{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T18:46:38Z","timestamp":1755801998175,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":42,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,11,12]],"date-time":"2023-11-12T00:00:00Z","timestamp":1699747200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Exascale Computing Project","award":["17-SC-20-SC"],"award-info":[{"award-number":["17-SC-20-SC"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,11,12]]},"DOI":"10.1145\/3624062.3624248","type":"proceedings-article","created":{"date-parts":[[2023,11,10]],"date-time":"2023-11-10T13:53:39Z","timestamp":1699624419000},"page":"1680-1687","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Task-Based Polar Decomposition Using SLATE on Massively Parallel Systems with Hardware Accelerators"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4228-4211","authenticated-orcid":false,"given":"Dalal","family":"Sukkari","sequence":"first","affiliation":[{"name":"ICL\/UTK, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2996-1641","authenticated-orcid":false,"given":"Mark","family":"Gates","sequence":"additional","affiliation":[{"name":"ICL\/UTK, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4988-4674","authenticated-orcid":false,"given":"Mohammed","family":"Al Farhan","sequence":"additional","affiliation":[{"name":"King Abdullah University of Science & Technology, Saudi Arabia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2177-952X","authenticated-orcid":false,"given":"Hartwig","family":"Anzt","sequence":"additional","affiliation":[{"name":"ICL\/UTK, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3247-1782","authenticated-orcid":false,"given":"Jack","family":"Dongarra","sequence":"additional","affiliation":[{"name":"ICL\/UTK, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,11,12]]},"reference":[{"unstructured":"2018. The Chameleon Project. http:\/\/project.inria.fr\/.","key":"e_1_3_2_2_1_1"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_2_1","DOI":"10.1088\/1742-6596\/180\/1\/012037"},{"key":"e_1_3_2_2_3_1","volume-title":"Anne Greenbaum, Sven Hammarling, A McKenney, and Danny\u00a0C Sorensen.","author":"Anderson Edward","year":"1999","unstructured":"Edward Anderson, Zhaojun Bai, Christian\u00a0Heinrich Bischof, Laura\u00a0Susan Blackford, James\u00a0Weldon Demmel, Jack\u00a0J Dongarra, Jeremy J\u00a0Du Croz, Anne Greenbaum, Sven Hammarling, A McKenney, and Danny\u00a0C Sorensen. 1999. LAPACK User\u2019s Guide (3rd ed.). Society for Industrial and Applied Mathematics, Philadelphia."},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_4_1","DOI":"10.1002\/cpe.1631"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_5_1","DOI":"10.1109\/TAES.1975.308025"},{"volume-title":"Guide","author":"Blackford Suzan","unstructured":"L.\u00a0Suzan Blackford, J. Choi, Andy Cleary, Eduardo\u00a0F. D\u2019Azevedo, James\u00a0W. Demmel, Inderjit\u00a0S. Dhillon, Jack\u00a0J. Dongarra, Sven Hammarling, Greg Henry, Antoine Petitet, Ken Stanley, David\u00a0W. Walker, and R.\u00a0Clint Whaley. 1997. ScaLAPACK Users\u2019 Guide. Society for Industrial and Applied Mathematics, Philadelphia.","key":"e_1_3_2_2_6_1"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_7_1","DOI":"10.1137\/070699895"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_8_1","DOI":"10.1145\/1248377.1248397"},{"unstructured":"Cray. [n. d.]. LibSci. http:\/\/docs.cray.com","key":"e_1_3_2_2_9_1"},{"doi-asserted-by":"publisher","unstructured":"Anthony Danalis George Bosilca Aurelien Bouteiller Thomas Herault and Jack Dongarra. 2014. PTG: An abstraction for unhindered parallelism. Proceedings of WOLFHPC 2014: 4th International Workshop on Domain-Specific Languages and High-Level Frameworks for High Performance Computing - Held in Conjunction with SC 2014: The International Conference for High Performance Computing Networking Stor (2014) 21\u201330. https:\/\/doi.org\/10.1109\/WOLFHPC.2014.8","key":"e_1_3_2_2_10_1","DOI":"10.1109\/WOLFHPC.2014.8"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_11_1","DOI":"10.1137\/17M1117732"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_12_1","DOI":"10.1080\/00029890.1985.11971554"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_13_1","DOI":"10.1145\/3295500.3356223"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_14_1","DOI":"10.1109\/P3HPC56579.2022.00009"},{"volume-title":"Matrix Computations","author":"Golub H.","unstructured":"Gene\u00a0H. Golub and Charles\u00a0F. Van Loan. 1996. Matrix Computations (third ed.). Johns Hopkins University Press, Baltimore, Maryland.","key":"e_1_3_2_2_15_1"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_16_1","DOI":"10.1137\/0905023"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_17_1","DOI":"10.1007\/BF01396242"},{"key":"e_1_3_2_2_18_1","volume-title":"Higham and Pythagoras Papadimitriou","author":"J.","year":"1993","unstructured":"Nicholas\u00a0J. Higham and Pythagoras Papadimitriou. 1993. Parallel Singular Value Decomposition via the Polar Decomposition. Numerical Analysis Report No. 239. University of Manchester, England. ftp:\/\/vtx.ma.man.ac.uk\/pub\/narep\/narep239.dvi.Z"},{"volume-title":"Proceedings of the Fifth SIAM Conference on Applied Linear Algebra, John\u00a0G. Lewis (Ed.). Society for Industrial and Applied Mathematics","author":"J.","unstructured":"Nicholas\u00a0J. Higham and Pythagoras Papadimitriou. 1994. A New Parallel Algorithm for Computing the Singular Value Decomposition. In Proceedings of the Fifth SIAM Conference on Applied Linear Algebra, John\u00a0G. Lewis (Ed.). Society for Industrial and Applied Mathematics, Philadelphia, PA, USA, 80\u201384.","key":"e_1_3_2_2_19_1"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_20_1","DOI":"10.1016\/0167-8191(94)90073-6"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_21_1","DOI":"10.1137\/0613044"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_22_1","DOI":"10.1137\/0613044"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_23_1","DOI":"10.1023\/A:1024098014869"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_24_1","DOI":"10.1007\/s10543-006-0053-4"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_25_1","DOI":"10.1145\/3328723"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_26_1","DOI":"10.1145\/3218176.3218225"},{"volume-title":"Matrix Algebra on GPU and Multicore Architectures. Innovative Computing Laboratory","author":"MAGMA.","unstructured":"MAGMA. 2009. Matrix Algebra on GPU and Multicore Architectures. Innovative Computing Laboratory, University of Tennessee. Available at http:\/\/icl.cs.utk.edu\/magma\/.","key":"e_1_3_2_2_27_1"},{"key":"e_1_3_2_2_28_1","series-title":"SIAM J. Matrix Anal. Appl. (2010), 2700\u20132720","volume-title":"Optimizing Halley\u2019s Iteration for Computing the Matrix Polar Decomposition","author":"Nakatsukasa Yuji","unstructured":"Yuji Nakatsukasa, Zhaojun Bai, and Fran\u00e7ois Gygi. 2010. Optimizing Halley\u2019s Iteration for Computing the Matrix Polar Decomposition. SIAM J. Matrix Anal. Appl. (2010), 2700\u20132720."},{"key":"e_1_3_2_2_29_1","series-title":"SIAM J. Matrix Anal. Appl. (2010), 2700\u20132720","volume-title":"Optimizing Halley\u2019s Iteration for Computing the Matrix Polar Decomposition","author":"Nakatsukasa Yuji","unstructured":"Yuji Nakatsukasa, Zhaojun Bai, and Fran\u00e7ois Gygi. 2010. Optimizing Halley\u2019s Iteration for Computing the Matrix Polar Decomposition. SIAM J. Matrix Anal. Appl. (2010), 2700\u20132720."},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_30_1","DOI":"10.1137\/110857544"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_31_1","DOI":"10.1137\/120876605"},{"unstructured":"Oak Ridge Leadership Computing Facility (OLCF). 2023. Frontier User Guide. https:\/\/docs.olcf.ornl.gov\/systems\/frontier_user_guide.html","key":"e_1_3_2_2_32_1"},{"unstructured":"Oak Ridge Leadership Computing Facility (OLCF). 2023. Summit User Guide. https:\/\/docs.olcf.ornl.gov\/systems\/summit_user_guide.html","key":"e_1_3_2_2_33_1"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_34_1","DOI":"10.1145\/2427023.2427030"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_35_1","DOI":"10.1007\/BF02289451"},{"doi-asserted-by":"publisher","unstructured":"Dalal Sukkari. 2019. High Performance Polar Decomposition on Manycore Systems and its application to Symmetric Eigensolvers and the Singular Value Decomposition. Ph.\u00a0D. Dissertation. KAUST. https:\/\/doi.org\/10.25781\/KAUST-R20B1","key":"e_1_3_2_2_36_1","DOI":"10.25781\/KAUST-R20B1"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_37_1","DOI":"10.1145\/3309548"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_38_1","DOI":"10.1109\/TPDS.2017.2755655"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_39_1","DOI":"10.1007\/978-3-319-43659-3"},{"volume-title":"Leveraging Task-Based Polar Decomposition Using PARSEC on Massively Parallel Systems. In 2019 IEEE International Conference on Cluster Computing (CLUSTER). 1\u201312","author":"Sukkari D.","unstructured":"D. Sukkari, H. Ltaief, D. Keyes, and M. Faverge. 2019. Leveraging Task-Based Polar Decomposition Using PARSEC on Massively Parallel Systems. In 2019 IEEE International Conference on Cluster Computing (CLUSTER). 1\u201312.","key":"e_1_3_2_2_40_1"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_41_1","DOI":"10.1145\/2894747"},{"key":"e_1_3_2_2_42_1","volume-title":"Trefethen and David Bau","author":"N.","year":"1997","unstructured":"Lloyd\u00a0N. Trefethen and David Bau. 1997. Numerical Linear Algebra. SIAM, Philadelphia, PA. http:\/\/www.siam.org\/books\/OT50\/Index.htm"}],"event":{"acronym":"SC-W 2023","name":"SC-W 2023: Workshops of The International Conference on High Performance Computing, Network, Storage, and Analysis","location":"Denver CO USA"},"container-title":["Proceedings of the SC '23 Workshops of the International Conference on High Performance Computing, Network, Storage, and Analysis"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3624062.3624248","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3624062.3624248","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T03:02:17Z","timestamp":1755745337000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3624062.3624248"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,12]]},"references-count":42,"alternative-id":["10.1145\/3624062.3624248","10.1145\/3624062"],"URL":"https:\/\/doi.org\/10.1145\/3624062.3624248","relation":{},"subject":[],"published":{"date-parts":[[2023,11,12]]},"assertion":[{"value":"2023-11-12","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}