https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Two-new-functions-in-V10-Beta/m-p/907217#M11809 <DIV id="r_text"><FONT size="2">In the help it is written:</FONT></DIV> <DIV><FONT size="2">"These routines perform the complex multiplication by forming the real and imaginary parts of the input matrices. It allows to use three real matrix multiplications and five real matrix additions, instead of the conventional four real matrix multiplications and two real matrix additions. The use of three real matrix multiplications only gives a 25% reduction of time in matrix operations. This can result in significant savings in computing time for large matrices."</FONT></DIV> <DIV> <DIV id="r_text"><FONT size="2">It would be desirable to note, that for IA32 dgemm in Intel MKL it is realized inefficiently (see: http://</FONT><A href="http://www.thesa-store.com/products/"><FONT size="2"></FONT></A><A href="https://community.intel.com/www.thesa-store.com/products/" target="_blank">www.thesa-store.com/products/</A><FONT size="2"> ).</FONT></DIV></DIV> Mon, 24 Sep 2007 19:53:00 GMT y_sigal 2007-09-24T19:53:00Z https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Two-new-functions-in-V10-Beta/m-p/907216#M11808 <P>Release notes and example code for MKL 10.0.006 Beta mention new functions CGEMM3M and ZGEMM3M, but no offer explanation of what they do. Does anybody here know? A link would suffice.</P> Mon, 24 Sep 2007 19:41:20 GMT https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Two-new-functions-in-V10-Beta/m-p/907216#M11808 rbarron 2007-09-24T19:41:20Z https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Two-new-functions-in-V10-Beta/m-p/907217#M11809 <DIV id="r_text"><FONT size="2">In the help it is written:</FONT></DIV> <DIV><FONT size="2">"These routines perform the complex multiplication by forming the real and imaginary parts of the input matrices. It allows to use three real matrix multiplications and five real matrix additions, instead of the conventional four real matrix multiplications and two real matrix additions. The use of three real matrix multiplications only gives a 25% reduction of time in matrix operations. This can result in significant savings in computing time for large matrices."</FONT></DIV> <DIV> <DIV id="r_text"><FONT size="2">It would be desirable to note, that for IA32 dgemm in Intel MKL it is realized inefficiently (see: http://</FONT><A href="http://www.thesa-store.com/products/"><FONT size="2"></FONT></A><A href="https://community.intel.com/www.thesa-store.com/products/" target="_blank">www.thesa-store.com/products/</A><FONT size="2"> ).</FONT></DIV></DIV> Mon, 24 Sep 2007 19:53:00 GMT https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Two-new-functions-in-V10-Beta/m-p/907217#M11809 y_sigal 2007-09-24T19:53:00Z