; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=riscv64 -mattr=+m,+v -verify-machineinstrs -riscv-v-vector-bits-min=128 \
; RUN:   < %s | FileCheck %s

define <2 x i64> @test_vp_reverse_v2i64_masked(<2 x i64> %src, <2 x i1> %mask, i32 zeroext %evl) {
; CHECK-LABEL: test_vp_reverse_v2i64_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 <2 x i64> @llvm.experimental.vp.reverse.v2i64(<2 x i64> %src, <2 x i1> %mask, i32 %evl)
  ret <2 x i64> %dst
}

define <2 x i64> @test_vp_reverse_v2i64(<2 x i64> %src, i32 zeroext %evl) {
; CHECK-LABEL: test_vp_reverse_v2i64:
; 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 <2 x i1> undef, i1 1, i32 0
  %allones = shufflevector <2 x i1> %head, <2 x i1> undef, <2 x i32> zeroinitializer

  %dst = call <2 x i64> @llvm.experimental.vp.reverse.v2i64(<2 x i64> %src, <2 x i1> %allones, i32 %evl)
  ret <2 x i64> %dst
}

define <4 x i32> @test_vp_reverse_v4i32_masked(<4 x i32> %src, <4 x i1> %mask, i32 zeroext %evl) {
; CHECK-LABEL: test_vp_reverse_v4i32_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 <4 x i32> @llvm.experimental.vp.reverse.v4i32(<4 x i32> %src, <4 x i1> %mask, i32 %evl)
  ret <4 x i32> %dst
}

define <4 x i32> @test_vp_reverse_v4i32(<4 x i32> %src, i32 zeroext %evl) {
; CHECK-LABEL: test_vp_reverse_v4i32:
; 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 <4 x i1> undef, i1 1, i32 0
  %allones = shufflevector <4 x i1> %head, <4 x i1> undef, <4 x i32> zeroinitializer

  %dst = call <4 x i32> @llvm.experimental.vp.reverse.v4i32(<4 x i32> %src, <4 x i1> %allones, i32 %evl)
  ret <4 x i32> %dst
}

define <8 x i16> @test_vp_reverse_v8i16_masked(<8 x i16> %src, <8 x i1> %mask, i32 zeroext %evl) {
; CHECK-LABEL: test_vp_reverse_v8i16_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 <8 x i16> @llvm.experimental.vp.reverse.v8i16(<8 x i16> %src, <8 x i1> %mask, i32 %evl)
  ret <8 x i16> %dst
}

define <8 x i16> @test_vp_reverse_v8i16(<8 x i16> %src, i32 zeroext %evl) {
; CHECK-LABEL: test_vp_reverse_v8i16:
; 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 <8 x i1> undef, i1 1, i32 0
  %allones = shufflevector <8 x i1> %head, <8 x i1> undef, <8 x i32> zeroinitializer

  %dst = call <8 x i16> @llvm.experimental.vp.reverse.v8i16(<8 x i16> %src, <8 x i1> %allones, i32 %evl)
  ret <8 x i16> %dst
}

define <16 x i8> @test_vp_reverse_v16i8_masked(<16 x i8> %src, <16 x i1> %mask, i32 zeroext %evl) {
; CHECK-LABEL: test_vp_reverse_v16i8_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 <16 x i8> @llvm.experimental.vp.reverse.v16i8(<16 x i8> %src, <16 x i1> %mask, i32 %evl)
  ret <16 x i8> %dst
}

define <16 x i8> @test_vp_reverse_v16i8(<16 x i8> %src, i32 zeroext %evl) {
; CHECK-LABEL: test_vp_reverse_v16i8:
; 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 <16 x i1> undef, i1 1, i32 0
  %allones = shufflevector <16 x i1> %head, <16 x i1> undef, <16 x i32> zeroinitializer

  %dst = call <16 x i8> @llvm.experimental.vp.reverse.v16i8(<16 x i8> %src, <16 x i1> %allones, i32 %evl)
  ret <16 x i8> %dst
}

declare <2 x i64> @llvm.experimental.vp.reverse.v2i64(<2 x i64>,<2 x i1>,i32)
declare <4 x i32> @llvm.experimental.vp.reverse.v4i32(<4 x i32>,<4 x i1>,i32)
declare <8 x i16> @llvm.experimental.vp.reverse.v8i16(<8 x i16>,<8 x i1>,i32)
declare <16 x i8> @llvm.experimental.vp.reverse.v16i8(<16 x i8>,<16 x i1>,i32)