reference, declarationdefinition
definition → references, declarations, derived classes, virtual overrides
reference to multiple definitions → definitions
unreferenced
    1
    2
    3
    4
    5
    6
    7
    8
    9
   10
   11
   12
   13
   14
   15
   16
   17
   18
   19
   20
   21
   22
   23
   24
   25
   26
   27
   28
   29
   30
   31
   32
   33
   34
   35
   36
   37
   38
   39
   40
   41
   42
   43
   44
   45
   46
   47
   48
   49
   50
   51
   52
   53
   54
   55
   56
   57
   58
   59
   60
   61
   62
   63
   64
   65
   66
   67
   68
   69
   70
   71
   72
   73
   74
   75
   76
   77
   78
   79
   80
   81
   82
   83
   84
   85
   86
   87
   88
   89
   90
   91
   92
   93
   94
   95
   96
   97
   98
   99
  100
  101
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=x86_64-apple-darwin -mcpu=knl | FileCheck %s

declare <4 x float> @llvm.x86.avx512.mask.vfmadd.ss(<4 x float>, <4 x float>, <4 x float>, i8, i32)
declare <4 x float> @llvm.x86.avx512.maskz.vfmadd.ss(<4 x float>, <4 x float>, <4 x float>, i8, i32)

define <4 x float>@test_var_mask(<4 x float> %v0, <4 x float> %v1, <4 x float> %v2, i8 %mask) {
; CHECK-LABEL: test_var_mask:
; CHECK:       ## %bb.0:
; CHECK-NEXT:    kmovw %edi, %k1
; CHECK-NEXT:    vfmadd213ss {{.*#+}} xmm0 = (xmm1 * xmm0) + xmm2
; CHECK-NEXT:    retq
  %res = call <4 x float> @llvm.x86.avx512.mask.vfmadd.ss(<4 x float> %v0,<4 x float> %v1, <4 x float> %v2,  i8 %mask, i32 4)
  ret < 4 x float> %res
}

define <4 x float>@test_var_maskz(<4 x float> %v0, <4 x float> %v1, <4 x float> %v2, i8 %mask) {
; CHECK-LABEL: test_var_maskz:
; CHECK:       ## %bb.0:
; CHECK-NEXT:    kmovw %edi, %k1
; CHECK-NEXT:    vfmadd213ss {{.*#+}} xmm0 = (xmm1 * xmm0) + xmm2
; CHECK-NEXT:    retq
  %res = call <4 x float> @llvm.x86.avx512.maskz.vfmadd.ss(<4 x float> %v0,<4 x float> %v1, <4 x float> %v2,  i8 %mask, i32 4)
  ret < 4 x float> %res
}

; FIXME: we should just return %xmm0 here.
define <4 x float>@test_const0_mask(<4 x float> %v0, <4 x float> %v1, <4 x float> %v2) {
; CHECK-LABEL: test_const0_mask:
; CHECK:       ## %bb.0:
; CHECK-NEXT:    retq
  %res = call <4 x float> @llvm.x86.avx512.mask.vfmadd.ss(<4 x float> %v0,<4 x float> %v1, <4 x float> %v2,  i8 0, i32 4)
  ret < 4 x float> %res
}

; FIXME: we should zero the lower element of xmm0 and return it.
define <4 x float>@test_const0_maskz(<4 x float> %v0, <4 x float> %v1, <4 x float> %v2) {
; CHECK-LABEL: test_const0_maskz:
; CHECK:       ## %bb.0:
; CHECK-NEXT:    vxorps %xmm1, %xmm1, %xmm1
; CHECK-NEXT:    vblendps {{.*#+}} xmm0 = xmm1[0],xmm0[1,2,3]
; CHECK-NEXT:    retq
  %res = call <4 x float> @llvm.x86.avx512.maskz.vfmadd.ss(<4 x float> %v0,<4 x float> %v1, <4 x float> %v2,  i8 0, i32 4)
  ret < 4 x float> %res
}

; FIXME: we should just return %xmm0 here.
define <4 x float>@test_const2_mask(<4 x float> %v0, <4 x float> %v1, <4 x float> %v2) {
; CHECK-LABEL: test_const2_mask:
; CHECK:       ## %bb.0:
; CHECK-NEXT:    retq
  %res = call <4 x float> @llvm.x86.avx512.mask.vfmadd.ss(<4 x float> %v0,<4 x float> %v1, <4 x float> %v2,  i8 2, i32 4)
  ret < 4 x float> %res
}

; FIXME: we should zero the lower element of xmm0 and return it.
define <4 x float>@test_const2_maskz(<4 x float> %v0, <4 x float> %v1, <4 x float> %v2) {
; CHECK-LABEL: test_const2_maskz:
; CHECK:       ## %bb.0:
; CHECK-NEXT:    vxorps %xmm1, %xmm1, %xmm1
; CHECK-NEXT:    vblendps {{.*#+}} xmm0 = xmm1[0],xmm0[1,2,3]
; CHECK-NEXT:    retq
  %res = call <4 x float> @llvm.x86.avx512.maskz.vfmadd.ss(<4 x float> %v0,<4 x float> %v1, <4 x float> %v2,  i8 2, i32 4)
  ret < 4 x float> %res
}

define <4 x float>@test_const_allone_mask(<4 x float> %v0, <4 x float> %v1, <4 x float> %v2) {
; CHECK-LABEL: test_const_allone_mask:
; CHECK:       ## %bb.0:
; CHECK-NEXT:    vfmadd213ss {{.*#+}} xmm0 = (xmm1 * xmm0) + xmm2
; CHECK-NEXT:    retq
  %res = call <4 x float> @llvm.x86.avx512.mask.vfmadd.ss(<4 x float> %v0,<4 x float> %v1, <4 x float> %v2,  i8 -1, i32 4)
  ret < 4 x float> %res
}

define <4 x float>@test_const_allone_maskz(<4 x float> %v0, <4 x float> %v1, <4 x float> %v2) {
; CHECK-LABEL: test_const_allone_maskz:
; CHECK:       ## %bb.0:
; CHECK-NEXT:    vfmadd213ss {{.*#+}} xmm0 = (xmm1 * xmm0) + xmm2
; CHECK-NEXT:    retq
  %res = call <4 x float> @llvm.x86.avx512.maskz.vfmadd.ss(<4 x float> %v0,<4 x float> %v1, <4 x float> %v2,  i8 -1, i32 4)
  ret < 4 x float> %res
}

define <4 x float>@test_const_3_mask(<4 x float> %v0, <4 x float> %v1, <4 x float> %v2) {
; CHECK-LABEL: test_const_3_mask:
; CHECK:       ## %bb.0:
; CHECK-NEXT:    vfmadd213ss {{.*#+}} xmm0 = (xmm1 * xmm0) + xmm2
; CHECK-NEXT:    retq
  %res = call <4 x float> @llvm.x86.avx512.mask.vfmadd.ss(<4 x float> %v0,<4 x float> %v1, <4 x float> %v2,  i8 3, i32 4)
  ret < 4 x float> %res
}

define <4 x float>@test_const_3_maskz(<4 x float> %v0, <4 x float> %v1, <4 x float> %v2) {
; CHECK-LABEL: test_const_3_maskz:
; CHECK:       ## %bb.0:
; CHECK-NEXT:    vfmadd213ss {{.*#+}} xmm0 = (xmm1 * xmm0) + xmm2
; CHECK-NEXT:    retq
  %res = call <4 x float> @llvm.x86.avx512.maskz.vfmadd.ss(<4 x float> %v0,<4 x float> %v1, <4 x float> %v2,  i8 3, i32 4)
  ret < 4 x float> %res
}