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
|
/*
* Copyright (c) 2017-2022 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 "src/cpu/kernels/CpuFloorKernel.h"
#include "arm_compute/core/Coordinates.h"
#include "arm_compute/core/Helpers.h"
#include "arm_compute/core/ITensor.h"
#include "arm_compute/core/Validate.h"
#include "src/core/common/Registrars.h"
#include "src/core/CPP/Validate.h"
#include "src/core/helpers/AutoConfiguration.h"
#include "src/core/helpers/WindowHelpers.h"
#include "src/cpu/kernels/floor/list.h"
namespace arm_compute
{
namespace cpu
{
namespace kernels
{
namespace
{
static const std::vector<CpuFloorKernel::FloorKernel> available_kernels = {
{"neon_fp16_floor", [](const DataTypeISASelectorData &data) { return data.dt == DataType::F16 && data.isa.fp16; },
REGISTER_FP16_NEON(arm_compute::cpu::fp16_neon_floor)},
{"neon_fp32_floor", [](const DataTypeISASelectorData &data) { return data.dt == DataType::F32; },
REGISTER_FP32_NEON(arm_compute::cpu::fp32_neon_floor)}};
Status validate_arguments(const ITensorInfo *src, const ITensorInfo *dst)
{
ARM_COMPUTE_RETURN_ERROR_ON_NULLPTR(src, dst);
const auto *uk =
CpuFloorKernel::get_implementation(DataTypeISASelectorData{src->data_type(), CPUInfo::get().get_isa()});
ARM_COMPUTE_RETURN_ERROR_ON(uk == nullptr || uk->ukernel == nullptr);
// Validate in case of configured output
if (dst->total_size() > 0)
{
ARM_COMPUTE_RETURN_ERROR_ON_MISMATCHING_DATA_TYPES(src, dst);
ARM_COMPUTE_RETURN_ERROR_ON_MISMATCHING_SHAPES(src, dst);
}
return Status{};
}
} // namespace
void CpuFloorKernel::configure(const ITensorInfo *src, ITensorInfo *dst)
{
ARM_COMPUTE_ERROR_ON_NULLPTR(src, dst);
ARM_COMPUTE_ERROR_THROW_ON(validate_arguments(src, dst));
auto_init_if_empty(*dst, src->tensor_shape(), 1, src->data_type());
const auto *uk =
CpuFloorKernel::get_implementation(DataTypeISASelectorData{src->data_type(), CPUInfo::get().get_isa()});
ARM_COMPUTE_ERROR_ON_NULLPTR(uk);
_run_method = uk->ukernel;
_name = std::string("CpuFloorKernel").append("/").append(uk->name);
// Configure kernel window
const Window win = calculate_max_window(*src, Steps());
ICPPKernel::configure(win);
}
Window CpuFloorKernel::infer_window(const ITensorInfo *src, const ITensorInfo *dst)
{
ARM_COMPUTE_UNUSED(dst);
ARM_COMPUTE_ERROR_ON(!bool(validate_arguments(src, dst)));
Window win;
win.use_tensor_dimensions(src->tensor_shape());
return win;
}
Status CpuFloorKernel::validate(const ITensorInfo *input, const ITensorInfo *output)
{
ARM_COMPUTE_RETURN_ON_ERROR(validate_arguments(input, output));
return Status{};
}
void CpuFloorKernel::run_op(ITensorPack &tensors, const Window &window, const ThreadInfo &info)
{
ARM_COMPUTE_UNUSED(info);
ARM_COMPUTE_ERROR_ON_UNCONFIGURED_KERNEL(this);
ARM_COMPUTE_ERROR_ON_INVALID_SUBWINDOW(IKernel::window(), window);
ARM_COMPUTE_ERROR_ON(tensors.empty());
ARM_COMPUTE_ERROR_ON(_run_method == nullptr);
const ITensor *src = tensors.get_const_tensor(TensorType::ACL_SRC);
ITensor *dst = tensors.get_tensor(TensorType::ACL_DST);
const auto len = static_cast<int>(window.x().end()) - static_cast<int>(window.x().start());
Window win{window};
win.set(Window::DimX, Window::Dimension(0, 1, 1));
Iterator src_it(src, win);
Iterator dst_it(dst, win);
execute_window_loop(
win, [&](const Coordinates &) { _run_method(src_it.ptr(), dst_it.ptr(), len); }, src_it, dst_it);
}
const char *CpuFloorKernel::name() const
{
return _name.c_str();
}
const std::vector<CpuFloorKernel::FloorKernel> &CpuFloorKernel::get_available_kernels()
{
return available_kernels;
}
} // namespace kernels
} // namespace cpu
} // namespace arm_compute
|
