Efficient hierarchical interconnection for multiprocessor systems

A performance analysis of a class of hierarchical interconnection networks is presented. The analysis includes both static analysis (i.e. queueing delays are neglected) and queueing analysis. In both cases, the hierarchical networks are shown to have better cost-benefit ratios. The queueing analysis is also validated by several simulation experiments. The impact of two performance enhancement schemes-replication of links and improved routing algorithms-on hierarchical interconnection network performance is also presented. >

Two neural network models for visual pattern recognition are discussed. The first model, called a "neocognitron", is a hierarchical multilayered network which has only afferent synaptic connections. It can acquire the ability to recognize patterns by "learning-without-a-teacher": the repeated presentation of a set of training patterns is sufficient, and no information about the categories of the patterns is necessary. The cells of the highest stage eventually become "gnostic cells", whose response shows the final result of the pattern-recognition of the network. Pattern recognition is performed on the basis of similarity in shape between patterns, and is not affected by deformation, nor by changes in size, nor by shifts in the position of the stimulus pattern. The second model has not only afferent but also efferent synaptic connections, and is endowed with the function of selective attention. The afferent and the efferent signals interact with each other in the hierarchical network: the efferent signals, that is, the signals for selective attention, have a facilitating effect on the afferent signals, and at the same time, the afferent signals gate efferent signal flow. When a complex figure, consisting of two patterns or more, is presented to the model, it is segmented into individual patterns, and each pattern is recognized separately. Even if one of the patterns to which the models is paying selective attention is affected by noise or defects, the model can "recall" the complete pattern from which the noise has been eliminated and the defects corrected.

Hierarchical interconnection networks (HINs) employ multiple levels in which Lower-level networks provide local communication while higher-level networks facilitate remote communication. HINs are cost effectiveness and fault-tolerant. They can be classified into two classes. The first class includes HINs that are constructed using nodes and/or links replication. The second class uses standby interface nodes. This paper provides performance comparison of HINs in terms of network degree, diameter, cost and packing density. The outcome of this study shows that the Root-Folded Heawood (RFH) and the Flooded Heawood (FloH) provide the best network cost, defined as the product of network diameter and degree. The study also shows that HFCube(n, n) provide the best packing density, i.e. the smallest chip area required for VLSI implementation.

Hierarchical interconnection networks (HINs) have been introduced to maintain a low node degree with an increasing network size. This paper presents a systematic procedure for designing a general class of HINs and could be based on existing topologies by connecting a partition of each disjoint cluster as a gateway to all other clusters in the network. The size of these gateways, or the gatewidth, can be varied to satisfy the required network characteristics. This scheme is illustrated by defining hypercube based HINs, and different designs are obtained by varying the cluster size, the gatewidth, and the number of network levels. Relations are obtained for the different network parameters.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>

Communication performance comparisons, in terms of message latency, between mesh and hierarchical ring interconnection networks for shared-memory multiprocessors are developed. Traffic in the networks is assumed to consist of the short, fixed-length messages needed for remote-memory read/write operations and cache coherency control. Square-mesh networks with bidirectional links and no end-around connections are compared to two- and three-level hierarchical rings. Wormhole routing is used in the meshes, with messages consisting of / flits, with each flit containing b bits. In the ring networks, each ring segment can contain a complete message of f × b bits. Meshes and three-level rings provide comparable delays for system sizes of up to 200 or 300 processor clusters. The delay comparisons are valid only for the lightly loaded traffic case in which contention and blocking are low. This is the situation in practical shared-memory multiprocessor systems with a low cache miss rate and a high physical locality of reference in the global address space.

In this paper, we have proposed a new hierarchical interconnection network called Tori-connected Flattened Butterfly Network (TFBN). It is a hierarchical interconnection network which is able to interconnect millions of nodes in the network to achieve high performance and cost-effective design for massively parallel computing system. TFBN consists of multiple basic modules of flattened butterfly network whereby the basic modules are connected using 2D-torus network. This paper focuses on the architecture of the TFBN and the evaluation of its static network performance such as degree, diameter, cost, average distance, arc connectivity, bisection width and wiring complexity. The comparison of performance shows better performance in terms of distance parameters as well as other parameters.

Hierarchical context-agnostic network with contrastive feature diversity for one-shot semantic segmentation

Machine-to-Machine (M2M) networks enabling networked nodes (sensors or actuators) to exchange information have been intensively studied lately. Key components of M2M networks include sensors that can be deployed with a large quantity for monitoring or surveillance. This paper deals with M2M networks hierarchically structured to accommodate efficient data transmission from terminal nodes to a sink node via cluster heads. A novel medium access control (MAC) protocol, more specifically backoff time decision rule, fit for hierarchical M2M networks is proposed and evaluated by simulations. Analytical success probability in channel access by cluster heads is derived and compared with simulation results. It is shown by simulation results that the proposed backoff time decision rule achieves smaller average latency and reduced per-node energy consumption in comparison with well-known MAC protocols, the DMAC and the SMAC, for sensor networks.

Zigbee, a key technology in the field of wireless networks for the Internet of Things, plays a significant role in the development of modern wireless network technologies. In this study, the analysis of coordinator failures in ZigBee networks with different topologies (“star”, “tree”, “mesh”) was carried out using the OPNET Modeler software tool. The problems related to the reliability and efficiency of systems using Zigbee technology are considered. Simulation of successive coordinator failures allowed us to compare the performance of topologies, revealing that the tree topology provides high traffic speed and bandwidth, but suffers from significant packet loss and delays. In turn, the star topology demonstrates minimal latency and high speed, and the mesh topology has better reliability with less packet loss, but the lowest speed and bandwidth. The findings emphasize the importance of choosing the optimal topology to ensure the efficiency and reliability of Zigbee networks in a volatile environment and increased load.

The LoRa technology is considered as one of the most potential solutions for Internet of Things (IoT) in the near future. The existing LoRa networks are based on the star topology. In this article, a tree network adopted for the LoRa technology and a communication protocol are proposed to mitigate the energy consumption constraints. In the proposed network, the nodes are self-configured based on the LoRa physical link behavior and can act as relays to propagate data from other nodes. The analysis, design, and evaluation of the proposed architecture for large scale LoRa networks are presented in detail. With analytical studies, the energy consumption of the star and tree LoRa networks are compared. The presented analytical results can provide developers with effective guidelines for scalable design and optimization of LoRa networks. Further, the results are verified using simulation and experimental tests. Both simulation and experimental results confirm that the presented method improves the energy consumption of the entire IoT network significantly. As a result, the presented tree network can be deployed in various applications.

In-network aggregation has become a promising technique for improving the energy efficiency of wireless sensor networks. Aggregating data at various nodes in the network results in a reduction in the amount of bits transmitted over the network, and hence, saves energy. In this paper, we focus on another important aspect of aggregation, i.e., delay performance. In conjunction with link scheduling, in-network aggregation can reduce the delay by lessening the demands for wireless resources and thus expediting data transmissions. We formulate the problem that minimizes the sum delay of sensed data, and analyze the performance of optimal scheduling with in-network aggregation in tree networks under the node-exclusive interference model. We provide a system wide lower bound on the delay and use it as a benchmark for evaluating different scheduling policies. We numerically evaluate the performance of myopic and non-myopic scheduling policies, where myopic one considers only the current system state for a scheduling decision while non-myopic one simulates future system states. We show that the one-step non-myopic policies can substantially improve the delay performance. In particular, the proposed non-myopic greedy scheduling achieves a good tradeoff between performance and implementability.

Supercomputers are today made up of hundreds of thousands of nodes. The interconnection network is responsible for connecting all these nodes to each other. Different interconnection networks have been proposed; high performance topologies have been introduced as a replacement for the conventional topologies of recent decades. A high order, a low degree and a small diameter are the usual properties aimed for by such topologies. However, this is not sufficient to lead to actual hardware implementations. Network scalability and topology simplicity are two critical parameters, and they are two of the reasons why modern supercomputers are often based on torus interconnection networks (e.g., Fujitsu K, IBM Sequoia). In this paper we first describe a new topology, torus-connected cycles (TCCs), realizing a combination of a torus and a ring, thus retaining interesting properties of torus networks in addition to those of hierarchical interconnection networks (HINs). Then, we formally establish the diameter of a TCC, and deduce a point-to-point routing algorithm. Next, we propose routing algorithms solving the Hamiltonian cycle problem, and, in a two dimensional TCC, the Hamiltonian path one. Correctness and complexities are formally proved. The proposed algorithms are time-optimal.

The increasing of the signaling technology motivated the research community to find alternative solutions to replace the sequential computing systems. These systems reached their limits, and it became an infeasible choice to manage the computational grand challenges. Thereby, many types of research have been conducted to improve a system with special characteristics able to cope with the new technology. Massively parallel computer (MPC) systems have been emerged to solve the complex computing challenges in parallel and concurrently. The performance of these systems is affected by the structure of the underlying interconnection network. Therefore, many designs of interconnection networks topologies have been presented looking for an optimal one. In this paper, we present the architecture of MMN which is a hierarchical interconnection network. The static and dynamic performance parameters of MMN have been evaluated in previous studies, and it provided good results compared to the conventional interconnection network topologies. This paper will focus on evaluating and determining the static cost-effective parameter of MMN which is the product of the relation between the node degree, network diameter, wiring complexity, and the total number of nodes in each network.

The effect of climate change and human activities leads to a series of dangerous phenomena, such as landslides and flood. In such a context, building a system to monitor environmental hazards is seriously needed. Some studies propose to use wireless sensor network (WSN) technique for landslide monitoring systems. Two important factors for these systems are the flexibility and the energy management. This paper focuses on the development of a flexible and efficient WSN for detecting rainfall-induced landslides. A flexible switching between star and tree topologies is used to adapt to weather conditions in order to maximize the reliability of the transmission. Moreover, the power management is designed concurrently with the weather condition to improve both the operation reliability and the power efficiency. The performance of our designed WSN is evaluated by both simulation and outdoor experiment. Detailed calculation of the power budget is presented thoughtfully to confirm the effectiveness of the proposed scheme.

Point cloud registration is a fundamental problem in 3D computer vision. Outdoor LiDAR point clouds are typically large-scale and complexly distributed, which makes the registration challenging. In this paper, we propose an efficient hierarchical network named HRegNet for large-scale out-door LiDAR point cloud registration. Instead of using all points in the point clouds, HRegNet performs registration on hierarchically extracted keypoints and descriptors. The overall framework combines the reliable features in deeper layer and the precise position information in shallower layers to achieve robust and precise registration. We present a correspondence network to generate correct and accurate keypoints correspondences. Moreover, bilateral consensus and neighborhood consensus are introduced for keypoints matching and novel similarity features are designed to in-corporate them into the correspondence network, which significantly improves the registration performance. Besides, the whole network is also highly efficient since only a small number of keypoints are used for registration. Extensive experiments are conducted on two large-scale outdoor LiDAR point cloud datasets to demonstrate the high accuracy and efficiency of the proposed HRegNet. The project website is https://ispc-group.github.io/hregnet.