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
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
|
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
; RUN: llc -mtriple=riscv64 < %s | FileCheck %s
define i1 @sink_li(ptr %text, ptr %text.addr.0) nounwind {
; CHECK-LABEL: sink_li:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: addi sp, sp, -32
; CHECK-NEXT: sd ra, 24(sp) # 8-byte Folded Spill
; CHECK-NEXT: sd s0, 16(sp) # 8-byte Folded Spill
; CHECK-NEXT: sd s1, 8(sp) # 8-byte Folded Spill
; CHECK-NEXT: sd s2, 0(sp) # 8-byte Folded Spill
; CHECK-NEXT: mv s1, a1
; CHECK-NEXT: mv s0, a0
; CHECK-NEXT: call toupper
; CHECK-NEXT: li a1, 0
; CHECK-NEXT: beqz s0, .LBB0_26
; CHECK-NEXT: # %bb.1: # %while.body.preheader
; CHECK-NEXT: li a2, 1
; CHECK-NEXT: li a3, 9
; CHECK-NEXT: li a4, 32
; CHECK-NEXT: .LBB0_2: # %while.body
; CHECK-NEXT: # =>This Inner Loop Header: Depth=1
; CHECK-NEXT: bnez a2, .LBB0_4
; CHECK-NEXT: # %bb.3: # %while.body
; CHECK-NEXT: # in Loop: Header=BB0_2 Depth=1
; CHECK-NEXT: bne a2, a3, .LBB0_16
; CHECK-NEXT: .LBB0_4: # %while.body.1
; CHECK-NEXT: # in Loop: Header=BB0_2 Depth=1
; CHECK-NEXT: bnez a2, .LBB0_6
; CHECK-NEXT: # %bb.5: # %while.body.1
; CHECK-NEXT: # in Loop: Header=BB0_2 Depth=1
; CHECK-NEXT: bne a2, a3, .LBB0_17
; CHECK-NEXT: .LBB0_6: # %while.body.3
; CHECK-NEXT: # in Loop: Header=BB0_2 Depth=1
; CHECK-NEXT: bnez a2, .LBB0_8
; CHECK-NEXT: # %bb.7: # %while.body.3
; CHECK-NEXT: # in Loop: Header=BB0_2 Depth=1
; CHECK-NEXT: bne a2, a4, .LBB0_19
; CHECK-NEXT: .LBB0_8: # %while.body.4
; CHECK-NEXT: # in Loop: Header=BB0_2 Depth=1
; CHECK-NEXT: bnez a2, .LBB0_10
; CHECK-NEXT: # %bb.9: # %while.body.4
; CHECK-NEXT: # in Loop: Header=BB0_2 Depth=1
; CHECK-NEXT: bne a2, a4, .LBB0_21
; CHECK-NEXT: .LBB0_10: # %while.body.5
; CHECK-NEXT: # in Loop: Header=BB0_2 Depth=1
; CHECK-NEXT: bnez a2, .LBB0_12
; CHECK-NEXT: # %bb.11: # %while.body.5
; CHECK-NEXT: # in Loop: Header=BB0_2 Depth=1
; CHECK-NEXT: bne a2, a3, .LBB0_23
; CHECK-NEXT: .LBB0_12: # %while.body.6
; CHECK-NEXT: # in Loop: Header=BB0_2 Depth=1
; CHECK-NEXT: bnez a2, .LBB0_2
; CHECK-NEXT: # %bb.13: # %while.body.6
; CHECK-NEXT: # in Loop: Header=BB0_2 Depth=1
; CHECK-NEXT: beq a2, a3, .LBB0_2
; CHECK-NEXT: # %bb.14: # %while.body.6
; CHECK-NEXT: beqz a2, .LBB0_24
; CHECK-NEXT: # %bb.15: # %strdup.exit.split.loop.exit126
; CHECK-NEXT: addi s0, s1, 7
; CHECK-NEXT: j .LBB0_25
; CHECK-NEXT: .LBB0_16: # %while.body
; CHECK-NEXT: beqz a2, .LBB0_26
; CHECK-NEXT: j .LBB0_18
; CHECK-NEXT: .LBB0_17: # %while.body.1
; CHECK-NEXT: beqz a2, .LBB0_24
; CHECK-NEXT: .LBB0_18: # %strdup.exit.loopexit
; CHECK-NEXT: li s0, 0
; CHECK-NEXT: j .LBB0_25
; CHECK-NEXT: .LBB0_19: # %while.body.3
; CHECK-NEXT: beqz a2, .LBB0_24
; CHECK-NEXT: # %bb.20: # %strdup.exit.split.loop.exit120
; CHECK-NEXT: addi s0, s1, 4
; CHECK-NEXT: j .LBB0_25
; CHECK-NEXT: .LBB0_21: # %while.body.4
; CHECK-NEXT: beqz a2, .LBB0_24
; CHECK-NEXT: # %bb.22: # %strdup.exit.split.loop.exit122
; CHECK-NEXT: addi s0, s1, 5
; CHECK-NEXT: j .LBB0_25
; CHECK-NEXT: .LBB0_23: # %while.body.5
; CHECK-NEXT: bnez a2, .LBB0_25
; CHECK-NEXT: .LBB0_24:
; CHECK-NEXT: li a1, 0
; CHECK-NEXT: j .LBB0_26
; CHECK-NEXT: .LBB0_25: # %strdup.exit
; CHECK-NEXT: li s1, 0
; CHECK-NEXT: mv s2, a0
; CHECK-NEXT: li a0, 0
; CHECK-NEXT: mv a1, s0
; CHECK-NEXT: jalr s1
; CHECK-NEXT: li a0, 0
; CHECK-NEXT: mv a1, s2
; CHECK-NEXT: li a2, 0
; CHECK-NEXT: jalr s1
; CHECK-NEXT: li a1, 1
; CHECK-NEXT: .LBB0_26: # %return
; CHECK-NEXT: mv a0, a1
; CHECK-NEXT: ld ra, 24(sp) # 8-byte Folded Reload
; CHECK-NEXT: ld s0, 16(sp) # 8-byte Folded Reload
; CHECK-NEXT: ld s1, 8(sp) # 8-byte Folded Reload
; CHECK-NEXT: ld s2, 0(sp) # 8-byte Folded Reload
; CHECK-NEXT: addi sp, sp, 32
; CHECK-NEXT: ret
entry:
%call = call i32 @toupper()
%tobool.not = icmp eq ptr %text, null
br i1 %tobool.not, label %return, label %while.body
while.body: ; preds = %while.body.6, %while.body.6, %entry
switch i8 1, label %strdup.exit.split.loop.exit114 [
i8 1, label %while.body.1
i8 9, label %while.body.1
i8 0, label %return
]
while.body.1: ; preds = %while.body, %while.body
switch i8 1, label %strdup.exit [
i8 1, label %while.body.3
i8 9, label %while.body.3
i8 0, label %return
]
while.body.3: ; preds = %while.body.1, %while.body.1
switch i8 1, label %strdup.exit.split.loop.exit120 [
i8 32, label %while.body.4
i8 1, label %while.body.4
i8 0, label %return
]
while.body.4: ; preds = %while.body.3, %while.body.3
switch i8 1, label %strdup.exit.split.loop.exit122 [
i8 32, label %while.body.5
i8 1, label %while.body.5
i8 0, label %return
]
while.body.5: ; preds = %while.body.4, %while.body.4
switch i8 1, label %strdup.exit.split.loop.exit124 [
i8 1, label %while.body.6
i8 9, label %while.body.6
i8 0, label %return
]
while.body.6: ; preds = %while.body.5, %while.body.5
switch i8 1, label %strdup.exit.split.loop.exit126 [
i8 1, label %while.body
i8 9, label %while.body
i8 0, label %return
]
strdup.exit.split.loop.exit114: ; preds = %while.body
br label %strdup.exit
strdup.exit.split.loop.exit120: ; preds = %while.body.3
%incdec.ptr.3.le = getelementptr i8, ptr %text.addr.0, i64 4
br label %strdup.exit
strdup.exit.split.loop.exit122: ; preds = %while.body.4
%incdec.ptr.4.le = getelementptr i8, ptr %text.addr.0, i64 5
br label %strdup.exit
strdup.exit.split.loop.exit124: ; preds = %while.body.5
br label %strdup.exit
strdup.exit.split.loop.exit126: ; preds = %while.body.6
%incdec.ptr.6.le = getelementptr i8, ptr %text.addr.0, i64 7
br label %strdup.exit
strdup.exit: ; preds = %strdup.exit.split.loop.exit126, %strdup.exit.split.loop.exit124, %strdup.exit.split.loop.exit122, %strdup.exit.split.loop.exit120, %strdup.exit.split.loop.exit114, %while.body.1
%text.addr.0.lcssa = phi ptr [ null, %strdup.exit.split.loop.exit114 ], [ %incdec.ptr.3.le, %strdup.exit.split.loop.exit120 ], [ %incdec.ptr.4.le, %strdup.exit.split.loop.exit122 ], [ %text, %strdup.exit.split.loop.exit124 ], [ %incdec.ptr.6.le, %strdup.exit.split.loop.exit126 ], [ null, %while.body.1 ]
%call5.i = tail call ptr null(ptr null, ptr %text.addr.0.lcssa)
%memchr64 = tail call ptr null(ptr null, i32 %call, i64 0)
br label %return
return: ; preds = %strdup.exit, %while.body.6, %while.body.5, %while.body.4, %while.body.3, %while.body.1, %while.body, %entry
%retval.1 = phi i1 [ false, %entry ], [ true, %strdup.exit ], [ false, %while.body ], [ false, %while.body.1 ], [ false, %while.body.3 ], [ false, %while.body.4 ], [ false, %while.body.5 ], [ false, %while.body.6 ]
ret i1 %retval.1
}
declare i32 @toupper()
; In this example, %arg and the return value (13) have overlapping live
; intervals because the ABI mandidates they both be placed in a0.
define signext i32 @overlap_live_ranges(ptr %arg, i32 signext %arg1) {
; CHECK-LABEL: overlap_live_ranges:
; CHECK: # %bb.0: # %bb
; CHECK-NEXT: li a2, 1
; CHECK-NEXT: bne a1, a2, .LBB1_2
; CHECK-NEXT: # %bb.1: # %bb2
; CHECK-NEXT: lw a0, 4(a0)
; CHECK-NEXT: ret
; CHECK-NEXT: .LBB1_2:
; CHECK-NEXT: li a0, 13
; CHECK-NEXT: ret
bb:
%i = icmp eq i32 %arg1, 1
br i1 %i, label %bb2, label %bb5
bb2: ; preds = %bb
%i3 = getelementptr inbounds nuw i8, ptr %arg, i64 4
%i4 = load i32, ptr %i3, align 4
br label %bb5
bb5: ; preds = %bb2, %bb
%i6 = phi i32 [ %i4, %bb2 ], [ 13, %bb ]
ret i32 %i6
}
; For switches, the values feeding the phi are always sunk into the
; target blocks as the IR syntax requires the intermediate block and
; DAG lowers it in the immediate predecessor of the phi.
define signext i32 @switch_dispatch(i8 %a) {
; CHECK-LABEL: switch_dispatch:
; CHECK: # %bb.0: # %bb
; CHECK-NEXT: addi sp, sp, -16
; CHECK-NEXT: .cfi_def_cfa_offset 16
; CHECK-NEXT: sd ra, 8(sp) # 8-byte Folded Spill
; CHECK-NEXT: sd s0, 0(sp) # 8-byte Folded Spill
; CHECK-NEXT: .cfi_offset ra, -8
; CHECK-NEXT: .cfi_offset s0, -16
; CHECK-NEXT: andi a0, a0, 255
; CHECK-NEXT: li a1, 31
; CHECK-NEXT: blt a1, a0, .LBB2_5
; CHECK-NEXT: # %bb.1: # %bb
; CHECK-NEXT: beqz a0, .LBB2_10
; CHECK-NEXT: # %bb.2: # %bb
; CHECK-NEXT: li a1, 12
; CHECK-NEXT: beq a0, a1, .LBB2_11
; CHECK-NEXT: # %bb.3: # %bb
; CHECK-NEXT: li a1, 13
; CHECK-NEXT: bne a0, a1, .LBB2_9
; CHECK-NEXT: # %bb.4: # %case.4
; CHECK-NEXT: li s0, 644
; CHECK-NEXT: j .LBB2_13
; CHECK-NEXT: .LBB2_5: # %bb
; CHECK-NEXT: li a1, 234
; CHECK-NEXT: beq a0, a1, .LBB2_9
; CHECK-NEXT: # %bb.6: # %bb
; CHECK-NEXT: li a1, 70
; CHECK-NEXT: beq a0, a1, .LBB2_12
; CHECK-NEXT: # %bb.7: # %bb
; CHECK-NEXT: li a1, 32
; CHECK-NEXT: bne a0, a1, .LBB2_9
; CHECK-NEXT: # %bb.8: # %case.0
; CHECK-NEXT: li s0, 13
; CHECK-NEXT: j .LBB2_13
; CHECK-NEXT: .LBB2_9: # %case.default
; CHECK-NEXT: li s0, 23
; CHECK-NEXT: j .LBB2_13
; CHECK-NEXT: .LBB2_10: # %case.5
; CHECK-NEXT: li s0, 54
; CHECK-NEXT: j .LBB2_13
; CHECK-NEXT: .LBB2_11: # %case.1
; CHECK-NEXT: li s0, 53
; CHECK-NEXT: j .LBB2_13
; CHECK-NEXT: .LBB2_12: # %case.2
; CHECK-NEXT: li s0, 33
; CHECK-NEXT: .LBB2_13: # %merge
; CHECK-NEXT: mv a0, s0
; CHECK-NEXT: call use
; CHECK-NEXT: mv a0, s0
; CHECK-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
; CHECK-NEXT: ld s0, 0(sp) # 8-byte Folded Reload
; CHECK-NEXT: .cfi_restore ra
; CHECK-NEXT: .cfi_restore s0
; CHECK-NEXT: addi sp, sp, 16
; CHECK-NEXT: .cfi_def_cfa_offset 0
; CHECK-NEXT: ret
bb:
switch i8 %a, label %case.default [
i8 32, label %case.0
i8 12, label %case.1
i8 70, label %case.2
i8 -22, label %case.3
i8 13, label %case.4
i8 0, label %case.5
]
case.0:
br label %merge
case.1:
br label %merge
case.2:
br label %merge
case.3:
br label %merge
case.4:
br label %merge
case.5:
br label %merge
case.default:
br label %merge
merge:
%res = phi i32 [ 23, %case.default ], [ 13, %case.0 ], [ 53, %case.1 ], [ 33, %case.2 ], [ 23, %case.3 ], [ 644, %case.4 ], [ 54, %case.5 ]
call void @use(i32 %res)
ret i32 %res
}
; Same as for the switch, but written via manual branching.
define signext i32 @branch_dispatch(i8 %a) {
; CHECK-LABEL: branch_dispatch:
; CHECK: # %bb.0: # %case.0
; CHECK-NEXT: addi sp, sp, -16
; CHECK-NEXT: .cfi_def_cfa_offset 16
; CHECK-NEXT: sd ra, 8(sp) # 8-byte Folded Spill
; CHECK-NEXT: sd s0, 0(sp) # 8-byte Folded Spill
; CHECK-NEXT: .cfi_offset ra, -8
; CHECK-NEXT: .cfi_offset s0, -16
; CHECK-NEXT: .cfi_remember_state
; CHECK-NEXT: andi a0, a0, 255
; CHECK-NEXT: li a1, 32
; CHECK-NEXT: beq a0, a1, .LBB3_7
; CHECK-NEXT: # %bb.1: # %case.1
; CHECK-NEXT: li a1, 12
; CHECK-NEXT: beq a0, a1, .LBB3_8
; CHECK-NEXT: # %bb.2: # %case.2
; CHECK-NEXT: li a1, 70
; CHECK-NEXT: beq a0, a1, .LBB3_9
; CHECK-NEXT: # %bb.3: # %case.3
; CHECK-NEXT: li a1, 234
; CHECK-NEXT: li s0, 23
; CHECK-NEXT: beq a0, a1, .LBB3_10
; CHECK-NEXT: # %bb.4: # %case.4
; CHECK-NEXT: beqz a0, .LBB3_11
; CHECK-NEXT: # %bb.5: # %case.5
; CHECK-NEXT: li a1, 5
; CHECK-NEXT: bne a0, a1, .LBB3_10
; CHECK-NEXT: # %bb.6:
; CHECK-NEXT: li s0, 54
; CHECK-NEXT: j .LBB3_10
; CHECK-NEXT: .LBB3_7:
; CHECK-NEXT: li s0, 13
; CHECK-NEXT: j .LBB3_10
; CHECK-NEXT: .LBB3_8:
; CHECK-NEXT: li s0, 53
; CHECK-NEXT: j .LBB3_10
; CHECK-NEXT: .LBB3_9:
; CHECK-NEXT: li s0, 33
; CHECK-NEXT: .LBB3_10: # %merge
; CHECK-NEXT: mv a0, s0
; CHECK-NEXT: call use
; CHECK-NEXT: mv a0, s0
; CHECK-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
; CHECK-NEXT: ld s0, 0(sp) # 8-byte Folded Reload
; CHECK-NEXT: .cfi_restore ra
; CHECK-NEXT: .cfi_restore s0
; CHECK-NEXT: addi sp, sp, 16
; CHECK-NEXT: .cfi_def_cfa_offset 0
; CHECK-NEXT: ret
; CHECK-NEXT: .LBB3_11:
; CHECK-NEXT: .cfi_restore_state
; CHECK-NEXT: li s0, 644
; CHECK-NEXT: j .LBB3_10
case.0:
%c0 = icmp ne i8 %a, 32
br i1 %c0, label %case.1, label %merge
case.1:
%c1 = icmp ne i8 %a, 12
br i1 %c1, label %case.2, label %merge
case.2:
%c2 = icmp ne i8 %a, 70
br i1 %c2, label %case.3, label %merge
case.3:
%c3 = icmp ne i8 %a, -22
br i1 %c3, label %case.4, label %merge
case.4:
%c4 = icmp ne i8 %a, 0
br i1 %c4, label %case.5, label %merge
case.5:
%c5 = icmp ne i8 %a, 5
br i1 %c5, label %case.default, label %merge
case.default:
br label %merge
merge:
%res = phi i32 [ 23, %case.default ], [ 13, %case.0 ], [ 53, %case.1 ], [ 33, %case.2 ], [ 23, %case.3 ], [ 644, %case.4 ], [ 54, %case.5 ]
call void @use(i32 %res)
ret i32 %res
}
declare void @use(i32)
|
