{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T14:19:33Z","timestamp":1766067573451,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":32,"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":[{"DOI":"10.13039\/501100000288","name":"Royal Society","doi-asserted-by":"publisher","award":["INF\/R1\/180012"],"award-info":[{"award-number":["INF\/R1\/180012"]}],"id":[{"id":"10.13039\/501100000288","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,6,28]]},"DOI":"10.1145\/3524059.3532371","type":"proceedings-article","created":{"date-parts":[[2022,6,16]],"date-time":"2022-06-16T16:13:11Z","timestamp":1655395991000},"page":"1-12","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["High throughput multidimensional tridiagonal system solvers on FPGAs"],"prefix":"10.1145","author":[{"given":"Kamalavasan","family":"Kamalakkannan","sequence":"first","affiliation":[{"name":"University of Warwick, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gihan R.","family":"Mudalige","sequence":"additional","affiliation":[{"name":"University of Warwick, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Istvan Z.","family":"Reguly","sequence":"additional","affiliation":[{"name":"Pazmany Peter Catholic University, Hungary"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Suhaib A.","family":"Fahmy","sequence":"additional","affiliation":[{"name":"King Abdullah University of Science and Technology (KAUST), Saudi Arabia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2022,6,28]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"2020. Nvidia V100 Data Sheet. https:\/\/images.nvidia.com\/content\/technologies\/volta\/pdff\/volta-v100-datasheet-update-us-1165301-r5.pdf.  2020. Nvidia V100 Data Sheet. https:\/\/images.nvidia.com\/content\/technologies\/volta\/pdff\/volta-v100-datasheet-update-us-1165301-r5.pdf."},{"key":"e_1_3_2_1_2_1","unstructured":"2020. Tridsolver Library. https:\/\/github.com\/OP-DSL\/tridsolver.  2020. Tridsolver Library. https:\/\/github.com\/OP-DSL\/tridsolver."},{"key":"e_1_3_2_1_3_1","unstructured":"2020. Vitis High-Level Synthesis User Guide. https:\/\/www.xilinx.com\/support\/documentation\/sw_manuals\/xilinx2020_2\/ug1399-vitis-hls.pdf.  2020. Vitis High-Level Synthesis User Guide. https:\/\/www.xilinx.com\/support\/documentation\/sw_manuals\/xilinx2020_2\/ug1399-vitis-hls.pdf."},{"key":"e_1_3_2_1_4_1","unstructured":"2020. Vitis Quantitative Finance Library V.2020.2. https:\/\/xilinx.github.io\/Vitis_Libraries\/quantitative_finance\/2020.2\/.  2020. Vitis Quantitative Finance Library V.2020.2. https:\/\/xilinx.github.io\/Vitis_Libraries\/quantitative_finance\/2020.2\/."},{"key":"e_1_3_2_1_5_1","unstructured":"2021. Batched Tridiagonal Systems Solver Library for FPGAs. [https:\/\/github.com\/Kamalavasan\/Tridsolver-FPGA].  2021. Batched Tridiagonal Systems Solver Library for FPGAs. [https:\/\/github.com\/Kamalavasan\/Tridsolver-FPGA]."},{"key":"e_1_3_2_1_6_1","unstructured":"2021. cuSPARSE API Reference. [https:\/\/docs.nvidia.com\/cuda\/cusparse\/index.html].  2021. cuSPARSE API Reference. [https:\/\/docs.nvidia.com\/cuda\/cusparse\/index.html]."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/MCSE.2021.3130544"},{"key":"e_1_3_2_1_8_1","volume-title":"Tal Ben-Nun, Dominic Hofer, and Torsten Hoefler.","author":"de Fine Licht Johannes","year":"2021","unstructured":"Johannes de Fine Licht , Andreas Kuster , Tiziano De Matteis , Tal Ben-Nun, Dominic Hofer, and Torsten Hoefler. 2021 . StencilFlow: Mapping Large Stencil Programs to Distributed Spatial Computing Systems ., 315--326 pages. Johannes de Fine Licht, Andreas Kuster, Tiziano De Matteis, Tal Ben-Nun, Dominic Hofer, and Torsten Hoefler. 2021. StencilFlow: Mapping Large Stencil Programs to Distributed Spatial Computing Systems., 315--326 pages."},{"key":"e_1_3_2_1_9_1","volume-title":"Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis","author":"Matteis Tiziano De","year":"2020","unstructured":"Tiziano De Matteis , Johannes de Fine Licht , and Torsten Hoefler . 2020 . FBLAS: Streaming Linear Algebra on FPGA . In Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis ( Atlanta, Georgia) (SC '20). IEEE Press, Article 59, 13 pages. Tiziano De Matteis, Johannes de Fine Licht, and Torsten Hoefler. 2020. FBLAS: Streaming Linear Algebra on FPGA. In Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis (Atlanta, Georgia) (SC '20). IEEE Press, Article 59, 13 pages."},{"key":"e_1_3_2_1_10_1","volume-title":"A General Formulation of Alternating Direction Methods. Num\u00e8rische math\u00e8matik 6, 1","author":"Douglas Jim","year":"1964","unstructured":"Jim Douglas and James E Gunn . 1964. A General Formulation of Alternating Direction Methods. Num\u00e8rische math\u00e8matik 6, 1 ( 1964 ), 428--453. Jim Douglas and James E Gunn. 1964. A General Formulation of Alternating Direction Methods. Num\u00e8rische math\u00e8matik 6, 1 (1964), 428--453."},{"key":"e_1_3_2_1_11_1","volume-title":"Cyclic Reduction---History and Applications. Scientific computing (Hong Kong) 7385","author":"Gander Walter","year":"1997","unstructured":"Walter Gander and Gene H Golub . 1997. Cyclic Reduction---History and Applications. Scientific computing (Hong Kong) 7385 ( 1997 ). Walter Gander and Gene H Golub. 1997. Cyclic Reduction---History and Applications. Scientific computing (Hong Kong) 7385 (1997)."},{"key":"e_1_3_2_1_12_1","volume-title":"GraphLily: Accelerating Graph Linear Algebra on HBM-Equipped FPGAs. In IEEE\/ACM International Conference On Computer Aided Design (ICCAD).","author":"Hu Yuwei","year":"2021","unstructured":"Yuwei Hu , Yixiao Du , Ecenur Ustun , and Zhiru Zhang . 2021 . GraphLily: Accelerating Graph Linear Algebra on HBM-Equipped FPGAs. In IEEE\/ACM International Conference On Computer Aided Design (ICCAD). Yuwei Hu, Yixiao Du, Ecenur Ustun, and Zhiru Zhang. 2021. GraphLily: Accelerating Graph Linear Algebra on HBM-Equipped FPGAs. In IEEE\/ACM International Conference On Computer Aided Design (ICCAD)."},{"volume-title":"High-Level FPGA Accelerator Design for Structured-Mesh-Based Explicit Numerical Solvers. In IEEE International Parallel and Distributed Processing Symposium (IPDPS). 1087--1096","author":"Kamalakkannan Kamalavasan","key":"e_1_3_2_1_13_1","unstructured":"Kamalavasan Kamalakkannan , Gihan R. Mudalige , Istvan Z. Reguly , and Suhaib A. Fahmy . 2021 . High-Level FPGA Accelerator Design for Structured-Mesh-Based Explicit Numerical Solvers. In IEEE International Parallel and Distributed Processing Symposium (IPDPS). 1087--1096 . Kamalavasan Kamalakkannan, Gihan R. Mudalige, Istvan Z. Reguly, and Suhaib A. Fahmy. 2021. High-Level FPGA Accelerator Design for Structured-Mesh-Based Explicit Numerical Solvers. In IEEE International Parallel and Distributed Processing Symposium (IPDPS). 1087--1096."},{"key":"e_1_3_2_1_14_1","volume-title":"High Bandwidth Memory on FPGAs: A Data Analytics Perspective. In International Conference on Field-Programmable Logic and Applications (FPL).","author":"Kara Kaan","year":"2020","unstructured":"Kaan Kara , Christoph Hagleitner , Dionysios Diamantopoulos , Dimitris Syrivelis , and Gustavo Alonso . 2020 . High Bandwidth Memory on FPGAs: A Data Analytics Perspective. In International Conference on Field-Programmable Logic and Applications (FPL). Kaan Kara, Christoph Hagleitner, Dionysios Diamantopoulos, Dimitris Syrivelis, and Gustavo Alonso. 2020. High Bandwidth Memory on FPGAs: A Data Analytics Perspective. In International Conference on Field-Programmable Logic and Applications (FPL)."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/2830568"},{"key":"e_1_3_2_1_16_1","volume-title":"Analysis of Parallel Processor Architectures for the Solution of the Black-Scholes PDE. In IEEE International Symposium on Circuits and Systems (ISCAS). 1977--1980","author":"L\u00e1szl\u00f3 Endre","year":"2015","unstructured":"Endre L\u00e1szl\u00f3 , Zolt\u00e1n Nagy , Michael B. Giles , Istv\u00e1n Reguly , Jeremy Appleyard , and Peter Szolgay . 2015 . Analysis of Parallel Processor Architectures for the Solution of the Black-Scholes PDE. In IEEE International Symposium on Circuits and Systems (ISCAS). 1977--1980 . Endre L\u00e1szl\u00f3, Zolt\u00e1n Nagy, Michael B. Giles, Istv\u00e1n Reguly, Jeremy Appleyard, and Peter Szolgay. 2015. Analysis of Parallel Processor Architectures for the Solution of the Black-Scholes PDE. In IEEE International Symposium on Circuits and Systems (ISCAS). 1977--1980."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"crossref","unstructured":"H. Macintosh Jasmine Banks and N. Kelson. 2019. Implementing and Evaluating an Heterogeneous Scalable Tridiagonal Linear System Solver with OpenCL to Target FPGAs GPUs and CPUs. International Journal of Reconfigurable Computing (2019).  H. Macintosh Jasmine Banks and N. Kelson. 2019. Implementing and Evaluating an Heterogeneous Scalable Tridiagonal Linear System Solver with OpenCL to Target FPGAs GPUs and CPUs. International Journal of Reconfigurable Computing (2019).","DOI":"10.1155\/2019\/3679839"},{"key":"e_1_3_2_1_18_1","volume-title":"Proceedings of the Biennial Computational Techniques and Applications Conference (CTAC)","volume":"56","author":"Macintosh H. J.","unstructured":"H. J. Macintosh , D. J. Warne , N. A. Kelson , J. E. Banks , and T. W. Farrell . 2016. Implementation of Parallel Tridiagonal Solvers for a Heterogeneous Computing Environment . In Proceedings of the Biennial Computational Techniques and Applications Conference (CTAC) , Vol. 56 . C446--C462. H. J. Macintosh, D. J. Warne, N. A. Kelson, J. E. Banks, and T. W. Farrell. 2016. Implementation of Parallel Tridiagonal Solvers for a Heterogeneous Computing Environment. In Proceedings of the Biennial Computational Techniques and Applications Conference (CTAC), Vol. 56. C446--C462."},{"key":"e_1_3_2_1_19_1","volume-title":"Alves","author":"Oliveira Filipe","year":"2008","unstructured":"Filipe Oliveira , C. Silva Santos , F. A. Castro , and Jos\u00e9 C . Alves . 2008 . A Custom Processor for a TDMA Solver in a CFD Application. In Reconfigurable Computing: Architectures, Tools and Applications, Roger Woods, Katherine Compton, Christos Bouganis, and Pedro C. Diniz (Eds.). Springer Berlin Heidelberg , Berlin, Heidelberg, 63--74. Filipe Oliveira, C. Silva Santos, F. A. Castro, and Jos\u00e9 C. Alves. 2008. A Custom Processor for a TDMA Solver in a CFD Application. In Reconfigurable Computing: Architectures, Tools and Applications, Roger Woods, Katherine Compton, Christos Bouganis, and Pedro C. Diniz (Eds.). Springer Berlin Heidelberg, Berlin, Heidelberg, 63--74."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1137\/0103003"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.parco.2005.07.005"},{"key":"e_1_3_2_1_22_1","volume-title":"Mudalige","author":"Reguly Istvan Z.","year":"2019","unstructured":"Istvan Z. Reguly , Branden Moore , Tim Schmielau , Jacques du Toit , and Gihan R . Mudalige . 2019 . Batch solution of small PDEs with the OPS DSL. In High Performance Computing, Mich\u00e8le Weiland, Guido Juckeland, Sadaf Alam, and Heike Jagode (Eds.). Springer International Publishing , Cham, 124--141. Istvan Z. Reguly, Branden Moore, Tim Schmielau, Jacques du Toit, and Gihan R. Mudalige. 2019. Batch solution of small PDEs with the OPS DSL. In High Performance Computing, Mich\u00e8le Weiland, Guido Juckeland, Sadaf Alam, and Heike Jagode (Eds.). Springer International Publishing, Cham, 124--141."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2015.2474363"},{"key":"e_1_3_2_1_24_1","volume-title":"NERO: A Near High-Bandwidth Memory Stencil Accelerator for Weather Prediction Modeling. In International Conference on Field-Programmable Logic and Applications (FPL). 9--7.","author":"Singh Gagandeep","year":"2020","unstructured":"Gagandeep Singh , Dionysios Diamantopoulos , Christoph Hagleitner , Juan Gomez-Luna , Sander Stuijk , Onur Mutlu , and Henk Corp oraal. 2020 . NERO: A Near High-Bandwidth Memory Stencil Accelerator for Weather Prediction Modeling. In International Conference on Field-Programmable Logic and Applications (FPL). 9--7. Gagandeep Singh, Dionysios Diamantopoulos, Christoph Hagleitner, Juan Gomez-Luna, Sander Stuijk, Onur Mutlu, and Henk Corporaal. 2020. NERO: A Near High-Bandwidth Memory Stencil Accelerator for Weather Prediction Modeling. In International Conference on Field-Programmable Logic and Applications (FPL). 9--7."},{"key":"e_1_3_2_1_25_1","unstructured":"G. Tataru and T. Fisher. 2010. Stochastic Local Volatility. Quantitative Development Group Bloomberg Version 1 (Feb 2010).  G. Tataru and T. Fisher. 2010. Stochastic Local Volatility. Quantitative Development Group Bloomberg Version 1 (Feb 2010)."},{"key":"e_1_3_2_1_26_1","volume-title":"NY","author":"Thomas Llewellyn","year":"1949","unstructured":"Llewellyn Thomas . 1949. Elliptic Problems in Linear Differential Equations Over a Network: Watson Scientific Computing Laboratory. Columbia Univ ., NY ( 1949 ). Llewellyn Thomas. 1949. Elliptic Problems in Linear Differential Equations Over a Network: Watson Scientific Computing Laboratory. Columbia Univ., NY (1949)."},{"key":"e_1_3_2_1_27_1","volume-title":"Pe\u00f1a","author":"Valero-Lara Pedro","year":"2018","unstructured":"Pedro Valero-Lara , Ivan Mart\u00ednez-P\u00e9rez , Ra\u00fcl Sirvent , Xavier Martorell , and Antonio J . Pe\u00f1a . 2018 . Nvidia GPUs Scalability to Solve Multiple (Batch) Tridiagonal Systems Implementation of cuThomasBatch. In Parallel Processing and Applied Mathematics, Roman Wyrzykowski, Jack Dongarra, Ewa Deelman, and Konrad Karczewski (Eds.). Springer International Publishing , Cham, 243--253. Pedro Valero-Lara, Ivan Mart\u00ednez-P\u00e9rez, Ra\u00fcl Sirvent, Xavier Martorell, and Antonio J. Pe\u00f1a. 2018. Nvidia GPUs Scalability to Solve Multiple (Batch) Tridiagonal Systems Implementation of cuThomasBatch. In Parallel Processing and Applied Mathematics, Roman Wyrzykowski, Jack Dongarra, Ewa Deelman, and Konrad Karczewski (Eds.). Springer International Publishing, Cham, 243--253."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/ScalA.2014.12"},{"key":"e_1_3_2_1_29_1","volume-title":"Proceedings of the International Conference on Computational Methods, Y Gu and S Saha (Eds.)","author":"Warne David","year":"2012","unstructured":"David Warne , Neil Kelson , and Ross Hayward . 2012 . Solving Tri-diagonal Linear Systems Using Field Programmable Gate Arrays . In Proceedings of the International Conference on Computational Methods, Y Gu and S Saha (Eds.) . Queensland University of Technology, Australia. David Warne, Neil Kelson, and Ross Hayward. 2012. Solving Tri-diagonal Linear Systems Using Field Programmable Gate Arrays. In Proceedings of the International Conference on Computational Methods, Y Gu and S Saha (Eds.). Queensland University of Technology, Australia."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2014.05.009"},{"volume-title":"Alveo U280 Data Center Accelerator Card Data Sheet","author":"Xilinx Inc. 2020.","key":"e_1_3_2_1_31_1","unstructured":"Xilinx Inc. 2020. Alveo U280 Data Center Accelerator Card Data Sheet . Xilinx Inc . v1.3. Xilinx Inc. 2020. Alveo U280 Data Center Accelerator Card Data Sheet. Xilinx Inc. v1.3."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/2133352.2133358"}],"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\/3524059.3532371","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3524059.3532371","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\/3524059.3532371"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,6,28]]},"references-count":32,"alternative-id":["10.1145\/3524059.3532371","10.1145\/3524059"],"URL":"https:\/\/doi.org\/10.1145\/3524059.3532371","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"}}]}}