ViennaCL - The Vienna Computing Library  1.5.1
Namespaces | Functions
viennacl/linalg/cuda/matrix_operations_prod.hpp File Reference

Dense matrix-matrix product CUDA kernels reside here. More...

Go to the source code of this file.

Namespaces

namespace  viennacl
 

Main namespace in ViennaCL. Holds all the basic types such as vector, matrix, etc. and defines operations upon them.


namespace  viennacl::linalg
 

Provides all linear algebra operations which are not covered by operator overloads.


namespace  viennacl::linalg::cuda
 

Holds all CUDA compute kernels used by ViennaCL.


Functions

template<typename T >
__global__ void matrix_matrix_col_col_col_prod_AA_kernel (T alpha, const T *A, unsigned int A_row_start, unsigned int A_col_start, unsigned int A_row_inc, unsigned int A_col_inc, unsigned int A_row_size, unsigned int A_col_size, unsigned int A_internal_rows, unsigned int A_internal_cols, const T *B, unsigned int B_row_start, unsigned int B_col_start, unsigned int B_row_inc, unsigned int B_col_inc, unsigned int B_row_size, unsigned int B_col_size, unsigned int B_internal_rows, unsigned int B_internal_cols, T beta, T *C, unsigned int C_row_start, unsigned int C_col_start, unsigned int C_row_inc, unsigned int C_col_inc, unsigned int C_row_size, unsigned int C_col_size, unsigned int C_internal_rows, unsigned int C_internal_cols)
template<typename T >
__global__ void matrix_matrix_col_col_col_prod_AT_kernel (T alpha, const T *A, unsigned int A_row_start, unsigned int A_col_start, unsigned int A_row_inc, unsigned int A_col_inc, unsigned int A_row_size, unsigned int A_col_size, unsigned int A_internal_rows, unsigned int A_internal_cols, const T *B, unsigned int B_row_start, unsigned int B_col_start, unsigned int B_row_inc, unsigned int B_col_inc, unsigned int B_row_size, unsigned int B_col_size, unsigned int B_internal_rows, unsigned int B_internal_cols, T beta, T *C, unsigned int C_row_start, unsigned int C_col_start, unsigned int C_row_inc, unsigned int C_col_inc, unsigned int C_row_size, unsigned int C_col_size, unsigned int C_internal_rows, unsigned int C_internal_cols)
template<typename T >
__global__ void matrix_matrix_col_col_col_prod_TA_kernel (T alpha, const T *A, unsigned int A_row_start, unsigned int A_col_start, unsigned int A_row_inc, unsigned int A_col_inc, unsigned int A_row_size, unsigned int A_col_size, unsigned int A_internal_rows, unsigned int A_internal_cols, const T *B, unsigned int B_row_start, unsigned int B_col_start, unsigned int B_row_inc, unsigned int B_col_inc, unsigned int B_row_size, unsigned int B_col_size, unsigned int B_internal_rows, unsigned int B_internal_cols, T beta, T *C, unsigned int C_row_start, unsigned int C_col_start, unsigned int C_row_inc, unsigned int C_col_inc, unsigned int C_row_size, unsigned int C_col_size, unsigned int C_internal_rows, unsigned int C_internal_cols)
template<typename T >
__global__ void matrix_matrix_col_col_col_prod_TT_kernel (T alpha, const T *A, unsigned int A_row_start, unsigned int A_col_start, unsigned int A_row_inc, unsigned int A_col_inc, unsigned int A_row_size, unsigned int A_col_size, unsigned int A_internal_rows, unsigned int A_internal_cols, const T *B, unsigned int B_row_start, unsigned int B_col_start, unsigned int B_row_inc, unsigned int B_col_inc, unsigned int B_row_size, unsigned int B_col_size, unsigned int B_internal_rows, unsigned int B_internal_cols, T beta, T *C, unsigned int C_row_start, unsigned int C_col_start, unsigned int C_row_inc, unsigned int C_col_inc, unsigned int C_row_size, unsigned int C_col_size, unsigned int C_internal_rows, unsigned int C_internal_cols)
template<typename T >
__global__ void matrix_matrix_row_col_col_prod_AA_kernel (T alpha, const T *A, unsigned int A_row_start, unsigned int A_col_start, unsigned int A_row_inc, unsigned int A_col_inc, unsigned int A_row_size, unsigned int A_col_size, unsigned int A_internal_rows, unsigned int A_internal_cols, const T *B, unsigned int B_row_start, unsigned int B_col_start, unsigned int B_row_inc, unsigned int B_col_inc, unsigned int B_row_size, unsigned int B_col_size, unsigned int B_internal_rows, unsigned int B_internal_cols, T beta, T *C, unsigned int C_row_start, unsigned int C_col_start, unsigned int C_row_inc, unsigned int C_col_inc, unsigned int C_row_size, unsigned int C_col_size, unsigned int C_internal_rows, unsigned int C_internal_cols)
template<typename T >
__global__ void matrix_matrix_row_col_col_prod_AT_kernel (T alpha, const T *A, unsigned int A_row_start, unsigned int A_col_start, unsigned int A_row_inc, unsigned int A_col_inc, unsigned int A_row_size, unsigned int A_col_size, unsigned int A_internal_rows, unsigned int A_internal_cols, const T *B, unsigned int B_row_start, unsigned int B_col_start, unsigned int B_row_inc, unsigned int B_col_inc, unsigned int B_row_size, unsigned int B_col_size, unsigned int B_internal_rows, unsigned int B_internal_cols, T beta, T *C, unsigned int C_row_start, unsigned int C_col_start, unsigned int C_row_inc, unsigned int C_col_inc, unsigned int C_row_size, unsigned int C_col_size, unsigned int C_internal_rows, unsigned int C_internal_cols)
template<typename T >
__global__ void matrix_matrix_row_col_col_prod_TA_kernel (T alpha, const T *A, unsigned int A_row_start, unsigned int A_col_start, unsigned int A_row_inc, unsigned int A_col_inc, unsigned int A_row_size, unsigned int A_col_size, unsigned int A_internal_rows, unsigned int A_internal_cols, const T *B, unsigned int B_row_start, unsigned int B_col_start, unsigned int B_row_inc, unsigned int B_col_inc, unsigned int B_row_size, unsigned int B_col_size, unsigned int B_internal_rows, unsigned int B_internal_cols, T beta, T *C, unsigned int C_row_start, unsigned int C_col_start, unsigned int C_row_inc, unsigned int C_col_inc, unsigned int C_row_size, unsigned int C_col_size, unsigned int C_internal_rows, unsigned int C_internal_cols)
template<typename T >
__global__ void matrix_matrix_row_col_col_prod_TT_kernel (T alpha, const T *A, unsigned int A_row_start, unsigned int A_col_start, unsigned int A_row_inc, unsigned int A_col_inc, unsigned int A_row_size, unsigned int A_col_size, unsigned int A_internal_rows, unsigned int A_internal_cols, const T *B, unsigned int B_row_start, unsigned int B_col_start, unsigned int B_row_inc, unsigned int B_col_inc, unsigned int B_row_size, unsigned int B_col_size, unsigned int B_internal_rows, unsigned int B_internal_cols, T beta, T *C, unsigned int C_row_start, unsigned int C_col_start, unsigned int C_row_inc, unsigned int C_col_inc, unsigned int C_row_size, unsigned int C_col_size, unsigned int C_internal_rows, unsigned int C_internal_cols)
template<typename T >
__global__ void matrix_matrix_col_col_row_prod_AA_kernel (T alpha, const T *A, unsigned int A_row_start, unsigned int A_col_start, unsigned int A_row_inc, unsigned int A_col_inc, unsigned int A_row_size, unsigned int A_col_size, unsigned int A_internal_rows, unsigned int A_internal_cols, const T *B, unsigned int B_row_start, unsigned int B_col_start, unsigned int B_row_inc, unsigned int B_col_inc, unsigned int B_row_size, unsigned int B_col_size, unsigned int B_internal_rows, unsigned int B_internal_cols, T beta, T *C, unsigned int C_row_start, unsigned int C_col_start, unsigned int C_row_inc, unsigned int C_col_inc, unsigned int C_row_size, unsigned int C_col_size, unsigned int C_internal_rows, unsigned int C_internal_cols)
template<typename T >
__global__ void matrix_matrix_col_col_row_prod_AT_kernel (T alpha, const T *A, unsigned int A_row_start, unsigned int A_col_start, unsigned int A_row_inc, unsigned int A_col_inc, unsigned int A_row_size, unsigned int A_col_size, unsigned int A_internal_rows, unsigned int A_internal_cols, const T *B, unsigned int B_row_start, unsigned int B_col_start, unsigned int B_row_inc, unsigned int B_col_inc, unsigned int B_row_size, unsigned int B_col_size, unsigned int B_internal_rows, unsigned int B_internal_cols, T beta, T *C, unsigned int C_row_start, unsigned int C_col_start, unsigned int C_row_inc, unsigned int C_col_inc, unsigned int C_row_size, unsigned int C_col_size, unsigned int C_internal_rows, unsigned int C_internal_cols)
template<typename T >
__global__ void matrix_matrix_col_col_row_prod_TA_kernel (T alpha, const T *A, unsigned int A_row_start, unsigned int A_col_start, unsigned int A_row_inc, unsigned int A_col_inc, unsigned int A_row_size, unsigned int A_col_size, unsigned int A_internal_rows, unsigned int A_internal_cols, const T *B, unsigned int B_row_start, unsigned int B_col_start, unsigned int B_row_inc, unsigned int B_col_inc, unsigned int B_row_size, unsigned int B_col_size, unsigned int B_internal_rows, unsigned int B_internal_cols, T beta, T *C, unsigned int C_row_start, unsigned int C_col_start, unsigned int C_row_inc, unsigned int C_col_inc, unsigned int C_row_size, unsigned int C_col_size, unsigned int C_internal_rows, unsigned int C_internal_cols)
template<typename T >
__global__ void matrix_matrix_col_col_row_prod_TT_kernel (T alpha, const T *A, unsigned int A_row_start, unsigned int A_col_start, unsigned int A_row_inc, unsigned int A_col_inc, unsigned int A_row_size, unsigned int A_col_size, unsigned int A_internal_rows, unsigned int A_internal_cols, const T *B, unsigned int B_row_start, unsigned int B_col_start, unsigned int B_row_inc, unsigned int B_col_inc, unsigned int B_row_size, unsigned int B_col_size, unsigned int B_internal_rows, unsigned int B_internal_cols, T beta, T *C, unsigned int C_row_start, unsigned int C_col_start, unsigned int C_row_inc, unsigned int C_col_inc, unsigned int C_row_size, unsigned int C_col_size, unsigned int C_internal_rows, unsigned int C_internal_cols)
template<typename T >
__global__ void matrix_matrix_row_col_row_prod_AA_kernel (T alpha, const T *A, unsigned int A_row_start, unsigned int A_col_start, unsigned int A_row_inc, unsigned int A_col_inc, unsigned int A_row_size, unsigned int A_col_size, unsigned int A_internal_rows, unsigned int A_internal_cols, const T *B, unsigned int B_row_start, unsigned int B_col_start, unsigned int B_row_inc, unsigned int B_col_inc, unsigned int B_row_size, unsigned int B_col_size, unsigned int B_internal_rows, unsigned int B_internal_cols, T beta, T *C, unsigned int C_row_start, unsigned int C_col_start, unsigned int C_row_inc, unsigned int C_col_inc, unsigned int C_row_size, unsigned int C_col_size, unsigned int C_internal_rows, unsigned int C_internal_cols)
template<typename T >
__global__ void matrix_matrix_row_col_row_prod_AT_kernel (T alpha, const T *A, unsigned int A_row_start, unsigned int A_col_start, unsigned int A_row_inc, unsigned int A_col_inc, unsigned int A_row_size, unsigned int A_col_size, unsigned int A_internal_rows, unsigned int A_internal_cols, const T *B, unsigned int B_row_start, unsigned int B_col_start, unsigned int B_row_inc, unsigned int B_col_inc, unsigned int B_row_size, unsigned int B_col_size, unsigned int B_internal_rows, unsigned int B_internal_cols, T beta, T *C, unsigned int C_row_start, unsigned int C_col_start, unsigned int C_row_inc, unsigned int C_col_inc, unsigned int C_row_size, unsigned int C_col_size, unsigned int C_internal_rows, unsigned int C_internal_cols)
template<typename T >
__global__ void matrix_matrix_row_col_row_prod_TA_kernel (T alpha, const T *A, unsigned int A_row_start, unsigned int A_col_start, unsigned int A_row_inc, unsigned int A_col_inc, unsigned int A_row_size, unsigned int A_col_size, unsigned int A_internal_rows, unsigned int A_internal_cols, const T *B, unsigned int B_row_start, unsigned int B_col_start, unsigned int B_row_inc, unsigned int B_col_inc, unsigned int B_row_size, unsigned int B_col_size, unsigned int B_internal_rows, unsigned int B_internal_cols, T beta, T *C, unsigned int C_row_start, unsigned int C_col_start, unsigned int C_row_inc, unsigned int C_col_inc, unsigned int C_row_size, unsigned int C_col_size, unsigned int C_internal_rows, unsigned int C_internal_cols)
template<typename T >
__global__ void matrix_matrix_row_col_row_prod_TT_kernel (T alpha, const T *A, unsigned int A_row_start, unsigned int A_col_start, unsigned int A_row_inc, unsigned int A_col_inc, unsigned int A_row_size, unsigned int A_col_size, unsigned int A_internal_rows, unsigned int A_internal_cols, const T *B, unsigned int B_row_start, unsigned int B_col_start, unsigned int B_row_inc, unsigned int B_col_inc, unsigned int B_row_size, unsigned int B_col_size, unsigned int B_internal_rows, unsigned int B_internal_cols, T beta, T *C, unsigned int C_row_start, unsigned int C_col_start, unsigned int C_row_inc, unsigned int C_col_inc, unsigned int C_row_size, unsigned int C_col_size, unsigned int C_internal_rows, unsigned int C_internal_cols)
template<typename T >
__global__ void matrix_matrix_col_row_col_prod_AA_kernel (T alpha, const T *A, unsigned int A_row_start, unsigned int A_col_start, unsigned int A_row_inc, unsigned int A_col_inc, unsigned int A_row_size, unsigned int A_col_size, unsigned int A_internal_rows, unsigned int A_internal_cols, const T *B, unsigned int B_row_start, unsigned int B_col_start, unsigned int B_row_inc, unsigned int B_col_inc, unsigned int B_row_size, unsigned int B_col_size, unsigned int B_internal_rows, unsigned int B_internal_cols, T beta, T *C, unsigned int C_row_start, unsigned int C_col_start, unsigned int C_row_inc, unsigned int C_col_inc, unsigned int C_row_size, unsigned int C_col_size, unsigned int C_internal_rows, unsigned int C_internal_cols)
template<typename T >
__global__ void matrix_matrix_col_row_col_prod_AT_kernel (T alpha, const T *A, unsigned int A_row_start, unsigned int A_col_start, unsigned int A_row_inc, unsigned int A_col_inc, unsigned int A_row_size, unsigned int A_col_size, unsigned int A_internal_rows, unsigned int A_internal_cols, const T *B, unsigned int B_row_start, unsigned int B_col_start, unsigned int B_row_inc, unsigned int B_col_inc, unsigned int B_row_size, unsigned int B_col_size, unsigned int B_internal_rows, unsigned int B_internal_cols, T beta, T *C, unsigned int C_row_start, unsigned int C_col_start, unsigned int C_row_inc, unsigned int C_col_inc, unsigned int C_row_size, unsigned int C_col_size, unsigned int C_internal_rows, unsigned int C_internal_cols)
template<typename T >
__global__ void matrix_matrix_col_row_col_prod_TA_kernel (T alpha, const T *A, unsigned int A_row_start, unsigned int A_col_start, unsigned int A_row_inc, unsigned int A_col_inc, unsigned int A_row_size, unsigned int A_col_size, unsigned int A_internal_rows, unsigned int A_internal_cols, const T *B, unsigned int B_row_start, unsigned int B_col_start, unsigned int B_row_inc, unsigned int B_col_inc, unsigned int B_row_size, unsigned int B_col_size, unsigned int B_internal_rows, unsigned int B_internal_cols, T beta, T *C, unsigned int C_row_start, unsigned int C_col_start, unsigned int C_row_inc, unsigned int C_col_inc, unsigned int C_row_size, unsigned int C_col_size, unsigned int C_internal_rows, unsigned int C_internal_cols)
template<typename T >
__global__ void matrix_matrix_col_row_col_prod_TT_kernel (T alpha, const T *A, unsigned int A_row_start, unsigned int A_col_start, unsigned int A_row_inc, unsigned int A_col_inc, unsigned int A_row_size, unsigned int A_col_size, unsigned int A_internal_rows, unsigned int A_internal_cols, const T *B, unsigned int B_row_start, unsigned int B_col_start, unsigned int B_row_inc, unsigned int B_col_inc, unsigned int B_row_size, unsigned int B_col_size, unsigned int B_internal_rows, unsigned int B_internal_cols, T beta, T *C, unsigned int C_row_start, unsigned int C_col_start, unsigned int C_row_inc, unsigned int C_col_inc, unsigned int C_row_size, unsigned int C_col_size, unsigned int C_internal_rows, unsigned int C_internal_cols)
template<typename T >
__global__ void matrix_matrix_row_row_col_prod_AA_kernel (T alpha, const T *A, unsigned int A_row_start, unsigned int A_col_start, unsigned int A_row_inc, unsigned int A_col_inc, unsigned int A_row_size, unsigned int A_col_size, unsigned int A_internal_rows, unsigned int A_internal_cols, const T *B, unsigned int B_row_start, unsigned int B_col_start, unsigned int B_row_inc, unsigned int B_col_inc, unsigned int B_row_size, unsigned int B_col_size, unsigned int B_internal_rows, unsigned int B_internal_cols, T beta, T *C, unsigned int C_row_start, unsigned int C_col_start, unsigned int C_row_inc, unsigned int C_col_inc, unsigned int C_row_size, unsigned int C_col_size, unsigned int C_internal_rows, unsigned int C_internal_cols)
template<typename T >
__global__ void matrix_matrix_row_row_col_prod_AT_kernel (T alpha, const T *A, unsigned int A_row_start, unsigned int A_col_start, unsigned int A_row_inc, unsigned int A_col_inc, unsigned int A_row_size, unsigned int A_col_size, unsigned int A_internal_rows, unsigned int A_internal_cols, const T *B, unsigned int B_row_start, unsigned int B_col_start, unsigned int B_row_inc, unsigned int B_col_inc, unsigned int B_row_size, unsigned int B_col_size, unsigned int B_internal_rows, unsigned int B_internal_cols, T beta, T *C, unsigned int C_row_start, unsigned int C_col_start, unsigned int C_row_inc, unsigned int C_col_inc, unsigned int C_row_size, unsigned int C_col_size, unsigned int C_internal_rows, unsigned int C_internal_cols)
template<typename T >
__global__ void matrix_matrix_row_row_col_prod_TA_kernel (T alpha, const T *A, unsigned int A_row_start, unsigned int A_col_start, unsigned int A_row_inc, unsigned int A_col_inc, unsigned int A_row_size, unsigned int A_col_size, unsigned int A_internal_rows, unsigned int A_internal_cols, const T *B, unsigned int B_row_start, unsigned int B_col_start, unsigned int B_row_inc, unsigned int B_col_inc, unsigned int B_row_size, unsigned int B_col_size, unsigned int B_internal_rows, unsigned int B_internal_cols, T beta, T *C, unsigned int C_row_start, unsigned int C_col_start, unsigned int C_row_inc, unsigned int C_col_inc, unsigned int C_row_size, unsigned int C_col_size, unsigned int C_internal_rows, unsigned int C_internal_cols)
template<typename T >
__global__ void matrix_matrix_row_row_col_prod_TT_kernel (T alpha, const T *A, unsigned int A_row_start, unsigned int A_col_start, unsigned int A_row_inc, unsigned int A_col_inc, unsigned int A_row_size, unsigned int A_col_size, unsigned int A_internal_rows, unsigned int A_internal_cols, const T *B, unsigned int B_row_start, unsigned int B_col_start, unsigned int B_row_inc, unsigned int B_col_inc, unsigned int B_row_size, unsigned int B_col_size, unsigned int B_internal_rows, unsigned int B_internal_cols, T beta, T *C, unsigned int C_row_start, unsigned int C_col_start, unsigned int C_row_inc, unsigned int C_col_inc, unsigned int C_row_size, unsigned int C_col_size, unsigned int C_internal_rows, unsigned int C_internal_cols)
template<typename T >
__global__ void matrix_matrix_col_row_row_prod_AA_kernel (T alpha, const T *A, unsigned int A_row_start, unsigned int A_col_start, unsigned int A_row_inc, unsigned int A_col_inc, unsigned int A_row_size, unsigned int A_col_size, unsigned int A_internal_rows, unsigned int A_internal_cols, const T *B, unsigned int B_row_start, unsigned int B_col_start, unsigned int B_row_inc, unsigned int B_col_inc, unsigned int B_row_size, unsigned int B_col_size, unsigned int B_internal_rows, unsigned int B_internal_cols, T beta, T *C, unsigned int C_row_start, unsigned int C_col_start, unsigned int C_row_inc, unsigned int C_col_inc, unsigned int C_row_size, unsigned int C_col_size, unsigned int C_internal_rows, unsigned int C_internal_cols)
template<typename T >
__global__ void matrix_matrix_col_row_row_prod_AT_kernel (T alpha, const T *A, unsigned int A_row_start, unsigned int A_col_start, unsigned int A_row_inc, unsigned int A_col_inc, unsigned int A_row_size, unsigned int A_col_size, unsigned int A_internal_rows, unsigned int A_internal_cols, const T *B, unsigned int B_row_start, unsigned int B_col_start, unsigned int B_row_inc, unsigned int B_col_inc, unsigned int B_row_size, unsigned int B_col_size, unsigned int B_internal_rows, unsigned int B_internal_cols, T beta, T *C, unsigned int C_row_start, unsigned int C_col_start, unsigned int C_row_inc, unsigned int C_col_inc, unsigned int C_row_size, unsigned int C_col_size, unsigned int C_internal_rows, unsigned int C_internal_cols)
template<typename T >
__global__ void matrix_matrix_col_row_row_prod_TA_kernel (T alpha, const T *A, unsigned int A_row_start, unsigned int A_col_start, unsigned int A_row_inc, unsigned int A_col_inc, unsigned int A_row_size, unsigned int A_col_size, unsigned int A_internal_rows, unsigned int A_internal_cols, const T *B, unsigned int B_row_start, unsigned int B_col_start, unsigned int B_row_inc, unsigned int B_col_inc, unsigned int B_row_size, unsigned int B_col_size, unsigned int B_internal_rows, unsigned int B_internal_cols, T beta, T *C, unsigned int C_row_start, unsigned int C_col_start, unsigned int C_row_inc, unsigned int C_col_inc, unsigned int C_row_size, unsigned int C_col_size, unsigned int C_internal_rows, unsigned int C_internal_cols)
template<typename T >
__global__ void matrix_matrix_col_row_row_prod_TT_kernel (T alpha, const T *A, unsigned int A_row_start, unsigned int A_col_start, unsigned int A_row_inc, unsigned int A_col_inc, unsigned int A_row_size, unsigned int A_col_size, unsigned int A_internal_rows, unsigned int A_internal_cols, const T *B, unsigned int B_row_start, unsigned int B_col_start, unsigned int B_row_inc, unsigned int B_col_inc, unsigned int B_row_size, unsigned int B_col_size, unsigned int B_internal_rows, unsigned int B_internal_cols, T beta, T *C, unsigned int C_row_start, unsigned int C_col_start, unsigned int C_row_inc, unsigned int C_col_inc, unsigned int C_row_size, unsigned int C_col_size, unsigned int C_internal_rows, unsigned int C_internal_cols)
template<typename T >
__global__ void matrix_matrix_row_row_row_prod_AA_kernel (T alpha, const T *A, unsigned int A_row_start, unsigned int A_col_start, unsigned int A_row_inc, unsigned int A_col_inc, unsigned int A_row_size, unsigned int A_col_size, unsigned int A_internal_rows, unsigned int A_internal_cols, const T *B, unsigned int B_row_start, unsigned int B_col_start, unsigned int B_row_inc, unsigned int B_col_inc, unsigned int B_row_size, unsigned int B_col_size, unsigned int B_internal_rows, unsigned int B_internal_cols, T beta, T *C, unsigned int C_row_start, unsigned int C_col_start, unsigned int C_row_inc, unsigned int C_col_inc, unsigned int C_row_size, unsigned int C_col_size, unsigned int C_internal_rows, unsigned int C_internal_cols)
template<typename T >
__global__ void matrix_matrix_row_row_row_prod_AT_kernel (T alpha, const T *A, unsigned int A_row_start, unsigned int A_col_start, unsigned int A_row_inc, unsigned int A_col_inc, unsigned int A_row_size, unsigned int A_col_size, unsigned int A_internal_rows, unsigned int A_internal_cols, const T *B, unsigned int B_row_start, unsigned int B_col_start, unsigned int B_row_inc, unsigned int B_col_inc, unsigned int B_row_size, unsigned int B_col_size, unsigned int B_internal_rows, unsigned int B_internal_cols, T beta, T *C, unsigned int C_row_start, unsigned int C_col_start, unsigned int C_row_inc, unsigned int C_col_inc, unsigned int C_row_size, unsigned int C_col_size, unsigned int C_internal_rows, unsigned int C_internal_cols)
template<typename T >
__global__ void matrix_matrix_row_row_row_prod_TA_kernel (T alpha, const T *A, unsigned int A_row_start, unsigned int A_col_start, unsigned int A_row_inc, unsigned int A_col_inc, unsigned int A_row_size, unsigned int A_col_size, unsigned int A_internal_rows, unsigned int A_internal_cols, const T *B, unsigned int B_row_start, unsigned int B_col_start, unsigned int B_row_inc, unsigned int B_col_inc, unsigned int B_row_size, unsigned int B_col_size, unsigned int B_internal_rows, unsigned int B_internal_cols, T beta, T *C, unsigned int C_row_start, unsigned int C_col_start, unsigned int C_row_inc, unsigned int C_col_inc, unsigned int C_row_size, unsigned int C_col_size, unsigned int C_internal_rows, unsigned int C_internal_cols)
template<typename T >
__global__ void matrix_matrix_row_row_row_prod_TT_kernel (T alpha, const T *A, unsigned int A_row_start, unsigned int A_col_start, unsigned int A_row_inc, unsigned int A_col_inc, unsigned int A_row_size, unsigned int A_col_size, unsigned int A_internal_rows, unsigned int A_internal_cols, const T *B, unsigned int B_row_start, unsigned int B_col_start, unsigned int B_row_inc, unsigned int B_col_inc, unsigned int B_row_size, unsigned int B_col_size, unsigned int B_internal_rows, unsigned int B_internal_cols, T beta, T *C, unsigned int C_row_start, unsigned int C_col_start, unsigned int C_row_inc, unsigned int C_col_inc, unsigned int C_row_size, unsigned int C_col_size, unsigned int C_internal_rows, unsigned int C_internal_cols)

Detailed Description

Dense matrix-matrix product CUDA kernels reside here.

Note: File created semi-automatically from OpenCL kernels.