21.02
|
Interface for calculating the final step of the Softmax Layer where each logit value is multiplied by the inverse of the sum of the logits. More...
#include <CLSoftmaxLayerKernel.h>
Public Member Functions | |
CLLogits1DNormKernel () | |
Default constructor. More... | |
CLLogits1DNormKernel (const CLLogits1DNormKernel &)=delete | |
Prevent instances of this class from being copied (As this class contains pointers) More... | |
CLLogits1DNormKernel & | operator= (const CLLogits1DNormKernel &)=delete |
Prevent instances of this class from being copied (As this class contains pointers) More... | |
CLLogits1DNormKernel (CLLogits1DNormKernel &&)=default | |
Allow instances of this class to be moved. More... | |
CLLogits1DNormKernel & | operator= (CLLogits1DNormKernel &&)=default |
Allow instances of this class to be moved. More... | |
void | configure (const ICLTensor *input, const ICLTensor *sum, ICLTensor *output, const SoftmaxKernelInfo &info) |
Set the input and output tensors. More... | |
void | configure (const CLCompileContext &compile_context, const ICLTensor *input, const ICLTensor *sum, ICLTensor *output, const SoftmaxKernelInfo &info) |
Set the input and output tensors. 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... | |
Static Public Member Functions | |
static Status | validate (const ITensorInfo *input, const ITensorInfo *sum, const ITensorInfo *output, const SoftmaxKernelInfo &info) |
Static function to check if given info will lead to a valid configuration of CLLogits1DNormKernel. More... | |
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 calculating the final step of the Softmax Layer where each logit value is multiplied by the inverse of the sum of the logits.
Definition at line 108 of file CLSoftmaxLayerKernel.h.
Default constructor.
Definition at line 282 of file CLSoftmaxLayerKernel.cpp.
|
delete |
Prevent instances of this class from being copied (As this class contains pointers)
|
default |
Allow instances of this class to be moved.
void configure | ( | const ICLTensor * | input, |
const ICLTensor * | sum, | ||
ICLTensor * | output, | ||
const SoftmaxKernelInfo & | info | ||
) |
Set the input and output tensors.
[in] | input | Source tensor. Data types supported: S32/F16/F32. If this kernel is used for log softmax, only F32/F16 is supported. |
[in] | sum | Sum tensor. Dimensions should be dim(input)-1. Data types supported: same as input |
[out] | output | Destination tensor. Data types supported: QASYMM8/QASYMM8_SIGNED for S32 input , or same as input |
[in] | info | Contains information consumed by kernels for softmax described in SoftmaxKernelInfo. |
Definition at line 287 of file CLSoftmaxLayerKernel.cpp.
References CLKernelLibrary::get().
void configure | ( | const CLCompileContext & | compile_context, |
const ICLTensor * | input, | ||
const ICLTensor * | sum, | ||
ICLTensor * | output, | ||
const SoftmaxKernelInfo & | info | ||
) |
Set the input and output tensors.
[in] | compile_context | The compile context to be used. |
[in] | input | Source tensor. Data types supported: S32/F16/F32. If this kernel is used for log softmax, only F32/F16 is supported. |
[in] | sum | Sum tensor. Dimensions should be dim(input)-1. Data types supported: same as input |
[out] | output | Destination tensor. Data types supported: QASYMM8/QASYMM8_SIGNED for S32 input , or same as input |
[in] | info | Contains information consumed by kernels for softmax described in SoftmaxKernelInfo. |
Definition at line 292 of file CLSoftmaxLayerKernel.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::auto_init_if_empty(), SoftmaxKernelInfo::beta, arm_compute::calculate_max_window(), ICloneable< T >::clone(), arm_compute::create_kernel(), ITensorInfo::dimension(), arm_compute::get_cl_type_from_data_type(), arm_compute::get_padding_info(), arm_compute::get_softmax_output_quantization_info(), arm_compute::has_padding_changed(), ITensor::info(), arm_compute::test::validation::info, arm_compute::test::validation::input, SoftmaxKernelInfo::input_data_type, arm_compute::is_data_type_quantized_asymmetric(), arm_compute::is_data_type_quantized_asymmetric_signed(), SoftmaxKernelInfo::is_log, kernel_name, arm_compute::test::validation::qinfo, ITensorInfo::quantization_info(), UniformQuantizationInfo::scale, sum(), arm_compute::support::cpp11::to_string(), and QuantizationInfo::uniform().
|
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 348 of file CLSoftmaxLayerKernel.cpp.
References ICLKernel::add_3D_tensor_argument(), ARM_COMPUTE_ERROR_ON_INVALID_SUBWINDOW, ARM_COMPUTE_ERROR_ON_UNCONFIGURED_KERNEL, Window::collapse_if_possible(), Window::DimX, Window::DimZ, arm_compute::enqueue(), Window::first_slice_window_3D(), ICLKernel::lws_hint(), Window::set(), arm_compute::test::validation::reference::slice(), Window::slide_window_slice_3D(), and IKernel::window().
|
static |
Static function to check if given info will lead to a valid configuration of CLLogits1DNormKernel.
[in] | input | Source tensor. Data types supported: S32/F16/F32. If this kernel is used for log softmax, only F32/F16 is supported. |
[in] | sum | Sum tensor. Dimensions should be dim(input)-1. Data types supported: same as input |
[in] | output | Destination tensor. Data types supported: QASYMM8 for S32 input , or same as input |
[in] | info | Contains information consumed by kernels for softmax described in SoftmaxKernelInfo. |
Definition at line 341 of file CLSoftmaxLayerKernel.cpp.
References ARM_COMPUTE_RETURN_ON_ERROR.
Referenced by CLSoftmaxLayerGeneric< IS_LOG >::validate().