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
|
// RUN: mlir-opt %s -sparsification="parallelization-strategy=none" | \
// RUN: FileCheck %s --check-prefix=CHECK-PAR0
// RUN: mlir-opt %s -sparsification="parallelization-strategy=dense-outer-loop" | \
// RUN: FileCheck %s --check-prefix=CHECK-PAR1
// RUN: mlir-opt %s -sparsification="parallelization-strategy=any-storage-outer-loop" | \
// RUN: FileCheck %s --check-prefix=CHECK-PAR2
// RUN: mlir-opt %s -sparsification="parallelization-strategy=dense-any-loop" | \
// RUN: FileCheck %s --check-prefix=CHECK-PAR3
// RUN: mlir-opt %s -sparsification="parallelization-strategy=any-storage-any-loop" | \
// RUN: FileCheck %s --check-prefix=CHECK-PAR4
#DenseMatrix = #sparse_tensor.encoding<{
dimLevelType = [ "dense", "dense" ]
}>
#SparseMatrix = #sparse_tensor.encoding<{
dimLevelType = [ "compressed", "compressed" ]
}>
#CSR = #sparse_tensor.encoding<{
dimLevelType = [ "dense", "compressed" ]
}>
#trait_dd = {
indexing_maps = [
affine_map<(i,j) -> (i,j)>, // A
affine_map<(i,j) -> (i,j)> // X (out)
],
iterator_types = ["parallel", "parallel"],
doc = "X(i,j) = A(i,j) * SCALE"
}
//
// CHECK-PAR0-LABEL: func @scale_dd
// CHECK-PAR0: scf.for
// CHECK-PAR0: scf.for
// CHECK-PAR0: return
//
// CHECK-PAR1-LABEL: func @scale_dd
// CHECK-PAR1: scf.parallel
// CHECK-PAR1: scf.for
// CHECK-PAR1: return
//
// CHECK-PAR2-LABEL: func @scale_dd
// CHECK-PAR2: scf.parallel
// CHECK-PAR2: scf.for
// CHECK-PAR2: return
//
// CHECK-PAR3-LABEL: func @scale_dd
// CHECK-PAR3: scf.parallel
// CHECK-PAR3: scf.parallel
// CHECK-PAR3: return
//
// CHECK-PAR4-LABEL: func @scale_dd
// CHECK-PAR4: scf.parallel
// CHECK-PAR4: scf.parallel
// CHECK-PAR4: return
//
func.func @scale_dd(%scale: f32,
%arga: tensor<?x?xf32, #DenseMatrix>,
%argx: tensor<?x?xf32>) -> tensor<?x?xf32> {
%0 = linalg.generic #trait_dd
ins(%arga: tensor<?x?xf32, #DenseMatrix>)
outs(%argx: tensor<?x?xf32>) {
^bb(%a: f32, %x: f32):
%0 = arith.mulf %a, %scale : f32
linalg.yield %0 : f32
} -> tensor<?x?xf32>
return %0 : tensor<?x?xf32>
}
#trait_ss = {
indexing_maps = [
affine_map<(i,j) -> (i,j)>, // A
affine_map<(i,j) -> (i,j)> // X (out)
],
iterator_types = ["parallel", "parallel"],
doc = "X(i,j) = A(i,j) * SCALE"
}
//
// CHECK-PAR0-LABEL: func @scale_ss
// CHECK-PAR0: scf.for
// CHECK-PAR0: scf.for
// CHECK-PAR0: return
//
// CHECK-PAR1-LABEL: func @scale_ss
// CHECK-PAR1: scf.for
// CHECK-PAR1: scf.for
// CHECK-PAR1: return
//
// CHECK-PAR2-LABEL: func @scale_ss
// CHECK-PAR2: scf.parallel
// CHECK-PAR2: scf.for
// CHECK-PAR2: return
//
// CHECK-PAR3-LABEL: func @scale_ss
// CHECK-PAR3: scf.for
// CHECK-PAR3: scf.for
// CHECK-PAR3: return
//
// CHECK-PAR4-LABEL: func @scale_ss
// CHECK-PAR4: scf.parallel
// CHECK-PAR4: scf.parallel
// CHECK-PAR4: return
//
func.func @scale_ss(%scale: f32,
%arga: tensor<?x?xf32, #SparseMatrix>,
%argx: tensor<?x?xf32>) -> tensor<?x?xf32> {
%0 = linalg.generic #trait_ss
ins(%arga: tensor<?x?xf32, #SparseMatrix>)
outs(%argx: tensor<?x?xf32>) {
^bb(%a: f32, %x: f32):
%0 = arith.mulf %a, %scale : f32
linalg.yield %0 : f32
} -> tensor<?x?xf32>
return %0 : tensor<?x?xf32>
}
#trait_matvec = {
indexing_maps = [
affine_map<(i,j) -> (i,j)>, // A
affine_map<(i,j) -> (j)>, // b
affine_map<(i,j) -> (i)> // x (out)
],
iterator_types = ["parallel", "reduction"],
doc = "x(i) += A(i,j) * b(j)"
}
//
// CHECK-PAR0-LABEL: func @matvec
// CHECK-PAR0: scf.for
// CHECK-PAR0: scf.for
// CHECK-PAR0: return
//
// CHECK-PAR1-LABEL: func @matvec
// CHECK-PAR1: scf.parallel
// CHECK-PAR1: scf.for
// CHECK-PAR1: return
//
// CHECK-PAR2-LABEL: func @matvec
// CHECK-PAR2: scf.parallel
// CHECK-PAR2: scf.for
// CHECK-PAR2: return
//
// CHECK-PAR3-LABEL: func @matvec
// CHECK-PAR3: scf.parallel
// CHECK-PAR3: scf.for
// CHECK-PAR3: return
//
// CHECK-PAR4-LABEL: func @matvec
// CHECK-PAR4: scf.parallel
// CHECK-PAR4: scf.parallel
// CHECK-PAR4: scf.reduce
// CHECK-PAR4: return
//
func.func @matvec(%arga: tensor<16x32xf32, #CSR>,
%argb: tensor<32xf32>,
%argx: tensor<16xf32>) -> tensor<16xf32> {
%0 = linalg.generic #trait_matvec
ins(%arga, %argb : tensor<16x32xf32, #CSR>, tensor<32xf32>)
outs(%argx: tensor<16xf32>) {
^bb(%A: f32, %b: f32, %x: f32):
%0 = arith.mulf %A, %b : f32
%1 = arith.addf %0, %x : f32
linalg.yield %1 : f32
} -> tensor<16xf32>
return %0 : tensor<16xf32>
}
|
