PARALUTION  1.0.0
PARALUTION
cuda_kernels_csr.hpp File Reference

Go to the source code of this file.

Namespaces

 paralution
 

Functions

template<typename ValueType , typename IndexType >
__global__ void paralution::kernel_csr_spmv_scalar (const IndexType nrow, const IndexType *row_offset, const IndexType *col, const ValueType *val, const ValueType *in, ValueType *out)
 
template<typename ValueType , typename IndexType >
__global__ void paralution::kernel_csr_add_spmv_scalar (const IndexType nrow, const IndexType *row_offset, const IndexType *col, const ValueType *val, const ValueType scalar, const ValueType *in, ValueType *out)
 
template<typename ValueType , typename IndexType >
__global__ void paralution::kernel_csr_scale_diagonal (const IndexType nrow, const IndexType *row_offset, const IndexType *col, const ValueType alpha, ValueType *val)
 
template<typename ValueType , typename IndexType >
__global__ void paralution::kernel_csr_scale_offdiagonal (const IndexType nrow, const IndexType *row_offset, const IndexType *col, const ValueType alpha, ValueType *val)
 
template<typename ValueType , typename IndexType >
__global__ void paralution::kernel_csr_add_diagonal (const IndexType nrow, const IndexType *row_offset, const IndexType *col, const ValueType alpha, ValueType *val)
 
template<typename ValueType , typename IndexType >
__global__ void paralution::kernel_csr_add_offdiagonal (const IndexType nrow, const IndexType *row_offset, const IndexType *col, const ValueType alpha, ValueType *val)
 
template<typename ValueType , typename IndexType >
__global__ void paralution::kernel_csr_extract_diag (const IndexType nrow, const IndexType *row_offset, const IndexType *col, const ValueType *val, ValueType *vec)
 
template<typename ValueType , typename IndexType >
__global__ void paralution::kernel_csr_extract_inv_diag (const IndexType nrow, const IndexType *row_offset, const IndexType *col, const ValueType *val, ValueType *vec)
 
template<typename ValueType , typename IndexType >
__global__ void paralution::kernel_csr_extract_submatrix_row_nnz (const IndexType *row_offset, const IndexType *col, const ValueType *val, const IndexType smrow_offset, const IndexType smcol_offset, const IndexType smrow_size, const IndexType smcol_size, IndexType *row_nnz)
 
template<typename ValueType , typename IndexType >
__global__ void paralution::kernel_csr_extract_submatrix_copy (const IndexType *row_offset, const IndexType *col, const ValueType *val, const IndexType smrow_offset, const IndexType smcol_offset, const IndexType smrow_size, const IndexType smcol_size, const IndexType *sm_row_offset, IndexType *sm_col, ValueType *sm_val)
 
template<typename ValueType , typename IndexType >
__global__ void paralution::kernel_csr_diagmatmult_r (const IndexType nrow, const IndexType *row_offset, const IndexType *col, const ValueType *diag, ValueType *val)
 
template<typename ValueType , typename IndexType >
__global__ void paralution::kernel_csr_diagmatmult_l (const IndexType nrow, const IndexType *row_offset, const ValueType *diag, ValueType *val)
 
template<typename IndexType >
__global__ void paralution::kernel_calc_row_nnz (const IndexType nrow, const IndexType *row_offset, IndexType *row_nnz)
 
template<typename IndexType >
__global__ void paralution::kernel_permute_row_nnz (const IndexType nrow, const IndexType *row_nnz_src, const IndexType *perm_vec, IndexType *row_nnz_dst)
 
template<typename ValueType , typename IndexType >
__global__ void paralution::kernel_permute_rows (const IndexType nrow, const IndexType *row_offset, const IndexType *perm_row_offset, const IndexType *col, const ValueType *data, const IndexType *perm_vec, const IndexType *row_nnz, IndexType *perm_col, ValueType *perm_data)
 
template<typename ValueType , typename IndexType , const IndexType size>
__global__ void paralution::kernel_permute_cols (const IndexType nrow, const IndexType *row_offset, const IndexType *perm_vec, const IndexType *row_nnz, const IndexType *perm_col, const ValueType *perm_data, IndexType *col, ValueType *data)
 
template<typename ValueType , typename IndexType >
__global__ void paralution::kernel_csr_add_csr_same_struct (const IndexType nrow, const IndexType *out_row_offset, const IndexType *out_col, const IndexType *in_row_offset, const IndexType *in_col, const ValueType *in_val, const ValueType alpha, const ValueType beta, ValueType *out_val)
 
template<typename ValueType , typename IndexType >
__global__ void paralution::kernel_csr_lower_nnz_per_row (const IndexType nrow, const IndexType *src_row_offset, const IndexType *src_col, IndexType *nnz_per_row)
 
template<typename ValueType , typename IndexType >
__global__ void paralution::kernel_csr_upper_nnz_per_row (const IndexType nrow, const IndexType *src_row_offset, const IndexType *src_col, IndexType *nnz_per_row)
 
template<typename ValueType , typename IndexType >
__global__ void paralution::kernel_csr_slower_nnz_per_row (const IndexType nrow, const IndexType *src_row_offset, const IndexType *src_col, IndexType *nnz_per_row)
 
template<typename ValueType , typename IndexType >
__global__ void paralution::kernel_csr_supper_nnz_per_row (const IndexType nrow, const IndexType *src_row_offset, const IndexType *src_col, IndexType *nnz_per_row)
 
template<typename ValueType , typename IndexType >
__global__ void paralution::kernel_csr_extract_l_triangular (const IndexType nrow, const IndexType *src_row_offset, const IndexType *src_col, const ValueType *src_val, IndexType *nnz_per_row, IndexType *dst_col, ValueType *dst_val)
 
template<typename ValueType , typename IndexType >
__global__ void paralution::kernel_csr_extract_u_triangular (const IndexType nrow, const IndexType *src_row_offset, const IndexType *src_col, const ValueType *src_val, IndexType *nnz_per_row, IndexType *dst_col, ValueType *dst_val)
 
template<typename ValueType , typename IndexType >
__global__ void paralution::kernel_csr_compress_count_nrow (const IndexType *row_offset, const IndexType *col, const ValueType *val, const IndexType nrow, const double drop_off, IndexType *row_offset_new)
 
template<typename ValueType , typename IndexType >
__global__ void paralution::kernel_csr_compress_copy (const IndexType *row_offset, const IndexType *col, const ValueType *val, const IndexType nrow, const double drop_off, const IndexType *row_offset_new, IndexType *col_new, ValueType *val_new)
 
template<typename ValueType , typename IndexType >
__global__ void paralution::kernel_csr_extract_column_vector (const IndexType *row_offset, const IndexType *col, const ValueType *val, const IndexType nrow, const IndexType idx, ValueType *vec)
 
template<typename ValueType , typename IndexType >
__global__ void paralution::kernel_csr_replace_column_vector_offset (const IndexType *row_offset, const IndexType *col, const IndexType nrow, const IndexType idx, const ValueType *vec, IndexType *offset)
 
template<typename ValueType , typename IndexType >
__global__ void paralution::kernel_csr_replace_column_vector (const IndexType *row_offset, const IndexType *col, const ValueType *val, const IndexType nrow, const IndexType idx, const ValueType *vec, const IndexType *offset, IndexType *new_col, ValueType *new_val)
 
template<typename ValueType , typename IndexType >
__global__ void paralution::kernel_csr_extract_row_vector (const IndexType *row_offset, const IndexType *col, const ValueType *val, const IndexType row_nnz, const IndexType idx, ValueType *vec)