An emerging trend in the field of Graphics Processing Unit (GPU) computing is the harnessing of multiple devices to cope with scalability and performance requirements. However, multi-GPU execution adds new challenges ...
详细信息
ISBN:
(纸本)9781450324694
An emerging trend in the field of Graphics Processing Unit (GPU) computing is the harnessing of multiple devices to cope with scalability and performance requirements. However, multi-GPU execution adds new challenges to the already complex world of General Purpose computing on GPUs (GPGPU), such as the efficient problem decomposition, and dealing with device heterogeneity. To this extent, we propose the use of the Marrow algorithmic skeleton framework (ASkF) to abstract most of the details intrinsic to the programming of such platforms. To the best of our knowledge, Marrow is the first ASkF to support skeleton nesting on single and (now) multiple GPU systems. In this paper we present how it can transparently distribute the execution of skeleton compositions among a set of, possibly, heterogeneous devices. An experimental evaluation assesses the proposal's effectiveness, from a scalability and performance perspective, with good results. Copyright 2014 acm.
The use of electronic medias for payment has been increasingly adopted, instead of employing money in currency paper or check directly. Considering this electronic funds transfer (EFT) scenario, we developed a model c...
详细信息
ISBN:
(纸本)9781450324694
The use of electronic medias for payment has been increasingly adopted, instead of employing money in currency paper or check directly. Considering this electronic funds transfer (EFT) scenario, we developed a model called GetLB which comprises not only a completely new and efficient scheduler but also a cooperative communication infrastructure for handling heterogeneous and dynamic environments. The scientific contribution consists of a scheduling heuristic that combines static data from transactions and dynamic one from processing nodes to overcome the limitations of Round-Robin. Besides the GetLB's description, this article also presents a prototype evaluation by using both traces and configurations obtained with a real EFT company. Copyright 2014 acm.
The use of computation alongside the natural sciences is moving research forward at unprecedented rates. Computational scientists are in high demand, and the undergraduate level is a great place to begin training stud...
详细信息
ISBN:
(纸本)9781450329668
The use of computation alongside the natural sciences is moving research forward at unprecedented rates. Computational scientists are in high demand, and the undergraduate level is a great place to begin training students for work in this area. Furthermore, studies have shown that applied programs such as computational science are attractive to students and aid in retention. Yet, the number of undergraduate computational science programs remains very limited. Throughout informal conversations with colleagues who were interested in combining computing and science, we repeatedly heard 2 reasons why a computational science program was missing from their institution: 1) they lacked counterparts in the natural sciences who were interested in working with them and 2) their department couldn't support the change in personnel or curriculum that they thought was required to introduce and maintain a computational science program. Addressing the first concern, this poster displays some of what was learned from interviews with 20 natural scientists regarding how they currently or might work with a computational counterpart. Our hope is that this information might be used in conversations with reluctant natural scientists. Addressing the second concern, this poster summarizes the content of computational science programs that currently exist for undergraduates, including majors, minors, computational tracks in science majors or science tracks in computational majors, and science or computational courses with complementary material. Our hope is that this summary will encourage colleagues that, given such variety, there is a place for some form of computational science at their institution.
Enclosure partitioning approaches, such as Treemaps, have proved their effectiveness in visualizing large hierarchical structures within a compact and limited display area. Most of the Treemaps techniques do not use n...
详细信息
ISBN:
(纸本)9781450324694
Enclosure partitioning approaches, such as Treemaps, have proved their effectiveness in visualizing large hierarchical structures within a compact and limited display area. Most of the Treemaps techniques do not use node-links to show the structural relations. This paper presents a new tree visualization approach known as Drawer-Tree that can be used to present the structure, organization and interrelation of big data. By utilizing the display space with traditional node-link visualization, we have developed a novel method for visualizing tree structures with high scalability. The name "drawer" is a metaphor that helps people understand the visualization. Copyright 2014 acm.
Relevance is a key concept nowadays. We need to search for relevant information but we do not want to spend much of our time doing it. Most times it is hard to choose what is worth looking at. To help it, this paper p...
详细信息
ISBN:
(纸本)9781450324694
Relevance is a key concept nowadays. We need to search for relevant information but we do not want to spend much of our time doing it. Most times it is hard to choose what is worth looking at. To help it, this paper proposes a framework that uses ontologies to suggest relevant topics. This framework is based on a cognitive theory called Relevance Theory [4]. In this particular case, we used a domain ontology to represent a proficiency test context and an application ontology to represent the relevance method. A proof of concept was conducted in order to demonstrate the validity of the framework. Some preliminary results point that the suggestion made from the system took to slightly more focused learning paths. Copyright 2014 acm.
In the social network, competitive influence spread is the problem of finding positive seed vertices that propagate information so as to minimize the influence spread of negative vertices. However, the existing heuris...
详细信息
ISBN:
(纸本)9781450324694
In the social network, competitive influence spread is the problem of finding positive seed vertices that propagate information so as to minimize the influence spread of negative vertices. However, the existing heuristic methods need to be further improved. Therefore, we devote to prevent the diffusion of negative information under the competitive independent cascade (CIC) model. In this paper, we propose a new way to tackle the competitive influence problem, referred to as local influence tree (LIT). We carry out experiments on the real-world datasets, the experiments have verified the effectiveness of the proposed methods compared to the baseline methods. Copyright 2014 acm.
There are several challenges for monitoring the patients with specific requirements such as people with dementia. For example, vascular dementia which is caused generally after stroke could result in serious condition...
详细信息
ISBN:
(纸本)9781450324694
There are several challenges for monitoring the patients with specific requirements such as people with dementia. For example, vascular dementia which is caused generally after stroke could result in serious conditions and change of behaviour such as wandering, loss of vision and speech. Although the nursing staff make sincere effort for taking care and monitoring of the patients, it is rare that a nursing staff is allocated to each patient. Hence even a minor lack of attention can lead to havoc situation if any of the patient is found to be missing. This results in high stress for the nursing staff and the hospital management. The aim of this work is to develop techniques for secure monitoring of dementia patients in hospital environments. Our model tracks the patients in real time and can generate alarms if the location of the patients is found to be suspicious. Furthermore, our model makes use of the existing infrastructures to minimize the cost of deployment. Copyright 2014 acm.
Security and privacy concerns are essential in cloud computing scenarios, because cloud customers and end customers have to trust the cloud provider with their critical business data and even their IT infrastructure. ...
详细信息
ISBN:
(纸本)9781450324694
Security and privacy concerns are essential in cloud computing scenarios, because cloud customers and end customers have to trust the cloud provider with their critical business data and even their IT infrastructure. In projects these are often addressed late in the software development life-cycle, because these are difficult to elicit in cloud scenarios, due to the large amount of stakeholders and technologies involved. We contribute a catalog of security and privacy requirement patterns that support software engineers in eliciting these requirements. As requirements patterns provide artifacts for re-using requirements. This paper shows how these requirements can be classified according to cloud security and privacy goals. Furthermore, we provide a structured method on how to elicit the right requirements for a given scenario. We mined these requirements patterns from existing security analysis of public organizations such as ENISA and the Cloud Security Alliance, from our practical experience in the cloud domain, and from our previous research in cloud security. We validate our requirements patterns in co-operation with industrial partners of the ClouDAT project. Copyright 2014 acm.
Our society has become ever more dependent on large datacenters. Search engines, e-commerce and cloud computing are just some of the broadly used services that rely on large scale datacenters. Datacenter managers are ...
详细信息
ISBN:
(纸本)9781450324694
Our society has become ever more dependent on large datacenters. Search engines, e-commerce and cloud computing are just some of the broadly used services that rely on large scale datacenters. Datacenter managers are reluctant to non-functional changes on the facilities of a perfectly operational installation as failures can be very expensive. Therefore, one of the big challenges of green computing is how to reduce the energy consumption and environmental impact of such systems without compromising the business. In this work, we propose a thermal monitoring tool for datacenters which is based on a WSN composed of ready-to-use modules. This tool provides a better understanding of the thermal behavior of datacenters and can help datacenter managers, for example, to manually adjust the cooling system in order to avoid energy waste and reduce cost. There is very low intrusiveness to the server facilities, as the tool is 100% independent of the server operability and requires only the setup of small wireless and battery powered sensors. Our tool was implemented and tested on a real datacenter in order to demonstrate the feasibility of our approach. Copyright 2014 acm.
With the widespread of rich mobile applications, the usage of mobile devices, especially smart phones and tablets, has become popular nowadays. However, battery in the mobile devices often limits continuous usages wit...
详细信息
ISBN:
(纸本)9781450324694
With the widespread of rich mobile applications, the usage of mobile devices, especially smart phones and tablets, has become popular nowadays. However, battery in the mobile devices often limits continuous usages with its small size and capacity. Therefore, power consumption of mobile devices is a critical issue, not only for extending lifetime use of mobile devices, but also for creating a green IT which is a raising concern in academic and industrial communities. The goal of this paper is to investigate the power consumption of mobile devices and resource usages for various applications. To meet the goal, we have performed a number of experiments and detailed evaluations of resource usages and power consumption for various applications using a number of tools. In addition, we have measured performance metrics for applications either using a mobile device or running in the Amazon cloud. We examine the impact of various factors and provide insights on power consumption for different mobile applications. Copyright 2014 acm.
暂无评论