The MathWorks Simplifies Development of Parallel Applications in MATLAB

Business Wire, May 12, 2008

Direct Support for Parallel Computing in MATLAB Optimization Toolboxes Now Available; Users Can Create Parallel Versions of Their Computationally-Intensive MATLAB Applications with Minimal Code Changes.

NATICK, Mass. -- The MathWorks today announced the integration of its Parallel Computing Toolbox with its widely used MATLAB optimization toolboxes to help further simplify the development of parallel applications. Parallel computing capabilities are now integrated inside the optimization solvers of MathWorks Optimization Toolbox and Genetic Algorithm and Direct Search Toolbox, enabling users to solve computationally-intensive optimization problems on multicore computers and computer clusters without significantly changing their existing programs.

The MathWorks optimization toolboxes give engineers and scientists the tools needed to find optimal solutions, perform tradeoff analysis, balance multiple design alternatives, and quickly incorporate optimization methods in their algorithms and models. The integration of select optimization solvers with Parallel Computing Toolbox allows for the use of available computational resources to solve more computationally-intensive problems than previously possible on a single core. The result is a reduction in the time to solution for optimization problems that are amenable to parallel computing. Example applications include calibrating an automotive engine control unit with experimental data, identifying an aircraft design that minimizes noise while maximizing fuel efficiency and selecting a portfolio of stocks that maximize gains while minimizing risk.

According to Jie Wu, high-performance computing (HPC) analyst for IDC, "Although revenue for hardware going into HPC reached an all-time high of 11.5 billion dollars in 2007, software development in this area will continue to be the number-one roadblock to further adoption of this advanced hardware. The MathWorks is taking the necessary steps toward helping the industry overcome this major hurdle by building solutions that allow engineers and scientist to easily program applications that make use of advanced parallel computing platforms."

"This latest announcement demonstrates our company's continued commitment to helping the industry overcome the challenges associated with development of parallel applications," said Silvina Grad-Freilich, manager of parallel computing and application deployment marketing of The MathWorks. "The parallel computing capabilities provided within our toolboxes allow MATLAB users to develop parallel applications using exactly the same functions that they use in their serial programs, empowering engineers and scientists to experience the benefits of high-performance computing without necessitating that they learn new skill sets."

Additional features with this release include support for two additional widely used schedulers in the Parallel Computing Toolbox: PBS Pro from Altair Grid Technologies and TORQUE. Support for third-party schedulers enable cluster administrators to integrate MathWorks parallel computing tools into their existing distributed computing environments.

About Parallel Computing Toolbox

Parallel Computing Toolbox offers features that simplify the development of parallel applications in MATLAB, including programming constructs such as parallel for-loops and distributed arrays that let users harness multicore and multiprocessor hardware environments. These constructs can be used without learning a complex parallel language or making significant changes to existing serial code. For further information, please visit the product Web site at: www.mathworks.com/products/distribtb/

About Optimization Toolbox

Optimization Toolbox extends the MATLAB technical computing environment with tools and widely used algorithms for standard and large-scale optimization. These algorithms solve constrained and unconstrained continuous and discrete problems. The toolbox includes functions for linear programming, quadratic programming, nonlinear optimization, nonlinear least squares, solving systems of nonlinear equations, multi-objective optimization, and binary integer programming. For further information, please visit the product Web site at: http://www.mathworks.com/products/optimization/

Genetic Algorithm and Direct Search Toolbox

Genetic Algorithm and Direct Search Toolbox software extends the optimization capabilities in MATLAB and Optimization Toolbox products with tools for using genetic algorithms, simulated annealing, and direct search. These algorithms can be used for problems that are difficult to solve with traditional optimization techniques, including problems that are not well defined or are difficult to model mathematically. For further information, please visit the product Web site at: www.mathworks.com/products/gads

About The MathWorks

The MathWorks is the world's leading developer of technical computing and Model-Based Design software for engineers and scientists in industry, government, and education. With an extensive product set based on MATLAB and Simulink, The MathWorks provides software and services to solve challenging problems and accelerate innovation in automotive, aerospace, communications, financial services, biotechnology, electronics, instrumentation, process, and other industries.