; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=thumbv8.1m.main -mattr=+mve.fp -verify-machineinstrs -o - %s | FileCheck %s

define arm_aapcs_vfpcc <8 x half> @test_vcvtq_m_f16_s16(<8 x half> %inactive, <8 x i16> %a, i16 zeroext %p) {
; CHECK-LABEL: test_vcvtq_m_f16_s16:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    vmsr p0, r0
; CHECK-NEXT:    vpst
; CHECK-NEXT:    vcvtt.f16.s16 q0, q1
; CHECK-NEXT:    bx lr
entry:
  %0 = zext i16 %p to i32
  %1 = tail call <8 x i1> @llvm.arm.mve.pred.i2v.v8i1(i32 %0)
  %2 = tail call <8 x half> @llvm.arm.mve.vcvt.fp.int.predicated.v8f16.v8i16.v8i1(<8 x i16> %a, i32 0, <8 x i1> %1, <8 x half> %inactive)
  ret <8 x half> %2
}

define arm_aapcs_vfpcc <8 x half> @test_vcvtq_m_f16_u16(<8 x half> %inactive, <8 x i16> %a, i16 zeroext %p) {
; CHECK-LABEL: test_vcvtq_m_f16_u16:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    vmsr p0, r0
; CHECK-NEXT:    vpst
; CHECK-NEXT:    vcvtt.f16.u16 q0, q1
; CHECK-NEXT:    bx lr
entry:
  %0 = zext i16 %p to i32
  %1 = tail call <8 x i1> @llvm.arm.mve.pred.i2v.v8i1(i32 %0)
  %2 = tail call <8 x half> @llvm.arm.mve.vcvt.fp.int.predicated.v8f16.v8i16.v8i1(<8 x i16> %a, i32 1, <8 x i1> %1, <8 x half> %inactive)
  ret <8 x half> %2
}

define arm_aapcs_vfpcc <4 x float> @test_vcvtq_m_f32_s32(<4 x float> %inactive, <4 x i32> %a, i16 zeroext %p) {
; CHECK-LABEL: test_vcvtq_m_f32_s32:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    vmsr p0, r0
; CHECK-NEXT:    vpst
; CHECK-NEXT:    vcvtt.f32.s32 q0, q1
; CHECK-NEXT:    bx lr
entry:
  %0 = zext i16 %p to i32
  %1 = tail call <4 x i1> @llvm.arm.mve.pred.i2v.v4i1(i32 %0)
  %2 = tail call <4 x float> @llvm.arm.mve.vcvt.fp.int.predicated.v4f32.v4i32.v4i1(<4 x i32> %a, i32 0, <4 x i1> %1, <4 x float> %inactive)
  ret <4 x float> %2
}

define arm_aapcs_vfpcc <4 x float> @test_vcvtq_m_f32_u32(<4 x float> %inactive, <4 x i32> %a, i16 zeroext %p) {
; CHECK-LABEL: test_vcvtq_m_f32_u32:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    vmsr p0, r0
; CHECK-NEXT:    vpst
; CHECK-NEXT:    vcvtt.f32.u32 q0, q1
; CHECK-NEXT:    bx lr
entry:
  %0 = zext i16 %p to i32
  %1 = tail call <4 x i1> @llvm.arm.mve.pred.i2v.v4i1(i32 %0)
  %2 = tail call <4 x float> @llvm.arm.mve.vcvt.fp.int.predicated.v4f32.v4i32.v4i1(<4 x i32> %a, i32 1, <4 x i1> %1, <4 x float> %inactive)
  ret <4 x float> %2
}

define arm_aapcs_vfpcc <8 x i16> @test_vcvtq_m_s16_f16(<8 x i16> %inactive, <8 x half> %a, i16 zeroext %p) {
; CHECK-LABEL: test_vcvtq_m_s16_f16:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    vmsr p0, r0
; CHECK-NEXT:    vpst
; CHECK-NEXT:    vcvtt.s16.f16 q0, q1
; CHECK-NEXT:    bx lr
entry:
  %0 = zext i16 %p to i32
  %1 = tail call <8 x i1> @llvm.arm.mve.pred.i2v.v8i1(i32 %0)
  %2 = tail call <8 x i16> @llvm.arm.mve.vcvt.fp.int.predicated.v8i16.v8f16.v8i1(<8 x half> %a, i32 0, <8 x i1> %1, <8 x i16> %inactive)
  ret <8 x i16> %2
}

define arm_aapcs_vfpcc <4 x i32> @test_vcvtq_m_s32_f32(<4 x i32> %inactive, <4 x float> %a, i16 zeroext %p) {
; CHECK-LABEL: test_vcvtq_m_s32_f32:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    vmsr p0, r0
; CHECK-NEXT:    vpst
; CHECK-NEXT:    vcvtt.s32.f32 q0, q1
; CHECK-NEXT:    bx lr
entry:
  %0 = zext i16 %p to i32
  %1 = tail call <4 x i1> @llvm.arm.mve.pred.i2v.v4i1(i32 %0)
  %2 = tail call <4 x i32> @llvm.arm.mve.vcvt.fp.int.predicated.v4i32.v4f32.v4i1(<4 x float> %a, i32 0, <4 x i1> %1, <4 x i32> %inactive)
  ret <4 x i32> %2
}

define arm_aapcs_vfpcc <8 x i16> @test_vcvtq_m_u16_f16(<8 x i16> %inactive, <8 x half> %a, i16 zeroext %p) {
; CHECK-LABEL: test_vcvtq_m_u16_f16:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    vmsr p0, r0
; CHECK-NEXT:    vpst
; CHECK-NEXT:    vcvtt.u16.f16 q0, q1
; CHECK-NEXT:    bx lr
entry:
  %0 = zext i16 %p to i32
  %1 = tail call <8 x i1> @llvm.arm.mve.pred.i2v.v8i1(i32 %0)
  %2 = tail call <8 x i16> @llvm.arm.mve.vcvt.fp.int.predicated.v8i16.v8f16.v8i1(<8 x half> %a, i32 1, <8 x i1> %1, <8 x i16> %inactive)
  ret <8 x i16> %2
}

define arm_aapcs_vfpcc <4 x i32> @test_vcvtq_m_u32_f32(<4 x i32> %inactive, <4 x float> %a, i16 zeroext %p) {
; CHECK-LABEL: test_vcvtq_m_u32_f32:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    vmsr p0, r0
; CHECK-NEXT:    vpst
; CHECK-NEXT:    vcvtt.u32.f32 q0, q1
; CHECK-NEXT:    bx lr
entry:
  %0 = zext i16 %p to i32
  %1 = tail call <4 x i1> @llvm.arm.mve.pred.i2v.v4i1(i32 %0)
  %2 = tail call <4 x i32> @llvm.arm.mve.vcvt.fp.int.predicated.v4i32.v4f32.v4i1(<4 x float> %a, i32 1, <4 x i1> %1, <4 x i32> %inactive)
  ret <4 x i32> %2
}

declare <8 x i1> @llvm.arm.mve.pred.i2v.v8i1(i32)
declare <4 x i1> @llvm.arm.mve.pred.i2v.v4i1(i32)

declare <8 x half> @llvm.arm.mve.vcvt.fp.int.predicated.v8f16.v8i16.v8i1(<8 x i16>, i32, <8 x i1>, <8 x half>)
declare <4 x float> @llvm.arm.mve.vcvt.fp.int.predicated.v4f32.v4i32.v4i1(<4 x i32>, i32, <4 x i1>, <4 x float>)
declare <8 x i16> @llvm.arm.mve.vcvt.fp.int.predicated.v8i16.v8f16.v8i1(<8 x half>, i32, <8 x i1>, <8 x i16>)
declare <4 x i32> @llvm.arm.mve.vcvt.fp.int.predicated.v4i32.v4f32.v4i1(<4 x float>, i32, <4 x i1>, <4 x i32>)