Deadlock-Free Adaptive Routing in Meshes with Fault-Tolerance Ability Based on Channel Overlapping

Compressionless Routing (GR) is a new adaptive routing framework which provides a unified framework for efficient deadlock-free adaptive routing and fault-tolerance. CR exploits the tight-coupling between wormhole routers for flow control to detect potential deadlock situations and recover from them. Fault-tolerant Compressionless Routing (FCR) extends Compressionless Routing to support end-to-end fault-tolerant delivery. Detailed routing algorithms, implementation complexity and performance simulation results for CR and FCR are presented.CR has the following advantages: deadlock-free adaptive routing in torus networks with no virtual channels, simple router designs, order-preserving message transmission, applicability to a wide variety of network topologies, and elimination of the need for buffer allocation messages. FCR has the following advantages: tolerates transient faults while maintaining data integrity (nonstop fault-tolerance), tolerates permanent faults, can be applied to a wide variety of network topologies, and eliminates the need for software buffering and retry for reliability. These advantages of CR and FCR not only simplify hardware support for adaptive routing and fault-tolerance, they also can simplify communication software layers.

A theory for the design of deadlock-free adaptive routing algorithms for wormhole networks, proposed by the author (1991, 1993), supplies sufficient conditions for an adaptive routing algorithm to be deadlock-free, even when there are cyclic dependencies between channels. Also, two design methodologies were proposed. Multicast communication refers to the delivery of the same message from one source node to an arbitrary number of destination nodes. A tree-like routing scheme is not suitable for hardware-supported multicast in wormhole networks because it produces many headers for each message, drastically increasing the probability of a message being blocked. A path-based multicast routing model was proposed by Lin and Ni (1991) for multicomputers with 2D-mesh and hypercube topologies. In this model, messages are not replicated at intermediate nodes. This paper develops the theoretical background for the design of deadlock-free adaptive multicast routing algorithms. This theory is valid for wormhole networks using the path-based routing model. It is also valid when messages with a single destination and multiple destinations are mixed together. The new channel dependencies produced by messages with several destinations are studied. Also, two theorems are proposed, developing conditions to verify that an adaptive multicast routing algorithm is deadlock-free, even when there are cyclic dependencies between channels. As an example, the multicast routing algorithms of Lin and Ni are extended, so that they can take advantage of the alternative paths offered by the network.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>

Deadlock-free adaptive routing is extensively adopted in interconnection networks to improve communication bandwidth and reduce latency. However, existing deadlock-free flow control schemes either underutilize memory resources due to inefficient buffer management for simple hardware implementations, or rely on complicated coordination and synchronization mechanisms with high hardware complexity. In this work, we solve the deadlock problem from a different perspective by considering the deadlock as a lack of credit. With minor modifications of the credit accumulation procedure, our proposed full-credit flow control (FFC) ensures atomic buffer usage only based on local credit status while making full use of the buffer space. FFC can be easily integrated in the industrial router to achieve deadlock freedom with less area and power consumption, but 112% higher throughput, compared to the critical bubble scheme (CBS). We further propose a credit reservation strategy to eliminate the escape virtual channel (VC) cost for fully adaptive routing implementation. The synthesizing results demonstrate that FFC along with credit reservation (FFC-CR) can reduce the area by 29% and power consumption by 26% compared with CBS.

This paper proposes novel two fault-tolerant routing methods for a 3D mesh network-on-chip (NoC). The existing method proposed by Boppana et al. combines two routing methods, minimal fully adaptive routing and fault-tolerant routing, for faulty region detouring. However, in the latter fault-tolerant routing, a detour direction is statically defined for each faulty region. Due to the long detour path and the use of eight virtual channels, this method has the problems of high communication latency and a large hardware overhead. To solve these problems, the first proposed method allows adaptive detours for faulty regions, and the second proposed method allows the passage of them. The simulation results show that, compared with the existing method, the second proposed method enables us to reduce the latency by about 30% and improve the throughput by about 3.1% with half of the virtual channels.

In this paper, we present an adaptive fault-tolerant wormhole routing algorithm for hypercubes by using 4 virtual networks. Each node is identified to be in one of the four states: safe, ordinarily unsafe, strongly unsafe, and faulty. Based on the concept of unsafe nodes, we design a routing algorithm for hypercubes that can tolerate at least n-1 faulty nodes and can route a message via a path of length no more than the Hamming distance between the source and destination plus four. Previous algorithms which achieve the same fault tolerant ability need at least 5 virtual channels per physical channel. Simulation results show that our algorithm outperforms previous known results.

This paper generalizes a theory for deadlock-free adaptive wormhole routing by considering a mixed set of resources: edge and central buffers. This generalized theory is then applied to a concurrent version of Disha deadlock-recovery which relaxes the sequential recovery requirement for simultaneous recovery from deadlocks. The proposed extension to Disha does not necessitate any additional resource cost; rather it serves to eliminate the requirement of mutual exclusive access to the deadlock-free lane implemented by a Token. With this extension, Disha Concurrent remains applicable to any topology with a Hamiltonian path including k-ary n-cube networks and is also applicable to tree-based networks.

Wormhole routing makes the communication latency insensitive of the network diameter and reduces the buffer size of each router. It has been widely adopted in many new generation distributed memory multiprocessor systems (DMMPs). The concept of virtual system is invented for deadlock-free routing design. Using a great deal of virtual channels is quite expensive to be implemented in practice and is not limitless. In this paper experimental results are given to evaluate the tradeoff between network congestion delay and throughput. Some results show that the congestion delay does not reduce visibly when the number of virtual channels is greater than that of internal channels by 2. A reasonable number of virtual channels can be derived from the results. A virtual networks system using only four virtual networks, two virtual channels in each direction, is presented. It shows that the minimum number of virtual networks to support a partially adaptive, minimal and deadlock free routing in k-ary n-cubes is just four. It uses only four virtual networks but can get a high degree of adaptiveness and high traffic capacity. Simulation results are presented to verify the performance.

Adaptive deadlock-free routing mechanisms are required to handle variable traffic patterns in dragonfly networks. However, distance-based deadlock avoidance mechanisms typically employed in Dragonflies increase the router cost and complexity as a function of the maximum allowed path length. This paper presents on-the-fly adaptive routing (OFAR), a routing/flow-control scheme that decouples the routing and the deadlock avoidance mechanisms. OFAR allows for in-transit adaptive routing with local and global misrouting, without imposing dependencies between virtual channels, and relying on a deadlock-free escape subnetwork to avoid deadlock. This model lowers latency, increases throughput, and adapts faster to transient traffic than previously proposed mechanisms. The low capacity of the escape subnetwork makes it prone to congestion. A simple congestion management mechanism based on injection restriction is considered to avoid such issues. Finally, reliability is considered by introducing mechanisms to find multiple edge-disjoint Hamiltonian rings embedded on the dragonfly, allowing to use multiple escape subnetworks.

Fault-tolerant routing is the ability to survive beyond the failure of individual components and usually uses several virtual channels (VCs) to pass faulty nodes or links. A well-known wormhole-switched routing algorithm for 2-D mesh interconnection network, f-cube3, uses three virtual channels to pass faulty blocks such as f-ring and f-chain, while only one virtual channel is used when a message does not encounter any fault. One of the key issues in the design of NoCs is the development of an efficient communication system to provide high throughput and low latency interconnection networks. We have evaluated a new fault-tolerant routing algorithm based on f-cube3 as a solution to increase the throughput of physical links more than f-cube3 with lower message delay which uses less number of VCs compared to f-cube3 by reducing required virtual channels to two. Simulation of both f-cube3 and improved algorithm, if-cube2 (improved f-cube2) for the same conditions presented. As the simulation results show, if-cube2 has a higher performance than f-cube3 algorithm even with one less VC. The results also show that our algorithm has less exist packets in network and better performance with 100% traffic load in Network-on-Chip.KeywordsNetwork-on-Chipthroughputperformanceinterconnectionfault-tolerant routingwormhole switchingvirtual channeldeterministic routing

Fully adaptive routing with less virtual channels is of technical trend in MPP interconnection network design. However imbalance of load offsets performances of many schemes. In this paper we give a fully adaptive load balanced routing algorithm cabled VBMAR. A new design tool called crossed turn model (CTM) is proposed to solve complex deadlock problems across virtual networks while keeping the load balanced. Non-deterministic finite automaton (NDFA) is used to model the routing process. The resulting algorithm features routing uniformity and channel priority concurrent architecture and parallel priority channel searching techniques are used in VBMAR router design, which make it cost efficient. Four algorithms are compared to evaluate the performance of VBMAR. Simulations show that VBMAR can considerably increase network throughput and shorten network delay under both uniform and nonuniform traffic patterns. We argue that VBMAR is a very competitive routing scheme for future commercial MPP systems.

In this paper, we would present a fault-tolerant wormhole routing scheme, called two-level-turn-model scheme, in the tori with convex faults. The reason why we choose the convex faults is that the shape of the convex faults is instrumental to design an effective fault-tolerant routing algorithm. Compared with many other solutions, which mainly focus on providing extra virtual channels to tolerate the faults, one of the advantages of our solution is that it is based on the turn model, which itself could tolerate some faults for some messages. At the same time, our solution could work effectively no matter where the fault region locates and no matter whether the fault regions are connected. In our solution, two patterns of the turn model are complementary to tolerate the faults. With a few limits to the shape of the convex faults, at most five virtual channels per physical channel are required to avoid the deadlock.

The selection of a topology is essential to the performance of interconnection networks, so designing a new, cost-effective topology is very significant. 2D mesh is one of the most popular topologies. However, the diameter and average distance of a 2D mesh are large enough to greatly influence the performance of the network. This paper presents a novel topology called TM, which combines the advantages of both a 2D torus and a 2D mesh. For an n×n network, the total number of links in a TM is the same as that in a mesh, while the diameter of a TM is extremely close to that of a torus. Besides, the average distance of a TM is at the middle of that of a torus and that of a mesh. To prevent deadlocks in TMs, a virtual network partitioning scheme is adopted into the TM network. Moreover, both of the deterministic and fully-adaptive routing techniques in TMs are proposed in this paper. Compared to mesh, the TM network provides average distance and diameter reduction, which contributes to the performance enhancement. Sufficient simulation results are presented to show the effectiveness of the TM network, and the new routing schemes proposed for it, by comparing with the mesh network. Compared to the torus, which requires at least 3 virtual channels to support fully-adaptive routing, the TM network can support fully-adaptive routing with only 2 virtual channels. Seen from the experimental results, in most cases, the performance of TM is worse than the torus, while in some cases, the performance of TM is comparable to torus or even better than the torus.

Fault-tolerant wormhole routing in mesh with overlapped solid fault regions

We propose a new fault block model, minimal-connected-component (MCC), for fault-tolerant adaptive routing in mesh-connected multiprocessor systems. This model refines the widely used rectangular model by including fewer nonfaulty nodes in fault blocks. The positions of source/destination nodes relative to faulty nodes are taken into consideration when constructing fault blocks. The main idea behind it is that a node will be included in a fault block only if using it in a routing will definitely make the route nonminimal. The resulting fault blocks are of the rectilinear-monotone polygonal shapes. A sufficient and necessary condition is proposed for the existence of the minimal "Manhattan" routes in the presence of such fault blocks. Based on the condition, an algorithm is proposed to determine the existence of Manhattan routes. Since MCC is designed to facilitate minimal route finding, if there exists no minimal route under MCC fault model, then there will be absolutely no minimal route whatsoever. We also present two adaptive routing algorithms that construct a Manhattan route avoiding all fault blocks, should such routes exist.

A new deadlock prevention scheme for nonminimal adaptive wormhole routing