Cyclops Tensor Framework
parallel arithmetic on multidimensional arrays
|
Folded matrix multiplication on 4D tensors. More...
Functions | |
int | gemm_4D (int const n, int const sym, int const niter, World &dw) |
char * | getCmdOption (char **begin, char **end, const std::string &option) |
int | main (int argc, char **argv) |
Folded matrix multiplication on 4D tensors.
int gemm_4D | ( | int const | n, |
int const | sym, | ||
int const | niter, | ||
World & | dw | ||
) |
Definition at line 11 of file gemm_4D.cxx.
References CTF::Tensor< dtype >::align(), AS, CTF::Tensor< dtype >::get_local_data(), ctf.core::np(), NS, ctf.core::rank(), SY, and CTF::Tensor< dtype >::write().
Referenced by main().
char* getCmdOption | ( | char ** | begin, |
char ** | end, | ||
const std::string & | option | ||
) |
Definition at line 102 of file gemm_4D.cxx.
Referenced by main().
int main | ( | int | argc, |
char ** | argv | ||
) |
Definition at line 113 of file gemm_4D.cxx.
References AS, gemm_4D(), getCmdOption(), ctf.core::np(), NS, ctf.core::rank(), SH, and SY.