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
|
/*
* Copyright (c) 2022 Arm Limited.
*
* SPDX-License-Identifier: MIT
*
* Permission is hereby granted, free of charge, to any person obtaining a copy
* of this software and associated documentation files (the "Software"), to
* deal in the Software without restriction, including without limitation the
* rights to use, copy, modify, merge, publish, distribute, sublicense, and/or
* sell copies of the Software, and to permit persons to whom the Software is
* furnished to do so, subject to the following conditions:
*
* The above copyright notice and this permission notice shall be included in all
* copies or substantial portions of the Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
* AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
* OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
* SOFTWARE.
*/
#include "ClTemplateStore.h"
#include "src/dynamic_fusion/sketch/gpu/GpuKernelComponentGroup.h"
namespace arm_compute
{
namespace experimental
{
namespace dynamic_fusion
{
ClTemplateStore::ClTemplateStore(ComponentId id, const ArgumentPack<ITensorInfo> &tensors)
: IGpuTemplateComponentWriter{id, tensors}, _src{}, _dst{}
{
_src = this->tensors().get_const_tensor(TensorType::ACL_SRC_0);
_dst = this->tensors().get_const_tensor(TensorType::ACL_DST_0);
}
std::string ClTemplateStore::get_name() const
{
return "store";
}
std::string ClTemplateStore::get_component_code(const ComponentGroup &comp_group) const
{
ARM_COMPUTE_UNUSED(comp_group);
return R"_(
//------------------ START KERNEL {{meta_kernel_id}} STORE ---------------------
{
bool x_cond = PARTIAL_N0 != 0 && get_global_id(0) == 0;
T_STORE_INDIRECT_WIDTH_SELECT({{DST_DATA_TYPE}}, M0, N0, PARTIAL_N0, {{DST_TENSOR_TYPE}}, {{dst}}, g_ind_0, {{dst}}_stride_y, x_cond, {{src}}, g_dst_indirect_y);
//------------------ END KERNEL {{meta_kernel_id}} STORE ---------------------
}
)_";
}
void ClTemplateStore::declare_variables(GpuKernelVariableTable &vtable, const ComponentGroup &comp_group) const
{
vtable.declare_variable(comp_group, _src, GpuKernelArgumentInfo(GpuKernelArgumentInfo::Type::Tensor_4D_t_Buffer),
"src");
vtable.declare_variable(comp_group, _dst, GpuKernelArgumentInfo(GpuKernelArgumentInfo::Type::Tensor_4D_t_Buffer),
"dst");
}
TagLUT ClTemplateStore::get_tag_lut(const GpuKernelVariableTable &vtable, const ComponentGroup &comp_group) const
{
TagLUT lut{};
// Arguments and global shared variables
lut["src"] = vtable.get_variable(_src);
lut["dst"] = vtable.get_variable(_dst);
// Local build options
lut["meta_kernel_id"] = id();
lut["DST_TENSOR_TYPE"] = "BUFFER";
lut["DST_DATA_TYPE"] = _dst->data_type();
ARM_COMPUTE_UNUSED(comp_group);
return lut;
}
} // namespace dynamic_fusion
} // namespace experimental
} // namespace arm_compute
|
