{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,14]],"date-time":"2026-03-14T09:52:34Z","timestamp":1773481954185,"version":"3.50.1"},"reference-count":38,"publisher":"Association for Computing Machinery (ACM)","issue":"2","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Proc. VLDB Endow."],"published-print":{"date-parts":[[2020,10]]},"abstract":"<jats:p>\n            In recent years, we have witnessed significant efforts to improve the performance of Online Analytical Processing (OLAP) on graphics processing units (GPUs). Most existing studies have focused on improving memory efficiency since memory stalls can play an essential role in query processing performance on GPUs. Motivated by the recent rise of just-in-time (JIT) compilation in query processing, we investigate whether and how we can further improve query processing performance on GPU. Specifically, we study the execution of state-of-the-art JIT compile-based query processing systems. We find that thanks to advanced techniques such as database compression and JIT compilation, memory stalls are\n            <jats:italic>no longer<\/jats:italic>\n            the most significant bottleneck. Instead, current JIT compile-based query processing encounters\n            <jats:italic>severe under-utilization of GPU hardware<\/jats:italic>\n            due to divergent execution and degraded parallelism arising from resource contention. To address these issues, we propose a JIT compile-based query engine named\n            <jats:italic>Pyper<\/jats:italic>\n            to improve GPU utilization during query execution. Specifically, Pyper has two new operators,\n            <jats:italic>Shuffle<\/jats:italic>\n            and\n            <jats:italic>Segment<\/jats:italic>\n            , for query plan transformation, which can be plugged into a physical query plan in order to reduce divergent execution and resolve resource contention, respectively. To determine the insertion points for these two operators, we present an analytical model that helps insert Shuffle and Segment operators into a query plan in a cost-based manner. Our experiments show that 1) the analytical analysis of divergent execution and resource contention helps to improve the accuracy of the cost model, 2) Pyper significantly outperforms other GPU query engines on TPC-H and SSB queries.\n          <\/jats:p>","DOI":"10.14778\/3425879.3425890","type":"journal-article","created":{"date-parts":[[2020,11,25]],"date-time":"2020-11-25T02:45:23Z","timestamp":1606272323000},"page":"202-214","source":"Crossref","is-referenced-by-count":20,"title":["Improving execution efficiency of just-in-time compilation based query processing on GPUs"],"prefix":"10.14778","volume":"14","author":[{"given":"Johns","family":"Paul","sequence":"first","affiliation":[{"name":"National University of Singapore"}]},{"given":"Bingsheng","family":"He","sequence":"additional","affiliation":[{"name":"National University of Singapore"}]},{"given":"Shengliang","family":"Lu","sequence":"additional","affiliation":[{"name":"National University of Singapore"}]},{"given":"Chiew Tong","family":"Lau","sequence":"additional","affiliation":[{"name":"Nanyang Technological University, Singapore"}]}],"member":"320","published-online":{"date-parts":[[2020,11,16]]},"reference":[{"key":"e_1_2_1_1_1","volume-title":"http:\/\/www.tpc.org\/tpch\/","year":"1999","unstructured":"Tpc-h. http:\/\/www.tpc.org\/tpch\/ , 1999 . Tpc-h. http:\/\/www.tpc.org\/tpch\/, 1999."},{"key":"e_1_2_1_2_1","volume-title":"accelerated analytics platform. https:\/\/www.omnisci.com\/","year":"2009","unstructured":"Omnisci. accelerated analytics platform. https:\/\/www.omnisci.com\/ , 2009 . Omnisci. accelerated analytics platform. https:\/\/www.omnisci.com\/, 2009."},{"key":"e_1_2_1_3_1","volume-title":"https:\/\/www.cs.umb.edu\/poneil\/StarSchemaB.PDF","year":"2009","unstructured":"Star schema bechmark. https:\/\/www.cs.umb.edu\/poneil\/StarSchemaB.PDF , 2009 . Star schema bechmark. https:\/\/www.cs.umb.edu\/poneil\/StarSchemaB.PDF, 2009."},{"key":"e_1_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3380930"},{"key":"e_1_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00778-018-0512-y"},{"key":"e_1_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.14778\/3303753.3303760"},{"key":"e_1_2_1_7_1","first-page":"9","volume-title":"Proceesings of the 9th Biennial Conference on Innovative Data Systems Research","author":"Chrysogelos P.","year":"2019","unstructured":"P. Chrysogelos , P. Sioulas , and A. Ailamaki . Hardware-conscious query processing in gpu-accelerated analytical engines . Proceesings of the 9th Biennial Conference on Innovative Data Systems Research , page 9 , 2019 . P. Chrysogelos, P. Sioulas, and A. Ailamaki. Hardware-conscious query processing in gpu-accelerated analytical engines. Proceesings of the 9th Biennial Conference on Innovative Data Systems Research, page 9, 2019."},{"key":"e_1_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE48307.2020.00114"},{"issue":"363","key":"e_1_2_1_9_1","first-page":"377","article-title":"Exploiting gpu and cluster parallelism in single scan frequent itemset mining","volume":"496","author":"Djenouri Y.","year":"2019","unstructured":"Y. Djenouri , D. Djenouri , A. Belhadi , and A. Cano . Exploiting gpu and cluster parallelism in single scan frequent itemset mining . Information Sciences , 496 : 363 -- 377 , 2019 . Y. Djenouri, D. Djenouri, A. Belhadi, and A. Cano. Exploiting gpu and cluster parallelism in single scan frequent itemset mining. Information Sciences, 496:363 -- 377, 2019.","journal-title":"Information Sciences"},{"key":"e_1_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/1247480.1247606"},{"key":"e_1_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3183713.3183734"},{"key":"e_1_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.14778\/3380750.3380758"},{"key":"e_1_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/1620585.1620588"},{"key":"e_1_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.14778\/2536206.2536216"},{"key":"e_1_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.14778\/2735496.2735497"},{"key":"e_1_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/2723372.2749438"},{"key":"e_1_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.14778\/2536360.2536370"},{"key":"e_1_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/2236584.2236592"},{"key":"e_1_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/2600212.2600227"},{"key":"e_1_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2019.2905235"},{"key":"e_1_2_1_21_1","article-title":"Evaluating Modern GPU Interconnect: PCIe, NVLink, NV-SLI, NVSwitch and GPUDirect","author":"Li A.","year":"2019","unstructured":"A. Li , S. Song , J. Chen , J. Li , X. Liu , N. Tallent , and K. J. Barker . Evaluating Modern GPU Interconnect: PCIe, NVLink, NV-SLI, NVSwitch and GPUDirect . IEEE Transactions on Parallel and Distributed Systems, pages 1--1 , 2019 . A. Li, S. Song, J. Chen, J. Li, X. Liu, N. Tallent, and K. J. Barker. Evaluating Modern GPU Interconnect: PCIe, NVLink, NV-SLI, NVSwitch and GPUDirect. IEEE Transactions on Parallel and Distributed Systems, pages 1--1, 2019.","journal-title":"IEEE Transactions on Parallel and Distributed Systems, pages 1--1"},{"key":"e_1_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3318464.3389705"},{"key":"e_1_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.14778\/3151113.3151114"},{"key":"e_1_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.disopt.2016.01.005"},{"key":"e_1_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.14778\/2002938.2002940"},{"key":"e_1_2_1_26_1","volume-title":"Compiling database queries into machine code","author":"Neumann T.","year":"2014","unstructured":"T. Neumann and V. Leis . Compiling database queries into machine code . IEEE Data Eng. Bull ., 2014 . T. Neumann and V. Leis. Compiling database queries into machine code. IEEE Data Eng. Bull., 2014."},{"key":"e_1_2_1_27_1","volume-title":"https:\/\/www.omnisci.com\/","year":"2019","unstructured":"OmniSci. https:\/\/www.omnisci.com\/ . 2019 . OmniSci. https:\/\/www.omnisci.com\/. 2019."},{"key":"e_1_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDEW.2019.00008"},{"key":"e_1_2_1_29_1","volume-title":"Improving execution efficiency of just-in-time compilation based query processing on gpus (complete version). In https:\/\/github.com\/Xtra-Computing\/Pyper","author":"Paul J.","year":"2020","unstructured":"J. Paul , B. He , S. Lu , and C. T. Lau . Improving execution efficiency of just-in-time compilation based query processing on gpus (complete version). In https:\/\/github.com\/Xtra-Computing\/Pyper , 2020 . J. Paul, B. He, S. Lu, and C. T. Lau. Improving execution efficiency of just-in-time compilation based query processing on gpus (complete version). In https:\/\/github.com\/Xtra-Computing\/Pyper, 2020."},{"key":"e_1_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/2882903.2915224"},{"key":"e_1_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.14778\/3007328.3007336"},{"key":"e_1_2_1_32_1","volume-title":"A study of the fundamental performance characteristics of gpus and cpus for database analytics (extended version). arXiv preprint arXiv:2003.01178","author":"Shanbhag A.","year":"2020","unstructured":"A. Shanbhag , S. Madden , and X. Yu . A study of the fundamental performance characteristics of gpus and cpus for database analytics (extended version). arXiv preprint arXiv:2003.01178 , 2020 . A. Shanbhag, S. Madden, and X. Yu. A study of the fundamental performance characteristics of gpus and cpus for database analytics (extended version). arXiv preprint arXiv:2003.01178, 2020."},{"key":"e_1_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3293883.3295736"},{"key":"e_1_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/2485278.2485282"},{"key":"e_1_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/2581122.2544166"},{"key":"e_1_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.14778\/2536206.2536210"},{"key":"e_1_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/1810085.1810104"},{"key":"e_1_2_1_38_1","first-page":"1","volume-title":"Distributed and Parallel Databases","author":"Zhang Y.","year":"2020","unstructured":"Y. Zhang , Y. Zhang , J. Lu , S. Wang , Z. Liu , and R. Han . One size does not fit all: accelerating olap workloads with gpus . Distributed and Parallel Databases , pages 1 -- 43 , 2020 . Y. Zhang, Y. Zhang, J. Lu, S. Wang, Z. Liu, and R. Han. One size does not fit all: accelerating olap workloads with gpus. Distributed and Parallel Databases, pages 1--43, 2020."}],"container-title":["Proceedings of the VLDB Endowment"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.14778\/3425879.3425890","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,28]],"date-time":"2022-12-28T11:07:40Z","timestamp":1672225660000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.14778\/3425879.3425890"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,10]]},"references-count":38,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2020,10]]}},"alternative-id":["10.14778\/3425879.3425890"],"URL":"https:\/\/doi.org\/10.14778\/3425879.3425890","relation":{},"ISSN":["2150-8097"],"issn-type":[{"value":"2150-8097","type":"print"}],"subject":[],"published":{"date-parts":[[2020,10]]}}}