topic yes, I am calling zheev to in Intel® oneAPI Math Kernel Library

Automated parallelizing not working with large matrixes

suarez__eric — Wed, 30 Dec 2015 17:14:54 GMT

I have a code in fortran that calculates eigenvectors and eigenfunctions of matrix and process the results. I use the ifort with the -mkl compilation, the code runs in parallel for an square matrix (N,N) when N is less than 100 (more or less) but when I try larger matrixes N>300 it only runs as one thread.

Any help?

Regards

Eric

Please clarify - are you

Steven_L_Intel1 — Wed, 30 Dec 2015 19:58:12 GMT

Please clarify - are you using MKL routines for the eigenvectors and eigenfunctions? Which routines?

yes, I am calling zheev to

suarez__eric — Wed, 30 Dec 2015 20:17:40 GMT

yes, I am calling zheev to calculate the eigenvalues and eigenvectors then I do some other calculations with the results.

Ok. I am going to move this

Steven_L_Intel1 — Wed, 30 Dec 2015 20:56:14 GMT

Ok. I am going to move this to the MKL forum, then, where MKL experts can help you.

Eric, Could you give us the

Gennady_F_Intel — Thu, 31 Dec 2015 05:44:49 GMT

Eric, Could you give us the example to check the problem on our side?