检索结果-内蒙古大学图书馆

您好，读者！请登录

内蒙古大学图书馆

首页
概况
党建
资源
服务
科研支持
- 论文收录引用证明
- 科技查新
知识产权
档案馆
帮助

咨询与建议

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

您的常用邮箱：*

您的手机号码：*

问题描述：

当前已输入0个字，您还可以输入200个字

全部搜索
期刊论文
图书
学位论文
标准
纸本馆藏
外文资源发现
数据库导航
超星发现

高级检索

时间限定

出版年份：

文献类型

图书期刊文献学位论文多媒体

馆藏选择

电子馆藏纸本馆藏

核心期刊

全部期刊 SCI 收录期刊 SSCI 收录期刊 EI 收录期刊 CSCD 收录期刊 CSSCI 收录期刊

语言

中文英文

文献类型

期刊文献图书学位论文标准纸本馆藏

帮助

文字说明：

T=题名（书名、题名），A=作者（责任者），K=主题词，P=出版物名称，PU=出版社名称，O=机构（作者单位、学位授予单位、专利申请人），L=中图分类号，C=学科分类号，U=全部字段，Y=年（出版发行年、学位年度、标准发布年）

检索规则说明：

AND代表“并且”；OR代表“或者”；NOT代表“不包含”；(注意必须大写,运算符两边需空一格)

检索范例：

范例一：(K=图书馆学 OR K=情报学) AND A=范并思 AND Y=1982-2016
范例二：P=计算机应用与软件 AND (U=C++ OR U=Basic) NOT K=Visual AND Y=2011-2016

分类表

所选分类

>> <<

限定检索结果

文献类型

768 篇 会议
27 篇 期刊文献
1 册 图书

馆藏范围

796 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

384 篇 工学
- 362 篇 计算机科学与技术...
- 194 篇 软件工程
- 59 篇 信息与通信工程
- 51 篇 电气工程
- 27 篇 电子科学与技术（可...
- 18 篇 控制科学与工程
- 13 篇 材料科学与工程（可...
- 7 篇 安全科学与工程
- 7 篇 网络空间安全
- 4 篇 生物医学工程（可授...
- 3 篇 光学工程
- 3 篇 动力工程及工程热...
- 3 篇 生物工程
- 2 篇 力学（可授工学、理...
- 2 篇 机械工程
- 2 篇 冶金工程
- 2 篇 土木工程
- 2 篇 交通运输工程
101 篇 理学
- 95 篇 数学
- 18 篇 统计学（可授理学、...
- 8 篇 系统科学
- 5 篇 物理学
- 4 篇 生物学
72 篇 管理学
- 51 篇 管理科学与工程(可...
- 38 篇 工商管理
- 24 篇 图书情报与档案管...
8 篇 经济学
- 8 篇 应用经济学
7 篇 医学
- 7 篇 临床医学
- 2 篇 基础医学(可授医学...
3 篇 法学
- 3 篇 社会学
1 篇 教育学
1 篇 文学
1 篇 农学
1 篇 军事学

主题

121 篇 computer science
94 篇 concurrent compu...
94 篇 distributed comp...
83 篇 distributed data...
79 篇 parallel process...
78 篇 application soft...
76 篇 databases
74 篇 database systems
73 篇 parallel process...
55 篇 delay
53 篇 distributed comp...
52 篇 processor schedu...
45 篇 computer archite...
43 篇 transaction data...
41 篇 algorithm design...
40 篇 costs
39 篇 relational datab...
35 篇 protocols
34 篇 computational mo...
33 篇 hardware

机构

6 篇 ibm thomas j. wa...
5 篇 ieee
4 篇 school of comput...
4 篇 department of co...
4 篇 department of co...
3 篇 center for paral...
3 篇 department of co...
3 篇 lip ens-lyon lyo...
3 篇 department of co...
2 篇 department of co...
2 篇 institute of inf...
2 篇 department of co...
2 篇 institute of inf...
2 篇 computer systems...
2 篇 department of co...
2 篇 school of comput...
2 篇 department of co...
2 篇 department of el...
2 篇 department of co...
2 篇 school of comput...

作者

7 篇 a. choudhary
6 篇 a. boukerche
5 篇 j. saltz
4 篇 s.k. das
4 篇 t. kurc
4 篇 a. el abbadi
3 篇 a. rau-chaplin
3 篇 o. wolfson
3 篇 f. dehne
3 篇 p.s. yu
3 篇 a. singh
3 篇 casanova henri
3 篇 c. liu
3 篇 a. bar-noy
3 篇 s. kipnis
3 篇 g. gupta
3 篇 d. agrawal
3 篇 x. shen
2 篇 grove matthew
2 篇 a. burger

语言

794 篇 英文
2 篇 其他

检索条件"任意字段=Proceedings of the first international symposium on Databases in parallel and distributed systems"

共 796 条记录，以下是41-50 订阅

全选清除本页清除全部题录导出标记到"检索档案"

详细简洁

排序：

Hierarchical Coding for distributed Computing

Hierarchical Coding for Distributed Computing

引用

IEEE international symposium on Information Theory (ISIT)

作者： Park, Hyegyeong Lee, Kangwook Sohn, Jy-yong Suh, Changho Moon, Jaekyun Korea Adv Inst Sci & Technol Sch Elect Engn Daejeon South Korea

ISBN: (纸本)9781538647813

Coding for distributed computing supports low-latency computation by relieving the burden of straggling workers. While most existing works assume a simple master-worker model, we consider a hierarchical computational structure consisting of groups of workers, motivated by the need to reflect the architectures of real-world distributed computing systems. In this work, we propose a hierarchical coding scheme for this model, as well as analyze its decoding cost and expected computation time. Specifically, we first provide upper and lower bounds on the expected computing time of the proposed scheme. We also show that our scheme enables efficient parallel decoding, thus reducing decoding costs by orders of magnitude over non-hierarchical schemes. When considering both decoding cost and computing time, the proposed hierarchical coding is shown to outperform existing schemes in many practical scenarios.

关键词： distributed computing Task analysis Encoding Decoding Computational modeling Switches"

来源：评论

学校读者我要写书评

暂无评论

A model-based approach to streamlining distributed training for asynchronous SGD

A model-based approach to streamlining distributed training ...

引用

26th IEEE international symposium on Modeling, Analysis and Simulation of Computer and Telecommunication systems (MASCOTS)

作者： Lin, Sung-Han Paolieri, Marco Chou, Cheng-Fu Golubchik, Leana Univ Southern Calif Dept Comp Sci Los Angeles CA 90007 USA Natl Taiwan Univ Dept Comp Sci Taipei Taiwan NetApp Inc Sunnyvale CA 94089 USA

ISBN: (纸本)9781538668863

The success of Deep Neural Networks (DNNs) has created significant interest in the development of software tools, hardware architectures, and cloud systems to meet the huge computational demand of their training jobs. A common approach to speeding up an individual job is to distribute training data and computation among multiple nodes, periodically exchanging intermediate results. In this paper, we address two important problems for the application of this strategy to large-scale clusters and multiple, heterogeneous jobs. first, we propose and validate a queueing model to estimate the throughput of a training job as a function of the number of nodes assigned to the job;this model targets asynchronous Stochastic Gradient Descent (SGD), a popular strategy for distributed training, and requires only data from quick, two-node profiling in addition to job characteristics (number of requested training epochs, mini-batch size, size of DNN parameters, assigned bandwidth). Throughput estimations are then used to explore several classes of scheduling heuristics to reduce response time in a scenario where heterogeneous jobs are continuously submitted to a large-scale cluster. These scheduling algorithms dynamically select which jobs to run and how many nodes to assign to each job, based on different trade-offs between service time reduction and efficiency (e.g., speedup per additional node). Heuristics are evaluated through extensive simulations of realistic DNN workloads, also investigating the effects of early termination, a common scenario for DNN training jobs.

关键词： distributed Machine Learning parallel Scheduling Queueing Networks TensorFlow

来源：评论

学校读者我要写书评

暂无评论

A Network-Centric Hardware/Algorithm Co-Design to Accelerate distributed Training of Deep Neural Networks 51

A Network-Centric Hardware/Algorithm Co-Design to Accelerate...

引用

51st Annual IEEE/ACM international symposium on Microarchitecture (MICRO)

作者： Li, Youjie Park, Jongse Alian, Mohammad Yuan, Yifan Qu, Zheng Pan, Peitian Wang, Ren Schwing, Alexander Gerhard Esmaeilzadeh, Hadi Kim, Nam Sung Univ Illinois Urbana IL 61801 USA Georgia Inst Technol Atlanta GA 30332 USA Tsinghua Univ Beijing Peoples R China Shanghai Jiao Tong Univ Shanghai Peoples R China Intel Corp Santa Clara CA 95051 USA Univ Calif San Diego San Diego CA 92103 USA

ISBN: (纸本)9781538662403

Training real-world Deep Neural Networks (DNNs) can take an eon (i.e., weeks or months) without leveraging distributed systems. Even distributed training takes inordinate time, of which a large fraction is spent in communicating weights and gradients over the network. State-of-the-art distributed training algorithms use a hierarchy of worker-aggregator nodes. The aggregators repeatedly receive gradient updates from their allocated group of the workers, and send back the updated weights. This paper sets out to reduce this significant communication cost by embedding data compression accelerators in the Network Interface Cards (NICs). To maximize the benefits of in-network acceleration, the proposed solution, named INCEPTIONN (In-Network Computing to Exchange and Process Training Information Of Neural Networks), uniquely combines hardware and algorithmic innovations by exploiting the following three observations. (1) Gradients are significantly more tolerant to precision loss than weights and as such lend themselves better to aggressive compression without the need for the complex mechanisms to avert any loss. (2) The existing training algorithms only communicate gradients in one leg of the communication, which reduces the opportunities for in-network acceleration of compression. (3) The aggregators can become a bottleneck with compression as they need to compress/decompress multiple streams from their allocated worker group. To this end, we first propose a lightweight and hardware friendly lossy-compression algorithm for floating-point gradients, which exploits their unique value characteristics. This compression not only enables significantly reducing the gradient communication with practically no loss of accuracy, but also comes with low complexity for direct implementation as a hardware block in the NIC. To maximize the opportunities for compression and avoid the bottleneck at aggregators, we also propose an aggregator-free training algorithm that exchanges gradien

关键词： Training Neural networks Hardware Acceleration Complexity theory Compression algorithms distributed databases

来源：评论

学校读者我要写书评

暂无评论

Context-Free Path Querying by Matrix Multiplication 1

Context-Free Path Querying by Matrix Multiplication

引用

1st ACM SIGMOD Joint international Workshop on Graph Data Management Experiences and systems (GRADES) and Network Data Analytics (NDA)

作者： Azimov, Rustam Grigorev, Semyon St Petersburg State Univ St Petersburg Russia

ISBN: (纸本)9781450356954

Context-free path querying is a technique, which recently gains popularity in many areas, for example, graph databases, bioinformatics, static analysis, etc. In some of these areas, it is often required to query large graphs, and existing algorithms demonstrate a poor performance in this case. The generalization of matrix-based Valiant's context-free language recognition algorithm for graph case is widely considered as a recipe for efficient context-free path querying;however, no progress has been made in this direction so far. We propose the first generalization of matrix-based Valiant's algorithm for context-free path querying. Our generalization does not deliver a truly sub-cubic worst-case complexity algorithm, whose existence still remains a hard open problem in the area. On the other hand, the utilization of matrix operations (such as matrix multiplication) in the process of context-free path query evaluation makes it possible to efficiently apply a wide class of optimizations and computing techniques, such as GPGPU (General-Purpose computing on Graphics Processing Units), parallel processing, sparse matrix representation, distributed-memory computation, etc. Indeed, the evaluation on a set of conventional benchmarks shows, that our algorithm outperforms the existing ones.

关键词： Transitive closure context-free path querying graph databases context-free grammar GPGPU matrix multiplication

来源：评论

学校读者我要写书评

暂无评论

Dynamic Load Balancing and Channel Strategy for Apache Flume Collecting Real-time Data Stream 15

Dynamic Load Balancing and Channel Strategy for Apache Flume...

引用

15th IEEE international symposium on parallel and distributed Processing with Applications (ISPA) / 16th IEEE international Conference on Ubiquitous Computing and Communications (IUCC)

作者： Shu, Buqing Chen, Haopeng Sun, Meng Shanghai Jiao Tong Univ Sch Software Shanghai Peoples R China

ISBN: (纸本)9781538637906

With the development of information technology, real-time data stream processing(RTDSP) has become a popular research topic. The first step of RTDSP is collecting data, requiring a data collector to receive data from the source and send them to the sink. Apache Flume, a distributed and reliable framework, used for this purpose, has some limitations and drawbacks on load balancing and storage. In this paper, we aim to improve performance and availability for collecting unstable real-time big data stream. So we propose a new load balancing strategy based on the free memory size and a storage strategy of integration memory channel with the multi-file channel to reduce the overhead of disk and network. Finally, the experimental results show that the availability and performance are improved under the condition of a poor network, high availability requirements, intense competition in memory resources and large data size. Specifically, the availability is higher than 99.999%, and the performance can be improved by 10%-50% under different conditions.

关键词： Load management Real-time systems distributed databases Throughput Monitoring Dynamic scheduling Memory management

来源：评论

学校读者我要写书评

暂无评论

HPDC 2017 - proceedings of the 26th international symposium on High-Performance parallel and distributed Computing

HPDC 2017 - Proceedings of the 26th International Symposium ...

引用

26th ACM international symposium on High-Performance parallel and distributed Computing, HPDC 2017

ISBN: (纸本)9781450346993

The proceedings contain 19 papers. The topics discussed include: enabling workflow-aware scheduling on HPC systems;parallel stream processing against workload skewness and variance;NICE: network-integrated cluster-efficient storage;MaDaTS: managing data on tiered storage for scientific workflows;ArrayUDF: user-defined scientific data analysis on arrays;knor: a NUMA-optimized in-memory, distributed and semi-external-memory k-means library;to push or to pull: on reducing communication and synchronization in graph computations;better safe than sorry: grappling with failures of in-memory data analytics frameworks;LetGo: a lightweight continuous framework for HPC applications under failures;towards a more complete understanding of SDC propagation;COS: a parallel performance model for dynamic variations in processor speed, memory speed, and thread concurrency;explaining wide area data transfer performance;predicting output performance of a petascale supercomputer;TCP throughput profiles using measurements over dedicated connections;IOGP: an incremental online graph partitioning algorithm for distributed graph databases;and machine and application aware partitioning for adaptive mesh refinement applications.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Incremental elasticity for NoSQL data stores 36

Incremental elasticity for NoSQL data stores

引用

36th IEEE symposium on Reliable distributed systems (SRDS)

作者： Papaioannou, Antonis Magoutis, Kostas Fdn Res & Technol Hellas Inst Comp Sci Iraklion 70013 Greece Univ Crete Comp Sci Dept Iraklion 70013 Greece Univ Ioannina Dept Comp Sci & Engn GR-45110 Ioannina Greece

ISBN: (纸本)9781538616796

Service elasticity, the ability to rapidly expand or shrink service processing capacity on demand, has become a first-class property in the domain of infrastructure services. Scalable NoSQL data stores are the de-facto choice of applications aiming for scalable, highly available data persistence. The elasticity of such data stores is still challenging, due to the complexity and performance impact of moving large amounts of data over the network to take advantage of new resources (servers). In this paper we propose incremental elasticity, a new mechanism that progressively increases processing capacity in a fine-grain manner during an elasticity action by making sub-sections of the transferred data available for access on the new server, prior to completing the full transfer. In addition, by scheduling data transfers during an elasticity action in sequence (rather than as simultaneous transfers) between each pre-existing server involved and the new server, incremental elasticity leads to smoother elasticity actions, reducing their overall impact on performance.

关键词： Elasticity Throughput Servers Data transfer distributed databases Schedules Receivers

来源：评论

学校读者我要写书评

暂无评论

proceedings - 2017 IEEE 16th international symposium on parallel and distributed Computing, ISPDC 2017

Proceedings - 2017 IEEE 16th International Symposium on Para...

引用

16th IEEE international symposium on parallel and distributed Computing, ISPDC 2017

ISBN: (纸本)9781538608623

The proceedings contain 20 papers. The topics discussed include: contention-aware selective caching to mitigate intra-warp contention on GPUs;an autonomic approach for the selection of robust dynamic loop scheduling techniques;towards the reproducibility of using DLS techniques in scientific applications;exploring the relation between two levels of scheduling using a novel simulation approach;reducing fragmentation on 3D Torus-based HPC systems using packing-based job scheduling and job placement reconfiguration;a bi-objective scheduling approach for energy optimisation of executing and transmitting HPC Applications in decentralised multi-cloud systems;three-tier private cloud application management system with on-site hardware;the performance and scalability of the SHMEM and corresponding MPI-3 routines on a Cray XC30;a new parallelization scheme for the Hermite interpolation based gyroaverage operator;Benchmarking the WRF Model on Bluegene/P, cluster, and cloud platforms and accelerating model setup through parallel genetic algorithms;the OpenDC vision: towards collaborative datacenter simulation and exploration for everybody;on reliability-aware server consolidation in cloud datacenters;accelerating machine learning on sparse datasets with a distributed memory vector architecture;graph-based speculative query execution in relational databases;and understanding the impact of fine-grained data sharing and thread communication on heterogeneous workload development.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Massively parallel first-principles simulation of electron dynamics in materials 30

Massively parallel first-principles simulation of electron d...

引用

30th IEEE international parallel and distributed Processing symposium (IPDPS)

作者： Draeger, Erik W. Andrade, Xavier Gunnels, John A. Bhatele, Abhinav Schleife, Andre Correa, Alfredo A. Lawrence Livermore Natl Lab Livermore CA 94551 USA IBM Thomas J Watson Res Ctr Yorktown Hts NY 10598 USA Univ Illinois Champaign IL 61801 USA

ISBN: (纸本)9781509021406

We present a highly scalable, parallel implementation of first-principles electron dynamics coupled with molecular dynamics (MD). By using optimized kernels, network topology aware communication, and by fully distributing all terms in the time-dependent Kohn-Sham equation, we demonstrate unprecedented time to solution for disordered aluminum systems of 2000 atoms (22,000 electrons) and 5400 atoms (59,400 electrons), with wall clock time as low as 7.5 s per MD time step. Despite a significant amount of non-local communication required in every iteration, we achieved excellent strong scaling and sustained performance on the Sequoia Blue Gene/Qsupercomputer at LLNL. We obtained up to 59% of the theoretical sustained peak performance on 16,384 nodes and performance of 8.75 Petaflop/s (43% of theoretical peak) on the full 98,304 node machine (1,572,864 cores). Scalable explicit electron dynamics allows for the study of phenomena beyond the reach of standard first-principles MD, in particular, materials subject to strong or rapid perturbations, such as pulsed electromagnetic radiation, particle irradiation, or strong electric currents. Published by Elsevier Inc.

关键词： Electron dynamics TDDFT Explicit time integration Blue Gene/Q

来源：评论

学校读者我要写书评

暂无评论

Understanding System Characteristics of Online Erasure Coding on Scalable, distributed and Large-Scale SSD Array systems

Understanding System Characteristics of Online Erasure Codin...

引用

IEEE international symposium on Workload Characterization (IISWC)

作者： Koh, Sungjoon Zhang, Jie Kwon, Miryeong Yoon, Jungyeon Donofrio, David Kim, Nam Sung Jung, Myoungsoo Yonsei Univ Comp Architecture & Memory Syst Lab Sch Integrated Technol Yonsei Inst Convergence Technol Seoul South Korea Lawrence Berkeley Natl Lab Berkeley CA USA SK Telecom Seoul South Korea Univ Illinois Urbana IL USA

ISBN: (纸本)9781538612330

Large-scale systems with arrays of solid state disks (SSDs) have become increasingly common in many computing segments. To make such systems resilient, we can adopt erasure coding such as Reed-Solomon (RS) code as an alternative to replication because erasure coding can offer a significantly lower storage cost than replication. To understand the impact of using erasure coding on system performance and other system aspects such as CPU utilization and network traffic, we build a storage cluster consisting of approximately one hundred processor cores with more than fifty high-performance SSDs, and evaluate the cluster with a popular open-source distributed parallel file system, Ceph. Then we analyze behaviors of systems adopting erasure coding from the following five viewpoints, compared with those of systems using replication: (1) storage system I/O performance;(2) computing and software overheads;(3) I/O amplification;(4) network traffic among storage nodes;(5) the impact of physical data layout on performance of RS-coded SSD arrays. For all these analyses, we examine two representative RS configurations, which are used by Google and Facebook file systems, and compare them with triple replication that a typical parallel file system employs as a default fault tolerance mechanism. Lastly, we collect 54 block-level traces from the cluster and make them available for other researchers.

关键词： Encoding Arrays Maintenance engineering Layout Performance evaluation distributed databases Reliability

来源：评论

学校读者我要写书评

暂无评论

没有更多数据了...

全选清除本页清除全部题录导出标记到“检索档案”

共80页 << < 1 2 3 4 5 6 7 8 9 10 > >>

检索报告对象比较合并检索0

隐藏清空

合并搜索

回到顶部

执行限定条件

内容：

评分：

请选择保存的检索档案：

请选择收藏分类：

订阅名称：

通借通还

温馨提示：

图书名称：

借书校区：

取书校区：

手机号码：

邮箱地址：

一卡通帐号：

电话和邮箱必须正确填写，我们会与您联系确认。

联系人：

所在院系：

联系邮箱：

联系电话：

内蒙古自治区呼和浩特市赛罕区大学西街235号邮编: 010021

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：