With the help of Interactive Supercomputing (ISC's) Star-P software and technical support from Computer Sciences (CSC), defense systems researchers hope to eliminate the complexities and critical time delays of programming parallel algorithms required to analyze terabytes of satellite data on high-performance computers (HPCs).

Star-P is an interactive parallel computing platform that lets researchers write applications on desktop computers using The MathWorks' MATLAB, and run them instantly and interactively on an eight-processor SGI Altix 3000 Server. This eliminates the need to re-program the applications in C, Fortran or MPI languages to run on the parallel computer, which previously took months to years to complete.

"For years the military relied on radar information from land-based facilities and reconnaissance aircraft, but has recently expanded their missions to include satellite-based radar systems," said Mark Barnell, a systems engineer with CSC. "But where traditional radar images might measure 10 megabytes, satellite radar can easily inundate a facility with terabytes of data daily, dramatically complicating and delaying the analysis process. Satellite radar can't help our military readiness if we have to wait a long time for the analysis results."

With the AFRL's mission to "lead the discovery, development, and integration of affordable warfighting technologies for our air and space forces," a key goal of the AFRL is to enable an agile workforce. Lab researchers believe that Star-P's desktop interactivity and ease-of-use will help provide this agility. Barnell explained that since researchers were skilled at evaluating radar analysis algorithms using MATLAB, they wanted to preserve the familiarity and interactivity of their desktop environment while taking advantage of the computational power of parallel HPCs. Due to the time-sensitivity of their work, they cannot afford the time required to re-program their algorithms for parallel processing.

Star-P will enable researchers to leverage their Altix server with 28 gigabytes of memory to solve this computational challenge. The software enables standard MATLAB commands and functions to execute in a parallel manner transparently to the user. "They can now preserve their familiar workflow while tackling data sets an order of magnitude larger than they process on their desktops," added Barnell. "Furthermore, we can leverage a 2048 processor Altix HPC with two terabytes of memory at Wright Patterson Air Force Base in the future to solve even larger problems."

The system also benefits researchers by supporting both fine- and coarse-grained parallelization. Where some problems are memory bound and require large-scale memory access and inter-processor communications, others can be segmented to run on a series of independent processors. Star-P makes it easy for researchers to tap either parallel approach.

Related Links
Air Force Research Laboratory
Interactive Supercomputing
Computer Sciences