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
|
; RUN: opt -mtriple=thumbv8.1m.main-arm-eabihf -mattr=+mve.fp -passes=loop-vectorize -tail-predication=enabled -S < %s | \
; RUN: FileCheck %s
target datalayout = "e-m:e-p:32:32-Fi8-i64:64-v128:64:128-a:0:32-n32-S64"
; Test that ARMTTIImpl::preferPredicateOverEpilogue triggers tail-folding.
define dso_local void @f1(ptr noalias nocapture %A, ptr noalias nocapture readonly %B, ptr noalias nocapture readonly %C, i32 %N) {
; CHECK-LABEL: f1(
; CHECK: entry:
; CHECK: @llvm.get.active.lane.mask
; CHECK: }
entry:
%cmp8 = icmp sgt i32 %N, 0
br i1 %cmp8, label %for.body.preheader, label %for.cond.cleanup
for.body.preheader: ; preds = %entry
br label %for.body
for.cond.cleanup.loopexit: ; preds = %for.body
br label %for.cond.cleanup
for.cond.cleanup: ; preds = %for.cond.cleanup.loopexit, %entry
ret void
for.body: ; preds = %for.body.preheader, %for.body
%i.09 = phi i32 [ %inc, %for.body ], [ 0, %for.body.preheader ]
%arrayidx = getelementptr inbounds i32, ptr %B, i32 %i.09
%0 = load i32, ptr %arrayidx, align 4
%arrayidx1 = getelementptr inbounds i32, ptr %C, i32 %i.09
%1 = load i32, ptr %arrayidx1, align 4
%add = add nsw i32 %1, %0
%arrayidx2 = getelementptr inbounds i32, ptr %A, i32 %i.09
store i32 %add, ptr %arrayidx2, align 4
%inc = add nuw nsw i32 %i.09, 1
%exitcond.not = icmp eq i32 %inc, %N
br i1 %exitcond.not, label %for.cond.cleanup.loopexit, label %for.body
}
define dso_local void @f32_reduction(ptr nocapture readonly %Input, i32 %N, ptr nocapture %Output) {
; CHECK-LABEL: f32_reduction(
; CHECK: vector.body:
; CHECK: @llvm.masked.load
; CHECK: br i1 %{{.*}}, label {{.*}}, label %vector.body
entry:
%cmp6 = icmp eq i32 %N, 0
br i1 %cmp6, label %while.end, label %while.body.preheader
while.body.preheader: ; preds = %entry
br label %while.body
while.body: ; preds = %while.body.preheader, %while.body
%blkCnt.09 = phi i32 [ %dec, %while.body ], [ %N, %while.body.preheader ]
%sum.08 = phi float [ %add, %while.body ], [ 0.000000e+00, %while.body.preheader ]
%Input.addr.07 = phi ptr [ %incdec.ptr, %while.body ], [ %Input, %while.body.preheader ]
%incdec.ptr = getelementptr inbounds float, ptr %Input.addr.07, i32 1
%0 = load float, ptr %Input.addr.07, align 4
%add = fadd fast float %0, %sum.08
%dec = add i32 %blkCnt.09, -1
%cmp = icmp eq i32 %dec, 0
br i1 %cmp, label %while.end.loopexit, label %while.body
while.end.loopexit: ; preds = %while.body
%add.lcssa = phi float [ %add, %while.body ]
br label %while.end
while.end: ; preds = %while.end.loopexit, %entry
%sum.0.lcssa = phi float [ 0.000000e+00, %entry ], [ %add.lcssa, %while.end.loopexit ]
%conv = uitofp i32 %N to float
%div = fdiv fast float %sum.0.lcssa, %conv
store float %div, ptr %Output, align 4
ret void
}
define dso_local void @f16_reduction(ptr nocapture readonly %Input, i32 %N, ptr nocapture %Output) {
; CHECK-LABEL: f16_reduction(
; CHECK: vector.body:
; CHECK: @llvm.masked.load
; CHECK: br i1 %{{.*}}, label {{.*}}, label %vector.body
entry:
%cmp6 = icmp eq i32 %N, 0
br i1 %cmp6, label %while.end, label %while.body.preheader
while.body.preheader: ; preds = %entry
br label %while.body
while.body: ; preds = %while.body.preheader, %while.body
%blkCnt.09 = phi i32 [ %dec, %while.body ], [ %N, %while.body.preheader ]
%sum.08 = phi half [ %add, %while.body ], [ 0.000000e+00, %while.body.preheader ]
%Input.addr.07 = phi ptr [ %incdec.ptr, %while.body ], [ %Input, %while.body.preheader ]
%incdec.ptr = getelementptr inbounds half, ptr %Input.addr.07, i32 1
%0 = load half, ptr %Input.addr.07, align 2
%add = fadd fast half %0, %sum.08
%dec = add i32 %blkCnt.09, -1
%cmp = icmp eq i32 %dec, 0
br i1 %cmp, label %while.end.loopexit, label %while.body
while.end.loopexit: ; preds = %while.body
%add.lcssa = phi half [ %add, %while.body ]
br label %while.end
while.end: ; preds = %while.end.loopexit, %entry
%sum.0.lcssa = phi half [ 0.000000e+00, %entry ], [ %add.lcssa, %while.end.loopexit ]
%conv = uitofp i32 %N to half
%div = fdiv fast half %sum.0.lcssa, %conv
store half %div, ptr %Output, align 2
ret void
}
define dso_local void @mixed_f32_i32_reduction(ptr nocapture readonly %fInput, ptr nocapture readonly %iInput, i32 %N, ptr nocapture %fOutput, ptr nocapture %iOutput) {
; CHECK-LABEL: mixed_f32_i32_reduction(
; CHECK: vector.body:
; CHECK: @llvm.masked.load
; CHECK: br i1 %{{.*}}, label {{.*}}, label %vector.body
entry:
%cmp15 = icmp eq i32 %N, 0
br i1 %cmp15, label %while.end, label %while.body.preheader
while.body.preheader:
br label %while.body
while.body:
%blkCnt.020 = phi i32 [ %dec, %while.body ], [ %N, %while.body.preheader ]
%isum.019 = phi i32 [ %add2, %while.body ], [ 0, %while.body.preheader ]
%fsum.018 = phi float [ %add, %while.body ], [ 0.000000e+00, %while.body.preheader ]
%fInput.addr.017 = phi ptr [ %incdec.ptr, %while.body ], [ %fInput, %while.body.preheader ]
%iInput.addr.016 = phi ptr [ %incdec.ptr1, %while.body ], [ %iInput, %while.body.preheader ]
%incdec.ptr = getelementptr inbounds float, ptr %fInput.addr.017, i32 1
%incdec.ptr1 = getelementptr inbounds i32, ptr %iInput.addr.016, i32 1
%0 = load i32, ptr %iInput.addr.016, align 4
%add2 = add nsw i32 %0, %isum.019
%1 = load float, ptr %fInput.addr.017, align 4
%add = fadd fast float %1, %fsum.018
%dec = add i32 %blkCnt.020, -1
%cmp = icmp eq i32 %dec, 0
br i1 %cmp, label %while.end.loopexit, label %while.body
while.end.loopexit:
%add.lcssa = phi float [ %add, %while.body ]
%add2.lcssa = phi i32 [ %add2, %while.body ]
%phitmp = sitofp i32 %add2.lcssa to float
br label %while.end
while.end:
%fsum.0.lcssa = phi float [ 0.000000e+00, %entry ], [ %add.lcssa, %while.end.loopexit ]
%isum.0.lcssa = phi float [ 0.000000e+00, %entry ], [ %phitmp, %while.end.loopexit ]
%conv = uitofp i32 %N to float
%div = fdiv fast float %fsum.0.lcssa, %conv
store float %div, ptr %fOutput, align 4
%div5 = fdiv fast float %isum.0.lcssa, %conv
%conv6 = fptosi float %div5 to i32
store i32 %conv6, ptr %iOutput, align 4
ret void
}
define dso_local i32 @i32_mul_reduction(ptr noalias nocapture readonly %B, i32 %N) {
; CHECK-LABEL: i32_mul_reduction(
; CHECK: vector.body:
; CHECK: @llvm.masked.load
; CHECK: br i1 %{{.*}}, label {{.*}}, label %vector.body
entry:
%cmp6 = icmp sgt i32 %N, 0
br i1 %cmp6, label %for.body.preheader, label %for.cond.cleanup
for.body.preheader:
br label %for.body
for.cond.cleanup.loopexit:
%mul.lcssa = phi i32 [ %mul, %for.body ]
br label %for.cond.cleanup
for.cond.cleanup:
%S.0.lcssa = phi i32 [ 1, %entry ], [ %mul.lcssa, %for.cond.cleanup.loopexit ]
ret i32 %S.0.lcssa
for.body:
%i.08 = phi i32 [ %inc, %for.body ], [ 0, %for.body.preheader ]
%S.07 = phi i32 [ %mul, %for.body ], [ 1, %for.body.preheader ]
%arrayidx = getelementptr inbounds i32, ptr %B, i32 %i.08
%0 = load i32, ptr %arrayidx, align 4
%mul = mul nsw i32 %0, %S.07
%inc = add nuw nsw i32 %i.08, 1
%exitcond = icmp eq i32 %inc, %N
br i1 %exitcond, label %for.cond.cleanup.loopexit, label %for.body
}
define dso_local i32 @i32_or_reduction(ptr noalias nocapture readonly %B, i32 %N) {
; CHECK-LABEL: i32_or_reduction(
; CHECK: vector.body:
; CHECK: @llvm.masked.load
; CHECK: br i1 %{{.*}}, label {{.*}}, label %vector.body
entry:
%cmp6 = icmp sgt i32 %N, 0
br i1 %cmp6, label %for.body.preheader, label %for.cond.cleanup
for.body.preheader: ; preds = %entry
br label %for.body
for.cond.cleanup.loopexit: ; preds = %for.body
%or.lcssa = phi i32 [ %or, %for.body ]
br label %for.cond.cleanup
for.cond.cleanup: ; preds = %for.cond.cleanup.loopexit, %entry
%S.0.lcssa = phi i32 [ 1, %entry ], [ %or.lcssa, %for.cond.cleanup.loopexit ]
ret i32 %S.0.lcssa
for.body: ; preds = %for.body.preheader, %for.body
%i.08 = phi i32 [ %inc, %for.body ], [ 0, %for.body.preheader ]
%S.07 = phi i32 [ %or, %for.body ], [ 1, %for.body.preheader ]
%arrayidx = getelementptr inbounds i32, ptr %B, i32 %i.08
%0 = load i32, ptr %arrayidx, align 4
%or = or i32 %0, %S.07
%inc = add nuw nsw i32 %i.08, 1
%exitcond = icmp eq i32 %inc, %N
br i1 %exitcond, label %for.cond.cleanup.loopexit, label %for.body
}
define dso_local i32 @i32_and_reduction(ptr noalias nocapture readonly %A, i32 %N, i32 %S) {
; CHECK-LABEL: i32_and_reduction(
; CHECK: vector.body:
; CHECK: @llvm.masked.load
; CHECK: br i1 %{{.*}}, label {{.*}}, label %vector.body
entry:
%cmp5 = icmp sgt i32 %N, 0
br i1 %cmp5, label %for.body.preheader, label %for.cond.cleanup
for.body.preheader: ; preds = %entry
br label %for.body
for.cond.cleanup.loopexit: ; preds = %for.body
%and.lcssa = phi i32 [ %and, %for.body ]
br label %for.cond.cleanup
for.cond.cleanup: ; preds = %for.cond.cleanup.loopexit, %entry
%S.addr.0.lcssa = phi i32 [ %S, %entry ], [ %and.lcssa, %for.cond.cleanup.loopexit ]
ret i32 %S.addr.0.lcssa
for.body: ; preds = %for.body.preheader, %for.body
%i.07 = phi i32 [ %inc, %for.body ], [ 0, %for.body.preheader ]
%S.addr.06 = phi i32 [ %and, %for.body ], [ %S, %for.body.preheader ]
%arrayidx = getelementptr inbounds i32, ptr %A, i32 %i.07
%0 = load i32, ptr %arrayidx, align 4
%and = and i32 %0, %S.addr.06
%inc = add nuw nsw i32 %i.07, 1
%exitcond = icmp eq i32 %inc, %N
br i1 %exitcond, label %for.cond.cleanup.loopexit, label %for.body
}
|
