{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,10]],"date-time":"2026-01-10T07:29:46Z","timestamp":1768030186953,"version":"3.49.0"},"publisher-location":"Cham","reference-count":80,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030346263","type":"print"},{"value":"9783030346270","type":"electronic"}],"license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"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":[],"published-print":{"date-parts":[[2019]]},"DOI":"10.1007\/978-3-030-34627-0_11","type":"book-chapter","created":{"date-parts":[[2019,11,12]],"date-time":"2019-11-12T09:02:55Z","timestamp":1573549375000},"page":"138-158","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":18,"title":["GASNet-EX: A High-Performance, Portable Communication Library for Exascale"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0724-9349","authenticated-orcid":false,"given":"Dan","family":"Bonachea","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6691-5287","authenticated-orcid":false,"given":"Paul H.","family":"Hargrove","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2019,11,13]]},"reference":[{"key":"11_CR1","unstructured":"Alverson, B., Froese, E., Kaplan, L., Roweth, D.: Cray XC series network. White Paper WP-Aries01-1112, Cray Inc., November 2012. \nhttps:\/\/www.cray.com\/sites\/default\/files\/resources\/CrayXCNetwork.pdf"},{"key":"11_CR2","unstructured":"Argonne National Laboratory: Joint Laboratory for System Evaluation. \nhttp:\/\/www.jlse.anl.gov"},{"key":"11_CR3","doi-asserted-by":"publisher","unstructured":"Bachan, J., Baden, S.B., Bonachea, D., Hargrove, P.H., Hofmeyr, S., Jacquelin, M., Kamil, A., van Straalen, B.: UPC++ specification, v1.0 draft 8. Technical report LBNL-2001179, Lawrence Berkeley National Laboratory, September 2018. \nhttps:\/\/doi.org\/10.25344\/S45P4X","DOI":"10.25344\/S45P4X"},{"key":"11_CR4","doi-asserted-by":"publisher","unstructured":"Bachan, J., Bonachea, D., Hargrove, P.H., Hofmeyr, S., Jacquelin, M., Kamil, A., van Straalen, B., Baden, S.B.: The UPC++ PGAS library for exascale computing. In: Proceedings of the Second Annual PGAS Applications Workshop, PAW17, pp. 7:1\u20137:4. ACM, New York (2017). \nhttps:\/\/doi.org\/10.1145\/3144779.3169108","DOI":"10.1145\/3144779.3169108"},{"key":"11_CR5","doi-asserted-by":"publisher","unstructured":"Barrett, B.W., Brightwell, R., Hemmert, S., Pedretti, K., Wheeler, K., Underwood, K., Riesen, R., Maccabe, A.B., Hudson, T.: The Portals 4.0 network programming interface. Technical report SAND2012-10087, Sandia National Laboratories, November 2012. \nhttps:\/\/doi.org\/10.2172\/1088065","DOI":"10.2172\/1088065"},{"key":"11_CR6","doi-asserted-by":"publisher","unstructured":"Bauer, M., Treichler, S., Slaughter, E., Aiken, A.: Legion: expressing locality and independence with logical regions. In: Proceedings of the International Conference on High Performance Computing, Networking, Storage and Analysis, SC 2012 (2012). \nhttps:\/\/doi.org\/10.1109\/SC.2012.71","DOI":"10.1109\/SC.2012.71"},{"key":"11_CR7","doi-asserted-by":"publisher","unstructured":"Bell, C., Bonachea, D.: A new DMA registration strategy for pinning-based high performance networks. In: Proceedings of the International Parallel and Distributed Processing Symposium (IPDPS) (2003). \nhttps:\/\/doi.org\/10.1109\/IPDPS.2003.1213363","DOI":"10.1109\/IPDPS.2003.1213363"},{"key":"11_CR8","doi-asserted-by":"publisher","unstructured":"Bell, C., Chen, W., Bonachea, D., Yelick, K.: Evaluating support for global address space languages on the Cray X1. In: 19th Annual International Conference on Supercomputing (ICS), June 2004. \nhttps:\/\/doi.org\/10.1145\/1006209.1006236","DOI":"10.1145\/1006209.1006236"},{"key":"11_CR9","doi-asserted-by":"publisher","unstructured":"Birrittella, M.S., Debbage, M., Huggahalli, R., Kunz, J., Lovett, T., Rimmer, T., Underwood, K.D., Zak, R.C.: Intel Omni-Path Architecture: enabling scalable, high performance fabrics. In: IEEE 23rd Annual Symposium on High-Performance Interconnects, pp. 1\u20139, August 2015. \nhttps:\/\/doi.org\/10.1109\/HOTI.2015.22","DOI":"10.1109\/HOTI.2015.22"},{"key":"11_CR10","doi-asserted-by":"publisher","unstructured":"Bocchino, R.L., Adve, V.S., Chamberlain, B.L.: Software transactional memory for large scale clusters. In: Proceedings of the ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming (PPoPP 2008), pp. 247\u2013258. ACM, New York (2008). \nhttps:\/\/doi.org\/10.1145\/1345206.1345242","DOI":"10.1145\/1345206.1345242"},{"issue":"1","key":"11_CR11","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1109\/40.342015","volume":"15","author":"NJ Boden","year":"1995","unstructured":"Boden, N.J., Cohen, D., Felderman, R.E., Kulawik, A.E., Seitz, C.L., Seizovic, J.N., Su, W.K.: Myrinet: a gigabit-per-second local area network. IEEE Micro 15(1), 29\u201336 (1995). \nhttps:\/\/doi.org\/10.1109\/40.342015","journal-title":"IEEE Micro"},{"key":"11_CR12","doi-asserted-by":"publisher","unstructured":"Bonachea, D.: Proposal for extending the UPC memory copy library functions and supporting extensions to GASNet, v2.0. Technical report LBNL-56495-v2.0, Lawrence Berkeley National Laboratory, March 2007. \nhttps:\/\/doi.org\/10.2172\/920052","DOI":"10.2172\/920052"},{"key":"11_CR13","unstructured":"Bonachea, D.: AMMPI home page. \nhttp:\/\/gasnet.lbl.gov\/ammpi"},{"key":"11_CR14","doi-asserted-by":"publisher","unstructured":"Bonachea, D.: GASNet specification, v1.1. Technical report, UCB\/CSD-02-1207, University of California, Berkeley, October 2002. \nhttps:\/\/doi.org\/10.25344\/S4MW28","DOI":"10.25344\/S4MW28"},{"issue":"1\u20133","key":"11_CR15","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1504\/IJHPCN.2004.007569","volume":"1","author":"D Bonachea","year":"2004","unstructured":"Bonachea, D., Duell, J.: Problems with using MPI 1.1 and 2.0 as compilation targets for parallel language implementations. Int. J. High Perform. Comput. Netw. 1(1\u20133), 91\u201399 (2004). \nhttps:\/\/doi.org\/10.1504\/IJHPCN.2004.007569","journal-title":"Int. J. High Perform. Comput. Netw."},{"key":"11_CR16","doi-asserted-by":"publisher","unstructured":"Bonachea, D., Hargrove, P., Welcome, M., Yelick, K.: Porting GASNet to Portals: Partitioned Global Address Space (PGAS) language support for the Cray XT. In: Cray Users Group (2009). \nhttps:\/\/doi.org\/10.25344\/S4RP46","DOI":"10.25344\/S4RP46"},{"key":"11_CR17","doi-asserted-by":"publisher","unstructured":"Bonachea, D., Hargrove, P.H.: GASNet specification, v1.8.1. Technical report, LBNL-2001064, Lawrence Berkeley National Laboratory, August 2017. \nhttps:\/\/doi.org\/10.2172\/1398512","DOI":"10.2172\/1398512"},{"key":"11_CR18","doi-asserted-by":"publisher","unstructured":"Buntinas, D., Mercier, G., Gropp, W.: Design and evaluation of Nemesis, a scalable, low-latency, message-passing communication subsystem. In: Sixth IEEE International Symposium on Cluster Computing and the Grid (CCGRID 2006), vol. 1, pp. 521\u2013530, May 2006. \nhttps:\/\/doi.org\/10.1109\/CCGRID.2006.31","DOI":"10.1109\/CCGRID.2006.31"},{"key":"11_CR19","doi-asserted-by":"publisher","unstructured":"Callahan, D., Chamberlain, B.L., Zima, H.P.: The Cascade High Productivity Language. In: International Workshop on High-Level Parallel Programming Models and Supportive Environments (HIPS), pp. 52\u201360 (2004). \nhttps:\/\/doi.org\/10.1109\/HIPS.2004.10002","DOI":"10.1109\/HIPS.2004.10002"},{"key":"11_CR20","doi-asserted-by":"publisher","unstructured":"Chan, C., Wang, B., Bachan, J., Macfarlane, J.: Mobiliti: scalable transportation simulation using high-performance parallel computing. In: IEEE International Conference on Intelligent Transportation Systems (ITSC), pp. 634\u2013641 (2018). \nhttps:\/\/doi.org\/10.1109\/ITSC.2018.8569397","DOI":"10.1109\/ITSC.2018.8569397"},{"issue":"10","key":"11_CR21","doi-asserted-by":"publisher","first-page":"519","DOI":"10.1145\/1103845.1094852","volume":"40","author":"Philippe Charles","year":"2005","unstructured":"Charles, P., Grothoff, C., Saraswat, V., Donawa, C., Kielstra, A., Ebcioglu, K., von Praun, C., Sarkar, V.: X10: an object-oriented approach to non-uniform cluster computing. In: Proceedings of the 20th Annual ACM SIGPLAN Conference on Object-Oriented Programming, Systems, Languages, and Applications (OOPSLA 2005) (2005). \nhttps:\/\/doi.org\/10.1145\/1103845.1094852","journal-title":"ACM SIGPLAN Notices"},{"key":"11_CR22","doi-asserted-by":"publisher","unstructured":"Chen, W., Bonachea, D., Duell, J., Husband, P., Iancu, C., Yelick, K.: A performance analysis of the Berkeley UPC compiler. In: Proceedings of the 17th International Conference on Supercomputing (ICS), June 2003. \nhttps:\/\/doi.org\/10.1145\/782814.782825","DOI":"10.1145\/782814.782825"},{"key":"11_CR23","unstructured":"Cray Inc.: Cray XC Series. \nhttps:\/\/www.cray.com\/sites\/default\/files\/Cray-XC-Series-Brochure.pdf\n\n. Accessed 17 July 2018"},{"key":"11_CR24","doi-asserted-by":"publisher","unstructured":"Daily, J., Vishnu, A., Palmer, B., van Dam, H., Kerbyson, D.: On the suitability of MPI as a PGAS runtime. In: 21st International Conference on High Performance Computing (HiPC), December 2014. \nhttps:\/\/doi.org\/10.1109\/HiPC.2014.7116712","DOI":"10.1109\/HiPC.2014.7116712"},{"issue":"1","key":"11_CR25","doi-asserted-by":"publisher","first-page":"e4297","DOI":"10.1002\/cpe.4297","volume":"30","author":"D Doerfler","year":"2017","unstructured":"Doerfler, D., Austin, B., Cook, B., Deslippe, J., Kandalla, K., Mendygral, P.: Evaluating the networking characteristics of the Cray XC-40 Intel Knights Landing-based Cori supercomputer at NERSC. Concurr. Comput. Pract. Exp. 30(1), e4297 (2017). \nhttps:\/\/doi.org\/10.1002\/cpe.4297","journal-title":"Concurr. Comput. Pract. Exp."},{"key":"11_CR26","doi-asserted-by":"publisher","unstructured":"Dotsenko, Y., Coarfa, C., Mellor-Crummey, J.: A multi-platform Co-array Fortran compiler. In: Proceedings of the 13th International Conference on Parallel Architecture and Compilation Techniques (PACT) (2004). \nhttps:\/\/doi.org\/10.1109\/PACT.2004.1342539","DOI":"10.1109\/PACT.2004.1342539"},{"key":"11_CR27","unstructured":"Driscoll, M.: PyGAS. \nhttp:\/\/mbdriscoll.github.io\/pygas"},{"key":"11_CR28","doi-asserted-by":"publisher","unstructured":"Dunigan, T.H., Vetter, J.S., Worley, P.H.: Performance evaluation of the SGI Altix 3700. In: International Conference on Parallel Processing (ICPP 2005), pp. 231\u2013240, June 2005. \nhttps:\/\/doi.org\/10.1109\/ICPP.2005.61","DOI":"10.1109\/ICPP.2005.61"},{"key":"11_CR29","doi-asserted-by":"publisher","unstructured":"Eachempati, D., Jun, H.J., Chapman, B.: An open-source compiler and runtime implementation for Coarray Fortran. In: Proceedings of the Fourth Conference on Partitioned Global Address Space Programming Models (PGAS 2010), pp. 13:1\u201313:8. ACM (2010). \nhttps:\/\/doi.org\/10.1145\/2020373.2020386","DOI":"10.1145\/2020373.2020386"},{"key":"11_CR30","doi-asserted-by":"publisher","unstructured":"von Eicken, T., Culler, D.E., Goldstein, S.C., Schauser, K.E.: Active Messages: a mechanism for integrated communication and computation. In: Proceedings of the 19th International Symposium on Computer Architecture, Gold Coast, Australia, pp. 256\u2013266, May 1992. \nhttps:\/\/doi.org\/10.1145\/139669.140382","DOI":"10.1145\/139669.140382"},{"key":"11_CR31","doi-asserted-by":"publisher","unstructured":"Faanes, G., Bataineh, A., Roweth, D., Court, T., Froese, E., Alverson, B., Johnson, T., Kopnick, J., Higgins, M., Reinhard, J.: Cray Cascade: a scalable HPC system based on a Dragonfly network. In: Proceedings of the International Conference on High Performance Computing, Networking, Storage and Analysis, SC 2012, Los Alamitos, CA, USA, pp. 103:1\u2013103:9. IEEE Computer Society Press (2012). \nhttps:\/\/doi.org\/10.1109\/SC.2012.39","DOI":"10.1109\/SC.2012.39"},{"key":"11_CR32","doi-asserted-by":"publisher","unstructured":"Fanfarillo, A., Burnus, T., Cardellini, V., Filippone, S., Nagle, D., Rouson, D.: OpenCoarrays: open-source transport layers supporting Coarray Fortran compilers. In: Proceedings of the 8th International Conference on Partitioned Global Address Space Programming Models, PGAS 2014, pp. 4:1\u20134:11. ACM, New York (2014). \nhttps:\/\/doi.org\/10.1145\/2676870.2676876","DOI":"10.1145\/2676870.2676876"},{"key":"11_CR33","unstructured":"GASNet. \nhttp:\/\/gasnet.lbl.gov"},{"key":"11_CR34","doi-asserted-by":"publisher","unstructured":"Gerstenberger, R., Besta, M., Hoefler, T.: Enabling highly-scalable remote memory access programming with MPI-3 one sided. In: Proceedings of the International Conference on High Performance Computing, Networking, Storage and Analysis (SC 2013), pp. 53:1\u201353:12. ACM, New York (2013). \nhttps:\/\/doi.org\/10.1145\/2503210.2503286","DOI":"10.1145\/2503210.2503286"},{"key":"11_CR35","doi-asserted-by":"publisher","unstructured":"Grun, P., Hefty, S., Sur, S., Goodell, D., Russell, R.D., Pritchard, H., Squyres, J.M.: A brief introduction to the OpenFabrics interfaces - a new network API for maximizing high performance application efficiency. In: IEEE 23rd Annual Symposium on High-Performance Interconnects, pp. 34\u201339, August 2015. \nhttps:\/\/doi.org\/10.1109\/HOTI.2015.19","DOI":"10.1109\/HOTI.2015.19"},{"key":"11_CR36","doi-asserted-by":"publisher","unstructured":"Hargrove, P.H., Bonachea, D.: GASNet-EX performance improvements due to specialization for the Cray Aries network. Technical report. LBNL-2001134, Lawrence Berkeley National Laboratory, March 2018. \nhttps:\/\/doi.org\/10.2172\/1430690","DOI":"10.2172\/1430690"},{"key":"11_CR37","unstructured":"Hargrove, P.H., Bonachea, D., Bell, C.: Experiences implementing Partitioned Global Address Space (PGAS) languages on InfiniBand. In: OpenFabrics Alliance International Workshop, April 2008. \nhttp:\/\/downloads.openfabrics.org\/Media\/Sonoma2008\/Sonoma_2008_Wed_PGAS%20over%20IB.pdf"},{"key":"11_CR38","doi-asserted-by":"publisher","unstructured":"Hilfinger, P., Bonachea, D., Datta, K., Gay, D., Graham, S., Kamil, A., Liblit, B., Pike, G., Su, J., Yelick, K.: Titanium language reference manual. Technical report, UCB\/EECS-2005-15.1, University of California, Berkeley, November 2001. \nhttps:\/\/doi.org\/10.25344\/S4H59R","DOI":"10.25344\/S4H59R"},{"key":"11_CR39","doi-asserted-by":"publisher","unstructured":"Hjelm, N.: An evaluation of the one-sided performance in Open MPI. In: Proceedings of the 23rd European MPI Users\u2019 Group Meeting, EuroMPI 2016, pp. 184\u2013187. ACM, New York (2016). \nhttps:\/\/doi.org\/10.1145\/2966884.2966890","DOI":"10.1145\/2966884.2966890"},{"key":"11_CR40","unstructured":"IBM: LAPI programming guide. IBM Technical report SA22-7936-00 (2003)"},{"key":"11_CR41","doi-asserted-by":"publisher","unstructured":"Ibrahim, K.Z., Yelick, K.: On the conditions for efficient interoperability with threads: an experience with PGAS languages using Cray communication domains. In: Proceedings of the 28th ACM International Conference on Supercomputing, ICS 2014, pp. 23\u201332. ACM (2014). \nhttps:\/\/doi.org\/10.1145\/2597652.2597657","DOI":"10.1145\/2597652.2597657"},{"key":"11_CR42","unstructured":"InfiniBand Trade Association. \nhttp:\/\/www.infinibandta.org"},{"key":"11_CR43","unstructured":"Intel Corporation: Introducing Intel\u00aeMPI Benchmarks. \nhttps:\/\/software.intel.com\/en-us\/articles\/intel-mpi-benchmarks\n\n. Accessed 17 July 2018"},{"key":"11_CR44","unstructured":"Intel Corporation: Performance Scaled Messaging 2 (PSM2) Programmer\u2019s Guide, April 2017. Order No.: H76473\u20136.0"},{"key":"11_CR45","unstructured":"Intrepid Technology Inc.: Clang UPC Compiler. \nhttp:\/\/clangupc.github.io"},{"key":"11_CR46","unstructured":"Intrepid Technology Inc.: GCC\/UPC Compiler. \nhttp:\/\/www.gccupc.org"},{"key":"11_CR47","doi-asserted-by":"publisher","unstructured":"Jose, J., Hamidouche, K., Zhang, J., Venkatesh, A., Panda, D.K.: Optimizing collective communication in UPC. In: IEEE International Parallel Distributed Processing Symposium Workshops, pp. 361\u2013370, May 2014. \nhttps:\/\/doi.org\/10.1109\/IPDPSW.2014.49","DOI":"10.1109\/IPDPSW.2014.49"},{"key":"11_CR48","doi-asserted-by":"publisher","unstructured":"Krasnov, A., Schultz, A., Wawrzynek, J., Gibeling, G., Droz, P.Y.: RAMP Blue: a message-passing manycore system in FPGAs. In: Proceedings of International Conference on Field Programmable Logic and Applications, pp. 54\u201361, August 2007. \nhttps:\/\/doi.org\/10.1109\/FPL.2007.4380625","DOI":"10.1109\/FPL.2007.4380625"},{"key":"11_CR49","doi-asserted-by":"publisher","unstructured":"Kumar, S., Mamidala, A.R., Faraj, D.A., Smith, B., Blocksome, M., Cernohous, B., Miller, D., Parker, J., Ratterman, J., Heidelberger, P., Chen, D., Steinmacher-Burrow, B.: PAMI: a parallel active message interface for the Blue Gene\/Q supercomputer. In: 2012 IEEE 26th International Parallel and Distributed Processing Symposium, pp. 763\u2013773, May 2012. \nhttps:\/\/doi.org\/10.1109\/IPDPS.2012.73","DOI":"10.1109\/IPDPS.2012.73"},{"key":"11_CR50","doi-asserted-by":"publisher","unstructured":"Kumar, S., Dozsa, G., Almasi, G., Chen, D., Giampapa, M.E., Heidelberger, P., Blocksome, M., Faraj, A., Parker, J., Ratterman, J., Smith, B., Archer, C.: The Deep Computing Messaging Framework: generalized scalable message passing on the Blue Gene\/P supercomputer. In: 22nd Annual International Conference on Supercomputing (ICS), June 2008. \nhttps:\/\/doi.org\/10.1145\/1375527.1375544","DOI":"10.1145\/1375527.1375544"},{"key":"11_CR51","doi-asserted-by":"publisher","unstructured":"Matsumiya, R., Endo, T.: Scalable RMA-based communication library featuring node-local NVMs. In: Proceedings of the IEEE High Performance Extreme Computing Conference (HPEC 2018), pp. 1\u20137 (2018). \nhttps:\/\/doi.org\/10.1109\/HPEC.2018.8547546","DOI":"10.1109\/HPEC.2018.8547546"},{"key":"11_CR52","doi-asserted-by":"publisher","unstructured":"Mattson, T.G., Cledat, R., Cav\u00e9, V., Sarkar, V., Budimlic, Z., Chatterjee, S., Fryman, J., Ganev, I., Knauerhase, R., Lee, M., Meister, B., Nickerson, B., Pepperling, N., Seshasayee, B., Tasirlar, S., Teller, J., Vrvilo, N.: The Open Community Runtime: a runtime system for extreme scale computing. In: IEEE High Performance Extreme Computing Conference (HPEC), pp. 1\u20137, September 2016. \nhttps:\/\/doi.org\/10.1109\/HPEC.2016.7761580","DOI":"10.1109\/HPEC.2016.7761580"},{"key":"11_CR53","unstructured":"Mellanox Technologies Inc.: MellanoX Messaging Library User Manual, Rev 2.1 (2014). Document Number: 4113"},{"key":"11_CR54","unstructured":"MPI Forum: MPI-2: a message-passing interface standard. Int. J. High Perform. Comput. Appl. 12, 1\u2013299 (1998). \nhttps:\/\/www.mpi-forum.org\/docs\/mpi-2.0\/mpi-20.ps"},{"key":"11_CR55","unstructured":"MPI Forum: MPI: a message-passing interface standard, v1.1. Technical report, University of Tennessee, Knoxville, 12 June 1995. \nhttps:\/\/www.mpi-forum.org\/docs\/mpi-1.1\/mpi-11.ps"},{"key":"11_CR56","unstructured":"MPI Forum: MPI: a message-passing interface standard, version 3.0. Technical report, University of Tennessee, Knoxville, 21 September 2012. \nhttps:\/\/www.mpi-forum.org\/docs\/mpi-3.0\/mpi30-report.pdf"},{"key":"11_CR57","doi-asserted-by":"publisher","unstructured":"Murai, H., Nakao, M., Iwashita, H., Sato, M.: Preliminary performance evaluation of Coarray-based implementation of fiber Miniapp suite using XcalableMP PGAS language. In: Proceedings of the Second Annual PGAS Applications Workshop, PAW17, pp. 1:1\u20131:7. ACM (2017). \nhttps:\/\/doi.org\/10.1145\/3144779.3144780","DOI":"10.1145\/3144779.3144780"},{"key":"11_CR58","unstructured":"MVAPICH: MPI over InfiniBand, Omni-Path, Ethernet\/iWARP, and RoCE. \nhttp:\/\/mvapich.cse.ohio-state.edu"},{"key":"11_CR59","doi-asserted-by":"publisher","unstructured":"NERSC: Cori Haswell Nodes. \nhttps:\/\/doi.org\/10.25344\/S4859K\n\n. Accessed 17 July 2018","DOI":"10.25344\/S4859K"},{"key":"11_CR60","doi-asserted-by":"publisher","unstructured":"NERSC: Cori Intel Xeon Phi (KNL) Nodes. \nhttps:\/\/doi.org\/10.25344\/S4D012\n\n. Accessed 17 July 2018","DOI":"10.25344\/S4D012"},{"key":"11_CR61","unstructured":"NERSC: National Energy Research Scientific Computing Center. \nhttp:\/\/www.nersc.gov"},{"key":"11_CR62","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"533","DOI":"10.1007\/BFb0097937","volume-title":"Parallel and Distributed Processing","author":"J Nieplocha","year":"1999","unstructured":"Nieplocha, J., Carpenter, B.: ARMCI: a portable remote memory copy library for distributed array libraries and compiler run-time systems. In: Rolim, J., Mueller, F., Zomaya, A.Y., Ercal, F., Olariu, S., Ravindran, B., Gustafsson, J., Takada, H., Olsson, R., Kale, L.V., Beckman, P., Haines, M., ElGindy, H., Caromel, D., Chaumette, S., Fox, G., Pan, Y., Li, K., Yang, T., Chiola, G., Conte, G., Mancini, L.V., M\u00e9ry, D., Sanders, B., Bhatt, D., Prasanna, V. (eds.) IPPS 1999. LNCS, vol. 1586, pp. 533\u2013546. Springer, Heidelberg (1999). \nhttps:\/\/doi.org\/10.1007\/BFb0097937"},{"key":"11_CR63","doi-asserted-by":"publisher","unstructured":"Nishtala, R., Hargrove, P.H., Bonachea, D.O., Yelick, K.A.: Scaling communication-intensive applications on BlueGene\/P using one-sided communication and overlap. In: Proceedings of the International Parallel and Distributed Processing Symposium (IPDPS) (2009). \nhttps:\/\/doi.org\/10.1109\/IPDPS.2009.5161076","DOI":"10.1109\/IPDPS.2009.5161076"},{"issue":"9","key":"11_CR64","doi-asserted-by":"publisher","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., Yelick, K.A.: Tuning collective communication for Partitioned Global Address Space programming models. Parallel Comput. 37(9), 576\u2013591 (2011). \nhttps:\/\/doi.org\/10.1016\/j.parco.2011.05.006","journal-title":"Parallel Comput."},{"issue":"2","key":"11_CR65","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/289918.289920","volume":"17","author":"RW Numrich","year":"1998","unstructured":"Numrich, R.W., Reid, J.: Co-array Fortran for parallel programming. ACM SIGPLAN Fortran Forum 17(2), 1\u201331 (1998). \nhttps:\/\/doi.org\/10.1145\/289918.289920","journal-title":"ACM SIGPLAN Fortran Forum"},{"key":"11_CR66","unstructured":"Oak Ridge Leadership Computing Facility. \nhttps:\/\/www.olcf.ornl.gov"},{"key":"11_CR67","unstructured":"Summitdev. \nhttps:\/\/www.olcf.ornl.gov\/tag\/summitdev\/\n\n. Accessed 17 July 2018"},{"key":"11_CR68","unstructured":"OpenFabrics Libfabric. \nhttps:\/\/ofiwg.github.io\/libfabric\/"},{"key":"11_CR69","doi-asserted-by":"publisher","unstructured":"Petrini, F., chun Feng, W., Hoisie, A., Coll, S., Frachtenberg, E.: The Quadrics network (QsNet): high-performance clustering technology. In: HOT 9 Interconnects. Symposium on High Performance Interconnects, pp. 125\u2013130 (2001). \nhttps:\/\/doi.org\/10.1109\/HIS.2001.946704","DOI":"10.1109\/HIS.2001.946704"},{"key":"11_CR70","unstructured":"Pophale, S., Nanjegowda, R., Curtis, T., Chapman, B., Jin, H., Poole, S., Kuehn, J.: OpenSHMEM performance and potential: a NPB experimental study. In: Proceedings of the 6th Conference on Partitioned Global Address Space Programming Models (PGAS 2012) (2012). \nhttps:\/\/www.osti.gov\/biblio\/1055092"},{"key":"11_CR71","unstructured":"Shah, V.B.: An interactive system for combinatorial scientific computing with an emphasis on programmer productivity. Ph.D. thesis, University of California at Santa Barbara, Santa Barbara, CA, USA (2007)"},{"key":"11_CR72","doi-asserted-by":"publisher","unstructured":"Shamis, P., Venkata, M.G., Lopez, M.G., Baker, M.B., Hernandez, O., Itigin, Y., Dubman, M., Shainer, G., Graham, R.L., Liss, L., Shahar, Y., Potluri, S., Rossetti, D., Becker, D., Poole, D., Lamb, C., Kumar, S., Stunkel, C., Bosilca, G., Bouteiller, A.: UCX: an open source framework for HPC network APIs and beyond. In: IEEE 23rd Annual Symposium on High-Performance Interconnects, pp. 40\u201343, August 2015. \nhttps:\/\/doi.org\/10.1109\/HOTI.2015.13","DOI":"10.1109\/HOTI.2015.13"},{"key":"11_CR73","doi-asserted-by":"publisher","unstructured":"Su, H., Gordon, B., Oral, S., George, A.: SCI networking for shared-memory computing in UPC: blueprints of the GASNet SCI conduit. In: Proceedings of the 29th Annual IEEE International Conference on Local Computer Networks. LCN 2004, pp. 718\u2013725. IEEE Computer Society, Washington, DC (2004). \nhttps:\/\/doi.org\/10.1109\/LCN.2004.107","DOI":"10.1109\/LCN.2004.107"},{"key":"11_CR74","unstructured":"UCX: Unified Communication X. \nhttp:\/\/www.openucx.org\/"},{"key":"11_CR75","doi-asserted-by":"publisher","unstructured":"UPC Consortium: UPC Language and Library Specifications, v1.3. Technical report, LBNL-6623E, Lawrence Berkeley National Laboratory, November 2013. \nhttps:\/\/doi.org\/10.2172\/1134233","DOI":"10.2172\/1134233"},{"key":"11_CR76","unstructured":"Vetter, S., Caldeira, A., Kahle, M.E., Saverimuthu, G., Vearner, K.C.: IBM Power System S822LC Technical Overview and Introduction, December 2015. IBM Form #REDP-5283-00"},{"key":"11_CR77","doi-asserted-by":"publisher","unstructured":"Willenberg, R., Chow, P.: A heterogeneous GASNet implementation for FPGA-accelerated computing. In: Proceedings of the 8th International Conference on Partitioned Global Address Space Programming Models, PGAS 2014, pp. 2:1\u20132:9. ACM, New York (2014). \nhttps:\/\/doi.org\/10.1145\/2676870.2676885","DOI":"10.1145\/2676870.2676885"},{"issue":"3","key":"11_CR78","doi-asserted-by":"publisher","first-page":"266","DOI":"10.1177\/1094342007078449","volume":"21","author":"K Yelick","year":"2007","unstructured":"Yelick, K., Hilfinger, P., Graham, S., Bonachea, D., Su, J., Kamil, A., Datta, K., Colella, P., Wen, T.: Parallel languages and compilers: perspective from the Titanium experience. Int. J. High Perform. Comput. Appl. 21(3), 266\u2013290 (2007). \nhttps:\/\/doi.org\/10.1177\/1094342007078449","journal-title":"Int. J. High Perform. Comput. Appl."},{"key":"11_CR79","doi-asserted-by":"publisher","unstructured":"Zheng, Y., Kamil, A., Driscoll, M.B., Shan, H., Yelick, K.: UPC++: a PGAS extension for C++. In: IEEE 28th International Parallel and Distributed Processing Symposium, pp. 1105\u20131114, May 2014. \nhttps:\/\/doi.org\/10.1109\/IPDPS.2014.115","DOI":"10.1109\/IPDPS.2014.115"},{"key":"11_CR80","doi-asserted-by":"publisher","unstructured":"Zhou, H., Mhedheb, Y., Idrees, K., Glass, C.W., Gracia, J., F\u00fcrlinger, K.: DART-MPI: an MPI-based implementation of a PGAS runtime system. In: Proceedings of the 8th International Conference on Partitioned Global Address Space Programming Models, PGAS 2014, pp. 3:1\u20133:11 (2014). \nhttps:\/\/doi.org\/10.1145\/2676870.2676875","DOI":"10.1145\/2676870.2676875"}],"container-title":["Lecture Notes in Computer Science","Languages and Compilers for Parallel Computing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-34627-0_11","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,11,12]],"date-time":"2019-11-12T09:04:38Z","timestamp":1573549478000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-34627-0_11"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030346263","9783030346270"],"references-count":80,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-34627-0_11","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019]]},"assertion":[{"value":"13 November 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"LCPC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Workshop on Languages and Compilers for Parallel Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Salt Lake City, UT","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"USA","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2018","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9 October 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11 October 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"31","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"lcpc2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.lcpcworkshop.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Confy","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"26","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"14","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"54% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"2","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"2","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}