Title :
The Georgia Tech digital signal multiprocessor
Author :
Barnwell, Thomas P., III ; Madisetti, Vijay K. ; McGrath, Stephen J A
Author_Institution :
Sch. of Electr. Eng., Georgia Inst. of Technol., Atlanta, GA, USA
fDate :
7/1/1993 12:00:00 AM
Abstract :
Techniques for implementation of digital signal processing (DSP) algorithms on synchronous multiprocessors studied for the past ten years are discussed. This research is characterised as a theoretical investigation of optimality criteria for the implementation of DSP algorithms and the development of a unique approach that can achieve these optimality criteria. A result of this ongoing research program has been the development of a set of formal techniques for the automatic realization of optimal synchronous supercomputer implementations for a large class of iterative or recursive DSP algorithms. Three experimental laboratory digital signal microprocessor (DSMP) systems designed to provide experimental verification of the theoretical results are described. This has provided important feedback to drive the theoretical developments. Compilers that take flow graph specifications of algorithms and generate optimal multiprocessor code are also discussed
Keywords :
digital signal processing chips; parallel algorithms; parallel architectures; signal processing; DSP algorithms; Georgia Tech digital signal multiprocessor; MIMD scheduling; compilers; digital signal processing; flow graph specifications; iterative algorithms; optimal multiprocessor code; optimal synchronous supercomputer implementations; optimality criteria; recursive algorithms; synchronous multiprocessors; Decoding; Digital signal processing; Iterative algorithms; Laboratories; Microprocessors; Parallel processing; Prototypes; Signal design; Signal processing algorithms; Supercomputers;
Journal_Title :
Signal Processing, IEEE Transactions on
