Translator Disclaimer
27 June 2006 Distributed computing architecture for image-based wavefront sensing and 2D FFTs
Author Affiliations +
Image-based wavefront sensing provides significant advantages over interferometric-based wavefront sensors such as optical design simplicity and stability. However, the image-based approach is computationally intensive, and therefore, applications utilizing the image-based approach gain substantial benefits using specialized high-performance computing architectures. The development and testing of these computing architectures are essential to missions such as James Webb Space Telescope (JWST), Terrestrial Planet Finder-Coronagraph (TPF-C and CorSpec), and the Spherical Primary Optical Telescope (SPOT). The algorithms implemented on these specialized computing architectures make use of numerous two-dimensional Fast Fourier Transforms (FFTs) which necessitate an all-to-all communication when applied on a distributed computational architecture. Several solutions for distributed computing are presented with an emphasis on a 64 Node cluster of digital signal processors (DSPs) and multiple DSP field programmable gate arrays (FPGAs), offering a novel application of low-diameter graph theory. Timing results and performance analysis are presented. The solutions offered could be applied to other computationally complex all-to-all communication problems.
© (2006) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Jeffrey S. Smith, Bruce H. Dean, and Shadan Haghani "Distributed computing architecture for image-based wavefront sensing and 2D FFTs", Proc. SPIE 6274, Advanced Software and Control for Astronomy, 627421 (27 June 2006);

Back to Top