vsched is a job scheduler that distributes jobs to a cluster of workstations and/or
to nodes of a multi-processor machine. The use of vsched to run serial jobs was
covered in this
module. You should understand these materials before continuing with
this topic.
The following terminology is used throughout this and other parallel programming
modules:
Node: One of the autonomous compute elements in the Velocity cluster.
Processor: One compute element on a node. E.g. a quad node is comprised of
four processors, each with its own cache, and all having shared memory.
Process or Task: A task is a unit of work to be performed by the computer.
An MPI program breaks work into tasks, each task to be performed on a processor.
The terms process and task are often used interchangeably. In this set of MPI documentation,
we use task, because processes and processors can get confusing. Note that other
materials, such as the MPI/Pro documentation, use the term process.
