topic Cache blocking techniques for element-wise math in large arrays - Fortran in Intel® oneAPI Math Kernel Library https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Cache-blocking-techniques-for-element-wise-math-in-large-arrays/m-p/919304#M12843 <DIV></DIV> <DIV> <DIV>I have a CFD code that does a lot of element-wise (A(i,j)*B(i,j)) math with large arrays. roughly 500x500 R*8s, with most sections of the code using a half dozen of these (1.5MB) arrays at a time.</DIV> <DIV></DIV> <DIV>To clean up the code, and in a naive hope that IFC would figure out the best way to manage the work, we vectorized most of the code. </DIV> <DIV></DIV> <DIV>VTune still shows a lot of time wasted with various stores, even with higher optimizations.</DIV> <DIV></DIV> <DIV>Is there a simple technique or a library that can block these operations to be efficient on a Xeon? Hopefully without rewriting all the code!</DIV> <DIV></DIV> <DIV>Thread moved to MKL from Fortran/Windows.</DIV> <DIV></DIV> <DIV>Thanks,</DIV> <DIV></DIV> <DIV>Art</DIV></DIV> Thu, 13 Jan 2005 23:00:53 GMT art-croucher 2005-01-13T23:00:53Z Cache blocking techniques for element-wise math in large arrays - Fortran https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Cache-blocking-techniques-for-element-wise-math-in-large-arrays/m-p/919304#M12843 <DIV></DIV> <DIV> <DIV>I have a CFD code that does a lot of element-wise (A(i,j)*B(i,j)) math with large arrays. roughly 500x500 R*8s, with most sections of the code using a half dozen of these (1.5MB) arrays at a time.</DIV> <DIV></DIV> <DIV>To clean up the code, and in a naive hope that IFC would figure out the best way to manage the work, we vectorized most of the code. </DIV> <DIV></DIV> <DIV>VTune still shows a lot of time wasted with various stores, even with higher optimizations.</DIV> <DIV></DIV> <DIV>Is there a simple technique or a library that can block these operations to be efficient on a Xeon? Hopefully without rewriting all the code!</DIV> <DIV></DIV> <DIV>Thread moved to MKL from Fortran/Windows.</DIV> <DIV></DIV> <DIV>Thanks,</DIV> <DIV></DIV> <DIV>Art</DIV></DIV> Thu, 13 Jan 2005 23:00:53 GMT https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Cache-blocking-techniques-for-element-wise-math-in-large-arrays/m-p/919304#M12843 art-croucher 2005-01-13T23:00:53Z