{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,12]],"date-time":"2026-08-12T08:28:24Z","timestamp":1786523304238,"version":"build-2736575974"},"publisher-location":"New York, NY, USA","reference-count":45,"publisher":"ACM","license":[{"start":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T00:00:00Z","timestamp":1763164800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/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-SC0023171"],"award-info":[{"award-number":["DE-SC0023171"]}],"id":[{"id":"10.13039\/100000015","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000181","name":"Air Force Office of Scientific Research","doi-asserted-by":"publisher","award":["FA9550-24-1-0327"],"award-info":[{"award-number":["FA9550-24-1-0327"]}],"id":[{"id":"10.13039\/100000181","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"NSF (National Science Foundation)","doi-asserted-by":"publisher","award":["DGE-2137420"],"award-info":[{"award-number":["DGE-2137420"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,11,16]]},"DOI":"10.1145\/3731599.3767490","type":"proceedings-article","created":{"date-parts":[[2025,11,7]],"date-time":"2025-11-07T16:20:02Z","timestamp":1762532402000},"page":"1133-1146","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Mixed-Precision Performance Portability of FFT-Based GPU-Accelerated Algorithms for Block-Triangular Toeplitz Matrices"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8622-1063","authenticated-orcid":false,"given":"Sreeram","family":"Venkat","sequence":"first","affiliation":[{"name":"Oden Institute, The University of Texas at Austin, Austin, Texas, USA and Advanced Micro Devices, Inc. (AMD), Austin, Texas, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5758-5394","authenticated-orcid":false,"given":"Kasia","family":"\u015awirydowicz","sequence":"additional","affiliation":[{"name":"Advanced Micro Devices, Inc. (AMD), Austin, Texas, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7935-421X","authenticated-orcid":false,"given":"Noah","family":"Wolfe","sequence":"additional","affiliation":[{"name":"Advanced Micro Devices, Inc. (AMD), Austin, Texas, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7742-2509","authenticated-orcid":false,"given":"Omar","family":"Ghattas","sequence":"additional","affiliation":[{"name":"Oden Institute, Walker Department of Mechanical Engineering, The University of Texas at Austin, Austin, Texas, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,11,15]]},"reference":[{"key":"e_1_3_3_3_2_2","doi-asserted-by":"publisher","unstructured":"Ahmad Abdelfattah Hartwig Anzt Erik\u00a0G Boman Erin Carson Terry Cojean Jack Dongarra Alyson Fox Mark Gates Nicholas\u00a0J Higham Xiaoye\u00a0S Li et\u00a0al. 2021. A survey of numerical linear algebra methods utilizing mixed-precision arithmetic. The International Journal of High Performance Computing Applications 35 4 (2021) 344\u2013369. 10.1177\/10943420211003313","DOI":"10.1177\/10943420211003313"},{"key":"e_1_3_3_3_3_2","doi-asserted-by":"publisher","unstructured":"J\u00a0S\u00a0F Alexander Shreyas Ananthan M\u00a0Y Arpinar A Arteaga W Bail D\u00a0E Bailey A\u00a0B Balantekin J Balewski M\u00a0A Berrill M Bhandarkar et\u00a0al. 2021. A survey of software implementations used by application codes in the Exascale Computing Project. The International Journal of High Performance Computing Applications 35 6 (2021) 571\u2013588. 10.1177\/10943420211028940","DOI":"10.1177\/10943420211028940"},{"key":"e_1_3_3_3_4_2","doi-asserted-by":"publisher","unstructured":"Alen Alexanderian Philip\u00a0J. Gloor and Omar Ghattas. 2016. On Bayesian A-and D-optimal experimental designs in infinite dimensions. Bayesian Analysis 11 3 (2016) 671\u2013695. 10.1214\/15-BA969","DOI":"10.1214\/15-BA969"},{"key":"e_1_3_3_3_5_2","doi-asserted-by":"publisher","unstructured":"Alen Alexanderian Noemi Petra Georg Stadler and Omar Ghattas. 2014. A-optimal design of experiments for infinite-dimensional Bayesian linear inverse problems with regularized \u21130-sparsification. SIAM Journal on Scientific Computing 36 5 (2014) A2122\u2013A2148. 10.1137\/130933381","DOI":"10.1137\/130933381"},{"key":"e_1_3_3_3_6_2","doi-asserted-by":"publisher","unstructured":"Alen Alexanderian Noemi Petra Georg Stadler and Omar Ghattas. 2016. A Fast and Scalable Method for A-Optimal Design of Experiments for Infinite-dimensional Bayesian Nonlinear Inverse Problems. SIAM Journal on Scientific Computing 38 1 (2016) A243\u2013A272. 10.1137\/140992564","DOI":"10.1137\/140992564"},{"key":"e_1_3_3_3_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2012.71"},{"key":"e_1_3_3_3_8_2","doi-asserted-by":"publisher","DOI":"10.1109\/p3hpc49587.2019.00012"},{"key":"e_1_3_3_3_9_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4612-1426-7"},{"key":"e_1_3_3_3_10_2","doi-asserted-by":"publisher","unstructured":"Alfredo Buttari Jack Dongarra Julie Langou Julien Langou Piotr Luszczek and Jakub Kurzak. 2007. Mixed precision iterative refinement techniques for the solution of dense linear systems. The International Journal of High Performance Computing Applications 21 4 (2007) 457\u2013466. 10.1177\/1094342007084026","DOI":"10.1177\/1094342007084026"},{"key":"e_1_3_3_3_11_2","doi-asserted-by":"publisher","unstructured":"Erin Carson and Nicholas\u00a0J Higham. 2018. Accelerating the solution of linear systems by iterative refinement in three precisions. SIAM Journal on Scientific Computing 40 2 (2018) A817\u2013A847. 10.1137\/17M1140819","DOI":"10.1137\/17M1140819"},{"key":"e_1_3_3_3_12_2","doi-asserted-by":"publisher","unstructured":"Tony\u00a0F Chan and Tarek\u00a0P Mathew. 1994. Domain decomposition algorithms. Acta numerica 3 (1994) 61\u2013143. 10.1017\/S0962492900002427","DOI":"10.1017\/S0962492900002427"},{"key":"e_1_3_3_3_13_2","doi-asserted-by":"publisher","DOI":"10.1145\/3388333.3388643"},{"key":"e_1_3_3_3_14_2","unstructured":"Kalyanmoy Deb. 2001. Multi-objective optimization using evolutionary algorithms John Wiley & Sons. Inc. New York NY (2001)."},{"key":"e_1_3_3_3_15_2","doi-asserted-by":"publisher","unstructured":"Omar Ghattas and Karen Willcox. 2021. Learning physics-based models from data: Perspectives from inverse problems and model reduction. Acta Numerica 30 (2021) 445\u2013554. 10.1017\/S0962492921000064","DOI":"10.1017\/S0962492921000064"},{"key":"e_1_3_3_3_16_2","doi-asserted-by":"publisher","unstructured":"Dominik G\u00f6ddeke Robert Strzodka and Stefan Turek. 2007. Performance and accuracy of hardware-oriented native- emulated-and mixed-precision solvers in FEM simulations. International Journal of Parallel Emergent and Distributed Systems 22 4 (2007) 221\u2013256. 10.1080\/17445760601122076","DOI":"10.1080\/17445760601122076"},{"key":"e_1_3_3_3_17_2","doi-asserted-by":"publisher","DOI":"10.56021\/9781421407944"},{"key":"e_1_3_3_3_18_2","doi-asserted-by":"publisher","unstructured":"Robert\u00a0M Gray et\u00a0al. 2006. Toeplitz and circulant matrices: A review. Foundations and Trends in Communications and Information Theory 2 3 (2006) 155\u2013239. 10.1561\/0100000006","DOI":"10.1561\/0100000006"},{"key":"e_1_3_3_3_19_2","doi-asserted-by":"publisher","unstructured":"Yichen Guo Eric de Sturler and Tim Warburton. 2025. An Adaptive Mixed Precision and Dynamically Scaled Preconditioned Conjugate Gradient Algorithm. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2505.04155 (2025). 10.48550\/arXiv.2505.04155","DOI":"10.48550\/arXiv.2505.04155"},{"key":"e_1_3_3_3_20_2","doi-asserted-by":"publisher","DOI":"10.1145\/2503210.2504566"},{"key":"e_1_3_3_3_21_2","doi-asserted-by":"publisher","unstructured":"Nick Hagerty Ver\u00f3nica\u00a0G Melesse\u00a0Vergara and Arnold Tharrington. 2023. Studying performance portability of LAMMPS across diverse GPU-based platforms. Concurrency and Computation: Practice and Experience 35 28 (2023) e7895. 10.1002\/cpe.7895","DOI":"10.1002\/cpe.7895"},{"key":"e_1_3_3_3_22_2","doi-asserted-by":"publisher","DOI":"10.1145\/3712285.3771787"},{"key":"e_1_3_3_3_23_2","doi-asserted-by":"publisher","unstructured":"Stefan Henneking Sreeram Venkat and Omar Ghattas. 2025. Goal-oriented real-time Bayesian inference for linear autonomous dynamical systems with application to digital twins for tsunami early warning. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2501.14911 (2025). 10.48550\/arXiv.2501.14911","DOI":"10.48550\/arXiv.2501.14911"},{"key":"e_1_3_3_3_24_2","doi-asserted-by":"publisher","DOI":"10.1137\/1.9780898718027"},{"key":"e_1_3_3_3_25_2","doi-asserted-by":"publisher","unstructured":"Nicholas\u00a0J Higham and Theo Mary. 2022. Mixed precision algorithms in numerical linear algebra. Acta Numerica 31 (2022) 347\u2013414. 10.1017\/S0962492922000022","DOI":"10.1017\/S0962492922000022"},{"key":"e_1_3_3_3_26_2","doi-asserted-by":"publisher","unstructured":"Jose\u00a0L Jodra Ibai Gurrutxaga and Javier Muguerza. 2015. Efficient 3D transpositions in graphics processing units. International Journal of Parallel Programming 43 5 (2015) 876\u2013891. 10.1007\/s10766-015-0366-5","DOI":"10.1007\/s10766-015-0366-5"},{"key":"e_1_3_3_3_27_2","volume-title":"Linear systems","author":"Kailath Thomas","year":"1980","unstructured":"Thomas Kailath. 1980. Linear systems. Vol.\u00a0156. Prentice-Hall Englewood Cliffs, NJ."},{"key":"e_1_3_3_3_28_2","doi-asserted-by":"publisher","unstructured":"Aditya Kashi Hao Lu Wesley Brewer David Rogers Michael Matheson Mallikarjun Shankar and Feiyi Wang. 2024. Mixed-precision numerics in scientific applications: survey and perspectives. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2412.19322 (2024). 10.48550\/arXiv.2412.19322","DOI":"10.48550\/arXiv.2412.19322"},{"key":"e_1_3_3_3_29_2","doi-asserted-by":"publisher","DOI":"10.2172\/1845651"},{"key":"e_1_3_3_3_30_2","doi-asserted-by":"publisher","unstructured":"Nikolay Kondratyuk Vsevolod Nikolskiy Daniil Pavlov and Vladimir Stegailov. 2021. GPU-accelerated molecular dynamics: State-of-art software performance and porting from Nvidia CUDA to AMD HIP. The International Journal of High Performance Computing Applications 35 4 (2021) 312\u2013324. 10.1177\/10943420211008288","DOI":"10.1177\/10943420211008288"},{"key":"e_1_3_3_3_31_2","doi-asserted-by":"publisher","DOI":"10.1145\/3581784.3627042"},{"key":"e_1_3_3_3_32_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-662-02691-5"},{"key":"e_1_3_3_3_33_2","doi-asserted-by":"publisher","unstructured":"David\u00a0S Medina Amik St-Cyr and Tim Warburton. 2014. OCCA: A unified approach to multi-threading languages. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1403.0968 (2014). 10.48550\/arXiv.1403.0968","DOI":"10.48550\/arXiv.1403.0968"},{"key":"e_1_3_3_3_34_2","unstructured":"Timothy\u00a0Prickett Morgan. 2021. NVIDIA\u2019s CUDA Moat Is Getting Deeper And Wider. The Next Platform (15 March 2021). https:\/\/www.nextplatform.com\/2021\/03\/15\/nvidias-cuda-moat-is-getting-deeper-and-wider\/"},{"key":"e_1_3_3_3_35_2","doi-asserted-by":"publisher","unstructured":"Katsuhisa Ozaki Yuki Uchino and Toshiyuki Imamura. 2025. Ozaki Scheme II: A GEMM-oriented emulation of floating-point matrix multiplication using an integer modular technique. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2504.08009 (2025). 10.48550\/arXiv.2504.08009","DOI":"10.48550\/arXiv.2504.08009"},{"key":"e_1_3_3_3_36_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-15976-81"},{"key":"e_1_3_3_3_37_2","doi-asserted-by":"publisher","DOI":"10.1109\/telfor63250.2024.10819073"},{"key":"e_1_3_3_3_38_2","doi-asserted-by":"publisher","DOI":"10.3233\/978-1-61499-621-7-673"},{"key":"e_1_3_3_3_39_2","doi-asserted-by":"publisher","DOI":"10.1137\/1.9780898718003"},{"key":"e_1_3_3_3_40_2","doi-asserted-by":"publisher","unstructured":"Alex Simpkins. 2012. System identification: Theory for the user (ljung l.; 1999)[on the shelf]. IEEE Robotics & Automation Magazine 19 2 (2012) 95\u201396. 10.1109\/mra.2012.2192817","DOI":"10.1109\/mra.2012.2192817"},{"key":"e_1_3_3_3_41_2","doi-asserted-by":"publisher","DOI":"10.1109\/HiPCW.2018.8634417"},{"key":"e_1_3_3_3_42_2","doi-asserted-by":"publisher","unstructured":"Andrew\u00a0M Stuart. 2010. Inverse problems: A Bayesian perspective. Acta Numerica 19 (2010) 451\u2013559. 10.1017\/S0962492910000061","DOI":"10.1017\/S0962492910000061"},{"key":"e_1_3_3_3_43_2","doi-asserted-by":"publisher","unstructured":"Christian\u00a0R Trott Damien Lebrun-Grandi\u00e9 Daniel Arndt Jan Ciesko Vinh Dang Nathan Ellingwood Rahulkumar Gayatri Evan Harvey Daisy\u00a0S Hollman Dan Ibanez et\u00a0al. 2021. Kokkos 3: Programming model extensions for the exascale era. IEEE Transactions on Parallel and Distributed Systems 33 4 (2021) 805\u2013817. 10.1109\/tpds.2021.3097283","DOI":"10.1109\/tpds.2021.3097283"},{"key":"e_1_3_3_3_44_2","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611970999"},{"key":"e_1_3_3_3_45_2","doi-asserted-by":"publisher","unstructured":"Sreeram Venkat Milinda Fernando Stefan Henneking and Omar Ghattas. 2025. Fast and scalable FFT-based GPU-accelerated algorithms for block-triangular Toeplitz matrices with application to linear inverse problems governed by autonomous dynamical systems. SIAM Journal on Scientific Computing (2025). 10.48550\/arXiv.2407.13066To appear.","DOI":"10.48550\/arXiv.2407.13066"},{"key":"e_1_3_3_3_46_2","doi-asserted-by":"publisher","unstructured":"Keyi Wu Peng Chen and Omar Ghattas. 2023. A fast and scalable computational framework for large-scale high-dimensional Bayesian optimal experimental design. SIAM\/ASA Journal on Uncertainty Quantification 11 1 (2023) 235\u2013261. 10.1137\/21M1466499","DOI":"10.1137\/21M1466499"}],"event":{"name":"SC Workshops '25: Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis","location":"St Louis MO USA","acronym":"SC Workshops '25","sponsor":["SIGHPC ACM Special Interest Group on High Performance Computing, Special Interest Group on High Performance Computing"]},"container-title":["Proceedings of the SC '25 Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/full\/10.1145\/3731599.3767490","content-type":"text\/html","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3731599.3767490","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3731599.3767490","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,12]],"date-time":"2026-08-12T07:42:41Z","timestamp":1786520561000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3731599.3767490"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,15]]},"references-count":45,"alternative-id":["10.1145\/3731599.3767490","10.1145\/3731599"],"URL":"https:\/\/doi.org\/10.1145\/3731599.3767490","relation":{},"subject":[],"published":{"date-parts":[[2025,11,15]]},"assertion":[{"value":"2025-11-15","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}