检索结果-内蒙古大学图书馆

FDGLib: A Communication Library for Efficient Large-Scale Graph Processing in FPGA-Accelerated Data Centers

Journal of Computer Science & technology 2021年第5期36卷 1051-1070页

作者： Yu-Wei Wu Qing-Gang Wang Long Zheng Xiao-Fei Liao Hai Jin Wen-Bin Jiang Ran Zheng Kan Hu National Engineering Research Center for Big Data Technology and System School of Computer Science and Technology Huazhong University of Science and TechnologyWuhan 430074China Services Computing Technology and System Laboratory School of Computer Science and Technology Huazhong University of Science and TechnologyWuhan 430074China Cluster and Grid Computing Laboratory School of Computer Science and TechnologyHuazhong University of Science and TechnologyWuhan 430074China

With the rapid growth of real-world graphs,the size of which can easily exceed the on-chip(board)storage capacity of an accelerator,processing large-scale graphs on a single Field Programmable Gate Array(FPGA)becomes *** multi-FPGA acceleration is of great necessity and *** cloud providers(e.g.,Amazon,Microsoft,and Baidu)now expose FPGAs to users in their data centers,providing opportunities to accelerate large-scale graph *** this paper,we present a communication library,called FDGLib,which can easily scale out any existing single FPGA-based graph accelerator to a distributed version in a data center,with minimal hardware engineering *** provides six APIs that can be easily used and integrated into any FPGA-based graph accelerator with only a few lines of code *** the torus-based FPGA interconnection in data centers,FDGLib also improves communication efficiency using simple yet effective torus-friendly graph partition and placement *** interface FDGLib into AccuGraph,a state-of-the-art graph *** results on a 32-node Microsoft Catapult-like data center show that the distributed AccuGraph can be 2.32x and 4.77x faster than a state-of-the-art distributed FPGA-based graph accelerator ForeGraph and a distributed CPU-based graph system Gemini,with better scalability.

关键词： data center accelerator graph processing distributed architecture communication optimization

来源：评论

学校读者我要写书评

暂无评论

A Survey on Graph Processing Accelerators:Challenges and Opportunities

引用

Journal of Computer Science & technology 2019年第2期34卷 339-371页

作者： Chuang-Yi Gui Long Zheng Bingsheng He Cheng Liu Xin-Yu Chen Xiao-Fei Liao Hai Jin National Engineering Research Center for Big Data Technology and System School of Computer Science and Technology Huazhong University of Science and Technology Wuhan 430074 China Services Computing Technology and System Laboratory School of Computer Science and Technology Huazhong University of Science and Technology Wuhan 430074 China Cluster and Grid Computing Laboratory School of Computer Science and Technology Huazhong University of Science and Technology Wuhan 430074 China School of Computing National University of Singapore Singapore 117418 Singapore Institute of Computing Technology Chinese Academy of Sciences Beijing 100190 China

Graph is a well known data structure to represent the associated relationships in a variety of applications,e.g.,data science and machine *** a wealth of existing efforts on developing graph processing systems for improving the performance and/or energy efficiency on traditional architectures,dedicated hardware solutions,also referred to as graph processing accelerators,are essential and emerging to provide the benefits significantly beyond what those pure software solutions can *** this paper,we conduct a systematical survey regarding the design and implementation of graph processing ***,we review the relevant techniques in three core components toward a graph processing accelerator:preprocessing,parallel graph computation,and runtime *** also examine the benchmarks and results in existing studies for evaluating a graph processing ***,we find that there is not an absolute winner for all three aspects in graph acceleration due to the diverse characteristics of graph processing and the complexity of hardware *** finally present and discuss several challenges in details,and further explore the opportunities for the future research.

关键词： graph processing accelerator domain-specific architecture performance energy efficiency

来源：评论

学校读者我要写书评

暂无评论

Towards High-Performance Graph Processing: From a Hardware/Software Co-Design Perspective

引用

Journal of Computer Science & technology 2024年第2期39卷 245-266页

作者：廖小飞赵文举金海姚鹏程黄禹王庆刚赵进郑龙张宇邵志远 National Engineering Research Center for Big Data Technology and System School of Computer Science and Technology Huazhong University of Science and TechnologyWuhan 430074China Services Computing Technology and System Laboratory School of Computer Science and Technology Huazhong University of Science and TechnologyWuhan 430074China Cluster and Grid Computing Laboratory School of Computer Science and TechnologyHuazhong University of Science and TechnologyWuhan 430074China Zhejiang Lab Hangzhou 311121China

Graph processing has been widely used in many scenarios,from scientific computing to artificial *** processing exhibits irregular computational parallelism and random memory accesses,unlike traditional ***,running graph processing workloads on conventional architectures(e.g.,CPUs and GPUs)often shows a significantly low compute-memory ratio with few performance benefits,which can be,in many cases,even slower than a specialized single-thread graph *** domain-specific hardware designs are essential for graph processing,it is still challenging to transform the hardware capability to performance boost without coupled software *** article presents a graph processing ecosystem from hardware to *** start by introducing a series of hardware accelerators as the foundation of this ***,the codesigned parallel graph systems and their distributed techniques are presented to support graph ***,we introduce our efforts on novel graph applications and hardware *** results show that various graph applications can be efficiently accelerated in this graph processing ecosystem.

关键词： graph processing hardware accelerator software system high performance ecosystem

来源：评论

学校读者我要写书评

暂无评论

HCOpt: An automatic optimizer for configuration parameters of Hadoop 2nd

HCOpt: An automatic optimizer for configuration parameters o...

引用

2nd International Conference on Human Centered computing, HCC 2016

作者： Zhang, Xiong Zeng, Linxi Shi, Xuanhua Wu, Song Xie, Xia Jin, Hai Services Computing Technology and System Laboratory Big Data Technology and System Laboratory Cluster and Grid Computing Laboratory School of Computer Science and Technology Huazhong University of Science and Technology Wuhan430074 China

ISBN: (纸本)9783319318530

MapReduce is an efficient tool for data-intensive applications. Hadoop, an open-source implementation of MapReduce, has been widely adopted and experienced by some enterprises and scientific computing communities. However, when users intend to run a MapReduce program in Hadoop, they have to set a number of configuration parameters to make sure the program runs efficiently. Users often run into performance problems because they are unaware of how to set these parameters. To address these performance problems, we focus on the optimization opportunities presented by the high configurability of Hadoop, and propose an automation tool named HCOpt for performance optimization of Hadoop configuration parameters. HCOpt uses a Profile Engine to collect monitoring information from running MapReduce programs, a Prediction Engine to estimate the performance of a given Hadoop configuration and a genetic-based search algorithm to find an optimized configuration in the large search space. Our evaluation shows that HCOpt reduces the job completion time of Hadoop applications by up to 20 % when compared to applications run with configuration parameters that suggested by the rule-based optimization. © Springer International Publishing Switzerland 2016.

关键词： MapReduce

来源：评论

学校读者我要写书评

暂无评论

Massively parallel algorithms for fully dynamic all-pairs shortest paths

引用

Frontiers of Computer Science 2024年第4期18卷 201-203页

作者： Chilei WANG Qiang-Sheng HUA Hai JIN Chaodong ZHENG National Engineering Research Center for Big Data Technology and System Services Computing Technology and System LabCluster and Grid Computing LabSchool of Computer Science and TechnologyHuazhong University of Science and TechnologyWuhan 430074China State Key Laboratory for Novel Software Technology Nanjing UniversityNanjing 210023China

1 Introduction In recent years,the Massively Parallel Computation(MPC)model has gained significant ***,most of distributed and parallel graph algorithms in the MPC model are designed for static graphs[1].In fact,the graphs in the real world are constantly *** size of the real-time changes in these graphs is smaller and more *** graph algorithms[2,3]can deal with graph changes more efficiently[4]than the corresponding static graph ***,most studies on dynamic graph algorithms are limited to the single machine ***,a few parallel dynamic graph algorithms(such as the graph connectivity)in the MPC model[5]have been proposed and shown superiority over their parallel static counterparts.

关键词： dynamic shortest gained

来源：评论

学校读者我要写书评

暂无评论

Improving the memory efficiency of in-memory mapreduce based HPC systems 1

引用

15th International Conference on Algorithms and Architectures for Parallel Processing, ICA3PP 2015

作者： Pei, Cheng Shi, Xuanhua Jin, Hai Services Computing Technology and System Laboratory Cluster and Grid Computing Laboratory School of Computer Science and Technology Huazhong University of Science and Technology Wuhan430074 China

ISBN: (数字)9783319271194

ISBN: (纸本)9783319271187

In-memory cluster computing systems based MapReduce, such as Spark, have made a great impact in addressing all kinds of big data problems. Given the overuse of memory speed, which stems from avoiding the latency caused by disk I/O operations, some process designs may cause resource inefficiency in traditional high performance computing (HPC) systems. Hash-based shuffle, particularly large-scale shuffle, can significantly affect job performance through excessive file operations and unreasonable use of memory. Some intermediate data unnecessarily overflow to the disk when memory usage is unevenly distributed or when memory runs out. Thus, in this study, Write Handle Reusing is proposed to fully utilize memory in shuffle file writing and reading. Load Balancing Optimizer is introduced to ensure the even distribution of data processing across all worker nodes, and Memory-Aware Task Scheduler that coordinates concurrency level and memory usage is also developed to prevent memory spilling. Experimental results on representative workloads demonstrate that the proposed approaches can decrease the overall job execution time and improve memory efficiency. © Springer International Publishing Switzerland 2015.

关键词： MapReduce

来源：评论

学校读者我要写书评

暂无评论

P3DC:Reducing DRAM Cache Hit Latency by Hybrid Mappings

引用

Journal of Computer Science & technology 2024年第6期39卷 1341-1360页

作者： Ye Chi Ren-Tong Guo Xiao-Fei Liao Hai-Kun Liu Jianhui Yue National Engineering Research Center for Big Data Technology and System Wuhan 430074China Services Computing Technology and System Laboratory Wuhan 430074China Cluster and Grid Computing Laboratory Wuhan 430074China School of Computer Science and Technology Huazhong University of Science and TechnologyWuhan 430074China School of Big Data and Internet Shenzhen Technology UniversityShenzhen 518118China Department of Computer Science Michigan Technological UniversityHoughton 49931-1295U.S.A.

Die-stacked dynamic random access memory(DRAM)caches are increasingly advocated to bridge the performance gap between the on-chip cache and the main *** fully realize their potential,it is essential to improve DRAM cache hit rate and lower its cache hit *** order to take advantage of the high hit-rate of set-association and the low hit latency of direct-mapping at the same time,we propose a partial direct-mapped die-stacked DRAM cache called *** design is motivated by a key observation,i.e.,applying a unified mapping policy to different types of blocks cannot achieve a high cache hit rate and low hit latency *** address this problem,P3DC classifies data blocks into leading blocks and following blocks,and places them at static positions and dynamic positions,respectively,in a unified set-associative *** also propose a replacement policy to balance the miss penalty and the temporal locality of different *** addition,P3DC provides a policy to mitigate cache thrashing due to block type *** results demonstrate that P3DC can reduce the cache hit latency by 20.5%while achieving a similar cache hit rate compared with typical set-associative caches.P3DC improves the instructions per cycle(IPC)by up to 66%(12%on average)compared with the state-of-the-art direct-mapped cache—BEAR,and by up to 19%(6%on average)compared with the tag-data decoupled set-associative cache—DEC-A8.

关键词： die-stacked dynamic random access memory(DRAM) cache set-associative direct-mapped hit latency

来源：评论

学校读者我要写书评

暂无评论

An efficient metadata management method in large distributed storage systems 1

引用

4th International Conference on Human-Centric computing, HumanCom'11 and the 6th International Conference on Embedded and Multimedia computing, EMC'11

作者： Ran, Longbo Jin, Hai Cluster and Grid Computing Lab. Services Computing Technology and System Laboratory Huazhong University of Science and Technology 430074 Wuhan China

ISBN: (数字)9789400721050

ISBN: (纸本)9789400721043

Efficient metadata management is a critical aspect of overall system performance in large distributed storage systems. Directory subtree partitioning and traditional hashing are two common techniques used for managing metadata in such systems, but both have some shortcomings, for example, in directory subtree partitioning method, the root node easily becomes a bottleneck, and for traditional hashing, a large directory hierarchy must be maintained and traversed. In this paper, we present a new method called directory-level-based metadata management that has high efficiency while avoiding the shortcomings of traditional methods. © 2011 Springer Science+Business Media B.V.

关键词： Metadata

来源：评论

学校读者我要写书评

暂无评论

Semi-probabilistic routing in intermittently connected mobile ad hoc networks

Semi-probabilistic routing in intermittently connected mobil...

引用

2007 2nd International Conference on Communications and Networking in China, ChinaCom 2007

作者： Ke, Shi Laboratory of Services Computing Technology and System College of Computer Science and Technology Huazhong University of Science and Technology Wuhan China

ISBN: (纸本)9781424410095

ICMANs (Intermittently Connected Mobile Ad hoc Networks) are wireless networks where most of the time there does not exist a complete path from the source to the destination. In this paper, a novel routing approach, SPR (Semi-Probabilistic Routing), is proposed to address routing problem in ICMANs. SPR takes into account information about host mobility and connectivity changes to produce estimates enabling more accurate message forwarding. These include maintaining proactive routing zones for stable local topology to minimize blind message forwarding, and identifying potential carriers to maximize message delivery despite network partitions and intermittent connectivity. We compare the performance of our protocol against others, using a mobility model validated with real-world traces.

关键词： Ad hoc networks

来源：评论

学校读者我要写书评

暂无评论

Public auditing for secure data storage in cloud through a third party auditor using modern ciphertext 11

Public auditing for secure data storage in cloud through a t...

引用

11th International Conference on Information Assurance and Security, IAS 2015

作者： Hussien, Zaid Alaa Jin, Hai Abduljabbar, Zaid Ameen Yassin, Ali A. Hussain, Mohammed Abdulridha Abbdal, Salah H. Zou, Deqing Cluster and Grid Computing Laboratory Services Computing Technology and System Laboratory School of Computer Science and Technology Huazhong University of Science and Technology Wuhan430074 China University of Basrah Basrah Iraq

ISBN: (纸本)9781467387156

Outsourced data in cloud and computation results are not always trustworthy because data owners lack physical possession and control over the data as a result of virtualization, replication, and migration techniques. Protecting outsourced data from security threats has become a challenging and potentially formidable task in cloud computing;hence, many schemes have focused on ameliorating this problem and on enabling public auditability for cloud data storage security. These schemes drop into two categories: total computation cost and burden on client side. Researchers have used bilinear map technology with public key cryptography. Although this technology is highly efficient, computation time is long and overhead cost is high. The client needs to perform numerous computations to ensure the integrity of data storage. To reduce auditing cost, we propose an efficient and robust scheme to maintain data integrity in cases that involve public auditing. Our scheme adopts modern cipher cryptography with a cryptographic hash function. We consider allowing a third party auditor to preprocess data on behalf of cloud users before uploading them to cloud service providers and then verifying data integrity afterward. Our proposed scheme has important security characteristics, such as privacy, key management, low cost computation, key exchange, low overhead cost, no burden on client side, inability of cloud service providers to create correct verifier respond without data, and one-time key. Finally, efficiency analysis shows that our scheme is faster and more cost-efficient than the bilinear map-based scheme. © 2015 IEEE.

关键词： Public key cryptography

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：