检索结果-内蒙古大学图书馆

IEEE Pacific Rim Conference on Communications, Computers and Signal Processing (PACRIM)

作者： Wada, Koichi Kawaguchi, Shinsuke Ono, Masaaki Yonezawa, Naoki Univ Tsukuba Dept Comp Sci 1-1-1 Tennodai Tsukuba Ibaraki 3058573 Japan Kanagawa Univ Dept Informat & Comp Sci Kanagawa Japan

ISBN: (纸本)9781457702518

distributed shared memory (DSM) is an important technology that provides programmers the underlying execution mechanism for shared memory programs. To improve the performance of DSM, recent studies have been carried out with introducing compiler assistance. The compiler generates codes for dependency analysis and communication. This paper proposes high-performance DSM, called Offloaded-DSM, in which the processes of dependency analysis and communication are offloaded to the cluster network. In Offloaded-DSM, the host machine can concentrate on computation of an application itself, while the network maintains coherency in parallel. Through the results of preliminary evaluation, Offloaded-DSM reduces execution time up to 32% in eight nodes and exhibits good scalability.

关键词： Arrays Field programmable gate arrays Libraries Nickel Runtime library Switches Synchronization cluster network offloading compiler assistance compiler code generation compiler generators dependency analysis distributed shared memory distributed shared me

来源：评论

学校读者我要写书评

暂无评论

distributed Parallel Super-Block-Based Star Detection and Centroid Calculation

引用

IEEE SENSORS JOURNAL 2018年第19期18卷 8096-8107页

作者： Wang, Zhen Jiang, Jie Zhang, Guangjun Beijing Univ Aeronaut & Astronaut Sch Instrumentat Sci & Optoelect Engn Minist Educ Key Lab Precis Optomechatron Technol Beijing 100191 Peoples R China

Due to the inadequacies of the speed of star detection and centroid calculation (SDCC), the applications of high-resolution and high-frame-rate image sensors are greatly limited in star trackers, restricting the performance of the star trackers. To resolve this problem, a novel distributed parallel super-block-based SDCC method is proposed in this paper. In contrast to the previous SDCC methods, the proposed method divides the star images into several sub-images and processes these sub-images in parallel. Then, by using a super-block-based method and a distributed shared memory-based method to process the stars in sub-images (sub-stars) and in adjacent sub-images (boundary stars), respectively, the position information of all the stars are detected during the parallel scan of the sub-images. The proposed method exhibits a speed that is up to 4 x M times faster than the previous SDCC methods in processing the star images that are divided into M sub-images. Experimental results demonstrate that the proposed method is correct and effective. It is applicable to the use of most high-performance image sensors and resolves the performance limitation of star trackers to achieve better attitude accuracy and attitude update rate.

关键词： distributed parallel star detection centroid location star tracker distributed shared memory image sensors application

来源：评论

学校读者我要写书评

暂无评论

A general-purpose distributed computing Java middleware

引用

CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE 2019年第7期31卷 e4967-e4967页

作者： Barroso Almeida, Andre Luis Cimino, Leonardo de Souza Eugenio de Resende, Jose Estevao Moreira Silva, Lucas Henrique Souza Rocha, Samuel Queiroz Gregorio, Guilherme Aparecido Paiva, Gustavo Silva Delabrida, Saul Santos, Haroldo Gambini Moreira de Carvalho, Marco Antonio Lins Aquino, Andre Luiz Lima, Joubert de Castro Univ Fed Ouro Preto DECOM Ouro Preto Brazil Inst Fed Minas Gerais Control & Automat Dept CODAAUT Ouro Preto Brazil Univ Fed Alagoas IC Maceio Brazil

The middleware solutions for General-Purpose distributed Computing (GPDC) have distinct requirements, such as task scheduling, processing/storage fault tolerance, code portability for parallel or distributed environments, simple deployment (including over grid or multi-cluster environments), collaborative development, low code refactoring, native support for distributed data structures, asynchronous task execution, and support for distributed global variables. These solutions do not integrate these requirements into a single deployment with a unique API exposing most of these requirements to users. The consequence is the utilization of several solutions with their particularities, thus requiring different user skills. Besides that, the users have to solve the integration and all heterogeneity issues. To reduce this integration gap, in this paper, we present Java Ca&La (JCL), a distributed-shared-memory and task-oriented lightweight middleware for the Java community that separates business logic from distribution issues during the development process and incorporates several requirements that were presented separately in the GPDC middleware literature over the last few decades. JCL allows building distributed or parallel applications with only a few portable API calls, thus reducing the integration problems. Finally, it also runs on different platforms, including small single-board computers. This work compares and contrasts JCL with other Java middleware systems and reports experimental evaluations of JCL applications in several distinct scenarios.

关键词： distributed computing distributed shared memory Java middleware parallel computing task-oriented

来源：评论

学校读者我要写书评

暂无评论

Scalable embedded computing through reconfigurable hardware: Comparing DF-Threads, cilk, openmpi and jump

引用

MICROPROCESSORS AND MICROSYSTEMS 2018年第Nov.期63卷 66-74页

作者： Giorgi, Roberto Univ Siena Dipartimento Ingn Informaz & Sci Matemat Siena Italy

Data-Flow Threads (DF-Threads) is a new execution model that permits to seamlessly distribute the workload across several cores (in a multi-core) and several nodes (in a multi-node/multi-board configuration). In this paper, the advance in deploying this execution model is shown while developing it by using a combination of a simulator model (i.e., the COTSon framework) and a reconfigurable hardware platform (i.e., the AXIOM-board). The AXIOM platform consists of a custom board based on the Xilinx Zynq Ultrascale+ ZU9EG, which incorporates the largest FPGA available on that System-on-Chip at the moment, four 64-bit ARM cores and two 32-bit ARM cores, up to 32GiB of main memory and several 16Gbit/s transceivers. While a complete DF-Threads system is still under development, but is already capable of running a full Linux OS and simple applications, so some initial results are presented here. In particular, well-known programming models that are used to exploit the Thread-Level Parallelism such as Cilk, OpenMPI and Jump are compared with DF-thread execution. Cilk is good for multi-cores, but it is not suitable for multi-nodes systems. In the latter cases, the distribution of the workload could be managed partly by the programmer when using programming models such as message-passing (OpenMPI has been chosen for reference) or distributed shared-memory (Jump in our case). The obtained results show that a DF-Thread execution on a cluster of eight 4-core boards can provide a speed-up of more than 14x compared to the same configuration when using OpenMPI and more than 80x when compared with a OpenMPI single core, single node execution.

关键词： Cyber-physical systems Reconfigurable systems FPGA Programming distributed shared memory Programming model Performance evaluation memory model

来源：评论

学校读者我要写书评

暂无评论

Value the Recent Past: Approximate Causal Consistency for Partially Replicated Systems

引用

IEEE TRANSACTIONS ON PARALLEL AND distributed SYSTEMS 2018年第1期29卷 212-225页

作者： Hsu, Ta-Yuan Kshemkalyani, Ajay D. Univ Illinois Dept Elect & Comp Engn Chicago IL 60607 USA Univ Illinois Dept Comp Sci Chicago IL 60607 USA

In wide-area distributed systems, data replication provides fault tolerance and low latency. Causal consistency in such systems is an interesting consistency model. Most existing works assume the data is fully replicated because this greatly simplifies the design of the algorithms to implement causal consistency. Recently, we proposed causal consistency under partial replication because it reduces the number of messages used under a wide range of workloads. One drawback of partial replication is that its meta-data tends to be relatively large when the message size is small. In this paper, we propose an algorithm Approx-Opt-Track which provides approximate causal consistency whereby we can reduce the meta-data at the cost of some violations of causal consistency. The amount of violations can be made arbitrarily small by controlling a tunable parameter, that we call credits. We present the analytic data to show the performance of Approx-Opt-Track. We then give simulation results to show the potential benefit of Approx-Opt-Track, viz., its ability to provide almost the same guarantees as causal consistency, at a smaller cost.

关键词： Causal consistency causality distributed shared memory partial replication

来源：评论

学校读者我要写书评

暂无评论

A Protocol of Mutual Exclusion for DSM Based on Vectors of Global Timestamps

引用

FUNDAMENTA INFORMATICAE 2018年第4期157卷 359-370页

作者： Czaja, Ludwik Vistula Univ Warsaw Poland Univ Warsaw Inst Informat Warsaw Poland

A new protocol using vectors of global timestamps for mutual exclusion in systems with distributed shared memory (DSM) is described and some of its properties are proved.

关键词： Cloning Vectors Diagnostic and Statistical Manual mutual exclusion distributed shared memory

来源：评论

学校读者我要写书评

暂无评论

Data race avoidance and replay scheme for developing and debugging parallel programs on distributed shared memory systems

引用

PARALLEL COMPUTING 2011年第1期37卷 11-25页

作者： Chiu, Yung-Chang Shieh, Ce-Kuen Huang, Tzu-Chi Liang, Tyng-Yeu Chu, Kuo-Chih Lunghwa Univ Sci & Technol Dept Elect Engn Tao Yuan 33306 Taiwan Natl Cheng Kung Univ Dept Elect Engn Tainan 701 Taiwan Natl Kaohsiung Univ Appl Sci Dept Elect Engn Kaohsiung 80778 Taiwan

distributed shared memory (DSM) allows parallel programs to run on distributed computers by simulating a global virtual shared memory, but data racing bugs may easily occur when the threads of a multi-threaded process concurrently access the physically distributed memory. Earlier tools to help programmers locate data racing bugs in non-DSM parallel programs are not easily applied to DSM systems. This study presents the data race avoidance and replay scheme (DRARS) to assist debugging parallel programs on DSM or multi-core systems. DRARS is a novel tool which controls the consistency protocol of the target program, automatically preventing a large class of data racing bugs when the parallel program is subsequently run, obviating much of the need for manual debugging. For data racing bugs that cannot be avoided automatically, DRARS performs a deterministic replay-type function on DSM systems, faithfully reproducing the behavior of the parallel program during run time. Because one class of data racing bugs has already been eliminated, the remaining manual debugging task is greatly simplified. Unlike previous debugging methods, DRARS does not require that the parallel program be written in a specific style or programming language. Moreover. DRARS can be implemented in most consistency protocols. In this paper, DRARS is realized and verified in real experiments using the eager release consistency protocol on a DSM system with various applications. (C) 2010 Elsevier B.V. All rights reserved.

关键词： Parallel program distributed shared memory DSM Debugger Data race Access conflict Deterministic replay

来源：评论

学校读者我要写书评

暂无评论

Brief Announcement: Partially Replicated Causally Consistent shared memory 18

Brief Announcement: Partially Replicated Causally Consistent...

引用

37th ACM SIGACT-SIGOPS Symposium on Principles of distributed Computing (PODC)

作者： Xiang, Zhuolun Vaidya, Nitin H. Univ Illinois Urbana IL 61801 USA

ISBN: (纸本)9781450357951

distributed shared memory systems maintain multiple replicas of the shared memory registers. Maintaining causal consistency in such systems has received significant attention in the past. However, much of the previous literature focuses on full replication wherein each replica stores a copy of all the registers in the shared memory. In this paper, we investigate causal consistency in partially replicated systems, wherein each replica may store only a subset of the shared data. To achieve causal consistency, it is necessary to ensure that, before an update is performed at any given replica, all causally preceding updates must also be performed. Achieving this goal requires some mechanism to track causal dependencies. In the context of full replication, this goal is often achieved using vector timestamps, with the number of vector elements being equal to the number of replicas. Building on the past work, this paper makes two key contributions: For a family of algorithms for maintaining causal consistency, we present necessary conditions on the metadata (which we refer as a timestamp) that must be maintained by each replica. We present an algorithm for achieving causal consistency using a timestamp that matches one of the necessary conditions referred above, thus showing that the condition is necessary and sufficient both.

关键词： distributed shared memory causal consistency partial replication timestamps lower bounds

来源：评论

学校读者我要写书评

暂无评论

CaCAO: Complex and Compositional Atomic Operations for NoC-Based Manycore Platforms 31st

CaCAO: Complex and Compositional Atomic Operations for NoC-B...

引用

31st International Conference on Computer Architecture (ARCS)

作者： Rheindt, Sven Schenk, Andreas Srivatsa, Akshay Wild, Thomas Herkersdorf, Andreas Tech Univ Munich Chair Integrated Syst Munich Germany

ISBN: (纸本)9783319776101;9783319776095

Tile-based distributed memory systems have increased the scalability of manycore platforms. However, inter-tile memory accesses, especially thread synchronization suffer from high remote access latencies. Our thorough investigations of lock-based and lock-free synchronization primitives show that there is a concurrency dependent crossover point between them, i.e. there is no one-fits-all solution. Therefore, we propose to combine the conceptual advantages (no retries and lock-free) of both variants by using dedicated hardware support for inter-tile atomic operations. For frequently used and highly concurrent data structures, we show a speedup factor of 23.9 and 35.4 over the lock-based and lock-free implementations respectively, which increases with higher concurrency.

关键词： Atomic operations Remote synchronization Compare-and-swap distributed shared memory Network-on-Chip

来源：评论

学校读者我要写书评

暂无评论

A distributed hypervisor for resource aggregation: poster 19

A distributed hypervisor for resource aggregation: poster

引用

Proceedings of the 24th Symposium on Principles and Practice of Parallel Programming

作者： Yubin Chen Zhuocheng Ding Jin Zhang Yun Wang Zhengwei Qi Haibing Guan Shanghai Jiao Tong University

ISBN: (纸本)9781450362252

Scale-out has become the standard answer to data analysis, machine learning and many other fields. Contrary to common belief, scale-up machines can outperform scale-out clusters for a considerable portion of tasks. However, those scale-up machines are not economical and may not be affordable for small businesses. This paper presents GiantVM, a distributed hypervisor that aggregates resources from multiple physical machines, providing the guest OS with a uniform hardware abstraction. We propose techniques to deal with the challenges of CPU, memory, and I/O virtualization in distributed environments.

关键词： distributed shared memory

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：