cfx5gtmconv
 

Hello.

Does anyone know if it's possible to run the cfx5gtmconv.exe in parallel (on a multiple-processors linux operating system)?

Specifically, I'm trying to convert a .cdb file into a .def file using the cfx5gtmconv on a supercomputer (access to memory isn't an issue). However, the size of the .cdb file is >9gb (40million nodes) and requires a substantial amount of RAM from each node to convert the data.

Hence, as cfx5gtmconv is by default run on only one node, in my case with 8 processors, so there is a limit of 8gb of memory; CFX is simply using more memory than the node has available. Yet, if i can tell cfx5gtmconv to run in parallel and use multiple nodes, i can reduce the per node memory requirements and it wont be limited to 8gb. any suggestions on how to do this?

thanks for the help in advance

Re: cfx5gtmconv
 

It doesn't run in parallel.

Can you split the mesh before saving it and convert each portion. You could then load each portion of the mesh into pre to reassemble it, though Pre is also serial, it may be irrelevant.

-CycLone