With the increasing popularity of smartphones, the mobile security issues have become serious, and more and more malware has been found. Android applications are often used to handle sensitive information, thus they have become the main targets of malware attacks. In order to efficiently detect Android malware, in this paper, we present a multi-strategy combination framework. We use five types of static features to characterize Android applications from multiple aspects. To improve the classification accuracy and reduce the overfitting of the framework, we use three filter-based feature selection methods to identify the most informative top-k features. Then we input the applications represented by the feature subsets into five classification algorithms to build classifiers. Finally, we predict the classification results by hard voting or soft voting. We have performed many experiments in a well-marked dataset consisting of 41,155 samples. The experimental results show that our approach can achieve over 98% in accuracy, precision, recall and F-score. Compared with other existing methods, our approach has the best malware detection rate of 98.75%.

Bluetooth Low Energy (BLE)-based localization is a promising candidate of indoor localization for low power mobile and Internet of Things (IoT) systems. Localization accuracy of BLE-based localization systems is lower than other localization technologies relying on wideband wireless communication such as WiFi due to limited channel bandwidth. In our previous paper, we proposed an accuracy improvement method named separate channel fingerprinting (SCF), which, however, suffers from a high maximum localization error more than 6 meters. This paper therefore presents 2-step separate channel fingerprinting (2SSCF). 2S-SCF first coarsely estimates location by conventional BLE fingerprinting and utilizes SCF to estimate the fine-grained location. We experimentally demonstrate that 2S-SCF successfully reduced localization errors 95 % of time with a small maximum localization error.

Craig interpolation has emerged as an effective approximation method and can be widely applied in hardware and software model checking. Since the quality of interpolants can critically affect the success and failure, or convergence and divergence of model checking, researchers have put forward a novel and flexible interpolation abstraction-based technique to guide the computation of promising interpolants. In this technique, abstraction lattice is constructed to arrange families of interpolation abstraction for improving the quality of resulting interpolants. However, the original search strategy to explore an abstraction lattice is not efficient when abstraction lattice enlarges and the elapsed time to perform multiple search on the same abstraction lattice is obviously distinct for many problems. In this paper, in order to alleviate these problems, we propose a top-down search space pruning-based algorithm to search the abstraction lattice and implement this algorithm in the well-known model checker Eldarica. We conduct experiments on 179 benchmarks to compare our algorithm respectively against the original search algorithm in Eldarica and the state-of-the-art SMT solver Z3. The experimental results show that our algorithm performs much better in the sense that it is more efficient than Eldarica for most of the benchmarks and it can solve much more benchmarks than Z3.

The paper reports authors' experience in teaching software product lines (SPL) for senior engineers in the company. An effective way for education in the experience is to teach SPL as a paradigm consisting of some key ideas and show how we can introduce the paradigm into the development process. The authors have used PLUS as a reference of such development process. Feature modeling is taught not only as a means of variability modeling but also as a means to facilitate construction of abstraction hierarchy and separation of concerns. Giving anti-patterns of feature modeling and countermeasures to them helps engineers discuss construction of better feature models.

We carried out an experiment to observe the role of transportation for adolescent female students in rural Bangladesh. A senior high school (in Bangladesh, they call it a college) student spends 180-230 minutes to travel only 22km (11 km, single trip) on an average to commute from home to college. Local transport (Tomtom) stops are not always close to their home. The walk 4km to get to the nearest Tomtom stop. The Tomtom does not have a regular timetable. In worst case, the students wait 30 minutes until the Tomtom driver finds sufficient number of passengers. This 11km distance is Female students find it uncomfortable to share congested space with male passengers. They cannot raise their voice when they face sexual harassment inside the car or when they walk. The parents of the female students find it safer to stop their education and arrange a marriage. We proposed a regular college bus service with an adaptive time schedule that follows the routine of the students. In order to make the service sustainable, we designed a model of multi service vehicle named SSW, so that it can earn extra income during its idle time. We concluded that the operational cost can be covered through the SSW model. We identified new requirements for multiservice vehicle to satisfy the needs of a rural community.

Sensor localization is one of the big problems when building large scale indoor sensor networks since GPS is unavailable in indoor environments. Many indoor localization systems have been proposed to tackle the sensor localization problem, yet user cooperation or many anchor nodes are required. In this paper, we propose a sensor localization system using WiFi APs as anchors. WiFi APs are largely installed in indoor environments and are managed by a network system manager. Using WiFi APs as anchors, we can localize sensor nodes without newly deployed anchor nodes. As a first step of our sensor localization system, this paper presents a WiFi AP-RSS monitoring system using sensor nodes. Sensor nodes are equipped with IEEE802.15.4 (ZigBee) modules, which cannot demodulate WiFi (IEEE802.11) signals. We therefore developed a cross-technology signal extraction scheme on sensor nodes. We herein describe the design and implementation of our AP-RSS monitoring system. The experimental evaluations show that our AP-RSS monitoring system successfully retrieves AP-RSS with an average error of 1.26dB.

Bounded Model Checking (BMC) converts a verification problem within a user-specified bound into satisfiability checks of propositional formulas. As the bound deepens, the formulas become larger in size and harder to solve. In this paper, we propose a hybrid approach in which stateless explicit-state exploration (SESE) is integrated into the BMC process to improve the scalability and performance of BMC for the verification of properties expressed in Linear Temporal Logic (LTL). Specifically, SESE is utilized to traverse, under the constraints of Bounded-Context Switching (BCS), the state space of a system design and memorize legal execution paths. These paths are classified according to heuristic state predicates into path clusters, which are then encoded into propositional formulas representing, together with the encoded formula for an LTL property, independent BMC instances. Such BMC instances are solved with SMT solvers running on mutilcores in parallel. Once a counterexample is found for one of the instances, the entire model checking (SESE as well as BMC) terminates. This hybrid checking procedure progresses in an incremental fashion until either a counterexample is found or the user-specified bound is reached. We have implemented this proposed hybrid approach in a tool called Garakabu2 with Yices 2 as its back-end solver. The experimental results show that Garakabu2 outperforms significantly the state-of-the-art BMC methods implemented in SAL for both safety and liveness properties.

Abstract The extended hierarchical state transition matrices (EHSTMs) are a table-based modelling language frequently used in industry for specifying behaviours of systems. However, assuring correctness, i.e., having a design satisfy certain desired properties, is a non-trivial task. To address this problem, a model checker dedicated to EHSTMs called Garakabu2 has been developed. However, there is no formal justification for Garakabu2, since its semantics has never been fully formalised. In this paper, we give a formal semantics to EHSTMs by translating them into CSP, Communicating Sequential Processes. Among the variants of CSP, we use CSP#, which is the modelling language used by PAT model checker, as a target of translation. Our semantics covers most of the features supported by Garakabu2. We manually translate the small examples of EHSTMs to CSP#, and verify them by PAT. We also verify the examples directly using Garakabu2 and show that the results are same. The experiments also indicate that verification using our translation and PAT is much faster than that of Garakabu2 in some cases.

A critical problem with location fingerprinting is the considerable time and effort spent measuring received signal strengths at all location candidates to create the survey database. To reduce this cost, existing methods use a signal path loss model to interpolate part of the survey database from data actually measured at location candidates. However, the positioning accuracy can become degraded, especially in an indoor area delimited by walls. In this paper, we confirm the degradation in accuracy of the existing method through a preliminary experiment, and propose an accurate interpolation method for survey databases. In the proposed method, part of the survey data is interpolated using a path loss model containing wall attenuation. Furthermore, to confirm the effectiveness of the proposed method, we evaluate the location estimation performance with the interpolated survey database and also verify the interpolated data. The proposed method improves the positioning accuracy by 25% over that of the existing method.

We have developed an adhoc wireless positioning network (AWPN) scheme for information-oriented construction that can temporarily and easily provide a positioning area in both indoor and outdoor environments. The particular requirements of AWPNs are easy deployment and easy configuration because the network should be removed on completion of construction and must frequently accompany the active construction section as it shifts from area to area. In this paper, we propose a localization scheme based on the multilateration method to fulfill the requirements of such AWPNs. The proposed scheme locally and dynamically calibrates the attenuation coefficient defined in the path loss model for radio wave propagation in order to reflect local, fresh propagation characteristics. The results of evaluations conducted on the efficacy of our proposed scheme indicate that it reduces the average error by 30% relative to the conventional approach.

We propose a hybrid approach to improving the verification performance of SMT-based bounded model checking for LTL properties. In this approach, stateless explicit-state exploration is utilized to traverse, under the constraints of bounded context switches, the state space of a system design and memorize legal execution paths. These paths are classified according to certain predicates into path clusters, which are then encoded into propositional formulas representing, together with the encoded formula for an LTL property, independent BMC instances. Such BMC instances are solved with SMT solvers running on mutilcores in parallel. Once a counterexample is found for one of the instances, the entire model checking terminates. This hybrid checking procedure progresses in an incremental fashion until either a counterexample is found or the user-specified bound is reached. We have implemented this proposed hybrid approach in a tool called Garakabu2 with CVC4 as its backend solver. The experimental results show that Garakabu2 often outperforms the state-of-the-art pure BMC methods implemented in SAL infinite bounded model checker for both safety and liveness properties.

This paper proposes a mechanism to share and utilize various sensors among multiple Android terminals for a functional enhancement and a battery life extension. The most important contribution is how to emulate the value from remote sensor as a value from a local sensor. By this emulation, all the other applications existed on Google Play Market can utilize remote sensors without any modification.

Hierarchical State Transition Matrix (HSTM) is a table-based modeling language for developing designs of software systems. We have proposed a Satisfiability Modulo Theory (SMT) based Bounded Model Checking (BMC) approach in [1] to provide formal verification supports for conducting rigorous and automatic analysis to improve reliability of HSTM designs. In this paper, we continue that work by developing and evaluating approaches to accelerating BMC of HSTM designs. The approaches center around an unrolled Bounded Reach ability Tree (BRT) of a HSTM design that is built with stateless explicit state exploration. Specifically, reach ability of invalid cells (representing undesired states) of a HSTM design, which occurs within the bound concerned, could be discovered during construction of the BRT, and furthermore, if no such occurrence, the constructed BRT could be utilized to rule out unnecessary subformulas of a BMC instance for verification of LTL properties. We have implemented these approaches in a tool called Garakabu2 with the state-of-the-art SMT solver CVC3 as its back-ended solver. Our preliminary experiments show that verification could be accelerated substantially.

In the region of Japan, broadband network and informatization have spread. However the field of agriculture has not come willingly. The infrastructure that has not been enough in mountainous areas, but various initiatives of computerization are being started using production and distribution as the subjects. Since this began in reality, there are still insufficient matters that have been resolved in regards to the technical validations and cost effectiveness. Therefore necessitates pouring in a tremendous amount of expertise, possibility is ICT and its related technologies of sensors. In our research and developments, we create demo hardware for the experiment using in the farm collected data. On the other hand, making study group with farmers for accumulation of data and experience. That visualized information configure to the platform of knowledge management.

The Mining Software Repositories (MSR) field integrates and analyzes data stored in repositories such as source control and bug repositories to support practitioners. Given the abundance of repository data, scaling up MSR analyses has become a major challenge. Recently, researchers have experimented with conventional techniques like a supercomputer or cloud computing, but these are either too expensive or too hard to configure. This paper proposes to scale up MSR analysis using “general-purpose computing on graphics processing units” (GPGPU) on off-the-shelf video cards. In a representative MSR case study to measure co-change on version history of the Eclipse project, we find that the GPU approach is up to a factor of 43.9 faster than a CPU-only approach.

In this paper, we propose a dynamic channel assignment method that utilizes location information of mobile terminals to calculate the optimal channel scheme in indoor WLAN positioning systems. Our method could achieve two goals: (a) the optimal channel scheme can guarantee a maximum throughput of overall wireless network. (b) terminals can communicate and be located simultaneously in our system. By taking advantage of positioning system, we can know the location of terminals, and such location information can be used to optimize network capacity through assigning appropriate channels. Assigning different channel to neighbouring APs is not only for optimizing network capacity, but also for improving the positioning accuracy due to that it can immigrate the interference among APs and receive accurate signal strength. To confirm its effectiveness, we evaluate our approach by simulation. We compare our method with the single, random, and static methods and the LCCS method. The results illustrate that the throughput of our channel assignment method is higher than other methods.

Reducing the energy consumed in the use of smart phones has become a major challenge for application developers. While this problem can be addressed at various levels, it is important to reduce the energy consumption of individual applications which can vary greatly depending on the behavior of the application. Energy profiling methods are required in order to identify the points in which the applications are consuming excessive energy and to examine how to reduce overall energy consumption by applications.

Hierarchical State Transition Matrix (HSTM) is a table-based modeling language for developing designs of software systems. Although widely used and adopted by (particularly Japanese) software industry, there is still lack of mechanized formal verification supports for conducting rigorous and automatic analysis to improve reliability of HSTM designs. In this paper, we first present a formalization of HSTM designs as state transition systems. Consequentially, based on this formalization, we propose a symbolic encoding approach, through which correctness of a HSTM design with respect to LTL properties could be represented as Bounded Model Checking (BMC) problems that could be determined by Satisfiability Modulo Theories (SMT) solving. We have implemented our encoding approach in a tool called Garakabu2 with the state-of-the-art SMT solver CVC3 as its back-ended solver. Furthermore, in our preliminary experiments, a conceptually simple but steadily effective way of accelerating SMT solving for HSTM designs is investigated and reported.

As the development of embedded systems grows in scale, it is becoming more important for engineers to share development documents such as requirements, design specifications and testing specifications, and to accurately circulate and understand the information necessary for development. Also, many defects that can be originated in the surface expression of the documents are reported through investigations of causes of defects in embedded systems development, In this paper, we highlight improper surface expressions of Japanese documents, and define quality criteria and critiquing rules to detect problems such as ambiguous expressions or omissions of information. We also carry out visual quality inspections and evaluate detection performance, correlations and working time. Then, we verify the validity of the critiquing rules we have defined and apply them to the document critiquing tool to evaluate the quality of the actual documents used in the development of embedded systems. And we quantify the quality of these documents by automatically detecting improper expression. We also apply supplemental critiquing rules to the document critiquing tool for use by non-native speakers of Japanese, and verify its efficacy at improving the quality of Japanese documents created by foreigners.

In this paper, we propose name resolution middleware that involves positional awareness to identify target hosts in wireless visible area communication (WVAC). WVAC is a wireless communication network that enables users to exchange information with nearby hosts, especially within the users' visible area, wherein the underlying network can be locally and temporarily constructed without the aid of any centralized administration. In such communication, the proposed middleware assists the user to intuitively identify a target host by presenting the relative positional relationship among the neighbor hosts. The middleware possesses the following characteristics: (1) it provides simple APIs to be easily utilized by various applications, (2) a dedicated server preliminarily located in the network is not required to operate it, and (3) it adopts a positioning method that could estimate the relative locations of neighbor hosts without any pre-configuration. Finally, we construct a prototype system and evaluate the middleware using this system. The results indicate that this middleware can sufficiently work even on resource-limited mobile devices.

In this paper, we propose three heuristics for high-efficiency selections of MPRs (multipoint relays) in link state QoS routing protocol: MIMS (maximizing integration metric selection), MQES (maximizing QoS-efficiency selection), and MCIS (minimizing cost-inefficiency selection). The basic approach of these selections is to determine a smaller set of MPRs that provide better QoS paths between any two nodes. The main objective in doing so is to maximize the QoS (quality of service) effect while limiting routing overhead for flooding control traffic. In addition, we evaluate the performance of the routing protocols with the proposed selections by simulation. The results indicate that the proposed methods achieve high-efficiency selection; as compared to an existing MPR selection taking into account the QoS requirements, MIMS reduces the maintenance cost by 30%, while the throughput of the resultant path is decreased by 13%, and MCIS reduces the cost by 21% without any decrease in the throughput.

In this paper we propose product line based component unification to reuse works required for component unification such as combined tests, WCET estimation, etc. and properties produced by component unification such as documents, binaries etc. We perform a case study of the personal destination screen with personal identification and find that component unification is worth to consider in product line engineering. Moreover, we present a sketch of an algorithm, which we expect to use in product line engineering tools, to exploit candidate components to be unified for strategic reuse along the product line with the feature model diagram of FORM product line engineering.

This paper presents a new multiple access control (MAC) protocol called adaptive acquisition multiple access with common-transmission channel assignment (AAMA-CT) and its improved one (AAMA-ICT) for wireless multihop mobile ad hoc networks. In the protocol, every node adaptively chooses a usable channel as its transmission channel in advance in multihop mobile environment and takes advantage of request-to-send (RTS) packet transmitted on a common channel to evoke its recipient to complete their communication process on their transmission channels without packet collisions. With this protocol, resource reservation is flexibly and effectively made on multiple channels by half-duplex radios without any help of powerful central controllers and wired backbone networks in an asynchronous fashion. The protocol can solve hidden and exposed terminal problems perfectly as is validated through analysis and simulation results.

This paper presents a new multiple access control (MAC) protocol called adaptive acquisition collision avoidance multiple access with common-transmission code assignment (AACA-CT) for multihop ad hoc wireless networks. Multiple channels are employed in this scheme. One channel is used as the common channel for mobile users (or nodes) contending to reserve traffic channels by means of request-to-send and clear-to-send (RTS/CTS) dialogue. Other channels are used as traffic channels to transmit traffic packets without collision. With this protocol, resource reservation is flexibly and effectively made on multiple frequency bands, frequency-hopping (FH) codes or direct-sequence spread-spectrum (DSSS) codes by half-duplex radios without any help of powerful base stations (BS) or central controllers and wired backbone networks in an asynchronous fashion. The protocol can solve hidden and exposed terminal problems perfectly as is validated through analysis and numerical results. A comparison among the proposed protocol, IEEE 802.11 MAC protocols and the slotted ALOHA protocol shows that the proposed reservation-based approach has advantages over other protocols.

We designed and built an information announcement basic software system that realizes a new using style, called the TAM. This style regards a mobile computer as a server as well as a client. In order to effectively announce information from a mobile computer as a server the system uses stationary computers, called SMHs, that manages mobile computers. The effectiveness of the system has been shown. The system works well and gives a useful environment to clients. In the system, however, communications between a client and a server are always done via the SMH computer associated with the server. This communication path is redundant in some cases. The server cannot provide high quality services to the client because of the redundancy. We design a new information announcement system, called the WOR, which is expansion of the TAM to solve the problem of the redundant path. In the WOR, we assume that a SMH is located at every network domain. The communication method uses two types of the SMH; Home SMH (HSMH) and Foreign SMH (FSMH). The HSMH is the same as the SMH in the TAM. The FSMH finds a shorter path for the mobile computer to provide the service to a client. We show the system to be a useful mobile computing environment to clients by implementing the system.

Since the traffic of NetNews is increasing, storage of all articles becomes a serious problem from the viewpoint of wasting network bandwidth and the amount of disk usage. In addition, not all incoming articles are read by users. We have proposed several caching algorithms to overcome this problem and shown that a selective prefetch scheme gives the best system performance among the proposed ones. However, since the selective prefetch scheme employed a simple prefetching policy, the scheme gave a low hit ratio in some cases. Therefore, the paper improves the selective prefetch scheme from the viewpoint of the amount of disk usage as well as hit ratio. We divide the scheme into three factors: reference span, criterion, and threshold in criterion. Through simulation experiments using actual NetNews logs, we investigate the influence of the factors of the reference span and the threshold to system performance. As a result, it is shown that the reference span is a more significant factor than the threshold and when the selective prefetch scheme has a value of around seven days, reference span keeps a high hit ratio and reduces the amount of disk usage.

Writing device drivers is one of the most difficult tasks to develop or port operating systems (OSs). A device driver needs to be described according to the target device and OS. In the description, programmers must know information about hardware such as specifications of devices and carefully describe complex parts such as timing control. This paper proposes a support system for device driver generation. The inputs for the system are device driver specification which shows operations of the device, OS dependent specification which shows dependent parts on the OS, and device dependent specification which shows dependent parts on the device. As an example, network devices are adopted. The inputs to generate device drivers by the proposed system are described.

The bandwidth problem between a mobile computer and an access point is pointed out, and a copy update mechanism, which can make the best use of the limited bandwidth, is proposed. If the bandwidth of a network is not sufficient, a mobile computer cannot announce all resources, and cannot update some copies on fixed computers. To satisfy client's requests with given bandwidth as much as possible, the proposed mechanism limits traffic of storage type resources in order to announce non-storage type resources prior to storage type resources. Traffic is controlled by limiting the number of concurrent update operations for announcing storage type resources. We implement the prototype and evaluate it. The results show that it can stably announce non-storage type resources.

In a distributed environment, a client-server model is often used because of its ease of implementation. The reliability of the server on the model determines the reliability of the whole system. By making a backup server, the tolerance of server failure can be improved. This method, however, has a long recovery time because a recovery operation includes generally detecting failure, switching to the backup server, starting the server process, and re-executing services executed at failure. Thus, the method cannot be introduced to application areas that have time constraints. The authors aim to implement the highly reliable and available client-server system which is able to recover failures in a very short time. In order to shorten recovery time, process level replication is employed. A server process has more than one copies on different hosts. Copies keep the same status as the original process. Thus, they can replace the original process very quickly when a failure occurs. Several protocols, such as updating the status of copies and recovering from failures, must be specified in order to implement the proposed system. In this paper, protocols for updating copies and recovering from failures are described formally in Timed CSP, which is a process algebraic language, for defining them precisely.

Applying conventional compiler design methodology to a parallelizing compiler, its internal data structures tend to get too complicated quickly. Thus, we introduce object oriented design from the problem analysis stage and achieve the following improvements: 1) consistent modeling from the theory to the implementation; 2) reduced program size through improved reusability based on better class design methodology; and 3) flexible coding through a stub class for parallelization. We extract objects based on stream and thus clarify similarities and differences to the conventional design schemes. Then we show the framework of the internal classes used in our parallelizing compiler which enhances design level reusability in C++ implementation of the compiler. Furthermore, we provide a virtual class to be used as a unit of MIMD style parallel execution and make it a common representation among different parallelization algorithms. Finally, we compare our design against SUIF, which also uses C++, and show the improvements on the design classes.

In traditional operating systems, there are many weak points. In monolithic kernel-based operating systems, many functions have been implemented in the kernel to satisfy various requests from user applications. As a result, the kernel itself has become more complex and bigger than expected, and many weak points have been appeared in it. A microkernel-based operating system improves the weak points of a monolithic kernel-based one by separating the kernel itself from the kernel functions (called system servers). In such a system, a microkernel architecture is supplied for flexibility and expansibility, but there are weak points in that structure too. In order to get over the weak points of traditional operating systems, a new operating system architecture is needed. In this paper, a new kernel structure is suggested. It enables one to reconstruct kernel functions dynamically at execution time, but there are some problems with realizing such a kernel. In this paper, we describe how to divide kernel functions into multiple modules and how to implement the suggested kernel. By implementing and evaluating a prototype of the kernel, the effectiveness of the suggested kernel architecture is confirmed.

We compare organization schemes of out-of-kernel functions in the microkernel-based operating systems, from the viewpoints of concurrent or parallel executions of the functions. We describe two methods; multiprocess method and multi-thread one. With the multiprocess method, the functions are partitioned into some modules to be allocated to processes. With the multi-thread one, the functions are allocated to a single process including multiple threads. We implement system servers according to the methods on uni-processor environment. Performance evaluation shows that the multi-process method gives good performance.>

Light-weight processes, threads, are fast vehicles for concurrent/parallel execution in a single program. There are two thread models: kernel-level thread model; and user-level one. Although the kernel-level threads are more light-weight than UNIX processes; it have observed that they are less light-weight than we expected. Therefore, the user-level thread model has attracted attention of researchers. There have been many user-level thread libraries. However, theses do not seem to support both of portability and parallelism, which are important aspects of software engineering and parallel processing. Parallel Pthread Library (PPL), we are developing, aims at supporting the both. In this paper, we describe PPL. Furthermore, through implementing the first version of PPL on two operating systems and hardware architectures, we compare the basic performance of it with that of other existing user-level thread libraries.>

Non-uniform memory access multiprocessors have potential gains for achieving high performance. These machines are frequently used as computation servers with multiple parallel processes (we use this word instead of jobs) executing at the same time. In such environments, the efficiency of a parallel process can be significantly affected by the processor scheduling strategy. LA two-level scheduling strategy, which is a kind of space-multiplexing scheduling strategy, is a promising one for large-scale multiprocessors. This paper describes the structure and interface of the two-level scheduling strategy. We also propose basic alternatives in this strategy: as alternatives of handling free processors, (1) running-process-first scheme and (2) waiting-process-first scheme; as alternatives of handling idle processors, (1) idle-processor-hold scheme and (2) idle-processor-release scheme. These alternatives are examined through simulation experiments.>

The reconfigurable parallel processor system under development at Kyushu University is an MIMD-type multiprocessor which consists of N processing-elements (currently N is 128) fully connected by S N × N crossbar networks (currently S is 1). Each PE (Processing Element) employs a Fujitsu SPARC MB86900/10 chip-set, a Weitek WTL1164/65 chip-set, an MMU (Memory Management Unit) with 64K bytes of cache, 4M bytes of memory, and an MCU (Message Communication Unit). The modular 128 × 128 crossbar network is implemented by arranging 256 identical 8 × 8 crossbar LSI-modules in a 16 × 16 matrix form. The full 128-PE configuration achieves supercomputer levels of performance by providing 1.28 GIPS and 205 MFLOPS of computing power, 512M bytes of memory, and 2.56G bytes/s of inter-PE communication bandwidth. At the same time, it exploits unique reconfigurability in the memory and intercommunication architectures. By utilizing these two types of reconfigurability, we believe that the system can be effectively tailored to a wide spectrum of applications such as numerical computation, image processing, computer graphics, artificial intelligence, neurocomputing, and so on.

The M/sup (m)//M/K and M/sup (m)//M/ infinity models with synchronous fluctuation of traffic intensity are considered. The phase process is assumed to make changes according to an irreducible m-phase Markov chain. In contrast to the model with asynchronous fluctuation of parameters, a phase change may occur only in synchronization with an arrival or beginning of service of a customer. The authors study the steady-state regime of their models and observe that closed-form solutions for the limiting probabilities are generally difficult to obtain. They give a necessary and sufficient condition for the steady state to be attained. Numerical examples are discussed that demonstrate the behavior of the system under different traffic conditions.>

An approximate analytic tool called equilibrium point analysis is applied to the problem of memory interference in multiprocessor systems. It is a simple and powerful analytic tool based on the fluid approximation and has been widely used for packet broadcast systems. It is shown that quite general multiprocessor systems can be studied quite simply with this technique, these systems include those made up of many classes of processors and memory modules with arbitrary static memory reference patterns, and systems with bus connections between processors and memories. In most cases, the approximation is shown to be sufficiently good. One of the advantages of this technique is that the error is smaller for larger systems for which no appropriate analytic tools have existed until now.>

In this paper, two-dimensional arrays of elements of an arbitrary finite field are examined, especially arrays having maximum-area matrices. We first define two-dimensional linear recurring arrays. In order to study the characteristics of two-dimensional linear recurring arrays, we also define two-dimensional linear cyclic codes. A systematic method of constructing two-dimensional linear recurring arrays having maximum-area matrices is given using the theory of two-dimensional cyclic codes. These arrays, here called\gamma \beta-arrays, may be said to be two-dimensional analogs ofM-sequences. A\gamma \beta-array of areaN_x \times N_yexists overGF(q)if and only ifN_x N_yis equal toq^N _ 1for some positive integerN. Many interesting characteristics of the\gamma \beta-array, such as the properties of its autocorrelation function and the properties of the characteristic arrays, are deduced and explained.