MetaCartSign in to MyCiteSeer

Include Citations | Advanced Search | Help

Include Citations | Advanced Search | Help

 

Download:
pdf
unknown authors
http://www.ieee-infocom.org/2002/papers/724.pdf
Add To MetaCart

Abstract:

An O(log 2 N) parallel algorithm for output queuing Abstract — Output queued switches are appealing because they have better latency and throughput than input queued switches. However, they are difficult to build: a direct implementation of an N × N output-queued switch requires the switching fabric and the packet memories at the outputs to run at N times the line rate. Attempts have been made to implement output queuing with slow components, e.g., by having memories at both inputs and outputs running at twice the line rate. In these approaches, even though the packet memory speed is reduced, the scheduler time complexity is high — at least Ω(N). We show that idealized output queuing can be simulated in a shared memory architecture with (3N − 2) packet memories running at the line rate, using a scheduling algorithm whose time complexity is O(log 2 N) on a parallel random access machine (PRAM). The number of processing elements and memory cells used by the PRAM are a small multiple of the size of the idealized switch. I.

Citations

5825 Introduction to Algorithms – Cormen, Leiserson, et al. - 1992
251 An Engineering Approach to Computer Networking – Keshav - 1997
152 The iSLIP Scheduling Algorithm for Input-Queued Switches – McKeown - 1999
100 Matching output queueing with a combined input output queued swtich – Chuang, Goel, et al. - 1998
26 Analysis of a packet switch with memories running slower than the line rate – Iyer, Awadallah, et al. - 2000
7 A sublinear parallel algorithm for stable matching – Feder, Megiddo, et al. - 1994
2 Synthesis of Parallel Algorithms, chapter Parallel Graph Matching – Vazirani - 1993
2 A fast parallel algorithm for routing in permutation networks – Diestel, Theory, et al. - 1998
1 APPENDIX A. Direct implementation of matching routine We run log Γ iteration of the 2-coloring based reduction procedure described below. Each iteration of the 2-coloring based reduction procedure reduces the degree of all the vertices to either the ceili – Feb - 1981