https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/No-scaling-for-mkl-dcsrsymv-correction/m-p/930832#M13723 <DIV></DIV><DIV>Thanks for your answer,</DIV><DIV></DIV><DIV>you're right - this size would have been rather small. I actually mixed things up a bit: I have a grid consisting of 40x40 points with 3 DOFs each. This means there are 1600x3=4800 unknowns and hence the dimension of the LES's matrixis rather 4800x4800. Although this is still much smaller than the problem size you were mentioning I think I should get a speed-up for that.</DIV><DIV>Maybe the level 2 Sparse BLAS routines aren't threaded at all?</DIV> Fri, 28 Apr 2006 14:33:37 GMT admin4 2006-04-28T14:33:37Z https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/No-scaling-for-mkl-dcsrsymv-correction/m-p/930832#M13723 <DIV></DIV><DIV>Thanks for your answer,</DIV><DIV></DIV><DIV>you're right - this size would have been rather small. I actually mixed things up a bit: I have a grid consisting of 40x40 points with 3 DOFs each. This means there are 1600x3=4800 unknowns and hence the dimension of the LES's matrixis rather 4800x4800. Although this is still much smaller than the problem size you were mentioning I think I should get a speed-up for that.</DIV><DIV>Maybe the level 2 Sparse BLAS routines aren't threaded at all?</DIV> Fri, 28 Apr 2006 14:33:37 GMT https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/No-scaling-for-mkl-dcsrsymv-correction/m-p/930832#M13723 admin4 2006-04-28T14:33:37Z