MATLAB simplified for parallel applications
13 May 2008
The MathWorks has integrated its Parallel Computing Toolbox with its MATLAB optimisation toolboxes to help simplify the development of parallel applications.
Parallel computing capabilities are now integrated inside the optimisation solvers of MathWorks Optimisation Toolbox and Genetic Algorithm and Direct Search Toolbox, enabling users to solve computationally-intensive optimisation problems on multicore computers and computer clusters without significantly changing their existing programs.
The MathWorks optimisation toolboxes give engineers and scientists the tools needed to find optimal solutions, perform trade-off analysis, balance multiple design alternatives and quickly incorporate optimisation methods in their algorithms and models. The integration of select optimisation 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 optimisation problems that are amenable to parallel computing. Example applications include calibrating an automotive engine control unit with experimental data, identifying an aircraft design that minimises noise while maximising fuel efficiency and selecting a portfolio of stocks that maximise gains while minimising risk.
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.