Parallel Computing Toolbox™ 3.3

Product Description

• Parallel Computing Toolbox Key Features
• Programming Task-Parallel Applications
• Programming Data-Parallel Applications
• Working in an Interactive Parallel Environment
• Working in a Batch Environment
• Scaling to a Cluster Using MATLAB® Distributed Computing Server™

Programming Data-Parallel Applications

For MATLAB algorithms that require large data set processing, Parallel Computing Toolbox provides distributed arrays and parallel functions. Using distributed arrays, you can allocate matrices of any data type across all workers participating in the parallel computation. Parallel functions let you perform mathematical operations such as indexing, matrix multiplication, decomposition, and transforms directly on distributed arrays. The toolbox also provides more than 150 parallel functions for distributed arrays, including linear algebra routines based on ScaLAPACK.

Using distributed arrays and associated functions simplifies the process of converting a serial application to a parallel MATLAB program. Because these parallel constructs handle the complexity of managing communication and coordination between algorithm segments, serial programs need few annotations to convert them to parallel MATLAB programs.

For explicit, fine-grained control over your parallelization scheme, Parallel Computing Toolbox functions provide access to message passing routines based on the MPI standard (MPICH2), including functions for send, receive, broadcast, barrier, and probe operations. These functions also require you to manage coordination between various segments of your algorithm.

Programming with distributed arrays. Distributed arrays and parallel algorithms let you create data-parallel MATLAB® programs with minimal changes to your code and without programming in MPI. Click on image to see enlarged view.