Efficient routing in network-on-chip for 3D topologies

With the increasing of the integration capability intra-chip, nowadays numerous integrated systems explore a set of processing elements, such as in multicore processors. An efficient interconnection of those elements can be obtained via the use of Network on chip (NoC). This approach is similar to the traditional computer networks where, not restricted to multiprocessors, it is possible to interconnect several dedicated devices. Like other networks, NoCs can be arranged in different topologies, such as ring, mesh and torus. It has shared links that can be used in the transmission of packets of different nodes. Thus, the network congestion is an issue and must be treated to reduce delays. Algorithms based on ant colony optimisation have proven to be effective in static routing in systems designed to perform a fixed set of tasks, or where the communication pattern is known. This article introduces 3D ant colony routing (3D-ACR) and applies it as routing policy of NoCs having three different 3D topologies: mesh, torus and hypercube. Experimental results show that 3D ant colony routing performs consistently better compared with the previously proposed routing strategies.     

Mesh routing topologies for multi-FPGA systems

There is currently great interest in using fixed arrays of FPGAs for logic emulators, custom computing devices, and software accelerators. An important part of designing such a system is determining the proper routing topology to use to interconnect the FPGAs. This topology can have a great effect on the area and delay of the resulting system. Crossbar, Hierarchical Crossbar, and Mesh interconnection schemes have all been proposed for use in FPGA-based systems. In this paper, we examine Mesh interconnection schemes, and propose several constructs for more efficient topologies. These reduce interchip delays by more than 60% over the basic four-way Mesh     

Efficient lookup on unstructured topologies

We present LMS, a protocol for efficient lookup on unstructured networks. Our protocol uses a virtual namespace without imposing specific topologies. It is more efficient than existing lookup protocols for unstructured networks, and thus is an attractive alternative for applications in which the topology cannot be structured as a Distributed Hash Table (DHT). We present analytic bounds for the worst-case performance of LMS. Through detailed simulations (with up to 100,000 nodes), we show that the actual performance on realistic topologies is significantly better. We also show in both simulations and a complete implementation (which includes over five hundred nodes) that our protocol is inherently robust against multiple node failures and can adapt its replication strategy to optimize searches according to a specific heuristic. Moreover, the simulation demonstrates the resilience of LMS to high node turnover rates, and that it can easily adapt to orders of magnitude changes in network size. The overhead incurred by LMS is small, and its performance approaches that of DHTs on networks of similar size     

Provisioning of adaptability to variable topologies for routing schemes in MANETs

Frequent changes in network topologies caused by mobility in mobile ad hoc networks (MANETs) impose great challenges to designing routing schemes for such networks. Various routing schemes each aiming at particular type of MANET (e.g., flat or clustered MANETs) with different mobility degrees (e.g., low, medium, and high mobility) have been proposed in the literature. However, since a mobile node should not be limited to operate in a particular MANET assumed by a routing scheme, an important issue is how to enable a mobile node to achieve routing performance as high as possible when it roams across different types of MANETs. To handle this issue, a quantity that can predict the link status for a time period in the future with the consideration of mobility is required. In this paper, we discuss such a quantity and investigate how well this quantity can be used by the link caching scheme in the dynamic source routing protocol to provide the adaptability to variable topologies caused by mobility through computer simulation in NS-2.     

Efficient algorithm for FPGA board routing

A simple and fast algorithm for solving the two-terminal board level routing problem in FPGA-based logic emulation systems is presented. The method is based on the net scan selection process. Experimental results are the first implemented results for an algorithm presented previously. The comparison results show that the current approach achieves better effectiveness and uses less CPU time.     

Efficient routing in MANETs using ordered walks

A new approach for routing protocols operating in MANETs is presented in which flooding is not required to establish paths from sources to destinations on demand in MANETs of moderate size. The concept of ordered walk is introduced as a depth-first search (DFS) that does not rely on geographical or virtual coordinate information and is much more efficient than mere random walks. The benefits of using DFS as the building block of the signaling in MANET routing protocols are exemplified by the introduction of the Ordered Walk Search Algorithm (OSA), which is used as part of the proposed Ordered Walk with Learning (OWL) protocol. OWL integrates OSA with the learning of paths from prior successful and failed attempts, and performs one or multiple concurrent ordered walks to search for destinations. Simulation experiments are used to compare the performance of OWL against that of well-known MANET routing protocols based on BFS (e.g., OLSR and AODV). The results show that OWL can achieve a performance comparable to traditional protocols that rely on some form of flooding of link states or network-wide dissemination of distance information in terms of packet delivery ratios and average end-to-end delays, while incurring up to ten times less overhead than AODV.     

On routing in large WDM networks

An important problem in WDM network design is to construct a logical topology and determine an optimal routing over that topology. Mixed Integer Linear Program (MILP) formulations to generate optimal solutions for this problem have been presented. Such formulations are computationally intractable, even for moderate sized networks. A standard approach is to decouple the problem of logical topology design and the problem of routing the traffic on this logical topology. Heuristics for finding the logical topology exist and a straight-forward linear program (LP), based on the node-arc formulation can be used to solve the routing problem over a given logical topology. We have found that such LP formulations become computationally infeasible for large networks. In this paper, we present a new formulation, based on the arc-chain representation, for optimally routing the specified traffic over a given logical topology to minimize the congestion of the network. We have used the revised simplex method incorporating an implicit column generation technique, and exploited the special Generalized Upper Bounding structure as well as the possibility of eta-factorization for efficiently updating the dual variables and finding the solution. Experimental results on a number of networks demonstrate the suitability of this approach.     

Efficient routing and wavelength assignment for reconfigurable WDMnetworks

Through the use of configurable wavelength-division-multiplexing (WDM) technology including tunable optical transceivers and frequency selective switches, next-generation WDM networks will allow multiple virtual topologies to be dynamically established on a given physical topology. For N node P port networks, we determine the number of wavelengths required to support all possible virtual topologies (PN lightpaths) on a bidirectional ring physical topology. We show that if shortest path routing is used, approximately N wavelengths are needed to map N lightpaths. We then present novel adaptive lightpath routing and wavelength assignment strategies that reduce the wavelength requirements to [(N/2)] working wavelengths per port for protected networks and [(N/3)] wavelengths in each direction per port for unprotected networks. We show that this reduced wavelength requirement is optimal in the sense that it is the minimum required to support the worst case logical topology. Furthermore, we prove that a significant number of logical topologies require this minimum number of wavelengths. We also develop joint routing and wavelength assignment strategies that not only minimize the number of wavelengths required to implement the worst case logical topologies but also reduce average wavelength requirements. Finally, methods for extending these routing and wavelength assignment results to general two-connected and three-connected physical topologies are presented     

Efficient retiming of large circuits

Retiming, introduced by Leiserson and Saxe (1983, 1991), is a powerful transformation of circuits that preserves functionality and improves performance. The ASTRA algorithm proposed an alternative view of retiming using the equivalence between retiming and clock skew optimization and also presented a fast algorithm for minimum period (minperiod) retiming. Since minperiod retiming may significantly increase the number of flip-flops in the circuit, minimum area (minarea) retiming is an important problem. Minarea retiming is a much harder problem than minperiod retiming, and previous techniques were not capable of handling large circuits in a reasonable time. This work defines the relationship between the Leiserson-Saxe and the ASTRA approaches and utilizes it for efficient minarea retiming of large circuits. The new algorithm, Minaret, uses the same basis as the Leiserson-Saxe approach. The underlying philosophy of the ASTRA approach is incorporated to reduce the number of variables and constraints generated in the problem. This allows minarea retiming of circuits with over 56 000 gates in under 15 min     

Efficient solutions to multicast routing in communication networks

An important problem in both wireless and wired communication networks is to be able to efficiently multicst information to a group of network sites. Multicasting reduces the transmission overhead of both wireless and wired networks and the time it takes for all the nodes in the subset to receive the information. Since transmission bandwidth is a scarce commodity especially in wireless networks, efficient and near minimum-cost multicast algorithms are particularly useful in the wireless context. In this paper, we discuss methods of establishing efficient and near minimum-cost multicast routing in communication networks. In particular, we discuss an efficient implementation of a widely used multicast routing method which can construct a multicast tree with a cost no greater than twice the cost of an optimal tree. We also present two efficient multicast tree constructions for a general version of the multicast routing problem in which a network consists of different classes of nodes, where each class can have one or more nodes of the same characteristic which is different from the characteristics of nodes from other classes. Because of their efficient running times, these multicast routing methods are particularly useful in the mobile communication environments where topology changes will imply recomputation of the multicast trees. Furthermore, the proposed efficient and near minimum-cost multicast routing methods are particularly suited to the wireless communication environments, where transmission bandwidth is more scarce than wired communication environments.Partially supported by NSF/LaSER under grant number EHR-9108765, by LEQSF grant number 94-RD-A-39, by NASA under grant number NAG 5-2842.     

Efficient network folding techniques for routing permutations inVLSI

Network folding is a technique for realizing permutations on N elements using interconnection networks with M input (and output) terminals, where M相似文献   

Efficient routing for IP subnet VLAN over Ethernet

Existing IP routing algorithms have been developed mainly for non‐VLAN networks. For these routing algorithms to work, an end station must be attached to its associated network. The introduction of VLAN has, however, allowed the physical location of the end station to be changed from time to time. Therefore, some extra mechanism is required to support routing in VLAN environment. Existing approaches have some drawbacks in terms of inefficiency in traffic forwarding and switch software complexity. In this paper, a simple and efficient method for routing over IP subnet VLAN in Ethernet is proposed. This method has been implemented in hardware and found to work correctly. Various measurements and analyses have been performed to verify the efficiency of this protocol. Copyright © 2002 John Wiley & Sons, Ltd.     

Efficient routing of information between interconnected cellularmobile switching centers

At the switch boundaries of cellular systems, it is necessary to provide an inter-switch handover procedure if calls are to remain in progress as users cross these boundaries. Both the North American and Pan European second generation standards provide mechanisms for inter-switch handover. Motivated by the need to develop procedures for inter-switch handover in the cellular packet switch (CPS), this paper develops a general set of procedures for inter-switch handover that, unlike their second generation counterparts, provide a mechanism for the transport of data. Unlike voice, data packets must all be delivered. The delivery may need to be sequential and/or restricted to a single copy. The path optimization procedures are all presented in the context of the CPS. In addition, we identify capabilities needed by the CPS and present suitable protocols. The path optimization procedures are evaluated based on the following performance criteria: guarantee of sequential delivery, avoidance of multiple copies, and delay. Fundamental limitations on data throughput result if both sequential delivery and a single copy are required     

Efficient transmission of compressed data for remote volume visualization

One of the goals of telemedicine is to enable remote visualization and browsing of medical volumes. There is a need to employ scalable compression schemes and efficient client-server models to obtain interactivity and an enhanced viewing experience. First, we present a scheme that uses JPEG2000 and JPIP (JPEG2000 Interactive Protocol) to transmit data in a multi-resolution and progressive fashion. The server exploits the spatial locality offered by the wavelet transform and packet indexing information to transmit, in so far as possible, compressed volume data relevant to the clients query. Once the client identifies its volume of interest (VOI), the volume is refined progressively within the VOI from an initial lossy to a final lossless representation. Contextual background information can also be made available having quality fading away from the VOI. Second, we present a prioritization that enables the client to progressively visualize scene content from a compressed file. In our specific example, the client is able to make requests to progressively receive data corresponding to any tissue type. The server is now capable of reordering the same compressed data file on the fly to serve data packets prioritized as per the client's request. Lastly, we describe the effect of compression parameters on compression ratio, decoding times and interactivity. We also present suggestions for optimizing JPEG2000 for remote volume visualization and volume browsing applications. The resulting system is ideally suited for client-server applications with the server maintaining the compressed volume data, to be browsed by a client with a low bandwidth constraint.     

Analysis of multipath routing, part 2: mitigation of the effects of frequently changing network topologies

In this paper, we extend the analysis of multipath routing presented in our previous work, so that the basic restrictions on the evaluation and optimization of that scheme can be dropped (e.g., disjoint paths and identical paths in terms of failure probability). In that work, we employed diversity coding in order to provide increased protection against frequent route failures by splitting data packets and distributing them over multiple disjoint paths. Motivated by the high increase in the packet delivery ratio, we study the increase we can achieve through the usage of multiple paths in the general case, where the paths are not necessarily independent and their failure probabilities vary. For this reason, a function that measures the probability of successful transmission is derived as a tight approximation of the evaluation function P/sub succ/. Given the failure probabilities of the available paths and their correlation, we are able to find in polynomial time the set of paths that maximizes the probability of reconstructing the original information at the destination.     

高效的移动Sink路由问题的启发式算法

移动sink最短路由问题可以看作是带邻近区域的旅行商问题(TSPN)的一个特例,其邻近区域为随机部署的传感器节点的无线通信范围,可建模成大小各异并且存在重叠的圆盘。由于目前还不存在多项式时间算法来解决该种TSPN问题,提出了一种新颖的启发式算法。它利用TSP路径为不自交环路的特性构造一条赛道,通过内圈启发式、弯道启发式以及捷径搜索在O(n2)时间复杂度内找出赛道内的近似最短路径。形式化证明和大规模模拟实验都验证了该算法较同类算法能够更高效地找出较优的近似解。     

Efficient routing and wavelength assignment for multicast in WDMnetworks

The next generation multimedia applications such as video conferencing and HDTV have raised tremendous challenges on the network design, both in bandwidth and service. As wavelength-division-multiplexing (WDM) networks have emerged as a promising candidate for future networks with large bandwidth, supporting efficient multicast in WDM networks becomes eminent. Different from the IP layer, the cost of multicast at the WDM layer involves not only bandwidth (wavelength) cost, but also wavelength conversion cost and light splitting cost. It is well known that the optimal multicast problem in WDM networks is NP-hard. In this paper, we develop an efficient approximation algorithm consisting of two separate but integrated steps: multicast routing and wavelength assignment. We prove that the problem of optimal wavelength assignment on a multicast tree is not NP-hard; in fact, an optimal wavelength assignment algorithm with complexity of O(NW) is presented. Simulation results have revealed that the optimal wavelength assignment beats greedy algorithms by a large margin in networks using many wavelengths on each link such as dense wavelength-division-multiplexing (DWDM) networks. Our proposed heuristic multicast routing algorithm takes into account both the cost of using wavelength on links and the cost of wavelength conversion. The resulting multicast tree is derived from the optimal lightpaths used for unicast     

基于博弈论的WSN有效分簇路由算法的研究

针对无线传感器网络中传感器节点能量受到限制及其能耗不均匀的问题,在经典的低功耗自适应分簇算法（LEACH）基础上,引入博弈理论概念,提出了一种基于博弈论的有效分簇路由算法。通过分析和仿真试验,结果表明与LEACH算法相比,该算法使簇分布更合理,达到了延长网络的生存周期的目的。