float-induction.ll
19.7 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
; RUN: opt < %s -loop-vectorize -force-vector-interleave=1 -force-vector-width=4 -dce -instcombine -S | FileCheck --check-prefix VEC4_INTERL1 %s
; RUN: opt < %s -loop-vectorize -force-vector-interleave=2 -force-vector-width=4 -dce -instcombine -S | FileCheck --check-prefix VEC4_INTERL2 %s
; RUN: opt < %s -loop-vectorize -force-vector-interleave=2 -force-vector-width=1 -dce -instcombine -S | FileCheck --check-prefix VEC1_INTERL2 %s
; RUN: opt < %s -loop-vectorize -force-vector-interleave=1 -force-vector-width=2 -dce -simplifycfg -instcombine -simplifycfg -keep-loops=false -S | FileCheck --check-prefix VEC2_INTERL1_PRED_STORE %s
@fp_inc = common global float 0.000000e+00, align 4
;void fp_iv_loop1(float init, float * __restrict__ A, int N) {
; float x = init;
; for (int i=0; i < N; ++i) {
; A[i] = x;
; x -= fp_inc;
; }
;}
; VEC4_INTERL1-LABEL: @fp_iv_loop1(
; VEC4_INTERL1: vector.ph:
; VEC4_INTERL1: [[DOTSPLATINSERT:%.*]] = insertelement <4 x float> undef, float %init, i32 0
; VEC4_INTERL1-NEXT: [[DOTSPLAT:%.*]] = shufflevector <4 x float> [[DOTSPLATINSERT]], <4 x float> undef, <4 x i32> zeroinitializer
; VEC4_INTERL1-NEXT: [[DOTSPLATINSERT2:%.*]] = insertelement <4 x float> undef, float %fpinc, i32 0
; VEC4_INTERL1-NEXT: [[DOTSPLAT3:%.*]] = shufflevector <4 x float> [[DOTSPLATINSERT2]], <4 x float> undef, <4 x i32> zeroinitializer
; VEC4_INTERL1-NEXT: [[TMP5:%.*]] = fmul fast <4 x float> [[DOTSPLAT3]], <float 0.000000e+00, float 1.000000e+00, float 2.000000e+00, float 3.000000e+00>
; VEC4_INTERL1-NEXT: [[INDUCTION4:%.*]] = fsub fast <4 x float> [[DOTSPLAT]], [[TMP5]]
; VEC4_INTERL1-NEXT: [[TMP6:%.*]] = fmul fast float %fpinc, 4.000000e+00
; VEC4_INTERL1-NEXT: [[DOTSPLATINSERT5:%.*]] = insertelement <4 x float> undef, float [[TMP6]], i32 0
; VEC4_INTERL1-NEXT: [[DOTSPLAT6:%.*]] = shufflevector <4 x float> [[DOTSPLATINSERT5]], <4 x float> undef, <4 x i32> zeroinitializer
; VEC4_INTERL1-NEXT: br label %vector.body
; VEC4_INTERL1: vector.body:
; VEC4_INTERL1-NEXT: [[INDEX:%.*]] = phi i64 [ 0, %vector.ph ], [ [[INDEX_NEXT:%.*]], %vector.body ]
; VEC4_INTERL1-NEXT: [[VEC_IND:%.*]] = phi <4 x float> [ [[INDUCTION4]], %vector.ph ], [ [[VEC_IND_NEXT:%.*]], %vector.body ]
; VEC4_INTERL1-NEXT: [[TMP8:%.*]] = getelementptr inbounds float, float* %A, i64 [[INDEX]]
; VEC4_INTERL1-NEXT: [[TMP9:%.*]] = bitcast float* [[TMP8]] to <4 x float>*
; VEC4_INTERL1-NEXT: store <4 x float> [[VEC_IND]], <4 x float>* [[TMP9]], align 4
; VEC4_INTERL1-NEXT: [[INDEX_NEXT]] = add i64 [[INDEX]], 4
; VEC4_INTERL1-NEXT: [[VEC_IND_NEXT]] = fsub fast <4 x float> [[VEC_IND]], [[DOTSPLAT6]]
; VEC4_INTERL1: br i1 {{.*}}, label %middle.block, label %vector.body
; VEC4_INTERL2-LABEL: @fp_iv_loop1(
; VEC4_INTERL2: vector.ph:
; VEC4_INTERL2: [[DOTSPLATINSERT:%.*]] = insertelement <4 x float> undef, float %init, i32 0
; VEC4_INTERL2-NEXT: [[DOTSPLAT:%.*]] = shufflevector <4 x float> [[DOTSPLATINSERT]], <4 x float> undef, <4 x i32> zeroinitializer
; VEC4_INTERL2-NEXT: [[DOTSPLATINSERT3:%.*]] = insertelement <4 x float> undef, float %fpinc, i32 0
; VEC4_INTERL2-NEXT: [[DOTSPLAT4:%.*]] = shufflevector <4 x float> [[DOTSPLATINSERT3]], <4 x float> undef, <4 x i32> zeroinitializer
; VEC4_INTERL2-NEXT: [[TMP5:%.*]] = fmul fast <4 x float> [[DOTSPLAT4]], <float 0.000000e+00, float 1.000000e+00, float 2.000000e+00, float 3.000000e+00>
; VEC4_INTERL2-NEXT: [[INDUCTION5:%.*]] = fsub fast <4 x float> [[DOTSPLAT]], [[TMP5]]
; VEC4_INTERL2-NEXT: [[TMP6:%.*]] = fmul fast float %fpinc, 4.000000e+00
; VEC4_INTERL2-NEXT: [[DOTSPLATINSERT6:%.*]] = insertelement <4 x float> undef, float [[TMP6]], i32 0
; VEC4_INTERL2-NEXT: [[DOTSPLAT7:%.*]] = shufflevector <4 x float> [[DOTSPLATINSERT6]], <4 x float> undef, <4 x i32> zeroinitializer
; VEC4_INTERL2-NEXT: br label %vector.body
; VEC4_INTERL2: vector.body:
; VEC4_INTERL2-NEXT: [[INDEX:%.*]] = phi i64 [ 0, %vector.ph ], [ [[INDEX_NEXT:%.*]], %vector.body ]
; VEC4_INTERL2-NEXT: [[VEC_IND:%.*]] = phi <4 x float> [ [[INDUCTION5]], %vector.ph ], [ [[VEC_IND_NEXT:%.*]], %vector.body ]
; VEC4_INTERL2-NEXT: [[STEP_ADD:%.*]] = fsub fast <4 x float> [[VEC_IND]], [[DOTSPLAT7]]
; VEC4_INTERL2-NEXT: [[TMP9:%.*]] = getelementptr inbounds float, float* %A, i64 [[INDEX]]
; VEC4_INTERL2-NEXT: [[TMP10:%.*]] = bitcast float* [[TMP9]] to <4 x float>*
; VEC4_INTERL2-NEXT: store <4 x float> [[VEC_IND]], <4 x float>* [[TMP10]], align 4
; VEC4_INTERL2-NEXT: [[TMP11:%.*]] = getelementptr inbounds float, float* [[TMP9]], i64 4
; VEC4_INTERL2-NEXT: [[TMP12:%.*]] = bitcast float* [[TMP11]] to <4 x float>*
; VEC4_INTERL2-NEXT: store <4 x float> [[STEP_ADD]], <4 x float>* [[TMP12]], align 4
; VEC4_INTERL2-NEXT: [[INDEX_NEXT]] = add i64 [[INDEX]], 8
; VEC4_INTERL2-NEXT: [[VEC_IND_NEXT]] = fsub fast <4 x float> [[STEP_ADD]], [[DOTSPLAT7]]
; VEC4_INTERL2: br i1 {{.*}}, label %middle.block, label %vector.body
; VEC1_INTERL2-LABEL: @fp_iv_loop1(
; VEC1_INTERL2: vector.ph:
; VEC1_INTERL2: br label %vector.body
; VEC1_INTERL2: vector.body:
; VEC1_INTERL2-NEXT: [[INDEX:%.*]] = phi i64 [ 0, %vector.ph ], [ [[INDEX_NEXT:%.*]], %vector.body ]
; VEC1_INTERL2-NEXT: [[INDUCTION2:%.*]] = or i64 [[INDEX]], 1
; VEC1_INTERL2-NEXT: [[TMP6:%.*]] = sitofp i64 [[INDEX]] to float
; VEC1_INTERL2-NEXT: [[TMP7:%.*]] = fmul fast float %fpinc, [[TMP6]]
; VEC1_INTERL2-NEXT: [[FP_OFFSET_IDX:%.*]] = fsub fast float %init, [[TMP7]]
; VEC1_INTERL2-NEXT: [[TMP8:%.*]] = fsub fast float [[FP_OFFSET_IDX]], %fpinc
; VEC1_INTERL2-NEXT: [[TMP9:%.*]] = getelementptr inbounds float, float* %A, i64 [[INDEX]]
; VEC1_INTERL2-NEXT: [[TMP10:%.*]] = getelementptr inbounds float, float* %A, i64 [[INDUCTION2]]
; VEC1_INTERL2-NEXT: store float [[FP_OFFSET_IDX]], float* [[TMP9]], align 4
; VEC1_INTERL2-NEXT: store float [[TMP8]], float* [[TMP10]], align 4
; VEC1_INTERL2-NEXT: [[INDEX_NEXT]] = add i64 [[INDEX]], 2
; VEC1_INTERL2: br i1 {{.*}}, label %middle.block, label %vector.body
define void @fp_iv_loop1(float %init, float* noalias nocapture %A, i32 %N) #1 {
entry:
%cmp4 = icmp sgt i32 %N, 0
br i1 %cmp4, label %for.body.lr.ph, label %for.end
for.body.lr.ph: ; preds = %entry
%fpinc = load float, float* @fp_inc, align 4
br label %for.body
for.body: ; preds = %for.body, %for.body.lr.ph
%indvars.iv = phi i64 [ 0, %for.body.lr.ph ], [ %indvars.iv.next, %for.body ]
%x.05 = phi float [ %init, %for.body.lr.ph ], [ %add, %for.body ]
%arrayidx = getelementptr inbounds float, float* %A, i64 %indvars.iv
store float %x.05, float* %arrayidx, align 4
%add = fsub fast float %x.05, %fpinc
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
%lftr.wideiv = trunc i64 %indvars.iv.next to i32
%exitcond = icmp eq i32 %lftr.wideiv, %N
br i1 %exitcond, label %for.end.loopexit, label %for.body
for.end.loopexit: ; preds = %for.body
br label %for.end
for.end: ; preds = %for.end.loopexit, %entry
ret void
}
;void fp_iv_loop2(float init, float * __restrict__ A, int N) {
; float x = init;
; for (int i=0; i < N; ++i) {
; A[i] = x;
; x += 0.5;
; }
;}
; VEC4_INTERL1-LABEL: @fp_iv_loop2(
; VEC4_INTERL1: vector.ph:
; VEC4_INTERL1: [[DOTSPLATINSERT:%.*]] = insertelement <4 x float> undef, float %init, i32 0
; VEC4_INTERL1-NEXT: [[DOTSPLAT:%.*]] = shufflevector <4 x float> [[DOTSPLATINSERT]], <4 x float> undef, <4 x i32> zeroinitializer
; VEC4_INTERL1-NEXT: [[INDUCTION2:%.*]] = fadd fast <4 x float> [[DOTSPLAT]], <float 0.000000e+00, float 5.000000e-01, float 1.000000e+00, float 1.500000e+00>
; VEC4_INTERL1-NEXT: br label %vector.body
; VEC4_INTERL1: vector.body:
; VEC4_INTERL1-NEXT: [[INDEX:%.*]] = phi i64 [ 0, %vector.ph ], [ [[INDEX_NEXT:%.*]], %vector.body ]
; VEC4_INTERL1-NEXT: [[VEC_IND:%.*]] = phi <4 x float> [ [[INDUCTION2]], %vector.ph ], [ [[VEC_IND_NEXT:%.*]], %vector.body ]
; VEC4_INTERL1-NEXT: [[TMP7:%.*]] = getelementptr inbounds float, float* %A, i64 [[INDEX]]
; VEC4_INTERL1-NEXT: [[TMP8:%.*]] = bitcast float* [[TMP7]] to <4 x float>*
; VEC4_INTERL1-NEXT: store <4 x float> [[VEC_IND]], <4 x float>* [[TMP8]], align 4
; VEC4_INTERL1-NEXT: [[INDEX_NEXT]] = add i64 [[INDEX]], 4
; VEC4_INTERL1-NEXT: [[VEC_IND_NEXT]] = fadd fast <4 x float> [[VEC_IND]], <float 2.000000e+00, float 2.000000e+00, float 2.000000e+00, float 2.000000e+00>
; VEC4_INTERL1: br i1 {{.*}}, label %middle.block, label %vector.body
define void @fp_iv_loop2(float %init, float* noalias nocapture %A, i32 %N) #0 {
entry:
%cmp4 = icmp sgt i32 %N, 0
br i1 %cmp4, label %for.body.preheader, label %for.end
for.body.preheader: ; preds = %entry
br label %for.body
for.body: ; preds = %for.body.preheader, %for.body
%indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %for.body.preheader ]
%x.06 = phi float [ %conv1, %for.body ], [ %init, %for.body.preheader ]
%arrayidx = getelementptr inbounds float, float* %A, i64 %indvars.iv
store float %x.06, float* %arrayidx, align 4
%conv1 = fadd fast float %x.06, 5.000000e-01
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
%lftr.wideiv = trunc i64 %indvars.iv.next to i32
%exitcond = icmp eq i32 %lftr.wideiv, %N
br i1 %exitcond, label %for.end.loopexit, label %for.body
for.end.loopexit: ; preds = %for.body
br label %for.end
for.end: ; preds = %for.end.loopexit, %entry
ret void
}
;void fp_iv_loop3(float init, float * __restrict__ A, float * __restrict__ B, float * __restrict__ C, int N) {
; int i = 0;
; float x = init;
; float y = 0.1;
; for (; i < N; ++i) {
; A[i] = x;
; x += fp_inc;
; y -= 0.5;
; B[i] = x + y;
; C[i] = y;
; }
;}
; VEC4_INTERL1-LABEL: @fp_iv_loop3(
; VEC4_INTERL1: for.body.lr.ph:
; VEC4_INTERL1: [[TMP0:%.*]] = load float, float* @fp_inc, align 4
; VEC4_INTERL1: vector.ph:
; VEC4_INTERL1: [[DOTSPLATINSERT:%.*]] = insertelement <4 x float> undef, float %init, i32 0
; VEC4_INTERL1-NEXT: [[DOTSPLAT:%.*]] = shufflevector <4 x float> [[DOTSPLATINSERT]], <4 x float> undef, <4 x i32> zeroinitializer
; VEC4_INTERL1-NEXT: [[DOTSPLATINSERT5:%.*]] = insertelement <4 x float> undef, float [[TMP0]], i32 0
; VEC4_INTERL1-NEXT: [[DOTSPLAT6:%.*]] = shufflevector <4 x float> [[DOTSPLATINSERT5]], <4 x float> undef, <4 x i32> zeroinitializer
; VEC4_INTERL1-NEXT: [[TMP7:%.*]] = fmul fast <4 x float> [[DOTSPLAT6]], <float 0.000000e+00, float 1.000000e+00, float 2.000000e+00, float 3.000000e+00>
; VEC4_INTERL1-NEXT: [[INDUCTION7:%.*]] = fadd fast <4 x float> [[DOTSPLAT]], [[TMP7]]
; VEC4_INTERL1-NEXT: [[TMP8:%.*]] = fmul fast float [[TMP0]], 4.000000e+00
; VEC4_INTERL1-NEXT: [[DOTSPLATINSERT8:%.*]] = insertelement <4 x float> undef, float [[TMP8]], i32 0
; VEC4_INTERL1-NEXT: [[DOTSPLAT9:%.*]] = shufflevector <4 x float> [[DOTSPLATINSERT8]], <4 x float> undef, <4 x i32> zeroinitializer
; VEC4_INTERL1-NEXT: [[BROADCAST_SPLATINSERT12:%.*]] = insertelement <4 x float> undef, float [[TMP0]], i32 0
; VEC4_INTERL1-NEXT: [[BROADCAST_SPLAT13:%.*]] = shufflevector <4 x float> [[BROADCAST_SPLATINSERT12]], <4 x float> undef, <4 x i32> zeroinitializer
; VEC4_INTERL1-NEXT: br label [[VECTOR_BODY:%.*]]
; VEC4_INTERL1: vector.body:
; VEC4_INTERL1-NEXT: [[INDEX:%.*]] = phi i64 [ 0, %vector.ph ], [ [[INDEX_NEXT:%.*]], %vector.body ]
; VEC4_INTERL1-NEXT: [[VEC_IND:%.*]] = phi <4 x float> [ <float 0x3FB99999A0000000, float 0xBFD99999A0000000, float 0xBFECCCCCC0000000, float 0xBFF6666660000000>, %vector.ph ], [ [[VEC_IND_NEXT:%.*]], %vector.body ]
; VEC4_INTERL1-NEXT: [[VEC_IND10:%.*]] = phi <4 x float> [ [[INDUCTION7]], %vector.ph ], [ [[VEC_IND_NEXT11:%.*]], %vector.body ]
; VEC4_INTERL1-NEXT: [[TMP12:%.*]] = getelementptr inbounds float, float* %A, i64 [[INDEX]]
; VEC4_INTERL1-NEXT: [[TMP13:%.*]] = bitcast float* [[TMP12]] to <4 x float>*
; VEC4_INTERL1-NEXT: store <4 x float> [[VEC_IND10]], <4 x float>* [[TMP13]], align 4
; VEC4_INTERL1-NEXT: [[TMP14:%.*]] = fadd fast <4 x float> [[VEC_IND10]], [[BROADCAST_SPLAT13]]
; VEC4_INTERL1-NEXT: [[TMP15:%.*]] = fadd fast <4 x float> [[VEC_IND]], <float -5.000000e-01, float -5.000000e-01, float -5.000000e-01, float -5.000000e-01>
; VEC4_INTERL1-NEXT: [[TMP16:%.*]] = fadd fast <4 x float> [[TMP15]], [[TMP14]]
; VEC4_INTERL1-NEXT: [[TMP17:%.*]] = getelementptr inbounds float, float* %B, i64 [[INDEX]]
; VEC4_INTERL1-NEXT: [[TMP18:%.*]] = bitcast float* [[TMP17]] to <4 x float>*
; VEC4_INTERL1-NEXT: store <4 x float> [[TMP16]], <4 x float>* [[TMP18]], align 4
; VEC4_INTERL1-NEXT: [[TMP19:%.*]] = getelementptr inbounds float, float* %C, i64 [[INDEX]]
; VEC4_INTERL1-NEXT: [[TMP20:%.*]] = bitcast float* [[TMP19]] to <4 x float>*
; VEC4_INTERL1-NEXT: store <4 x float> [[TMP15]], <4 x float>* [[TMP20]], align 4
; VEC4_INTERL1-NEXT: [[INDEX_NEXT]] = add i64 [[INDEX]], 4
; VEC4_INTERL1-NEXT: [[VEC_IND_NEXT]] = fadd fast <4 x float> [[VEC_IND]], <float -2.000000e+00, float -2.000000e+00, float -2.000000e+00, float -2.000000e+00>
; VEC4_INTERL1-NEXT: [[VEC_IND_NEXT11]] = fadd fast <4 x float> [[VEC_IND10]], [[DOTSPLAT9]]
; VEC4_INTERL1: br i1 {{.*}}, label %middle.block, label %vector.body
define void @fp_iv_loop3(float %init, float* noalias nocapture %A, float* noalias nocapture %B, float* noalias nocapture %C, i32 %N) #1 {
entry:
%cmp9 = icmp sgt i32 %N, 0
br i1 %cmp9, label %for.body.lr.ph, label %for.end
for.body.lr.ph: ; preds = %entry
%0 = load float, float* @fp_inc, align 4
br label %for.body
for.body: ; preds = %for.body, %for.body.lr.ph
%indvars.iv = phi i64 [ 0, %for.body.lr.ph ], [ %indvars.iv.next, %for.body ]
%y.012 = phi float [ 0x3FB99999A0000000, %for.body.lr.ph ], [ %conv1, %for.body ]
%x.011 = phi float [ %init, %for.body.lr.ph ], [ %add, %for.body ]
%arrayidx = getelementptr inbounds float, float* %A, i64 %indvars.iv
store float %x.011, float* %arrayidx, align 4
%add = fadd fast float %x.011, %0
%conv1 = fadd fast float %y.012, -5.000000e-01
%add2 = fadd fast float %conv1, %add
%arrayidx4 = getelementptr inbounds float, float* %B, i64 %indvars.iv
store float %add2, float* %arrayidx4, align 4
%arrayidx6 = getelementptr inbounds float, float* %C, i64 %indvars.iv
store float %conv1, float* %arrayidx6, align 4
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
%lftr.wideiv = trunc i64 %indvars.iv.next to i32
%exitcond = icmp eq i32 %lftr.wideiv, %N
br i1 %exitcond, label %for.end.loopexit, label %for.body
for.end.loopexit:
br label %for.end
for.end:
ret void
}
; Start and step values are constants. There is no 'fmul' operation in this case
;void fp_iv_loop4(float * __restrict__ A, int N) {
; float x = 1.0;
; for (int i=0; i < N; ++i) {
; A[i] = x;
; x += 0.5;
; }
;}
; VEC4_INTERL1-LABEL: @fp_iv_loop4(
; VEC4_INTERL1: vector.ph:
; VEC4_INTERL1: br label %vector.body
; VEC4_INTERL1: vector.body:
; VEC4_INTERL1-NEXT: [[INDEX:%.*]] = phi i64 [ 0, %vector.ph ], [ [[INDEX_NEXT:%.*]], %vector.body ]
; VEC4_INTERL1-NEXT: [[VEC_IND:%.*]] = phi <4 x float> [ <float 1.000000e+00, float 1.500000e+00, float 2.000000e+00, float 2.500000e+00>, %vector.ph ], [ [[VEC_IND_NEXT:%.*]], %vector.body ]
; VEC4_INTERL1-NEXT: [[TMP7:%.*]] = getelementptr inbounds float, float* %A, i64 [[INDEX]]
; VEC4_INTERL1-NEXT: [[TMP8:%.*]] = bitcast float* [[TMP7]] to <4 x float>*
; VEC4_INTERL1-NEXT: store <4 x float> [[VEC_IND]], <4 x float>* [[TMP8]], align 4
; VEC4_INTERL1-NEXT: [[INDEX_NEXT]] = add i64 [[INDEX]], 4
; VEC4_INTERL1-NEXT: [[VEC_IND_NEXT]] = fadd fast <4 x float> [[VEC_IND]], <float 2.000000e+00, float 2.000000e+00, float 2.000000e+00, float 2.000000e+00>
; VEC4_INTERL1: br i1 {{.*}}, label %middle.block, label %vector.body
define void @fp_iv_loop4(float* noalias nocapture %A, i32 %N) {
entry:
%cmp4 = icmp sgt i32 %N, 0
br i1 %cmp4, label %for.body.preheader, label %for.end
for.body.preheader: ; preds = %entry
br label %for.body
for.body: ; preds = %for.body.preheader, %for.body
%indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %for.body.preheader ]
%x.06 = phi float [ %conv1, %for.body ], [ 1.000000e+00, %for.body.preheader ]
%arrayidx = getelementptr inbounds float, float* %A, i64 %indvars.iv
store float %x.06, float* %arrayidx, align 4
%conv1 = fadd fast float %x.06, 5.000000e-01
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
%lftr.wideiv = trunc i64 %indvars.iv.next to i32
%exitcond = icmp eq i32 %lftr.wideiv, %N
br i1 %exitcond, label %for.end.loopexit, label %for.body
for.end.loopexit: ; preds = %for.body
br label %for.end
for.end: ; preds = %for.end.loopexit, %entry
ret void
}
; VEC2_INTERL1_PRED_STORE-LABEL: @non_primary_iv_float_scalar(
; VEC2_INTERL1_PRED_STORE: vector.body:
; VEC2_INTERL1_PRED_STORE-NEXT: [[INDEX:%.*]] = phi i64 [ 0, %vector.ph ], [ [[INDEX_NEXT:%.*]], %[[PRED_STORE_CONTINUE7:.*]] ]
; VEC2_INTERL1_PRED_STORE-NEXT: [[TMP1:%.*]] = sitofp i64 [[INDEX]] to float
; VEC2_INTERL1_PRED_STORE-NEXT: [[TMP2:%.*]] = getelementptr inbounds float, float* %A, i64 [[INDEX]]
; VEC2_INTERL1_PRED_STORE-NEXT: [[TMP3:%.*]] = bitcast float* [[TMP2]] to <2 x float>*
; VEC2_INTERL1_PRED_STORE-NEXT: [[WIDE_LOAD:%.*]] = load <2 x float>, <2 x float>* [[TMP3]], align 4
; VEC2_INTERL1_PRED_STORE-NEXT: [[TMP4:%.*]] = fcmp fast oeq <2 x float> [[WIDE_LOAD]], zeroinitializer
; VEC2_INTERL1_PRED_STORE-NEXT: [[TMP5:%.*]] = extractelement <2 x i1> [[TMP4]], i32 0
; VEC2_INTERL1_PRED_STORE-NEXT: br i1 [[TMP5]], label %[[PRED_STORE_IF:.*]], label %[[PRED_STORE_CONTINUE:.*]]
; VEC2_INTERL1_PRED_STORE: [[PRED_STORE_IF]]:
; VEC2_INTERL1_PRED_STORE-NEXT: store float [[TMP1]], float* [[TMP2]], align 4
; VEC2_INTERL1_PRED_STORE-NEXT: br label %[[PRED_STORE_CONTINUE]]
; VEC2_INTERL1_PRED_STORE: [[PRED_STORE_CONTINUE]]:
; VEC2_INTERL1_PRED_STORE-NEXT: [[TMP8:%.*]] = extractelement <2 x i1> [[TMP4]], i32 1
; VEC2_INTERL1_PRED_STORE-NEXT: br i1 [[TMP8]], label %[[PRED_STORE_IF6:.*]], label %[[PRED_STORE_CONTINUE7]]
; VEC2_INTERL1_PRED_STORE: [[PRED_STORE_IF6]]:
; VEC2_INTERL1_PRED_STORE-NEXT: [[TMP9:%.*]] = fadd fast float [[TMP1]], 1.000000e+00
; VEC2_INTERL1_PRED_STORE-NEXT: [[TMP10:%.*]] = or i64 [[INDEX]], 1
; VEC2_INTERL1_PRED_STORE-NEXT: [[TMP11:%.*]] = getelementptr inbounds float, float* %A, i64 [[TMP10]]
; VEC2_INTERL1_PRED_STORE-NEXT: store float [[TMP9]], float* [[TMP11]], align 4
; VEC2_INTERL1_PRED_STORE-NEXT: br label %[[PRED_STORE_CONTINUE7]]
; VEC2_INTERL1_PRED_STORE: [[PRED_STORE_CONTINUE7]]:
; VEC2_INTERL1_PRED_STORE-NEXT: [[INDEX_NEXT]] = add i64 [[INDEX]], 2
; VEC2_INTERL1_PRED_STORE: br i1 {{.*}}, label %middle.block, label %vector.body
define void @non_primary_iv_float_scalar(float* %A, i64 %N) {
entry:
br label %for.body
for.body:
%i = phi i64 [ %i.next, %for.inc ], [ 0, %entry ]
%j = phi float [ %j.next, %for.inc ], [ 0.0, %entry ]
%tmp0 = getelementptr inbounds float, float* %A, i64 %i
%tmp1 = load float, float* %tmp0, align 4
%tmp2 = fcmp fast oeq float %tmp1, 0.0
br i1 %tmp2, label %if.pred, label %for.inc
if.pred:
store float %j, float* %tmp0, align 4
br label %for.inc
for.inc:
%i.next = add nuw nsw i64 %i, 1
%j.next = fadd fast float %j, 1.0
%cond = icmp slt i64 %i.next, %N
br i1 %cond, label %for.body, label %for.end
for.end:
ret void
}