{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,2,13]],"date-time":"2024-02-13T15:09:30Z","timestamp":1707836970480},"reference-count":37,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2008,10,16]],"date-time":"2008-10-16T00:00:00Z","timestamp":1224115200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Cluster Comput"],"published-print":{"date-parts":[[2008,12]]},"DOI":"10.1007\/s10586-008-0065-8","type":"journal-article","created":{"date-parts":[[2008,10,15]],"date-time":"2008-10-15T14:19:53Z","timestamp":1224080393000},"page":"341-354","source":"Crossref","is-referenced-by-count":5,"title":["Efficient shared memory and RDMA based collectives on\u00a0multi-rail QsNetII SMP clusters"],"prefix":"10.1007","volume":"11","author":[{"given":"Ying","family":"Qian","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ahmad","family":"Afsahi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2008,10,16]]},"reference":[{"key":"65_CR1","unstructured":"Alexandrov, A., Ionescu, M., Schauser, K.E., Scheiman, C.: Incorporating long messages into the logp model\u2014one step closer towards a realistic model for parallel computation. In: Proc. 7th ACM Symposium on Parallel Algorithms and Architecture (SPAA\u201995), 1995"},{"issue":"4","key":"65_CR2","doi-asserted-by":"crossref","first-page":"34","DOI":"10.1109\/MM.2005.75","volume":"25","author":"J. Beecroft","year":"2005","unstructured":"Beecroft, J., Addison, D., Hewson, D., McLaren, M., Roweth, D., Petrini, F., Nieplocha, J.: QsNetII: defining high-performance network design. IEEE Micro 25(4), 34\u201347 (2005)","journal-title":"IEEE Micro"},{"issue":"3","key":"65_CR3","doi-asserted-by":"crossref","first-page":"45","DOI":"10.1109\/88.532139","volume":"4","author":"S.H. Bokhari","year":"1996","unstructured":"Bokhari, S.H.: Multiphase complete exchange on Paragon, SP2, and CS-2. IEEE Parallel Distrib. Technol. 4(3), 45\u201359 (1996)","journal-title":"IEEE Parallel Distrib. Technol."},{"issue":"11","key":"65_CR4","doi-asserted-by":"crossref","first-page":"1143","DOI":"10.1109\/71.642949","volume":"8","author":"J. Bruck","year":"1997","unstructured":"Bruck, J., Ho, C.-T., Kipnis, S., Upfal, E., Weathersby, D.: Efficient algorithms for all-to-all communications in multiport message-passing systems. IEEE Trans. Parallel Distrib. Syst. 8(11), 1143\u20131156 (1997)","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"key":"65_CR5","doi-asserted-by":"crossref","unstructured":"Buntinas, D., Mercier, G., Gropp, W.: Data transfers between processes in an SMP system: performance study and application to MPI. In: Proc. 35th Int. Conf. on Parallel Processing (ICPP 2006), 2006","DOI":"10.1109\/ICPP.2006.31"},{"key":"65_CR6","doi-asserted-by":"crossref","unstructured":"Chai, L., Hartono, A., Panda, D.K.: Designing high performance and scalable MPI intra-node communication support for clusters. In: Proc. 8th IEEE Int. Conf. on Cluster Computing (Cluster 2006), 2006","DOI":"10.1109\/CLUSTR.2006.311850"},{"key":"65_CR7","doi-asserted-by":"crossref","unstructured":"Chan, E., Van de Geijn, R., Gropp, W., Thakur, R.: Collective communication on architectures that support simultaneous communication over multiple links. In: Proc. 11th ACM SIGPLAN Symposium on Principles and practice of parallel programming (PPoPP\u201906), pp. 2\u201311 (2006)","DOI":"10.1145\/1122971.1122975"},{"issue":"7-8","key":"65_CR8","doi-asserted-by":"crossref","first-page":"625","DOI":"10.1002\/cpe.725","volume":"15","author":"S. Coll","year":"2003","unstructured":"Coll, S., Frachtenberg, E., Petrini, F., Hoisie, A., Gurvits, L.: Using multirail networks in high performance clusters. Concurr. Comput. Pract. Exp. 15(7-8), 625\u2013651 (2003)","journal-title":"Concurr. Comput. Pract. Exp."},{"key":"65_CR9","unstructured":"Cray Man Page Collection: Shared Memory Access (SHMEM) S-2383-2, http:\/\/docs.cray.com\/"},{"key":"65_CR10","doi-asserted-by":"crossref","unstructured":"Culler, D.E., Karp, R.M., Patterson, D.A., Sahay, A., Schauser, K.E., Santos, E., Subramonian, R., von Eiken, T.: LogP: towards a realistic model of parallel computation. In: Proc. 4th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming, 1993","DOI":"10.1145\/155332.155333"},{"issue":"3","key":"65_CR11","doi-asserted-by":"crossref","first-page":"389","DOI":"10.1016\/S0167-8191(06)80021-9","volume":"20","author":"R. Hockney","year":"1994","unstructured":"Hockney, R.: The communication challenge for MPP, Intel Paragon and Meiko CS-2. Parallel Comput. 20(3), 389\u2013398 (1994)","journal-title":"Parallel Comput."},{"key":"65_CR12","unstructured":"InfiniBand Architecture, http:\/\/www.infinibandta.org\/"},{"key":"65_CR13","unstructured":"Jin, H.-W., Sur, S., Chai, L., Panda, D.K.: LiMIC: support for high-performance mpi intra-node communication on Linux clusters. In: Proc. 34th Int. Conf. on Parallel Processing (ICPP 2005), 2005"},{"key":"65_CR14","doi-asserted-by":"crossref","unstructured":"Kielmann, T., Bal, H.E., Verstoep, K.: Fast measurement of LogP parameters for message passing platforms. In: Proc. 4th Workshop on Runtime Systems for Parallel Programming (RTSPP), 2000","DOI":"10.1007\/3-540-45591-4_162"},{"key":"65_CR15","unstructured":"Liu, J., Vishnu, A., Panda, D.K.: Building multirail infiniband clusters: MPI-level design and performance evaluation, In: Proc. 2004 ACM\/IEEE Conf. on Supercomputing (SC\u201904), 2004"},{"key":"65_CR16","doi-asserted-by":"crossref","unstructured":"Mamidala, A.R., Chai, L., Jin, H.-W., Panda, D.K.: Efficient SMP-aware MPI-level Broadcast over InfiniBand\u2019s Hardware Multicast. In: Proc. 6th Workshop on Communication Architecture for Clusters (CAC 2006), 2006","DOI":"10.1109\/IPDPS.2006.1639562"},{"key":"65_CR17","doi-asserted-by":"crossref","unstructured":"Mamidala, A.R., Vishnu, A., Panda, D.K.: Efficient shared memory and RDMA based design for MPI-allgather over InfiniBand. In: Proc. EuroPVM\/MPI, pp. 66\u201375 (2006)","DOI":"10.1007\/11846802_17"},{"key":"65_CR18","unstructured":"MPI: A Message-Passing Interface standard (1997)"},{"key":"65_CR19","unstructured":"Myricom, http:\/\/www.myricom.com\/"},{"key":"65_CR20","unstructured":"PDSH, http:\/\/www.llnl.gov\/linux\/pdsh\/"},{"key":"65_CR21","doi-asserted-by":"crossref","unstructured":"Pjesivac-Grbovic, J., Angskun, T., Bosilca, G., Fagg, G.E., Gabriel, E., Dongarra, J.J.: Performance analysis of MPI collective operations. In: Proc. 19th IEEE Int. Parallel and Distributed Processing Symposium (IPDPS\u201905), 2005","DOI":"10.1109\/IPDPS.2005.335"},{"key":"65_CR22","unstructured":"Qian, Y., Afsahi, A.: Efficient RDMA-based multi-port collectives on multi-rail QsNetII clusters. In: Proc. 6th Workshop on Communication Architecture for Clusters (CAC 2006), 2006"},{"key":"65_CR23","unstructured":"Qian, Y., Afsahi, A.: RDMA-based and SMP-aware multi-port all-gather on multi-rail QsNetII SMP clusters. In: Proc. 36th Int. Conf. on Parallel Processing (ICPP 2007), 2007"},{"key":"65_CR24","doi-asserted-by":"crossref","unstructured":"Rashti, M.J., Afsahi, A.: Assessing the ability of computation\/communication overlap and communication progress in modern interconnects. In: Proc. 15th IEEE Symposium on High-Performance Interconnects (Hot Interconnects 2007), pp. 117\u2013124 (2007)","DOI":"10.1109\/HOTI.2007.12"},{"key":"65_CR25","doi-asserted-by":"crossref","unstructured":"Ritzdorf, H., Traff, J.L.: Collective operations in NEC\u2019s high-performance MPI libraries. In: Proc. 20th Int. Parallel and Distributed Processing Symposium (IPDPS\u201906), 2006","DOI":"10.1109\/IPDPS.2006.1639334"},{"key":"65_CR26","doi-asserted-by":"crossref","unstructured":"Roweth, D., Addison, D.: Optimized gather collectives on QsNetII. In: Proc. EuroPVM\/MPI, pp. 407\u2013414 (2005)","DOI":"10.1007\/11557265_52"},{"key":"65_CR27","unstructured":"Roweth, D., Pittman, A., Beecroft, J.: Performance of all-to-all on QsNetII. Quadrics White Paper (2005). http:\/\/www.quadrics.com\/"},{"key":"65_CR28","doi-asserted-by":"crossref","first-page":"167","DOI":"10.1016\/S0167-8191(02)00222-3","volume":"29","author":"H. Shan","year":"2003","unstructured":"Shan, H., Singh, J.P., Oliker, L., Biswas, R.: Message passing and shared address space parallelism on an SMP cluster. Parallel Comput. 29, 167\u2013186 (2003)","journal-title":"Parallel Comput."},{"key":"65_CR29","doi-asserted-by":"crossref","unstructured":"Sistare, S., vandeVaart, R., Loh, E.: Optimization of MPI collectives on clusters of large-scale SMPs. In: Proc. 1999 ACM\/IEEE Conf. on Supercomputing (SC\u201999), 1999","DOI":"10.1145\/331532.331555"},{"key":"65_CR30","doi-asserted-by":"crossref","unstructured":"Sur, S., Jin, H.-W., Panda, D.K.: Efficient and scalable all-to-all personalized exchange for InfiniBand clusters. In: Proc. 33rd Int. Conf. on Parallel Processing (ICCP\u201904), pp. 275\u2013282 (2004)","DOI":"10.1109\/ICPP.2004.1327932"},{"key":"65_CR31","doi-asserted-by":"crossref","unstructured":"Sur, S., Bondhugula, U.K.R., Mamidala, A., Jin, H.-W., Panda, D.K.: High performance RDMA based all-to-all broadcast for Infiniband clusters. In: Proc. Int. Conf. on High Performance Computing (HiPC 2005), 2005","DOI":"10.1007\/11602569_19"},{"issue":"1","key":"65_CR32","doi-asserted-by":"crossref","first-page":"49","DOI":"10.1177\/1094342005051521","volume":"19","author":"R. Thakur","year":"2005","unstructured":"Thakur, R., Rabenseifner, R., Gropp, W.: Optimization of collective communication operations in MPICH. Int. J. High Perform. Comput. Appl. 19(1), 49\u201366 (2005)","journal-title":"Int. J. High Perform. Comput. Appl."},{"key":"65_CR33","doi-asserted-by":"crossref","unstructured":"Tipparaju, V., Nieplocha, J.: Optimizing all-to-all collective communication by exploiting concurrency in modern networks. In: Proc. 2005 ACM\/IEEE Conf. on Supercomputing (SC\u201905), 2005","DOI":"10.1109\/SC.2005.51"},{"key":"65_CR34","doi-asserted-by":"crossref","unstructured":"Tipparaju, V., Nieplocha, J., Panda, D.K.: Fast collective operations using shared and remote memory access protocols on clusters. In: Proc. 17th IEEE Int. Parallel and Distributed Processing Symposium (IPDPS\u201903), 2003","DOI":"10.1109\/IPDPS.2003.1213188"},{"key":"65_CR35","doi-asserted-by":"crossref","unstructured":"Traff, J.L.: Efficient allgather for regular SMP-clusters. In: Proc. EuroPVM\/MPI, pp. 58\u201365 (2006)","DOI":"10.1007\/11846802_16"},{"key":"65_CR36","doi-asserted-by":"crossref","unstructured":"Vadhiyar, S.S., Fagg, G.E., Dongarra, J.: Automatically tuned collective communications. In: Proc. 2000 ACM\/IEEE Conf. on Supercomputing (SC2000) (2000)","DOI":"10.1109\/SC.2000.10024"},{"key":"65_CR37","unstructured":"Wu, M., Kendall, R.A., Wright, K.: Optimizing collective communications on SMP clusters. In: Proc. 34th Int. Conf. on Parallel Processing (ICPP 2005), pp. 399\u2013407 (2005)"}],"container-title":["Cluster Computing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10586-008-0065-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10586-008-0065-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10586-008-0065-8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,30]],"date-time":"2019-05-30T14:40:10Z","timestamp":1559227210000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10586-008-0065-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2008,10,16]]},"references-count":37,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2008,12]]}},"alternative-id":["65"],"URL":"https:\/\/doi.org\/10.1007\/s10586-008-0065-8","relation":{},"ISSN":["1386-7857","1573-7543"],"issn-type":[{"value":"1386-7857","type":"print"},{"value":"1573-7543","type":"electronic"}],"subject":[],"published":{"date-parts":[[2008,10,16]]}}}