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

define <2 x double> @test_vp_reverse_v2f64_masked(<2 x double> %src, <2 x i1> %mask, i32 zeroext %evl) {
; CHECK-LABEL: test_vp_reverse_v2f64_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 double> @llvm.experimental.vp.reverse.v2f64(<2 x double> %src, <2 x i1> %mask, i32 %evl)
  ret <2 x double> %dst
}

define <2 x double> @test_vp_reverse_v2f64(<2 x double> %src, i32 zeroext %evl) {
; CHECK-LABEL: test_vp_reverse_v2f64:
; 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

  %dst = call <2 x double> @llvm.experimental.vp.reverse.v2f64(<2 x double> %src, <2 x i1> splat (i1 1), i32 %evl)
  ret <2 x double> %dst
}

define <4 x float> @test_vp_reverse_v4f32_masked(<4 x float> %src, <4 x i1> %mask, i32 zeroext %evl) {
; CHECK-LABEL: test_vp_reverse_v4f32_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 float> @llvm.experimental.vp.reverse.v4f32(<4 x float> %src, <4 x i1> %mask, i32 %evl)
  ret <4 x float> %dst
}

define <4 x float> @test_vp_reverse_v4f32(<4 x float> %src, i32 zeroext %evl) {
; CHECK-LABEL: test_vp_reverse_v4f32:
; 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

  %dst = call <4 x float> @llvm.experimental.vp.reverse.v4f32(<4 x float> %src, <4 x i1> splat (i1 1), i32 %evl)
  ret <4 x float> %dst
}

define <4 x half> @test_vp_reverse_v4f16_masked(<4 x half> %src, <4 x i1> %mask, i32 zeroext %evl) {
; CHECK-LABEL: test_vp_reverse_v4f16_masked:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a0, e16, mf2, 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:    vmv1r.v v8, v9
; CHECK-NEXT:    ret
  %dst = call <4 x half> @llvm.experimental.vp.reverse.v4f16(<4 x half> %src, <4 x i1> %mask, i32 %evl)
  ret <4 x half> %dst
}

define <4 x half> @test_vp_reverse_v4f16(<4 x half> %src, i32 zeroext %evl) {
; CHECK-LABEL: test_vp_reverse_v4f16:
; CHECK:       # %bb.0:
; CHECK-NEXT:    addi a1, a0, -1
; CHECK-NEXT:    vsetvli zero, a0, e16, mf2, ta, ma
; CHECK-NEXT:    vid.v v9
; CHECK-NEXT:    vrsub.vx v10, v9, a1
; CHECK-NEXT:    vrgather.vv v9, v8, v10
; CHECK-NEXT:    vmv1r.v v8, v9
; CHECK-NEXT:    ret

  %dst = call <4 x half> @llvm.experimental.vp.reverse.v4f16(<4 x half> %src, <4 x i1> splat (i1 1), i32 %evl)
  ret <4 x half> %dst
}

define <4 x bfloat> @test_vp_reverse_v4bf16_masked(<4 x bfloat> %src, <4 x i1> %mask, i32 zeroext %evl) {
; CHECK-LABEL: test_vp_reverse_v4bf16_masked:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a0, e16, mf2, 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:    vmv1r.v v8, v9
; CHECK-NEXT:    ret
  %dst = call <4 x bfloat> @llvm.experimental.vp.reverse.v4bf16(<4 x bfloat> %src, <4 x i1> %mask, i32 %evl)
  ret <4 x bfloat> %dst
}

define <4 x bfloat> @test_vp_reverse_v4bf16(<4 x bfloat> %src, i32 zeroext %evl) {
; CHECK-LABEL: test_vp_reverse_v4bf16:
; CHECK:       # %bb.0:
; CHECK-NEXT:    addi a1, a0, -1
; CHECK-NEXT:    vsetvli zero, a0, e16, mf2, ta, ma
; CHECK-NEXT:    vid.v v9
; CHECK-NEXT:    vrsub.vx v10, v9, a1
; CHECK-NEXT:    vrgather.vv v9, v8, v10
; CHECK-NEXT:    vmv1r.v v8, v9
; CHECK-NEXT:    ret

  %dst = call <4 x bfloat> @llvm.experimental.vp.reverse.v4bf16(<4 x bfloat> %src, <4 x i1> splat (i1 1), i32 %evl)
  ret <4 x bfloat> %dst
}