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
|
// RUN: mlir-opt %s -transform-interpreter --cse --canonicalize -split-input-file -verify-diagnostics | FileCheck %s
func.func @test(%A : tensor<128x128xf32>, %B1 : tensor<128x128xf32>, %B2 : tensor<128x128xf32>) -> (tensor<128x128xf32>, tensor<128x128xf32>) {
%zero = arith.constant 0.0 : f32
%out_alloc = tensor.empty() : tensor<128x128xf32>
%out = linalg.fill ins(%zero : f32) outs(%out_alloc : tensor<128x128xf32>) -> tensor<128x128xf32>
// CHECK: scf.forall ([[I:%.*]]) in (4) shared_outs([[S1:%.*]] = [[IN1:%.*]], [[S2:%.*]] = [[IN2:%.*]]) -> (tensor<128x128xf32>, tensor<128x128xf32>) {
// CHECK: [[T:%.*]] = affine.apply
// CHECK: tensor.extract_slice [[S1]][[[T]], 0] [32, 128] [1, 1]
// CHECK: [[OUT1:%.*]] = linalg.matmul
// CHECK: tensor.extract_slice [[S2]][[[T]], 0] [32, 128] [1, 1]
// CHECK: [[OUT2:%.*]] = linalg.matmul
// CHECK: scf.forall.in_parallel {
// CHECK: tensor.parallel_insert_slice [[OUT1]] into [[S1]][[[T]], 0] [32, 128] [1, 1]
// CHECK: tensor.parallel_insert_slice [[OUT2]] into [[S2]][[[T]], 0] [32, 128] [1, 1]
// CHECK: }
// CHECK: }
%out1 = linalg.matmul ins(%A, %B1 : tensor<128x128xf32>, tensor<128x128xf32>) outs(%out : tensor<128x128xf32>) -> tensor<128x128xf32>
%out2 = linalg.matmul ins(%A, %B2 : tensor<128x128xf32>, tensor<128x128xf32>) outs(%out : tensor<128x128xf32>) -> tensor<128x128xf32>
func.return %out1, %out2 : tensor<128x128xf32>, tensor<128x128xf32>
}
module attributes {transform.with_named_sequence} {
transform.named_sequence @__transform_main(%variant_op : !transform.any_op {transform.readonly}) {
%matched = transform.structured.match ops{["linalg.matmul"]} in %variant_op : (!transform.any_op) -> (!transform.any_op)
%mm1, %mm2 = transform.split_handle %matched : (!transform.any_op) -> (!transform.any_op, !transform.any_op)
%tiled_mm1, %loop1 = transform.structured.tile_using_forall %mm1 tile_sizes [32] : (!transform.any_op) -> (!transform.any_op, !transform.any_op)
%tiled_mm2, %loop2 = transform.structured.tile_using_forall %mm2 tile_sizes [32] : (!transform.any_op) -> (!transform.any_op, !transform.any_op)
%fused_loop = transform.loop.fuse_sibling %loop1 into %loop2 : (!transform.any_op, !transform.any_op) -> !transform.any_op
transform.yield
}
}
// -----
func.func @test(%A : tensor<128x128xf32>, %B1 : tensor<128x128xf32>, %B2 : tensor<128x128xf32>) -> (tensor<128x128xf32>, tensor<128x128xf32>) {
%zero = arith.constant 0.0 : f32
%out_alloc = tensor.empty() : tensor<128x128xf32>
%out = linalg.fill ins(%zero : f32) outs(%out_alloc : tensor<128x128xf32>) -> tensor<128x128xf32>
// expected-error @below {{user of results of target should be properly dominated by source}}
%out1 = linalg.matmul ins(%A, %B1 : tensor<128x128xf32>, tensor<128x128xf32>) outs(%out : tensor<128x128xf32>) -> tensor<128x128xf32>
%out2 = linalg.matmul ins(%A, %out1 : tensor<128x128xf32>, tensor<128x128xf32>) outs(%out : tensor<128x128xf32>) -> tensor<128x128xf32>
func.return %out1, %out2 : tensor<128x128xf32>, tensor<128x128xf32>
}
module attributes {transform.with_named_sequence} {
transform.named_sequence @__transform_main(%variant_op : !transform.any_op {transform.readonly}) {
%matched = transform.structured.match ops{["linalg.matmul"]} in %variant_op : (!transform.any_op) -> (!transform.any_op)
%mm1, %mm2 = transform.split_handle %matched : (!transform.any_op) -> (!transform.any_op, !transform.any_op)
%tiled_mm1, %loop1 = transform.structured.tile_using_forall %mm1 tile_sizes [32] : (!transform.any_op) -> (!transform.any_op, !transform.any_op)
%tiled_mm2, %loop2 = transform.structured.tile_using_forall %mm2 tile_sizes [32] : (!transform.any_op) -> (!transform.any_op, !transform.any_op)
%fused_loop = transform.loop.fuse_sibling %loop1 into %loop2 : (!transform.any_op, !transform.any_op) -> !transform.any_op
transform.yield
}
}
// -----
func.func @test(%A : tensor<128x128xf32>, %B1 : tensor<128x128xf32>, %B2 : tensor<128x128xf32>) -> (tensor<128x128xf32>, tensor<128x128xf32>) {
%zero = arith.constant 0.0 : f32
%out_alloc = tensor.empty() : tensor<128x128xf32>
%out = linalg.fill ins(%zero : f32) outs(%out_alloc : tensor<128x128xf32>) -> tensor<128x128xf32>
%out1 = linalg.matmul ins(%A, %B1 : tensor<128x128xf32>, tensor<128x128xf32>) outs(%out : tensor<128x128xf32>) -> tensor<128x128xf32>
// expected-error @below {{values used inside regions of target should be properly dominated by source}}
%out2 = linalg.matmul ins(%A, %out1 : tensor<128x128xf32>, tensor<128x128xf32>) outs(%out : tensor<128x128xf32>) -> tensor<128x128xf32>
func.return %out1, %out2 : tensor<128x128xf32>, tensor<128x128xf32>
}
module attributes {transform.with_named_sequence} {
transform.named_sequence @__transform_main(%variant_op : !transform.any_op {transform.readonly}) {
%matched = transform.structured.match ops{["linalg.matmul"]} in %variant_op : (!transform.any_op) -> (!transform.any_op)
%mm1, %mm2 = transform.split_handle %matched : (!transform.any_op) -> (!transform.any_op, !transform.any_op)
%tiled_mm1, %loop1 = transform.structured.tile_using_forall %mm1 tile_sizes [32] : (!transform.any_op) -> (!transform.any_op, !transform.any_op)
%tiled_mm2, %loop2 = transform.structured.tile_using_forall %mm2 tile_sizes [32] : (!transform.any_op) -> (!transform.any_op, !transform.any_op)
%fused_loop = transform.loop.fuse_sibling %loop2 into %loop1 : (!transform.any_op, !transform.any_op) -> !transform.any_op
transform.yield
}
}
// -----
func.func @test(%A : tensor<128x128xf32>, %B1 : tensor<128x128xf32>, %B2 : tensor<128x128xf32>) -> (tensor<128x128xf32>, tensor<128x128xf32>) {
%zero = arith.constant 0.0 : f32
%out_alloc = tensor.empty() : tensor<128x128xf32>
%out = linalg.fill ins(%zero : f32) outs(%out_alloc : tensor<128x128xf32>) -> tensor<128x128xf32>
%out1 = linalg.matmul ins(%A, %B1 : tensor<128x128xf32>, tensor<128x128xf32>) outs(%out : tensor<128x128xf32>) -> tensor<128x128xf32>
// expected-error @below {{operands of target should be properly dominated by source}}
%out2 = linalg.matmul ins(%A, %B2 : tensor<128x128xf32>, tensor<128x128xf32>) outs(%out1 : tensor<128x128xf32>) -> tensor<128x128xf32>
func.return %out1, %out2 : tensor<128x128xf32>, tensor<128x128xf32>
}
module attributes {transform.with_named_sequence} {
transform.named_sequence @__transform_main(%variant_op : !transform.any_op {transform.readonly}) {
%matched = transform.structured.match ops{["linalg.matmul"]} in %variant_op : (!transform.any_op) -> (!transform.any_op)
%mm1, %mm2 = transform.split_handle %matched : (!transform.any_op) -> (!transform.any_op, !transform.any_op)
%tiled_mm1, %loop1 = transform.structured.tile_using_forall %mm1 tile_sizes [32] : (!transform.any_op) -> (!transform.any_op, !transform.any_op)
%tiled_mm2, %loop2 = transform.structured.tile_using_forall %mm2 tile_sizes [32] : (!transform.any_op) -> (!transform.any_op, !transform.any_op)
%fused_loop = transform.loop.fuse_sibling %loop2 into %loop1 : (!transform.any_op, !transform.any_op) -> !transform.any_op
transform.yield
}
}
|
