https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Threading/m-p/906539#M11761 I am a computer science student and I am intested to see the performance speed up and scalability of Intel MKL for our algorithm. We are using Intels woodcrest processor with corresponding bensley platform, thus having 4 cores available.<BR /> <BR /> The algorithm we are looking at is CG , it needs to solve Ax = b , for 500 b's . An obvious way to parallelize over multiple cores is letting each core solve one Ax=b. I've seen that a CG framework is provided by MKL and that we just need to fill in the operations.<BR /> <BR /> Probably the most important operation in CG is the sparse matrix vector multiplication. I've read in the Intel MKL documentation that sparse blas lvl2 also uses OpenMP for threading and I am thus wondering how this is implemented. Does this function spread the matrix over different cores and then mtultiply it rowwise? I know it is possible to thread in the way I want with OpenMP but I am interested to know how Intel did this.<BR /> <BR /> <BR /> Wed, 11 Oct 2006 04:24:08 GMT Anonymous62 2006-10-11T04:24:08Z https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Threading/m-p/906539#M11761 I am a computer science student and I am intested to see the performance speed up and scalability of Intel MKL for our algorithm. We are using Intels woodcrest processor with corresponding bensley platform, thus having 4 cores available.<BR /> <BR /> The algorithm we are looking at is CG , it needs to solve Ax = b , for 500 b's . An obvious way to parallelize over multiple cores is letting each core solve one Ax=b. I've seen that a CG framework is provided by MKL and that we just need to fill in the operations.<BR /> <BR /> Probably the most important operation in CG is the sparse matrix vector multiplication. I've read in the Intel MKL documentation that sparse blas lvl2 also uses OpenMP for threading and I am thus wondering how this is implemented. Does this function spread the matrix over different cores and then mtultiply it rowwise? I know it is possible to thread in the way I want with OpenMP but I am interested to know how Intel did this.<BR /> <BR /> <BR /> Wed, 11 Oct 2006 04:24:08 GMT https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Threading/m-p/906539#M11761 Anonymous62 2006-10-11T04:24:08Z