Papers - FUNAHASHI Akira

An I/O mechanism on a dynamically reconfigurable processor-which should be moved: data or configuration?

H Amano, S Abe, K Deguchi, Y Hasegawa

International Conference on Field Programmable Logic and Applications, 2005 … 2005   347 - 352 2005

Research paper (scientific journal), Joint Work, Accepted

　View Summary

In some applications on Dynamically Reconfigurable Processor (DRP), the input/output of data stream occupies about 20% of total execution time. In order to hide the overhead of input/output, the separation of the I/O context and double-buffering mechanism are proposed. Using the mechanism, I/O overhead of six streaming processing programs can be completely hidden. Based on the analysis of I/O performance, two alternatives for executing parallel processing with multiple DRP Cores are compared and discussed. © 2005 IEEE.

• Access to Document (DOI)

Evolving a lingua franca and associated software infrastructure for computational systems biology: the Systems Biology Markup Language (SBML) project.

Hucka, M., Finney, A., Bornstein, B. J., Keating, S. M., Shapiro, B. E., Matthews, J., Kovitz, B. L., Schilstra, M. J., Funahashi, A., Doyle J. C., and Kitano, H.

IEE Systems Biology 1 ( 1 ) 41-53 - 53 2004.09

Research paper (scientific journal), Joint Work, Accepted

• Access to Document (DOI)

Molecular Interaction Map of Macrophage.

Oda, K., Kimura, T, Matsuoka, Y., Funahashi, A., Muramatsu, M., and Kitano, H.

AfCS Report 2 ( 14 ) 1-12 2004.08

Research paper (scientific journal), Joint Work

Molecular interaction map of a macrophage

K Oda, T Kimura, Y Matsuoka, A Funahashi, M Muramatsu, H Kitano

AfCS Research Reports 2 (14), 1-12  2004

Research paper (scientific journal), Joint Work, Accepted

CellDesigner: a process diagram editor for gene-regulatory and biochemical networks.

Funahashi, A., Tanimura, N., Morohashi, M., and Kitano, H.

BioSilico 1 ( 5 ) 159-162 2003.11

Research paper (scientific journal), Joint Work

• Access to Document (DOI)

[The ERATO Systems Biology Workbench and Systems Biology Markup Language: an integrated environment and standardization for systems biology].

Funahashi A

Tanpakushitsu kakusan koso. Protein, nucleic acid, enzyme 48 ( 7 ) 810 - 6 2003.06

Research paper (scientific journal), Joint Work, Accepted,  ISSN  0039-9450

The ERATO Systems Biology Workbench and Systems Biology Markup Language

Funahashi Akira

Tanpakushitsu kakusan koso. Protein, nucleic acid, enzyme 48 ( 7 ) 810 - 816 2003

ISSN  0039-9450

Z-routing: Adaptive routing on irregular networks

Igawa, Y. and Funahashi, A.

IPSJ Journal 43 ( 3 ) 754-763 2002.03

Research paper (scientific journal), Joint Work, Accepted

An Output Selection Function based on the characteristic of virtual channel

Sugiyama, S. and Funahashi, A.

IPSJ Journal 43 ( 3 ) 764-775 2002.03

Research paper (scientific journal), Joint Work, Accepted

Routing algorithms based on 2D turn model for irregular networks

Jouraku, A; Koibuchi, M; Amano, H; Funahashi, A

I-SPAN'02: INTERNATIONAL SYMPOSIUM ON PARALLEL ARCHITECTURES, ALGORITHMS AND NETWORKS, PROCEEDINGS    289 - 294 2002

Joint Work, Accepted

• Access to Document (DOI)

The Impact of Output Selection Function on Adaptive Routing.

Funahashi, A., Koibuchi, M., Jouraku, A., and Amano, H.

ISCA Information: An International Journal 4 ( 4 ) 541-550 2001.11

Research paper (scientific journal), Joint Work, Accepted

L-turn routing: An Adaptive Routing in Irregular Networks

Koibuchi, M., Funahashi, A., Jouraku, A., and Amano, H.

IPSJ Journal of High Performance Computing System (Information Processing Society of Japan (IPSJ))  42 ( SIG9 ) 119-134 - 134 2001.08

Research paper (scientific journal), Joint Work, Accepted,  ISSN  0-7695-1257-7

　View Summary

Network-based parallel processing using commodity personal computers has been widely developed. Since such systems require high degree of flexibility and scalability of wiring, a high-speed network with an irregular topology is often needed. In traditional routing algorithms for irregular networks, available paths are considerably restricted in order to avoid deadlocks. In this paper, we propose a novel routing algorithm called Left-up-first turn routing(L-turn routing), which makes a better traffic balancing in irregular networks by building a specific directed-graph. Result of simulations shows that L-turn routing achieves better performance than traditional ones with each topology.

Recursive Diagonal Torus: an interconnection network for massively parallel computers.

Yang, Y., Funahashi, A., Jouraku, A., Nishi, H., Amano, H., and Sueyoshi, T.

IEEE Trans. on Parallel and Distributed Systems 12 ( 7 ) 701-715 - 715 2001.07

Research paper (scientific journal), Joint Work, Accepted,  ISSN  1045-9219

• Access to Document (DOI)

The Impact of Output Selection Function on Adaptive Routing.

Koibuchi, M., Funahashi, A., Jouraku, A., and Amano, H.

IPSJ Journal 42 ( 4 ) 704-713 2001.04

Research paper (scientific journal), Joint Work, Accepted

Adaptive routing for Recursive Diagonal Torus.

Funahashi, A., Jouraku, A., and Amano, H.

IEICE Transactions on Information and Systems (The Institute of Electronics, Information and Communication Engineers)  J89-D-I ( 11 ) 1143-1153 - 1153 2000.11

Research paper (scientific journal), Joint Work, Accepted,  ISSN  09151915

　View Summary

相互結合網RDTは再帰構造をもつTorusの重なりから構成されており, 超並列計算機のプロセッサ間接続を行うために優れた性質を多くもっている.超並列計算機に用いられる相互結合網において, 混雑若しくは故障したノードを回避できるルーチングアルゴリズムは必要不可欠である.既存のベクトルルーチングはシンプルではあるが, 固定ルーチング(deterministic routing)であるためこのようなノードを迂回することはできない.本研究では, Duatoによる必要十分条件を用いることによりRDT(2, 4, 1)/α上でデッドロックフリーなadaptive routing algorithim D-RDTとFD-RDTを提案し, デッドロックフリーであることを証明し, 評価を行った.D-RDTは各ランク内のトーラスではfully adaptive routingを行うが, e-cube routingをベースにしているため使用するランク順が固定される.FD-RDTは自由にランクを使用することが可能なバーチャルチャネルを付加したことにより, D-RDTに比べルーチングの自由度は高い.シミュレーションによる評価の結果, 両アリゴリズムとも既存のdeterministic routingに比べ通過率, レイテンシともに性能向上が見られ, 特にFD-RDTを用いたルーチングでは顕著であった.

Torus assignment for an interconnection network recursive diagonal torus

Fan Qin, Yang Yulu, Funahashi Akira, Amano Hideharu

Proceedings of the International Symposium on Parallel Architectures, Algorithms and Networks, I-SPAN    74 - 79 1999

Joint Work, Accepted,  ISSN  1087-4089

　View Summary

<p>Recursive Diagonal Torus (RDT) is a class of interconnection network consisting of recursively overlaid two-dimensional square diagonal tori for massively parallel computers with up to 2¹⁶ nodes. Connection structures of the RDT vary according to the assignment of upper rank diagonal tori into a node. Although traditional simple assignment called RDT(2, 4, 1)/α shows enough performance under the uniform traffic, the congestion of low rank tori degrades the performance when local communication is dominant. In this paper, RDT(2, 4, 1)/β torus assignment is proposed, focusing on improving the performance for local communication. With a simplified simulation algorithm, results shows that RDT(2, 4, 1)/β improves the average distance compared with RDT(2, 4, 1)/α assignment when considering local area.</p>

A torus assignment for an interconnection network recursive diagonal torus

Q Fan, Y Yang, A Funahashi, H Amano

Proceedings Fourth International Symposium on Parallel Architectures … (IEEE COMPUTER SOC)     74 - 79 1999

Research paper (scientific journal), Joint Work, Accepted

　View Summary

Recursive Diagonal Torus (RDT) is a class of interconnection network consisting of recursively overlaid two-dimensional square diagonal tori for massively parallel computers with up to 2(16) nodes. Connection structures of the RDT vary according to the assignment of tipper rank diagonal tori into a node: Although traditional simple assignment called RDT(2,4,1)/alpha shows enough performance under the uniform traffic, the congestion of low rank tori degrades the performance when local communication is dominant.
In this paper RDT(2,4,1)/beta torus assignment is proposed, focusing an improving the performance for local communication. With a simplified simulation algorithm, result shows that RDT(2,4,1)/beta improves the average distance compared with RDT(2,4,1)/alpha assignment when considering local area.

Adaptive routing on the recursive Diagonal torus

A Funahashi, T Hanawa, T Kudoh, H Amano

International Symposium on High Performance Computing, 171-182  1997

Research paper (scientific journal), Joint Work, Accepted

Fault tolerance of the TBSF (Tandem Banyan Switching Fabrics) and PBSF (Piled Banyan Switching Fabrics).

Funahashi, A., Hanawa, T., and Amano, H.

IEICE Transactions on Information and Systems (IEICE-INST ELECTRONICS INFORMATION COMMUNICATIONS ENG)  E79-D ( 8 ) 1180-1189 - 1189 1996.08

Research paper (scientific journal), Joint Work, Accepted,  ISSN  09168532

　View Summary

Multistage Interconnection Networks (MIN) with multiple outlets are networks which can support higher bandwidth than those of nonblocking networks by passing multiple packets to the same destination. Fault recovery mechanisms are proposed for two of such networks (TBSF/PBSF) with the best use of their inherent Fault tolerant capability. With these mechanisms, on-the-try fault recovery is possible for multiple faults on switching elements. For the link fault, the networks are reconfigured after fault diagnosis, and the network is available with some performance degradation. The bandwidth degradation under multiple faults on link/element is analyzed with both theoretical models and simulation. Through the analysis, F-PBSF shows high fault tolerance under high traffic load and low reliability by using 3 or more banyan networks.