{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,26]],"date-time":"2025-09-26T13:30:55Z","timestamp":1758893455890},"publisher-location":"Cham","reference-count":37,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319413204"},{"type":"electronic","value":"9783319413211"}],"license":[{"start":{"date-parts":[[2016,1,1]],"date-time":"2016-01-01T00:00:00Z","timestamp":1451606400000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2016]]},"DOI":"10.1007\/978-3-319-41321-1_17","type":"book-chapter","created":{"date-parts":[[2016,6,14]],"date-time":"2016-06-14T06:19:15Z","timestamp":1465885155000},"page":"321-339","source":"Crossref","is-referenced-by-count":14,"title":["Comparing Runtime Systems with Exascale Ambitions Using the Parallel Research Kernels"],"prefix":"10.1007","author":[{"given":"Rob F.","family":"Van der Wijngaart","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Abdullah","family":"Kayi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jeff R.","family":"Hammond","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gabriele","family":"Jost","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tom","family":"St. John","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Srinivas","family":"Sridharan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Timothy G.","family":"Mattson","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"John","family":"Abercrombie","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jacob","family":"Nelson","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2016,6,15]]},"reference":[{"key":"17_CR1","unstructured":"OpenSHMEM Specification. http:\/\/www.openshmem.org"},{"key":"17_CR2","doi-asserted-by":"crossref","unstructured":"Alverson, R., et al.: The Tera computer system. In: International Conference on Supercomputing, pp. 1\u20136. ACM, New York, NY, USA (1990)","DOI":"10.1145\/77726.255132"},{"issue":"3","key":"17_CR3","doi-asserted-by":"crossref","first-page":"63","DOI":"10.1177\/109434209100500306","volume":"5","author":"DH Bailey","year":"1991","unstructured":"Bailey, D.H., et al.: The NAS parallel benchmarks. Int. J. High Perf. Comp. Appl. 5(3), 63\u201373 (1991)","journal-title":"Int. J. High Perf. Comp. Appl."},{"key":"17_CR4","doi-asserted-by":"crossref","unstructured":"Barrett, R.F., et al.: Toward an evolutionary task parallel integrated MPI+X programming model. In: Proceedings of Sixth International Workshop on Programming Models and Applications for Multicores and Manycores, pp. 30\u201339. ACM (2015)","DOI":"10.1145\/2712386.2712388"},{"key":"17_CR5","doi-asserted-by":"crossref","unstructured":"Bauer, M., Treichler, S., Slaughter, E., Aiken, A.: Legion: expressing locality and independence with logical regions. In: Supercomputing, p. 66. IEEE Computer Society Press (2012)","DOI":"10.1109\/SC.2012.71"},{"key":"17_CR6","doi-asserted-by":"crossref","unstructured":"Belli, R., Hoefler, T.: Notified access: extending remote memory access programming models for producer-consumer synchronization. In: IPDPS, Hyderabad, India, May 2015","DOI":"10.1109\/IPDPS.2015.30"},{"key":"17_CR7","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"crossref","first-page":"194","DOI":"10.1007\/978-3-540-24644-2_13","volume-title":"Languages and Compilers for Parallel Computing","author":"K Berlin","year":"2004","unstructured":"Berlin, K., et al.: Evaluating the impact of programming language features on the performance of parallel applications on cluster architectures. In: Rauchwerger, L. (ed.) LCPC 2003. LNCS, vol. 2958, pp. 194\u2013208. Springer, Heidelberg (2004)"},{"key":"17_CR8","unstructured":"Bonachea, D., et al.: Efficient point-to-point synchronization in UPC. In: PGAS. ACM (2006)"},{"key":"17_CR9","unstructured":"Bull, J.M., Ball, C.: Point-to-point synchronisation on shared memory architectures. In: 5th European Workshop on OpenMP (2003)"},{"key":"17_CR10","doi-asserted-by":"crossref","unstructured":"Cantonnet, F., Yao, Y., Zahran, M., El-Ghazawi, T.: Productivity analysis of the UPC language. In: IPDPS, p. 254. IEEE (2004)","DOI":"10.1109\/IPDPS.2004.1303318"},{"key":"17_CR11","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"crossref","first-page":"177","DOI":"10.1007\/978-3-540-24644-2_12","volume-title":"Languages and Compilers for Parallel Computing","author":"C Coarfa","year":"2004","unstructured":"Coarfa, C., Dotsenko, Y., Eckhardt, J., Mellor-Crummey, J.: Co-array Fortran performance and potential: an NPB experimental study. In: Rauchwerger, L. (ed.) LCPC 2003. LNCS, vol. 2958, pp. 177\u2013193. Springer, Heidelberg (2004)"},{"key":"17_CR12","doi-asserted-by":"crossref","unstructured":"Coarfa, C., et al.: An evaluation of global address space languages: co-array fortran and unified parallel C. In: PPoPP, pp. 36\u201347. ACM (2005)","DOI":"10.1145\/1065944.1065950"},{"key":"17_CR13","doi-asserted-by":"crossref","unstructured":"Cook, R., Dube, E., Lee, I., Nau, L., Shereda, C., Wang, F.: Survey of novel programming models for parallelizing applications at exascale. Technical report LLNL-TR-515971, Lawrence Livermore National Laboratory (2011)","DOI":"10.2172\/1107306"},{"key":"17_CR14","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"crossref","first-page":"163","DOI":"10.1007\/978-3-319-05215-1_12","volume-title":"OpenSHMEM and Related Technologies","author":"J Dinan","year":"2014","unstructured":"Dinan, J., Cole, C., Jost, G., Smith, S., Underwood, K., Wisniewski, R.W.: Reducing synchronization overhead through bundled communication. In: Poole, S., Hernandez, O., Shamis, P. (eds.) OpenSHMEM 2014. LNCS, vol. 8356, pp. 163\u2013177. Springer, Heidelberg (2014)"},{"key":"17_CR15","doi-asserted-by":"crossref","unstructured":"Dun, N., Taura, K.: An empirical performance study of Chapel programming language. In: IPDPSW, pp. 497\u2013506. IEEE (2012)","DOI":"10.1109\/IPDPSW.2012.64"},{"key":"17_CR16","doi-asserted-by":"crossref","unstructured":"El-Ghazawi, T., Cantonnet, F.: UPC performance, potential: a NPB experimental study. In: Supercomputing, p. 17. IEEE (2002)","DOI":"10.1109\/SC.2002.10034"},{"key":"17_CR17","unstructured":"Feind, K.: Shared memory access (SHMEM) routines. In: CUG (1995)"},{"key":"17_CR18","doi-asserted-by":"crossref","unstructured":"Feo, J., et al.: Eldorado. In: Computing Frontiers, pp. 28\u201334. ACM (2005)","DOI":"10.1145\/1062261.1062268"},{"key":"17_CR19","doi-asserted-by":"crossref","unstructured":"Georganas, E., Van der Wijngaart, R.F., Mattson, T.G.: Design and implementation of a parallel research kernel for assessing dynamic load-balancing capabilities. In: Parallel and Distributed Processing, ser. IPDPS, vol. 16 (2016, to appear)","DOI":"10.1109\/IPDPS.2016.65"},{"key":"17_CR20","unstructured":"Heroux, M.A., Brightwell, R., Wolf, M.M.: Bi-modal MPI and MPI+threads computing on scalable multicore systems (2011)"},{"issue":"12","key":"17_CR21","doi-asserted-by":"crossref","first-page":"1121","DOI":"10.1007\/s00607-013-0324-2","volume":"95","author":"T Hoefler","year":"2013","unstructured":"Hoefler, T., et al.: MPI + MPI: a new hybrid approach to parallel programming with MPI plus shared memory. Computing 95(12), 1121\u20131136 (2013)","journal-title":"Computing"},{"key":"17_CR22","doi-asserted-by":"crossref","unstructured":"Kaiser, H., et al.: HPX: a task based programming model in a global address space. In : PGAS, p. 6. ACM (2014)","DOI":"10.1145\/2676870.2676883"},{"key":"17_CR23","doi-asserted-by":"crossref","unstructured":"Kale, L.V., Krishnan, S.: CHARM++: a portable concurrent object oriented system based on C++, vol. 28. ACM (1993)","DOI":"10.1145\/165854.165874"},{"key":"17_CR24","doi-asserted-by":"crossref","unstructured":"Kamal, H., Wagner, A.: FG-MPI: fine-grain MPI for multicore and clusters. In: IEEE International Symposium on Parallel and Distributed Processing, Workshops and Phd Forum (IPDPSW), pp. 1\u20138. IEEE (2010)","DOI":"10.1109\/IPDPSW.2010.5470773"},{"key":"17_CR25","doi-asserted-by":"crossref","unstructured":"Karlin, I., et al.: Exploring traditional and emerging parallel programming models using a proxy application. In: IPDPS, pp. 919\u2013932. IEEE (2013)","DOI":"10.1109\/IPDPS.2013.115"},{"key":"17_CR26","unstructured":"MPI Forum: MPI: a message-passing interface standard (1994)"},{"key":"17_CR27","unstructured":"MPI Forum: MPI-2: Extensions to the message-passing interface (1996)"},{"key":"17_CR28","unstructured":"MPI Forum: MPI: a message-passing interface standard. Version 3.0, November 2012"},{"key":"17_CR29","doi-asserted-by":"crossref","unstructured":"Nanz, S., et al.: Benchmarking usability and performance of multicore languages. In: International Symposium on Empirical Software Engineeringg. Measurement, pp. 183\u2013192. IEEE (2013)","DOI":"10.1109\/ESEM.2013.10"},{"key":"17_CR30","unstructured":"Nelson, J., Holt, B., Myers, B., Briggs, P., Ceze, L., Kahan, S., Oskin, M.: Latency-tolerant software distributed shared memory. In: 2015 USENIX Annual Technical Conference (USENIX ATC 2015). USENIX Association, Santa Clara, CA, July 2015"},{"key":"17_CR31","doi-asserted-by":"crossref","unstructured":"Patel, I., Gilbert, J.R.: An empirical study of the performance and productivity of two parallel programming models. In: IPDPS, pp. 1\u20137. IEEE (2008)","DOI":"10.1109\/IPDPS.2008.4536192"},{"issue":"2","key":"17_CR32","doi-asserted-by":"crossref","first-page":"92","DOI":"10.1145\/2381056.2381077","volume":"40","author":"H Shan","year":"2012","unstructured":"Shan, H., et al.: A preliminary evaluation of the hardware acceleration of the Cray Gemini interconnect for PGAS languages and comparison with MPI. ACM SIGMETRICS Perf. Eval. Rev. 40(2), 92\u201398 (2012)","journal-title":"ACM SIGMETRICS Perf. Eval. Rev."},{"key":"17_CR33","doi-asserted-by":"crossref","unstructured":"Shet, A.G., et al.: Programmability of the HPCS languages: a case study with a quantum chemistry kernel. In: IPDPS, pp. 1\u20138. IEEE (2008)","DOI":"10.1109\/IPDPS.2008.4536191"},{"key":"17_CR34","unstructured":"UPC Consortium: UPC lang. spec. v. 1.3, November 2013"},{"key":"17_CR35","doi-asserted-by":"crossref","unstructured":"Van der Wijngaart, R.F., et al.: Using the parallel research kernels to study PGAS models. In: PGAS. IEEE (2015)","DOI":"10.1109\/PGAS.2015.24"},{"key":"17_CR36","doi-asserted-by":"crossref","unstructured":"Van der Wijngaart, R.F., Mattson, T.G.: The parallel research kernels: a tool for architecture and programming system investigation. In: HPEC. IEEE (2014)","DOI":"10.1109\/HPEC.2014.7040972"},{"key":"17_CR37","unstructured":"Zerr, R., Baker, R.: Snap: Sn (discrete ordinates) application proxy: description. Technical report, Los Alamos National Laboratories, LAUR-13-21070 (2013)"}],"container-title":["Lecture Notes in Computer Science","High Performance Computing"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-41321-1_17","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,9,9]],"date-time":"2019-09-09T14:32:19Z","timestamp":1568039539000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-41321-1_17"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016]]},"ISBN":["9783319413204","9783319413211"],"references-count":37,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-41321-1_17","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2016]]}}}