Compute Library
 22.05
CpuConvertFullyConnectedWeightsKernel.cpp
Go to the documentation of this file.
1 /*
2  * Copyright (c) 2018-2021 Arm Limited.
3  *
4  * SPDX-License-Identifier: MIT
5  *
6  * Permission is hereby granted, free of charge, to any person obtaining a copy
7  * of this software and associated documentation files (the "Software"), to
8  * deal in the Software without restriction, including without limitation the
9  * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or
10  * sell copies of the Software, and to permit persons to whom the Software is
11  * furnished to do so, subject to the following conditions:
12  *
13  * The above copyright notice and this permission notice shall be included in all
14  * copies or substantial portions of the Software.
15  *
16  * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
17  * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
18  * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
19  * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
20  * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
21  * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
22  * SOFTWARE.
23  */
25 
27 #include "arm_compute/core/Types.h"
30 
31 namespace arm_compute
32 {
33 namespace cpu
34 {
35 namespace kernels
36 {
39 
40 {
42 
43  // Output tensor auto initialisation if not yet initialized
44  auto_init_if_empty(*dst, *src->clone());
45 
46  ARM_COMPUTE_ERROR_THROW_ON(CpuConvertFullyConnectedWeightsKernel::validate(src, dst, original_input_shape, data_layout));
47 
48  const DataLayout input_data_layout = (data_layout == DataLayout::NCHW) ? DataLayout::NHWC : DataLayout::NCHW;
49 
50  const int width_idx = get_data_layout_dimension_index(input_data_layout, DataLayoutDimension::WIDTH);
51  const int height_idx = get_data_layout_dimension_index(input_data_layout, DataLayoutDimension::HEIGHT);
52  const int channel_idx = get_data_layout_dimension_index(input_data_layout, DataLayoutDimension::CHANNEL);
53 
54  const unsigned int num_elems_per_input_plane = original_input_shape[width_idx] * original_input_shape[height_idx];
55  const unsigned int num_channels = original_input_shape[channel_idx];
56 
57  _factor1 = (data_layout == DataLayout::NCHW) ? num_elems_per_input_plane : num_channels;
58  _factor2 = (data_layout == DataLayout::NCHW) ? num_channels : num_elems_per_input_plane;
59 
60  // Configure kernel window
61  Window win = calculate_max_window(*src, Steps());
62  ICpuKernel::configure(win);
63 }
64 
67 {
71  ARM_COMPUTE_RETURN_ERROR_ON(src->dimension(1) != original_input_shape.total_size_lower(3));
73 
74  // Checks performed when dst is configured
75  if((dst != nullptr) && (dst->total_size() != 0))
76  {
79  }
80 
81  return Status{};
82 }
83 
85 {
86  ARM_COMPUTE_UNUSED(info);
89 
90  const auto src = tensors.get_const_tensor(TensorType::ACL_SRC);
91  auto dst = tensors.get_tensor(TensorType::ACL_DST);
92 
93  const unsigned int dst_stride_x = dst->info()->strides_in_bytes().x();
94  const unsigned int dst_stride_y = dst->info()->strides_in_bytes().y();
95  const unsigned int element_size = src->info()->element_size();
96 
97  Iterator input(src, window);
98  Iterator output(dst, window);
99 
100  execute_window_loop(window, [&](const Coordinates & id)
101  {
102  memcpy(output.ptr() + id.x() * dst_stride_x + (id.y() % _factor1 * _factor2 + id.y() / _factor1) * dst_stride_y, input.ptr(), element_size);
103  },
104  input);
105 }
106 
108 {
109  return "CpuConvertFullyConnectedWeightsKernel";
110 }
111 } // namespace kernels
112 } // namespace cpu
113 } // namespace arm_compute
virtual size_t num_dimensions() const =0
The number of dimensions of the tensor (rank)
Window calculate_max_window(const ValidRegion &valid_region, const Steps &steps, bool skip_border, BorderSize border_size)
const Window & window() const
The maximum window the kernel can be executed on.
Definition: IKernel.cpp:28
Shape of a tensor.
Definition: TensorShape.h:39
virtual size_t dimension(size_t index) const =0
Return the size of the requested dimension.
void configure(const ITensorInfo *src, ITensorInfo *dst, const TensorShape &original_input_shape, DataLayout data_layout)
Set the src and dst tensor.
virtual DataType data_type() const =0
Data type used for each element of the tensor.
Store the tensor's metadata.
Definition: ITensorInfo.h:40
#define ARM_COMPUTE_ERROR_THROW_ON(status)
Definition: Error.h:455
Status class.
Definition: Error.h:52
#define ARM_COMPUTE_RETURN_ERROR_ON(cond)
If the condition is true, an error is returned.
Definition: Error.h:296
size_t total_size_lower(size_t dimension) const
Compute size of dimensions lower than the given one.
Definition: TensorShape.h:194
SimpleTensor< float > src
Definition: DFT.cpp:155
Copyright (c) 2017-2022 Arm Limited.
#define ARM_COMPUTE_RETURN_ERROR_ON_NULLPTR(...)
Definition: Validate.h:159
const ITensor * get_const_tensor(int id) const
Get constant tensor of a given id.
Definition: ITensorPack.cpp:54
#define ARM_COMPUTE_UNUSED(...)
To avoid unused variables warnings.
Definition: Error.h:152
void run_op(ITensorPack &tensors, const Window &window, const ThreadInfo &info) override
Execute the kernel on the passed window.
static Status validate(const ITensorInfo *src, const ITensorInfo *dst, const TensorShape &original_input_shape, DataLayout data_layout)
Static function to check if given info will lead to a valid configuration.
Class to describe a number of elements in each dimension.
Definition: Steps.h:40
Coordinates of an item.
Definition: Coordinates.h:37
bool auto_init_if_empty(ITensorInfo &info, const TensorShape &shape, int num_channels, DataType data_type, QuantizationInfo quantization_info=QuantizationInfo())
Auto initialize the tensor info (shape, number of channels and data type) if the current assignment i...
virtual std::unique_ptr< T > clone() const =0
Provide a clone of the current object of class T.
constexpr uint8_t * ptr() const
Return a pointer to the current pixel.
Definition: Helpers.inl:139
#define ARM_COMPUTE_ERROR_ON_UNCONFIGURED_KERNEL(k)
Definition: Validate.h:915
Num samples, channels, height, width.
ScaleKernelInfo info(interpolation_policy, default_border_mode, PixelValue(), sampling_policy, false)
ITensor * get_tensor(int id)
Get tensor of a given id from the pac.
Definition: ITensorPack.cpp:64
Information about executing thread and CPU.
Definition: CPPTypes.h:169
virtual size_t total_size() const =0
Returns the total size of the tensor in bytes.
#define ARM_COMPUTE_RETURN_ERROR_ON_MISMATCHING_SHAPES(...)
Definition: Validate.h:439
size_t get_data_layout_dimension_index(const DataLayout &data_layout, const DataLayoutDimension &data_layout_dimension)
Get the index of the given dimension.
Definition: Helpers.inl:193
#define ARM_COMPUTE_RETURN_ERROR_ON_MISMATCHING_DATA_TYPES(...)
Definition: Validate.h:541
Num samples, height, width, channels.
Tensor packing service.
Definition: ITensorPack.h:39
#define ARM_COMPUTE_ERROR_ON_NULLPTR(...)
Definition: Validate.h:157
void execute_window_loop(const Window &w, L &&lambda_function, Ts &&... iterators)
Iterate through the passed window, automatically adjusting the iterators and calling the lambda_funct...
Definition: Helpers.inl:77
Iterator updated by execute_window_loop for each window element.
Definition: Helpers.h:46
DataLayout
[DataLayout enum definition]
Definition: Types.h:113
Describe a multidimensional execution window.
Definition: Window.h:39
#define ARM_COMPUTE_ERROR_ON_INVALID_SUBWINDOW(f, s)
Definition: Validate.h:201