Difference between revisions of "Parallel Computing Support User Guide"
Jump to navigation
Jump to search
Line 28: | Line 28: | ||
== Using MPI-START and mpiexec to perform non mpi workloads == | == Using MPI-START and mpiexec to perform non mpi workloads == | ||
In the example above, the hello_bin command will run with a single argument "hello" on each of the nodes allocated to the job. |
Revision as of 02:31, 2 March 2012
Summary
This page discusses support for generic parallel computing jobs on the EGI infrastructure. We consider using the MPI-START framework as a means for launching multiple jobs on a cluster. The are several clearly apparent application areas:
* Hadoop-On-Demand/myHadoop * Charm++ * Parallel R
This is a work in progress.
JDL requirements
As we are using the MPI-START framework, the format of the JDL is the same as for an MPI job. However, the executable hello_bin may launch any process
JobType = "Normal"; CPUNumber = 4; Executable = "starter.sh"; Arguments = "OPENMPI hello_bin hello"; InputSandbox = {"starter.sh", "hello_bin"}; OutputSandbox = {"std.out", "std.err"}; StdOutput = "std.out"; StdError = "std.err"; Requirements = member("MPI-START", other.GlueHostApplicationSoftwareRunTimeEnvironment) && member("OPENMPI", other.GlueHostApplicationSoftwareRunTimeEnvironment);
Using MPI-START and mpiexec to perform non mpi workloads
In the example above, the hello_bin command will run with a single argument "hello" on each of the nodes allocated to the job.