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
|
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=aarch64 -hoist-const-loads=false < %s | FileCheck %s
@A = external dso_local local_unnamed_addr global [8 x [8 x i64]], align 8
@B = external dso_local local_unnamed_addr global [8 x [8 x i64]], align 8
@C = external dso_local local_unnamed_addr global [8 x [8 x i64]], align 8
define dso_local void @run_test() local_unnamed_addr uwtable {
; CHECK-LABEL: run_test:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: sub sp, sp, #208
; CHECK-NEXT: .cfi_def_cfa_offset 208
; CHECK-NEXT: stp d15, d14, [sp, #96] // 16-byte Folded Spill
; CHECK-NEXT: stp d13, d12, [sp, #112] // 16-byte Folded Spill
; CHECK-NEXT: stp d11, d10, [sp, #128] // 16-byte Folded Spill
; CHECK-NEXT: stp d9, d8, [sp, #144] // 16-byte Folded Spill
; CHECK-NEXT: str x23, [sp, #160] // 8-byte Folded Spill
; CHECK-NEXT: stp x22, x21, [sp, #176] // 16-byte Folded Spill
; CHECK-NEXT: stp x20, x19, [sp, #192] // 16-byte Folded Spill
; CHECK-NEXT: .cfi_offset w19, -8
; CHECK-NEXT: .cfi_offset w20, -16
; CHECK-NEXT: .cfi_offset w21, -24
; CHECK-NEXT: .cfi_offset w22, -32
; CHECK-NEXT: .cfi_offset w23, -48
; CHECK-NEXT: .cfi_offset b8, -56
; CHECK-NEXT: .cfi_offset b9, -64
; CHECK-NEXT: .cfi_offset b10, -72
; CHECK-NEXT: .cfi_offset b11, -80
; CHECK-NEXT: .cfi_offset b12, -88
; CHECK-NEXT: .cfi_offset b13, -96
; CHECK-NEXT: .cfi_offset b14, -104
; CHECK-NEXT: .cfi_offset b15, -112
; CHECK-NEXT: movi v2.2d, #0000000000000000
; CHECK-NEXT: // implicit-def: $q1
; CHECK-NEXT: mov x8, xzr
; CHECK-NEXT: adrp x9, B+48
; CHECK-NEXT: add x9, x9, :lo12:B+48
; CHECK-NEXT: adrp x10, A
; CHECK-NEXT: add x10, x10, :lo12:A
; CHECK-NEXT: mov x11, xzr
; CHECK-NEXT: // kill: killed $q1
; CHECK-NEXT: // implicit-def: $q1
; CHECK-NEXT: mov x12, xzr
; CHECK-NEXT: // implicit-def: $q0
; CHECK-NEXT: // implicit-def: $q3
; CHECK-NEXT: // implicit-def: $q4
; CHECK-NEXT: // implicit-def: $q5
; CHECK-NEXT: // implicit-def: $q7
; CHECK-NEXT: // implicit-def: $q10
; CHECK-NEXT: // implicit-def: $q17
; CHECK-NEXT: // implicit-def: $q6
; CHECK-NEXT: // implicit-def: $q18
; CHECK-NEXT: // implicit-def: $q19
; CHECK-NEXT: // implicit-def: $q20
; CHECK-NEXT: // implicit-def: $q21
; CHECK-NEXT: // implicit-def: $q22
; CHECK-NEXT: // implicit-def: $q23
; CHECK-NEXT: // implicit-def: $q24
; CHECK-NEXT: // implicit-def: $q9
; CHECK-NEXT: // implicit-def: $q27
; CHECK-NEXT: // implicit-def: $q12
; CHECK-NEXT: // implicit-def: $q28
; CHECK-NEXT: // implicit-def: $q14
; CHECK-NEXT: // implicit-def: $q15
; CHECK-NEXT: // implicit-def: $q29
; CHECK-NEXT: // implicit-def: $q30
; CHECK-NEXT: // implicit-def: $q11
; CHECK-NEXT: // implicit-def: $q31
; CHECK-NEXT: // implicit-def: $q13
; CHECK-NEXT: // kill: killed $q1
; CHECK-NEXT: // implicit-def: $q1
; CHECK-NEXT: // kill: killed $q1
; CHECK-NEXT: .LBB0_1: // %for.cond1.preheader
; CHECK-NEXT: // =>This Inner Loop Header: Depth=1
; CHECK-NEXT: stp q29, q15, [sp] // 32-byte Folded Spill
; CHECK-NEXT: ldr q15, [x8]
; CHECK-NEXT: ldr x15, [x8]
; CHECK-NEXT: str q14, [sp, #32] // 16-byte Folded Spill
; CHECK-NEXT: add x20, x10, x11
; CHECK-NEXT: mov v8.16b, v28.16b
; CHECK-NEXT: fmov x2, d15
; CHECK-NEXT: mov x17, v15.d[1]
; CHECK-NEXT: ldr q14, [x8]
; CHECK-NEXT: mov v28.16b, v24.16b
; CHECK-NEXT: mov v24.16b, v20.16b
; CHECK-NEXT: mov v20.16b, v17.16b
; CHECK-NEXT: fmov x13, d14
; CHECK-NEXT: mov x16, v14.d[1]
; CHECK-NEXT: mov v17.16b, v5.16b
; CHECK-NEXT: mul x3, x2, x15
; CHECK-NEXT: ldr q14, [x9], #64
; CHECK-NEXT: ldr q5, [sp, #64] // 16-byte Folded Reload
; CHECK-NEXT: ldr x6, [x8]
; CHECK-NEXT: ldr x20, [x20, #128]
; CHECK-NEXT: mul x1, x17, x15
; CHECK-NEXT: mov x14, v14.d[1]
; CHECK-NEXT: fmov x5, d14
; CHECK-NEXT: mov v29.16b, v21.16b
; CHECK-NEXT: mov v21.16b, v0.16b
; CHECK-NEXT: mov v25.16b, v6.16b
; CHECK-NEXT: mul x18, x13, x15
; CHECK-NEXT: mov v6.16b, v2.16b
; CHECK-NEXT: mov v26.16b, v22.16b
; CHECK-NEXT: fmov d15, x3
; CHECK-NEXT: mov v22.16b, v18.16b
; CHECK-NEXT: mov v18.16b, v7.16b
; CHECK-NEXT: mul x0, x16, x15
; CHECK-NEXT: mov v7.16b, v3.16b
; CHECK-NEXT: mov v16.16b, v4.16b
; CHECK-NEXT: add x11, x11, #8
; CHECK-NEXT: add x12, x12, #1
; CHECK-NEXT: mov v15.d[1], x1
; CHECK-NEXT: mul x4, x14, x15
; CHECK-NEXT: cmp x11, #64
; CHECK-NEXT: fmov d14, x18
; CHECK-NEXT: mul x15, x5, x15
; CHECK-NEXT: add v5.2d, v5.2d, v15.2d
; CHECK-NEXT: mul x21, x2, x6
; CHECK-NEXT: mov v14.d[1], x0
; CHECK-NEXT: mul x2, x2, x20
; CHECK-NEXT: fmov d0, x15
; CHECK-NEXT: str q5, [sp, #64] // 16-byte Folded Spill
; CHECK-NEXT: ldr q5, [sp, #48] // 16-byte Folded Reload
; CHECK-NEXT: mul x22, x13, x20
; CHECK-NEXT: add v5.2d, v5.2d, v14.2d
; CHECK-NEXT: fmov d3, x21
; CHECK-NEXT: mul x19, x17, x6
; CHECK-NEXT: mov v0.d[1], x4
; CHECK-NEXT: fmov d1, x2
; CHECK-NEXT: mul x17, x17, x20
; CHECK-NEXT: str q5, [sp, #48] // 16-byte Folded Spill
; CHECK-NEXT: add v5.2d, v13.2d, v14.2d
; CHECK-NEXT: fmov d2, x22
; CHECK-NEXT: ldr q13, [sp, #80] // 16-byte Folded Reload
; CHECK-NEXT: mul x7, x16, x6
; CHECK-NEXT: ldp q15, q14, [sp, #16] // 32-byte Folded Reload
; CHECK-NEXT: mov v3.d[1], x19
; CHECK-NEXT: add v13.2d, v13.2d, v0.2d
; CHECK-NEXT: mul x16, x16, x20
; CHECK-NEXT: mov v1.d[1], x17
; CHECK-NEXT: mul x23, x5, x20
; CHECK-NEXT: str q13, [sp, #80] // 16-byte Folded Spill
; CHECK-NEXT: mov v13.16b, v5.16b
; CHECK-NEXT: mov v5.16b, v17.16b
; CHECK-NEXT: mov v17.16b, v20.16b
; CHECK-NEXT: mov v20.16b, v24.16b
; CHECK-NEXT: mul x13, x13, x6
; CHECK-NEXT: mov v24.16b, v28.16b
; CHECK-NEXT: add v11.2d, v11.2d, v3.2d
; CHECK-NEXT: mov v2.d[1], x16
; CHECK-NEXT: add v15.2d, v15.2d, v1.2d
; CHECK-NEXT: add v27.2d, v27.2d, v3.2d
; CHECK-NEXT: mul x18, x14, x20
; CHECK-NEXT: add v23.2d, v23.2d, v3.2d
; CHECK-NEXT: add v19.2d, v19.2d, v3.2d
; CHECK-NEXT: fmov d4, x23
; CHECK-NEXT: add v10.2d, v10.2d, v3.2d
; CHECK-NEXT: mul x15, x5, x6
; CHECK-NEXT: fmov d0, x13
; CHECK-NEXT: add v14.2d, v14.2d, v2.2d
; CHECK-NEXT: add v2.2d, v6.2d, v3.2d
; CHECK-NEXT: mul x14, x14, x6
; CHECK-NEXT: mov v3.16b, v7.16b
; CHECK-NEXT: mov v7.16b, v18.16b
; CHECK-NEXT: mov v4.d[1], x18
; CHECK-NEXT: mov v18.16b, v22.16b
; CHECK-NEXT: mov v0.d[1], x7
; CHECK-NEXT: fmov d1, x15
; CHECK-NEXT: add v28.2d, v8.2d, v4.2d
; CHECK-NEXT: mov v1.d[1], x14
; CHECK-NEXT: add v31.2d, v31.2d, v0.2d
; CHECK-NEXT: add v30.2d, v30.2d, v0.2d
; CHECK-NEXT: add v12.2d, v12.2d, v0.2d
; CHECK-NEXT: add v24.2d, v24.2d, v0.2d
; CHECK-NEXT: add v22.2d, v26.2d, v0.2d
; CHECK-NEXT: add v20.2d, v20.2d, v0.2d
; CHECK-NEXT: add v18.2d, v18.2d, v0.2d
; CHECK-NEXT: add v17.2d, v17.2d, v0.2d
; CHECK-NEXT: add v7.2d, v7.2d, v0.2d
; CHECK-NEXT: add v4.2d, v16.2d, v0.2d
; CHECK-NEXT: add v3.2d, v3.2d, v0.2d
; CHECK-NEXT: mov v0.16b, v21.16b
; CHECK-NEXT: mov v21.16b, v29.16b
; CHECK-NEXT: ldr q29, [sp] // 16-byte Folded Reload
; CHECK-NEXT: add v9.2d, v9.2d, v1.2d
; CHECK-NEXT: add v6.2d, v25.2d, v1.2d
; CHECK-NEXT: add v5.2d, v5.2d, v1.2d
; CHECK-NEXT: add v29.2d, v29.2d, v1.2d
; CHECK-NEXT: add v21.2d, v21.2d, v1.2d
; CHECK-NEXT: add v0.2d, v0.2d, v1.2d
; CHECK-NEXT: b.ne .LBB0_1
; CHECK-NEXT: // %bb.2: // %for.cond.cleanup
; CHECK-NEXT: ldr q1, [sp, #48] // 16-byte Folded Reload
; CHECK-NEXT: adrp x8, C
; CHECK-NEXT: add x8, x8, :lo12:C
; CHECK-NEXT: stp q11, q30, [x8, #80]
; CHECK-NEXT: ldp x20, x19, [sp, #192] // 16-byte Folded Reload
; CHECK-NEXT: str q1, [x8]
; CHECK-NEXT: ldr q1, [sp, #64] // 16-byte Folded Reload
; CHECK-NEXT: ldr x23, [sp, #160] // 8-byte Folded Reload
; CHECK-NEXT: stp q15, q14, [x8, #144]
; CHECK-NEXT: ldp x22, x21, [sp, #176] // 16-byte Folded Reload
; CHECK-NEXT: stp q1, q13, [x8, #16]
; CHECK-NEXT: ldr q1, [sp, #80] // 16-byte Folded Reload
; CHECK-NEXT: stp q28, q12, [x8, #176]
; CHECK-NEXT: ldp d13, d12, [sp, #112] // 16-byte Folded Reload
; CHECK-NEXT: stp q1, q31, [x8, #48]
; CHECK-NEXT: ldp d15, d14, [sp, #96] // 16-byte Folded Reload
; CHECK-NEXT: stp q9, q24, [x8, #240]
; CHECK-NEXT: ldp d9, d8, [sp, #144] // 16-byte Folded Reload
; CHECK-NEXT: stp q19, q18, [x8, #336]
; CHECK-NEXT: stp q10, q7, [x8, #400]
; CHECK-NEXT: ldp d11, d10, [sp, #128] // 16-byte Folded Reload
; CHECK-NEXT: str q29, [x8, #112]
; CHECK-NEXT: str q27, [x8, #208]
; CHECK-NEXT: stp q23, q22, [x8, #272]
; CHECK-NEXT: stp q21, q20, [x8, #304]
; CHECK-NEXT: stp q6, q17, [x8, #368]
; CHECK-NEXT: stp q5, q4, [x8, #432]
; CHECK-NEXT: stp q2, q3, [x8, #464]
; CHECK-NEXT: str q0, [x8, #496]
; CHECK-NEXT: add sp, sp, #208
; CHECK-NEXT: .cfi_def_cfa_offset 0
; CHECK-NEXT: .cfi_restore w19
; CHECK-NEXT: .cfi_restore w20
; CHECK-NEXT: .cfi_restore w21
; CHECK-NEXT: .cfi_restore w22
; CHECK-NEXT: .cfi_restore w23
; CHECK-NEXT: .cfi_restore b8
; CHECK-NEXT: .cfi_restore b9
; CHECK-NEXT: .cfi_restore b10
; CHECK-NEXT: .cfi_restore b11
; CHECK-NEXT: .cfi_restore b12
; CHECK-NEXT: .cfi_restore b13
; CHECK-NEXT: .cfi_restore b14
; CHECK-NEXT: .cfi_restore b15
; CHECK-NEXT: ret
; CH`ECK-NEXT: .cfi_offset b9, -16
entry:
br label %for.cond1.preheader
for.cond1.preheader: ; preds = %for.cond1.preheader, %entry
%0 = phi <2 x i64> [ undef, %entry ], [ %118, %for.cond1.preheader ]
%1 = phi <2 x i64> [ undef, %entry ], [ %116, %for.cond1.preheader ]
%2 = phi <2 x i64> [ zeroinitializer, %entry ], [ %114, %for.cond1.preheader ]
%3 = phi <2 x i64> [ undef, %entry ], [ %112, %for.cond1.preheader ]
%4 = phi <2 x i64> [ undef, %entry ], [ %107, %for.cond1.preheader ]
%5 = phi <2 x i64> [ undef, %entry ], [ %105, %for.cond1.preheader ]
%6 = phi <2 x i64> [ undef, %entry ], [ %103, %for.cond1.preheader ]
%7 = phi <2 x i64> [ undef, %entry ], [ %101, %for.cond1.preheader ]
%8 = phi <2 x i64> [ undef, %entry ], [ %96, %for.cond1.preheader ]
%9 = phi <2 x i64> [ undef, %entry ], [ %94, %for.cond1.preheader ]
%10 = phi <2 x i64> [ undef, %entry ], [ %92, %for.cond1.preheader ]
%11 = phi <2 x i64> [ undef, %entry ], [ %90, %for.cond1.preheader ]
%12 = phi <2 x i64> [ undef, %entry ], [ %85, %for.cond1.preheader ]
%13 = phi <2 x i64> [ undef, %entry ], [ %83, %for.cond1.preheader ]
%14 = phi <2 x i64> [ undef, %entry ], [ %81, %for.cond1.preheader ]
%15 = phi <2 x i64> [ undef, %entry ], [ %79, %for.cond1.preheader ]
%16 = phi <2 x i64> [ undef, %entry ], [ %74, %for.cond1.preheader ]
%17 = phi <2 x i64> [ undef, %entry ], [ %72, %for.cond1.preheader ]
%18 = phi <2 x i64> [ undef, %entry ], [ %70, %for.cond1.preheader ]
%19 = phi <2 x i64> [ undef, %entry ], [ %65, %for.cond1.preheader ]
%20 = phi <2 x i64> [ undef, %entry ], [ %63, %for.cond1.preheader ]
%21 = phi <2 x i64> [ undef, %entry ], [ %61, %for.cond1.preheader ]
%22 = phi <2 x i64> [ undef, %entry ], [ %56, %for.cond1.preheader ]
%23 = phi <2 x i64> [ undef, %entry ], [ %54, %for.cond1.preheader ]
%24 = phi <2 x i64> [ undef, %entry ], [ %52, %for.cond1.preheader ]
%25 = phi <2 x i64> [ undef, %entry ], [ %50, %for.cond1.preheader ]
%26 = phi <2 x i64> [ undef, %entry ], [ %45, %for.cond1.preheader ]
%27 = phi <2 x i64> [ undef, %entry ], [ %43, %for.cond1.preheader ]
%28 = phi <2 x i64> [ undef, %entry ], [ %41, %for.cond1.preheader ]
%29 = phi <2 x i64> [ undef, %entry ], [ %39, %for.cond1.preheader ]
%indvars.iv40 = phi i64 [ 0, %entry ], [ %indvars.iv.next41, %for.cond1.preheader ]
%30 = load <2 x i64>, ptr null, align 8
%31 = load <2 x i64>, ptr undef, align 8
%arrayidx14.4.phi.trans.insert = getelementptr inbounds [8 x [8 x i64]], ptr @B, i64 0, i64 %indvars.iv40, i64 4
%32 = load <2 x i64>, ptr null, align 8
%arrayidx14.6.phi.trans.insert = getelementptr inbounds [8 x [8 x i64]], ptr @B, i64 0, i64 %indvars.iv40, i64 6
%33 = bitcast ptr %arrayidx14.6.phi.trans.insert to ptr
%34 = load <2 x i64>, ptr %33, align 8
%35 = load i64, ptr null, align 8
%36 = insertelement <2 x i64> undef, i64 %35, i32 0
%37 = shufflevector <2 x i64> %36, <2 x i64> undef, <2 x i32> zeroinitializer
%38 = mul nsw <2 x i64> %30, %37
%39 = add nsw <2 x i64> %29, %38
%40 = mul nsw <2 x i64> %31, %37
%41 = add nsw <2 x i64> %28, %40
%42 = mul nsw <2 x i64> %32, %37
%43 = add nsw <2 x i64> %27, %42
%44 = mul nsw <2 x i64> %34, %37
%45 = add nsw <2 x i64> %26, %44
%46 = load i64, ptr undef, align 8
%47 = insertelement <2 x i64> undef, i64 %46, i32 0
%48 = shufflevector <2 x i64> %47, <2 x i64> undef, <2 x i32> zeroinitializer
%49 = mul nsw <2 x i64> %30, %48
%50 = add nsw <2 x i64> %25, %49
%51 = mul nsw <2 x i64> %31, %48
%52 = add nsw <2 x i64> %24, %51
%53 = mul nsw <2 x i64> %32, %48
%54 = add nsw <2 x i64> %23, %53
%55 = mul nsw <2 x i64> %34, %48
%56 = add nsw <2 x i64> %22, %55
%arrayidx10.2 = getelementptr inbounds [8 x [8 x i64]], ptr @A, i64 0, i64 2, i64 %indvars.iv40
%57 = load i64, ptr %arrayidx10.2, align 8
%58 = insertelement <2 x i64> undef, i64 %57, i32 0
%59 = shufflevector <2 x i64> %58, <2 x i64> undef, <2 x i32> zeroinitializer
%60 = mul nsw <2 x i64> %31, %59
%61 = add nsw <2 x i64> %21, %60
%62 = mul nsw <2 x i64> %32, %59
%63 = add nsw <2 x i64> %20, %62
%64 = mul nsw <2 x i64> %34, %59
%65 = add nsw <2 x i64> %19, %64
%66 = load i64, ptr undef, align 8
%67 = insertelement <2 x i64> undef, i64 %66, i32 0
%68 = shufflevector <2 x i64> %67, <2 x i64> undef, <2 x i32> zeroinitializer
%69 = mul nsw <2 x i64> %30, %68
%70 = add nsw <2 x i64> %18, %69
%71 = mul nsw <2 x i64> %31, %68
%72 = add nsw <2 x i64> %17, %71
%73 = mul nsw <2 x i64> %34, %68
%74 = add nsw <2 x i64> %16, %73
%75 = load i64, ptr undef, align 8
%76 = insertelement <2 x i64> undef, i64 %75, i32 0
%77 = shufflevector <2 x i64> %76, <2 x i64> undef, <2 x i32> zeroinitializer
%78 = mul nsw <2 x i64> %30, %77
%79 = add nsw <2 x i64> %15, %78
%80 = mul nsw <2 x i64> %31, %77
%81 = add nsw <2 x i64> %14, %80
%82 = mul nsw <2 x i64> %32, %77
%83 = add nsw <2 x i64> %13, %82
%84 = mul nsw <2 x i64> %34, %77
%85 = add nsw <2 x i64> %12, %84
%86 = load i64, ptr undef, align 8
%87 = insertelement <2 x i64> undef, i64 %86, i32 0
%88 = shufflevector <2 x i64> %87, <2 x i64> undef, <2 x i32> zeroinitializer
%89 = mul nsw <2 x i64> %30, %88
%90 = add nsw <2 x i64> %11, %89
%91 = mul nsw <2 x i64> %31, %88
%92 = add nsw <2 x i64> %10, %91
%93 = mul nsw <2 x i64> %32, %88
%94 = add nsw <2 x i64> %9, %93
%95 = mul nsw <2 x i64> %34, %88
%96 = add nsw <2 x i64> %8, %95
%97 = load i64, ptr undef, align 8
%98 = insertelement <2 x i64> undef, i64 %97, i32 0
%99 = shufflevector <2 x i64> %98, <2 x i64> undef, <2 x i32> zeroinitializer
%100 = mul nsw <2 x i64> %30, %99
%101 = add nsw <2 x i64> %7, %100
%102 = mul nsw <2 x i64> %31, %99
%103 = add nsw <2 x i64> %6, %102
%104 = mul nsw <2 x i64> %32, %99
%105 = add nsw <2 x i64> %5, %104
%106 = mul nsw <2 x i64> %34, %99
%107 = add nsw <2 x i64> %4, %106
%108 = load i64, ptr undef, align 8
%109 = insertelement <2 x i64> undef, i64 %108, i32 0
%110 = shufflevector <2 x i64> %109, <2 x i64> undef, <2 x i32> zeroinitializer
%111 = mul nsw <2 x i64> %30, %110
%112 = add nsw <2 x i64> %3, %111
%113 = mul nsw <2 x i64> %31, %110
%114 = add nsw <2 x i64> %2, %113
%115 = mul nsw <2 x i64> %32, %110
%116 = add nsw <2 x i64> %1, %115
%117 = mul nsw <2 x i64> %34, %110
%118 = add nsw <2 x i64> %0, %117
%indvars.iv.next41 = add nuw nsw i64 %indvars.iv40, 1
%exitcond42 = icmp eq i64 %indvars.iv.next41, 8
br i1 %exitcond42, label %for.cond.cleanup, label %for.cond1.preheader
for.cond.cleanup: ; preds = %for.cond1.preheader
store <2 x i64> %39, ptr @C, align 8
store <2 x i64> %41, ptr getelementptr inbounds ([8 x [8 x i64]], ptr @C, i64 0, i64 0, i64 2), align 8
store <2 x i64> %43, ptr getelementptr inbounds ([8 x [8 x i64]], ptr @C, i64 0, i64 0, i64 4), align 8
store <2 x i64> %45, ptr getelementptr inbounds ([8 x [8 x i64]], ptr @C, i64 0, i64 0, i64 6), align 8
store <2 x i64> %50, ptr getelementptr inbounds ([8 x [8 x i64]], ptr @C, i64 0, i64 1, i64 0), align 8
store <2 x i64> %52, ptr getelementptr inbounds ([8 x [8 x i64]], ptr @C, i64 0, i64 1, i64 2), align 8
store <2 x i64> %54, ptr getelementptr inbounds ([8 x [8 x i64]], ptr @C, i64 0, i64 1, i64 4), align 8
store <2 x i64> %56, ptr getelementptr inbounds ([8 x [8 x i64]], ptr @C, i64 0, i64 1, i64 6), align 8
store <2 x i64> %61, ptr getelementptr inbounds ([8 x [8 x i64]], ptr @C, i64 0, i64 2, i64 2), align 8
store <2 x i64> %63, ptr getelementptr inbounds ([8 x [8 x i64]], ptr @C, i64 0, i64 2, i64 4), align 8
store <2 x i64> %65, ptr getelementptr inbounds ([8 x [8 x i64]], ptr @C, i64 0, i64 2, i64 6), align 8
store <2 x i64> %70, ptr getelementptr inbounds ([8 x [8 x i64]], ptr @C, i64 0, i64 3, i64 0), align 8
store <2 x i64> %72, ptr getelementptr inbounds ([8 x [8 x i64]], ptr @C, i64 0, i64 3, i64 2), align 8
store <2 x i64> %74, ptr getelementptr inbounds ([8 x [8 x i64]], ptr @C, i64 0, i64 3, i64 6), align 8
store <2 x i64> %79, ptr getelementptr inbounds ([8 x [8 x i64]], ptr @C, i64 0, i64 4, i64 0), align 8
store <2 x i64> %81, ptr getelementptr inbounds ([8 x [8 x i64]], ptr @C, i64 0, i64 4, i64 2), align 8
store <2 x i64> %83, ptr getelementptr inbounds ([8 x [8 x i64]], ptr @C, i64 0, i64 4, i64 4), align 8
store <2 x i64> %85, ptr getelementptr inbounds ([8 x [8 x i64]], ptr @C, i64 0, i64 4, i64 6), align 8
store <2 x i64> %90, ptr getelementptr inbounds ([8 x [8 x i64]], ptr @C, i64 0, i64 5, i64 0), align 8
store <2 x i64> %92, ptr getelementptr inbounds ([8 x [8 x i64]], ptr @C, i64 0, i64 5, i64 2), align 8
store <2 x i64> %94, ptr getelementptr inbounds ([8 x [8 x i64]], ptr @C, i64 0, i64 5, i64 4), align 8
store <2 x i64> %96, ptr getelementptr inbounds ([8 x [8 x i64]], ptr @C, i64 0, i64 5, i64 6), align 8
store <2 x i64> %101, ptr getelementptr inbounds ([8 x [8 x i64]], ptr @C, i64 0, i64 6, i64 0), align 8
store <2 x i64> %103, ptr getelementptr inbounds ([8 x [8 x i64]], ptr @C, i64 0, i64 6, i64 2), align 8
store <2 x i64> %105, ptr getelementptr inbounds ([8 x [8 x i64]], ptr @C, i64 0, i64 6, i64 4), align 8
store <2 x i64> %107, ptr getelementptr inbounds ([8 x [8 x i64]], ptr @C, i64 0, i64 6, i64 6), align 8
store <2 x i64> %112, ptr getelementptr inbounds ([8 x [8 x i64]], ptr @C, i64 0, i64 7, i64 0), align 8
store <2 x i64> %114, ptr getelementptr inbounds ([8 x [8 x i64]], ptr @C, i64 0, i64 7, i64 2), align 8
store <2 x i64> %116, ptr getelementptr inbounds ([8 x [8 x i64]], ptr @C, i64 0, i64 7, i64 4), align 8
store <2 x i64> %118, ptr getelementptr inbounds ([8 x [8 x i64]], ptr @C, i64 0, i64 7, i64 6), align 8
ret void
}
|
