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
|
// RUN: mlir-opt -allow-unregistered-dialect -split-input-file %s | FileCheck %s
// RUN: mlir-opt -allow-unregistered-dialect %s -mlir-print-op-generic | FileCheck -check-prefix=GENERIC %s
// Check that the attributes for the affine operations are round-tripped.
// Check that `affine.yield` is visible in the generic form.
// CHECK-LABEL: @empty
func.func @empty() {
// CHECK: affine.for
// CHECK-NEXT: } {some_attr = true}
//
// GENERIC: "affine.for"()
// GENERIC-NEXT: ^bb0(%{{.*}}: index):
// GENERIC-NEXT: "affine.yield"() : () -> ()
// GENERIC-NEXT: })
affine.for %i = 0 to 10 {
} {some_attr = true}
// CHECK: affine.if
// CHECK-NEXT: } {some_attr = true}
//
// GENERIC: "affine.if"()
// GENERIC-NEXT: "affine.yield"() : () -> ()
// GENERIC-NEXT: }, {
// GENERIC-NEXT: })
affine.if affine_set<() : ()> () {
} {some_attr = true}
// CHECK: } else {
// CHECK: } {some_attr = true}
//
// GENERIC: "affine.if"()
// GENERIC-NEXT: "affine.yield"() : () -> ()
// GENERIC-NEXT: }, {
// GENERIC-NEXT: "foo"() : () -> ()
// GENERIC-NEXT: "affine.yield"() : () -> ()
// GENERIC-NEXT: })
affine.if affine_set<() : ()> () {
} else {
"foo"() : () -> ()
} {some_attr = true}
return
}
// Check that an explicit affine.yield is not printed in custom format.
// Check that no extra terminator is introduced.
// CHECK-LABEL: @affine.yield
func.func @affine.yield() {
// CHECK: affine.for
// CHECK-NEXT: }
//
// GENERIC: "affine.for"() ({
// GENERIC-NEXT: ^bb0(%{{.*}}: index):
// GENERIC-NEXT: "affine.yield"() : () -> ()
// GENERIC-NEXT: }) {lower_bound = #map, step = 1 : index, upper_bound = #map1} : () -> ()
affine.for %i = 0 to 10 {
"affine.yield"() : () -> ()
}
return
}
// -----
// CHECK-DAG: #[[$MAP0:map[0-9]*]] = affine_map<(d0)[s0] -> (1000, d0 + 512, s0)>
// CHECK-DAG: #[[$MAP1:map[0-9]*]] = affine_map<(d0, d1)[s0] -> (d0 - d1, s0 + 512)>
// CHECK-DAG: #[[$MAP2:map[0-9]*]] = affine_map<()[s0, s1] -> (s0 - s1, 11)>
// CHECK-DAG: #[[$MAP3:map[0-9]*]] = affine_map<() -> (77, 78, 79)>
// CHECK-LABEL: @affine_min
func.func @affine_min(%arg0 : index, %arg1 : index, %arg2 : index) {
// CHECK: affine.min #[[$MAP0]](%arg0)[%arg1]
%0 = affine.min affine_map<(d0)[s0] -> (1000, d0 + 512, s0)> (%arg0)[%arg1]
// CHECK: affine.min #[[$MAP1]](%arg0, %arg1)[%arg2]
%1 = affine.min affine_map<(d0, d1)[s0] -> (d0 - d1, s0 + 512)> (%arg0, %arg1)[%arg2]
// CHECK: affine.min #[[$MAP2]]()[%arg1, %arg2]
%2 = affine.min affine_map<()[s0, s1] -> (s0 - s1, 11)> ()[%arg1, %arg2]
// CHECK: affine.min #[[$MAP3]]()
%3 = affine.min affine_map<()[] -> (77, 78, 79)> ()[]
return
}
// CHECK-LABEL: @affine_max
func.func @affine_max(%arg0 : index, %arg1 : index, %arg2 : index) {
// CHECK: affine.max #[[$MAP0]](%arg0)[%arg1]
%0 = affine.max affine_map<(d0)[s0] -> (1000, d0 + 512, s0)> (%arg0)[%arg1]
// CHECK: affine.max #[[$MAP1]](%arg0, %arg1)[%arg2]
%1 = affine.max affine_map<(d0, d1)[s0] -> (d0 - d1, s0 + 512)> (%arg0, %arg1)[%arg2]
// CHECK: affine.max #[[$MAP2]]()[%arg1, %arg2]
%2 = affine.max affine_map<()[s0, s1] -> (s0 - s1, 11)> ()[%arg1, %arg2]
// CHECK: affine.max #[[$MAP3]]()
%3 = affine.max affine_map<()[] -> (77, 78, 79)> ()[]
return
}
// -----
func.func @valid_symbols(%arg0: index, %arg1: index, %arg2: index) {
%c1 = arith.constant 1 : index
%c0 = arith.constant 0 : index
%0 = memref.alloc(%arg0, %arg1) : memref<?x?xf32>
affine.for %arg3 = 0 to %arg2 step 768 {
%13 = memref.dim %0, %c1 : memref<?x?xf32>
affine.for %arg4 = 0 to %13 step 264 {
%18 = memref.dim %0, %c0 : memref<?x?xf32>
%20 = memref.subview %0[%c0, %c0][%18,%arg4][%c1,%c1] : memref<?x?xf32>
to memref<?x?xf32, strided<[?, ?], offset: ?>>
%24 = memref.dim %20, %c0 : memref<?x?xf32, strided<[?, ?], offset: ?>>
affine.for %arg5 = 0 to %24 step 768 {
"foo"() : () -> ()
}
}
}
return
}
// -----
// Test symbol constraints for ops with AffineScope trait.
// CHECK-LABEL: func @valid_symbol_affine_scope
func.func @valid_symbol_affine_scope(%n : index, %A : memref<?xf32>) {
test.affine_scope {
%c1 = arith.constant 1 : index
%l = arith.subi %n, %c1 : index
// %l, %n are valid symbols since test.affine_scope defines a new affine
// scope.
affine.for %i = %l to %n {
%m = arith.subi %l, %i : index
test.affine_scope {
// %m and %n are valid symbols.
affine.for %j = %m to %n {
%v = affine.load %A[%n - 1] : memref<?xf32>
affine.store %v, %A[%n - 1] : memref<?xf32>
}
"terminate"() : () -> ()
}
}
"terminate"() : () -> ()
}
return
}
// -----
// Test the fact that module op always provides an affine scope.
%idx = "test.foo"() : () -> (index)
"test.func"() ({
^bb0(%A : memref<?xf32>):
affine.load %A[%idx] : memref<?xf32>
"terminate"() : () -> ()
}) : () -> ()
// -----
// CHECK-LABEL: func @parallel
// CHECK-SAME: (%[[A:.*]]: memref<100x100xf32>, %[[N:.*]]: index)
func.func @parallel(%A : memref<100x100xf32>, %N : index) {
// CHECK: affine.parallel (%[[I0:.*]], %[[J0:.*]]) = (0, 0) to (symbol(%[[N]]), 100) step (10, 10)
affine.parallel (%i0, %j0) = (0, 0) to (symbol(%N), 100) step (10, 10) {
// CHECK: affine.parallel (%{{.*}}, %{{.*}}) = (%[[I0]], %[[J0]]) to (%[[I0]] + 10, %[[J0]] + 10) reduce ("minf", "maxf") -> (f32, f32)
%0:2 = affine.parallel (%i1, %j1) = (%i0, %j0) to (%i0 + 10, %j0 + 10) reduce ("minf", "maxf") -> (f32, f32) {
%2 = affine.load %A[%i0 + %i0, %j0 + %j1] : memref<100x100xf32>
affine.yield %2, %2 : f32, f32
}
}
return
}
// -----
// CHECK-LABEL: @parallel_min_max
// CHECK: %[[A:.*]]: index, %[[B:.*]]: index, %[[C:.*]]: index, %[[D:.*]]: index
func.func @parallel_min_max(%a: index, %b: index, %c: index, %d: index) {
// CHECK: affine.parallel (%{{.*}}, %{{.*}}, %{{.*}}) =
// CHECK: (max(%[[A]], %[[B]])
// CHECK: to (%[[C]], min(%[[C]], %[[D]]), %[[B]])
affine.parallel (%i, %j, %k) = (max(%a, %b), %b, max(%a, %c))
to (%c, min(%c, %d), %b) {
affine.yield
}
return
}
// -----
// CHECK-LABEL: @parallel_no_ivs
func.func @parallel_no_ivs() {
// CHECK: affine.parallel () = () to ()
affine.parallel () = () to () {
affine.yield
}
return
}
// -----
// CHECK-LABEL: func @affine_if
func.func @affine_if() -> f32 {
// CHECK: %[[ZERO:.*]] = arith.constant {{.*}} : f32
%zero = arith.constant 0.0 : f32
// CHECK: %[[OUT:.*]] = affine.if {{.*}}() -> f32 {
%0 = affine.if affine_set<() : ()> () -> f32 {
// CHECK: affine.yield %[[ZERO]] : f32
affine.yield %zero : f32
} else {
// CHECK: affine.yield %[[ZERO]] : f32
affine.yield %zero : f32
}
// CHECK: return %[[OUT]] : f32
return %0 : f32
}
// -----
// Test affine.for with yield values.
#set = affine_set<(d0): (d0 - 10 >= 0)>
// CHECK-LABEL: func @yield_loop
func.func @yield_loop(%buffer: memref<1024xf32>) -> f32 {
%sum_init_0 = arith.constant 0.0 : f32
%res = affine.for %i = 0 to 10 step 2 iter_args(%sum_iter = %sum_init_0) -> f32 {
%t = affine.load %buffer[%i] : memref<1024xf32>
%sum_next = affine.if #set(%i) -> (f32) {
%new_sum = arith.addf %sum_iter, %t : f32
affine.yield %new_sum : f32
} else {
affine.yield %sum_iter : f32
}
affine.yield %sum_next : f32
}
return %res : f32
}
// CHECK: %[[const_0:.*]] = arith.constant 0.000000e+00 : f32
// CHECK-NEXT: %[[output:.*]] = affine.for %{{.*}} = 0 to 10 step 2 iter_args(%{{.*}} = %[[const_0]]) -> (f32) {
// CHECK: affine.if #set(%{{.*}}) -> f32 {
// CHECK: affine.yield %{{.*}} : f32
// CHECK-NEXT: } else {
// CHECK-NEXT: affine.yield %{{.*}} : f32
// CHECK-NEXT: }
// CHECK-NEXT: affine.yield %{{.*}} : f32
// CHECK-NEXT: }
// CHECK-NEXT: return %[[output]] : f32
// CHECK-LABEL: func @affine_for_multiple_yield
func.func @affine_for_multiple_yield(%buffer: memref<1024xf32>) -> (f32, f32) {
%init_0 = arith.constant 0.0 : f32
%res1, %res2 = affine.for %i = 0 to 10 step 2 iter_args(%iter_arg1 = %init_0, %iter_arg2 = %init_0) -> (f32, f32) {
%t = affine.load %buffer[%i] : memref<1024xf32>
%ret1 = arith.addf %t, %iter_arg1 : f32
%ret2 = arith.addf %t, %iter_arg2 : f32
affine.yield %ret1, %ret2 : f32, f32
}
return %res1, %res2 : f32, f32
}
// CHECK: %[[const_0:.*]] = arith.constant 0.000000e+00 : f32
// CHECK-NEXT: %[[output:[0-9]+]]:2 = affine.for %{{.*}} = 0 to 10 step 2 iter_args(%[[iter_arg1:.*]] = %[[const_0]], %[[iter_arg2:.*]] = %[[const_0]]) -> (f32, f32) {
// CHECK: %[[res1:.*]] = arith.addf %{{.*}}, %[[iter_arg1]] : f32
// CHECK-NEXT: %[[res2:.*]] = arith.addf %{{.*}}, %[[iter_arg2]] : f32
// CHECK-NEXT: affine.yield %[[res1]], %[[res2]] : f32, f32
// CHECK-NEXT: }
// -----
// CHECK-LABEL: func @delinearize
func.func @delinearize(%linear_idx: index, %basis0: index, %basis1 :index) -> (index, index) {
// CHECK: affine.delinearize_index %{{.+}} into (%{{.+}}, %{{.+}}) : index, index
%1:2 = affine.delinearize_index %linear_idx into (%basis0, %basis1) : index, index
return %1#0, %1#1 : index, index
}
|
