Filters








348 Hits in 3.3 sec

A Component Architecture for LAM/MPI [chapter]

Jeffrey M. Squyres, Andrew Lumsdaine
2003 Lecture Notes in Computer Science  
To better manage the ever increasing complexity of LAM/MPI, we have created a lightweight component architecture for it that is specifically designed for high-performance message passing.  ...  This paper describes the basic design of the component architecture, as well as some of the particular component instances that constitute the latest release of LAM/MPI.  ...  Component Architecture The LAM/MPI component architecture supports four major types of components [8] .  ... 
doi:10.1007/978-3-540-39924-7_52 fatcat:m4jgyxo3qjdujcr2c57qvdjmq4

Local Area Multicomputer (LAM -MPI)

Athanasios I. Margaris
2013 Computer and Information Science  
support for checkpoint/restart functionality and they are used by the LAM-MPI commands as well as the MPI processes.  ...  These two modules allow the application programmers to design and implement collective algorithms without any knowledge of the LAM-MPI internal details. • cr SSI modules: the modules of this type provide  ...  The Future of LAM-MPI LAM-MPI served as a platform for the development of parallel applications for a long time period leading to new ideas and parallel programming techniques.  ... 
doi:10.5539/cis.v6n2p1 fatcat:37jlt6ggxvh67m3a6gg7du5ixi

The Lam/Mpi Checkpoint/Restart Framework: System-Initiated Checkpointing

Sriram Sankaran, Jeffrey M. Squyres, Brian Barrett, Vishal Sahay, Andrew Lumsdaine, Jason Duell, Paul Hargrove, Eric Roman
2005 The international journal of high performance computing applications  
Experimental results show negligible communication performance impact due to the incorporation of the checkpoint support capabilities into LAM/MPI.  ...  To address these issues, we present the design and implementation of a system for providing coordinated checkpointing and rollback recovery for MPI-based parallel applications.  ...  Brian Barrett was supported by a Department of Energy High Performance Computer Science fellowship.  ... 
doi:10.1177/1094342005056139 fatcat:eactszrrhncorlr4lu2f3hagla

A Job Pause Service under LAM/MPI+BLCR for Transparent Fault Tolerance

Chao Wang, Frank Mueller, Christian Engelmann, Stephen L. Scott
2007 2007 IEEE International Parallel and Distributed Processing Symposium  
Instead of job restart, we have developed a transparent mechanism for job pause within LAM/MPI+BLCR.  ...  a BLCR enhancement for job pause.  ...  Enhancements to LAM/MPI include (1) support of scalable group communication with fluctuating number of nodes, (2) transparent coordinated checkpointing, (3) reuse of network connections upon failures for  ... 
doi:10.1109/ipdps.2007.370307 dblp:conf/ipps/WangMES07 fatcat:ooawhnl7wvcjfbs6hl7bawldve

A comparative study on performance of MPICH, LAM/MPI and PVM on a Linux cluster over Fast Ethernet

Nguyễn Hải Châu
2012 Journal of Computer Science and Cybernetics  
Trong bai nay, chung toi dira ra Slr so sanh hieu nang ctia cac phan mern cai d~t cac giao tlnrc MPI va PVM: MPICH 1.2.1, LAM/MPI 6.3.2 va PVM 3.4.2 tren cum may tinh Linux dtro'c Ht n5i qua mang Fast  ...  In this paper, we give a practical comparative study on the performance of MPICH 1.2.1, LAM/MPI6.3.2 and PVM 3.4.2 implementations of the MPI and PVM protocols, on a Linux cluster over our Fast Ethernet  ...  Nguyen Trong Dung (JAIST) for their supports and advices.  ... 
doi:10.15625/1813-9663/17/3/2623 fatcat:u2lzay3xkbcx7gwjj7ypivv26u

Analysis of the Component Architecture Overhead in Open MPI [chapter]

B. Barrett, J. M. Squyres, A. Lumsdaine, R. L. Graham, G. Bosilca
2005 Lecture Notes in Computer Science  
Component architectures provide a useful framework for developing an extensible and maintainable code base upon which largescale software projects can be built.  ...  The Open MPI project is creating a new implementation of the Message Passing Interface standard, based on a custom component architecture -the Modular Component Architecture (MCA) -to enable straightforward  ...  Acknowledgments This work was supported by a grant from the Lilly Endowment and National Science Foundation grants NSF-0116050, EIA-0202048 and ANI-0330620.  ... 
doi:10.1007/11557265_25 fatcat:zbdme4qnu5g7jkonrx4jck5zt4

Design of a VIA based communication protocol for LAM/MPI suite

M. Bertozzi, M. Panella, M. Reggiani
Proceedings Ninth Euromicro Workshop on Parallel and Distributed Processing  
The reported results, referring to a software VIA implementation for Fast Ethernet networks, exhibits a significant reduction in latency time of LAM/MPI based on VIA with respect to the same library based  ...  To validate the goodness of the proposed protocol, a new communication layer based on VIA has been introduced in the LAM/MPI suite.  ...  Transmission times for LAM/MPI on VIA or TCP/IP.  ... 
doi:10.1109/empdp.2001.904967 dblp:conf/pdp/BertozziPR01 fatcat:rylafscnffblhfwfbugi4amqgy

An MPI Implementation on the Top of the Virtual Interface Architecture [chapter]

Massimo Bertozzi, Franco Boselli, Gianni Conte, Monica Reggiani
1999 Lecture Notes in Computer Science  
This paper describes an implementation of the LAM MPI suite on the top of the Virtual Interface Architecture.  ...  This paper presents an implementation of the LAM MPI suite on the top of the Virtual Interface Architecture.  ...  The VIA based LAM-MPI implementation is freely downloadable from: http://www.ce.unipr.it/pardis/parma2/.  ... 
doi:10.1007/3-540-48158-3_25 fatcat:dozfpz3zrzdwffd4or4yrjfsoq

Open MPI: Goals, Concept, and Design of a Next Generation MPI Implementation [chapter]

Edgar Gabriel, Graham E. Fagg, George Bosilca, Thara Angskun, Jack J. Dongarra, Jeffrey M. Squyres, Vishal Sahay, Prabhanjan Kambadur, Brian Barrett, Andrew Lumsdaine, Ralph H. Castain, David J. Daniel (+2 others)
2004 Lecture Notes in Computer Science  
Its component architecture provides both a stable platform for third-party research as well as enabling the run-time composition of independent software add-ons.  ...  Building upon prior research, and influenced by experience gained from the code bases of the LAM/MPI, LA-MPI, and FT-MPI projects, Open MPI is an all-new, productionquality MPI-2 implementation that is  ...  Acknowledgments This work was supported by a grant from the Lilly Endowment, National Science Foundation grants 0116050, EIA-0202048, EIA-9972889, and ANI-0330620, and Department of Energy Contract DE-FG02  ... 
doi:10.1007/978-3-540-30218-6_19 fatcat:fakvh4zesfgxffcpeu4wc7bv5y

Proactive process-level live migration in HPC environments

Chao Wang, F. Mueller, C. Engelmann, S.L. Scott
2008 2008 SC - International Conference for High Performance Computing, Networking, Storage and Analysis  
BT/CG/FT/LU/SP Class C on 4/8/16 nodes is 23 seconds) Tf: MTBF, 1.25hrs [I.Philp HPCRI'05] 6 Modular, component-based architecture -2 major layers -Daemon-based RTE: lamd -"Plug in" C/R to MPI  ...  distributed C/R: LAM-MPI jobsOur Design & Implementation -LAM/MPIStep 3 is optional: live migration (w/ step 3) vs. frozen (w/o step 3)Live Migration vs.  ... 
doi:10.1109/sc.2008.5222634 dblp:conf/sc/WangMES08 fatcat:p2wzdxpunff5xjjkvmsv5jxmwa

Message Passing Interface (MPI) [chapter]

2005 Advanced Computer Architecture and Parallel Processing  
Squyres This work presents the design and implementation of a component system architecture in LAM/MPI, a production quality, open source implementation of the MPI-1 and MPI-2 standards.  ...  To address these issues, the current version of LAM/MPI has been re-architected to utilize a component system architecture consisting of four component frameworks and a meta framework that ties them together  ...  FIGURES2. 1 1 High-level architecture of LAM/MPI. . . . . . . . . . . . . . . . . . . . 13 2.2 LAM/MPI as a component system architecture containing component frameworks and modules. . . . . . . . . .  ... 
doi:10.1002/0471478385.ch9 fatcat:dze6oxxnirftpnqrdqzuczbzcu

The Design and Implementation of Checkpoint/Restart Process Fault Tolerance for Open MPI

Joshua Hursey, Jeffrey M. Squyres, Timothy I. Mattox, Andrew Lumsdaine
2007 2007 IEEE International Parallel and Distributed Processing Symposium  
We identify the general capabilities required for distributed checkpoint/restart and realize these capabilities as extensible frameworks within Open MPI's modular component architecture.  ...  Although our implementation includes support for some initial checkpoint/restart mechanisms, the framework is meant to be extensible and to encourage experimentation of alternative techniques within a  ...  LAM/MPI did not provide any API for synchronous checkpointing and/or restarting from within a process.  ... 
doi:10.1109/ipdps.2007.370605 dblp:conf/ipps/HurseySML07 fatcat:f3r2txar5nexnbpz2zsav6vj6a

Open MPI's TEG Point-to-Point Communications Methodology: Comparison to Existing Implementations [chapter]

T. S. Woodall, R. L. Graham, R. H. Castain, D. J. Daniel, M. W. Sukalski, G. E. Fagg, E. Gabriel, G. Bosilca, T. Angskun, J. J. Dongarra, J. M. Squyres, V. Sahay (+3 others)
2004 Lecture Notes in Computer Science  
TEG is a new methodology for point-to-point messaging developed as a part of the Open MPI project.  ...  Open MPI/TEG's provides an enhanced feature set with support for dropped packets, corrupt packets, and NIC failures; concurrent network types (e.g. Myrinet, Infini-  ...  Acknowledgments This work was supported by a grant from the Lilly Endowment, National Science Foundation grants 0116050, EIA-0202048, EIA-9972889, and ANI-0330620, and Department of Energy Contract DE-FG02  ... 
doi:10.1007/978-3-540-30218-6_20 fatcat:frtkrftwnjax5mqaaww3oe5rwy

Experiences parallelizing, configuring, monitoring, and visualizing applications for clusters and multi-clusters [chapter]

O.J. Anshus, J.M. Bjørndalen, L.A. Bongo
2004 Advances in Parallel Computing  
By reconfiguring the LAM-MPI Allreduce operation we achieved a performance gain of 1.52, 1.79, and 1.98 on respectively two, four and eight-way clusters.  ...  For larger packet sizes the Allreduce operation rapidly detoriated performancewise.  ...  of LAM-MPI when running identical configurations.  ... 
doi:10.1016/s0927-5452(04)80107-2 fatcat:n4tvnaftzzhrxes4m2z5vxvfxa

A Skeletal-Based Approach for the Development of Fault-Tolerant SPMD Applications

Constantinos Makassikis, Virginie Galtier, Stephane Vialle
2010 2010 International Conference on Parallel and Distributed Computing, Applications and Technologies  
Comparisons with existing system-level checkpoint solutions, namely LAM/MPI and DMTCP, point out that FT-SPMD has a lower runtime overhead while being more robust when a higher level of fault tolerance  ...  Experiments show that the complexity for developing an application is small and the use of the framework has a small impact on performance.  ...  ACKNOWLEDGMENT The authors would like to thank Region Lorraine for supporting this work.  ... 
doi:10.1109/pdcat.2010.89 dblp:conf/pdcat/MakassikisGV10 fatcat:gku4vawyzfdefgzdao47rfkw4a
« Previous Showing results 1 — 15 out of 348 results