-
IEEE Communications Magazine. 01/2011; 49:83-87.
-
2010 International Conference on Machine Vision and Human-machine Interface, MVHI 2010, Kaifeng, China, April 24-25, 2010; 01/2010
-
[show abstract]
[hide abstract]
ABSTRACT: PIM-SM (Protocol Independent Multicast-Sparse Mode) is a main multicast routing protocol in the IPv6 (Internet Protocol version
6). It can use either a shared tree or a shortest path tree to deliver data packets, consequently the multicast IP lookup
engine requires, in some cases, two searches to get a correct lookup result according to its multicast forwarding rule, and
it may result in a new requirement of doubling the lookup speed of the lookup engine. The ordinary method to satisfy this
requirement in TCAM (Ternary Content Addressable Memory) based lookup engines is to exploit parallelism among multiple TCAMs.
However, traditional parallel methods always induce more resources and higher design difficulty. We propose in this paper
a novel approach to solve this problem. By arranging multicast forwarding table in class sequence in TCAM and making full
use of the intrinsic characteristic of the TCAM, our approach can get the right lookup result with just one search and a single
TCAM, while keeping the hardware of lookup engine unchanged. Experimental results have shown that the approach make it possible
to satisfy forwarding IPv6 multicast packets at the full link rate of 20 Gb/s with just one TCAM with the current TCAM chip.
Journal of Electronics (China) 01/2009; 26(2):214-221.
-
2009 International Conference on Signal Acquisition and Processing, ICSAP 2009, Kuala Lumpur, Malaysia, April 3-5, 2009; 01/2009
-
Proceedings of the Second International Joint Conference on Computational Sciences and Optimization, CSO 2009, Sanya, Hainan, China, 24-26 April 2009, Volume 1; 01/2009
-
Proceedings of IEEE International Conference on Communications, ICC 2008, Beijing, China, 19-23 May 2008; 01/2008
-
[show abstract]
[hide abstract]
ABSTRACT: Recently, buffered-crossbar (CICQ) switch is becoming more and more attractive to high performance router builders than other bufferless schemes, as it can achieve throughput, rate and delay guarantees. In this article, we propose a practical scheduling algorithm called the least congested cross-point buffer first, shorted by LC<sup>2</sup>BF. The main features of this scheduling algorithm are in its easier implementation in hardware, as the complexity is merely associated with the size of the cross-point buffers, and fewer hardware resources are needed than existing schemes. By controlling size of the cross-point buffers, our scheduling scheme can achieve good delay and stability performances. Finally in this article, we present one hardware implement framework for our algorithm, according to it, users can implement our scheduling scheme using VHDL.
Wireless, Mobile and Multimedia Networks, 2006 IET International Conference on; 12/2006
-
[show abstract]
[hide abstract]
ABSTRACT: The convergence of diverse traffic requires modern networks to provide QoS (Quality of Service) solutions to time-critical applications. Due to its simplicity and scalability, the differentiated service (DiffServ) solution is expected to be widely deployed across the Internet. In this paper, we propose a distributed DiffServ supporting scheduling (DDSS) scheme based on buffered crossbar switches. The schedulers of the proposed DDSS scheme can be implemented on each input and each output independently and in parallel, hence are more practical and scalable. Simulation results show that DDSS scheme can provide minimum bandwidth guarantees for EF and AF traffic and fair bandwidth allocation for BE traffic. DDSS scheme also exhibits good delay performance for EF traffic and AF traffic through simulations.
Wireless, Mobile and Multimedia Networks, 2006 IET International Conference on; 12/2006
-
[show abstract]
[hide abstract]
ABSTRACT: This paper present a multiple input-crosspoint-output-queued (MICOQ) switch, and proved that the MICOQ switch with its dimension equal to two can exactly emulate OQ switch with no speedup. Furthermore, while increasing the dimension of MICOQ switch the multiple buffered crossbar of which can work under the line rate. All scheduling algorithms used in proving emulating OQ switch are distributed, thus are practical. Finally, for the simplicity of implementation, an engineering design scheme for MICOQ switch is presented, and the simulation results exhibit a good performance of the MICOQ switch
Communications and Networking in China, 2006. ChinaCom '06. First International Conference on; 11/2006
-
[show abstract]
[hide abstract]
ABSTRACT: Output queuing is well known for being able to offer high performance switching. Unfortunately, the high-speed memory requirements of OQ switch limit its use for large capacity switching architecture. Hence a practical manner for large capacity switching architecture to obtain high performance switching is to build novel switch architecture which can emulate output queued (OQ) switch. Most of the presented schemes either still need a mild speedup or need scheduling algorithms with great complexity. In this paper, we build a high performance switch architecture with port distributed memories which is denoted as PDM switch. It is proved by fluid model techniques that the PDM switch can achieve a throughput of 100% with no speedup when subjected to arbitrary distributed admissible traffic that satisfies the strong low of large numbers (SLLN). Furthermore, we prove that the PDM switch can exactly emulate an output queued (OQ) switch with no speedup, regardless of the incoming traffic pattern. Based on the PDM switch, we present a two stage priority round robin (TSPRR) algorithm. The simulation results illuminate that the PDM switch with TSPRR algorithm can obtain a preferable performance
Communications, Circuits and Systems Proceedings, 2006 International Conference on; 07/2006
-
[show abstract]
[hide abstract]
ABSTRACT: The combined input-crosspoint-queued (CICQ) crossbar switch is very appealing because it can obtain high throughput with simple scheduling mechanisms. However, in order to support multiple priority levels, separate queues per priority are required at each crosspoint, hence there needs much more memories and many priority schedulers to be implemented in a buffered crossbar, which is of great complexity. In this paper we propose a scheme that uses a hierarchical priority queuing mechanism in the input queues and a simple queue per crosspoint to effectively support multiple priorities. We present a priority weighted double round robin (PWDRR) scheduling algorithm in input scheduler to implement bandwidth allocation among multiple priorities and a simple compensation priority round robin (CPRR) scheduling policy in crosspoint scheduler to transfer cells to the output. The simulation results verify a preferable performance of our scheme.
Advanced Information Networking and Applications, 2006. AINA 2006. 20th International Conference on; 05/2006
-
20th International Conference on Advanced Information Networking and Applications (AINA 2006), 18-20 April 2006, Vienna, Austria; 01/2006
-
Proceedings of the Global Telecommunications Conference, 2006. GLOBECOM '06, San Francisco, CA, USA, 27 November - 1 December 2006; 01/2006
-
Grid and Cooperative Computing, Second International Workshop, GCC 2003, Shanghai, China, December 7-10, 2003, Revised Papers, Part I; 01/2003
-
[show abstract]
[hide abstract]
ABSTRACT: A new approximation of fair queuing called Compensating Round Robin (CRR) is presented in this paper. The algorithm uses packet-by-packet
scheduler with a compensating measure. It achieves good fairness in terms of throughput, requires only O(1) time complexity to process a packet, and is simple enough to be implemented in hardware. After the performances are analyzed,
the fairness and packet loss rate of the algorithm are simulated. Simulation results show that the CRR can effectively isolate
the effects of contending sources.
Journal of Electronics (China) 01/2002; 19(2):139-145.
