<?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: Using GPU on IMX-8qxp for CNN Inference in i.MX Processors</title>
    <link>https://community.nxp.com/t5/i-MX-Processors/Using-GPU-on-IMX-8qxp-for-CNN-Inference/m-p/1248244#M171070</link>
    <description>&lt;P&gt;Hello parag,&lt;/P&gt;
&lt;P&gt;&amp;nbsp;&lt;/P&gt;
&lt;P&gt;1. The MX8X has the GPU7000Lite but not have NPU. the eIQ that can access is on L5.4.70.&lt;/P&gt;
&lt;P&gt;2. The eIQ documents are in your yocto relases.&lt;/P&gt;
&lt;P&gt;3. Is in the L5.4.70 BSP&lt;/P&gt;
&lt;P&gt;4. you can download the demos from &lt;A href="https://github.com/NXPmicro/gtec-demo-framework" target="_blank"&gt;https://github.com/NXPmicro/gtec-demo-framework&lt;/A&gt;&lt;/P&gt;
&lt;P&gt;&amp;nbsp;&lt;/P&gt;
&lt;P&gt;Regards&lt;/P&gt;
&lt;P&gt;&amp;nbsp;&lt;/P&gt;</description>
    <pubDate>Thu, 18 Mar 2021 14:30:18 GMT</pubDate>
    <dc:creator>Bio_TICFSL</dc:creator>
    <dc:date>2021-03-18T14:30:18Z</dc:date>
    <item>
      <title>Using GPU on IMX-8qxp for CNN Inference</title>
      <link>https://community.nxp.com/t5/i-MX-Processors/Using-GPU-on-IMX-8qxp-for-CNN-Inference/m-p/1248174#M171062</link>
      <description>&lt;P&gt;&lt;STRONG&gt;Context :&lt;/STRONG&gt;&lt;/P&gt;&lt;P&gt;I would like to inference my CNN model on IMX-8qxp unit. As your website states, inference is supported on Vulkan GPU on IMX-8qxp through eIQ for ARM-NN &amp;amp; TF-Lite models(&lt;A href="https://www.nxp.com/docs/en/fact-sheet/EIQ-FS.pdf" target="_blank" rel="noopener"&gt;https://www.nxp.com/docs/en/fact-sheet/EIQ-FS.pdf&lt;/A&gt; )[Page-2] . Following are the related questions.&amp;nbsp;&lt;BR /&gt;&lt;BR /&gt;&lt;STRONG&gt;Questions :&lt;/STRONG&gt;&lt;/P&gt;&lt;P&gt;1) IMX-8qxp has 1x4-shader Vulkan GPU. Can we access this GPU using latest eIQ package for CNN model inference?&amp;nbsp;&lt;BR /&gt;2) If yes, would you please share some reference documents?&amp;nbsp;&lt;BR /&gt;3) If GPU based CNN inference is supported, can we use eIQ as stand-alone module or does it BSP to be rebuilt?&amp;nbsp;&lt;BR /&gt;4) GpuAcc flag in ARM-NN supports only Mali-based GPU. Can you please point me to a sample C++ testapp in which eIQ is used for inference on Vulkan GPU?&lt;/P&gt;</description>
      <pubDate>Thu, 18 Mar 2021 12:49:21 GMT</pubDate>
      <guid>https://community.nxp.com/t5/i-MX-Processors/Using-GPU-on-IMX-8qxp-for-CNN-Inference/m-p/1248174#M171062</guid>
      <dc:creator>parag_jain</dc:creator>
      <dc:date>2021-03-18T12:49:21Z</dc:date>
    </item>
    <item>
      <title>Re: Using GPU on IMX-8qxp for CNN Inference</title>
      <link>https://community.nxp.com/t5/i-MX-Processors/Using-GPU-on-IMX-8qxp-for-CNN-Inference/m-p/1248244#M171070</link>
      <description>&lt;P&gt;Hello parag,&lt;/P&gt;
&lt;P&gt;&amp;nbsp;&lt;/P&gt;
&lt;P&gt;1. The MX8X has the GPU7000Lite but not have NPU. the eIQ that can access is on L5.4.70.&lt;/P&gt;
&lt;P&gt;2. The eIQ documents are in your yocto relases.&lt;/P&gt;
&lt;P&gt;3. Is in the L5.4.70 BSP&lt;/P&gt;
&lt;P&gt;4. you can download the demos from &lt;A href="https://github.com/NXPmicro/gtec-demo-framework" target="_blank"&gt;https://github.com/NXPmicro/gtec-demo-framework&lt;/A&gt;&lt;/P&gt;
&lt;P&gt;&amp;nbsp;&lt;/P&gt;
&lt;P&gt;Regards&lt;/P&gt;
&lt;P&gt;&amp;nbsp;&lt;/P&gt;</description>
      <pubDate>Thu, 18 Mar 2021 14:30:18 GMT</pubDate>
      <guid>https://community.nxp.com/t5/i-MX-Processors/Using-GPU-on-IMX-8qxp-for-CNN-Inference/m-p/1248244#M171070</guid>
      <dc:creator>Bio_TICFSL</dc:creator>
      <dc:date>2021-03-18T14:30:18Z</dc:date>
    </item>
  </channel>
</rss>

