Juan Miguel Martínez

Software-based deadlock recovery technique for true fully adaptive routing in wormhole networks

In this paper, we take a different approach to handle deadlocks and performance degradation. We propose the use of an injection limitation mechanism that prevents performance degradation near the saturation point and reduces the probability of deadlock to negligible values even when fully adaptive routing is used. We also propose an improved deadlock detection mechanism that only uses local information, detects all the deadlocks, and considerably reduces the probability of false deadlock detection over previous proposals. In the rare case when impending deadlock is detected, our proposed recovery technique absorbs the deadlocked message at the current node and later re-injects it for continued routing towards its destination. Performance evaluation results show that our new approach to deadlock handling is more efficient than previously proposed techniques.

A very efficient distributed deadlock detection mechanism for wormhole networks

Networks using wormhole switching have traditionally relied upon deadlock avoidance strategies for the design of routing algorithms. More recently, deadlock recovery strategies have begun to gain acceptance. Progressive deadlock recovery techniques are very attractive because they allocate a few dedicated resources to quickly deliver deadlocked messages, instead of killing them. However, the distributed deadlock detection techniques proposed up to now detect many false deadlocks, especially when the network is heavily loaded and messages have different lengths. As a consequence, messages detected as deadlocked may saturate the bandwidth offered by recovery resources, thus degrading performance considerably. In this paper we propose an improved distributed deadlock detection mechanism that uses only local information, detects all the deadlocks, considerably reduces the probability of false deadlock detection and is not strongly affected by variations in message length and message destination distribution.

DRIL: dynamically reduced message injection limitation mechanism for wormhole networks

Deadlock avoidance and recovery techniques are alternatives to deal with the interconnection network deadlock problem. Both techniques allow fully adaptive routing on some set of resources while providing dedicated resources to escape from deadlock. They mainly differ in the way they supply escape paths and when those paths are used. As the escape paths only provide limited bandwidth to escape from deadlocks, both techniques suffer from severe performance degradation when the network is close to saturation. On the other hand, deadlock recovery is based on the assumption that deadlocks are rare. Several studies show that deadlock are more prone when the network is close to or beyond saturation. In this paper we propose a new mechanism that prevents network saturation by dynamically adjusting message injection limitation into the network. As a consequence, this mechanism will avoid the performance degradation problem that typically occurs in both deadlock avoidance and recovery techniques, making fully adaptive feasible. Also, it will guarantee that the frequency of deadlock is really negligible, allowing the use of simple low-cost recovery strategies.

Dynamic power saving in fat-tree interconnection networks using on/off links

Current trends in high-performance parallel computers show that fat-tree interconnection networks are one of the most popular topologies. The particular characteristics of this topology, that provide multiple alternative paths for each source/destination pair, make it an excellent candidate for applying power consumption reduction techniques. Such techniques are being increasingly applied in computer systems and the interconnection network is not an exception, since its contribution to the system power budget is not negligible. In this paper, we present a mechanism that dynamically switches on and off network links as a function of traffic. The mechanism is designed to guarantee network connectivity, according to the underlying routing algorithm. In this way, the default routing algorithm can be used regardless of the power saving actions taken, thus simplifying router design. Our simulation results show that significant network power consumption reductions can be obtained at no cost. Latency remains the same although the number of operating network links is dynamically adjusted.

On the Reduction of Deadlock Frequency by Limiting Message Injection in Wormhole Networks

Recently, deadlock recovery strategies began to gain accep- tance in networks using wormhole switching. In particular, progressive deadlock recovery techniques are very attractive because they allocate a few dedicated resources to quickly deliver deadlocked packets, instead of killing them. Deadlock recovery is based on the assumption that dead- locks are really rare. Otherwise, recovery techniques are not efficient.

Power saving in regular interconnection networks built with high-degree switches

Nowadays, high-degree switches are available as building blocks of the interconnection network of clusters of PCs. An alternative to take advantage of the high number of switch ports is to connect every pair of switches through not only one but also several links (this is known as link trunking in other environments). This extra connectivity can be exploited by using adaptive routing algorithms, thus improving network throughput and reducing network congestion. However with low traffic loads, all the links that compose the trunk link will not be utilized, but this idle links continue consuming power. Power consumption reduction techniques are being applied everywhere in computer systems and the interconnection network is not an exception, as its contribution is not negligible. In this paper, we present a mechanism that dynamically switches on and off network links as a function of traffic. It is specially targeted to those networks where trunk links are used. The mechanism can switch off any link, provided that network connectivity is guaranteed, (i.e. every pair of switches should be connected through at least one active link). Indeed, this restriction makes possible to use the same routing algorithm regardless the power saving actions taken, thus simplifying router design. Our simulation results show that the network power consumption can be greatly reduced, at the expense of some increase in latency. Nevertheless, it is shown that the power reduction is always higher that this latency increases.

Power saving in regular interconnection networks

The high level of computing power required for some applications can only be achieved by multiprocessor systems. These systems consist of several processors that communicate by means of an interconnection network. The huge increase both in size and complexity of high-end multiprocessor systems has triggered up their power consumption. Complex cooling systems are needed, which, in turn, increases power consumption. Power consumption reduction techniques are being applied everywhere in computer systems and the interconnection network is not an exception, as its contribution is not negligible. In this paper, we propose a mechanism to reduce interconnect power consumption that combines two alternative techniques: (i) dynamically switching on and off network links as a function of traffic (any link can be switched off, provided that network connectivity is guaranteed), (ii) dynamically reducing the available network bandwidth when traffic becomes low. In both cases, the topology of the network is not modified. Therefore, the same routing algorithm can be used regardless of the power saving actions taken, thus simplifying router design. Our simulation results show that the network power consumption can be greatly reduced, at the expense of some increase in latency. However, the achieved power reduction is always higher than the latency penalty.

Reducing Power Consumption in Interconnection Networks by Dynamically Adjusting Link Width

The huge increase both in size and complexity of high-end multiprocessor systems has triggered their power consumption. Air or liquid cooling systems are needed, which, in turn, increases power consumption. Another important percentage of the consumption is due to the interconnection network.

LIFE: a limited injection, fully adaptive, recovery-based routing algorithm

Networks using wormhole switching have traditionally relied upon deadlock avoidance strategies for the design of deadlock-free algorithms. The past few years have seen a rise in popularity of deadlock recovery strategies, that are based on the property that deadlocks are quite rare in practice and happen only at or beyond the network saturation point. In fact, recovery-based routing algorithms have a higher potential performance over the deadlock avoidance-based ones which allow less routing freedom. We present a recovery-based fully adaptive routing algorithm, LIFE, which is based on an innovative injection policy that reduces the probability of deadlocks to negligible values, both with uniform and non-uniform traffic patterns. The experimental results, conducted on an 8-ary 3-cube with 512 nodes, show that it is possible to implement true fully adaptive routing using only two virtual channels. Also, LIFE outperforms state-of-the-art avoidance- and recovery-based algorithms of the same cost both in terms of throughput and message latency under uniform traffic and provides stable throughput under non-uniform traffic patterns.

Power-aware fat-tree networks using on/off links

Nowadays, power consumption reduction techniques are being increasingly used in computer systems, and high-performance computing systems are not an exception. In particular, the power consumed by the interconnect circuitry has a non-negligible contribution to the total system budget. In this scenario, fat-tree interconnection networks are one of the most popular topologies. This topology is particularly well-suited for applying power consumption reduction techniques since it provides multiple alternative paths for each source/destination pair. In this paper, we present a mechanism that dynamically adjusts the available network bandwidth by switching links on and off, according to the traffic requirements. This mechanism provides significant reduction in power consumption while maintaining the original underlying routing algorithm, at the expense of slight latency increase for low loads.