Optical Interconnection For Multiprocessor Computer Bus Systems

We review the recent results on the design and implementation of the performance-optimized bidirectional optical backplane bus aimed at high speed multiprocessor systems. It employs an array of multiplexed holograms, in conjunction with a waveguiding plate within which cascaded fanouts are generated. Data transfer rate of 1.2 Gbit/sec at 1300 nm is demonstrated with a single bus line for a system composed of nine boards. Packaging-related issues and misalignment effects are addressed. Theoretical treatment to minimize fluctuations among the received powers at each board was carried out and the overall performance was optimized. We also introduce a hybrid optical backplane with multiple bus lines. The hybrid backplane maintains the same waveguiding structure, and exploits optoelectronic array devices. A new demonstration system is being implemented. The optical backplane that we developed is transparent to higher level bus protocols, thus can support standard backplane buses such as Futurebus+, Multibus II, and VMEbus.

Large-scale MIN-based shared-memory multiprocessor systems have long shared memory latency. Private caches can improve memory access latency but they may suf fer from the cache coherence problem and potentially lower data locality due to data sharing and multiproces sor scheduling. These two problems also increase shared memory load and may result in frequent memory stalls. In this paper, we evaluate the performance of memory caches, a cache memory placed in front of shared memory, in a large-scale multiprocessor system in the presence of pro cessor caches. The memory cache is shown to have good performance and scalability.

As faults are unavoidable in large scale multiprocessor systems, it is important to be able to determine which units of the system are working and which are faulty. System-level diagnosis is a long-standing realistic approach to detect faults in multiprocessor systems. Diagnosis is based on the results of tests executed on the system units. In this work we evaluate the performance of evolutionary algorithms applied to the diagnosis problem. Experimental results are presented for both the traditional genetic algorithm (GA) and specialized versions of the GA. We then propose and evaluate specialized versions of Estimation of Distribution Algorithms (EDA) for system-level diagnosis: the compact GA and Population-Based Incremental Learning both with and without negative examples. The evaluation was performed using four metrics: the average number of generations needed to find the solution, the average fitness after up to 500 generations, the percentage of tests that got to the optimal solution and the average time until the solution was found. An analysis of experimental results shows that more sophisticated algorithms converge faster to the optimal solution.

Approximate performance/cost analysis of m-level hierarchical multiprocessor systems

Directory-based cache coherence scheme using number-balanced binary tree

This paper presents a real-time and cost effective method for sensing moving objects on the freeway. Based on the proposed method, we can evaluate the traffic rate of vehicles, the speed of moving objects and distinguish the kind of vehicle using their length. It is different from the conventional vehicle detection systems that need expensive hardware architecture, such as the multiprocessor system and VME bus, to implement the complicated algorithm. We develop an efficient and simple algorithm that has been successfully installed in a general industrial IBM-compatible PC. The two trigger lines policy is proposed to reduce the computation time of this system. Because there is an error signal due to the difference between the moving objects and that of the background on the trigger line, we construct a formal grammar to describe these pulse-like error signals based on the compiler's technique in the software engineering. Therefore, the system states can be easily derived by the semantic routines. To overcome the brightness of day/night-switching and the cover of cloudy shadow, etc., we use a novel adaptive neural network to train the grey level of the background, and then the system parameters can be adapted quickly. The analyzer is called VSS (Vehicle Supervising System), and has been developed and tested on the freeway between Taipei and Lin-Ko City in Taiwan. >

Одним із домінуючих напрямів удосконалення конструкції автобусів є роботи з підвищення ефективності функціонування їх допоміжних систем, при цьому одночасно зі зниженням ними експлуатаційних витрат енергії, тобто покращення паливної ощадливості. На паливну ощадливість автобусів істотно впливають енергетичні витрати допоміжних агрегатів і систем. Щодо автобусів будь-якого класу, то однією із найбільших споживачів енергії є система опалення пасажирського приміщення і робочого місця водія. Встановлено, що реалізація завдання зниження енергетичних витрат системою опалення салонів автобусів є важливою проблемою під час проєктування й експлуатації автобусів. Отримано результати випробувань і здійснено їх аналіз щодо доцільності використання опалювачів салону автобусів з одним вентилятором, замість двох. Практична значущість досліджень полягає у зменшенні кількості електродвигунів з вентиляторами та зниження енергоспоживання системою опалення салону автобусів. Під час експериментальних досліджень проведено випробування аеродинамічних характеристик опалювачів з двома і одним осьовим вентилятором. Випробовували продуктивність за різних значень напруги на клемах електродвигунів та теплової ефективності радіатора обігрівача – температури повітря на вході і виході з обігрівача. За результатами експерименту встановлено, що продуктивність обігрівача із двома вентиляторами є тільки на 25 % більша, ніж з одним. Це явище пояснено на основі моделювання процесу з допомогою електричної аналогії. Обґрунтовано, що за одного і того самого типу теплорозсіювального радіатора, доцільно використовувати опалювачі салону пасажирських транспортних засобів із одним вентилятором замість двох. Причиною меншої ефективності опалювачів з двома вентиляторами є насамперед те, що аеродинамічний опір на вході двох вентиляторів є удвічі більшим, ніж на одному вентиляторі. Зі збільшенням продуктивності вентилятора теплотворність радіатора зменшується. Це пов'язано з тим, що зі збільшенням повітряного потоку через серцевину радіатора, зростання зняття повітрям температури з поверхні трубок радіатора перевищує інтенсивність теплообміну між нагріваючою рідиною і внутрішньою поверхнею трубок радіатора. Для збільшення аеродинамічної ефективності опалювачів салону доцільно зменшити аеродинамічний опір на вході у вентилятор, наприклад, застосуванням вентиляторів з високими аеродинамічними характеристиками.

Through analysis and experiments, this paper investigates two-phase waiting algorithms to minimize the cost of waiting for synchronization in large-scale multiprocessors. In a two-phase algorithm, a thread first waits by polling a synchronization variable. If the cost of polling reaches a limit L poll and further waiting is necessary, the thread is blocked, incurring an additional fixed cost, B . The choice of L poll is a critical determinant of the performance of two-phase algorithms. We focus on methods for statically determining L poll because the run-time overhead of dynamically determining L poll can be comparable to the cost of blocking in large-scale multiprocessor systems with lightweight threads. Our experiments show that always-block ( L poll = 0) is a good waiting algorithm with performance that is usually close to the best of the algorithms compared. We show that even better performance can be achieved with a static choice of L poll based on knowledge of likely wait-time distributions. Motivated by the observation that different synchronization types exhibit different wait-time distributions, we prove that a static choice of L poll can yield close to optimal on-line performance against an adversary that is restricted to choosing wait times from a fixed family of probability distributions. This result allows us to make an optimal static choice of L poll based on synchronization type. For exponentially distributed wait times, we prove that setting L poll = 1n(e-1) B results in a waiting cost that is no more than e/(e-1) times the cost of an optimal off-line algorithm. For uniformly distributed wait times, we prove that setting L poll =1/2(square root of 5 -1) B results in a waiting cost that is no more than (square root of 5 + 1)/2 (the golden ratio) times the cost of an optimal off-line algorithm. Experimental measurements of several parallel applications on the Alewife multiprocessor simulator corroborate our theoretical findings.

This report provides guidelines for the planning, design, and implementation of Bus On Shoulder (BOS) operations along urban freeways and major arterials. Making BOS a reality requires a closely coordinated partnership effort involving transit agencies, state departments of transportation (DOTs), metropolitan planning organizations (MPOs), enforcement agencies, and the Federal Highway Administration (FHWA). The report should be useful as a decision-making guide to assist transit operators, state DOTs, MPOs, and other stakeholders in assessing the feasibility of the BOS concept, developing safe and effective BOS plans, implementing initial BOS operations, and maintaining or expanding ongoing BOS operations. This guide includes seven case studies in the following cities: Minneapolis-St. Paul, Minnesota; Miami-Dade, Florida; San Diego, California; Old Bridge, New Jersey; Ottawa, Ontario, Canada; Columbus, Ohio; and Atlanta, Georgia.

In order to further scale down the size of computers and increase their speed, optical technology is expected to substitute electrical technology for inter-chip motherboard communication. The increasing inter-chip requirements makes it extremely difficult to overcome the delay, power, and bandwidth limitations of the existing electrical wires technology In this research, unguided optical communication bus (UOCB) design for inter-chip communication is analyzed. A UOCB includes transceiver arrays for each chip that transmit information without a waveguide, such that an array of beams propagates through a solid plate. The solid plate is the computer motherboard and is used to hold the chip physically and, in addition, as a propagation medium for the communication beams. The bus space is reused, or multiplexed, such that more than one beam propagates though it simultaneously. The communication through the bus takes advantage of the scattering effect, reflection and diffusion from the walls. We examined the data transmission requirement for uncorrelated optical communication paths between the multiple-input multiple-output (MIMO) optical receiver and transmission arrays over highly diffused propagation bus. Each optical communication path between potential receiver and transmitter locations was described in terms of the optical channel gain, representing the individual optical path. An example of a MIMO gain matrix H between multiple spatial locations was evaluated.

The best approach to a large computing capability is to build your own multi-processor system, utilizing the most effective elements available from the leading hardware manufacturers. To understand this approach, it would be useful to describe the type of system which is to be built. It is evident that many of the system characteristics will be prescribed by the application, others will be purely a matter of personal choice. The essential characteristics are few in number and must not be confused with the non-essential characteristics. The remainder of this paper presents a set of do-it-yourself instructions for designing your own multi-processor system which stresses the essential characteristics. The intent being that the reader can follow through these instructions and design his own system for his own particular application. In this way, each reader can have a specific system in mind which he can evaluate critically. Although there would be individual differences in the systems under consideration by different individuals, the essential characteristics would be the same, and discussion would then tend to center about these essential features. The paper concludes with a summary in which the design approach is reviewed in an attempt to emphasize the utility of the approach.

Order statistics on optically interconnected multiprocessor systems

Optical interconnections using two-dimensional waveguides are presented. Light beams whose incident angles are greater than the critical angle of a waveguide can propagate within that waveguide, which behaves as an optical bus. Such optical buses are suitable for massively parallel processing because they have a large number fan-outs and no skew. Estimated propagation distance in the waveguides is roughly 500 mm. One to several hundred interconnections may be achieved. Glass plates with concave lenses are used to demonstrate bus operations.

The Role of Quality Assessment for Development of Sustainable Bus Service in Mid-sized Cities of India: A Case Study of Patna

Commuters and tourists in the Philippines heavily rely on buses as transportation links in cities and provinces, yet an issue that remains unsolved is the lack of real-time bus information readily available for bus passengers and operators. Victory Liner, Inc. is one of the country's largest provincial bus companies. However, their bus schedules are still drastically affected by unpredictable conditions, resulting to passengers cluelessly waiting for their buses' arrival. Hence, this paper explores the development of a real-time bus- tracking Android application called “BusTap” to address the gap in knowledge in the public bus transport service in Victory Liner Baguio using Global Positioning System (GPS) technology. With the use of Scrum methodology, the researchers were able to identify the necessary information requirements needed to create BusTap, determine the application's architectural framework, design and develop its features, as well as measure the app's extent of usability by floating Usefulness, Satisfaction, and Ease of use (USE) questionnaires to Baguio City bus passengers and Victory Liner Baguio drivers. It was concluded that: a) the identified information requirements were vital in developing the application's features, b)using a 4+1 architectural view model was helpful for project cohesion and organization, c) the features identified were crucial in eliminating the gap in knowledge between the bus operator and bus passengers, and d) based from the computed overall mean levelof agreement of 6.46 and 6.48 from the evaluation of passenger respondents and driver respondents respectively, BusTap users strongly agree that BusTap is a useful, easy to use, and easy to learn mobile application that satisfies its users' needs.