Enabling High-Productivity SIP Application Development: Modeling and Simulation of Superconducting Quantum Interference Filters

• DOI: 10.1109/hpcmp-ugc.2009.49
• Publication Date: 2011-03-15T10:42:57Z
• Authors: Juan C. Chaves; Alan Chalker; David Hudak; Vijay Gadepally; Fernando Escobar; Patrick Longhini
• Keywords: InfiniBand; Message Passing Interface

The inherent complexity in utilizing and programming high performance computing (HPC) systems is the main obstacle to widespread exploitation of HPC resources technologies Department Defense (DoD). Consequently, there persistent need simplify interface for generic user. This particularly acute Signal/Image Processing (SIP), Integrated Modeling Test Environments (IMT), related DoD communities where typical users have heterogeneous unconsolidated needs. Mastering traditional tools (C, MPI, etc.) often seen as a diversion energy that could be applied study given scientific domain. Many SIP instead prefer high-level languages (HLLs) within integrated development environments, such MATLAB. We report on our collaborative effort use HLL distribution called ParaM optimize parallelize compute-intensive Superconducting Quantum Interference Filter (SQIF) application provided by Navy SPAWAR Systems Center San Diego, CA. an open-source developed at Ohio Supercomputer (OSC), includes support processor architectures not supported MATLAB (e.g., Itanium POWER5) well high-speed interconnects InfiniBand Myrinet). make installations available Army Research Laboratory (ARL) Supercomputing Resource (DSRC) OSC perform successful optimization/parallelization SQIF application. may used assess feasibility using devices extremely sensitive detectors electromagnetic radiation which great importance general.