Compute Library
 21.02
CLPadLayerKernel Class Reference

Interface for the PadLayer function. More...

#include <CLPadLayerKernel.h>

Collaboration diagram for CLPadLayerKernel:
[legend]

Public Member Functions

 CLPadLayerKernel ()
 Default constructor. More...
 
 CLPadLayerKernel (const CLPadLayerKernel &)=delete
 Prevent instances of this class from being copied (As this class contains pointers) More...
 
CLPadLayerKerneloperator= (const CLPadLayerKernel &)=delete
 Prevent instances of this class from being copied (As this class contains pointers) More...
 
 CLPadLayerKernel (CLPadLayerKernel &&)=default
 Allow instances of this class to be moved. More...
 
CLPadLayerKerneloperator= (CLPadLayerKernel &&)=default
 Allow instances of this class to be moved. More...
 
 ~CLPadLayerKernel ()=default
 Default destructor. More...
 
void configure (const ICLTensor *input, ICLTensor *output, const PaddingList &padding, PixelValue constant_value=PixelValue(), PaddingMode mode=PaddingMode::CONSTANT)
 Set the input and output tensor. More...
 
void configure (const CLCompileContext &compile_context, const ICLTensor *input, ICLTensor *output, const PaddingList &padding, PixelValue constant_value=PixelValue(), PaddingMode mode=PaddingMode::CONSTANT)
 Set the input and output tensor. 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...
 
virtual void run_op (ITensorPack &tensors, const Window &window, cl::CommandQueue &queue)
 Enqueue the OpenCL kernel to process the given window on the passed OpenCL command queue. 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...
 
void set_wbsm_hint (const cl_int &wbsm_hint)
 Set the workgroup batch size modifier hint. More...
 
cl_int wbsm_hint () const
 Return the workgroup batch size modifier 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<unsigned int dimension_size>
void add_tensor_argument (unsigned &idx, const ICLTensor *tensor, const Window &window)
 
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...
 
- 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, PixelValue constant_value=PixelValue(), PaddingMode mode=PaddingMode::CONSTANT)
 Static function to check if given info will lead to a valid configuration of CLPadLayerKernel. 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

Interface for the PadLayer function.

Definition at line 34 of file CLPadLayerKernel.h.

Constructor & Destructor Documentation

◆ CLPadLayerKernel() [1/3]

Default constructor.

Definition at line 67 of file CLPadLayerKernel.cpp.

68  : _input(nullptr), _output(nullptr), _4d_enabled(false)
69 {
70 }

◆ CLPadLayerKernel() [2/3]

CLPadLayerKernel ( const CLPadLayerKernel )
delete

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

◆ CLPadLayerKernel() [3/3]

Allow instances of this class to be moved.

◆ ~CLPadLayerKernel()

~CLPadLayerKernel ( )
default

Default destructor.

Member Function Documentation

◆ configure() [1/2]

void configure ( const ICLTensor input,
ICLTensor output,
const PaddingList padding,
PixelValue  constant_value = PixelValue(),
PaddingMode  mode = PaddingMode::CONSTANT 
)

Set the input and output tensor.

Parameters
[in]inputSource tensor. Data types supported: All.
[out]outputOutput tensor. Data type supported: same as input
[in]paddingThe padding for each spatial dimension of the input tensor. The pair padding[i] specifies the front and the end padding in the i-th dimension.
[in]constant_value(Optional) Constant value to be used for the padding.
[in]mode(Optional) Controls whether the padding should be filled with constant_value using CONSTANT, or reflect the input, either including the border values (SYMMETRIC) or not (REFLECT).

Definition at line 72 of file CLPadLayerKernel.cpp.

References CLKernelLibrary::get().

73 {
74  configure(CLKernelLibrary::get().get_compile_context(), input, output, padding, constant_value, mode);
75 }
static CLKernelLibrary & get()
Access the KernelLibrary singleton.
void configure(const ICLTensor *input, ICLTensor *output, const PaddingList &padding, PixelValue constant_value=PixelValue(), PaddingMode mode=PaddingMode::CONSTANT)
Set the input and output tensor.

◆ configure() [2/2]

void configure ( const CLCompileContext compile_context,
const ICLTensor input,
ICLTensor output,
const PaddingList padding,
PixelValue  constant_value = PixelValue(),
PaddingMode  mode = PaddingMode::CONSTANT 
)

Set the input and output tensor.

Parameters
[in]compile_contextThe compile context to be used.
[in]inputSource tensor. Data types supported: All.
[out]outputOutput tensor. Data type supported: same as input
[in]paddingThe padding for each spatial dimension of the input tensor. The pair padding[i] specifies the front and the end padding in the i-th dimension.
[in]constant_value(Optional) Constant value to be used for the padding.
[in]mode(Optional) Controls whether the padding should be filled with constant_value using CONSTANT, or reflect the input, either including the border values (SYMMETRIC) or not (REFLECT).

Definition at line 77 of file CLPadLayerKernel.cpp.

References CLBuildOptions::add_option(), arm_compute::adjust_vec_size(), ARM_COMPUTE_ERROR, ARM_COMPUTE_ERROR_ON, ARM_COMPUTE_ERROR_ON_NULLPTR, ARM_COMPUTE_ERROR_THROW_ON, arm_compute::auto_init_if_empty(), arm_compute::calculate_max_window(), arm_compute::ceil_to_multiple(), ICloneable< T >::clone(), arm_compute::misc::shape_calculator::compute_padded_shape(), arm_compute::CONSTANT, arm_compute::create_kernel(), arm_compute::test::validation::data_type, ITensorInfo::data_type(), ITensorInfo::dimension(), arm_compute::element_size_from_data_type(), arm_compute::get_cl_type_from_data_type(), arm_compute::get_padding_info(), arm_compute::has_padding_changed(), ITensor::info(), arm_compute::test::validation::input, input_depth, input_height, input_width, kernel_name, clang_tidy_rules::mode, arm_compute::REFLECT, arm_compute::string_from_pixel_value(), arm_compute::SYMMETRIC, ITensorInfo::tensor_shape(), arm_compute::support::cpp11::to_string(), arm_compute::U, and arm_compute::validate_arguments().

78 {
80  auto_init_if_empty(*output->info(), input->info()->clone()->set_tensor_shape(misc::shape_calculator::compute_padded_shape(input->info()->tensor_shape(), padding)));
81  ARM_COMPUTE_ERROR_THROW_ON(validate_arguments(input->info(), output->info(), padding, constant_value, mode));
82 
83  auto padding_info = get_padding_info({ input, output });
84 
85  _input = input;
86  _output = output;
87  _4d_enabled = (mode == PaddingMode::CONSTANT) && (padding.size() > 3);
88 
89  // Set build options
90  const DataType &data_type = input->info()->data_type();
91  const unsigned int input_width = input->info()->dimension(0);
92  const unsigned int input_height = input->info()->dimension(1);
93  const unsigned int input_depth = input->info()->dimension(2);
94  const unsigned int pad_x_before = padding.at(0).first;
95  const unsigned int pad_y_before = padding.size() > 1 ? padding.at(1).first : 0;
96  const unsigned int pad_z_before = padding.size() > 2 ? padding.at(2).first : 0;
97  const unsigned int vec_size = adjust_vec_size(std::min(16U, 32U / static_cast<unsigned int>(element_size_from_data_type(input->info()->data_type()))), input_width);
98  const unsigned int pad_right_start = input_width + pad_x_before;
99  const unsigned int pad_x_before_remainder = pad_x_before % vec_size;
100  const unsigned int vec_size_leftover_write = vec_size - (ceil_to_multiple(output->info()->dimension(0), vec_size) - output->info()->dimension(0));
101 
102  CLBuildOptions build_opts;
103  build_opts.add_option("-DDATA_TYPE=" + get_cl_type_from_data_type(data_type));
104  build_opts.add_option("-DVEC_SIZE=" + support::cpp11::to_string(vec_size));
105  build_opts.add_option("-DPAD_X_BEFORE=" + support::cpp11::to_string(pad_x_before));
106  build_opts.add_option("-DSRC_WIDTH=" + support::cpp11::to_string(input_width));
107  build_opts.add_option("-DPAD_X_BEFORE_REMAINDER=" + support::cpp11::to_string(pad_x_before_remainder));
108  build_opts.add_option("-DVEC_SIZE_LEFTOVER_WRITE=" + support::cpp11::to_string(vec_size_leftover_write));
109  if(padding.size() > 1)
110  {
111  build_opts.add_option("-DPAD_Y_BEFORE=" + support::cpp11::to_string(pad_y_before));
112  build_opts.add_option("-DSRC_HEIGHT=" + support::cpp11::to_string(input_height));
113 
114  if(padding.size() > 2)
115  {
116  build_opts.add_option("-DPAD_Z_BEFORE=" + support::cpp11::to_string(pad_z_before));
117  build_opts.add_option("-DSRC_DEPTH=" + support::cpp11::to_string(input_depth));
118  }
119  }
120 
121  std::string kernel_name = "pad_layer_";
122  switch(mode)
123  {
125  {
126  kernel_name += "constant";
127 
128  const unsigned int vec_size_leftover_read = vec_size - (ceil_to_multiple(pad_right_start, vec_size) - pad_right_start);
129 
130  build_opts.add_option("-DCONST_VAL=" + string_from_pixel_value(constant_value, data_type));
131  build_opts.add_option("-DVEC_SIZE_LEFTOVER_READ=" + support::cpp11::to_string(vec_size_leftover_read));
132 
133  if(pad_x_before >= vec_size)
134  {
135  build_opts.add_option("-DTHREADS_TO_SKIP_BEFORE=" + support::cpp11::to_string(pad_x_before / vec_size));
136  build_opts.add_option("-DTHREADS_TO_SKIP_AFTER=" + support::cpp11::to_string(pad_right_start / vec_size));
137  }
138  if(_4d_enabled)
139  {
140  build_opts.add_option("-DPAD_W_BEFORE=" + support::cpp11::to_string(padding.at(3).first));
141  build_opts.add_option("-DSRC_BATCH=" + support::cpp11::to_string(input->info()->dimension(3)));
142  }
143 
144  break;
145  }
148  {
149  kernel_name += "symmetric_reflect";
150 
151  const auto is_reflect = static_cast<unsigned int>(mode == PaddingMode::REFLECT);
152 
153  const unsigned int pad_x_after_remainder = pad_right_start % vec_size;
154  const unsigned int after_pad_fact_x = (2 * input_width + pad_x_before) - is_reflect;
155  const unsigned int output_last_x = ceil_to_multiple(pad_right_start + padding.at(0).second, vec_size);
156 
157  build_opts.add_option("-DIS_REFLECT=" + support::cpp11::to_string(is_reflect));
158  build_opts.add_option("-DPAD_X_AFTER_REMAINDER=" + support::cpp11::to_string(pad_x_after_remainder));
159  build_opts.add_option("-DPAD_X_BEFORE_REMAINDER_REFL=" + support::cpp11::to_string((pad_x_before_remainder + is_reflect) % vec_size));
160  build_opts.add_option("-DPAD_X_AFTER_REMAINDER_REFL=" + support::cpp11::to_string((pad_x_after_remainder - is_reflect) % vec_size));
161  build_opts.add_option("-DAFTER_PAD_FACT_X=" + support::cpp11::to_string(after_pad_fact_x));
162  build_opts.add_option_if(after_pad_fact_x < output_last_x, "-DAFTER_PAD_REM=" + support::cpp11::to_string(after_pad_fact_x % vec_size));
163 
164  break;
165  }
166  default:
167  ARM_COMPUTE_ERROR("Padding mode not supported.");
168  }
169 
170  // Create kernel
171  _kernel = create_kernel(compile_context, kernel_name, build_opts.options());
172 
173  // Configure window
174  Window win = calculate_max_window(*output->info(), Steps(vec_size));
175  ICLKernel::configure_internal(win);
176 
178 }
Window calculate_max_window(const ValidRegion &valid_region, const Steps &steps, bool skip_border, BorderSize border_size)
#define ARM_COMPUTE_ERROR(msg)
Print the given message then throw an std::runtime_error.
Definition: Error.h:352
std::string to_string(T &&value)
Convert integer and float values to string.
size_t element_size_from_data_type(DataType dt)
The size in bytes of the data type.
Definition: Utils.h:185
std::string string_from_pixel_value(const PixelValue &value, const DataType data_type)
Convert a PixelValue to a string, represented through the specific data type.
Definition: Utils.cpp:273
#define ARM_COMPUTE_ERROR_ON(cond)
If the condition is true then an error message is printed and an exception thrown.
Definition: Error.h:466
#define ARM_COMPUTE_ERROR_THROW_ON(status)
Definition: Error.h:455
const DataType data_type
Definition: Im2Col.cpp:150
cl::Kernel create_kernel(const CLCompileContext &ctx, const std::string &kernel_name, const std::set< std::string > &build_opts=std::set< std::string >())
Creates an opencl kernel using a compile context.
Definition: CLHelpers.cpp:403
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:71
std::string kernel_name
std::string get_cl_type_from_data_type(const DataType &dt)
Translates a tensor data type to the appropriate OpenCL type.
Definition: CLHelpers.cpp: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...
TensorShape compute_padded_shape(const TensorShape &input_shape, const PaddingList &padding)
Calculate the padded shape of a tensor.
bool has_padding_changed(const std::unordered_map< const ITensorInfo *, PaddingSize > &padding_map)
Check if the previously stored padding info has changed after configuring a kernel.
Definition: Utils.cpp:528
std::unordered_map< const ITensorInfo *, PaddingSize > get_padding_info(std::initializer_list< const ITensorInfo *> infos)
Stores padding information before configuring a kernel.
Definition: Utils.cpp:513
Status validate_arguments(const ITensorInfo *input, const ITensorInfo *bias, const ITensorInfo *output, const GEMMLowpOutputStageInfo *output_stage)
#define ARM_COMPUTE_ERROR_ON_NULLPTR(...)
Definition: Validate.h:161
unsigned int adjust_vec_size(unsigned int vec_size, size_t dim0)
Returns the adjusted vector size in case it is less than the input&#39;s first dimension, getting rounded down to its closest valid vector size.
Definition: Utils.h:1358
DataType
Available data types.
Definition: Types.h:77

◆ operator=() [1/2]

CLPadLayerKernel& operator= ( const CLPadLayerKernel )
delete

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

◆ operator=() [2/2]

CLPadLayerKernel& operator= ( CLPadLayerKernel &&  )
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.

Reimplemented from ICLKernel.

Definition at line 186 of file CLPadLayerKernel.cpp.

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

187 {
190 
192  unsigned int batch = 0;
193  do
194  {
195  unsigned int idx = 0;
196  add_3D_tensor_argument(idx, _input, slice);
197  add_3D_tensor_argument(idx, _output, slice);
198  if(_4d_enabled)
199  {
200  add_argument<unsigned int>(idx, batch++);
201  }
202 
203  enqueue(queue, *this, slice, lws_hint());
204  }
205  while(window.slide_window_slice_3D(slice));
206 }
const Window & window() const
The maximum window the kernel can be executed on.
Definition: IKernel.cpp:28
void enqueue(IGCKernel &kernel, const Window &window, const gles::NDRange &lws=gles::NDRange(1U, 1U, 1U))
Add the kernel to the command queue with the given window.
Definition: IGCKernel.cpp:41
cl::NDRange lws_hint() const
Return the Local-Workgroup-Size hint.
Definition: ICLKernel.h:276
void add_3D_tensor_argument(unsigned int &idx, const ICLTensor *tensor, const Window &window)
Add the passed 3D tensor&#39;s parameters to the object&#39;s kernel&#39;s arguments starting from the index idx...
Definition: ICLKernel.h:172
bool slide_window_slice_3D(Window &slice) const
Slide the passed 3D window slice.
Definition: Window.h:335
#define ARM_COMPUTE_ERROR_ON_UNCONFIGURED_KERNEL(k)
Definition: Validate.h:941
Window first_slice_window_3D() const
First 3D slice of the window.
Definition: Window.h:291
#define ARM_COMPUTE_ERROR_ON_INVALID_SUBWINDOW(f, s)
Definition: Validate.h:205
SimpleTensor< T > slice(const SimpleTensor< T > &src, Coordinates starts, Coordinates ends)

◆ validate()

Status validate ( const ITensorInfo input,
const ITensorInfo output,
const PaddingList padding,
PixelValue  constant_value = PixelValue(),
PaddingMode  mode = PaddingMode::CONSTANT 
)
static

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

Parameters
[in]inputSource tensor info. Data types supported: All.
[in]outputOutput tensor info. Data type supported: same as input
[in]paddingThe padding for each spatial dimension of the input tensor. The pair padding[i] specifies the front and the end padding in the i-th dimension.
[in]constant_value(Optional) Constant value to be used for the padding.
[in]mode(Optional) Controls whether the padding should be filled with constant_value using CONSTANT, or reflect the input, either including the border values (SYMMETRIC) or not (REFLECT).

Definition at line 180 of file CLPadLayerKernel.cpp.

References ARM_COMPUTE_RETURN_ON_ERROR, and arm_compute::validate_arguments().

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

181 {
182  ARM_COMPUTE_RETURN_ON_ERROR(validate_arguments(input, output, padding, constant_value, mode));
183  return Status{};
184 }
#define ARM_COMPUTE_RETURN_ON_ERROR(status)
Checks if a status contains an error and returns it.
Definition: Error.h:204
Status validate_arguments(const ITensorInfo *input, const ITensorInfo *bias, const ITensorInfo *output, const GEMMLowpOutputStageInfo *output_stage)

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