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
|
; REQUIRES: asserts
; RUN: opt < %s -force-vector-width=2 -passes=loop-vectorize -debug-only=loop-vectorize -disable-output 2>&1 | FileCheck %s
target datalayout = "e-m:e-i64:64-i128:128-n32:64-S128"
target triple = "aarch64--linux-gnu"
; Check predication-related cost calculations, including scalarization overhead
; and block probability scaling. Note that the functionality being tested is
; not specific to AArch64. We specify a target to get actual values for the
; instruction costs.
; CHECK-LABEL: predicated_udiv
;
; This test checks that we correctly compute the cost of the predicated udiv
; instruction. If we assume the block probability is 50%, we compute the cost
; as:
;
; Cost of udiv:
; (udiv(2) + extractelement(8) + insertelement(4)) / 2 = 7
;
; CHECK: Scalarizing and predicating: %tmp4 = udiv i32 %tmp2, %tmp3
; CHECK: Found an estimated cost of 7 for VF 2 For instruction: %tmp4 = udiv i32 %tmp2, %tmp3
;
define i32 @predicated_udiv(ptr %a, ptr %b, i1 %c, i64 %n) {
entry:
br label %for.body
for.body:
%i = phi i64 [ 0, %entry ], [ %i.next, %for.inc ]
%r = phi i32 [ 0, %entry ], [ %tmp6, %for.inc ]
%tmp0 = getelementptr inbounds i32, ptr %a, i64 %i
%tmp1 = getelementptr inbounds i32, ptr %b, i64 %i
%tmp2 = load i32, ptr %tmp0, align 4
%tmp3 = load i32, ptr %tmp1, align 4
br i1 %c, label %if.then, label %for.inc
if.then:
%tmp4 = udiv i32 %tmp2, %tmp3
br label %for.inc
for.inc:
%tmp5 = phi i32 [ %tmp3, %for.body ], [ %tmp4, %if.then]
%tmp6 = add i32 %r, %tmp5
%i.next = add nuw nsw i64 %i, 1
%cond = icmp slt i64 %i.next, %n
br i1 %cond, label %for.body, label %for.end
for.end:
%tmp7 = phi i32 [ %tmp6, %for.inc ]
ret i32 %tmp7
}
; CHECK-LABEL: predicated_store
;
; This test checks that we correctly compute the cost of the predicated store
; instruction. If we assume the block probability is 50%, we compute the cost
; as:
;
; Cost of store:
; (store(4) + extractelement(4)) / 2 = 4
;
; CHECK: Scalarizing and predicating: store i32 %tmp2, ptr %tmp0, align 4
; CHECK: Found an estimated cost of 4 for VF 2 For instruction: store i32 %tmp2, ptr %tmp0, align 4
;
define void @predicated_store(ptr %a, i1 %c, i32 %x, i64 %n) {
entry:
br label %for.body
for.body:
%i = phi i64 [ 0, %entry ], [ %i.next, %for.inc ]
%tmp0 = getelementptr inbounds i32, ptr %a, i64 %i
%tmp1 = load i32, ptr %tmp0, align 4
%tmp2 = add nsw i32 %tmp1, %x
br i1 %c, label %if.then, label %for.inc
if.then:
store i32 %tmp2, ptr %tmp0, align 4
br label %for.inc
for.inc:
%i.next = add nuw nsw i64 %i, 1
%cond = icmp slt i64 %i.next, %n
br i1 %cond, label %for.body, label %for.end
for.end:
ret void
}
; CHECK-LABEL: predicated_store_phi
;
; Same as predicate_store except we use a pointer PHI to maintain the address
;
; CHECK: Found scalar instruction: %addr = phi ptr [ %a, %entry ], [ %addr.next, %for.inc ]
; CHECK: Found scalar instruction: %addr.next = getelementptr inbounds i32, ptr %addr, i64 1
; CHECK: Scalarizing and predicating: store i32 %tmp2, ptr %addr, align 4
; CHECK: Found an estimated cost of 0 for VF 2 For instruction: %addr = phi ptr [ %a, %entry ], [ %addr.next, %for.inc ]
; CHECK: Found an estimated cost of 4 for VF 2 For instruction: store i32 %tmp2, ptr %addr, align 4
;
define void @predicated_store_phi(ptr %a, i1 %c, i32 %x, i64 %n) {
entry:
br label %for.body
for.body:
%i = phi i64 [ 0, %entry ], [ %i.next, %for.inc ]
%addr = phi ptr [ %a, %entry ], [ %addr.next, %for.inc ]
%tmp1 = load i32, ptr %addr, align 4
%tmp2 = add nsw i32 %tmp1, %x
br i1 %c, label %if.then, label %for.inc
if.then:
store i32 %tmp2, ptr %addr, align 4
br label %for.inc
for.inc:
%i.next = add nuw nsw i64 %i, 1
%cond = icmp slt i64 %i.next, %n
%addr.next = getelementptr inbounds i32, ptr %addr, i64 1
br i1 %cond, label %for.body, label %for.end
for.end:
ret void
}
; CHECK-LABEL: predicated_udiv_scalarized_operand
;
; This test checks that we correctly compute the cost of the predicated udiv
; instruction and the add instruction it uses. The add is scalarized and sunk
; inside the predicated block. If we assume the block probability is 50%, we
; compute the cost as:
;
; Cost of add:
; (add(2) + extractelement(4)) / 2 = 3
; Cost of udiv:
; (udiv(2) + extractelement(4) + insertelement(4)) / 2 = 5
;
; CHECK: Scalarizing: %tmp3 = add nsw i32 %tmp2, %x
; CHECK: Scalarizing and predicating: %tmp4 = udiv i32 %tmp2, %tmp3
; CHECK: Found an estimated cost of 3 for VF 2 For instruction: %tmp3 = add nsw i32 %tmp2, %x
; CHECK: Found an estimated cost of 5 for VF 2 For instruction: %tmp4 = udiv i32 %tmp2, %tmp3
;
define i32 @predicated_udiv_scalarized_operand(ptr %a, i1 %c, i32 %x, i64 %n) {
entry:
br label %for.body
for.body:
%i = phi i64 [ 0, %entry ], [ %i.next, %for.inc ]
%r = phi i32 [ 0, %entry ], [ %tmp6, %for.inc ]
%tmp0 = getelementptr inbounds i32, ptr %a, i64 %i
%tmp2 = load i32, ptr %tmp0, align 4
br i1 %c, label %if.then, label %for.inc
if.then:
%tmp3 = add nsw i32 %tmp2, %x
%tmp4 = udiv i32 %tmp2, %tmp3
br label %for.inc
for.inc:
%tmp5 = phi i32 [ %tmp2, %for.body ], [ %tmp4, %if.then]
%tmp6 = add i32 %r, %tmp5
%i.next = add nuw nsw i64 %i, 1
%cond = icmp slt i64 %i.next, %n
br i1 %cond, label %for.body, label %for.end
for.end:
%tmp7 = phi i32 [ %tmp6, %for.inc ]
ret i32 %tmp7
}
; CHECK-LABEL: predicated_store_scalarized_operand
;
; This test checks that we correctly compute the cost of the predicated store
; instruction and the add instruction it uses. The add is scalarized and sunk
; inside the predicated block. If we assume the block probability is 50%, we
; compute the cost as:
;
; Cost of add:
; (add(2) + extractelement(4)) / 2 = 3
; Cost of store:
; store(4) / 2 = 2
;
; CHECK: Scalarizing: %tmp2 = add nsw i32 %tmp1, %x
; CHECK: Scalarizing and predicating: store i32 %tmp2, ptr %tmp0, align 4
; CHECK: Found an estimated cost of 3 for VF 2 For instruction: %tmp2 = add nsw i32 %tmp1, %x
; CHECK: Found an estimated cost of 2 for VF 2 For instruction: store i32 %tmp2, ptr %tmp0, align 4
;
define void @predicated_store_scalarized_operand(ptr %a, i1 %c, i32 %x, i64 %n) {
entry:
br label %for.body
for.body:
%i = phi i64 [ 0, %entry ], [ %i.next, %for.inc ]
%tmp0 = getelementptr inbounds i32, ptr %a, i64 %i
%tmp1 = load i32, ptr %tmp0, align 4
br i1 %c, label %if.then, label %for.inc
if.then:
%tmp2 = add nsw i32 %tmp1, %x
store i32 %tmp2, ptr %tmp0, align 4
br label %for.inc
for.inc:
%i.next = add nuw nsw i64 %i, 1
%cond = icmp slt i64 %i.next, %n
br i1 %cond, label %for.body, label %for.end
for.end:
ret void
}
; CHECK-LABEL: predication_multi_context
;
; This test checks that we correctly compute the cost of multiple predicated
; instructions in the same block. The sdiv, udiv, and store must be scalarized
; and predicated. The sub feeding the store is scalarized and sunk inside the
; store's predicated block. However, the add feeding the sdiv and udiv cannot
; be sunk and is not scalarized. If we assume the block probability is 50%, we
; compute the cost as:
;
; Cost of add:
; add(1) = 1
; Cost of sdiv:
; (sdiv(2) + extractelement(8) + insertelement(4)) / 2 = 7
; Cost of udiv:
; (udiv(2) + extractelement(8) + insertelement(4)) / 2 = 7
; Cost of sub:
; (sub(2) + extractelement(4)) / 2 = 3
; Cost of store:
; store(4) / 2 = 2
;
; CHECK-NOT: Scalarizing: %tmp2 = add i32 %tmp1, %x
; CHECK: Scalarizing and predicating: %tmp3 = sdiv i32 %tmp1, %tmp2
; CHECK: Scalarizing and predicating: %tmp4 = udiv i32 %tmp3, %tmp2
; CHECK: Scalarizing: %tmp5 = sub i32 %tmp4, %x
; CHECK: Scalarizing and predicating: store i32 %tmp5, ptr %tmp0, align 4
; CHECK: Found an estimated cost of 1 for VF 2 For instruction: %tmp2 = add i32 %tmp1, %x
; CHECK: Found an estimated cost of 7 for VF 2 For instruction: %tmp3 = sdiv i32 %tmp1, %tmp2
; CHECK: Found an estimated cost of 7 for VF 2 For instruction: %tmp4 = udiv i32 %tmp3, %tmp2
; CHECK: Found an estimated cost of 3 for VF 2 For instruction: %tmp5 = sub i32 %tmp4, %x
; CHECK: Found an estimated cost of 2 for VF 2 For instruction: store i32 %tmp5, ptr %tmp0, align 4
;
define void @predication_multi_context(ptr %a, i1 %c, i32 %x, i64 %n) {
entry:
br label %for.body
for.body:
%i = phi i64 [ 0, %entry ], [ %i.next, %for.inc ]
%tmp0 = getelementptr inbounds i32, ptr %a, i64 %i
%tmp1 = load i32, ptr %tmp0, align 4
br i1 %c, label %if.then, label %for.inc
if.then:
%tmp2 = add i32 %tmp1, %x
%tmp3 = sdiv i32 %tmp1, %tmp2
%tmp4 = udiv i32 %tmp3, %tmp2
%tmp5 = sub i32 %tmp4, %x
store i32 %tmp5, ptr %tmp0, align 4
br label %for.inc
for.inc:
%i.next = add nuw nsw i64 %i, 1
%cond = icmp slt i64 %i.next, %n
br i1 %cond, label %for.body, label %for.end
for.end:
ret void
}
|
