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
|
// RUN: mlir-opt %s -test-sink-vector-broadcast -split-input-file | FileCheck %s
// CHECK-LABEL: func.func @broadcast_scalar_with_bcast(
// CHECK-SAME: %[[ARG_0:.*]]: index, %[[ARG_1:.*]]: index) -> vector<1x4xindex> {
// CHECK: %[[ADD:.*]] = arith.addi %[[ARG_0]], %[[ARG_1]] : index
// CHECK: %[[BCAST:.*]] = vector.broadcast %[[ADD]] : index to vector<1x4xindex>
// CHECK: return %[[BCAST]] : vector<1x4xindex>
func.func @broadcast_scalar_with_bcast( %arg1: index, %arg2: index) -> vector<1x4xindex> {
%0 = vector.broadcast %arg1 : index to vector<1x4xindex>
%1 = vector.broadcast %arg2 : index to vector<1x4xindex>
%2 = arith.addi %0, %1 : vector<1x4xindex>
return %2 : vector<1x4xindex>
}
// -----
// CHECK-LABEL: func.func @broadcast_scalar_with_bcast_and_splat(
// CHECK-SAME: %[[ARG1:.*]]: index,
// CHECK-SAME: %[[ARG2:.*]]: index) -> vector<1x4xindex> {
// CHECK: %[[ADD:.*]] = arith.addi %[[ARG1]], %[[ARG2]] : index
// CHECK: %[[BCAST:.*]] = vector.broadcast %[[ADD]] : index to vector<1x4xindex>
// CHECK: return %[[BCAST]] : vector<1x4xindex>
func.func @broadcast_scalar_with_bcast_and_splat( %arg1: index, %arg2: index) -> vector<1x4xindex> {
%0 = vector.splat %arg1 : vector<1x4xindex>
%1 = vector.broadcast %arg2 : index to vector<1x4xindex>
%2 = arith.addi %0, %1 : vector<1x4xindex>
return %2 : vector<1x4xindex>
}
// -----
// CHECK-LABEL: func.func @broadcast_vector(
// CHECK-SAME: %[[ARG_0:.*]]: vector<4xf32>,
// CHECK-SAME: %[[ARG_1:.*]]: vector<4xf32>) -> vector<3x4xf32> {
// CHECK: %[[ADDF:.*]] = arith.addf %[[ARG_0]], %[[ARG_1]] : vector<4xf32>
// CHECK: %[[BCAST:.*]] = vector.broadcast %[[ADDF]] : vector<4xf32> to vector<3x4xf32>
// CHECK: return %[[BCAST]] : vector<3x4xf32>
func.func @broadcast_vector( %arg1: vector<4xf32>, %arg2: vector<4xf32>) -> vector<3x4xf32> {
%arg1_bcast = vector.broadcast %arg1 : vector<4xf32> to vector<3x4xf32>
%arg2_bcast = vector.broadcast %arg2 : vector<4xf32> to vector<3x4xf32>
%2 = arith.addf %arg1_bcast, %arg2_bcast : vector<3x4xf32>
return %2 : vector<3x4xf32>
}
// -----
// CHECK-LABEL: func.func @broadcast_scalar_and_vec(
// CHECK-SAME: %[[ARG1:.*]]: index,
// CHECK-SAME: %[[ARG2:.*]]: vector<4xindex>) -> vector<1x4xindex> {
// CHECK: %[[SPLAT:.*]] = vector.splat %[[ARG1]] : vector<1x4xindex>
// CHECK: %[[BCAST:.*]] = vector.broadcast %[[ARG2]] : vector<4xindex> to vector<1x4xindex>
// CHECK: %[[ADD:.*]] = arith.addi %[[SPLAT]], %[[BCAST]] : vector<1x4xindex>
// CHECK: return %[[ADD]] : vector<1x4xindex>
func.func @broadcast_scalar_and_vec( %arg1: index, %arg2: vector<4xindex>) -> vector<1x4xindex> {
%0 = vector.splat %arg1 : vector<1x4xindex>
%1 = vector.broadcast %arg2 : vector<4xindex> to vector<1x4xindex>
%2 = arith.addi %0, %1 : vector<1x4xindex>
return %2 : vector<1x4xindex>
}
// -----
// CHECK-LABEL: func.func @broadcast_vector_and_scalar(
// CHECK-SAME: %[[ARG_0:.*]]: i32,
// CHECK-SAME: %[[ARG_1:.*]]: vector<4xi32>) -> vector<4xi32> {
// CHECK: %[[BCAST:.*]] = vector.broadcast %[[ARG_0]] : i32 to vector<4xi32>
// CHECK: %[[ADD:.*]] = arith.addi %[[BCAST]], %[[ARG_1]] : vector<4xi32>
// CHECK: return %[[ADD]] : vector<4xi32>
func.func @broadcast_vector_and_scalar( %arg1: i32, %arg2: vector<4xi32>) -> vector<4xi32> {
%arg1_bcast = vector.broadcast %arg1 : i32 to vector<4xi32>
%2 = arith.addi %arg1_bcast, %arg2 : vector<4xi32>
return %2 : vector<4xi32>
}
// -----
#matmat_accesses = [
affine_map<(i, j, k) -> (i, k)>,
affine_map<(i, j, k) -> (k, j)>,
affine_map<(i, j, k) -> (i, j)>
]
#matmat_trait = {
indexing_maps = #matmat_accesses,
iterator_types = ["parallel", "parallel", "reduction"]
}
// CHECK-LABEL: func.func @broadcast_not_elementwise() -> vector<2x2xf32> {
// CHECK-DAG: %[[VAL_0:.*]] = arith.constant dense<1.000000e+00> : vector<2x2xf32>
// CHECK-DAG: %[[VAL_1:.*]] = arith.constant dense<2.000000e+00> : vector<2x2xf32>
// CHECK-DAG: %[[VAL_2:.*]] = arith.constant dense<3.000000e+00> : vector<2x2xf32>
// CHECK: %[[VAL_3:.*]] = vector.contract {indexing_maps = [#map, #map1, #map2], iterator_types = ["parallel", "parallel", "reduction"], kind = #vector.kind<add>} %[[VAL_0]], %[[VAL_1]], %[[VAL_2]] : vector<2x2xf32>, vector<2x2xf32> into vector<2x2xf32>
func.func @broadcast_not_elementwise() -> vector<2x2xf32> {
%f1 = arith.constant 1.0: f32
%f2 = arith.constant 2.0: f32
%f3 = arith.constant 3.0: f32
%A = vector.broadcast %f1 : f32 to vector<2x2xf32>
%B = vector.broadcast %f2 : f32 to vector<2x2xf32>
%C = vector.broadcast %f3 : f32 to vector<2x2xf32>
%mm1 = vector.contract #matmat_trait %A, %B, %C
: vector<2x2xf32>, vector<2x2xf32> into vector<2x2xf32>
return %mm1 : vector<2x2xf32>
}
// CHECK-LABEL: func.func @dont_sink_cmp(
// CHECK: %[[BROADCAST:.+]] = vector.broadcast
// CHECK: %[[RETURN:.+]] = arith.cmpf uno, %[[BROADCAST]], %[[BROADCAST]]
// CHECK: return %[[RETURN]]
func.func @dont_sink_cmp(%arg0 : f32, %arg1 : vector<1xf32>) -> vector<1xi1> {
%0 = vector.broadcast %arg0 : f32 to vector<1xf32>
%1 = arith.cmpf uno, %0, %0 : vector<1xf32>
return %1 : vector<1xi1>
}
// CHECK-LABEL: func.func @dont_sink_fma(
// CHECK: %[[BROADCAST:.+]] = vector.broadcast
// CHECK: %[[RESULT:.+]] = vector.fma %[[BROADCAST]]
// CHECK: return %[[RESULT]]
func.func @dont_sink_fma(%arg0 : f32) -> vector<1xf32> {
%0 = vector.broadcast %arg0 : f32 to vector<1xf32>
%1 = vector.fma %0, %0, %0 : vector<1xf32>
return %1 : vector<1xf32>
}
|
