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

14,260 篇 会议
263 篇 期刊文献
118 册 图书
3 篇 学位论文

馆藏范围

14,644 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

8,858 篇 工学
- 7,943 篇 计算机科学与技术...
- 3,876 篇 软件工程
- 1,708 篇 电气工程
- 1,258 篇 信息与通信工程
- 739 篇 控制科学与工程
- 347 篇 电子科学与技术（可...
- 240 篇 机械工程
- 164 篇 动力工程及工程热...
- 143 篇 仪器科学与技术
- 106 篇 生物工程
- 105 篇 石油与天然气工程
- 93 篇 材料科学与工程（可...
- 84 篇 土木工程
- 80 篇 建筑学
- 74 篇 生物医学工程（可授...
- 65 篇 力学（可授工学、理...
- 60 篇 化学工程与技术
- 59 篇 交通运输工程
- 58 篇 网络空间安全
2,007 篇 理学
- 1,502 篇 数学
- 279 篇 系统科学
- 241 篇 物理学
- 222 篇 统计学（可授理学、...
- 132 篇 生物学
- 77 篇 化学
1,164 篇 管理学
- 809 篇 管理科学与工程(可...
- 437 篇 图书情报与档案管...
- 436 篇 工商管理
110 篇 医学
- 97 篇 临床医学
86 篇 经济学
- 86 篇 应用经济学
62 篇 法学
48 篇 农学
35 篇 教育学
21 篇 文学
6 篇 军事学
4 篇 艺术学

主题

1,419 篇 distributed comp...
1,292 篇 parallel process...
884 篇 concurrent compu...
653 篇 distributed comp...
594 篇 computer science
590 篇 computer archite...
512 篇 computational mo...
502 篇 application soft...
475 篇 parallel process...
412 篇 distributed data...
382 篇 scalability
363 篇 parallel program...
341 篇 parallel algorit...
321 篇 hardware
304 篇 fault tolerance
280 篇 computer network...
249 篇 algorithm design...
236 篇 processor schedu...
225 篇 runtime
215 篇 message passing

机构

47 篇 national laborat...
45 篇 institute of par...
30 篇 univ stuttgart i...
28 篇 univ stuttgart i...
26 篇 natl univ def te...
24 篇 institute for pa...
23 篇 college of compu...
23 篇 institute of par...
22 篇 national laborat...
22 篇 institute of par...
20 篇 institute for pa...
19 篇 school of comput...
18 篇 tech univ berlin
18 篇 department of co...
17 篇 univ stuttgart i...
17 篇 department of co...
16 篇 natl univ def te...
15 篇 school of comput...
15 篇 shanghai jiao to...
15 篇 institute of par...

作者

47 篇 kurt rothermel
31 篇 mitschang bernha...
30 篇 duerr frank
24 篇 m. takizawa
24 篇 hirmer pascal
23 篇 chen haibo
22 篇 liu jie
21 篇 li dongsheng
19 篇 dongsheng li
19 篇 stach christoph
18 篇 fahringer thomas
18 篇 koldehofe boris
18 篇 wang yijie
17 篇 bernhard mitscha...
16 篇 thamsen lauritz
15 篇 jack dongarra
14 篇 rajkumar buyya
14 篇 dou yong
14 篇 yijie wang
14 篇 wang wei

语言

14,428 篇 英文
158 篇 其他
49 篇 中文
11 篇 俄文
1 篇 德文
1 篇 法文
1 篇 土耳其文

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

共 14644 条记录，以下是251-260 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：

Research on Optimization of Communication Technology Based on Deep Learning 3

Research on Optimization of Communication Technology Based o...

引用

3rd international conference on Electronics and Information Technology, EIT 2024

作者： Zhang, Zhaoxiang China Mobile Group Device Co. Ltd BeiJing100053 China

ISBN: (数字)9798350369151

ISBN: (纸本)9798350369151

distributed deep learning systems commonly use synchronous data parallelism to train models. However, communication overhead can be costly in distributed environments with limited communication bandwidth. To reduce communication overhead, an intuitive approach is to increase the communication interval. However, increasing the communication interval often affects the convergence speed of the model, requiring more epochs to train the model to the target accuracy, thereby reducing the statistical efficiency of the training algorithm. To address these issues in distributed synchronous data parallel training algorithms and communication interval selection methods, this paper proposes a training algorithm that combines skip communication strategies and correction techniques to ensure low communication overhead and high statistical efficiency. The training algorithm maintains a small batch size through local updates in each training process and employs correction techniques to reduce the divergence among individual local models, thereby ensuring high statistical efficiency. At the same time, the training algorithm utilizes a skip communication strategy to update the global model, meaning that the global model is not updated with every iteration, but rather updated once every few iterations. This reduces the frequency of communication, ensuring low communication overhead. Experimental results show that this training algorithm reduces total training time by 88.9%, 74.9%, 34.1%, and 82.4% compared to SSGD, SkipSSGD, LocalSGD, and SMA, respectively. © 2024 IEEE.

关键词： Training Deep learning distributed databases Bandwidth parallel processing Data models Communications technology Information technology Optimization Convergence

来源：评论

学校读者我要写书评

暂无评论

Markov Stochastic Processes Application Tools to Improve the Characteristics of distributed systems Synchronization Procedures 5

Markov Stochastic Processes Application Tools to Improve the...

引用

5th international conference on Control systems, Mathematical Modeling, Automation and Energy Efficiency, SUMMA 2023

作者： Azarnova, Tatyana Vasilyevna Polukhin, Pavel Valerievich Kashirina, Irina Leonidovna Voronezh State University Applied Mathematics Informatics and Mechanics Voronezh Russia

ISBN: (纸本)9798350309126

Appling mathematical modeling methods for analyses synchronization processes of distributed data processing systems makes it possible to significantly optimize these processes and guarantee the required level of consistency. To analyze stochastic distributed synchronization procedures, mathematical modeling tools are needed to adequately reflect their stochastic nature and form a probabilistic time characteristics assessment of the shared resource ownership distributed between the parallel processes. The research carried out within the current paper shows that stochastic modeling tools are able to solve a number of complex problems in this area and in particular to adapt synchronization algorithms for use in heterogeneous computing systems with a different set of hardware components and providing an acceptable synchronization time for a large amount of data. The paper essentially analyzes Markov synchronization models with group maintenance and considers tools for bringing these models to the case of arbitrary service time. © 2023 IEEE.

关键词： Random processes

来源：评论

学校读者我要写书评

暂无评论

Accelerating I/O in distributed Data Processing systems with Apache Arrow CHFS 25

Accelerating I/O in Distributed Data Processing Systems with...

引用

25th IEEE international conference on Cluster Computing (CLUSTER)

作者： Koyama, Sohei Hiraga, Kohei Tatebe, Osamu Univ Tsukuba Tsukuba Ibaraki Japan

ISBN: (纸本)9798350370621

In recent years, distributed data-processing frameworks have become popular for processing big data. However, in an HPC, where the computation and storage nodes are separated, the bandwidth between the computation and storage components is small, causing a reduction in data processing throughput. Therefore, in this paper, data were stored on the computation node to solve the data processing throughput degradation. We propose an I/O acceleration method that integrates Apache Arrow and CHFS. It leverages non-volatile memory, a state-of-the-art storage device, via CHFS and leverages CHFS from a distributed data processing framework via Apache Arrow's abstract file system API. The evaluation results showed that the system achieved up to 11.60 times higher bandwidth than when reading data from the parallel file system Lustre. This study also compared with Apache Arrow with BeeOND and UnifyFS, other ad hoc filesystems. The proposed Apache Arrow CHFS showed up to 1.67x/1.23x better write performance. The implementation is published at https://***/tsukuba-hpcs/arrow-chfs

关键词： parallel file system distributed data processing HPC

来源：评论

学校读者我要写书评

暂无评论

Accelerating BFT Database with Transaction Reconstruction

Accelerating BFT Database with Transaction Reconstruction

引用

1st international conference on Smart Energy systems and Artificial Intelligence (SESAI)

作者： Kida, Aoi Kawashima, Hideyuki Keio Univ Yokohama Kanagawa Japan

ISBN: (纸本)9798350364613;9798350364606

Data stores utilized in modern data-intensive applications are expected to demonstrate rapid read and write capabilities and robust fault tolerance. Byzantine fault-tolerant database (BFT database) can execute transactions concurrently and tolerate arbitrary faults (Byzantine fault). We consider cryptographic and communication processing as performance bottlenecks in the transaction processing of BFT databases. This paper presents a transaction reconstruction method, reconstructing a single transaction from multiple transactions to streamline cryptographic and communication processes. We evaluated the proposed method with Basil (state-of-the-art BFT database) in experiments. In an environment where nodes are geographically centralized, the proposed method demonstrates up to approximately 2.5 times higher throughput and reduces latency by up to about 30% than vanilla Basil. In an environment where nodes are geographically distributed, the proposed method demonstrates up to approximately 50 times higher throughput and reduces latency by up to about 75% than vanilla Basil.

关键词： Byzantine fault tolerance distributed database Transaction processing

来源：评论

学校读者我要写书评

暂无评论

parallel Maximum Cardinality Matching for General Graphs on GPUs

Parallel Maximum Cardinality Matching for General Graphs on ...

引用

1st international conference on Smart Energy systems and Artificial Intelligence (SESAI)

作者： Schwing, Gregory Grosu, Daniel Schwiebert, Loren Wayne State Univ Dept Comp Sci Detroit MI 48202 USA

ISBN: (纸本)9798350364613;9798350364606

The matching problem formulated as Maximum Cardinality Matching in General Graphs (MCMGG) finds the largest matching on graphs without restrictions. The Micah-Vazirani algorithm has the best asymptotic complexity for solving MCMGG when the graphs are sparse. parallelizing matching in general graphs on the GPU is difficult for multiple reasons. First, the augmenting path procedure is highly recursive, and NVID1A GPUs use registers to store kernel arguments, which eventually spill into cached device memory, with a performance penalty. Second, extracting parallelism from the matching process requires partitioning the graph to avoid any overlapping augmenting paths. We propose an implementation of the Micali-Vazirani algorithm which identifies bridge edges using threadparallel breadth-first search, followed by block-parallel path augmentation and blossom contraction. Augmenting path and Union find methods were implemented as stack-based iterative methods, with a stack allocated in shared memory. Our experimentation shows that compared to the serial implementation, our approach results in up to 15-fold speed-up for very sparse regular graphs, up to 5 -fold slowdown for denser regular graphs, and finally a 50-fold slowdown for power-law distributed Kronecker graphs. This implementation has been open-sourced for further research on developing combinatorial graph algorithms on GPUs.

关键词： matching general graphs Micali-Vazirani algorithm CUDA GPU

来源：评论

学校读者我要写书评

暂无评论

Research on the Fusion Method of distributed Photovoltaic Power Flow and Information Flow Based on HPLC 4

Research on the Fusion Method of Distributed Photovoltaic Po...

引用

4th international conference on Information Science, parallel and distributed systems, ISPDS 2023

作者： Li, Bo Shi, Zhan Deng, Xiaozhi Yang, Zhihua Wang, Xiuzhu Electric Power Dispatching Control Center of Guangdong Power Grid Co. Ltd. Guangdong Guangzhou510600 China Guangdong Electric Power Communication Technology Co. Ltd. Guangdong Guangzhou510600 China

ISBN: (纸本)9798350337181

distributed photovoltaic systems are a recently developed form of distributed power generation that offer the benefits of being both environmentally friendly and highly *** power demand continues to rise and the importance of protecting the environment becomes more evident, increasing distributed photovoltaic capacity has become an important development direction. To enable the distributed photovoltaic power generation system to efficiently connect to the power grid, this paper proposes a distributed photovoltaic power flow and information flow fusion method based on power line carrier communication technology. Power line carrier communication is categorized based on voltage levels, while low voltage PLC technology is classified based on its frequency band characteristics, it is divided into broadband PLC and narrowband PLC. To address random signal errors caused by the noise characteristics of OFDM multi-carrier modulation technology, an anti-interference channel coding approach is proposed. Additionally, this study focuses on the preprocessing of distributed photovoltaic information transmitted to the main station through HPLC, including data cleaning, integration, conversion, and protocol adaptation techniques, and the data is mined and analyzed to improve the intelligent level of distributed photovoltaic access to the power grid. © 2023 IEEE.

关键词： Carrier transmission on power lines

来源：评论

学校读者我要写书评

暂无评论

REVENUE FORECASTING USING distributed MACHINE LEARNING IN ONLINE ADVERTISING systems

REVENUE FORECASTING USING DISTRIBUTED MACHINE LEARNING IN ON...

引用

2023 IEEE international conference on Research Methodologies in Knowledge Management, Artificial Intelligence and Telecommunication Engineering, RMKMATE 2023

作者： Murugan, P. Esakkiammal, S. Kanagavalli, N. Priya, P. Krishna Martis, Jason Elroy Kavitha, P. Pallavaram Tamilnadu Chennai India Department of Library Central University of Tamil Nadu Neelakudi Tamilnadu Thiruvarur India Department of CSE Rajalakshmi Institute of Technology Kuthambakkam Tamilnadu Chennai India KL Business School KL Education Foundation Guntur Andrha Pradesh Vaddeswaram India Department of Information Science and Engineering NMAM Institute of Technology Nitte Deemed to be University Karnataka Karkala India Department of Computer Science and Engineering R.M.K. Engineering College Tamilnadu India

ISBN: (纸本)9798350305708

This research delves into the utilization of distributed machine learning methods for revenue forecasting in the realm of online advertising systems. As the domain of digital advertising continues to expand rapidly, the accurate prediction of revenue becomes indispensable for optimizing resource allocation and making well-informed decisions. Conventional approaches frequently encounter difficulties in managing the sheer volume and intricacy of advertising data. In contrast, distributed machine learning harnesses the capabilities of parallel processing and distributed computing to efficiently process and analyze large datasets. This investigation explores diverse distributed machine learning algorithms, including gradient boosting, random forests, and neural networks, within the context of revenue forecasting. The research assesses their performance, scalability, and precision in comparison to traditional techniques. Through empirical experiments and case studies, we showcase the potential of distributed machine learning to elevate the accuracy of revenue forecasting in online advertising systems, ultimately contributing to more informed business strategies and enhanced revenue generation. © 2023 IEEE.

关键词： algorithm scalability distributed machine learning online advertising systems parallel processing revenue forecasting

来源：评论

学校读者我要写书评

暂无评论

Detailed Analysis and Optimization of Irregular-Shaped Matrix Multiplication on Multi-Core DSPs 24

Detailed Analysis and Optimization of Irregular-Shaped Matri...

引用

53rd international conference on parallel Processing (ICPP)

作者： Mo, Haotian Wang, Qinglin Liao, Linyu Li, Biao Chi, Lihua Liu, Jie Natl Univ Def Technol Lab Digitizing Software Frontier Equipment Changsha Peoples R China Natl Univ Def Technol Natl Key Lab Parallel & Distributed Comp Changsha Peoples R China Hunan GuoKe Computil Technol Co Ltd Changsha Peoples R China

ISBN: (纸本)9798400717932

Irregular-shaped General Matrix Multiplication (GEMM) is extensively used in diverse workloads, such as scientific simulation and deep learning. In response to energy efficiency constraints, low-power multi-core digital signal processors (DSPs) have emerged as a viable alternative architecture in HPC systems. This study examines the performance of existing GEMM implementations working on irregular-shaped matrices and observes sub-optimal outcomes due to deficiencies in memory optimization and core-level parallelism extraction. For multi-core DSPs in FT-M7032, a CPU-DSP heterogeneous processor for HPC, we introduce dspIMM - a new multi-core parallel implementation for irregular-shaped matrix multiplications. dspIMM incorporates a new loop ordering, stack-space optimization, multi-dimensional core-level parallelization, a communication-computation overlap implementation with data prefetch across loops, and blocking optimization. These optimizations effectively enhance memory access and the core-level parallelism in irregular-shaped GEMMs. Experimental results demonstrate that the proposed communication-computation overlap optimization achieves the highest performance improvement in dspIMM, and the average speedup of dspIMM over previous implementations finally achieves up to 3.34 times.

关键词： Matrix-matrix multiplication Irregular-shaped matrix DSPs parallel algorithm Performance optimization

来源：评论

学校读者我要写书评

暂无评论

SeqDLM: A Sequencer-Based distributed Lock Manager for Efficient Shared File Access in a parallel File System

SeqDLM: A Sequencer-Based Distributed Lock Manager for Effic...

引用

international conference for High Performance Computing, Networking, Storage and Analysis (HPC)

作者： Chen, Qi Ma, Shaonan Chen, Kang Ma, Teng Liu, Xin Chen, Dexun Wu, Yongwei Chen, Zuoning Tsinghua Univ Beijing Peoples R China Alibaba Inc Hangzhou Peoples R China Natl Supercomp Ctr Wuxi Wuxi Peoples R China Chinese Acad Engn Beijing Peoples R China

ISBN: (纸本)9781665454445

distributed locks are used to guarantee the distributed client-cache coherence in parallel file systems. However, they lead to poor performance in the case of parallel writes under high-contention workloads. We analyze the distributed lock manager and find out that lock conflict resolution is the root cause of the poor performance, which involves frequent lock revocations and slow data flushing from client caches to data servers. We design a distributed lock manager named SeqDLM by exploiting the sequencer mechanism. SeqDLM mitigates the lock conflict resolution overhead using early grant and early revocation while keeping the same semantics as traditional distributed locks. To evaluate SeqDLM, we have implemented a parallel file system called ccPFS using both SeqDLM and traditional distributed locks. Evaluations on 96 nodes show SeqDLM outperforms the traditional distributed locks by up to 10.3x for high-contention parallel writes on a shared file with multiple stripes.

关键词： high performance computing file systems cache coherence distributed lock sequencer

来源：评论

学校读者我要写书评

暂无评论

OSDP: Optimal Sharded Data parallel for distributed Deep Learning 32

OSDP: Optimal Sharded Data Parallel for Distributed Deep Lea...

引用

32nd international Joint conference on Artificial Intelligence (IJCAI)

作者： Jiang, Youhe Fu, Fangcheng Miao, Xupeng Nie, Xiaonan Cui, Bin Peking Univ Sch CS Beijing Peoples R China Peking Univ Key Lab High Confidence Software Technol MOE Beijing Peoples R China Carnegie Mellon Univ Comp Sci Dept Pittsburgh PA USA Peking Univ Qingdao Inst Computat Social Sci Qingdao Peoples R China

ISBN: (纸本)9781956792034

Large-scale deep learning models contribute to significant performance improvements on varieties of downstream tasks. Current data and model parallelism approaches utilize model replication and partition techniques to support the distributed training of ultra-large models. However, directly deploying these systems often leads to sub-optimal training efficiency due to the complex model architectures and the strict device memory constraints. In this paper, we propose Optimal Sharded Data parallel (OSDP), an automated parallel training system that combines the advantages from both data and model parallelism. Given the model description and the device information, OSDP makes trade-offs between the memory consumption and the hardware utilization, thus automatically generates the distributed computation graph and maximizes the overall system throughput. In addition, OSDP introduces operator splitting to further alleviate peak memory footprints during training with negligible overheads, which enables the trainability of larger models as well as the higher throughput. Extensive experimental results of OSDP on multiple different kinds of large-scale models demonstrate that the proposed strategy outperforms the state-of-the-art in multiple regards.

关键词： Personnel training

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 << < 22 23 24 25 26 27 28 29 30 31 > >>

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：