{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T02:46:02Z","timestamp":1783737962099,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":147,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,6,10]],"date-time":"2022-06-10T00:00:00Z","timestamp":1654819200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100010667","name":"H2020 Industrial Leadership","doi-asserted-by":"publisher","award":["780245"],"award-info":[{"award-number":["780245"]}],"id":[{"id":"10.13039\/100010667","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100006360","name":"Bundesministerium f\u00fcr Wirtschaft und Energie","doi-asserted-by":"publisher","award":["01MD19002B"],"award-info":[{"award-number":["01MD19002B"]}],"id":[{"id":"10.13039\/501100006360","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002347","name":"Bundesministerium f\u00fcr Bildung und Forschung","doi-asserted-by":"publisher","award":["01IS18025A"],"award-info":[{"award-number":["01IS18025A"]}],"id":[{"id":"10.13039\/501100002347","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002347","name":"Bundesministerium f\u00fcr Bildung und Forschung","doi-asserted-by":"publisher","award":["01IS18037A"],"award-info":[{"award-number":["01IS18037A"]}],"id":[{"id":"10.13039\/501100002347","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,6,10]]},"DOI":"10.1145\/3514221.3517911","type":"proceedings-article","created":{"date-parts":[[2022,6,12]],"date-time":"2022-06-12T02:33:49Z","timestamp":1655001229000},"page":"1017-1032","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":20,"title":["Triton Join: Efficiently Scaling to a Large Join State on GPUs with Fast Interconnects"],"prefix":"10.1145","author":[{"given":"Clemens","family":"Lutz","sequence":"first","affiliation":[{"name":"Technische Universit\u00e4t Berlin, Berlin, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sebastian","family":"Bre\u00df","sequence":"additional","affiliation":[{"name":"Snowflake, Berlin, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Steffen","family":"Zeuch","sequence":"additional","affiliation":[{"name":"DFKI GmbH, Berlin, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tilmann","family":"Rabl","sequence":"additional","affiliation":[{"name":"HPI & University of Potsdam, Potsdam, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Volker","family":"Markl","sequence":"additional","affiliation":[{"name":"DFKI GmbH & Technische Universit\u00e4t Berlin, Berlin, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2022,6,11]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2015.7056046"},{"key":"e_1_3_2_1_2_1","unstructured":"AMD 2015. Asynchronous shaders: Unlocking the full potential of the GPU. AMD. https:\/\/developer.amd.com\/wordpress\/media\/2012\/10\/Asynchronous-Shaders-White-Paper-FINAL.pdf"},{"key":"e_1_3_2_1_3_1","unstructured":"AMD 2017. Radeon's next-generation Vega architecture. AMD. https:\/\/en.wikichip.org\/w\/images\/a\/a1\/vega-whitepaper.pdf"},{"key":"e_1_3_2_1_4_1","unstructured":"AMD 2020. OpenCL optimization. AMD. https:\/\/rocmdocs.amd.com\/en\/latest\/Programming_Guides\/Opencl-optimization.html Git Revision 1f057816."},{"key":"e_1_3_2_1_5_1","unstructured":"AMD 2020. OpenCL programming guide. AMD. https:\/\/rocmdocs.amd.com\/en\/latest\/Programming_Guides\/Opencl-programming-guide.html Git Revision 611e249."},{"key":"e_1_3_2_1_6_1","unstructured":"AMD 2021. AMD CDNA 2 architecture. AMD. https:\/\/www.amd.com\/system\/files\/documents\/amd-cdna2-white-paper.pdf"},{"key":"e_1_3_2_1_7_1","unstructured":"AMD 2021. AMD EPYC 7003 series processors. AMD. https:\/\/www.amd.com\/system\/files\/documents\/amd-epyc-7003-series-datasheet.pdf LE-77202-0002\/21."},{"key":"e_1_3_2_1_8_1","unstructured":"AMD 2021. GPU performance API. AMD. https:\/\/gpuperfapi.readthedocs.io\/en\/latest\/ Git Revision 3642849d."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","unstructured":"Arash Ashari Shirish Tatikonda Matthias Boehm Berthold Reinwald Keith Campbell John Keenleyside and P. Sadayappan. 2015. On optimizing machine learning workloads via kernel fusion. In PPoPP. ACM New York NY USA 173--182. https:\/\/doi.org\/10.1145\/2688500.2688521","DOI":"10.1145\/2688500.2688521"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3123939.3123975"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.14778\/2732219.2732227"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2013.6544839"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3448016.3452831"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.14778\/2735496.2735499"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/1815961.1815970"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.14778\/3055540.3055545"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/2723372.2750547"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3410463.3414639"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/2213836.2213851"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2018.00030"},{"key":"e_1_3_2_1_21_1","volume-title":"Filed Jun. 23th.","author":"Blaner Bartholomew","year":"2016","unstructured":"Bartholomew Blaner, Jay G Heaslip, Robert D Herzl, and Jody B Joyner. 2020. Maintaining consistency between address translations in a data processing system. Patent No. US10599569B2, Filed Jun. 23th., 2016, Issued Mar. 24th., 2020."},{"key":"e_1_3_2_1_22_1","volume-title":"Patent App. No. US20180300256A1, Filed Apr. 13th.","author":"Blaner Bartholomew","year":"2018","unstructured":"Bartholomew Blaner, Jody B Joyner, Ronald N Kalla, Jon K Kriegel, and Charles D Wait. 2018. Maintaining agent inclusivity within a distributed MMU. Patent App. No. US20180300256A1, Filed Apr. 13th., 2017."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/2882903.2882936"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00778-018-0512-y"},{"key":"e_1_3_2_1_25_1","unstructured":"Xinyu Chen Yao Chen Ronak Bajaj Jiong He Bingsheng He Weng-Fai Wong and Deming Chen. 2020. Is FPGA useful for hash joins?. In CIDR. www.cidrdb.org 1--9."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3132847.3132916"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2018.022071134"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/329.318578"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.14778\/3303753.3303760"},{"key":"e_1_3_2_1_30_1","unstructured":"Periklis Chrysogelos Panagiotis Sioulas and Anastasia Ailamaki. 2019. Hardware-conscious query processing in GPU-accelerated analytical engines. In CIDR. www.cidrdb.org 1--9."},{"key":"e_1_3_2_1_31_1","unstructured":"CXL 2020. Compute Express Link specification Revision 2.0. CXL. https:\/\/www.computeexpresslink.org"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/178243.178259"},{"key":"e_1_3_2_1_33_1","volume-title":"Mark Allen Mosley, and William Craig McKnight","author":"Deming James Leroy","year":"2017","unstructured":"James Leroy Deming, Mark Allen Mosley, and William Craig McKnight. 2017. Method for automatic page table compression. Patent No. US9569348B1, Filed Jul. 23rd., 2010, Issued Feb. 14th., 2011."},{"key":"e_1_3_2_1_34_1","volume-title":"Patent No. US20110072235A1, Filed Oct. 8th., 2005","author":"Deming James Leroy","year":"2011","unstructured":"James Leroy Deming, Mark Allen Mosley, William Craig McKnight, Emmett M. Kilgrariff, Steven E. Molnar, and Colyn Scott Case. 2011. Efficient memory translator with variable size cache line coverage. Patent No. US20110072235A1, Filed Oct. 8th., 2005, Issued Mar. 24th., 2011."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/602259.602261"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1006\/jagm.1997.0873"},{"key":"e_1_3_2_1_37_1","volume-title":"LWN. Retrieved","author":"Drepper Ulrich","year":"2007","unstructured":"Ulrich Drepper. 2007. Memory part 5: What programmers can do. LWN. Retrieved Jun 23, 2021 from https:\/\/lwn.net\/Articles\/255364\/"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2017.37"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3183713.3183734"},{"key":"e_1_3_2_1_40_1","unstructured":"Hao Gao and Nikolai Sakharnykh. 2021. Scaling joins to a thousand GPUs. In ADMS. 55--64."},{"key":"e_1_3_2_1_41_1","volume-title":"Understanding the Linux virtual memory manager","author":"Gorman Mel","unstructured":"Mel Gorman. 2004. Understanding the Linux virtual memory manager. Prentice Hall PTR, Upper Saddle River, NJ, USA."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3329785.3329926"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2011.5762730"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3329785.3329934"},{"key":"e_1_3_2_1_45_1","volume-title":"Tsotras","author":"Halstead Robert J.","year":"2015","unstructured":"Robert J. Halstead, Ildar Absalyamov, Walid A. Najjar, and Vassilis J. Tsotras. 2015. FPGA-based multithreading for in-memory hash joins. In CIDR. www.cidrdb.org, 1--9."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/FCCM.2013.17"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/1620585.1620588"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/1376616.1376670"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.14778\/2536206.2536216"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.14778\/2735496.2735497"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.14778\/2536360.2536370"},{"key":"e_1_3_2_1_52_1","volume-title":"Patterson","author":"Hennessy John L.","year":"2017","unstructured":"John L. Hennessy and David A. Patterson. 2017. Computer architecture - A quantitative approach (6th ed.). Morgan Kaufmann, Cambridge, MA, USA.","edition":"6"},{"key":"e_1_3_2_1_53_1","volume-title":"GTC '21 keynote. Nvidia. Retrieved","author":"Huang Jensen","year":"2021","unstructured":"Jensen Huang. 2021. GTC '21 keynote. Nvidia. Retrieved May 31, 2021 from https:\/\/images.nvidia.com\/gtc\/keynote\/GTC21-Jensen-Huang-Keynote_04.pdf"},{"key":"e_1_3_2_1_54_1","unstructured":"IBM 2017. POWER ISA version 3.0B. IBM."},{"key":"e_1_3_2_1_55_1","unstructured":"IBM 2018. POWER9 performance monitor unit user's guide. IBM. Version 1.2."},{"key":"e_1_3_2_1_56_1","unstructured":"IBM 2018. POWER9 processor user's manual. IBM. Version 2.0."},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1147\/JRD.2018.2846978"},{"key":"e_1_3_2_1_58_1","volume-title":"Intel. Retrieved","year":"2019","unstructured":"Intel. 2019. Intel unveils new GPU architecture with high-performance computing and AI acceleration, and oneAPI software stack with unified and scalable abstraction for heterogeneous architectures. Intel. Retrieved Jun 10, 2021 from https:\/\/newsroom.intel.com\/news-releases\/intel-unveils-new-gpu-architecture-optimized-for-hpc-ai-oneapi"},{"key":"e_1_3_2_1_59_1","unstructured":"Intel 2021. Intel Xeon Gold 6338 processor. Intel. https:\/\/ark.intel.com\/content\/www\/us\/en\/ark\/products\/212285\/intel-xeon-gold-6338-processor-48m-cache-2-00-ghz.html"},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1145\/3224430"},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1145\/3309710"},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1147\/JRD.2018.2846959"},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.14778\/2735703.2735704"},{"key":"e_1_3_2_1_64_1","unstructured":"Zhe Jia Marco Maggioni Jeffrey Smith and Daniele Paolo Scarpazza. 2019. Dissecting the Nvidia Turing T4 GPU via microbenchmarking. arXiv:1903.07486 [cs.DC]"},{"key":"e_1_3_2_1_65_1","unstructured":"Zhe Jia Marco Maggioni Benjamin Staiger and Daniele Paolo Scarpazza. 2018. Dissecting the Nvidia Volta GPU architecture via microbenchmarking. arXiv:1804.06826 [cs.DC]"},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.1145\/2236584.2236592"},{"key":"e_1_3_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.1145\/3035918.3035946"},{"key":"e_1_3_2_1_68_1","doi-asserted-by":"crossref","unstructured":"Kaan Kara Christoph Hagleitner Dionysios Diamantopoulos Dimitris Syrivelis and Gustavo Alonso. 2020. High bandwidth memory on FPGAs: A data analytics perspective. arXiv:2004.01635 [cs.DC]","DOI":"10.1109\/FPL50879.2020.00013"},{"key":"e_1_3_2_1_69_1","doi-asserted-by":"publisher","DOI":"10.1145\/3076113.3076115"},{"key":"e_1_3_2_1_70_1","volume-title":"Lohman","author":"Karnagel Tomas","year":"2015","unstructured":"Tomas Karnagel, Ren\u00e9 M\u00fcller, and Guy M. Lohman. 2015. Optimizing GPU- accelerated group-by and aggregation. In ADMS. 13--24."},{"key":"e_1_3_2_1_71_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA45697.2020.00047"},{"key":"e_1_3_2_1_72_1","doi-asserted-by":"publisher","DOI":"10.14778\/1687553.1687564"},{"key":"e_1_3_2_1_73_1","volume-title":"Seminumerical algorithms","author":"Knuth Donald E.","unstructured":"Donald E. Knuth. 1981. Seminumerical algorithms (2nd ed.). The art of computer programming, Vol. 2. Addison-Wesley, Reading, MA, USA.","edition":"2"},{"key":"e_1_3_2_1_74_1","doi-asserted-by":"publisher","DOI":"10.18420\/btw2021-01"},{"key":"e_1_3_2_1_75_1","doi-asserted-by":"publisher","DOI":"10.1145\/3225058.3225095"},{"key":"e_1_3_2_1_76_1","doi-asserted-by":"publisher","DOI":"10.5441\/002"},{"key":"e_1_3_2_1_77_1","doi-asserted-by":"publisher","DOI":"10.14778\/2733004.2733008"},{"key":"e_1_3_2_1_78_1","doi-asserted-by":"publisher","DOI":"10.14778\/3476311.3476378"},{"key":"e_1_3_2_1_79_1","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2008.31"},{"key":"e_1_3_2_1_80_1","doi-asserted-by":"publisher","DOI":"10.1007\/s13222-018-0293-x"},{"key":"e_1_3_2_1_81_1","doi-asserted-by":"publisher","DOI":"10.1145\/3318464.3389705"},{"key":"e_1_3_2_1_82_1","doi-asserted-by":"publisher","DOI":"10.14778\/3236187.3236188"},{"key":"e_1_3_2_1_83_1","volume-title":"SIGMOD. ACM","author":"Maltenberger Tobias","unstructured":"Tobias Maltenberger, Ivan Ilic, Ilin Tolovski, and Tilmann Rabl. 2022. Evaluating multi-GPU sorting with modern interconnects. In SIGMOD. ACM, New York, NY, USA, 15 pages. To appear."},{"key":"e_1_3_2_1_84_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2002.1019210"},{"key":"e_1_3_2_1_85_1","doi-asserted-by":"publisher","DOI":"10.1016\/B978-012088469--8.50061--9"},{"key":"e_1_3_2_1_86_1","volume-title":"GPU Database Market. MarketsandMarkets Research. Retrieved","author":"Research MarketsandMarkets","year":"2019","unstructured":"MarketsandMarkets Research. 2018. GPU Database Market. MarketsandMarkets Research. Retrieved Oct 1, 2019 from https:\/\/www.marketsandmarkets.com\/Market-Reports\/gpu-database-market-259046335.html"},{"key":"e_1_3_2_1_87_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00778-006-0030--1"},{"key":"e_1_3_2_1_88_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2016.2549523"},{"key":"e_1_3_2_1_89_1","doi-asserted-by":"publisher","DOI":"10.1145\/3465998.3466005"},{"key":"e_1_3_2_1_90_1","doi-asserted-by":"publisher","DOI":"10.14778\/3425879.3425883"},{"key":"e_1_3_2_1_91_1","unstructured":"Milan Navr\u00e1til Laura Bailey and Charlie Boyle. 2018. Red Hat Enterprise Linux 7 Performance Tuning Guide. Red Hat. Revision 10.13--59."},{"key":"e_1_3_2_1_92_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCS.2018.00046"},{"key":"e_1_3_2_1_93_1","volume-title":"IBM power system AC922 introduction and technical overview","author":"Nohria Ritesh","unstructured":"Ritesh Nohria, Gustavo Santos, and Volker Haug. 2019. IBM power system AC922 introduction and technical overview (1st ed.). IBM International Technical Support Organization, Poughkeepsie, NY, USA. REDP-5494-00.","edition":"1"},{"key":"e_1_3_2_1_94_1","volume-title":"Filed Jan. 24th.","author":"Nordquist Bryon S","year":"2006","unstructured":"Bryon S Nordquist and Stephen D Lew. 2009. Apparatus, system, and method for coalescing parallel memory requests. Patent No. US7492368B1, Filed Jan. 24th., 2006, Issued Feb. 17th., 2009."},{"key":"e_1_3_2_1_95_1","unstructured":"Nvidia 2009. Nvidia's next generation CUDA compute architecture: Fermi. Nvidia. https:\/\/www.nvidia.com\/content\/PDF\/fermi_white_papers\/NVIDIA_Fermi_Compute_Architecture_Whitepaper.pdf v1.1."},{"key":"e_1_3_2_1_96_1","unstructured":"Nvidia 2016. Nvidia Tesla P100. Nvidia. https:\/\/images.nvidia.com\/content\/pdf\/tesla\/whitepaper\/pascal-architecture-whitepaper.pdf WP-08019-001_v01.1."},{"key":"e_1_3_2_1_97_1","unstructured":"Nvidia 2017. Nvidia Tesla V100 GPU architecture. Nvidia. https:\/\/images.nvidia.com\/content\/volta-architecture\/pdf\/volta-architecture-whitepaper.pdf WP-08608-001_v1.1."},{"key":"e_1_3_2_1_98_1","unstructured":"Nvidia 2019. Pascal MMU format changes. Nvidia. https:\/\/nvidia.github.io\/open-gpu-doc\/pascal\/gp100-mmu-format.pdf Git Revision 60b67c3."},{"key":"e_1_3_2_1_99_1","unstructured":"Nvidia 2020. CUPTI user's guide. Nvidia. https:\/\/docs.nvidia.com\/cupti\/pdf\/Cupti.pdf DA-05679-001_v11.1."},{"key":"e_1_3_2_1_100_1","unstructured":"Nvidia 2020. Nvidia A100 tensore core GPU architecture. Nvidia. https:\/\/www.nvidia.com\/content\/dam\/en-zz\/Solutions\/Data-Center\/nvidia-ampere-architecture-whitepaper.pdf v1.0."},{"key":"e_1_3_2_1_101_1","unstructured":"Nvidia 2021. CUDA C programming guide. Nvidia. http:\/\/docs.nvidia.com\/pdf\/CUDA_C_Programming_Guide.pdf PG-02829-001_v11.3."},{"key":"e_1_3_2_1_102_1","unstructured":"Nvidia 2021. Parallel thread execution ISA. Nvidia. https:\/\/docs.nvidia.com\/cuda\/pdf\/ptx_isa_7.3.pdf v7.3."},{"key":"e_1_3_2_1_103_1","unstructured":"OpenCAPI Consortium 2020. OpenCAPI 4.0 transaction layer specification. Open- CAPI Consortium. Version 1.0."},{"key":"e_1_3_2_1_104_1","volume-title":"AMD. Retrieved","author":"Papermaster Mark","year":"2020","unstructured":"Mark Papermaster. 2020. AMD Financial Analyst Day. AMD. Retrieved Jun 10, 2021 from https:\/\/ir.amd.com\/news-events\/analyst-day"},{"key":"e_1_3_2_1_105_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDEW.2019.00008"},{"key":"e_1_3_2_1_106_1","doi-asserted-by":"publisher","DOI":"10.1145\/2882903.2915224"},{"key":"e_1_3_2_1_107_1","doi-asserted-by":"publisher","DOI":"10.1145\/3448016.3457254"},{"key":"e_1_3_2_1_108_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICFPT52863.2021.9609833"},{"key":"e_1_3_2_1_109_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICFPT51103.2020.00048"},{"key":"e_1_3_2_1_110_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2014.6835964"},{"key":"e_1_3_2_1_111_1","doi-asserted-by":"publisher","DOI":"10.1145\/2541940.2541942"},{"key":"e_1_3_2_1_112_1","volume-title":"Kersten","author":"Pirk Holger","year":"2011","unstructured":"Holger Pirk, Stefan Manegold, and Martin L. Kersten. 2011. Accelerating foreign-key joins using asymmetric memory channels. In ADMS. 27--35."},{"key":"e_1_3_2_1_113_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2014.6816677"},{"key":"e_1_3_2_1_114_1","doi-asserted-by":"publisher","DOI":"10.1145\/3211922.3211929"},{"key":"e_1_3_2_1_115_1","doi-asserted-by":"publisher","DOI":"10.1145\/2723372.2747645"},{"key":"e_1_3_2_1_116_1","doi-asserted-by":"publisher","DOI":"10.1145\/3329785.3329928"},{"key":"e_1_3_2_1_117_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00778-020-00621-w"},{"key":"e_1_3_2_1_118_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2014.6835965"},{"key":"e_1_3_2_1_119_1","unstructured":"Aunn Raza Periklis Chrysogelos Panagiotis Sioulas Vladimir Indjic Angelos-Christos G. Anadiotis and Anastasia Ailamaki. 2020. GPU-accelerated data management under the test of time. In CIDR. www.cidrdb.org 1--11."},{"key":"e_1_3_2_1_120_1","doi-asserted-by":"publisher","DOI":"10.14778\/2850583.2850585"},{"key":"e_1_3_2_1_121_1","doi-asserted-by":"publisher","DOI":"10.1145\/2897839.2927468"},{"key":"e_1_3_2_1_122_1","doi-asserted-by":"publisher","DOI":"10.1145\/3485126"},{"key":"e_1_3_2_1_123_1","doi-asserted-by":"publisher","DOI":"10.1145\/3329785.3329922"},{"key":"e_1_3_2_1_124_1","doi-asserted-by":"publisher","DOI":"10.14778\/3436905.3436927"},{"key":"e_1_3_2_1_125_1","doi-asserted-by":"publisher","DOI":"10.1145\/3085504.3085521"},{"key":"e_1_3_2_1_126_1","volume-title":"Nvidia. Retrieved","author":"Sakharnykh Nikolay","year":"2017","unstructured":"Nikolay Sakharnykh. 2017. Maximizing unified memory performance in CUDA. Nvidia. Retrieved Jun 10, 2021 from https:\/\/developer.nvidia.com\/blog\/maximizing-unified-memory-performance-cuda"},{"key":"e_1_3_2_1_127_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2009.5161005"},{"key":"e_1_3_2_1_128_1","doi-asserted-by":"publisher","DOI":"10.1145\/1807167.1807207"},{"key":"e_1_3_2_1_129_1","doi-asserted-by":"publisher","DOI":"10.14778\/3476249.3476286"},{"key":"e_1_3_2_1_130_1","doi-asserted-by":"publisher","DOI":"10.1145\/2882903.2882917"},{"key":"e_1_3_2_1_131_1","doi-asserted-by":"publisher","DOI":"10.14778\/2777598.2777602"},{"key":"e_1_3_2_1_132_1","doi-asserted-by":"publisher","DOI":"10.1145\/3318464.3380595"},{"key":"e_1_3_2_1_133_1","volume-title":"Naughton","author":"Shatdal Ambuj","year":"1994","unstructured":"Ambuj Shatdal, Chander Kant, and Jeffrey F. Naughton. 1994. Cache conscious algorithms for relational query processing. In PVLDB. Morgan Kaufmann, San Francisco, CA, USA, 510--521. https:\/\/dl.acm.org\/doi\/10.5555\/645920.758363"},{"key":"e_1_3_2_1_134_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2019.00068"},{"key":"e_1_3_2_1_135_1","doi-asserted-by":"publisher","DOI":"10.1145\/2485278.2485282"},{"key":"e_1_3_2_1_136_1","unstructured":"Greg Smith. 2014. Stack Overflow. Nvidia. Retrieved Nov 8 2021 from https:\/\/stackoverflow.com\/questions\/27253434\/what-does-overflow-mean-during-cuda-profiling\/27262797#27262797"},{"key":"e_1_3_2_1_137_1","volume-title":"Nvidia. Retrieved","author":"Smith Greg","year":"2019","unstructured":"Greg Smith. 2019. Nvidia Developer Forums. Nvidia. Retrieved Oct 13, 2020 from https:\/\/forums.developer.nvidia.com\/t\/pascal-l1-cache\/49571\/14"},{"key":"e_1_3_2_1_138_1","volume-title":"Nvidia. Retrieved","author":"Smith Greg","year":"2019","unstructured":"Greg Smith. 2019. Nvidia Developer Forums. Nvidia. Retrieved Oct 13, 2020 from https:\/\/forums.developer.nvidia.com\/t\/performance-counters-similar-to-cpu\/74949\/2"},{"key":"e_1_3_2_1_139_1","doi-asserted-by":"publisher","DOI":"10.1147\/JRD.2018.2846159"},{"key":"e_1_3_2_1_140_1","doi-asserted-by":"publisher","DOI":"10.1145\/3035918.3064043"},{"key":"e_1_3_2_1_141_1","doi-asserted-by":"publisher","DOI":"10.1109\/FPL.2015.7293941"},{"key":"e_1_3_2_1_142_1","doi-asserted-by":"publisher","DOI":"10.1007\/978--3--642--23397--5_16"},{"key":"e_1_3_2_1_143_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2017.2677451"},{"key":"e_1_3_2_1_144_1","doi-asserted-by":"publisher","DOI":"10.1145\/1995441.1995442"},{"key":"e_1_3_2_1_145_1","doi-asserted-by":"publisher","DOI":"10.14778\/2536206.2536210"},{"key":"e_1_3_2_1_146_1","volume-title":"Patel","author":"Zhang Zuyu","year":"2019","unstructured":"Zuyu Zhang, Harshad Deshmukh, and Jignesh M. Patel. 2019. Data partitioning for in-memory systems: Myths, challenges, and opportunities. In CIDR. www.cidrdb.org, 1--8."},{"key":"e_1_3_2_1_147_1","doi-asserted-by":"publisher","DOI":"10.1145\/1140402.1140410"}],"event":{"name":"SIGMOD\/PODS '22: International Conference on Management of Data","location":"Philadelphia PA USA","acronym":"SIGMOD\/PODS '22","sponsor":["SIGMOD ACM Special Interest Group on Management of Data"]},"container-title":["Proceedings of the 2022 International Conference on Management of Data"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3514221.3517911","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3514221.3517911","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T18:10:06Z","timestamp":1750183806000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3514221.3517911"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,6,10]]},"references-count":147,"alternative-id":["10.1145\/3514221.3517911","10.1145\/3514221"],"URL":"https:\/\/doi.org\/10.1145\/3514221.3517911","relation":{},"subject":[],"published":{"date-parts":[[2022,6,10]]},"assertion":[{"value":"2022-06-11","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}