21.02
|
OpenCL kernel to perform a remap on a tensor. More...
#include <CLRemapKernel.h>
Public Member Functions | |
CLRemapKernel () | |
Default constructor. More... | |
CLRemapKernel (const CLRemapKernel &)=delete | |
Prevent instances of this class from being copied (As this class contains pointers) More... | |
CLRemapKernel & | operator= (const CLRemapKernel &)=delete |
Prevent instances of this class from being copied (As this class contains pointers) More... | |
CLRemapKernel (CLRemapKernel &&)=default | |
Allow instances of this class to be moved. More... | |
CLRemapKernel & | operator= (CLRemapKernel &&)=default |
Allow instances of this class to be moved. More... | |
void | configure (const ICLTensor *input, const ICLTensor *map_x, const ICLTensor *map_y, ICLTensor *output, InterpolationPolicy policy, bool border_undefined) |
Initialize the kernel's input, output and border mode. More... | |
void | configure (const CLCompileContext &compile_context, const ICLTensor *input, const ICLTensor *map_x, const ICLTensor *map_y, ICLTensor *output, InterpolationPolicy policy, bool border_undefined) |
Initialize the kernel's input, output and border mode. 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... | |
BorderSize | border_size () const override |
The size of the border for that 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... | |
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... | |
const Window & | window () const |
The maximum window the kernel can be executed on. More... | |
Additional Inherited Members | |
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... | |
OpenCL kernel to perform a remap on a tensor.
Definition at line 35 of file CLRemapKernel.h.
CLRemapKernel | ( | ) |
Default constructor.
Definition at line 39 of file CLRemapKernel.cpp.
|
delete |
Prevent instances of this class from being copied (As this class contains pointers)
|
default |
Allow instances of this class to be moved.
|
overridevirtual |
The size of the border for that kernel.
Reimplemented from IKernel.
Definition at line 44 of file CLRemapKernel.cpp.
Referenced by CLRemapKernel::configure().
void configure | ( | const ICLTensor * | input, |
const ICLTensor * | map_x, | ||
const ICLTensor * | map_y, | ||
ICLTensor * | output, | ||
InterpolationPolicy | policy, | ||
bool | border_undefined | ||
) |
Initialize the kernel's input, output and border mode.
[in] | input | Source tensor. Data types supported: U8. |
[in] | map_x | Map for X coordinates. Data types supported: F32. |
[in] | map_y | Map for Y coordinates. Data types supported: F32. |
[out] | output | Destination tensor. Data types supported: U8. All but the lowest two dimensions must be the same size as in the input tensor, i.e. remapping is only performed within the XY-plane. |
[in] | policy | The interpolation type. |
[in] | border_undefined | True if the border mode is undefined. False if it's replicate or constant. |
Definition at line 49 of file CLRemapKernel.cpp.
References CLKernelLibrary::get().
void configure | ( | const CLCompileContext & | compile_context, |
const ICLTensor * | input, | ||
const ICLTensor * | map_x, | ||
const ICLTensor * | map_y, | ||
ICLTensor * | output, | ||
InterpolationPolicy | policy, | ||
bool | border_undefined | ||
) |
Initialize the kernel's input, output and border mode.
[in] | compile_context | The compile context to be used. |
[in] | input | Source tensor. Data types supported: U8. |
[in] | map_x | Map for X coordinates. Data types supported: F32. |
[in] | map_y | Map for Y coordinates. Data types supported: F32. |
[out] | output | Destination tensor. Data types supported: U8. All but the lowest two dimensions must be the same size as in the input tensor, i.e. remapping is only performed within the XY-plane. |
[in] | policy | The interpolation type. |
[in] | border_undefined | True if the border mode is undefined. False if it's replicate or constant. |
Definition at line 54 of file CLRemapKernel.cpp.
References arm_compute::AREA, ARM_COMPUTE_ERROR_ON_DATA_TYPE_CHANNEL_NOT_IN, ARM_COMPUTE_ERROR_ON_MSG, ARM_COMPUTE_UNUSED, CLRemapKernel::border_size(), BorderSize::bottom, arm_compute::calculate_max_window(), arm_compute::ceil_to_multiple(), arm_compute::create_kernel(), ITensorInfo::data_type(), ITensorInfo::dimension(), arm_compute::F32, arm_compute::get_cl_type_from_data_type(), ITensor::info(), arm_compute::test::validation::input, kernel_name, BorderSize::left, ICLKernel::num_arguments_per_2D_tensor(), num_elems_processed_per_iteration, BorderSize::right, arm_compute::string_from_interpolation_policy(), ITensorInfo::tensor_shape(), arm_compute::utility::tolower(), BorderSize::top, arm_compute::U8, and arm_compute::update_window_and_padding().
|
delete |
Prevent instances of this class from being copied (As this class contains pointers)
|
default |
Allow instances of this class to be moved.
|
overridevirtual |
Enqueue the OpenCL kernel to process the given window on the passed OpenCL command queue.
[in] | window | Region on which to execute the kernel. (Must be a valid region of the window returned by window()). |
[in,out] | queue | Command queue on which to enqueue the kernel. |
Reimplemented from ICLKernel.
Definition at line 99 of file CLRemapKernel.cpp.
References ICLKernel::add_2D_tensor_argument(), ARM_COMPUTE_ERROR_ON_INVALID_SUBWINDOW, ARM_COMPUTE_ERROR_ON_UNCONFIGURED_KERNEL, arm_compute::enqueue(), Window::first_slice_window_2D(), ICLKernel::lws_hint(), arm_compute::test::validation::reference::slice(), Window::slide_window_slice_2D(), and IKernel::window().