https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/about-hybrid-multithreaded-MPI-solver/m-p/765617#M211 I am wondering whether it is possible to use MKL and Intel MPI to realize hybrid multithreaded-MPI solver with simple codes the users write. Thanks a lot. Tue, 10 Aug 2010 14:47:01 GMT recrusader 2010-08-10T14:47:01Z https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/about-hybrid-multithreaded-MPI-solver/m-p/765617#M211 I am wondering whether it is possible to use MKL and Intel MPI to realize hybrid multithreaded-MPI solver with simple codes the users write. Thanks a lot. Tue, 10 Aug 2010 14:47:01 GMT https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/about-hybrid-multithreaded-MPI-solver/m-p/765617#M211 recrusader 2010-08-10T14:47:01Z https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/about-hybrid-multithreaded-MPI-solver/m-p/765618#M212 Yes, there are several production codes as well as demonstrations of Intel MPI usage with Intel OpenMP as the MPI FUNNELED implementation. Currently supported versions of Intel MPI default to using the OMP_NUM_THREADS to optimize thread placement on each node. MKL works well in both the 1 MPI process per node and 1 process per socket modes. Tue, 10 Aug 2010 22:21:21 GMT https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/about-hybrid-multithreaded-MPI-solver/m-p/765618#M212 TimP 2010-08-10T22:21:21Z https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/about-hybrid-multithreaded-MPI-solver/m-p/765619#M213 Intel MKL from version 10.2 and Intel MPI Library from version 4.0 may balance workload on a node. Number of MPI processes plus number of MKL threads will not exceed number of cores on a node. You don't even need to use OMP_NUM_THREADS or MKL_NUM_THREADS.<BR /><BR />Give it a try!<BR /><BR />Regards!<BR /> Dmitry<BR /> Wed, 11 Aug 2010 07:23:44 GMT https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/about-hybrid-multithreaded-MPI-solver/m-p/765619#M213 Dmitry_K_Intel2 2010-08-11T07:23:44Z