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
|
; RUN: opt -loop-vectorize -force-vector-width=4 -force-vector-interleave=1 -S %s | FileCheck %s
@p = external local_unnamed_addr global [257 x i32], align 16
@q = external local_unnamed_addr global [257 x i32], align 16
; Test case for PR43398.
define void @can_sink_after_store(i32 %x, i32* %ptr, i64 %tc) local_unnamed_addr #0 {
; CHECK-LABEL: vector.ph:
; CHECK: %broadcast.splatinsert1 = insertelement <4 x i32> undef, i32 %x, i32 0
; CHECK-NEXT: %broadcast.splat2 = shufflevector <4 x i32> %broadcast.splatinsert1, <4 x i32> undef, <4 x i32> zeroinitializer
; CHECK-NEXT: %vector.recur.init = insertelement <4 x i32> undef, i32 %.pre, i32 3
; CHECK-NEXT: br label %vector.body
; CHECK-LABEL: vector.body:
; CHECK-NEXT: %index = phi i64 [ 0, %vector.ph ], [ %index.next, %vector.body ]
; CHECK-NEXT: %vector.recur = phi <4 x i32> [ %vector.recur.init, %vector.ph ], [ %wide.load, %vector.body ]
; CHECK-NEXT: %offset.idx = add i64 1, %index
; CHECK-NEXT: %broadcast.splatinsert = insertelement <4 x i64> undef, i64 %offset.idx, i32 0
; CHECK-NEXT: %broadcast.splat = shufflevector <4 x i64> %broadcast.splatinsert, <4 x i64> undef, <4 x i32> zeroinitializer
; CHECK-NEXT: %induction = add <4 x i64> %broadcast.splat, <i64 0, i64 1, i64 2, i64 3>
; CHECK-NEXT: %0 = add i64 %offset.idx, 0
; CHECK-NEXT: %1 = getelementptr inbounds [257 x i32], [257 x i32]* @p, i64 0, i64 %0
; CHECK-NEXT: %2 = getelementptr inbounds i32, i32* %1, i32 0
; CHECK-NEXT: %3 = bitcast i32* %2 to <4 x i32>*
; CHECK-NEXT: %wide.load = load <4 x i32>, <4 x i32>* %3, align 4
; CHECK-NEXT: %4 = shufflevector <4 x i32> %vector.recur, <4 x i32> %wide.load, <4 x i32> <i32 3, i32 4, i32 5, i32 6>
; CHECK-NEXT: %5 = add <4 x i32> %4, %broadcast.splat2
; CHECK-NEXT: %6 = add <4 x i32> %5, %wide.load
; CHECK-NEXT: %7 = getelementptr inbounds [257 x i32], [257 x i32]* @q, i64 0, i64 %0
; CHECK-NEXT: %8 = getelementptr inbounds i32, i32* %7, i32 0
; CHECK-NEXT: %9 = bitcast i32* %8 to <4 x i32>*
; CHECK-NEXT: store <4 x i32> %6, <4 x i32>* %9, align 4
; CHECK-NEXT: %index.next = add i64 %index, 4
; CHECK-NEXT: %10 = icmp eq i64 %index.next, 1996
; CHECK-NEXT: br i1 %10, label %middle.block, label %vector.body
;
entry:
br label %preheader
preheader:
%idx.phi.trans = getelementptr inbounds [257 x i32], [257 x i32]* @p, i64 0, i64 1
%.pre = load i32, i32* %idx.phi.trans, align 4
br label %for
for:
%pre.phi = phi i32 [ %.pre, %preheader ], [ %pre.next, %for ]
%iv = phi i64 [ 1, %preheader ], [ %iv.next, %for ]
%add.1 = add i32 %pre.phi, %x
%idx.1 = getelementptr inbounds [257 x i32], [257 x i32]* @p, i64 0, i64 %iv
%pre.next = load i32, i32* %idx.1, align 4
%add.2 = add i32 %add.1, %pre.next
%idx.2 = getelementptr inbounds [257 x i32], [257 x i32]* @q, i64 0, i64 %iv
store i32 %add.2, i32* %idx.2, align 4
%iv.next = add nuw nsw i64 %iv, 1
%exitcond = icmp eq i64 %iv.next, 2000
br i1 %exitcond, label %exit, label %for
exit:
ret void
}
; We can sink potential trapping instructions, as this will only delay the trap
; and not introduce traps on additional paths.
define void @sink_sdiv(i32 %x, i32* %ptr, i64 %tc) local_unnamed_addr #0 {
; CHECK-LABEL: vector.ph:
; CHECK: %broadcast.splatinsert1 = insertelement <4 x i32> undef, i32 %x, i32 0
; CHECK-NEXT: %broadcast.splat2 = shufflevector <4 x i32> %broadcast.splatinsert1, <4 x i32> undef, <4 x i32> zeroinitializer
; CHECK-NEXT: %vector.recur.init = insertelement <4 x i32> undef, i32 %.pre, i32 3
; CHECK-NEXT: br label %vector.body
; CHECK-LABEL: vector.body:
; CHECK-NEXT: %index = phi i64 [ 0, %vector.ph ], [ %index.next, %vector.body ]
; CHECK-NEXT: %vector.recur = phi <4 x i32> [ %vector.recur.init, %vector.ph ], [ %wide.load, %vector.body ]
; CHECK-NEXT: %offset.idx = add i64 1, %index
; CHECK-NEXT: %broadcast.splatinsert = insertelement <4 x i64> undef, i64 %offset.idx, i32 0
; CHECK-NEXT: %broadcast.splat = shufflevector <4 x i64> %broadcast.splatinsert, <4 x i64> undef, <4 x i32> zeroinitializer
; CHECK-NEXT: %induction = add <4 x i64> %broadcast.splat, <i64 0, i64 1, i64 2, i64 3>
; CHECK-NEXT: %0 = add i64 %offset.idx, 0
; CHECK-NEXT: %1 = getelementptr inbounds [257 x i32], [257 x i32]* @p, i64 0, i64 %0
; CHECK-NEXT: %2 = getelementptr inbounds i32, i32* %1, i32 0
; CHECK-NEXT: %3 = bitcast i32* %2 to <4 x i32>*
; CHECK-NEXT: %wide.load = load <4 x i32>, <4 x i32>* %3, align 4
; CHECK-NEXT: %4 = shufflevector <4 x i32> %vector.recur, <4 x i32> %wide.load, <4 x i32> <i32 3, i32 4, i32 5, i32 6>
; CHECK-NEXT: %5 = sdiv <4 x i32> %4, %broadcast.splat2
; CHECK-NEXT: %6 = add <4 x i32> %5, %wide.load
; CHECK-NEXT: %7 = getelementptr inbounds [257 x i32], [257 x i32]* @q, i64 0, i64 %0
; CHECK-NEXT: %8 = getelementptr inbounds i32, i32* %7, i32 0
; CHECK-NEXT: %9 = bitcast i32* %8 to <4 x i32>*
; CHECK-NEXT: store <4 x i32> %6, <4 x i32>* %9, align 4
; CHECK-NEXT: %index.next = add i64 %index, 4
; CHECK-NEXT: %10 = icmp eq i64 %index.next, 1996
; CHECK-NEXT: br i1 %10, label %middle.block, label %vector.body
;
entry:
br label %preheader
preheader:
%idx.phi.trans = getelementptr inbounds [257 x i32], [257 x i32]* @p, i64 0, i64 1
%.pre = load i32, i32* %idx.phi.trans, align 4
br label %for
for:
%pre.phi = phi i32 [ %.pre, %preheader ], [ %pre.next, %for ]
%iv = phi i64 [ 1, %preheader ], [ %iv.next, %for ]
%div.1 = sdiv i32 %pre.phi, %x
%idx.1 = getelementptr inbounds [257 x i32], [257 x i32]* @p, i64 0, i64 %iv
%pre.next = load i32, i32* %idx.1, align 4
%add.2 = add i32 %div.1, %pre.next
%idx.2 = getelementptr inbounds [257 x i32], [257 x i32]* @q, i64 0, i64 %iv
store i32 %add.2, i32* %idx.2, align 4
%iv.next = add nuw nsw i64 %iv, 1
%exitcond = icmp eq i64 %iv.next, 2000
br i1 %exitcond, label %exit, label %for
exit:
ret void
}
; FIXME: Currently we can only sink a single instruction. For the example below,
; we also have to sink users.
define void @cannot_sink_with_additional_user(i32 %x, i32* %ptr, i64 %tc) {
; CHECK-LABEL: define void @cannot_sink_with_additional_user(
; CHECK-NEXT: entry:
; CHECK-NEXT: br label %preheader
; CHECK-LABEL: preheader: ; preds = %entry
; CHECK: br label %for
; CHECK-LABEL: for: ; preds = %for, %preheader
; CHECK br i1 %exitcond, label %exit, label %for
; CHECK-LABEL: exit:
; CHECK-NEXT: ret void
entry:
br label %preheader
preheader:
%idx.phi.trans = getelementptr inbounds [257 x i32], [257 x i32]* @p, i64 0, i64 1
%.pre = load i32, i32* %idx.phi.trans, align 4
br label %for
for:
%pre.phi = phi i32 [ %.pre, %preheader ], [ %pre.next, %for ]
%iv = phi i64 [ 1, %preheader ], [ %iv.next, %for ]
%add.1 = add i32 %pre.phi, %x
%add.2 = add i32 %add.1, %x
%idx.1 = getelementptr inbounds [257 x i32], [257 x i32]* @p, i64 0, i64 %iv
%pre.next = load i32, i32* %idx.1, align 4
%add.3 = add i32 %add.1, %pre.next
%add.4 = add i32 %add.2, %add.3
%idx.2 = getelementptr inbounds [257 x i32], [257 x i32]* @q, i64 0, i64 %iv
store i32 %add.4, i32* %idx.2, align 4
%iv.next = add nuw nsw i64 %iv, 1
%exitcond = icmp eq i64 %iv.next, 2000
br i1 %exitcond, label %exit, label %for
exit:
ret void
}
; FIXME: We can sink a store, if we can guarantee that it does not alias any
; loads/stores in between.
define void @cannot_sink_store(i32 %x, i32* %ptr, i64 %tc) {
; CHECK-LABEL: define void @cannot_sink_store(
; CHECK-NEXT: entry:
; CHECK-NEXT: br label %preheader
; CHECK-LABEL: preheader: ; preds = %entry
; CHECK: br label %for
; CHECK-LABEL: for: ; preds = %for, %preheader
; CHECK br i1 %exitcond, label %exit, label %for
; CHECK-LABEL: exit:
; CHECK-NEXT: ret void
;
entry:
br label %preheader
preheader:
%idx.phi.trans = getelementptr inbounds [257 x i32], [257 x i32]* @p, i64 0, i64 1
%.pre = load i32, i32* %idx.phi.trans, align 4
br label %for
for:
%pre.phi = phi i32 [ %.pre, %preheader ], [ %pre.next, %for ]
%iv = phi i64 [ 1, %preheader ], [ %iv.next, %for ]
%add.1 = add i32 %pre.phi, %x
store i32 %add.1, i32* %ptr
%idx.1 = getelementptr inbounds [257 x i32], [257 x i32]* @p, i64 0, i64 %iv
%pre.next = load i32, i32* %idx.1, align 4
%add.2 = add i32 %add.1, %pre.next
%idx.2 = getelementptr inbounds [257 x i32], [257 x i32]* @q, i64 0, i64 %iv
store i32 %add.2, i32* %idx.2, align 4
%iv.next = add nuw nsw i64 %iv, 1
%exitcond = icmp eq i64 %iv.next, 2000
br i1 %exitcond, label %exit, label %for
exit:
ret void
}
; Some kinds of reductions are not detected by IVDescriptors. If we have a
; cycle, we cannot sink it.
define void @cannot_sink_reduction(i32 %x, i32* %ptr, i64 %tc) {
; CHECK-LABEL: define void @cannot_sink_reduction(
; CHECK-NEXT: entry:
; CHECK-NEXT: br label %preheader
; CHECK-LABEL: preheader: ; preds = %entry
; CHECK: br label %for
; CHECK-LABEL: for: ; preds = %for, %preheader
; CHECK br i1 %exitcond, label %exit, label %for
; CHECK-LABEL: exit: ; preds = %for
; CHECK-NET: ret void
;
entry:
br label %preheader
preheader:
%idx.phi.trans = getelementptr inbounds [257 x i32], [257 x i32]* @p, i64 0, i64 1
%.pre = load i32, i32* %idx.phi.trans, align 4
br label %for
for:
%pre.phi = phi i32 [ %.pre, %preheader ], [ %d, %for ]
%iv = phi i64 [ 1, %preheader ], [ %iv.next, %for ]
%d = sdiv i32 %pre.phi, %x
%idx.1 = getelementptr inbounds [257 x i32], [257 x i32]* @p, i64 0, i64 %iv
%pre.next = load i32, i32* %idx.1, align 4
%add.2 = add i32 %x, %pre.next
%idx.2 = getelementptr inbounds [257 x i32], [257 x i32]* @q, i64 0, i64 %iv
store i32 %add.2, i32* %idx.2, align 4
%iv.next = add nuw nsw i64 %iv, 1
%exitcond = icmp eq i64 %iv.next, 2000
br i1 %exitcond, label %exit, label %for
exit:
ret void
}
; TODO: We should be able to sink %tmp38 after %tmp60.
define void @instruction_with_2_FOR_operands() {
; CHECK-LABEL: define void @instruction_with_2_FOR_operands(
; CHECK-NEXT: bb:
; CHECK-NEXT: br label %bb13
; CHECK-LABEL: bb13:
; CHECK: br i1 %tmp12, label %bb13, label %bb74
; CHECK-LABEL: bb74:
; CHECK-NEXT: ret void
;
bb:
br label %bb13
bb13: ; preds = %bb13, %bb
%tmp37 = phi float [ %tmp60, %bb13 ], [ undef, %bb ]
%tmp27 = phi float [ %tmp49, %bb13 ], [ undef, %bb ]
%indvars.iv = phi i64 [ %indvars.iv.next, %bb13 ], [ 0, %bb ]
%tmp38 = fmul fast float %tmp37, %tmp27
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
%tmp49 = load float, float* undef, align 4
%tmp60 = load float, float* undef, align 4
%tmp12 = icmp slt i64 %indvars.iv, undef
br i1 %tmp12, label %bb13, label %bb74
bb74: ; preds = %bb13
ret void
}
|
