<br><br><div class="gmail_quote">2010/5/7 Matthew Knepley <span dir="ltr"><<a href="mailto:knepley@gmail.com">knepley@gmail.com</a>></span><br><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex;">
<div class="im">On Fri, May 7, 2010 at 2:06 PM, Pedro Torres <span dir="ltr"><<a href="mailto:torres.pedrozpk@gmail.com" target="_blank">torres.pedrozpk@gmail.com</a>></span> wrote:<br></div><div class="gmail_quote">
<div class="im"><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">
Hello,<div><br></div><div>I have a sparse linear system, block dense, one block for each process, and solve with cg and block jacobi (ICC(0)) as preconditioners, with different reordering. During my tests I found quasi linear speed on kspsetup() and KSPSetUpOnBlocks() using 1wd,nd,rcm reorderings, but using qmd I get superlinear speedup. My CPU is a Xeon 5410.</div>
<div><br></div><div>Is that possible or something is going wrong?, and if I want to explain that, what functions on this stage should I monitor??. I really </div><div><span style="font-family:arial, sans-serif;line-height:25px">appreciate</span> any advice. </div>
</blockquote><div><br></div></div><div>It is possible (but unlikely) that the ordering on a larger number of processes creates a better</div><div>preconditioner, particularly because ICC(0) is so unpredictable. You can try and separate</div>
<div>arithmetic efficiency from algorithmic efficiency by looking at the number of iterates between these </div></div></blockquote><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex;">
<div class="gmail_quote"><div>runs.</div></div></blockquote><div>Thanks for a swift response. I found that given an ordering, the number of iterations is almost <span class="Apple-style-span" style="font-family: arial, sans-serif; font-size: 13px; line-height: 19px; white-space: nowrap; -webkit-border-horizontal-spacing: 2px; -webkit-border-vertical-spacing: 2px; "> uniform,with just a little increase, but 1wd have the minimun numbers of iterations. May be I should look</span></div>
<div><span class="Apple-style-span" style="font-family: arial, sans-serif; font-size: 13px; line-height: 19px; white-space: nowrap; -webkit-border-horizontal-spacing: 2px; -webkit-border-vertical-spacing: 2px; ">in the ratio of cache miss of MatCholeskyFactorNumeric to explain this <span class="Apple-style-span" style="line-height: 25px; white-space: normal; -webkit-border-horizontal-spacing: 0px; -webkit-border-vertical-spacing: 0px; font-size: small; ">behavior, rigth?.</span></span></div>
<div><span class="Apple-style-span" style="font-family: arial, sans-serif; font-size: 13px; line-height: 19px; white-space: nowrap; -webkit-border-horizontal-spacing: 2px; -webkit-border-vertical-spacing: 2px; "><span class="Apple-style-span" style="line-height: 25px; white-space: normal; -webkit-border-horizontal-spacing: 0px; -webkit-border-vertical-spacing: 0px; font-size: small; ">Thanks a lot!</span></span></div>
<blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex;"><div class="gmail_quote"><div> Matt</div><div class="im"><div> </div><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">
<div>Thanks in advance.</div><div><div><br>-- <br>Pedro Torres<br>GESAR/UERJ<br>Rua Fonseca Teles 121, São Cristóvão<br>Rio de Janeiro - Brasil<br>
</div></div>
</blockquote></div></div><font color="#888888"><br><br clear="all"><br>-- <br>What most experimenters take for granted before they begin their experiments is infinitely more interesting than any results to which their experiments lead.<br>
-- Norbert Wiener<br>
</font></blockquote></div><br><br clear="all"><br><br>