PLSSVM - Parallel Least Squares Support Vector Machine  2.0.0
A Least Squares Support Vector Machine implementation using different backends.
Public Types | Public Member Functions | List of all members
plssvm::sycl::detail::hierarchical_device_kernel_linear< T > Class Template Reference

Calculates the C-SVM kernel using the hierarchical formulation and the linear kernel function. More...

#include <svm_kernel_hierarchical.hpp>

Public Types

using real_type = T
 The type of the data.
 

Public Member Functions

 hierarchical_device_kernel_linear (const real_type *q, real_type *ret, const real_type *d, const real_type *data_d, const real_type QA_cost, const real_type cost, const kernel_index_type num_rows, const kernel_index_type feature_range, const real_type add, const kernel_index_type id)
 Construct a new device kernel calculating the C-SVM kernel using the linear C-SVM kernel. More...
 
void operator() (::sycl::group< 2 > group) const
 Function call operator overload performing the actual calculation. More...
 

Detailed Description

template<typename T>
class plssvm::sycl::detail::hierarchical_device_kernel_linear< T >

Calculates the C-SVM kernel using the hierarchical formulation and the linear kernel function.

Supports multi-GPU execution.

Template Parameters
Tthe type of the data

Constructor & Destructor Documentation

◆ hierarchical_device_kernel_linear()

template<typename T >
plssvm::sycl::detail::hierarchical_device_kernel_linear< T >::hierarchical_device_kernel_linear ( const real_type q,
real_type ret,
const real_type d,
const real_type data_d,
const real_type  QA_cost,
const real_type  cost,
const kernel_index_type  num_rows,
const kernel_index_type  feature_range,
const real_type  add,
const kernel_index_type  id 
)
inline

Construct a new device kernel calculating the C-SVM kernel using the linear C-SVM kernel.

Parameters
[in]qthe q vector
[out]retthe result vector
[in]dthe right-hand side of the equation
[in]data_dthe one-dimension data matrix
[in]QA_costhe bottom right matrix entry multiplied by cost
[in]cost1 / the cost parameter in the C-SVM
[in]num_rowsthe number of columns in the data matrix
[in]feature_rangenumber of features used for the calculation on the device id
[in]adddenotes whether the values are added or subtracted from the result vector
[in]idthe id of the device

Member Function Documentation

◆ operator()()

template<typename T >
void plssvm::sycl::detail::hierarchical_device_kernel_linear< T >::operator() ( ::sycl::group< 2 >  group) const
inline

Function call operator overload performing the actual calculation.

Parameters
[in]groupthe sycl::group identifying an instance of the currently execution work-group

The documentation for this class was generated from the following file: