{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2023,4,27]],"date-time":"2023-04-27T10:38:02Z","timestamp":1682591882520},"publisher-location":"New York, NY, USA","reference-count":21,"publisher":"ACM","funder":[{"DOI":"10.13039\/100010661","name":"Horizon 2020 Framework Programme","doi-asserted-by":"publisher","award":["842528"]},{"DOI":"10.13039\/501100001691","name":"Japan Society for the Promotion of Science","doi-asserted-by":"publisher","award":["19K20286"]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2021,1,20]]},"DOI":"10.1145\/3432261.3432270","type":"proceedings-article","created":{"date-parts":[[2021,1,14]],"date-time":"2021-01-14T03:24:09Z","timestamp":1610594649000},"update-policy":"http:\/\/dx.doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Conjugate Gradient Solvers with High Accuracy and Bit-wise Reproducibility between CPU and GPU using Ozaki scheme"],"prefix":"10.1145","author":[{"given":"Daichi","family":"Mukunoki","sequence":"first","affiliation":[{"name":"RIKEN Center for Computational Science, Hyogo"}]},{"given":"Katsuhisa","family":"Ozaki","sequence":"additional","affiliation":[{"name":"Shibaura Institute of Technology, Japan"}]},{"given":"Takeshi","family":"Ogita","sequence":"additional","affiliation":[{"name":"Tokyo Woman\u2019s Christian University, Japan."}]},{"given":"Roman","family":"Iakymchuk","sequence":"additional","affiliation":[{"name":"Sorbonne University, France"}]}],"member":"320","published-online":{"date-parts":[[2021,1,20]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"crossref","unstructured":"S.\u00a0W.\u00a0D. Chien I.\u00a0B. Peng and S. Markidis. 2019. Posit NPB: Assessing the Precision Improvement in HPC Scientific Applications. (to appear). S.\u00a0W.\u00a0D. Chien I.\u00a0B. Peng and S. Markidis. 2019. Posit NPB: Assessing the Precision Improvement in HPC Scientific Applications. (to appear).","DOI":"10.1007\/978-3-030-43229-4_26"},{"key":"e_1_3_2_1_2_1","volume-title":"Accurately Rounded and Efficient BLAS. In 22nd International European Conference on Parallel and Distributed Computing (Euro-Par","author":"Chohra C.","year":"2016","unstructured":"C. Chohra , P. Langlois , and D. Parello . 2016. Reproducible , Accurately Rounded and Efficient BLAS. In 22nd International European Conference on Parallel and Distributed Computing (Euro-Par 2016 ). 609\u2013620. C. Chohra, P. Langlois, and D. Parello. 2016. Reproducible, Accurately Rounded and Efficient BLAS. In 22nd International European Conference on Parallel and Distributed Computing (Euro-Par 2016). 609\u2013620."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.parco.2015.09.001"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/2049662.2049663"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/1236463.1236468"},{"key":"e_1_3_2_1_8_1","volume-title":"Reproducibility of Parallel Preconditioned Conjugate Gradient in Hybrid Programming Environments. IJHPCA","author":"Iakymchuk R.","year":"2020","unstructured":"R. Iakymchuk , M. Barreda , S. Graillat , J.\u00a0 I. Aliaga , and E.\u00a0 S. Quintana-Ort\u00ed . 2020. Reproducibility of Parallel Preconditioned Conjugate Gradient in Hybrid Programming Environments. IJHPCA ( 2020 ). Available OnlineFirst 17 June 2020. https:\/\/doi.org\/10.1177\/1094342020932650. 10.1177\/1094342020932650 R. Iakymchuk, M. Barreda, S. Graillat, J.\u00a0I. Aliaga, and E.\u00a0S. Quintana-Ort\u00ed. 2020. Reproducibility of Parallel Preconditioned Conjugate Gradient in Hybrid Programming Environments. IJHPCA (2020). Available OnlineFirst 17 June 2020. https:\/\/doi.org\/10.1177\/1094342020932650."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cam.2019.112697"},{"key":"e_1_3_2_1_10_1","volume-title":"Proc. Numerical Reproducibility at Exascale (NRE2015)","author":"Iakymchuk R.","unstructured":"R. Iakymchuk , S. Collange , D. Defour , and S. Graillat . 2015. ExBLAS: Reproducible and Accurate BLAS Library . In Proc. Numerical Reproducibility at Exascale (NRE2015) at SC\u201915. R. Iakymchuk, S. Collange, D. Defour, and S. Graillat. 2015. ExBLAS: Reproducible and Accurate BLAS Library. In Proc. Numerical Reproducibility at Exascale (NRE2015) at SC\u201915."},{"key":"e_1_3_2_1_11_1","volume-title":"Computer arithmetic and validity","author":"Kulisch W.","unstructured":"U.\u00a0 W. Kulisch . 2013. Computer arithmetic and validity ( 2 nd ed.). de Gruyter Studies in Mathematics, Vol.\u00a033. Walter de Gruyter & Co. , Berlin. xxii+434 pages. Theory, implementation, and applications. U.\u00a0W. Kulisch. 2013. Computer arithmetic and validity(2nd ed.). de Gruyter Studies in Mathematics, Vol.\u00a033. Walter de Gruyter & Co., Berlin. xxii+434 pages. Theory, implementation, and applications.","edition":"2"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/567806.567808"},{"key":"e_1_3_2_1_13_1","volume-title":"Proc.\u00a013th International Conference on Parallel Processing and Applied Mathematics (PPAM2019)","author":"Mukunoki D.","year":"2043","unstructured":"D. Mukunoki , T. Ogita , and K. Ozaki . 2020. Reproducible BLAS Routines with Tunable Accuracy Using Ozaki Scheme for Many-core Architectures . In Proc.\u00a013th International Conference on Parallel Processing and Applied Mathematics (PPAM2019) , Lecture Notes in Computer Science, Vol.\u00a01 2043 . Springer Berlin Heidelberg, 516\u2013527. https:\/\/doi.org\/10.1007\/978-3-030-43229-4_44 10.1007\/978-3-030-43229-4_44 D. Mukunoki, T. Ogita, and K. Ozaki. 2020. Reproducible BLAS Routines with Tunable Accuracy Using Ozaki Scheme for Many-core Architectures. In Proc.\u00a013th International Conference on Parallel Processing and Applied Mathematics (PPAM2019), Lecture Notes in Computer Science, Vol.\u00a012043. Springer Berlin Heidelberg, 516\u2013527. https:\/\/doi.org\/10.1007\/978-3-030-43229-4_44"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"crossref","unstructured":"D.\n Mukunoki K.\n Ozaki T.\n Ogita and \n T.\n Imamura\n . \n 2020\n . DGEMM using Tensor Cores and Its Accurate and Reproducible Versions. In ISC High Performance 2020 Lecture Notes in Computer Science Vol.\u00a012151. \n Springer International Publishing 230\u2013248. https:\/\/doi.org\/10.1007\/978-3-030-50743-5_12 10.1007\/978-3-030-50743-5_12\nD. Mukunoki K. Ozaki T. Ogita and T. Imamura. 2020. DGEMM using Tensor Cores and Its Accurate and Reproducible Versions. In ISC High Performance 2020 Lecture Notes in Computer Science Vol.\u00a012151. Springer International Publishing 230\u2013248. https:\/\/doi.org\/10.1007\/978-3-030-50743-5_12","DOI":"10.1007\/978-3-030-50743-5_12"},{"key":"e_1_3_2_1_15_1","volume-title":"10th International Conference on Parallel Processing and Applied Mathematics (PPAM2013)","author":"Mukunoki D.","unstructured":"D. Mukunoki and D. Takahashi . 2014. Using Quadruple Precision Arithmetic to Accelerate Krylov Subspace Methods on GPUs . In 10th International Conference on Parallel Processing and Applied Mathematics (PPAM2013) . 632\u2013642. D. Mukunoki and D. Takahashi. 2014. Using Quadruple Precision Arithmetic to Accelerate Krylov Subspace Methods on GPUs. In 10th International Conference on Parallel Processing and Applied Mathematics (PPAM2013). 632\u2013642."},{"key":"e_1_3_2_1_16_1","volume-title":"The MPACK","author":"Nakata M.","unstructured":"M. Nakata . [n.d.]. The MPACK ; Multiple precision arithmetic BLAS (MBLAS) and LAPACK (MLAPACK) . http:\/\/mplapack.sourceforge.net. M. Nakata. [n.d.]. The MPACK; Multiple precision arithmetic BLAS (MBLAS) and LAPACK (MLAPACK). http:\/\/mplapack.sourceforge.net."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11075-011-9478-1"},{"key":"e_1_3_2_1_18_1","first-page":"2","article-title":"Generalization of error-free transformation for matrix multiplication and its application. Nonlinear Theory and Its Applications","volume":"4","author":"Ozaki K.","year":"2013","unstructured":"K. Ozaki , T. Ogita , S. Oishi , and S.\u00a0 M. Rump . 2013 . Generalization of error-free transformation for matrix multiplication and its application. Nonlinear Theory and Its Applications , IEICE 4 (2013), 2 \u2013 11 . K. Ozaki, T. Ogita, S. Oishi, and S.\u00a0M. Rump. 2013. Generalization of error-free transformation for matrix multiplication and its application. Nonlinear Theory and Its Applications, IEICE 4 (2013), 2\u201311.","journal-title":"IEICE"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1137\/050645671"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1137\/07068816X"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1137\/07068816X"},{"key":"e_1_3_2_1_22_1","first-page":"2","article-title":"Fast high precision summation. Nonlinear Theory and Its Applications","volume":"1","author":"Rump M.","year":"2010","unstructured":"S.\u00a0 M. Rump , T. Ogita , and S. Oishi . 2010 . Fast high precision summation. Nonlinear Theory and Its Applications , IEICE 1 , 1 (2010), 2 \u2013 24 . S.\u00a0M. Rump, T. Ogita, and S. Oishi. 2010. Fast high precision summation. Nonlinear Theory and Its Applications, IEICE 1, 1 (2010), 2\u201324.","journal-title":"IEICE"},{"key":"e_1_3_2_1_23_1","unstructured":"R. Todd. 2012. Introduction to Conditional Numerical Reproducibility (CNR). https:\/\/software.intel.com\/en-us\/articles\/introduction-to-the-conditional-numerical-reproducibility-cnr. R. Todd. 2012. Introduction to Conditional Numerical Reproducibility (CNR). https:\/\/software.intel.com\/en-us\/articles\/introduction-to-the-conditional-numerical-reproducibility-cnr."}],"event":{"name":"HPC Asia 2021: The International Conference on High Performance Computing in Asia-Pacific Region","location":"Virtual Event Republic of Korea","acronym":"HPC Asia 2021"},"container-title":["The International Conference on High Performance Computing in Asia-Pacific Region"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3432261.3432270","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,12]],"date-time":"2023-01-12T12:33:40Z","timestamp":1673526820000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3432261.3432270"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,1,20]]},"references-count":21,"alternative-id":["10.1145\/3432261.3432270","10.1145\/3432261"],"URL":"http:\/\/dx.doi.org\/10.1145\/3432261.3432270","relation":{},"published":{"date-parts":[[2021,1,20]]},"assertion":[{"value":"2021-01-20","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}