{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,6]],"date-time":"2026-01-06T13:05:53Z","timestamp":1767704753349,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":49,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,6,28]],"date-time":"2022-06-28T00:00:00Z","timestamp":1656374400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Texas Advanced Computing Center (TACC)","award":["DMS21075, A-ee6, CCR21019"],"award-info":[{"award-number":["DMS21075, A-ee6, CCR21019"]}]},{"name":"ExxonMobil Research and Engineering Company,","award":["EM10480.36"],"award-info":[{"award-number":["EM10480.36"]}]},{"name":"National Science Foundation (NSF)","award":["1763848"],"award-info":[{"award-number":["1763848"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,6,28]]},"DOI":"10.1145\/3524059.3532373","type":"proceedings-article","created":{"date-parts":[[2022,6,16]],"date-time":"2022-06-16T16:13:11Z","timestamp":1655395991000},"page":"1-13","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":10,"title":["GAPS"],"prefix":"10.1145","author":[{"given":"Bagus","family":"Hanindhito","sequence":"first","affiliation":[{"name":"The University of Texas at Austin"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dimitrios","family":"Gourounas","sequence":"additional","affiliation":[{"name":"The University of Texas at Austin"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Arash","family":"Fathi","sequence":"additional","affiliation":[{"name":"ExxonMobil Technology and Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dimitar","family":"Trenev","sequence":"additional","affiliation":[{"name":"ExxonMobil Technology and Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andreas","family":"Gerstlauer","sequence":"additional","affiliation":[{"name":"The University of Texas at Austin"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lizy K.","family":"John","sequence":"additional","affiliation":[{"name":"The University of Texas at Austin"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2022,6,28]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1177\/1094342017694427"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/PIERS.2016.7734532"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1137\/100791634"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcp.2016.04.003"},{"key":"e_1_3_2_1_5_1","unstructured":"NVIDIA Corporation. 2017. NVIDIA TESLA V100 GPU ARCHITECTURE: THE WORLD'S MOST ADVANCED DATA CENTER GPU. https:\/\/images.nvidia.com\/content\/volta-architecture\/pdf\/volta-architecture-whitepaper.pdf.  NVIDIA Corporation. 2017. NVIDIA TESLA V100 GPU ARCHITECTURE: THE WORLD'S MOST ADVANCED DATA CENTER GPU. https:\/\/images.nvidia.com\/content\/volta-architecture\/pdf\/volta-architecture-whitepaper.pdf."},{"key":"e_1_3_2_1_6_1","unstructured":"NVIDIA Corporation. 2019. NVIDIA CUDA Toolkit Documentation. https:\/\/docs.nvidia.com\/cuda\/profiler-users-guide\/index.html\/.  NVIDIA Corporation. 2019. NVIDIA CUDA Toolkit Documentation. https:\/\/docs.nvidia.com\/cuda\/profiler-users-guide\/index.html\/."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/2818950.2818972"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1121\/AT.2019.15.3.28"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cma.2015.07.008"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1002\/nme.4780"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.soildyn.2016.04.010"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.4208\/cicp.070114.271114a"},{"key":"e_1_3_2_1_13_1","volume-title":"Meng-Xing Tang, Parashkev Nachev, and Michael Warner.","author":"Guasch Llu\u00eds","year":"2020","unstructured":"Llu\u00eds Guasch , Oscar Calderon Agudo , Meng-Xing Tang, Parashkev Nachev, and Michael Warner. 2020 . Full-waveform inversion imaging of the human brain. npj Digital Medicine 3 (2020), 1 -- 12. Llu\u00eds Guasch, Oscar Calderon Agudo, Meng-Xing Tang, Parashkev Nachev, and Michael Warner. 2020. Full-waveform inversion imaging of the human brain. npj Digital Medicine 3 (2020), 1 -- 12."},{"key":"e_1_3_2_1_14_1","volume-title":"Wave-PIM: Accelerating Wave Simulation Using Processing-in-Memory. In 50th International Conference on Parallel Processing","author":"Hanindhito Bagus","year":"2021","unstructured":"Bagus Hanindhito , Ruihao Li , Dimitrios Gourounas , Arash Fathi , Karan Govil , Dimitar Trenev , Andreas Gerstlauer , and Lizy John . 2021 . Wave-PIM: Accelerating Wave Simulation Using Processing-in-Memory. In 50th International Conference on Parallel Processing ( Lemont, IL, USA) (ICPP 2021). Association for Computing Machinery, New York, NY, USA, Article 8, 11 pages. Bagus Hanindhito, Ruihao Li, Dimitrios Gourounas, Arash Fathi, Karan Govil, Dimitar Trenev, Andreas Gerstlauer, and Lizy John. 2021. Wave-PIM: Accelerating Wave Simulation Using Processing-in-Memory. In 50th International Conference on Parallel Processing (Lemont, IL, USA) (ICPP 2021). Association for Computing Machinery, New York, NY, USA, Article 8, 11 pages."},{"key":"e_1_3_2_1_15_1","unstructured":"J.S. Hesthaven and T. Warburton. 2010. Nodal Discontinuous Galerkin Methods: Algorithms Analysis and Applications. Springer.  J.S. Hesthaven and T. Warburton. 2010. Nodal Discontinuous Galerkin Methods: Algorithms Analysis and Applications. Springer."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"crossref","unstructured":"S.B. Hong N. Vlahopoulos R. M. Mantey and D. J. Gorsich. 2004. A computational approach for evaluating the probability of acoustic detection of a military vehicle. In Targets and Backgrounds X: Characterization and Representation Wendell R. Watkins Dieter Clement and William R. Reynolds (Eds.) Vol. 5431. International Society for Optics and Photonics SPIE 150 -- 159.  S.B. Hong N. Vlahopoulos R. M. Mantey and D. J. Gorsich. 2004. A computational approach for evaluating the probability of acoustic detection of a military vehicle. In Targets and Backgrounds X: Characterization and Representation Wendell R. Watkins Dieter Clement and William R. Reynolds (Eds.) Vol. 5431. International Society for Optics and Photonics SPIE 150 -- 159.","DOI":"10.1117\/12.542064"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503470.3503474"},{"volume-title":"Finite element analysis of acoustic scattering","author":"Ihlenburg Frank","key":"e_1_3_2_1_18_1","unstructured":"Frank Ihlenburg . 1998. Finite element analysis of acoustic scattering . Springer . Frank Ihlenburg. 1998. Finite element analysis of acoustic scattering. Springer."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.soildyn.2012.12.012"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcp.2019.04.010"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10915-018-0682-1"},{"volume-title":"Frontiers in PDE-Constrained Optimization","author":"Lacasse D","key":"e_1_3_2_1_22_1","unstructured":"Martin- D Lacasse , Laurent White , Huseyin Denli , and Lingyun Qiu . 2018. Full-wavefield inversion: An extreme-scale PDE-constrained optimization problem . In Frontiers in PDE-Constrained Optimization . Springer , 205--255. Martin-D Lacasse, Laurent White, Huseyin Denli, and Lingyun Qiu. 2018. Full-wavefield inversion: An extreme-scale PDE-constrained optimization problem. In Frontiers in PDE-Constrained Optimization. Springer, 205--255."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3295500.3356176"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2019.2928289"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2018.8573483"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/TBME.2015.2506680"},{"key":"e_1_3_2_1_27_1","volume-title":"MPI: A Message-Passing Interface Standard Version 3.1. https:\/\/www.mpi-forum.org\/docs\/mpi-3.1\/mpi31-report.pdf","author":"Interface Forum Message Passing","year":"2015","unstructured":"Message Passing Interface Forum . 2015 . MPI: A Message-Passing Interface Standard Version 3.1. https:\/\/www.mpi-forum.org\/docs\/mpi-3.1\/mpi31-report.pdf Message Passing Interface Forum. 2015. MPI: A Message-Passing Interface Standard Version 3.1. https:\/\/www.mpi-forum.org\/docs\/mpi-3.1\/mpi31-report.pdf"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cageo.2016.03.008"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-34132-8_17"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cageo.2012.07.017"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2014.70"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jocs.2020.101208"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1023\/a:1023204631825"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.soildyn.2016.10.031"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.soildyn.2019.105909"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"crossref","unstructured":"A. Quarteroni and A. Valli. 1994. Numerical Approximation of Partial Differential Equations. Springer.  A. Quarteroni and A. Valli. 1994. Numerical Approximation of Partial Differential Equations. Springer.","DOI":"10.1007\/978-3-540-85268-1"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3178487.3178500"},{"volume-title":"Proceedings of the 25th European MPI Users' Group Meeting","author":"Ruhela Amit","key":"e_1_3_2_1_38_1","unstructured":"Amit Ruhela , Hari Subramoni , Sourav Chakraborty , Mohammadreza Bayatpour , Pouya Kousha , and Dhabaleswar K. Panda . 2018. Efficient Asynchronous Communication Progress for MPI without Dedicated Resources . In Proceedings of the 25th European MPI Users' Group Meeting ( Barcelona, Spain) (EuroMPI'18). Association for Computing Machinery, New York, NY, USA, Article 14, 11 pages. Amit Ruhela, Hari Subramoni, Sourav Chakraborty, Mohammadreza Bayatpour, Pouya Kousha, and Dhabaleswar K. Panda. 2018. Efficient Asynchronous Communication Progress for MPI without Dedicated Resources. In Proceedings of the 25th European MPI Users' Group Meeting (Barcelona, Spain) (EuroMPI'18). Association for Computing Machinery, New York, NY, USA, Article 14, 11 pages."},{"volume-title":"Seismic Exploration Methods","author":"Sengbush R. L.","key":"e_1_3_2_1_39_1","unstructured":"R. L. Sengbush . 1983. Seismic Exploration Methods . Springer Netherlands , Dordrecht . R. L. Sengbush. 1983. Seismic Exploration Methods. Springer Netherlands, Dordrecht."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCC-SmartCity-DSS.2017.27"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2017.2703149"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2014.21"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICPPW.2016.32"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcp.2010.09.008"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/1498765.1498785"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/2751205.2751213"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/2442516.2442523"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/216585.216588"},{"key":"e_1_3_2_1_49_1","unstructured":"Charlene Yang. 2015. Berkeley CS Roofline Toolkit. https:\/\/bitbucket.org\/berkeleylab\/cs-roofline-toolkit.  Charlene Yang. 2015. Berkeley CS Roofline Toolkit. https:\/\/bitbucket.org\/berkeleylab\/cs-roofline-toolkit."}],"event":{"name":"ICS '22: 2022 International Conference on Supercomputing","sponsor":["SIGARCH ACM Special Interest Group on Computer Architecture"],"location":"Virtual Event","acronym":"ICS '22"},"container-title":["Proceedings of the 36th ACM International Conference on Supercomputing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3524059.3532373","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3524059.3532373","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:30:37Z","timestamp":1750188637000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3524059.3532373"}},"subtitle":["GPU-acceleration of PDE solvers for wave simulation"],"short-title":[],"issued":{"date-parts":[[2022,6,28]]},"references-count":49,"alternative-id":["10.1145\/3524059.3532373","10.1145\/3524059"],"URL":"https:\/\/doi.org\/10.1145\/3524059.3532373","relation":{},"subject":[],"published":{"date-parts":[[2022,6,28]]},"assertion":[{"value":"2022-06-28","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}