<?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: Nd-range groups in Intel® oneAPI DPC++/C++ Compiler</title>
    <link>https://community.intel.com/t5/Intel-oneAPI-DPC-C-Compiler/Nd-range-groups/m-p/1730796#M4643</link>
    <description>&lt;P&gt;I’ve been working with &amp;nbsp;and work-group sizes in DPC++ recently, and I agree this can be confusing at first. One tip that helped me was to start with simple, evenly divisible global and local sizes so you can clearly see how &amp;nbsp;and behave. Once that’s working, you can adjust for performance. Also pay attention to how the work-group size affects memory access and barriers mismatched sizes or non-uniform divisions often lead to unexpected behavior. If you can share the specific kernel and the sizes you’re using, it might be easier to pinpoint where the issue is happening.&lt;/P&gt;</description>
    <pubDate>Fri, 19 Dec 2025 05:11:41 GMT</pubDate>
    <dc:creator>mbwhatpapp</dc:creator>
    <dc:date>2025-12-19T05:11:41Z</dc:date>
    <item>
      <title>Nd-range groups</title>
      <link>https://community.intel.com/t5/Intel-oneAPI-DPC-C-Compiler/Nd-range-groups/m-p/1726613#M4622</link>
      <description>Greetings! I would like to answer a question how the partitioning in nd-range works.&lt;BR /&gt;&lt;BR /&gt;I have a sycl::nd_range&amp;lt;2&amp;gt;(sycl::range&amp;lt;2&amp;gt;(6,3), sycl::range&amp;lt;2&amp;gt;(6,1)...) and expected to partition with 18/6=3 groups, however when i use item.get_group it shows that i have only one, zero number, group. Therefore how to make a 3 groups or, if its impossible with this approach, how to make a loop like in pseudocode:&lt;BR /&gt;&lt;BR /&gt;Total =6&lt;BR /&gt;Groups=3&lt;BR /&gt;NinGroup=Total/Groups&lt;BR /&gt;For(i=0, i&amp;lt;5, i++)&lt;BR /&gt;For(ii in TotalNinGroup)</description>
      <pubDate>Mon, 17 Nov 2025 07:28:04 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-oneAPI-DPC-C-Compiler/Nd-range-groups/m-p/1726613#M4622</guid>
      <dc:creator>alex2671</dc:creator>
      <dc:date>2025-11-17T07:28:04Z</dc:date>
    </item>
    <item>
      <title>Re: Nd-range groups</title>
      <link>https://community.intel.com/t5/Intel-oneAPI-DPC-C-Compiler/Nd-range-groups/m-p/1726636#M4623</link>
      <description>Solved a problem. I used to obtain group id as get_group(0), however should be get_group(1).</description>
      <pubDate>Mon, 17 Nov 2025 08:49:24 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-oneAPI-DPC-C-Compiler/Nd-range-groups/m-p/1726636#M4623</guid>
      <dc:creator>alex2671</dc:creator>
      <dc:date>2025-11-17T08:49:24Z</dc:date>
    </item>
    <item>
      <title>Re: Nd-range groups</title>
      <link>https://community.intel.com/t5/Intel-oneAPI-DPC-C-Compiler/Nd-range-groups/m-p/1730796#M4643</link>
      <description>&lt;P&gt;I’ve been working with &amp;nbsp;and work-group sizes in DPC++ recently, and I agree this can be confusing at first. One tip that helped me was to start with simple, evenly divisible global and local sizes so you can clearly see how &amp;nbsp;and behave. Once that’s working, you can adjust for performance. Also pay attention to how the work-group size affects memory access and barriers mismatched sizes or non-uniform divisions often lead to unexpected behavior. If you can share the specific kernel and the sizes you’re using, it might be easier to pinpoint where the issue is happening.&lt;/P&gt;</description>
      <pubDate>Fri, 19 Dec 2025 05:11:41 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-oneAPI-DPC-C-Compiler/Nd-range-groups/m-p/1730796#M4643</guid>
      <dc:creator>mbwhatpapp</dc:creator>
      <dc:date>2025-12-19T05:11:41Z</dc:date>
    </item>
  </channel>
</rss>

