<?xml version="1.0" encoding="UTF-8"?>
<feed xmlns="http://www.w3.org/2005/Atom" xmlns:dc="http://purl.org/dc/elements/1.1/">
  <title>Is an entire node on Forge the minimum allocation?</title>
  <link rel="alternate" href="https://conferences.xsede.org/c/message_boards/find_thread?p_l_id=&amp;threadId=151478" />
  <subtitle>Is an entire node on Forge the minimum allocation?</subtitle>
  <entry>
    <title>Is an entire node on Forge the minimum allocation?</title>
    <link rel="alternate" href="https://conferences.xsede.org/c/message_boards/find_message?p_l_id=&amp;messageId=151477" />
    <author>
      <name>Stanley Seibert</name>
    </author>
    <id>https://conferences.xsede.org/c/message_boards/find_message?p_l_id=&amp;messageId=151477</id>
    <updated>2011-10-17T18:25:15Z</updated>
    <published>2011-10-17T18:25:15Z</published>
    <summary type="html">Hi, after looking through the Forge users guide, I had one question:&lt;br /&gt;  When submitting a job, is the minimum resource allocation always an entire node (16 CPU cores + 6 CUDA devices)?  (I see that the charging formula is in units of nodes, not CUDA devices.)&lt;br /&gt;&lt;br /&gt;We typically run our software locally in a mode where a job only uses 4 CPU cores and 1 CUDA device, but if the Forge scheduler is reserving an entire node for a job, our code will tremendously underutilize the hardware.  We could adjust things to use multiple CUDA devices per job without too much trouble, however.  Should we go that direction?</summary>
    <dc:creator>Stanley Seibert</dc:creator>
    <dc:date>2011-10-17T18:25:15Z</dc:date>
  </entry>
</feed>

