; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=thumbv8.1m.main-arm-none-eabi -mattr=+mve,+fullfp16 -enable-arm-maskedldst -verify-machineinstrs %s -o - | FileCheck %s --check-prefix=CHECK --check-prefix=CHECK-LE
; RUN: llc -mtriple=thumbebv8.1m.main-arm-none-eabi -mattr=+mve,+fullfp16 -enable-arm-maskedldst -verify-machineinstrs %s -o - | FileCheck %s --check-prefix=CHECK --check-prefix=CHECK-BE

define arm_aapcs_vfpcc void @masked_v4i32(<4 x i32> *%dest, <4 x i32> %a) {
; CHECK-LE-LABEL: masked_v4i32:
; CHECK-LE:       @ %bb.0: @ %entry
; CHECK-LE-NEXT:    vpt.s32 gt, q0, zr
; CHECK-LE-NEXT:    vstrwt.32 q0, [r0]
; CHECK-LE-NEXT:    bx lr
;
; CHECK-BE-LABEL: masked_v4i32:
; CHECK-BE:       @ %bb.0: @ %entry
; CHECK-BE-NEXT:    vrev64.32 q1, q0
; CHECK-BE-NEXT:    vpt.s32 gt, q1, zr
; CHECK-BE-NEXT:    vstrwt.32 q1, [r0]
; CHECK-BE-NEXT:    bx lr
entry:
  %c = icmp sgt <4 x i32> %a, zeroinitializer
  call void @llvm.masked.store.v4i32.p0v4i32(<4 x i32> %a, <4 x i32>* %dest, i32 4, <4 x i1> %c)
  ret void
}

define arm_aapcs_vfpcc void @masked_v4i32_align1(<4 x i32> *%dest, <4 x i32> %a) {
; CHECK-LE-LABEL: masked_v4i32_align1:
; CHECK-LE:       @ %bb.0: @ %entry
; CHECK-LE-NEXT:    vpt.s32 gt, q0, zr
; CHECK-LE-NEXT:    vstrbt.8 q0, [r0]
; CHECK-LE-NEXT:    bx lr
;
; CHECK-BE-LABEL: masked_v4i32_align1:
; CHECK-BE:       @ %bb.0: @ %entry
; CHECK-BE-NEXT:    vrev64.32 q1, q0
; CHECK-BE-NEXT:    vrev32.8 q0, q1
; CHECK-BE-NEXT:    vpt.s32 gt, q1, zr
; CHECK-BE-NEXT:    vstrbt.8 q0, [r0]
; CHECK-BE-NEXT:    bx lr
entry:
  %c = icmp sgt <4 x i32> %a, zeroinitializer
  call void @llvm.masked.store.v4i32.p0v4i32(<4 x i32> %a, <4 x i32>* %dest, i32 1, <4 x i1> %c)
  ret void
}

define i8* @masked_v4i32_pre(i8* %y, i8* %x, <4 x i32> %a) {
; CHECK-LE-LABEL: masked_v4i32_pre:
; CHECK-LE:       @ %bb.0: @ %entry
; CHECK-LE-NEXT:    vldr d1, [sp]
; CHECK-LE-NEXT:    vldrw.u32 q1, [r1]
; CHECK-LE-NEXT:    vmov d0, r2, r3
; CHECK-LE-NEXT:    vpt.s32 gt, q0, zr
; CHECK-LE-NEXT:    vstrwt.32 q1, [r0, #4]
; CHECK-LE-NEXT:    adds r0, #4
; CHECK-LE-NEXT:    bx lr
;
; CHECK-BE-LABEL: masked_v4i32_pre:
; CHECK-BE:       @ %bb.0: @ %entry
; CHECK-BE-NEXT:    vldr d1, [sp]
; CHECK-BE-NEXT:    vldrw.u32 q1, [r1]
; CHECK-BE-NEXT:    vmov d0, r3, r2
; CHECK-BE-NEXT:    vrev64.32 q2, q0
; CHECK-BE-NEXT:    vpt.s32 gt, q2, zr
; CHECK-BE-NEXT:    vstrwt.32 q1, [r0, #4]
; CHECK-BE-NEXT:    adds r0, #4
; CHECK-BE-NEXT:    bx lr
entry:
  %z = getelementptr inbounds i8, i8* %y, i32 4
  %0 = bitcast i8* %x to <4 x i32>*
  %1 = load <4 x i32>, <4 x i32>* %0, align 4
  %2 = bitcast i8* %z to <4 x i32>*
  %c = icmp sgt <4 x i32> %a, zeroinitializer
  call void @llvm.masked.store.v4i32.p0v4i32(<4 x i32> %1, <4 x i32>* %2, i32 4, <4 x i1> %c)
  ret i8* %z
}

define i8* @masked_v4i32_post(i8* %y, i8* %x, <4 x i32> %a) {
; CHECK-LE-LABEL: masked_v4i32_post:
; CHECK-LE:       @ %bb.0: @ %entry
; CHECK-LE-NEXT:    vldr d1, [sp]
; CHECK-LE-NEXT:    vldrw.u32 q1, [r1]
; CHECK-LE-NEXT:    vmov d0, r2, r3
; CHECK-LE-NEXT:    vpt.s32 gt, q0, zr
; CHECK-LE-NEXT:    vstrwt.32 q1, [r0]
; CHECK-LE-NEXT:    adds r0, #4
; CHECK-LE-NEXT:    bx lr
;
; CHECK-BE-LABEL: masked_v4i32_post:
; CHECK-BE:       @ %bb.0: @ %entry
; CHECK-BE-NEXT:    vldr d1, [sp]
; CHECK-BE-NEXT:    vldrw.u32 q1, [r1]
; CHECK-BE-NEXT:    vmov d0, r3, r2
; CHECK-BE-NEXT:    vrev64.32 q2, q0
; CHECK-BE-NEXT:    vpt.s32 gt, q2, zr
; CHECK-BE-NEXT:    vstrwt.32 q1, [r0]
; CHECK-BE-NEXT:    adds r0, #4
; CHECK-BE-NEXT:    bx lr
entry:
  %z = getelementptr inbounds i8, i8* %y, i32 4
  %0 = bitcast i8* %x to <4 x i32>*
  %1 = load <4 x i32>, <4 x i32>* %0, align 4
  %2 = bitcast i8* %y to <4 x i32>*
  %c = icmp sgt <4 x i32> %a, zeroinitializer
  call void @llvm.masked.store.v4i32.p0v4i32(<4 x i32> %1, <4 x i32>* %2, i32 4, <4 x i1> %c)
  ret i8* %z
}


define arm_aapcs_vfpcc void @masked_v8i16(<8 x i16> *%dest, <8 x i16> %a) {
; CHECK-LE-LABEL: masked_v8i16:
; CHECK-LE:       @ %bb.0: @ %entry
; CHECK-LE-NEXT:    vpt.s16 gt, q0, zr
; CHECK-LE-NEXT:    vstrht.16 q0, [r0]
; CHECK-LE-NEXT:    bx lr
;
; CHECK-BE-LABEL: masked_v8i16:
; CHECK-BE:       @ %bb.0: @ %entry
; CHECK-BE-NEXT:    vrev64.16 q1, q0
; CHECK-BE-NEXT:    vpt.s16 gt, q1, zr
; CHECK-BE-NEXT:    vstrht.16 q1, [r0]
; CHECK-BE-NEXT:    bx lr
entry:
  %c = icmp sgt <8 x i16> %a, zeroinitializer
  call void @llvm.masked.store.v8i16.p0v8i16(<8 x i16> %a, <8 x i16>* %dest, i32 2, <8 x i1> %c)
  ret void
}

define arm_aapcs_vfpcc void @masked_v8i16_align1(<8 x i16> *%dest, <8 x i16> %a) {
; CHECK-LE-LABEL: masked_v8i16_align1:
; CHECK-LE:       @ %bb.0: @ %entry
; CHECK-LE-NEXT:    vpt.s16 gt, q0, zr
; CHECK-LE-NEXT:    vstrbt.8 q0, [r0]
; CHECK-LE-NEXT:    bx lr
;
; CHECK-BE-LABEL: masked_v8i16_align1:
; CHECK-BE:       @ %bb.0: @ %entry
; CHECK-BE-NEXT:    vrev64.16 q1, q0
; CHECK-BE-NEXT:    vrev16.8 q0, q1
; CHECK-BE-NEXT:    vpt.s16 gt, q1, zr
; CHECK-BE-NEXT:    vstrbt.8 q0, [r0]
; CHECK-BE-NEXT:    bx lr
entry:
  %c = icmp sgt <8 x i16> %a, zeroinitializer
  call void @llvm.masked.store.v8i16.p0v8i16(<8 x i16> %a, <8 x i16>* %dest, i32 1, <8 x i1> %c)
  ret void
}

define i8* @masked_v8i16_pre(i8* %y, i8* %x, <8 x i16> %a) {
; CHECK-LE-LABEL: masked_v8i16_pre:
; CHECK-LE:       @ %bb.0: @ %entry
; CHECK-LE-NEXT:    vldr d1, [sp]
; CHECK-LE-NEXT:    vldrw.u32 q1, [r1]
; CHECK-LE-NEXT:    vmov d0, r2, r3
; CHECK-LE-NEXT:    vpt.s16 gt, q0, zr
; CHECK-LE-NEXT:    vstrht.16 q1, [r0, #4]
; CHECK-LE-NEXT:    adds r0, #4
; CHECK-LE-NEXT:    bx lr
;
; CHECK-BE-LABEL: masked_v8i16_pre:
; CHECK-BE:       @ %bb.0: @ %entry
; CHECK-BE-NEXT:    vldr d1, [sp]
; CHECK-BE-NEXT:    vldrh.u16 q1, [r1]
; CHECK-BE-NEXT:    vmov d0, r3, r2
; CHECK-BE-NEXT:    vrev64.16 q2, q0
; CHECK-BE-NEXT:    vpt.s16 gt, q2, zr
; CHECK-BE-NEXT:    vstrht.16 q1, [r0, #4]
; CHECK-BE-NEXT:    adds r0, #4
; CHECK-BE-NEXT:    bx lr
entry:
  %z = getelementptr inbounds i8, i8* %y, i32 4
  %0 = bitcast i8* %x to <8 x i16>*
  %1 = load <8 x i16>, <8 x i16>* %0, align 4
  %2 = bitcast i8* %z to <8 x i16>*
  %c = icmp sgt <8 x i16> %a, zeroinitializer
  call void @llvm.masked.store.v8i16.p0v8i16(<8 x i16> %1, <8 x i16>* %2, i32 2, <8 x i1> %c)
  ret i8* %z
}

define i8* @masked_v8i16_post(i8* %y, i8* %x, <8 x i16> %a) {
; CHECK-LE-LABEL: masked_v8i16_post:
; CHECK-LE:       @ %bb.0: @ %entry
; CHECK-LE-NEXT:    vldr d1, [sp]
; CHECK-LE-NEXT:    vldrw.u32 q1, [r1]
; CHECK-LE-NEXT:    vmov d0, r2, r3
; CHECK-LE-NEXT:    vpt.s16 gt, q0, zr
; CHECK-LE-NEXT:    vstrht.16 q1, [r0]
; CHECK-LE-NEXT:    adds r0, #4
; CHECK-LE-NEXT:    bx lr
;
; CHECK-BE-LABEL: masked_v8i16_post:
; CHECK-BE:       @ %bb.0: @ %entry
; CHECK-BE-NEXT:    vldr d1, [sp]
; CHECK-BE-NEXT:    vldrh.u16 q1, [r1]
; CHECK-BE-NEXT:    vmov d0, r3, r2
; CHECK-BE-NEXT:    vrev64.16 q2, q0
; CHECK-BE-NEXT:    vpt.s16 gt, q2, zr
; CHECK-BE-NEXT:    vstrht.16 q1, [r0]
; CHECK-BE-NEXT:    adds r0, #4
; CHECK-BE-NEXT:    bx lr
entry:
  %z = getelementptr inbounds i8, i8* %y, i32 4
  %0 = bitcast i8* %x to <8 x i16>*
  %1 = load <8 x i16>, <8 x i16>* %0, align 4
  %2 = bitcast i8* %y to <8 x i16>*
  %c = icmp sgt <8 x i16> %a, zeroinitializer
  call void @llvm.masked.store.v8i16.p0v8i16(<8 x i16> %1, <8 x i16>* %2, i32 2, <8 x i1> %c)
  ret i8* %z
}


define arm_aapcs_vfpcc void @masked_v16i8(<16 x i8> *%dest, <16 x i8> %a) {
; CHECK-LE-LABEL: masked_v16i8:
; CHECK-LE:       @ %bb.0: @ %entry
; CHECK-LE-NEXT:    vpt.s8 gt, q0, zr
; CHECK-LE-NEXT:    vstrbt.8 q0, [r0]
; CHECK-LE-NEXT:    bx lr
;
; CHECK-BE-LABEL: masked_v16i8:
; CHECK-BE:       @ %bb.0: @ %entry
; CHECK-BE-NEXT:    vrev64.8 q1, q0
; CHECK-BE-NEXT:    vpt.s8 gt, q1, zr
; CHECK-BE-NEXT:    vstrbt.8 q1, [r0]
; CHECK-BE-NEXT:    bx lr
entry:
  %c = icmp sgt <16 x i8> %a, zeroinitializer
  call void @llvm.masked.store.v16i8.p0v16i8(<16 x i8> %a, <16 x i8>* %dest, i32 1, <16 x i1> %c)
  ret void
}

define i8* @masked_v16i8_pre(i8* %y, i8* %x, <16 x i8> %a) {
; CHECK-LE-LABEL: masked_v16i8_pre:
; CHECK-LE:       @ %bb.0: @ %entry
; CHECK-LE-NEXT:    vldr d1, [sp]
; CHECK-LE-NEXT:    vldrw.u32 q1, [r1]
; CHECK-LE-NEXT:    vmov d0, r2, r3
; CHECK-LE-NEXT:    vpt.s8 gt, q0, zr
; CHECK-LE-NEXT:    vstrbt.8 q1, [r0, #4]
; CHECK-LE-NEXT:    adds r0, #4
; CHECK-LE-NEXT:    bx lr
;
; CHECK-BE-LABEL: masked_v16i8_pre:
; CHECK-BE:       @ %bb.0: @ %entry
; CHECK-BE-NEXT:    vldr d1, [sp]
; CHECK-BE-NEXT:    vldrb.u8 q1, [r1]
; CHECK-BE-NEXT:    vmov d0, r3, r2
; CHECK-BE-NEXT:    vrev64.8 q2, q0
; CHECK-BE-NEXT:    vpt.s8 gt, q2, zr
; CHECK-BE-NEXT:    vstrbt.8 q1, [r0, #4]
; CHECK-BE-NEXT:    adds r0, #4
; CHECK-BE-NEXT:    bx lr
entry:
  %z = getelementptr inbounds i8, i8* %y, i32 4
  %0 = bitcast i8* %x to <16 x i8>*
  %1 = load <16 x i8>, <16 x i8>* %0, align 4
  %2 = bitcast i8* %z to <16 x i8>*
  %c = icmp sgt <16 x i8> %a, zeroinitializer
  call void @llvm.masked.store.v16i8.p0v16i8(<16 x i8> %1, <16 x i8>* %2, i32 1, <16 x i1> %c)
  ret i8* %z
}

define i8* @masked_v16i8_post(i8* %y, i8* %x, <16 x i8> %a) {
; CHECK-LE-LABEL: masked_v16i8_post:
; CHECK-LE:       @ %bb.0: @ %entry
; CHECK-LE-NEXT:    vldr d1, [sp]
; CHECK-LE-NEXT:    vldrw.u32 q1, [r1]
; CHECK-LE-NEXT:    vmov d0, r2, r3
; CHECK-LE-NEXT:    vpt.s8 gt, q0, zr
; CHECK-LE-NEXT:    vstrbt.8 q1, [r0]
; CHECK-LE-NEXT:    adds r0, #4
; CHECK-LE-NEXT:    bx lr
;
; CHECK-BE-LABEL: masked_v16i8_post:
; CHECK-BE:       @ %bb.0: @ %entry
; CHECK-BE-NEXT:    vldr d1, [sp]
; CHECK-BE-NEXT:    vldrb.u8 q1, [r1]
; CHECK-BE-NEXT:    vmov d0, r3, r2
; CHECK-BE-NEXT:    vrev64.8 q2, q0
; CHECK-BE-NEXT:    vpt.s8 gt, q2, zr
; CHECK-BE-NEXT:    vstrbt.8 q1, [r0]
; CHECK-BE-NEXT:    adds r0, #4
; CHECK-BE-NEXT:    bx lr
entry:
  %z = getelementptr inbounds i8, i8* %y, i32 4
  %0 = bitcast i8* %x to <16 x i8>*
  %1 = load <16 x i8>, <16 x i8>* %0, align 4
  %2 = bitcast i8* %y to <16 x i8>*
  %c = icmp sgt <16 x i8> %a, zeroinitializer
  call void @llvm.masked.store.v16i8.p0v16i8(<16 x i8> %1, <16 x i8>* %2, i32 1, <16 x i1> %c)
  ret i8* %z
}


define arm_aapcs_vfpcc void @masked_v4f32(<4 x float> *%dest, <4 x float> %a, <4 x i32> %b) {
; CHECK-LE-LABEL: masked_v4f32:
; CHECK-LE:       @ %bb.0: @ %entry
; CHECK-LE-NEXT:    vpt.i32 ne, q1, zr
; CHECK-LE-NEXT:    vstrwt.32 q0, [r0]
; CHECK-LE-NEXT:    bx lr
;
; CHECK-BE-LABEL: masked_v4f32:
; CHECK-BE:       @ %bb.0: @ %entry
; CHECK-BE-NEXT:    vrev64.32 q2, q1
; CHECK-BE-NEXT:    vrev64.32 q1, q0
; CHECK-BE-NEXT:    vpt.i32 ne, q2, zr
; CHECK-BE-NEXT:    vstrwt.32 q1, [r0]
; CHECK-BE-NEXT:    bx lr
entry:
  %c = icmp ugt <4 x i32> %b, zeroinitializer
  call void @llvm.masked.store.v4f32.p0v4f32(<4 x float> %a, <4 x float>* %dest, i32 4, <4 x i1> %c)
  ret void
}

define arm_aapcs_vfpcc void @masked_v4f32_align1(<4 x float> *%dest, <4 x float> %a, <4 x i32> %b) {
; CHECK-LE-LABEL: masked_v4f32_align1:
; CHECK-LE:       @ %bb.0: @ %entry
; CHECK-LE-NEXT:    vpt.i32 ne, q1, zr
; CHECK-LE-NEXT:    vstrbt.8 q0, [r0]
; CHECK-LE-NEXT:    bx lr
;
; CHECK-BE-LABEL: masked_v4f32_align1:
; CHECK-BE:       @ %bb.0: @ %entry
; CHECK-BE-NEXT:    vrev64.32 q2, q1
; CHECK-BE-NEXT:    vrev64.32 q1, q0
; CHECK-BE-NEXT:    vrev32.8 q0, q1
; CHECK-BE-NEXT:    vpt.i32 ne, q2, zr
; CHECK-BE-NEXT:    vstrbt.8 q0, [r0]
; CHECK-BE-NEXT:    bx lr
entry:
  %c = icmp ugt <4 x i32> %b, zeroinitializer
  call void @llvm.masked.store.v4f32.p0v4f32(<4 x float> %a, <4 x float>* %dest, i32 1, <4 x i1> %c)
  ret void
}

define i8* @masked_v4f32_pre(i8* %y, i8* %x, <4 x i32> %a) {
; CHECK-LE-LABEL: masked_v4f32_pre:
; CHECK-LE:       @ %bb.0: @ %entry
; CHECK-LE-NEXT:    vldr d1, [sp]
; CHECK-LE-NEXT:    vldrw.u32 q1, [r1]
; CHECK-LE-NEXT:    vmov d0, r2, r3
; CHECK-LE-NEXT:    vpt.s32 gt, q0, zr
; CHECK-LE-NEXT:    vstrwt.32 q1, [r0, #4]
; CHECK-LE-NEXT:    adds r0, #4
; CHECK-LE-NEXT:    bx lr
;
; CHECK-BE-LABEL: masked_v4f32_pre:
; CHECK-BE:       @ %bb.0: @ %entry
; CHECK-BE-NEXT:    vldr d1, [sp]
; CHECK-BE-NEXT:    vldrw.u32 q1, [r1]
; CHECK-BE-NEXT:    vmov d0, r3, r2
; CHECK-BE-NEXT:    vrev64.32 q2, q0
; CHECK-BE-NEXT:    vpt.s32 gt, q2, zr
; CHECK-BE-NEXT:    vstrwt.32 q1, [r0, #4]
; CHECK-BE-NEXT:    adds r0, #4
; CHECK-BE-NEXT:    bx lr
entry:
  %z = getelementptr inbounds i8, i8* %y, i32 4
  %0 = bitcast i8* %x to <4 x float>*
  %1 = load <4 x float>, <4 x float>* %0, align 4
  %2 = bitcast i8* %z to <4 x float>*
  %c = icmp sgt <4 x i32> %a, zeroinitializer
  call void @llvm.masked.store.v4f32.p0v4f32(<4 x float> %1, <4 x float>* %2, i32 4, <4 x i1> %c)
  ret i8* %z
}

define i8* @masked_v4f32_post(i8* %y, i8* %x, <4 x i32> %a) {
; CHECK-LE-LABEL: masked_v4f32_post:
; CHECK-LE:       @ %bb.0: @ %entry
; CHECK-LE-NEXT:    vldr d1, [sp]
; CHECK-LE-NEXT:    vldrw.u32 q1, [r1]
; CHECK-LE-NEXT:    vmov d0, r2, r3
; CHECK-LE-NEXT:    vpt.s32 gt, q0, zr
; CHECK-LE-NEXT:    vstrwt.32 q1, [r0]
; CHECK-LE-NEXT:    adds r0, #4
; CHECK-LE-NEXT:    bx lr
;
; CHECK-BE-LABEL: masked_v4f32_post:
; CHECK-BE:       @ %bb.0: @ %entry
; CHECK-BE-NEXT:    vldr d1, [sp]
; CHECK-BE-NEXT:    vldrw.u32 q1, [r1]
; CHECK-BE-NEXT:    vmov d0, r3, r2
; CHECK-BE-NEXT:    vrev64.32 q2, q0
; CHECK-BE-NEXT:    vpt.s32 gt, q2, zr
; CHECK-BE-NEXT:    vstrwt.32 q1, [r0]
; CHECK-BE-NEXT:    adds r0, #4
; CHECK-BE-NEXT:    bx lr
entry:
  %z = getelementptr inbounds i8, i8* %y, i32 4
  %0 = bitcast i8* %x to <4 x float>*
  %1 = load <4 x float>, <4 x float>* %0, align 4
  %2 = bitcast i8* %y to <4 x float>*
  %c = icmp sgt <4 x i32> %a, zeroinitializer
  call void @llvm.masked.store.v4f32.p0v4f32(<4 x float> %1, <4 x float>* %2, i32 4, <4 x i1> %c)
  ret i8* %z
}


define arm_aapcs_vfpcc void @masked_v8f16(<8 x half> *%dest, <8 x half> %a, <8 x i16> %b) {
; CHECK-LE-LABEL: masked_v8f16:
; CHECK-LE:       @ %bb.0: @ %entry
; CHECK-LE-NEXT:    vpt.i16 ne, q1, zr
; CHECK-LE-NEXT:    vstrht.16 q0, [r0]
; CHECK-LE-NEXT:    bx lr
;
; CHECK-BE-LABEL: masked_v8f16:
; CHECK-BE:       @ %bb.0: @ %entry
; CHECK-BE-NEXT:    vrev64.16 q2, q1
; CHECK-BE-NEXT:    vrev64.16 q1, q0
; CHECK-BE-NEXT:    vpt.i16 ne, q2, zr
; CHECK-BE-NEXT:    vstrht.16 q1, [r0]
; CHECK-BE-NEXT:    bx lr
entry:
  %c = icmp ugt <8 x i16> %b, zeroinitializer
  call void @llvm.masked.store.v8f16.p0v8f16(<8 x half> %a, <8 x half>* %dest, i32 2, <8 x i1> %c)
  ret void
}

define arm_aapcs_vfpcc void @masked_v8f16_align1(<8 x half> *%dest, <8 x half> %a, <8 x i16> %b) {
; CHECK-LE-LABEL: masked_v8f16_align1:
; CHECK-LE:       @ %bb.0: @ %entry
; CHECK-LE-NEXT:    vpt.i16 ne, q1, zr
; CHECK-LE-NEXT:    vstrbt.8 q0, [r0]
; CHECK-LE-NEXT:    bx lr
;
; CHECK-BE-LABEL: masked_v8f16_align1:
; CHECK-BE:       @ %bb.0: @ %entry
; CHECK-BE-NEXT:    vrev64.16 q2, q0
; CHECK-BE-NEXT:    vrev16.8 q0, q2
; CHECK-BE-NEXT:    vrev64.16 q2, q1
; CHECK-BE-NEXT:    vpt.i16 ne, q2, zr
; CHECK-BE-NEXT:    vstrbt.8 q0, [r0]
; CHECK-BE-NEXT:    bx lr
entry:
  %c = icmp ugt <8 x i16> %b, zeroinitializer
  call void @llvm.masked.store.v8f16.p0v8f16(<8 x half> %a, <8 x half>* %dest, i32 1, <8 x i1> %c)
  ret void
}

define i8* @masked_v8f16_pre(i8* %y, i8* %x, <8 x i16> %a) {
; CHECK-LE-LABEL: masked_v8f16_pre:
; CHECK-LE:       @ %bb.0: @ %entry
; CHECK-LE-NEXT:    vldr d1, [sp]
; CHECK-LE-NEXT:    vldrw.u32 q1, [r1]
; CHECK-LE-NEXT:    vmov d0, r2, r3
; CHECK-LE-NEXT:    vpt.s16 gt, q0, zr
; CHECK-LE-NEXT:    vstrht.16 q1, [r0, #4]
; CHECK-LE-NEXT:    adds r0, #4
; CHECK-LE-NEXT:    bx lr
;
; CHECK-BE-LABEL: masked_v8f16_pre:
; CHECK-BE:       @ %bb.0: @ %entry
; CHECK-BE-NEXT:    vldr d1, [sp]
; CHECK-BE-NEXT:    vldrh.u16 q1, [r1]
; CHECK-BE-NEXT:    vmov d0, r3, r2
; CHECK-BE-NEXT:    vrev64.16 q2, q0
; CHECK-BE-NEXT:    vpt.s16 gt, q2, zr
; CHECK-BE-NEXT:    vstrht.16 q1, [r0, #4]
; CHECK-BE-NEXT:    adds r0, #4
; CHECK-BE-NEXT:    bx lr
entry:
  %z = getelementptr inbounds i8, i8* %y, i32 4
  %0 = bitcast i8* %x to <8 x half>*
  %1 = load <8 x half>, <8 x half>* %0, align 4
  %2 = bitcast i8* %z to <8 x half>*
  %c = icmp sgt <8 x i16> %a, zeroinitializer
  call void @llvm.masked.store.v8f16.p0v8f16(<8 x half> %1, <8 x half>* %2, i32 2, <8 x i1> %c)
  ret i8* %z
}

define i8* @masked_v8f16_post(i8* %y, i8* %x, <8 x i16> %a) {
; CHECK-LE-LABEL: masked_v8f16_post:
; CHECK-LE:       @ %bb.0: @ %entry
; CHECK-LE-NEXT:    vldr d1, [sp]
; CHECK-LE-NEXT:    vldrw.u32 q1, [r1]
; CHECK-LE-NEXT:    vmov d0, r2, r3
; CHECK-LE-NEXT:    vpt.s16 gt, q0, zr
; CHECK-LE-NEXT:    vstrht.16 q1, [r0]
; CHECK-LE-NEXT:    adds r0, #4
; CHECK-LE-NEXT:    bx lr
;
; CHECK-BE-LABEL: masked_v8f16_post:
; CHECK-BE:       @ %bb.0: @ %entry
; CHECK-BE-NEXT:    vldr d1, [sp]
; CHECK-BE-NEXT:    vldrh.u16 q1, [r1]
; CHECK-BE-NEXT:    vmov d0, r3, r2
; CHECK-BE-NEXT:    vrev64.16 q2, q0
; CHECK-BE-NEXT:    vpt.s16 gt, q2, zr
; CHECK-BE-NEXT:    vstrht.16 q1, [r0]
; CHECK-BE-NEXT:    adds r0, #4
; CHECK-BE-NEXT:    bx lr
entry:
  %z = getelementptr inbounds i8, i8* %y, i32 4
  %0 = bitcast i8* %x to <8 x half>*
  %1 = load <8 x half>, <8 x half>* %0, align 4
  %2 = bitcast i8* %y to <8 x half>*
  %c = icmp sgt <8 x i16> %a, zeroinitializer
  call void @llvm.masked.store.v8f16.p0v8f16(<8 x half> %1, <8 x half>* %2, i32 2, <8 x i1> %c)
  ret i8* %z
}


define arm_aapcs_vfpcc void @masked_v2i64(<2 x i64> *%dest, <2 x i64> %a) {
; CHECK-LE-LABEL: masked_v2i64:
; CHECK-LE:       @ %bb.0: @ %entry
; CHECK-LE-NEXT:    .pad #4
; CHECK-LE-NEXT:    sub sp, #4
; CHECK-LE-NEXT:    vmov r2, s0
; CHECK-LE-NEXT:    movs r3, #0
; CHECK-LE-NEXT:    vmov r1, s1
; CHECK-LE-NEXT:    vmov r12, s3
; CHECK-LE-NEXT:    rsbs r2, r2, #0
; CHECK-LE-NEXT:    vmov r2, s2
; CHECK-LE-NEXT:    sbcs.w r1, r3, r1
; CHECK-LE-NEXT:    mov.w r1, #0
; CHECK-LE-NEXT:    it lt
; CHECK-LE-NEXT:    movlt r1, #1
; CHECK-LE-NEXT:    rsbs r2, r2, #0
; CHECK-LE-NEXT:    sbcs.w r2, r3, r12
; CHECK-LE-NEXT:    it lt
; CHECK-LE-NEXT:    movlt r3, #1
; CHECK-LE-NEXT:    cmp r3, #0
; CHECK-LE-NEXT:    it ne
; CHECK-LE-NEXT:    mvnne r3, #1
; CHECK-LE-NEXT:    bfi r3, r1, #0, #1
; CHECK-LE-NEXT:    and r1, r3, #3
; CHECK-LE-NEXT:    lsls r2, r3, #31
; CHECK-LE-NEXT:    it ne
; CHECK-LE-NEXT:    vstrne d0, [r0]
; CHECK-LE-NEXT:    lsls r1, r1, #30
; CHECK-LE-NEXT:    it mi
; CHECK-LE-NEXT:    vstrmi d1, [r0, #8]
; CHECK-LE-NEXT:    add sp, #4
; CHECK-LE-NEXT:    bx lr
;
; CHECK-BE-LABEL: masked_v2i64:
; CHECK-BE:       @ %bb.0: @ %entry
; CHECK-BE-NEXT:    .pad #4
; CHECK-BE-NEXT:    sub sp, #4
; CHECK-BE-NEXT:    vrev64.32 q1, q0
; CHECK-BE-NEXT:    movs r3, #0
; CHECK-BE-NEXT:    vmov r2, s7
; CHECK-BE-NEXT:    vmov r1, s6
; CHECK-BE-NEXT:    vmov r12, s4
; CHECK-BE-NEXT:    rsbs r2, r2, #0
; CHECK-BE-NEXT:    vmov r2, s5
; CHECK-BE-NEXT:    sbcs.w r1, r3, r1
; CHECK-BE-NEXT:    mov.w r1, #0
; CHECK-BE-NEXT:    it lt
; CHECK-BE-NEXT:    movlt r1, #1
; CHECK-BE-NEXT:    rsbs r2, r2, #0
; CHECK-BE-NEXT:    sbcs.w r2, r3, r12
; CHECK-BE-NEXT:    it lt
; CHECK-BE-NEXT:    movlt r3, #1
; CHECK-BE-NEXT:    cmp r3, #0
; CHECK-BE-NEXT:    it ne
; CHECK-BE-NEXT:    mvnne r3, #1
; CHECK-BE-NEXT:    bfi r3, r1, #0, #1
; CHECK-BE-NEXT:    and r1, r3, #3
; CHECK-BE-NEXT:    lsls r2, r3, #31
; CHECK-BE-NEXT:    it ne
; CHECK-BE-NEXT:    vstrne d0, [r0]
; CHECK-BE-NEXT:    lsls r1, r1, #30
; CHECK-BE-NEXT:    it mi
; CHECK-BE-NEXT:    vstrmi d1, [r0, #8]
; CHECK-BE-NEXT:    add sp, #4
; CHECK-BE-NEXT:    bx lr
entry:
  %c = icmp sgt <2 x i64> %a, zeroinitializer
  call void @llvm.masked.store.v2i64.p0v2i64(<2 x i64> %a, <2 x i64>* %dest, i32 8, <2 x i1> %c)
  ret void
}

define arm_aapcs_vfpcc void @masked_v2f64(<2 x double> *%dest, <2 x double> %a, <2 x i64> %b) {
; CHECK-LE-LABEL: masked_v2f64:
; CHECK-LE:       @ %bb.0: @ %entry
; CHECK-LE-NEXT:    .pad #4
; CHECK-LE-NEXT:    sub sp, #4
; CHECK-LE-NEXT:    vmov r2, s4
; CHECK-LE-NEXT:    movs r3, #0
; CHECK-LE-NEXT:    vmov r1, s5
; CHECK-LE-NEXT:    vmov r12, s7
; CHECK-LE-NEXT:    rsbs r2, r2, #0
; CHECK-LE-NEXT:    vmov r2, s6
; CHECK-LE-NEXT:    sbcs.w r1, r3, r1
; CHECK-LE-NEXT:    mov.w r1, #0
; CHECK-LE-NEXT:    it lt
; CHECK-LE-NEXT:    movlt r1, #1
; CHECK-LE-NEXT:    rsbs r2, r2, #0
; CHECK-LE-NEXT:    sbcs.w r2, r3, r12
; CHECK-LE-NEXT:    it lt
; CHECK-LE-NEXT:    movlt r3, #1
; CHECK-LE-NEXT:    cmp r3, #0
; CHECK-LE-NEXT:    it ne
; CHECK-LE-NEXT:    mvnne r3, #1
; CHECK-LE-NEXT:    bfi r3, r1, #0, #1
; CHECK-LE-NEXT:    and r1, r3, #3
; CHECK-LE-NEXT:    lsls r2, r3, #31
; CHECK-LE-NEXT:    it ne
; CHECK-LE-NEXT:    vstrne d0, [r0]
; CHECK-LE-NEXT:    lsls r1, r1, #30
; CHECK-LE-NEXT:    it mi
; CHECK-LE-NEXT:    vstrmi d1, [r0, #8]
; CHECK-LE-NEXT:    add sp, #4
; CHECK-LE-NEXT:    bx lr
;
; CHECK-BE-LABEL: masked_v2f64:
; CHECK-BE:       @ %bb.0: @ %entry
; CHECK-BE-NEXT:    .pad #4
; CHECK-BE-NEXT:    sub sp, #4
; CHECK-BE-NEXT:    vrev64.32 q2, q1
; CHECK-BE-NEXT:    movs r3, #0
; CHECK-BE-NEXT:    vmov r2, s11
; CHECK-BE-NEXT:    vmov r1, s10
; CHECK-BE-NEXT:    vmov r12, s8
; CHECK-BE-NEXT:    rsbs r2, r2, #0
; CHECK-BE-NEXT:    vmov r2, s9
; CHECK-BE-NEXT:    sbcs.w r1, r3, r1
; CHECK-BE-NEXT:    mov.w r1, #0
; CHECK-BE-NEXT:    it lt
; CHECK-BE-NEXT:    movlt r1, #1
; CHECK-BE-NEXT:    rsbs r2, r2, #0
; CHECK-BE-NEXT:    sbcs.w r2, r3, r12
; CHECK-BE-NEXT:    it lt
; CHECK-BE-NEXT:    movlt r3, #1
; CHECK-BE-NEXT:    cmp r3, #0
; CHECK-BE-NEXT:    it ne
; CHECK-BE-NEXT:    mvnne r3, #1
; CHECK-BE-NEXT:    bfi r3, r1, #0, #1
; CHECK-BE-NEXT:    and r1, r3, #3
; CHECK-BE-NEXT:    lsls r2, r3, #31
; CHECK-BE-NEXT:    it ne
; CHECK-BE-NEXT:    vstrne d0, [r0]
; CHECK-BE-NEXT:    lsls r1, r1, #30
; CHECK-BE-NEXT:    it mi
; CHECK-BE-NEXT:    vstrmi d1, [r0, #8]
; CHECK-BE-NEXT:    add sp, #4
; CHECK-BE-NEXT:    bx lr
entry:
  %c = icmp sgt <2 x i64> %b, zeroinitializer
  call void @llvm.masked.store.v2f64.p0v2f64(<2 x double> %a, <2 x double>* %dest, i32 8, <2 x i1> %c)
  ret void
}


declare void @llvm.masked.store.v4i32.p0v4i32(<4 x i32>, <4 x i32>*, i32, <4 x i1>)
declare void @llvm.masked.store.v8i16.p0v8i16(<8 x i16>, <8 x i16>*, i32, <8 x i1>)
declare void @llvm.masked.store.v16i8.p0v16i8(<16 x i8>, <16 x i8>*, i32, <16 x i1>)
declare void @llvm.masked.store.v4f32.p0v4f32(<4 x float>, <4 x float>*, i32, <4 x i1>)
declare void @llvm.masked.store.v8f16.p0v8f16(<8 x half>, <8 x half>*, i32, <8 x i1>)
declare void @llvm.masked.store.v2i64.p0v2i64(<2 x i64>, <2 x i64>*, i32, <2 x i1>)
declare void @llvm.masked.store.v2f64.p0v2f64(<2 x double>, <2 x double>*, i32, <2 x i1>)