{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,3]],"date-time":"2025-05-03T04:11:55Z","timestamp":1746245515350,"version":"3.40.4"},"reference-count":34,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2014,5,8]],"date-time":"2014-05-08T00:00:00Z","timestamp":1399507200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Cluster Comput"],"published-print":{"date-parts":[[2014,12]]},"DOI":"10.1007\/s10586-014-0377-9","type":"journal-article","created":{"date-parts":[[2014,5,7]],"date-time":"2014-05-07T10:30:03Z","timestamp":1399458603000},"page":"1473-1495","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Scalable PGAS collective operations in NUMA clusters"],"prefix":"10.1007","volume":"17","author":[{"given":"Dami\u00e1n A.","family":"Mall\u00f3n","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guillermo L.","family":"Taboada","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Carlos","family":"Teijeiro","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jorge","family":"Gonz\u00e1lez-Dom\u00ednguez","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andr\u00e9s","family":"G\u00f3mez","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Brian","family":"Wibecan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2014,5,8]]},"reference":[{"key":"377_CR1","unstructured":"Advanced Micro Devices, Inc.: Magny\u2013Cours and direct connect architecture 2.0 (2009)"},{"key":"377_CR2","doi-asserted-by":"crossref","unstructured":"Antony, J., Janes, P.P., Rendell, A.P.: Exploring thread and memory placement on NUMA architectures: Solaris and Linux, UltraSPARC\/FirePlane and Opteron\/HyperTransport. In: Proceedings of 13th IEEE International Conference on High Performance Computing (HiPC\u201906), pp. 338\u2013352. Bangalore (2006)","DOI":"10.1007\/11945918_35"},{"key":"377_CR3","doi-asserted-by":"crossref","unstructured":"Brightwell, R., Pedretti, K.T.: Optimizing multi-core MPI collectives with SMARTMAP. In: Proceedings of 3rd International Workshop on Advanced Distributed and Parallel Network Applications (ADPNA 2009), pp. 370\u2013377. Vienna (2009)","DOI":"10.1109\/ICPPW.2009.65"},{"key":"377_CR4","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: Proceedings of 11th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming (PPoPP\u201906), pp. 2\u201311. Manhattan (2006)","DOI":"10.1145\/1122971.1122975"},{"key":"377_CR5","doi-asserted-by":"crossref","first-page":"16","DOI":"10.1109\/MM.2010.31","volume":"30","author":"P Conway","year":"2010","unstructured":"Conway, P., Kalyanasundharam, N., Donley, G., Lepak, K., Hughes, B.: Cache hierarchy and memory subsystem of the AMD Opteron processor. IEEE Micro. 30, 16\u201329 (2010)","journal-title":"IEEE Micro."},{"key":"377_CR6","unstructured":"George Washington University.: GWU unified testing suite (GUTS). http:\/\/threads.hpcl.gwu.edu\/sites\/guts (2010). Accessed March 2014"},{"key":"377_CR7","doi-asserted-by":"crossref","unstructured":"Graham, R.L., Shipman, G.M.: MPI support for multi-core architectures: optimized shared memory collectives. In: Proceedings 15th European PVM\/MPI Users\u2019 Group Meeting (EuroPVM\/MPI\u201908), pp. 130\u2013140. Dublin (2008)","DOI":"10.1007\/978-3-540-87475-1_21"},{"key":"377_CR8","doi-asserted-by":"crossref","unstructured":"Hoefler, T., Siebert, C., Rehm, W.: A practically constant-time MPI broadcast algorithm for large-scale InfiniBand clusters with multicast. In: Proceedings of 7th Workshop on Communication Architecture for Clusters (CAC\u201907), pp. 1\u20138. Long Beach (2007)","DOI":"10.1109\/IPDPS.2007.370475"},{"key":"377_CR9","unstructured":"Intel Corporation.: \u201cIntel MPI Benchmarks\u201d, http:\/\/software.intel.com\/en-us\/articles\/intel-mpi-benchmarks . Accessed March 2014"},{"key":"377_CR10","doi-asserted-by":"crossref","unstructured":"Jeannot, E., Mercier, G.: Near-optimal placement of MPI processes on hierarchical NUMA architectures. In: Proceedings of 16th International European Conference on Parallel and Distributed Computing (Euro-Par\u201910), pp. 199\u2013210. Ischia (2010)","DOI":"10.1007\/978-3-642-15291-7_20"},{"key":"377_CR11","doi-asserted-by":"crossref","unstructured":"Jiang, W., Liu, J., Wook Jin, H., Panda, D.K., Gropp, W., Thakur, R.: High performance MPI-2 one-sided communication over InfiniBand. In: Proceedings of 4th IEEE\/ACM International Symposium on Cluster Computing and the Grid (CCGrid\u201904), pp. 531\u2013538. Chicago (2004)","DOI":"10.1109\/CCGrid.2004.1336648"},{"key":"377_CR12","doi-asserted-by":"crossref","unstructured":"Kandalla, K.C., Subramoni, H., Santhanaraman, G., Koop, M., Panda, D.K.: Designing multi-leader-based allgather algorithms for multi-core clusters. In: Proceedings of 9th Workshop on Communication Architecture for Clusters (CAC\u201909), pp. 1\u20138. Rome (2009)","DOI":"10.1109\/IPDPS.2009.5160896"},{"key":"377_CR13","doi-asserted-by":"crossref","unstructured":"Kandalla, K.C., Subramoni, H., Vishnu, A., Panda, D.K.: Designing topology-aware collective communication algorithms for large scale InfiniBand clusters: case studies with scatter and gather. In: Proceedings of 10th Workshop on Communication Architecture for Clusters (CAC\u201910), pp. 1\u20138. Atlanta (2010)","DOI":"10.1109\/IPDPSW.2010.5470853"},{"key":"377_CR14","doi-asserted-by":"crossref","unstructured":"Koop, M.J., Sridhar, J.K., Panda, D.K.: Scalable MPI design over InfiniBand using eXtended Reliable Connection. In: Proceedings of 10th IEEE International Conference on Cluster Computing (Cluster\u201908), pp. 203\u2013212. Tsukuba (2008)","DOI":"10.1109\/CLUSTR.2008.4663773"},{"key":"377_CR15","doi-asserted-by":"crossref","unstructured":"Kumar, R., Mamidala, A.R., Panda, D.K.: Scaling alltoall collective on multi-core systems. In: Proceedings of 8th Workshop on Communication Architecture for Clusters (CAC\u201908), pp. 1\u20138. Miami (2008)","DOI":"10.1109\/IPDPS.2008.4536141"},{"key":"377_CR16","doi-asserted-by":"crossref","unstructured":"Li, S., Hoefler, T., Snir, M.: NUMA-aware shared memory collective communication for MPI. In: Proceedings of 22nd International ACM Symposium on High Performance Parallel and Distributed Computing (HPDC\u201913), pp. 85\u201396. New York (2013)","DOI":"10.1145\/2493123.2462903"},{"key":"377_CR17","doi-asserted-by":"crossref","unstructured":"Lorenzo, J.A., Rivera, F.F., Tuma, P., Pichel, J.C.: On the influence of thread allocation for irregular codes in NUMA systems. In: Proceedings of 10th International Conference on Parallel and Distributed Computing, Applications and Technologies (PDCAT\u201909), pp. 146\u2013153. Hiroshima (2009)","DOI":"10.1109\/PDCAT.2009.42"},{"key":"377_CR18","unstructured":"Mall\u00f3n, D.A., Mouri\u00f1o, J.C., G\u00f3mez, A., Taboada, G.L., Teijeiro, C., Touri\u00f1o, J., Fraguela, B.B., Doallo, R., Wibecan, B.: UPC operations microbenchmarking suite. In: Proceedings of 25th International Supercomputing Conference (ISC\u201910), Research Poster, Hamburg. http:\/\/upc.cesga.es (2010). Accessed March 2014"},{"key":"377_CR19","doi-asserted-by":"crossref","unstructured":"Mamidala, A.R., Kumar, R., De, D., Panda, D.K.: MPI collectives on modern multicore clusters: performance optimizations and communication characteristics. In: Proceedings of 8th IEEE\/ACM International Symposium on Cluster Computing and the Grid (CCGrid\u201908), pp. 130\u2013137. Lyon (2008)","DOI":"10.1109\/CCGRID.2008.87"},{"key":"377_CR20","doi-asserted-by":"crossref","unstructured":"Miao, Q., Sun, G., Shan, J., Chen, G.: Single data copying for MPI communication optimization on shared memory system. In: Proceedings of 7th International Conference on Computational Science (ICCS\u201907), pp. 700\u2013707. Beijing (2007)","DOI":"10.1007\/978-3-540-72584-8_93"},{"issue":"3\u20134","key":"377_CR21","first-page":"169","volume":"23","author":"JC Mouri\u00f1o","year":"2009","unstructured":"Mouri\u00f1o, J.C., G\u00f3mez, A., Taboada, J.M., Landesa, L., B\u00e9rtolo, J.M., Obelleiro, F., Rodr\u00edguez, J.L.: High scalability multipole method. Solving half billion of unknowns. Comput Sci R&D 23(3\u20134), 169\u2013175 (2009)","journal-title":"Comput Sci R&D"},{"key":"377_CR22","unstructured":"Nishtala, R., Yelick, K.A.: Optimizing collective communication on multicores. In: Proceedings of 1st USENIX Workshop on Hot Topics in Parallelism (HotPar\u201909), pp. 1\u20136. Berkeley (2009)"},{"issue":"9","key":"377_CR23","doi-asserted-by":"crossref","first-page":"576","DOI":"10.1016\/j.parco.2011.05.006","volume":"37","author":"R Nishtala","year":"2011","unstructured":"Nishtala, R., Zheng, Y., Hargrove, P.H., Yelick, K.A.: Tuning collective communication for partitioned global address space programming models. J. Parallel Comput. 37(9), 576\u2013591 (2011)","journal-title":"J. Parallel Comput."},{"key":"377_CR24","unstructured":"Qian, Y.: Design and evaluation of efficient collective communications on modern interconnects and multi-core clusters. Thesis PhD, Electrical & Computer Engineering, Queen\u2019s University. http:\/\/hdl.handle.net\/1974\/5383 (2010). Accessed March 2014"},{"key":"377_CR25","unstructured":"Rabenseifner, R.: A new optimized MPI reduce algorithm. http:\/\/www.hlrs.de\/mpi\/myreduce.html (2007). Accessed March 2014"},{"key":"377_CR26","unstructured":"Ryne, Z., Seidel, S.: Ideas and specifications for the new one-sided collective operations in UPC. http:\/\/www.upc.mtu.edu\/papers\/OnesidedColl (2005). Accessed March 2014"},{"key":"377_CR27","unstructured":"Salama, R.A., Sameh, A.: Potential performance improvement of collective operations in UPC. In: Proceedings of 12th International Conference on Parallel Computing (ParCo\u201907), pp. 413\u2013422. J\u00fclich and Aachen (2007)"},{"key":"377_CR28","doi-asserted-by":"crossref","unstructured":"Shipman, G.M., Poole, S., Shamis, P., Rabinovitz, I.: X-SRQ: improving scalability and performance of multi-core infiniband clusters. In: Proceedings of 15th European PVM\/MPI Users\u2019 Group Meeting (EuroPVM\/MPI\u201908), pp. 33\u201342. Dublin (2008)","DOI":"10.1007\/978-3-540-87475-1_11"},{"issue":"1","key":"377_CR29","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":"377_CR30","doi-asserted-by":"crossref","unstructured":"Trahay, F., Brunet, E., Denis, A., Namyst, R.: A multithreaded communication engine for multicore architectures. In: Proceedings of 8th Workshop on Communication Architecture for Clusters (CAC\u201908), pp. 1\u20137. Miami (2008)","DOI":"10.1109\/IPDPS.2008.4536139"},{"issue":"1","key":"377_CR31","doi-asserted-by":"crossref","first-page":"141","DOI":"10.1007\/s11227-009-0296-3","volume":"60","author":"B Tu","year":"2012","unstructured":"Tu, B., Fan, J., Zhan, J., Zhao, X.: Performance analysis and optimization of MPI collective operations on multi-core clusters. J. Supercomput. 60(1), 141\u2013162 (2012)","journal-title":"J. Supercomput."},{"key":"377_CR32","doi-asserted-by":"crossref","unstructured":"Vadhiyar, S.S., Fagg, G.E., Dongarra, J.J.: Automatically tuned collective communications. In: Proceedings of 2000 ACM\/IEEE Conference on Supercomputing (SC\u201900), pp. 1\u201311. Dallas (2000)","DOI":"10.1109\/SC.2000.10024"},{"key":"377_CR33","doi-asserted-by":"crossref","unstructured":"Velamati, M.K., Kumar, A., Jayam, N., Senthilkumar, G., Baruah, P.K., Sharma, R., Kapoor, S., Srinivasan, A.: Optimization of collective communication in intra-cell MPI. In: Proceedings of 14th International Conference on High Performance Computing (HiPC\u201907), pp. 488\u2013499. Goa (2007)","DOI":"10.1007\/978-3-540-77220-0_45"},{"key":"377_CR34","unstructured":"Wibecan, B.: Proposal for privatizability functions. http:\/\/www2.hpcl.gwu.edu\/pgas09\/HP_UPC_Proposal (2009). Accessed March 2014"}],"container-title":["Cluster Computing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10586-014-0377-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10586-014-0377-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10586-014-0377-9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,2]],"date-time":"2025-05-02T20:39:40Z","timestamp":1746218380000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10586-014-0377-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,5,8]]},"references-count":34,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2014,12]]}},"alternative-id":["377"],"URL":"https:\/\/doi.org\/10.1007\/s10586-014-0377-9","relation":{},"ISSN":["1386-7857","1573-7543"],"issn-type":[{"type":"print","value":"1386-7857"},{"type":"electronic","value":"1573-7543"}],"subject":[],"published":{"date-parts":[[2014,5,8]]}}}