topic multithreaded performance of sparse blas not good in Intel® oneAPI Math Kernel Library https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/multithreaded-performance-of-sparse-blas-not-good/m-p/766172#M254 Ashade,<DIV><DIV>Do you mean that you see 5% of scalability with 4 cores vs 1 core?</DIV><DIV>what is the matrixes size? </DIV></DIV> Sun, 10 Apr 2011 15:56:39 GMT Gennady_F_Intel 2011-04-10T15:56:39Z multithreaded performance of sparse blas not good https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/multithreaded-performance-of-sparse-blas-not-good/m-p/766170#M252 <P>Hi all</P><P>I'm having trouble with matrix multiplication on Sparse Blas. I am trying to multiply 2 huge matrices and compare multithreaded and single threaded performance on an quad core AMD Phenom II 940 with 4GB of DDR3 RAM.</P><P>I am using mkl_scsrmm. On benchmark, I repeat the call to mkl_scsrmm a hundred times and I compute the total time in seconds. The matrices have 700,000 (dense) and 20,000 (sparse) elements.</P><P>The problem is that the multithreaded performance is only 5% better than single threaded sequential performance.</P><P>What is happening?</P><P>Ashade</P> Sat, 09 Apr 2011 21:56:28 GMT https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/multithreaded-performance-of-sparse-blas-not-good/m-p/766170#M252 ashade 2011-04-09T21:56:28Z multithreaded performance of sparse blas not good https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/multithreaded-performance-of-sparse-blas-not-good/m-p/766171#M253 With such benchmarks, the devil is in the details. You may be interested to see what Amdahl's Law states regarding your runs.<BR /><BR />If you want more specific help, you will have to document what you did, and state reasons why the results are not what was expected. Sun, 10 Apr 2011 12:09:27 GMT https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/multithreaded-performance-of-sparse-blas-not-good/m-p/766171#M253 mecej4 2011-04-10T12:09:27Z multithreaded performance of sparse blas not good https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/multithreaded-performance-of-sparse-blas-not-good/m-p/766172#M254 Ashade,<DIV><DIV>Do you mean that you see 5% of scalability with 4 cores vs 1 core?</DIV><DIV>what is the matrixes size? </DIV></DIV> Sun, 10 Apr 2011 15:56:39 GMT https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/multithreaded-performance-of-sparse-blas-not-good/m-p/766172#M254 Gennady_F_Intel 2011-04-10T15:56:39Z