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
|
// RUN: mlir-opt %s -pass-pipeline='builtin.module(func.func(scf-for-loop-range-folding))' -split-input-file | FileCheck %s
func.func @fold_one_loop(%arg0: memref<?xi32>, %arg1: index, %arg2: index) {
%c0 = arith.constant 0 : index
%c1 = arith.constant 1 : index
%c4 = arith.constant 4 : index
scf.for %i = %c0 to %arg1 step %c1 {
%0 = arith.addi %arg2, %i : index
%1 = arith.muli %0, %c4 : index
%2 = memref.load %arg0[%1] : memref<?xi32>
%3 = arith.muli %2, %2 : i32
memref.store %3, %arg0[%1] : memref<?xi32>
}
return
}
// CHECK-LABEL: func @fold_one_loop
// CHECK-SAME: (%[[ARG0:.*]]: {{.*}}, %[[ARG1:.*]]: {{.*}}, %[[ARG2:.*]]: {{.*}}
// CHECK: %[[C0:.*]] = arith.constant 0 : index
// CHECK: %[[C1:.*]] = arith.constant 1 : index
// CHECK: %[[C4:.*]] = arith.constant 4 : index
// CHECK: %[[I0:.*]] = arith.addi %[[ARG2]], %[[C0]] : index
// CHECK: %[[I1:.*]] = arith.addi %[[ARG2]], %[[ARG1]] : index
// CHECK: %[[I2:.*]] = arith.muli %[[I1]], %[[C4]] : index
// CHECK: %[[I3:.*]] = arith.muli %[[C1]], %[[C4]] : index
// CHECK: scf.for %[[I:.*]] = %[[I0]] to %[[I2]] step %[[I3]] {
// CHECK: %[[I4:.*]] = memref.load %[[ARG0]]{{\[}}%[[I]]
// CHECK: %[[I5:.*]] = arith.muli %[[I4]], %[[I4]] : i32
// CHECK: memref.store %[[I5]], %[[ARG0]]{{\[}}%[[I]]
func.func @fold_one_loop2(%arg0: memref<?xi32>, %arg1: index, %arg2: index) {
%c0 = arith.constant 0 : index
%c1 = arith.constant 1 : index
%c4 = arith.constant 4 : index
%c10 = arith.constant 10 : index
scf.for %j = %c0 to %c10 step %c1 {
scf.for %i = %c0 to %arg1 step %c1 {
%0 = arith.addi %arg2, %i : index
%1 = arith.muli %0, %c4 : index
%2 = memref.load %arg0[%1] : memref<?xi32>
%3 = arith.muli %2, %2 : i32
memref.store %3, %arg0[%1] : memref<?xi32>
}
}
return
}
// CHECK-LABEL: func @fold_one_loop2
// CHECK-SAME: (%[[ARG0:.*]]: {{.*}}, %[[ARG1:.*]]: {{.*}}, %[[ARG2:.*]]: {{.*}}
// CHECK: %[[C0:.*]] = arith.constant 0 : index
// CHECK: %[[C1:.*]] = arith.constant 1 : index
// CHECK: %[[C4:.*]] = arith.constant 4 : index
// CHECK: %[[C10:.*]] = arith.constant 10 : index
// CHECK: scf.for %[[J:.*]] = %[[C0]] to %[[C10]] step %[[C1]] {
// CHECK: %[[I0:.*]] = arith.addi %[[ARG2]], %[[C0]] : index
// CHECK: %[[I1:.*]] = arith.addi %[[ARG2]], %[[ARG1]] : index
// CHECK: %[[I2:.*]] = arith.muli %[[I1]], %[[C4]] : index
// CHECK: %[[I3:.*]] = arith.muli %[[C1]], %[[C4]] : index
// CHECK: scf.for %[[I:.*]] = %[[I0]] to %[[I2]] step %[[I3]] {
// CHECK: %[[I4:.*]] = memref.load %[[ARG0]]{{\[}}%[[I]]
// CHECK: %[[I5:.*]] = arith.muli %[[I4]], %[[I4]] : i32
// CHECK: memref.store %[[I5]], %[[ARG0]]{{\[}}%[[I]]
func.func @fold_two_loops(%arg0: memref<?xi32>, %arg1: index, %arg2: index) {
%c0 = arith.constant 0 : index
%c1 = arith.constant 1 : index
%c4 = arith.constant 4 : index
%c10 = arith.constant 10 : index
scf.for %j = %c0 to %c10 step %c1 {
scf.for %i = %j to %arg1 step %c1 {
%0 = arith.addi %arg2, %i : index
%1 = arith.muli %0, %c4 : index
%2 = memref.load %arg0[%1] : memref<?xi32>
%3 = arith.muli %2, %2 : i32
memref.store %3, %arg0[%1] : memref<?xi32>
}
}
return
}
// CHECK-LABEL: func @fold_two_loops
// CHECK-SAME: (%[[ARG0:.*]]: {{.*}}, %[[ARG1:.*]]: {{.*}}, %[[ARG2:.*]]: {{.*}}
// CHECK: %[[C0:.*]] = arith.constant 0 : index
// CHECK: %[[C1:.*]] = arith.constant 1 : index
// CHECK: %[[C4:.*]] = arith.constant 4 : index
// CHECK: %[[C10:.*]] = arith.constant 10 : index
// CHECK: %[[I0:.*]] = arith.addi %[[ARG2]], %[[C0]] : index
// CHECK: %[[I1:.*]] = arith.addi %[[ARG2]], %[[C10]] : index
// CHECK: scf.for %[[J:.*]] = %[[I0]] to %[[I1]] step %[[C1]] {
// CHECK: %[[I1:.*]] = arith.addi %[[ARG2]], %[[ARG1]] : index
// CHECK: %[[I2:.*]] = arith.muli %[[I1]], %[[C4]] : index
// CHECK: %[[I3:.*]] = arith.muli %[[C1]], %[[C4]] : index
// CHECK: scf.for %[[I:.*]] = %[[J]] to %[[I2]] step %[[I3]] {
// CHECK: %[[I4:.*]] = memref.load %[[ARG0]]{{\[}}%[[I]]
// CHECK: %[[I5:.*]] = arith.muli %[[I4]], %[[I4]] : i32
// CHECK: memref.store %[[I5]], %[[ARG0]]{{\[}}%[[I]]
// If an instruction's operands are not defined outside the loop, we cannot
// perform the optimization, as is the case with the arith.muli below. (If
// paired with loop invariant code motion we can continue.)
func.func @fold_only_first_add(%arg0: memref<?xi32>, %arg1: index, %arg2: index) {
%c0 = arith.constant 0 : index
%c1 = arith.constant 1 : index
%c4 = arith.constant 4 : index
scf.for %i = %c0 to %arg1 step %c1 {
%0 = arith.addi %arg2, %i : index
%1 = arith.addi %arg2, %c4 : index
%2 = arith.muli %0, %1 : index
%3 = memref.load %arg0[%2] : memref<?xi32>
%4 = arith.muli %3, %3 : i32
memref.store %4, %arg0[%2] : memref<?xi32>
}
return
}
// CHECK-LABEL: func @fold_only_first_add
// CHECK-SAME: (%[[ARG0:.*]]: {{.*}}, %[[ARG1:.*]]: {{.*}}, %[[ARG2:.*]]: {{.*}}
// CHECK: %[[C0:.*]] = arith.constant 0 : index
// CHECK: %[[C1:.*]] = arith.constant 1 : index
// CHECK: %[[C4:.*]] = arith.constant 4 : index
// CHECK: %[[I0:.*]] = arith.addi %[[ARG2]], %[[C0]] : index
// CHECK: %[[I1:.*]] = arith.addi %[[ARG2]], %[[ARG1]] : index
// CHECK: scf.for %[[I:.*]] = %[[I0]] to %[[I1]] step %[[C1]] {
// CHECK: %[[I2:.*]] = arith.addi %[[ARG2]], %[[C4]] : index
// CHECK: %[[I3:.*]] = arith.muli %[[I]], %[[I2]] : index
// CHECK: %[[I4:.*]] = memref.load %[[ARG0]]{{\[}}%[[I3]]
// CHECK: %[[I5:.*]] = arith.muli %[[I4]], %[[I4]] : i32
// CHECK: memref.store %[[I5]], %[[ARG0]]{{\[}}%[[I3]]
|
