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

33,159 篇 会议
831 篇 期刊文献
229 册 图书
1 篇 学位论文
1 篇 科技报告

馆藏范围

34,221 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

20,136 篇 工学
- 17,854 篇 计算机科学与技术...
- 7,807 篇 软件工程
- 4,543 篇 电气工程
- 2,839 篇 信息与通信工程
- 1,459 篇 控制科学与工程
- 745 篇 电子科学与技术（可...
- 685 篇 动力工程及工程热...
- 468 篇 机械工程
- 381 篇 生物工程
- 339 篇 石油与天然气工程
- 302 篇 仪器科学与技术
- 248 篇 生物医学工程（可授...
- 247 篇 环境科学与工程（可...
- 247 篇 网络空间安全
- 217 篇 力学（可授工学、理...
- 205 篇 建筑学
- 192 篇 材料科学与工程（可...
- 190 篇 安全科学与工程
- 185 篇 土木工程
4,376 篇 理学
- 2,838 篇 数学
- 884 篇 物理学
- 531 篇 系统科学
- 471 篇 生物学
- 424 篇 统计学（可授理学、...
- 229 篇 化学
3,202 篇 管理学
- 2,473 篇 管理科学与工程(可...
- 1,262 篇 工商管理
- 964 篇 图书情报与档案管...
287 篇 经济学
- 281 篇 应用经济学
287 篇 医学
- 217 篇 临床医学
191 篇 法学
98 篇 农学
97 篇 教育学
77 篇 文学
10 篇 艺术学
9 篇 军事学
1 篇 哲学

主题

4,289 篇 grid computing
4,219 篇 distributed comp...
2,063 篇 concurrent compu...
2,043 篇 cloud computing
2,017 篇 parallel process...
1,844 篇 computational mo...
1,619 篇 computer archite...
1,403 篇 computer science
1,362 篇 application soft...
1,288 篇 resource managem...
1,257 篇 computer network...
988 篇 processor schedu...
782 篇 scalability
777 篇 distributed comp...
765 篇 high performance...
760 篇 peer to peer com...
682 篇 costs
670 篇 distributed data...
666 篇 algorithm design...
651 篇 middleware

机构

52 篇 department of co...
47 篇 school of comput...
46 篇 institute of com...
45 篇 college of compu...
39 篇 huazhong univ sc...
34 篇 china electric p...
34 篇 shanghai jiao to...
33 篇 school of comput...
32 篇 school of comput...
31 篇 univ chinese aca...
31 篇 department of co...
27 篇 inria
27 篇 tsinghua univ de...
27 篇 university of ch...
25 篇 shandong provinc...
24 篇 tsinghua univers...
23 篇 huazhong univers...
23 篇 institute of par...
23 篇 nanjing univ sta...
23 篇 college of intel...

作者

69 篇 jin hai
51 篇 hai jin
49 篇 rajkumar buyya
39 篇 fahringer thomas
37 篇 zomaya albert y.
33 篇 liu yang
31 篇 li dongsheng
29 篇 dongsheng li
29 篇 m. takizawa
27 篇 duerr frank
26 篇 li li
25 篇 xhafa fatos
23 篇 wei li
22 篇 wang lei
22 篇 yang yang
20 篇 lei wang
20 篇 xuejun yang
19 篇 dongarra jack
18 篇 singh bhim
18 篇 bala piotr

语言

33,791 篇 英文
251 篇 其他
143 篇 中文
43 篇 俄文
2 篇 乌克兰文
1 篇 德文
1 篇 西班牙文
1 篇 法文
1 篇 葡萄牙文
1 篇 土耳其文

检索条件"任意字段=International Conference on Parallel Distributed and Grid Computing"

共 34221 条记录，以下是4771-4780 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：

Taming Resource Heterogeneity In distributed ML Training With Dynamic Batching 1

Taming Resource Heterogeneity In Distributed ML Training Wit...

引用

1st IEEE international conference on Autonomic computing and Self-Organizing Systems (ACSOS)

作者： Tyagi, Sahil Sharma, Prateek Indiana Univ Bloomington Bloomington IN 47405 USA

ISBN: (纸本)9781728172774

Current techniques and systems for distributed model training mostly assume that clusters are comprised of homogeneous servers with a constant resource availability. However, cluster heterogeneity is pervasive in computing infrastructure, and is a fundamental characteristic of low-cost transient resources (such as EC2 spot instances). In this paper, we develop a dynamic batching technique for distributed data-parallel training that adjusts the mini-batch sizes on each worker based on its resource availability and throughput. Our mini-batch controller seeks to equalize iteration times on all workers, and facilitates training on clusters comprised of servers with different amounts of CPU and GPU resources. This variable mini-batch technique uses proportional control and ideas from PID controllers to find stable mini-batch sizes. Our empirical evaluation shows that dynamic batching can reduce model training times by more than 4x on heterogeneous clusters.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

Towards Flexible and Compiler-Friendly Layer Fusion for CNNs on Multicore CPUs 27th

Towards Flexible and Compiler-Friendly Layer Fusion for CNNs...

引用

27th international European conference on parallel and distributed computing (Euro-Par)

作者： Lin, Zhongyi Georganas, Evangelos Owens, John D. Univ Calif Davis Davis CA 95616 USA Intel Corp Parallel Comp Lab Santa Clara CA USA

ISBN: (纸本)9783030856656;9783030856649

In deep learning pipelines, we demonstrate the performance benefits and tradeoffs of combining two convolution layers into a single layer on multicore CPUs. We analyze when and why fusion may result in runtime speedups, and study three types of layer fusion: (a) 3-by-3 depthwise convolution with 1-by-1 convolution, (b) 3-by-3 convolution with 1-by-1 convolution, and (c) two 3-by-3 convolutions. We show that whether fusion is beneficial is dependent on numerous factors, including arithmetic intensity, machine balance, memory footprints, memory access pattern, and the way the output tensor is tiled. We devise a schedule for all these fusion types to automatically generate fused kernels for multicore CPUs through auto-tuning. With more than 30 layers extracted from five CNNs, we achieve a 1.04x geomean with 1.44x max speedup against separate kernels from MKLDNN, and a 1.24x geomean with 2.73x max speed up against AutoTVM-tuned separate kernels in standalone kernel benchmarks. We also show a 1.09x geomean with 1.29x max speedup against TVM, and a 2.09x geomean with 3.35x max speedup against MKLDNN-backed PyTorch, in end-to-end inference tests.

关键词： Layer fusion CNN Multicore CPUs Auto-tuning

来源：评论

学校读者我要写书评

暂无评论

Finite Element Simulation of the Influence of the Bending Roll Profile on the Stress-Strain State of Billets for Longitudinal-Welded Rolled Pipes 15th

Finite Element Simulation of the Influence of the Bending Ro...

引用

15th international Scientific conference on parallel Computational Technologies (PCT)

作者： Gurevich, Leonid M. Novikov, Roman E. Bannikov, Alexandr, I Pronichev, Dmitriy Vladimirovich Frunkin, Dmitry B. Volgograd State Tech Univ Volgograd Russia Volzhsky Pipe Plant Volzhsky Russia

ISBN: (纸本)9783030816919;9783030816902

In this paper, we describe 3D finite-element models for the study of billets used in pipe rolling and made of steel sheets thicker than 25 mm. Relying on 3D modeling with the MSC Marc software package, we study how several alternatives of lowering the upper roller of a traditional profile affect the geometry of the resulting pipe billet and, also, the distribution of deformations and stress during the bending process. We manage to reduce the computation time for a 3D model with a finite element mesh containing more than one million nodes, which is possible through multi-threaded computation distributed over the nodes of a computing cluster. The main load during the first pass of a bending tool with a traditional profile is exerted on local areas of the outer surface of the pipe billet. Those areas are located on the border of the edges and the chamfers of the weld groove. Plastic deformation occurs on them and leads to local thinning of the pipe billet. We suggest alternatives for changing the profile of the bending tool to create additional contact pads during the bending process.

关键词： Longitudinal welded pipes Finish bending Finite element method Bending roll shape parallel computations Cluster Stress-strain state

来源：评论

学校读者我要写书评

暂无评论

3rd Workshop on Education for High Performance computing (EduHiPC - 2021)

3rd Workshop on Education for High Performance Computing (Ed...

引用

IEEE international conference on High Performance computing Workshops (HiPCW)

作者： Sheikh Ghafoor Sushil K. Prasad

ISBN: (纸本)9781665410380

High Performance computing (HPC) and, in general, parallel and distributed computing (PDC) is ubiquitous. Every computing device, from a smartphone to a supercomputer, relies on parallel processing. Compute clusters of multicore and manycore processors (CPUs and GPUs) are routinely used in many subdomains of computer science, such as data science, parallel machine learning and high performance computing. Therefore, it is important for every computing professional (and especially every programmer) to understand how parallelism and distributed computing affect problem solving. It is essential for educators to impart a range of PDC and HPC skills and knowledge at multiple levels within the curriculum of Computer Science (CS), Computer Engineering (CE), and related disciplines such as computational data science. Software industry and research laboratories require people with these skills, more so now. Therefore, they now engage in extensive on-the-job training. Additionally, rapid changes in hardware platforms, languages, and programming environments increasingly challenge educators to decide what to teach and how to teach it, in order to prepare students for careers that are increasingly likely to involve PDC and HPC. EduHiPC aims to provide a forum that brings together academia, industry, government, and non-profit organizations - especially from India, its vicinity, and Asia - for exploring and exchanging experiences and ideas about the inclusion of high-performance, parallel, and distributed computing into undergraduate and graduate curriculum of Computer Science, Computer Engineering, Computational Science, Computational Engineering, and computational courses for STEM and business and other non-STEM disciplines.

关键词： High Performance computing distributed computing PDC gene computer science Curriculum Nonprofit Organizations Education educators supercomputer Smartphone COMPUTER ENGINEERING Laboratory Research Multi-core processors HIGH-PERFORMANCE career

来源：评论

学校读者我要写书评

暂无评论

IMpart: A Partitioning-based parallel Approach to Accelerate Influence Maximization

IMpart: A Partitioning-based Parallel Approach to Accelerate...

引用

international conference on High Performance computing

作者： Reet Barik Marco Minutoli Mahantesh Halappanavar Ananth Kalyanaraman Washington State University Pullman WA Pacific Northwest National Laboratory Richland WA

Influence maximization (IM) is a fundamental operation among graph problems that involve simulating a stochastic diffusion process on real-world networks. Given a graph G(V, E), the objective is to identify a small set of key influential "seeds"— i.e., a fixed-size set of k nodes, which when influenced is likely to lead to the maximum number of nodes in the network getting influenced. The problem has numerous applications including (but not limited to) viral marketing in social networks, epidemic control in contact networks, and in finding influential proteins in molecular networks. Despite its importance, application of influence maximization at scale continues to pose significant challenges. While the problem is NP-hard, efficient approximation algorithms that use greedy hill climbing are used in practice. However those algorithms consume hours of multithreaded execution time even on modest-sized inputs with hundreds of thousands of nodes. In this paper, we present IMpart, a partitioning-based approach to accelerate greedy hill climbing based IM approaches on both shared and distributed memory computers. In particular, we present two parallel algorithms— one that uses graph partitioning (IMpart-metis) and another that uses community-aware partitioning (IMpart-gratis)— with provable guarantees on the quality of approximation. Experimental results show that our approaches are able to deliver two to three orders of magnitude speedup over a state-of-the-art multithreaded hill climbing implementation with negligible loss in quality. For instance, on one of the modest-sized inputs (Slashdot: 73K nodes; 905K edges), our partitioning-based shared memory implementation yields 4610× speedup, reducing the runtime from 9h 36m to 7 seconds on 128 threads. Furthermore, our distributed memory implementation enhances problem size reach to graph inputs with ×10 6 nodes and ×10 8 edges and enables sub-minute computation of IM solutions.

关键词： Proteins Privacy Runtime Social networking (online) Instruction sets Pipelines Memory management

来源：评论

学校读者我要写书评

暂无评论

DeepHop on Edge: Hop-by-hop Routing by distributed Learning with Semantic Attention 20

DeepHop on Edge: Hop-by-hop Routing by Distributed Learning ...

引用

49th international conference on parallel Processing (ICPP)

作者： He, Bo Wang, Jingyu Qi, Qi Sun, Haifeng Zhuang, Zirui Liu, Cong Liao, Jianxin Beijing Univ Posts & Telecommun Beijing Peoples R China China Mobile Res Inst Beijing Peoples R China

ISBN: (纸本)9781450388160

Multi-access Edge computing (MEC) and ubiquitous smart devices help serve end-users efficiently and optimally through providing emerging edge-deployed services. Meanwhile, heavy and time-varying traffic loads are produced in the edge network, so that an efficient traffic forwarding mechanism is required. In this paper, we propose a parallel and distributed learning approach, DeepHop, to adapt to the volatile environments and realize hop-by-hop routing. The Multi-Agent Deep Reinforcement Learning (MADRL) is used to alleviate the edge network congestion and maximize the utilization of network resources. DeepHop determines the routing among edge network nodes for heterogeneous types of traffic according to the current workload and capability. By joining with an attention mechanism, DeepHop obtains the semantics from the elements of the network state to help the agents learn the importance of each element on routing. Experiment results show that DeepHop achieves the increase of successfully transmitted packets by 15% compared with the state-of-the-art algorithms. Besides, DeepHop with an attention mechanism reduces convergence time by nearly half compared with the common-used structures of neural networks.

关键词： distributed routing wireless edge networks multi-agent reinforcement learning self-attention

来源：评论

学校读者我要写书评

暂无评论

Integration of Fog computing and Internet of Things: An Useful Overview 2nd

Integration of Fog Computing and Internet of Things: An Usef...

引用

2nd international conference on Recent Innovations in computing (ICRIC)

作者： Rekha, G. Tyagi, Amit Kumar Anuradha, Nandula Koneru Lakshmaiah Educ Fdn Dept Comp Sci & Engn Guntur 522502 Andhra Pradesh India Lingayas Vidyapeeth Dept Comp Sci & Engn Faridabad 121002 Haryana India

ISBN: (纸本)9783030294076;9783030294069

In the past decade, the evolution of computing has moved from distributed, parallel, grid, cloud, and now to fog computing. The massive amount of data generated by Internet of Things (IoT) devices is growing up exponentially. The flood of information (generated by those IoT/Internet-connected devices) becomes troublesome for data processing and analytical prediction functionality using cloud computation. Several problems have been investigated with cloud computing with respect to latency, limited bandwidth, low Internet connectivity, etc. Here, solution to such problems can be solved by introducing fog computing with powerful functionality of cloud framework, i.e., based on the deployment of fog nodes called microclouds at nearest edge of data sources. Fog computing for big data/IoT data analytics is in evolving phase and requires extensive research to produce more knowledge and smart decisions. This article discusses several basic facts related to fog commuting, challenges in fog computing and opportunities in the near future, in the context of fog big IoT data analytics. In addition, this work also emphasizes the key characteristics in some proposed research works, those make the fog computing as a suitable (useful) platform for new proliferating IoT devices, services, and applications. Most significant fog applications (e.g. healthcare monitoring, smart cities, connected vehicles, and smart grid, etc.) will be discussed here to create a well-organized green and quantum computing paradigm to support the next generation of IoT applications.

关键词： Internet of Things Cloud computing Fog computing Big data Data analytics

来源：评论

学校读者我要写书评

暂无评论

An A3C Deep Reinforcement Learning FPGA Accelerator based on Heterogeneous Compute Units

An A3C Deep Reinforcement Learning FPGA Accelerator based on...

引用

international conference on Communication Technology (ICCT)

作者： Ziyu Li Fen Ge Fang Zhou Ning Wu College of Electronic and Information Engineering Nanjing University of Aeronautics and Astronautics Nanjing China

Deep reinforcement leaning (DRL) has a great performance in intelligent decision-making question. As one of well-performance DRL algorithms, Asynchronous Advantage Actor-Critic (A3C) can make distributed agents work simultaneously to infer and train without experience pool. However, the multiple agents also bring complex deep neural network (DNN) computations in each agent which costs the almost time in A3C algorithm. In this paper, we propose a DRL FPGA accelerator based on heterogeneous compute units for A3C algorithm to reduce the DNN computing periods. According to A3C algorithm computing flow, we implement both inference and training steps on accelerator and pipeline their computations. In DNN forward propagation (FP) and backward propagation (BP) computing, the Multiply-ADDer-tree (MADD) structure with high input parallelism and Multiply-Accumulation (MAC) structure with high output parallelism are proposed to be employed, respectively. Heterogeneous computing method makes the weight parameters layout of inference and training consistent, and improves the access efficiency of on-chip memory. Experimental results show that our design achieves 40-times speedup in inference-training speedup compared to CPU, and 54-times speedup compared to GPU. Moreover, our heterogeneous computing method lead to better efficiency in memory accessing compared to exiting approaches.

关键词： Training Deep learning Accelerated aging Memory management Graphics processing units parallel processing Inference algorithms

来源：评论

学校读者我要写书评

暂无评论

Violence Detection In Videos via Motion-Guided Global and Local Views

Violence Detection In Videos via Motion-Guided Global and Lo...

引用

IEEE international conference on Data Science in Cyberspace (DSC)

作者： Ning Su Lijuan Sun Yutong Gao Jingchen Wu Xu Wu Key Laboratory of Trustworthy Distributed Computing and Service Ministry of Education School of Cyberspace Security BUPT School of Economics and Management Beijing University of Posts and Telecommunications Beijing China Beijing Key Lab of Traffic Data Analysis and Mining Beijing Jiaotong University Beijing China School of Computer Science (National Pilot Software Engineering School) BUPT

Video violence detection aims to locate the time window in which violent behavior occurs. Most methods focus on utilizing RGB features directly or only fusing RGB and audio features, ignoring the effective exploitation of motion information carried in optical flow. This lack of emphasis on motion information may impact the overall accuracy of violence detection. Moreover, we observe that videos contain strong local correlations, so it is insufficient to analyze only from a holistic perspective without capturing finer details. Therefore, in this paper, we design a novel Global-and-Local Cross-Modal Network (GL-CMN) for violence detection, which effectively integrates motion information and multi-granularity features from target videos. Specifically, we first propose a Motion-Guided Attention Module (MGAM) to obtain enhanced visual features by calibrating RGB features through optical flow features. Secondly, The enhanced features are simultaneously fed into two parallel branches of the network. The global branch fuses the visual and audio features into holistic representations. The local branch extracts multi-scale temporal dependencies through dilated convolutions. Experiments demonstrate that our method exhibits significant improvement compared to previous state-of-the-art methods on the XD-Violence dataset.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Resource Discovery Mechanisms in Shared computing Infrastructure: A Survey 4th

Resource Discovery Mechanisms in Shared Computing Infrastruc...

引用

4th international conference of Reliable Information and Communication Technology (IRICT)

作者： Alzboon, Mowafaq Salem Mahmuddin, M. Arif, Suki Jadara Univ POB 150459 Irbid 13115 Jordan Univ Utara Malaysia Sch Comp InterNetWorks Res Lab Sintok 06010 Kedah Malaysia

ISBN: (纸本)9783030335823;9783030335816

The increased number of computers, enlarged network bandwidth, more powerful computers, consumed resources and the acceptance of the Internet has driven the ongoing demand for new and better ways to execute huge problems in shared computing infrastructure such as grid and P2P computing. Resource discovery is extremely significant and challenging issues in grid and P2P. It is complex because resources are heterogeneous, dynamic, geographically distributed, manageability and autonomous. A well-organized resource discovery mechanism is the fundamental requirements for resource sharing infrastructure, as it supports and facilities the resource administration and scheduling of applications. In computing systems like grid, provide many resources across multiple administrative domains for the achievement of the goal. The major challenge faced by the system is to find the right resources on the network. In this paper, we study the resource discovery mechanisms that have been used in distributed computing systems so far. The mechanism for discovery of resource is divided into different types: centralized, decentralized, and hierarchical. We review the main developments in these categories and outline the new challenges. This paper also provides a discussion of the differences between the mechanisms considered for scalability, dynamism, reliability and real consultations as well as directions for future research.

关键词： grid computing Resource discovery 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500页 << < 474 475 476 477 478 479 480 481 482 483 > >>

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：