Evaluating scalability of the 2-D FFT on parallel computers
- 30 December 2002
- proceedings article
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 109-116
- https://doi.org/10.1109/camp.1993.622464
Abstract
Parallel computers have demonstrated a remarkablepotential for achieving high performance at a reasonablecost for many computer vision and image processing(CVIP) applications. A major obstacle to theuse of parallel computers is the lack of a universallyaccepted metric to study the scalability of parallel algorithmsand architectures. In this paper, we applydifferent scalability measures to various 2-D FFT algorithmsand target architectures and compare the expectedperformance to the...Keywords
This publication has 11 references indexed in Scilit:
- On the scalability of FFT on parallel computersPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- The scalability of FFT on parallel computersIEEE Transactions on Parallel and Distributed Systems, 1993
- LogP: towards a realistic model of parallel computationPublished by Association for Computing Machinery (ACM) ,1993
- A methodology for performance evaluation of parallel applications on multiprocessorsJournal of Parallel and Distributed Computing, 1992
- Performance evaluation of parallel fast fourier transform on a multiprocessor workstationJournal of Parallel and Distributed Computing, 1991
- Ordered fast fourier transforms on a massively parallel hypercube multiprocessorJournal of Parallel and Distributed Computing, 1991
- Scalability of parallel machinesCommunications of the ACM, 1991
- A parallel FFT on an MIMD machineParallel Computing, 1990
- A bridging model for parallel computationCommunications of the ACM, 1990
- FAST FOURIER TRANSFORM ALGORITHM DESIGN AND TRADEOFFS ON THE CM-2International Journal of High Speed Computing, 1989