2015 IEEE International Conference on Cluster Computing最新文献_第10页

Expressing Parallelism on Many-Core for Deterministic Discrete Ordinates Transport 确定性离散坐标传输的多核并行性表示

2015 IEEE International Conference on Cluster Computing Pub Date : 2015-09-08 DOI: 10.1109/CLUSTER.2015.127

Tom Deakin, Simon McIntosh-Smith, W. Gaudin

引用次数: 4

The Cost of Synchronizing Imbalanced Processes in Message Passing Systems 消息传递系统中同步不平衡进程的代价

2015 IEEE International Conference on Cluster Computing Pub Date : 2015-09-08 DOI: 10.1109/CLUSTER.2015.63

I. Peng, S. Markidis, E. Laure

{"title":"The Cost of Synchronizing Imbalanced Processes in Message Passing Systems","authors":"I. Peng, S. Markidis, E. Laure","doi":"10.1109/CLUSTER.2015.63","DOIUrl":"https://doi.org/10.1109/CLUSTER.2015.63","url":null,"abstract":"Synchronization in message passing systems is achieved by communication among processes. System and architectural noise and different workloads cause processes to be imbalanced and to reach synchronization points at different time. Thus, both communication and imbalance impact the synchronization performance. In this paper, we study the algorithmic properties that allow the communication in synchronization to absorb the initial imbalance among processes. We quantify the imbalance absorption properties of different barrier algorithms using a LogP Monte Carlo simulator. We found that linear and f-way tournament barriers can absorb up to 95% of random exponential imbalance with the standard deviation equal to the communication time for one message. Dissemination, butterfly and pairwise exchange barriers, on the other hand, do not absorb imbalance but can effectively bound the post-barrier imbalance. We identify that synchronization transits from communication-dominated to imbalance-dominated when the standard deviation of imbalance distribution is more than twice the communication time for one message. In our study, f-way tournament barriers provided the best imbalance absorption rate and convenient communication time.","PeriodicalId":187042,"journal":{"name":"2015 IEEE International Conference on Cluster Computing","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-09-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123525958","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 11

Distributed-Memory Algorithms for Maximal Cardinality Matching Using Matrix Algebra 基于矩阵代数的最大基数匹配分布式存储算法

2015 IEEE International Conference on Cluster Computing Pub Date : 2015-09-08 DOI: 10.1109/CLUSTER.2015.62

A. Azad, A. Buluç

引用次数: 6

Ensuring Data Durability with Increasingly Interdependent Content 通过日益相互依赖的内容确保数据的持久性

2015 IEEE International Conference on Cluster Computing Pub Date : 2015-09-08 DOI: 10.1109/CLUSTER.2015.33

Veronica Estrada Galinanes, P. Felber

引用次数: 4

Detecting Thread-Safety Violations in Hybrid OpenMP/MPI Programs 在混合OpenMP/MPI程序中检测线程安全违规

2015 IEEE International Conference on Cluster Computing Pub Date : 2015-09-08 DOI: 10.1109/CLUSTER.2015.70

Hongyi Ma, Liqiang Wang, K. Krishnamoorthy

引用次数: 12

Scaling Data Intensive Physics Applications to 10k Cores on Non-dedicated Clusters with Lobster 在非专用集群上使用Lobster将数据密集型物理应用扩展到10k核

2015 IEEE International Conference on Cluster Computing Pub Date : 2015-09-08 DOI: 10.1109/CLUSTER.2015.53

A. Woodard, M. Wolf, C. Müller, N. Valls, Benjamín Tovar, P. Donnelly, Peter Ivie, K. H. Anampa, P. Brenner, D. Thain, K. Lannon, M. Hildreth

引用次数: 11

Can Cloud Service Get His Family? A Step Towards Service Family Detecting 云服务能得到他的家人吗?迈向服务家族检测的一步

2015 IEEE International Conference on Cluster Computing Pub Date : 2015-09-08 DOI: 10.1109/CLUSTER.2015.80

Xinkui Zhao, Jianwei Yin, Chen Zhi, Pengxiang Lin, Zuoning Chen

引用次数: 0

RDMA-Based Direct Transfer of File Data to Remote Page Cache 基于rdma的文件数据直接传输到远程页面缓存

2015 IEEE International Conference on Cluster Computing Pub Date : 2015-09-08 DOI: 10.1109/CLUSTER.2015.40

Shin Sasaki, Kazushi Takahashi, Y. Oyama, O. Tatebe

{"title":"RDMA-Based Direct Transfer of File Data to Remote Page Cache","authors":"Shin Sasaki, Kazushi Takahashi, Y. Oyama, O. Tatebe","doi":"10.1109/CLUSTER.2015.40","DOIUrl":"https://doi.org/10.1109/CLUSTER.2015.40","url":null,"abstract":"The performance of a distributed file system significantly affects data-intensive applications that frequently execute I/O operations on large amounts of data. Although many modern distributed file systems are geared to provide highly efficient I/O performance, their operations are nonetheless affected by runtime overhead in data transfer between client nodes and I/O servers. A large part of the overhead is caused by memory copies executed by the client interface using the FUSE framework or a special kernel module. In this paper, we propose a method based on InfiniBand RDMA that improves data transfer performance between client and server in a distributed file system. The major characteristic of the method is that it transfers file data directly from a server's memory to the page cache of a client node. The method minimizes memory copies that are otherwise executed in the client interface or the operating system kernel. We implemented the proposed method in the Gfarm distributed file system and tested it using I/O benchmark software and real applications. The experimental results showed that our method effected a performance improvement of up to 78.4% and 256.0% in sequential and random file reads, respectively, and an improvement of up to 6.3% in data-intensive applications.","PeriodicalId":187042,"journal":{"name":"2015 IEEE International Conference on Cluster Computing","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-09-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123909547","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 3

VEF Traces: A Framework for Modelling MPI Traffic in Interconnection Network Simulators VEF跟踪:互连网络模拟器中MPI流量建模的框架

2015 IEEE International Conference on Cluster Computing Pub Date : 2015-09-08 DOI: 10.1109/CLUSTER.2015.141

Francisco J. Andújar, Juan A. Villar, J. L. Sánchez, F. J. Alfaro, J. Escudero-Sahuquillo

{"title":"VEF Traces: A Framework for Modelling MPI Traffic in Interconnection Network Simulators","authors":"Francisco J. Andújar, Juan A. Villar, J. L. Sánchez, F. J. Alfaro, J. Escudero-Sahuquillo","doi":"10.1109/CLUSTER.2015.141","DOIUrl":"https://doi.org/10.1109/CLUSTER.2015.141","url":null,"abstract":"Simulation is often used to evaluate the behaviour and measure the performance of computing systems. Specifically, in high-performance interconnection networks, the simulation has been extensively considered to verify the behaviour of the network itself and to evaluate its performance. In this context, network simulation must be fed with network traffic, also referred to as network workload, whose nature has been traditionally synthetic. These workloads can be used for the purpose of driving studies on network performance, but often such workloads are not accurate enough if a realistic evaluation is pursued. For this reason, other non-synthetic workloads have gained popularity over last decades since they are best to capture the realistic behaviour of existing applications. In this paper, we present the VEF traces framework, a self-related trace model, and all their associated tools. The main novelty of this framework is that, unlike existing ones, it does not provide a network simulation framework, but only offers an MPI task simulation framework, which allows one to use the MPI-based network traffic by any third-party network simulator, since this framework does not depend on any specific simulation platform.","PeriodicalId":187042,"journal":{"name":"2015 IEEE International Conference on Cluster Computing","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-09-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125067840","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 18

Performance Evaluation of Unstructured Mesh Physics on Advanced Architectures 非结构化网格物理在高级体系结构上的性能评估

2015 IEEE International Conference on Cluster Computing Pub Date : 2015-09-08 DOI: 10.1109/CLUSTER.2015.126

C. Ferenbaugh

引用次数: 0