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
|
// RUN: mlir-opt %s -test-tensor-copy-insertion="allow-return-allocs" -allow-unregistered-dialect -split-input-file | FileCheck %s
// RUN: mlir-opt %s -test-tensor-copy-insertion="bufferize-function-boundaries allow-return-allocs" -split-input-file | FileCheck %s --check-prefix=CHECK-FUNC
// CHECK-LABEL: func @scf_for(
// CHECK-SAME: %[[A:.*]]: tensor<?xf32>, %[[B:.*]]: tensor<?xf32>
func.func @scf_for(%A : tensor<?xf32>, %B : tensor<?xf32>,
%lb : index, %ub : index, %step : index)
-> (tensor<?xf32>, tensor<?xf32>)
{
// CHECK: %[[A_copy:.*]] = bufferization.alloc_tensor() copy(%[[A]]) {bufferization.escape = [false]} : tensor<?xf32>
// CHECK: %[[B_copy:.*]] = bufferization.alloc_tensor() copy(%[[B]]) {bufferization.escape = [false]} : tensor<?xf32>
// CHECK: %[[for:.*]]:2 = scf.for {{.*}} iter_args(%[[iter1:.*]] = %[[A_copy]], %[[iter2:.*]] = %[[B_copy]])
%r0:2 = scf.for %i = %lb to %ub step %step iter_args(%tA = %A, %tB = %B)
-> (tensor<?xf32>, tensor<?xf32>)
{
// CHECK: scf.yield %[[iter1]], %[[iter2]]
scf.yield %tA, %tB : tensor<?xf32>, tensor<?xf32>
}
return %r0#0, %r0#1 : tensor<?xf32>, tensor<?xf32>
}
// -----
// CHECK-LABEL: func @scf_for_swapping_yields(
// CHECK-SAME: %[[A:.*]]: tensor<?xf32>, %[[B:.*]]: tensor<?xf32>
func.func @scf_for_swapping_yields(%A : tensor<?xf32>, %B : tensor<?xf32>,
%lb : index, %ub : index, %step : index)
-> (tensor<?xf32>, tensor<?xf32>)
{
// CHECK: %[[A_copy:.*]] = bufferization.alloc_tensor() copy(%[[A]]) {bufferization.escape = [false]} : tensor<?xf32>
// CHECK: %[[B_copy:.*]] = bufferization.alloc_tensor() copy(%[[B]]) {bufferization.escape = [false]} : tensor<?xf32>
// CHECK: %[[for:.*]]:2 = scf.for {{.*}} iter_args(%[[iter1:.*]] = %[[A_copy]], %[[iter2:.*]] = %[[B_copy]])
%r0:2 = scf.for %i = %lb to %ub step %step iter_args(%tA = %A, %tB = %B)
-> (tensor<?xf32>, tensor<?xf32>)
{
// Yield tensors in different order.
// CHECK-DAG: %[[yield1:.*]] = bufferization.alloc_tensor() copy(%[[iter2]]) {bufferization.escape = [true]} : tensor<?xf32>
// CHECK-DAG: %[[yield2:.*]] = bufferization.alloc_tensor() copy(%[[iter1]]) {bufferization.escape = [true]} : tensor<?xf32>
// CHECK: scf.yield %[[yield1]], %[[yield2]]
scf.yield %tB, %tA : tensor<?xf32>, tensor<?xf32>
}
return %r0#0, %r0#1 : tensor<?xf32>, tensor<?xf32>
}
// -----
// CHECK-LABEL: func @scf_while(
// CHECK-SAME: %[[A:.*]]: tensor<5xi1>, %[[B:.*]]: tensor<5xi1>
func.func @scf_while(%A: tensor<5xi1>, %B: tensor<5xi1>, %idx: index)
-> (tensor<5xi1>, tensor<5xi1>)
{
// CHECK: %[[A_copy:.*]] = bufferization.alloc_tensor() copy(%[[A]]) {bufferization.escape = [false]} : tensor<5xi1>
// CHECK: %[[B_copy:.*]] = bufferization.alloc_tensor() copy(%[[B]]) {bufferization.escape = [false]} : tensor<5xi1>
// CHECK: %[[loop:.*]]:2 = scf.while (%[[w0:.*]] = %[[A_copy]], %[[w1:.*]] = %[[B_copy]]) {{.*}} {
%r0, %r1 = scf.while (%w0 = %A, %w1 = %B)
: (tensor<5xi1>, tensor<5xi1>) -> (tensor<5xi1>, tensor<5xi1>) {
// CHECK: %[[condition:.*]] = tensor.extract %[[w0]]
%condition = tensor.extract %w0[%idx] : tensor<5xi1>
// Yield tensors in different order.
// CHECK: scf.condition(%[[condition]]) %[[w0]], %[[w1]]
scf.condition(%condition) %w0, %w1 : tensor<5xi1>, tensor<5xi1>
} do {
^bb0(%b0: tensor<5xi1>, %b1: tensor<5xi1>):
// CHECK: } do {
// CHECK: ^bb0(%[[b0:.*]]: tensor<5xi1>, %[[b1:.*]]: tensor<5xi1>):
// CHECK: scf.yield %[[b0]], %[[b1]]
// CHECK: }
scf.yield %b0, %b1 : tensor<5xi1>, tensor<5xi1>
}
return %r0, %r1 : tensor<5xi1>, tensor<5xi1>
}
// -----
// CHECK-LABEL: func @scf_while_non_equiv_condition_and_body(
// CHECK-SAME: %[[A:.*]]: tensor<5xi1>, %[[B:.*]]: tensor<5xi1>
func.func @scf_while_non_equiv_condition_and_body(%A: tensor<5xi1>,
%B: tensor<5xi1>,
%idx: index)
-> (tensor<5xi1>, tensor<5xi1>)
{
// CHECK: %[[A_copy:.*]] = bufferization.alloc_tensor() copy(%[[A]]) {bufferization.escape = [false]} : tensor<5xi1>
// CHECK: %[[B_copy:.*]] = bufferization.alloc_tensor() copy(%[[B]]) {bufferization.escape = [false]} : tensor<5xi1>
// CHECK: %[[loop:.*]]:2 = scf.while (%[[w0:.*]] = %[[A_copy]], %[[w1:.*]] = %[[B_copy]]) {{.*}} {
%r0, %r1 = scf.while (%w0 = %A, %w1 = %B)
: (tensor<5xi1>, tensor<5xi1>) -> (tensor<5xi1>, tensor<5xi1>) {
// CHECK: %[[condition:.*]] = tensor.extract %[[w0]]
%condition = tensor.extract %w0[%idx] : tensor<5xi1>
// Yield tensors in different order.
// CHECK-DAG: %[[yield0:.*]] = bufferization.alloc_tensor() copy(%[[w1]]) {bufferization.escape = [true]} : tensor<5xi1>
// CHECK-DAG: %[[yield1:.*]] = bufferization.alloc_tensor() copy(%[[w0]]) {bufferization.escape = [true]} : tensor<5xi1>
// CHECK: scf.condition(%[[condition]]) %[[yield0]], %[[yield1]]
scf.condition(%condition) %w1, %w0 : tensor<5xi1>, tensor<5xi1>
} do {
^bb0(%b0: tensor<5xi1>, %b1: tensor<5xi1>):
// CHECK: } do {
// CHECK: ^bb0(%[[b0:.*]]: tensor<5xi1>, %[[b1:.*]]: tensor<5xi1>):
// CHECK: scf.yield %[[b1]], %[[b0]]
// CHECK: }
scf.yield %b1, %b0 : tensor<5xi1>, tensor<5xi1>
}
return %r0, %r1 : tensor<5xi1>, tensor<5xi1>
}
// -----
// CHECK-LABEL: func @scf_forall_out_of_place(
// CHECK-SAME: %[[arg0:.*]]: tensor<100xf32>, %[[arg1:.*]]: tensor<100xf32>
// CHECK-FUNC-LABEL: func @scf_forall_out_of_place(
func.func @scf_forall_out_of_place(%in: tensor<100xf32>,
%out: tensor<100xf32>) {
%c1 = arith.constant 1 : index
%num_threads = arith.constant 100 : index
// CHECK-FUNC-NOT: alloc_tensor
// CHECK: %[[alloc:.*]] = bufferization.alloc_tensor() copy(%[[arg1]]) {bufferization.escape = [false]} : tensor<100xf32>
// CHECK: scf.forall {{.*}} shared_outs(%[[o:.*]] = %[[alloc]])
%result = scf.forall (%thread_idx) in (%num_threads) shared_outs(%o = %out) -> tensor<100xf32> {
// CHECK: tensor.extract_slice
// CHECK: scf.forall.in_parallel
// CHECK: tensor.parallel_insert_slice %{{.*}} into %[[o]]
%1 = tensor.extract_slice %in[%thread_idx][1][1] : tensor<100xf32> to tensor<1xf32>
scf.forall.in_parallel {
tensor.parallel_insert_slice %1 into %o[%thread_idx][1][1] :
tensor<1xf32> into tensor<100xf32>
}
// CHECK: } {mapping = [#gpu.thread<x>]}
} {mapping = [#gpu.thread<x>]}
return
}
|
