Search

Introduces an approach to acceleration of nonnumeric, database and information retrieval operations using hardware support for the ordered table hashing and radix algorithms. Architecture of the proposed algorithm; Implementation hierarchy of database operations; Analytical modeling of select, sort and join database operations.

Bus-based shared memory multiprocessors with private caches and snooping write-invalidate cache coherence protocols are dominant form of small- to medium-scale parallel machines today. In these systems, the high memory latency poses the major hurdle in achieving high performance. One way to cope with this problem is to use various techniques for tolerating high memory latency. Software-controlled cache prefetching and data forwarding are two widely used techniques for tolerating high memory latency in scalable cache-coherent shared memory multiprocessors. However, some previous studies have shown that these techniques are not so effective in bus-based shared memory multiprocessors. In this paper, we propose a novel software-controlled technique called cache injection, which combines consumer and producer initiated approach, and broadcasting nature of bus. Performance evaluation based on program-driven simulation and a set of scientific applications and test benchmarks shows that cache injection is highly effective in reducing misses and bus traffic. [Copyright &y& Elsevier]

Looks at the application of Obelix search engine in electronic commerce; Concept of the search engine; Design of Obelix; Three phases of information acquisition.

Presents a classification for software solutions to cache coherence in shared-memory multiprocessors. How this classification can be applied to more completely understand existing approaches and explore possible alternatives; Limitations of existing classifications; Criteria on which classification scheme was based; Application of classification scheme to existing software cache coherence schemes. INSET: When is a memory system incoherent..

The article discusses the three dimensions of human intelligence including vertical, lateral, and longitudinal that computer scientists and engineers who undertake daily technical challenges often overlook that relate to professional issues. Intelligence relates to deep knowledge about the profession, other scientific fields, cultures and languages. It also pertains to the ability to foresee possible problem and prepare for the future in order to reduce loss and optimize benefits. Several layers of human knowledge which every professional in computer science and engineering must know are also explored.

Considers whether distance learning could result in the creation of a global university. Future scenarios for distance learning resulting from the widespread adoption of the Internet; Prerequisites of a global university; Role of knowledge delivery in addressing strategic distance learning issues; Obstacles to the creation of a global university.

Focuses on the concept of cache memory as a solution for the time domain gap between processor technology and memory technology. Hardware-based and software-based solutions; Exploitation of the principles of temporal and spatial locality; Systems with unified treatment of different locality types.

Big data processing is becoming a reality in numerous real-world applications. With the emergence of new data intensive technologies and increasing amounts of data, new computing concepts are needed. The integration of big data producing technologies, such as wireless sensor networks, Internet of Things, and cloud computing, into cyber-physical systems is reducing the available time to find the appropriate solutions. This paper presents one possible solution for the coming exascale big data processing: a data flow computing concept. The performance of data flow systems that are processing big data should not be measured with the measures defined for the prevailing control flow systems. A new benchmarking methodology is proposed, which integrates the performance issues of speed, area, and power needed to execute the task. The computer ranking would look different if the new benchmarking methodologies were used; data flow systems would outperform control flow systems. This statement is backed by the recent results gained from implementations of specialized algorithms and applications in data flow systems. They show considerable factors of speedup, space savings, and power reductions regarding the implementations of the same in control flow computers. In our view, the next step of data flow computing development should be a move from specialized to more general algorithms and applications. [ABSTRACT FROM AUTHOR]

This paper presents a new muscle contraction (MC) sensor. This MC sensor is based on a novel principle whereby muscle tension is measured during muscle contractions. During the measurement, the sensor is fixed on the skin surface above the muscle, while the sensor tip applies pressure and causes an indentation of the skin and intermediate layer directly above the muscle and muscle itself. The force on the sensor tip is then measured. This force is roughly proportional to the tension of the muscle. The measurement is non-invasive and selective. Selectivity of MC measurement refers to the specific muscle or part of the muscle that is being measured and is limited by the size of the sensor tip. The sensor is relatively small and light so that the measurements can be performed while the measured subject performs different activities. Test measurements with this MC sensor on the biceps brachii muscle under isometric conditions (elbow angle 90°) showed a high individual linear correlation between the isometric force and MC signal amplitudes (0.97 = r = 1). The measurements also revealed a strong correlation between the MC and electromyogram (EMG) signals as well as good dynamic behaviour by the MC sensor. We believe that this MC sensor, when fully tested, will be a useful device for muscle mechanic diagnostics and that it will be complementary to existing methods. [ABSTRACT FROM AUTHOR]

This paper describes the structure and the underlying rationale of a new course dedicated to capability maturity model integration (CMMI)-directed design of wireless sensor networks (WSNs)-based biomedical applications that stresses: 1) engineering-, medico-engineering-, and informatics-related issues; 2) design for general- and special-purpose systems; and 3) the creation of synergistic effects that enable formation of entrepreneurial multidisciplinary teams able to organize and implement the development of these health-related pervasive computing applications. Formal education so far still focuses on treating only strictly separated and specialized topic areas. However, as the need for cooperation and mutual learning between students oriented toward different fields grows, the need for a multidisciplinary educational approach becomes more and more important. For a technical education to be complete, it is no longer enough to train scientists and engineers solely in technical areas. In development and implementation of technology-driven applications, multidisciplinary issues should be properly addressed in the academic sense. The interdisciplinary understanding and synergy achieved are tested through examinations and workshops. The transdisciplinary knowledge improvement is also statistically evaluated, using a system of metrics developed experimentally. [ABSTRACT FROM AUTHOR]

The purpose of the methodology described in this paper is to highlight an effective method for the organization of research results into written and oral forms. Authorities within supervising universities have realized that strong research by a candidate is often obscured by poor presentation, leading to the paper being ignored by the research community and journal reviewers. On the basis of their academic background, the writers of this paper decided to form a set of clear guidelines for writing research papers and giving oral presentations aimed at helping Ph.D. students. To support the effectiveness of the methodology proposed, a statistical analysis has been conducted. The methodology described in this paper was initially intended for use in the fields of computer engineering; however, it is applicable more widely. In conclusion, if the methodology reported in this paper is followed strictly, it is much less likely that a good piece of work would be rejected for publication, and/or remain anonymous, due to inadequate presentation. [ABSTRACT FROM AUTHOR]

Courses in Computer Architecture and Organization are regularly included in Computer Engineering curricula. These courses are usually organized in such a way that students obtain not only a purely theoretical experience, but also a practical understanding of the topics lectured. This practical work is usually done in a laboratory using simulators of computer systems. Since the open literature contains a variety of simulators being used for such purposes, this paper attempts to give a survey of simulators suitable for teaching courses in computer architecture and organization, to establish the evaluation criteria and to evaluate selected simulators according to these criteria. [ABSTRACT FROM AUTHOR]

Presents four manet routing algorithms along with a hybrid approach. Explanation of the functions of a link-state routing algorithms; Advantages of ad hoc on-demand distance vector routing (AODVR); Comparison between AODVR and dynamic source routing.