{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T18:58:43Z","timestamp":1743101923974,"version":"3.40.3"},"publisher-location":"Cham","reference-count":32,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030787127"},{"type":"electronic","value":"9783030787134"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"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":[[2021]]},"DOI":"10.1007\/978-3-030-78713-4_17","type":"book-chapter","created":{"date-parts":[[2021,6,16]],"date-time":"2021-06-16T23:06:15Z","timestamp":1623884775000},"page":"313-331","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Optimizing GPU-Enhanced HPC System and Cloud Procurements for Scientific Workloads"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7304-6056","authenticated-orcid":false,"given":"Richard Todd","family":"Evans","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Matthew","family":"Cawood","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5327-525X","authenticated-orcid":false,"given":"Stephen Lien","family":"Harrell","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lei","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0171-9124","authenticated-orcid":false,"given":"Si","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chun-Yaung","family":"Lu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6547-714X","authenticated-orcid":false,"given":"Amit","family":"Ruhela","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8505-0223","authenticated-orcid":false,"given":"Yinzhi","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5921-0035","authenticated-orcid":false,"given":"Zhao","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,6,17]]},"reference":[{"key":"17_CR1","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"469","DOI":"10.1007\/978-3-319-21909-7_45","volume-title":"Parallel Computing Technologies","author":"VV Stegailov","year":"2015","unstructured":"Stegailov, V.V., Orekhov, N.D., Smirnov, G.S.: HPC hardware efficiency for quantum and classical molecular dynamics. In: Malyshkin, V. (ed.) PaCT 2015. LNCS, vol. 9251, pp. 469\u2013473. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-21909-7_45"},{"key":"17_CR2","unstructured":"Bauer, G., Hoefler, T., Kramer, W., Fiedler, B.: Analyses and modeling of applications used to demonstrate sustained petascale performance on Blue Waters. Cray User Group, May 2012"},{"key":"17_CR3","unstructured":"Evans, R.T.: Application performance in the frontera acceptance process. In: 2020 ACM SIGHPC SYSPROS Workshop (2020)"},{"key":"17_CR4","unstructured":"Tsai, Y.M., Cojean, T., Anzt, H.: Evaluating the performance of NVIDIA\u2019s a100 Ampere GPU for sparse linear algebra computations (2020)"},{"key":"17_CR5","doi-asserted-by":"publisher","first-page":"947","DOI":"10.1016\/j.future.2017.08.007","volume":"92","author":"S Pennycook","year":"2019","unstructured":"Pennycook, S., Sewall, J., Lee, V.: Implications of a metric for performance portability. Future Gener. Comput. Syst. 92, 947\u2013958 (2019)","journal-title":"Future Gener. Comput. Syst."},{"key":"17_CR6","unstructured":"NVIDIA: NVIDIA HPC application performance. https:\/\/developer.nvidia.com\/hpc-application-performance. Accessed 17 May 2021"},{"key":"17_CR7","unstructured":"GROMACS (2020). http:\/\/www.gromacs.org. Accessed 17 May 2021"},{"key":"17_CR8","doi-asserted-by":"crossref","unstructured":"Kutzner, C., P\u00e1ll, S., Fechner, M., Esztermann, A., de Groot, B.L., Grubm\u00fcller, H.: More bang for your buck: improved use of GPU nodes for GROMACS 2018 (2019)","DOI":"10.1002\/jcc.26011"},{"key":"17_CR9","unstructured":"Case, D.A.: AMBER 2020. University of California, San Francisco (2020)"},{"issue":"2\u20133","key":"17_CR10","doi-asserted-by":"publisher","first-page":"390","DOI":"10.1016\/j.jmb.2012.02.004","volume":"421","author":"D Matthes","year":"2012","unstructured":"Matthes, D., Gapsys, V., de Groot, B.L.: Driving forces and structural determinants of steric zipper peptide oligomer formation elucidated by atomistic simulations. J. Mol. Biol. 421(2\u20133), 390\u2013416 (2012)","journal-title":"J. Mol. Biol."},{"key":"17_CR11","unstructured":"Kutzner, C.: A free GROMACS benchmark set. https:\/\/www.mpibpc.mpg.de\/grubmueller\/bench. Accessed 17 May 2021"},{"key":"17_CR12","doi-asserted-by":"crossref","unstructured":"Plimpton, S.: Fast parallel algorithms for short-range molecular dynamics. J. Comput. Phys. 117(1), 1\u201319 (1995). http:\/\/www.sciencedirect.com\/science\/article\/pii\/S002199918571039X","DOI":"10.1006\/jcph.1995.1039"},{"issue":"12","key":"17_CR13","doi-asserted-by":"publisher","first-page":"3202","DOI":"10.1016\/j.jpdc.2014.07.003","volume":"74","author":"HC Edwards","year":"2014","unstructured":"Edwards, H.C., Trott, C.R., Sunderland, D.: Kokkos: enabling manycore performance portability through polymorphic memory access patterns. J. Parallel Distrib. Comput. 74(12), 3202\u20133216 (2014)","journal-title":"J. Parallel Distrib. Comput."},{"key":"17_CR14","doi-asserted-by":"publisher","first-page":"316","DOI":"10.1016\/j.jcp.2014.12.018","volume":"285","author":"A Thompson","year":"2015","unstructured":"Thompson, A., Swiler, L., Trott, C., Foiles, S., Tucker, G.: Spectral neighbor analysis method for automated generation of quantum-accurate interatomic potentials. J. Comput. Phys. 285, 316\u2013330 (2015)","journal-title":"J. Comput. Phys."},{"issue":"26","key":"17_CR15","doi-asserted-by":"publisher","first-page":"5456","DOI":"10.1021\/acs.jpca.0c02450","volume":"124","author":"MA Cusentino","year":"2020","unstructured":"Cusentino, M.A., Wood, M.A., Thompson, A.P.: Explicit multielement extension of the spectral neighbor analysis potential for chemically complex systems. J. Phys. Chem. A 124(26), 5456\u20135464 (2020)","journal-title":"J. Phys. Chem. A"},{"key":"17_CR16","unstructured":"The MIMD Lattice Computation (MILC) Collaboration (2020). http:\/\/www.physics.utah.edu\/detar\/milc. Accessed 17 May 2021"},{"issue":"9","key":"17_CR17","doi-asserted-by":"publisher","first-page":"1517","DOI":"10.1016\/j.cpc.2010.05.002","volume":"181","author":"M Clark","year":"2010","unstructured":"Clark, M., Babich, R., Barros, K., Brower, R., Rebbi, C.: Solving lattice QCD systems of equations using mixed precision solvers on GPUs. Comput. Phys. Commun. 181(9), 1517\u20131528 (2010)","journal-title":"Comput. Phys. Commun."},{"key":"17_CR18","unstructured":"NERSC (2020). https:\/\/github.com\/lattice\/quda\/wiki\/Running-the-NERSC-MILC-Benchmarks. Accessed 17 May 2021"},{"issue":"16","key":"17_CR19","doi-asserted-by":"publisher","first-page":"1781","DOI":"10.1002\/jcc.20289","volume":"26","author":"JC Phillips","year":"2005","unstructured":"Phillips, J.C., et al.: Scalable molecular dynamics with NAMD. J. Comput. Chem. 26(16), 1781\u20131802 (2005)","journal-title":"J. Comput. Chem."},{"key":"17_CR20","doi-asserted-by":"crossref","unstructured":"You, Y., Hseu, J., Ying, C., Demmel, J., Keutzer, K., Hsieh, C.J.: Large-batch training for LSTM and beyond. In: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, SC 2019. Association for Computing Machinery, New York (2019)","DOI":"10.1145\/3295500.3356137"},{"key":"17_CR21","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"17_CR22","doi-asserted-by":"crossref","unstructured":"Pauloski, J.G., Zhang, Z., Huang, L., Xu, W., Foster, I.T.: Convolutional neural network training with distributed K-FAC. In: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, pp. 1\u201314 (2020)","DOI":"10.1109\/SC41405.2020.00098"},{"key":"17_CR23","unstructured":"MLCommons. https:\/\/www.mlperf.org. Accessed 17 May 2021"},{"issue":"3","key":"17_CR24","doi-asserted-by":"publisher","first-page":"806","DOI":"10.1046\/j.1365-246x.1999.00967.x","volume":"139","author":"D Komatitsch","year":"1999","unstructured":"Komatitsch, D., Tromp, J.: Introduction to the spectral element method for three-dimensional seismic wave propagation. Geophys. J. Int. 139(3), 806\u2013822 (1999)","journal-title":"Geophys. J. Int."},{"key":"17_CR25","unstructured":"NVIDIA: SPECFEM3d globe GPU & software configurations from NVIDIA data center. https:\/\/www.nvidia.com\/en-sg\/data-center\/gpu-accelerated-applications\/specfem3d-globe\/. Accessed 17 May 2021"},{"issue":"5","key":"17_CR26","doi-asserted-by":"publisher","first-page":"055703","DOI":"10.1063\/1.2840133","volume":"15","author":"KJ Bowers","year":"2008","unstructured":"Bowers, K.J., Albright, B.J., Yin, L., Bergen, B., Kwan, T.J.T.: Ultrahigh performance three-dimensional electromagnetic relativistic kinetic plasma simulation. Phys. Plasmas 15(5), 055703 (2008)","journal-title":"Phys. Plasmas"},{"key":"17_CR27","doi-asserted-by":"crossref","unstructured":"Bowers, K.J., et al.: Advances in petascale kinetic plasma simulation with VPIC and Roadrunner. In: Journal of Physics: Conference Series, vol. 180, p. 012055, July 2009","DOI":"10.1088\/1742-6596\/180\/1\/012055"},{"key":"17_CR28","unstructured":"Byna, S., Sisneros, R., Chadalavada, K., Koziol, Q.: Tuning parallel I\/O on blue waters for writing 10 trillion particles. In: Cray User Group (CUG) 2015. Citeseer, April 2015"},{"key":"17_CR29","doi-asserted-by":"crossref","unstructured":"Harrell, S.L., et al.: Effective performance portability. In: 2018 IEEE\/ACM International Workshop on Performance, Portability and Productivity in HPC (P3HPC), pp. 24\u201336 (2018)","DOI":"10.1109\/P3HPC.2018.00006"},{"key":"17_CR30","unstructured":"Skamarock, W., et al.: A description of the advanced research WRF. NCAR Technical Notes (2018). https:\/\/opensky.ucar.edu\/islandora\/object\/technotes:500"},{"key":"17_CR31","unstructured":"TQI: WRFg - GPU Accelerated WRF. https:\/\/wrfg.net\/. Accessed 17 May 2021"},{"key":"17_CR32","unstructured":"The National Center for Atmospheric Research: CISL High-Performance Computing (HPC) Benchmarks (2010). https:\/\/www2.cisl.ucar.edu\/hpc_benchmarking"}],"container-title":["Lecture Notes in Computer Science","High Performance Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-78713-4_17","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,3,29]],"date-time":"2023-03-29T07:07:14Z","timestamp":1680073634000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-78713-4_17"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030787127","9783030787134"],"references-count":32,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-78713-4_17","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"17 June 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ISC High Performance","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on High Performance Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24 June 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 July 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"36","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"supercomputing2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.isc-hpc.com\/","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":"Linklings","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"74","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":"24","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":"32% - 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":"4.28","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":"4.13","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":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"In the ISC High Performance Workshop, there were 49 submissions, out of which 35  were accepted.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}