Executive Summary: A researcher needs to run one or more applications many times with varying inputs on a single community high-throughput computing (HTC) resource. Each application run is called a “job.” The complete set of jobs is called a “project.” Some jobs may use the outputs of other jobs as their inputs. (This is called a “dependency.”) Once the jobs and dependencies are specified to the system, the system executes them without further involvement by the researcher.
No effort or changes are proposed at this time.
|Component||User facing?||Component’s role in the capability|
|Service Provider Batch Processing Services||no||XSEDE's HPC Service Providers (SPs) provide batch processing systems on their resources. The batch processing system accepts tasks to be executed on the resource into one or more queues, schedules the tasks in each queue according to the queue's scheduling policy, then executes the tasks on the resource as scheduled. This batch processing system processes the tasks described in this use case when they are submitted by the dependency manager.|