24.02.1
|
Interface for the direct convolution 3d kernel. More...
#include <ClDirectConv3dKernel.h>
Public Member Functions | |
ClDirectConv3dKernel () | |
Construtor. More... | |
ClDirectConv3dKernel (const ClDirectConv3dKernel &)=delete | |
Prevent instances of this class from being copied (As this class contains pointers) More... | |
ClDirectConv3dKernel & | operator= (const ClDirectConv3dKernel &)=delete |
Prevent instances of this class from being copied (As this class contains pointers) More... | |
ClDirectConv3dKernel (ClDirectConv3dKernel &&)=default | |
Default move constructor. More... | |
ClDirectConv3dKernel & | operator= (ClDirectConv3dKernel &&)=default |
Default move assignment operator. More... | |
void | configure (const CLCompileContext &compile_context, const ITensorInfo *src0, const ITensorInfo *src1, const ITensorInfo *src2, ITensorInfo *dst, const Conv3dInfo &conv3d_info) |
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 *src0, const ITensorInfo *src1, const ITensorInfo *src2, const ITensorInfo *dst, const Conv3dInfo &conv3d_info) |
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 3d kernel.
Definition at line 39 of file ClDirectConv3dKernel.h.
Construtor.
Definition at line 102 of file ClDirectConv3dKernel.cpp.
References arm_compute::DIRECT.
|
delete |
Prevent instances of this class from being copied (As this class contains pointers)
|
default |
Default move constructor.
void configure | ( | const CLCompileContext & | compile_context, |
const ITensorInfo * | src0, | ||
const ITensorInfo * | src1, | ||
const ITensorInfo * | src2, | ||
ITensorInfo * | dst, | ||
const Conv3dInfo & | conv3d_info | ||
) |
Set the src, weights, biases and dst tensors info.
Valid data layouts:
Valid data type configurations:
src0 | src1 | src2 | dst |
---|---|---|---|
F16 | F16 | F16 | F16 |
F32 | F32 | F32 | F32 |
QASYMM8 | QASYMM8 | S32 | QASYMM8 |
QASYMM8_SIGNED | QASYMM8_SIGNED | S32 | QASYMM8_SIGNED |
[in] | compile_context | The compile context to be used. |
[in] | src0 | Source tensor. 4 lower dimensions represent a single src [IFM, width, height, depth], while every optional dimension from 5 and above represent a batch of srcs. |
[in] | src1 | Weights tensor. Weights are 5D tensor with dimensions [OFM, IFM, kernel_w, kernel_h, kernel_d]. |
[in] | src2 | Biases tensor. Shared biases supported. Biases are 1D tensor with dimensions [OFM]. |
[out] | dst | Destination tensor. 4 lower dimensions represent a single dst [OFM, width, height, depth], while the rest represent batch of dsts. |
[in] | conv3d_info | Contains strides, padding, rounding, activation, dilation and fast math information. Activation and fast math are currently unused. |
Definition at line 107 of file ClDirectConv3dKernel.cpp.
References arm_compute::adjust_vec_size(), ARM_COMPUTE_ERROR_ON_NULLPTR, ARM_COMPUTE_ERROR_THROW_ON, build_options, arm_compute::calculate_max_window(), arm_compute::quantization::calculate_quantized_multiplier(), arm_compute::create_kernel(), arm_compute::test::validation::data_type, ITensorInfo::data_type(), ITensorInfo::dimension(), arm_compute::test::validation::dst, arm_compute::F32, Padding3D::front, PixelValue::get(), arm_compute::get_cl_type_from_data_type(), arm_compute::is_data_type_quantized(), kernel_name, Padding3D::left, arm_compute::lower_string(), UniformQuantizationInfo::offset, Conv3dInfo::padding, ITensorInfo::quantization_info(), arm_compute::S32, UniformQuantizationInfo::scale, Conv3dInfo::stride, arm_compute::string_from_data_type(), arm_compute::support::cpp11::to_string(), Padding3D::top, arm_compute::utils::cast::U, QuantizationInfo::uniform(), arm_compute::cpu::kernels::validate_arguments(), Size3D::x(), Size3D::y(), and Size3D::z().
|
default |
Default move assignment operator.
|
delete |
Prevent instances of this class from being copied (As this class contains pointers)
|
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 248 of file ClDirectConv3dKernel.cpp.
References arm_compute::ACL_DST, arm_compute::ACL_SRC_0, arm_compute::ACL_SRC_1, arm_compute::ACL_SRC_2, ICLKernel::add_1D_tensor_argument(), ICLKernel::add_4D_tensor_argument(), ARM_COMPUTE_ERROR_ON_INVALID_SUBWINDOW, ARM_COMPUTE_ERROR_ON_UNCONFIGURED_KERNEL, arm_compute::ceil_to_multiple(), Window::DimY, Window::DimZ, arm_compute::test::validation::dst, arm_compute::enqueue(), Window::first_slice_window_3D(), ITensorPack::get_const_tensor(), ITensorPack::get_tensor(), ICLKernel::lws_hint(), arm_compute::test::validation::reference::slice(), arm_compute::test::validation::src, and IKernel::window().
|
static |
Static function to check if given info will lead to a valid configuration.
Similar to ClDirectConv3dKernel::configure()
Definition at line 238 of file ClDirectConv3dKernel.cpp.
References ARM_COMPUTE_RETURN_ON_ERROR, arm_compute::test::validation::dst, and arm_compute::cpu::kernels::validate_arguments().
Referenced by ClDirectConv3d::validate().