<?xml version="1.0" encoding="UTF-8"?>
<rss xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns:taxo="http://purl.org/rss/1.0/modules/taxonomy/" version="2.0">
  <channel>
    <title>topic Re: IPP vs SPL low performance in Intel® Integrated Performance Primitives</title>
    <link>https://community.intel.com/t5/Intel-Integrated-Performance/IPP-vs-SPL-low-performance/m-p/867297#M8453</link>
    <description>&lt;DIV style="margin:0px;"&gt;That can be possible if you link with IPP static libraries and did not call ippStaticInit function which cause IPP static dispatcher switch to 'generic C' code instead of optimized branch.&lt;/DIV&gt;
&lt;DIV style="margin:0px;"&gt;Regards,&lt;BR /&gt; Vladimir&lt;/DIV&gt;
&lt;DIV style="margin:0px;"&gt;&lt;/DIV&gt;
&lt;P&gt;&lt;/P&gt;</description>
    <pubDate>Thu, 23 Oct 2008 17:16:24 GMT</pubDate>
    <dc:creator>Vladimir_Dudnik</dc:creator>
    <dc:date>2008-10-23T17:16:24Z</dc:date>
    <item>
      <title>IPP vs SPL low performance</title>
      <link>https://community.intel.com/t5/Intel-Integrated-Performance/IPP-vs-SPL-low-performance/m-p/867296#M8452</link>
      <description>&lt;P&gt;Hi,I wrote a simple application which compares performance of SPL and IPP libraries.I'm using function which searches maximum value in vector.Here is the source:&lt;/P&gt;
&lt;P&gt;DWORD time1,time2,SPL,IPP;float max;&lt;BR /&gt; int maxindex;&lt;/P&gt;
&lt;P&gt;float signal[32768];&lt;BR /&gt; for (UINT i=0;i&amp;lt;32768;++i)&lt;BR /&gt; signal&lt;I&gt; = i;&lt;BR /&gt; time1 = GetTickCount();&lt;BR /&gt; for (int i=0;i&amp;lt;1000;++i)&lt;BR /&gt; ippsMaxIndx_32f(signal,32768,&amp;amp;max,&amp;amp;maxindex); //it is IPP function&lt;BR /&gt; time2 = GetTickCount();&lt;BR /&gt;&lt;BR /&gt; IPP = time2-time1;&lt;BR /&gt;&lt;BR /&gt; time1 = GetTickCount();&lt;BR /&gt; for (int i=0;i&amp;lt;1000;++i)&lt;BR /&gt; max = nspsMaxExt(signal,32768,&amp;amp;maxindex); //it is SPL function&lt;BR /&gt; time2 = GetTickCount();&lt;BR /&gt;&lt;BR /&gt; SPL = time2-time1;&lt;BR /&gt; &lt;BR /&gt; printf("%s%d%s","SPL Performance:",SPL,"\n");&lt;BR /&gt; printf("%s%d%s","IPP Performance:",IPP,"\n");&lt;/I&gt;&lt;/P&gt;
&lt;P&gt;&lt;/P&gt;
&lt;P&gt;the result was very strange:&lt;/P&gt;
&lt;P&gt;SPL Performance:172&lt;BR /&gt;IPP Performance:203&lt;/P&gt;
&lt;P&gt;It is impossible tha IPP could be slower than SPL.&lt;/P&gt;
&lt;P&gt;&lt;/P&gt;</description>
      <pubDate>Tue, 14 Oct 2008 15:52:56 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-Integrated-Performance/IPP-vs-SPL-low-performance/m-p/867296#M8452</guid>
      <dc:creator>shdow</dc:creator>
      <dc:date>2008-10-14T15:52:56Z</dc:date>
    </item>
    <item>
      <title>Re: IPP vs SPL low performance</title>
      <link>https://community.intel.com/t5/Intel-Integrated-Performance/IPP-vs-SPL-low-performance/m-p/867297#M8453</link>
      <description>&lt;DIV style="margin:0px;"&gt;That can be possible if you link with IPP static libraries and did not call ippStaticInit function which cause IPP static dispatcher switch to 'generic C' code instead of optimized branch.&lt;/DIV&gt;
&lt;DIV style="margin:0px;"&gt;Regards,&lt;BR /&gt; Vladimir&lt;/DIV&gt;
&lt;DIV style="margin:0px;"&gt;&lt;/DIV&gt;
&lt;P&gt;&lt;/P&gt;</description>
      <pubDate>Thu, 23 Oct 2008 17:16:24 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-Integrated-Performance/IPP-vs-SPL-low-performance/m-p/867297#M8453</guid>
      <dc:creator>Vladimir_Dudnik</dc:creator>
      <dc:date>2008-10-23T17:16:24Z</dc:date>
    </item>
  </channel>
</rss>

