{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T00:50:04Z","timestamp":1740099004175,"version":"3.37.3"},"publisher-location":"Cham","reference-count":12,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319738130"},{"type":"electronic","value":"9783319738147"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"unspecified","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":[[2018]]},"DOI":"10.1007\/978-3-319-73814-7_10","type":"book-chapter","created":{"date-parts":[[2018,1,9]],"date-time":"2018-01-09T04:59:13Z","timestamp":1515473953000},"page":"143-158","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Exploiting and Evaluating OpenSHMEM on KNL Architecture"],"prefix":"10.1007","author":[{"given":"Jahanzeb Maqbool","family":"Hashmi","sequence":"first","affiliation":[]},{"given":"Mingzhe","family":"Li","sequence":"additional","affiliation":[]},{"given":"Hari","family":"Subramoni","sequence":"additional","affiliation":[]},{"given":"Dhabaleswar K.","family":"Panda","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2018,1,10]]},"reference":[{"key":"10_CR1","unstructured":"OSU Micro-Benchmarks (2015)"},{"key":"10_CR2","unstructured":"TACC Stampede KNL Cluster (2017). \nhttps:\/\/portal.tacc.utexas.edu\/user-guides\/stampede"},{"key":"10_CR3","doi-asserted-by":"crossref","unstructured":"Barnes, T., Cook, B., Deslippe, J., Doerfler, D., Friesen, B., He, Y., Kurth, T., Koskela, T., Lobet, M., Malas, T., et al.: Evaluating and optimizing the NERSC workload on knights landing. In: International Workshop on Performance Modeling, Benchmarking and Simulation of High Performance Computer Systems (PMBS), pp. 43\u201353. IEEE (2016)","DOI":"10.1109\/PMBS.2016.010"},{"key":"10_CR4","unstructured":"Cantalupo, C., Venkatesan, V., Hammond, J., Czurlyo, K., Hammond, S.D.: Memkind: An Extensible Heap Memory Manager for Heterogeneous Memory Platforms and Mixed Memory Policies. Technical report, Sandia National Laboratories (SNL-NM), Albuquerque, NM (United States) (2015)"},{"key":"10_CR5","doi-asserted-by":"crossref","unstructured":"Cong, G., Almasi, G., Saraswat, V.: Fast PGAS implementation of distributed graph algorithms. In: Proceedings of the 2010 ACM\/IEEE International Conference for High Performance Computing, Networking, Storage and Analysis, SC 2010, pp. 1\u201311. IEEE Computer Society, Washington, DC (2010)","DOI":"10.1109\/SC.2010.26"},{"key":"10_CR6","doi-asserted-by":"crossref","unstructured":"Doerfler, D., Deslippe, J., Williams, S., Oliker, L., Cook, B., Kurth, T., Lobet, M., Malas, T., Vay, J.-L., Vincenti, H.: Applying the roofline performance model to the intel xeon phi knights landing processor. In: Intel Xeon Phi User\u2019s Group (IXPUG 2016) (2016)","DOI":"10.1007\/978-3-319-46079-6_24"},{"key":"10_CR7","unstructured":"Kandalla, K., Mendygral, P., Radcliffe, N., Cernohous, B., Knaak, D., McMahon, K., Pagel, M.: Optimizing Cray MPI and SHMEM Software Stacks for Cray-XC Supercomputers based on Intel KNL Processors (2016)"},{"key":"10_CR8","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"164","DOI":"10.1007\/978-3-319-26428-8_11","volume-title":"OpenSHMEM and Related Technologies. Experiences, Implementations, and Technologies","author":"J Lin","year":"2015","unstructured":"Lin, J., Hamidouche, K., Zhang, J., Lu, X., Vishnu, A., Panda, D.: Accelerating k-NN algorithm with hybrid MPI and OpenSHMEM. In: Gorentla Venkata, M., Shamis, P., Imam, N., Lopez, M.G. (eds.) OpenSHMEM 2014. LNCS, vol. 9397, pp. 164\u2013177. Springer, Cham (2015). \nhttps:\/\/doi.org\/10.1007\/978-3-319-26428-8_11"},{"key":"10_CR9","unstructured":"Memory Latency on the Intel Xeon Phi x200 Knights Landing processor. \nhttps:\/\/sites.utexas.edu\/jdm4372\/2016\/12\/06\/memory-latency-on-the-intel-xeon-phi-x200-knights-landing-processor\/"},{"key":"10_CR10","doi-asserted-by":"crossref","unstructured":"Potluri, S., Venkatesh, A., Bureddy, D., Kandalla, K., Panda, D.K.: Efficient intra-node communication on intel-MIC clusters. In: 13th IEEE International Symposium on Cluster Computing and the Grid (CCGrid 2013) (2013)","DOI":"10.1109\/CCGrid.2013.86"},{"key":"10_CR11","doi-asserted-by":"crossref","unstructured":"Zhang, J., Behzad, B., Snir, M.: Optimizing the Barnes-Hut algorithm in UPC. In: Proceedings of 2011 International Conference for High Performance Computing, Networking, Storage and Analysis, SC 2011, pp. 75:1\u201375:11. ACM, New York (2011)","DOI":"10.1145\/2063384.2063485"},{"key":"10_CR12","unstructured":"Zhao, Z., Marsman, M.: Estimating the performance impact of the MCDRAM on KNL using dual-socket Ivy bridge nodes on Cray XC30. In: Cray User Group Meeting (CUG 2016) (2016)"}],"container-title":["Lecture Notes in Computer Science","OpenSHMEM and Related Technologies. Big Compute and Big Data Convergence"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-73814-7_10","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2018,1,9]],"date-time":"2018-01-09T05:02:10Z","timestamp":1515474130000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-73814-7_10"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783319738130","9783319738147"],"references-count":12,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-73814-7_10","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2018]]}}}