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
|
; Test spilling using MVC.
;
; RUN: llc < %s -mtriple=s390x-linux-gnu | FileCheck %s
declare void @foo()
@g0 = global i32 0
@g1 = global i32 1
@g2 = global i32 2
@g3 = global i32 3
@g4 = global i32 4
@g5 = global i32 5
@g6 = global i32 6
@g7 = global i32 7
@g8 = global i32 8
@g9 = global i32 9
@h0 = global i64 0
@h1 = global i64 1
@h2 = global i64 2
@h3 = global i64 3
@h4 = global i64 4
@h5 = global i64 5
@h6 = global i64 6
@h7 = global i64 7
@h8 = global i64 8
@h9 = global i64 9
; This function shouldn't spill anything
define void @f1(i32 *%ptr0) {
; CHECK: f1:
; CHECK: stmg
; CHECK: aghi %r15, -160
; CHECK-NOT: %r15
; CHECK: brasl %r14, foo@PLT
; CHECK-NOT: %r15
; CHECK: lmg
; CHECK: br %r14
%ptr1 = getelementptr i32 *%ptr0, i32 2
%ptr2 = getelementptr i32 *%ptr0, i32 4
%ptr3 = getelementptr i32 *%ptr0, i32 6
%ptr4 = getelementptr i32 *%ptr0, i32 8
%ptr5 = getelementptr i32 *%ptr0, i32 10
%ptr6 = getelementptr i32 *%ptr0, i32 12
%val0 = load i32 *%ptr0
%val1 = load i32 *%ptr1
%val2 = load i32 *%ptr2
%val3 = load i32 *%ptr3
%val4 = load i32 *%ptr4
%val5 = load i32 *%ptr5
%val6 = load i32 *%ptr6
call void @foo()
store i32 %val0, i32 *%ptr0
store i32 %val1, i32 *%ptr1
store i32 %val2, i32 *%ptr2
store i32 %val3, i32 *%ptr3
store i32 %val4, i32 *%ptr4
store i32 %val5, i32 *%ptr5
store i32 %val6, i32 *%ptr6
ret void
}
; Test a case where at least one i32 load and at least one i32 store
; need spills.
define void @f2(i32 *%ptr0) {
; CHECK: f2:
; CHECK: mvc [[OFFSET1:16[04]]](4,%r15), [[OFFSET2:[0-9]+]]({{%r[0-9]+}})
; CHECK: brasl %r14, foo@PLT
; CHECK: mvc [[OFFSET2]](4,{{%r[0-9]+}}), [[OFFSET1]](%r15)
; CHECK: br %r14
%ptr1 = getelementptr i32 *%ptr0, i64 2
%ptr2 = getelementptr i32 *%ptr0, i64 4
%ptr3 = getelementptr i32 *%ptr0, i64 6
%ptr4 = getelementptr i32 *%ptr0, i64 8
%ptr5 = getelementptr i32 *%ptr0, i64 10
%ptr6 = getelementptr i32 *%ptr0, i64 12
%ptr7 = getelementptr i32 *%ptr0, i64 14
%ptr8 = getelementptr i32 *%ptr0, i64 16
%val0 = load i32 *%ptr0
%val1 = load i32 *%ptr1
%val2 = load i32 *%ptr2
%val3 = load i32 *%ptr3
%val4 = load i32 *%ptr4
%val5 = load i32 *%ptr5
%val6 = load i32 *%ptr6
%val7 = load i32 *%ptr7
%val8 = load i32 *%ptr8
call void @foo()
store i32 %val0, i32 *%ptr0
store i32 %val1, i32 *%ptr1
store i32 %val2, i32 *%ptr2
store i32 %val3, i32 *%ptr3
store i32 %val4, i32 *%ptr4
store i32 %val5, i32 *%ptr5
store i32 %val6, i32 *%ptr6
store i32 %val7, i32 *%ptr7
store i32 %val8, i32 *%ptr8
ret void
}
; Test a case where at least one i64 load and at least one i64 store
; need spills.
define void @f3(i64 *%ptr0) {
; CHECK: f3:
; CHECK: mvc 160(8,%r15), [[OFFSET:[0-9]+]]({{%r[0-9]+}})
; CHECK: brasl %r14, foo@PLT
; CHECK: mvc [[OFFSET]](8,{{%r[0-9]+}}), 160(%r15)
; CHECK: br %r14
%ptr1 = getelementptr i64 *%ptr0, i64 2
%ptr2 = getelementptr i64 *%ptr0, i64 4
%ptr3 = getelementptr i64 *%ptr0, i64 6
%ptr4 = getelementptr i64 *%ptr0, i64 8
%ptr5 = getelementptr i64 *%ptr0, i64 10
%ptr6 = getelementptr i64 *%ptr0, i64 12
%ptr7 = getelementptr i64 *%ptr0, i64 14
%ptr8 = getelementptr i64 *%ptr0, i64 16
%val0 = load i64 *%ptr0
%val1 = load i64 *%ptr1
%val2 = load i64 *%ptr2
%val3 = load i64 *%ptr3
%val4 = load i64 *%ptr4
%val5 = load i64 *%ptr5
%val6 = load i64 *%ptr6
%val7 = load i64 *%ptr7
%val8 = load i64 *%ptr8
call void @foo()
store i64 %val0, i64 *%ptr0
store i64 %val1, i64 *%ptr1
store i64 %val2, i64 *%ptr2
store i64 %val3, i64 *%ptr3
store i64 %val4, i64 *%ptr4
store i64 %val5, i64 *%ptr5
store i64 %val6, i64 *%ptr6
store i64 %val7, i64 *%ptr7
store i64 %val8, i64 *%ptr8
ret void
}
; Test a case where at least at least one f32 load and at least one f32 store
; need spills. The 8 call-saved FPRs could be used for 8 of the %vals
; (and are at the time of writing), but it would really be better to use
; MVC for all 10.
define void @f4(float *%ptr0) {
; CHECK: f4:
; CHECK: mvc [[OFFSET1:16[04]]](4,%r15), [[OFFSET2:[0-9]+]]({{%r[0-9]+}})
; CHECK: brasl %r14, foo@PLT
; CHECK: mvc [[OFFSET2]](4,{{%r[0-9]+}}), [[OFFSET1]](%r15)
; CHECK: br %r14
%ptr1 = getelementptr float *%ptr0, i64 2
%ptr2 = getelementptr float *%ptr0, i64 4
%ptr3 = getelementptr float *%ptr0, i64 6
%ptr4 = getelementptr float *%ptr0, i64 8
%ptr5 = getelementptr float *%ptr0, i64 10
%ptr6 = getelementptr float *%ptr0, i64 12
%ptr7 = getelementptr float *%ptr0, i64 14
%ptr8 = getelementptr float *%ptr0, i64 16
%ptr9 = getelementptr float *%ptr0, i64 18
%val0 = load float *%ptr0
%val1 = load float *%ptr1
%val2 = load float *%ptr2
%val3 = load float *%ptr3
%val4 = load float *%ptr4
%val5 = load float *%ptr5
%val6 = load float *%ptr6
%val7 = load float *%ptr7
%val8 = load float *%ptr8
%val9 = load float *%ptr9
call void @foo()
store float %val0, float *%ptr0
store float %val1, float *%ptr1
store float %val2, float *%ptr2
store float %val3, float *%ptr3
store float %val4, float *%ptr4
store float %val5, float *%ptr5
store float %val6, float *%ptr6
store float %val7, float *%ptr7
store float %val8, float *%ptr8
store float %val9, float *%ptr9
ret void
}
; Similarly for f64.
define void @f5(double *%ptr0) {
; CHECK: f5:
; CHECK: mvc 160(8,%r15), [[OFFSET:[0-9]+]]({{%r[0-9]+}})
; CHECK: brasl %r14, foo@PLT
; CHECK: mvc [[OFFSET]](8,{{%r[0-9]+}}), 160(%r15)
; CHECK: br %r14
%ptr1 = getelementptr double *%ptr0, i64 2
%ptr2 = getelementptr double *%ptr0, i64 4
%ptr3 = getelementptr double *%ptr0, i64 6
%ptr4 = getelementptr double *%ptr0, i64 8
%ptr5 = getelementptr double *%ptr0, i64 10
%ptr6 = getelementptr double *%ptr0, i64 12
%ptr7 = getelementptr double *%ptr0, i64 14
%ptr8 = getelementptr double *%ptr0, i64 16
%ptr9 = getelementptr double *%ptr0, i64 18
%val0 = load double *%ptr0
%val1 = load double *%ptr1
%val2 = load double *%ptr2
%val3 = load double *%ptr3
%val4 = load double *%ptr4
%val5 = load double *%ptr5
%val6 = load double *%ptr6
%val7 = load double *%ptr7
%val8 = load double *%ptr8
%val9 = load double *%ptr9
call void @foo()
store double %val0, double *%ptr0
store double %val1, double *%ptr1
store double %val2, double *%ptr2
store double %val3, double *%ptr3
store double %val4, double *%ptr4
store double %val5, double *%ptr5
store double %val6, double *%ptr6
store double %val7, double *%ptr7
store double %val8, double *%ptr8
store double %val9, double *%ptr9
ret void
}
; Repeat f2 with atomic accesses. We shouldn't use MVC here.
define void @f6(i32 *%ptr0) {
; CHECK: f6:
; CHECK-NOT: mvc
; CHECK: br %r14
%ptr1 = getelementptr i32 *%ptr0, i64 2
%ptr2 = getelementptr i32 *%ptr0, i64 4
%ptr3 = getelementptr i32 *%ptr0, i64 6
%ptr4 = getelementptr i32 *%ptr0, i64 8
%ptr5 = getelementptr i32 *%ptr0, i64 10
%ptr6 = getelementptr i32 *%ptr0, i64 12
%ptr7 = getelementptr i32 *%ptr0, i64 14
%ptr8 = getelementptr i32 *%ptr0, i64 16
%val0 = load atomic i32 *%ptr0 unordered, align 4
%val1 = load atomic i32 *%ptr1 unordered, align 4
%val2 = load atomic i32 *%ptr2 unordered, align 4
%val3 = load atomic i32 *%ptr3 unordered, align 4
%val4 = load atomic i32 *%ptr4 unordered, align 4
%val5 = load atomic i32 *%ptr5 unordered, align 4
%val6 = load atomic i32 *%ptr6 unordered, align 4
%val7 = load atomic i32 *%ptr7 unordered, align 4
%val8 = load atomic i32 *%ptr8 unordered, align 4
call void @foo()
store atomic i32 %val0, i32 *%ptr0 unordered, align 4
store atomic i32 %val1, i32 *%ptr1 unordered, align 4
store atomic i32 %val2, i32 *%ptr2 unordered, align 4
store atomic i32 %val3, i32 *%ptr3 unordered, align 4
store atomic i32 %val4, i32 *%ptr4 unordered, align 4
store atomic i32 %val5, i32 *%ptr5 unordered, align 4
store atomic i32 %val6, i32 *%ptr6 unordered, align 4
store atomic i32 %val7, i32 *%ptr7 unordered, align 4
store atomic i32 %val8, i32 *%ptr8 unordered, align 4
ret void
}
; ...likewise volatile accesses.
define void @f7(i32 *%ptr0) {
; CHECK: f7:
; CHECK-NOT: mvc
; CHECK: br %r14
%ptr1 = getelementptr i32 *%ptr0, i64 2
%ptr2 = getelementptr i32 *%ptr0, i64 4
%ptr3 = getelementptr i32 *%ptr0, i64 6
%ptr4 = getelementptr i32 *%ptr0, i64 8
%ptr5 = getelementptr i32 *%ptr0, i64 10
%ptr6 = getelementptr i32 *%ptr0, i64 12
%ptr7 = getelementptr i32 *%ptr0, i64 14
%ptr8 = getelementptr i32 *%ptr0, i64 16
%val0 = load volatile i32 *%ptr0
%val1 = load volatile i32 *%ptr1
%val2 = load volatile i32 *%ptr2
%val3 = load volatile i32 *%ptr3
%val4 = load volatile i32 *%ptr4
%val5 = load volatile i32 *%ptr5
%val6 = load volatile i32 *%ptr6
%val7 = load volatile i32 *%ptr7
%val8 = load volatile i32 *%ptr8
call void @foo()
store volatile i32 %val0, i32 *%ptr0
store volatile i32 %val1, i32 *%ptr1
store volatile i32 %val2, i32 *%ptr2
store volatile i32 %val3, i32 *%ptr3
store volatile i32 %val4, i32 *%ptr4
store volatile i32 %val5, i32 *%ptr5
store volatile i32 %val6, i32 *%ptr6
store volatile i32 %val7, i32 *%ptr7
store volatile i32 %val8, i32 *%ptr8
ret void
}
; Check that LRL and STRL are not converted.
define void @f8() {
; CHECK: f8:
; CHECK-NOT: mvc
; CHECK: br %r14
%val0 = load i32 *@g0
%val1 = load i32 *@g1
%val2 = load i32 *@g2
%val3 = load i32 *@g3
%val4 = load i32 *@g4
%val5 = load i32 *@g5
%val6 = load i32 *@g6
%val7 = load i32 *@g7
%val8 = load i32 *@g8
%val9 = load i32 *@g9
call void @foo()
store i32 %val0, i32 *@g0
store i32 %val1, i32 *@g1
store i32 %val2, i32 *@g2
store i32 %val3, i32 *@g3
store i32 %val4, i32 *@g4
store i32 %val5, i32 *@g5
store i32 %val6, i32 *@g6
store i32 %val7, i32 *@g7
store i32 %val8, i32 *@g8
store i32 %val9, i32 *@g9
ret void
}
; Likewise LGRL and STGRL.
define void @f9() {
; CHECK: f9:
; CHECK-NOT: mvc
; CHECK: br %r14
%val0 = load i64 *@h0
%val1 = load i64 *@h1
%val2 = load i64 *@h2
%val3 = load i64 *@h3
%val4 = load i64 *@h4
%val5 = load i64 *@h5
%val6 = load i64 *@h6
%val7 = load i64 *@h7
%val8 = load i64 *@h8
%val9 = load i64 *@h9
call void @foo()
store i64 %val0, i64 *@h0
store i64 %val1, i64 *@h1
store i64 %val2, i64 *@h2
store i64 %val3, i64 *@h3
store i64 %val4, i64 *@h4
store i64 %val5, i64 *@h5
store i64 %val6, i64 *@h6
store i64 %val7, i64 *@h7
store i64 %val8, i64 *@h8
store i64 %val9, i64 *@h9
ret void
}
|
