https://community.intel.com/t5/Intel-Integrated-Performance/need-help-optimizing-a-function/m-p/766919#M315 I need help optimizing an implementation of a function to compute the normal probability density function of a vector of n values. This is for use in a mex call from Matlab, so basically my goal is for the IPP-implemented version of the function to be faster than Matlab's "normpdf" toolbox function.<BR /><BR />I have an implementation working that uses ippsSub, not in place, and then ippsSqr, ippsMulC, ippsExp, and ippsDiv, all in place. I get the values in from Matlab -- I don't copy them -- then I use a Mathworks provided call for allocating an output array, then call the not-inplace subtraction from the input to the output buffer, and then do the rest of the arithmetic operations in place on the output buffer.<BR /><BR />The above results in an implementation that is faster than Matlab if n is less than about a million for single precision data. Above a million Matlab becomes consistently faster than my implementation. To me this doesn't make sense. If anything I would think this IPP-based implementation I am describing would be slower for small n's and faster for high n's. Can anyone explain the behavior I'm seeing? or provide suggestions for optimizations I can make?<BR /><BR />Also, in the IPP "Reference Manual, Volume 1: Signal Processing" from March 2009, I see that there used to be a call in the "Speech Recognition Functions" section called ippsExpNegSqr, but it doesn't seem to be around any more. What happened to this function? Tue, 23 Aug 2011 18:00:20 GMT Joe_Wezorek 2011-08-23T18:00:20Z https://community.intel.com/t5/Intel-Integrated-Performance/need-help-optimizing-a-function/m-p/766919#M315 I need help optimizing an implementation of a function to compute the normal probability density function of a vector of n values. This is for use in a mex call from Matlab, so basically my goal is for the IPP-implemented version of the function to be faster than Matlab's "normpdf" toolbox function.<BR /><BR />I have an implementation working that uses ippsSub, not in place, and then ippsSqr, ippsMulC, ippsExp, and ippsDiv, all in place. I get the values in from Matlab -- I don't copy them -- then I use a Mathworks provided call for allocating an output array, then call the not-inplace subtraction from the input to the output buffer, and then do the rest of the arithmetic operations in place on the output buffer.<BR /><BR />The above results in an implementation that is faster than Matlab if n is less than about a million for single precision data. Above a million Matlab becomes consistently faster than my implementation. To me this doesn't make sense. If anything I would think this IPP-based implementation I am describing would be slower for small n's and faster for high n's. Can anyone explain the behavior I'm seeing? or provide suggestions for optimizations I can make?<BR /><BR />Also, in the IPP "Reference Manual, Volume 1: Signal Processing" from March 2009, I see that there used to be a call in the "Speech Recognition Functions" section called ippsExpNegSqr, but it doesn't seem to be around any more. What happened to this function? Tue, 23 Aug 2011 18:00:20 GMT https://community.intel.com/t5/Intel-Integrated-Performance/need-help-optimizing-a-function/m-p/766919#M315 Joe_Wezorek 2011-08-23T18:00:20Z https://community.intel.com/t5/Intel-Integrated-Performance/need-help-optimizing-a-function/m-p/766920#M316 <P>Hi,</P><P>Regarding <B>speech recognition</B> functions</P><P>As in the IPP release notes - The speech recognition functions (ippSR domain) are not part of this release; this domain will continue to be supported in the IPP 6.1 product.</P><P><A href="http://software.intel.com/en-us/articles/intel-ipp-70-library-release-notes/"><SPAN style="text-decoration: underline;"></SPAN></A><A href="http://software.intel.com/en-us/articles/intel-ipp-70-library-release-notes/" target="_blank">http://software.intel.com/en-us/articles/intel-ipp-70-library-release-notes/</A></P><P>Regards,</P><P>Naveen Gv</P> Thu, 25 Aug 2011 10:53:56 GMT https://community.intel.com/t5/Intel-Integrated-Performance/need-help-optimizing-a-function/m-p/766920#M316 Naveen_G_Intel 2011-08-25T10:53:56Z https://community.intel.com/t5/Intel-Integrated-Performance/need-help-optimizing-a-function/m-p/766921#M317 Regarding your question about n, if I am not mistaken IPP is faster for smaller sets, MKL on the other hand should be faster for larger sets. Your mileage may vary.<BR /> Thu, 25 Aug 2011 22:04:01 GMT https://community.intel.com/t5/Intel-Integrated-Performance/need-help-optimizing-a-function/m-p/766921#M317 levicki 2011-08-25T22:04:01Z