By the way, when we solve the same systems of equations with the direct solver Pardiso processor utilization is a constant 50% (the system has 32 virtual cores, 16 physical cores). Gonzalo
The cause of the case may be that dfgmres is not threaded or may be not efficiency implemented. What version of mkl do you use? Could you please export env varaible MKL_VERBOSE=1 and check the version number.
Thank you for reply! We are using version 2017.1.143. I was under the impression that dfgmres is parallelized, and would be surprised if it is not. PARDISO, sparse matrix-vector products are parallelized so I thought this would extent to the functions implementing iterative solvers.
Please, let me know!
Hello Gonzalo, actually fgmres is not threaded, but we don't expect to that will be a problem because of the perf bottleneck of such sort of computations - matrix-vector multiplication and precondition handle. But based on your results, you see the bottleneck is fgmres itself. How could we check the problem on our side? thanks