Cyclops Tensor Framework
parallel arithmetic on multidimensional arrays
|
#include "summation.h"
Go to the source code of this file.
Namespaces | |
CTF_int | |
Functions | |
int | CTF_int::sym_seq_sum_ref (char const *alpha, char const *A, algstrct const *sr_A, int order_A, int const *edge_len_A, int const *sym_A, int const *idx_map_A, char const *beta, char *B, algstrct const *sr_B, int order_B, int const *edge_len_B, int const *sym_B, int const *idx_map_B) |
performs symmetric contraction with unblocked reference kernel More... | |
int | CTF_int::sym_seq_sum_cust (char const *alpha, char const *A, algstrct const *sr_A, int order_A, int const *edge_len_A, int const *sym_A, int const *idx_map_A, char const *beta, char *B, algstrct const *sr_B, int order_B, int const *edge_len_B, int const *sym_B, int const *idx_map_B, univar_function const *func) |
performs symmetric summation with custom elementwise function More... | |
int | CTF_int::sym_seq_sum_inr (char const *alpha, char const *A, algstrct const *sr_A, int order_A, int const *edge_len_A, int const *sym_A, int const *idx_map_A, char const *beta, char *B, algstrct const *sr_B, int order_B, int const *edge_len_B, int const *sym_B, int const *idx_map_B, int inr_stride) |
performs symmetric summation with blocked daxpy More... | |