; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=thumbv8.1m.main-arm-none-eabi -mattr=+mve,+fullfp16 -verify-machineinstrs %s -o - | FileCheck %s --check-prefix=CHECK --check-prefix=CHECK-MVE
; RUN: llc -mtriple=thumbv8.1m.main-arm-none-eabi -mattr=+mve.fp -verify-machineinstrs %s -o - | FileCheck %s --check-prefix=CHECK --check-prefix=CHECK-MVEFP

define arm_aapcs_vfpcc <16 x i8> @add_int8_t(<16 x i8> %src1, <16 x i8> %src2) {
; CHECK-LABEL: add_int8_t:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    vadd.i8 q0, q0, q1
; CHECK-NEXT:    bx lr
entry:
  %0 = add <16 x i8> %src1, %src2
  ret <16 x i8> %0
}

define arm_aapcs_vfpcc <8 x i16> @add_int16_t(<8 x i16> %src1, <8 x i16> %src2) {
; CHECK-LABEL: add_int16_t:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    vadd.i16 q0, q0, q1
; CHECK-NEXT:    bx lr
entry:
  %0 = add <8 x i16> %src1, %src2
  ret <8 x i16> %0
}

define arm_aapcs_vfpcc <4 x i32> @add_int32_t(<4 x i32> %src1, <4 x i32> %src2) {
; CHECK-LABEL: add_int32_t:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    vadd.i32 q0, q0, q1
; CHECK-NEXT:    bx lr
entry:
  %0 = add nsw <4 x i32> %src1, %src2
  ret <4 x i32> %0
}

define arm_aapcs_vfpcc <4 x float> @add_float32_t(<4 x float> %src1, <4 x float> %src2) {
; CHECK-MVE-LABEL: add_float32_t:
; CHECK-MVE:       @ %bb.0: @ %entry
; CHECK-MVE-NEXT:    vadd.f32 s8, s4, s0
; CHECK-MVE-NEXT:    movs r0, #0
; CHECK-MVE-NEXT:    vadd.f32 s10, s5, s1
; CHECK-MVE-NEXT:    vadd.f32 s12, s6, s2
; CHECK-MVE-NEXT:    vadd.f32 s4, s7, s3
; CHECK-MVE-NEXT:    vdup.32 q0, r0
; CHECK-MVE-NEXT:    vmov.f32 s0, s8
; CHECK-MVE-NEXT:    vmov.f32 s1, s10
; CHECK-MVE-NEXT:    vmov.f32 s2, s12
; CHECK-MVE-NEXT:    vmov.f32 s3, s4
; CHECK-MVE-NEXT:    bx lr
;
; CHECK-MVEFP-LABEL: add_float32_t:
; CHECK-MVEFP:       @ %bb.0: @ %entry
; CHECK-MVEFP-NEXT:    vadd.f32 q0, q1, q0
; CHECK-MVEFP-NEXT:    bx lr
entry:
  %0 = fadd nnan ninf nsz <4 x float> %src2, %src1
  ret <4 x float> %0
}

define arm_aapcs_vfpcc <8 x half> @add_float16_t(<8 x half> %src1, <8 x half> %src2) {
; CHECK-MVE-LABEL: add_float16_t:
; CHECK-MVE:       @ %bb.0: @ %entry
; CHECK-MVE-NEXT:    vmov.u16 r0, q0[0]
; CHECK-MVE-NEXT:    vmov.u16 r1, q1[0]
; CHECK-MVE-NEXT:    vmov s10, r1
; CHECK-MVE-NEXT:    vmov.u16 r1, q0[1]
; CHECK-MVE-NEXT:    vmov s8, r0
; CHECK-MVE-NEXT:    movs r2, #0
; CHECK-MVE-NEXT:    vadd.f16 s8, s10, s8
; CHECK-MVE-NEXT:    vmov r0, s8
; CHECK-MVE-NEXT:    vmov s8, r1
; CHECK-MVE-NEXT:    vmov.u16 r1, q1[1]
; CHECK-MVE-NEXT:    vmov s10, r1
; CHECK-MVE-NEXT:    vadd.f16 s8, s10, s8
; CHECK-MVE-NEXT:    vmov r1, s8
; CHECK-MVE-NEXT:    vdup.16 q2, r2
; CHECK-MVE-NEXT:    vmov.16 q2[0], r0
; CHECK-MVE-NEXT:    vmov.u16 r0, q0[2]
; CHECK-MVE-NEXT:    vmov s12, r0
; CHECK-MVE-NEXT:    vmov.u16 r0, q1[2]
; CHECK-MVE-NEXT:    vmov s14, r0
; CHECK-MVE-NEXT:    vmov.16 q2[1], r1
; CHECK-MVE-NEXT:    vadd.f16 s12, s14, s12
; CHECK-MVE-NEXT:    vmov r0, s12
; CHECK-MVE-NEXT:    vmov.16 q2[2], r0
; CHECK-MVE-NEXT:    vmov.u16 r0, q0[3]
; CHECK-MVE-NEXT:    vmov s12, r0
; CHECK-MVE-NEXT:    vmov.u16 r0, q1[3]
; CHECK-MVE-NEXT:    vmov s14, r0
; CHECK-MVE-NEXT:    vadd.f16 s12, s14, s12
; CHECK-MVE-NEXT:    vmov r0, s12
; CHECK-MVE-NEXT:    vmov.16 q2[3], r0
; CHECK-MVE-NEXT:    vmov.u16 r0, q0[4]
; CHECK-MVE-NEXT:    vmov s12, r0
; CHECK-MVE-NEXT:    vmov.u16 r0, q1[4]
; CHECK-MVE-NEXT:    vmov s14, r0
; CHECK-MVE-NEXT:    vadd.f16 s12, s14, s12
; CHECK-MVE-NEXT:    vmov r0, s12
; CHECK-MVE-NEXT:    vmov.16 q2[4], r0
; CHECK-MVE-NEXT:    vmov.u16 r0, q0[5]
; CHECK-MVE-NEXT:    vmov s12, r0
; CHECK-MVE-NEXT:    vmov.u16 r0, q1[5]
; CHECK-MVE-NEXT:    vmov s14, r0
; CHECK-MVE-NEXT:    vadd.f16 s12, s14, s12
; CHECK-MVE-NEXT:    vmov r0, s12
; CHECK-MVE-NEXT:    vmov.16 q2[5], r0
; CHECK-MVE-NEXT:    vmov.u16 r0, q0[6]
; CHECK-MVE-NEXT:    vmov s12, r0
; CHECK-MVE-NEXT:    vmov.u16 r0, q1[6]
; CHECK-MVE-NEXT:    vmov s14, r0
; CHECK-MVE-NEXT:    vadd.f16 s12, s14, s12
; CHECK-MVE-NEXT:    vmov r0, s12
; CHECK-MVE-NEXT:    vmov.16 q2[6], r0
; CHECK-MVE-NEXT:    vmov.u16 r0, q0[7]
; CHECK-MVE-NEXT:    vmov s0, r0
; CHECK-MVE-NEXT:    vmov.u16 r0, q1[7]
; CHECK-MVE-NEXT:    vmov s2, r0
; CHECK-MVE-NEXT:    vadd.f16 s0, s2, s0
; CHECK-MVE-NEXT:    vmov r0, s0
; CHECK-MVE-NEXT:    vmov.16 q2[7], r0
; CHECK-MVE-NEXT:    vmov q0, q2
; CHECK-MVE-NEXT:    bx lr
;
; CHECK-MVEFP-LABEL: add_float16_t:
; CHECK-MVEFP:       @ %bb.0: @ %entry
; CHECK-MVEFP-NEXT:    vadd.f16 q0, q1, q0
; CHECK-MVEFP-NEXT:    bx lr
entry:
  %0 = fadd nnan ninf nsz <8 x half> %src2, %src1
  ret <8 x half> %0
}


define arm_aapcs_vfpcc <16 x i8> @sub_int8_t(<16 x i8> %src1, <16 x i8> %src2) {
; CHECK-LABEL: sub_int8_t:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    vsub.i8 q0, q1, q0
; CHECK-NEXT:    bx lr
entry:
  %0 = sub <16 x i8> %src2, %src1
  ret <16 x i8> %0
}

define arm_aapcs_vfpcc <8 x i16> @sub_int16_t(<8 x i16> %src1, <8 x i16> %src2) {
; CHECK-LABEL: sub_int16_t:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    vsub.i16 q0, q1, q0
; CHECK-NEXT:    bx lr
entry:
  %0 = sub <8 x i16> %src2, %src1
  ret <8 x i16> %0
}

define arm_aapcs_vfpcc <4 x i32> @sub_int32_t(<4 x i32> %src1, <4 x i32> %src2) {
; CHECK-LABEL: sub_int32_t:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    vsub.i32 q0, q1, q0
; CHECK-NEXT:    bx lr
entry:
  %0 = sub nsw <4 x i32> %src2, %src1
  ret <4 x i32> %0
}

define arm_aapcs_vfpcc <4 x float> @sub_float32_t(<4 x float> %src1, <4 x float> %src2) {
; CHECK-MVE-LABEL: sub_float32_t:
; CHECK-MVE:       @ %bb.0: @ %entry
; CHECK-MVE-NEXT:    vsub.f32 s8, s4, s0
; CHECK-MVE-NEXT:    movs r0, #0
; CHECK-MVE-NEXT:    vsub.f32 s10, s5, s1
; CHECK-MVE-NEXT:    vsub.f32 s12, s6, s2
; CHECK-MVE-NEXT:    vsub.f32 s4, s7, s3
; CHECK-MVE-NEXT:    vdup.32 q0, r0
; CHECK-MVE-NEXT:    vmov.f32 s0, s8
; CHECK-MVE-NEXT:    vmov.f32 s1, s10
; CHECK-MVE-NEXT:    vmov.f32 s2, s12
; CHECK-MVE-NEXT:    vmov.f32 s3, s4
; CHECK-MVE-NEXT:    bx lr
;
; CHECK-MVEFP-LABEL: sub_float32_t:
; CHECK-MVEFP:       @ %bb.0: @ %entry
; CHECK-MVEFP-NEXT:    vsub.f32 q0, q1, q0
; CHECK-MVEFP-NEXT:    bx lr
entry:
  %0 = fsub nnan ninf nsz <4 x float> %src2, %src1
  ret <4 x float> %0
}

define arm_aapcs_vfpcc <8 x half> @sub_float16_t(<8 x half> %src1, <8 x half> %src2) {
; CHECK-MVE-LABEL: sub_float16_t:
; CHECK-MVE:       @ %bb.0: @ %entry
; CHECK-MVE-NEXT:    vmov.u16 r0, q0[0]
; CHECK-MVE-NEXT:    vmov.u16 r1, q1[0]
; CHECK-MVE-NEXT:    vmov s10, r1
; CHECK-MVE-NEXT:    vmov.u16 r1, q0[1]
; CHECK-MVE-NEXT:    vmov s8, r0
; CHECK-MVE-NEXT:    movs r2, #0
; CHECK-MVE-NEXT:    vsub.f16 s8, s10, s8
; CHECK-MVE-NEXT:    vmov r0, s8
; CHECK-MVE-NEXT:    vmov s8, r1
; CHECK-MVE-NEXT:    vmov.u16 r1, q1[1]
; CHECK-MVE-NEXT:    vmov s10, r1
; CHECK-MVE-NEXT:    vsub.f16 s8, s10, s8
; CHECK-MVE-NEXT:    vmov r1, s8
; CHECK-MVE-NEXT:    vdup.16 q2, r2
; CHECK-MVE-NEXT:    vmov.16 q2[0], r0
; CHECK-MVE-NEXT:    vmov.u16 r0, q0[2]
; CHECK-MVE-NEXT:    vmov s12, r0
; CHECK-MVE-NEXT:    vmov.u16 r0, q1[2]
; CHECK-MVE-NEXT:    vmov s14, r0
; CHECK-MVE-NEXT:    vmov.16 q2[1], r1
; CHECK-MVE-NEXT:    vsub.f16 s12, s14, s12
; CHECK-MVE-NEXT:    vmov r0, s12
; CHECK-MVE-NEXT:    vmov.16 q2[2], r0
; CHECK-MVE-NEXT:    vmov.u16 r0, q0[3]
; CHECK-MVE-NEXT:    vmov s12, r0
; CHECK-MVE-NEXT:    vmov.u16 r0, q1[3]
; CHECK-MVE-NEXT:    vmov s14, r0
; CHECK-MVE-NEXT:    vsub.f16 s12, s14, s12
; CHECK-MVE-NEXT:    vmov r0, s12
; CHECK-MVE-NEXT:    vmov.16 q2[3], r0
; CHECK-MVE-NEXT:    vmov.u16 r0, q0[4]
; CHECK-MVE-NEXT:    vmov s12, r0
; CHECK-MVE-NEXT:    vmov.u16 r0, q1[4]
; CHECK-MVE-NEXT:    vmov s14, r0
; CHECK-MVE-NEXT:    vsub.f16 s12, s14, s12
; CHECK-MVE-NEXT:    vmov r0, s12
; CHECK-MVE-NEXT:    vmov.16 q2[4], r0
; CHECK-MVE-NEXT:    vmov.u16 r0, q0[5]
; CHECK-MVE-NEXT:    vmov s12, r0
; CHECK-MVE-NEXT:    vmov.u16 r0, q1[5]
; CHECK-MVE-NEXT:    vmov s14, r0
; CHECK-MVE-NEXT:    vsub.f16 s12, s14, s12
; CHECK-MVE-NEXT:    vmov r0, s12
; CHECK-MVE-NEXT:    vmov.16 q2[5], r0
; CHECK-MVE-NEXT:    vmov.u16 r0, q0[6]
; CHECK-MVE-NEXT:    vmov s12, r0
; CHECK-MVE-NEXT:    vmov.u16 r0, q1[6]
; CHECK-MVE-NEXT:    vmov s14, r0
; CHECK-MVE-NEXT:    vsub.f16 s12, s14, s12
; CHECK-MVE-NEXT:    vmov r0, s12
; CHECK-MVE-NEXT:    vmov.16 q2[6], r0
; CHECK-MVE-NEXT:    vmov.u16 r0, q0[7]
; CHECK-MVE-NEXT:    vmov s0, r0
; CHECK-MVE-NEXT:    vmov.u16 r0, q1[7]
; CHECK-MVE-NEXT:    vmov s2, r0
; CHECK-MVE-NEXT:    vsub.f16 s0, s2, s0
; CHECK-MVE-NEXT:    vmov r0, s0
; CHECK-MVE-NEXT:    vmov.16 q2[7], r0
; CHECK-MVE-NEXT:    vmov q0, q2
; CHECK-MVE-NEXT:    bx lr
;
; CHECK-MVEFP-LABEL: sub_float16_t:
; CHECK-MVEFP:       @ %bb.0: @ %entry
; CHECK-MVEFP-NEXT:    vsub.f16 q0, q1, q0
; CHECK-MVEFP-NEXT:    bx lr
entry:
  %0 = fsub nnan ninf nsz <8 x half> %src2, %src1
  ret <8 x half> %0
}

define arm_aapcs_vfpcc <16 x i8> @mul_int8_t(<16 x i8> %src1, <16 x i8> %src2) {
; CHECK-LABEL: mul_int8_t:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    vmul.i8 q0, q0, q1
; CHECK-NEXT:    bx lr
entry:
  %0 = mul <16 x i8> %src1, %src2
  ret <16 x i8> %0
}

define arm_aapcs_vfpcc <8 x i16> @mul_int16_t(<8 x i16> %src1, <8 x i16> %src2) {
; CHECK-LABEL: mul_int16_t:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    vmul.i16 q0, q0, q1
; CHECK-NEXT:    bx lr
entry:
  %0 = mul <8 x i16> %src1, %src2
  ret <8 x i16> %0
}

define arm_aapcs_vfpcc <4 x i32> @mul_int32_t(<4 x i32> %src1, <4 x i32> %src2) {
; CHECK-LABEL: mul_int32_t:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    vmul.i32 q0, q0, q1
; CHECK-NEXT:    bx lr
entry:
  %0 = mul nsw <4 x i32> %src1, %src2
  ret <4 x i32> %0
}

define arm_aapcs_vfpcc <8 x half> @mul_float16_t(<8 x half> %src1, <8 x half> %src2) {
; CHECK-MVE-LABEL: mul_float16_t:
; CHECK-MVE:       @ %bb.0: @ %entry
; CHECK-MVE-NEXT:    vmov.u16 r0, q0[0]
; CHECK-MVE-NEXT:    vmov.u16 r1, q1[0]
; CHECK-MVE-NEXT:    vmov s10, r1
; CHECK-MVE-NEXT:    vmov.u16 r1, q0[1]
; CHECK-MVE-NEXT:    vmov s8, r0
; CHECK-MVE-NEXT:    movs r2, #0
; CHECK-MVE-NEXT:    vmul.f16 s8, s10, s8
; CHECK-MVE-NEXT:    vmov r0, s8
; CHECK-MVE-NEXT:    vmov s8, r1
; CHECK-MVE-NEXT:    vmov.u16 r1, q1[1]
; CHECK-MVE-NEXT:    vmov s10, r1
; CHECK-MVE-NEXT:    vmul.f16 s8, s10, s8
; CHECK-MVE-NEXT:    vmov r1, s8
; CHECK-MVE-NEXT:    vdup.16 q2, r2
; CHECK-MVE-NEXT:    vmov.16 q2[0], r0
; CHECK-MVE-NEXT:    vmov.u16 r0, q0[2]
; CHECK-MVE-NEXT:    vmov s12, r0
; CHECK-MVE-NEXT:    vmov.u16 r0, q1[2]
; CHECK-MVE-NEXT:    vmov s14, r0
; CHECK-MVE-NEXT:    vmov.16 q2[1], r1
; CHECK-MVE-NEXT:    vmul.f16 s12, s14, s12
; CHECK-MVE-NEXT:    vmov r0, s12
; CHECK-MVE-NEXT:    vmov.16 q2[2], r0
; CHECK-MVE-NEXT:    vmov.u16 r0, q0[3]
; CHECK-MVE-NEXT:    vmov s12, r0
; CHECK-MVE-NEXT:    vmov.u16 r0, q1[3]
; CHECK-MVE-NEXT:    vmov s14, r0
; CHECK-MVE-NEXT:    vmul.f16 s12, s14, s12
; CHECK-MVE-NEXT:    vmov r0, s12
; CHECK-MVE-NEXT:    vmov.16 q2[3], r0
; CHECK-MVE-NEXT:    vmov.u16 r0, q0[4]
; CHECK-MVE-NEXT:    vmov s12, r0
; CHECK-MVE-NEXT:    vmov.u16 r0, q1[4]
; CHECK-MVE-NEXT:    vmov s14, r0
; CHECK-MVE-NEXT:    vmul.f16 s12, s14, s12
; CHECK-MVE-NEXT:    vmov r0, s12
; CHECK-MVE-NEXT:    vmov.16 q2[4], r0
; CHECK-MVE-NEXT:    vmov.u16 r0, q0[5]
; CHECK-MVE-NEXT:    vmov s12, r0
; CHECK-MVE-NEXT:    vmov.u16 r0, q1[5]
; CHECK-MVE-NEXT:    vmov s14, r0
; CHECK-MVE-NEXT:    vmul.f16 s12, s14, s12
; CHECK-MVE-NEXT:    vmov r0, s12
; CHECK-MVE-NEXT:    vmov.16 q2[5], r0
; CHECK-MVE-NEXT:    vmov.u16 r0, q0[6]
; CHECK-MVE-NEXT:    vmov s12, r0
; CHECK-MVE-NEXT:    vmov.u16 r0, q1[6]
; CHECK-MVE-NEXT:    vmov s14, r0
; CHECK-MVE-NEXT:    vmul.f16 s12, s14, s12
; CHECK-MVE-NEXT:    vmov r0, s12
; CHECK-MVE-NEXT:    vmov.16 q2[6], r0
; CHECK-MVE-NEXT:    vmov.u16 r0, q0[7]
; CHECK-MVE-NEXT:    vmov s0, r0
; CHECK-MVE-NEXT:    vmov.u16 r0, q1[7]
; CHECK-MVE-NEXT:    vmov s2, r0
; CHECK-MVE-NEXT:    vmul.f16 s0, s2, s0
; CHECK-MVE-NEXT:    vmov r0, s0
; CHECK-MVE-NEXT:    vmov.16 q2[7], r0
; CHECK-MVE-NEXT:    vmov q0, q2
; CHECK-MVE-NEXT:    bx lr
;
; CHECK-MVEFP-LABEL: mul_float16_t:
; CHECK-MVEFP:       @ %bb.0: @ %entry
; CHECK-MVEFP-NEXT:    vmul.f16 q0, q1, q0
; CHECK-MVEFP-NEXT:    bx lr
entry:
  %0 = fmul nnan ninf nsz <8 x half> %src2, %src1
  ret <8 x half> %0
}

define arm_aapcs_vfpcc <4 x float> @mul_float32_t(<4 x float> %src1, <4 x float> %src2) {
; CHECK-MVE-LABEL: mul_float32_t:
; CHECK-MVE:       @ %bb.0: @ %entry
; CHECK-MVE-NEXT:    vmul.f32 s8, s4, s0
; CHECK-MVE-NEXT:    movs r0, #0
; CHECK-MVE-NEXT:    vmul.f32 s10, s5, s1
; CHECK-MVE-NEXT:    vmul.f32 s12, s6, s2
; CHECK-MVE-NEXT:    vmul.f32 s4, s7, s3
; CHECK-MVE-NEXT:    vdup.32 q0, r0
; CHECK-MVE-NEXT:    vmov.f32 s0, s8
; CHECK-MVE-NEXT:    vmov.f32 s1, s10
; CHECK-MVE-NEXT:    vmov.f32 s2, s12
; CHECK-MVE-NEXT:    vmov.f32 s3, s4
; CHECK-MVE-NEXT:    bx lr
;
; CHECK-MVEFP-LABEL: mul_float32_t:
; CHECK-MVEFP:       @ %bb.0: @ %entry
; CHECK-MVEFP-NEXT:    vmul.f32 q0, q1, q0
; CHECK-MVEFP-NEXT:    bx lr
entry:
  %0 = fmul nnan ninf nsz <4 x float> %src2, %src1
  ret <4 x float> %0
}