csvm.hpp

Go to the documentation of this file.

 
#ifndef PLSSVM_BACKENDS_CUDA_CSVM_HPP_
#define PLSSVM_BACKENDS_CUDA_CSVM_HPP_
#pragma once
 
#include "plssvm/backends/CUDA/detail/device_ptr.cuh"  // plssvm::cuda::detail::device_ptr
#include "plssvm/backends/gpu_csvm.hpp"                // plssvm::detail::gpu_csvm
#include "plssvm/parameter.hpp"                        // plssvm::parameter, plssvm::detail::parameter
#include "plssvm/target_platforms.hpp"                 // plssvm::target_platform
 
#include <cstddef>                                     // std::size_t
#include <type_traits>                                 // std::true_type
#include <utility>                                     // std::forward
 
namespace plssvm {
 
namespace detail {
 
// forward declare execution_range class
class execution_range;
 
}  // namespace detail
 
namespace cuda {
 
class csvm : public ::plssvm::detail::gpu_csvm<detail::device_ptr, int> {
  protected:
    // protected for the test mock class
    using base_type = ::plssvm::detail::gpu_csvm<detail::device_ptr, int>;
 
    using base_type::devices_;
 
  public:
    using base_type::device_ptr_type;
    using typename base_type::queue_type;
 
    explicit csvm(parameter params = {});
    explicit csvm(target_platform target, parameter params = {});
 
    template <typename... Args, PLSSVM_REQUIRES(::plssvm::detail::has_only_parameter_named_args_v<Args...>)>
    explicit csvm(Args &&...named_args) :
        csvm{ plssvm::target_platform::automatic, std::forward<Args>(named_args)... } {}
    template <typename... Args, PLSSVM_REQUIRES(::plssvm::detail::has_only_parameter_named_args_v<Args...>)>
    explicit csvm(const target_platform target, Args &&...named_args) :
        base_type{ std::forward<Args>(named_args)... } {
        this->init(target);
    }
 
    csvm(const csvm &) = delete;
    csvm(csvm &&) noexcept = default;
    csvm &operator=(const csvm &) = delete;
    csvm &operator=(csvm &&) noexcept = default;
    ~csvm() override;
 
  protected:
    void device_synchronize(const queue_type &queue) const final;
 
    void run_q_kernel(std::size_t device, const ::plssvm::detail::execution_range &range, const ::plssvm::detail::parameter<float> &params, device_ptr_type<float> &q_d, const device_ptr_type<float> &data_d, const device_ptr_type<float> &data_last_d, std::size_t num_data_points_padded, std::size_t num_features) const final { this->run_q_kernel_impl(device, range, params, q_d, data_d, data_last_d, num_data_points_padded, num_features); }
    void run_q_kernel(std::size_t device, const ::plssvm::detail::execution_range &range, const ::plssvm::detail::parameter<double> &params, device_ptr_type<double> &q_d, const device_ptr_type<double> &data_d, const device_ptr_type<double> &data_last_d, std::size_t num_data_points_padded, std::size_t num_features) const final { this->run_q_kernel_impl(device, range, params, q_d, data_d, data_last_d, num_data_points_padded, num_features); }
    template <typename real_type>
    void run_q_kernel_impl(std::size_t device, const ::plssvm::detail::execution_range &range, const ::plssvm::detail::parameter<real_type> &params, device_ptr_type<real_type> &q_d, const device_ptr_type<real_type> &data_d, const device_ptr_type<real_type> &data_last_d, std::size_t num_data_points_padded, std::size_t num_features) const;
    void run_svm_kernel(std::size_t device, const ::plssvm::detail::execution_range &range, const ::plssvm::detail::parameter<float> &params, const device_ptr_type<float> &q_d, device_ptr_type<float> &r_d, const device_ptr_type<float> &x_d, const device_ptr_type<float> &data_d, float QA_cost, float add, std::size_t num_data_points_padded, std::size_t num_features) const final { this->run_svm_kernel_impl(device, range, params, q_d, r_d, x_d, data_d, QA_cost, add, num_data_points_padded, num_features); }
    void run_svm_kernel(std::size_t device, const ::plssvm::detail::execution_range &range, const ::plssvm::detail::parameter<double> &params, const device_ptr_type<double> &q_d, device_ptr_type<double> &r_d, const device_ptr_type<double> &x_d, const device_ptr_type<double> &data_d, double QA_cost, double add, std::size_t num_data_points_padded, std::size_t num_features) const final { this->run_svm_kernel_impl(device, range, params, q_d, r_d, x_d, data_d, QA_cost, add, num_data_points_padded, num_features); }
    template <typename real_type>
    void run_svm_kernel_impl(std::size_t device, const ::plssvm::detail::execution_range &range, const ::plssvm::detail::parameter<real_type> &params, const device_ptr_type<real_type> &q_d, device_ptr_type<real_type> &r_d, const device_ptr_type<real_type> &x_d, const device_ptr_type<real_type> &data_d, real_type QA_cost, real_type add, std::size_t num_data_points_padded, std::size_t num_features) const;
    void run_w_kernel(std::size_t device, const ::plssvm::detail::execution_range &range, device_ptr_type<float> &w_d, const device_ptr_type<float> &alpha_d, const device_ptr_type<float> &data_d, const device_ptr_type<float> &data_last_d, std::size_t num_data_points, std::size_t num_features) const final { this->run_w_kernel_impl(device, range, w_d, alpha_d, data_d, data_last_d, num_data_points, num_features); }
    void run_w_kernel(std::size_t device, const ::plssvm::detail::execution_range &range, device_ptr_type<double> &w_d, const device_ptr_type<double> &alpha_d, const device_ptr_type<double> &data_d, const device_ptr_type<double> &data_last_d, std::size_t num_data_points, std::size_t num_features) const final { this->run_w_kernel_impl(device, range, w_d, alpha_d, data_d, data_last_d, num_data_points, num_features); }
    template <typename real_type>
    void run_w_kernel_impl(std::size_t device, const ::plssvm::detail::execution_range &range, device_ptr_type<real_type> &w_d, const device_ptr_type<real_type> &alpha_d, const device_ptr_type<real_type> &data_d, const device_ptr_type<real_type> &data_last_d, std::size_t num_data_points, std::size_t num_features) const;
    void run_predict_kernel(const ::plssvm::detail::execution_range &range, const ::plssvm::detail::parameter<float> &params, device_ptr_type<float> &out_d, const device_ptr_type<float> &alpha_d, const device_ptr_type<float> &point_d, const device_ptr_type<float> &data_d, const device_ptr_type<float> &data_last_d, std::size_t num_support_vectors, std::size_t num_predict_points, std::size_t num_features) const final { this->run_predict_kernel_impl(range, params, out_d, alpha_d, point_d, data_d, data_last_d, num_support_vectors, num_predict_points, num_features); }
    void run_predict_kernel(const ::plssvm::detail::execution_range &range, const ::plssvm::detail::parameter<double> &params, device_ptr_type<double> &out_d, const device_ptr_type<double> &alpha_d, const device_ptr_type<double> &point_d, const device_ptr_type<double> &data_d, const device_ptr_type<double> &data_last_d, std::size_t num_support_vectors, std::size_t num_predict_points, std::size_t num_features) const final { this->run_predict_kernel_impl(range, params, out_d, alpha_d, point_d, data_d, data_last_d, num_support_vectors, num_predict_points, num_features); }
    template <typename real_type>
    void run_predict_kernel_impl(const ::plssvm::detail::execution_range &range, const ::plssvm::detail::parameter<real_type> &params, device_ptr_type<real_type> &out_d, const device_ptr_type<real_type> &alpha_d, const device_ptr_type<real_type> &point_d, const device_ptr_type<real_type> &data_d, const device_ptr_type<real_type> &data_last_d, std::size_t num_support_vectors, std::size_t num_predict_points, std::size_t num_features) const;
 
  private:
    void init(target_platform target);
};
 
}  // namespace cuda
 
namespace detail {
 
template <>
struct csvm_backend_exists<cuda::csvm> : std::true_type {};
 
}  // namespace detail
 
}  // namespace plssvm
 
#endif  // PLSSVM_BACKENDS_CUDA_CSVM_HPP_