{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T14:08:35Z","timestamp":1766066915561,"version":"3.40.3"},"publisher-location":"Cham","reference-count":24,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319969824"},{"type":"electronic","value":"9783319969831"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018]]},"DOI":"10.1007\/978-3-319-96983-1_34","type":"book-chapter","created":{"date-parts":[[2018,7,31]],"date-time":"2018-07-31T15:50:06Z","timestamp":1533052206000},"page":"480-491","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":21,"title":["Measuring Multithreaded Message Matching Misery"],"prefix":"10.1007","author":[{"given":"Whit","family":"Schonbein","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Matthew G. F.","family":"Dosanjh","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ryan E.","family":"Grant","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Patrick G.","family":"Bridges","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,8,1]]},"reference":[{"issue":"8","key":"34_CR1","doi-asserted-by":"publisher","first-page":"239","DOI":"10.1145\/2858788.2688522","volume":"50","author":"A Amer","year":"2015","unstructured":"Amer, A., Lu, H., Wei, Y., Balaji, P., Matsuoka, S.: MPI+ threads: runtime contention and remedies. ACM SIGPLAN Not. 50(8), 239\u2013248 (2015)","journal-title":"ACM SIGPLAN Not."},{"issue":"1","key":"34_CR2","doi-asserted-by":"publisher","first-page":"49","DOI":"10.1177\/1094342009360206","volume":"24","author":"P Balaji","year":"2010","unstructured":"Balaji, P., Buntinas, D., Goodell, D., Gropp, W.D., Thakur, R.: Fine-grained multithreading support for hybrid threaded MPI programming. Int. J. High Perform. Comput. Appl. 24(1), 49\u201357 (2010)","journal-title":"Int. J. High Perform. Comput. Appl."},{"issue":"4","key":"34_CR3","doi-asserted-by":"publisher","first-page":"415","DOI":"10.1177\/1094342014552085","volume":"28","author":"BW Barrett","year":"2014","unstructured":"Barrett, B.W., Brightwell, R., Grant, R.E., Hammond, S.D., Hemmert, K.S.: An evaluation of MPI message rate on hybrid-core processors. Int. J. High Perform. Comput. Appl. 28(4), 415\u2013424 (2014)","journal-title":"Int. J. High Perform. Comput. Appl."},{"key":"34_CR4","doi-asserted-by":"crossref","unstructured":"Barrett, B.W., et al.: The Portals 4.0.2 networking programming interface (2014)","DOI":"10.2172\/1561686"},{"key":"34_CR5","doi-asserted-by":"crossref","unstructured":"Barrett, R.F., Stark, D.T., Vaughan, C.T., Grant, R.E., Olivier, S.L., Pedretti, K.T.: Toward an evolutionary task parallel integrated MPI+X programming model. In: Proceedings of the Sixth International Workshop on Programming Models and Applications for Multicores and Manycores, pp. 30\u201339. ACM (2015)","DOI":"10.1145\/2712386.2712388"},{"key":"34_CR6","doi-asserted-by":"crossref","unstructured":"Bayatpour, M., Subramoni, H., Chakraborty, S., Panda, D.K.: Adaptive and dynamic design for MPI tag matching. In: 2016 IEEE International Conference on Cluster Computing (CLUSTER), pp. 1\u201310. IEEE (2016)","DOI":"10.1109\/CLUSTER.2016.69"},{"key":"34_CR7","doi-asserted-by":"crossref","unstructured":"Bernholdt, D.E., et al.: A survey of MPI usage in the U.S. exascale computing project. Concurrency and Computation: Practice and Experience (2017, in Press)","DOI":"10.1002\/cpe.4851"},{"key":"34_CR8","doi-asserted-by":"crossref","unstructured":"Dang, H.-V., Snir, M., Gropp, W.: Towards millions of communicating threads. In: Proceedings of the 23rd European MPI Users\u2019 Group Meeting, pp. 1\u201314. ACM (2016)","DOI":"10.1145\/2966884.2966914"},{"key":"34_CR9","doi-asserted-by":"crossref","unstructured":"Derradji, S., Palfer-Sollier, T., Panziera, J.-P., Poudes, A., Atos, F.W.: The BXI interconnect architecture. In: 2015 IEEE 23rd Annual Symposium on High-Performance Interconnects (HOTI), pp. 18\u201325. IEEE (2015)","DOI":"10.1109\/HOTI.2015.15"},{"key":"34_CR10","doi-asserted-by":"crossref","unstructured":"Dosanjh, M.G., Groves, T., Grant, R.E., Brightwell, R., Bridges, P.G.: RMA-MT: a benchmark suite for assessing MPI multi-threaded RMA performance. In: 2016 16th IEEE\/ACM International Symposium on Cluster, Cloud and Grid Computing (CCGrid), pp. 550\u2013559. IEEE (2016)","DOI":"10.1109\/CCGrid.2016.84"},{"key":"34_CR11","doi-asserted-by":"crossref","unstructured":"Ferreira, K.B., Levy, S., Pedretti, K., Grant, R.E.: Characterizing MPI matching via trace-based simulation. In: Proceedings of the 24th European MPI Users\u2019 Group Meeting, p. 8. ACM (2017)","DOI":"10.1145\/3127024.3127040"},{"key":"34_CR12","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"281","DOI":"10.1007\/978-3-319-41321-1_15","volume-title":"High Performance Computing","author":"M Flajslik","year":"2016","unstructured":"Flajslik, M., Dinan, J., Underwood, K.D.: Mitigating MPI message matching misery. In: Kunkel, J.M., Balaji, P., Dongarra, J. (eds.) ISC High Performance 2016. LNCS, vol. 9697, pp. 281\u2013299. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-41321-1_15"},{"key":"34_CR13","doi-asserted-by":"crossref","unstructured":"Klenk, B., Froning, H., Eberle, H., Dennison, L.: Relaxations for high-performance message passing on massively parallel SIMT processors. In: 31st International Parallel and Distributed Processing Symposium (IPDPS). IEEE (2017)","DOI":"10.1109\/IPDPS.2017.94"},{"key":"34_CR14","unstructured":"Lindahl, E., Hess, B., P\u00e1ll, S., Metere, A.: GROMACS 5.0 benchmarks (2017)"},{"key":"34_CR15","unstructured":"MPI Forum: MPI: a message-passing interface standard version 3.0. Technical report, University of Tennessee, Knoxville (2012)"},{"key":"34_CR16","unstructured":"Plimpton, S., Crozier, P., Thompson, A.: LAMMPS-large-scale atomic\/molecular massively parallel simulator, vol. 18. Sandia National Laboratories (2007)"},{"key":"34_CR17","unstructured":"Rodrigues, A., Murphy, R., Brightwell, R., Underwood, K.D.: Enhancing NIC performance for MPI using processing-in-memory. In: 19th IEEE International Parallel and Distributed Processing Symposium (IPDPS), p. 8\u2013pp. IEEE (2005)"},{"key":"34_CR18","doi-asserted-by":"crossref","unstructured":"Stark, D.T., Barrett, R.F., Grant, R.E., Olivier, S.L., Pedretti, K.T., Vaughan, C.T.: Early experiences co-scheduling work and communication tasks for hybrid MPI+X applications. In: Proceedings of the 2014 Workshop on Exascale MPI, pp. 9\u201319. IEEE Press (2014)","DOI":"10.1109\/ExaMPI.2014.6"},{"key":"34_CR19","unstructured":"MPICH Development Team: MPICH (2017). Accessed 30 Mar 2017"},{"key":"34_CR20","unstructured":"Open MPI Development Team: Open MPI (2017). Accessed 28 Mar 2017"},{"key":"34_CR21","doi-asserted-by":"crossref","unstructured":"Underwood, K.D., Brightwell, R.: The impact of MPI queue usage on message latency. In: International Conference on Parallel Processing (ICPP), pp. 152\u2013160. IEEE (2004)","DOI":"10.1109\/ICPP.2004.1327915"},{"key":"34_CR22","unstructured":"Underwood, K.D., Hemmert, K.S., Rodrigues, A., Murphy, R., Brightwell, R.: A hardware acceleration unit for MPI queue processing. In: 19th IEEE International Parallel and Distributed Processing Symposium (IPDPS), p. 10\u2013pp. IEEE (2005)"},{"key":"34_CR23","doi-asserted-by":"crossref","unstructured":"Vaidyanathan, K., et al.: Improving concurrency and asynchrony in multithreaded MPI applications using software offloading. In: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, p. 30. ACM (2015)","DOI":"10.1145\/2807591.2807602"},{"key":"34_CR24","doi-asserted-by":"publisher","first-page":"265","DOI":"10.1016\/j.future.2013.07.003","volume":"30","author":"JA Zounmevo","year":"2014","unstructured":"Zounmevo, J.A., Afsahi, A.: A fast and resource-conscious MPI message queue mechanism for large-scale jobs. Future Gener. Comput. Syst. 30, 265\u2013290 (2014)","journal-title":"Future Gener. Comput. Syst."}],"container-title":["Lecture Notes in Computer Science","Euro-Par 2018: Parallel Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-96983-1_34","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,1]],"date-time":"2022-08-01T01:07:43Z","timestamp":1659316063000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-319-96983-1_34"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783319969824","9783319969831"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-96983-1_34","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2018]]},"assertion":[{"value":"1 August 2018","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"Euro-Par","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Parallel Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Turin","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","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":"27 August 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"31 August 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"europar2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/europar2018.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}