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
|
// RUN: mlir-opt %s --test-transform-dialect-interpreter --split-input-file | FileCheck %s
// CHECK-LABEL: func @outerproduct_noacc
// CHECK-SAME: %[[A:.*0]]: vector<2xf32>,
// CHECK-SAME: %[[B:.*1]]: vector<3xf32>
// CHECK: %[[C0:.*]] = arith.constant dense<0.000000e+00> : vector<2x3xf32>
// CHECK: %[[T0:.*]] = vector.extract %[[A]][0] : vector<2xf32>
// CHECK: %[[T1:.*]] = vector.splat %[[T0]] : vector<3xf32>
// CHECK: %[[T2:.*]] = arith.mulf %[[T1]], %[[B]] : vector<3xf32>
// CHECK: %[[T3:.*]] = vector.insert %[[T2]], %[[C0]] [0] : vector<3xf32> into vector<2x3xf32>
// CHECK: %[[T4:.*]] = vector.extract %[[A]][1] : vector<2xf32>
// CHECK: %[[T5:.*]] = vector.splat %[[T4]] : vector<3xf32>
// CHECK: %[[T6:.*]] = arith.mulf %[[T5]], %[[B]] : vector<3xf32>
// CHECK: %[[T7:.*]] = vector.insert %[[T6]], %[[T3]] [1] : vector<3xf32> into vector<2x3xf32>
// CHECK: return %[[T7]] : vector<2x3xf32>
func.func @outerproduct_noacc(%arg0: vector<2xf32>,
%arg1: vector<3xf32>) -> vector<2x3xf32> {
%0 = vector.outerproduct %arg0, %arg1 : vector<2xf32>, vector<3xf32>
return %0: vector<2x3xf32>
}
// CHECK-LABEL: func @outerproduct_acc
// CHECK-SAME: %[[A:.*0]]: vector<2xf32>,
// CHECK-SAME: %[[B:.*1]]: vector<3xf32>,
// CHECK-SAME: %[[C:.*2]]: vector<2x3xf32>
// CHECK: %[[C0:.*]] = arith.constant dense<0.000000e+00> : vector<2x3xf32>
// CHECK: %[[T0:.*]] = vector.extract %[[A]][0] : vector<2xf32>
// CHECK: %[[T1:.*]] = vector.splat %[[T0]] : vector<3xf32>
// CHECK: %[[T2:.*]] = vector.extract %[[C]][0] : vector<2x3xf32>
// CHECK: %[[T3:.*]] = vector.fma %[[T1]], %[[B]], %[[T2]] : vector<3xf32>
// CHECK: %[[T4:.*]] = vector.insert %[[T3]], %[[C0]] [0] : vector<3xf32> into vector<2x3xf32>
// CHECK: %[[T5:.*]] = vector.extract %[[A]][1] : vector<2xf32>
// CHECK: %[[T6:.*]] = vector.splat %[[T5]] : vector<3xf32>
// CHECK: %[[T7:.*]] = vector.extract %[[C]][1] : vector<2x3xf32>
// CHECK: %[[T8:.*]] = vector.fma %[[T6]], %[[B]], %[[T7]] : vector<3xf32>
// CHECK: %[[T9:.*]] = vector.insert %[[T8]], %[[T4]] [1] : vector<3xf32> into vector<2x3xf32>
// CHECK: return %[[T9]] : vector<2x3xf32>
func.func @outerproduct_acc(%arg0: vector<2xf32>,
%arg1: vector<3xf32>,
%arg2: vector<2x3xf32>) -> vector<2x3xf32> {
%0 = vector.outerproduct %arg0, %arg1, %arg2 : vector<2xf32>, vector<3xf32>
return %0: vector<2x3xf32>
}
// CHECK-LABEL: func @outerproduct_noacc_int
// CHECK-SAME: %[[A:.*0]]: vector<2xi32>,
// CHECK-SAME: %[[B:.*1]]: vector<3xi32>
// CHECK: %[[C0:.*]] = arith.constant dense<0> : vector<2x3xi32>
// CHECK: %[[T0:.*]] = vector.extract %[[A]][0] : vector<2xi32>
// CHECK: %[[T1:.*]] = vector.splat %[[T0]] : vector<3xi32>
// CHECK: %[[T2:.*]] = arith.muli %[[T1]], %[[B]] : vector<3xi32>
// CHECK: %[[T3:.*]] = vector.insert %[[T2]], %[[C0]] [0] : vector<3xi32> into vector<2x3xi32>
// CHECK: %[[T4:.*]] = vector.extract %[[A]][1] : vector<2xi32>
// CHECK: %[[T5:.*]] = vector.splat %[[T4]] : vector<3xi32>
// CHECK: %[[T6:.*]] = arith.muli %[[T5]], %[[B]] : vector<3xi32>
// CHECK: %[[T7:.*]] = vector.insert %[[T6]], %[[T3]] [1] : vector<3xi32> into vector<2x3xi32>
// CHECK: return %[[T7]] : vector<2x3xi32>
func.func @outerproduct_noacc_int(%arg0: vector<2xi32>,
%arg1: vector<3xi32>) -> vector<2x3xi32> {
%0 = vector.outerproduct %arg0, %arg1 : vector<2xi32>, vector<3xi32>
return %0: vector<2x3xi32>
}
// CHECK-LABEL: func @outerproduct_acc_int
// CHECK-SAME: %[[A:.*0]]: vector<2xi32>,
// CHECK-SAME: %[[B:.*1]]: vector<3xi32>,
// CHECK-SAME: %[[C:.*2]]: vector<2x3xi32>
// CHECK: %[[C0:.*]] = arith.constant dense<0> : vector<2x3xi32>
// CHECK: %[[T0:.*]] = vector.extract %[[A]][0] : vector<2xi32>
// CHECK: %[[T1:.*]] = vector.splat %[[T0]] : vector<3xi32>
// CHECK: %[[T2:.*]] = vector.extract %[[C]][0] : vector<2x3xi32>
// CHECK: %[[T3:.*]] = arith.muli %[[T1]], %[[B]] : vector<3xi32>
// CHECK: %[[T4:.*]] = arith.addi %[[T3]], %[[T2]] : vector<3xi32>
// CHECK: %[[T5:.*]] = vector.insert %[[T4]], %[[C0]] [0] : vector<3xi32> into vector<2x3xi32>
// CHECK: %[[T6:.*]] = vector.extract %[[A]][1] : vector<2xi32>
// CHECK: %[[T7:.*]] = vector.splat %[[T6]] : vector<3xi32>
// CHECK: %[[T8:.*]] = vector.extract %[[C]][1] : vector<2x3xi32>
// CHECK: %[[T9:.*]] = arith.muli %[[T7]], %[[B]] : vector<3xi32>
// CHECK: %[[T10:.*]] = arith.addi %[[T9]], %[[T8]] : vector<3xi32>
// CHECK: %[[T11:.*]] = vector.insert %[[T10]], %[[T5]] [1] : vector<3xi32> into vector<2x3xi32>
// CHECK: return %[[T11]] : vector<2x3xi32>
func.func @outerproduct_acc_int(%arg0: vector<2xi32>,
%arg1: vector<3xi32>,
%arg2: vector<2x3xi32>) -> vector<2x3xi32> {
%0 = vector.outerproduct %arg0, %arg1, %arg2 : vector<2xi32>, vector<3xi32>
return %0: vector<2x3xi32>
}
// CHECK-LABEL: func @axpy_fp(
// CHECK-SAME: %[[A:.*0]]: vector<16xf32>,
// CHECK-SAME: %[[B:.*1]]: f32)
// CHECK: %[[T0:.*]] = vector.splat %[[B]] : vector<16xf32>
// CHECK: %[[T1:.*]] = arith.mulf %[[A]], %[[T0]] : vector<16xf32>
// CHECK: return %[[T1]] : vector<16xf32>
func.func @axpy_fp(%arg0: vector<16xf32>, %arg1: f32) -> vector<16xf32> {
%0 = vector.outerproduct %arg0, %arg1: vector<16xf32>, f32
return %0: vector<16xf32>
}
// CHECK-LABEL: func @axpy_fp_add(
// CHECK-SAME: %[[A:.*0]]: vector<16xf32>,
// CHECK-SAME: %[[B:.*1]]: f32,
// CHECK-SAME: %[[C:.*2]]: vector<16xf32>)
// CHECK: %[[T0:.*]] = vector.splat %[[B]] : vector<16xf32>
// CHECK: %[[T1:.*]] = vector.fma %[[A]], %[[T0]], %[[C]] : vector<16xf32>
// CHECK: return %[[T1]] : vector<16xf32>
func.func @axpy_fp_add(%arg0: vector<16xf32>, %arg1: f32, %arg2 : vector<16xf32>) -> vector<16xf32> {
%0 = vector.outerproduct %arg0, %arg1, %arg2: vector<16xf32>, f32
return %0: vector<16xf32>
}
// CHECK-LABEL: func @axpy_int(
// CHECK-SAME: %[[A:.*0]]: vector<16xi32>,
// CHECK-SAME: %[[B:.*1]]: i32)
// CHECK: %[[T0:.*]] = vector.splat %[[B]] : vector<16xi32>
// CHECK: %[[T1:.*]] = arith.muli %[[A]], %[[T0]] : vector<16xi32>
// CHECK: return %[[T1]] : vector<16xi32>
func.func @axpy_int(%arg0: vector<16xi32>, %arg1: i32) -> vector<16xi32> {
%0 = vector.outerproduct %arg0, %arg1: vector<16xi32>, i32
return %0: vector<16xi32>
}
// CHECK-LABEL: func @axpy_int_add(
// CHECK-SAME: %[[A:.*0]]: vector<16xi32>,
// CHECK-SAME: %[[B:.*1]]: i32,
// CHECK-SAME: %[[C:.*2]]: vector<16xi32>)
// CHECK: %[[T0:.*]] = vector.splat %[[B]] : vector<16xi32>
// CHECK: %[[T1:.*]] = arith.muli %[[A]], %[[T0]] : vector<16xi32>
// CHECK: %[[T2:.*]] = arith.addi %[[T1]], %[[C]] : vector<16xi32>
// CHECK: return %[[T2]] : vector<16xi32>
func.func @axpy_int_add(%arg0: vector<16xi32>, %arg1: i32, %arg2: vector<16xi32>) -> vector<16xi32> {
%0 = vector.outerproduct %arg0, %arg1, %arg2: vector<16xi32>, i32
return %0: vector<16xi32>
}
transform.sequence failures(propagate) {
^bb1(%module_op: !transform.any_op):
%f = transform.structured.match ops{["func.func"]} in %module_op
: (!transform.any_op) -> !transform.any_op
transform.apply_patterns to %f {
transform.apply_patterns.vector.lower_outerproduct
} : !transform.any_op
transform.apply_patterns to %f {
transform.apply_patterns.vector.lower_broadcast
} : !transform.any_op
}
|
