{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,5,4]],"date-time":"2024-05-04T00:29:12Z","timestamp":1714782552382},"reference-count":35,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100002855","name":"Ministry of Science and Technology of the People's Republic of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002855","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Journal of Parallel and Distributed Computing"],"published-print":{"date-parts":[[2024,8]]},"DOI":"10.1016\/j.jpdc.2024.104884","type":"journal-article","created":{"date-parts":[[2024,3,27]],"date-time":"2024-03-27T17:47:52Z","timestamp":1711561672000},"page":"104884","update-policy":"http:\/\/dx.doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"title":["A novel HPL-AI approach for FP16-only accelerator and its instantiation on Kunpeng+Ascend AI-specific platform"],"prefix":"10.1016","volume":"190","author":[{"ORCID":"http:\/\/orcid.org\/0009-0007-5584-5624","authenticated-orcid":false,"given":"Zijian","family":"Cao","sequence":"first","affiliation":[]},{"given":"Qiao","family":"Sun","sequence":"additional","affiliation":[]},{"given":"Wenhao","family":"Yang","sequence":"additional","affiliation":[]},{"given":"Changcheng","family":"Song","sequence":"additional","affiliation":[]},{"given":"Zhe","family":"Wang","sequence":"additional","affiliation":[]},{"ORCID":"http:\/\/orcid.org\/0000-0002-6326-9926","authenticated-orcid":false,"given":"Huiyuan","family":"Li","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"issue":"12","key":"10.1016\/j.jpdc.2024.104884_br0290","doi-asserted-by":"crossref","first-page":"2526","DOI":"10.1016\/j.cpc.2008.11.005","article-title":"Accelerating scientific computations with mixed precision algorithms","volume":"180","author":"Baboulin","year":"2009","journal-title":"Comput. Phys. Commun."},{"issue":"3\u20134","key":"10.1016\/j.jpdc.2024.104884_br0150","doi-asserted-by":"crossref","first-page":"153","DOI":"10.1007\/s00450-011-0161-5","article-title":"Optimized HPL for AMD GPU and multi-core CPU usage","volume":"26","author":"Bach","year":"2011","journal-title":"Comput. Sci. Res. Dev."},{"issue":"6","key":"10.1016\/j.jpdc.2024.104884_br0100","doi-asserted-by":"crossref","first-page":"A2834","DOI":"10.1137\/17M1122918","article-title":"A new analysis of iterative refinement and its application to accurate solution of ill-conditioned sparse linear systems","volume":"39","author":"Carson","year":"2017","journal-title":"SIAM J. Sci. Comput."},{"issue":"2","key":"10.1016\/j.jpdc.2024.104884_br0090","doi-asserted-by":"crossref","first-page":"A817","DOI":"10.1137\/17M1140819","article-title":"Accelerating the solution of linear systems by iterative refinement in three precisions","volume":"40","author":"Carson","year":"2018","journal-title":"SIAM J. Sci. Comput."},{"key":"10.1016\/j.jpdc.2024.104884_br0210","author":"Cornebize"},{"key":"10.1016\/j.jpdc.2024.104884_br0180","series-title":"Mathematical Methods of Statistics","author":"Cram\u00e9r","year":"1999"},{"issue":"1","key":"10.1016\/j.jpdc.2024.104884_br0160","doi-asserted-by":"crossref","first-page":"417","DOI":"10.1137\/20M1357238","article-title":"Matrices with tunable infinity-norm condition number and no need for pivoting in Lu factorization","volume":"42","author":"Fasi","year":"2021","journal-title":"SIAM J. Matrix Anal. Appl."},{"issue":"2","key":"10.1016\/j.jpdc.2024.104884_br0170","doi-asserted-by":"crossref","first-page":"180","DOI":"10.1017\/S0305004100015681","article-title":"Limiting forms of the frequency distribution of the largest or smallest member of a sample","volume":"24","author":"Fisher","year":"1928","journal-title":"Math. Proc. Camb. Philos. Soc."},{"key":"10.1016\/j.jpdc.2024.104884_br0330","series-title":"Proceedings of the 8th Workshop on Latest Advances in Scalable Algorithms for Large-Scale Systems, ScalA '17","first-page":"1","article-title":"Investigating half precision arithmetic to accelerate dense linear system solvers","author":"Haidar","year":"2017"},{"key":"10.1016\/j.jpdc.2024.104884_br0340","series-title":"SC18: International Conference for High Performance Computing, Networking, Storage and Analysis","first-page":"603","article-title":"Harnessing GPU tensor cores for fast FP16 arithmetic to speed up mixed-precision iterative refinement solvers","author":"Haidar","year":"2018"},{"issue":"2243","key":"10.1016\/j.jpdc.2024.104884_br0350","article-title":"Mixed-precision iterative refinement using tensor cores on GPUs to accelerate solution of linear systems","volume":"476","author":"Haidar","year":"2020","journal-title":"Proc. R. Soc. A, Math. Phys. Eng. Sci."},{"key":"10.1016\/j.jpdc.2024.104884_br0140","series-title":"2013 IEEE 27th International Symposium on Parallel and Distributed Processing","first-page":"126","article-title":"Design and implementation of the Linpack benchmark for single and multi-node systems based on Intel\u00ae Xeon Phi coprocessor","author":"Heinecke","year":"2013"},{"key":"10.1016\/j.jpdc.2024.104884_br0200","series-title":"2019 IEEE Intl Conf on Parallel & Distributed Processing with Applications, Big Data & Cloud Computing, Sustainable Computing & Communications, Social Computing & Networking (ISPA\/BDCloud\/SocialCom\/SustainCom)","first-page":"1371","article-title":"Performance optimization of high-performance LINPACK based on GPU-centric model on heterogeneous systems","author":"Huang","year":"2019"},{"key":"10.1016\/j.jpdc.2024.104884_br0110","author":"Huawei"},{"key":"10.1016\/j.jpdc.2024.104884_br0120","author":"Huawei"},{"key":"10.1016\/j.jpdc.2024.104884_br0010","author":"ICL"},{"key":"10.1016\/j.jpdc.2024.104884_br0020","author":"ICL"},{"key":"10.1016\/j.jpdc.2024.104884_br0060","author":"ICL"},{"key":"10.1016\/j.jpdc.2024.104884_br0130","author":"IEEE"},{"key":"10.1016\/j.jpdc.2024.104884_br0030","series-title":"2020 IEEE\/ACM 11th Workshop on Latest Advances in Scalable Algorithms for Large-Scale Systems (ScalA)","first-page":"69","article-title":"Implementation and numerical techniques for one EFlop\/s HPL-AI benchmark on Fugaku","author":"Kudo","year":"2020"},{"key":"10.1016\/j.jpdc.2024.104884_br0040","series-title":"2020 IEEE International Conference on Cluster Computing (CLUSTER)","first-page":"418","article-title":"Prompt report on exa-scale HPL-AI benchmark","author":"Kudo","year":"2020"},{"key":"10.1016\/j.jpdc.2024.104884_br0300","series-title":"Implementation of the mixed-precision High Performance LINPACK benchmark on the CELL processor","author":"Kurzak","year":"2006"},{"issue":"10","key":"10.1016\/j.jpdc.2024.104884_br0310","doi-asserted-by":"crossref","first-page":"1371","DOI":"10.1002\/cpe.1164","article-title":"Implementation of mixed precision in solving systems of linear equations on the CELL processor","volume":"19","author":"Kurzak","year":"2007","journal-title":"Concurr. Comput."},{"key":"10.1016\/j.jpdc.2024.104884_br0280","series-title":"SC '06: Proceedings of the 2006 ACM\/IEEE Conference on Supercomputing","first-page":"50","article-title":"Exploiting the performance of 32 bit floating point arithmetic in obtaining 64 bit accuracy (revisiting iterative refinement for linear systems)","author":"Langou","year":"2006"},{"key":"10.1016\/j.jpdc.2024.104884_br0320","series-title":"2010 10th IEEE International Conference on Computer and Information Technology","first-page":"1169","article-title":"Accelerating Linpack performance with mixed precision algorithm on CPU+GPGPU heterogeneous cluster","author":"Lei","year":"2010"},{"key":"10.1016\/j.jpdc.2024.104884_br0050","series-title":"SC22: International Conference for High Performance Computing, Networking, Storage and Analysis","first-page":"1","article-title":"Climbing the Summit and pushing the Frontier of mixed precision benchmarks at extreme scale","author":"Lu","year":"2022"},{"issue":"2","key":"10.1016\/j.jpdc.2024.104884_br0260","doi-asserted-by":"crossref","first-page":"316","DOI":"10.1145\/321386.321394","article-title":"Iterative refinement in floating point","volume":"14","author":"Moler","year":"1967","journal-title":"J. ACM"},{"key":"10.1016\/j.jpdc.2024.104884_br0230","author":"Nicely"},{"key":"10.1016\/j.jpdc.2024.104884_br0220","author":"NVIDIA"},{"key":"10.1016\/j.jpdc.2024.104884_br0240","author":"NVIDIA"},{"key":"10.1016\/j.jpdc.2024.104884_br0250","author":"NVIDIA"},{"issue":"3","key":"10.1016\/j.jpdc.2024.104884_br0080","doi-asserted-by":"crossref","first-page":"856","DOI":"10.1137\/0907058","article-title":"GMRES: a generalized minimal residual algorithm for solving nonsymmetric linear systems","volume":"7","author":"Saad","year":"1986","journal-title":"SIAM J. Sci. Stat. Comput."},{"issue":"3","key":"10.1016\/j.jpdc.2024.104884_br0190","doi-asserted-by":"crossref","first-page":"281","DOI":"10.1145\/321075.321076","article-title":"Error analysis of direct methods of matrix inversion","volume":"8","author":"Wilkinson","year":"1961","journal-title":"J. ACM"},{"key":"10.1016\/j.jpdc.2024.104884_br0270","series-title":"The Algebraic Eigenvalue Problem","author":"Wilkinson","year":"1988"},{"key":"10.1016\/j.jpdc.2024.104884_br0070","series-title":"Rounding Errors in Algebraic Processes","author":"Wilkinson","year":"1994"}],"container-title":["Journal of Parallel and Distributed Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0743731524000480?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0743731524000480?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2024,5,3]],"date-time":"2024-05-03T21:39:14Z","timestamp":1714772354000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0743731524000480"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8]]},"references-count":35,"alternative-id":["S0743731524000480"],"URL":"https:\/\/doi.org\/10.1016\/j.jpdc.2024.104884","relation":{},"ISSN":["0743-7315"],"issn-type":[{"value":"0743-7315","type":"print"}],"subject":[],"published":{"date-parts":[[2024,8]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"A novel HPL-AI approach for FP16-only accelerator and its instantiation on Kunpeng+Ascend AI-specific platform","name":"articletitle","label":"Article Title"},{"value":"Journal of Parallel and Distributed Computing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.jpdc.2024.104884","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2024 Elsevier Inc. All rights reserved.","name":"copyright","label":"Copyright"}],"article-number":"104884"}}
