MATLAB Distributed Computing Server 4.0

Grid Engine and Sun N1 Grid Engine

Sun Microsystems supports both the open-source Grid Engine and the commercial N1 Grid Engine scheduling systems.

Integration with Parallel Computing Toolbox and MATLAB Distributed Computing Server

Parallel Computing Toolbox and MATLAB Distributed Computing Server can be integrated in computing environments managed by the two schedulers using the generic scheduler interface API that is available with the MathWorks products. Examples are also provided.

Features

Grid Engine offers several features, including:

• Ability to manage multiple applications that include MathWorks parallel computing products
• Enterprise-grade scalability
• Flexible, extensible resource management capabilities including resource reservation and backfilling
• Sophisticated scheduler with advanced planning abilities including support for job arrays
• Detailed statistics gathering for analysis and utility billing
• Support for virtually all commercial operation systems including Linux, Mac, and Windows

Information Resources

The following resources provide information on Grid Engine:

• Technical note demonstrates How to Integrate Parallel Computing Toolbox with Sun Grid Engine (SGE) scheduler.
• 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 Sun N1 Grid Engine contains detailed information about the scheduler.
• Project Web site for the Grid Engine open-source offering from Sun contains information about the project, source files, and documentation.