Parallel Computation of Data Summation for Multiple Problem Spaces on Partitioned Optical Passive Stars Network

In Partitioned Optical Passive Stars POPS network, nodes and couplers become free after slot to slot in some computation. It is necessary to efficiently utilize free couplers and nodes to be cost effective. Improving parallelism, we present the fast data summation algorithm for multiple problem spaces on POPS(g, g) with smaller number of nodes for the case of d = √ n = g. For the case of d > √ n > g, we simulate the calculation of large number of data items dedicated to larger system with many nodes on smaller system with smaller number of nodes. The algorithm is faster than the best know algorithm and using smaller number of nodes and groups make the system low cost and practical. Keywords— Partitioned optical passive stars network, parallel computing, optical computing, data sum

[1]  Sartaj Sahni,et al.  The Partitioned Optical Passive Stars Network: Simulations and Fundamental Operations , 2000, IEEE Trans. Parallel Distributed Syst..

[2]  Rami Melhem,et al.  The Communication Capabilities of Partitioned Optical Passive Stars Networks , 1998 .

[3]  Rami G. Melhem,et al.  Realizing Common Communication Patterns in Partitioned Optical Passive Stars (POPS) Networks , 1998, IEEE Trans. Computers.

[4]  Yitzhak Birk,et al.  Power-optimal layout of passive, single-hop, fiber-optic interconnections whose capacity increases with the number of stations , 1993, IEEE INFOCOM '93 The Conference on Computer Communications, Proceedings.

[5]  Aura Ganz,et al.  Reconfigurability of multi-star based lightwave LANs , 1992, [Conference Record] GLOBECOM '92 - Communications for Global Users: IEEE.

[6]  Sartaj Sahni.  Models and algorithms for optical and optoelectronic parallel computers , 1999, Proceedings Fourth International Symposium on Parallel Architectures, Algorithms, and Networks (I-SPAN'99).

[7]  A. S. Thoke,et al.  International Journal of Electrical and Computer Engineering 3:16 2008 Fault Classification of Double Circuit Transmission Line Using Artificial Neural Network , 2022 .

[8]  Donald M. Chiarulli,et al.  Partitioned optical passive star (POPS) multiprocessor interconnection networks with distributed control , 1996 .

[9]  Sartaj Sahni.  Matrix Multiplication and Data Routing Using a Partitioned Optical Passive Stars Network , 2000, IEEE Trans. Parallel Distributed Syst..

[10]  Afonso Ferreira,et al.  Embedding Tori in Partitioned Optical Passive Star Networks , 1997, SIROCCO.

[11]  Amitava Datta,et al.  Summation and routing on a partitioned optical passive stars network with large group size , 2003, IEEE Trans. Parallel Distributed Syst..

[12]  G. G. Stokes.  "J." , 1890, The New Yale Book of Quotations.

[13]  P. Berthome,et al.  Improved embeddings in POPS networks through stack-graph models , 1996, Proceedings of Massively Parallel Processing Using Optical Interconnections.

[14]  Rami G. Melhem,et al.  The Partitioned Optical Passive Stars (POPS) topology , 1995, Proceedings of 9th International Parallel Processing Symposium.