{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,7]],"date-time":"2025-08-07T08:51:13Z","timestamp":1754556673093},"reference-count":41,"publisher":"Elsevier BV","issue":"6","license":[{"start":{"date-parts":[[2001,4,1]],"date-time":"2001-04-01T00:00:00Z","timestamp":986083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Future Generation Computer Systems"],"published-print":{"date-parts":[[2001,4]]},"DOI":"10.1016\/s0167-739x(00)00103-5","type":"journal-article","created":{"date-parts":[[2002,7,25]],"date-time":"2002-07-25T16:53:54Z","timestamp":1027616034000},"page":"769-782","source":"Crossref","is-referenced-by-count":28,"title":["Sensitivity of parallel applications to large differences in bandwidth and latency in two-layer interconnects"],"prefix":"10.1016","volume":"17","author":[{"given":"Aske","family":"Plaat","sequence":"first","affiliation":[]},{"given":"Henri E.","family":"Bal","sequence":"additional","affiliation":[]},{"given":"Rutger F.H.","family":"Hofman","sequence":"additional","affiliation":[]},{"given":"Thilo","family":"Kielmann","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"key":"10.1016\/S0167-739X(00)00103-5_BIB1","doi-asserted-by":"crossref","unstructured":"H. Bal, L. Allis, Parallel retrograde analysis on a distributed system, in: Supercomputing\u201995, December 1995. http:\/\/www.supercomp.org\/sc95\/proceedings\/.","DOI":"10.1145\/224170.224470"},{"issue":"1","key":"10.1016\/S0167-739X(00)00103-5_BIB2","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/273011.273014","article-title":"Performance evaluation of the Orca shared object system","volume":"16","author":"Bal","year":"1998","journal-title":"ACM Trans. Comput. Syst."},{"key":"10.1016\/S0167-739X(00)00103-5_BIB3","doi-asserted-by":"crossref","unstructured":"H. Bal, A. Plaat, M. Bakker, P. Dozy, R. Hofman, Optimizing parallel applications for wide area clusters, in: IPPS\u201998 International Parallel Processing Symposium, April 1998, pp. 784\u2013790.","DOI":"10.1109\/IPPS.1998.670017"},{"issue":"11","key":"10.1016\/S0167-739X(00)00103-5_BIB4","doi-asserted-by":"crossref","first-page":"53","DOI":"10.1109\/2.730737","article-title":"User-level network interface protocols","volume":"31","author":"Bhoedjang","year":"1998","journal-title":"IEEE Comput."},{"key":"10.1016\/S0167-739X(00)00103-5_BIB5","doi-asserted-by":"crossref","unstructured":"D. Blackston, T. Suel, Highly portable and efficient implementations of parallel adaptive n-body methods, in: SC\u201997, November 1997. http:\/\/www.supercomp.org\/sc97\/program\/TECH\/BLACKSTO\/.","DOI":"10.1145\/509593.509597"},{"issue":"1","key":"10.1016\/S0167-739X(00)00103-5_BIB6","doi-asserted-by":"crossref","first-page":"29","DOI":"10.1109\/40.342015","article-title":"Myrinet: a gigabit-per-second local area network","volume":"15","author":"Boden","year":"1995","journal-title":"IEEE Micro"},{"key":"10.1016\/S0167-739X(00)00103-5_BIB7","doi-asserted-by":"crossref","first-page":"205","DOI":"10.1145\/210126.210127","article-title":"Techniques for reducing consistency-related communication in distributed shared memory system","volume":"13","author":"Carter","year":"1995","journal-title":"ACM Trans. Comput. Syst."},{"key":"10.1016\/S0167-739X(00)00103-5_BIB8","doi-asserted-by":"crossref","unstructured":"S. Chakrabarti, K. Yelick, Implementing an irregular application on a distributed memory multiprocessor, in: ACM Symposium on Principles and Practice of Parallel Programming, June 1993.","DOI":"10.1145\/155332.155350"},{"key":"10.1016\/S0167-739X(00)00103-5_BIB9","doi-asserted-by":"crossref","unstructured":"S. Chandra, J. Larus, A. Rogers, Where is time spent in message-passing and shared-memory programs, in: ASPLOS\u201994 Architectural Support for Programming Languages and Operating Systems, 1994.","DOI":"10.1145\/195473.195501"},{"key":"10.1016\/S0167-739X(00)00103-5_BIB10","doi-asserted-by":"crossref","unstructured":"F. Chong, R. Barua, F. Dahlgren, J. Kubiatowicz, A. Agarwal, The sensitivity of communication mechanisms to bandwidth and latency, in: HPCA-4 High Performance Communication Architectures, February 1998, pp. 37\u201346.","DOI":"10.1109\/HPCA.1998.650544"},{"key":"10.1016\/S0167-739X(00)00103-5_BIB11","doi-asserted-by":"crossref","unstructured":"A. Cox, S. Dwarkadas, P. Keheler, H. Lu, R. Rajamony, W. Zwaenepoel, Software versus hardware shared-memory implementation: a case study, in: Proceedings of the 21st International Symposium on Computer Architectures, April 1994, pp. 106\u2013117.","DOI":"10.1109\/ISCA.1994.288157"},{"key":"10.1016\/S0167-739X(00)00103-5_BIB12","doi-asserted-by":"crossref","unstructured":"A. Erlichson, N. Nuckolls, G. Chesson, J. Hennessy, SoftFLASH: analyzing the performance of clustered distributed virtual shared memory, in: Proceedings of the Seventh International Conference on Architectural Support for Programming Languages and Operating Systems, October 1996, pp. 210\u2013220.","DOI":"10.1145\/237090.237187"},{"issue":"2","key":"10.1016\/S0167-739X(00)00103-5_BIB13","doi-asserted-by":"crossref","first-page":"115","DOI":"10.1177\/109434209701100205","article-title":"Globus: a metacomputing infrastructure toolkit","volume":"11","author":"Foster","year":"1997","journal-title":"Int. J. Supercomput. Appl."},{"key":"10.1016\/S0167-739X(00)00103-5_BIB14","doi-asserted-by":"crossref","unstructured":"A. Grama, V. Kumar, A. Sameh, Scalable parallel formulations of the Barnes-Hut algorithm for n-body simulations, in: Supercomputing\u201994, November 1994.","DOI":"10.1145\/602770.602846"},{"issue":"1","key":"10.1016\/S0167-739X(00)00103-5_BIB15","doi-asserted-by":"crossref","first-page":"39","DOI":"10.1145\/242857.242867","article-title":"The legion vision of a worldwide virtual computer","volume":"40","author":"Grimshaw","year":"1997","journal-title":"Commun. ACM"},{"issue":"6","key":"10.1016\/S0167-739X(00)00103-5_BIB16","doi-asserted-by":"crossref","first-page":"789","DOI":"10.1016\/0167-8191(96)00024-5","article-title":"A high-performance, portable implementation of the MPI message passing interface standard","volume":"22","author":"Gropp","year":"1996","journal-title":"Parallel Comput."},{"key":"10.1016\/S0167-739X(00)00103-5_BIB17","doi-asserted-by":"crossref","unstructured":"T. Jeremiassen, S. Eggers, Reducing false sharing on shared memory multiprocessors through compile-time data transformations, in: Symposium on Principles and Practice of Parallel Programming, July 1995.","DOI":"10.1145\/209936.209955"},{"key":"10.1016\/S0167-739X(00)00103-5_BIB18","doi-asserted-by":"crossref","unstructured":"D. Jiang, G. Shan, J. Singh, Application restructuring and performance portability on shared virtual memory and hardware-coherent multiprocessors, in: PPoPP\u201997 Symposium on Principles and Practice of Parallel Programming, June 1997.","DOI":"10.1145\/263764.263792"},{"key":"10.1016\/S0167-739X(00)00103-5_BIB19","doi-asserted-by":"crossref","unstructured":"D. Jiang, J. Singh, A methodology and an evaluation of the SGI origin2000, in: ACM Sigmetrics\/Performance\u201998, June 1998.","DOI":"10.1145\/277858.277902"},{"key":"10.1016\/S0167-739X(00)00103-5_BIB20","doi-asserted-by":"crossref","unstructured":"K. Johnson, F. Kaashoek, D. Wallach, Crl: high-performance all-software distributed shared memory, in: Symposium on Operating Systems Principles, Vol. 15, December 1995, pp. 213\u2013228.","DOI":"10.1145\/224056.224073"},{"key":"10.1016\/S0167-739X(00)00103-5_BIB21","doi-asserted-by":"crossref","unstructured":"T. Kielmann, R.F.H. Hofman, H.E. Bal, A. Plaat, R.A.F. Bhoedjang, MagPIe: MPIs collective communication operations for clustered wide area systems, in: ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming (PPoPP\u201999), Atlanta, GA, May 1999.","DOI":"10.1145\/301104.301116"},{"key":"10.1016\/S0167-739X(00)00103-5_BIB22","doi-asserted-by":"crossref","unstructured":"L. Kontothanassis, G. Hunt, R. Stets, N. Hardavellas, M. Cierniak, S. Parthasarathy, W. Meira, S. Dwarkadas, M. Scott, VM-based shared memory on low-latency, remote-memory-access networks, in: ISCA-24, Proceedings of the 24th Annual International Symposium on Computer Architecture, June 1997, pp. 157\u2013169.","DOI":"10.1145\/264107.264163"},{"key":"10.1016\/S0167-739X(00)00103-5_BIB23","unstructured":"V. Kumar, A. Grama, A. Gupta, G. Karypis, Introduction to Parallel Computing: Design and Analysis of Algorithms, Benjamin\/Cummings, Menlo Park, CA, November 1993."},{"key":"10.1016\/S0167-739X(00)00103-5_BIB24","doi-asserted-by":"crossref","unstructured":"J. Laudon, D. Lenoski, The SGI origin: a ccNUMA highly scalable server, in: Proceedings of the 24th Annual International Symposium on Computer Architecture, June 1997, pp. 241\u2013251.","DOI":"10.1145\/264107.264206"},{"key":"10.1016\/S0167-739X(00)00103-5_BIB25","doi-asserted-by":"crossref","unstructured":"S. Lumetta, A. Mainwaring, D. Culler, Multi-protocol active messages on a cluster of SMPs, in: SC\u201997, November 1997. http:\/\/www.supercomp.org\/sc97\/proceedings\/.","DOI":"10.1145\/509593.509596"},{"key":"10.1016\/S0167-739X(00)00103-5_BIB26","doi-asserted-by":"crossref","unstructured":"J. Maassen, R. van Nieuwpoort, R. Veldema, H.E. Bal, A. Plaat, An efficient implementation of Java\u2019s remote method invocation, in: Proceedings of the Symposium on Principles and Practice of Parallel Programming (PPoPP\u201999), Atlanta, GA, May 1999.","DOI":"10.1145\/301104.301120"},{"key":"10.1016\/S0167-739X(00)00103-5_BIB27","unstructured":"MPI Forum, MPI: a message passing interface standard, Int. J. Supercomput. Appl. 8 (3\/4), 1994, Version 1.1. http:\/\/www.mcs.anl.gov\/mpi\/mpi-report-1.1\/mpi-report.html."},{"key":"10.1016\/S0167-739X(00)00103-5_BIB28","doi-asserted-by":"crossref","unstructured":"S. Pakin, M. Lauria, A. Chien, High performance messaging on workstations: Illinois fast messages (FM) for Myrinet, in: Supercomputing\u201995, San Diego, CA, December 1995.","DOI":"10.1145\/224170.224360"},{"key":"10.1016\/S0167-739X(00)00103-5_BIB29","doi-asserted-by":"crossref","unstructured":"J.W. Romein, H.E. Bal, Parallel n-body simulation on a large-scale homogeneous distributed system, in: S. Haridi, K. Ali, P. Magnusson (Eds.), EURO-PAR\u201995 Parallel Processing, Lecture Notes in Computer Science, Vol. 966, Stockholm, Sweden, Springer, Berlin, August 1995, pp. 473\u2013484.","DOI":"10.1007\/BFb0020486"},{"key":"10.1016\/S0167-739X(00)00103-5_BIB30","doi-asserted-by":"crossref","unstructured":"D.J. Scales, K. Gharachorloo, A. Aggarwal, Fine-grain software distributed shared memory on SMP clusters, in: HPCA-4 High-Performance Computer Architecture, February 1998, pp. 125\u2013137.","DOI":"10.1109\/HPCA.1998.650552"},{"issue":"3","key":"10.1016\/S0167-739X(00)00103-5_BIB31","doi-asserted-by":"crossref","first-page":"85","DOI":"10.1109\/88.242459","article-title":"The enterprise model for developing distributed applications","volume":"1","author":"Schaeffer","year":"1993","journal-title":"IEEE Parallel Distributed Technol."},{"key":"10.1016\/S0167-739X(00)00103-5_BIB32","doi-asserted-by":"crossref","unstructured":"J. Singh, C. Holt, T. Totsuka, A. Gupta, J. Hennessy, Load balancing and data locality in adaptive hierarchical n-body methods: Barnes-Hut, fast multipole and radiosity, J. Parallel Distributed Comput. 27 (June 1995) 118\u2013141.","DOI":"10.1006\/jpdc.1995.1077"},{"issue":"1","key":"10.1016\/S0167-739X(00)00103-5_BIB33","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1145\/130823.130824","article-title":"SPLASH: Stanford parallel applications for shared memory","volume":"20","author":"Singh","year":"1992","journal-title":"ACM Comput. Arch. News"},{"key":"10.1016\/S0167-739X(00)00103-5_BIB34","doi-asserted-by":"crossref","unstructured":"V. Soundararajan, M. Heinrich, B. Verghese, K. Gharachorloo, A. Gupta, J. Hennessy, Flexible use of memory for replication\/migration in cache-coherent DSM multiprocessors, in: ISCA\u201998, 25th International Symposium on Computer Architecture, June 1998, pp. 342\u2013355.","DOI":"10.1145\/279361.279403"},{"key":"10.1016\/S0167-739X(00)00103-5_BIB35","doi-asserted-by":"crossref","unstructured":"R. Stets, S. Dwarkadas, N. Hardavellas, G. Hunt, L. Kontothanassis, S. Parthasarathy, M. Scott, Cashmere-2L: software coherent shared memory on a clustered remote-write network, in: Proceedings of the 16th ACM Symposium on Oper. Systems Princ., October 1997.","DOI":"10.1145\/268998.266675"},{"key":"10.1016\/S0167-739X(00)00103-5_BIB36","doi-asserted-by":"crossref","unstructured":"T. Suel, M. Goudreau, K. Lang, S.B. Rao, T. Tsantilas, Towards efficiency and portability: programming with the BSP model, in: Proceedings of the Eighth Annual ACM Symposium on Parallel Algorithms and Architectures (SPAA\u201996), June 1996, pp. 1\u201312. www.bsp-worldwide.org.","DOI":"10.1145\/237502.237503"},{"issue":"8","key":"10.1016\/S0167-739X(00)00103-5_BIB37","doi-asserted-by":"crossref","first-page":"100","DOI":"10.1145\/79173.79181","article-title":"A bridging model for parallel computation","volume":"33","author":"Valiant","year":"1990","journal-title":"Commun. ACM"},{"key":"10.1016\/S0167-739X(00)00103-5_BIB38","doi-asserted-by":"crossref","unstructured":"R. van Nieuwpoort, J. Maassen, H.E. Bal, T. Kielmann, R. Veldema, Wide area parallel computing in Java, in: Proceedings of the ACM JavaGrande Conference, Palo Alto, CA, June 1999.","DOI":"10.1145\/304065.304087"},{"key":"10.1016\/S0167-739X(00)00103-5_BIB39","doi-asserted-by":"crossref","unstructured":"M. Warren, J. Salmon, A parallel hashed oct-tree n-body algorithm, in: Supercomputing\u201993, November 1993.","DOI":"10.1145\/169627.169640"},{"key":"10.1016\/S0167-739X(00)00103-5_BIB40","doi-asserted-by":"crossref","unstructured":"S. Woo, M. Ohara, E. Torrie, J. Singh, A. Gupta, The Splash-2 programs: characterization and methodological considerations, in: Proceedings of the 22nd International Symposium on Computer Architecture, June 1995, pp. 24\u201336.","DOI":"10.1145\/223982.223990"},{"key":"10.1016\/S0167-739X(00)00103-5_BIB41","doi-asserted-by":"crossref","unstructured":"D. Yeung, J. Kubiatowicz, A. Agarwal, MGS: a multigrain shared memory system, in: Proceedings of the 23rd Annual International Symposium on Computer Architecture, May 1996, pp. 45\u201356.","DOI":"10.1145\/232973.232980"}],"container-title":["Future Generation Computer Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0167739X00001035?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0167739X00001035?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2020,1,16]],"date-time":"2020-01-16T23:02:34Z","timestamp":1579215754000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0167739X00001035"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2001,4]]},"references-count":41,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2001,4]]}},"alternative-id":["S0167739X00001035"],"URL":"https:\/\/doi.org\/10.1016\/s0167-739x(00)00103-5","relation":{},"ISSN":["0167-739X"],"issn-type":[{"value":"0167-739X","type":"print"}],"subject":[],"published":{"date-parts":[[2001,4]]}}}