Compute Library
 22.05
CLDeconvolutionReshapeOutputKernel Class Reference

Interface for the OpenCL kernel to be used for reshaping the tensor before returning the result of deconvolution. More...

#include <CLDeconvolutionReshapeOutputKernel.h>

Collaboration diagram for CLDeconvolutionReshapeOutputKernel:
[legend]

Public Member Functions

 CLDeconvolutionReshapeOutputKernel ()
 Default constructor. More...
 
 CLDeconvolutionReshapeOutputKernel (const CLDeconvolutionReshapeOutputKernel &)=delete
 Prevent instances of this class from being copied (As this class contains pointers) More...
 
CLDeconvolutionReshapeOutputKerneloperator= (const CLDeconvolutionReshapeOutputKernel &)=delete
 Prevent instances of this class from being copied (As this class contains pointers) More...
 
 CLDeconvolutionReshapeOutputKernel (CLDeconvolutionReshapeOutputKernel &&)=default
 Allow instances of this class to be moved. More...
 
CLDeconvolutionReshapeOutputKerneloperator= (CLDeconvolutionReshapeOutputKernel &&)=default
 Allow instances of this class to be moved. More...
 
 ~CLDeconvolutionReshapeOutputKernel ()=default
 Default destructor. More...
 
void configure (const ICLTensor *input, const ICLTensor *bias, ICLTensor *output, const ITensorInfo *input_info, const ITensorInfo *weights_info, const PadStrideInfo &deconv_info)
 Initialise the kernel's source and destination. More...
 
void configure (const CLCompileContext &compile_context, const ICLTensor *input, const ICLTensor *bias, ICLTensor *output, const ITensorInfo *input_info, const ITensorInfo *weights_info, const PadStrideInfo &deconv_info)
 Initialise the kernel's source and destination. 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 ICLSimpleKernel
 ICLSimpleKernel ()
 Constructor. More...
 
 ICLSimpleKernel (const ICLSimpleKernel &)=delete
 Prevent instances of this class from being copied (As this class contains pointers) More...
 
ICLSimpleKerneloperator= (const ICLSimpleKernel &)=delete
 Prevent instances of this class from being copied (As this class contains pointers) More...
 
 ICLSimpleKernel (ICLSimpleKernel &&)=default
 Allow instances of this class to be moved. More...
 
ICLSimpleKerneloperator= (ICLSimpleKernel &&)=default
 Allow instances of this class to be moved. More...
 
 ~ICLSimpleKernel ()=default
 Default destructor. More...
 
void configure (const ICLTensor *input, ICLTensor *output, unsigned int num_elems_processed_per_iteration, bool border_undefined=false, const BorderSize &border_size=BorderSize())
 Configure the kernel. 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 *bias, const ITensorInfo *output, const ITensorInfo *input_info, const ITensorInfo *weights_info, const PadStrideInfo &deconv_info)
 Static function to check if given info will lead to a valid configuration of CLDeconvolutionReshapeOutputKernel. 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

Interface for the OpenCL kernel to be used for reshaping the tensor before returning the result of deconvolution.

The input tensor to this OpenCL kernel is expected to be the result of a CLGEMM operation between the Deconvolution input and the Deconvolution filter.

The input tensor should have the following shape: [filter_width * filter_height * ofms, width, height, batch_size]

The output tensor should have the following shape: [stride_x * (input_width - 1) + filter_width - 2 * padx, stride_y * (input_height - 1) + filter_height - 2 * pady, ofms, batch_size]

For example, given a tensor with dimensions [4, 2, 2] this function returns a tensor with dimensions [1, 4, 4].

Definition at line 44 of file CLDeconvolutionReshapeOutputKernel.h.

Constructor & Destructor Documentation

◆ CLDeconvolutionReshapeOutputKernel() [1/3]

Default constructor.

Definition at line 112 of file CLDeconvolutionReshapeOutputKernel.cpp.

References arm_compute::ELEMENTWISE.

113  : _add_bias(false),
114  _bias(nullptr)
115 {
117 }
Elementeise CL kernel type.
Definition: CLTypes.h:84

◆ CLDeconvolutionReshapeOutputKernel() [2/3]

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

◆ CLDeconvolutionReshapeOutputKernel() [3/3]

Allow instances of this class to be moved.

◆ ~CLDeconvolutionReshapeOutputKernel()

Default destructor.

Member Function Documentation

◆ configure() [1/2]

void configure ( const ICLTensor input,
const ICLTensor bias,
ICLTensor output,
const ITensorInfo input_info,
const ITensorInfo weights_info,
const PadStrideInfo deconv_info 
)

Initialise the kernel's source and destination.

Parameters
[in]inputInput tensor. Supported data types: QASYMM8/QASYMM8_SIGNED/S32/F16/F32.
[in]biasBias tensor to be added directly during the reshape operation. Supported data types: same as input. Supported data layouts: same as input.
[out]outputOutput tensor with the following shape: [stride_x * (input_width - 1) + filter_width - 2 * padx, stride_y * (input_height - 1) + filter_height - 2 * pady, ofms, batch_size] Supported data types: same as input. Supported data layouts: same as input.
[in]input_infoDeconvolution input tensor info. Supported data types: same as input. Supported data layouts: same as input.
[in]weights_infoDeconvolution weights tensor info. Supported data types: same as input. Supported data layouts: same as input.
[in]deconv_infoContains padding and policies to be used in the deconvolution, this is described in PadStrideInfo. This kernel supports only stride_x = weights.width && stride_y = weights.height. Moreover, padding is not supported.

Definition at line 119 of file CLDeconvolutionReshapeOutputKernel.cpp.

References CLKernelLibrary::get().

121 {
122  configure(CLKernelLibrary::get().get_compile_context(), input, bias, output, input_info, weights_info, deconv_info);
123 }
static CLKernelLibrary & get()
Access the KernelLibrary singleton.
void configure(const ICLTensor *input, const ICLTensor *bias, ICLTensor *output, const ITensorInfo *input_info, const ITensorInfo *weights_info, const PadStrideInfo &deconv_info)
Initialise the kernel&#39;s source and destination.
const int32_t * bias

◆ configure() [2/2]

void configure ( const CLCompileContext compile_context,
const ICLTensor input,
const ICLTensor bias,
ICLTensor output,
const ITensorInfo input_info,
const ITensorInfo weights_info,
const PadStrideInfo deconv_info 
)

Initialise the kernel's source and destination.

Parameters
[in]compile_contextThe compile context to be used.
[in]inputInput tensor. Supported data types: QASYMM8/QASYMM8_SIGNED/S32/F16/F32.
[in]biasBias tensor to be added directly during the reshape operation. Supported data types: same as input. Supported data layouts: same as input.
[out]outputOutput tensor with the following shape: [stride_x * (input_width - 1) + filter_width - 2 * padx, stride_y * (input_height - 1) + filter_height - 2 * pady, ofms, batch_size] Supported data types: same as input. Supported data layouts: same as input.
[in]input_infoDeconvolution input tensor info. Supported data types: same as input. Supported data layouts: same as input.
[in]weights_infoDeconvolution weights tensor info. Supported data types: same as input. Supported data layouts: same as input.
[in]deconv_infoContains padding and policies to be used in the deconvolution, this is described in PadStrideInfo. This kernel supports only stride_x = weights.width && stride_y = weights.height. Moreover, padding is not supported.

Definition at line 125 of file CLDeconvolutionReshapeOutputKernel.cpp.

References CLBuildOptions::add_option(), CLBuildOptions::add_option_if(), ARM_COMPUTE_ERROR_ON, ARM_COMPUTE_ERROR_ON_NULLPTR, ARM_COMPUTE_ERROR_THROW_ON, arm_compute::BATCHES, bias, arm_compute::create_kernel(), ITensorInfo::data_layout(), ITensorInfo::data_type(), ITensorInfo::dimension(), arm_compute::get_cl_type_from_data_type(), arm_compute::get_data_layout_dimension_index(), arm_compute::get_padding_info(), arm_compute::has_padding_changed(), arm_compute::HEIGHT, ITensor::info(), arm_compute::test::validation::input, arm_compute::test::validation::input_info, arm_compute::lower_string(), arm_compute::NCHW, CLBuildOptions::options(), arm_compute::string_from_data_layout(), arm_compute::string_from_data_type(), arm_compute::support::cpp11::to_string(), arm_compute::cpu::kernels::validate_and_configure_window(), arm_compute::cpu::kernels::validate_arguments(), arm_compute::test::validation::weights_info, and arm_compute::WIDTH.

128 {
130  ARM_COMPUTE_ERROR_THROW_ON(validate_arguments(input->info(), (bias != nullptr ? bias->info() : nullptr), output->info(), input_info, weights_info, deconv_info));
131 
132  auto padding_info = get_padding_info({ input, bias, output });
133  // Configure kernel window
134  auto win_config = validate_and_configure_window(input->info(), output->info(), input_info, weights_info, deconv_info);
135  ARM_COMPUTE_ERROR_THROW_ON(win_config.first);
136 
137  const DataLayout data_layout = input_info->data_layout();
138  const size_t idx_w = get_data_layout_dimension_index(data_layout, DataLayoutDimension::WIDTH);
139  const size_t idx_h = get_data_layout_dimension_index(data_layout, DataLayoutDimension::HEIGHT);
140  const size_t idx_b = get_data_layout_dimension_index(data_layout, DataLayoutDimension::BATCHES);
141 
142  _input = input;
143  _output = output;
144  _add_bias = (bias != nullptr);
145  _bias = bias;
146 
147  const int filter_w = weights_info->dimension(idx_w);
148  const int filter_h = weights_info->dimension(idx_h);
149  const int filter_b = weights_info->dimension(idx_b);
150  const int img_w = input_info->dimension(idx_w);
151  const int img_h = input_info->dimension(idx_h);
152 
153  CLBuildOptions build_opts;
154  build_opts.add_option("-DDATA_TYPE=" + get_cl_type_from_data_type(input->info()->data_type()));
155  build_opts.add_option("-DFILTER_WIDTH=" + support::cpp11::to_string(filter_w));
156  build_opts.add_option("-DFILTER_HEIGHT=" + support::cpp11::to_string(filter_h));
157  build_opts.add_option("-DSRC_WIDTH=" + support::cpp11::to_string(img_w));
158  build_opts.add_option("-DSRC_HEIGHT=" + support::cpp11::to_string(img_h));
159  build_opts.add_option_if(data_layout == DataLayout::NCHW, "-DNUM_FILTERS=" + support::cpp11::to_string(filter_b));
160  build_opts.add_option_if(_add_bias, "-DADD_BIAS");
161 
162  _kernel = create_kernel(compile_context, "deconvolution_reshape", build_opts.options());
163  ICLKernel::configure_internal(win_config.second);
164 
165  // Set config_id for enabling LWS tuning
166  _config_id = "deconvolution_reshape_output_";
167  _config_id += lower_string(string_from_data_type(input->info()->data_type()));
168  _config_id += "_";
169  _config_id += lower_string(string_from_data_layout(input->info()->data_layout()));
170  _config_id += "_";
171  _config_id += support::cpp11::to_string(input->info()->dimension(0));
172  _config_id += "_";
173  _config_id += support::cpp11::to_string(input->info()->dimension(1));
174  _config_id += "_";
175  _config_id += support::cpp11::to_string(output->info()->dimension(0));
176  _config_id += "_";
177  _config_id += support::cpp11::to_string(output->info()->dimension(1));
179 }
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: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
std::string get_cl_type_from_data_type(const DataType &dt)
Translates a tensor data type to the appropriate OpenCL type.
Definition: CLHelpers.cpp:39
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:601
Num samples, channels, height, width.
std::pair< Status, Window > validate_and_configure_window(ITensorInfo *src, ITensorInfo *dst)
const std::string & string_from_data_layout(DataLayout dl)
Convert a data layout identity into a string.
Definition: Utils.cpp:123
size_t get_data_layout_dimension_index(const DataLayout &data_layout, const DataLayoutDimension &data_layout_dimension)
Get the index of the given dimension.
Definition: Helpers.inl:193
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:586
#define ARM_COMPUTE_ERROR_ON_NULLPTR(...)
Definition: Validate.h:157
DataLayout
[DataLayout enum definition]
Definition: Types.h:113
const int32_t * bias

◆ 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 188 of file CLDeconvolutionReshapeOutputKernel.cpp.

References ICLKernel::add_1D_tensor_argument(), 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(), ICLKernel::lws_hint(), and IKernel::window().

189 {
193 
194  unsigned int idx = 0;
195  add_3D_tensor_argument(idx, _input, collapsed);
196  add_3D_tensor_argument(idx, _output, collapsed);
197  if(_add_bias)
198  {
199  add_1D_tensor_argument(idx, _bias, collapsed);
200  }
201  enqueue(queue, *this, collapsed, lws_hint());
202 }
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
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:227
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_1D_tensor_argument(unsigned int &idx, const ICLTensor *tensor, const Window &window)
Add the passed 1D tensor&#39;s parameters to the object&#39;s kernel&#39;s arguments starting from the index idx...
Definition: ICLKernel.h:179
#define ARM_COMPUTE_ERROR_ON_INVALID_SUBWINDOW(f, s)
Definition: Validate.h:201

◆ validate()

Status validate ( const ITensorInfo input,
const ITensorInfo bias,
const ITensorInfo output,
const ITensorInfo input_info,
const ITensorInfo weights_info,
const PadStrideInfo deconv_info 
)
static

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

Parameters
[in]inputGEMM output tensor info to be reshaped. Supported data types: QASYMM8/QASYMM8_SIGNED/S32/F16/F32.
[in]bias(Optional) Optional bias tensor info to be added directly during the reshape operation. Supported data types: same as input. Supported data layouts: same as input.
[in]outputReshaped output tensor info. Supported data types: same as input. Supported data layouts: same as input.
[in]input_infoOriginal input tensor info. Supported data types: same as input. Supported data layouts: same as input.
[in]weights_infoOriginal weights tensor info output. Supported data types: same as input. Supported data layouts: same as input.
[in]deconv_infoContains padding and policies to be used in the deconvolution, this is described in PadStrideInfo. This kernel supports only stride_x = weights.width && stride_y = weights.height. Moreover, padding is not supported.
Returns
a Status

Definition at line 181 of file CLDeconvolutionReshapeOutputKernel.cpp.

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

Referenced by CLGEMMDeconvolutionLayer::validate().

183 {
185  return Status{};
186 }
#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)
const int32_t * bias

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