• Journal of KIISE:Computer Systems and Theory
• /
• v.35 no.8
• /
• pp.361-371
• /
• 2008

In this paper, the hypercube, hyperpetersen networks, whose degree is increasing in accordance with expansion of number of node and complete binary tree are one-to-one embedded into peterson-torus(PT) network which has fixed degree. The one-to-one embedding has less risk of overload or idle for the processor comparative to one-to-many and many-to-one embedding. For the algorithms which were developed on hypercube or hyperpetersen are used for PT network, it is one-to one embedded at expansion ${\doteqdot}1$, dilation 1.5n+2 and link congestion O(n) not to generate large numbers of idle processor. The complete binary tree is embedded into PT network with link congestion =1, expansion ${\doteqdot}5$ and dilation O(n) to avoid the bottleneck at the wormhole routing system which is not affected by the path length.

• Proceedings of the Korean Information Science Society Conference
• /
• 2008.06b
• /
• pp.580-583
• /
• 2008

본 논문은 정이진트리(full binary tree)를 PT 네트워크에 임베딩 가능함을 보인다. 메쉬 네트워크에 H-트리을 생성하는 방법을 응용하여 밀집을 1, 확장율 ${\doteqdot}5$ 그리고 연장율 $\frac{3(n+1)}{4}+1$에 일대일 임베딩 하였다. 밀집을 1에 임베딩 함으로써 store-and-forward 라우팅 방식과 윔홀 라우팅 방식에 적합하며 일대일 임베딩 함으로써 프로세서의 부하를 줄였다.