多點傳播在平行的應用程式中是常用的運算。多點傳播運算的效能大大地影響著應用程式以及通訊運算。在此論文中，我們利用了InfiniBand架構所提供的硬體多點傳播，在m-port n-tree 的InfiniBand 的網路上提出了多點傳播的機制。我們所提出機制的基本觀念是找出介於來源結點與在多點傳播群組結點中，所經過交換器的輸出埠聯集集合。基於聯集集合和多重LID訊息繞徑機制，我們可以建立出多點傳播群組所需用到的封包傳遞對映表。我們將提出的機制實作在m-port n-tree 的InfiniBand網路模擬器上。並且模擬了幾個一對多、多對多的多點傳播實例。在所有的模擬實例結果中，顯示出多點傳播機制的效能優於單點傳播機制。

The multicast operation is a very commonly used operation in parallel application programs. The performance of a multicast operation will affect applications programs and collective communication operations greatly. With the hardware multicast support of the InfiniBand architecture (IBA), in this thesis, we proposed an efficient multicast scheme for m-port n-tree InfiniBand networks. The basic concept of the proposed scheme is to find the union sets of the output ports of switches in the paths between the source processing node and each destination processing node in the multicast group. Based on the union sets and the multiple LID routing scheme, the forwarding table for a given multicast group can be constructed. We have implemented the proposed multicast scheme on an m-port n-tree InfiniBand network simulator. Several one-to-many and many-to-many multicast cases are simulated. The simulated results show that the proposed multicast scheme outperforms the unicast scheme for all simulated cases.

References
[1] C. -M. Chiang and L. M. Ni, “Deadlock-free multi-head wormhole routing,” Proceedings of the First High Performance Computing-Asia, 1995.
[2] J. Duato, S. Yalamanchili, and L. Ni, Interconnection Networks - An Engineering Approach, IEEE CS Press, 1997.
[3] Kai Hwang, Advanced Computer Architecture – Parallelism, Scalability, Programmability, McGraw-Hill, 1993.
[4] InfiniBand™ Trade Association, InfiniBand™ Architecture Specification Volume 1, Release 1. 1, November 2002.
[5] S. Kumar and L. V. Kale, “Scaling Collective Multicast on Fat-Tree Networks,” To appear in International Conference on Parallel and Distributed Systems, 2004.
[6] F. T. Leighton. Introduction to Parallel Algorithms and Architectures: Arrays, Trees, Hypercubes. Morgan Kaufmann Publishers, San Mateo, CA, USA, 1992.
[7] C. E. Leiserson, “Fat-Trees: Universal Networks for Hardware-Efficient Supercomputing,” IEEE Transactions on Computers, vol. 34, no. 10, October 1985, pp. 892-901.
[8] X. Y. Lin, Y. C. Chung, and T. Y. Huang, “A Multiple LID Routing Scheme for Fat-Tree-Based InfiniBand Networks,” Proceedings of IEEE International Parallel and Distributed Proceeding Symposiums (CD-ROM), Aril 2004.
[9] X. Lin, P. K. McKinley, and L. M. Ni, “Performance evaluation of multicast wormhole routing in 2D-mesh multicomputers,” Proceedings of the 1991 International Conference on Parallel Proceeding, vol. I, pp. 435-442, August 1991.
[10] J. Liu, A. R. Mamidala, and D. K. Panda, “Fast and Scalable MPI-Level Broadcast using InfiniBand’s Hardware Multicast Support,” Proceedings of IEEE International Parallel and Distributed Proceeding Symposiums (CD-ROM), Aril 2004.
[11] R. J. Littlefield, “Charaterizing and tuning communications performance for real applications,” Proceedings of the First Intel DELTA Applications Workshop, February 1992.
[12] P. López, J. Flich, and J. Duato, “Deadlock-Free Routing in InfiniBand™ through Destination Renaming,” in Proceedings of the International Conference on Parallel Processing, ICPP '01, Sept. 2001, pp. 427-434.
[13] F. Petrini and M. Vanneschi, “k-ary n-trees: High Performance Networks for Massively Parallel Architectures,” in Proceedings of the 11th International Parallel Processing Symposium, IPPS’97, April 1997, pp. 87-93.
[14] J. C. Sancho, A. Robles, and J. Duato, “Effective Strategy to Compute Forwarding Tables for InfiniBand Networks,” in Proceedings of the International Conference on Parallel Processing, ICPP '01, Sept. 2001, pp. 48-57.
[15] J. C. Sancho, A. Robles, J. Flich, P. López, and J. Duato, “Effective Methodology for Deadlock-Free Minimal Routing in InfiniBand Networks,” in Proceedings of the International Conference on Parallel Processing, ICPP '02, Aug. 2002, pp. 48-57.
[16] R. Sivaram, D. K. Panda, and C. B. Stunkel, “Efficient broadcast and multicast on multistage interconnection networks using multiport encoding,” Proceedings of the 8th IEEE Symposium on Parallel and Distributed Proceeding, pp. 36-45, October 1996.
[17] M. Valerio, L. Moser, and P. Melliar-Smith, “Recursively Scalable Fat-Trees as Interconnection Networks,” in Proceedings of the 13th IEEE International Phoenix Conference on Computers and Communications, April 1994, pp. 40-46.