<div dir="ltr"><div><div>Thanks. I now have a better matrix B in my eigenproblem than last time. Now I included MUMPS. I get this error when I give large matrices to solve:<br><br>'Error reported by MUMPS in numerical factorization phase: INFO(1)=-1, INFO(2)=0'<br><br></div>I checked the manual, there is only one instance of INFO(2)=0 and I am not able to get it. <br><br></div><div>Can someone help. <br><br></div><div>cheers,<br></div><div><br></div>Venkatesh<br><div><div><div><div><br><br><div class="gmail_extra"><br><div class="gmail_quote">On Mon, May 25, 2015 at 6:56 PM, Jose E. Roman <span dir="ltr"><<a href="mailto:jroman@dsic.upv.es" target="_blank">jroman@dsic.upv.es</a>></span> wrote:<br><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">Once again, you need a parallel linear solver.<br>
Read FAQ #6 and the corresponding section on the users manual.<br>
<a href="http://slepc.upv.es/documentation/faq.htm" target="_blank">http://slepc.upv.es/documentation/faq.htm</a><br>
Jose<br>
<div><div class="h5"><br>
<br>
El 25/05/2015, a las 15:18, venkatesh g escribió:<br>
<br>
> Hi,<br>
><br>
> I am solving the generalized eigen problem Ax=lambda Bx given in EX7 in Slepc manual.<br>
><br>
> Now I have restructured my matrix and I get reasonable answers.<br>
><br>
> However, when I submit the problem in multiple cores, it is accessing a large amount of memory than a serial job.<br>
><br>
> 1 Serial job - Amount of memory used = 18 GB<br>
><br>
> Parallel job in 240 cores - Amount of memory used = 456 GB<br>
><br>
> I have attached the performance log for the run.<br>
><br>
> I think it is loading the full matrix in each core for a parallel job, but I am not sure how to resolve or whether I am correct..<br>
><br>
> Kindly help.<br>
><br>
> cheers,<br>
> Venkatesh<br>
><br>
</div></div>> <performance_log.txt><br>
<br>
</blockquote></div><br></div></div></div></div></div></div>