Clusters have become a very cost-effective platform for high-pelformance computing. In these systems, the trend is towards the interconnection network becoming the system bottleneck. Therefore, in the future, scheduling strategies will have to take into account the communication requirements of the applications and the communication bandwidth that the network can offeel: One of the key issues i...

This paper describes how entrepreneurial firms can use superior architectural knowledge to open up a technical system to gain strategic advantage. The strategy involves, first, identifying “bottlenecks” in the existing system, and then creating a new open architecture that isolates the bottlenecks in modules and allows others to connect to the system at key interfaces. An entrepreneurial firm w...

The model of a single central bottleneck for human information processing is critically examined. Most evidence cited in support of the model has been observed within the overlapping tasks paradigm. It is shown here that most findings obtained within that paradigm and that were used to support the model are also consistent with a simple resource model. The most prominent findings are the millis...

In a middleware environment, various types of transactions are processed simultaneously. In such an environment, it is very important to know the amount of resources necessary for processing each type of transaction. Such data can be used both for resource planning and bottleneck identification. This report proposes a new approach to estimate the per-transaction-type resource consumption in a r...

Text mining for global health surveillance is an emerging technology that is gaining increased attention from public health organisations and governments. The lack of multilingual resources such as WordNets specifically targeted at this task have so far been a major bottleneck. This paper reports on a major upgrade to the BioCaster Web monitoring system and its freely available multilingual ont...

In multicast applications such as video conference which consist of multiple streams, not all streams are of equal interest to all receivers. In this case we believe that this disparity in receiver interest should be reflected in the rate adaptation. This paper presents collaborative rate management architecture, named CRM, for layered multicast streams. CRM estimates shared bottleneck links am...

Some natural language processing tasks can be learned from example corpora, but having enough examples for the task at hands can be a bottleneck. In this work we address how Wikipedia and DBpedia, two freely available language resources, can be used to support Named Entity Recognition, a fundamental task in Information Extraction and a necessary step of other tasks such as Co-reference Resoluti...

The amount of scientific data generated by simulations or collected from large scale experiments have reached levels that cannot be stored in the researcher’s workstation or even in his/her local computer center. Such data are vital to large scientific collaborations dispersed over wide-area networks. In the past, the concept of a Grid infrastructure [1] mainly emphasized the computational aspe...

A class of open processing networks operating under a maximum pressure policy is considered in the heavy traffic regime. We prove that the diffusion-scaled workload process for a network with several bottleneck resources converges to a semimartingale reflecting Brownian motion (SRBM) living in a polyhedral cone. We also establish a state space collapse result that the queue length process can b...

With the development of high-speed backbone network, more and more traffic load is pushed to the Internet edge equipments and end hosts. Newly emerged bottleneck problems in end systems ask for deploying Quality of Service (QoS) in them. Meanwhile, the tremendous traffic brought by multimedia communications asks for End-to-End QoS. Facing these facts and challenges, a framework of deploying QoS...