{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,7]],"date-time":"2025-05-07T14:28:58Z","timestamp":1746628138841,"version":"3.37.3"},"reference-count":58,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2020,10,15]],"date-time":"2020-10-15T00:00:00Z","timestamp":1602720000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,10,15]],"date-time":"2020-10-15T00:00:00Z","timestamp":1602720000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100012165","name":"Key Technologies Research and Development Program","doi-asserted-by":"publisher","award":["2020YFB150001"],"award-info":[{"award-number":["2020YFB150001"]}],"id":[{"id":"10.13039\/501100012165","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62072018"],"award-info":[{"award-number":["62072018"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Open Project Program of the State Key Laboratory of Mathematical Engineering and Advanced Computing","award":["2019A12"],"award-info":[{"award-number":["2019A12"]}]},{"name":"Center for High Performance Computing and System Simulation"},{"name":"Pilot National Laboratory for Marine Science and Technology"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Supercomput"],"published-print":{"date-parts":[[2021,5]]},"DOI":"10.1007\/s11227-020-03444-2","type":"journal-article","created":{"date-parts":[[2020,10,15]],"date-time":"2020-10-15T12:02:51Z","timestamp":1602763371000},"page":"4533-4564","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Towards efficient tile low-rank GEMM computation on sunway many-core processors"],"prefix":"10.1007","volume":"77","author":[{"given":"Qingchang","family":"Han","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1101-7927","authenticated-orcid":false,"given":"Hailong","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ming","family":"Dun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhongzhi","family":"Luan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lin","family":"Gan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guangwen","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Depei","family":"Qian","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2020,10,15]]},"reference":[{"issue":"2","key":"3444_CR1","doi-asserted-by":"publisher","first-page":"89","DOI":"10.1007\/s006070050015","volume":"62","author":"Hackbusch Wolfgang","year":"1999","unstructured":"Wolfgang Hackbusch (1999) A sparse matrix arithmetic based on $$\\cal{H}$$-matrices. part i: Introduction to $${\\cal{H}}$$-matrices. Computing 62(2):89\u2013108","journal-title":"Computing"},{"issue":"4","key":"3444_CR2","doi-asserted-by":"publisher","first-page":"295","DOI":"10.1007\/s00607-003-0019-1","volume":"70","author":"L Grasedyck","year":"2003","unstructured":"Grasedyck L, Hackbusch Wolfgang (2003) Construction and arithmetics of $${\\cal{H}}$$-matrices. Computing 70(4):295\u2013334","journal-title":"Computing"},{"key":"3444_CR3","doi-asserted-by":"crossref","unstructured":"Akbudak K, Ltaief H, Mikhalev A, and Keyes D 2017) Tile low rank cholesky factorization for climate\/weather modeling applications on manycore architectures. In: International Supercomputing Conference, pp 22\u201340. Springer","DOI":"10.1007\/978-3-319-58667-0_2"},{"key":"3444_CR4","doi-asserted-by":"crossref","unstructured":"Charara A, Keyes D, and Ltaief H (2018) Tile low-rank gemm using batched operations on gpus. In: European Conference on Parallel Processing, pp 811\u2013825. Springer","DOI":"10.1007\/978-3-319-96983-1_57"},{"issue":"2","key":"3444_CR5","doi-asserted-by":"publisher","first-page":"135","DOI":"10.1145\/567806.567807","volume":"28","author":"BL Susan","year":"2002","unstructured":"Susan BL, Antoine P, Roldan P, Karin R, Clint WR, James D, Jack D, Iain D, Sven H, Greg Henry et al (2002) An updated set of basic linear algebra subprograms (blas). ACM Trans Math Softw 28(2):135\u2013151","journal-title":"ACM Trans Math Softw"},{"issue":"3","key":"3444_CR6","doi-asserted-by":"publisher","first-page":"273","DOI":"10.1007\/s00607-004-0102-2","volume":"74","author":"Ronald Kriemann","year":"2005","unstructured":"Kriemann Ronald (2005) Parallel $${\\cal{H}}$$-matrix arithmetics on shared memory systems. Computing 74(3):273\u2013297","journal-title":"Computing"},{"key":"3444_CR7","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1016\/j.parco.2017.09.001","volume":"74","author":"BW Halim","year":"2018","unstructured":"Halim BW, George T, Hatem L, Keyes David E (2018) Batched qr and svd algorithms on gpus with applications in hierarchical matrix compression. Parallel Comput 74:19\u201333","journal-title":"Parallel Comput"},{"key":"3444_CR8","first-page":"31","volume-title":"Cublas library","author":"CUDA Nvidia","year":"2008","unstructured":"Nvidia CUDA (2008) Cublas library. NVIDIA Corporation, Santa Clara, CaliforniaSanta Clara, CaliforniaSanta Clara, CaliforniaSanta Clara, California, p 31"},{"issue":"2","key":"3444_CR9","doi-asserted-by":"publisher","first-page":"187","DOI":"10.1002\/cpe.1631","volume":"23","author":"C Augonnet","year":"2011","unstructured":"Augonnet C, Thibault S, Namyst R, Wacrenier Pierre-Andr\u00e9 (2011) Starpu: a unified platform for task scheduling on heterogeneous multicore architectures. Concurr Comput: Pract Exp 23(2):187\u2013198","journal-title":"Concurr Comput: Pract Exp"},{"key":"3444_CR10","unstructured":"Dongarra J (2016) Report on the sunway taihulight system. PDF). www. netlib. org. Retrieved June, 20,"},{"issue":"7","key":"3444_CR11","doi-asserted-by":"publisher","first-page":"072001","DOI":"10.1007\/s11432-016-5588-7","volume":"59","author":"F Haohuan","year":"2016","unstructured":"Haohuan F, Liao J, Yang J, Wang L, Song Z, Huang X, Yang C, Xue W, Liu F, Qiao Fangli et al (2016) The sunway taihulight supercomputer: system and applications. Sci China Inf Sci 59(7):072001","journal-title":"Sci China Inf Sci"},{"key":"3444_CR12","doi-asserted-by":"crossref","unstructured":"Jiang L, Yang C, Ao Y, Yin W, Ma W, Sun Q, Liu F, Lin R, and Zhang P (2017) Towards highly efficient dgemm on the emerging sw26010 many-core processor. In: 2017 46th International Conference on Parallel Processing (ICPP), pp 422\u2013431. IEEE","DOI":"10.1109\/ICPP.2017.51"},{"key":"3444_CR13","doi-asserted-by":"crossref","unstructured":"Fang J, Fu H, Zhao W, Chen B, Zheng W, and Yang G (2017) swdnn: a library for accelerating deep learning applications on sunway taihulight. In: 2017 IEEE International Parallel and Distributed Processing Symposium (IPDPS), pp 615\u2013624. IEEE","DOI":"10.1109\/IPDPS.2017.20"},{"key":"3444_CR14","doi-asserted-by":"crossref","unstructured":"de\u00a0Dinechin BD Ayrignac R, Beaucamps PE, Couvert P, Ganne B, de\u00a0Massas PG Jacquet F, Jones S, Chaisemartin NM, Riss F et\u00a0al (2013) A clustered manycore processor architecture for embedded and accelerated applications. In: 2013 IEEE High Performance Extreme Computing Conference (HPEC), pp 1\u20136. IEEE","DOI":"10.1109\/HPEC.2013.6670342"},{"issue":"10\u201311","key":"3444_CR15","doi-asserted-by":"publisher","first-page":"576","DOI":"10.1016\/j.parco.2012.07.001","volume":"38","author":"V \u00c7ataly\u00fcrek \u00dcmit","year":"2012","unstructured":"\u00c7ataly\u00fcrek \u00dcmit V, Feo J, Gebremedhin AH, Halappanavar M, Pothen A (2012) Graph coloring algorithms for multi-core and massively multithreaded architectures. Parallel Comput 38(10\u201311):576\u2013594","journal-title":"Parallel Comput"},{"key":"3444_CR16","doi-asserted-by":"crossref","unstructured":"Williams S, Shalf J , Oliker L, Kamil S, Husbands P, and Yelick K (2006) The potential of the cell processor for scientific computing. In: Proceedings of the 3rd Conference on Computing Frontiers, pp 9\u201320","DOI":"10.1145\/1128022.1128027"},{"key":"3444_CR17","series-title":"Lectures on applied mathematics","first-page":"9","volume-title":"On $${\\cal{H}}^2$$-matrices","author":"W Hackbusch","year":"2000","unstructured":"Hackbusch W, Khoromskij B, Sauter SA (2000) On $${\\cal{H}}^2$$-matrices. Lectures on applied mathematics. Springer, Berlin, pp 9\u201329"},{"issue":"4","key":"3444_CR18","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1145\/2930660","volume":"42","author":"FH Rouet","year":"2016","unstructured":"Rouet FH, Li XS, Ghysels P, Napov A (2016) A distributed-memory package for dense hierarchically semi-separable matrix computations using randomization. ACM Trans Math Softw (TOMS) 42(4):27","journal-title":"ACM Trans Math Softw (TOMS)"},{"issue":"3","key":"3444_CR19","doi-asserted-by":"publisher","first-page":"477","DOI":"10.1007\/s10915-013-9714-z","volume":"57","author":"S Ambikasaran","year":"2013","unstructured":"Ambikasaran S, Darve E (2013) An $${\\cal{O}}(n \\log n)$$ fast direct solver for partial hierarchically semi-separable matrices. J Sci Comput 57(3):477\u2013501","journal-title":"J Sci Comput"},{"issue":"3","key":"3444_CR20","doi-asserted-by":"publisher","first-page":"A1451","DOI":"10.1137\/120903476","volume":"37","author":"P Amestoy","year":"2015","unstructured":"Amestoy P, Ashcraft C, Boiteau O, Buttari A, L\u2019Excellent JY, Weisbecker Cl\u00e9ment (2015) Improving multifrontal methods by means of block low-rank representations. SIAM J Sci Comput 37(3):A1451\u2013A1474","journal-title":"SIAM J Sci Comput"},{"issue":"3","key":"3444_CR21","doi-asserted-by":"publisher","first-page":"105","DOI":"10.1007\/s00791-014-0226-7","volume":"16","author":"Ronald Kriemann","year":"2013","unstructured":"Kriemann Ronald (2013) $${\\cal{H}}$$-lu factorization on many-core systems. Comput Visualiz Sci 16(3):105\u2013117","journal-title":"Comput Visualiz Sci"},{"key":"3444_CR22","doi-asserted-by":"crossref","unstructured":"Noha Al-Harthi, Rabab Alomairy, Kadir Akbudak, Rui Chen, Hatem Ltaief, Hakan Bagci, and David E. Keyes. Solving acoustic boundary integral equations using high performance tile low-rank LU factorization. In: 2020 International Conference on High Performance Computing (ISC), pp 209\u2013229. Springer","DOI":"10.1007\/978-3-030-50743-5_11"},{"key":"3444_CR23","doi-asserted-by":"crossref","unstructured":"Cao Q, Pei Y, Akbudak K, Mikhalev A, Bosilca G, Ltaief H, Keyes D, and Dongarra J (2020) Extreme-scale task-based cholesky factorization toward climate and weather prediction applications. In: Proceedings of the Platform for Advanced Scientific Computing Conference, pp 1\u201311","DOI":"10.1145\/3394277.3401846"},{"key":"3444_CR24","doi-asserted-by":"crossref","unstructured":"Duan X, Gao P, Zhang T, Zhang M, Liu W, Zhang W , Xue W, Fu H, Gan L, Chen D et\u00a0al (2018) Redesigning lammps for peta-scale and hundred-billion-atom simulation on sunway taihulight. In: Proceedings of the International Conference for High Performance Computing, Networking, Storage, and Analysis, p 12. IEEE Press","DOI":"10.1109\/SC.2018.00015"},{"key":"3444_CR25","doi-asserted-by":"crossref","unstructured":"Chen B, Fu H, Wei Y, He C, Zhang W, Li Y, Wan W, Zhang W, Gan L, Zhang W et\u00a0al (2018) Simulating the wenchuan earthquake with accurate surface topography on sunway taihulight. In: Proceedings of the International Conference for High Performance Computing, Networking, Storage, and Analysis, p 40. IEEE Press","DOI":"10.1109\/SC.2018.00043"},{"key":"3444_CR26","doi-asserted-by":"crossref","unstructured":"Lin H, Zhu X, Yu B, Tang X, Xue W, Chen W, Zhang L , Hoefler T, Ma X, Liu X et\u00a0al (2018) hentu: processing multi-trillion edge graphs on millions of cores in seconds. In: Proceedings of the International Conference for High Performance Computing, Networking, Storage, and Analysis, pp 56. IEEE Press","DOI":"10.1109\/SC.2018.00059"},{"issue":"5","key":"3444_CR27","first-page":"1194","volume":"31","author":"H Yongmin","year":"2019","unstructured":"Yongmin H, Yang H, Luan Z, Gan L, Yang G, Qian Depei (2019) Massively scaling seismic processing on sunway taihulight supercomputer. IEEE Trans Parallel Distrib Syst 31(5):1194\u20131208","journal-title":"IEEE Trans Parallel Distrib Syst"},{"key":"3444_CR28","doi-asserted-by":"crossref","unstructured":"Fu H, Liao J, Ding N, Duan X, Gan L, Liang Y, Wang X, Yang J, Zheng Y, Liu W et\u00a0al (2017) Redesigning cam-se for peta-scale climate modeling performance and ultra-high resolution on sunway taihulight. In: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, p 1. ACM","DOI":"10.1145\/3126908.3126909"},{"key":"3444_CR29","unstructured":"Liu C, Yang H, Sun R, Luan Z, and Qian D (2019) swtvm: Exploring the automated compilation for deep learning on sunway architecture. arXiv preprint arXiv:1904.07404,"},{"key":"3444_CR30","doi-asserted-by":"crossref","unstructured":"Li L, Fang J, Fu H, Jiang J, Zhao W, He C, You X, and Yang G (2018) swcaffe: a parallel framework for accelerating deep learning applications on sunway taihulight. In: 2018 IEEE International Conference on Cluster Computing (CLUSTER), pp 413\u2013422. IEEE","DOI":"10.1109\/CLUSTER.2018.00087"},{"key":"3444_CR31","doi-asserted-by":"publisher","DOI":"10.1109\/TETC.2018.2881265","author":"X Zhong","year":"2018","unstructured":"Zhong X, Li M, Yang H, Liu Y, Qian D (2018) swMR: a framework for accelerating mapreduce applications on sunway taihulight. IEEE Trans Emerg Topics Comput. https:\/\/doi.org\/10.1109\/TETC.2018.2881265","journal-title":"IEEE Trans Emerg Topics Comput"},{"key":"3444_CR32","doi-asserted-by":"crossref","unstructured":"Liu C, Xie B, Liu X, Xue W, Yang H, and Liu X (2018) Towards efficient spmv on sunway manycore architectures. In: Proceedings of the 2018 International Conference on Supercomputing, pp 363\u2013373. ACM","DOI":"10.1145\/3205289.3205313"},{"key":"3444_CR33","doi-asserted-by":"crossref","unstructured":"Li M, Liu Y, Yang H, Luan Z, and Qian D (2018) Multi-role sptrsv on sunway many-core architecture. In: 2018 IEEE 20th International Conference on High Performance Computing and Communications; IEEE 16th International Conference on Smart City; IEEE 4th International Conference on Data Science and Systems (HPCC\/SmartCity\/DSS), pp 594\u2013601. IEEE","DOI":"10.1109\/HPCC\/SmartCity\/DSS.2018.00109"},{"key":"3444_CR34","doi-asserted-by":"crossref","unstructured":"Wang X, Liu W, Xue W , and Wu L (2018) swsptrsv: a fast sparse triangular solve with sparse level tile layout on sunway architectures. In: Proceedings of the 23rd ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming, pp 338\u2013353. ACM","DOI":"10.1145\/3178487.3178513"},{"issue":"3","key":"3444_CR35","doi-asserted-by":"publisher","first-page":"404","DOI":"10.1109\/TPDS.2008.105","volume":"20","author":"E Ayguad\u00e9","year":"2008","unstructured":"Ayguad\u00e9 E, Copty N, Duran A, Hoeflinger J, Lin Y, Massaioli F, Teruel X, Unnikrishnan P, Zhang G (2008) The design of openmp tasks. IEEE Trans Parallel Distrib Syst 20(3):404\u2013418","journal-title":"IEEE Trans Parallel Distrib Syst"},{"issue":"02","key":"3444_CR36","doi-asserted-by":"publisher","first-page":"173","DOI":"10.1142\/S0129626411000151","volume":"21","author":"D Alejandro","year":"2011","unstructured":"Alejandro D, Eduard A, Badia Rosa M, Jes\u00fas L, Luis M, Xavier M, Judit P (2011) Ompss: a proposal for programming heterogeneous multi-core architectures. Parallel process lett 21(02):173\u2013193","journal-title":"Parallel process lett"},{"issue":"11","key":"3444_CR37","doi-asserted-by":"publisher","first-page":"2212","DOI":"10.1080\/03081087.2016.1267104","volume":"65","author":"N Kishore Kumar","year":"2017","unstructured":"Kishore Kumar N, Schneider J (2017) Literature survey on low rank approximation of matrices. Linear Multilinear Algebra 65(11):2212\u20132244","journal-title":"Linear Multilinear Algebra"},{"issue":"2","key":"3444_CR38","doi-asserted-by":"publisher","first-page":"149","DOI":"10.1007\/s00365-010-9103-x","volume":"34","author":"M Bebendorf","year":"2011","unstructured":"Bebendorf M (2011) Adaptive cross approximation of multivariate functions. Construct Approx 34(2):149\u2013179","journal-title":"Construct Approx"},{"key":"3444_CR39","first-page":"67","volume":"88","author":"TF Chan","year":"1987","unstructured":"Chan TF (1987) Rank revealing qr factorizations. Linear algebra Appl 88:67\u201382","journal-title":"Linear algebra Appl"},{"issue":"2","key":"3444_CR40","doi-asserted-by":"publisher","first-page":"217","DOI":"10.1137\/090771806","volume":"53","author":"N Halko","year":"2011","unstructured":"Halko N, Martinsson PG, Tropp JA (2011) Finding structure with randomness: Probabilistic algorithms for constructing approximate matrix decompositions. SIAM Rev 53(2):217\u2013288","journal-title":"SIAM Rev"},{"key":"3444_CR41","volume-title":"Machine learning: a probabilistic perspective","author":"KP Murphy","year":"2012","unstructured":"Murphy KP (2012) Machine learning: a probabilistic perspective. MIT press, Cambridge"},{"key":"3444_CR42","doi-asserted-by":"publisher","DOI":"10.1201\/9781584888338","volume-title":"Understanding complex datasets: data mining with matrix decompositions","author":"David Skillicorn","year":"2007","unstructured":"Skillicorn David (2007) Understanding complex datasets: data mining with matrix decompositions. CRC Press, Boca Raton"},{"issue":"3","key":"3444_CR43","doi-asserted-by":"publisher","first-page":"474","DOI":"10.1109\/TMM.2016.2518478","volume":"18","author":"X Li","year":"2016","unstructured":"Li X, Shen B, Liu BD, Zhang YJ (2016) A locality sensitive low-rank model for image tag completion. IEEE Trans Multimed 18(3):474\u2013483","journal-title":"IEEE Trans Multimed"},{"key":"3444_CR44","unstructured":"Park H and Elden L (2003) Matrix rank reduction for data analysis and feature extraction. Technical report, Tr 03-015, University of Minnesota"},{"issue":"7","key":"3444_CR45","doi-asserted-by":"publisher","first-page":"1636","DOI":"10.1109\/TPDS.2019.2953852","volume":"31","author":"M Li","year":"2019","unstructured":"Li M, Liu Y, Yang H, Luan Z, Gan L, Yang G, Qian D (2019) Accelerating sparse cholesky factorization on sunway manycore architecture. IEEE Trans Parallel Distrib Syst 31(7):1636\u20131650","journal-title":"IEEE Trans Parallel Distrib Syst"},{"issue":"3","key":"3444_CR46","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/2764454","volume":"41","author":"G Van Zee Field","year":"2015","unstructured":"Van Zee Field G, Van De\u00a0Geijn RA (2015) Blis: a framework for rapidly instantiating blas functionality. ACM Trans Math Softw 41(3):1\u201333","journal-title":"ACM Trans Math Softw"},{"key":"3444_CR47","doi-asserted-by":"crossref","unstructured":"Anderson E, Bai Z, Bischof C, Blackford S, Dongarra J, Du\u00a0Croz J, Greenbaum A, Hammarling S, McKenney A, Sorensen D (1999) LAPACK users\u2019 guide, vol 9. Society for industrial and applied mathematics","DOI":"10.1137\/1.9780898719604"},{"issue":"02","key":"3444_CR48","first-page":"1251","volume":"80","author":"Walter Gander","year":"1980","unstructured":"Gander Walter (1980) Algorithms for the qr decomposition. Res. Rep 80(02):1251\u20131268","journal-title":"Res. Rep"},{"key":"3444_CR49","volume-title":"Matrix computations","author":"HG Golub","year":"1996","unstructured":"Golub HG, Van Loan Charles F (1996) Matrix computations. Johns hopkins university Press, London"},{"key":"3444_CR50","volume-title":"Linear algebra","author":"JH Wilkinson","year":"2013","unstructured":"Wilkinson JH, Bauer FL, Reinsch C (2013) Linear algebra, vol 2. Springer, Berlin"},{"key":"3444_CR51","unstructured":"Cannon LE (1969) A cellular computer to implement the Kalman filter algorithm. PhD thesis, Montana State University-Bozeman, College of Engineering"},{"issue":"4","key":"3444_CR52","doi-asserted-by":"publisher","first-page":"354","DOI":"10.1007\/BF02165411","volume":"13","author":"V Strassen","year":"1969","unstructured":"Strassen V (1969) Gaussian elimination is not optimal. Numer Mathem 13(4):354\u2013356","journal-title":"Numer Mathem"},{"issue":"4","key":"3444_CR53","doi-asserted-by":"publisher","first-page":"255","DOI":"10.1002\/(SICI)1096-9128(199704)9:4<255::AID-CPE250>3.0.CO;2-2","volume":"9","author":"RA Van De Geijn","year":"1997","unstructured":"Van De Geijn RA, Watts J (1997) Summa: scalable universal matrix multiplication algorithm. Concurr: Pract Exp 9(4):255\u2013274","journal-title":"Concurr: Pract Exp"},{"key":"3444_CR54","doi-asserted-by":"crossref","unstructured":"Solomonik E and Demmel J (2011) Communication-optimal parallel 2.5 d matrix multiplication and lu factorization algorithms. In: European Conference on Parallel Processing, pp 90\u2013109. Springer","DOI":"10.1007\/978-3-642-23397-5_10"},{"key":"3444_CR55","doi-asserted-by":"crossref","unstructured":"Demmel J, Eliahu D, Fox A, Kamil S, Lipshitz B, Schwartz O, and Spillinger O (2013) Communication-optimal parallel recursive rectangular matrix multiplication. In: 2013 IEEE 27th International Symposium on Parallel and Distributed Processing, pp 261\u2013272. IEEE","DOI":"10.1109\/IPDPS.2013.80"},{"key":"3444_CR56","doi-asserted-by":"crossref","unstructured":"Kwasniewski G, Kabi\u0107 M, Besta M, VandeVondele J , Solc\u00e0 R, and Hoefler T (2019) Red-blue pebbling revisited: near optimal parallel matrix-matrix multiplication. In: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, pp 1\u201322","DOI":"10.1145\/3295500.3356181"},{"key":"3444_CR57","doi-asserted-by":"publisher","first-page":"18797","DOI":"10.1109\/ACCESS.2020.2968595","volume":"8","author":"X Yi-Han","year":"2020","unstructured":"Yi-Han X, Yang CC, Hua M, Zhou Wen (2020) Deep deterministic policy gradient (ddpg)-based resource allocation scheme for noma vehicular communications. IEEE Access 8:18797\u201318807","journal-title":"IEEE Access"},{"issue":"1","key":"3444_CR58","first-page":"44","volume":"20","author":"X Yi-Han","year":"2020","unstructured":"Yi-Han X, Xie JW, Zhang YG, Hua M, Zhou Wen (2020) Reinforcement learning (rl)-based energy efficient resource allocation for energy harvesting-powered wireless body area network. Sensors 20(1):44","journal-title":"Sensors"}],"container-title":["The Journal of Supercomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-020-03444-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11227-020-03444-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-020-03444-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,23]],"date-time":"2022-11-23T12:07:43Z","timestamp":1669205263000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11227-020-03444-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,10,15]]},"references-count":58,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2021,5]]}},"alternative-id":["3444"],"URL":"https:\/\/doi.org\/10.1007\/s11227-020-03444-2","relation":{},"ISSN":["0920-8542","1573-0484"],"issn-type":[{"type":"print","value":"0920-8542"},{"type":"electronic","value":"1573-0484"}],"subject":[],"published":{"date-parts":[[2020,10,15]]},"assertion":[{"value":"29 September 2020","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 October 2020","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}