<?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 Need for data transfer directives in OpenCL using igpu in GPU Compute Software</title>
    <link>https://community.intel.com/t5/GPU-Compute-Software/Need-for-data-transfer-directives-in-OpenCL-using-igpu/m-p/1732338#M2214</link>
    <description>Hi,&lt;BR /&gt;&lt;BR /&gt;I have a Fortran code which runs fine using OpenACC on nvidia GPUs. I intend to run it on my intel iGPU. The parallelisation is done using DO CCONCURRENT. Will there be any need for using data transfer directives from opencl as my cpu and the igpu share the same memory?&lt;BR /&gt;&lt;BR /&gt;Thanks a lot!</description>
    <pubDate>Sun, 04 Jan 2026 21:19:22 GMT</pubDate>
    <dc:creator>Hest12</dc:creator>
    <dc:date>2026-01-04T21:19:22Z</dc:date>
    <item>
      <title>Need for data transfer directives in OpenCL using igpu</title>
      <link>https://community.intel.com/t5/GPU-Compute-Software/Need-for-data-transfer-directives-in-OpenCL-using-igpu/m-p/1732338#M2214</link>
      <description>Hi,&lt;BR /&gt;&lt;BR /&gt;I have a Fortran code which runs fine using OpenACC on nvidia GPUs. I intend to run it on my intel iGPU. The parallelisation is done using DO CCONCURRENT. Will there be any need for using data transfer directives from opencl as my cpu and the igpu share the same memory?&lt;BR /&gt;&lt;BR /&gt;Thanks a lot!</description>
      <pubDate>Sun, 04 Jan 2026 21:19:22 GMT</pubDate>
      <guid>https://community.intel.com/t5/GPU-Compute-Software/Need-for-data-transfer-directives-in-OpenCL-using-igpu/m-p/1732338#M2214</guid>
      <dc:creator>Hest12</dc:creator>
      <dc:date>2026-01-04T21:19:22Z</dc:date>
    </item>
  </channel>
</rss>

