检索结果-内蒙古大学图书馆

22nd acm International symposium on High-Performance Parallel and distributed computing, HPDC 2013

作者： Wang, Bin Qi, Zhengwei Guan, Haibing Dong, Haoliang Sun, Wei Dong, Yaozu Shanghai Key Laboratory of Scalable Computing and Systems Shanghai Jiao Tong University Shanghai China School of Software Shanghai Jiao Tong University Shanghai China Intel China Software Center Shanghai China

ISBN: (纸本)9781450319102

Today's commercial cloud service providers require the availability with an annual uptime percentage at least 99.95%. While memory errors become norms instead of exceptions with the increasing memory's density and capacity in cloud applications. Thus, uncorrected errors from DRAM can be a significant source of system downtime. To address this increasingly important concern, both hardware and software memory mirroring technologies are studied nowadays to provide memory high availability. However, hardware solutions like mirror memory, which uses doubled chip, need dedicated and costly peripheral hardware. While existing software approaches, i.e., virtual machine's checkpoint technology, reduce the expense but incur the high overhead in practical usage. In this paper, we present a novel system called kMemvisor to provide system-wide high availability memory mirroring. It is a software approach achieving flexible multi-granularity memory mirroring via virtualization and binary translation technology. Specifically, kMemvisor first creates backup space of the same size of the specified memory for applications or virtual machines. We can flexibly set memory areas to be mirrored or not mirrored from application level to system-wide. Then, all memory write instructions in the native memory space are captured and instrumented by mirror memory write instructions to synchronize the data in backup space. Furthermore, this instruction level memory synchronization reduces backup overhead and lowers the probability of data loss compared with traditional software approaches. So kMemvisor could use data from the backup space to recover when memory failures happen. The results show that kMemvisor causes 55% overhead in the worst case of system-wide high availability and 30% average for the real world applications, which outperforms the state-of-the-art software approaches even in the worst case. © 2013 acm.

关键词： Virtual machine

来源：评论

学校读者我要写书评

暂无评论

COSMIC: Middleware for high performance and reliable multiprocessing on Xeon Phi coprocessors

COSMIC: Middleware for high performance and reliable multipr...

引用

22nd acm International symposium on High-Performance Parallel and distributed computing, HPDC 2013

作者： Cadambi, Srihari Coviello, Giuseppe Li, Cheng-Hong Phull, Rajat Rao, Kunal Sankaradass, Murugan Chakradhar, Srimat Computing Systems Architecture Department NEC Laboratories America Inc. Princeton NJ United States

ISBN: (纸本)9781450319102

It is remarkably easy to offload processing to Intel's newest manycore coprocessor, the Xeon-Phi: it supports a popular ISA (x86-based), a popular OS (Linux) and a popular programming model (OpenMP). Unfortunately, easy portability does not automatically ensure high performance. Additional programmer effort is necessary to leverage the new performance-oriented hardware features. But programmer optimizations alone are insufficient. Multiprocessing is also necessary to improve hardware utilization, and Linux makes it easy for processes to share the manycore coprocessor. However multiprocessing inefficiencies can easily offset gains made by the programmer. Our experiments on a production, high-performance Xeon server with multiple Xeon Phi coprocessors show that multiprocessing on coprocessors not only slows down the processes but also introduces unreliability (some processes crash unexpectedly). We propose a new, user-level middleware called COSMIC that improves performance and reliability of multiprocessing on coprocessors like the Xeon Phi. COSMIC seamlessly fits in the existing Xeon Phi software stack and is transparent to programmers. It manages Xeon Phi processes that execute parallel regions offloaded to the coprocessors. Offloads typically have programmer-driven performance directives like thread and affinity requirements. Unlike the existing Xeon Phi software stack, COSMIC does fair scheduling of both processes and offloads, and takes into account conflicting requirements of offloads belonging to different processes. By doing so, COSMIC has two clear benefits. First, it improves multiprocessing performance by preventing thread and memory oversubscription, by avoiding inter-offload interference and by reducing load imbalance on coprocessors and cores. Second, it increases multiprocessing reliability by exploiting programmer-specified per-process coprocessor memory requirements to completely avoid memory oversubscription and crashes. Our experiments on several r

关键词： Middleware

来源：评论

学校读者我要写书评

暂无评论

Extensible sparse functional arrays with circuit parallelism 13

Extensible sparse functional arrays with circuit parallelism

引用

15th symposium on principles and Practice of Declarative Programming, PPDP 2013

作者： O'Donnell, John T. School of Computing Science University of Glasgow United Kingdom

ISBN: (纸本)9781450321549

A longstanding open question in algorithms and data structures is the time and space complexity of pure functional arrays. Imperative arrays provide update and lookup operations that require constant time in the RAM theoretical model, but it is conjectured that there does not exist a RAM algorithm that achieves the same complexity for functional arrays, unless restrictions are placed on the operations. The main result of this paper is an algorithm that does achieve optimal unit time and space complexity for update and lookup on functional arrays. This algorithm does not run on a RAM, but instead it exploits the massive parallelism inherent in digital circuits. The algorithm also provides unit time operations that support storage management, as well as sparse and extensible arrays. The main idea behind the algorithm is to replace a RAM memory by a tree circuit that is more powerful than the RAM yet has the same asymptotic complexity in time (gate delays) and size (number of components). The algorithm uses an array representation that allows elements to be shared between many arrays with only a small constant factor penalty in space and time. This system exemplifies circuit parallelism, which exploits very large numbers of transistors per chip in order to speed up key algorithms. Extensible Sparse Functional Arrays (ESFA) can be used with both functional and imperative programming languages. The system comprises a set of algorithms and a circuit specification, and it has been implemented on a GPGPU with good performance. © 2013 acm.

关键词： Timing circuits

来源：评论

学校读者我要写书评

暂无评论

distributed Greedy approximation to Maximum Weighted Independent Set for scheduling with fading channels 13

Distributed Greedy approximation to Maximum Weighted Indepen...

引用

14th acm International symposium on Mobile Ad Hoc Networking and computing, MobiHoc 2013

作者： Joo, Changhee Lin, Xiaojun Ryu, Jiho Shroff, Ness B. ECE UNIST UNIST-gil 50 Ulsan Korea Republic of ECE Purdue University 465 Northwestern Ave. West Lafayette IN 47907 United States ECE and CSE OSU 2015 Neil Ave. Columbus OH 43210 United States

ISBN: (纸本)9781450321938

Developing scheduling mechanisms that can simultaneously achieve throughput optimality and good delay performance often require solving the Maximum Independent Weighted Set (MWIS) problem. However, under most realistic network settings, the MWIS problem can be shown to be NPhard. In non-fading environments, low-complexity scheduling algorithms have been provided that converge either to the MWIS solution in time or to a solution that achieves at least a provable fraction of the achievable throughput. However, in more practical systems the channel conditions can vary at faster time-scales than convergence occurs in these lower-complexity algorithms. Hence, these algorithms cannot take advantage of the opportunistic gain, and may no longer guarantee good performance. In this paper, we propose a low-complexity scheduling scheme that performs provably well under fading channels and is amenable to implement in a distributed manner. To the best of our knowledge, this is the first scheduling scheme under fading environments that requires only local information, has a low complexity that grows logarithmically with the network size, and achieves provable performance guarantees (which is arbitrarily close to that of the well-known centralized Greedy Maximal Scheduler). Through simulations we verify that both the throughput and the delay under our proposed distributed scheduling scheme are close to that of the optimal solution to MWIS. Further, we implement a preliminary version of our algorithm in a testbed by modifying the existing IEEE 802.11 DCF. The preliminary experiment results show that our implementation successfully accounts for wireless fading, and attains the opportunistic gains in practice, and hence substantially outperforms IEEE 802.11 DCF. Copyright 2013 acm.

关键词： Fading channels

来源：评论

学校读者我要写书评

暂无评论

distributed deterministic edge coloring using bounded neighborhood independence

引用

distributed computing 2013年第5-6期26卷 273-287页

作者： Barenboim, Leonid Elkin, Michael Ben Gurion Univ Negev Dept Comp Sci IL-84105 Beer Sheva Israel

We study the edge-coloring problem in the message-passing model of distributed computing. This is one of the most fundamental problems in this area. Currently, the best-known deterministic algorithms for (2 Delta -1)-edge-coloring requires O(Delta) + log* n time (Panconesi and Rizzi in Distrib Comput 14(2):97-100, 2001), where Delta is the maximum degree of the input graph. Also, recent results of Barenboim and Elkin (2010) for vertex-coloring imply that one can get an O(Delta)-edge-coloring in time, and an -edge-coloring in O(log Delta log n) time, for an arbitrarily small constant . In this paper we devise a significantly faster deterministic edge-coloring algorithm. Specifically, our algorithm computes an O(Delta)-edge-coloring in time, and an -edge-coloring in O(log Delta) + log* n time. This result improves the state-of-the-art running time for deterministic edge-coloring with this number of colors in almost the entire range of maximum degree Delta. Moreover, it improves it exponentially in a wide range of Delta, specifically, for 2 (Omega(log*n)) a parts per thousand currency sign Delta a parts per thousand currency sign polylog(n). In addition, for small values of Delta (up to log(1 - delta) n, for some fixed delta > 0) our deterministic algorithm outperforms all the existing randomized algorithms for this problem. Also, our algorithm is the first O(Delta)-edge-coloring algorithm that has running time o(Delta) + log* n, for the entire range of Delta. All previous (deterministic and randomized) O(Delta)-edge-coloring algorithms require time. On our way to these results we study the vertex-coloring problem on graphs with bounded neighborhood independence. This is a large family of graphs, which strictly includes line graphs of r-hypergraphs (i.e., hypergraphs in which each hyperedge contains r or less vertices) for r = O(1), and graphs of bounded growth. We devise a very fast deterministic algorithm for vertex-coloring graphs with bounded neighborhood independe

关键词： Defective-coloring Legal-coloring Line-graphs

来源：评论

学校读者我要写书评

暂无评论

proceedings of the 4th symposium on Information and Communication Technology, SoICT 2013

Proceedings of the 4th Symposium on Information and Communic...

引用

4th symposium on Information and Communication Technology, SoICT 2013

ISBN: (纸本)9781450324540

The proceedings contain 42 papers. The topics discussed include: in situ spatial AR surgical planning using projector-kinect system;on approaching 2D-FPCA technique to improve image representation in frequency domain;state-space modeling based on principal component analysis and oxygenated-deoxygenated correlation to improve near-infrared spectroscopy signals;restoring surfaces after removing objects in indoor 3D point clouds;violent scene detection using mid-level feature;principal direction analysis-based real-time 3D human pose reconstruction from a single depth image;a method for hand detection using internal features and active boosting-based learning;P2P shared-caching model: using P2P to improve client-server application performance;mobile peer-to-peer approach for social computing services in distributed environment;applying time series analysis and neighborhood voting in a decentralized approach for fault detection and classification in WSNs;and correlation-based clustering in wireless sensor network for energy saving protocol.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A distributed Delaunay triangulation algorithm based on centroidal Voronoi tessellation for wireless sensor networks 13

A distributed Delaunay triangulation algorithm based on cent...

引用

14th acm International symposium on Mobile Ad Hoc Networking and computing, MobiHoc 2013

作者： Zhou, Hongyu Jin, Miao Wu, Hongyi University of Louisiana at Lafayette Lafayette LA 70503 United States

ISBN: (纸本)9781450321938

A wireless sensor network can be represented by a graph. While the network graph is extremely useful, it often exhibits undesired irregularity. Therefore, special treatment of the graph is required by a variety of network algorithms and protocols. In particular, many geometry-oriented algorithms depend on a type of subgraph called Delaunay triangulation. However, when location information is unavailable, it is nontrivial to achieve Delaunay triangulation by using connectivity information only. The only connectivitybased algorithm available for Delaunay triangulation is built upon the property that the dual graph for a Voronoi diagram is a Delaunay triangulation. This approach, however, often fails in practical wireless sensor networks because the boundaries of Voronoi cells can be arbitrarily short in discrete sensor network settings. In a sensor network with connectivity information only, it is fundamentally unattainable to correctly judge neighboring cells when a Voronoi cell boundary is less than one hop. Consequently, the Voronoi diagram-based Delaunay triangulation fails. The proposed algorithm employs a distributed approach to perform centroidal Voronoi tessellation, and constructs its dual graph to yield Delaunay triangulation. It exhibits several distinctive properties. First, it eliminates the problem due to short cell boundaries and thus effectively avoids crossing edges. Second, the proposed algorithm is proven to converge and succeed in constructing a Delaunay triangulation, if the CVT cell size is greater than a constant threshold. Third, the established Delaunay triangulation consists of close-to-equilateral triangles, benefiting a range of applications such as geometric routing, localization, coverage, segmentation, and data storage and processing. Extensive simulations are carried out under various 2D network models to evaluate the effectiveness and efficiency of the proposed CVT-based triangulation algorithm. Copyright 2013 acm.

关键词： Computational geometry

来源：评论

学校读者我要写书评

暂无评论

Special session: Engaging mathematical reasoning exercises

Special session: Engaging mathematical reasoning exercises

引用

44th acm Technical symposium on Computer Science Education, SIGCSE 2013

作者： Hollingsworth, Joseph Krone, Joan Weide, Bruce Hallstrom, Jason O. Sitaraman, Murali Indiana University Southeast Computer Science New Albany IN 47150 United States Denison University Mathematics and Computer Science Granville OH United States Ohio State University Computer Science and Engineering Columbus OH 43210 United States Clemson University School of Computing Clemson SC 29634 United States

ISBN: (纸本)9781450320306

SIGCSE has for a long time nourished an audience excited about teaching mathematical reasoning principles across the curriculum. A math thinking-related Birds-of-a-Feather (BoF) session is perhaps the longest running such session at SIGCSE, and every year it has attracted 30 or so participants. Every two or three years, there has been a panel devoted to related topics;recent examples include [1,3,4] with the 2012 SIGCSE panel attracting well over 100 attendees. The "Math Thinking" group started in 1999 by Doug Baldwin and Peter Henderson still remains a source for ongoing discussion among regular SIGCSE participants through a mailing list [5] several years after its founding. While these other forums are useful for discussing reasoning topics, they do not provide a consistent venue for sharing math reasoning activities. Therefore, SIGCSE attendees interested in math thinking have routinely wished for a place where engaging math reasoning examples and assignments that help connect mathematics and software development can be shared and discussed. Providing such a forum is the purpose of this session. The exercises and assignments will help faculty find ways to incorporate mathematical reasoning in CS1, CS2, data structures and algorithms, discrete math, and software engineering courses. Copyright © 2013 acm.

关键词： Software design

来源：评论

学校读者我要写书评

暂无评论

Dual-mode optimum distance routing scheme for vehicular ad hoc networks

Dual-mode optimum distance routing scheme for vehicular ad h...

引用

3rd acm Int. Symp. on Design and Analysis of Intelligent Vehicular Networks and Applications, DIVANet 2013, Held in Conjunction with the 16th acm Int. Conf. on Modeling, Analysis and Simulation of Wireless and Mobile Systems, MSWiM 2013

作者： Matar, Yaser K. Villas, Leandro A. Pazzi, Richard W. Faculty of Business and Information Technology University of Ontario Institute of Technology Oshawa ON Canada LRC - Computer Networks Laboratory Institute of Computing University of Campinas Campinas Brazil

ISBN: (纸本)9781450323581

Vehicular Ad hoc Networks (VANETs) are an emerging technology that allows vehicles to form self-organized networks without the need of permanent infrastructure. Communications in VANETs require the establishment of efficient routes between communicating vehicles. An efficient VANET routing protocol must be able to adapt to the frequent topology changes induced by high mobility. Most of the geographic-based VANET protocols rely on beacons for collecting neighbor nodes' information and to make position-based routing decisions. However, using beacons in routing decisions can cause performance deficiencies due to stale link-state information. In this paper, we present an efficient contention-based geographic routing protocol for VANETs, called Dual-Mode Optimum Distance (DMOD) routing protocol. DMOD is proposed to serve unicast messaging applications. The neighbor selection in DMOD is done opportunistically in collaboration with the neighbors depending on their distances from the destination. DMOD uses two distance computing modes in creating routing decision;greedy distance and driving distance. Forwarding decisions are built upon distributed contention process depending on the driving distances of the neighbors to the destination. If the driving distance method fails, greedy forwarding is used to explore further neighbors with better progress. Simulation results show that DMOD outperforms existing position-based approaches over a variety of network densities. DMOD can also improve packet delivery success ratio and reduce network overhead significantly. © 2013 acm.

关键词： Vehicular ad hoc networks

来源：评论

学校读者我要写书评

暂无评论

Cut-and-sew: A distributed autonomous localization algorithm for 3D surface wireless sensor networks 13

Cut-and-sew: A distributed autonomous localization algorithm...

引用

14th acm International symposium on Mobile Ad Hoc Networking and computing, MobiHoc 2013

作者： Zhao, Yao Wu, Hongyi Jin, Miao Yang, Yang Zhou, Hongyu Xia, Su Center for Advanced Computer Studies University of Louisiana at Lafayette Lafayette United States

ISBN: (纸本)9781450321938

Location awareness is imperative for a variety of sensing applications and network operations. Although a diversity of GPS-less and GPS-free solutions have been developed recently for autonomous localization in wireless sensor networks, they primarily target at 2D planar or 3D volumetric settings. There exists unique and fundamental hardness to extend them to 3D surface. The contributions of this work are twofold. First, it proposes a theoretically-proven algorithm for the 3D surface localization problem. Seeing the chal-lenges to localize general 3D surface networks and the solvability of the localization problem on single-value (SV) surface, this work proposes the cut-and-sew algorithm that takes a divide-and-conquer approach by partitioning a general 3D surface network into SV patches, which are localized individually and then merged into a unified coordinates system. The algorithm is optimized by discovering the minimum SV partition, an optimal partition that creates a minimum set of SV patches. Second, it develops practically-viable solutions for real-world sensor network settings where the inputs are often noisy. The proposed algorithm is implemented and evaluated via simulations and experiments in an indoor testbed. The results demonstrate that the proposed cut-and-sew algorithm achieves perfect 100% localization rate and the desired robustness against measurement errors. Copyright 2013 acm.

关键词： Wireless sensor networks

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：