Ahh, I forgot about the Power of 2 thing, that does explain it. Also, glad to hear it was accepted.. Woohoo! :)<br><br>As for the Data, that's what I did actually. The original files were a PLY and a Legacy VTK. I loaded them, painfully, and applied D3 + Extract Surface, then saved them back as PVTP's. So when I said the files were "load balanced", that's what I meant (they had been D3's & saved back in parallel).
<br><br>Is there any "preferred" implementation of MPI? We're using openMPI 1.0.1 here.<br><br><div><span class="gmail_quote">On 8/7/06, <b class="gmail_sendername">Wylie, Brian</b> <<a href="mailto:bnwylie@sandia.gov">
bnwylie@sandia.gov</a>> wrote:</span><blockquote class="gmail_quote" style="border-left: 1px solid rgb(204, 204, 204); margin: 0pt 0pt 0pt 0.8ex; padding-left: 1ex;"><div>
<div vlink="purple" link="blue" lang="EN-US">
<div dir="ltr" align="left"><span><font color="#0000ff" face="Arial" size="2">I wanted to interject a general comment.
</font></span></div>
<div dir="ltr" align="left"><span><font color="#0000ff" face="Arial" size="2"></font></span> </div>
<div dir="ltr" align="left"><span><font color="#0000ff" face="Arial" size="2">D3 is a 'heavy weight' load balancing filter. It's really
intended for unstructured data and, right now, it will take vtkPolydata and
turn it to vtkUnstructuredGrid.</font></span></div>
<div dir="ltr" align="left"><span><font color="#0000ff" face="Arial" size="2"></font></span> </div>
<div dir="ltr" align="left"><span><font color="#0000ff" face="Arial" size="2">You might just want to run it once, right after the reader,
and then run 'Extract Surface' to get back to vtkPolyData. You also might play
with the immediate mode and t-strip options to see if they make a big diff on
your rendering times.</font></span></div>
<div dir="ltr" align="left"><span><font color="#0000ff" face="Arial" size="2"></font></span> </div>
<div dir="ltr" align="left"><span><font color="#0000ff" face="Arial" size="2">Also, if your dataset has lots of files, you should see how
it runs without D3 at all, just for comparison. :)</font></span></div>
<div> </div>
<p><font size="2"> Brian Wylie - Org 1424<br> Sandia National
Laboratories<br> MS 0822 - Building 880/A1-J<br> (505)844-2238
FAX(505)845-0833 <br>
____
_ __<br> / __ \____
_________ | | / (_)__ _
__<br> / /_/ / __ `/ ___/ __ `/ | / / / _ \ | /| /
/<br> / ____/ /_/ / / / /_/ /| |/ / / __/ |/ |/
/<br> /_/ \__,_/_/ \__,_/
|___/_/\___/|__/|__/ <br>
Unleash the Beast<br></font></p>
<div> </div><br>
<blockquote dir="ltr" style="border-left: 2px solid rgb(0, 0, 255); padding-left: 5px; margin-left: 5px; margin-right: 0px;">
<div dir="ltr" align="left" lang="en-us">
<hr>
<font face="Tahoma" size="2"><b>From:</b>
paraview-bounces+bnwylie=<a href="mailto:sandia.gov@paraview.org" target="_blank" onclick="return top.js.OpenExtLink(window,event,this)">sandia.gov@paraview.org</a>
[mailto:<a href="mailto:paraview-bounces+bnwylie=sandia.gov@paraview.org" target="_blank" onclick="return top.js.OpenExtLink(window,event,this)">paraview-bounces+bnwylie=sandia.gov@paraview.org</a>] <b>On Behalf Of
</b>Moreland, Kenneth<br><b>Sent:</b> Monday, August 07, 2006 3:01
PM<br><b>To:</b> Randall Hand; Paraview List<br><b>Subject:</b> RE: [Paraview]
Even more Questions about ParaView on a Tiled Display<br></font><br></div></blockquote></div><div><span class="e" id="q_10cea7c029042f38_1">
<div></div>
<div>
<ol style="margin-top: 0in;" start="0" type="1">
<li style="color: maroon;"><font color="maroon" face="Courier New" size="2"><span style="font-size: 10pt;">I just finished
incorporating your patch. Because it's late, I'm going to wait until
tomorrow to check it in.</span></font> </li></ol>
<p><font color="maroon" face="Courier New" size="2"><span style="font-size: 10pt; color: maroon;"> </span></font></p>
<p><font color="maroon" face="Courier New" size="2"><span style="font-size: 10pt; color: maroon;">1. There
are two reasons that your memory usage is varying. First, it is true
that the memory is not freed-up from the Cut operation. The same is true
of the data between reader and the first D3. Second, if the number of
processes you have is not a power of 2, than D3 is not perfect at distributing
your data. You can have up to twice as much data on one node as the
other.</span></font></p>
<p><font color="maroon" face="Courier New" size="2"><span style="font-size: 10pt; color: maroon;"> </span></font></p>
<p><font color="maroon" face="Courier New" size="2"><span style="font-size: 10pt; color: maroon;">2. It does
seem strange that one would be so different than the other 12. I don't
have a good explanation for that.</span></font></p>
<p><font color="maroon" face="Courier New" size="2"><span style="font-size: 10pt; color: maroon;"> </span></font></p>
<p><font color="maroon" face="Courier New" size="2"><span style="font-size: 10pt; color: maroon;">3. I'm
guess that has to do with your MPI implementation. It looks like it
forks a couple of times. I notice that of the 3 processes, only one is
running. The other 2 may be parents that have forked and are now waiting
(perhaps as a precaution in case the MPI job crashes and needs to be shut down
cleanly).</span></font></p>
<p><font color="maroon" face="Courier New" size="2"><span style="font-size: 10pt; color: maroon;"> </span></font></p>
<p><font color="maroon" face="Courier New" size="2"><span style="font-size: 10pt; color: maroon;">4. That
sounds like a glitch. Go ahead and submit a bug
report.</span></font></p>
<p><font color="maroon" face="Courier New" size="2"><span style="font-size: 10pt; color: maroon;"> </span></font></p>
<p><font color="maroon" face="Courier New" size="2"><span style="font-size: 10pt; color: maroon;">-Ken</span></font></p>
<p><font color="maroon" face="Courier New" size="2"><span style="font-size: 10pt; color: maroon;"> </span></font></p>
<div style="border-style: none none none solid; border-color: -moz-use-text-color -moz-use-text-color -moz-use-text-color blue; border-width: medium medium medium 1.5pt; padding: 0in 0in 0in 4pt;">
<div>
<div style="text-align: center;" align="center"><font face="Times New Roman" size="3"><span style="font-size: 12pt;">
<hr align="center" size="2" width="100%">
</span></font></div>
<p><b><font face="Tahoma" size="2"><span style="font-weight: bold; font-size: 10pt; font-family: Tahoma;">From:</span></font></b><font face="Tahoma" size="2"><span style="font-size: 10pt; font-family: Tahoma;">
paraview-bounces+kmorel=<a href="mailto:sandia.gov@paraview.org" target="_blank" onclick="return top.js.OpenExtLink(window,event,this)">sandia.gov@paraview.org</a>
[mailto:<a href="mailto:paraview-bounces+kmorel=sandia.gov@paraview.org" target="_blank" onclick="return top.js.OpenExtLink(window,event,this)">paraview-bounces+kmorel=sandia.gov@paraview.org</a>] <b><span style="font-weight: bold;">
On Behalf Of </span></b>Randall Hand<br><b><span style="font-weight: bold;">Sent:</span></b> Monday, August 07, 2006 2:28
PM<br><b><span style="font-weight: bold;">To:</span></b> Paraview
List<br><b><span style="font-weight: bold;">Subject:</span></b> [Paraview] Even
more Questions about ParaView on a Tiled
Display</span></font></p></div>
<p><font face="Times New Roman" size="3"><span style="font-size: 12pt;"> </span></font></p>
<p><font face="Times New Roman" size="3"><span style="font-size: 12pt;">Ok, so I've got my Mullions code (still looking for
any comments about that) working on our RenderWall and I'm noticing some
interesting behaviour that i've got some questions about.<br><br>In this
cluster, we have 12 nodes + 1 head node, each one connected via a GeForce
7800GTX to a 1600x1200 LCD Display. Each node has 2 single-core Xeon
processors Hyperthreaded, for an "effective" 4 cores, and 8G of ram. All
connected via Infiniband. I've loaded up 2 PVTP datasets:
<br> a) Dataset A is a 52Million Triangle 24-part surface, RGB per
point<br> b) Dataset B is a 67Million Triangle 12-part surface, no
data per point (Geometry only)<br><br>(Both datasets were load-balanced with
Paraview's D3 filter.) <br><br>Now when I load them in Paraview, with a Tiled
Display, they both load and I'm able to interact with them beautifully.
119Million Triangles rendered in 1s (for a still frame). I applied a
cutting plane to one of them, and then another D3 (to balance the newly cut
surface, right?), and the results are still fabulously interactive. But
a few things i've noticed: <br>1) Even tho the results are now "load balanced"
again (via the D3), my memory usage is still fairly varying. I'm seeing
numbers ranging from 1.8G to 3.8G on various nodes. Is this because the
memory isn't really freed-up from the Cut operation? <br>2) One of my 12 nodes
is basically "idle". While the other 11 nodes show runtimes of over
250minutes on the pvserver process, one node shows less than 5. Images
are visible on all 12 displays.<br>3) On every node I have 3 processes.
4 I would understand, and 1 I had expected. But 3? It seems one is
for the Rendering & MPI work, while the other 2 are for computations (one
has the usual spinlock runtime of 250+minutes, while the others have
0.00).<br><br>An example:</span></font></p>
<div style="margin-left: 30pt;">
<p><font face="Courier New" size="3"><span style="font-size: 12pt;">[rhand@plasma proc]$ pdsh
-a top -b -n1 | grep pvserver | sort<br>plasma01ib: 18580
rhand 25 0 1969M 1.9G 21052
R 25.0 25.0 275:25 1 pvserver<br>plasma01ib:
18581 rhand 25 0 1969M 1.9G 21052
S 0.0 25.0 0:00 3
pvserver<br>plasma01ib: 18582 rhand 25 0
1969M 1.9G 21052 S 0.0 25.0
0:00 3 pvserver<br>plasma02ib: 18367 rhand
25 0 1926M 1.9G 21052 R 25.0 24.5
275:22 1 pvserver <br>plasma02ib: 18368
rhand 25 0 1926M 1.9G 21052
S 0.0 24.5 0:00 0
pvserver<br>plasma02ib: 18369 rhand 25 0
1926M 1.9G 21052 S 0.0 24.5
0:00 0 pvserver<br>plasma03ib: 18407 rhand
25 0 3268M 3.2G 21052 R 25.2 41.7
275:20 1 pvserver<br>...(snip)...<br>plasma11ib: 20771
rhand 25 0 1997M 1.9G 21060
S 0.0 25.4 0:00 3
pvserver<br>plasma12ib: 18301 rhand 18 0
4161M 4.0G 21164 S 0.0 53.1
6:38 1 pvserver<br>plasma12ib: 18302 rhand
25 0 4161M 4.0G 21164 S 0.0
53.1 0:00 1 pvserver<br>plasma12ib: 18303
rhand 25 0 4161M 4.0G 21164
S 0.0 53.1 0:00 1 pvserver
</span></font></p></div>
<p><font face="Times New Roman" size="3"><span style="font-size: 12pt;"><br clear="all"><br>4) While interacting, the 2D Scalar
Bar seems to resize/move down to the display closest the origin (lower-left
corner), and then return to it's desired location when the full-res image is
rendered again. Is this a glitch, or by design? <br><br>So can someone
explain to me a bit of what's going on "behind the curtain"? I've also
had no luck chasing down what's going on with the Slow Renderings &mangled
options on tiled Displays (On the <b><span style="font-weight: bold;">production</span></b> 2.4.4 release, not my
customized mullion-enabled one)<br>--
<br>----------------------------------------<br>Randall Hand<br>Visualization
Scientist<br>ERDC MSRC-ITL
</span></font></p></div></div></span></div><div></div>
</div></blockquote></div><br><br clear="all"><br>-- <br>----------------------------------------<br>Randall Hand<br>Visualization Scientist<br>ERDC MSRC-ITL