<?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 FFT Filtering Phase Issues in Intel® Integrated Performance Primitives</title>
    <link>https://community.intel.com/t5/Intel-Integrated-Performance/FFT-Filtering-Phase-Issues/m-p/985902#M21795</link>
    <description>&lt;DIV&gt;I am trying to filter a 2048 point vector by performing an FFT, multiplying with a gaussian, and then performing an inverse FFT. All is well except I have a phase injected onto my signal when I multiply by the Gaussian. The Gaussian was created by performing an FFT on a Gaussian vector and it was put into the "pack" format. Becuase the Guassian was centered in a vector when I took the FFT, then a fixed phase delay was added by the imaginary components. Can you recommend a good way to get around this so that I can create a Gaussian filter with zero phase? The pack format is a bit confusing, so I was hoping to use the exisitng IPP calls to generate the pack formatted Gaussian and not need to manually create one. Are there any general tricks or advice on FFT filtering using IPP that you can pass along as well?&lt;/DIV&gt;</description>
    <pubDate>Fri, 08 Jul 2005 06:01:22 GMT</pubDate>
    <dc:creator>webbmb</dc:creator>
    <dc:date>2005-07-08T06:01:22Z</dc:date>
    <item>
      <title>FFT Filtering Phase Issues</title>
      <link>https://community.intel.com/t5/Intel-Integrated-Performance/FFT-Filtering-Phase-Issues/m-p/985902#M21795</link>
      <description>&lt;DIV&gt;I am trying to filter a 2048 point vector by performing an FFT, multiplying with a gaussian, and then performing an inverse FFT. All is well except I have a phase injected onto my signal when I multiply by the Gaussian. The Gaussian was created by performing an FFT on a Gaussian vector and it was put into the "pack" format. Becuase the Guassian was centered in a vector when I took the FFT, then a fixed phase delay was added by the imaginary components. Can you recommend a good way to get around this so that I can create a Gaussian filter with zero phase? The pack format is a bit confusing, so I was hoping to use the exisitng IPP calls to generate the pack formatted Gaussian and not need to manually create one. Are there any general tricks or advice on FFT filtering using IPP that you can pass along as well?&lt;/DIV&gt;</description>
      <pubDate>Fri, 08 Jul 2005 06:01:22 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-Integrated-Performance/FFT-Filtering-Phase-Issues/m-p/985902#M21795</guid>
      <dc:creator>webbmb</dc:creator>
      <dc:date>2005-07-08T06:01:22Z</dc:date>
    </item>
  </channel>
</rss>

