<?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 FFT and OpenMP in Intel® Integrated Performance Primitives</title>
    <link>https://community.intel.com/t5/Intel-Integrated-Performance/IPP-FFT-and-OpenMP/m-p/902250#M12945</link>
    <description>&lt;P&gt;Hi Austin,&lt;/P&gt;
&lt;P&gt;our experts said that you not necessary need to copy FFT spec for each thread. By IPP conventions, Spec is read-only data. So all threads can share the same Spec&lt;/P&gt;
&lt;P&gt;Regards,&lt;BR /&gt; Vladimir&lt;/P&gt;</description>
    <pubDate>Thu, 24 Apr 2008 19:33:56 GMT</pubDate>
    <dc:creator>Vladimir_Dudnik</dc:creator>
    <dc:date>2008-04-24T19:33:56Z</dc:date>
    <item>
      <title>IPP FFT and OpenMP</title>
      <link>https://community.intel.com/t5/Intel-Integrated-Performance/IPP-FFT-and-OpenMP/m-p/902249#M12944</link>
      <description>&lt;P&gt;Hello everyone,&lt;/P&gt;
&lt;P&gt;I would like to combine OpenMP and the FFT code and had a quick question. I havea for loop that is executing an FFT routine multiple times, but when it gets to the actual FFT routine, I have only allocated 1 memory space (see code) which all threads need to share, which is non-ideal.&lt;/P&gt;&lt;FONT size="2"&gt;
&lt;P&gt;IppsFFTSpec_R_32f* spec;&lt;/P&gt;&lt;FONT size="2"&gt;
&lt;P&gt;ippsFFTInitAlloc_R_32f(&amp;amp;spec, x, IPP_FFT_DIV_FWD_BY_N, ippAlgHintFast);&lt;/P&gt;&lt;FONT size="2"&gt;
&lt;P&gt;omp_set_num_threads(2);&lt;/P&gt;&lt;FONT color="#0000ff" size="2"&gt;
&lt;P&gt;#pragma&lt;/P&gt;&lt;/FONT&gt;&lt;FONT size="2"&gt; omp parallel &lt;/FONT&gt;&lt;FONT color="#0000ff" size="2"&gt;for&lt;/FONT&gt;&lt;P&gt;&lt;/P&gt;
&lt;P&gt;&lt;FONT color="#0000ff" size="2"&gt;for(int counter = 0; counter &amp;lt; 10000; counter++)&lt;/FONT&gt;&lt;/P&gt;
&lt;P&gt;&lt;FONT color="#0000ff"&gt;{&lt;/FONT&gt;&lt;/P&gt;
&lt;P&gt;&lt;FONT color="#008000"&gt;//I would like to allocate and copy the spec table so that the loops are independant&lt;/FONT&gt;&lt;/P&gt;
&lt;P&gt;&lt;FONT color="#0000ff"&gt;&lt;FONT size="2"&gt;ippsFFTFwd_RToPerm_32f((&lt;/FONT&gt;&lt;FONT color="#0000ff" size="2"&gt;float&lt;/FONT&gt;&lt;FONT size="2"&gt;*)ptrFFTVector, (&lt;/FONT&gt;&lt;FONT color="#0000ff" size="2"&gt;float&lt;/FONT&gt;&lt;FONT size="2"&gt;*)ptrFFTVector, spec, 0);&lt;/FONT&gt;&lt;/FONT&gt;&lt;/P&gt;
&lt;P&gt;&lt;FONT color="#0000ff"&gt;&lt;FONT size="2"&gt;}&lt;/FONT&gt;&lt;/FONT&gt;&lt;/P&gt;
&lt;P&gt;&lt;FONT color="#0000ff"&gt;&lt;FONT size="2"&gt;&lt;FONT color="#000000"&gt;The question is, how can I allocate and copy the spec space into another, loop independant local variable. In the IPP, there is a command to initialize an FFT table, a command to allocate memoryand initialize a table, but no command to allocate and copy a table. How can I do this?&lt;/FONT&gt;&lt;/FONT&gt;&lt;/FONT&gt;&lt;/P&gt;
&lt;P&gt;&lt;FONT color="#0000ff"&gt;&lt;FONT size="2"&gt;&lt;FONT color="#000000"&gt;Thanks in advance,&lt;/FONT&gt;&lt;/FONT&gt;&lt;/FONT&gt;&lt;/P&gt;
&lt;P&gt;&lt;FONT color="#0000ff"&gt;&lt;FONT size="2"&gt;&lt;FONT color="#000000"&gt;Austin&lt;/FONT&gt;&lt;/FONT&gt;&lt;/FONT&gt;&lt;/P&gt;&lt;/FONT&gt;&lt;FONT size="2"&gt;&lt;/FONT&gt;&lt;/FONT&gt;&lt;/FONT&gt;</description>
      <pubDate>Thu, 17 Apr 2008 16:49:24 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-Integrated-Performance/IPP-FFT-and-OpenMP/m-p/902249#M12944</guid>
      <dc:creator>amcelroy</dc:creator>
      <dc:date>2008-04-17T16:49:24Z</dc:date>
    </item>
    <item>
      <title>Re: IPP FFT and OpenMP</title>
      <link>https://community.intel.com/t5/Intel-Integrated-Performance/IPP-FFT-and-OpenMP/m-p/902250#M12945</link>
      <description>&lt;P&gt;Hi Austin,&lt;/P&gt;
&lt;P&gt;our experts said that you not necessary need to copy FFT spec for each thread. By IPP conventions, Spec is read-only data. So all threads can share the same Spec&lt;/P&gt;
&lt;P&gt;Regards,&lt;BR /&gt; Vladimir&lt;/P&gt;</description>
      <pubDate>Thu, 24 Apr 2008 19:33:56 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-Integrated-Performance/IPP-FFT-and-OpenMP/m-p/902250#M12945</guid>
      <dc:creator>Vladimir_Dudnik</dc:creator>
      <dc:date>2008-04-24T19:33:56Z</dc:date>
    </item>
    <item>
      <title>Re: IPP FFT and OpenMP</title>
      <link>https://community.intel.com/t5/Intel-Integrated-Performance/IPP-FFT-and-OpenMP/m-p/902251#M12946</link>
      <description>Hello Experts&lt;BR /&gt;How about speed? Will it slow down calculations? Maybe it is more comfortable to have separate copy of FFT table for each thread? Even if I am using architecture with shared memory - Quad Core.&lt;BR /&gt;Thanks&lt;BR /&gt;</description>
      <pubDate>Sun, 27 Apr 2008 06:38:45 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-Integrated-Performance/IPP-FFT-and-OpenMP/m-p/902251#M12946</guid>
      <dc:creator>you7878</dc:creator>
      <dc:date>2008-04-27T06:38:45Z</dc:date>
    </item>
  </channel>
</rss>

