 32 x i16> @test_vp_reverse_nxv32i16_masked(<vscale x 32 x i16> %src, <vscale x 32 x i1> %mask, i32 zeroext %evl) {
; CHECK-LABEL: test_vp_reverse_nxv32i16_masked:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a0, e16, m8, ta, ma
; CHECK-NEXT:    vid.v v16, v0.t
; CHECK-NEXT:    addi a0, a0, -1
; CHECK-NEXT:    vrsub.vx v24, v16, a0, v0.t
; CHECK-NEXT:    vrgather.vv v16, v8, v24, v0.t
; CHECK-NEXT:    vmv.v.v v8, v16
; CHECK-NEXT:    ret
  %dst = call <vscale x 32 x i16> @llvm.experimental.vp.reverse.nxv32i16(<vscale x 32 x i16> %src, <vscale x 32 x i1> %mask, i32 %evl)
  ret <vscale x 32 x i16> %dst
}

define <vscale x 32 x i16> @test_vp_reverse_nxv32i16(<vscale x 32 x i16> %src, i32 zeroext %evl) {
; CHECK-LABEL: test_vp_reverse_nxv32i16:
; CHECK:       # %bb.0:
; CHECK-NEXT:    addi a1, a0, -1
; CHECK-NEXT:    vsetvli zero, a0, e16, m8, ta, ma
; CHECK-NEXT:    vid.v v16
; CHECK-NEXT:    vrsub.vx v24, v16, a1
; CHECK-NEXT:    vrgather.vv v16, v8, v24
; CHECK-NEXT:    vmv.v.v v8, v16
; CHECK-NEXT:    ret
  %head = insertelement <vscale x 32 x i1> undef, i1 1, i32 0
  %allones = shufflevector <vscale x 32 x i1> %head, <vscale x 32 x i1> undef, <vscale x 32 x i32> zeroinitializer

  %dst = call <vscale x 32 x i16> @llvm.experimental.vp.reverse.nxv32i16(<vscale x 32 x i16> %src, <vscale x 32 x i1> %allones, i32 %evl)
  ret <vscale x 32 x i16> %dst
}

define <vscale x 64 x i8> @test_vp_reverse_nxv64i8_masked(<vscale x 64 x i8> %src, <vscale x 64 x i1> %mask, i32 zeroext %evl) {
; CHECK-LABEL: test_vp_reverse_nxv64i8_masked:
; CHECK:       # %bb.0:
; CHECK-NEXT:    csrr a1, vlenb
; CHECK-NEXT:    slli a2, a1, 2
; CHECK-NEXT:    addi a2, a2, -1
; CHECK-NEXT:    vsetvli a3, zero, e16, m8, ta, ma
; CHECK-NEXT:    vid.v v16
; CHECK-NEXT:    vrsub.vx v24, v16, a2
; CHECK-NEXT:    vsetvli zero, zero, e8, m4, ta, ma
; CHECK-NEXT:    vrgatherei16.vv v20, v8, v24
; CHECK-NEXT:    vrgatherei16.vv v16, v12, v24
; CHECK-NEXT:    slli a1, a1, 3
; CHECK-NEXT:    sub a1, a1, a0
; CHECK-NEXT:    vsetvli zero, a0, e8, m8, ta, ma
; CHECK-NEXT:    vslidedown.vx v8, v16, a1, v0.t
; CHECK-NEXT:    ret
  %dst = call <vscale x 64 x i8> @llvm.experimental.vp.reverse.nxv64i8(<vscale x 64 x i8> %src, <vscale x 64 x i1> %mask, i32 %evl)
  ret <vscale x 64 x i8> %dst
}

define <vscale x 64 x i8> @test_vp_reverse_nxv64i8(<vscale x 64 x i8> %src, i32 zeroext %evl) {
; CHECK-LABEL: test_vp_reverse_nxv64i8:
; CHECK:       # %bb.0:
; CHECK-NEXT:    csrr a1, vlenb
; CHECK-NEXT:    slli a2, a1, 2
; CHECK-NEXT:    addi a2, a2, -1
; CHECK-NEXT:    vsetvli a3, zero, e16, m8, ta, ma
; CHECK-NEXT:    vid.v v16
; CHECK-NEXT:    vrsub.vx v16, v16, a2
; CHECK-NEXT:    vsetvli zero, zero, e8, m4, ta, ma
; CHECK-NEXT:    vrgatherei16.vv v28, v8, v16
; CHECK-NEXT:    vrgatherei16.vv v24, v12, v16
; CHECK-NEXT:    slli a1, a1, 3
; CHECK-NEXT:    sub a1, a1, a0
; CHECK-NEXT:    vsetvli zero, a0, e8, m8, ta, ma
; CHECK-NEXT:    vslidedown.vx v8, v24, a1
; CHECK-NEXT:    ret
  %head = insertelement <vscale x 64 x i1> undef, i1 1, i32 0
  %allones = shufflevector <vscale x 64 x i1> %head, <vscale x 64 x i1> undef, <vscale x 64 x i32> zeroinitializer

  %dst = call <vscale x 64 x i8> @llvm.experimental.vp.reverse.nxv64i8(<vscale x 64 x i8> %src, <vscale x 64 x i1> %allones, i32 %evl)
  ret <vscale x 64 x i8> %dst
}

define <vscale x 128 x i8> @test_vp_reverse_nxv128i8(<vscale x 128 x i8> %src, i32 zeroext %evl) {
; CHECK-LABEL: test_vp_reverse_nxv128i8:
; CHECK:       # %bb.0:
; CHECK-NEXT:    csrr a1, vlenb
; CHECK-NEXT:    slli a1, a1, 3
; CHECK-NEXT:    mv a2, a0
; CHECK-NEXT:    bltu a0, a1, .LBB32_2
; CHECK-NEXT:  # %bb.1:
; CHECK-NEXT:    mv a2, a1
; CHECK-NEXT:  .LBB32_2:
; CHECK-NEXT:    addi sp, sp, -80
; CHECK-NEXT:    .cfi_def_cfa_offset 80
; CHECK-NEXT:    sd ra, 72(sp) # 8-byte Folded Spill
; CHECK-NEXT:    sd s0, 64(sp) # 8-byte Folded Spill
; CHECK-NEXT:    .cfi_offset ra, -8
; CHECK-NEXT:    .cfi_offset s0, -16
; CHECK-NEXT:    addi s0, sp, 80
; CHECK-NEXT:    .cfi_def_cfa s0, 0
; CHECK-NEXT:    csrr a3, vlenb
; CHECK-NEXT:    slli a3, a3, 4
; CHECK-NEXT:    sub sp, sp, a3
; CHECK-NEXT:    andi sp, sp, -64
; CHECK-NEXT:    addi a3, sp, 64
; CHECK-NEXT:    add a4, a0, a3
; CHECK-NEXT:    addi a4, a4, -1
; CHECK-NEXT:    li a5, -1
; CHECK-NEXT:    vsetvli zero, a2, e8, m8, ta, ma
; CHECK-NEXT:    vsse8.v v8, (a4), a5
; CHECK-NEXT:    sub a4, a4, a2
; CHECK-NEXT:    sub a6, a0, a1
; CHECK-NEXT:    sltu a0, a0, a6
; CHECK-NEXT:    addi a0, a0, -1
; CHECK-NEXT:    and a0, a0, a6
; CHECK-NEXT:    vsetvli zero, a0, e8, m8, ta, ma
; CHECK-NEXT:    vsse8.v v16, (a4), a5
; CHECK-NEXT:    add a1, a3, a1
; CHECK-NEXT:    vle8.v v16, (a1)
; CHECK-NEXT:    vsetvli zero, a2, e8, m8, ta, ma
; CHECK-NEXT:    vle8.v v8, (a3)
; CHECK-NEXT:    addi sp, s0, -80
; CHECK-NEXT:    ld ra, 72(sp) # 8-byte Folded Reload
; CHECK-NEXT:    ld s0, 64(sp) # 8-byte Folded Reload
; CHECK-NEXT:    addi sp, sp, 80
; CHECK-NEXT:    ret
  %head = insertelement <vscale x 128 x i1> undef, i1 1, i32 0
  %allones = shufflevector <vscale x 128 x i1> %head, <vscale x 128 x i1> undef, <vscale x 128 x i32> zeroinitializer

  %dst = call <vscale x 128 x i8> @llvm.experimental.vp.reverse.nxv128i8(<vscale x 128 x i8> %src, <vscale x 128 x i1> %allones, i32 %evl)
  ret <vscale x 128 x i8> %dst
}

; LMUL = 1
declare <vscale x 1 x i64> @llvm.experimental.vp.reverse.nxv1i64(<vscale x 1 x i64>,<vscale x 1 x i1>,i32)
declare <vscale x 2 x i32> @llvm.experimental.vp.reverse.nxv2i32(<vscale x 2 x i32>,<vscale x 2 x i1>,i32)
declare <vscale x 4 x i16> @llvm.experimental.vp.reverse.nxv4i16(<vscale x 4 x i16>,<vscale x 4 x i1>,i32)
declare <vscale x 8 x i8> @llvm.experimental.vp.reverse.nxv8i8(<vscale x 8 x i8>,<vscale x 8 x i1>,i32)

; LMUL = 2
declare <vscale x 2 x i64> @llvm.experimental.vp.reverse.nxv2i64(<vscale x 2 x i64>,<vscale x 2 x i1>,i32)
declare <vscale x 4 x i32> @llvm.experimental.vp.reverse.nxv4i32(<vscale x 4 x i32>,<vscale x 4 x i1>,i32)
declare <vscale x 8 x i16> @llvm.experimental.vp.reverse.nxv8i16(<vscale x 8 x i16>,<vscale x 8 x i1>,i32)
declare <vscale x 16 x i8> @llvm.experimental.vp.reverse.nxv16i8(<vscale x 16 x i8>,<vscale x 16 x i1>,i32)

; LMUL = 4
declare <vscale x 4 x i64> @llvm.experimental.vp.reverse.nxv4i64(<vscale x 4 x i64>,<vscale x 4 x i1>,i32)
declare <vscale x 8 x i32> @llvm.experimental.vp.reverse.nxv8i32(<vscale x 8 x i32>,<vscale x 8 x i1>,i32)
declare <vscale x 16 x i16> @llvm.experimental.vp.reverse.nxv16i16(<vscale x 16 x i16>,<vscale x 16 x i1>,i32)
declare <vscale x 32 x i8> @llvm.experimental.vp.reverse.nxv32i8(<vscale x 32 x i8>,<vscale x 32 x i1>,i32)

; LMUL = 8
declare <vscale x 8 x i64> @llvm.experimental.vp.reverse.nxv8i64(<vscale x 8 x i64>,<vscale x 8 x i1>,i32)
declare <vscale x 16 x i32> @llvm.experimental.vp.reverse.nxv16i32(<vscale x 16 x i32>,<vscale x 16 x i1>,i32)
declare <vscale x 32 x i16> @llvm.experimental.vp.reverse.nxv32i16(<vscale x 32 x i16>,<vscale x 32 x i1>,i32)
declare <vscale x 64 x i8> @llvm.experimental.vp.reverse.nxv64i8(<vscale x 64 x i8>,<vscale x 64 x i1>,i32)

declare <vscale x 128 x i8> @llvm.experimental.vp.reverse.nxv128i8(<vscale x 128 x i8>,<vscale x 128 x i1>,i32)