24.02.1
|
Interface for the direct convolution kernel. More...
#include <ClIndirectConv2dAddressPrecalculationKernel.h>
Public Member Functions | |
ClIndirectConv2dAddressPrecalculationKernel () | |
ARM_COMPUTE_DISALLOW_COPY_ALLOW_MOVE (ClIndirectConv2dAddressPrecalculationKernel) | |
void | configure (const CLCompileContext &compile_context, ITensorInfo *src, ITensorInfo *weights, ITensorInfo *dst, const PadStrideInfo &conv_info, const DirectConvComputeKernelInfo &desc) |
Set the src, weights, biases and dst tensors info. 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 *weights, const ITensorInfo *dst, const PadStrideInfo &conv_info, const DirectConvComputeKernelInfo &desc) |
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... | |
Interface for the direct convolution kernel.
Definition at line 41 of file ClIndirectConv2dAddressPrecalculationKernel.h.
Definition at line 77 of file ClIndirectConv2dAddressPrecalculationKernel.cpp.
References arm_compute::ELEMENTWISE.
ARM_COMPUTE_DISALLOW_COPY_ALLOW_MOVE | ( | ClIndirectConv2dAddressPrecalculationKernel | ) |
void configure | ( | const CLCompileContext & | compile_context, |
ITensorInfo * | src, | ||
ITensorInfo * | weights, | ||
ITensorInfo * | dst, | ||
const PadStrideInfo & | conv_info, | ||
const DirectConvComputeKernelInfo & | desc | ||
) |
Set the src, weights, biases and dst tensors info.
[in] | compile_context | The compile context to be used. |
[in] | src | The src tensor info to convolve. 3 lower dimensions represent a single src [IFM, width, height], while every optional dimension from 4 and above represent a batch of inputs. Data types supported: F16/F32. |
[in] | weights | Weights tensor info. Weights are 4D tensor with dimensions [IFM, kernel_x, kernel_y, OFM]. The 1st dimension must be the same as the src's volume 1st dimension. Data type supported:Same as src . |
[out] | dst | Output tensor info where to store the precalculated offsets. Data types supported: S32. The output is a 3D tensor with the following dimensions: [M0 x Kw x Kh, ceil(M/M0), batch-size], where: Kw=Kernel width, Kh=Kernel height, M0=number of rows processed by each workitem, and M=dst_width x dst_height. |
[in] | conv_info | Contains padding and stride information described in PadStrideInfo. |
[in] | desc | Direct convolution descriptor used to build the NHWC direct/indirect convolution kernel. |
Definition at line 82 of file ClIndirectConv2dAddressPrecalculationKernel.cpp.
References ARM_COMPUTE_ERROR_ON_NULLPTR, ARM_COMPUTE_ERROR_THROW_ON, arm_compute::auto_init_if_empty(), build_options, arm_compute::calculate_max_window(), arm_compute::misc::shape_calculator::compute_deep_convolution_shape(), arm_compute::misc::shape_calculator::compute_indirect_buffer_shape(), arm_compute::test::validation::conv_info, arm_compute::create_kernel(), ITensorInfo::dimension(), arm_compute::test::validation::dst, arm_compute::get_cl_type_from_data_type(), arm_compute::cpu::height_idx, kernel_name, DirectConvComputeKernelInfo::m0, arm_compute::test::validation::output_shape, arm_compute::S32, arm_compute::test::validation::src, ITensorInfo::tensor_shape(), arm_compute::support::cpp11::to_string(), arm_compute::upper_string(), arm_compute::cpu::kernels::validate_arguments(), and arm_compute::cpu::width_idx.
|
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 154 of file ClIndirectConv2dAddressPrecalculationKernel.cpp.
References arm_compute::ACL_DST, ICLKernel::add_4d_tensor_nhwc_argument(), ARM_COMPUTE_ERROR_ON_INVALID_SUBWINDOW, ARM_COMPUTE_ERROR_ON_UNCONFIGURED_KERNEL, arm_compute::test::validation::dst, arm_compute::enqueue(), Window::first_slice_window_3D(), ITensorPack::get_tensor(), arm_compute::test::validation::reference::slice(), and IKernel::window().
|
static |
Static function to check if given info will lead to a valid configuration.
Similar to ClIndirectConv2dAddressPreCalculationKernel::configure()
Definition at line 144 of file ClIndirectConv2dAddressPrecalculationKernel.cpp.
References ARM_COMPUTE_RETURN_ON_ERROR, arm_compute::test::validation::conv_info, arm_compute::test::validation::dst, arm_compute::test::validation::src, and arm_compute::cpu::kernels::validate_arguments().