parallel-loop-tiling.mlir
5.71 KB
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
// RUN: mlir-opt %s -pass-pipeline='func(parallel-loop-tiling{parallel-loop-tile-sizes=1,4})' -split-input-file | FileCheck %s
func @parallel_loop(%arg0 : index, %arg1 : index, %arg2 : index,
%arg3 : index, %arg4 : index, %arg5 : index,
%A: memref<?x?xf32>, %B: memref<?x?xf32>,
%C: memref<?x?xf32>, %result: memref<?x?xf32>) {
scf.parallel (%i0, %i1) = (%arg0, %arg1) to (%arg2, %arg3) step (%arg4, %arg5) {
%B_elem = load %B[%i0, %i1] : memref<?x?xf32>
%C_elem = load %C[%i0, %i1] : memref<?x?xf32>
%sum_elem = addf %B_elem, %C_elem : f32
store %sum_elem, %result[%i0, %i1] : memref<?x?xf32>
}
return
}
// CHECK: #map0 = affine_map<(d0, d1, d2) -> (d0, d1 - d2)>
// CHECK-LABEL: func @parallel_loop(
// CHECK-SAME: [[ARG1:%.*]]: index, [[ARG2:%.*]]: index, [[ARG3:%.*]]: index, [[ARG4:%.*]]: index, [[ARG5:%.*]]: index, [[ARG6:%.*]]: index, [[ARG7:%.*]]: memref<?x?xf32>, [[ARG8:%.*]]: memref<?x?xf32>, [[ARG9:%.*]]: memref<?x?xf32>, [[ARG10:%.*]]: memref<?x?xf32>) {
// CHECK: [[C0:%.*]] = constant 0 : index
// CHECK: [[C1:%.*]] = constant 1 : index
// CHECK: [[C4:%.*]] = constant 4 : index
// CHECK: [[V1:%.*]] = muli [[ARG5]], [[C1]] : index
// CHECK: [[V2:%.*]] = muli [[ARG6]], [[C4]] : index
// CHECK: scf.parallel ([[V3:%.*]], [[V4:%.*]]) = ([[ARG1]], [[ARG2]]) to ([[ARG3]], [[ARG4]]) step ([[V1]], [[V2]]) {
// CHECK: [[V5:%.*]] = affine.min #map0([[V1]], [[ARG3]], [[V3]])
// CHECK: [[V6:%.*]] = affine.min #map0([[V2]], [[ARG4]], [[V4]])
// CHECK: scf.parallel ([[V7:%.*]], [[V8:%.*]]) = ([[C0]], [[C0]]) to ([[V5]], [[V6]]) step ([[ARG5]], [[ARG6]]) {
// CHECK: [[V9:%.*]] = addi [[V7]], [[V3]] : index
// CHECK: [[V10:%.*]] = addi [[V8]], [[V4]] : index
// CHECK: [[V11:%.*]] = load [[ARG8]]{{\[}}[[V9]], [[V10]]] : memref<?x?xf32>
// CHECK: [[V12:%.*]] = load [[ARG9]]{{\[}}[[V9]], [[V10]]] : memref<?x?xf32>
// CHECK: [[V13:%.*]] = addf [[V11]], [[V12]] : f32
// CHECK: store [[V13]], [[ARG10]]{{\[}}[[V9]], [[V10]]] : memref<?x?xf32>
// CHECK: }
// CHECK: }
// CHECK: return
// -----
func @static_loop_with_step() {
%c0 = constant 0 : index
%c3 = constant 3 : index
%c22 = constant 22 : index
%c24 = constant 24 : index
scf.parallel (%i0, %i1) = (%c0, %c0) to (%c22, %c24) step (%c3, %c3) {
}
return
}
// CHECK-LABEL: func @static_loop_with_step() {
// CHECK: [[C0:%.*]] = constant 0 : index
// CHECK: [[C3:%.*]] = constant 3 : index
// CHECK: [[C22:%.*]] = constant 22 : index
// CHECK: [[C24:%.*]] = constant 24 : index
// CHECK: [[C0_1:%.*]] = constant 0 : index
// CHECK: [[C1:%.*]] = constant 1 : index
// CHECK: [[C4:%.*]] = constant 4 : index
// CHECK: [[V1:%.*]] = muli [[C3]], [[C1]] : index
// CHECK: [[V2:%.*]] = muli [[C3]], [[C4]] : index
// CHECK: scf.parallel ([[V3:%.*]], [[V4:%.*]]) = ([[C0]], [[C0]]) to ([[C22]], [[C24]]) step ([[V1]], [[V2]]) {
// CHECK: scf.parallel ([[V5:%.*]], [[V6:%.*]]) = ([[C0_1]], [[C0_1]]) to ([[V1]], [[V2]]) step ([[C3]], [[C3]]) {
// CHECK: = addi [[V5]], [[V3]] : index
// CHECK: = addi [[V6]], [[V4]] : index
// CHECK: }
// CHECK: }
// CHECK: return
// -----
func @tile_nested_innermost() {
%c2 = constant 2 : index
%c0 = constant 0 : index
%c1 = constant 1 : index
scf.parallel (%i, %j) = (%c0, %c0) to (%c2, %c2) step (%c1, %c1) {
scf.parallel (%k, %l) = (%c0, %c0) to (%c2, %c2) step (%c1, %c1) {
}
}
scf.parallel (%i, %j) = (%c0, %c0) to (%c2, %c2) step (%c1, %c1) {
}
return
}
// CHECK-LABEL: func @tile_nested_innermost() {
// CHECK: [[C2:%.*]] = constant 2 : index
// CHECK: [[C0:%.*]] = constant 0 : index
// CHECK: [[C1:%.*]] = constant 1 : index
// CHECK: scf.parallel ([[V1:%.*]], [[V2:%.*]]) = ([[C0]], [[C0]]) to ([[C2]], [[C2]]) step ([[C1]], [[C1]]) {
// CHECK: [[C0_1:%.*]] = constant 0 : index
// CHECK: [[C1_1:%.*]] = constant 1 : index
// CHECK: [[C4:%.*]] = constant 4 : index
// CHECK: [[V3:%.*]] = muli [[C1]], [[C1_1]] : index
// CHECK: [[V4:%.*]] = muli [[C1]], [[C4]] : index
// CHECK: scf.parallel ([[V5:%.*]], [[V6:%.*]]) = ([[C0]], [[C0]]) to ([[C2]], [[C2]]) step ([[V3]], [[V4]]) {
// CHECK: [[V7:%.*]] = affine.min #map0([[V4]], [[C2]], [[V6]])
// CHECK: scf.parallel ([[V8:%.*]], [[V9:%.*]]) = ([[C0_1]], [[C0_1]]) to ([[V3]], [[V7]]) step ([[C1]], [[C1]]) {
// CHECK: = addi [[V8]], [[V5]] : index
// CHECK: = addi [[V9]], [[V6]] : index
// CHECK: }
// CHECK: }
// CHECK: }
// CHECK: [[C0_2:%.*]] = constant 0 : index
// CHECK: [[C1_2:%.*]] = constant 1 : index
// CHECK: [[C4_1:%.*]] = constant 4 : index
// CHECK: [[V10:%.*]] = muli [[C1]], [[C1_2]] : index
// CHECK: [[V11:%.*]] = muli [[C1]], [[C4_1]] : index
// CHECK: scf.parallel ([[V12:%.*]], [[V13:%.*]]) = ([[C0]], [[C0]]) to ([[C2]], [[C2]]) step ([[V10]], [[V11]]) {
// CHECK: [[V14:%.*]] = affine.min #map0([[V11]], [[C2]], [[V13]])
// CHECK: scf.parallel ([[V15:%.*]], [[V16:%.*]]) = ([[C0_2]], [[C0_2]]) to ([[V10]], [[V14]]) step ([[C1]], [[C1]]) {
// CHECK: = addi [[V15]], [[V12]] : index
// CHECK: = addi [[V16]], [[V13]] : index
// CHECK: }
// CHECK: }
// CHECK: return
// CHECK: }