{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,24]],"date-time":"2025-08-24T01:32:27Z","timestamp":1755999147078,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":58,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,7,11]],"date-time":"2022-07-11T00:00:00Z","timestamp":1657497600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100000015","name":"DOE U.S. Department of Energy","doi-asserted-by":"publisher","award":["DE-NA0003525"],"award-info":[{"award-number":["DE-NA0003525"]}],"id":[{"id":"10.13039\/100000015","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"NSF (National Science Foundation)","doi-asserted-by":"publisher","award":["CCF-1824303, CCF-1845146, CCF-2121744, CCF-1733873, CMMI-1938909, CCF-2106699, CCF-1733873, SPX-1725647, CCF-2118832, CCF-2106827, CSR-1763680, CCF-1716252, CNS-1938709, CCF-1725543"],"award-info":[{"award-number":["CCF-1824303, CCF-1845146, CCF-2121744, CCF-1733873, CMMI-1938909, CCF-2106699, CCF-1733873, SPX-1725647, CCF-2118832, CCF-2106827, CSR-1763680, CCF-1716252, CNS-1938709, CCF-1725543"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100006785","name":"Google","doi-asserted-by":"publisher","award":["Google Research Award"],"award-info":[{"award-number":["Google Research Award"]}],"id":[{"id":"10.13039\/100006785","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,7,11]]},"DOI":"10.1145\/3490148.3538570","type":"proceedings-article","created":{"date-parts":[[2022,7,10]],"date-time":"2022-07-10T22:10:15Z","timestamp":1657491015000},"page":"147-159","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["Automatic HBM Management"],"prefix":"10.1145","author":[{"given":"Daniel","family":"DeLayo","sequence":"first","affiliation":[{"name":"Stony Brook University, Stony Brook, NY, USA"}]},{"given":"Kenny","family":"Zhang","sequence":"additional","affiliation":[{"name":"Stony Brook University, Stony Brook, NY, USA"}]},{"given":"Kunal","family":"Agrawal","sequence":"additional","affiliation":[{"name":"Washington University in St. Louis, St. Louis, MO, USA"}]},{"given":"Michael A.","family":"Bender","sequence":"additional","affiliation":[{"name":"Stony Brook University, Stony Brook, NY, USA"}]},{"given":"Jonathan W.","family":"Berry","sequence":"additional","affiliation":[{"name":"Sandia National Laboratories, Albuquerque, NM, USA"}]},{"given":"Rathish","family":"Das","sequence":"additional","affiliation":[{"name":"University of Waterloo, Waterloo, ON, Canada"}]},{"given":"Benjamin","family":"Moseley","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University, Pittsburgh, PA, USA"}]},{"given":"Cynthia A.","family":"Phillips","sequence":"additional","affiliation":[{"name":"Sandia National Laboratories, Albuquerque, NM, USA"}]}],"member":"320","published-online":{"date-parts":[[2022,7,11]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/28395.28428"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"crossref","unstructured":"A. Aggarwal A.K. Chandra and M. Snir. 1990. Communication Complexity of PRAMs. Theoretical Computer Science (March 1990) 3--28.  A. Aggarwal A.K. Chandra and M. Snir. 1990. Communication Complexity of PRAMs. Theoretical Computer Science (March 1990) 3--28.","DOI":"10.1016\/0304-3975(90)90188-N"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/48529.48535"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3350755.3400231"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3490148.3538577"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611976465.180"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3409964.3461802"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/SFCS.1996.548514"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00453-001-0071-1"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/1378533.1378573"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPEC43674.2020.9286174"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2015.94"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2016.12.009"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3323165.3323210"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.5555\/1347082.1347137"},{"volume-title":"Online Computation and Competitive Analysis","author":"Borodin Allan","key":"e_1_3_2_1_16_1","unstructured":"Allan Borodin and Ran El-Yaniv . 1998. Online Computation and Competitive Analysis . Cambridge University Press . Allan Borodin and Ran El-Yaniv. 1998. Online Computation and Competitive Analysis .Cambridge University Press."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/103418.103422"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1137\/110848244"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3225058.3225116"},{"key":"e_1_3_2_1_20_1","volume-title":"et almbox","author":"Byun Chansup","year":"2017","unstructured":"Chansup Byun , Jeremy Kepner , William Arcand , David Bestor , Bill Bergeron , Vijay Gadepally , Michael Houle , Matthew Hubbell , Michael Jones , Anna Klein , et almbox . 2017 . Benchmarking data analysis and machine learning applications on the Intel KNL many-core processor. arXiv preprint arXiv:1707.03515 (2017). Chansup Byun, Jeremy Kepner, William Arcand, David Bestor, Bill Bergeron, Vijay Gadepally, Michael Houle, Matthew Hubbell, Michael Jones, Anna Klein, et almbox. 2017. Benchmarking data analysis and machine learning applications on the Intel KNL many-core processor. arXiv preprint arXiv:1707.03515 (2017)."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/1248377.1248396"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3276493"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3350755.3400233"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3323165.3323209"},{"key":"e_1_3_2_1_25_1","first-page":"21","article-title":"New results on fair multi-threaded paging","volume":"1","author":"de Loma Alejandro Strejilevich","year":"1998","unstructured":"Alejandro Strejilevich de Loma . 1998 . New results on fair multi-threaded paging . Electronic Journal of SADIO , Vol. 1 , 1 (1998), 21 -- 36 . Alejandro Strejilevich de Loma. 1998. New results on fair multi-threaded paging. Electronic Journal of SADIO , Vol. 1, 1 (1998), 21--36.","journal-title":"Electronic Journal of SADIO"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.parco.2018.06.009"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00453-001-0073-z"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1016\/0196-6774(91)90041-V"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/SFFCS.1999.814600"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/2071379.2071383"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/2989081.2989101"},{"key":"e_1_3_2_1_32_1","volume-title":"Proc. Innovations in Computer Science (ICS), Andrew Chi-Chih Yao (Ed.). 501--509","author":"Hassidim Avinatan","year":"2010","unstructured":"Avinatan Hassidim . 2010 . Cache Replacement Policies for Multicore Processors . In Proc. Innovations in Computer Science (ICS), Andrew Chi-Chih Yao (Ed.). 501--509 . Avinatan Hassidim. 2010. Cache Replacement Policies for Multicore Processors. In Proc. Innovations in Computer Science (ICS), Andrew Chi-Chih Yao (Ed.). 501--509."},{"key":"e_1_3_2_1_33_1","unstructured":"Nicole Hemsoth. 2014. Micron Intel reveal memory slice of Knight's Landing. http:\/\/www.hpcwire.com\/2014\/06\/24\/micron-intel-reveal-memory-slice-knights-landing\/.  Nicole Hemsoth. 2014. Micron Intel reveal memory slice of Knight's Landing. http:\/\/www.hpcwire.com\/2014\/06\/24\/micron-intel-reveal-memory-slice-knights-landing\/."},{"key":"e_1_3_2_1_34_1","volume-title":"Toward Efficient Architecture-Independent Algorithms for Dynamic Programs. In International Conference on High Performance Computing. Springer, 143--164","author":"Javanmard Mohammad Mahdi","year":"2019","unstructured":"Mohammad Mahdi Javanmard , Pramod Ganapathi , Rathish Das , Zafar Ahmad , Stephen Tschudi , and Rezaul Chowdhury . 2019 . Toward Efficient Architecture-Independent Algorithms for Dynamic Programs. In International Conference on High Performance Computing. Springer, 143--164 . Mohammad Mahdi Javanmard, Pramod Ganapathi, Rathish Das, Zafar Ahmad, Stephen Tschudi, and Rezaul Chowdhury. 2019. Toward Efficient Architecture-Independent Algorithms for Dynamic Programs. In International Conference on High Performance Computing. Springer, 143--164."},{"key":"e_1_3_2_1_35_1","volume-title":"USENIX Annual Technical Conference, General Track. 323--336","author":"Jiang Song","year":"2005","unstructured":"Song Jiang , Feng Chen , and Xiaodong Zhang . 2005 . CLOCK-Pro: An Effective Improvement of the CLOCK Replacement .. In USENIX Annual Technical Conference, General Track. 323--336 . Song Jiang, Feng Chen, and Xiaodong Zhang. 2005. CLOCK-Pro: An Effective Improvement of the CLOCK Replacement.. In USENIX Annual Technical Conference, General Track. 323--336."},{"key":"e_1_3_2_1_36_1","volume-title":"An Efficient Data Prefetch Strategy for Deep Learning Based on Non-volatile Memory. In International Conference on Green, Pervasive, and Cloud Computing. Springer, 101--114","author":"Jiang Wenbin","year":"2020","unstructured":"Wenbin Jiang , Pai Liu , Hai Jin , and Jing Peng . 2020 . An Efficient Data Prefetch Strategy for Deep Learning Based on Non-volatile Memory. In International Conference on Green, Pervasive, and Cloud Computing. Springer, 101--114 . Wenbin Jiang, Pai Liu, Hai Jin, and Jing Peng. 2020. An Efficient Data Prefetch Strategy for Deep Learning Based on Non-volatile Memory. In International Conference on Green, Pervasive, and Cloud Computing. Springer, 101--114."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/2155620.2155624"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2012.29"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3133901"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/SBAC-PAD.2017.24"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3126908.3126931"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/2090236.2090246"},{"key":"e_1_3_2_1_43_1","volume-title":"Introduction to the HPC Challenge Benchmark Suite. (12","author":"Luszczek Piotr","year":"2004","unstructured":"Piotr Luszczek , Jack Dongarra , David Koester , Rolf Rabenseifner , Bob Lucas , Jeremy Kepner , John McCalpin , David Bailey , and Daisuke Takahashi . 2004. Introduction to the HPC Challenge Benchmark Suite. (12 2004 ). Piotr Luszczek, Jack Dongarra, David Koester, Rolf Rabenseifner, Bob Lucas, Jeremy Kepner, John McCalpin, David Bailey, and Daisuke Takahashi. 2004. Introduction to the HPC Challenge Benchmark Suite. (12 2004)."},{"volume-title":"Randomized Algorithms","author":"Motwani Rajeev","key":"e_1_3_2_1_44_1","unstructured":"Rajeev Motwani and Prabhakar Raghavan . 1995. Randomized Algorithms . Cambridge University Press , Cambridge, England . Rajeev Motwani and Prabhakar Raghavan. 1995. Randomized Algorithms .Cambridge University Press, Cambridge, England."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3229710.3229720"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/3156685.3092273"},{"volume-title":"Cache-Oblivious Algorithms . Master's thesis. Department of Electrical Engineering and Computer Science","author":"Prokop Harald","key":"e_1_3_2_1_47_1","unstructured":"Harald Prokop . 1999. Cache-Oblivious Algorithms . Master's thesis. Department of Electrical Engineering and Computer Science , Massachusetts Institute of Technology . Harald Prokop. 1999. Cache-Oblivious Algorithms . Master's thesis. Department of Electrical Engineering and Computer Science, Massachusetts Institute of Technology."},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/342001.339668"},{"key":"e_1_3_2_1_49_1","unstructured":"Ruchira Sasanka. 2022. Enabling High-Bandwidth Memory in Future Intel Processors. https:\/\/hpcevents.intel.com\/devhub\/Enabling-High-Bandwidth-Memory-in-Future-Intel-Processors .  Ruchira Sasanka. 2022. Enabling High-Bandwidth Memory in Future Intel Processors. https:\/\/hpcevents.intel.com\/devhub\/Enabling-High-Bandwidth-Memory-in-Future-Intel-Processors ."},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.5555\/762350.762353"},{"key":"e_1_3_2_1_51_1","unstructured":"Anton Shilov. 2021. Intel Shows Off Multi-Chiplet Sapphire Rapids CPU with HBM. https:\/\/www.tomshardware.com\/news\/sapphire-rapids-with-hbm-pictured .  Anton Shilov. 2021. Intel Shows Off Multi-Chiplet Sapphire Rapids CPU with HBM. https:\/\/www.tomshardware.com\/news\/sapphire-rapids-with-hbm-pictured ."},{"key":"e_1_3_2_1_52_1","unstructured":"Johannes Singler and Benjamin Konsik. 2008. The GNU libstdc  Johannes Singler and Benjamin Konsik. 2008. The GNU libstdc"},{"volume-title":"Proceedings of the 1st international workshop on Multicore software engineering . 15--22","key":"e_1_3_2_1_53_1","unstructured":"parallel mode : software engineering considerations . In Proceedings of the 1st international workshop on Multicore software engineering . 15--22 . parallel mode: software engineering considerations. In Proceedings of the 1st international workshop on Multicore software engineering . 15--22."},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1145\/2786.2793"},{"key":"e_1_3_2_1_55_1","volume-title":"Experimental Design of Work Chunking for Graph Algorithms on High Bandwidth Memory Architectures. In 2018 IEEE International Parallel and Distributed Processing Symposium (IPDPS). IEEE, 875--884","author":"Slota George M","year":"2018","unstructured":"George M Slota and Siva Rajamanickam . 2018 . Experimental Design of Work Chunking for Graph Algorithms on High Bandwidth Memory Architectures. In 2018 IEEE International Parallel and Distributed Processing Symposium (IPDPS). IEEE, 875--884 . George M Slota and Siva Rajamanickam. 2018. Experimental Design of Work Chunking for Graph Algorithms on High Bandwidth Memory Architectures. In 2018 IEEE International Parallel and Distributed Processing Symposium (IPDPS). IEEE, 875--884."},{"key":"e_1_3_2_1_56_1","volume-title":"Knights landing: Second-generation intel xeon phi product. Ieee micro","author":"Sodani Avinash","year":"2016","unstructured":"Avinash Sodani , Roger Gramunt , Jesus Corbal , Ho-Seop Kim , Krishna Vinod , Sundaram Chinthamani , Steven Hutsell , Rajat Agarwal , and Yen-Chen Liu . 2016. Knights landing: Second-generation intel xeon phi product. Ieee micro , Vol. 36 , 2 ( 2016 ), 34--46. Avinash Sodani, Roger Gramunt, Jesus Corbal, Ho-Seop Kim, Krishna Vinod, Sundaram Chinthamani, Steven Hutsell, Rajat Agarwal, and Yen-Chen Liu. 2016. Knights landing: Second-generation intel xeon phi product. Ieee micro , Vol. 36, 2 (2016), 34--46."},{"key":"e_1_3_2_1_57_1","unstructured":"TACC. 2022. Stampede2 User Guide. https:\/\/portal.tacc.utexas.edu\/user-guides\/stampede2  TACC. 2022. Stampede2 User Guide. https:\/\/portal.tacc.utexas.edu\/user-guides\/stampede2"},{"key":"e_1_3_2_1_58_1","unstructured":"Tiffany Trader. 2018. Requiem for a Phi: Knights Landing Discontinued. https:\/\/www.hpcwire.com\/2018\/07\/25\/end-of-the-road-for-knights-landing-phi\/  Tiffany Trader. 2018. Requiem for a Phi: Knights Landing Discontinued. https:\/\/www.hpcwire.com\/2018\/07\/25\/end-of-the-road-for-knights-landing-phi\/"}],"event":{"name":"SPAA '22: 34th ACM Symposium on Parallelism in Algorithms and Architectures","sponsor":["SIGACT ACM Special Interest Group on Algorithms and Computation Theory","SIGARCH ACM Special Interest Group on Computer Architecture","EATCS European Association for Theoretical Computer Science"],"location":"Philadelphia PA USA","acronym":"SPAA '22"},"container-title":["Proceedings of the 34th ACM Symposium on Parallelism in Algorithms and Architectures"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3490148.3538570","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3490148.3538570","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3490148.3538570","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:12:08Z","timestamp":1750191128000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3490148.3538570"}},"subtitle":["Models and Algorithms"],"short-title":[],"issued":{"date-parts":[[2022,7,11]]},"references-count":58,"alternative-id":["10.1145\/3490148.3538570","10.1145\/3490148"],"URL":"https:\/\/doi.org\/10.1145\/3490148.3538570","relation":{},"subject":[],"published":{"date-parts":[[2022,7,11]]},"assertion":[{"value":"2022-07-11","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}