[Paraview] parallel MPI volume rendering

[Dan White]

Hi all,
I am testing the speed advantage of volume rendering in parallel -  
MPI with paraview
on the Sun microsystems server at corona.csc.fi

with the settings i have tried so far on a small dataset 56x56x56
with the render server running as pvserver-mpi
and the client running on my local OSX machine
pvclient
versions both 2.2

i am using 8 processors,
but not seeing any speed enhancement in volume rendering
compared to running it on my local machine with a single processor.

in fact it is much slower on the server using 8 processors

there is plenty of bandwidth between the server and my local machine

can anyone give me any pointers about the critical things to get  
right to get this to work.

In the end i want to do this with very large datasets that take too  
long to volume render on my local single processor machine.

cheers

Dan


Dr. Daniel James White BSc. (Hons.) PhD
Bioimaging Coordinator
Nanoscience Centre and Department of Biological and Environmental  
Sciences
Division of Molecular Recognition
Ambiotica C242
PO Box 35
University of Jyväskylä
Jyväskylä
FIN 40014
Finland

+358 14 260 4183 (work)
+358 468102840 (mobile)
http://www.bioimagexd.org
http://www.chalkie.org.uk
dan at chalkie.org.uk
white at cc.jyu.fi