Using MPI with CUDA C

Hi I am planning to use tera grid cluster( http://www.ncsa.illinois.edu/UserInfo/Reso…64TeslaCluster) to run my Monte Carlo fortran codes,with CUDA C,using fortran wrapper.I am planning to run
it on multiple nodes,each node having some tesla cards.MPI is used to communicate between processors.But I am confused that,when I run my code,each processor will need a GPU to run it’s part of the CUDA C code,hence each might compete for a particular Tesla card.How can I have control over this competition.Is there any way to do that?

What’s the ratio of CPUs to GPUs in a node?

I have got an reply for this question http://forums.nvidia.com/index.php?showtopic=152414 I will try this suggestion.I have cross posted this question,so sorry about that