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
|
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt -loop-vectorize -dce -instcombine -mtriple aarch64-linux-gnu -mattr=+sve -S %s -o - | FileCheck %s
define void @cond_inv_load_i32i32i16(i32* noalias nocapture %a, i32* noalias nocapture readonly %cond, i16* noalias nocapture readonly %inv, i64 %n) #0 {
; CHECK-LABEL: @cond_inv_load_i32i32i16(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT: [[TMP1:%.*]] = shl nuw nsw i64 [[TMP0]], 2
; CHECK-NEXT: [[MIN_ITERS_CHECK:%.*]] = icmp ugt i64 [[TMP1]], [[N:%.*]]
; CHECK-NEXT: br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
; CHECK: vector.ph:
; CHECK-NEXT: [[TMP2:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT: [[TMP3:%.*]] = shl nuw nsw i64 [[TMP2]], 2
; CHECK-NEXT: [[N_MOD_VF:%.*]] = urem i64 [[N]], [[TMP3]]
; CHECK-NEXT: [[N_VEC:%.*]] = sub i64 [[N]], [[N_MOD_VF]]
; CHECK-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <vscale x 4 x i16*> poison, i16* [[INV:%.*]], i64 0
; CHECK-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <vscale x 4 x i16*> [[BROADCAST_SPLATINSERT]], <vscale x 4 x i16*> poison, <vscale x 4 x i32> zeroinitializer
; CHECK-NEXT: br label [[VECTOR_BODY:%.*]]
; CHECK: vector.body:
; CHECK-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT: [[TMP4:%.*]] = getelementptr inbounds i32, i32* [[COND:%.*]], i64 [[INDEX]]
; CHECK-NEXT: [[TMP5:%.*]] = bitcast i32* [[TMP4]] to <vscale x 4 x i32>*
; CHECK-NEXT: [[WIDE_LOAD:%.*]] = load <vscale x 4 x i32>, <vscale x 4 x i32>* [[TMP5]], align 4
; CHECK-NEXT: [[TMP6:%.*]] = icmp ne <vscale x 4 x i32> [[WIDE_LOAD]], zeroinitializer
; CHECK-NEXT: [[WIDE_MASKED_GATHER:%.*]] = call <vscale x 4 x i16> @llvm.masked.gather.nxv4i16.nxv4p0i16(<vscale x 4 x i16*> [[BROADCAST_SPLAT]], i32 2, <vscale x 4 x i1> [[TMP6]], <vscale x 4 x i16> undef)
; CHECK-NEXT: [[TMP7:%.*]] = sext <vscale x 4 x i16> [[WIDE_MASKED_GATHER]] to <vscale x 4 x i32>
; CHECK-NEXT: [[TMP8:%.*]] = getelementptr i32, i32* [[A:%.*]], i64 [[INDEX]]
; CHECK-NEXT: [[TMP9:%.*]] = bitcast i32* [[TMP8]] to <vscale x 4 x i32>*
; CHECK-NEXT: call void @llvm.masked.store.nxv4i32.p0nxv4i32(<vscale x 4 x i32> [[TMP7]], <vscale x 4 x i32>* [[TMP9]], i32 4, <vscale x 4 x i1> [[TMP6]])
; CHECK-NEXT: [[TMP10:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT: [[TMP11:%.*]] = shl nuw nsw i64 [[TMP10]], 2
; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP11]]
; CHECK-NEXT: [[TMP12:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
; CHECK-NEXT: br i1 [[TMP12]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
; CHECK: middle.block:
; CHECK-NEXT: [[CMP_N:%.*]] = icmp eq i64 [[N_MOD_VF]], 0
; CHECK-NEXT: br i1 [[CMP_N]], label [[EXIT:%.*]], label [[SCALAR_PH]]
; CHECK: scalar.ph:
; CHECK-NEXT: [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
; CHECK-NEXT: br label [[FOR_BODY:%.*]]
; CHECK: for.body:
; CHECK-NEXT: [[I_07:%.*]] = phi i64 [ [[INC:%.*]], [[FOR_INC:%.*]] ], [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ]
; CHECK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds i32, i32* [[COND]], i64 [[I_07]]
; CHECK-NEXT: [[TMP13:%.*]] = load i32, i32* [[ARRAYIDX]], align 4
; CHECK-NEXT: [[TOBOOL_NOT:%.*]] = icmp eq i32 [[TMP13]], 0
; CHECK-NEXT: br i1 [[TOBOOL_NOT]], label [[FOR_INC]], label [[IF_THEN:%.*]]
; CHECK: if.then:
; CHECK-NEXT: [[TMP14:%.*]] = load i16, i16* [[INV]], align 2
; CHECK-NEXT: [[CONV:%.*]] = sext i16 [[TMP14]] to i32
; CHECK-NEXT: [[ARRAYIDX1:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 [[I_07]]
; CHECK-NEXT: store i32 [[CONV]], i32* [[ARRAYIDX1]], align 4
; CHECK-NEXT: br label [[FOR_INC]]
; CHECK: for.inc:
; CHECK-NEXT: [[INC]] = add nuw nsw i64 [[I_07]], 1
; CHECK-NEXT: [[EXITCOND_NOT:%.*]] = icmp eq i64 [[INC]], [[N]]
; CHECK-NEXT: br i1 [[EXITCOND_NOT]], label [[EXIT]], label [[FOR_BODY]], !llvm.loop [[LOOP3:![0-9]+]]
; CHECK: exit:
; CHECK-NEXT: ret void
;
entry:
br label %for.body
for.body: ; preds = %entry, %for.inc
%i.07 = phi i64 [ %inc, %for.inc ], [ 0, %entry ]
%arrayidx = getelementptr inbounds i32, i32* %cond, i64 %i.07
%0 = load i32, i32* %arrayidx, align 4
%tobool.not = icmp eq i32 %0, 0
br i1 %tobool.not, label %for.inc, label %if.then
if.then: ; preds = %for.body
%1 = load i16, i16* %inv, align 2
%conv = sext i16 %1 to i32
%arrayidx1 = getelementptr inbounds i32, i32* %a, i64 %i.07
store i32 %conv, i32* %arrayidx1, align 4
br label %for.inc
for.inc: ; preds = %for.body, %if.then
%inc = add nuw nsw i64 %i.07, 1
%exitcond.not = icmp eq i64 %inc, %n
br i1 %exitcond.not, label %exit, label %for.body, !llvm.loop !0
exit: ; preds = %for.inc
ret void
}
define void @cond_inv_load_f64f64f64(double* noalias nocapture %a, double* noalias nocapture readonly %cond, double* noalias nocapture readonly %inv, i64 %n) #0 {
; CHECK-LABEL: @cond_inv_load_f64f64f64(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT: [[TMP1:%.*]] = shl nuw nsw i64 [[TMP0]], 2
; CHECK-NEXT: [[MIN_ITERS_CHECK:%.*]] = icmp ugt i64 [[TMP1]], [[N:%.*]]
; CHECK-NEXT: br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
; CHECK: vector.ph:
; CHECK-NEXT: [[TMP2:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT: [[TMP3:%.*]] = shl nuw nsw i64 [[TMP2]], 2
; CHECK-NEXT: [[N_MOD_VF:%.*]] = urem i64 [[N]], [[TMP3]]
; CHECK-NEXT: [[N_VEC:%.*]] = sub i64 [[N]], [[N_MOD_VF]]
; CHECK-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <vscale x 4 x double*> poison, double* [[INV:%.*]], i64 0
; CHECK-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <vscale x 4 x double*> [[BROADCAST_SPLATINSERT]], <vscale x 4 x double*> poison, <vscale x 4 x i32> zeroinitializer
; CHECK-NEXT: br label [[VECTOR_BODY:%.*]]
; CHECK: vector.body:
; CHECK-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT: [[TMP4:%.*]] = getelementptr inbounds double, double* [[COND:%.*]], i64 [[INDEX]]
; CHECK-NEXT: [[TMP5:%.*]] = bitcast double* [[TMP4]] to <vscale x 4 x double>*
; CHECK-NEXT: [[WIDE_LOAD:%.*]] = load <vscale x 4 x double>, <vscale x 4 x double>* [[TMP5]], align 8
; CHECK-NEXT: [[TMP6:%.*]] = fcmp ogt <vscale x 4 x double> [[WIDE_LOAD]], shufflevector (<vscale x 4 x double> insertelement (<vscale x 4 x double> poison, double 4.000000e-01, i32 0), <vscale x 4 x double> poison, <vscale x 4 x i32> zeroinitializer)
; CHECK-NEXT: [[WIDE_MASKED_GATHER:%.*]] = call <vscale x 4 x double> @llvm.masked.gather.nxv4f64.nxv4p0f64(<vscale x 4 x double*> [[BROADCAST_SPLAT]], i32 8, <vscale x 4 x i1> [[TMP6]], <vscale x 4 x double> undef)
; CHECK-NEXT: [[TMP7:%.*]] = getelementptr double, double* [[A:%.*]], i64 [[INDEX]]
; CHECK-NEXT: [[TMP8:%.*]] = bitcast double* [[TMP7]] to <vscale x 4 x double>*
; CHECK-NEXT: call void @llvm.masked.store.nxv4f64.p0nxv4f64(<vscale x 4 x double> [[WIDE_MASKED_GATHER]], <vscale x 4 x double>* [[TMP8]], i32 8, <vscale x 4 x i1> [[TMP6]])
; CHECK-NEXT: [[TMP9:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT: [[TMP10:%.*]] = shl nuw nsw i64 [[TMP9]], 2
; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP10]]
; CHECK-NEXT: [[TMP11:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
; CHECK-NEXT: br i1 [[TMP11]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP5:![0-9]+]]
; CHECK: middle.block:
; CHECK-NEXT: [[CMP_N:%.*]] = icmp eq i64 [[N_MOD_VF]], 0
; CHECK-NEXT: br i1 [[CMP_N]], label [[EXIT:%.*]], label [[SCALAR_PH]]
; CHECK: scalar.ph:
; CHECK-NEXT: [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
; CHECK-NEXT: br label [[FOR_BODY:%.*]]
; CHECK: for.body:
; CHECK-NEXT: [[I_08:%.*]] = phi i64 [ [[INC:%.*]], [[FOR_INC:%.*]] ], [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ]
; CHECK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds double, double* [[COND]], i64 [[I_08]]
; CHECK-NEXT: [[TMP12:%.*]] = load double, double* [[ARRAYIDX]], align 8
; CHECK-NEXT: [[CMP1:%.*]] = fcmp ogt double [[TMP12]], 4.000000e-01
; CHECK-NEXT: br i1 [[CMP1]], label [[IF_THEN:%.*]], label [[FOR_INC]]
; CHECK: if.then:
; CHECK-NEXT: [[TMP13:%.*]] = load double, double* [[INV]], align 8
; CHECK-NEXT: [[ARRAYIDX2:%.*]] = getelementptr inbounds double, double* [[A]], i64 [[I_08]]
; CHECK-NEXT: store double [[TMP13]], double* [[ARRAYIDX2]], align 8
; CHECK-NEXT: br label [[FOR_INC]]
; CHECK: for.inc:
; CHECK-NEXT: [[INC]] = add nuw nsw i64 [[I_08]], 1
; CHECK-NEXT: [[EXITCOND_NOT:%.*]] = icmp eq i64 [[INC]], [[N]]
; CHECK-NEXT: br i1 [[EXITCOND_NOT]], label [[EXIT]], label [[FOR_BODY]], !llvm.loop [[LOOP6:![0-9]+]]
; CHECK: exit:
; CHECK-NEXT: ret void
;
entry:
br label %for.body
for.body: ; preds = %entry, %for.inc
%i.08 = phi i64 [ %inc, %for.inc ], [ 0, %entry ]
%arrayidx = getelementptr inbounds double, double* %cond, i64 %i.08
%0 = load double, double* %arrayidx, align 8
%cmp1 = fcmp ogt double %0, 4.000000e-01
br i1 %cmp1, label %if.then, label %for.inc
if.then: ; preds = %for.body
%1 = load double, double* %inv, align 8
%arrayidx2 = getelementptr inbounds double, double* %a, i64 %i.08
store double %1, double* %arrayidx2, align 8
br label %for.inc
for.inc: ; preds = %for.body, %if.then
%inc = add nuw nsw i64 %i.08, 1
%exitcond.not = icmp eq i64 %inc, %n
br i1 %exitcond.not, label %exit, label %for.body, !llvm.loop !0
exit: ; preds = %for.inc
ret void
}
define void @invariant_load_cond(i32* noalias nocapture %a, i32* nocapture readonly %b, i32* nocapture readonly %cond, i64 %n) #0 {
; CHECK-LABEL: @invariant_load_cond(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT: [[TMP1:%.*]] = shl nuw nsw i64 [[TMP0]], 2
; CHECK-NEXT: [[MIN_ITERS_CHECK:%.*]] = icmp ugt i64 [[TMP1]], [[N:%.*]]
; CHECK-NEXT: br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
; CHECK: vector.ph:
; CHECK-NEXT: [[TMP2:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT: [[TMP3:%.*]] = shl nuw nsw i64 [[TMP2]], 2
; CHECK-NEXT: [[N_MOD_VF:%.*]] = urem i64 [[N]], [[TMP3]]
; CHECK-NEXT: [[N_VEC:%.*]] = sub i64 [[N]], [[N_MOD_VF]]
; CHECK-NEXT: br label [[VECTOR_BODY:%.*]]
; CHECK: vector.body:
; CHECK-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT: [[TMP4:%.*]] = getelementptr inbounds i32, i32* [[B:%.*]], i64 42
; CHECK-NEXT: [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32*> poison, i32* [[TMP4]], i64 0
; CHECK-NEXT: [[DOTSPLAT:%.*]] = shufflevector <vscale x 4 x i32*> [[DOTSPLATINSERT]], <vscale x 4 x i32*> poison, <vscale x 4 x i32> zeroinitializer
; CHECK-NEXT: [[TMP5:%.*]] = getelementptr inbounds i32, i32* [[COND:%.*]], i64 [[INDEX]]
; CHECK-NEXT: [[TMP6:%.*]] = bitcast i32* [[TMP5]] to <vscale x 4 x i32>*
; CHECK-NEXT: [[WIDE_LOAD:%.*]] = load <vscale x 4 x i32>, <vscale x 4 x i32>* [[TMP6]], align 4
; CHECK-NEXT: [[TMP7:%.*]] = icmp ne <vscale x 4 x i32> [[WIDE_LOAD]], zeroinitializer
; CHECK-NEXT: [[TMP8:%.*]] = getelementptr i32, i32* [[B]], i64 [[INDEX]]
; CHECK-NEXT: [[TMP9:%.*]] = bitcast i32* [[TMP8]] to <vscale x 4 x i32>*
; CHECK-NEXT: [[WIDE_MASKED_LOAD:%.*]] = call <vscale x 4 x i32> @llvm.masked.load.nxv4i32.p0nxv4i32(<vscale x 4 x i32>* [[TMP9]], i32 4, <vscale x 4 x i1> [[TMP7]], <vscale x 4 x i32> poison)
; CHECK-NEXT: [[WIDE_MASKED_GATHER:%.*]] = call <vscale x 4 x i32> @llvm.masked.gather.nxv4i32.nxv4p0i32(<vscale x 4 x i32*> [[DOTSPLAT]], i32 4, <vscale x 4 x i1> [[TMP7]], <vscale x 4 x i32> undef)
; CHECK-NEXT: [[TMP10:%.*]] = add nsw <vscale x 4 x i32> [[WIDE_MASKED_GATHER]], [[WIDE_MASKED_LOAD]]
; CHECK-NEXT: [[TMP11:%.*]] = getelementptr i32, i32* [[A:%.*]], i64 [[INDEX]]
; CHECK-NEXT: [[TMP12:%.*]] = bitcast i32* [[TMP11]] to <vscale x 4 x i32>*
; CHECK-NEXT: call void @llvm.masked.store.nxv4i32.p0nxv4i32(<vscale x 4 x i32> [[TMP10]], <vscale x 4 x i32>* [[TMP12]], i32 4, <vscale x 4 x i1> [[TMP7]])
; CHECK-NEXT: [[TMP13:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT: [[TMP14:%.*]] = shl nuw nsw i64 [[TMP13]], 2
; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP14]]
; CHECK-NEXT: [[TMP15:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
; CHECK-NEXT: br i1 [[TMP15]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP7:![0-9]+]]
; CHECK: middle.block:
; CHECK-NEXT: [[CMP_N:%.*]] = icmp eq i64 [[N_MOD_VF]], 0
; CHECK-NEXT: br i1 [[CMP_N]], label [[FOR_END:%.*]], label [[SCALAR_PH]]
; CHECK: scalar.ph:
; CHECK-NEXT: [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
; CHECK-NEXT: br label [[FOR_BODY:%.*]]
; CHECK: for.body:
; CHECK-NEXT: [[IV:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[IV_NEXT:%.*]], [[FOR_INC:%.*]] ]
; CHECK-NEXT: [[ARRAYIDX2:%.*]] = getelementptr inbounds i32, i32* [[COND]], i64 [[IV]]
; CHECK-NEXT: [[TMP16:%.*]] = load i32, i32* [[ARRAYIDX2]], align 4
; CHECK-NEXT: [[TOBOOL_NOT:%.*]] = icmp eq i32 [[TMP16]], 0
; CHECK-NEXT: br i1 [[TOBOOL_NOT]], label [[FOR_INC]], label [[IF_THEN:%.*]]
; CHECK: if.then:
; CHECK-NEXT: [[ARRAYIDX1:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 42
; CHECK-NEXT: [[ARRAYIDX3:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 [[IV]]
; CHECK-NEXT: [[TMP17:%.*]] = load i32, i32* [[ARRAYIDX3]], align 4
; CHECK-NEXT: [[TMP18:%.*]] = load i32, i32* [[ARRAYIDX1]], align 4
; CHECK-NEXT: [[ADD:%.*]] = add nsw i32 [[TMP18]], [[TMP17]]
; CHECK-NEXT: [[ARRAYIDX4:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 [[IV]]
; CHECK-NEXT: store i32 [[ADD]], i32* [[ARRAYIDX4]], align 4
; CHECK-NEXT: br label [[FOR_INC]]
; CHECK: for.inc:
; CHECK-NEXT: [[IV_NEXT]] = add nuw nsw i64 [[IV]], 1
; CHECK-NEXT: [[EXITCOND_NOT:%.*]] = icmp eq i64 [[IV_NEXT]], [[N]]
; CHECK-NEXT: br i1 [[EXITCOND_NOT]], label [[FOR_END]], label [[FOR_BODY]], !llvm.loop [[LOOP8:![0-9]+]]
; CHECK: for.end:
; CHECK-NEXT: ret void
;
entry:
br label %for.body
for.body:
%iv = phi i64 [ 0, %entry ], [ %iv.next, %for.inc ]
%arrayidx1 = getelementptr inbounds i32, i32* %b, i64 42
%arrayidx2 = getelementptr inbounds i32, i32* %cond, i64 %iv
%0 = load i32, i32* %arrayidx2, align 4
%tobool.not = icmp eq i32 %0, 0
br i1 %tobool.not, label %for.inc, label %if.then
if.then:
%arrayidx3 = getelementptr inbounds i32, i32* %b, i64 %iv
%1 = load i32, i32* %arrayidx3, align 4
%2 = load i32, i32* %arrayidx1, align 4
%add = add nsw i32 %2, %1
%arrayidx4 = getelementptr inbounds i32, i32* %a, i64 %iv
store i32 %add, i32* %arrayidx4, align 4
br label %for.inc
for.inc:
%iv.next = add nuw nsw i64 %iv, 1
%exitcond.not = icmp eq i64 %iv.next, %n
br i1 %exitcond.not, label %for.end, label %for.body, !llvm.loop !0
for.end:
ret void
}
attributes #0 = { vscale_range(1, 16) }
!0 = distinct !{!0, !1, !2, !3, !4, !5}
!1 = !{!"llvm.loop.mustprogress"}
!2 = !{!"llvm.loop.vectorize.width", i32 4}
!3 = !{!"llvm.loop.vectorize.scalable.enable", i1 true}
!4 = !{!"llvm.loop.interleave.count", i32 1}
!5 = !{!"llvm.loop.vectorize.enable", i1 true}
|
