MATLAB® Distributed Computing Server™ 3.3

Grid MP

Integration with Parallel Computing Toolbox and MATLAB Distributed Computing Server

Parallel Computing Toolbox and MATLAB Distributed Computing Server support the creation and execution of both distributed and parallel jobs with Grid MP scheduler from United Devices. Using the generic scheduler interface, you can integrate the toolbox and the engine with Grid MP.

Callbacks and dynamic addition of tasks to running jobs are not supported in Grid MP.

With the MathWorks job manager, the MATLAB Distributed Computing Server workers on the cluster run as a service and remain running at all times. With Grid MP, the workers run as an application that is started for the evaluation of tasks, and stopped when their tasks are complete. As a result, you incur an extra overhead of worker start-up and stop time. Create your tasks taking this overhead into account; for small tasks, this may represent a significant percentage of the overall execution time.

Features

Grid MP offers several features, including:

• Ability to manage multiple applications that include MathWorks distributed computing tools
• Provisioning capabilities to control and share heterogeneous enterprise resources based on departmental policies
• Ability to secure, automate and optimize the distribution, execution, and storage of compute-intensive applications and data within the enterprise
• Support for a comprehensive range of parallel job types and rapid application integration
• Workload optimization, optimized job scheduling, and guaranteed job completion with minimal impact to the network
• Scalability, manageability, and fault-tolerance
• Multiplatform support including Linux, Solaris, AIX, HP-UX, IRIX, Mac OS, and Windows

Information Resources

The following resources provide information on Grid MP:

• MATLAB Central File Exchange contains sample scripts and documentation created by United Devices.
• Documentation lists details on how to use the generic API available with the toolbox to integrate the toolbox and the engine with any scheduler in Using the Generic Scheduler Interface.
• Product Web site for Grid MP contains detailed information about the scheduler.