21.02
|
Interface for the channel combine kernel. More...
#include <CLChannelCombineKernel.h>
Public Member Functions | |
CLChannelCombineKernel () | |
Default constructor. More... | |
CLChannelCombineKernel (const CLChannelCombineKernel &)=delete | |
Prevent instances of this class from being copied (As this class contains pointers) More... | |
CLChannelCombineKernel & | operator= (const CLChannelCombineKernel &)=delete |
Prevent instances of this class from being copied (As this class contains pointers) More... | |
CLChannelCombineKernel (CLChannelCombineKernel &&)=default | |
Allow instances of this class to be moved. More... | |
CLChannelCombineKernel & | operator= (CLChannelCombineKernel &&)=default |
Allow instances of this class to be moved. More... | |
~CLChannelCombineKernel ()=default | |
Default destructor. More... | |
void | configure (const ICLTensor *plane0, const ICLTensor *plane1, const ICLTensor *plane2, const ICLTensor *plane3, ICLTensor *output) |
Configure function's inputs and outputs. More... | |
void | configure (const CLCompileContext &compile_context, const ICLTensor *plane0, const ICLTensor *plane1, const ICLTensor *plane2, const ICLTensor *plane3, ICLTensor *output) |
Configure function's inputs and outputs. More... | |
void | configure (const ICLImage *plane0, const ICLImage *plane1, const ICLImage *plane2, ICLMultiImage *output) |
Configure function's inputs and outputs. More... | |
void | configure (const CLCompileContext &compile_context, const ICLImage *plane0, const ICLImage *plane1, const ICLImage *plane2, ICLMultiImage *output) |
Configure function's inputs and outputs. 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 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... | |
Interface for the channel combine kernel.
Definition at line 39 of file CLChannelCombineKernel.h.
Default constructor.
Definition at line 47 of file CLChannelCombineKernel.cpp.
|
delete |
Prevent instances of this class from being copied (As this class contains pointers)
|
default |
Allow instances of this class to be moved.
|
default |
Default destructor.
void configure | ( | const ICLTensor * | plane0, |
const ICLTensor * | plane1, | ||
const ICLTensor * | plane2, | ||
const ICLTensor * | plane3, | ||
ICLTensor * | output | ||
) |
Configure function's inputs and outputs.
[in] | plane0 | The 2D plane that forms channel 0. Must be of U8 format. |
[in] | plane1 | The 2D plane that forms channel 1. Must be of U8 format. |
[in] | plane2 | The 2D plane that forms channel 2. Must be of U8 format. |
[in] | plane3 | The 2D plane that forms channel 3. Must be of U8 format. |
[out] | output | The single planar output tensor. Supported formats: RGB888/RGBA8888/YUYV422/UYVY422. |
Definition at line 52 of file CLChannelCombineKernel.cpp.
References CLKernelLibrary::get().
Referenced by CLChannelCombineKernel::configure().
void configure | ( | const CLCompileContext & | compile_context, |
const ICLTensor * | plane0, | ||
const ICLTensor * | plane1, | ||
const ICLTensor * | plane2, | ||
const ICLTensor * | plane3, | ||
ICLTensor * | output | ||
) |
Configure function's inputs and outputs.
[in] | compile_context | The compile context to be used. |
[in] | plane0 | The 2D plane that forms channel 0. Must be of U8 format. |
[in] | plane1 | The 2D plane that forms channel 1. Must be of U8 format. |
[in] | plane2 | The 2D plane that forms channel 2. Must be of U8 format. |
[in] | plane3 | The 2D plane that forms channel 3. Must be of U8 format. |
[out] | output | The single planar output tensor. |
Definition at line 57 of file CLChannelCombineKernel.cpp.
References ValidRegion::anchor, ARM_COMPUTE_ERROR_ON_DATA_TYPE_CHANNEL_NOT_IN, ARM_COMPUTE_ERROR_ON_FORMAT_NOT_IN, ARM_COMPUTE_ERROR_ON_NULLPTR, ARM_COMPUTE_ERROR_ON_TENSOR_NOT_2D, ARM_COMPUTE_ERROR_ON_TENSORS_NOT_EVEN, ARM_COMPUTE_ERROR_ON_TENSORS_NOT_SUBSAMPLED, arm_compute::calculate_max_window(), arm_compute::create_kernel(), ITensorInfo::format(), ITensor::info(), arm_compute::intersect_valid_regions(), kernel_name, num_elems_processed_per_iteration, arm_compute::RGB888, arm_compute::RGBA8888, arm_compute::string_from_format(), ITensorInfo::tensor_shape(), arm_compute::U8, arm_compute::update_window_and_padding(), arm_compute::UYVY422, arm_compute::test::validation::valid_region, ITensorInfo::valid_region(), and arm_compute::YUYV422.
void configure | ( | const ICLImage * | plane0, |
const ICLImage * | plane1, | ||
const ICLImage * | plane2, | ||
ICLMultiImage * | output | ||
) |
Configure function's inputs and outputs.
[in] | plane0 | The 2D plane that forms channel 0. Must be of U8 format. |
[in] | plane1 | The 2D plane that forms channel 1. Must be of U8 format. |
[in] | plane2 | The 2D plane that forms channel 2. Must be of U8 format. |
[out] | output | The multi planar output tensor. Supported formats: RGB888/RGBA8888/YUYV422/UYVY422. |
Definition at line 140 of file CLChannelCombineKernel.cpp.
References CLChannelCombineKernel::configure(), and CLKernelLibrary::get().
void configure | ( | const CLCompileContext & | compile_context, |
const ICLImage * | plane0, | ||
const ICLImage * | plane1, | ||
const ICLImage * | plane2, | ||
ICLMultiImage * | output | ||
) |
Configure function's inputs and outputs.
[in] | compile_context | The compile context to be used. |
[in] | plane0 | The 2D plane that forms channel 0. Must be of U8 format. |
[in] | plane1 | The 2D plane that forms channel 1. Must be of U8 format. |
[in] | plane2 | The 2D plane that forms channel 2. Must be of U8 format. |
[out] | output | The multi planar output tensor. Supported formats: RGB888/RGBA8888/YUYV422/UYVY422. |
Definition at line 145 of file CLChannelCombineKernel.cpp.
References ValidRegion::anchor, ARM_COMPUTE_ERROR_ON_DATA_TYPE_CHANNEL_NOT_IN, ARM_COMPUTE_ERROR_ON_FORMAT_NOT_IN, ARM_COMPUTE_ERROR_ON_NULLPTR, ARM_COMPUTE_ERROR_ON_TENSOR_NOT_2D, ARM_COMPUTE_ERROR_ON_TENSORS_NOT_EVEN, ARM_COMPUTE_ERROR_ON_TENSORS_NOT_SUBSAMPLED, arm_compute::calculate_max_window(), arm_compute::create_kernel(), MultiImageInfo::format(), IMultiImage::info(), ITensor::info(), arm_compute::intersect_valid_regions(), arm_compute::IYUV, kernel_name, num_elems_processed_per_iteration, arm_compute::NV12, arm_compute::NV21, ICLMultiImage::plane(), ITensorInfo::tensor_shape(), arm_compute::U8, arm_compute::update_window_and_padding(), ITensorInfo::valid_region(), and arm_compute::YUV444.
|
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 247 of file CLChannelCombineKernel.cpp.
References ICLKernel::add_2D_tensor_argument(), ICLKernel::add_2D_tensor_argument_if(), ARM_COMPUTE_ERROR_ON_INVALID_SUBWINDOW, ARM_COMPUTE_ERROR_ON_UNCONFIGURED_KERNEL, ICLMultiImage::cl_plane(), Window::DimX, Window::DimY, Window::Dimension::end(), arm_compute::enqueue(), Window::first_slice_window_2D(), MultiImageInfo::format(), IMultiImage::info(), ICLKernel::lws_hint(), arm_compute::num_planes_from_format(), Window::set(), Window::set_dimension_step(), arm_compute::test::validation::reference::slice(), Window::slide_window_slice_2D(), Window::Dimension::start(), Window::Dimension::step(), IKernel::window(), Window::x(), and Window::y().