The MathWorks Introduces New Versions of MATLAB Parallel Computing Products

Products Enable Users to Take Advantage of Advanced Multicore Desktop Environments and Computer Clusters.

NATICK, Mass : The MathWorks today announced new versions of its MATLAB parallel computing products. Parallel Computing Toolbox enables users to run applications in up to eight cores, empowering MATLAB users to take more advantage of multicore desktop computers without major programming efforts. MATLAB Distributed Computing Server now supports Microsoft HPC Server 2008, providing users with access to the most recent enhancements in this cluster environment software. The MathWorks also introduced enhancements to other products in the MATLAB and Simulink product families that help users take advantage of advanced hardware systems.

High-end desktop machines are shipping with an ever-expanding number of cores, making them extremely powerful. Parallel Computing Toolbox helps users access the capabilities of their sophisticated hardware. The latest version allows engineers and scientists to easily program parallel applications that make use of the desktop hardware available to them by increasing the number of MATLAB sessions that users can run on their desktop computers from four to eight.

Looking beyond the desktop to larger computing resources, The MathWorks support for third-party schedulers, which now includes Microsoft HPC Server 2008, allows cluster administrators to integrate MathWorks parallel computing tools into existing distributed computing environments. Once the application is programmed, users can scale to larger resources, such as clusters and grids, without having to modify the code by relying on MATLAB Distributed Computing Server.

Enhancements to MathWorks parallel computing products come as analysts predict parallel programming challenges will continue to increase. According to IDC’s Worldwide Technical Computing 2009 Top 10 Predictions for 2009 (February 2009), “Rampant hardware parallelism from burgeoning core counts and system sizes is racing ahead of programming paradigms and the time available to programmers.”

“Users are looking to easily access the power of high performance computing resources, whether it be maximizing the multicore capabilities of their local desktops or using clusters and grids,” said Silvina Grad-Freilich, manager of parallel computing and application deployment marketing at The MathWorks. “By increasing the number of cores supported by Parallel Computing Toolbox, these users can leverage the increased hardware capabilities without requiring significant programming.”

The MathWorks also introduced several new features that take advantage of multicore desktops in other products, including MATLAB, Simulink Design Optimization, and Real-Time Workshop Embedded Coder.

Pricing and Availability

Parallel Computing Toolbox is available for the Microsoft Windows, Solaris, Linux, and Macintosh platforms. U.S. list prices start at $1,000.