{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,11]],"date-time":"2024-09-11T04:27:04Z","timestamp":1726028824710},"publisher-location":"Cham","reference-count":29,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030049171"},{"type":"electronic","value":"9783030049188"}],"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"},{"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\/978-3-030-04918-8_12","type":"book-chapter","created":{"date-parts":[[2019,3,18]],"date-time":"2019-03-18T06:05:44Z","timestamp":1552889144000},"page":"180-201","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Lightweight Instrumentation and Analysis Using OpenSHMEM Performance Counters"],"prefix":"10.1007","author":[{"given":"Md. Wasi-ur-","family":"Rahman","sequence":"first","affiliation":[]},{"given":"David","family":"Ozog","sequence":"additional","affiliation":[]},{"given":"James","family":"Dinan","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2019,3,19]]},"reference":[{"issue":"6","key":"12_CR1","doi-asserted-by":"crossref","first-page":"685","DOI":"10.1002\/cpe.1553","volume":"22","author":"L Adhianto","year":"2010","unstructured":"Adhianto, L., et al.: HPCTOOLKIT: tools for performance analysis of optimized parallel programs. Concurr. Comput.: Pract. Exper. 22(6), 685\u2013701 (2010). Http:\/\/hpctoolkit.Org","journal-title":"Concurr. Comput.: Pract. Exper."},{"key":"12_CR2","doi-asserted-by":"crossref","unstructured":"Barrett, B.W., Brigthwell, R., Hemmert, K.S., Pedretti, K., Wheeler, K., Underwood, K.D.: Enhanced support for openSHMEM communication in portals. In: IEEE 19th Annual Symposium on High Performance Interconnects. HotI, August 2011","DOI":"10.1109\/HOTI.2011.18"},{"key":"12_CR3","unstructured":"Brandt, J., Froese, E., Gentile, A., Kaplan, L., Allan, B., Walsh, E.: Network performance counter monitoring and analysis on the Cray XC platform. In: Proceedings of Cray Users Group (2016)"},{"key":"12_CR4","doi-asserted-by":"crossref","unstructured":"Browne, S., Dongarra, J., Garner, N., London, K., Mucci, P.: A scalable cross-platform infrastructure for application performance tuning using hardware counters. In: Proceedings of the 2000 ACM\/IEEE Conference on Supercomputing. SC 2000, IEEE Computer Society, Washington, DC, USA (2000)","DOI":"10.1109\/SC.2000.10029"},{"key":"12_CR5","doi-asserted-by":"crossref","unstructured":"Cong, G., Wen, H., Murata, H., Negishi, Y.: Tool-assisted optimization of shared-memory accesses in UPC applications. In: IEEE International Conference on High Performance Computing and Communication & IEEE International Conference on Embedded Software and Systems, (HPCC-ICESS), pp. 104\u2013111, June 2012","DOI":"10.1109\/HPCC.2012.24"},{"key":"12_CR6","doi-asserted-by":"publisher","first-page":"191","DOI":"10.1007\/978-3-540-68564-7_12","volume-title":"Tools for High Performance Computing","author":"L DeRose","year":"2008","unstructured":"DeRose, L., Homer, B., Johnson, D., Kaufmann, S., Poxon, H.: Cray performance analysis tools. In: Resch, M., Keller, R., Himmler, V., Krammer, B., Schulz, A. (eds.) Tools for High Performance Computing, pp. 191\u2013199. Springer, Heidelberg (2008). https:\/\/doi.org\/10.1007\/978-3-540-68564-7_12"},{"key":"12_CR7","unstructured":"Eschweiler, D., Wagner, M., Geimer, M., Knpfer, A., Nagel, W., Wolf, F.: Open trace format 2: The next generation of scalable trace formats and support libraries. In: Applications, Tools and Techniques on the Road to Exascale Computing. vol. 22, pp. 481\u2013490, January 2012"},{"key":"12_CR8","doi-asserted-by":"crossref","unstructured":"Grun, P., et al.: A brief introduction to the openfabrics interfaces - a new network API for maximizing high performance application efficiency. In: 2015 IEEE 23rd Annual Symposium on High-Performance Interconnects, pp. 34\u201339, August 2015","DOI":"10.1109\/HOTI.2015.19"},{"key":"12_CR9","doi-asserted-by":"crossref","unstructured":"Hanebutte, U., Hemstad, J.: ISx: A scalable integer sort for co-design in the exascale era. In: 2015 9th International Conference on Partitioned Global Address Space Programming Models (PGAS), pp. 102\u2013104, September 2015","DOI":"10.1109\/PGAS.2015.21"},{"key":"12_CR10","doi-asserted-by":"crossref","unstructured":"Hanebutte, U., Hemstad, J.: ISx: a scalable integer sort for co-design in the exascale era. In: 9th International Conference on Partitioned Global Address Space Programming Models. pp. 102\u2013104, September 2015","DOI":"10.1109\/PGAS.2015.21"},{"key":"12_CR11","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1007\/978-3-642-03770-2_10","volume-title":"Recent Advances in Parallel Virtual Machine and Message Passing Interface","author":"M-A Hermanns","year":"2009","unstructured":"Hermanns, M.-A., Geimer, M., Mohr, B., Wolf, F.: Scalable detection of MPI-2 remote memory access inefficiency patterns. In: Ropo, M., Westerholm, J., Dongarra, J. (eds.) EuroPVM\/MPI 2009. LNCS, vol. 5759, pp. 31\u201341. Springer, Heidelberg (2009). https:\/\/doi.org\/10.1007\/978-3-642-03770-2_10"},{"key":"12_CR12","doi-asserted-by":"publisher","first-page":"79","DOI":"10.1007\/978-3-642-31476-6_7","volume-title":"Tools for High Performance Computing","author":"A Kn\u00fcpfer","year":"2012","unstructured":"Kn\u00fcpfer, A., et al.: Score-P: a joint performance measurement run-time infrastructure for periscope, scalasca, TAU, and vampir. Tools for High Performance Computing, pp. 79\u201391. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-31476-6_7"},{"key":"12_CR13","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"105","DOI":"10.1007\/978-3-319-05215-1_8","volume-title":"OpenSHMEM and Related Technologies. Experiences, Implementations, and Tools","author":"J Linford","year":"2014","unstructured":"Linford, J., Simon, T.A., Shende, S., Malony, A.D.: Profiling non-numeric OpenSHMEM applications with the TAU performance system. In: Poole, S., Hernandez, O., Shamis, P. (eds.) OpenSHMEM 2014. LNCS, vol. 8356, pp. 105\u2013119. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-05215-1_8"},{"key":"12_CR14","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"161","DOI":"10.1007\/978-3-319-73814-7_11","volume-title":"OpenSHMEM and Related Technologies. Big Compute and Big Data Convergence","author":"JC Linford","year":"2018","unstructured":"Linford, J.C., Khuvis, S., Shende, S., Malony, A., Imam, N., Venkata, M.G.: Performance analysis of openSHMEM applications with TAU commander. In: Gorentla Venkata, M., Imam, N., Pophale, S. (eds.) OpenSHMEM 2017. LNCS, vol. 10679, pp. 161\u2013179. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-319-73814-7_11"},{"key":"12_CR15","unstructured":"Mohr, B., K\u00fchnal, A., Hermanns, M., Wolf, F.: Performance analysis of one-sided communication mechanisms. In: Joubert, G.R., Nagel, W.E., Peters, F.J., Plata, O.G., Tirado, P., Zapata, E.L. (eds.) Parallel Computing: Current & Future Issues of High-End Computing, Proceedings of the International Conference ParCo 2005. John von Neumann Institute for Computing Series, 13\u201316 September 2005, Department of Computer Architecture, University of Malaga, Spain, vol. 33, pp. 885\u2013892. Central Institute for Applied Mathematics, J\u00fclich (2005)"},{"key":"12_CR16","unstructured":"MPI Forum: MPI: A message-passing interface standard version 3.1. Technical report, University of Tennessee, Knoxville, June 2015"},{"key":"12_CR17","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"90","DOI":"10.1007\/978-3-319-05215-1_7","volume-title":"OpenSHMEM and Related Technologies. Experiences, Implementations, and Tools","author":"S Oeste","year":"2014","unstructured":"Oeste, S., Kn\u00fcpfer, A., Ilsche, T.: Towards parallel performance analysis tools for the openSHMEM standard. In: Poole, S., Hernandez, O., Shamis, P. (eds.) OpenSHMEM 2014. LNCS, vol. 8356, pp. 90\u2013104. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-05215-1_7"},{"key":"12_CR18","unstructured":"OpenSHMEM application programming interface, version 1.3., February 2016. http:\/\/www.openshmem.org"},{"key":"12_CR19","unstructured":"OpenSHMEM application programming interface, version 1.4., December 2017. http:\/\/www.openshmem.org"},{"key":"12_CR20","unstructured":"Pedretti, K., Vaughan, C.T., Barrett, R.F., Devine, K.D., Hemmert, K.S.: Using the Cray Gemini performance counters. In: Proceedings of the Cray Users Group (2013)"},{"key":"12_CR21","unstructured":"Portals 4.0. http:\/\/www.cs.sandia.gov\/Portals\/portals4.html"},{"key":"12_CR22","unstructured":"Performance Scaled Messaging 2 (PSM2) Programmer\u2019s Guide, October 2017. https:\/\/intel.ly\/2y2uvjb"},{"key":"12_CR23","unstructured":"Sandia OpenSHMEM (2018). https:\/\/github.com\/Sandia-OpenSHMEM\/SOS"},{"key":"12_CR24","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"97","DOI":"10.1007\/978-3-319-50995-2_7","volume-title":"OpenSHMEM and Related Technologies. Enhancing OpenSHMEM for Hybrid Environments","author":"K Seager","year":"2016","unstructured":"Seager, K., Choi, S.-E., Dinan, J., Pritchard, H., Sur, S.: Design and implementation of openSHMEM using OFI on the aries interconnect. In: Gorentla Venkata, M., Imam, N., Pophale, S., Mintz, T.M. (eds.) OpenSHMEM 2016. LNCS, vol. 10007, pp. 97\u2013113. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-50995-2_7"},{"issue":"4","key":"12_CR25","doi-asserted-by":"publisher","first-page":"485","DOI":"10.1177\/1094342010370953","volume":"24","author":"HH Su","year":"2010","unstructured":"Su, H.H., Billingsley, M., George, A.D.: Parallel performance wizard: a performance system for the analysis of partitioned global-address-space applications. Int. J. High Perform. Comput. Appl. 24(4), 485\u2013510 (2010)","journal-title":"Int. J. High Perform. Comput. Appl."},{"key":"12_CR26","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"450","DOI":"10.1007\/978-3-540-75755-9_54","volume-title":"Applied Parallel Computing. State of the Art in Scientific Computing","author":"H-H Su","year":"2007","unstructured":"Su, H.-H., Bonachea, D., Leko, A., Sherburne, H., Billingsley, M., George, A.D.: GASP! a standardized performance analysis tool interface for global address space programming models. In: K\u00e5gstr\u00f6m, B., Elmroth, E., Dongarra, J., Wa\u015bniewski, J. (eds.) PARA 2006. LNCS, vol. 4699, pp. 450\u2013459. Springer, Heidelberg (2007). https:\/\/doi.org\/10.1007\/978-3-540-75755-9_54"},{"key":"12_CR27","doi-asserted-by":"crossref","unstructured":"Tallent, N.R., Vishnu, A., Van Dam, H., Daily, J., Kerbyson, D.J., Hoisie, A.: Diagnosing the causes and severity of one-sided message contention. In: Proceedings of the 20th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming, PPoPP 2015, pp. 130\u2013139. ACM, New York, NY, USA (2015)","DOI":"10.1145\/2688500.2688516"},{"key":"12_CR28","doi-asserted-by":"crossref","unstructured":"UPC Consortium: UPC language and library specifications, v1.3. Technical Report LBNL-6623E, Lawrence Berkeley National Lab, November 2013","DOI":"10.2172\/1134233"},{"key":"12_CR29","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"321","DOI":"10.1007\/978-3-319-41321-1_17","volume-title":"High Performance Computing","author":"RF Van der Wijngaart","year":"2016","unstructured":"Van der Wijngaart, R.F., et al.: Comparing runtime systems with exascale ambitions using the parallel research Kernels. In: Kunkel, J.M., Balaji, P., Dongarra, J. (eds.) ISC High Performance 2016. LNCS, vol. 9697, pp. 321\u2013339. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-41321-1_17"}],"container-title":["Lecture Notes in Computer Science","OpenSHMEM and Related Technologies. OpenSHMEM in the Era of Extreme Heterogeneity"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-04918-8_12","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,14]],"date-time":"2023-09-14T12:23:52Z","timestamp":1694694232000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-04918-8_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030049171","9783030049188"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-04918-8_12","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2019]]},"assertion":[{"value":"19 March 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"OpenSHMEM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Workshop on OpenSHMEM and Related Technologies","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Baltimore, MD","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":"21 August 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 August 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"openshmem2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.csm.ornl.gov\/workshops\/openshmem2018\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}