<HTML><HEAD></HEAD>
<BODY dir=ltr>
<DIV dir=ltr>
<DIV style="FONT-FAMILY: 'Calibri'; COLOR: #000000; FONT-SIZE: 12pt">
<DIV>Hello all,</DIV>
<DIV> </DIV>
<DIV>I’m trying to use paraview in parallel. For that I’ve got a self-compiled
paraview version 3.14 and I use client/server mode.</DIV>
<DIV>In paraview I use these settings: use multicore, remote render threshold
(100MByte), client outline threshold (0MByte) and interactive subsample rate
(2pixels).</DIV>
<DIV> </DIV>
<DIV>I’ve got unstructered test data. The data was created in four processes as
*.vtu file (4times 352MByte) or as a whole *.pvtu file.</DIV>
<DIV> </DIV>
<DIV>So I start with ssh the pvservers on the server (there are 48cores on the
server) with </DIV>
<DIV>mpirun –np ‘number’ ../pvserver –display localhost:0</DIV>
<DIV>and then I connect via my PC to this server (there’s a ethernet cable with
1GB/s between server and PC).</DIV>
<DIV> </DIV>
<DIV>I tried different numbers of pvservers (2,4,8 and 16).</DIV>
<DIV>I loaded the data and used different filters like wireframe, contour, slice
and clip and I moved the data around (with drag and drop).</DIV>
<DIV> </DIV>
<DIV>But I could only see a little improvement in the time of representation
(e.g. the contour filter took 5.3s on 4pvservers and 5s on 16pvservers).</DIV>
<DIV>I thought I could see a greater improvement.</DIV>
<DIV> </DIV>
<DIV>So why do I see no improvement or when can I see an improvement? Or am I
doing something wrong?</DIV>
<DIV> </DIV>
<DIV>Also I’m surprised that it took lesser than 4 times as long when I use the
whole data in compare with only a fourth of the data.</DIV>
<DIV>e.g. on 16 pvservers it took 6s to change the representation of a fourth of
the data to wireframe and it took 20s for the whole data</DIV>
<DIV>Why is this happening?</DIV>
<DIV> </DIV>
<DIV>Thank you for your help.</DIV>
<DIV> </DIV>
<DIV> </DIV>
<DIV>Greetings,</DIV>
<DIV>Kevin</DIV></DIV></DIV></BODY></HTML>