arm-ieee-vectorize.ll
14.6 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
; RUN: opt -mtriple armv7-linux-gnueabihf -loop-vectorize -S %s -debug-only=loop-vectorize -o /dev/null 2>&1 | FileCheck %s --check-prefix=CHECK --check-prefix=LINUX
; RUN: opt -mtriple armv8-linux-gnu -loop-vectorize -S %s -debug-only=loop-vectorize -o /dev/null 2>&1 | FileCheck %s --check-prefix=CHECK --check-prefix=LINUX
; RUN: opt -mtriple armv8.1.m-none-eabi -mattr=+mve.fp -loop-vectorize -S %s -debug-only=loop-vectorize -o /dev/null 2>&1 | FileCheck %s --check-prefix=CHECK --check-prefix=MVE
; RUN: opt -mtriple armv7-unknwon-darwin -loop-vectorize -S %s -debug-only=loop-vectorize -o /dev/null 2>&1 | FileCheck %s --check-prefix=CHECK --check-prefix=DARWIN
; REQUIRES: asserts
; Testing the ability of the loop vectorizer to tell when SIMD is safe or not
; regarding IEEE 754 standard.
; On Linux, we only want the vectorizer to work when -ffast-math flag is set,
; because NEON is not IEEE compliant.
; Darwin, on the other hand, doesn't support subnormals, and all optimizations
; are allowed, even without -ffast-math.
; Integer loops are always vectorizeable
; CHECK: Checking a loop in "sumi"
; CHECK: We can vectorize this loop!
define void @sumi(i32* noalias nocapture readonly %A, i32* noalias nocapture readonly %B, i32* noalias nocapture %C, i32 %N) {
entry:
%cmp5 = icmp eq i32 %N, 0
br i1 %cmp5, label %for.end, label %for.body.preheader
for.body.preheader: ; preds = %entry
br label %for.body
for.body: ; preds = %for.body.preheader, %for.body
%i.06 = phi i32 [ %inc, %for.body ], [ 0, %for.body.preheader ]
%arrayidx = getelementptr inbounds i32, i32* %A, i32 %i.06
%0 = load i32, i32* %arrayidx, align 4
%arrayidx1 = getelementptr inbounds i32, i32* %B, i32 %i.06
%1 = load i32, i32* %arrayidx1, align 4
%mul = mul nsw i32 %1, %0
%arrayidx2 = getelementptr inbounds i32, i32* %C, i32 %i.06
store i32 %mul, i32* %arrayidx2, align 4
%inc = add nuw nsw i32 %i.06, 1
%exitcond = icmp eq i32 %inc, %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
}
; Floating-point loops need fast-math to be vectorizeable
; LINUX: Checking a loop in "sumf"
; LINUX: Potentially unsafe FP op prevents vectorization
; MVE: Checking a loop in "sumf"
; MVE: We can vectorize this loop!
; DARWIN: Checking a loop in "sumf"
; DARWIN: We can vectorize this loop!
define void @sumf(float* noalias nocapture readonly %A, float* noalias nocapture readonly %B, float* noalias nocapture %C, i32 %N) {
entry:
%cmp5 = icmp eq i32 %N, 0
br i1 %cmp5, label %for.end, label %for.body.preheader
for.body.preheader: ; preds = %entry
br label %for.body
for.body: ; preds = %for.body.preheader, %for.body
%i.06 = phi i32 [ %inc, %for.body ], [ 0, %for.body.preheader ]
%arrayidx = getelementptr inbounds float, float* %A, i32 %i.06
%0 = load float, float* %arrayidx, align 4
%arrayidx1 = getelementptr inbounds float, float* %B, i32 %i.06
%1 = load float, float* %arrayidx1, align 4
%mul = fmul float %0, %1
%arrayidx2 = getelementptr inbounds float, float* %C, i32 %i.06
store float %mul, float* %arrayidx2, align 4
%inc = add nuw nsw i32 %i.06, 1
%exitcond = icmp eq i32 %inc, %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
}
; Integer loops are always vectorizeable
; CHECK: Checking a loop in "redi"
; CHECK: We can vectorize this loop!
define i32 @redi(i32* noalias nocapture readonly %a, i32* noalias nocapture readonly %b, i32 %N) {
entry:
%cmp5 = icmp eq i32 %N, 0
br i1 %cmp5, label %for.end, label %for.body.preheader
for.body.preheader: ; preds = %entry
br label %for.body
for.body: ; preds = %for.body.preheader, %for.body
%i.07 = phi i32 [ %inc, %for.body ], [ 0, %for.body.preheader ]
%Red.06 = phi i32 [ %add, %for.body ], [ undef, %for.body.preheader ]
%arrayidx = getelementptr inbounds i32, i32* %a, i32 %i.07
%0 = load i32, i32* %arrayidx, align 4
%arrayidx1 = getelementptr inbounds i32, i32* %b, i32 %i.07
%1 = load i32, i32* %arrayidx1, align 4
%mul = mul nsw i32 %1, %0
%add = add nsw i32 %mul, %Red.06
%inc = add nuw nsw i32 %i.07, 1
%exitcond = icmp eq i32 %inc, %N
br i1 %exitcond, label %for.end.loopexit, label %for.body
for.end.loopexit: ; preds = %for.body
%add.lcssa = phi i32 [ %add, %for.body ]
br label %for.end
for.end: ; preds = %for.end.loopexit, %entry
%Red.0.lcssa = phi i32 [ undef, %entry ], [ %add.lcssa, %for.end.loopexit ]
ret i32 %Red.0.lcssa
}
; Floating-point loops need fast-math to be vectorizeable
; LINUX: Checking a loop in "redf"
; LINUX: Potentially unsafe FP op prevents vectorization
; MVE: Checking a loop in "redf"
; MVE: We can vectorize this loop!
; DARWIN: Checking a loop in "redf"
; DARWIN: We can vectorize this loop!
define float @redf(float* noalias nocapture readonly %a, float* noalias nocapture readonly %b, i32 %N) {
entry:
%cmp5 = icmp eq i32 %N, 0
br i1 %cmp5, label %for.end, label %for.body.preheader
for.body.preheader: ; preds = %entry
br label %for.body
for.body: ; preds = %for.body.preheader, %for.body
%i.07 = phi i32 [ %inc, %for.body ], [ 0, %for.body.preheader ]
%Red.06 = phi float [ %add, %for.body ], [ undef, %for.body.preheader ]
%arrayidx = getelementptr inbounds float, float* %a, i32 %i.07
%0 = load float, float* %arrayidx, align 4
%arrayidx1 = getelementptr inbounds float, float* %b, i32 %i.07
%1 = load float, float* %arrayidx1, align 4
%mul = fmul float %0, %1
%add = fadd float %Red.06, %mul
%inc = add nuw nsw i32 %i.07, 1
%exitcond = icmp eq i32 %inc, %N
br i1 %exitcond, label %for.end.loopexit, label %for.body
for.end.loopexit: ; preds = %for.body
%add.lcssa = phi float [ %add, %for.body ]
br label %for.end
for.end: ; preds = %for.end.loopexit, %entry
%Red.0.lcssa = phi float [ undef, %entry ], [ %add.lcssa, %for.end.loopexit ]
ret float %Red.0.lcssa
}
; Make sure calls that turn into builtins are also covered
; LINUX: Checking a loop in "fabs"
; LINUX: Potentially unsafe FP op prevents vectorization
; DARWIN: Checking a loop in "fabs"
; DARWIN: We can vectorize this loop!
define void @fabs(float* noalias nocapture readonly %A, float* noalias nocapture readonly %B, float* noalias nocapture %C, i32 %N) {
entry:
%cmp10 = icmp eq i32 %N, 0
br i1 %cmp10, label %for.end, label %for.body
for.body: ; preds = %entry, %for.body
%i.011 = phi i32 [ %inc, %for.body ], [ 0, %entry ]
%arrayidx = getelementptr inbounds float, float* %A, i32 %i.011
%0 = load float, float* %arrayidx, align 4
%arrayidx1 = getelementptr inbounds float, float* %B, i32 %i.011
%1 = load float, float* %arrayidx1, align 4
%fabsf = tail call float @fabsf(float %1) #1
%conv3 = fmul float %0, %fabsf
%arrayidx4 = getelementptr inbounds float, float* %C, i32 %i.011
store float %conv3, float* %arrayidx4, align 4
%inc = add nuw nsw i32 %i.011, 1
%exitcond = icmp eq i32 %inc, %N
br i1 %exitcond, label %for.end, label %for.body
for.end: ; preds = %for.body, %entry
ret void
}
; Integer loops are always vectorizeable
; CHECK: Checking a loop in "sumi_fast"
; CHECK: We can vectorize this loop!
define void @sumi_fast(i32* noalias nocapture readonly %A, i32* noalias nocapture readonly %B, i32* noalias nocapture %C, i32 %N) {
entry:
%cmp5 = icmp eq i32 %N, 0
br i1 %cmp5, label %for.end, label %for.body.preheader
for.body.preheader: ; preds = %entry
br label %for.body
for.body: ; preds = %for.body.preheader, %for.body
%i.06 = phi i32 [ %inc, %for.body ], [ 0, %for.body.preheader ]
%arrayidx = getelementptr inbounds i32, i32* %A, i32 %i.06
%0 = load i32, i32* %arrayidx, align 4
%arrayidx1 = getelementptr inbounds i32, i32* %B, i32 %i.06
%1 = load i32, i32* %arrayidx1, align 4
%mul = mul nsw i32 %1, %0
%arrayidx2 = getelementptr inbounds i32, i32* %C, i32 %i.06
store i32 %mul, i32* %arrayidx2, align 4
%inc = add nuw nsw i32 %i.06, 1
%exitcond = icmp eq i32 %inc, %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
}
; Floating-point loops can be vectorizeable with fast-math
; CHECK: Checking a loop in "sumf_fast"
; CHECK: We can vectorize this loop!
define void @sumf_fast(float* noalias nocapture readonly %A, float* noalias nocapture readonly %B, float* noalias nocapture %C, i32 %N) {
entry:
%cmp5 = icmp eq i32 %N, 0
br i1 %cmp5, label %for.end, label %for.body.preheader
for.body.preheader: ; preds = %entry
br label %for.body
for.body: ; preds = %for.body.preheader, %for.body
%i.06 = phi i32 [ %inc, %for.body ], [ 0, %for.body.preheader ]
%arrayidx = getelementptr inbounds float, float* %A, i32 %i.06
%0 = load float, float* %arrayidx, align 4
%arrayidx1 = getelementptr inbounds float, float* %B, i32 %i.06
%1 = load float, float* %arrayidx1, align 4
%mul = fmul fast float %1, %0
%arrayidx2 = getelementptr inbounds float, float* %C, i32 %i.06
store float %mul, float* %arrayidx2, align 4
%inc = add nuw nsw i32 %i.06, 1
%exitcond = icmp eq i32 %inc, %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
}
; Integer loops are always vectorizeable
; CHECK: Checking a loop in "redi_fast"
; CHECK: We can vectorize this loop!
define i32 @redi_fast(i32* noalias nocapture readonly %a, i32* noalias nocapture readonly %b, i32 %N) {
entry:
%cmp5 = icmp eq i32 %N, 0
br i1 %cmp5, label %for.end, label %for.body.preheader
for.body.preheader: ; preds = %entry
br label %for.body
for.body: ; preds = %for.body.preheader, %for.body
%i.07 = phi i32 [ %inc, %for.body ], [ 0, %for.body.preheader ]
%Red.06 = phi i32 [ %add, %for.body ], [ undef, %for.body.preheader ]
%arrayidx = getelementptr inbounds i32, i32* %a, i32 %i.07
%0 = load i32, i32* %arrayidx, align 4
%arrayidx1 = getelementptr inbounds i32, i32* %b, i32 %i.07
%1 = load i32, i32* %arrayidx1, align 4
%mul = mul nsw i32 %1, %0
%add = add nsw i32 %mul, %Red.06
%inc = add nuw nsw i32 %i.07, 1
%exitcond = icmp eq i32 %inc, %N
br i1 %exitcond, label %for.end.loopexit, label %for.body
for.end.loopexit: ; preds = %for.body
%add.lcssa = phi i32 [ %add, %for.body ]
br label %for.end
for.end: ; preds = %for.end.loopexit, %entry
%Red.0.lcssa = phi i32 [ undef, %entry ], [ %add.lcssa, %for.end.loopexit ]
ret i32 %Red.0.lcssa
}
; Floating-point loops can be vectorizeable with fast-math
; CHECK: Checking a loop in "redf_fast"
; CHECK: We can vectorize this loop!
define float @redf_fast(float* noalias nocapture readonly %a, float* noalias nocapture readonly %b, i32 %N) {
entry:
%cmp5 = icmp eq i32 %N, 0
br i1 %cmp5, label %for.end, label %for.body.preheader
for.body.preheader: ; preds = %entry
br label %for.body
for.body: ; preds = %for.body.preheader, %for.body
%i.07 = phi i32 [ %inc, %for.body ], [ 0, %for.body.preheader ]
%Red.06 = phi float [ %add, %for.body ], [ undef, %for.body.preheader ]
%arrayidx = getelementptr inbounds float, float* %a, i32 %i.07
%0 = load float, float* %arrayidx, align 4
%arrayidx1 = getelementptr inbounds float, float* %b, i32 %i.07
%1 = load float, float* %arrayidx1, align 4
%mul = fmul fast float %1, %0
%add = fadd fast float %mul, %Red.06
%inc = add nuw nsw i32 %i.07, 1
%exitcond = icmp eq i32 %inc, %N
br i1 %exitcond, label %for.end.loopexit, label %for.body
for.end.loopexit: ; preds = %for.body
%add.lcssa = phi float [ %add, %for.body ]
br label %for.end
for.end: ; preds = %for.end.loopexit, %entry
%Red.0.lcssa = phi float [ undef, %entry ], [ %add.lcssa, %for.end.loopexit ]
ret float %Red.0.lcssa
}
; Make sure calls that turn into builtins are also covered
; CHECK: Checking a loop in "fabs_fast"
; CHECK: We can vectorize this loop!
define void @fabs_fast(float* noalias nocapture readonly %A, float* noalias nocapture readonly %B, float* noalias nocapture %C, i32 %N) {
entry:
%cmp10 = icmp eq i32 %N, 0
br i1 %cmp10, label %for.end, label %for.body
for.body: ; preds = %entry, %for.body
%i.011 = phi i32 [ %inc, %for.body ], [ 0, %entry ]
%arrayidx = getelementptr inbounds float, float* %A, i32 %i.011
%0 = load float, float* %arrayidx, align 4
%arrayidx1 = getelementptr inbounds float, float* %B, i32 %i.011
%1 = load float, float* %arrayidx1, align 4
%fabsf = tail call fast float @fabsf(float %1) #2
%conv3 = fmul fast float %fabsf, %0
%arrayidx4 = getelementptr inbounds float, float* %C, i32 %i.011
store float %conv3, float* %arrayidx4, align 4
%inc = add nuw nsw i32 %i.011, 1
%exitcond = icmp eq i32 %inc, %N
br i1 %exitcond, label %for.end, label %for.body
for.end: ; preds = %for.body, %entry
ret void
}
declare float @fabsf(float)
attributes #1 = { nounwind readnone "disable-tail-calls"="false" "less-precise-fpmad"="false" "frame-pointer"="all" "no-infs-fp-math"="false" "no-nans-fp-math"="false" "stack-protector-buffer-size"="8" "target-cpu"="cortex-a8" "target-features"="+dsp,+neon,+vfp3" "unsafe-fp-math"="false" "use-soft-float"="false" }
attributes #2 = { nounwind readnone "disable-tail-calls"="false" "less-precise-fpmad"="false" "frame-pointer"="all" "no-infs-fp-math"="true" "no-nans-fp-math"="true" "stack-protector-buffer-size"="8" "target-cpu"="cortex-a8" "target-features"="+dsp,+neon,+vfp3" "unsafe-fp-math"="true" "use-soft-float"="false" }