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
  188
  189
  190
  191
  192
  193
  194
  195
  196
  197
  198
  199
  200
  201
  202
  203
  204
  205
  206
  207
  208
  209
  210
  211
  212
  213
  214
  215
  216
  217
  218
  219
  220
  221
  222
  223
  224
  225
  226
  227
  228
  229
  230
  231
  232
  233
  234
  235
  236
  237
  238
  239
  240
  241
  242
  243
  244
  245
  246
  247
  248
  249
  250
  251
  252
  253
  254
  255
  256
  257
  258
  259
  260
  261
  262
  263
; RUN: llc -mtriple=aarch64-gnu-linux -mcpu=cortex-a57 -enable-unsafe-fp-math -disable-post-ra < %s | FileCheck %s

; Incremental updates of the instruction depths should be enough for this test
; case.
; RUN: llc -mtriple=aarch64-gnu-linux -mcpu=cortex-a57 -enable-unsafe-fp-math \
; RUN:     -disable-post-ra -machine-combiner-inc-threshold=0 -machine-combiner-verify-pattern-order=true < %s | FileCheck %s

; Verify that the first two adds are independent regardless of how the inputs are
; commuted. The destination registers are used as source registers for the third add.

define float @reassociate_adds1(float %x0, float %x1, float %x2, float %x3) {
; CHECK-LABEL:   reassociate_adds1:
; CHECK:         fadd  s0, s0, s1
; CHECK-NEXT:    fadd  s1, s2, s3
; CHECK-NEXT:    fadd  s0, s0, s1
; CHECK-NEXT:    ret
  %t0 = fadd float %x0, %x1
  %t1 = fadd float %t0, %x2
  %t2 = fadd float %t1, %x3
  ret float %t2
}

define float @reassociate_adds2(float %x0, float %x1, float %x2, float %x3) {
; CHECK-LABEL:   reassociate_adds2:
; CHECK:         fadd  s0, s0, s1
; CHECK-NEXT:    fadd  s1, s2, s3
; CHECK-NEXT:    fadd  s0, s0, s1
; CHECK-NEXT:    ret
  %t0 = fadd float %x0, %x1
  %t1 = fadd float %x2, %t0
  %t2 = fadd float %t1, %x3
  ret float %t2
}

define float @reassociate_adds3(float %x0, float %x1, float %x2, float %x3) {
; CHECK-LABEL:   reassociate_adds3:
; CHECK:         s0, s0, s1
; CHECK-NEXT:    s1, s2, s3
; CHECK-NEXT:    s0, s0, s1
; CHECK-NEXT:    ret
  %t0 = fadd float %x0, %x1
  %t1 = fadd float %t0, %x2
  %t2 = fadd float %x3, %t1
  ret float %t2
}

define float @reassociate_adds4(float %x0, float %x1, float %x2, float %x3) {
; CHECK-LABEL:   reassociate_adds4:
; CHECK:         s0, s0, s1
; CHECK-NEXT:    s1, s2, s3
; CHECK-NEXT:    s0, s0, s1
; CHECK-NEXT:    ret
  %t0 = fadd float %x0, %x1
  %t1 = fadd float %x2, %t0
  %t2 = fadd float %x3, %t1
  ret float %t2
}

; Verify that we reassociate some of these ops. The optimal balanced tree of adds is not
; produced because that would cost more compile time.

define float @reassociate_adds5(float %x0, float %x1, float %x2, float %x3, float %x4, float %x5, float %x6, float %x7) {
; CHECK-LABEL:   reassociate_adds5:
; CHECK:         fadd  s0, s0, s1
; CHECK-NEXT:    fadd  s1, s2, s3
; CHECK-NEXT:    fadd  s0, s0, s1
; CHECK-NEXT:    fadd  s1, s4, s5
; CHECK-NEXT:    fadd  s1, s1, s6
; CHECK-NEXT:    fadd  s0, s0, s1
; CHECK-NEXT:    fadd  s0, s0, s7
; CHECK-NEXT:    ret
  %t0 = fadd float %x0, %x1
  %t1 = fadd float %t0, %x2
  %t2 = fadd float %t1, %x3
  %t3 = fadd float %t2, %x4
  %t4 = fadd float %t3, %x5
  %t5 = fadd float %t4, %x6
  %t6 = fadd float %t5, %x7
  ret float %t6
}

; Verify that we only need two associative operations to reassociate the operands.
; Also, we should reassociate such that the result of the high latency division
; is used by the final 'add' rather than reassociating the %x3 operand with the
; division. The latter reassociation would not improve anything.

define float @reassociate_adds6(float %x0, float %x1, float %x2, float %x3) {
; CHECK-LABEL:   reassociate_adds6:
; CHECK:         fdiv  s0, s0, s1
; CHECK-NEXT:    fadd  s1, s2, s3
; CHECK-NEXT:    fadd  s0, s0, s1
; CHECK-NEXT:    ret
  %t0 = fdiv float %x0, %x1
  %t1 = fadd float %x2, %t0
  %t2 = fadd float %x3, %t1
  ret float %t2
}

; Verify that scalar single-precision multiplies are reassociated.

define float @reassociate_muls1(float %x0, float %x1, float %x2, float %x3) {
; CHECK-LABEL:   reassociate_muls1:
; CHECK:         fdiv  s0, s0, s1
; CHECK-NEXT:    fmul  s1, s2, s3
; CHECK-NEXT:    fmul  s0, s0, s1
; CHECK-NEXT:    ret
  %t0 = fdiv float %x0, %x1
  %t1 = fmul float %x2, %t0
  %t2 = fmul float %x3, %t1
  ret float %t2
}

; Verify that scalar double-precision adds are reassociated.

define double @reassociate_adds_double(double %x0, double %x1, double %x2, double %x3) {
; CHECK-LABEL:   reassociate_adds_double:
; CHECK:         fdiv  d0, d0, d1
; CHECK-NEXT:    fadd  d1, d2, d3
; CHECK-NEXT:    fadd  d0, d0, d1
; CHECK-NEXT:    ret
  %t0 = fdiv double %x0, %x1
  %t1 = fadd double %x2, %t0
  %t2 = fadd double %x3, %t1
  ret double %t2
}

; Verify that scalar double-precision multiplies are reassociated.

define double @reassociate_muls_double(double %x0, double %x1, double %x2, double %x3) {
; CHECK-LABEL:   reassociate_muls_double:
; CHECK:         fdiv  d0, d0, d1
; CHECK-NEXT:    fmul  d1, d2, d3
; CHECK-NEXT:    fmul  d0, d0, d1
; CHECK-NEXT:    ret
  %t0 = fdiv double %x0, %x1
  %t1 = fmul double %x2, %t0
  %t2 = fmul double %x3, %t1
  ret double %t2
}

; Verify that we reassociate vector instructions too.

define <4 x float> @vector_reassociate_adds1(<4 x float> %x0, <4 x float> %x1, <4 x float> %x2, <4 x float> %x3) {
; CHECK-LABEL:   vector_reassociate_adds1:
; CHECK:         fadd  v0.4s, v0.4s, v1.4s
; CHECK-NEXT:    fadd  v1.4s, v2.4s, v3.4s
; CHECK-NEXT:    fadd  v0.4s, v0.4s, v1.4s
; CHECK-NEXT:    ret
  %t0 = fadd <4 x float> %x0, %x1
  %t1 = fadd <4 x float> %t0, %x2
  %t2 = fadd <4 x float> %t1, %x3
  ret <4 x float> %t2
}

define <4 x float> @vector_reassociate_adds2(<4 x float> %x0, <4 x float> %x1, <4 x float> %x2, <4 x float> %x3) {
; CHECK-LABEL:   vector_reassociate_adds2:
; CHECK:         fadd  v0.4s, v0.4s, v1.4s
; CHECK-NEXT:    fadd  v1.4s, v2.4s, v3.4s
; CHECK-NEXT:    fadd  v0.4s, v0.4s, v1.4s
  %t0 = fadd <4 x float> %x0, %x1
  %t1 = fadd <4 x float> %x2, %t0
  %t2 = fadd <4 x float> %t1, %x3
  ret <4 x float> %t2
}

define <4 x float> @vector_reassociate_adds3(<4 x float> %x0, <4 x float> %x1, <4 x float> %x2, <4 x float> %x3) {
; CHECK-LABEL:   vector_reassociate_adds3:
; CHECK:         fadd  v0.4s, v0.4s, v1.4s
; CHECK-NEXT:    fadd  v1.4s, v2.4s, v3.4s
; CHECK-NEXT:    fadd  v0.4s, v0.4s, v1.4s
  %t0 = fadd <4 x float> %x0, %x1
  %t1 = fadd <4 x float> %t0, %x2
  %t2 = fadd <4 x float> %x3, %t1
  ret <4 x float> %t2
}

define <4 x float> @vector_reassociate_adds4(<4 x float> %x0, <4 x float> %x1, <4 x float> %x2, <4 x float> %x3) {
; CHECK-LABEL:   vector_reassociate_adds4:
; CHECK:         fadd  v0.4s, v0.4s, v1.4s
; CHECK-NEXT:    fadd  v1.4s, v2.4s, v3.4s
; CHECK-NEXT:    fadd  v0.4s, v0.4s, v1.4s
  %t0 = fadd <4 x float> %x0, %x1
  %t1 = fadd <4 x float> %x2, %t0
  %t2 = fadd <4 x float> %x3, %t1
  ret <4 x float> %t2
}
; Verify that 128-bit vector single-precision multiplies are reassociated.

define <4 x float> @reassociate_muls_v4f32(<4 x float> %x0, <4 x float> %x1, <4 x float> %x2, <4 x float> %x3) {
; CHECK-LABEL:   reassociate_muls_v4f32:
; CHECK:         fadd  v0.4s, v0.4s, v1.4s
; CHECK-NEXT:    fmul  v1.4s, v2.4s, v3.4s
; CHECK-NEXT:    fmul  v0.4s, v0.4s, v1.4s
; CHECK-NEXT:    ret
  %t0 = fadd <4 x float> %x0, %x1
  %t1 = fmul <4 x float> %x2, %t0
  %t2 = fmul <4 x float> %x3, %t1
  ret <4 x float> %t2
}

; Verify that 128-bit vector double-precision multiplies are reassociated.

define <2 x double> @reassociate_muls_v2f64(<2 x double> %x0, <2 x double> %x1, <2 x double> %x2, <2 x double> %x3) {
; CHECK-LABEL:   reassociate_muls_v2f64:
; CHECK:         fadd  v0.2d, v0.2d, v1.2d
; CHECK-NEXT:    fmul  v1.2d, v2.2d, v3.2d
; CHECK-NEXT:    fmul  v0.2d, v0.2d, v1.2d
; CHECK-NEXT:    ret
  %t0 = fadd <2 x double> %x0, %x1
  %t1 = fmul <2 x double> %x2, %t0
  %t2 = fmul <2 x double> %x3, %t1
  ret <2 x double> %t2
}

; PR25016: https://llvm.org/bugs/show_bug.cgi?id=25016
; Verify that reassociation is not happening needlessly or wrongly.

declare double @bar()

define double @reassociate_adds_from_calls() {
; CHECK-LABEL: reassociate_adds_from_calls:
; CHECK:       bl   bar
; CHECK-NEXT:  mov  v8.16b, v0.16b 
; CHECK-NEXT:  bl   bar
; CHECK-NEXT:  mov  v9.16b, v0.16b
; CHECK-NEXT:  bl   bar
; CHECK-NEXT:  mov  v10.16b, v0.16b 
; CHECK-NEXT:  bl   bar
; CHECK:       fadd d1, d8, d9 
; CHECK-NEXT:  fadd d0, d10, d0
; CHECK-NEXT:  fadd d0, d1, d0
  %x0 = call double @bar()
  %x1 = call double @bar()
  %x2 = call double @bar()
  %x3 = call double @bar()
  %t0 = fadd double %x0, %x1
  %t1 = fadd double %t0, %x2
  %t2 = fadd double %t1, %x3
  ret double %t2
}

define double @already_reassociated() {
; CHECK-LABEL: already_reassociated:
; CHECK:       bl   bar
; CHECK-NEXT:  mov  v8.16b, v0.16b 
; CHECK-NEXT:  bl   bar
; CHECK-NEXT:  mov  v9.16b, v0.16b
; CHECK-NEXT:  bl   bar
; CHECK-NEXT:  mov  v10.16b, v0.16b 
; CHECK-NEXT:  bl   bar
; CHECK:       fadd d1, d8, d9 
; CHECK-NEXT:  fadd d0, d10, d0
; CHECK-NEXT:  fadd d0, d1, d0
  %x0 = call double @bar()
  %x1 = call double @bar()
  %x2 = call double @bar()
  %x3 = call double @bar()
  %t0 = fadd double %x0, %x1
  %t1 = fadd double %x2, %x3
  %t2 = fadd double %t0, %t1
  ret double %t2
}