{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,9]],"date-time":"2026-01-09T12:02:34Z","timestamp":1767960154132,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":23,"publisher":"ACM","funder":[{"name":"JSPS KAKENHI","award":["25K03126"],"award-info":[{"award-number":["25K03126"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,1,26]]},"DOI":"10.1145\/3773656.3773681","type":"proceedings-article","created":{"date-parts":[[2026,1,9]],"date-time":"2026-01-09T10:22:11Z","timestamp":1767954131000},"page":"165-176","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Mixed-precision Interpolative Decomposition on GPUs"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4688-5644","authenticated-orcid":false,"given":"Qianxiang","family":"Ma","sequence":"first","affiliation":[{"name":"Large-scale Parallel Numerical Computing Technology Research Team, RIKEN Center for Computational Science, Kobe, Hyogo, Japan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1601-9710","authenticated-orcid":false,"given":"Toshiyuki","family":"Imamura","sequence":"additional","affiliation":[{"name":"Large-scale Parallel Numerical Computing Technology Research Team, RIKEN Center for Computational Science, Kobe, Hyogo, Japan"}]}],"member":"320","published-online":{"date-parts":[[2026,1,25]]},"reference":[{"key":"e_1_3_3_1_2_2","doi-asserted-by":"publisher","unstructured":"Patrick\u00a0R. Amestoy Alfredo Buttari Jean-Yves L\u2019Excellent and Theo Mary. 2016. On the Complexity of the Block Low-Rank Multifrontal Factorization. SIAM Journal on Scientific Computing 39 4 (May 2016) 34. 10.1137\/16M1077192Publisher: Society for Industrial and Applied Mathematics.","DOI":"10.1137\/16M1077192"},{"key":"e_1_3_3_1_3_2","doi-asserted-by":"publisher","unstructured":"Steffen Borm. 2004. \\(\\mathcal {H}^2\\)-Matrices \u2013 Multilevel Methods for the Approximation of Integral Operators. Computing and Visualization in Science 7 3-4 (Oct. 2004) 173\u2013181. 10.1007\/s00791-004-0135-2Number: 3-4.","DOI":"10.1007\/s00791-004-0135-2"},{"key":"e_1_3_3_1_4_2","doi-asserted-by":"publisher","unstructured":"H. Cheng Z. Gimbutas P.\u00a0G. Martinsson and V. Rokhlin. 2005. On the Compression of Low Rank Matrices. SIAM Journal on Scientific Computing 26 4 (2005) 1389\u20131404. 10.1137\/030602678Number: 4.","DOI":"10.1137\/030602678"},{"key":"e_1_3_3_1_5_2","doi-asserted-by":"crossref","unstructured":"Jack Dongarra Mark Gates Azzam Haidar Jakub Kurzak Piotr Luszczek Stanimire Tomov and Ichitaro Yamazaki. 2014. Accelerating Numerical Dense Linear Algebra Calculations with GPUs. Numerical Computations with GPUs (2014) 1\u201326.","DOI":"10.1007\/978-3-319-06548-9_1"},{"key":"e_1_3_3_1_6_2","doi-asserted-by":"publisher","unstructured":"Jed\u00a0A. Duersch and Ming Gu. 2017. Randomized QR with Column Pivoting. SIAM Journal on Scientific Computing 39 4 (Jan. 2017) C263\u2013C291. 10.1137\/15m1044680","DOI":"10.1137\/15m1044680"},{"key":"e_1_3_3_1_7_2","doi-asserted-by":"crossref","unstructured":"M. Faustmann J.\u00a0M. Melenk and D. Praetorius. 2016. Existence of H-Matrix Approximants to the Inverses of BEM Matrices: The Simple-Layer Operator. Math. Comp. 85 297 (2016) 119\u2013152. Number: 297.","DOI":"10.1090\/mcom\/2990"},{"key":"e_1_3_3_1_8_2","unstructured":"Jordi Feliu-Fab\u00e0 and Lexing Ying. 2020. Hierarchical Interpolative Factorization Preconditioner for Parabolic Equations. arXiv:https:\/\/arXiv.org\/abs\/2004.05566 [cs math] (April 2020). http:\/\/arxiv.org\/abs\/2004.05566 arXiv:https:\/\/arXiv.org\/abs\/2004.05566."},{"key":"e_1_3_3_1_9_2","unstructured":"Shmuel Friedland and Venu Tammali. 2014. Low-rank approximation of tensors. arxiv:https:\/\/arXiv.org\/abs\/1410.6089\u00a0[math.NA] https:\/\/arxiv.org\/abs\/1410.6089"},{"key":"e_1_3_3_1_10_2","unstructured":"Nathan Halko Per-Gunnar Martinsson and Joel\u00a0A. Tropp. 2010. Finding structure with randomness: Probabilistic algorithms for constructing approximate matrix decompositions. arxiv:https:\/\/arXiv.org\/abs\/0909.4061\u00a0[math.NA] https:\/\/arxiv.org\/abs\/0909.4061"},{"key":"e_1_3_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/ARITH.2001.930115"},{"key":"e_1_3_3_1_12_2","doi-asserted-by":"publisher","unstructured":"Tamara\u00a0G. Kolda and Brett\u00a0W. Bader. 2009. Tensor Decompositions and Applications. SIAM Rev. 51 3 (2009) 455\u2013500. 10.1137\/07070111X_eprint: https:\/\/doi.org\/10.1137\/07070111X.","DOI":"10.1137\/07070111X"},{"key":"e_1_3_3_1_13_2","doi-asserted-by":"publisher","unstructured":"E. Liberty F. Woolfe P.\u00a0G. Martinsson V. Rokhlin and M. Tygert. 2007. Randomized Algorithms for the Low-Rank Approximation of Matrices. PNAS 104 51 (2007) 20167\u201320172. 10.1073\/pnas.0709640104Number: 51.","DOI":"10.1073\/pnas.0709640104"},{"key":"e_1_3_3_1_14_2","doi-asserted-by":"publisher","unstructured":"Yuji Nakatsukasa Zhaojun Bai and Francois Gygi. 2010. Optimizing Halley\u2019s Iteration for Computing the Matrix Polar Decomposition. SIAM J. Matrix Anal. Appl. 31 (09 2010) 2700\u20132720. 10.1137\/090774999","DOI":"10.1137\/090774999"},{"key":"e_1_3_3_1_15_2","doi-asserted-by":"publisher","unstructured":"Hiroyuki Ootomo Katsuhisa Ozaki and Rio Yokota. 2024. DGEMM on integer matrix multiplication unit. The International Journal of High Performance Computing Applications 38 4 (2024) 297\u2013313. arXiv:10.1177\/1094342024123958810.1177\/10943420241239588","DOI":"10.1177\/10943420241239588"},{"key":"e_1_3_3_1_16_2","doi-asserted-by":"publisher","unstructured":"I.\u00a0V. Oseledets. 2011. Tensor-Train Decomposition. SIAM Journal on Scientific Computing 33 5 (2011) 2295\u20132317. 10.1137\/090752286_eprint: https:\/\/doi.org\/10.1137\/090752286.","DOI":"10.1137\/090752286"},{"key":"e_1_3_3_1_17_2","doi-asserted-by":"publisher","unstructured":"Katsuhisa Ozaki Takeshi Ogita Shin\u2019ichi Oishi and Siegfried\u00a0M. Rump. 2013. Generalization of error-free transformation for matrix multiplication and its application. Nonlinear Theory and Its Applications IEICE 4 1 (2013) 2\u201311. 10.1587\/nolta.4.2","DOI":"10.1587\/nolta.4.2"},{"key":"e_1_3_3_1_18_2","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:https:\/\/arXiv.org\/abs\/2504.08009\u00a0[cs.MS] https:\/\/arxiv.org\/abs\/2504.08009"},{"key":"e_1_3_3_1_19_2","volume-title":"International Association for Boundary Element Methods","author":"Rjasanow S.","year":"2002","unstructured":"S. Rjasanow. 2002. Adaptive Cross Approximation of Dense Matrices. In International Association for Boundary Element Methods. UT Austin, TX, USA. https:\/\/www.researchgate.net\/publication\/265984385_Adaptive_Cross_Approximation_of_Dense_Matrices"},{"key":"e_1_3_3_1_20_2","doi-asserted-by":"publisher","DOI":"10.23919\/ISC.2025.11017731"},{"key":"e_1_3_3_1_21_2","doi-asserted-by":"crossref","unstructured":"Yuki Uchino Katsuhisa Ozaki and Toshiyuki Imamura. 2025. High-Performance and Power-Efficient Emulation of Matrix Multiplication using INT8 Matrix Engines. arxiv:https:\/\/arXiv.org\/abs\/2508.03984\u00a0[cs.DC] https:\/\/arxiv.org\/abs\/2508.03984","DOI":"10.1145\/3731599.3767539"},{"key":"e_1_3_3_1_22_2","unstructured":"Hao Wu Patrick Judd Xiaojie Zhang Mikhail Isaev and Paulius Micikevicius. 2020. Integer Quantization for Deep Learning Inference: Principles and Empirical Evaluation. arxiv:https:\/\/arXiv.org\/abs\/2004.09602\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/2004.09602"},{"key":"e_1_3_3_1_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/hipc.2017.00035"},{"key":"e_1_3_3_1_24_2","unstructured":"Xin Xing Hua Huang and Edmond Chow. 2021. Efficient construction of an HSS preconditioner for symmetric positive definite \\(\\mathcal {H}^2\\) matrices. arXiv:https:\/\/arXiv.org\/abs\/2011.07632 [cs math] (Jan. 2021). http:\/\/arxiv.org\/abs\/2011.07632 arXiv:https:\/\/arXiv.org\/abs\/2011.07632."}],"event":{"name":"SCA\/HPCAsia 2026: Supercomputing Asia and International Conference on High Performance Computing in Asia Pacific Region","location":"Osaka Japan","acronym":"SCA\/HPCAsia 2026"},"container-title":["Proceedings of the Supercomputing Asia and International Conference on High Performance Computing in Asia Pacific Region"],"original-title":[],"deposited":{"date-parts":[[2026,1,9]],"date-time":"2026-01-09T10:23:09Z","timestamp":1767954189000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3773656.3773681"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,25]]},"references-count":23,"alternative-id":["10.1145\/3773656.3773681","10.1145\/3773656"],"URL":"https:\/\/doi.org\/10.1145\/3773656.3773681","relation":{},"subject":[],"published":{"date-parts":[[2026,1,25]]},"assertion":[{"value":"2026-01-25","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}