Compute Library
 21.02
CLWinogradFilterTransformKernel Class Reference

Interface for the Winograd filter transform kernel. More...

#include <CLWinogradFilterTransformKernel.h>

Collaboration diagram for CLWinogradFilterTransformKernel:
[legend]

Public Member Functions

 CLWinogradFilterTransformKernel ()
 Default constructor. More...
 
 CLWinogradFilterTransformKernel (const CLWinogradFilterTransformKernel &)=delete
 Prevent instances of this class from being copied (As this class contains pointers) More...
 
CLWinogradFilterTransformKerneloperator= (const CLWinogradFilterTransformKernel &)=delete
 Prevent instances of this class from being copied (As this class contains pointers) More...
 
 CLWinogradFilterTransformKernel (CLWinogradFilterTransformKernel &&)=default
 Allow instances of this class to be moved. More...
 
CLWinogradFilterTransformKerneloperator= (CLWinogradFilterTransformKernel &&)=default
 Allow instances of this class to be moved. More...
 
 ~CLWinogradFilterTransformKernel ()=default
 Default destructor. More...
 
void configure (const ICLTensor *input, ICLTensor *output, const WinogradInfo &winograd_info)
 Set the input and output tensor. More...
 
void configure (const CLCompileContext &compile_context, const ICLTensor *input, ICLTensor *output, const WinogradInfo &winograd_info)
 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 WinogradInfo &winograd_info)
 Static function to check if given info will lead to a valid configuration of CLWinogradFilterTransformKernel. 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 Winograd filter transform kernel.

Definition at line 34 of file CLWinogradFilterTransformKernel.h.

Constructor & Destructor Documentation

◆ CLWinogradFilterTransformKernel() [1/3]

Default constructor.

Definition at line 92 of file CLWinogradFilterTransformKernel.cpp.

93  : _input(nullptr), _output(nullptr)
94 {
95 }

◆ CLWinogradFilterTransformKernel() [2/3]

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

◆ CLWinogradFilterTransformKernel() [3/3]

Allow instances of this class to be moved.

◆ ~CLWinogradFilterTransformKernel()

Default destructor.

Member Function Documentation

◆ configure() [1/2]

void configure ( const ICLTensor input,
ICLTensor output,
const WinogradInfo winograd_info 
)

Set the input and output tensor.

Note
Winograd filter transform supports the following configurations for NCWH data layout F(output tile, kernel size):F(2x2, 3x3), F(2x1, 3x1), F(1x2, 1x3), F(4x4, 3x3), F(4x1, 3x1), F(1x4, 1x3), F(4x4, 5x5), F(4x1, 5x1), F(1x4, 1x5)
Winograd filter transform supports the following configurations for NHWC data layout F(output tile, kernel size):F(4x4, 3x3), F(4x1, 3x1), F(1x4, 1x3), F(4x4, 5x5), F(4x1, 5x1), F(1x4, 1x5)

Strides: only unit strides

Parameters
[in]inputSource tensor. The input is a 4D tensor with dimensions [kernel_x, kernel_y, IFM, OFM] (NCHW data layout) or [IFM, kernel_x, kernel_y, OFM] (NHWC data layout). Data types supported: F16/F32.
[out]outputThe output tensor. The shape for this tensor can be calculated using the utility function compute_winograd_filter_transform_shape. Data types supported: Same as input
[in]winograd_infoContains Winograd's information described in WinogradInfo

Definition at line 97 of file CLWinogradFilterTransformKernel.cpp.

References CLKernelLibrary::get().

98 {
99  configure(CLKernelLibrary::get().get_compile_context(), input, output, winograd_info);
100 }
static CLKernelLibrary & get()
Access the KernelLibrary singleton.
void configure(const ICLTensor *input, ICLTensor *output, const WinogradInfo &winograd_info)
Set the input and output tensor.

◆ configure() [2/2]

void configure ( const CLCompileContext compile_context,
const ICLTensor input,
ICLTensor output,
const WinogradInfo winograd_info 
)

Set the input and output tensor.

Note
Winograd filter transform supports the following configurations for NCWH data layout F(output tile, kernel size):F(2x2, 3x3), F(2x1, 3x1), F(1x2, 1x3), F(4x4, 3x3), F(4x1, 3x1), F(1x4, 1x3), F(4x4, 5x5), F(4x1, 5x1), F(1x4, 1x5)
Winograd filter transform supports the following configurations for NHWC data layout F(output tile, kernel size):F(4x4, 3x3), F(4x1, 3x1), F(1x4, 1x3), F(4x4, 5x5), F(4x1, 5x1), F(1x4, 1x5)

Strides: only unit strides

Parameters
[in]compile_contextThe compile context to be used.
[in]inputSource tensor. The input is a 4D tensor with dimensions [kernel_x, kernel_y, IFM, OFM] (NCHW data layout) or [IFM, kernel_x, kernel_y, OFM] (NHWC data layout). Data types supported: F16/F32.
[out]outputThe output tensor. The shape for this tensor can be calculated using the utility function compute_winograd_filter_transform_shape. Data types supported: Same as input
[in]winograd_infoContains Winograd's information described in WinogradInfo

Definition at line 102 of file CLWinogradFilterTransformKernel.cpp.

References CLBuildOptions::add_option(), ARM_COMPUTE_ERROR_ON, ARM_COMPUTE_ERROR_ON_NULLPTR, ARM_COMPUTE_ERROR_THROW_ON, arm_compute::auto_init_if_empty(), ICloneable< T >::clone(), arm_compute::misc::shape_calculator::compute_winograd_filter_transform_shape(), arm_compute::create_kernel(), ITensorInfo::data_layout(), ITensorInfo::data_type(), ITensorInfo::dimension(), arm_compute::get_cl_type_from_data_type(), arm_compute::get_padding_info(), arm_compute::has_padding_changed(), Size2D::height, ITensor::info(), arm_compute::test::validation::input, kernel_name, WinogradInfo::kernel_size, arm_compute::lower_string(), WinogradInfo::output_tile_size, arm_compute::string_from_data_layout(), Size2D::to_string(), arm_compute::support::cpp11::to_string(), arm_compute::validate_arguments(), Size2D::width, and arm_compute::test::validation::winograd_info.

103 {
105 
106  // Output auto initialization if not yet initialized
107  auto_init_if_empty(*output->info(), input->info()->clone()->set_tensor_shape(compute_winograd_filter_transform_shape(*input->info(), winograd_info)));
108 
110  auto padding_info = get_padding_info({ input, output });
111 
112  // Set build options
113  CLBuildOptions build_opts;
114  build_opts.add_option("-DSRC_DIM_Z=" + support::cpp11::to_string(input->info()->dimension(2)));
115  build_opts.add_option("-DDATA_TYPE=" + get_cl_type_from_data_type(input->info()->data_type()));
116  build_opts.add_option_if(winograd_info.kernel_size.height == 1, "-DWINOGRAD_FILTER_TRANSFORM_HORIZONTAL");
117  build_opts.add_option_if(winograd_info.kernel_size.width == 1, "-DWINOGRAD_FILTER_TRANSFORM_VERTICAL");
118  const Size2D kernel_size = winograd_info.kernel_size;
119  const Size2D output_tile_size = winograd_info.output_tile_size;
120 
121  // Create kernel
122  std::string kernel_name = "winograd_filter_transform_" + output_tile_size.to_string() + "_" + kernel_size.to_string() + "_" + lower_string(string_from_data_layout(input->info()->data_layout()));
123  _kernel = create_kernel(compile_context, kernel_name, build_opts.options());
124 
125  _input = input;
126  _output = output;
127 
128  // Configure kernel window
129  auto win_config = validate_and_configure_window(input->info(), output->info());
130  ARM_COMPUTE_ERROR_THROW_ON(win_config.first);
131  ICLKernel::configure_internal(win_config.second);
133 }
std::string to_string(T &&value)
Convert integer and float values to string.
#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
std::string lower_string(const std::string &val)
Lower a given string.
Definition: Utils.cpp:350
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
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_winograd_filter_transform_shape(const ITensorInfo &input, const WinogradInfo &winograd_info)
Calculate the winograd filter transform shape.
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
const std::string & string_from_data_layout(DataLayout dl)
Convert a data layout identity into a string.
Definition: Utils.cpp:123
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

◆ operator=() [1/2]

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

◆ operator=() [2/2]

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 143 of file CLWinogradFilterTransformKernel.cpp.

References ICLKernel::add_3D_tensor_argument(), ICLKernel::add_4D_tensor_argument(), ARM_COMPUTE_ERROR_ON_INVALID_SUBWINDOW, ARM_COMPUTE_ERROR_ON_UNCONFIGURED_KERNEL, arm_compute::enqueue(), ITensor::info(), ICLKernel::lws_hint(), ITensorInfo::tensor_shape(), Window::use_tensor_dimensions(), and IKernel::window().

144 {
147 
148  // Setup output window
149  Window window_out;
150  window_out.use_tensor_dimensions(_output->info()->tensor_shape(), 0);
151 
152  unsigned int idx = 0;
153  add_4D_tensor_argument(idx, _input, window);
154  add_3D_tensor_argument(idx, _output, window_out);
155  enqueue(queue, *this, window, lws_hint());
156 }
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
virtual const TensorShape & tensor_shape() const =0
Size for each dimension of the tensor.
virtual ITensorInfo * info() const =0
Interface to be implemented by the child class to return the tensor&#39;s metadata.
#define ARM_COMPUTE_ERROR_ON_UNCONFIGURED_KERNEL(k)
Definition: Validate.h:941
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:182
#define ARM_COMPUTE_ERROR_ON_INVALID_SUBWINDOW(f, s)
Definition: Validate.h:205

◆ validate()

Status validate ( const ITensorInfo input,
const ITensorInfo output,
const WinogradInfo winograd_info 
)
static

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

Note
Winograd filter transform supports the following configurations for NCWH data layout F(output tile, kernel size):F(2x2, 3x3), F(2x1, 3x1), F(1x2, 1x3), F(4x4, 3x3), F(4x1, 3x1), F(1x4, 1x3), F(4x4, 5x5), F(4x1, 5x1), F(1x4, 1x5)
Winograd filter transform supports the following configurations for NHWC data layout F(output tile, kernel size):F(4x4, 3x3), F(4x1, 3x1), F(1x4, 1x3), F(4x4, 5x5), F(4x1, 5x1), F(1x4, 1x5)

Strides: only unit strides

Parameters
[in]inputSource tensor. The input is a 4D tensor with dimensions [kernel_x, kernel_y, IFM, OFM] (NCHW data layout) or [IFM, kernel_x, kernel_y, OFM] (NHWC data layout). Data types supported: F16/F32.
[out]outputThe output tensor. The shape for this tensor can be calculated using the utility function compute_winograd_filter_transform_shape. Data types supported: Same as input
[in]winograd_infoContains Winograd's information described in WinogradInfo
Returns
a status

Definition at line 135 of file CLWinogradFilterTransformKernel.cpp.

References ARM_COMPUTE_RETURN_ON_ERROR, ICloneable< T >::clone(), and arm_compute::validate_arguments().

Referenced by CLWinogradConvolutionLayer::validate().

136 {
138  ARM_COMPUTE_RETURN_ON_ERROR(validate_and_configure_window(input->clone().get(), output->clone().get()).first);
139 
140  return Status{};
141 }
#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: