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
|
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -verify-machineinstrs -mtriple powerpc64le-unknown-linux-gnu \
; RUN: -mcpu=pwr10 -ppc-vsr-nums-as-vr -ppc-asm-full-reg-names < %s \
; RUN: | FileCheck %s
; RUN: llc -verify-machineinstrs -mtriple powerpc64le-unknown-linux-gnu \
; RUN: -mcpu=pwr10 -ppc-vsr-nums-as-vr -ppc-asm-full-reg-names \
; RUN: -ppc-track-subreg-liveness < %s | FileCheck %s --check-prefix=TRACKLIVE
%0 = type <{ double }>
%1 = type <{ double }>
define void @acc_regalloc(i32* %arg, [0 x %0]* %arg1, [0 x %1]* %arg2) local_unnamed_addr {
; CHECK-LABEL: acc_regalloc:
; CHECK: # %bb.0: # %bb
; CHECK-NEXT: lwz r3, 0(r3)
; CHECK-NEXT: lxv v4, 0(0)
; CHECK-NEXT: xxlxor v0, v0, v0
; CHECK-NEXT: xxlxor v1, v1, v1
; CHECK-NEXT: xxlxor v2, v2, v2
; CHECK-NEXT: li r6, 1
; CHECK-NEXT: li r4, 16
; CHECK-NEXT: stfd f14, -144(r1) # 8-byte Folded Spill
; CHECK-NEXT: stfd f15, -136(r1) # 8-byte Folded Spill
; CHECK-NEXT: extswsli r3, r3, 3
; CHECK-NEXT: xvmaddadp v1, v4, v1
; CHECK-NEXT: lxvdsx v5, 0, r3
; CHECK-NEXT: xvmaddadp v0, v5, v0
; CHECK-NEXT: .p2align 4
; CHECK-NEXT: .LBB0_1: # %bb9
; CHECK-NEXT: #
; CHECK-NEXT: addi r6, r6, 2
; CHECK-NEXT: lxv vs0, 16(0)
; CHECK-NEXT: lxv vs1, -64(r5)
; CHECK-NEXT: xxlxor v7, v7, v7
; CHECK-NEXT: vmr v9, v0
; CHECK-NEXT: xxlxor v10, v10, v10
; CHECK-NEXT: mulld r6, r6, r3
; CHECK-NEXT: xvmaddadp v7, vs0, v5
; CHECK-NEXT: xvmuldp v6, vs0, v2
; CHECK-NEXT: lxv vs0, -16(r5)
; CHECK-NEXT: xvmaddadp v9, vs1, v2
; CHECK-NEXT: xxlxor v8, v8, v8
; CHECK-NEXT: xvmaddadp v7, v2, v2
; CHECK-NEXT: xvmaddadp v6, v2, v2
; CHECK-NEXT: lxvdsx v14, r6, r4
; CHECK-NEXT: li r6, 0
; CHECK-NEXT: xvmaddadp v8, vs1, v8
; CHECK-NEXT: xvmaddadp v10, vs0, v10
; CHECK-NEXT: xvmuldp v3, vs1, v14
; CHECK-NEXT: xvmuldp v11, vs0, v14
; CHECK-NEXT: xvmuldp vs5, v14, v2
; CHECK-NEXT: xvmuldp v13, v4, v14
; CHECK-NEXT: xxlor vs0, v2, v2
; CHECK-NEXT: vmr v12, v2
; CHECK-NEXT: xxlor vs14, v10, v10
; CHECK-NEXT: xxlor vs4, v2, v2
; CHECK-NEXT: # kill: def $vsrp2 killed $vsrp2 def $uacc1
; CHECK-NEXT: xxlor vs6, v6, v6
; CHECK-NEXT: xxlor vs7, v7, v7
; CHECK-NEXT: xxlor vs8, v12, v12
; CHECK-NEXT: xxlor vs9, v13, v13
; CHECK-NEXT: vmr v12, v1
; CHECK-NEXT: xxlor vs1, v3, v3
; CHECK-NEXT: xxlor vs2, v8, v8
; CHECK-NEXT: xxlor vs3, v9, v9
; CHECK-NEXT: xxlor vs15, v11, v11
; CHECK-NEXT: vmr v10, v2
; CHECK-NEXT: xxlor vs10, v12, v12
; CHECK-NEXT: xxlor vs11, v13, v13
; CHECK-NEXT: xxmtacc acc1
; CHECK-NEXT: xxlor vs12, v10, v10
; CHECK-NEXT: xxlor vs13, v11, v11
; CHECK-NEXT: xxmtacc acc0
; CHECK-NEXT: xxmtacc acc2
; CHECK-NEXT: xxmtacc acc3
; CHECK-NEXT: xvf64gerpp acc0, vsp34, vs0
; CHECK-NEXT: xvf64gerpp acc1, vsp34, vs0
; CHECK-NEXT: xvf64gerpp acc2, vsp34, vs0
; CHECK-NEXT: xvf64gerpp acc3, vsp34, vs0
; CHECK-NEXT: xvf64gerpp acc0, vsp34, vs0
; CHECK-NEXT: xvf64gerpp acc1, vsp34, vs0
; CHECK-NEXT: xvf64gerpp acc2, vsp34, vs0
; CHECK-NEXT: xvf64gerpp acc3, vsp34, vs0
; CHECK-NEXT: xvf64gerpp acc0, vsp34, vs0
; CHECK-NEXT: xvf64gerpp acc1, vsp34, vs0
; CHECK-NEXT: xvf64gerpp acc2, vsp34, vs0
; CHECK-NEXT: xvf64gerpp acc3, vsp34, vs0
; CHECK-NEXT: xvf64gerpp acc0, vsp34, vs0
; CHECK-NEXT: xvf64gerpp acc1, vsp34, vs0
; CHECK-NEXT: xvf64gerpp acc2, vsp34, vs0
; CHECK-NEXT: xvf64gerpp acc3, vsp34, vs0
; CHECK-NEXT: xvf64gerpp acc0, vsp34, vs0
; CHECK-NEXT: xvf64gerpp acc1, vsp34, vs0
; CHECK-NEXT: xvf64gerpp acc2, vsp34, vs0
; CHECK-NEXT: xvf64gerpp acc3, vsp34, vs0
; CHECK-NEXT: xvf64gerpp acc0, vsp34, vs0
; CHECK-NEXT: xvf64gerpp acc1, vsp34, vs0
; CHECK-NEXT: xvf64gerpp acc2, vsp34, vs0
; CHECK-NEXT: xvf64gerpp acc3, vsp34, vs0
; CHECK-NEXT: xvf64gerpp acc0, vsp34, vs0
; CHECK-NEXT: xvf64gerpp acc1, vsp34, vs0
; CHECK-NEXT: xvf64gerpp acc2, vsp34, vs0
; CHECK-NEXT: xvf64gerpp acc3, vsp34, vs0
; CHECK-NEXT: xxmfacc acc0
; CHECK-NEXT: xxmfacc acc1
; CHECK-NEXT: xxmfacc acc2
; CHECK-NEXT: xxmfacc acc3
; CHECK-NEXT: stxv vs1, 0(r3)
; CHECK-NEXT: stxv vs9, 32(r3)
; CHECK-NEXT: stxv vs4, 16(0)
; CHECK-NEXT: stxv vs12, 48(0)
; CHECK-NEXT: b .LBB0_1
;
; TRACKLIVE-LABEL: acc_regalloc:
; TRACKLIVE: # %bb.0: # %bb
; TRACKLIVE-NEXT: lwz r3, 0(r3)
; TRACKLIVE-NEXT: lxv v4, 0(0)
; TRACKLIVE-NEXT: xxlxor v0, v0, v0
; TRACKLIVE-NEXT: xxlxor v1, v1, v1
; TRACKLIVE-NEXT: xxlxor v2, v2, v2
; TRACKLIVE-NEXT: li r6, 1
; TRACKLIVE-NEXT: li r4, 16
; TRACKLIVE-NEXT: stfd f14, -144(r1) # 8-byte Folded Spill
; TRACKLIVE-NEXT: stfd f15, -136(r1) # 8-byte Folded Spill
; TRACKLIVE-NEXT: extswsli r3, r3, 3
; TRACKLIVE-NEXT: xvmaddadp v1, v4, v1
; TRACKLIVE-NEXT: lxvdsx v5, 0, r3
; TRACKLIVE-NEXT: xvmaddadp v0, v5, v0
; TRACKLIVE-NEXT: .p2align 4
; TRACKLIVE-NEXT: .LBB0_1: # %bb9
; TRACKLIVE-NEXT: #
; TRACKLIVE-NEXT: addi r6, r6, 2
; TRACKLIVE-NEXT: lxv vs0, 16(0)
; TRACKLIVE-NEXT: lxv vs1, -64(r5)
; TRACKLIVE-NEXT: xxlxor vs7, vs7, vs7
; TRACKLIVE-NEXT: xxlor vs3, v0, v0
; TRACKLIVE-NEXT: xxlxor vs2, vs2, vs2
; TRACKLIVE-NEXT: xxlxor vs12, vs12, vs12
; TRACKLIVE-NEXT: mulld r6, r6, r3
; TRACKLIVE-NEXT: xxlor vs10, v2, v2
; TRACKLIVE-NEXT: xxlor vs4, v2, v2
; TRACKLIVE-NEXT: xxlor vs8, vs10, vs10
; TRACKLIVE-NEXT: xxlor vs10, v1, v1
; TRACKLIVE-NEXT: xvmaddadp vs7, vs0, v5
; TRACKLIVE-NEXT: xvmuldp vs6, vs0, v2
; TRACKLIVE-NEXT: lxv vs0, -16(r5)
; TRACKLIVE-NEXT: xvmaddadp vs3, vs1, v2
; TRACKLIVE-NEXT: xvmaddadp vs2, vs1, vs2
; TRACKLIVE-NEXT: lxvdsx v6, r6, r4
; TRACKLIVE-NEXT: li r6, 0
; TRACKLIVE-NEXT: xvmaddadp vs7, v2, v2
; TRACKLIVE-NEXT: xvmaddadp vs6, v2, v2
; TRACKLIVE-NEXT: xvmaddadp vs12, vs0, vs12
; TRACKLIVE-NEXT: xvmuldp v3, vs1, v6
; TRACKLIVE-NEXT: xvmuldp vs11, v4, v6
; TRACKLIVE-NEXT: xvmuldp vs13, vs0, v6
; TRACKLIVE-NEXT: xvmuldp vs5, v6, v2
; TRACKLIVE-NEXT: xxlor vs0, v2, v2
; TRACKLIVE-NEXT: xxlor vs14, vs12, vs12
; TRACKLIVE-NEXT: xxlor vs12, v2, v2
; TRACKLIVE-NEXT: xxlor vs1, v3, v3
; TRACKLIVE-NEXT: xxlor vs9, vs11, vs11
; TRACKLIVE-NEXT: xxlor vs15, vs13, vs13
; TRACKLIVE-NEXT: xxmtacc acc1
; TRACKLIVE-NEXT: xxmtacc acc0
; TRACKLIVE-NEXT: xxmtacc acc2
; TRACKLIVE-NEXT: xxmtacc acc3
; TRACKLIVE-NEXT: xvf64gerpp acc0, vsp34, vs0
; TRACKLIVE-NEXT: xvf64gerpp acc1, vsp34, vs0
; TRACKLIVE-NEXT: xvf64gerpp acc2, vsp34, vs0
; TRACKLIVE-NEXT: xvf64gerpp acc3, vsp34, vs0
; TRACKLIVE-NEXT: xvf64gerpp acc0, vsp34, vs0
; TRACKLIVE-NEXT: xvf64gerpp acc1, vsp34, vs0
; TRACKLIVE-NEXT: xvf64gerpp acc2, vsp34, vs0
; TRACKLIVE-NEXT: xvf64gerpp acc3, vsp34, vs0
; TRACKLIVE-NEXT: xvf64gerpp acc0, vsp34, vs0
; TRACKLIVE-NEXT: xvf64gerpp acc1, vsp34, vs0
; TRACKLIVE-NEXT: xvf64gerpp acc2, vsp34, vs0
; TRACKLIVE-NEXT: xvf64gerpp acc3, vsp34, vs0
; TRACKLIVE-NEXT: xvf64gerpp acc0, vsp34, vs0
; TRACKLIVE-NEXT: xvf64gerpp acc1, vsp34, vs0
; TRACKLIVE-NEXT: xvf64gerpp acc2, vsp34, vs0
; TRACKLIVE-NEXT: xvf64gerpp acc3, vsp34, vs0
; TRACKLIVE-NEXT: xvf64gerpp acc0, vsp34, vs0
; TRACKLIVE-NEXT: xvf64gerpp acc1, vsp34, vs0
; TRACKLIVE-NEXT: xvf64gerpp acc2, vsp34, vs0
; TRACKLIVE-NEXT: xvf64gerpp acc3, vsp34, vs0
; TRACKLIVE-NEXT: xvf64gerpp acc0, vsp34, vs0
; TRACKLIVE-NEXT: xvf64gerpp acc1, vsp34, vs0
; TRACKLIVE-NEXT: xvf64gerpp acc2, vsp34, vs0
; TRACKLIVE-NEXT: xvf64gerpp acc3, vsp34, vs0
; TRACKLIVE-NEXT: xvf64gerpp acc0, vsp34, vs0
; TRACKLIVE-NEXT: xvf64gerpp acc1, vsp34, vs0
; TRACKLIVE-NEXT: xvf64gerpp acc2, vsp34, vs0
; TRACKLIVE-NEXT: xvf64gerpp acc3, vsp34, vs0
; TRACKLIVE-NEXT: xxmfacc acc0
; TRACKLIVE-NEXT: xxmfacc acc1
; TRACKLIVE-NEXT: xxmfacc acc2
; TRACKLIVE-NEXT: xxmfacc acc3
; TRACKLIVE-NEXT: stxv vs1, 0(r3)
; TRACKLIVE-NEXT: stxv vs9, 32(r3)
; TRACKLIVE-NEXT: stxv vs4, 16(0)
; TRACKLIVE-NEXT: stxv vs12, 48(0)
; TRACKLIVE-NEXT: b .LBB0_1
bb:
%i = load i32, i32* %arg, align 4
%i3 = sext i32 %i to i64
%i4 = shl nsw i64 %i3, 3
%i5 = bitcast [0 x %0]* %arg1 to i8*
%i6 = getelementptr i8, i8* %i5, i64 undef
%i7 = getelementptr [0 x %1], [0 x %1]* %arg2, i64 0, i64 -8
%i8 = getelementptr i8, i8* %i6, i64 undef
br label %bb9
bb9: ; preds = %bb95, %bb
%i10 = phi i64 [ 1, %bb ], [ 0, %bb95 ]
%i11 = getelementptr %1, %1* null, i64 2
%i12 = bitcast %1* %i11 to <2 x double>*
%i13 = load <2 x double>, <2 x double>* %i12, align 1
%i14 = add nuw nsw i64 %i10, 2
%i15 = getelementptr inbounds %1, %1* %i7, i64 undef
%i16 = bitcast %1* %i15 to <2 x double>*
%i17 = load <2 x double>, <2 x double>* %i16, align 1
%i18 = load <2 x double>, <2 x double>* null, align 1
%i19 = getelementptr %1, %1* %i15, i64 6
%i20 = bitcast %1* %i19 to <2 x double>*
%i21 = load <2 x double>, <2 x double>* %i20, align 1
%i22 = load i64, i64* undef, align 8
%i23 = insertelement <2 x i64> poison, i64 %i22, i32 0
%i24 = bitcast <2 x i64> %i23 to <2 x double>
%i25 = shufflevector <2 x double> %i24, <2 x double> undef, <2 x i32> zeroinitializer
%i26 = mul i64 %i14, %i4
%i27 = getelementptr i8, i8* null, i64 %i26
%i28 = getelementptr inbounds i8, i8* %i27, i64 0
%i29 = getelementptr i8, i8* %i28, i64 16
%i30 = bitcast i8* %i29 to i64*
%i31 = load i64, i64* %i30, align 8
%i32 = insertelement <2 x i64> poison, i64 %i31, i32 0
%i33 = bitcast <2 x i64> %i32 to <2 x double>
%i34 = shufflevector <2 x double> %i33, <2 x double> undef, <2 x i32> zeroinitializer
%i35 = tail call contract <2 x double> @llvm.fma.v2f64(<2 x double> zeroinitializer, <2 x double> %i25, <2 x double> zeroinitializer)
%i36 = tail call contract <2 x double> @llvm.fma.v2f64(<2 x double> %i13, <2 x double> %i25, <2 x double> zeroinitializer)
%i37 = fmul contract <2 x double> %i13, zeroinitializer
%i38 = tail call contract <2 x double> @llvm.fma.v2f64(<2 x double> %i17, <2 x double> zeroinitializer, <2 x double> %i35)
%i39 = tail call contract <2 x double> @llvm.fma.v2f64(<2 x double> zeroinitializer, <2 x double> zeroinitializer, <2 x double> %i36)
%i40 = tail call contract <2 x double> @llvm.fma.v2f64(<2 x double> %i17, <2 x double> zeroinitializer, <2 x double> zeroinitializer)
%i41 = tail call contract <2 x double> @llvm.fma.v2f64(<2 x double> zeroinitializer, <2 x double> zeroinitializer, <2 x double> %i37)
%i42 = tail call contract <2 x double> @llvm.fma.v2f64(<2 x double> %i18, <2 x double> zeroinitializer, <2 x double> zeroinitializer)
%i43 = tail call contract <2 x double> @llvm.fma.v2f64(<2 x double> %i21, <2 x double> zeroinitializer, <2 x double> zeroinitializer)
%i44 = fmul contract <2 x double> %i17, %i34
%i45 = fmul contract <2 x double> zeroinitializer, %i34
%i46 = fmul contract <2 x double> %i18, %i34
%i47 = fmul contract <2 x double> %i21, %i34
%i48 = bitcast <2 x double> %i44 to <16 x i8>
%i49 = bitcast <2 x double> %i40 to <16 x i8>
%i50 = bitcast <2 x double> %i38 to <16 x i8>
%i51 = tail call <512 x i1> @llvm.ppc.mma.assemble.acc(<16 x i8> zeroinitializer, <16 x i8> %i48, <16 x i8> %i49, <16 x i8> %i50)
%i52 = bitcast <2 x double> %i45 to <16 x i8>
%i53 = bitcast <2 x double> %i41 to <16 x i8>
%i54 = bitcast <2 x double> %i39 to <16 x i8>
%i55 = tail call <512 x i1> @llvm.ppc.mma.assemble.acc(<16 x i8> zeroinitializer, <16 x i8> %i52, <16 x i8> %i53, <16 x i8> %i54)
%i56 = bitcast <2 x double> %i46 to <16 x i8>
%i57 = bitcast <2 x double> %i42 to <16 x i8>
%i58 = tail call <512 x i1> @llvm.ppc.mma.assemble.acc(<16 x i8> zeroinitializer, <16 x i8> %i56, <16 x i8> %i57, <16 x i8> %i56)
%i59 = bitcast <2 x double> %i47 to <16 x i8>
%i60 = bitcast <2 x double> %i43 to <16 x i8>
%i61 = tail call <512 x i1> @llvm.ppc.mma.assemble.acc(<16 x i8> zeroinitializer, <16 x i8> %i59, <16 x i8> %i60, <16 x i8> %i59)
%i62 = tail call <512 x i1> @llvm.ppc.mma.xvf64gerpp(<512 x i1> %i51, <256 x i1> undef, <16 x i8> undef)
%i63 = tail call <512 x i1> @llvm.ppc.mma.xvf64gerpp(<512 x i1> %i55, <256 x i1> undef, <16 x i8> undef)
%i64 = tail call <512 x i1> @llvm.ppc.mma.xvf64gerpp(<512 x i1> %i58, <256 x i1> undef, <16 x i8> undef)
%i65 = tail call <512 x i1> @llvm.ppc.mma.xvf64gerpp(<512 x i1> %i61, <256 x i1> undef, <16 x i8> undef)
%i66 = tail call <512 x i1> @llvm.ppc.mma.xvf64gerpp(<512 x i1> %i62, <256 x i1> undef, <16 x i8> undef)
%i67 = tail call <512 x i1> @llvm.ppc.mma.xvf64gerpp(<512 x i1> %i63, <256 x i1> undef, <16 x i8> undef)
%i68 = tail call <512 x i1> @llvm.ppc.mma.xvf64gerpp(<512 x i1> %i64, <256 x i1> undef, <16 x i8> undef)
%i69 = tail call <512 x i1> @llvm.ppc.mma.xvf64gerpp(<512 x i1> %i65, <256 x i1> undef, <16 x i8> undef)
%i70 = tail call <512 x i1> @llvm.ppc.mma.xvf64gerpp(<512 x i1> %i66, <256 x i1> undef, <16 x i8> undef)
%i71 = tail call <512 x i1> @llvm.ppc.mma.xvf64gerpp(<512 x i1> %i67, <256 x i1> undef, <16 x i8> undef)
%i72 = tail call <512 x i1> @llvm.ppc.mma.xvf64gerpp(<512 x i1> %i68, <256 x i1> undef, <16 x i8> undef)
%i73 = tail call <512 x i1> @llvm.ppc.mma.xvf64gerpp(<512 x i1> %i69, <256 x i1> undef, <16 x i8> undef)
%i74 = tail call <512 x i1> @llvm.ppc.mma.xvf64gerpp(<512 x i1> %i70, <256 x i1> undef, <16 x i8> undef)
%i75 = tail call <512 x i1> @llvm.ppc.mma.xvf64gerpp(<512 x i1> %i71, <256 x i1> undef, <16 x i8> undef)
%i76 = tail call <512 x i1> @llvm.ppc.mma.xvf64gerpp(<512 x i1> %i72, <256 x i1> undef, <16 x i8> undef)
%i77 = tail call <512 x i1> @llvm.ppc.mma.xvf64gerpp(<512 x i1> %i73, <256 x i1> undef, <16 x i8> undef)
%i78 = tail call <512 x i1> @llvm.ppc.mma.xvf64gerpp(<512 x i1> %i74, <256 x i1> undef, <16 x i8> undef)
%i79 = tail call <512 x i1> @llvm.ppc.mma.xvf64gerpp(<512 x i1> %i75, <256 x i1> undef, <16 x i8> undef)
%i80 = tail call <512 x i1> @llvm.ppc.mma.xvf64gerpp(<512 x i1> %i76, <256 x i1> undef, <16 x i8> undef)
%i81 = tail call <512 x i1> @llvm.ppc.mma.xvf64gerpp(<512 x i1> %i77, <256 x i1> undef, <16 x i8> undef)
br label %bb82
bb82: ; preds = %bb82, %bb9
%i83 = phi <512 x i1> [ %i94, %bb82 ], [ %i81, %bb9 ]
%i84 = phi <512 x i1> [ %i93, %bb82 ], [ %i80, %bb9 ]
%i85 = phi <512 x i1> [ %i92, %bb82 ], [ %i79, %bb9 ]
%i86 = phi <512 x i1> [ %i91, %bb82 ], [ %i78, %bb9 ]
%i87 = tail call <512 x i1> @llvm.ppc.mma.xvf64gerpp(<512 x i1> %i86, <256 x i1> undef, <16 x i8> undef)
%i88 = tail call <512 x i1> @llvm.ppc.mma.xvf64gerpp(<512 x i1> %i85, <256 x i1> undef, <16 x i8> undef)
%i89 = tail call <512 x i1> @llvm.ppc.mma.xvf64gerpp(<512 x i1> %i84, <256 x i1> undef, <16 x i8> undef)
%i90 = tail call <512 x i1> @llvm.ppc.mma.xvf64gerpp(<512 x i1> %i83, <256 x i1> undef, <16 x i8> undef)
%i91 = tail call <512 x i1> @llvm.ppc.mma.xvf64gerpp(<512 x i1> %i87, <256 x i1> undef, <16 x i8> undef)
%i92 = tail call <512 x i1> @llvm.ppc.mma.xvf64gerpp(<512 x i1> %i88, <256 x i1> undef, <16 x i8> undef)
%i93 = tail call <512 x i1> @llvm.ppc.mma.xvf64gerpp(<512 x i1> %i89, <256 x i1> undef, <16 x i8> undef)
%i94 = tail call <512 x i1> @llvm.ppc.mma.xvf64gerpp(<512 x i1> %i90, <256 x i1> undef, <16 x i8> undef)
br i1 undef, label %bb95, label %bb82
bb95: ; preds = %bb82
%i96 = tail call { <16 x i8>, <16 x i8>, <16 x i8>, <16 x i8> } @llvm.ppc.mma.disassemble.acc(<512 x i1> %i91)
%i97 = extractvalue { <16 x i8>, <16 x i8>, <16 x i8>, <16 x i8> } %i96, 2
%i98 = tail call { <16 x i8>, <16 x i8>, <16 x i8>, <16 x i8> } @llvm.ppc.mma.disassemble.acc(<512 x i1> %i92)
%i99 = extractvalue { <16 x i8>, <16 x i8>, <16 x i8>, <16 x i8> } %i98, 3
%i100 = tail call { <16 x i8>, <16 x i8>, <16 x i8>, <16 x i8> } @llvm.ppc.mma.disassemble.acc(<512 x i1> %i93)
%i101 = extractvalue { <16 x i8>, <16 x i8>, <16 x i8>, <16 x i8> } %i100, 2
%i102 = tail call { <16 x i8>, <16 x i8>, <16 x i8>, <16 x i8> } @llvm.ppc.mma.disassemble.acc(<512 x i1> %i94)
%i103 = extractvalue { <16 x i8>, <16 x i8>, <16 x i8>, <16 x i8> } %i102, 3
%i104 = getelementptr inbounds i8, i8* %i8, i64 undef
%i105 = bitcast i8* %i104 to <16 x i8>*
store <16 x i8> %i97, <16 x i8>* %i105, align 1
%i106 = getelementptr i8, i8* %i104, i64 32
%i107 = bitcast i8* %i106 to <16 x i8>*
store <16 x i8> %i101, <16 x i8>* %i107, align 1
%i108 = getelementptr i8, i8* null, i64 16
%i109 = bitcast i8* %i108 to <16 x i8>*
store <16 x i8> %i99, <16 x i8>* %i109, align 1
%i110 = getelementptr i8, i8* null, i64 48
%i111 = bitcast i8* %i110 to <16 x i8>*
store <16 x i8> %i103, <16 x i8>* %i111, align 1
br label %bb9
}
declare <2 x double> @llvm.fma.v2f64(<2 x double>, <2 x double>, <2 x double>)
declare <512 x i1> @llvm.ppc.mma.assemble.acc(<16 x i8>, <16 x i8>, <16 x i8>, <16 x i8>)
declare <512 x i1> @llvm.ppc.mma.xvf64gerpp(<512 x i1>, <256 x i1>, <16 x i8>)
declare { <16 x i8>, <16 x i8>, <16 x i8>, <16 x i8> } @llvm.ppc.mma.disassemble.acc(<512 x i1>)
|
