23.05
|
Interface for the width concatenate kernel of 4 tensors. More...
#include <ClWidthConcatenate4TensorsKernel.h>
Public Member Functions | |
ClWidthConcatenate4TensorsKernel () | |
ARM_COMPUTE_DISALLOW_COPY_ALLOW_MOVE (ClWidthConcatenate4TensorsKernel) | |
void | configure (const CLCompileContext &compile_context, ITensorInfo *src1, ITensorInfo *src2, ITensorInfo *src3, ITensorInfo *src4, ITensorInfo *dst) |
Initialise the kernel's sources and destination. More... | |
void | run_op (ITensorPack &tensors, const Window &window, ::cl::CommandQueue &queue) override |
![]() | |
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 (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_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... | |
cl::NDRange | get_cached_gws () const |
Get the cached gws used to enqueue this kernel. More... | |
void | cache_gws (const cl::NDRange &gws) |
Cache the latest gws used to enqueue this kernel. 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... | |
![]() | |
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... | |
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 *src1, const ITensorInfo *src2, const ITensorInfo *src3, const ITensorInfo *src4, const ITensorInfo *dst) |
Static function to check if given info will lead to a valid configuration. More... | |
![]() | |
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, bool use_dummy_work_items) |
Get the global work size given an execution window. More... | |
Interface for the width concatenate kernel of 4 tensors.
All source tensors will be concatenated into the destination tensor.
Definition at line 41 of file ClWidthConcatenate4TensorsKernel.h.
Definition at line 67 of file ClWidthConcatenate4TensorsKernel.cpp.
References arm_compute::ELEMENTWISE.
ARM_COMPUTE_DISALLOW_COPY_ALLOW_MOVE | ( | ClWidthConcatenate4TensorsKernel | ) |
void configure | ( | const CLCompileContext & | compile_context, |
ITensorInfo * | src1, | ||
ITensorInfo * | src2, | ||
ITensorInfo * | src3, | ||
ITensorInfo * | src4, | ||
ITensorInfo * | dst | ||
) |
Initialise the kernel's sources and destination.
[in] | compile_context | The compile context to be used. |
[in] | src1 | First source tensor info. Data types supported: All. |
[in] | src2 | Second source tensor info. Data types supported: same as src1 |
[in] | src3 | Third source tensor info. Data types supported: same as src1 |
[in] | src4 | Fourth source tensor info. Data types supported: same as src1 |
[out] | dst | Destination tensor info. Data types supported: same as src1 . |
Definition at line 78 of file ClWidthConcatenate4TensorsKernel.cpp.
References CLBuildOptions::add_option(), arm_compute::adjust_vec_size(), ARM_COMPUTE_ERROR_ON, ARM_COMPUTE_ERROR_ON_NULLPTR, ARM_COMPUTE_ERROR_THROW_ON, arm_compute::calculate_max_window(), arm_compute::create_kernel(), ITensorInfo::data_type(), ITensorInfo::dimension(), Window::DimZ, ITensorInfo::element_size(), arm_compute::float_to_string_with_full_precision(), arm_compute::get_cl_type_from_data_type(), arm_compute::get_padding_info(), arm_compute::has_padding_changed(), arm_compute::is_data_type_quantized_asymmetric(), kernel_name, arm_compute::lower_string(), num_elems_processed_per_iteration, UniformQuantizationInfo::offset, CLBuildOptions::options(), ITensorInfo::quantization_info(), UniformQuantizationInfo::scale, arm_compute::string_from_data_type(), arm_compute::helpers::tensor_info::tensors_have_different_quantization_info(), arm_compute::support::cpp11::to_string(), QuantizationInfo::uniform(), arm_compute::upper_string(), and arm_compute::cpu::kernels::validate_arguments().
|
override |
Definition at line 162 of file ClWidthConcatenate4TensorsKernel.cpp.
References arm_compute::ACL_DST, arm_compute::ACL_SRC_VEC, ICLKernel::add_4D_tensor_argument(), ARM_COMPUTE_ERROR_ON_INVALID_SUBWINDOW, ARM_COMPUTE_ERROR_ON_UNCONFIGURED_KERNEL, arm_compute::enqueue(), Window::first_slice_window_4D(), ITensorPack::get_const_tensor(), ITensorPack::get_tensor(), ICLKernel::lws_hint(), arm_compute::test::validation::reference::slice(), Window::slide_window_slice_4D(), and IKernel::window().
|
static |
Static function to check if given info will lead to a valid configuration.
Similar to ClWidthConcatenate4TensorsKernel::configure()
Definition at line 72 of file ClWidthConcatenate4TensorsKernel.cpp.
References ARM_COMPUTE_RETURN_ON_ERROR, and arm_compute::cpu::kernels::validate_arguments().
Referenced by ClConcatenate::validate().