Compute Library
 22.05
CLTileKernel Class Reference

OpenCL kernel to perform a Tile operation. More...

#include <CLTileKernel.h>

Collaboration diagram for CLTileKernel:
[legend]

Public Member Functions

 CLTileKernel ()
 Default constructor. More...
 
 CLTileKernel (const CLTileKernel &)=delete
 Prevent instances of this class from being copied (As this class contains pointers) More...
 
CLTileKerneloperator= (const CLTileKernel &)=delete
 Prevent instances of this class from being copied (As this class contains pointers) More...
 
 CLTileKernel (CLTileKernel &&)=default
 Allow instances of this class to be moved. More...
 
CLTileKerneloperator= (CLTileKernel &&)=default
 Allow instances of this class to be moved. More...
 
 ~CLTileKernel ()=default
 Default destructor. More...
 
void configure (const ICLTensor *input, ICLTensor *output, const Multiples &multiples)
 Set the source, destination of the kernel. More...
 
void configure (const CLCompileContext &compile_context, const ICLTensor *input, ICLTensor *output, const Multiples &multiples)
 Set the source, destination of the kernel. 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...
 
CLKernelType type () const
 Returns the CL kernel type. 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...
 
void add_5D_tensor_argument (unsigned int &idx, const ICLTensor *tensor, const Window &window)
 Add the passed 5D tensor's parameters to the object's kernel's arguments starting from the index idx. More...
 
void add_3d_tensor_nhw_argument (unsigned int &idx, const ICLTensor *tensor)
 Add the passed NHW 3D tensor's parameters to the object's kernel's arguments by passing strides, dimensions and the offset to the first valid element in bytes. More...
 
void add_4d_tensor_nhwc_argument (unsigned int &idx, const ICLTensor *tensor)
 Add the passed NHWC 4D tensor's parameters to the object's kernel's arguments by passing strides, dimensions and the offset to the first valid element in bytes. 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...
 
virtual void run_composite_op (ITensorPack &tensors, const Window &window, cl::CommandQueue &queue, const experimental::dynamic_fusion::ClExecutionDescriptor &exec_desc)
 The execution is carried out through run_op method. But the run_op method needs to be extended to include ClExecutionDescriptor as now LWS GWS tuning will be separated from the IKernel. 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...
 
bool is_window_configured () const
 Function to check if the embedded window of this kernel has been configured. More...
 

Static Public Member Functions

static Status validate (const ITensorInfo *input, const ITensorInfo *output, const Multiples &multiples)
 Static function to check if given info will lead to a valid configuration of CLTileKernel. More...
 
- Static Public Member Functions inherited from ICLKernel
static constexpr unsigned int num_arguments_per_3d_tensor_nhw ()
 Returns the number of arguments enqueued per NHW 3D Tensor object. More...
 
static constexpr unsigned int num_arguments_per_4d_tensor_nhwc ()
 Returns the number of arguments enqueued per NHWC 4D Tensor object. More...
 
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 Tile operation.

Definition at line 34 of file CLTileKernel.h.

Constructor & Destructor Documentation

◆ CLTileKernel() [1/3]

Default constructor.

Definition at line 57 of file CLTileKernel.cpp.

References arm_compute::ELEMENTWISE.

58  : _input(nullptr), _output(nullptr)
59 {
61 }
Elementeise CL kernel type.
Definition: CLTypes.h:84

◆ CLTileKernel() [2/3]

CLTileKernel ( const CLTileKernel )
delete

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

◆ CLTileKernel() [3/3]

CLTileKernel ( CLTileKernel &&  )
default

Allow instances of this class to be moved.

◆ ~CLTileKernel()

~CLTileKernel ( )
default

Default destructor.

Member Function Documentation

◆ configure() [1/2]

void configure ( const ICLTensor input,
ICLTensor output,
const Multiples multiples 
)

Set the source, destination of the kernel.

Parameters
[in]inputSource tensor. Data type supported: All.
[in]multiplesContains the number of times the input tensor should be replicated on the given dimension. Cannot have more than 4 elements (tiling in dimensions greater than 4 is not supported).
[out]outputDestination tensor. Same as input

Definition at line 63 of file CLTileKernel.cpp.

References CLKernelLibrary::get().

64 {
65  configure(CLKernelLibrary::get().get_compile_context(), input, output, multiples);
66 }
static CLKernelLibrary & get()
Access the KernelLibrary singleton.
void configure(const ICLTensor *input, ICLTensor *output, const Multiples &multiples)
Set the source, destination of the kernel.

◆ configure() [2/2]

void configure ( const CLCompileContext compile_context,
const ICLTensor input,
ICLTensor output,
const Multiples multiples 
)

Set the source, destination of the kernel.

Parameters
[in]compile_contextThe compile context to be used.
[in]inputSource tensor. Data type supported: All.
[in]multiplesContains the number of times the input tensor should be replicated on the given dimension. Cannot have more than 4 elements (tiling in dimensions greater than 4 is not supported).
[out]outputDestination tensor. Same as input

Definition at line 68 of file CLTileKernel.cpp.

References CLBuildOptions::add_option(), CLBuildOptions::add_option_if(), 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(), arm_compute::misc::shape_calculator::compute_tiled_shape(), arm_compute::create_kernel(), arm_compute::data_size_from_type(), arm_compute::test::validation::data_type, ITensorInfo::data_type(), ITensorInfo::dimension(), Window::DimX, ITensorInfo::element_size(), arm_compute::get_cl_unsigned_type_from_element_size(), ITensor::info(), arm_compute::test::validation::input, arm_compute::lower_string(), offset(), CLBuildOptions::options(), arm_compute::string_from_data_type(), ITensorInfo::tensor_shape(), arm_compute::support::cpp11::to_string(), arm_compute::cpu::kernels::validate_arguments(), and Dimensions< T >::x().

69 {
71 
72  // Auto initialize output
73  TensorShape tiled_shape = misc::shape_calculator::compute_tiled_shape(input->info()->tensor_shape(), multiples);
74  auto_init_if_empty(*output->info(), tiled_shape, 1, input->info()->data_type());
75 
76  // Validate
77  ARM_COMPUTE_ERROR_THROW_ON(validate_arguments(input->info(), output->info(), multiples));
78 
79  _input = input;
80  _output = output;
81 
82  const DataType data_type = input->info()->data_type();
83  const int vec_size_x = 16 / input->info()->element_size();
84  const int input_width_x = input->info()->tensor_shape().x();
85  const unsigned int offset = ceil_to_multiple(input_width_x, vec_size_x) - input_width_x;
86  const bool multi_access_x = (input_width_x / vec_size_x > 0);
87 
88  // Create kernel
89  CLBuildOptions build_opts;
90  build_opts.add_option("-DDATA_TYPE=" + get_cl_unsigned_type_from_element_size(data_size_from_type(data_type)));
91  build_opts.add_option("-DSRC_WIDTH=" + support::cpp11::to_string(input_width_x));
92  build_opts.add_option("-DSRC_HEIGHT=" + support::cpp11::to_string(input->info()->dimension(1)));
93  build_opts.add_option("-DSRC_DEPTH=" + support::cpp11::to_string(input->info()->dimension(2)));
94  build_opts.add_option("-DSRC_BATCHES=" + support::cpp11::to_string(input->info()->dimension(3)));
95  build_opts.add_option("-DDST_DEPTH=" + support::cpp11::to_string(output->info()->dimension(2)));
96  build_opts.add_option_if(multi_access_x, "-DOFFSET=" + support::cpp11::to_string(offset));
97  build_opts.add_option_if(multi_access_x, "-DVEC_SIZE=" + support::cpp11::to_string(vec_size_x));
98  _kernel = create_kernel(compile_context, "tile", build_opts.options());
99 
100  // Configure window without padding
101  Window win = calculate_max_window(*output->info());
102 
103  if(multi_access_x)
104  {
105  // If multi-access is enabled, no thread should cross the tile boundaries. This means we need
106  // as many threads as those to cover a single tile times multiples[0]. Note that if threads
107  // do not cross the boundaries of the tiles, they won't cross the boundaries of the last tile, and
108  // we don't need to pad the output
109  const unsigned int size_win_x = ceil_to_multiple(input->info()->dimension(0), vec_size_x) * multiples[0];
110  win.set(Window::DimX,
111  Window::Dimension(win.x().start(), size_win_x, vec_size_x));
112  }
113 
114  ICLKernel::configure_internal(win);
115 
116  // Set config_id for enabling LWS tuning
117  _config_id = "tile";
118  _config_id += "_";
119  _config_id += lower_string(string_from_data_type(input->info()->data_type()));
120  for(unsigned int i = 0; i < multiples.size(); ++i)
121  {
122  _config_id += "_";
123  _config_id += support::cpp11::to_string(input->info()->dimension(i));
124  _config_id += "_";
125  _config_id += support::cpp11::to_string(multiples[i]);
126  }
127 }
__global uchar * offset(const Image *img, int x, int y)
Get the pointer position of a Image.
Definition: helpers.h:1083
Window calculate_max_window(const ValidRegion &valid_region, const Steps &steps, bool skip_border, BorderSize border_size)
std::string to_string(T &&value)
Convert integer and float values to string.
#define ARM_COMPUTE_ERROR_THROW_ON(status)
Definition: Error.h:455
std::string lower_string(const std::string &val)
Lower a given string.
Definition: Utils.cpp:351
Status validate_arguments(const ITensorInfo *src, const ITensorInfo *weights, const ITensorInfo *dst, const PadStrideInfo &conv_info)
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:391
const std::string & string_from_data_type(DataType dt)
Convert a data type identity into a string.
Definition: Utils.cpp:135
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:71
TensorShape compute_tiled_shape(const TensorShape &input_shape, const Multiples &multiples)
Calculate the tiled shape of a tensor.
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...
size_t data_size_from_type(DataType data_type)
The size in bytes of the data type.
Definition: Utils.h:106
std::string get_cl_unsigned_type_from_element_size(size_t element_size)
Translates the element size to an unsigned integer data type.
Definition: CLHelpers.cpp:105
#define ARM_COMPUTE_ERROR_ON_NULLPTR(...)
Definition: Validate.h:157
DataType
Available data types.
Definition: Types.h:79

◆ operator=() [1/2]

CLTileKernel& operator= ( const CLTileKernel )
delete

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

◆ operator=() [2/2]

CLTileKernel& operator= ( CLTileKernel &&  )
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 135 of file CLTileKernel.cpp.

References ICLKernel::add_4D_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_4D(), ICLKernel::lws_hint(), arm_compute::test::validation::reference::slice(), Window::slide_window_slice_4D(), and IKernel::window().

136 {
139 
141  Window slice = collapsed.first_slice_window_4D();
142 
143  do
144  {
145  unsigned int idx = 0;
146  add_4D_tensor_argument(idx, _input, slice);
147  add_4D_tensor_argument(idx, _output, slice);
148  enqueue(queue, *this, slice, lws_hint());
149  }
150  while(collapsed.slide_window_slice_4D(slice));
151 }
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:32
cl::NDRange lws_hint() const
Return the Local-Workgroup-Size hint.
Definition: ICLKernel.h:384
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:68
#define ARM_COMPUTE_ERROR_ON_UNCONFIGURED_KERNEL(k)
Definition: Validate.h:915
static constexpr size_t DimZ
Alias for dimension 2 also known as Z dimension.
Definition: Window.h:47
void add_4D_tensor_argument(unsigned int &idx, const ICLTensor *tensor, const Window &window)
Add the passed 4D tensor&#39;s parameters to the object&#39;s kernel&#39;s arguments starting from the index idx...
Definition: ICLKernel.h:237
#define ARM_COMPUTE_ERROR_ON_INVALID_SUBWINDOW(f, s)
Definition: Validate.h:201
SimpleTensor< T > slice(const SimpleTensor< T > &src, Coordinates starts, Coordinates ends)

◆ validate()

Status validate ( const ITensorInfo input,
const ITensorInfo output,
const Multiples multiples 
)
static

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

Parameters
[in]inputSource tensor info. Data type supported: All.
[in]multiplesContains the number of times the input tensor should be replicated on the given dimension. Cannot have more than 4 elements (tiling in dimensions greater than 4 is not supported).
[in]outputDestination tensor info. Same as input
Returns
a status

Definition at line 129 of file CLTileKernel.cpp.

References ARM_COMPUTE_RETURN_ON_ERROR, and arm_compute::cpu::kernels::validate_arguments().

Referenced by CLTile::validate().

130 {
132  return Status{};
133 }
#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 *src, const ITensorInfo *weights, const ITensorInfo *dst, const PadStrideInfo &conv_info)

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