The Parallel Computing Toolbox is a toolbox within MATLAB. It lets you solve computationally-intensive and data-intensive problems using MATLAB and Simulink on your local multicore computer or the Shared Computing Cluster (SCC). GPU operations are also supported provided that Nvidia GPU graphics cards are installed. Many of the SCC nodes are equipped with Nvidia GPUs. Parallel processing operations such as parallel for-loops, parallel numerical algorithms, and message-passing functions let you implement task- and data-parallel algorithms in MATLAB. Converting serial MATLAB applications to parallel MATLAB applications generally requires few code modifications and no programming in a low-level language is necessary. You can run your applications interactively or in batch.

In MATLAB R2014a or newer, the PCT supports up to 32 workers on one computer or one node on a computer cluster. Currently on the SCC, MATLAB parallel computing on multiple cores of a single node is well supported, and the maximum number of cores on a single node is 28. However, parallel computing across nodes is not supported on the SCC.

If your MATLAB application is to run multiple independent tasks, such as parametric studies of an analysis, please consult the Running Multiple Batch Jobs With qsub Array Job Option page. This alternative method does not require the PCT.

Please visit the following Boston University-developed tutorial for more details about the MATLAB PCT.

A PCT User’s Guide is available online at the Mathworks site. (HTML, PDF).