24.02.1
|
Interface for the pooling layer kernel. More...
#include <ClPool2dKernel.h>
Public Member Functions | |
ClPool2dKernel () | |
ARM_COMPUTE_DISALLOW_COPY_ALLOW_MOVE (ClPool2dKernel) | |
void | configure (const ClCompileContext &compile_context, ITensorInfo *src, ITensorInfo *dst, const PoolingLayerInfo &pool_info, ITensorInfo *indices=nullptr) |
Configure kernel for a given list of arguments. More... | |
void | run_op (ITensorPack &tensors, 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... | |
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... | |
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... | |
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... | |
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 *src, const ITensorInfo *dst, const PoolingLayerInfo &pool_info, const ITensorInfo *indices=nullptr) |
Static function to check if given info will lead to a valid configuration. More... | |
Static Public Member Functions inherited from ICLKernel | |
constexpr static unsigned int | num_arguments_per_3d_tensor_nhw () |
Returns the number of arguments enqueued per NHW 3D Tensor object. More... | |
constexpr static unsigned int | num_arguments_per_4d_tensor_nhwc () |
Returns the number of arguments enqueued per NHWC 4D Tensor object. More... | |
constexpr static unsigned int | num_arguments_per_1D_array () |
Returns the number of arguments enqueued per 1D array object. More... | |
constexpr static unsigned int | num_arguments_per_1D_tensor () |
Returns the number of arguments enqueued per 1D tensor object. More... | |
constexpr static unsigned int | num_arguments_per_2D_tensor () |
Returns the number of arguments enqueued per 2D tensor object. More... | |
constexpr static unsigned int | num_arguments_per_3D_tensor () |
Returns the number of arguments enqueued per 3D tensor object. More... | |
constexpr static 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... | |
Data Fields | |
PoolingLayerInfo | _pool_info {} |
DataLayout | _data_layout {DataLayout::UNKNOWN} |
unsigned int | _num_elems_processed_per_iteration {1} |
Interface for the pooling layer kernel.
Definition at line 38 of file ClPool2dKernel.h.
ClPool2dKernel | ( | ) |
Definition at line 107 of file ClPool2dKernel.cpp.
References arm_compute::POOL.
ARM_COMPUTE_DISALLOW_COPY_ALLOW_MOVE | ( | ClPool2dKernel | ) |
void configure | ( | const ClCompileContext & | compile_context, |
ITensorInfo * | src, | ||
ITensorInfo * | dst, | ||
const PoolingLayerInfo & | pool_info, | ||
ITensorInfo * | indices = nullptr |
||
) |
Configure kernel for a given list of arguments.
[in] | compile_context | The compile context to be used. |
[in] | src | Source tensor info. Data types supported: QASYMM8/QASYMM8_SIGNED/F16/F32. |
[out] | dst | Destination tensor info. Data types supported: same as src . |
[in] | pool_info | Contains pooling operation information described in PoolingLayerInfo. |
[out] | indices | (optional) The indices of the maximal values. Data type supported: U32. |
Definition at line 112 of file ClPool2dKernel.cpp.
References CLBuildOptions::add_option(), CLBuildOptions::add_option_if(), arm_compute::adjust_vec_size(), ARM_COMPUTE_ERROR, ARM_COMPUTE_ERROR_ON, ARM_COMPUTE_ERROR_ON_NULLPTR, ARM_COMPUTE_ERROR_THROW_ON, arm_compute::auto_init_if_empty(), arm_compute::BATCHES, arm_compute::calculate_max_window(), arm_compute::CHANNEL, arm_compute::misc::shape_calculator::compute_pool_shape(), arm_compute::create_kernel(), PoolingLayerInfo::data_layout, arm_compute::test::validation::data_type, arm_compute::test::validation::dst, PoolingLayerInfo::exclude_padding, arm_compute::F16, arm_compute::F32, arm_compute::float_to_string_with_full_precision(), PoolingLayerInfo::fp_mixed_precision, arm_compute::get_cl_type_from_data_type(), arm_compute::get_data_layout_dimension_index(), arm_compute::get_min_max(), arm_compute::get_padding_info(), arm_compute::has_padding_changed(), Size2D::height, arm_compute::HEIGHT, arm_compute::test::validation::idx_height, arm_compute::test::validation::idx_width, arm_compute::is_data_type_float(), arm_compute::is_data_type_quantized(), arm_compute::is_data_type_quantized_asymmetric(), PoolingLayerInfo::is_global_pooling, kernel_name, arm_compute::lower_string(), arm_compute::support::cpp11::lowest(), arm_compute::MAX, arm_compute::NCHW, arm_compute::NHWC, UniformQuantizationInfo::offset, CLBuildOptions::options(), PadStrideInfo::pad_left(), PoolingLayerInfo::pad_stride_info, PadStrideInfo::pad_top(), PoolingLayerInfo::pool_size, PoolingLayerInfo::pool_type, arm_compute::S32, UniformQuantizationInfo::scale, arm_compute::test::validation::src, PadStrideInfo::stride(), arm_compute::string_from_data_layout(), arm_compute::string_from_data_type(), arm_compute::string_from_pooling_type(), arm_compute::support::cpp11::to_string(), arm_compute::U32, arm_compute::UNKNOWN, PoolingLayerInfo::use_inf_as_limit, arm_compute::cpu::kernels::validate_arguments(), Size2D::width, and arm_compute::WIDTH.
|
overridevirtual |
Enqueue the OpenCL kernel to process the given window on the passed OpenCL command queue.
[in] | tensors | A vector containing the tensors to operato on. |
[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 330 of file ClPool2dKernel.cpp.
References arm_compute::ACL_DST_0, arm_compute::ACL_DST_1, arm_compute::ACL_SRC, ARM_COMPUTE_ERROR, ARM_COMPUTE_ERROR_ON_INVALID_SUBWINDOW, ARM_COMPUTE_ERROR_ON_UNCONFIGURED_KERNEL, Window::collapse_if_possible(), Window::DimX, Window::DimY, Window::DimZ, arm_compute::test::validation::dst, arm_compute::enqueue(), Window::first_slice_window_3D(), Window::first_slice_window_4D(), ITensorPack::get_const_tensor(), ITensorPack::get_tensor(), arm_compute::is_data_type_float(), arm_compute::MAX, arm_compute::NCHW, arm_compute::NHWC, Window::set(), arm_compute::test::validation::reference::slice(), Window::slide_window_slice_3D(), Window::slide_window_slice_4D(), arm_compute::test::validation::src, and IKernel::window().
|
static |
Static function to check if given info will lead to a valid configuration.
Similar to ClPool2dKernel::configure()
Definition at line 321 of file ClPool2dKernel.cpp.
References ARM_COMPUTE_RETURN_ON_ERROR, arm_compute::test::validation::dst, arm_compute::test::validation::src, and arm_compute::cpu::kernels::validate_arguments().
Referenced by ClPool2d::validate().
DataLayout _data_layout {DataLayout::UNKNOWN} |
Definition at line 74 of file ClPool2dKernel.h.
unsigned int _num_elems_processed_per_iteration {1} |
Definition at line 75 of file ClPool2dKernel.h.
PoolingLayerInfo _pool_info {} |
Definition at line 73 of file ClPool2dKernel.h.