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
397
398
399
400
401
402
403
404
405
406
407
| ; Test that floating-point compares are omitted if CC already has the
; right value.
;
; RUN: llc < %s -mtriple=s390x-linux-gnu -mcpu=z10 -no-integrated-as | FileCheck %s
declare float @llvm.fabs.f32(float %f)
; Test addition followed by EQ, which can use the CC result of the addition.
define float @f1(float %a, float %b, float *%dest) {
; CHECK-LABEL: f1:
; CHECK: aebr %f0, %f2
; CHECK-NEXT: ber %r14
; CHECK: br %r14
entry:
%res = fadd float %a, %b
%cmp = fcmp oeq float %res, 0.0
br i1 %cmp, label %exit, label %store
store:
store float %b, float *%dest
br label %exit
exit:
ret float %res
}
; ...and again with LT.
define float @f2(float %a, float %b, float *%dest) {
; CHECK-LABEL: f2:
; CHECK: aebr %f0, %f2
; CHECK-NEXT: blr %r14
; CHECK: br %r14
entry:
%res = fadd float %a, %b
%cmp = fcmp olt float %res, 0.0
br i1 %cmp, label %exit, label %store
store:
store float %b, float *%dest
br label %exit
exit:
ret float %res
}
; ...and again with GT.
define float @f3(float %a, float %b, float *%dest) {
; CHECK-LABEL: f3:
; CHECK: aebr %f0, %f2
; CHECK-NEXT: bhr %r14
; CHECK: br %r14
entry:
%res = fadd float %a, %b
%cmp = fcmp ogt float %res, 0.0
br i1 %cmp, label %exit, label %store
store:
store float %b, float *%dest
br label %exit
exit:
ret float %res
}
; ...and again with UEQ.
define float @f4(float %a, float %b, float *%dest) {
; CHECK-LABEL: f4:
; CHECK: aebr %f0, %f2
; CHECK-NEXT: bnlhr %r14
; CHECK: br %r14
entry:
%res = fadd float %a, %b
%cmp = fcmp ueq float %res, 0.0
br i1 %cmp, label %exit, label %store
store:
store float %b, float *%dest
br label %exit
exit:
ret float %res
}
; Subtraction also provides a zero-based CC value.
define float @f5(float %a, float %b, float *%dest) {
; CHECK-LABEL: f5:
; CHECK: seb %f0, 0(%r2)
; CHECK-NEXT: bnher %r14
; CHECK: br %r14
entry:
%cur = load float, float *%dest
%res = fsub float %a, %cur
%cmp = fcmp ult float %res, 0.0
br i1 %cmp, label %exit, label %store
store:
store float %b, float *%dest
br label %exit
exit:
ret float %res
}
; Test the result of LOAD POSITIVE.
define float @f6(float %dummy, float %a, float *%dest) {
; CHECK-LABEL: f6:
; CHECK: lpebr %f0, %f2
; CHECK-NEXT: bhr %r14
; CHECK: br %r14
entry:
%res = call float @llvm.fabs.f32(float %a)
%cmp = fcmp ogt float %res, 0.0
br i1 %cmp, label %exit, label %store
store:
store float %res, float *%dest
br label %exit
exit:
ret float %res
}
; Test the result of LOAD NEGATIVE.
define float @f7(float %dummy, float %a, float *%dest) {
; CHECK-LABEL: f7:
; CHECK: lnebr %f0, %f2
; CHECK-NEXT: blr %r14
; CHECK: br %r14
entry:
%abs = call float @llvm.fabs.f32(float %a)
%res = fsub float -0.0, %abs
%cmp = fcmp olt float %res, 0.0
br i1 %cmp, label %exit, label %store
store:
store float %res, float *%dest
br label %exit
exit:
ret float %res
}
; Test the result of LOAD COMPLEMENT.
define float @f8(float %dummy, float %a, float *%dest) {
; CHECK-LABEL: f8:
; CHECK: lcebr %f0, %f2
; CHECK-NEXT: bler %r14
; CHECK: br %r14
entry:
%res = fsub float -0.0, %a
%cmp = fcmp ole float %res, 0.0
br i1 %cmp, label %exit, label %store
store:
store float %res, float *%dest
br label %exit
exit:
ret float %res
}
; Multiplication (for example) does not modify CC.
define float @f9(float %a, float %b, float *%dest) {
; CHECK-LABEL: f9:
; CHECK: meebr %f0, %f2
; CHECK-NEXT: ltebr %f0, %f0
; CHECK-NEXT: blhr %r14
; CHECK: br %r14
entry:
%res = fmul float %a, %b
%cmp = fcmp one float %res, 0.0
br i1 %cmp, label %exit, label %store
store:
store float %b, float *%dest
br label %exit
exit:
ret float %res
}
; Test a combination involving a CC-setting instruction followed by
; a non-CC-setting instruction.
define float @f10(float %a, float %b, float %c, float *%dest) {
; CHECK-LABEL: f10:
; CHECK: aebr %f0, %f2
; CHECK-NEXT: debr %f0, %f4
; CHECK-NEXT: ltebr %f0, %f0
; CHECK-NEXT: bner %r14
; CHECK: br %r14
entry:
%add = fadd float %a, %b
%res = fdiv float %add, %c
%cmp = fcmp une float %res, 0.0
br i1 %cmp, label %exit, label %store
store:
store float %b, float *%dest
br label %exit
exit:
ret float %res
}
; Test a case where CC is set based on a different register from the
; compare input.
define float @f11(float %a, float %b, float %c, float *%dest1, float *%dest2) {
; CHECK-LABEL: f11:
; CHECK: aebr %f0, %f2
; CHECK-NEXT: sebr %f4, %f0
; CHECK-DAG: ste %f4, 0(%r2)
; CHECK-DAG: ltebr %f0, %f0
; CHECK-NEXT: ber %r14
; CHECK: br %r14
entry:
%add = fadd float %a, %b
%sub = fsub float %c, %add
store float %sub, float *%dest1
%cmp = fcmp oeq float %add, 0.0
br i1 %cmp, label %exit, label %store
store:
store float %sub, float *%dest2
br label %exit
exit:
ret float %add
}
; Test that LER gets converted to LTEBR where useful.
define float @f12(float %dummy, float %val, float *%dest) {
; CHECK-LABEL: f12:
; CHECK: ltebr %f0, %f2
; CHECK-NEXT: #APP
; CHECK-NEXT: blah %f0
; CHECK-NEXT: #NO_APP
; CHECK-NEXT: blr %r14
; CHECK: br %r14
entry:
call void asm sideeffect "blah $0", "{f0}"(float %val)
%cmp = fcmp olt float %val, 0.0
br i1 %cmp, label %exit, label %store
store:
store float %val, float *%dest
br label %exit
exit:
ret float %val
}
; Test that LDR gets converted to LTDBR where useful.
define double @f13(double %dummy, double %val, double *%dest) {
; CHECK-LABEL: f13:
; CHECK: ltdbr %f0, %f2
; CHECK-NEXT: #APP
; CHECK-NEXT: blah %f0
; CHECK-NEXT: #NO_APP
; CHECK-NEXT: blr %r14
; CHECK: br %r14
entry:
call void asm sideeffect "blah $0", "{f0}"(double %val)
%cmp = fcmp olt double %val, 0.0
br i1 %cmp, label %exit, label %store
store:
store double %val, double *%dest
br label %exit
exit:
ret double %val
}
; Test that LXR gets converted to LTXBR where useful.
define void @f14(fp128 *%ptr1, fp128 *%ptr2) {
; CHECK-LABEL: f14:
; CHECK: ltxbr
; CHECK-NEXT: dxbr
; CHECK-NEXT: std
; CHECK-NEXT: std
; CHECK-NEXT: mxbr
; CHECK-NEXT: std
; CHECK-NEXT: std
; CHECK-NEXT: blr %r14
; CHECK: br %r14
entry:
%val1 = load fp128, fp128 *%ptr1
%val2 = load fp128, fp128 *%ptr2
%div = fdiv fp128 %val1, %val2
store fp128 %div, fp128 *%ptr1
%mul = fmul fp128 %val1, %val2
store fp128 %mul, fp128 *%ptr2
%cmp = fcmp olt fp128 %val1, 0xL00000000000000000000000000000000
br i1 %cmp, label %exit, label %store
store:
call void asm sideeffect "blah", ""()
br label %exit
exit:
ret void
}
; Test a case where it is the source rather than destination of LER that
; we need.
define float @f15(float %val, float %dummy, float *%dest) {
; CHECK-LABEL: f15:
; CHECK: ltebr %f2, %f0
; CHECK-NEXT: #APP
; CHECK-NEXT: blah %f2
; CHECK-NEXT: #NO_APP
; CHECK-NEXT: blr %r14
; CHECK: br %r14
entry:
call void asm sideeffect "blah $0", "{f2}"(float %val)
%cmp = fcmp olt float %val, 0.0
br i1 %cmp, label %exit, label %store
store:
store float %val, float *%dest
br label %exit
exit:
ret float %val
}
; Test a case where it is the source rather than destination of LDR that
; we need.
define double @f16(double %val, double %dummy, double *%dest) {
; CHECK-LABEL: f16:
; CHECK: ltdbr %f2, %f0
; CHECK-NEXT: #APP
; CHECK-NEXT: blah %f2
; CHECK-NEXT: #NO_APP
; CHECK-NEXT: blr %r14
; CHECK: br %r14
entry:
call void asm sideeffect "blah $0", "{f2}"(double %val)
%cmp = fcmp olt double %val, 0.0
br i1 %cmp, label %exit, label %store
store:
store double %val, double *%dest
br label %exit
exit:
ret double %val
}
; Repeat f2 with a comparison against -0.
define float @f17(float %a, float %b, float *%dest) {
; CHECK-LABEL: f17:
; CHECK: aebr %f0, %f2
; CHECK-NEXT: blr %r14
; CHECK: br %r14
entry:
%res = fadd float %a, %b
%cmp = fcmp olt float %res, -0.0
br i1 %cmp, label %exit, label %store
store:
store float %b, float *%dest
br label %exit
exit:
ret float %res
}
; Test another form of f7 in which the condition is based on the unnegated
; result. This is what InstCombine would produce.
define float @f18(float %dummy, float %a, float *%dest) {
; CHECK-LABEL: f18:
; CHECK: lnebr %f0, %f2
; CHECK-NEXT: blr %r14
; CHECK: br %r14
entry:
%abs = call float @llvm.fabs.f32(float %a)
%res = fsub float -0.0, %abs
%cmp = fcmp ogt float %abs, 0.0
br i1 %cmp, label %exit, label %store
store:
store float %res, float *%dest
br label %exit
exit:
ret float %res
}
; Similarly for f8.
define float @f19(float %dummy, float %a, float *%dest) {
; CHECK-LABEL: f19:
; CHECK: lcebr %f0, %f2
; CHECK-NEXT: bler %r14
; CHECK: br %r14
entry:
%res = fsub float -0.0, %a
%cmp = fcmp oge float %a, 0.0
br i1 %cmp, label %exit, label %store
store:
store float %res, float *%dest
br label %exit
exit:
ret float %res
}
|