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
  264
  265
  266
  267
  268
  269
  270
  271
  272
  273
  274
  275
  276
  277
  278
  279
  280
  281
  282
  283
; RUN: llc < %s -mtriple=x86_64-unknown-linux-gnu -asm-verbose=false | FileCheck %s

; These tests check for loop branching structure, and that the loop align
; directive is placed in the expected place.

; CodeGen should insert a branch into the middle of the loop in
; order to avoid a branch within the loop.

; CHECK-LABEL: simple:
;      CHECK:   align
; CHECK-NEXT: .LBB0_1:
; CHECK-NEXT:   callq loop_header
;      CHECK:   js .LBB0_3
; CHECK-NEXT:   callq loop_latch
; CHECK-NEXT:   jmp .LBB0_1
; CHECK-NEXT: .LBB0_3:
; CHECK-NEXT:   callq exit

define void @simple() nounwind {
entry:
  br label %loop

loop:
  call void @loop_header()
  %t0 = tail call i32 @get()
  %t1 = icmp slt i32 %t0, 0
  br i1 %t1, label %done, label %bb

bb:
  call void @loop_latch()
  br label %loop

done:
  call void @exit()
  ret void
}

; CodeGen should move block_a to the top of the loop so that it
; falls through into the loop, avoiding a branch within the loop.

; CHECK-LABEL: slightly_more_involved:
;      CHECK:   jmp .LBB1_1
; CHECK-NEXT:   align
; CHECK-NEXT: .LBB1_4:
; CHECK-NEXT:   callq bar99
; CHECK-NEXT: .LBB1_1:
; CHECK-NEXT:   callq body

define void @slightly_more_involved() nounwind {
entry:
  br label %loop

loop:
  call void @body()
  %t0 = call i32 @get()
  %t1 = icmp slt i32 %t0, 2
  br i1 %t1, label %block_a, label %bb

bb:
  %t2 = call i32 @get()
  %t3 = icmp slt i32 %t2, 99
  br i1 %t3, label %exit, label %loop

block_a:
  call void @bar99()
  br label %loop

exit:
  call void @exit()
  ret void
}

; Same as slightly_more_involved, but block_a is now a CFG diamond with
; fallthrough edges which should be preserved.
; "callq block_a_merge_func" is tail duped.

; CHECK-LABEL: yet_more_involved:
;      CHECK:   jmp .LBB2_1
; CHECK-NEXT:   align

;      CHECK: .LBB2_1:
; CHECK-NEXT:   callq body
; CHECK-NEXT:   callq get
; CHECK-NEXT:   cmpl $2, %eax
; CHECK-NEXT:   jge .LBB2_2
; CHECK-NEXT:   callq bar99
; CHECK-NEXT:   callq get
; CHECK-NEXT:   cmpl $2999, %eax
; CHECK-NEXT:   jg .LBB2_6
; CHECK-NEXT:   callq block_a_true_func
; CHECK-NEXT:   callq block_a_merge_func
; CHECK-NEXT:   jmp .LBB2_1
; CHECK-NEXT:   align
; CHECK-NEXT: .LBB2_6:
; CHECK-NEXT:   callq block_a_false_func
; CHECK-NEXT:   callq block_a_merge_func
; CHECK-NEXT:   jmp .LBB2_1

define void @yet_more_involved() nounwind {
entry:
  br label %loop

loop:
  call void @body()
  %t0 = call i32 @get()
  %t1 = icmp slt i32 %t0, 2
  br i1 %t1, label %block_a, label %bb

bb:
  %t2 = call i32 @get()
  %t3 = icmp slt i32 %t2, 99
  br i1 %t3, label %exit, label %loop

block_a:
  call void @bar99()
  %z0 = call i32 @get()
  %z1 = icmp slt i32 %z0, 3000
  br i1 %z1, label %block_a_true, label %block_a_false

block_a_true:
  call void @block_a_true_func()
  br label %block_a_merge

block_a_false:
  call void @block_a_false_func()
  br label %block_a_merge

block_a_merge:
  call void @block_a_merge_func()
  br label %loop

exit:
  call void @exit()
  ret void
}

; CodeGen should move the CFG islands that are part of the loop but don't
; conveniently fit anywhere so that they are at least contiguous with the
; loop.

; CHECK-LABEL: cfg_islands:
;      CHECK:   jmp     .LBB3_1
; CHECK-NEXT:   align
; CHECK-NEXT: .LBB3_7:
; CHECK-NEXT:   callq   bar100
; CHECK-NEXT: .LBB3_1:
; CHECK-NEXT:   callq   loop_header
;      CHECK:   jl .LBB3_7
;      CHECK:   jge .LBB3_3
; CHECK-NEXT:   callq   bar101
; CHECK-NEXT:   jmp     .LBB3_1
; CHECK-NEXT:   align
; CHECK-NEXT: .LBB3_3:
;      CHECK:   jge .LBB3_4
; CHECK-NEXT:   callq   bar102
; CHECK-NEXT:   jmp     .LBB3_1
; CHECK-NEXT: .LBB3_4:
;      CHECK:   jl .LBB3_6
; CHECK-NEXT:   callq   loop_latch
; CHECK-NEXT:   jmp     .LBB3_1
; CHECK-NEXT: .LBB3_6:

define void @cfg_islands() nounwind {
entry:
  br label %loop

loop:
  call void @loop_header()
  %t0 = call i32 @get()
  %t1 = icmp slt i32 %t0, 100
  br i1 %t1, label %block100, label %bb

bb:
  %t2 = call i32 @get()
  %t3 = icmp slt i32 %t2, 101
  br i1 %t3, label %block101, label %bb1

bb1:
  %t4 = call i32 @get()
  %t5 = icmp slt i32 %t4, 102
  br i1 %t5, label %block102, label %bb2

bb2:
  %t6 = call i32 @get()
  %t7 = icmp slt i32 %t6, 103
  br i1 %t7, label %exit, label %bb3

bb3:
  call void @loop_latch()
  br label %loop

exit:
  call void @exit()
  ret void

block100:
  call void @bar100()
  br label %loop

block101:
  call void @bar101()
  br label %loop

block102:
  call void @bar102()
  br label %loop
}

; CHECK-LABEL: check_minsize:
; CHECK-NOT:   align
; CHECK:      .LBB4_1:
; CHECK-NEXT:   callq loop_header
; CHECK:        callq loop_latch
; CHECK:      .LBB4_3:
; CHECK:        callq exit


define void @check_minsize() minsize nounwind {
entry:
  br label %loop

loop:
  call void @loop_header()
  %t0 = tail call i32 @get()
  %t1 = icmp slt i32 %t0, 0
  br i1 %t1, label %done, label %bb

bb:
  call void @loop_latch()
  br label %loop

done:
  call void @exit()
  ret void
}

; This is exactly the same function as slightly_more_involved.
; The difference is that when optimising for size, we do not want
; to see this reordering.

; CHECK-LABEL: slightly_more_involved_2:
; CHECK-NOT:      jmp .LBB5_1
; CHECK:          .LBB5_1:
; CHECK-NEXT:     callq body

define void @slightly_more_involved_2() #0 {
entry:
  br label %loop

loop:
  call void @body()
  %t0 = call i32 @get()
  %t1 = icmp slt i32 %t0, 2
  br i1 %t1, label %block_a, label %bb

bb:
  %t2 = call i32 @get()
  %t3 = icmp slt i32 %t2, 99
  br i1 %t3, label %exit, label %loop

block_a:
  call void @bar99()
  br label %loop

exit:
  call void @exit()
  ret void
}

attributes #0 = { minsize norecurse nounwind optsize readnone uwtable }

declare void @bar99() nounwind
declare void @bar100() nounwind
declare void @bar101() nounwind
declare void @bar102() nounwind
declare void @body() nounwind
declare void @exit() nounwind
declare void @loop_header() nounwind
declare void @loop_latch() nounwind
declare i32 @get() nounwind
declare void @block_a_true_func() nounwind
declare void @block_a_false_func() nounwind
declare void @block_a_merge_func() nounwind