<?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>Deciding between research and renewal allocations.</title>
  <link rel="alternate" href="https://conferences.xsede.org/c/message_boards/find_recent_posts?p_l_id=" />
  <subtitle>Deciding between research and renewal allocations.</subtitle>
  <entry>
    <title>Deciding between research and renewal allocations.</title>
    <link rel="alternate" href="https://conferences.xsede.org/c/message_boards/find_message?p_l_id=&amp;messageId=437268" />
    <author>
      <name>Neal E Davis</name>
    </author>
    <id>https://conferences.xsede.org/c/message_boards/find_message?p_l_id=&amp;messageId=437268</id>
    <updated>2013-01-10T20:27:05Z</updated>
    <published>2013-01-10T20:27:05Z</published>
    <summary type="html">My group has a currently active allocation, on Trestles and Kraken, which has been working reasonably well for the first portion of our research project.  We have found that the next stage of the problem generally requires much more memory than is typical on those machines per processor, leading us to partially pack the nodes and burn SUs unnecessarily.  Consequently, we&amp;#039;re thinking about putting in a request for access to Blacklight since it is a shared memory machine and will use XSEDE SUs more efficiently for those calculations.  Would it be better to put in this new request as a new &amp;#034;research&amp;#034; allocation, or to ask for a &amp;#034;renewal&amp;#034;?  (&amp;#034;Startup&amp;#034; is probably out of the question since that would push us back another three months in the application cycle.)</summary>
    <dc:creator>Neal E Davis</dc:creator>
    <dc:date>2013-01-10T20:27:05Z</dc:date>
  </entry>
</feed>

