<html>
<head>
<meta content="text/html; charset=ISO-8859-1"
http-equiv="Content-Type">
</head>
<body bgcolor="#FFFFFF" text="#000000">
<div class="moz-cite-prefix">On 27/9/2012 1:44 PM, Matthew Knepley
wrote:<br>
</div>
<blockquote
cite="mid:CAMYG4GnfEFaF8naVRO+thiKaKESDpGxv2pJ2ei0iFrtnZbpdZw@mail.gmail.com"
type="cite">On Thu, Sep 27, 2012 at 3:49 AM, TAY wee-beng <span
dir="ltr"><<a moz-do-not-send="true"
href="mailto:zonexo@gmail.com" target="_blank">zonexo@gmail.com</a>></span>
wrote:<br>
<div class="gmail_quote">
<blockquote class="gmail_quote" style="margin:0 0 0
.8ex;border-left:1px #ccc solid;padding-left:1ex">
Hi,<br>
<br>
I'm doing a log summary for my 3d cfd code. I have some
questions:<br>
<br>
1. if I'm solving 3 linear equations using ksp, is the result
given in the log summary the total of the 3 linear eqns'
performance? How can I get the performance for each individual
eqn?<br>
</blockquote>
<div><br>
</div>
<div>Use logging stages: <a moz-do-not-send="true"
href="http://www.mcs.anl.gov/petsc/petsc-dev/docs/manualpages/Profiling/PetscLogStagePush.html">http://www.mcs.anl.gov/petsc/petsc-dev/docs/manualpages/Profiling/PetscLogStagePush.html</a></div>
</div>
</blockquote>
<br>
I retried using :<br>
<br>
PetscLogStage stage<br>
<br>
call PetscInitialize(PETSC_NULL_CHARACTER,ierr)<br>
<br>
call PetscLogStageRegister("momentum",stage,ierr)<br>
<br>
call PetscLogStagePush(stage,ierr)<br>
<i><br>
</i><i>... 1st stage - solving momentum eqn</i><i> - run 1st logging</i>
<br>
<br>
call PetscLogStagePop(ierr)<br>
<br>
call PetscLogStageRegister("poisson",stage,ierr)<br>
<br>
call PetscLogStagePush(stage,ierr)<br>
<br>
<i>... 2nd stage - solve poisson eqn</i><i> - run 2nd logging</i><br>
<br>
call PetscLogStagePop(ierr)<br>
<br>
call PetscFinalize(ierr)<br>
<br>
I have attached the log_summary results. Turns out that there are 3
stages - 0,1 (momentum),2 (poisson). Shouldn't I be getting 2 stages
instead? How can I correct it? Or it doesn't matter?<br>
<blockquote
cite="mid:CAMYG4GnfEFaF8naVRO+thiKaKESDpGxv2pJ2ei0iFrtnZbpdZw@mail.gmail.com"
type="cite">
<div class="gmail_quote">
<div> </div>
<blockquote class="gmail_quote" style="margin:0 0 0
.8ex;border-left:1px #ccc solid;padding-left:1ex">
2. If I run my code for 10 time steps, does the log summary
gives the total or avg performance/ratio?<br>
</blockquote>
<div><br>
</div>
<div>Total.</div>
<div> </div>
<blockquote class="gmail_quote" style="margin:0 0 0
.8ex;border-left:1px #ccc solid;padding-left:1ex">
3. Besides PETSc, I'm also using HYPRE's native geometric MG
(Struct) to solve my Cartesian's grid CFD poisson eqn. Is
there any way I can use PETSc's log summary to get HYPRE's
performance? If I use boomerAMG thru PETSc, can I get its
performance?</blockquote>
<div><br>
</div>
<div>If you mean flops, only if you count them yourself and tell
PETSc using <a moz-do-not-send="true"
href="http://www.mcs.anl.gov/petsc/petsc-dev/docs/manualpages/Profiling/PetscLogFlops.html">http://www.mcs.anl.gov/petsc/petsc-dev/docs/manualpages/Profiling/PetscLogFlops.html</a></div>
<div><br>
</div>
<div>This is the disadvantage of using packages that do not
properly monitor things :)</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">
<span class="HOEnZb"><font color="#888888"><br>
-- <br>
Yours sincerely,<br>
<br>
TAY wee-beng<br>
<br>
</font></span></blockquote>
</div>
<br>
<br clear="all">
<div><br>
</div>
-- <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>
</blockquote>
<br>
</body>
</html>