346 Hits in 5.7 sec

Xen-Based HPC: A Parallel I/O Perspective

Weikuan Yu, Jeffrey S. Vetter
2008 2008 Eighth IEEE International Symposium on Cluster Computing and the Grid (CCGRID)  
Virtualization using Xen-based virtual machine environment has yet to permeate the field of high performance computing (HPC).  ...  We have analyzed the overheads and migration costs for parallel I/O programs in a Xen-based virtual machine cluster.  ...  We carried out a detailed analysis of parallel I/O programs' virtualization overhead and migration cost.  ... 
doi:10.1109/ccgrid.2008.119 dblp:conf/ccgrid/YuV08 fatcat:gegu6vq4bva7pkisbmanot5iem

Making Wide-Area, Multi-site MPI Feasible Using Xen VM [chapter]

Masaki Tatezono, Naoya Maruyama, Satoshi Matsuoka
2006 Lecture Notes in Computer Science  
Our current work involves using Xen as the underlying virtual machine layer to implement such migration, along with performance-optimizing migration strategies-this particular paper deals with performance  ...  evaluations of MPI on Xen VMs including what are the possible performance hindrances, implications of migrations, as well as the effect of variations in latencies and bandwidth parameters as realized  ...  in part by the Ministry of Education, Culture, Sports, Science, and Technology, Grant-in-Aid for Scientific Research on Priority Areas, 18049028, 2006.  ... 
doi:10.1007/11942634_41 fatcat:5zk2aeq6kremjmtvsdllvfwaha

Characterizing the Performance of Parallel Applications on Multi-socket Virtual Machines

Khaled Z. Ibrahim, Steven Hofmeyr, Costin Iancu
2011 2011 11th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing  
Our results using MPI, UPC and OpenMP implementations of the NAS Parallel Benchmarks, running on Intel and AMD NUMA systems, indicate that applications observe an overall average performance degradation  ...  NUMA locality on current solutions (KVM and Xen) is enforced by pinning virtual machines to CPUs and providing NUMA aware allocation in hypervisors.  ...  Youssef et al [27] evaluate the impact of Xen on MPI performance and report a low overhead of virtualization.  ... 
doi:10.1109/ccgrid.2011.50 dblp:conf/ccgrid/IbrahimHI11 fatcat:ecki7jdvvfckfdjogvcthi6sju

Evaluate the Performance and Scalability of Image Deployment in Virtual Data Center [chapter]

Kejiang Ye, Xiaohong Jiang, Qinming He, Xing Li, Jianhai Chen
2010 Lecture Notes in Computer Science  
In this paper, we explore the performance and scalability issues for virtual machine deployment in a virtualized data center.  ...  (ii) More physical machines do not always benefit for some specific applications to support a fixed number of virtual machines.  ...  For example, if one parallel job needs 16 threads running simultaneously, we will create 16 virtual machines to support it with MPI communication between each virtual machine.  ... 
doi:10.1007/978-3-642-15672-4_32 fatcat:oornqoifrzhzvnb3ra2egdaoky

Dynamic Creation of BSP/CGM Clusters on Cloud Computing Platforms

Alessandro Kraemer, Junior Cesar de Oliveira, Fabio Andre Garaluz dos Santos, Ana Claudia Maciel, Alfredo Goldman, Daniel Cordeiro
2013 2013 Fourth International Conference on Emerging Intelligent Data and Web Technologies  
We show how to build and instantiate virtual machines templates for BSP/CGM applications that can be used on private cloud computing platforms.  ...  Cloud computing platforms have the potential to benefit scientific projects on all fields of knowledge.  ...  Our proposal is based on the usage of virtual machines templates optimized for a particular distributed programming model.  ... 
doi:10.1109/eidwt.2013.140 dblp:conf/eidwt/KraemerOSMGC13 fatcat:de44tnadcrgapluf74kz4ibggy

A fault-tolerant strategy for virtualized HPC clusters

John Paul Walters, Vipin Chaudhary
2008 Journal of Supercomputing  
Using VMWare Server, Xen, and OpenVZ we examine the suitability of full virtualization (VMWare), paravirtualization (Xen), and operating system-level virtualization (OpenVZ) in terms of network utilization  ...  , SMP performance, file system performance, and MPI scalability.  ...  We also acknowledge Minsuk 26 Cha, Salvatore Guercio Jr, and Steve Gallo for their contributions to the virtual machine evaluations.  ... 
doi:10.1007/s11227-008-0259-0 fatcat:aamobmotrvhphgvtnzuygfu2ti

Detailed author index

2007 2007 IEEE International Conference on Cluster Computing  
Management of Grid Services Panda, Dhabaleswar K. 11 High Performance Virtual Machine Migration with RDMA Over Modern Interconnects 159 Efficient Asynchronous Memory Copy Operations on Multi-Core  ...  Using Xen on InfiniBand Tomkins, James L. 50 Red Storm IO Performance Analysis Tu, Bibo 404 A Layered Design Methodology of Cluster System Stack Tufo, Henry M. 357 High Throughput Grid  ... 
doi:10.1109/clustr.2007.4629206 fatcat:dsvfpa7uffc75e4iotlu2vjrqe

Virtual Machine Performance upon Intensive Computations

B.O. Yenké, A. A. Abba Ari, C. Dibamou Mbeuyo, D. A. Voundi
2015 GSTF International Journal on Computing  
The Virtual Machine (VM) technology has increased considerably within the last two decades and the performance of VMs seems closest to the host machine.  ...  This paper presents the result of a comparison of the performance of the most commonly used VMs solutions: OpenVz, Linux-Vserver, LXC, XEN, KVM and VMware ESXi.  ...  The performance analysis is performed by deploying on VMs, one program which allows to stress the component that performance is analyzed.  ... 
doi:10.7603/s40601-014-0020-x fatcat:fcnnzlanvzbjnex67rgx3wbja4

Analyzing and Improving MPI Communication Performance in Overcommitted Virtualized Systems

Zhiyuan Shao, Qiang Wang, Xuejiao Xie, Hai Jin, Ligang He
2011 2011 IEEE 19th Annual International Symposium on Modelling, Analysis, and Simulation of Computer and Telecommunication Systems  
Studies revealed that the communication performance of the MPI library, which is widely used by the HPC applications, would suffer a high penalty when a physical host machine becomes overcommitted by virtual  ...  In this paper, we investigate the reasons behind the performance penalty, and propose a solution to improve the communication performance of running MPI applications in the overcommitted virtualized systems  ...  Among these virtualization technologies, the Xen hypervisor [4] , which allow users to execute hundreds of virtual machines on a single physical machine with low extra overhead, is widely adopted for  ... 
doi:10.1109/mascots.2011.27 dblp:conf/mascots/ShaoWXJH11 fatcat:5slsghqfwvajzdgflis3blry6i

High Performance Parallel Computing with Clouds and Cloud Technologies [chapter]

Jaliya Ekanayake, Geoffrey Fox
2010 Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering  
In this paper, we first discuss large scale data analysis using different MapReduce implementations and then, we present a performance analysis of high performance parallel applications on virtualized  ...  MPI.  ...  According to the Xen para-virtualization architecture [6] , domUs (VMs that run on top of Xen para-virtualization) are not capable of performing I/O operations by themselves.  ... 
doi:10.1007/978-3-642-12636-9_2 fatcat:bduic2a6srd2fafpofspohhbze

Cloud technologies for bioinformatics applications

Xiaohong Qiu, Jaliya Ekanayake, Scott Beason, Thilina Gunarathne, Geoffrey Fox, Roger Barga, Dennis Gannon
2009 Proceedings of the 2nd Workshop on Many-Task Computing on Grids and Supercomputers - MTAGS '09  
First we compare the performance of these cloud technologies using the above case and also compare them with traditional MPI implementation in one application.  ...  Finally we present a comparison of performance of the cloud technologies under virtual and non-virtual hardware platforms.  ...  on Xen virtual machines.  ... 
doi:10.1145/1646468.1646474 dblp:conf/sc/QiuEBGFBG09 fatcat:5sul5tdsvbhgvnoduzeehllt4m

Cloud Technologies for Bioinformatics Applications

J Ekanayake, T Gunarathne, J Qiu
2011 IEEE Transactions on Parallel and Distributed Systems  
First we compare the performance of these cloud technologies using the above case and also compare them with traditional MPI implementation in one application.  ...  Finally we present a comparison of performance of the cloud technologies under virtual and non-virtual hardware platforms.  ...  on Xen virtual machines.  ... 
doi:10.1109/tpds.2010.178 fatcat:lbxn7vfeurf6dn7oew7vptzq2a

Evaluation of messaging middleware for high-performance cloud computing

Roberto R. Expósito, Guillermo L. Taboada, Sabela Ramos, Juan Touriño, Ramón Doallo
2012 Personal and Ubiquitous Computing  
The analysis of the experimental results, confronted with a similar testbed, has shown the significant impact that virtualized environments still have on communications performance, which demands more  ...  In this scenario, the performance of communications depends both on the network fabric and its efficient support in virtualized environments, which ultimately determines the overall system performance.  ...  Then, the significant impact of virtualized communication overhead on the scalability of representative parallel codes, NAS Parallel Benchmarks (NPB) kernels [6] , has been assessed.  ... 
doi:10.1007/s00779-012-0605-3 fatcat:6izn55mtqrcq5p2akp3qu4obbi

Building a Private HPC Cloud for Compute and Data-Intensive Applications

Moussa Taifi, Abdallah Khreishah, Justin Y. Shi
2013 International Journal on Cloud Computing Services and Architecture  
In addition, we show that even if the overhead of virtualization is present, efficient scalability for virtual clusters can be achieved by understanding the effects of virtualization overheads on various  ...  The existing HPC programming models were designed for dedicated homogeneous parallel processors. The HPC cloud is typically heterogeneous and shared.  ...  ACKNOWLEDGEMENTS The authors would like Thomas Stauffer, AakashPradeep and Dr.Jie Wu for useful feedback and suggestions, as well operational support during the design and deployment phases of the private  ... 
doi:10.5121/ijccsa.2013.3201 fatcat:73pwlzqdgnavlp6rjhs2yjtycq

Performance analysis of virtualized environments using HPC Challenge benchmark suite and Analytic Hierarchy Process

Reza Bakhshayeshi, Mohammad Kazem Akbari, Morteza Sargolzaei Javan
2014 2014 Iranian Conference on Intelligent Systems (ICIS)  
In this paper we are goi performance of some virtualized environ VMware ESXi, KVM, Xen, Oracle VirtualB Workstation using HPC Challenge (HPCC) be Open MPI in order to represent solutions for v of cloud  ...  Steep improvement of cloud com years, persuaded experts admit it as a suitabl substitution for traditional computing method and more organizations are getting used to cre on the other hand, public clouds  ...  shown better 5 and 0.29 GB/s in B/s, which is only nd Xen performed 0.72 and 53.29 μs Bandwidth (b_eff) benchmark on a single machin and latency.  ... 
doi:10.1109/iraniancis.2014.6802585 fatcat:2sejep2dgvdbvhte5ft5zyzyku
« Previous Showing results 1 — 15 out of 346 results