检索结果-内蒙古大学图书馆

MPI-HMMER-boost: Distributed FPGA acceleration

Journal of VLSI Signal Processing Systems for Signal, Image, and Video Technology 2007年第3期48卷 223-238页

作者： Walters, John Paul Meng, Xiandong Chaudhary, Vipin Oliver, Tim Yeow, Leow Yuan Nathan, Darran Schmidt, Bertil Landman, Joseph Institute for Scientific Computing Wayne State University Detroit MI 48202 United States Electrical and Computer Engineering Department Wayne State University Detroit MI 48202 United States Department of Computer Science and Engineering University at Buffalo State University of New York Buffalo NY 14260 United States Progeniq Pte Ltd. 8 Prince George's Park 118407 Singapore Singapore UNSW Asia 1 Kay Siang Road 248922 Queenstown Singapore Scalable Informatics LLC 2433 Woodmont Canton MI 48188 United States

HMMER, based on the profile Hidden Markov Model (HMM) is one of the most widely used sequence database searching tools, allowing researchers to compare HMMs to sequence databases or sequences to HMM databases. Such searches often take many hours and consume a great number of CPU cycles on modern computers. We present a cluster-enabled hardware/software-accelerated implementation of the HMMER search tool hmmsearch. Our results show that combining the parallel efficiency of a cluster with one or more high-speed hardware accelerators (FPGAs) can significantly improve performance for even the most time consuming searches, often reducing search times from several hours to minutes. © 2007 Springer science + Business Media, LLC.

关键词： data mining

来源：评论

学校读者我要写书评

暂无评论

Identification and removal of program slice criteria for code size reduction in embedded systems

IFIP Advances in Information and Communication Technology

引用

IFIP Advances in Information and Communication Technology 2007年 231卷 269-278页

作者： Panahi, Mark Harmon, Trevor Colmenares, Juan A. Gorappa, Shruti Klefstad, Raymond Department of Electrical Engineering and Computer Science University of California IrvineCA92697 United States Applied Computing Institute University of Zulia Venezuela

ISBN: (纸本)9780387722573

Code shrinking is a technique for reducing the size of a software system by detecting and eliminating unused features. It is a static approach that is limited to information known at build time. We demonstrate how to extend code shrinking to take dynamic behavior into account. Our technique, Slice Criteria Identification and REmoval (SCIRE), combines conditional compilation and code shrinking techniques with information provided by the developer about run-time behavior. This integration allows SCIRE to achieve code reduction that is close to optimal while remaining mostly automatic. Our results show that SCIRE reduces code size substantially: In many cases, removal of unused features shrinks middleware footprint to less than 5% of its original size, allowing CORBA and other large software libraries to be used in embedded systems. © 2007, IFIP International Federation for Information Processing. All rights reserved.

关键词： Embedded systems

来源：评论

学校读者我要写书评

暂无评论

Software documents: Comparison and measurement

Software documents: Comparison and measurement

引用

19th International Conference on Software engineering and Knowledge engineering, SEKE 2007

作者： Arbuckle, Tom Balaban, Adam Peters, Dennis K. Lawford, Mark Department of Computer Science and Information Systems CSIS Building University of Limerick Plassey Park Limerick Ireland Institute of Informatics Warsaw University Banacha 2 02-097 Warsaw Poland Electrical and Computer Engineering Faculty of Engineering and Applied Science Memorial University of Newfoundland St. John's NL A1B 3X5 Canada Department of Computing and Software Faculty of Engineering McMaster University Hamilton ON L8S 4K1 Canada

ISBN: (纸本)9781627486613

For some time now, researchers have been seeking to place software measurement on a more firmly grounded footing by establishing a theoretical basis for software comparison. Although there has been some work on trying to employ information theoretic concepts for the quantification of code documents, particularly on employing entropy and entropy-like measurements, we propose that employing the Similarity Metric of Li, Vit´anyi, and coworkers for the comparison of software documents will lead to the establishment of a theoretically justifiable means of comparing and evaluating software artifacts. In this paper, we review previous work on software measurement with a particular emphasis on information theoretic aspects, we examine the body of work on Kolmogorov complexity (upon which the Similarity Metric is based), and we report on some experiments that lend credence to our proposals. Finally, we discuss the potential advantages derived from the application of this theory to areas in the of software engineering. Copyright © (2007) by Knowledge Systems institute (KSI).

关键词： Entropy

来源：评论

学校读者我要写书评

暂无评论

Efficient Adaptations of the Non-Blocking Buffer for Event Message Communication between Real-Time Threads

Efficient Adaptations of the Non-Blocking Buffer for Event M...

引用

International Symposium on Object-Oriented Real-Time Distributed computing

作者： K.H. Kim Juan A. Colmenares Kee-Wook Rim Department of Electrical Engineering and Computer Science University of California Irvine USA Computing Institute Engineering Faculty University of Zulia Venezuela Division of Computer and Information Sciences Sunmoon University South Korea

Enabling message communication among concurrent computing threads without relying on mutual exclusion (i.e., locking) is highly desirable in real-time computing systems. This paper presents a refined version of the Non-Blocking Buffer (NBB), which is a lock-free interaction mechanism that enables efficient event-message communication between a single producer thread and a single consumer thread. The NBB scheme presented here contains improvements over the previous version in two aspects. First, application designers now have the flexibility of choosing the consumer's retry strategy for the case when the buffer is empty but the producer is in the middle of inserting an item. Second, in the refined version the producer inserts pointers to data items into the buffer whereas the consumer obtains copies of the items. This design is consistent with the fact that shared heap management must be avoided to enable fully lock-free interaction between the producer and the consumer. This paper also discusses the approaches based on the NBB mechanism for supporting all conceivable producer-consumer scenarios.

关键词： Yarn Real time systems Concurrent computing Timing Refining Middleware Distributed computing Operating systems Programming profession Design engineering

来源：评论

学校读者我要写书评

暂无评论

Context-based Arithmetic Coding Reexamined for DCT Video Compression

Context-based Arithmetic Coding Reexamined for DCT Video Com...

引用

IEEE International Symposium on Circuits and Systems (ISCAS)

作者： Li Zhang Xiaolin Wu Ning Zhang Wen Gao Qiang Wang Debin Zhao Chinese Academy of Sciences Institute for Computing Technology China Department of Electrical and Computer Engineering McMaster University Hamilton ONT Canada Chinese Academy of Sciences Institute for Computing Technology Harbin China Department of Computer Science and Technology Harbin Institute of Technology Harbin China

This paper presents a new context modeling technique for arithmetic coding of DCT coefficients in video compression. A key feature of the new technique is the inclusion of all previously coded coefficient magnitudes in a DCT block in context modeling. This enables adaptive arithmetic coding to exploit the redundancy of the high-order Markov process in the DCT domain with a few conditioning states. In addition, a context weighting technique is used to further improve the coding efficiency. The complexity of the new arithmetic coding scheme is slightly lower than that of context-based adaptive binary arithmetic coding (CABAC) of H.264. Moreover, the scheme is made compatible to the AVS baseline profile. It achieves on average 13% improvement in compression ratio over context-based two dimension variable length coding (C2DVLC) designed for the DCT domain, and a similar coding efficiency as the CABAC technique in H.264.

关键词： Discrete cosine transforms Video compression Entropy coding Context modeling Digital arithmetic Paper technology Statistics Switches Transform coding computers

来源：评论

学校读者我要写书评

暂无评论

A Distributed Connectivity Restoration Algorithm in Wireless Sensor and Actor Networks

A Distributed Connectivity Restoration Algorithm in Wireless...

引用

Conference on Local computer Networks (LCN)

作者： Ameer Ahmed Abbasi Kemal Akkaya Mohamed Younis Department of Computing Al-Hussan Institute of Management and Computer Science Dammam Saudi Arabia Department of Computer Science Southem Illinois University Carbondale IL USA Department of Computer Science & Electrical Engineering University of Maryland Baltimore County Baltimore MD USA

There has been an increased interest in applications of wireless sensor and actor networks (WSANs) in recent years. In such applications, a set of mobile actor nodes are deployed in addition to sensors in order to collect sensors' data and perform specific tasks in response to detected events/objects. In most scenarios actors have to respond collectively which requires an inter-actor coordination. Therefore, maintaining a connected inter-actor network is crucial to the effectiveness of WSANs. However, WSANs often operate unattended in harsh environments where actors can easily fail or get damaged. Due to such failures an actor will be unable to communicate with its neighbors which may lead to partitioning the inter-actor network. In this paper we present DARA; a Distributed Actor Recovery Algorithm, which opts to efficiently restore the connectivity of the inter-actor network that has been affected by the failure of an actor. The idea is to identify the least set of actors that should be repositioned in order to establish connectivity among disjoint network partitions. DARA strives to localize the scope of the recovery process and minimize the movement overhead imposed on the involved actors. The effectiveness of DARA is validated through simulation experiments.

关键词： Wireless sensor networks Event detection Fires computer networks computer science Application software Partitioning algorithms Optimized production technology Collaboration Distributed computing

来源：评论

学校读者我要写书评

暂无评论

ParalleX: A Study of A New Parallel Computation Model

ParalleX: A Study of A New Parallel Computation Model

引用

International Symposium on Parallel and Distributed Processing (IPDPS)

作者： Guang R. Gao Thomas Sterling Rick Stevens Mark Hereld Weirong Zhu Department of Electrical and Computer Engineering University of Delaware USA Center for Advanced Computing Research California Institute of Technology USA Department of Computer Science Louisiana State University USA Mathematics and Computer Science Division Argonne National Laboratory USA

This paper proposes the study of a new computation model that attempts to address the underlying sources of performance degradation (e.g. latency, overhead, and starvation) and the difficulties of programmer productivity (e.g. explicit locality management and scheduling, performance tuning, fragmented memory, and synchronous global barriers) to dramatically enhance the broad effectiveness of parallel processing for high end computing. In this paper, we present the progress of our research on a parallel programming and execution model - mainly, ParalleX. We describe the functional elements of ParalleX, one such model being explored as part of this project. We also report our progress on the development and study of a subset of ParalleX $the LITL-X at University of Delaware. We then present a novel architecture model - Gilgamesh II - as a ParalleX processing architecture. A design point study of Gilgamesh II and the architecture concept strategy are presented.

关键词： Concurrent computing Computational modeling High performance computing Degradation Delay Programming profession Productivity Processor scheduling Memory management Parallel processing

来源：评论

学校读者我要写书评

暂无评论

Routing and reliable transport layer protocols interactions in MANETs

Routing and reliable transport layer protocols interactions ...

引用

International Conference on computer engineering and Systems

作者： Hoda Hassan Mai El-Shehaly Ayman Abdel-Hamid Bradely Department of Electrical and Computer Engineering Virginia Polytechnic Institute and State University USA Department of Computer Science Virginia Polytechnic Institute and State University USA College of Computing and Information Technology Arab Academy for Science Technology and Maritime Transport Egypt

ISBN: (纸本)1424413656;9781424413652

Several research works have attempted to study the performance of TCP and SCTP in MANETS. In this paper we further aim to study the effects of these two transport layer protocols and that of the underlying routing protocols using a two-factor full factorial experimental design with replication through simulations. The routing protocols considered are AODV, DSR, and DSDV. Our motivation is that despite the efforts in comparing the different protocols at each layer separately, little is known about which layer has the greater effect on throughput in MANETS, and hence deserves further research, and how relevant the interaction between the layers is. We attempted to use mobility models to reflect realistic mobility scenarios. Our results show that the transport layer protocols have significant effect on throughput regardless of the routing layer protocol used: SCTP outperformed TCP in all cases.

关键词： Routing protocols Transport protocols Mobile ad hoc networks Throughput TCPIP Design for experiments computer science Educational institutions Information technology Network topology

来源：评论

学校读者我要写书评

暂无评论

External vibration compensation via loop shaping and H∞ feedforward control design for hard disk drives in mobile applications

External vibration compensation via loop shaping and H∞ fee...

引用

IEEE International Symposium on Intelligent Control (ISIC)

作者： Chunling Du Shuzhi Sam Ge F. L. Lewis Jingliang Zhang Data Storage Institute Agency for Science Technology and Research (ASTAR) Singapore Department of Electrical and Computer Engineering National University of Singapore Singapore Automation and Robotics Research Institute University of Technology Arlington TX USA Data Storage Institute Agency for Science Technology and Research Singapore

This paper focuses on compensation for external vibration effect on the positioning accuracy of hard disk drives. A feedforward controller is designed to attenuate the effect with the aid of a sensor to detect external vibrations. Loop shaping in frequency domain and H ∞ method in state space are used to design the feedforward controller. The application results in a 1.8-inch disk drive with an accelerometer to measure acceleration signal show that 70% and 97% reduction of the position error signal can be achieved with the feedforward control designed by the loop shaping and H ∞ method respectively. The robustness of the two methods is also evaluated and compared for external vibrations with amplitude variations.

关键词： Shape control Accelerometers Hard disks Vibration control Frequency domain analysis State-space methods Disk drives Position measurement Acceleration Error correction

来源：评论

学校读者我要写书评

暂无评论

Design Principles and Formulation for Optical SMART Networks

Design Principles and Formulation for Optical SMART Networks

引用

MILCOM, Military Communications Conference

作者： Tao Zhang Kejie Lu Gaoxi Xiao S.-Q. Zheng School of Engineering and Computing Sciences New York Institute of Technology Old Westbury NY USA Department of Electrical and Computer Engineering University of Puerto Rico Mayaguez Puerto Rico Network Technology Research Centre School of Electrical and Electronic Engineering Nanyang Technological University Singapore Department of Computer Science University of Texas Dallas Richardson TX USA

Optical SMART (Scalable Multi-Access Reconfigurable Transport) network [1] is an emerging optical networking paradigm that can effectively provide connectivity based on the hypergraph theory. Similar to a conventional graph, which consists of a set of edges, a hypergraph consists of a set of hyperedges (or hyperchannels), each of which can connect two or more nodes and can support communications amongst the nodes inside the hyperchannel. To enable hyperchannel in optical SMART networks, we have designed a hybrid node architecture in our previous study [1]. In this paper, we explore the network design principles and formulation for optical SMART networks. In particular, we formulate the static hyperchannel establishment problem as a Mixed Integer Linear Program (MILP), where the set of possible hyperchannels is given.

关键词： Optical design Optical fiber networks Optical packet switching High speed optical techniques Optical buffering Optical network units Scalability Telecommunication traffic Optical fiber communication Wavelength division multiplexing

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：