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
  102
  103
  104
  105
  106
  107
  108
  109
  110
  111
  112
  113
  114
  115
  116
  117
  118
  119
  120
  121
  122
  123
  124
  125
  126
  127
  128
  129
  130
  131
  132
  133
  134
  135
  136
  137
  138
  139
  140
  141
  142
  143
  144
  145
  146
  147
  148
  149
  150
  151
  152
  153
  154
  155
  156
  157
  158
  159
  160
  161
  162
  163
  164
  165
  166
  167
  168
  169
  170
  171
  172
  173
  174
  175
  176
  177
  178
  179
  180
  181
  182
  183
  184
  185
  186
  187
; RUN: opt -vector-library=SVML -loop-vectorize -S < %s | FileCheck %s

; Test to verify that when math headers are built with
; __FINITE_MATH_ONLY__ enabled, causing use of __<func>_finite
; function versions, vectorization can map these to vector versions.

target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
target triple = "x86_64-unknown-linux-gnu"

declare float @__expf_finite(float) #0

; CHECK-LABEL: @exp_f32
; CHECK: <4 x float> @__svml_expf4
; CHECK: ret
define void @exp_f32(float* nocapture %varray) {
entry:
  br label %for.body

for.body:                                         ; preds = %for.body, %entry
  %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
  %tmp = trunc i64 %indvars.iv to i32
  %conv = sitofp i32 %tmp to float
  %call = tail call fast float @__expf_finite(float %conv)
  %arrayidx = getelementptr inbounds float, float* %varray, i64 %indvars.iv
  store float %call, float* %arrayidx, align 4
  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
  %exitcond = icmp eq i64 %indvars.iv.next, 1000
  br i1 %exitcond, label %for.end, label %for.body, !llvm.loop !1

for.end:                                          ; preds = %for.body
  ret void
}

!1 = distinct !{!1, !2, !3}
!2 = !{!"llvm.loop.vectorize.width", i32 4}
!3 = !{!"llvm.loop.vectorize.enable", i1 true}


declare double @__exp_finite(double) #0

; CHECK-LABEL: @exp_f64
; CHECK: <4 x double> @__svml_exp4
; CHECK: ret
define void @exp_f64(double* nocapture %varray) {
entry:
  br label %for.body

for.body:                                         ; preds = %for.body, %entry
  %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
  %tmp = trunc i64 %indvars.iv to i32
  %conv = sitofp i32 %tmp to double
  %call = tail call fast double @__exp_finite(double %conv)
  %arrayidx = getelementptr inbounds double, double* %varray, i64 %indvars.iv
  store double %call, double* %arrayidx, align 4
  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
  %exitcond = icmp eq i64 %indvars.iv.next, 1000
  br i1 %exitcond, label %for.end, label %for.body, !llvm.loop !11

for.end:                                          ; preds = %for.body
  ret void
}

!11 = distinct !{!11, !12, !13}
!12 = !{!"llvm.loop.vectorize.width", i32 4}
!13 = !{!"llvm.loop.vectorize.enable", i1 true}




declare float @__logf_finite(float) #0

; CHECK-LABEL: @log_f32
; CHECK: <4 x float> @__svml_logf4
; CHECK: ret
define void @log_f32(float* nocapture %varray) {
entry:
  br label %for.body

for.body:                                         ; preds = %for.body, %entry
  %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
  %tmp = trunc i64 %indvars.iv to i32
  %conv = sitofp i32 %tmp to float
  %call = tail call fast float @__logf_finite(float %conv)
  %arrayidx = getelementptr inbounds float, float* %varray, i64 %indvars.iv
  store float %call, float* %arrayidx, align 4
  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
  %exitcond = icmp eq i64 %indvars.iv.next, 1000
  br i1 %exitcond, label %for.end, label %for.body, !llvm.loop !21

for.end:                                          ; preds = %for.body
  ret void
}

!21 = distinct !{!21, !22, !23}
!22 = !{!"llvm.loop.vectorize.width", i32 4}
!23 = !{!"llvm.loop.vectorize.enable", i1 true}


declare double @__log_finite(double) #0

; CHECK-LABEL: @log_f64
; CHECK: <4 x double> @__svml_log4
; CHECK: ret
define void @log_f64(double* nocapture %varray) {
entry:
  br label %for.body

for.body:                                         ; preds = %for.body, %entry
  %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
  %tmp = trunc i64 %indvars.iv to i32
  %conv = sitofp i32 %tmp to double
  %call = tail call fast double @__log_finite(double %conv)
  %arrayidx = getelementptr inbounds double, double* %varray, i64 %indvars.iv
  store double %call, double* %arrayidx, align 4
  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
  %exitcond = icmp eq i64 %indvars.iv.next, 1000
  br i1 %exitcond, label %for.end, label %for.body, !llvm.loop !31

for.end:                                          ; preds = %for.body
  ret void
}

!31 = distinct !{!31, !32, !33}
!32 = !{!"llvm.loop.vectorize.width", i32 4}
!33 = !{!"llvm.loop.vectorize.enable", i1 true}


declare float @__powf_finite(float, float) #0

; CHECK-LABEL: @pow_f32
; CHECK: <4 x float> @__svml_powf4
; CHECK: ret
define void @pow_f32(float* nocapture %varray, float* nocapture readonly %exp) {
entry:
  br label %for.body

for.body:                                         ; preds = %for.body, %entry
  %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
  %tmp = trunc i64 %indvars.iv to i32
  %conv = sitofp i32 %tmp to float
  %arrayidx = getelementptr inbounds float, float* %exp, i64 %indvars.iv
  %tmp1 = load float, float* %arrayidx, align 4
  %tmp2 = tail call fast float @__powf_finite(float %conv, float %tmp1)
  %arrayidx2 = getelementptr inbounds float, float* %varray, i64 %indvars.iv
  store float %tmp2, float* %arrayidx2, align 4
  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
  %exitcond = icmp eq i64 %indvars.iv.next, 1000
  br i1 %exitcond, label %for.end, label %for.body, !llvm.loop !41

for.end:                                          ; preds = %for.body
  ret void
}

!41 = distinct !{!41, !42, !43}
!42 = !{!"llvm.loop.vectorize.width", i32 4}
!43 = !{!"llvm.loop.vectorize.enable", i1 true}


declare double @__pow_finite(double, double) #0

; CHECK-LABEL: @pow_f64
; CHECK: <4 x double> @__svml_pow4
; CHECK: ret
define void @pow_f64(double* nocapture %varray, double* nocapture readonly %exp) {
entry:
  br label %for.body

for.body:                                         ; preds = %for.body, %entry
  %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
  %tmp = trunc i64 %indvars.iv to i32
  %conv = sitofp i32 %tmp to double
  %arrayidx = getelementptr inbounds double, double* %exp, i64 %indvars.iv
  %tmp1 = load double, double* %arrayidx, align 4
  %tmp2 = tail call fast double @__pow_finite(double %conv, double %tmp1)
  %arrayidx2 = getelementptr inbounds double, double* %varray, i64 %indvars.iv
  store double %tmp2, double* %arrayidx2, align 4
  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
  %exitcond = icmp eq i64 %indvars.iv.next, 1000
  br i1 %exitcond, label %for.end, label %for.body, !llvm.loop !51

for.end:                                          ; preds = %for.body
  ret void
}

!51 = distinct !{!51, !52, !53}
!52 = !{!"llvm.loop.vectorize.width", i32 4}
!53 = !{!"llvm.loop.vectorize.enable", i1 true}