Current Issue
Ready for an LCD speedo? 22/4/2008
MORE BLOG POSTS
PCIM Europe 
To help engineers and scientists model increasingly complex systems in less time by allowing development of parallel applications independently of the resources that are available for execution, The MathWorks recently announced four enhancements in its Matlab and Distributed Computing Toolbox products. The enhancements allow increased performance and large-data-set handling.
Matlab now supports multithreaded computation for multicore systems and 64-bit Solaris platforms. Distributed Computing Toolbox now offers designers the ability to develop applications that interleave parallel and serial code and interactively prototype parallel algorithms on a desktop computer by running four local Matlab sessions. With Matlab and Distributed Computing Toolbox, engineers can prototype parallel applications on multicore desktop computers via as many as four processors and four Matlab sessions. For more computing power, these applications can scale to a computer cluster without code change by using the Matlab Distributed Computing Engine. The applications can also include serial code that executes in the desktop machine.
Using the multithreading feature, Matlab applications using element-wise and linear- algebra functions can leverage multicore machines by simultaneously running multiple threads for improved performance. The 64-bit Solaris support allows engineers using Matlab to exploit the benefi ts of 64-bit computing to develop applications involving large data sets and computationally intensive tasks. Matlab 7.5 is available now for the Microsoft Windows, Solaris, Linux, and Macintosh platforms. US list prices start at $1900.
US list prices for the Distributed Computing Toolbox 3.2 begin at $1000. Prices for the Matlab Distributed Computing Engine start at $6000.
The MathWorks, www.mathworks.com