How do I submit a “ADF” parallel job with Grid Engine?
ADF parallel jobs that are to be submitted to Grid Engine will use the MPI parallel environment and queues already defined for the HPCVL users. Users need to write a batch script that contains all the information needed by MPI and Grid Engine, and also the information needed to start ADF. The script is similar to the one used to run a serial ADF job. However, a few additional definitions are required. Grid Engine will start the MPI parallel environment (PE) with a given number of slots that you specify by the setting #$ -pe dist.pe {number of processes} where the number of processes requested replaces the expression in {}. An example of Grid Engine script for ADF parallel jobs on HPCVL machines can be found here. Note that you need to replace all entries enclosed in {} by the proper values. Back to Top… Where can I get further help? ADF is a complex software package, and requires some practice to be used efficiently. In this FAQ we can not explain its use in detail. A User’s Guides f
