Toshinori Takabatake

A hybrid bootstrap mechanism for multicast routing in PIM-SM

In many multicast routing protocols, Protocol Independent Multicast - Sparse Mode (for short, PIM-SM) has been studied and implemented. Data transmission in the PIM-SM domain is performed on a shared tree. The shared tree has a Rendezvous Point (RP) which plays a central role of the data transmission. The bootstrap mechanism is one of the methods to discover the RP dynamically in the PIM-SM domain. However, because the mechanism needs data flooding for all routers to find the RP, some traffic or congestion is prone to occur on the domain. The processing of the mechanism is also time-consuming. In this paper, a hybrid bootstrap mechanism in PIM-SM is proposed and its performance is evaluated. Since the proposed method consists of distributed and centralized processes, it is called a hybrid one. The key for the proposed method is that the role of the RP selection is played in a Bootstrap Router, not that a Designated Router, since the RP-Set distribution is not performed. Especially, the proposed method dose not need the flooding and can be reduced the processing time efficiently to discover the RP. Simulation results show that the proposed method can reduce the processing time by more than 40% compared with that of the conventional one.

Low-Cost IP Core Test Using Multiple-Mode Loading Scan Chain and Scan Chain Clusters

A fixing-shifting encoding (FSE) method is proposed to reduce test cost of IP cores. The FSE method reduces test cost by supporting multiple-mode loading test data, i.e., parallel loading, left-direction, and right-direction serial loading for each test slice data. Furthermore, the FSE that utilizes only two test channels can support a large number of internal scan chains and achieve further reduction in test cost by combining with scan chain clustering method. As a non-intrusive and automatic test pattern generation (ATPG) independent solution, the approach is applicable to IP core testing because it requires neither redesign of the core under test (CUT) nor running any additional ATPG for the encoding procedure. In addition, the decoder has low hardware overhead, and its design is independent of the CUT. Experimental results for some large ISCAS 89 benchmarks and an industry ASIC design have proven the efficiency of the proposed approach

Node-disjoint paths in a level block of generalized hierarchical completely connected networks

Generalized hierarchical completely connected networks (for short, HCCs), which include conventional hierarchical networks, have been proposed. An HCC is a network topology for a massively parallel computer system. To apply an HCC to a parallel computer system effectively and to execute data processing on the HCC efficiently, the inherent fault-tolerant properties in an HCC must be revealed. However, these properties have not been clarified sufficiently. In this paper, node-disjoint paths are verified for a level block of the HCC.

Probabilistic fault diagnosis and its analysis in multicomputer systems

F.P.Preparata et al. have proposed a fault diagnosis model to find all faulty units in the multicomputer system by using outcomes which each unit tests some other units. In this paper, for probabilistic diagnosis models, we show an efficient diagnosis algorithm to obtain a posteriori probability that each of units is faulty given the test outcomes. Furthermore, we propose a method to analyze the diagnostic error probability of this algorithm.

Simulations of NoC topologies for generalized hierarchical completely-connected networks

The density of integration in a single chip has progressed by use of the deep submicron of VLSI design rule. Systems on a chip (for short, SoCs), i.e., several functional cores being integrated in a single chip, have become the mainstream technology. On the other hand, A Network on a Chip (NoC), i.e., a communication-centric platform, offers an on-chip interconnection network. The NoC is one of the on-chip communication systems. The NoC is used in place of conventional shared bus systems. There are many NoC topologies for connecting cores to each other, such as Mesh, Ring, Spidergon, and so on. To evaluate the NoC topologies, a simulation based approach was used for the modeling and analysis of the topologies. However, some properties of the topologies could affect the performance of the NoC systems. In this paper, we present the performances of the topologies about the communication aspects by the simulation based approach. In particular, Generalized Hierarchical Completely-Connected Networks (HCC) as the NoC topology is presented. An experimental study is conducted to compare the HCC with the other topologies. Simulation results show that the HCC has enough performance to be used by the NoC topology.

Evaluation of the P2P file sharing technique by Indexed-Priority Metric

Recently, the improvements in processing performance of a computer and high speed communication of an optical fiber have been achieved, so that the amount of data which are processed by a computer and flowed on a network has been increasing greatly. However, in a client-server system, since the server receives and processes the amount of data from the clients through the network, a load on the server is increasing. Thus, there are needed to introduce a server with high processing ability and to have a line with high bandwidth. In this paper, concerning to P2P networks to resolve the load on a specific server, a criterion called an Indexed-Priority Metric has been proposed and its performance is evaluated. The proposed metric is to allocate some files to each node. As a result, the load on a specific server can distribute them to each node equally well. Simulation results show that the proposed metric can make files distribution on the specific server.

Evaluation of the hybrid bootstrap mechanism for multicast routing

In this paper, the hybrid bootstrap mechanism for multicast routing in PIM-SM is presented and its performance is evaluated. Since the hybrid bootstrap mechanism consists of distributed and centralized processes, it is called hybrid one. The key for the hybrid method is that the role of a rendezvous point (for short, RP) selection is played in a bootstrap router (BSR), not that a designated router (DR), because the process of the RP-Set distribution is not needed. Especially, the hybrid method finds the RP by communication between the DR and the BSR. Evaluation results show that the hybrid method can reduce efficiently the processing delay about more than 50% by compared with that of the traditional one.

A simple packet-classifier algorithm for QoS control in home networks

Recently, technology of appliances being networked together in the home has been deployed. To connect the Internet with the home, a home gateway plays an important role in a home network. However, to be more comfortable in the environment of living for the home by networked appliances and by controlling them, services such as quality of service (for short, QoS) supported applications, remote control of appliances, and safety/security of the home network still have not been realized enough. In such services, especially, the home gateway for QoS control needs to deal with real-time data in applications. In this paper, a packet-classifier algorithm for QoS control in the home gateway is proposed and its performance is evaluated. The proposed method is forwarded a real-time packet precedent. The feature of the proposed method is a simple and deterministic process for packets such as a round-robin manner. Simulation studies show that the proposed method can balance the process of the packets compared with the algorithm without QoS.

A Min-Max Hop-Count Based Self-discovering Method of a Bootstrap Router for the Bootstrap Mechanism in Multicast Routing

In this paper, a min-max hop-count based self-discovering method of a Bootstrap Router (BSR) for the bootstrap mechanism in multicast routing is proposed and its performance is evaluated. The key for the proposed method is that the BSR is selected as to become a position such as almost equal distances from the other routers by the min-max hop-count way. Especially, the proposed method can reduce the processing time efficiently to discover a Rendezvous Point which plays a central role of the data transmission. Simulation results show that the proposed method can reduce the processing time by average more than 43% compared with that of the conventional one.