<div dir="ltr"><div class="gmail_default" style="font-family:comic sans ms,sans-serif;color:#38761d">It turned out to be an error in the way they installed the pnetcdf module, it's been fixed now. </div></div><div class="gmail_extra"><br><div class="gmail_quote">On Wed, Nov 9, 2016 at 4:55 PM, Michael Raymond <span dir="ltr"><<a href="mailto:mraymond@sgi.com" target="_blank">mraymond@sgi.com</a>></span> wrote:<br><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"> This is SGI MPT bug 1066364. You have a pre-release of SGI MPT 2.15, as the actual release (which has the fix) doesn’t ship until the end of the month. This bug was discussed on this list a few weeks ago.<br>
<div><div class="h5"><br>
> On Nov 9, 2016, at 15:37 , Jim Edwards <<a href="mailto:jedwards@ucar.edu">jedwards@ucar.edu</a>> wrote:<br>
><br>
> I'm using pnetcdf on an sgi system with mpt/2.15, the system support group has installed a pnetcdf-1.7.0 module that causes runtime errors in my application, but when I download from subversion and build my own pnetcdf it works fine - are you aware of any fixes that could explain this? If so could you tag a new version so that I can ask the system folks to install it?<br>
> The runtime error is:<br>
> 10:MPT ERROR: rank:10, function:MPI_TYPE_CREATE_<wbr>HVECTOR, Invalid argument<br>
><br>
> Thanks,<br>
><br>
> --<br>
> Jim Edwards<br>
><br>
> CESM Software Engineer<br>
> National Center for Atmospheric Research<br>
> Boulder, CO<br>
<br>
</div></div>Michael A. Raymond<br>
SGI MPT Team Leader<br>
<a href="tel:1%20%28651%29%20683-7523" value="+16516837523">1 (651) 683-7523</a><br>
<br>
<br>
<br>
</blockquote></div><br><br clear="all"><div><br></div>-- <br><div class="gmail_signature" data-smartmail="gmail_signature"><div dir="ltr"><div><div><div>Jim Edwards<br><br></div><font size="1">CESM Software Engineer<br></font></div><font size="1">National Center for Atmospheric Research<br></font></div><font size="1">Boulder, CO</font> <br></div></div>
</div>