Compute Library
 19.08
CLCopyKernel Class Reference

OpenCL kernel to perform a copy between two tensors. More...

#include <CLCopyKernel.h>

Collaboration diagram for CLCopyKernel:
[legend]

Public Member Functions

 CLCopyKernel ()
 Default constructor. More...
 
 CLCopyKernel (const CLCopyKernel &)=delete
 Prevent instances of this class from being copied (As this class contains pointers). More...
 
CLCopyKerneloperator= (const CLCopyKernel &)=delete
 Prevent instances of this class from being copied (As this class contains pointers). More...
 
 CLCopyKernel (CLCopyKernel &&)=default
 Allow instances of this class to be moved. More...
 
CLCopyKerneloperator= (CLCopyKernel &&)=default
 Allow instances of this class to be moved. More...
 
void configure (const ICLTensor *input, ICLTensor *output, const PaddingList &padding=PaddingList(), Window *output_window=nullptr)
 Initialize the kernel's input, output. More...
 
void run (const Window &window, cl::CommandQueue &queue) override
 Enqueue the OpenCL kernel to process the given window on the passed OpenCL command queue. More...
 
- Public Member Functions inherited from ICLKernel
 ICLKernel ()
 Constructor. More...
 
cl::Kernel & kernel ()
 Returns a reference to the OpenCL kernel of this object. More...
 
template<typename T >
void add_1D_array_argument (unsigned int &idx, const ICLArray< T > *array, const Strides &strides, unsigned int num_dimensions, const Window &window)
 Add the passed 1D array's parameters to the object's kernel's arguments starting from the index idx. More...
 
void add_1D_tensor_argument (unsigned int &idx, const ICLTensor *tensor, const Window &window)
 Add the passed 1D tensor's parameters to the object's kernel's arguments starting from the index idx. More...
 
void add_1D_tensor_argument_if (bool cond, unsigned int &idx, const ICLTensor *tensor, const Window &window)
 Add the passed 1D tensor's parameters to the object's kernel's arguments starting from the index idx if the condition is true. More...
 
void add_2D_tensor_argument (unsigned int &idx, const ICLTensor *tensor, const Window &window)
 Add the passed 2D tensor's parameters to the object's kernel's arguments starting from the index idx. More...
 
void add_2D_tensor_argument_if (bool cond, unsigned int &idx, const ICLTensor *tensor, const Window &window)
 Add the passed 2D tensor's parameters to the object's kernel's arguments starting from the index idx if the condition is true. More...
 
void add_3D_tensor_argument (unsigned int &idx, const ICLTensor *tensor, const Window &window)
 Add the passed 3D tensor's parameters to the object's kernel's arguments starting from the index idx. More...
 
void add_4D_tensor_argument (unsigned int &idx, const ICLTensor *tensor, const Window &window)
 Add the passed 4D tensor's parameters to the object's kernel's arguments starting from the index idx. More...
 
template<typename T >
void add_argument (unsigned int &idx, T value)
 Add the passed parameters to the object's kernel's arguments starting from the index idx. More...
 
void set_lws_hint (const cl::NDRange &lws_hint)
 Set the Local-Workgroup-Size hint. More...
 
cl::NDRange lws_hint () const
 Return the Local-Workgroup-Size hint. More...
 
const std::string & config_id () const
 Get the configuration ID. More...
 
void set_target (GPUTarget target)
 Set the targeted GPU architecture. More...
 
void set_target (cl::Device &device)
 Set the targeted GPU architecture according to the CL device. More...
 
GPUTarget get_target () const
 Get the targeted GPU architecture. More...
 
size_t get_max_workgroup_size ()
 Get the maximum workgroup size for the device the CLKernelLibrary uses. More...
 
template<typename T , unsigned int dimension_size>
void add_array_argument (unsigned &idx, const ICLArray< T > *array, const Strides &strides, unsigned int num_dimensions, const Window &window)
 Add the passed array's parameters to the object's kernel's arguments starting from the index idx. More...
 
template<unsigned int dimension_size>
void add_tensor_argument (unsigned &idx, const ICLTensor *tensor, const Window &window)
 
- Public Member Functions inherited from IKernel
 IKernel ()
 Constructor. More...
 
virtual ~IKernel ()=default
 Destructor. More...
 
virtual bool is_parallelisable () const
 Indicates whether or not the kernel is parallelisable. More...
 
virtual BorderSize border_size () const
 The size of the border for that kernel. More...
 
const Windowwindow () const
 The maximum window the kernel can be executed on. More...
 

Static Public Member Functions

static Status validate (const ITensorInfo *input, const ITensorInfo *output, const PaddingList &padding=PaddingList(), Window *output_window=nullptr)
 Static function to check if given info will lead to a valid configuration of CLCopyKernel. More...
 
- Static Public Member Functions inherited from ICLKernel
static constexpr unsigned int num_arguments_per_1D_array ()
 Returns the number of arguments enqueued per 1D array object. More...
 
static constexpr unsigned int num_arguments_per_1D_tensor ()
 Returns the number of arguments enqueued per 1D tensor object. More...
 
static constexpr unsigned int num_arguments_per_2D_tensor ()
 Returns the number of arguments enqueued per 2D tensor object. More...
 
static constexpr unsigned int num_arguments_per_3D_tensor ()
 Returns the number of arguments enqueued per 3D tensor object. More...
 
static constexpr unsigned int num_arguments_per_4D_tensor ()
 Returns the number of arguments enqueued per 4D tensor object. More...
 
static cl::NDRange gws_from_window (const Window &window)
 Get the global work size given an execution window. More...
 

Detailed Description

OpenCL kernel to perform a copy between two tensors.

Definition at line 35 of file CLCopyKernel.h.

Constructor & Destructor Documentation

◆ CLCopyKernel() [1/3]

Default constructor.

Definition at line 152 of file CLCopyKernel.cpp.

153  : _input(nullptr), _output(nullptr), _output_window(), _has_output_window(false)
154 {
155 }

◆ CLCopyKernel() [2/3]

CLCopyKernel ( const CLCopyKernel )
delete

Prevent instances of this class from being copied (As this class contains pointers).

◆ CLCopyKernel() [3/3]

CLCopyKernel ( CLCopyKernel &&  )
default

Allow instances of this class to be moved.

Member Function Documentation

◆ configure()

void configure ( const ICLTensor input,
ICLTensor output,
const PaddingList padding = PaddingList(),
Window output_window = nullptr 
)

Initialize the kernel's input, output.

Parameters
[in]inputSource tensor. Data types supported: U8/S8/QASYMM8/U16/S16/F16/U32/S32/F32.
[out]outputDestination tensor. Data types supported: same as input.
[in]padding(Optional) Padding to be applied to the input tensor
[in]output_window(Optional) Window to be used in case only copying into part of a tensor. Default is nullptr.

Definition at line 157 of file CLCopyKernel.cpp.

158 {
159  ARM_COMPUTE_ERROR_ON_NULLPTR(input, output);
160  ARM_COMPUTE_ERROR_THROW_ON(validate_arguments(input->info(), output->info(), padding, output_window));
161 
162  _input = input;
163  _output = output;
164 
165  // Create kernel
166  CLBuildOptions build_opts;
167  build_opts.add_option("-DDATA_TYPE=" + get_cl_type_from_data_type(input->info()->data_type()));
168 
169  std::pair<Status, Window> win_config;
170 
171  const unsigned int vec_size_x = 16 / input->info()->element_size();
172 
173  if(padding.empty())
174  {
175  // Configure window
176  win_config = validate_and_configure_window(input->info(), output->info(), output_window);
177 
178  if(output_window != nullptr)
179  {
180  _has_output_window = true;
181  _output_window = Window(*output_window);
182  const int width_x = output_window->num_iterations(0);
183  const bool multi_access_x = width_x >= static_cast<int32_t>(vec_size_x);
184  const bool remainder_x = width_x % vec_size_x > 0;
185 
186  if(multi_access_x)
187  {
188  _output_window.set(Window::DimX, Window::Dimension(output_window->x().start(), ceil_to_multiple(output_window->x().end(), vec_size_x), vec_size_x));
189  win_config.second.set(Window::DimX, Window::Dimension(win_config.second.x().start(), ceil_to_multiple(win_config.second.x().end(), vec_size_x), vec_size_x));
190  }
191 
192  build_opts.add_option_if(multi_access_x, "-DVEC_SIZE=" + support::cpp11::to_string(vec_size_x));
193  build_opts.add_option_if(multi_access_x && remainder_x, "-DLAST_ACCESSED_X=" + support::cpp11::to_string(std::max<int>(width_x - vec_size_x, 0)));
194  }
195  else
196  {
197  build_opts.add_option("-DVEC_SIZE=" + support::cpp11::to_string(vec_size_x));
198  }
199 
200  // Build kernel
201  _kernel = static_cast<cl::Kernel>(CLKernelLibrary::get().create_kernel("copy_tensor", build_opts.options()));
202  }
203  else
204  {
205  build_opts.add_option("-DVEC_SIZE=" + support::cpp11::to_string(vec_size_x));
206 
207  // Add compile time options
208  add_padding_as_build_options(padding, build_opts);
209 
210  // If we are padding in the fourth dimension the kernel needs to know the depth of the
211  // different cubes
212  if(padding.size() == 4)
213  {
214  const size_t depth = input->info()->tensor_shape()[2];
215  build_opts.add_option("-DDEPTH=" + support::cpp11::to_string(depth));
216  }
217 
218  // Build kernel
219  _kernel = static_cast<cl::Kernel>(CLKernelLibrary::get().create_kernel("copy_pad_tensor", build_opts.options()));
220 
221  // Configure window
222  win_config = validate_and_configure_window_with_padding(input->info(), output->info(), padding);
223  }
224 
225  // Validate and set the window
226  ARM_COMPUTE_ERROR_THROW_ON(win_config.first);
227  ICLKernel::configure_internal(win_config.second);
228 }
std::pair< Status, Window > validate_and_configure_window(ITensorInfo *input, ITensorInfo *weights, ITensorInfo *biases, ITensorInfo *output, const PadStrideInfo &conv_info, unsigned int depth_multiplier, const Size2D &dilation)
std::string to_string(T &&value)
Convert integer and float values to string.
static CLKernelLibrary & get()
Access the KernelLibrary singleton.
#define ARM_COMPUTE_ERROR_THROW_ON(status)
Definition: Error.h:327
static constexpr size_t DimX
Alias for dimension 0 also known as X dimension.
Definition: Window.h:43
auto ceil_to_multiple(S value, T divisor) -> decltype(((value+divisor - 1)/divisor) *divisor)
Computes the smallest number larger or equal to value that is a multiple of divisor.
Definition: Utils.h:66
std::string get_cl_type_from_data_type(const DataType &dt)
Translates a tensor data type to the appropriate OpenCL type.
Definition: CLHelpers.cpp:35
virtual ITensorInfo * info() const =0
Interface to be implemented by the child class to return the tensor's metadata.
virtual size_t element_size() const =0
Element size in bytes calculated as data_size() * num_channels()
void set(size_t dimension, const Dimension &dim)
Set the values of a given dimension.
Definition: Window.inl:48
std::unique_ptr< Kernel > create_kernel()
Helper function to create and return a unique_ptr pointed to a CL/GLES kernel object.
Definition: Helpers.h:86
#define ARM_COMPUTE_ERROR_ON_NULLPTR(...)
Definition: Validate.h:161
constexpr bool empty() const
Check if the entire border is zero.
Definition: Types.h:286

References CLBuildOptions::add_option(), CLBuildOptions::add_option_if(), ARM_COMPUTE_ERROR_ON_NULLPTR, ARM_COMPUTE_ERROR_THROW_ON, arm_compute::ceil_to_multiple(), arm_compute::create_kernel(), ITensorInfo::data_type(), Window::DimX, ITensorInfo::element_size(), BorderSize::empty(), Window::Dimension::end(), CLKernelLibrary::get(), arm_compute::get_cl_type_from_data_type(), ITensor::info(), Window::num_iterations(), CLBuildOptions::options(), arm_compute::test::validation::padding, Window::set(), Window::Dimension::start(), ITensorInfo::tensor_shape(), arm_compute::support::cpp11::to_string(), arm_compute::validate_and_configure_window(), and Window::x().

Referenced by CLRNNLayer::configure(), CLPadLayer::configure(), CLGenerateProposalsLayer::configure(), and CLLSTMLayer::configure().

◆ operator=() [1/2]

CLCopyKernel& operator= ( const CLCopyKernel )
delete

Prevent instances of this class from being copied (As this class contains pointers).

◆ operator=() [2/2]

CLCopyKernel& operator= ( CLCopyKernel &&  )
default

Allow instances of this class to be moved.

◆ run()

void run ( const Window window,
cl::CommandQueue &  queue 
)
overridevirtual

Enqueue the OpenCL kernel to process the given window on the passed OpenCL command queue.

Note
The queue is not flushed by this method, and therefore the kernel will not have been executed by the time this method returns.
Parameters
[in]windowRegion on which to execute the kernel. (Must be a valid region of the window returned by window()).
[in,out]queueCommand queue on which to enqueue the kernel.

Implements ICLKernel.

Definition at line 246 of file CLCopyKernel.cpp.

247 {
250 
251  Window slice;
252 
253  if(_has_output_window)
254  {
256  Window out_slice = _output_window.first_slice_window_3D();
257  do
258  {
259  unsigned int idx = 0;
260  add_3D_tensor_argument(idx, _input, slice);
261  add_3D_tensor_argument(idx, _output, out_slice);
262  enqueue(queue, *this, slice);
263  }
264  while(window.slide_window_slice_3D(slice) && _output_window.slide_window_slice_3D(out_slice));
265  }
266  else
267  {
269  slice = collapsed.first_slice_window_3D();
270  do
271  {
272  unsigned int idx = 0;
273  add_3D_tensor_argument(idx, _input, slice);
274  add_3D_tensor_argument(idx, _output, slice);
275  enqueue(queue, *this, slice);
276  }
277  while(collapsed.slide_window_slice_3D(slice));
278  }
279 }
const Window & window() const
The maximum window the kernel can be executed on.
Definition: IKernel.cpp:28
void enqueue(cl::CommandQueue &queue, ICLKernel &kernel, const Window &window, const cl::NDRange &lws_hint=CLKernelLibrary::get().default_ndrange(), bool use_dummy_work_items=false)
Add the kernel to the command queue with the given window.
Definition: ICLKernel.cpp:39
void add_3D_tensor_argument(unsigned int &idx, const ICLTensor *tensor, const Window &window)
Add the passed 3D tensor's parameters to the object's kernel's arguments starting from the index idx.
Definition: ICLKernel.h:158
Window collapse_if_possible(const Window &full_window, size_t first, size_t last, bool *has_collapsed=nullptr) const
Collapse the dimensions between first and last if possible.
Definition: Window.inl:54
bool slide_window_slice_3D(Window &slice) const
Slide the passed 3D window slice.
Definition: Window.h:319
static constexpr size_t DimZ
Alias for dimension 2 also known as Z dimension.
Definition: Window.h:47
Window first_slice_window_3D() const
First 3D slice of the window.
Definition: Window.h:275
#define ARM_COMPUTE_ERROR_ON_INVALID_SUBWINDOW(f, s)
Definition: Validate.h:205
#define ARM_COMPUTE_ERROR_ON_UNCONFIGURED_KERNEL(k)
Definition: Validate.h:940
SimpleTensor< T > slice(const SimpleTensor< T > &src, Coordinates starts, Coordinates ends)

References ICLKernel::add_3D_tensor_argument(), ARM_COMPUTE_ERROR_ON_INVALID_SUBWINDOW, ARM_COMPUTE_ERROR_ON_UNCONFIGURED_KERNEL, Window::collapse_if_possible(), Window::DimZ, arm_compute::enqueue(), Window::first_slice_window_3D(), arm_compute::test::validation::reference::slice(), Window::slide_window_slice_3D(), and IKernel::window().

◆ validate()

Status validate ( const ITensorInfo input,
const ITensorInfo output,
const PaddingList padding = PaddingList(),
Window output_window = nullptr 
)
static

Static function to check if given info will lead to a valid configuration of CLCopyKernel.

Parameters
[in]inputSource tensor info. Data types supported: U8/S8/QASYMM8/U16/S16/F16/U32/S32/F32.
[in]outputDestination tensor info. Data types supported: same as input.
[in]padding(Optional) Padding to be applied to the input tensor
[in]output_window(Optional) Window to be used in case only copying into part of a tensor. Default is nullptr.
Returns
a status

Definition at line 230 of file CLCopyKernel.cpp.

231 {
232  ARM_COMPUTE_RETURN_ON_ERROR(validate_arguments(input, output, padding, output_window));
233 
234  if(padding.empty())
235  {
236  ARM_COMPUTE_RETURN_ON_ERROR(validate_and_configure_window(input->clone().get(), output->clone().get(), output_window).first);
237  }
238  else
239  {
240  ARM_COMPUTE_RETURN_ON_ERROR(validate_and_configure_window_with_padding(input->clone().get(), output->clone().get(), padding).first);
241  }
242 
243  return Status{};
244 }
std::pair< Status, Window > validate_and_configure_window(ITensorInfo *input, ITensorInfo *weights, ITensorInfo *biases, ITensorInfo *output, const PadStrideInfo &conv_info, unsigned int depth_multiplier, const Size2D &dilation)
#define ARM_COMPUTE_RETURN_ON_ERROR(status)
Checks if a status contains an error and returns it.
Definition: Error.h:193
constexpr bool empty() const
Check if the entire border is zero.
Definition: Types.h:286

References ARM_COMPUTE_RETURN_ON_ERROR, ICloneable< T >::clone(), BorderSize::empty(), arm_compute::test::validation::padding, and arm_compute::validate_and_configure_window().

Referenced by CLCopy::validate(), CLPadLayer::validate(), CLGenerateProposalsLayer::validate(), and CLLSTMLayer::validate().


The documentation for this class was generated from the following files: