检索结果-内蒙古大学图书馆

39th IEEE International Conference on Data engineering, ICDE 2023

作者： Xing, Yipeng Li, Yongkun Wang, Zhiqiang Xu, Yinlong Lui, John C. S. University of Science and Technology of China China Anhui Province Key Laboratory of High Performance Computing China The Chinese University of Hong Kong Department of Computer Science and Engineering Hong Kong

ISBN: (纸本)9798350322279

As a fundamental tool for graph analysis, random walk receives extensive attention in both industry and academia. For computing massive random walks, recent works show that GPUs provide a good option to accelerate the performance. However, due to the limited memory space of modern GPUs, it is infeasible to have both the graph data and walk index fully reside in GPU memory when running large-scale random walks. Thus, it necessitates an out-of-GPU-memory design, but this inevitably induces large amounts of CPU-GPU data transmission traffic and thus hinders the overall performance. In this paper, we develop LightTraffic, which optimizes the data transmission between CPU and GPU memory under the constraint of GPU memory capacity with various system designs, including a memory-efficient scheme for partition-based management and multiple scheduling techniques. LightTraffic is a fully out-of-GPU-memory design, so it supports running large-scale random walks on GPUs. Experiments on our prototype show that LightTraffic outperforms various state-of-the-art CPU-based in-memory systems which also support large-scale random walks. For example, compared to the CPU-based systems FlashMob and ThunderRW, which are highly optimized for random walks, LightTraffic achieves 1.7-5.0× and 1.4 - 12.8× performance speedup, respectively. It also achieves up to an order of magnitude speedup when compared to the GPU-based system Subway which also supports large-scale random walks with an out-of-GPU-memory design for graph data. © 2023 IEEE.

关键词： Graphics processing unit

来源：评论

学校读者我要写书评

暂无评论

A carbon 2.0 framework based on cloud computing

A carbon 2.0 framework based on cloud computing

引用

IEEE/International Association for computer and Information science International Conference on computer and Information science

作者： Li, Jiandun Zhang, Wu Peng, Junjie Lei, Zhou Lei, Yu School of Computer Engineering and Science High Performance Computing Center Shanghai University Shanghai China Department of Computer Science and Engineering University of Texas at Arlington Arlington TX United States

ISBN: (纸本)9780769541471

The Copenhagen climate conference 2009 has concluded that we have to change the way how we live. Currently, several carbon management systems are being developed to meet enterprises' requirement. In addition, a number of carbon footprint calculation tools have been developed to fulfill carbon calculation needs from industries, households and individuals. However, under the current circumstance, it is still a challenging issue on how to take advantage of the latest IT technologies to improve carbon calculations with comprehensive functionality. In this paper, we extend carbon 2.0, the concept proposed by previous studies, and introduce a new carbon framework based on cloud computing. This new framework is massively scalable and can configure and deliver carbon-related services dynamically and on demand. Moreover, it is a real low-carbon framework itself! © 2010 IEEE.

关键词： Greenhouse gases

来源：评论

学校读者我要写书评

暂无评论

Adapting Memory Hierarchies for Emerging Datacenter Interconnects

引用

Journal of computer science & Technology 2015年第1期30卷 97-109页

作者：江涛侯锐董建波柴琳 Sally A. McKee 田斌张立新孙凝晖 State Key Laboratory of Computer Architecture Institute of Computing Technology Chinese Academy of Sciences Beijing 100190 China University of Chinese Academy of Sciences Beijing 100049 China Computer Science and Engineering Chalmers University of Technology Gothenburg 41296 Sweden National High Performance Integrated Circuit Design Center (Shanghai) Shanghai 201204 China

Efficient resource utilization requires that emerging datacenter interconnects support both high performance communication and efficient remote resource sharing. These goals require that the network be more tightly coupled with the CPU chips. Designing a new interconnection technology thus requires considering not only the interconnection itself, but also the design of the processors that will rely on it. In this paper, we study memory hierarchy implications for the design of high-speed datacenter interconnects particularly as they affect remote memory access -- and we use PCIe as the vehicle for our investigations. To that end, we build three complementary platforms： a PCIe-interconnected prototype server with which we measure and analyze current bottlenecks; a software simulator that lets us model microarchitectural and cache hierarchy changes; and an FPGA prototype system with a streamlined switchless customized protocol Thunder with which we study hardware optimizations outside the processor. We highlight several architectural modifications to better support remote memory access and communication, and quantify their impact and ]imitations.

关键词： high-speed interconnect memory hierarchy time shared memory datacenter network

来源：评论

学校读者我要写书评

暂无评论

Implementation of global digital library grid platform using data grid technology

Implementation of global digital library grid platform using...

引用

作者： Yang, Chao-Tung Ho, Hsin-Chuan Yang, I.-Hsien High-Performance Computing Laboratory Department of Computer Science and Information Engineering Tunghai University Taichung Taiwan Department of Computer Science and Information Engineering Tunghai University Taichung Taiwan Lizen High School Taichung Taiwan Knowledge and Service Information Corporation Taichung City Taiwan

Since the beginning of the 21st century, knowledge has been accumulating at a tremendous speed. The amount of global books, literature, and data available has increased in astounding quantities. The traditional library service system is no longer able to meet the requirements of the present reality. With the development of Internet and rapid advancement of information technology, a totally new knowledge transfer model has been developed: Books and other forms of data (including text, voice and images) are digitized and then provided to readers by way of a more convenient method, in order to search for and obtain the exact content they need from libraries. We propose a concept for a Global Digital Library Grid. This digital library organization would not only include new members (new libraries or new museums) but be flexible enough not to affect the systems and framework of the original Grid member. As the organization grows, it will form an enormous Virtual Grid Digital Library to provide readers with speedy Knowledge Service that meets their requirements.

关键词： Digital libraries

来源：评论

学校读者我要写书评

暂无评论

On n-Coherent Rings and （n, d）-Injective Modules

引用

Algebra Colloquium 2015年第2期22卷 349-360页

作者： Dongdong Zhang Baiyu Ouyang Department of Mathematics Zhejiang Normal University Jinhua Zhejiang 321004 China Key Laboratory of High Performance Computing and Stochastic Information Processing (Ministry of Education of China) College of Mathematics and Computer Science Hunan Normal University Changsha Hunan 410081 China

Let R be a ring, n, d be fixed non-negative integers, Jn,d the class of （n, d）- injective left R-modules, and Fn,d the class of （n, d）-flat right R-modules. In this paper, we prove that if R is a left n-coherent ring and m ≥ 2, then gl-right-Jn,a-dimRM ≤ m if and only if gl-left-Jn,d-dimRM ≤ m -- 2, if and only if Extm＋k（M, N） = 0 for all left R-modules M, N and all k 〉 -1, if and only if Extm-l（M, N） = 0 for all left R-modules M, N. Meanwhile, we prove that if R is a left n-coherent ring, then - - is right balanced on MR ×RM by Fn,d × Jn,d, and investigate the global right Jn,d-dimension of RM and the global right Fn,d-dimension of MR by right derived functors of - -. Some known results are obtained as corollaries.

关键词：（n d）-injective left R-module （n d）-flat right R-module left n-coherent ring

来源：评论

学校读者我要写书评

暂无评论

Research on performance optimization of virtual data space across WAN

引用

Frontiers of computer science 2024年第6期18卷 167-187页

作者： Jiantong HUO Zhisheng HUO Limin XIAO Zhenxue HE State Key Laboratory of Software Development Environment Beihang UniversityBeijing 100191China School of Computer Science and Engineering Beihang UniversityBeijing 100191China High Performance Computing Center Beihang UniversityBeijing 100191China Hebei Key Laboratory of Agricultural Big Data Hebei Agricultural UniversityBaoding 071001China

For the high-performance computing in a WAN environment,the geographical locations of national supercomputing centers are scattered and the network topology is complex,so it is difficult to form a unified view of *** aggregate the widely dispersed storage resources of national supercomputing centers in China,we have previously proposed a global virtual data space named GVDS in the project of“high performance computing Virtual Data Space”,a part of the National Key Research and Development Program of *** GVDS enables large-scale applications of the high-performance computing to run efficiently across ***,the applications running on the GVDS are often data-intensive,requiring large amounts of data from multiple supercomputing centers across *** this regard,the GVDS suffers from performance bottlenecks in data migration and access across *** solve the above-mentioned problem,this paper proposes a performance optimization framework of GVDS including the multitask-oriented data migration method and the request access-aware IO proxy resource allocation *** a WAN environment,the framework proposed in this paper can make an efficient migration decision based on the amount of migrated data and the number of multiple data sources,guaranteeing lower average migration latency when multiple data migration tasks are running in *** addition,it can ensure that the thread resource of the IO proxy node is fairly allocated among different types of requests(the IO proxy is a module of GVDS),so as to improve the application’s performance across *** experimental results show that the framework can effectively reduce the average data access delay of GVDS while improving the performance of the application greatly.

关键词： storage aggregation across WANs large-scale applications GVDS data migration allocation of IO proxy resource

来源：评论

学校读者我要写书评

暂无评论

Improved multi-objective evolutionary algorithm for multi-agent coalition formation

Journal of Software

引用

Journal of Software 2013年第12期8卷 2991-2995页

作者： Xu, Bo Zhang, Ruizhe Yu, Jian Ping Department of Computer Science and Technology of Guangdong University of Petrochemical Technology Guangdong Province China Computer Science and Technic Academy Department Pingdingshan University Henan Province China College of Mathematics and Computer Science Key Laboratory of High Performance Computing and Stochastic Information Processing Hunan Normal University Hunan Province China

One of the key problems in multi-agent coalition formation is to optimally assign and schedule resources. An improved multi-objective evolutionary Algorithm (IMOEA) is proposed to solve this problem. Compared with several well-known algorithms such as NSGA, MOEA, experimental results show the algorithm is very suitable for coalition formation problem. © 2013 Academy Publisher.

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

Dynamic partitioning to mitigate stuck-at faults in emerging memories 36

Dynamic partitioning to mitigate stuck-at faults in emerging...

引用

36th IEEE/ACM International Conference on computer-Aided Design, ICCAD 2017

作者： Zhang, Jiangwei Kline, Donald Fang, Liang Melhem, Rami Jones, Alex K. State Key Laboratory of High Performance Computing College of Computer National University of Defense Technology China Department of Electrical and Computer Engineering University of Pittsburgh United States Department of Computer Science University of Pittsburgh United States

ISBN: (纸本)9781538630938

Emerging non-volatile memories have many advantages over conventional memory. Unfortunately, many are susceptible to write endurance challenges, resulting in stuck-at faults. Existing mitigation methods statically partition and invert data within a block containing such faults (partition-and-flip) to ensure data is written to match stuck-at cells such that they may remain in service. Unfortunately, these schemes have limited fault tolerance capabilities and require the assumption that their auxiliary bits are fault free. We propose a dynamic partitioning scheme that improves the number of tolerated stuck-at faults and simultaneously protects auxiliary bits. Dynamic partitioning can significantly improve the fault tolerance over existing static partitioning approaches with an equal number of auxiliary bits. Moreover, it can often still improve fault tolerance while reducing the number of auxiliary bits. Compared to flip-N-write and Aegis, a leading mitigation scheme, dynamic partitioning can achieve 7-72% and 5-53 x lower write error rates, respectively, for the same capacity overhead with a stuck-at-fault rate of 10-3. © 2017 IEEE.

关键词： Fault tolerance

来源：评论

学校读者我要写书评

暂无评论

Yoda: Judge me by my size, do you? 35

Yoda: Judge me by my size, do you?

引用

35th IEEE International Conference on computer Design, ICCD 2017

ISBN: (纸本)9781538622544

Phase change memory is a promising alternative to conventional memories such as DRAM due to its density and non-volatility. Unfortunately, reliability is still a challenge as limited write endurance, exacerbated by process variation, leads to increasing numbers of stuck-at faults over the memory's lifetime. Error-correcting Pointers (ECP) is a popular proposal to mitigate stuck-at faults by recording the addresses and the values of faulty bits in order to extend the memory lifetime. In this paper, we propose Yoda, a method to extend ECP with one or a small number of additional encoding bits in order to dramatically improve the effectiveness and guaranteed fault correction capability of ECP. Our simulation results demonstrate that Yoda has a 3.0x improvement in fault coverage compared to a fault-aware ECP with a similar overhead, while also providing a 2.5-3.0x improvement over state-of-the-art schemes with comparable complexity. © 2017 IEEE.

关键词： Phase change memory

来源：评论

学校读者我要写书评

暂无评论

Parallel multilevel block ILU preconditioning techniques for large sparse linear systems

Parallel multilevel block ILU preconditioning techniques for...

引用

International Parallel and Distributed Processing Symposium, IPDPS 2003

作者： Shen, Chi Zhang, Jun Wang, Kai Laboratory for High Performance Scientific Computing and Computer Simulation Department of Computer Science University of Kentucky 773 Anderson Hall LexingtonKY40506-0046 United States

ISBN: (纸本)0769519261

We present a class of parallel preconditioning strategies built on a multilevel block incomplete LU (ILU)factorization technique to solve large sparse linear systems on distributed memory parallel computers. The preconditioners are constructed by using the concept of block independent sets. Two algorithms for constructing block independent sets of a distributed sparse matrix are proposed. We compare a few implementations of the parallel multilevel ILU preconditioners with different block independent set algorithms and different coarse level solution strategies. We also use some diagonal thresholding and perturbation strategies to enhance factorization stability. Numerical experiments indicate that our parallel multilevel block ILU preconditioners are robust and efficient. © 2003 IEEE.

关键词： Factorization

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：