Cholesky with pdpotrf()

Georgios_S_ — Wed, 01 Jul 2015 11:30:51 GMT

I am performing a Cholesky factorization with pdpotrf(). I am reading the whole matrix in the master node and then I distribute it. Then, every node is handling a submatrix and call pdpotrf(). Then I just send back the submatrices to the master node and compose the solution.

I am amazed by that. How does it do it? I mean what algorithm does it implement? I suspect it's block partitioning and every node is communicating (I hope not much, but I would really like to know how much).

Moreover, I feel I should understand the algorithmic part, in order to choose properly the block sizes.

Finally, I would like to know if pdpotrf() is multithreaded. For example, I read in this paper, that 4-threaded approaches do exist.

It seems that it's not

Georgios_S_ — Thu, 09 Jul 2015 12:30:13 GMT

It seems that it's not multithreaded, since I checked with Top and the number of the appearance of my executable there, was equal to the number of processes I summoned via MPI.

topic It seems that it's not in Intel® oneAPI Math Kernel Library

Cholesky with pdpotrf()

It seems that it's not