; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+sse2     | FileCheck %s --check-prefix=SSE
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx      | FileCheck %s --check-prefixes=AVX,AVX-RECIP
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx,+fma | FileCheck %s --check-prefixes=AVX,FMA-RECIP
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=bdver2 | FileCheck %s --check-prefixes=AVX,BDVER2
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=btver2 | FileCheck %s --check-prefixes=AVX,BTVER2
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=sandybridge | FileCheck %s --check-prefixes=AVX,SANDY
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=haswell | FileCheck %s --check-prefixes=AVX,HASWELL
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=haswell -mattr=-fma | FileCheck %s --check-prefixes=AVX,HASWELL-NO-FMA
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=knl | FileCheck %s --check-prefixes=AVX,AVX512,KNL
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=skx | FileCheck %s --check-prefixes=AVX,AVX512,SKX

; If the target's divss/divps instructions are substantially
; slower than rcpss/rcpps with a Newton-Raphson refinement,
; we should generate the estimate sequence.

; See PR21385 ( http://llvm.org/bugs/show_bug.cgi?id=21385 )
; for details about the accuracy, speed, and implementation
; differences of x86 reciprocal estimates.

define float @f32_no_estimate(float %x) #0 {
; SSE-LABEL: f32_no_estimate:
; SSE:       # %bb.0:
; SSE-NEXT:    movss {{.*#+}} xmm1 = mem[0],zero,zero,zero
; SSE-NEXT:    divss %xmm0, %xmm1
; SSE-NEXT:    movaps %xmm1, %xmm0
; SSE-NEXT:    retq
;
; AVX-LABEL: f32_no_estimate:
; AVX:       # %bb.0:
; AVX-NEXT:    vmovss {{.*#+}} xmm1 = mem[0],zero,zero,zero
; AVX-NEXT:    vdivss %xmm0, %xmm1, %xmm0
; AVX-NEXT:    retq
  %div = fdiv fast float 1.0, %x
  ret float %div
}

define float @f32_one_step(float %x) #1 {
; SSE-LABEL: f32_one_step:
; SSE:       # %bb.0:
; SSE-NEXT:    rcpss %xmm0, %xmm2
; SSE-NEXT:    mulss %xmm2, %xmm0
; SSE-NEXT:    movss {{.*#+}} xmm1 = mem[0],zero,zero,zero
; SSE-NEXT:    subss %xmm0, %xmm1
; SSE-NEXT:    mulss %xmm2, %xmm1
; SSE-NEXT:    addss %xmm2, %xmm1
; SSE-NEXT:    movaps %xmm1, %xmm0
; SSE-NEXT:    retq
;
; AVX-RECIP-LABEL: f32_one_step:
; AVX-RECIP:       # %bb.0:
; AVX-RECIP-NEXT:    vrcpss %xmm0, %xmm0, %xmm1
; AVX-RECIP-NEXT:    vmulss %xmm1, %xmm0, %xmm0
; AVX-RECIP-NEXT:    vmovss {{.*#+}} xmm2 = mem[0],zero,zero,zero
; AVX-RECIP-NEXT:    vsubss %xmm0, %xmm2, %xmm0
; AVX-RECIP-NEXT:    vmulss %xmm0, %xmm1, %xmm0
; AVX-RECIP-NEXT:    vaddss %xmm0, %xmm1, %xmm0
; AVX-RECIP-NEXT:    retq
;
; FMA-RECIP-LABEL: f32_one_step:
; FMA-RECIP:       # %bb.0:
; FMA-RECIP-NEXT:    vrcpss %xmm0, %xmm0, %xmm1
; FMA-RECIP-NEXT:    vfmsub213ss {{.*#+}} xmm0 = (xmm1 * xmm0) - mem
; FMA-RECIP-NEXT:    vfnmadd132ss {{.*#+}} xmm0 = -(xmm0 * xmm1) + xmm1
; FMA-RECIP-NEXT:    retq
;
; BDVER2-LABEL: f32_one_step:
; BDVER2:       # %bb.0:
; BDVER2-NEXT:    vrcpss %xmm0, %xmm0, %xmm1
; BDVER2-NEXT:    vfmsubss {{.*#+}} xmm0 = (xmm0 * xmm1) - mem
; BDVER2-NEXT:    vfnmaddss {{.*#+}} xmm0 = -(xmm1 * xmm0) + xmm1
; BDVER2-NEXT:    retq
;
; BTVER2-LABEL: f32_one_step:
; BTVER2:       # %bb.0:
; BTVER2-NEXT:    vmovss {{.*#+}} xmm2 = mem[0],zero,zero,zero
; BTVER2-NEXT:    vrcpss %xmm0, %xmm0, %xmm1
; BTVER2-NEXT:    vmulss %xmm1, %xmm0, %xmm0
; BTVER2-NEXT:    vsubss %xmm0, %xmm2, %xmm0
; BTVER2-NEXT:    vmulss %xmm0, %xmm1, %xmm0
; BTVER2-NEXT:    vaddss %xmm0, %xmm1, %xmm0
; BTVER2-NEXT:    retq
;
; SANDY-LABEL: f32_one_step:
; SANDY:       # %bb.0:
; SANDY-NEXT:    vrcpss %xmm0, %xmm0, %xmm1
; SANDY-NEXT:    vmulss %xmm1, %xmm0, %xmm0
; SANDY-NEXT:    vmovss {{.*#+}} xmm2 = mem[0],zero,zero,zero
; SANDY-NEXT:    vsubss %xmm0, %xmm2, %xmm0
; SANDY-NEXT:    vmulss %xmm0, %xmm1, %xmm0
; SANDY-NEXT:    vaddss %xmm0, %xmm1, %xmm0
; SANDY-NEXT:    retq
;
; HASWELL-LABEL: f32_one_step:
; HASWELL:       # %bb.0:
; HASWELL-NEXT:    vrcpss %xmm0, %xmm0, %xmm1
; HASWELL-NEXT:    vfmsub213ss {{.*#+}} xmm0 = (xmm1 * xmm0) - mem
; HASWELL-NEXT:    vfnmadd132ss {{.*#+}} xmm0 = -(xmm0 * xmm1) + xmm1
; HASWELL-NEXT:    retq
;
; HASWELL-NO-FMA-LABEL: f32_one_step:
; HASWELL-NO-FMA:       # %bb.0:
; HASWELL-NO-FMA-NEXT:    vrcpss %xmm0, %xmm0, %xmm1
; HASWELL-NO-FMA-NEXT:    vmulss %xmm1, %xmm0, %xmm0
; HASWELL-NO-FMA-NEXT:    vmovss {{.*#+}} xmm2 = mem[0],zero,zero,zero
; HASWELL-NO-FMA-NEXT:    vsubss %xmm0, %xmm2, %xmm0
; HASWELL-NO-FMA-NEXT:    vmulss %xmm0, %xmm1, %xmm0
; HASWELL-NO-FMA-NEXT:    vaddss %xmm0, %xmm1, %xmm0
; HASWELL-NO-FMA-NEXT:    retq
;
; AVX512-LABEL: f32_one_step:
; AVX512:       # %bb.0:
; AVX512-NEXT:    vrcpss %xmm0, %xmm0, %xmm1
; AVX512-NEXT:    vfmsub213ss {{.*#+}} xmm0 = (xmm1 * xmm0) - mem
; AVX512-NEXT:    vfnmadd132ss {{.*#+}} xmm0 = -(xmm0 * xmm1) + xmm1
; AVX512-NEXT:    retq
  %div = fdiv fast float 1.0, %x
  ret float %div
}

define float @f32_one_step_variables(float %x, float %y) #1 {
; SSE-LABEL: f32_one_step_variables:
; SSE:       # %bb.0:
; SSE-NEXT:    rcpss %xmm1, %xmm2
; SSE-NEXT:    movaps %xmm0, %xmm3
; SSE-NEXT:    mulss %xmm2, %xmm3
; SSE-NEXT:    mulss %xmm3, %xmm1
; SSE-NEXT:    subss %xmm1, %xmm0
; SSE-NEXT:    mulss %xmm2, %xmm0
; SSE-NEXT:    addss %xmm3, %xmm0
; SSE-NEXT:    retq
;
; AVX-RECIP-LABEL: f32_one_step_variables:
; AVX-RECIP:       # %bb.0:
; AVX-RECIP-NEXT:    vrcpss %xmm1, %xmm1, %xmm2
; AVX-RECIP-NEXT:    vmulss %xmm2, %xmm0, %xmm3
; AVX-RECIP-NEXT:    vmulss %xmm3, %xmm1, %xmm1
; AVX-RECIP-NEXT:    vsubss %xmm1, %xmm0, %xmm0
; AVX-RECIP-NEXT:    vmulss %xmm0, %xmm2, %xmm0
; AVX-RECIP-NEXT:    vaddss %xmm0, %xmm3, %xmm0
; AVX-RECIP-NEXT:    retq
;
; FMA-RECIP-LABEL: f32_one_step_variables:
; FMA-RECIP:       # %bb.0:
; FMA-RECIP-NEXT:    vrcpss %xmm1, %xmm1, %xmm2
; FMA-RECIP-NEXT:    vmulss %xmm2, %xmm0, %xmm3
; FMA-RECIP-NEXT:    vfmsub231ss {{.*#+}} xmm0 = (xmm3 * xmm1) - xmm0
; FMA-RECIP-NEXT:    vfnmadd213ss {{.*#+}} xmm0 = -(xmm2 * xmm0) + xmm3
; FMA-RECIP-NEXT:    retq
;
; BDVER2-LABEL: f32_one_step_variables:
; BDVER2:       # %bb.0:
; BDVER2-NEXT:    vrcpss %xmm1, %xmm1, %xmm2
; BDVER2-NEXT:    vmulss %xmm2, %xmm0, %xmm3
; BDVER2-NEXT:    vfmsubss {{.*#+}} xmm0 = (xmm1 * xmm3) - xmm0
; BDVER2-NEXT:    vfnmaddss {{.*#+}} xmm0 = -(xmm2 * xmm0) + xmm3
; BDVER2-NEXT:    retq
;
; BTVER2-LABEL: f32_one_step_variables:
; BTVER2:       # %bb.0:
; BTVER2-NEXT:    vrcpss %xmm1, %xmm1, %xmm2
; BTVER2-NEXT:    vmulss %xmm2, %xmm0, %xmm3
; BTVER2-NEXT:    vmulss %xmm3, %xmm1, %xmm1
; BTVER2-NEXT:    vsubss %xmm1, %xmm0, %xmm0
; BTVER2-NEXT:    vmulss %xmm0, %xmm2, %xmm0
; BTVER2-NEXT:    vaddss %xmm0, %xmm3, %xmm0
; BTVER2-NEXT:    retq
;
; SANDY-LABEL: f32_one_step_variables:
; SANDY:       # %bb.0:
; SANDY-NEXT:    vrcpss %xmm1, %xmm1, %xmm2
; SANDY-NEXT:    vmulss %xmm2, %xmm0, %xmm3
; SANDY-NEXT:    vmulss %xmm3, %xmm1, %xmm1
; SANDY-NEXT:    vsubss %xmm1, %xmm0, %xmm0
; SANDY-NEXT:    vmulss %xmm0, %xmm2, %xmm0
; SANDY-NEXT:    vaddss %xmm0, %xmm3, %xmm0
; SANDY-NEXT:    retq
;
; HASWELL-LABEL: f32_one_step_variables:
; HASWELL:       # %bb.0:
; HASWELL-NEXT:    vrcpss %xmm1, %xmm1, %xmm2
; HASWELL-NEXT:    vmulss %xmm2, %xmm0, %xmm3
; HASWELL-NEXT:    vfmsub231ss {{.*#+}} xmm0 = (xmm3 * xmm1) - xmm0
; HASWELL-NEXT:    vfnmadd213ss {{.*#+}} xmm0 = -(xmm2 * xmm0) + xmm3
; HASWELL-NEXT:    retq
;
; HASWELL-NO-FMA-LABEL: f32_one_step_variables:
; HASWELL-NO-FMA:       # %bb.0:
; HASWELL-NO-FMA-NEXT:    vrcpss %xmm1, %xmm1, %xmm2
; HASWELL-NO-FMA-NEXT:    vmulss %xmm2, %xmm0, %xmm3
; HASWELL-NO-FMA-NEXT:    vmulss %xmm3, %xmm1, %xmm1
; HASWELL-NO-FMA-NEXT:    vsubss %xmm1, %xmm0, %xmm0
; HASWELL-NO-FMA-NEXT:    vmulss %xmm0, %xmm2, %xmm0
; HASWELL-NO-FMA-NEXT:    vaddss %xmm0, %xmm3, %xmm0
; HASWELL-NO-FMA-NEXT:    retq
;
; AVX512-LABEL: f32_one_step_variables:
; AVX512:       # %bb.0:
; AVX512-NEXT:    vrcpss %xmm1, %xmm1, %xmm2
; AVX512-NEXT:    vmulss %xmm2, %xmm0, %xmm3
; AVX512-NEXT:    vfmsub231ss {{.*#+}} xmm0 = (xmm3 * xmm1) - xmm0
; AVX512-NEXT:    vfnmadd213ss {{.*#+}} xmm0 = -(xmm2 * xmm0) + xmm3
; AVX512-NEXT:    retq
  %div = fdiv fast float %x, %y
  ret float %div
}

define float @f32_two_step(float %x) #2 {
; SSE-LABEL: f32_two_step:
; SSE:       # %bb.0:
; SSE-NEXT:    rcpss %xmm0, %xmm2
; SSE-NEXT:    movaps %xmm0, %xmm3
; SSE-NEXT:    mulss %xmm2, %xmm3
; SSE-NEXT:    movss {{.*#+}} xmm1 = mem[0],zero,zero,zero
; SSE-NEXT:    movaps %xmm1, %xmm4
; SSE-NEXT:    subss %xmm3, %xmm4
; SSE-NEXT:    mulss %xmm2, %xmm4
; SSE-NEXT:    addss %xmm2, %xmm4
; SSE-NEXT:    mulss %xmm4, %xmm0
; SSE-NEXT:    subss %xmm0, %xmm1
; SSE-NEXT:    mulss %xmm4, %xmm1
; SSE-NEXT:    addss %xmm4, %xmm1
; SSE-NEXT:    movaps %xmm1, %xmm0
; SSE-NEXT:    retq
;
; AVX-RECIP-LABEL: f32_two_step:
; AVX-RECIP:       # %bb.0:
; AVX-RECIP-NEXT:    vrcpss %xmm0, %xmm0, %xmm1
; AVX-RECIP-NEXT:    vmulss %xmm1, %xmm0, %xmm2
; AVX-RECIP-NEXT:    vmovss {{.*#+}} xmm3 = mem[0],zero,zero,zero
; AVX-RECIP-NEXT:    vsubss %xmm2, %xmm3, %xmm2
; AVX-RECIP-NEXT:    vmulss %xmm2, %xmm1, %xmm2
; AVX-RECIP-NEXT:    vaddss %xmm2, %xmm1, %xmm1
; AVX-RECIP-NEXT:    vmulss %xmm1, %xmm0, %xmm0
; AVX-RECIP-NEXT:    vsubss %xmm0, %xmm3, %xmm0
; AVX-RECIP-NEXT:    vmulss %xmm0, %xmm1, %xmm0
; AVX-RECIP-NEXT:    vaddss %xmm0, %xmm1, %xmm0
; AVX-RECIP-NEXT:    retq
;
; FMA-RECIP-LABEL: f32_two_step:
; FMA-RECIP:       # %bb.0:
; FMA-RECIP-NEXT:    vrcpss %xmm0, %xmm0, %xmm1
; FMA-RECIP-NEXT:    vmovss {{.*#+}} xmm2 = mem[0],zero,zero,zero
; FMA-RECIP-NEXT:    vmovaps %xmm1, %xmm3
; FMA-RECIP-NEXT:    vfmsub213ss {{.*#+}} xmm3 = (xmm0 * xmm3) - xmm2
; FMA-RECIP-NEXT:    vfnmadd132ss {{.*#+}} xmm3 = -(xmm3 * xmm1) + xmm1
; FMA-RECIP-NEXT:    vfmsub213ss {{.*#+}} xmm0 = (xmm3 * xmm0) - xmm2
; FMA-RECIP-NEXT:    vfnmadd132ss {{.*#+}} xmm0 = -(xmm0 * xmm3) + xmm3
; FMA-RECIP-NEXT:    retq
;
; BDVER2-LABEL: f32_two_step:
; BDVER2:       # %bb.0:
; BDVER2-NEXT:    vrcpss %xmm0, %xmm0, %xmm1
; BDVER2-NEXT:    vmovss {{.*#+}} xmm2 = mem[0],zero,zero,zero
; BDVER2-NEXT:    vfmsubss {{.*#+}} xmm3 = (xmm0 * xmm1) - xmm2
; BDVER2-NEXT:    vfnmaddss {{.*#+}} xmm1 = -(xmm1 * xmm3) + xmm1
; BDVER2-NEXT:    vfmsubss {{.*#+}} xmm0 = (xmm0 * xmm1) - xmm2
; BDVER2-NEXT:    vfnmaddss {{.*#+}} xmm0 = -(xmm1 * xmm0) + xmm1
; BDVER2-NEXT:    retq
;
; BTVER2-LABEL: f32_two_step:
; BTVER2:       # %bb.0:
; BTVER2-NEXT:    vmovss {{.*#+}} xmm3 = mem[0],zero,zero,zero
; BTVER2-NEXT:    vrcpss %xmm0, %xmm0, %xmm1
; BTVER2-NEXT:    vmulss %xmm1, %xmm0, %xmm2
; BTVER2-NEXT:    vsubss %xmm2, %xmm3, %xmm2
; BTVER2-NEXT:    vmulss %xmm2, %xmm1, %xmm2
; BTVER2-NEXT:    vaddss %xmm2, %xmm1, %xmm1
; BTVER2-NEXT:    vmulss %xmm1, %xmm0, %xmm0
; BTVER2-NEXT:    vsubss %xmm0, %xmm3, %xmm0
; BTVER2-NEXT:    vmulss %xmm0, %xmm1, %xmm0
; BTVER2-NEXT:    vaddss %xmm0, %xmm1, %xmm0
; BTVER2-NEXT:    retq
;
; SANDY-LABEL: f32_two_step:
; SANDY:       # %bb.0:
; SANDY-NEXT:    vrcpss %xmm0, %xmm0, %xmm1
; SANDY-NEXT:    vmulss %xmm1, %xmm0, %xmm2
; SANDY-NEXT:    vmovss {{.*#+}} xmm3 = mem[0],zero,zero,zero
; SANDY-NEXT:    vsubss %xmm2, %xmm3, %xmm2
; SANDY-NEXT:    vmulss %xmm2, %xmm1, %xmm2
; SANDY-NEXT:    vaddss %xmm2, %xmm1, %xmm1
; SANDY-NEXT:    vmulss %xmm1, %xmm0, %xmm0
; SANDY-NEXT:    vsubss %xmm0, %xmm3, %xmm0
; SANDY-NEXT:    vmulss %xmm0, %xmm1, %xmm0
; SANDY-NEXT:    vaddss %xmm0, %xmm1, %xmm0
; SANDY-NEXT:    retq
;
; HASWELL-LABEL: f32_two_step:
; HASWELL:       # %bb.0:
; HASWELL-NEXT:    vrcpss %xmm0, %xmm0, %xmm1
; HASWELL-NEXT:    vmovss {{.*#+}} xmm2 = mem[0],zero,zero,zero
; HASWELL-NEXT:    vmovaps %xmm1, %xmm3
; HASWELL-NEXT:    vfmsub213ss {{.*#+}} xmm3 = (xmm0 * xmm3) - xmm2
; HASWELL-NEXT:    vfnmadd132ss {{.*#+}} xmm3 = -(xmm3 * xmm1) + xmm1
; HASWELL-NEXT:    vfmsub213ss {{.*#+}} xmm0 = (xmm3 * xmm0) - xmm2
; HASWELL-NEXT:    vfnmadd132ss {{.*#+}} xmm0 = -(xmm0 * xmm3) + xmm3
; HASWELL-NEXT:    retq
;
; HASWELL-NO-FMA-LABEL: f32_two_step:
; HASWELL-NO-FMA:       # %bb.0:
; HASWELL-NO-FMA-NEXT:    vrcpss %xmm0, %xmm0, %xmm1
; HASWELL-NO-FMA-NEXT:    vmulss %xmm1, %xmm0, %xmm2
; HASWELL-NO-FMA-NEXT:    vmovss {{.*#+}} xmm3 = mem[0],zero,zero,zero
; HASWELL-NO-FMA-NEXT:    vsubss %xmm2, %xmm3, %xmm2
; HASWELL-NO-FMA-NEXT:    vmulss %xmm2, %xmm1, %xmm2
; HASWELL-NO-FMA-NEXT:    vaddss %xmm2, %xmm1, %xmm1
; HASWELL-NO-FMA-NEXT:    vmulss %xmm1, %xmm0, %xmm0
; HASWELL-NO-FMA-NEXT:    vsubss %xmm0, %xmm3, %xmm0
; HASWELL-NO-FMA-NEXT:    vmulss %xmm0, %xmm1, %xmm0
; HASWELL-NO-FMA-NEXT:    vaddss %xmm0, %xmm1, %xmm0
; HASWELL-NO-FMA-NEXT:    retq
;
; AVX512-LABEL: f32_two_step:
; AVX512:       # %bb.0:
; AVX512-NEXT:    vrcpss %xmm0, %xmm0, %xmm1
; AVX512-NEXT:    vmovss {{.*#+}} xmm2 = mem[0],zero,zero,zero
; AVX512-NEXT:    vmovaps %xmm1, %xmm3
; AVX512-NEXT:    vfmsub213ss {{.*#+}} xmm3 = (xmm0 * xmm3) - xmm2
; AVX512-NEXT:    vfnmadd132ss {{.*#+}} xmm3 = -(xmm3 * xmm1) + xmm1
; AVX512-NEXT:    vfmsub213ss {{.*#+}} xmm0 = (xmm3 * xmm0) - xmm2
; AVX512-NEXT:    vfnmadd132ss {{.*#+}} xmm0 = -(xmm0 * xmm3) + xmm3
; AVX512-NEXT:    retq
  %div = fdiv fast float 1.0, %x
  ret float %div
}

define <4 x float> @v4f32_no_estimate(<4 x float> %x) #0 {
; SSE-LABEL: v4f32_no_estimate:
; SSE:       # %bb.0:
; SSE-NEXT:    movaps {{.*#+}} xmm1 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0]
; SSE-NEXT:    divps %xmm0, %xmm1
; SSE-NEXT:    movaps %xmm1, %xmm0
; SSE-NEXT:    retq
;
; AVX-RECIP-LABEL: v4f32_no_estimate:
; AVX-RECIP:       # %bb.0:
; AVX-RECIP-NEXT:    vmovaps {{.*#+}} xmm1 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0]
; AVX-RECIP-NEXT:    vdivps %xmm0, %xmm1, %xmm0
; AVX-RECIP-NEXT:    retq
;
; FMA-RECIP-LABEL: v4f32_no_estimate:
; FMA-RECIP:       # %bb.0:
; FMA-RECIP-NEXT:    vmovaps {{.*#+}} xmm1 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0]
; FMA-RECIP-NEXT:    vdivps %xmm0, %xmm1, %xmm0
; FMA-RECIP-NEXT:    retq
;
; BDVER2-LABEL: v4f32_no_estimate:
; BDVER2:       # %bb.0:
; BDVER2-NEXT:    vmovaps {{.*#+}} xmm1 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0]
; BDVER2-NEXT:    vdivps %xmm0, %xmm1, %xmm0
; BDVER2-NEXT:    retq
;
; BTVER2-LABEL: v4f32_no_estimate:
; BTVER2:       # %bb.0:
; BTVER2-NEXT:    vmovaps {{.*#+}} xmm1 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0]
; BTVER2-NEXT:    vdivps %xmm0, %xmm1, %xmm0
; BTVER2-NEXT:    retq
;
; SANDY-LABEL: v4f32_no_estimate:
; SANDY:       # %bb.0:
; SANDY-NEXT:    vmovaps {{.*#+}} xmm1 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0]
; SANDY-NEXT:    vdivps %xmm0, %xmm1, %xmm0
; SANDY-NEXT:    retq
;
; HASWELL-LABEL: v4f32_no_estimate:
; HASWELL:       # %bb.0:
; HASWELL-NEXT:    vbroadcastss {{.*#+}} xmm1 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0]
; HASWELL-NEXT:    vdivps %xmm0, %xmm1, %xmm0
; HASWELL-NEXT:    retq
;
; HASWELL-NO-FMA-LABEL: v4f32_no_estimate:
; HASWELL-NO-FMA:       # %bb.0:
; HASWELL-NO-FMA-NEXT:    vbroadcastss {{.*#+}} xmm1 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0]
; HASWELL-NO-FMA-NEXT:    vdivps %xmm0, %xmm1, %xmm0
; HASWELL-NO-FMA-NEXT:    retq
;
; AVX512-LABEL: v4f32_no_estimate:
; AVX512:       # %bb.0:
; AVX512-NEXT:    vbroadcastss {{.*#+}} xmm1 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0]
; AVX512-NEXT:    vdivps %xmm0, %xmm1, %xmm0
; AVX512-NEXT:    retq
  %div = fdiv fast <4 x float> <float 1.0, float 1.0, float 1.0, float 1.0>, %x
  ret <4 x float> %div
}

define <4 x float> @v4f32_one_step(<4 x float> %x) #1 {
; SSE-LABEL: v4f32_one_step:
; SSE:       # %bb.0:
; SSE-NEXT:    rcpps %xmm0, %xmm2
; SSE-NEXT:    mulps %xmm2, %xmm0
; SSE-NEXT:    movaps {{.*#+}} xmm1 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0]
; SSE-NEXT:    subps %xmm0, %xmm1
; SSE-NEXT:    mulps %xmm2, %xmm1
; SSE-NEXT:    addps %xmm2, %xmm1
; SSE-NEXT:    movaps %xmm1, %xmm0
; SSE-NEXT:    retq
;
; AVX-RECIP-LABEL: v4f32_one_step:
; AVX-RECIP:       # %bb.0:
; AVX-RECIP-NEXT:    vrcpps %xmm0, %xmm1
; AVX-RECIP-NEXT:    vmulps %xmm1, %xmm0, %xmm0
; AVX-RECIP-NEXT:    vmovaps {{.*#+}} xmm2 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0]
; AVX-RECIP-NEXT:    vsubps %xmm0, %xmm2, %xmm0
; AVX-RECIP-NEXT:    vmulps %xmm0, %xmm1, %xmm0
; AVX-RECIP-NEXT:    vaddps %xmm0, %xmm1, %xmm0
; AVX-RECIP-NEXT:    retq
;
; FMA-RECIP-LABEL: v4f32_one_step:
; FMA-RECIP:       # %bb.0:
; FMA-RECIP-NEXT:    vrcpps %xmm0, %xmm1
; FMA-RECIP-NEXT:    vfmsub213ps {{.*#+}} xmm0 = (xmm1 * xmm0) - mem
; FMA-RECIP-NEXT:    vfnmadd132ps {{.*#+}} xmm0 = -(xmm0 * xmm1) + xmm1
; FMA-RECIP-NEXT:    retq
;
; BDVER2-LABEL: v4f32_one_step:
; BDVER2:       # %bb.0:
; BDVER2-NEXT:    vrcpps %xmm0, %xmm1
; BDVER2-NEXT:    vfmsubps {{.*#+}} xmm0 = (xmm0 * xmm1) - mem
; BDVER2-NEXT:    vfnmaddps {{.*#+}} xmm0 = -(xmm1 * xmm0) + xmm1
; BDVER2-NEXT:    retq
;
; BTVER2-LABEL: v4f32_one_step:
; BTVER2:       # %bb.0:
; BTVER2-NEXT:    vmovaps {{.*#+}} xmm2 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0]
; BTVER2-NEXT:    vrcpps %xmm0, %xmm1
; BTVER2-NEXT:    vmulps %xmm1, %xmm0, %xmm0
; BTVER2-NEXT:    vsubps %xmm0, %xmm2, %xmm0
; BTVER2-NEXT:    vmulps %xmm0, %xmm1, %xmm0
; BTVER2-NEXT:    vaddps %xmm0, %xmm1, %xmm0
; BTVER2-NEXT:    retq
;
; SANDY-LABEL: v4f32_one_step:
; SANDY:       # %bb.0:
; SANDY-NEXT:    vrcpps %xmm0, %xmm1
; SANDY-NEXT:    vmulps %xmm1, %xmm0, %xmm0
; SANDY-NEXT:    vmovaps {{.*#+}} xmm2 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0]
; SANDY-NEXT:    vsubps %xmm0, %xmm2, %xmm0
; SANDY-NEXT:    vmulps %xmm0, %xmm1, %xmm0
; SANDY-NEXT:    vaddps %xmm0, %xmm1, %xmm0
; SANDY-NEXT:    retq
;
; HASWELL-LABEL: v4f32_one_step:
; HASWELL:       # %bb.0:
; HASWELL-NEXT:    vrcpps %xmm0, %xmm1
; HASWELL-NEXT:    vbroadcastss {{.*#+}} xmm2 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0]
; HASWELL-NEXT:    vfmsub213ps {{.*#+}} xmm0 = (xmm1 * xmm0) - xmm2
; HASWELL-NEXT:    vfnmadd132ps {{.*#+}} xmm0 = -(xmm0 * xmm1) + xmm1
; HASWELL-NEXT:    retq
;
; HASWELL-NO-FMA-LABEL: v4f32_one_step:
; HASWELL-NO-FMA:       # %bb.0:
; HASWELL-NO-FMA-NEXT:    vrcpps %xmm0, %xmm1
; HASWELL-NO-FMA-NEXT:    vmulps %xmm1, %xmm0, %xmm0
; HASWELL-NO-FMA-NEXT:    vbroadcastss {{.*#+}} xmm2 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0]
; HASWELL-NO-FMA-NEXT:    vsubps %xmm0, %xmm2, %xmm0
; HASWELL-NO-FMA-NEXT:    vmulps %xmm0, %xmm1, %xmm0
; HASWELL-NO-FMA-NEXT:    vaddps %xmm0, %xmm1, %xmm0
; HASWELL-NO-FMA-NEXT:    retq
;
; KNL-LABEL: v4f32_one_step:
; KNL:       # %bb.0:
; KNL-NEXT:    vrcpps %xmm0, %xmm1
; KNL-NEXT:    vbroadcastss {{.*#+}} xmm2 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0]
; KNL-NEXT:    vfmsub213ps {{.*#+}} xmm0 = (xmm1 * xmm0) - xmm2
; KNL-NEXT:    vfnmadd132ps {{.*#+}} xmm0 = -(xmm0 * xmm1) + xmm1
; KNL-NEXT:    retq
;
; SKX-LABEL: v4f32_one_step:
; SKX:       # %bb.0:
; SKX-NEXT:    vrcpps %xmm0, %xmm1
; SKX-NEXT:    vfmsub213ps {{.*#+}} xmm0 = (xmm1 * xmm0) - mem
; SKX-NEXT:    vfnmadd132ps {{.*#+}} xmm0 = -(xmm0 * xmm1) + xmm1
; SKX-NEXT:    retq
  %div = fdiv fast <4 x float> <float 1.0, float 1.0, float 1.0, float 1.0>, %x
  ret <4 x float> %div
}

define <4 x float> @v4f32_one_step_variables(<4 x float> %x, <4 x float> %y) #1 {
; SSE-LABEL: v4f32_one_step_variables:
; SSE:       # %bb.0:
; SSE-NEXT:    rcpps %xmm1, %xmm2
; SSE-NEXT:    movaps %xmm0, %xmm3
; SSE-NEXT:    mulps %xmm2, %xmm3
; SSE-NEXT:    mulps %xmm3, %xmm1
; SSE-NEXT:    subps %xmm1, %xmm0
; SSE-NEXT:    mulps %xmm2, %xmm0
; SSE-NEXT:    addps %xmm3, %xmm0
; SSE-NEXT:    retq
;
; AVX-RECIP-LABEL: v4f32_one_step_variables:
; AVX-RECIP:       # %bb.0:
; AVX-RECIP-NEXT:    vrcpps %xmm1, %xmm2
; AVX-RECIP-NEXT:    vmulps %xmm2, %xmm0, %xmm3
; AVX-RECIP-NEXT:    vmulps %xmm3, %xmm1, %xmm1
; AVX-RECIP-NEXT:    vsubps %xmm1, %xmm0, %xmm0
; AVX-RECIP-NEXT:    vmulps %xmm0, %xmm2, %xmm0
; AVX-RECIP-NEXT:    vaddps %xmm0, %xmm3, %xmm0
; AVX-RECIP-NEXT:    retq
;
; FMA-RECIP-LABEL: v4f32_one_step_variables:
; FMA-RECIP:       # %bb.0:
; FMA-RECIP-NEXT:    vrcpps %xmm1, %xmm2
; FMA-RECIP-NEXT:    vmulps %xmm2, %xmm0, %xmm3
; FMA-RECIP-NEXT:    vfmsub231ps {{.*#+}} xmm0 = (xmm3 * xmm1) - xmm0
; FMA-RECIP-NEXT:    vfnmadd213ps {{.*#+}} xmm0 = -(xmm2 * xmm0) + xmm3
; FMA-RECIP-NEXT:    retq
;
; BDVER2-LABEL: v4f32_one_step_variables:
; BDVER2:       # %bb.0:
; BDVER2-NEXT:    vrcpps %xmm1, %xmm2
; BDVER2-NEXT:    vmulps %xmm2, %xmm0, %xmm3
; BDVER2-NEXT:    vfmsubps {{.*#+}} xmm0 = (xmm1 * xmm3) - xmm0
; BDVER2-NEXT:    vfnmaddps {{.*#+}} xmm0 = -(xmm2 * xmm0) + xmm3
; BDVER2-NEXT:    retq
;
; BTVER2-LABEL: v4f32_one_step_variables:
; BTVER2:       # %bb.0:
; BTVER2-NEXT:    vrcpps %xmm1, %xmm2
; BTVER2-NEXT:    vmulps %xmm2, %xmm0, %xmm3
; BTVER2-NEXT:    vmulps %xmm3, %xmm1, %xmm1
; BTVER2-NEXT:    vsubps %xmm1, %xmm0, %xmm0
; BTVER2-NEXT:    vmulps %xmm0, %xmm2, %xmm0
; BTVER2-NEXT:    vaddps %xmm0, %xmm3, %xmm0
; BTVER2-NEXT:    retq
;
; SANDY-LABEL: v4f32_one_step_variables:
; SANDY:       # %bb.0:
; SANDY-NEXT:    vrcpps %xmm1, %xmm2
; SANDY-NEXT:    vmulps %xmm2, %xmm0, %xmm3
; SANDY-NEXT:    vmulps %xmm3, %xmm1, %xmm1
; SANDY-NEXT:    vsubps %xmm1, %xmm0, %xmm0
; SANDY-NEXT:    vmulps %xmm0, %xmm2, %xmm0
; SANDY-NEXT:    vaddps %xmm0, %xmm3, %xmm0
; SANDY-NEXT:    retq
;
; HASWELL-LABEL: v4f32_one_step_variables:
; HASWELL:       # %bb.0:
; HASWELL-NEXT:    vrcpps %xmm1, %xmm2
; HASWELL-NEXT:    vmulps %xmm2, %xmm0, %xmm3
; HASWELL-NEXT:    vfmsub231ps {{.*#+}} xmm0 = (xmm3 * xmm1) - xmm0
; HASWELL-NEXT:    vfnmadd213ps {{.*#+}} xmm0 = -(xmm2 * xmm0) + xmm3
; HASWELL-NEXT:    retq
;
; HASWELL-NO-FMA-LABEL: v4f32_one_step_variables:
; HASWELL-NO-FMA:       # %bb.0:
; HASWELL-NO-FMA-NEXT:    vrcpps %xmm1, %xmm2
; HASWELL-NO-FMA-NEXT:    vmulps %xmm2, %xmm0, %xmm3
; HASWELL-NO-FMA-NEXT:    vmulps %xmm3, %xmm1, %xmm1
; HASWELL-NO-FMA-NEXT:    vsubps %xmm1, %xmm0, %xmm0
; HASWELL-NO-FMA-NEXT:    vmulps %xmm0, %xmm2, %xmm0
; HASWELL-NO-FMA-NEXT:    vaddps %xmm0, %xmm3, %xmm0
; HASWELL-NO-FMA-NEXT:    retq
;
; AVX512-LABEL: v4f32_one_step_variables:
; AVX512:       # %bb.0:
; AVX512-NEXT:    vrcpps %xmm1, %xmm2
; AVX512-NEXT:    vmulps %xmm2, %xmm0, %xmm3
; AVX512-NEXT:    vfmsub231ps {{.*#+}} xmm0 = (xmm3 * xmm1) - xmm0
; AVX512-NEXT:    vfnmadd213ps {{.*#+}} xmm0 = -(xmm2 * xmm0) + xmm3
; AVX512-NEXT:    retq
  %div = fdiv fast <4 x float> %x, %y
  ret <4 x float> %div
}

define <4 x float> @v4f32_two_step(<4 x float> %x) #2 {
; SSE-LABEL: v4f32_two_step:
; SSE:       # %bb.0:
; SSE-NEXT:    rcpps %xmm0, %xmm2
; SSE-NEXT:    movaps %xmm0, %xmm3
; SSE-NEXT:    mulps %xmm2, %xmm3
; SSE-NEXT:    movaps {{.*#+}} xmm1 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0]
; SSE-NEXT:    movaps %xmm1, %xmm4
; SSE-NEXT:    subps %xmm3, %xmm4
; SSE-NEXT:    mulps %xmm2, %xmm4
; SSE-NEXT:    addps %xmm2, %xmm4
; SSE-NEXT:    mulps %xmm4, %xmm0
; SSE-NEXT:    subps %xmm0, %xmm1
; SSE-NEXT:    mulps %xmm4, %xmm1
; SSE-NEXT:    addps %xmm4, %xmm1
; SSE-NEXT:    movaps %xmm1, %xmm0
; SSE-NEXT:    retq
;
; AVX-RECIP-LABEL: v4f32_two_step:
; AVX-RECIP:       # %bb.0:
; AVX-RECIP-NEXT:    vrcpps %xmm0, %xmm1
; AVX-RECIP-NEXT:    vmulps %xmm1, %xmm0, %xmm2
; AVX-RECIP-NEXT:    vmovaps {{.*#+}} xmm3 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0]
; AVX-RECIP-NEXT:    vsubps %xmm2, %xmm3, %xmm2
; AVX-RECIP-NEXT:    vmulps %xmm2, %xmm1, %xmm2
; AVX-RECIP-NEXT:    vaddps %xmm2, %xmm1, %xmm1
; AVX-RECIP-NEXT:    vmulps %xmm1, %xmm0, %xmm0
; AVX-RECIP-NEXT:    vsubps %xmm0, %xmm3, %xmm0
; AVX-RECIP-NEXT:    vmulps %xmm0, %xmm1, %xmm0
; AVX-RECIP-NEXT:    vaddps %xmm0, %xmm1, %xmm0
; AVX-RECIP-NEXT:    retq
;
; FMA-RECIP-LABEL: v4f32_two_step:
; FMA-RECIP:       # %bb.0:
; FMA-RECIP-NEXT:    vrcpps %xmm0, %xmm1
; FMA-RECIP-NEXT:    vmovaps {{.*#+}} xmm2 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0]
; FMA-RECIP-NEXT:    vmovaps %xmm1, %xmm3
; FMA-RECIP-NEXT:    vfmsub213ps {{.*#+}} xmm3 = (xmm0 * xmm3) - xmm2
; FMA-RECIP-NEXT:    vfnmadd132ps {{.*#+}} xmm3 = -(xmm3 * xmm1) + xmm1
; FMA-RECIP-NEXT:    vfmsub213ps {{.*#+}} xmm0 = (xmm3 * xmm0) - xmm2
; FMA-RECIP-NEXT:    vfnmadd132ps {{.*#+}} xmm0 = -(xmm0 * xmm3) + xmm3
; FMA-RECIP-NEXT:    retq
;
; BDVER2-LABEL: v4f32_two_step:
; BDVER2:       # %bb.0:
; BDVER2-NEXT:    vrcpps %xmm0, %xmm1
; BDVER2-NEXT:    vmovaps {{.*#+}} xmm2 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0]
; BDVER2-NEXT:    vfmsubps {{.*#+}} xmm3 = (xmm0 * xmm1) - xmm2
; BDVER2-NEXT:    vfnmaddps {{.*#+}} xmm1 = -(xmm1 * xmm3) + xmm1
; BDVER2-NEXT:    vfmsubps {{.*#+}} xmm0 = (xmm0 * xmm1) - xmm2
; BDVER2-NEXT:    vfnmaddps {{.*#+}} xmm0 = -(xmm1 * xmm0) + xmm1
; BDVER2-NEXT:    retq
;
; BTVER2-LABEL: v4f32_two_step:
; BTVER2:       # %bb.0:
; BTVER2-NEXT:    vmovaps {{.*#+}} xmm3 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0]
; BTVER2-NEXT:    vrcpps %xmm0, %xmm1
; BTVER2-NEXT:    vmulps %xmm1, %xmm0, %xmm2
; BTVER2-NEXT:    vsubps %xmm2, %xmm3, %xmm2
; BTVER2-NEXT:    vmulps %xmm2, %xmm1, %xmm2
; BTVER2-NEXT:    vaddps %xmm2, %xmm1, %xmm1
; BTVER2-NEXT:    vmulps %xmm1, %xmm0, %xmm0
; BTVER2-NEXT:    vsubps %xmm0, %xmm3, %xmm0
; BTVER2-NEXT:    vmulps %xmm0, %xmm1, %xmm0
; BTVER2-NEXT:    vaddps %xmm0, %xmm1, %xmm0
; BTVER2-NEXT:    retq
;
; SANDY-LABEL: v4f32_two_step:
; SANDY:       # %bb.0:
; SANDY-NEXT:    vrcpps %xmm0, %xmm1
; SANDY-NEXT:    vmulps %xmm1, %xmm0, %xmm2
; SANDY-NEXT:    vmovaps {{.*#+}} xmm3 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0]
; SANDY-NEXT:    vsubps %xmm2, %xmm3, %xmm2
; SANDY-NEXT:    vmulps %xmm2, %xmm1, %xmm2
; SANDY-NEXT:    vaddps %xmm2, %xmm1, %xmm1
; SANDY-NEXT:    vmulps %xmm1, %xmm0, %xmm0
; SANDY-NEXT:    vsubps %xmm0, %xmm3, %xmm0
; SANDY-NEXT:    vmulps %xmm0, %xmm1, %xmm0
; SANDY-NEXT:    vaddps %xmm0, %xmm1, %xmm0
; SANDY-NEXT:    retq
;
; HASWELL-LABEL: v4f32_two_step:
; HASWELL:       # %bb.0:
; HASWELL-NEXT:    vrcpps %xmm0, %xmm1
; HASWELL-NEXT:    vbroadcastss {{.*#+}} xmm2 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0]
; HASWELL-NEXT:    vmovaps %xmm1, %xmm3
; HASWELL-NEXT:    vfmsub213ps {{.*#+}} xmm3 = (xmm0 * xmm3) - xmm2
; HASWELL-NEXT:    vfnmadd132ps {{.*#+}} xmm3 = -(xmm3 * xmm1) + xmm1
; HASWELL-NEXT:    vfmsub213ps {{.*#+}} xmm0 = (xmm3 * xmm0) - xmm2
; HASWELL-NEXT:    vfnmadd132ps {{.*#+}} xmm0 = -(xmm0 * xmm3) + xmm3
; HASWELL-NEXT:    retq
;
; HASWELL-NO-FMA-LABEL: v4f32_two_step:
; HASWELL-NO-FMA:       # %bb.0:
; HASWELL-NO-FMA-NEXT:    vrcpps %xmm0, %xmm1
; HASWELL-NO-FMA-NEXT:    vmulps %xmm1, %xmm0, %xmm2
; HASWELL-NO-FMA-NEXT:    vbroadcastss {{.*#+}} xmm3 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0]
; HASWELL-NO-FMA-NEXT:    vsubps %xmm2, %xmm3, %xmm2
; HASWELL-NO-FMA-NEXT:    vmulps %xmm2, %xmm1, %xmm2
; HASWELL-NO-FMA-NEXT:    vaddps %xmm2, %xmm1, %xmm1
; HASWELL-NO-FMA-NEXT:    vmulps %xmm1, %xmm0, %xmm0
; HASWELL-NO-FMA-NEXT:    vsubps %xmm0, %xmm3, %xmm0
; HASWELL-NO-FMA-NEXT:    vmulps %xmm0, %xmm1, %xmm0
; HASWELL-NO-FMA-NEXT:    vaddps %xmm0, %xmm1, %xmm0
; HASWELL-NO-FMA-NEXT:    retq
;
; AVX512-LABEL: v4f32_two_step:
; AVX512:       # %bb.0:
; AVX512-NEXT:    vrcpps %xmm0, %xmm1
; AVX512-NEXT:    vbroadcastss {{.*#+}} xmm2 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0]
; AVX512-NEXT:    vmovaps %xmm1, %xmm3
; AVX512-NEXT:    vfmsub213ps {{.*#+}} xmm3 = (xmm0 * xmm3) - xmm2
; AVX512-NEXT:    vfnmadd132ps {{.*#+}} xmm3 = -(xmm3 * xmm1) + xmm1
; AVX512-NEXT:    vfmsub213ps {{.*#+}} xmm0 = (xmm3 * xmm0) - xmm2
; AVX512-NEXT:    vfnmadd132ps {{.*#+}} xmm0 = -(xmm0 * xmm3) + xmm3
; AVX512-NEXT:    retq
  %div = fdiv fast <4 x float> <float 1.0, float 1.0, float 1.0, float 1.0>, %x
  ret <4 x float> %div
}

define <8 x float> @v8f32_no_estimate(<8 x float> %x) #0 {
; SSE-LABEL: v8f32_no_estimate:
; SSE:       # %bb.0:
; SSE-NEXT:    movaps {{.*#+}} xmm2 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0]
; SSE-NEXT:    movaps %xmm2, %xmm3
; SSE-NEXT:    divps %xmm0, %xmm3
; SSE-NEXT:    divps %xmm1, %xmm2
; SSE-NEXT:    movaps %xmm3, %xmm0
; SSE-NEXT:    movaps %xmm2, %xmm1
; SSE-NEXT:    retq
;
; AVX-RECIP-LABEL: v8f32_no_estimate:
; AVX-RECIP:       # %bb.0:
; AVX-RECIP-NEXT:    vmovaps {{.*#+}} ymm1 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0]
; AVX-RECIP-NEXT:    vdivps %ymm0, %ymm1, %ymm0
; AVX-RECIP-NEXT:    retq
;
; FMA-RECIP-LABEL: v8f32_no_estimate:
; FMA-RECIP:       # %bb.0:
; FMA-RECIP-NEXT:    vmovaps {{.*#+}} ymm1 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0]
; FMA-RECIP-NEXT:    vdivps %ymm0, %ymm1, %ymm0
; FMA-RECIP-NEXT:    retq
;
; BDVER2-LABEL: v8f32_no_estimate:
; BDVER2:       # %bb.0:
; BDVER2-NEXT:    vmovaps {{.*#+}} ymm1 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0]
; BDVER2-NEXT:    vdivps %ymm0, %ymm1, %ymm0
; BDVER2-NEXT:    retq
;
; BTVER2-LABEL: v8f32_no_estimate:
; BTVER2:       # %bb.0:
; BTVER2-NEXT:    vmovaps {{.*#+}} ymm1 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0]
; BTVER2-NEXT:    vdivps %ymm0, %ymm1, %ymm0
; BTVER2-NEXT:    retq
;
; SANDY-LABEL: v8f32_no_estimate:
; SANDY:       # %bb.0:
; SANDY-NEXT:    vmovaps {{.*#+}} ymm1 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0]
; SANDY-NEXT:    vdivps %ymm0, %ymm1, %ymm0
; SANDY-NEXT:    retq
;
; HASWELL-LABEL: v8f32_no_estimate:
; HASWELL:       # %bb.0:
; HASWELL-NEXT:    vbroadcastss {{.*#+}} ymm1 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0]
; HASWELL-NEXT:    vdivps %ymm0, %ymm1, %ymm0
; HASWELL-NEXT:    retq
;
; HASWELL-NO-FMA-LABEL: v8f32_no_estimate:
; HASWELL-NO-FMA:       # %bb.0:
; HASWELL-NO-FMA-NEXT:    vbroadcastss {{.*#+}} ymm1 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0]
; HASWELL-NO-FMA-NEXT:    vdivps %ymm0, %ymm1, %ymm0
; HASWELL-NO-FMA-NEXT:    retq
;
; AVX512-LABEL: v8f32_no_estimate:
; AVX512:       # %bb.0:
; AVX512-NEXT:    vbroadcastss {{.*#+}} ymm1 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0]
; AVX512-NEXT:    vdivps %ymm0, %ymm1, %ymm0
; AVX512-NEXT:    retq
  %div = fdiv fast <8 x float> <float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0>, %x
  ret <8 x float> %div
}

define <8 x float> @v8f32_one_step(<8 x float> %x) #1 {
; SSE-LABEL: v8f32_one_step:
; SSE:       # %bb.0:
; SSE-NEXT:    rcpps %xmm0, %xmm4
; SSE-NEXT:    mulps %xmm4, %xmm0
; SSE-NEXT:    movaps {{.*#+}} xmm2 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0]
; SSE-NEXT:    movaps %xmm2, %xmm3
; SSE-NEXT:    subps %xmm0, %xmm3
; SSE-NEXT:    mulps %xmm4, %xmm3
; SSE-NEXT:    addps %xmm4, %xmm3
; SSE-NEXT:    rcpps %xmm1, %xmm0
; SSE-NEXT:    mulps %xmm0, %xmm1
; SSE-NEXT:    subps %xmm1, %xmm2
; SSE-NEXT:    mulps %xmm0, %xmm2
; SSE-NEXT:    addps %xmm0, %xmm2
; SSE-NEXT:    movaps %xmm3, %xmm0
; SSE-NEXT:    movaps %xmm2, %xmm1
; SSE-NEXT:    retq
;
; AVX-RECIP-LABEL: v8f32_one_step:
; AVX-RECIP:       # %bb.0:
; AVX-RECIP-NEXT:    vrcpps %ymm0, %ymm1
; AVX-RECIP-NEXT:    vmulps %ymm1, %ymm0, %ymm0
; AVX-RECIP-NEXT:    vmovaps {{.*#+}} ymm2 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0]
; AVX-RECIP-NEXT:    vsubps %ymm0, %ymm2, %ymm0
; AVX-RECIP-NEXT:    vmulps %ymm0, %ymm1, %ymm0
; AVX-RECIP-NEXT:    vaddps %ymm0, %ymm1, %ymm0
; AVX-RECIP-NEXT:    retq
;
; FMA-RECIP-LABEL: v8f32_one_step:
; FMA-RECIP:       # %bb.0:
; FMA-RECIP-NEXT:    vrcpps %ymm0, %ymm1
; FMA-RECIP-NEXT:    vfmsub213ps {{.*#+}} ymm0 = (ymm1 * ymm0) - mem
; FMA-RECIP-NEXT:    vfnmadd132ps {{.*#+}} ymm0 = -(ymm0 * ymm1) + ymm1
; FMA-RECIP-NEXT:    retq
;
; BDVER2-LABEL: v8f32_one_step:
; BDVER2:       # %bb.0:
; BDVER2-NEXT:    vrcpps %ymm0, %ymm1
; BDVER2-NEXT:    vfmsubps {{.*#+}} ymm0 = (ymm0 * ymm1) - mem
; BDVER2-NEXT:    vfnmaddps {{.*#+}} ymm0 = -(ymm1 * ymm0) + ymm1
; BDVER2-NEXT:    retq
;
; BTVER2-LABEL: v8f32_one_step:
; BTVER2:       # %bb.0:
; BTVER2-NEXT:    vmovaps {{.*#+}} ymm2 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0]
; BTVER2-NEXT:    vrcpps %ymm0, %ymm1
; BTVER2-NEXT:    vmulps %ymm1, %ymm0, %ymm0
; BTVER2-NEXT:    vsubps %ymm0, %ymm2, %ymm0
; BTVER2-NEXT:    vmulps %ymm0, %ymm1, %ymm0
; BTVER2-NEXT:    vaddps %ymm0, %ymm1, %ymm0
; BTVER2-NEXT:    retq
;
; SANDY-LABEL: v8f32_one_step:
; SANDY:       # %bb.0:
; SANDY-NEXT:    vrcpps %ymm0, %ymm1
; SANDY-NEXT:    vmulps %ymm1, %ymm0, %ymm0
; SANDY-NEXT:    vmovaps {{.*#+}} ymm2 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0]
; SANDY-NEXT:    vsubps %ymm0, %ymm2, %ymm0
; SANDY-NEXT:    vmulps %ymm0, %ymm1, %ymm0
; SANDY-NEXT:    vaddps %ymm0, %ymm1, %ymm0
; SANDY-NEXT:    retq
;
; HASWELL-LABEL: v8f32_one_step:
; HASWELL:       # %bb.0:
; HASWELL-NEXT:    vrcpps %ymm0, %ymm1
; HASWELL-NEXT:    vbroadcastss {{.*#+}} ymm2 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0]
; HASWELL-NEXT:    vfmsub213ps {{.*#+}} ymm0 = (ymm1 * ymm0) - ymm2
; HASWELL-NEXT:    vfnmadd132ps {{.*#+}} ymm0 = -(ymm0 * ymm1) + ymm1
; HASWELL-NEXT:    retq
;
; HASWELL-NO-FMA-LABEL: v8f32_one_step:
; HASWELL-NO-FMA:       # %bb.0:
; HASWELL-NO-FMA-NEXT:    vrcpps %ymm0, %ymm1
; HASWELL-NO-FMA-NEXT:    vmulps %ymm1, %ymm0, %ymm0
; HASWELL-NO-FMA-NEXT:    vbroadcastss {{.*#+}} ymm2 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0]
; HASWELL-NO-FMA-NEXT:    vsubps %ymm0, %ymm2, %ymm0
; HASWELL-NO-FMA-NEXT:    vmulps %ymm0, %ymm1, %ymm0
; HASWELL-NO-FMA-NEXT:    vaddps %ymm0, %ymm1, %ymm0
; HASWELL-NO-FMA-NEXT:    retq
;
; KNL-LABEL: v8f32_one_step:
; KNL:       # %bb.0:
; KNL-NEXT:    vrcpps %ymm0, %ymm1
; KNL-NEXT:    vbroadcastss {{.*#+}} ymm2 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0]
; KNL-NEXT:    vfmsub213ps {{.*#+}} ymm0 = (ymm1 * ymm0) - ymm2
; KNL-NEXT:    vfnmadd132ps {{.*#+}} ymm0 = -(ymm0 * ymm1) + ymm1
; KNL-NEXT:    retq
;
; SKX-LABEL: v8f32_one_step:
; SKX:       # %bb.0:
; SKX-NEXT:    vrcpps %ymm0, %ymm1
; SKX-NEXT:    vfmsub213ps {{.*#+}} ymm0 = (ymm1 * ymm0) - mem
; SKX-NEXT:    vfnmadd132ps {{.*#+}} ymm0 = -(ymm0 * ymm1) + ymm1
; SKX-NEXT:    retq
  %div = fdiv fast <8 x float> <float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0>, %x
  ret <8 x float> %div
}

define <8 x float> @v8f32_two_step(<8 x float> %x) #2 {
; SSE-LABEL: v8f32_two_step:
; SSE:       # %bb.0:
; SSE-NEXT:    movaps %xmm1, %xmm2
; SSE-NEXT:    rcpps %xmm0, %xmm3
; SSE-NEXT:    movaps %xmm0, %xmm4
; SSE-NEXT:    mulps %xmm3, %xmm4
; SSE-NEXT:    movaps {{.*#+}} xmm1 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0]
; SSE-NEXT:    movaps %xmm1, %xmm5
; SSE-NEXT:    subps %xmm4, %xmm5
; SSE-NEXT:    mulps %xmm3, %xmm5
; SSE-NEXT:    addps %xmm3, %xmm5
; SSE-NEXT:    mulps %xmm5, %xmm0
; SSE-NEXT:    movaps %xmm1, %xmm3
; SSE-NEXT:    subps %xmm0, %xmm3
; SSE-NEXT:    mulps %xmm5, %xmm3
; SSE-NEXT:    addps %xmm5, %xmm3
; SSE-NEXT:    rcpps %xmm2, %xmm0
; SSE-NEXT:    movaps %xmm2, %xmm4
; SSE-NEXT:    mulps %xmm0, %xmm4
; SSE-NEXT:    movaps %xmm1, %xmm5
; SSE-NEXT:    subps %xmm4, %xmm5
; SSE-NEXT:    mulps %xmm0, %xmm5
; SSE-NEXT:    addps %xmm0, %xmm5
; SSE-NEXT:    mulps %xmm5, %xmm2
; SSE-NEXT:    subps %xmm2, %xmm1
; SSE-NEXT:    mulps %xmm5, %xmm1
; SSE-NEXT:    addps %xmm5, %xmm1
; SSE-NEXT:    movaps %xmm3, %xmm0
; SSE-NEXT:    retq
;
; AVX-RECIP-LABEL: v8f32_two_step:
; AVX-RECIP:       # %bb.0:
; AVX-RECIP-NEXT:    vrcpps %ymm0, %ymm1
; AVX-RECIP-NEXT:    vmulps %ymm1, %ymm0, %ymm2
; AVX-RECIP-NEXT:    vmovaps {{.*#+}} ymm3 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0]
; AVX-RECIP-NEXT:    vsubps %ymm2, %ymm3, %ymm2
; AVX-RECIP-NEXT:    vmulps %ymm2, %ymm1, %ymm2
; AVX-RECIP-NEXT:    vaddps %ymm2, %ymm1, %ymm1
; AVX-RECIP-NEXT:    vmulps %ymm1, %ymm0, %ymm0
; AVX-RECIP-NEXT:    vsubps %ymm0, %ymm3, %ymm0
; AVX-RECIP-NEXT:    vmulps %ymm0, %ymm1, %ymm0
; AVX-RECIP-NEXT:    vaddps %ymm0, %ymm1, %ymm0
; AVX-RECIP-NEXT:    retq
;
; FMA-RECIP-LABEL: v8f32_two_step:
; FMA-RECIP:       # %bb.0:
; FMA-RECIP-NEXT:    vrcpps %ymm0, %ymm1
; FMA-RECIP-NEXT:    vmovaps {{.*#+}} ymm2 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0]
; FMA-RECIP-NEXT:    vmovaps %ymm1, %ymm3
; FMA-RECIP-NEXT:    vfmsub213ps {{.*#+}} ymm3 = (ymm0 * ymm3) - ymm2
; FMA-RECIP-NEXT:    vfnmadd132ps {{.*#+}} ymm3 = -(ymm3 * ymm1) + ymm1
; FMA-RECIP-NEXT:    vfmsub213ps {{.*#+}} ymm0 = (ymm3 * ymm0) - ymm2
; FMA-RECIP-NEXT:    vfnmadd132ps {{.*#+}} ymm0 = -(ymm0 * ymm3) + ymm3
; FMA-RECIP-NEXT:    retq
;
; BDVER2-LABEL: v8f32_two_step:
; BDVER2:       # %bb.0:
; BDVER2-NEXT:    vrcpps %ymm0, %ymm1
; BDVER2-NEXT:    vmovaps {{.*#+}} ymm2 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0]
; BDVER2-NEXT:    vfmsubps {{.*#+}} ymm3 = (ymm0 * ymm1) - ymm2
; BDVER2-NEXT:    vfnmaddps {{.*#+}} ymm1 = -(ymm1 * ymm3) + ymm1
; BDVER2-NEXT:    vfmsubps {{.*#+}} ymm0 = (ymm0 * ymm1) - ymm2
; BDVER2-NEXT:    vfnmaddps {{.*#+}} ymm0 = -(ymm1 * ymm0) + ymm1
; BDVER2-NEXT:    retq
;
; BTVER2-LABEL: v8f32_two_step:
; BTVER2:       # %bb.0:
; BTVER2-NEXT:    vmovaps {{.*#+}} ymm3 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0]
; BTVER2-NEXT:    vrcpps %ymm0, %ymm1
; BTVER2-NEXT:    vmulps %ymm1, %ymm0, %ymm2
; BTVER2-NEXT:    vsubps %ymm2, %ymm3, %ymm2
; BTVER2-NEXT:    vmulps %ymm2, %ymm1, %ymm2
; BTVER2-NEXT:    vaddps %ymm2, %ymm1, %ymm1
; BTVER2-NEXT:    vmulps %ymm1, %ymm0, %ymm0
; BTVER2-NEXT:    vsubps %ymm0, %ymm3, %ymm0
; BTVER2-NEXT:    vmulps %ymm0, %ymm1, %ymm0
; BTVER2-NEXT:    vaddps %ymm0, %ymm1, %ymm0
; BTVER2-NEXT:    retq
;
; SANDY-LABEL: v8f32_two_step:
; SANDY:       # %bb.0:
; SANDY-NEXT:    vrcpps %ymm0, %ymm1
; SANDY-NEXT:    vmulps %ymm1, %ymm0, %ymm2
; SANDY-NEXT:    vmovaps {{.*#+}} ymm3 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0]
; SANDY-NEXT:    vsubps %ymm2, %ymm3, %ymm2
; SANDY-NEXT:    vmulps %ymm2, %ymm1, %ymm2
; SANDY-NEXT:    vaddps %ymm2, %ymm1, %ymm1
; SANDY-NEXT:    vmulps %ymm1, %ymm0, %ymm0
; SANDY-NEXT:    vsubps %ymm0, %ymm3, %ymm0
; SANDY-NEXT:    vmulps %ymm0, %ymm1, %ymm0
; SANDY-NEXT:    vaddps %ymm0, %ymm1, %ymm0
; SANDY-NEXT:    retq
;
; HASWELL-LABEL: v8f32_two_step:
; HASWELL:       # %bb.0:
; HASWELL-NEXT:    vrcpps %ymm0, %ymm1
; HASWELL-NEXT:    vbroadcastss {{.*#+}} ymm2 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0]
; HASWELL-NEXT:    vmovaps %ymm1, %ymm3
; HASWELL-NEXT:    vfmsub213ps {{.*#+}} ymm3 = (ymm0 * ymm3) - ymm2
; HASWELL-NEXT:    vfnmadd132ps {{.*#+}} ymm3 = -(ymm3 * ymm1) + ymm1
; HASWELL-NEXT:    vfmsub213ps {{.*#+}} ymm0 = (ymm3 * ymm0) - ymm2
; HASWELL-NEXT:    vfnmadd132ps {{.*#+}} ymm0 = -(ymm0 * ymm3) + ymm3
; HASWELL-NEXT:    retq
;
; HASWELL-NO-FMA-LABEL: v8f32_two_step:
; HASWELL-NO-FMA:       # %bb.0:
; HASWELL-NO-FMA-NEXT:    vrcpps %ymm0, %ymm1
; HASWELL-NO-FMA-NEXT:    vmulps %ymm1, %ymm0, %ymm2
; HASWELL-NO-FMA-NEXT:    vbroadcastss {{.*#+}} ymm3 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0]
; HASWELL-NO-FMA-NEXT:    vsubps %ymm2, %ymm3, %ymm2
; HASWELL-NO-FMA-NEXT:    vmulps %ymm2, %ymm1, %ymm2
; HASWELL-NO-FMA-NEXT:    vaddps %ymm2, %ymm1, %ymm1
; HASWELL-NO-FMA-NEXT:    vmulps %ymm1, %ymm0, %ymm0
; HASWELL-NO-FMA-NEXT:    vsubps %ymm0, %ymm3, %ymm0
; HASWELL-NO-FMA-NEXT:    vmulps %ymm0, %ymm1, %ymm0
; HASWELL-NO-FMA-NEXT:    vaddps %ymm0, %ymm1, %ymm0
; HASWELL-NO-FMA-NEXT:    retq
;
; AVX512-LABEL: v8f32_two_step:
; AVX512:       # %bb.0:
; AVX512-NEXT:    vrcpps %ymm0, %ymm1
; AVX512-NEXT:    vbroadcastss {{.*#+}} ymm2 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0]
; AVX512-NEXT:    vmovaps %ymm1, %ymm3
; AVX512-NEXT:    vfmsub213ps {{.*#+}} ymm3 = (ymm0 * ymm3) - ymm2
; AVX512-NEXT:    vfnmadd132ps {{.*#+}} ymm3 = -(ymm3 * ymm1) + ymm1
; AVX512-NEXT:    vfmsub213ps {{.*#+}} ymm0 = (ymm3 * ymm0) - ymm2
; AVX512-NEXT:    vfnmadd132ps {{.*#+}} ymm0 = -(ymm0 * ymm3) + ymm3
; AVX512-NEXT:    retq
  %div = fdiv fast <8 x float> <float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0>, %x
  ret <8 x float> %div
}

define <16 x float> @v16f32_no_estimate(<16 x float> %x) #0 {
; SSE-LABEL: v16f32_no_estimate:
; SSE:       # %bb.0:
; SSE-NEXT:    movaps {{.*#+}} xmm4 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0]
; SSE-NEXT:    movaps %xmm4, %xmm5
; SSE-NEXT:    divps %xmm0, %xmm5
; SSE-NEXT:    movaps %xmm4, %xmm6
; SSE-NEXT:    divps %xmm1, %xmm6
; SSE-NEXT:    movaps %xmm4, %xmm7
; SSE-NEXT:    divps %xmm2, %xmm7
; SSE-NEXT:    divps %xmm3, %xmm4
; SSE-NEXT:    movaps %xmm5, %xmm0
; SSE-NEXT:    movaps %xmm6, %xmm1
; SSE-NEXT:    movaps %xmm7, %xmm2
; SSE-NEXT:    movaps %xmm4, %xmm3
; SSE-NEXT:    retq
;
; AVX-RECIP-LABEL: v16f32_no_estimate:
; AVX-RECIP:       # %bb.0:
; AVX-RECIP-NEXT:    vmovaps {{.*#+}} ymm2 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0]
; AVX-RECIP-NEXT:    vdivps %ymm0, %ymm2, %ymm0
; AVX-RECIP-NEXT:    vdivps %ymm1, %ymm2, %ymm1
; AVX-RECIP-NEXT:    retq
;
; FMA-RECIP-LABEL: v16f32_no_estimate:
; FMA-RECIP:       # %bb.0:
; FMA-RECIP-NEXT:    vmovaps {{.*#+}} ymm2 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0]
; FMA-RECIP-NEXT:    vdivps %ymm0, %ymm2, %ymm0
; FMA-RECIP-NEXT:    vdivps %ymm1, %ymm2, %ymm1
; FMA-RECIP-NEXT:    retq
;
; BDVER2-LABEL: v16f32_no_estimate:
; BDVER2:       # %bb.0:
; BDVER2-NEXT:    vmovaps {{.*#+}} ymm2 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0]
; BDVER2-NEXT:    vdivps %ymm0, %ymm2, %ymm0
; BDVER2-NEXT:    vdivps %ymm1, %ymm2, %ymm1
; BDVER2-NEXT:    retq
;
; BTVER2-LABEL: v16f32_no_estimate:
; BTVER2:       # %bb.0:
; BTVER2-NEXT:    vmovaps {{.*#+}} ymm2 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0]
; BTVER2-NEXT:    vdivps %ymm0, %ymm2, %ymm0
; BTVER2-NEXT:    vdivps %ymm1, %ymm2, %ymm1
; BTVER2-NEXT:    retq
;
; SANDY-LABEL: v16f32_no_estimate:
; SANDY:       # %bb.0:
; SANDY-NEXT:    vmovaps {{.*#+}} ymm2 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0]
; SANDY-NEXT:    vdivps %ymm0, %ymm2, %ymm0
; SANDY-NEXT:    vdivps %ymm1, %ymm2, %ymm1
; SANDY-NEXT:    retq
;
; HASWELL-LABEL: v16f32_no_estimate:
; HASWELL:       # %bb.0:
; HASWELL-NEXT:    vbroadcastss {{.*#+}} ymm2 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0]
; HASWELL-NEXT:    vdivps %ymm0, %ymm2, %ymm0
; HASWELL-NEXT:    vdivps %ymm1, %ymm2, %ymm1
; HASWELL-NEXT:    retq
;
; HASWELL-NO-FMA-LABEL: v16f32_no_estimate:
; HASWELL-NO-FMA:       # %bb.0:
; HASWELL-NO-FMA-NEXT:    vbroadcastss {{.*#+}} ymm2 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0]
; HASWELL-NO-FMA-NEXT:    vdivps %ymm0, %ymm2, %ymm0
; HASWELL-NO-FMA-NEXT:    vdivps %ymm1, %ymm2, %ymm1
; HASWELL-NO-FMA-NEXT:    retq
;
; AVX512-LABEL: v16f32_no_estimate:
; AVX512:       # %bb.0:
; AVX512-NEXT:    vbroadcastss {{.*#+}} zmm1 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0]
; AVX512-NEXT:    vdivps %zmm0, %zmm1, %zmm0
; AVX512-NEXT:    retq
  %div = fdiv fast <16 x float> <float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0>, %x
  ret <16 x float> %div
}

define <16 x float> @v16f32_one_step(<16 x float> %x) #1 {
; SSE-LABEL: v16f32_one_step:
; SSE:       # %bb.0:
; SSE-NEXT:    movaps %xmm3, %xmm4
; SSE-NEXT:    movaps %xmm0, %xmm5
; SSE-NEXT:    rcpps %xmm0, %xmm6
; SSE-NEXT:    mulps %xmm6, %xmm5
; SSE-NEXT:    movaps {{.*#+}} xmm3 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0]
; SSE-NEXT:    movaps %xmm3, %xmm0
; SSE-NEXT:    subps %xmm5, %xmm0
; SSE-NEXT:    mulps %xmm6, %xmm0
; SSE-NEXT:    addps %xmm6, %xmm0
; SSE-NEXT:    rcpps %xmm1, %xmm6
; SSE-NEXT:    mulps %xmm6, %xmm1
; SSE-NEXT:    movaps %xmm3, %xmm5
; SSE-NEXT:    subps %xmm1, %xmm5
; SSE-NEXT:    mulps %xmm6, %xmm5
; SSE-NEXT:    addps %xmm6, %xmm5
; SSE-NEXT:    rcpps %xmm2, %xmm1
; SSE-NEXT:    mulps %xmm1, %xmm2
; SSE-NEXT:    movaps %xmm3, %xmm6
; SSE-NEXT:    subps %xmm2, %xmm6
; SSE-NEXT:    mulps %xmm1, %xmm6
; SSE-NEXT:    addps %xmm1, %xmm6
; SSE-NEXT:    rcpps %xmm4, %xmm1
; SSE-NEXT:    mulps %xmm1, %xmm4
; SSE-NEXT:    subps %xmm4, %xmm3
; SSE-NEXT:    mulps %xmm1, %xmm3
; SSE-NEXT:    addps %xmm1, %xmm3
; SSE-NEXT:    movaps %xmm5, %xmm1
; SSE-NEXT:    movaps %xmm6, %xmm2
; SSE-NEXT:    retq
;
; AVX-RECIP-LABEL: v16f32_one_step:
; AVX-RECIP:       # %bb.0:
; AVX-RECIP-NEXT:    vrcpps %ymm0, %ymm2
; AVX-RECIP-NEXT:    vmulps %ymm2, %ymm0, %ymm0
; AVX-RECIP-NEXT:    vmovaps {{.*#+}} ymm3 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0]
; AVX-RECIP-NEXT:    vsubps %ymm0, %ymm3, %ymm0
; AVX-RECIP-NEXT:    vmulps %ymm0, %ymm2, %ymm0
; AVX-RECIP-NEXT:    vaddps %ymm0, %ymm2, %ymm0
; AVX-RECIP-NEXT:    vrcpps %ymm1, %ymm2
; AVX-RECIP-NEXT:    vmulps %ymm2, %ymm1, %ymm1
; AVX-RECIP-NEXT:    vsubps %ymm1, %ymm3, %ymm1
; AVX-RECIP-NEXT:    vmulps %ymm1, %ymm2, %ymm1
; AVX-RECIP-NEXT:    vaddps %ymm1, %ymm2, %ymm1
; AVX-RECIP-NEXT:    retq
;
; FMA-RECIP-LABEL: v16f32_one_step:
; FMA-RECIP:       # %bb.0:
; FMA-RECIP-NEXT:    vrcpps %ymm0, %ymm2
; FMA-RECIP-NEXT:    vmovaps {{.*#+}} ymm3 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0]
; FMA-RECIP-NEXT:    vfmsub213ps {{.*#+}} ymm0 = (ymm2 * ymm0) - ymm3
; FMA-RECIP-NEXT:    vfnmadd132ps {{.*#+}} ymm0 = -(ymm0 * ymm2) + ymm2
; FMA-RECIP-NEXT:    vrcpps %ymm1, %ymm2
; FMA-RECIP-NEXT:    vfmsub213ps {{.*#+}} ymm1 = (ymm2 * ymm1) - ymm3
; FMA-RECIP-NEXT:    vfnmadd132ps {{.*#+}} ymm1 = -(ymm1 * ymm2) + ymm2
; FMA-RECIP-NEXT:    retq
;
; BDVER2-LABEL: v16f32_one_step:
; BDVER2:       # %bb.0:
; BDVER2-NEXT:    vrcpps %ymm0, %ymm2
; BDVER2-NEXT:    vmovaps {{.*#+}} ymm3 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0]
; BDVER2-NEXT:    vrcpps %ymm1, %ymm4
; BDVER2-NEXT:    vfmsubps {{.*#+}} ymm0 = (ymm0 * ymm2) - ymm3
; BDVER2-NEXT:    vfmsubps {{.*#+}} ymm1 = (ymm1 * ymm4) - ymm3
; BDVER2-NEXT:    vfnmaddps {{.*#+}} ymm0 = -(ymm2 * ymm0) + ymm2
; BDVER2-NEXT:    vfnmaddps {{.*#+}} ymm1 = -(ymm4 * ymm1) + ymm4
; BDVER2-NEXT:    retq
;
; BTVER2-LABEL: v16f32_one_step:
; BTVER2:       # %bb.0:
; BTVER2-NEXT:    vmovaps {{.*#+}} ymm3 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0]
; BTVER2-NEXT:    vrcpps %ymm0, %ymm2
; BTVER2-NEXT:    vrcpps %ymm1, %ymm4
; BTVER2-NEXT:    vmulps %ymm2, %ymm0, %ymm0
; BTVER2-NEXT:    vmulps %ymm4, %ymm1, %ymm1
; BTVER2-NEXT:    vsubps %ymm0, %ymm3, %ymm0
; BTVER2-NEXT:    vsubps %ymm1, %ymm3, %ymm1
; BTVER2-NEXT:    vmulps %ymm0, %ymm2, %ymm0
; BTVER2-NEXT:    vmulps %ymm1, %ymm4, %ymm1
; BTVER2-NEXT:    vaddps %ymm0, %ymm2, %ymm0
; BTVER2-NEXT:    vaddps %ymm1, %ymm4, %ymm1
; BTVER2-NEXT:    retq
;
; SANDY-LABEL: v16f32_one_step:
; SANDY:       # %bb.0:
; SANDY-NEXT:    vrcpps %ymm0, %ymm2
; SANDY-NEXT:    vmulps %ymm2, %ymm0, %ymm0
; SANDY-NEXT:    vmovaps {{.*#+}} ymm3 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0]
; SANDY-NEXT:    vsubps %ymm0, %ymm3, %ymm0
; SANDY-NEXT:    vrcpps %ymm1, %ymm4
; SANDY-NEXT:    vmulps %ymm0, %ymm2, %ymm0
; SANDY-NEXT:    vaddps %ymm0, %ymm2, %ymm0
; SANDY-NEXT:    vmulps %ymm4, %ymm1, %ymm1
; SANDY-NEXT:    vsubps %ymm1, %ymm3, %ymm1
; SANDY-NEXT:    vmulps %ymm1, %ymm4, %ymm1
; SANDY-NEXT:    vaddps %ymm1, %ymm4, %ymm1
; SANDY-NEXT:    retq
;
; HASWELL-LABEL: v16f32_one_step:
; HASWELL:       # %bb.0:
; HASWELL-NEXT:    vrcpps %ymm0, %ymm2
; HASWELL-NEXT:    vbroadcastss {{.*#+}} ymm3 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0]
; HASWELL-NEXT:    vrcpps %ymm1, %ymm4
; HASWELL-NEXT:    vfmsub213ps {{.*#+}} ymm0 = (ymm2 * ymm0) - ymm3
; HASWELL-NEXT:    vfnmadd132ps {{.*#+}} ymm0 = -(ymm0 * ymm2) + ymm2
; HASWELL-NEXT:    vfmsub213ps {{.*#+}} ymm1 = (ymm4 * ymm1) - ymm3
; HASWELL-NEXT:    vfnmadd132ps {{.*#+}} ymm1 = -(ymm1 * ymm4) + ymm4
; HASWELL-NEXT:    retq
;
; HASWELL-NO-FMA-LABEL: v16f32_one_step:
; HASWELL-NO-FMA:       # %bb.0:
; HASWELL-NO-FMA-NEXT:    vrcpps %ymm0, %ymm2
; HASWELL-NO-FMA-NEXT:    vmulps %ymm2, %ymm0, %ymm0
; HASWELL-NO-FMA-NEXT:    vbroadcastss {{.*#+}} ymm3 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0]
; HASWELL-NO-FMA-NEXT:    vsubps %ymm0, %ymm3, %ymm0
; HASWELL-NO-FMA-NEXT:    vmulps %ymm0, %ymm2, %ymm0
; HASWELL-NO-FMA-NEXT:    vaddps %ymm0, %ymm2, %ymm0
; HASWELL-NO-FMA-NEXT:    vrcpps %ymm1, %ymm2
; HASWELL-NO-FMA-NEXT:    vmulps %ymm2, %ymm1, %ymm1
; HASWELL-NO-FMA-NEXT:    vsubps %ymm1, %ymm3, %ymm1
; HASWELL-NO-FMA-NEXT:    vmulps %ymm1, %ymm2, %ymm1
; HASWELL-NO-FMA-NEXT:    vaddps %ymm1, %ymm2, %ymm1
; HASWELL-NO-FMA-NEXT:    retq
;
; AVX512-LABEL: v16f32_one_step:
; AVX512:       # %bb.0:
; AVX512-NEXT:    vrcp14ps %zmm0, %zmm1
; AVX512-NEXT:    vfmsub213ps {{.*#+}} zmm0 = (zmm1 * zmm0) - mem
; AVX512-NEXT:    vfnmadd132ps {{.*#+}} zmm0 = -(zmm0 * zmm1) + zmm1
; AVX512-NEXT:    retq
  %div = fdiv fast <16 x float> <float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0>, %x
  ret <16 x float> %div
}

define <16 x float> @v16f32_two_step(<16 x float> %x) #2 {
; SSE-LABEL: v16f32_two_step:
; SSE:       # %bb.0:
; SSE-NEXT:    movaps %xmm3, %xmm4
; SSE-NEXT:    movaps %xmm1, %xmm5
; SSE-NEXT:    movaps %xmm0, %xmm1
; SSE-NEXT:    rcpps %xmm0, %xmm0
; SSE-NEXT:    movaps %xmm1, %xmm6
; SSE-NEXT:    mulps %xmm0, %xmm6
; SSE-NEXT:    movaps {{.*#+}} xmm3 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0]
; SSE-NEXT:    movaps %xmm3, %xmm7
; SSE-NEXT:    subps %xmm6, %xmm7
; SSE-NEXT:    mulps %xmm0, %xmm7
; SSE-NEXT:    addps %xmm0, %xmm7
; SSE-NEXT:    mulps %xmm7, %xmm1
; SSE-NEXT:    movaps %xmm3, %xmm0
; SSE-NEXT:    subps %xmm1, %xmm0
; SSE-NEXT:    mulps %xmm7, %xmm0
; SSE-NEXT:    addps %xmm7, %xmm0
; SSE-NEXT:    rcpps %xmm5, %xmm1
; SSE-NEXT:    movaps %xmm5, %xmm6
; SSE-NEXT:    mulps %xmm1, %xmm6
; SSE-NEXT:    movaps %xmm3, %xmm7
; SSE-NEXT:    subps %xmm6, %xmm7
; SSE-NEXT:    mulps %xmm1, %xmm7
; SSE-NEXT:    addps %xmm1, %xmm7
; SSE-NEXT:    mulps %xmm7, %xmm5
; SSE-NEXT:    movaps %xmm3, %xmm1
; SSE-NEXT:    subps %xmm5, %xmm1
; SSE-NEXT:    mulps %xmm7, %xmm1
; SSE-NEXT:    addps %xmm7, %xmm1
; SSE-NEXT:    rcpps %xmm2, %xmm5
; SSE-NEXT:    movaps %xmm2, %xmm6
; SSE-NEXT:    mulps %xmm5, %xmm6
; SSE-NEXT:    movaps %xmm3, %xmm7
; SSE-NEXT:    subps %xmm6, %xmm7
; SSE-NEXT:    mulps %xmm5, %xmm7
; SSE-NEXT:    addps %xmm5, %xmm7
; SSE-NEXT:    mulps %xmm7, %xmm2
; SSE-NEXT:    movaps %xmm3, %xmm5
; SSE-NEXT:    subps %xmm2, %xmm5
; SSE-NEXT:    mulps %xmm7, %xmm5
; SSE-NEXT:    addps %xmm7, %xmm5
; SSE-NEXT:    rcpps %xmm4, %xmm2
; SSE-NEXT:    movaps %xmm4, %xmm6
; SSE-NEXT:    mulps %xmm2, %xmm6
; SSE-NEXT:    movaps %xmm3, %xmm7
; SSE-NEXT:    subps %xmm6, %xmm7
; SSE-NEXT:    mulps %xmm2, %xmm7
; SSE-NEXT:    addps %xmm2, %xmm7
; SSE-NEXT:    mulps %xmm7, %xmm4
; SSE-NEXT:    subps %xmm4, %xmm3
; SSE-NEXT:    mulps %xmm7, %xmm3
; SSE-NEXT:    addps %xmm7, %xmm3
; SSE-NEXT:    movaps %xmm5, %xmm2
; SSE-NEXT:    retq
;
; AVX-RECIP-LABEL: v16f32_two_step:
; AVX-RECIP:       # %bb.0:
; AVX-RECIP-NEXT:    vrcpps %ymm0, %ymm2
; AVX-RECIP-NEXT:    vmulps %ymm2, %ymm0, %ymm3
; AVX-RECIP-NEXT:    vmovaps {{.*#+}} ymm4 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0]
; AVX-RECIP-NEXT:    vsubps %ymm3, %ymm4, %ymm3
; AVX-RECIP-NEXT:    vmulps %ymm3, %ymm2, %ymm3
; AVX-RECIP-NEXT:    vaddps %ymm3, %ymm2, %ymm2
; AVX-RECIP-NEXT:    vmulps %ymm2, %ymm0, %ymm0
; AVX-RECIP-NEXT:    vsubps %ymm0, %ymm4, %ymm0
; AVX-RECIP-NEXT:    vmulps %ymm0, %ymm2, %ymm0
; AVX-RECIP-NEXT:    vaddps %ymm0, %ymm2, %ymm0
; AVX-RECIP-NEXT:    vrcpps %ymm1, %ymm2
; AVX-RECIP-NEXT:    vmulps %ymm2, %ymm1, %ymm3
; AVX-RECIP-NEXT:    vsubps %ymm3, %ymm4, %ymm3
; AVX-RECIP-NEXT:    vmulps %ymm3, %ymm2, %ymm3
; AVX-RECIP-NEXT:    vaddps %ymm3, %ymm2, %ymm2
; AVX-RECIP-NEXT:    vmulps %ymm2, %ymm1, %ymm1
; AVX-RECIP-NEXT:    vsubps %ymm1, %ymm4, %ymm1
; AVX-RECIP-NEXT:    vmulps %ymm1, %ymm2, %ymm1
; AVX-RECIP-NEXT:    vaddps %ymm1, %ymm2, %ymm1
; AVX-RECIP-NEXT:    retq
;
; FMA-RECIP-LABEL: v16f32_two_step:
; FMA-RECIP:       # %bb.0:
; FMA-RECIP-NEXT:    vrcpps %ymm0, %ymm2
; FMA-RECIP-NEXT:    vmovaps {{.*#+}} ymm3 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0]
; FMA-RECIP-NEXT:    vmovaps %ymm2, %ymm4
; FMA-RECIP-NEXT:    vfmsub213ps {{.*#+}} ymm4 = (ymm0 * ymm4) - ymm3
; FMA-RECIP-NEXT:    vfnmadd132ps {{.*#+}} ymm4 = -(ymm4 * ymm2) + ymm2
; FMA-RECIP-NEXT:    vfmsub213ps {{.*#+}} ymm0 = (ymm4 * ymm0) - ymm3
; FMA-RECIP-NEXT:    vfnmadd132ps {{.*#+}} ymm0 = -(ymm0 * ymm4) + ymm4
; FMA-RECIP-NEXT:    vrcpps %ymm1, %ymm2
; FMA-RECIP-NEXT:    vmovaps %ymm2, %ymm4
; FMA-RECIP-NEXT:    vfmsub213ps {{.*#+}} ymm4 = (ymm1 * ymm4) - ymm3
; FMA-RECIP-NEXT:    vfnmadd132ps {{.*#+}} ymm4 = -(ymm4 * ymm2) + ymm2
; FMA-RECIP-NEXT:    vfmsub213ps {{.*#+}} ymm1 = (ymm4 * ymm1) - ymm3
; FMA-RECIP-NEXT:    vfnmadd132ps {{.*#+}} ymm1 = -(ymm1 * ymm4) + ymm4
; FMA-RECIP-NEXT:    retq
;
; BDVER2-LABEL: v16f32_two_step:
; BDVER2:       # %bb.0:
; BDVER2-NEXT:    vrcpps %ymm0, %ymm2
; BDVER2-NEXT:    vmovaps {{.*#+}} ymm3 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0]
; BDVER2-NEXT:    vfmsubps {{.*#+}} ymm4 = (ymm0 * ymm2) - ymm3
; BDVER2-NEXT:    vfnmaddps {{.*#+}} ymm2 = -(ymm2 * ymm4) + ymm2
; BDVER2-NEXT:    vfmsubps {{.*#+}} ymm0 = (ymm0 * ymm2) - ymm3
; BDVER2-NEXT:    vfnmaddps {{.*#+}} ymm0 = -(ymm2 * ymm0) + ymm2
; BDVER2-NEXT:    vrcpps %ymm1, %ymm2
; BDVER2-NEXT:    vfmsubps {{.*#+}} ymm4 = (ymm1 * ymm2) - ymm3
; BDVER2-NEXT:    vfnmaddps {{.*#+}} ymm2 = -(ymm2 * ymm4) + ymm2
; BDVER2-NEXT:    vfmsubps {{.*#+}} ymm1 = (ymm1 * ymm2) - ymm3
; BDVER2-NEXT:    vfnmaddps {{.*#+}} ymm1 = -(ymm2 * ymm1) + ymm2
; BDVER2-NEXT:    retq
;
; BTVER2-LABEL: v16f32_two_step:
; BTVER2:       # %bb.0:
; BTVER2-NEXT:    vmovaps {{.*#+}} ymm4 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0]
; BTVER2-NEXT:    vrcpps %ymm0, %ymm2
; BTVER2-NEXT:    vmulps %ymm2, %ymm0, %ymm3
; BTVER2-NEXT:    vsubps %ymm3, %ymm4, %ymm3
; BTVER2-NEXT:    vmulps %ymm3, %ymm2, %ymm3
; BTVER2-NEXT:    vaddps %ymm3, %ymm2, %ymm2
; BTVER2-NEXT:    vmulps %ymm2, %ymm0, %ymm0
; BTVER2-NEXT:    vsubps %ymm0, %ymm4, %ymm0
; BTVER2-NEXT:    vmulps %ymm0, %ymm2, %ymm0
; BTVER2-NEXT:    vaddps %ymm0, %ymm2, %ymm0
; BTVER2-NEXT:    vrcpps %ymm1, %ymm2
; BTVER2-NEXT:    vmulps %ymm2, %ymm1, %ymm3
; BTVER2-NEXT:    vsubps %ymm3, %ymm4, %ymm3
; BTVER2-NEXT:    vmulps %ymm3, %ymm2, %ymm3
; BTVER2-NEXT:    vaddps %ymm3, %ymm2, %ymm2
; BTVER2-NEXT:    vmulps %ymm2, %ymm1, %ymm1
; BTVER2-NEXT:    vsubps %ymm1, %ymm4, %ymm1
; BTVER2-NEXT:    vmulps %ymm1, %ymm2, %ymm1
; BTVER2-NEXT:    vaddps %ymm1, %ymm2, %ymm1
; BTVER2-NEXT:    retq
;
; SANDY-LABEL: v16f32_two_step:
; SANDY:       # %bb.0:
; SANDY-NEXT:    vrcpps %ymm0, %ymm2
; SANDY-NEXT:    vmulps %ymm2, %ymm0, %ymm3
; SANDY-NEXT:    vmovaps {{.*#+}} ymm4 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0]
; SANDY-NEXT:    vsubps %ymm3, %ymm4, %ymm3
; SANDY-NEXT:    vmulps %ymm3, %ymm2, %ymm3
; SANDY-NEXT:    vaddps %ymm3, %ymm2, %ymm2
; SANDY-NEXT:    vmulps %ymm2, %ymm0, %ymm0
; SANDY-NEXT:    vsubps %ymm0, %ymm4, %ymm0
; SANDY-NEXT:    vrcpps %ymm1, %ymm3
; SANDY-NEXT:    vmulps %ymm0, %ymm2, %ymm0
; SANDY-NEXT:    vaddps %ymm0, %ymm2, %ymm0
; SANDY-NEXT:    vmulps %ymm3, %ymm1, %ymm2
; SANDY-NEXT:    vsubps %ymm2, %ymm4, %ymm2
; SANDY-NEXT:    vmulps %ymm2, %ymm3, %ymm2
; SANDY-NEXT:    vaddps %ymm2, %ymm3, %ymm2
; SANDY-NEXT:    vmulps %ymm2, %ymm1, %ymm1
; SANDY-NEXT:    vsubps %ymm1, %ymm4, %ymm1
; SANDY-NEXT:    vmulps %ymm1, %ymm2, %ymm1
; SANDY-NEXT:    vaddps %ymm1, %ymm2, %ymm1
; SANDY-NEXT:    retq
;
; HASWELL-LABEL: v16f32_two_step:
; HASWELL:       # %bb.0:
; HASWELL-NEXT:    vrcpps %ymm0, %ymm2
; HASWELL-NEXT:    vbroadcastss {{.*#+}} ymm3 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0]
; HASWELL-NEXT:    vmovaps %ymm2, %ymm4
; HASWELL-NEXT:    vfmsub213ps {{.*#+}} ymm4 = (ymm0 * ymm4) - ymm3
; HASWELL-NEXT:    vfnmadd132ps {{.*#+}} ymm4 = -(ymm4 * ymm2) + ymm2
; HASWELL-NEXT:    vfmsub213ps {{.*#+}} ymm0 = (ymm4 * ymm0) - ymm3
; HASWELL-NEXT:    vfnmadd132ps {{.*#+}} ymm0 = -(ymm0 * ymm4) + ymm4
; HASWELL-NEXT:    vrcpps %ymm1, %ymm2
; HASWELL-NEXT:    vmovaps %ymm2, %ymm4
; HASWELL-NEXT:    vfmsub213ps {{.*#+}} ymm4 = (ymm1 * ymm4) - ymm3
; HASWELL-NEXT:    vfnmadd132ps {{.*#+}} ymm4 = -(ymm4 * ymm2) + ymm2
; HASWELL-NEXT:    vfmsub213ps {{.*#+}} ymm1 = (ymm4 * ymm1) - ymm3
; HASWELL-NEXT:    vfnmadd132ps {{.*#+}} ymm1 = -(ymm1 * ymm4) + ymm4
; HASWELL-NEXT:    retq
;
; HASWELL-NO-FMA-LABEL: v16f32_two_step:
; HASWELL-NO-FMA:       # %bb.0:
; HASWELL-NO-FMA-NEXT:    vrcpps %ymm0, %ymm2
; HASWELL-NO-FMA-NEXT:    vmulps %ymm2, %ymm0, %ymm3
; HASWELL-NO-FMA-NEXT:    vbroadcastss {{.*#+}} ymm4 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0]
; HASWELL-NO-FMA-NEXT:    vsubps %ymm3, %ymm4, %ymm3
; HASWELL-NO-FMA-NEXT:    vmulps %ymm3, %ymm2, %ymm3
; HASWELL-NO-FMA-NEXT:    vaddps %ymm3, %ymm2, %ymm2
; HASWELL-NO-FMA-NEXT:    vmulps %ymm2, %ymm0, %ymm0
; HASWELL-NO-FMA-NEXT:    vsubps %ymm0, %ymm4, %ymm0
; HASWELL-NO-FMA-NEXT:    vmulps %ymm0, %ymm2, %ymm0
; HASWELL-NO-FMA-NEXT:    vaddps %ymm0, %ymm2, %ymm0
; HASWELL-NO-FMA-NEXT:    vrcpps %ymm1, %ymm2
; HASWELL-NO-FMA-NEXT:    vmulps %ymm2, %ymm1, %ymm3
; HASWELL-NO-FMA-NEXT:    vsubps %ymm3, %ymm4, %ymm3
; HASWELL-NO-FMA-NEXT:    vmulps %ymm3, %ymm2, %ymm3
; HASWELL-NO-FMA-NEXT:    vaddps %ymm3, %ymm2, %ymm2
; HASWELL-NO-FMA-NEXT:    vmulps %ymm2, %ymm1, %ymm1
; HASWELL-NO-FMA-NEXT:    vsubps %ymm1, %ymm4, %ymm1
; HASWELL-NO-FMA-NEXT:    vmulps %ymm1, %ymm2, %ymm1
; HASWELL-NO-FMA-NEXT:    vaddps %ymm1, %ymm2, %ymm1
; HASWELL-NO-FMA-NEXT:    retq
;
; AVX512-LABEL: v16f32_two_step:
; AVX512:       # %bb.0:
; AVX512-NEXT:    vrcp14ps %zmm0, %zmm1
; AVX512-NEXT:    vbroadcastss {{.*#+}} zmm2 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0]
; AVX512-NEXT:    vmovaps %zmm1, %zmm3
; AVX512-NEXT:    vfmsub213ps {{.*#+}} zmm3 = (zmm0 * zmm3) - zmm2
; AVX512-NEXT:    vfnmadd132ps {{.*#+}} zmm3 = -(zmm3 * zmm1) + zmm1
; AVX512-NEXT:    vfmsub213ps {{.*#+}} zmm0 = (zmm3 * zmm0) - zmm2
; AVX512-NEXT:    vfnmadd132ps {{.*#+}} zmm0 = -(zmm0 * zmm3) + zmm3
; AVX512-NEXT:    retq
  %div = fdiv fast <16 x float> <float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0>, %x
  ret <16 x float> %div
}

attributes #0 = { "unsafe-fp-math"="true" "reciprocal-estimates"="!divf,!vec-divf" }
attributes #1 = { "unsafe-fp-math"="true" "reciprocal-estimates"="divf,vec-divf" }
attributes #2 = { "unsafe-fp-math"="true" "reciprocal-estimates"="divf:2,vec-divf:2" }