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
386
387
388
389
390
391
392
393
394
395
396
|
# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py UTC_ARGS: --version 5
# RUN: llc -mtriple=amdgcn -mcpu=gfx900 -verify-machineinstrs -run-pass=si-fold-operands %s -o - | FileCheck -check-prefixes=CHECK,GFX9 %s
# RUN: llc -mtriple=amdgcn -mcpu=gfx1030 -mattr=+wavefrontsize64 -verify-machineinstrs -run-pass=si-fold-operands %s -o - | FileCheck -check-prefixes=CHECK,GFX10 %s
# RUN: llc -mtriple=amdgcn -mcpu=gfx1200 -mattr=+wavefrontsize64 -verify-machineinstrs -run-pass=si-fold-operands %s -o - | FileCheck -check-prefixes=CHECK,GFX12 %s
---
name: fold_frame_index__s_add_i32__fi_const
tracksRegLiveness: true
frameInfo:
maxAlignment: 4
localFrameSize: 16384
stack:
- { id: 0, size: 16384, alignment: 4, local-offset: 0 }
body: |
bb.0:
; CHECK-LABEL: name: fold_frame_index__s_add_i32__fi_const
; CHECK: [[S_ADD_I32_:%[0-9]+]]:sreg_32 = S_ADD_I32 %stack.0, 128, implicit-def $scc
; CHECK-NEXT: $sgpr4 = COPY [[S_ADD_I32_]]
; CHECK-NEXT: SI_RETURN implicit $sgpr4
%0:sreg_32 = S_MOV_B32 %stack.0
%1:sreg_32 = S_ADD_I32 %0, 128, implicit-def $scc
$sgpr4 = COPY %1
SI_RETURN implicit $sgpr4
...
---
name: fold_frame_index__s_add_i32__const_fi
tracksRegLiveness: true
frameInfo:
maxAlignment: 4
localFrameSize: 16384
stack:
- { id: 0, size: 16384, alignment: 4, local-offset: 0 }
body: |
bb.0:
; CHECK-LABEL: name: fold_frame_index__s_add_i32__const_fi
; CHECK: [[S_ADD_I32_:%[0-9]+]]:sreg_32 = S_ADD_I32 128, %stack.0, implicit-def $scc
; CHECK-NEXT: $sgpr4 = COPY [[S_ADD_I32_]]
; CHECK-NEXT: SI_RETURN implicit $sgpr4
%0:sreg_32 = S_MOV_B32 %stack.0
%1:sreg_32 = S_ADD_I32 128, %0, implicit-def $scc
$sgpr4 = COPY %1
SI_RETURN implicit $sgpr4
...
---
name: fold_frame_index__s_add_i32__materializedconst_fi
tracksRegLiveness: true
frameInfo:
maxAlignment: 4
localFrameSize: 16384
stack:
- { id: 0, size: 16384, alignment: 4, local-offset: 0 }
body: |
bb.0:
; CHECK-LABEL: name: fold_frame_index__s_add_i32__materializedconst_fi
; CHECK: [[S_ADD_I32_:%[0-9]+]]:sreg_32 = S_ADD_I32 256, %stack.0, implicit-def $scc
; CHECK-NEXT: $sgpr4 = COPY [[S_ADD_I32_]]
; CHECK-NEXT: SI_RETURN implicit $sgpr4
%0:sreg_32 = S_MOV_B32 256
%1:sreg_32 = S_MOV_B32 %stack.0
%2:sreg_32 = S_ADD_I32 %0, %1, implicit-def $scc
$sgpr4 = COPY %2
SI_RETURN implicit $sgpr4
...
---
name: fold_frame_index__s_add_i32__fi_materializedconst_0
tracksRegLiveness: true
frameInfo:
maxAlignment: 4
localFrameSize: 16384
stack:
- { id: 0, size: 16384, alignment: 4, local-offset: 0 }
body: |
bb.0:
; CHECK-LABEL: name: fold_frame_index__s_add_i32__fi_materializedconst_0
; CHECK: [[S_MOV_B32_:%[0-9]+]]:sreg_32 = S_MOV_B32 256
; CHECK-NEXT: [[S_ADD_I32_:%[0-9]+]]:sreg_32 = S_ADD_I32 %stack.0, [[S_MOV_B32_]], implicit-def $scc
; CHECK-NEXT: $sgpr4 = COPY [[S_ADD_I32_]]
; CHECK-NEXT: SI_RETURN implicit $sgpr4
%0:sreg_32 = S_MOV_B32 %stack.0
%1:sreg_32 = S_MOV_B32 256
%2:sreg_32 = S_ADD_I32 %0, %1, implicit-def $scc
$sgpr4 = COPY %2
SI_RETURN implicit $sgpr4
...
---
name: fold_frame_index__s_add_i32__fi_materializedconst_1
tracksRegLiveness: true
frameInfo:
maxAlignment: 4
localFrameSize: 16384
stack:
- { id: 0, size: 16384, alignment: 4, local-offset: 0 }
body: |
bb.0:
; CHECK-LABEL: name: fold_frame_index__s_add_i32__fi_materializedconst_1
; CHECK: [[S_ADD_I32_:%[0-9]+]]:sreg_32 = S_ADD_I32 256, %stack.0, implicit-def $scc
; CHECK-NEXT: $sgpr4 = COPY [[S_ADD_I32_]]
; CHECK-NEXT: SI_RETURN implicit $sgpr4
%0:sreg_32 = S_MOV_B32 256
%1:sreg_32 = S_MOV_B32 %stack.0
%2:sreg_32 = S_ADD_I32 %0, %1, implicit-def $scc
$sgpr4 = COPY %2
SI_RETURN implicit $sgpr4
...
---
name: fold_frame_index__s_add_i32__reg_fi
tracksRegLiveness: true
frameInfo:
maxAlignment: 4
localFrameSize: 16384
stack:
- { id: 0, size: 16384, alignment: 4, local-offset: 0 }
body: |
bb.0:
liveins: $sgpr4
; CHECK-LABEL: name: fold_frame_index__s_add_i32__reg_fi
; CHECK: liveins: $sgpr4
; CHECK-NEXT: {{ $}}
; CHECK-NEXT: [[COPY:%[0-9]+]]:sreg_32 = COPY $sgpr4
; CHECK-NEXT: [[S_ADD_I32_:%[0-9]+]]:sreg_32 = S_ADD_I32 [[COPY]], %stack.0, implicit-def $scc
; CHECK-NEXT: $sgpr4 = COPY [[S_ADD_I32_]]
; CHECK-NEXT: SI_RETURN implicit $sgpr4
%0:sreg_32 = COPY $sgpr4
%1:sreg_32 = S_MOV_B32 %stack.0
%2:sreg_32 = S_ADD_I32 %0, %1, implicit-def $scc
$sgpr4 = COPY %2
SI_RETURN implicit $sgpr4
...
---
name: fold_frame_index__s_add_i32__fi_reg
tracksRegLiveness: true
frameInfo:
maxAlignment: 4
localFrameSize: 16384
stack:
- { id: 0, size: 16384, alignment: 4, local-offset: 0 }
body: |
bb.0:
liveins: $sgpr4
; CHECK-LABEL: name: fold_frame_index__s_add_i32__fi_reg
; CHECK: liveins: $sgpr4
; CHECK-NEXT: {{ $}}
; CHECK-NEXT: [[COPY:%[0-9]+]]:sreg_32 = COPY $sgpr4
; CHECK-NEXT: [[S_ADD_I32_:%[0-9]+]]:sreg_32 = S_ADD_I32 %stack.0, [[COPY]], implicit-def $scc
; CHECK-NEXT: $sgpr4 = COPY [[S_ADD_I32_]]
; CHECK-NEXT: SI_RETURN implicit $sgpr4
%0:sreg_32 = COPY $sgpr4
%1:sreg_32 = S_MOV_B32 %stack.0
%2:sreg_32 = S_ADD_I32 %1, %0, implicit-def $scc
$sgpr4 = COPY %2
SI_RETURN implicit $sgpr4
...
---
name: fold_frame_index__v_add_u32_e32__const_v_fi
tracksRegLiveness: true
frameInfo:
maxAlignment: 4
localFrameSize: 16384
stack:
- { id: 0, size: 16384, alignment: 4, local-offset: 0 }
body: |
bb.0:
; CHECK-LABEL: name: fold_frame_index__v_add_u32_e32__const_v_fi
; CHECK: [[V_ADD_U32_e32_:%[0-9]+]]:vgpr_32 = V_ADD_U32_e32 128, %stack.0, implicit $exec
; CHECK-NEXT: $sgpr4 = COPY [[V_ADD_U32_e32_]]
; CHECK-NEXT: SI_RETURN implicit $sgpr4
%0:vgpr_32 = V_MOV_B32_e32 %stack.0, implicit $exec
%1:vgpr_32 = V_ADD_U32_e32 128, %0, implicit $exec
$sgpr4 = COPY %1
SI_RETURN implicit $sgpr4
...
---
name: fold_frame_index__v_add_u32_e32__materialized_v_const_v_fi
tracksRegLiveness: true
frameInfo:
maxAlignment: 4
localFrameSize: 16384
stack:
- { id: 0, size: 16384, alignment: 4, local-offset: 0 }
body: |
bb.0:
; CHECK-LABEL: name: fold_frame_index__v_add_u32_e32__materialized_v_const_v_fi
; CHECK: [[V_MOV_B32_e32_:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 128, implicit $exec
; CHECK-NEXT: [[V_ADD_U32_e32_:%[0-9]+]]:vgpr_32 = V_ADD_U32_e32 %stack.0, [[V_MOV_B32_e32_]], implicit $exec
; CHECK-NEXT: $sgpr4 = COPY [[V_ADD_U32_e32_]]
; CHECK-NEXT: SI_RETURN implicit $sgpr4
%0:vgpr_32 = V_MOV_B32_e32 %stack.0, implicit $exec
%1:vgpr_32 = V_MOV_B32_e32 128, implicit $exec
%2:vgpr_32 = V_ADD_U32_e32 %1, %0, implicit $exec
$sgpr4 = COPY %2
SI_RETURN implicit $sgpr4
...
---
name: fold_frame_index__v_add_u32_e64__imm_v_fi
tracksRegLiveness: true
frameInfo:
maxAlignment: 4
localFrameSize: 16384
stack:
- { id: 0, size: 16384, alignment: 4, local-offset: 0 }
body: |
bb.0:
; CHECK-LABEL: name: fold_frame_index__v_add_u32_e64__imm_v_fi
; CHECK: [[V_ADD_U32_e64_:%[0-9]+]]:vgpr_32 = V_ADD_U32_e64 64, %stack.0, 0, implicit $exec
; CHECK-NEXT: $sgpr4 = COPY [[V_ADD_U32_e64_]]
; CHECK-NEXT: SI_RETURN implicit $sgpr4
%0:vgpr_32 = V_MOV_B32_e32 %stack.0, implicit $exec
%1:vgpr_32 = V_ADD_U32_e64 64, %0, 0, implicit $exec
$sgpr4 = COPY %1
SI_RETURN implicit $sgpr4
...
---
name: fold_frame_index__v_add_u32_e64___v_fi_imm
tracksRegLiveness: true
frameInfo:
maxAlignment: 4
localFrameSize: 16384
stack:
- { id: 0, size: 16384, alignment: 4, local-offset: 0 }
body: |
bb.0:
; CHECK-LABEL: name: fold_frame_index__v_add_u32_e64___v_fi_imm
; CHECK: [[V_ADD_U32_e64_:%[0-9]+]]:vgpr_32 = V_ADD_U32_e64 %stack.0, 64, 0, implicit $exec
; CHECK-NEXT: $sgpr4 = COPY [[V_ADD_U32_e64_]]
; CHECK-NEXT: SI_RETURN implicit $sgpr4
%0:vgpr_32 = V_MOV_B32_e32 %stack.0, implicit $exec
%1:vgpr_32 = V_ADD_U32_e64 %0, 64, 0, implicit $exec
$sgpr4 = COPY %1
SI_RETURN implicit $sgpr4
...
---
name: fold_frame_index__v_add_co_u32_e32__const_v_fi
tracksRegLiveness: true
frameInfo:
maxAlignment: 4
localFrameSize: 16384
stack:
- { id: 0, size: 16384, alignment: 4, local-offset: 0 }
body: |
bb.0:
; CHECK-LABEL: name: fold_frame_index__v_add_co_u32_e32__const_v_fi
; CHECK: [[V_ADD_CO_U32_e32_:%[0-9]+]]:vgpr_32 = V_ADD_CO_U32_e32 128, %stack.0, implicit-def $vcc, implicit $exec
; CHECK-NEXT: $vgpr0 = COPY [[V_ADD_CO_U32_e32_]]
; CHECK-NEXT: SI_RETURN implicit $vgpr0
%0:vgpr_32 = V_MOV_B32_e32 %stack.0, implicit $exec
%1:vgpr_32 = V_ADD_CO_U32_e32 128, %0, implicit-def $vcc, implicit $exec
$vgpr0 = COPY %1
SI_RETURN implicit $vgpr0
...
---
name: fold_frame_index__v_add_co_u32_e64__v_fi_imm
tracksRegLiveness: true
frameInfo:
maxAlignment: 4
localFrameSize: 16384
stack:
- { id: 0, size: 16384, alignment: 4, local-offset: 0 }
body: |
bb.0:
; CHECK-LABEL: name: fold_frame_index__v_add_co_u32_e64__v_fi_imm
; CHECK: [[V_ADD_CO_U32_e64_:%[0-9]+]]:vgpr_32, [[V_ADD_CO_U32_e64_1:%[0-9]+]]:sreg_64 = V_ADD_CO_U32_e64 %stack.0, 64, 0, implicit $exec
; CHECK-NEXT: $vgpr0 = COPY [[V_ADD_CO_U32_e64_]]
; CHECK-NEXT: SI_RETURN implicit $vgpr0
%0:vgpr_32 = V_MOV_B32_e32 %stack.0, implicit $exec
%1:vgpr_32, %2:sreg_64 = V_ADD_CO_U32_e64 %0, 64, 0, implicit $exec
$vgpr0 = COPY %1
SI_RETURN implicit $vgpr0
...
---
name: fold_frame_index__v_add_co_u32_e64__imm_v_fi
tracksRegLiveness: true
frameInfo:
maxAlignment: 4
localFrameSize: 16384
stack:
- { id: 0, size: 16384, alignment: 4, local-offset: 0 }
body: |
bb.0:
; CHECK-LABEL: name: fold_frame_index__v_add_co_u32_e64__imm_v_fi
; CHECK: [[V_ADD_CO_U32_e64_:%[0-9]+]]:vgpr_32, [[V_ADD_CO_U32_e64_1:%[0-9]+]]:sreg_64 = V_ADD_CO_U32_e64 64, %stack.0, 0, implicit $exec
; CHECK-NEXT: $vgpr0 = COPY [[V_ADD_CO_U32_e64_]]
; CHECK-NEXT: SI_RETURN implicit $vgpr0
%0:vgpr_32 = V_MOV_B32_e32 %stack.0, implicit $exec
%1:vgpr_32, %2:sreg_64 = V_ADD_CO_U32_e64 64, %0, 0, implicit $exec
$vgpr0 = COPY %1
SI_RETURN implicit $vgpr0
...
---
name: multi_use_scalar_fi__add_imm_add_inline_imm
tracksRegLiveness: true
frameInfo:
maxAlignment: 4
localFrameSize: 16384
stack:
- { id: 0, size: 16384, alignment: 4, local-offset: 0 }
body: |
bb.0:
liveins: $sgpr0, $sgpr1
; CHECK-LABEL: name: multi_use_scalar_fi__add_imm_add_inline_imm
; CHECK: liveins: $sgpr0, $sgpr1
; CHECK-NEXT: {{ $}}
; CHECK-NEXT: [[COPY:%[0-9]+]]:sreg_32 = COPY $sgpr0
; CHECK-NEXT: [[COPY1:%[0-9]+]]:sreg_32 = COPY $sgpr1
; CHECK-NEXT: [[S_MOV_B32_:%[0-9]+]]:sreg_32 = S_MOV_B32 %stack.0
; CHECK-NEXT: [[S_ADD_I32_:%[0-9]+]]:sreg_32 = S_ADD_I32 [[S_MOV_B32_]], 16380, implicit-def dead $scc
; CHECK-NEXT: [[S_ADD_I32_1:%[0-9]+]]:sreg_32 = S_ADD_I32 %stack.0, 56, implicit-def dead $scc
; CHECK-NEXT: $sgpr4 = COPY [[S_ADD_I32_]]
; CHECK-NEXT: $sgpr5 = COPY [[S_ADD_I32_1]]
; CHECK-NEXT: SI_RETURN implicit $sgpr4, implicit $sgpr5
%0:sreg_32 = COPY $sgpr0
%1:sreg_32 = COPY $sgpr1
%2:sreg_32 = S_MOV_B32 16380
%3:sreg_32 = S_MOV_B32 56
%4:sreg_32 = S_MOV_B32 %stack.0
%5:sreg_32 = S_ADD_I32 %4, killed %2, implicit-def dead $scc
%6:sreg_32 = S_ADD_I32 %4, killed %3, implicit-def dead $scc
$sgpr4 = COPY %5
$sgpr5 = COPY %6
SI_RETURN implicit $sgpr4, implicit $sgpr5
...
---
name: multi_add_use_vector_fi__add_imm_add_inline_imm
tracksRegLiveness: true
frameInfo:
maxAlignment: 4
localFrameSize: 16384
stack:
- { id: 0, size: 16384, alignment: 4, local-offset: 0 }
body: |
bb.0:
liveins: $vgpr0, $vgpr1
; GFX9-LABEL: name: multi_add_use_vector_fi__add_imm_add_inline_imm
; GFX9: liveins: $vgpr0, $vgpr1
; GFX9-NEXT: {{ $}}
; GFX9-NEXT: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
; GFX9-NEXT: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr1
; GFX9-NEXT: [[V_MOV_B32_e32_:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 %stack.0, implicit $exec
; GFX9-NEXT: [[V_ADD_U32_e64_:%[0-9]+]]:vgpr_32 = V_ADD_U32_e64 [[V_MOV_B32_e32_]], killed [[COPY1]], 0, implicit $exec
; GFX9-NEXT: [[V_ADD_U32_e64_1:%[0-9]+]]:vgpr_32 = V_ADD_U32_e64 [[V_MOV_B32_e32_]], 56, 0, implicit $exec
; GFX9-NEXT: $vgpr0 = COPY [[V_ADD_U32_e64_]]
; GFX9-NEXT: $vgpr1 = COPY [[V_ADD_U32_e64_1]]
; GFX9-NEXT: SI_RETURN implicit $vgpr0, implicit $vgpr1
;
; GFX10-LABEL: name: multi_add_use_vector_fi__add_imm_add_inline_imm
; GFX10: liveins: $vgpr0, $vgpr1
; GFX10-NEXT: {{ $}}
; GFX10-NEXT: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
; GFX10-NEXT: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr1
; GFX10-NEXT: [[V_ADD_U32_e64_:%[0-9]+]]:vgpr_32 = V_ADD_U32_e64 %stack.0, killed [[COPY1]], 0, implicit $exec
; GFX10-NEXT: [[V_ADD_U32_e64_1:%[0-9]+]]:vgpr_32 = V_ADD_U32_e64 %stack.0, 56, 0, implicit $exec
; GFX10-NEXT: $vgpr0 = COPY [[V_ADD_U32_e64_]]
; GFX10-NEXT: $vgpr1 = COPY [[V_ADD_U32_e64_1]]
; GFX10-NEXT: SI_RETURN implicit $vgpr0, implicit $vgpr1
;
; GFX12-LABEL: name: multi_add_use_vector_fi__add_imm_add_inline_imm
; GFX12: liveins: $vgpr0, $vgpr1
; GFX12-NEXT: {{ $}}
; GFX12-NEXT: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
; GFX12-NEXT: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr1
; GFX12-NEXT: [[V_ADD_U32_e64_:%[0-9]+]]:vgpr_32 = V_ADD_U32_e64 %stack.0, killed [[COPY1]], 0, implicit $exec
; GFX12-NEXT: [[V_ADD_U32_e64_1:%[0-9]+]]:vgpr_32 = V_ADD_U32_e64 %stack.0, 56, 0, implicit $exec
; GFX12-NEXT: $vgpr0 = COPY [[V_ADD_U32_e64_]]
; GFX12-NEXT: $vgpr1 = COPY [[V_ADD_U32_e64_1]]
; GFX12-NEXT: SI_RETURN implicit $vgpr0, implicit $vgpr1
%0:vgpr_32 = COPY $vgpr0
%1:vgpr_32 = COPY $vgpr1
%2:vgpr_32 = V_MOV_B32_e32 %stack.0, implicit $exec
%3:vgpr_32 = V_ADD_U32_e64 %2, killed %1, 0, implicit $exec
%4:vgpr_32 = V_MOV_B32_e32 999, implicit $exec
%5:vgpr_32 = COPY %3
%6:sreg_32 = S_MOV_B32 56
%7:vgpr_32 = V_ADD_U32_e64 %2, killed %6, 0, implicit $exec
%8:vgpr_32 = COPY %7
$vgpr0 = COPY %3
$vgpr1 = COPY %7
SI_RETURN implicit $vgpr0, implicit $vgpr1
...
|
