; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -verify-machineinstrs | FileCheck %s --check-prefixes=SSE2
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx -verify-machineinstrs | FileCheck %s --check-prefixes=AVX
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512f -verify-machineinstrs | FileCheck %s --check-prefixes=AVX512

define half @test(float %f, ptr %p) nounwind {
; SSE2-LABEL: test:
; SSE2:       # %bb.0:
; SSE2-NEXT:    pushq %rbx
; SSE2-NEXT:    subq $16, %rsp
; SSE2-NEXT:    movq %rdi, %rbx
; SSE2-NEXT:    callq __truncsfhf2@PLT
; SSE2-NEXT:    movss %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 4-byte Spill
; SSE2-NEXT:    callq __extendhfsf2@PLT
; SSE2-NEXT:    movss %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 4-byte Spill
; SSE2-NEXT:    #APP
; SSE2-NEXT:    #NO_APP
; SSE2-NEXT:    movss {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 4-byte Reload
; SSE2-NEXT:    # xmm0 = mem[0],zero,zero,zero
; SSE2-NEXT:    movss %xmm0, (%rbx)
; SSE2-NEXT:    movss {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 4-byte Reload
; SSE2-NEXT:    # xmm0 = mem[0],zero,zero,zero
; SSE2-NEXT:    addq $16, %rsp
; SSE2-NEXT:    popq %rbx
; SSE2-NEXT:    retq
;
; AVX-LABEL: test:
; AVX:       # %bb.0:
; AVX-NEXT:    pushq %rbx
; AVX-NEXT:    subq $16, %rsp
; AVX-NEXT:    movq %rdi, %rbx
; AVX-NEXT:    callq __truncsfhf2@PLT
; AVX-NEXT:    vmovss %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 4-byte Spill
; AVX-NEXT:    callq __extendhfsf2@PLT
; AVX-NEXT:    vmovss %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 4-byte Spill
; AVX-NEXT:    #APP
; AVX-NEXT:    #NO_APP
; AVX-NEXT:    vmovss {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 4-byte Reload
; AVX-NEXT:    # xmm0 = mem[0],zero,zero,zero
; AVX-NEXT:    vmovss %xmm0, (%rbx)
; AVX-NEXT:    vmovss {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 4-byte Reload
; AVX-NEXT:    # xmm0 = mem[0],zero,zero,zero
; AVX-NEXT:    addq $16, %rsp
; AVX-NEXT:    popq %rbx
; AVX-NEXT:    retq
;
; AVX512-LABEL: test:
; AVX512:       # %bb.0:
; AVX512-NEXT:    vcvtps2ph $4, %xmm0, %xmm0
; AVX512-NEXT:    vmovaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
; AVX512-NEXT:    vcvtph2ps %xmm0, %xmm0
; AVX512-NEXT:    vmovaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
; AVX512-NEXT:    #APP
; AVX512-NEXT:    #NO_APP
; AVX512-NEXT:    vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
; AVX512-NEXT:    vmovss %xmm0, (%rdi)
; AVX512-NEXT:    vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
; AVX512-NEXT:    retq
  %t = fptrunc float %f to half
  %t2 = fpext half %t to float
  tail call void asm sideeffect "", "~{xmm0},~{xmm1},~{xmm2},~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{dirflag},~{fpsr},~{flags}"()
  store float %t2, ptr %p
  ret half %t
}