Compute Library
 21.11
CpuWeightsReshapeKernel.cpp
Go to the documentation of this file.
1 /*
2  * Copyright (c) 2017-2021 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 
30 
31 namespace arm_compute
32 {
33 namespace cpu
34 {
35 namespace kernels
36 {
37 namespace
38 {
39 TensorShape get_output_shape(const ITensorInfo *src, bool has_bias)
40 {
41  TensorShape output_shape{ src->tensor_shape() };
42 
43  output_shape.collapse(3);
44  const size_t tmp_dim = output_shape[0];
45  output_shape.set(0, output_shape[1]);
46  output_shape.set(1, tmp_dim + (has_bias ? 1 : 0));
47 
48  return output_shape;
49 }
50 
51 Status validate_arguments(const ITensorInfo *src, const ITensorInfo *biases, const ITensorInfo *dst)
52 {
54  //Note: ARM_COMPUTE_RETURN_ERROR_ON_CPU_F16_UNSUPPORTED(src) is not needed here as this kernel doesn't use CPU FP16 instructions.
56 
57  if(biases != nullptr)
58  {
61  ARM_COMPUTE_RETURN_ERROR_ON((src->num_dimensions() == 4) && (biases->num_dimensions() != 1));
62  ARM_COMPUTE_RETURN_ERROR_ON((src->num_dimensions() == 5) && (biases->num_dimensions() != 2));
63  ARM_COMPUTE_RETURN_ERROR_ON((src->num_dimensions() == 4) && (biases->dimension(0) != src->tensor_shape()[3]));
64  ARM_COMPUTE_RETURN_ERROR_ON((src->num_dimensions() == 5) && (biases->dimension(0) != src->tensor_shape()[3] || biases->dimension(1) != src->tensor_shape()[4]));
65  }
66 
67  // Checks performed when output is configured
68  if(dst->total_size() != 0)
69  {
70  ARM_COMPUTE_RETURN_ERROR_ON_MISMATCHING_DIMENSIONS(dst->tensor_shape(), get_output_shape(src, biases != nullptr));
73  }
74 
75  return Status{};
76 }
77 } // namespace
78 
80 {
82 
83  // Output tensor auto inizialitation if not yet initialized
84  auto_init_if_empty(*dst, src->clone()->set_tensor_shape(get_output_shape(src, (biases != nullptr))));
85 
86  // Perform validation step
87  ARM_COMPUTE_ERROR_THROW_ON(validate_arguments(src,
88  biases,
89  dst));
90 
91  // Configure kernel
93  window.set(Window::DimX, Window::Dimension(0, src->dimension(0), src->dimension(0)));
94  window.set(Window::DimY, Window::Dimension(0, src->dimension(1), src->dimension(1)));
95  window.set(Window::DimZ, Window::Dimension(0, src->dimension(2), src->dimension(2)));
96  ICpuKernel::configure(window);
97 }
98 
100 {
101  ARM_COMPUTE_RETURN_ON_ERROR(validate_arguments(src, biases, dst));
102  return Status{};
103 }
104 
106 {
107  ARM_COMPUTE_UNUSED(info);
110 
111  auto src = tensors.get_const_tensor(TensorType::ACL_SRC);
112  auto biases = tensors.get_const_tensor(TensorType::ACL_BIAS);
113  auto dst = tensors.get_tensor(TensorType::ACL_DST);
114 
115  const unsigned int kernel_size_x = src->info()->dimension(0);
116  const unsigned int kernel_size_y = src->info()->dimension(1);
117  const unsigned int kernel_depth = src->info()->dimension(2);
118  const unsigned int input_stride_x = src->info()->strides_in_bytes().x();
119  const unsigned int input_stride_y = src->info()->strides_in_bytes().y();
120  const unsigned int input_stride_z = src->info()->strides_in_bytes().z();
121  const unsigned int output_stride_y = dst->info()->strides_in_bytes().y();
122 
123  // Create iterators
124  Iterator in(src, window);
125  execute_window_loop(window, [&](const Coordinates & id)
126  {
127  // Get column index
128  const int kernel_idx = id[3];
129  const int kernel_idz = id[4];
130 
131  // Setup pointers
132  const uint8_t *tmp_input_ptr = in.ptr();
133  uint8_t *tmp_output_ptr = dst->ptr_to_element(Coordinates(kernel_idx, 0, kernel_idz));
134  const uint8_t *curr_input_row_ptr = tmp_input_ptr;
135  const uint8_t *curr_input_depth_ptr = tmp_input_ptr;
136 
137  // Linearize volume
138  for(unsigned int d = 0; d < kernel_depth; ++d)
139  {
140  for(unsigned int j = 0; j < kernel_size_y; ++j)
141  {
142  for(unsigned int i = 0; i < kernel_size_x; ++i)
143  {
144  std::memcpy(tmp_output_ptr, tmp_input_ptr, src->info()->element_size());
145  tmp_input_ptr += input_stride_x;
146  tmp_output_ptr += output_stride_y;
147  }
148  curr_input_row_ptr += input_stride_y;
149  tmp_input_ptr = curr_input_row_ptr;
150  }
151  curr_input_depth_ptr += input_stride_z;
152  curr_input_row_ptr = curr_input_depth_ptr;
153  tmp_input_ptr = curr_input_depth_ptr;
154  }
155 
156  // Add bias
157  if(biases != nullptr)
158  {
159  std::memcpy(tmp_output_ptr, biases->ptr_to_element(Coordinates(kernel_idx, kernel_idz)), src->info()->element_size());
160  }
161  },
162  in);
163 }
164 const char *CpuWeightsReshapeKernel::name() const
165 {
166  return "CpuWeightsReshapeKernel";
167 }
168 } // namespace kernels
169 } // namespace cpu
170 } // namespace arm_compute
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
void configure(const ITensorInfo *src, const ITensorInfo *biases, ITensorInfo *dst)
Set the input and output of the kernel.
void run_op(ITensorPack &tensors, const Window &window, const ThreadInfo &info) override
Execute the kernel on the passed window.
virtual size_t dimension(size_t index) const =0
Return the size of the requested dimension.
#define ARM_COMPUTE_RETURN_ERROR_ON_MISMATCHING_QUANTIZATION_INFO(...)
Definition: Validate.h:606
const size_t input_stride_y
#define ARM_COMPUTE_RETURN_ON_ERROR(status)
Checks if a status contains an error and returns it.
Definition: Error.h:204
Store the tensor&#39;s metadata.
Definition: ITensorInfo.h:40
#define ARM_COMPUTE_ERROR_THROW_ON(status)
Definition: Error.h:455
Describe one of the image&#39;s dimensions with a start, end and step.
Definition: Window.h:77
const size_t input_stride_z
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
#define ARM_COMPUTE_RETURN_ERROR_ON_MISMATCHING_DIMENSIONS(...)
Definition: Validate.h:284
SimpleTensor< float > src
Definition: DFT.cpp:155
Copyright (c) 2017-2021 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
static Status validate(const ITensorInfo *src, const ITensorInfo *biases, const ITensorInfo *dst)
Static function to check if given info will lead to a valid configuration.
static constexpr size_t DimX
Alias for dimension 0 also known as X dimension.
Definition: Window.h:43
#define ARM_COMPUTE_UNUSED(...)
To avoid unused variables warnings.
Definition: Error.h:152
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.
virtual ITensorInfo * info() const =0
Interface to be implemented by the child class to return the tensor&#39;s metadata.
constexpr uint8_t * ptr() const
Return a pointer to the current pixel.
Definition: Helpers.inl:139
void set(size_t dimension, const Dimension &dim)
Set the values of a given dimension.
Definition: Window.inl:49
#define ARM_COMPUTE_ERROR_ON_UNCONFIGURED_KERNEL(k)
Definition: Validate.h:915
bool is_data_type_quantized_asymmetric(DataType dt)
Check if a given data type is of asymmetric quantized type.
Definition: Utils.h:1003
static constexpr size_t DimY
Alias for dimension 1 also known as Y dimension.
Definition: Window.h:45
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:158
static constexpr size_t DimZ
Alias for dimension 2 also known as Z dimension.
Definition: Window.h:47
#define ARM_COMPUTE_RETURN_ERROR_ON_MISMATCHING_DATA_TYPES(...)
Definition: Validate.h:541
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
const char * name() const override
Name of the kernel.
Describe a multidimensional execution window.
Definition: Window.h:39
#define ARM_COMPUTE_ERROR_ON_INVALID_SUBWINDOW(f, s)
Definition: Validate.h:201