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
|
// RUN: mlir-opt %s --pass-pipeline="builtin.module(llvm.func(sroa))" --split-input-file | FileCheck %s
// CHECK-LABEL: llvm.func @basic_struct
llvm.func @basic_struct() -> i32 {
// CHECK: %[[SIZE:.*]] = llvm.mlir.constant(1 : i32)
%0 = llvm.mlir.constant(1 : i32) : i32
// CHECK: %[[ALLOCA:.*]] = llvm.alloca %[[SIZE]] x i32
%1 = llvm.alloca %0 x !llvm.struct<"foo", (i32, f64, i32)> {alignment = 8 : i64} : (i32) -> !llvm.ptr
%2 = llvm.getelementptr inbounds %1[0, 2] : (!llvm.ptr) -> !llvm.ptr, !llvm.struct<"foo", (i32, f64, i32)>
// CHECK: %[[RES:.*]] = llvm.load %[[ALLOCA]]
%3 = llvm.load %2 : !llvm.ptr -> i32
// CHECK: llvm.return %[[RES]] : i32
llvm.return %3 : i32
}
// -----
// CHECK-LABEL: llvm.func @basic_array
llvm.func @basic_array() -> i32 {
// CHECK: %[[SIZE:.*]] = llvm.mlir.constant(1 : i32)
%0 = llvm.mlir.constant(1 : i32) : i32
// CHECK: %[[ALLOCA:.*]] = llvm.alloca %[[SIZE]] x i32
%1 = llvm.alloca %0 x !llvm.array<10 x i32> {alignment = 8 : i64} : (i32) -> !llvm.ptr
%2 = llvm.getelementptr inbounds %1[0, 2] : (!llvm.ptr) -> !llvm.ptr, !llvm.array<10 x i32>
// CHECK: %[[RES:.*]] = llvm.load %[[ALLOCA]]
%3 = llvm.load %2 : !llvm.ptr -> i32
// CHECK: llvm.return %[[RES]] : i32
llvm.return %3 : i32
}
// -----
// CHECK-LABEL: llvm.func @multi_level_direct
llvm.func @multi_level_direct() -> i32 {
// CHECK: %[[SIZE:.*]] = llvm.mlir.constant(1 : i32)
%0 = llvm.mlir.constant(1 : i32) : i32
// CHECK: %[[ALLOCA:.*]] = llvm.alloca %[[SIZE]] x i32
%1 = llvm.alloca %0 x !llvm.struct<"foo", (i32, f64, struct<"bar", (i8, array<10 x array<10 x i32>>, i8)>)> {alignment = 8 : i64} : (i32) -> !llvm.ptr
%2 = llvm.getelementptr inbounds %1[0, 2, 1, 5, 8] : (!llvm.ptr) -> !llvm.ptr, !llvm.struct<"foo", (i32, f64, struct<"bar", (i8, array<10 x array<10 x i32>>, i8)>)>
// CHECK: %[[RES:.*]] = llvm.load %[[ALLOCA]]
%3 = llvm.load %2 : !llvm.ptr -> i32
// CHECK: llvm.return %[[RES]] : i32
llvm.return %3 : i32
}
// -----
// The first application of SROA would generate a GEP with indices [0, 0]. This
// test ensures this GEP is not eliminated during the first application. Even
// though doing it would be correct, it would prevent the second application
// of SROA to eliminate the array. GEPs should be eliminated only when they are
// truly trivial (with indices [0]).
// CHECK-LABEL: llvm.func @multi_level_direct_two_applications
llvm.func @multi_level_direct_two_applications() -> i32 {
// CHECK: %[[SIZE:.*]] = llvm.mlir.constant(1 : i32)
%0 = llvm.mlir.constant(1 : i32) : i32
// CHECK: %[[ALLOCA:.*]] = llvm.alloca %[[SIZE]] x i32
%1 = llvm.alloca %0 x !llvm.struct<"foo", (i32, f64, array<10 x i32>, i8)> {alignment = 8 : i64} : (i32) -> !llvm.ptr
%2 = llvm.getelementptr inbounds %1[0, 2, 0] : (!llvm.ptr) -> !llvm.ptr, !llvm.struct<"foo", (i32, f64, array<10 x i32>, i8)>
// CHECK: %[[RES:.*]] = llvm.load %[[ALLOCA]]
%3 = llvm.load %2 : !llvm.ptr -> i32
// CHECK: llvm.return %[[RES]] : i32
llvm.return %3 : i32
}
// -----
// CHECK-LABEL: llvm.func @multi_level_indirect
llvm.func @multi_level_indirect() -> i32 {
// CHECK: %[[SIZE:.*]] = llvm.mlir.constant(1 : i32)
%0 = llvm.mlir.constant(1 : i32) : i32
// CHECK: %[[ALLOCA:.*]] = llvm.alloca %[[SIZE]] x i32
%1 = llvm.alloca %0 x !llvm.struct<"foo", (i32, f64, struct<"bar", (i8, array<10 x array<10 x i32>>, i8)>)> {alignment = 8 : i64} : (i32) -> !llvm.ptr
%2 = llvm.getelementptr inbounds %1[0, 2, 1, 5] : (!llvm.ptr) -> !llvm.ptr, !llvm.struct<"foo", (i32, f64, struct<"bar", (i8, array<10 x array<10 x i32>>, i8)>)>
%3 = llvm.getelementptr inbounds %2[0, 8] : (!llvm.ptr) -> !llvm.ptr, !llvm.array<10 x i32>
// CHECK: %[[RES:.*]] = llvm.load %[[ALLOCA]]
%4 = llvm.load %3 : !llvm.ptr -> i32
// CHECK: llvm.return %[[RES]] : i32
llvm.return %4 : i32
}
// -----
// CHECK-LABEL: llvm.func @resolve_alias
// CHECK-SAME: (%[[ARG:.*]]: i32)
llvm.func @resolve_alias(%arg: i32) -> i32 {
// CHECK: %[[SIZE:.*]] = llvm.mlir.constant(1 : i32)
%0 = llvm.mlir.constant(1 : i32) : i32
// CHECK: %[[ALLOCA:.*]] = llvm.alloca %[[SIZE]] x i32
%1 = llvm.alloca %0 x !llvm.struct<"foo", (i32, f64, i32)> {alignment = 8 : i64} : (i32) -> !llvm.ptr
%2 = llvm.getelementptr %1[0, 2] : (!llvm.ptr) -> !llvm.ptr, !llvm.struct<"foo", (i32, f64, i32)>
%3 = llvm.getelementptr inbounds %1[0, 2] : (!llvm.ptr) -> !llvm.ptr, !llvm.struct<"foo", (i32, f64, i32)>
// CHECK: llvm.store %[[ARG]], %[[ALLOCA]]
llvm.store %arg, %2 : i32, !llvm.ptr
// CHECK: %[[RES:.*]] = llvm.load %[[ALLOCA]]
%4 = llvm.load %3 : !llvm.ptr -> i32
// CHECK: llvm.return %[[RES]] : i32
llvm.return %4 : i32
}
// -----
// CHECK-LABEL: llvm.func @no_non_single_support
llvm.func @no_non_single_support() -> i32 {
// CHECK: %[[SIZE:.*]] = llvm.mlir.constant
%0 = llvm.mlir.constant(2 : i32) : i32
// CHECK: %[[ALLOCA:.*]] = llvm.alloca %[[SIZE]] x !llvm.struct<"foo", (i32, f64, i32)> {alignment = 8 : i64} : (i32) -> !llvm.ptr
%1 = llvm.alloca %0 x !llvm.struct<"foo", (i32, f64, i32)> {alignment = 8 : i64} : (i32) -> !llvm.ptr
// CHECK-NOT: = llvm.alloca
%2 = llvm.getelementptr inbounds %1[0, 2] : (!llvm.ptr) -> !llvm.ptr, !llvm.struct<"foo", (i32, f64, i32)>
%3 = llvm.load %2 : !llvm.ptr -> i32
llvm.return %3 : i32
}
// -----
// CHECK-LABEL: llvm.func @no_pointer_indexing
llvm.func @no_pointer_indexing() -> i32 {
// CHECK: %[[SIZE:.*]] = llvm.mlir.constant(1 : i32)
%0 = llvm.mlir.constant(1 : i32) : i32
// CHECK: %[[ALLOCA:.*]] = llvm.alloca %[[SIZE]] x !llvm.struct<"foo", (i32, f64, i32)> {alignment = 8 : i64} : (i32) -> !llvm.ptr
%1 = llvm.alloca %0 x !llvm.struct<"foo", (i32, f64, i32)> {alignment = 8 : i64} : (i32) -> !llvm.ptr
// CHECK-NOT: = llvm.alloca
%2 = llvm.getelementptr %1[1, 2] : (!llvm.ptr) -> !llvm.ptr, !llvm.struct<"foo", (i32, f64, i32)>
%3 = llvm.load %2 : !llvm.ptr -> i32
llvm.return %3 : i32
}
// -----
// CHECK-LABEL: llvm.func @no_direct_use
llvm.func @no_direct_use() -> i32 {
// CHECK: %[[SIZE:.*]] = llvm.mlir.constant(1 : i32)
%0 = llvm.mlir.constant(1 : i32) : i32
// CHECK: %[[ALLOCA:.*]] = llvm.alloca %[[SIZE]] x !llvm.struct<"foo", (i32, f64, i32)> {alignment = 8 : i64} : (i32) -> !llvm.ptr
%1 = llvm.alloca %0 x !llvm.struct<"foo", (i32, f64, i32)> {alignment = 8 : i64} : (i32) -> !llvm.ptr
// CHECK-NOT: = llvm.alloca
%2 = llvm.getelementptr %1[0, 2] : (!llvm.ptr) -> !llvm.ptr, !llvm.struct<"foo", (i32, f64, i32)>
%3 = llvm.load %2 : !llvm.ptr -> i32
llvm.call @use(%1) : (!llvm.ptr) -> ()
llvm.return %3 : i32
}
llvm.func @use(!llvm.ptr)
// -----
// CHECK-LABEL: llvm.func @direct_promotable_use_is_fine
llvm.func @direct_promotable_use_is_fine() -> i32 {
// CHECK: %[[SIZE:.*]] = llvm.mlir.constant(1 : i32)
%0 = llvm.mlir.constant(1 : i32) : i32
// CHECK: %[[ALLOCA:.*]] = llvm.alloca %[[SIZE]] x i32
%1 = llvm.alloca %0 x !llvm.struct<"foo", (i32, f64, i32)> {alignment = 8 : i64} : (i32) -> !llvm.ptr
%2 = llvm.getelementptr %1[0, 2] : (!llvm.ptr) -> !llvm.ptr, !llvm.struct<"foo", (i32, f64, i32)>
// CHECK: %[[RES:.*]] = llvm.load %[[ALLOCA]]
%3 = llvm.load %2 : !llvm.ptr -> i32
// This is a direct use of the slot but it can be removed because it implements PromotableOpInterface.
llvm.intr.lifetime.start 2, %1 : !llvm.ptr
// CHECK: llvm.return %[[RES]] : i32
llvm.return %3 : i32
}
// -----
// CHECK-LABEL: llvm.func @direct_promotable_use_is_fine_on_accessor
llvm.func @direct_promotable_use_is_fine_on_accessor() -> i32 {
// CHECK: %[[SIZE:.*]] = llvm.mlir.constant(1 : i32)
%0 = llvm.mlir.constant(1 : i32) : i32
// CHECK: %[[ALLOCA:.*]] = llvm.alloca %[[SIZE]] x i32
%1 = llvm.alloca %0 x !llvm.struct<"foo", (i32, f64, i32)> {alignment = 8 : i64} : (i32) -> !llvm.ptr
%2 = llvm.getelementptr %1[0, 2] : (!llvm.ptr) -> !llvm.ptr, !llvm.struct<"foo", (i32, f64, i32)>
// CHECK: %[[RES:.*]] = llvm.load %[[ALLOCA]]
%3 = llvm.load %2 : !llvm.ptr -> i32
// This does not provide side-effect info but it can be removed because it implements PromotableOpInterface.
llvm.intr.lifetime.start 2, %2 : !llvm.ptr
// CHECK: llvm.return %[[RES]] : i32
llvm.return %3 : i32
}
// -----
// CHECK-LABEL: llvm.func @no_dynamic_indexing
// CHECK-SAME: (%[[ARG:.*]]: i32)
llvm.func @no_dynamic_indexing(%arg: i32) -> i32 {
// CHECK: %[[SIZE:.*]] = llvm.mlir.constant(1 : i32)
%0 = llvm.mlir.constant(1 : i32) : i32
// CHECK: %[[ALLOCA:.*]] = llvm.alloca %[[SIZE]] x !llvm.array<10 x i32> {alignment = 8 : i64} : (i32) -> !llvm.ptr
%1 = llvm.alloca %0 x !llvm.array<10 x i32> {alignment = 8 : i64} : (i32) -> !llvm.ptr
// CHECK-NOT: = llvm.alloca
// CHECK: %[[GEP:.*]] = llvm.getelementptr %[[ALLOCA]][0, %[[ARG]]]
%2 = llvm.getelementptr %1[0, %arg] : (!llvm.ptr, i32) -> !llvm.ptr, !llvm.array<10 x i32>
// CHECK: %[[RES:.*]] = llvm.load %[[GEP]]
%3 = llvm.load %2 : !llvm.ptr -> i32
// CHECK: llvm.return %[[RES]] : i32
llvm.return %3 : i32
}
// -----
// CHECK-LABEL: llvm.func @no_typed_pointers
llvm.func @no_typed_pointers() -> i32 {
// CHECK: %[[SIZE:.*]] = llvm.mlir.constant(1 : i32)
%0 = llvm.mlir.constant(1 : i32) : i32
// CHECK: %[[ALLOCA:.*]] = llvm.alloca %[[SIZE]] x !llvm.array<10 x i32> {alignment = 8 : i64} : (i32) -> !llvm.ptr<array<10 x i32>>
%1 = llvm.alloca %0 x !llvm.array<10 x i32> {alignment = 8 : i64} : (i32) -> !llvm.ptr<array<10 x i32>>
// CHECK-NOT: = llvm.alloca
%2 = llvm.getelementptr %1[0, 1] : (!llvm.ptr<array<10 x i32>>) -> !llvm.ptr<i32>
%3 = llvm.load %2 : !llvm.ptr<i32>
llvm.return %3 : i32
}
|
