<div dir="ltr"><div class="gmail_extra"><div class="gmail_quote">On Thu, Mar 29, 2018 at 1:48 AM, TAY wee-beng <span dir="ltr"><<a href="mailto:zonexo@gmail.com" target="_blank">zonexo@gmail.com</a>></span> wrote:<br><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">
<div text="#000000" bgcolor="#FFFFFF">
<br>
<div class="m_7647832711676883853moz-cite-prefix">On 28/3/2018 5:45 PM, Matthew Knepley
wrote:<br>
</div>
<blockquote type="cite">
<div dir="ltr">
<div class="gmail_extra">
<div class="gmail_quote">On Tue, Mar 27, 2018 at 10:17 PM, TAY
wee-beng <span dir="ltr"><<a href="mailto:zonexo@gmail.com" target="_blank">zonexo@gmail.com</a>></span>
wrote:<br>
<blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">
<div text="#000000" bgcolor="#FFFFFF">
<p>Hi Dave,<br>
<br>
I looked at the output using log_view and re-compile.
However, although I use the same options "-xHost -g
-O3 -openmp" (some filenames and dir names are now
different but they are actually the same), I still get
different results timing. I have attach both, fast and
slow. So what else can I do to pinpoint the
differences?</p>
</div>
</blockquote>
<div>The solver options must be different. In Fast, there is
almost no time in LUFactor, but in Slow its half the time.</div>
<div><br>
</div>
<div> Matt <br>
</div>
</div>
</div>
</div>
</blockquote>
Hi Matt,<br>
<br>
Finally found that it was because I was using KSPRICHARDSON in the
new code. KSPGMRES in the old code is much faster.<br>
<br>
I also tried cg, lsqr, fgmres. CG and GMRES seem similar in term of
best performance. Are there any other recommendations to try? The
Poisson eqn is symmetric.<br></div></blockquote><div><br></div><div>Krylov solvers fundamentally do not matter for solving elliptic problems. It comes down to your preconditioner.</div><div> </div><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"><div text="#000000" bgcolor="#FFFFFF">
I also tried -pc_type mg -pc_mg_nlevels 2 instead of
-poisson_pc_type gamg -poisson_pc_gamg_agg_nsmooths 1.<br>
<br>
It reduces the runtime from 2.25 to 1.46min.<br></div></blockquote><div><br></div><div>Yes, GMG has faster setup time than AMG. The solve time should be similar.</div><div> </div><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"><div text="#000000" bgcolor="#FFFFFF">
However, I found that my subroutine is very similar to my momentum
subroutine, which is based on KSPSolve:<br>
<br>
0. DMDACreate, DMDACreate3d etc<br>
1. Assemble matrix<br>
2. KSPSetOperators, KSPSetType etc<br>
3. KSPSolve<br>
<br>
However, the 2D Poisson example in ex5f.F90 uses SNESSetDM,
SNESSolve etc. So does it matter if I use SNESSolve or KSPSolve if
I'm using -pc_type mg?<br></div></blockquote><div><br></div><div>Not really.</div><div><br></div><div> Thanks,</div><div><br></div><div> Matt</div><div> </div><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"><div text="#000000" bgcolor="#FFFFFF">
<blockquote type="cite">
<div dir="ltr">
<div class="gmail_extra">
<div class="gmail_quote">
<blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">
<div text="#000000" bgcolor="#FFFFFF">
<pre class="m_7647832711676883853m_-6652733264220142091moz-signature" cols="72">Thank you very much.
Yours sincerely,
==============================<wbr>==================
TAY Wee-Beng (Zheng Weiming) 郑伟明
Personal research webpage: <a class="m_7647832711676883853m_-6652733264220142091moz-txt-link-freetext" href="http://tayweebeng.wixsite.com/website" target="_blank">http://tayweebeng.wixsite.com/<wbr>website</a>
Youtube research showcase: <a class="m_7647832711676883853m_-6652733264220142091moz-txt-link-freetext" href="https://www.youtube.com/channel/UC72ZHtvQNMpNs2uRTSToiLA" target="_blank">https://www.youtube.com/channe<wbr>l/UC72ZHtvQNMpNs2uRTSToiLA</a>
linkedin: <a class="m_7647832711676883853m_-6652733264220142091moz-txt-link-abbreviated" href="http://www.linkedin.com/in/tay-weebeng" target="_blank">www.linkedin.com/in/tay-weeben<wbr>g</a>
==============================<wbr>==================</pre>
<div class="m_7647832711676883853m_-6652733264220142091moz-cite-prefix">On
27/3/2018 5:22 PM, Dave May wrote:<br>
</div>
<blockquote type="cite">
<div dir="ltr"><br>
<div class="gmail_extra"><br>
<div class="gmail_quote">On 27 March 2018 at
10:16, TAY wee-beng <span dir="ltr"><<a href="mailto:zonexo@gmail.com" target="_blank">zonexo@gmail.com</a>></span>
wrote:<br>
<blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">Hi,<br>
<br>
I have been compiling and building different
version of my CFD with the intel 2016, 2018
compilers, and also different compiling
options.<br>
<br>
I tested a version of my a.out and it is much
faster than the other a.out, using only 3 min
instead of more than 10min to solve a certain
case using GAMG.<br>
<br>
However, I can't recall how it was compiled. I
only know that I used the intel 2016 compiler.<br>
<br>
So is there any way I can find out how the
a.out was compiled? Like what options were
used?</blockquote>
<div><br>
</div>
<div>Since you posted to the list I presume
"a.out" links against petsc...</div>
<div>If so, run your code with </div>
<div> -log_view</div>
<div><br>
</div>
<div>Upon calling PetscFinalize(), you will get
all the options given to PETSc configure, plus
the CFLAGS, link lines, etc.</div>
<div><br>
</div>
</div>
</div>
</div>
</blockquote>
<br>
</div>
</blockquote>
</div>
<br>
<br clear="all"><span class="HOEnZb"><font color="#888888">
<div><br>
</div>
-- <br>
<div class="m_7647832711676883853gmail_signature" data-smartmail="gmail_signature">
<div dir="ltr">
<div>
<div dir="ltr">
<div>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</div>
<div><br>
</div>
<div><a href="http://www.caam.rice.edu/%7Emk51/" target="_blank">https://www.cse.buffalo.edu/~<wbr>knepley/</a><br>
</div>
</div>
</div>
</div>
</div>
</font></span></div>
</div>
</blockquote>
<br>
</div>
</blockquote></div><br><br clear="all"><div><br></div>-- <br><div class="gmail_signature" data-smartmail="gmail_signature"><div dir="ltr"><div><div dir="ltr"><div>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</div><div><br></div><div><a href="http://www.caam.rice.edu/~mk51/" target="_blank">https://www.cse.buffalo.edu/~knepley/</a><br></div></div></div></div></div>
</div></div>