FFTs in external or hierarchical memory
The Journal of Supercomputing
Introduction to parallel algorithms and architectures: array, trees, hypercubes
Introduction to parallel algorithms and architectures: array, trees, hypercubes
Parallel 1D-FFT computation on constant-valence multicomputers
Software—Practice & Experience
Parallel programming: techniques and applications using networked workstations and parallel computers
IEEE/ACM Transactions on Networking (TON)
Parallel Computers: Theory and Practice
Parallel Computers: Theory and Practice
Parallel Computing Using Optical Interconnections
Parallel Computing Using Optical Interconnections
Routing and wavelength assignment in optical networks
IEEE/ACM Transactions on Networking (TON)
MPPOI '98 Proceedings of the The Fifth International Conference on Massively Parallel Processing Using Optical Interconnections
Two parallel implementations for one dimension FFT on symmetric multiprocessors
ACM-SE 42 Proceedings of the 42nd annual Southeast regional conference
Cost-Effective Designs of WDM Optical Interconnects
IEEE Transactions on Parallel and Distributed Systems
Optimal hypercube simulation on the partitioned optical passive stars network
The Journal of Supercomputing
Routing and wavelength assignment for hypercube in array-based WDM optical networks
Journal of Parallel and Distributed Computing
Routing and wavelength assignment for 3-ary n-cube in array-based optical network
Information Processing Letters
Hi-index | 0.00 |
Routing and wavelength assignment (RWA) is a central issue to increase efficiency and reduce cost in Wavelength Division Multiplexing (WDM) optical networks. In this paper, we address the problem of wavelength assignment for realizing parallel FFT on a class of regular optical WDM networks. We propose two methods for sequential mapping and shift-reversal mapping of FFT communication pattern to the optical WDM networks concerned. By sequential mapping, the numbers of wavelengths required to realize parallel FFT with 2n nodes on WDM linear arrays, rings, 2-D meshes and 2-D tori are 2n 驴 1, 2n 驴 1, 2max (k,n 驴 k) 驴 1 and 2max (k,n 驴 k) 驴 1 respectively. By shift-reversal mapping, the numbers of wavelengths required are max (3脳 2n 驴 3,2), 2n 驴 2, max (3脳 2max (k,n 驴 k) 驴 3,2) and 2max (k,n 驴 k) 驴 2. These results show that shift-reversal mapping outperforms sequential mapping. Our results have a clear significance for applications because FFT represents a common computation pattern shared by a large class of scientific and engineering problems and WDM optical networks as a promising technology in networking has an increasing popularity.