vector-reductions-expanded.ll
15.7 KB
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
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt -O2 -expand-reductions -S < %s | FileCheck %s
; Test if SLP vector reduction patterns are recognized
; and optionally converted to reduction intrinsics and
; back to raw IR.
target triple = "x86_64--"
target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
define i32 @add_v4i32(i32* %p) #0 {
; CHECK-LABEL: @add_v4i32(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[TMP0:%.*]] = bitcast i32* [[P:%.*]] to <4 x i32>*
; CHECK-NEXT: [[TMP1:%.*]] = load <4 x i32>, <4 x i32>* [[TMP0]], align 4, [[TBAA0:!tbaa !.*]]
; CHECK-NEXT: [[RDX_SHUF:%.*]] = shufflevector <4 x i32> [[TMP1]], <4 x i32> undef, <4 x i32> <i32 2, i32 3, i32 undef, i32 undef>
; CHECK-NEXT: [[BIN_RDX:%.*]] = add <4 x i32> [[TMP1]], [[RDX_SHUF]]
; CHECK-NEXT: [[RDX_SHUF3:%.*]] = shufflevector <4 x i32> [[BIN_RDX]], <4 x i32> undef, <4 x i32> <i32 1, i32 undef, i32 undef, i32 undef>
; CHECK-NEXT: [[BIN_RDX4:%.*]] = add <4 x i32> [[BIN_RDX]], [[RDX_SHUF3]]
; CHECK-NEXT: [[TMP2:%.*]] = extractelement <4 x i32> [[BIN_RDX4]], i32 0
; CHECK-NEXT: ret i32 [[TMP2]]
;
entry:
br label %for.cond
for.cond:
%r.0 = phi i32 [ 0, %entry ], [ %add, %for.inc ]
%i.0 = phi i32 [ 0, %entry ], [ %inc, %for.inc ]
%cmp = icmp slt i32 %i.0, 4
br i1 %cmp, label %for.body, label %for.cond.cleanup
for.cond.cleanup:
br label %for.end
for.body:
%idxprom = sext i32 %i.0 to i64
%arrayidx = getelementptr inbounds i32, i32* %p, i64 %idxprom
%0 = load i32, i32* %arrayidx, align 4, !tbaa !3
%add = add nsw i32 %r.0, %0
br label %for.inc
for.inc:
%inc = add nsw i32 %i.0, 1
br label %for.cond
for.end:
ret i32 %r.0
}
define signext i16 @mul_v8i16(i16* %p) #0 {
; CHECK-LABEL: @mul_v8i16(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[TMP0:%.*]] = bitcast i16* [[P:%.*]] to <8 x i16>*
; CHECK-NEXT: [[TMP1:%.*]] = load <8 x i16>, <8 x i16>* [[TMP0]], align 2, [[TBAA4:!tbaa !.*]]
; CHECK-NEXT: [[RDX_SHUF:%.*]] = shufflevector <8 x i16> [[TMP1]], <8 x i16> undef, <8 x i32> <i32 4, i32 5, i32 6, i32 7, i32 undef, i32 undef, i32 undef, i32 undef>
; CHECK-NEXT: [[BIN_RDX:%.*]] = mul <8 x i16> [[TMP1]], [[RDX_SHUF]]
; CHECK-NEXT: [[RDX_SHUF3:%.*]] = shufflevector <8 x i16> [[BIN_RDX]], <8 x i16> undef, <8 x i32> <i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
; CHECK-NEXT: [[BIN_RDX4:%.*]] = mul <8 x i16> [[BIN_RDX]], [[RDX_SHUF3]]
; CHECK-NEXT: [[RDX_SHUF5:%.*]] = shufflevector <8 x i16> [[BIN_RDX4]], <8 x i16> undef, <8 x i32> <i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
; CHECK-NEXT: [[BIN_RDX6:%.*]] = mul <8 x i16> [[BIN_RDX4]], [[RDX_SHUF5]]
; CHECK-NEXT: [[TMP2:%.*]] = extractelement <8 x i16> [[BIN_RDX6]], i32 0
; CHECK-NEXT: ret i16 [[TMP2]]
;
entry:
br label %for.cond
for.cond:
%r.0 = phi i16 [ 1, %entry ], [ %conv2, %for.inc ]
%i.0 = phi i32 [ 0, %entry ], [ %inc, %for.inc ]
%cmp = icmp slt i32 %i.0, 8
br i1 %cmp, label %for.body, label %for.cond.cleanup
for.cond.cleanup:
br label %for.end
for.body:
%idxprom = sext i32 %i.0 to i64
%arrayidx = getelementptr inbounds i16, i16* %p, i64 %idxprom
%0 = load i16, i16* %arrayidx, align 2, !tbaa !7
%conv = sext i16 %0 to i32
%conv1 = sext i16 %r.0 to i32
%mul = mul nsw i32 %conv1, %conv
%conv2 = trunc i32 %mul to i16
br label %for.inc
for.inc:
%inc = add nsw i32 %i.0, 1
br label %for.cond
for.end:
ret i16 %r.0
}
define signext i8 @or_v16i8(i8* %p) #0 {
; CHECK-LABEL: @or_v16i8(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[TMP0:%.*]] = bitcast i8* [[P:%.*]] to <16 x i8>*
; CHECK-NEXT: [[TMP1:%.*]] = load <16 x i8>, <16 x i8>* [[TMP0]], align 1, [[TBAA6:!tbaa !.*]]
; CHECK-NEXT: [[RDX_SHUF:%.*]] = shufflevector <16 x i8> [[TMP1]], <16 x i8> undef, <16 x i32> <i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
; CHECK-NEXT: [[BIN_RDX:%.*]] = or <16 x i8> [[TMP1]], [[RDX_SHUF]]
; CHECK-NEXT: [[RDX_SHUF4:%.*]] = shufflevector <16 x i8> [[BIN_RDX]], <16 x i8> undef, <16 x i32> <i32 4, i32 5, i32 6, i32 7, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
; CHECK-NEXT: [[BIN_RDX5:%.*]] = or <16 x i8> [[BIN_RDX]], [[RDX_SHUF4]]
; CHECK-NEXT: [[RDX_SHUF6:%.*]] = shufflevector <16 x i8> [[BIN_RDX5]], <16 x i8> undef, <16 x i32> <i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
; CHECK-NEXT: [[BIN_RDX7:%.*]] = or <16 x i8> [[BIN_RDX5]], [[RDX_SHUF6]]
; CHECK-NEXT: [[RDX_SHUF8:%.*]] = shufflevector <16 x i8> [[BIN_RDX7]], <16 x i8> undef, <16 x i32> <i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
; CHECK-NEXT: [[BIN_RDX9:%.*]] = or <16 x i8> [[BIN_RDX7]], [[RDX_SHUF8]]
; CHECK-NEXT: [[TMP2:%.*]] = extractelement <16 x i8> [[BIN_RDX9]], i32 0
; CHECK-NEXT: ret i8 [[TMP2]]
;
entry:
br label %for.cond
for.cond:
%r.0 = phi i8 [ 0, %entry ], [ %conv2, %for.inc ]
%i.0 = phi i32 [ 0, %entry ], [ %inc, %for.inc ]
%cmp = icmp slt i32 %i.0, 16
br i1 %cmp, label %for.body, label %for.cond.cleanup
for.cond.cleanup:
br label %for.end
for.body:
%idxprom = sext i32 %i.0 to i64
%arrayidx = getelementptr inbounds i8, i8* %p, i64 %idxprom
%0 = load i8, i8* %arrayidx, align 1, !tbaa !9
%conv = sext i8 %0 to i32
%conv1 = sext i8 %r.0 to i32
%or = or i32 %conv1, %conv
%conv2 = trunc i32 %or to i8
br label %for.inc
for.inc:
%inc = add nsw i32 %i.0, 1
br label %for.cond
for.end:
ret i8 %r.0
}
define i32 @smin_v4i32(i32* %p) #0 {
; CHECK-LABEL: @smin_v4i32(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[TMP0:%.*]] = bitcast i32* [[P:%.*]] to <4 x i32>*
; CHECK-NEXT: [[TMP1:%.*]] = load <4 x i32>, <4 x i32>* [[TMP0]], align 4, [[TBAA0]]
; CHECK-NEXT: [[RDX_SHUF:%.*]] = shufflevector <4 x i32> [[TMP1]], <4 x i32> undef, <4 x i32> <i32 2, i32 3, i32 undef, i32 undef>
; CHECK-NEXT: [[RDX_MINMAX_CMP:%.*]] = icmp slt <4 x i32> [[TMP1]], [[RDX_SHUF]]
; CHECK-NEXT: [[RDX_MINMAX_SELECT:%.*]] = select <4 x i1> [[RDX_MINMAX_CMP]], <4 x i32> [[TMP1]], <4 x i32> [[RDX_SHUF]]
; CHECK-NEXT: [[RDX_SHUF3:%.*]] = shufflevector <4 x i32> [[RDX_MINMAX_SELECT]], <4 x i32> undef, <4 x i32> <i32 1, i32 undef, i32 undef, i32 undef>
; CHECK-NEXT: [[RDX_MINMAX_CMP4:%.*]] = icmp slt <4 x i32> [[RDX_MINMAX_SELECT]], [[RDX_SHUF3]]
; CHECK-NEXT: [[RDX_MINMAX_SELECT5:%.*]] = select <4 x i1> [[RDX_MINMAX_CMP4]], <4 x i32> [[RDX_MINMAX_SELECT]], <4 x i32> [[RDX_SHUF3]]
; CHECK-NEXT: [[TMP2:%.*]] = extractelement <4 x i32> [[RDX_MINMAX_SELECT5]], i32 0
; CHECK-NEXT: ret i32 [[TMP2]]
;
entry:
br label %for.cond
for.cond:
%r.0 = phi i32 [ 2147483647, %entry ], [ %cond, %for.inc ]
%i.0 = phi i32 [ 0, %entry ], [ %inc, %for.inc ]
%cmp = icmp slt i32 %i.0, 4
br i1 %cmp, label %for.body, label %for.cond.cleanup
for.cond.cleanup:
br label %for.end
for.body:
%idxprom = sext i32 %i.0 to i64
%arrayidx = getelementptr inbounds i32, i32* %p, i64 %idxprom
%0 = load i32, i32* %arrayidx, align 4, !tbaa !3
%cmp1 = icmp slt i32 %0, %r.0
br i1 %cmp1, label %cond.true, label %cond.false
cond.true:
%idxprom2 = sext i32 %i.0 to i64
%arrayidx3 = getelementptr inbounds i32, i32* %p, i64 %idxprom2
%1 = load i32, i32* %arrayidx3, align 4, !tbaa !3
br label %cond.end
cond.false:
br label %cond.end
cond.end:
%cond = phi i32 [ %1, %cond.true ], [ %r.0, %cond.false ]
br label %for.inc
for.inc:
%inc = add nsw i32 %i.0, 1
br label %for.cond
for.end:
ret i32 %r.0
}
define i32 @umax_v4i32(i32* %p) #0 {
; CHECK-LABEL: @umax_v4i32(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[TMP0:%.*]] = bitcast i32* [[P:%.*]] to <4 x i32>*
; CHECK-NEXT: [[TMP1:%.*]] = load <4 x i32>, <4 x i32>* [[TMP0]], align 4, [[TBAA0]]
; CHECK-NEXT: [[RDX_SHUF:%.*]] = shufflevector <4 x i32> [[TMP1]], <4 x i32> undef, <4 x i32> <i32 2, i32 3, i32 undef, i32 undef>
; CHECK-NEXT: [[RDX_MINMAX_CMP:%.*]] = icmp ugt <4 x i32> [[TMP1]], [[RDX_SHUF]]
; CHECK-NEXT: [[RDX_MINMAX_SELECT:%.*]] = select <4 x i1> [[RDX_MINMAX_CMP]], <4 x i32> [[TMP1]], <4 x i32> [[RDX_SHUF]]
; CHECK-NEXT: [[RDX_SHUF3:%.*]] = shufflevector <4 x i32> [[RDX_MINMAX_SELECT]], <4 x i32> undef, <4 x i32> <i32 1, i32 undef, i32 undef, i32 undef>
; CHECK-NEXT: [[RDX_MINMAX_CMP4:%.*]] = icmp ugt <4 x i32> [[RDX_MINMAX_SELECT]], [[RDX_SHUF3]]
; CHECK-NEXT: [[RDX_MINMAX_SELECT5:%.*]] = select <4 x i1> [[RDX_MINMAX_CMP4]], <4 x i32> [[RDX_MINMAX_SELECT]], <4 x i32> [[RDX_SHUF3]]
; CHECK-NEXT: [[TMP2:%.*]] = extractelement <4 x i32> [[RDX_MINMAX_SELECT5]], i32 0
; CHECK-NEXT: ret i32 [[TMP2]]
;
entry:
br label %for.cond
for.cond:
%r.0 = phi i32 [ 0, %entry ], [ %cond, %for.inc ]
%i.0 = phi i32 [ 0, %entry ], [ %inc, %for.inc ]
%cmp = icmp slt i32 %i.0, 4
br i1 %cmp, label %for.body, label %for.cond.cleanup
for.cond.cleanup:
br label %for.end
for.body:
%idxprom = sext i32 %i.0 to i64
%arrayidx = getelementptr inbounds i32, i32* %p, i64 %idxprom
%0 = load i32, i32* %arrayidx, align 4, !tbaa !3
%cmp1 = icmp ugt i32 %0, %r.0
br i1 %cmp1, label %cond.true, label %cond.false
cond.true:
%idxprom2 = sext i32 %i.0 to i64
%arrayidx3 = getelementptr inbounds i32, i32* %p, i64 %idxprom2
%1 = load i32, i32* %arrayidx3, align 4, !tbaa !3
br label %cond.end
cond.false:
br label %cond.end
cond.end:
%cond = phi i32 [ %1, %cond.true ], [ %r.0, %cond.false ]
br label %for.inc
for.inc:
%inc = add nsw i32 %i.0, 1
br label %for.cond
for.end:
ret i32 %r.0
}
define float @fadd_v4i32(float* %p) #0 {
; CHECK-LABEL: @fadd_v4i32(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[TMP0:%.*]] = bitcast float* [[P:%.*]] to <4 x float>*
; CHECK-NEXT: [[TMP1:%.*]] = load <4 x float>, <4 x float>* [[TMP0]], align 4, [[TBAA7:!tbaa !.*]]
; CHECK-NEXT: [[RDX_SHUF:%.*]] = shufflevector <4 x float> [[TMP1]], <4 x float> undef, <4 x i32> <i32 2, i32 3, i32 undef, i32 undef>
; CHECK-NEXT: [[BIN_RDX:%.*]] = fadd fast <4 x float> [[TMP1]], [[RDX_SHUF]]
; CHECK-NEXT: [[RDX_SHUF3:%.*]] = shufflevector <4 x float> [[BIN_RDX]], <4 x float> undef, <4 x i32> <i32 1, i32 undef, i32 undef, i32 undef>
; CHECK-NEXT: [[BIN_RDX4:%.*]] = fadd fast <4 x float> [[BIN_RDX]], [[RDX_SHUF3]]
; CHECK-NEXT: [[TMP2:%.*]] = extractelement <4 x float> [[BIN_RDX4]], i32 0
; CHECK-NEXT: [[BIN_RDX5:%.*]] = fadd fast float 0.000000e+00, [[TMP2]]
; CHECK-NEXT: [[OP_EXTRA:%.*]] = fadd fast float [[BIN_RDX5]], 4.200000e+01
; CHECK-NEXT: ret float [[OP_EXTRA]]
;
entry:
br label %for.cond
for.cond:
%r.0 = phi float [ 4.200000e+01, %entry ], [ %add, %for.inc ]
%i.0 = phi i32 [ 0, %entry ], [ %inc, %for.inc ]
%cmp = icmp slt i32 %i.0, 4
br i1 %cmp, label %for.body, label %for.cond.cleanup
for.cond.cleanup:
br label %for.end
for.body:
%idxprom = sext i32 %i.0 to i64
%arrayidx = getelementptr inbounds float, float* %p, i64 %idxprom
%0 = load float, float* %arrayidx, align 4, !tbaa !10
%add = fadd fast float %r.0, %0
br label %for.inc
for.inc:
%inc = add nsw i32 %i.0, 1
br label %for.cond
for.end:
ret float %r.0
}
define float @fmul_v4i32(float* %p) #0 {
; CHECK-LABEL: @fmul_v4i32(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[TMP0:%.*]] = bitcast float* [[P:%.*]] to <4 x float>*
; CHECK-NEXT: [[TMP1:%.*]] = load <4 x float>, <4 x float>* [[TMP0]], align 4, [[TBAA7]]
; CHECK-NEXT: [[RDX_SHUF:%.*]] = shufflevector <4 x float> [[TMP1]], <4 x float> undef, <4 x i32> <i32 2, i32 3, i32 undef, i32 undef>
; CHECK-NEXT: [[BIN_RDX:%.*]] = fmul fast <4 x float> [[TMP1]], [[RDX_SHUF]]
; CHECK-NEXT: [[RDX_SHUF3:%.*]] = shufflevector <4 x float> [[BIN_RDX]], <4 x float> undef, <4 x i32> <i32 1, i32 undef, i32 undef, i32 undef>
; CHECK-NEXT: [[BIN_RDX4:%.*]] = fmul fast <4 x float> [[BIN_RDX]], [[RDX_SHUF3]]
; CHECK-NEXT: [[TMP2:%.*]] = extractelement <4 x float> [[BIN_RDX4]], i32 0
; CHECK-NEXT: [[BIN_RDX5:%.*]] = fmul fast float 1.000000e+00, [[TMP2]]
; CHECK-NEXT: [[OP_EXTRA:%.*]] = fmul fast float [[BIN_RDX5]], 4.200000e+01
; CHECK-NEXT: ret float [[OP_EXTRA]]
;
entry:
br label %for.cond
for.cond:
%r.0 = phi float [ 4.200000e+01, %entry ], [ %mul, %for.inc ]
%i.0 = phi i32 [ 0, %entry ], [ %inc, %for.inc ]
%cmp = icmp slt i32 %i.0, 4
br i1 %cmp, label %for.body, label %for.cond.cleanup
for.cond.cleanup:
br label %for.end
for.body:
%idxprom = sext i32 %i.0 to i64
%arrayidx = getelementptr inbounds float, float* %p, i64 %idxprom
%0 = load float, float* %arrayidx, align 4, !tbaa !10
%mul = fmul fast float %r.0, %0
br label %for.inc
for.inc:
%inc = add nsw i32 %i.0, 1
br label %for.cond
for.end:
ret float %r.0
}
define float @fmin_v4i32(float* %p) #0 {
; CHECK-LABEL: @fmin_v4i32(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[TMP0:%.*]] = load float, float* [[P:%.*]], align 4, [[TBAA7]]
; CHECK-NEXT: [[ARRAYIDX_1:%.*]] = getelementptr inbounds float, float* [[P]], i64 1
; CHECK-NEXT: [[TMP1:%.*]] = load float, float* [[ARRAYIDX_1]], align 4, [[TBAA7]]
; CHECK-NEXT: [[TMP2:%.*]] = tail call fast float @llvm.minnum.f32(float [[TMP1]], float [[TMP0]])
; CHECK-NEXT: [[ARRAYIDX_2:%.*]] = getelementptr inbounds float, float* [[P]], i64 2
; CHECK-NEXT: [[TMP3:%.*]] = load float, float* [[ARRAYIDX_2]], align 4, [[TBAA7]]
; CHECK-NEXT: [[TMP4:%.*]] = tail call fast float @llvm.minnum.f32(float [[TMP3]], float [[TMP2]])
; CHECK-NEXT: [[ARRAYIDX_3:%.*]] = getelementptr inbounds float, float* [[P]], i64 3
; CHECK-NEXT: [[TMP5:%.*]] = load float, float* [[ARRAYIDX_3]], align 4, [[TBAA7]]
; CHECK-NEXT: [[TMP6:%.*]] = tail call fast float @llvm.minnum.f32(float [[TMP5]], float [[TMP4]])
; CHECK-NEXT: ret float [[TMP6]]
;
entry:
br label %for.cond
for.cond:
%r.0 = phi float [ 0x47EFFFFFE0000000, %entry ], [ %cond, %for.inc ]
%i.0 = phi i32 [ 0, %entry ], [ %inc, %for.inc ]
%cmp = icmp slt i32 %i.0, 4
br i1 %cmp, label %for.body, label %for.cond.cleanup
for.cond.cleanup:
br label %for.end
for.body:
%idxprom = sext i32 %i.0 to i64
%arrayidx = getelementptr inbounds float, float* %p, i64 %idxprom
%0 = load float, float* %arrayidx, align 4, !tbaa !10
%cmp1 = fcmp fast olt float %0, %r.0
br i1 %cmp1, label %cond.true, label %cond.false
cond.true:
%idxprom2 = sext i32 %i.0 to i64
%arrayidx3 = getelementptr inbounds float, float* %p, i64 %idxprom2
%1 = load float, float* %arrayidx3, align 4, !tbaa !10
br label %cond.end
cond.false:
br label %cond.end
cond.end:
%cond = phi fast float [ %1, %cond.true ], [ %r.0, %cond.false ]
br label %for.inc
for.inc:
%inc = add nsw i32 %i.0, 1
br label %for.cond
for.end:
ret float %r.0
}
attributes #0 = { nounwind ssp uwtable "correctly-rounded-divide-sqrt-fp-math"="false" "disable-tail-calls"="false" "frame-pointer"="all" "less-precise-fpmad"="false" "min-legal-vector-width"="0" "no-infs-fp-math"="true" "no-jump-tables"="false" "no-nans-fp-math"="true" "no-signed-zeros-fp-math"="true" "no-trapping-math"="true" "stack-protector-buffer-size"="8" "target-cpu"="penryn" "target-features"="+avx,+cx16,+cx8,+fxsr,+mmx,+popcnt,+sahf,+sse,+sse2,+sse3,+sse4.1,+sse4.2,+ssse3,+x87,+xsave" "unsafe-fp-math"="true" "use-soft-float"="false" }
;attributes #1 = { argmemonly nounwind willreturn }
!0 = !{i32 1, !"wchar_size", i32 4}
!1 = !{i32 7, !"PIC Level", i32 2}
!2 = !{!"clang version 11.0.0 (https://github.com/llvm/llvm-project.git a9fe69c359de653015c39e413e48630d069abe27)"}
!3 = !{!4, !4, i64 0}
!4 = !{!"int", !5, i64 0}
!5 = !{!"omnipotent char", !6, i64 0}
!6 = !{!"Simple C/C++ TBAA"}
!7 = !{!8, !8, i64 0}
!8 = !{!"short", !5, i64 0}
!9 = !{!5, !5, i64 0}
!10 = !{!11, !11, i64 0}
!11 = !{!"float", !5, i64 0}