{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T10:38:13Z","timestamp":1778755093111,"version":"3.51.4"},"reference-count":26,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2016,12,16]],"date-time":"2016-12-16T00:00:00Z","timestamp":1481846400000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Supercomput"],"published-print":{"date-parts":[[2017,6]]},"DOI":"10.1007\/s11227-016-1943-0","type":"journal-article","created":{"date-parts":[[2016,12,17]],"date-time":"2016-12-17T10:22:05Z","timestamp":1481970125000},"page":"2506-2524","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":11,"title":["Performance modeling and optimization of parallel LU-SGS on many-core processors for 3D high-order CFD simulations"],"prefix":"10.1007","volume":"73","author":[{"given":"Dali","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chuanfu","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bin","family":"Cheng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Min","family":"Xiong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiang","family":"Gao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaogang","family":"Deng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2016,12,16]]},"reference":[{"key":"1943_CR1","doi-asserted-by":"crossref","unstructured":"Aftosmis M, Berger M, Biswas R, Djomehri MJ, Hood R, Jin H, Kiris C (2006) A detailed performance characterization of columbia using aeronautics benchmarks and applications. In: Proc. 44th AIAA Aerospace Sciences Meeting & Exhibit","DOI":"10.2514\/6.2006-84"},{"key":"1943_CR2","doi-asserted-by":"crossref","unstructured":"Biswas R, Djomehri MJ, Hood R, Jin H, Kiris C, Saini S (2005) An application-based performance characterization of the columbia supercluster. In: Proceedings of the 2005 ACM\/IEEE conference on Supercomputing, p 26. IEEE Computer Society","DOI":"10.1109\/SC.2005.11"},{"key":"1943_CR3","unstructured":"Che Y, Cheng X, Xu C, Zhu X, Wang Z (2015) Performance engineering of a supersonic combustion simulator on heterogeneous platforms. In: Proceedings of 27th International Conference on Parallel Computational Fluid Dynamics"},{"issue":"12","key":"1943_CR4","doi-asserted-by":"crossref","first-page":"2238","DOI":"10.2514\/2.914","volume":"38","author":"R Chen","year":"2000","unstructured":"Chen R, Wang Z (2000) Fast, block lower-upper symmetric gauss-seidel scheme for arbitrary grids. AIAA j 38(12):2238\u20132245","journal-title":"AIAA j"},{"key":"1943_CR5","doi-asserted-by":"crossref","unstructured":"Deng X, Mao M (1997) Weighted compact high-order nonlinear schemes for the euler equations. AIAA paper, pp 97\u20131941","DOI":"10.2514\/6.1997-1941"},{"key":"1943_CR6","first-page":"2011","volume":"3857","author":"X Deng","year":"2011","unstructured":"Deng X, Mao M, Jiang Y, Liu H (2011) New high-order hybrid cell-edge and cell-node weighted compact nonlinear schemes. AIAA Pap 3857:2011","journal-title":"AIAA Pap"},{"issue":"1","key":"1943_CR7","doi-asserted-by":"crossref","first-page":"22","DOI":"10.1006\/jcph.2000.6594","volume":"165","author":"X Deng","year":"2000","unstructured":"Deng X, Zhang H (2000) Developing high-order weighted compact nonlinear schemes. J Comput Phys 165(1):22\u201344","journal-title":"J Comput Phys"},{"key":"1943_CR8","unstructured":"Djomehri MJ, Jin HH, Biegel B (2002) Hybrid mpi+ openmp programming of an overset cfd solver and performance investigations. Tech. rep., NASA Ames Research Center, NAS Technical Report, NAS-02-002"},{"key":"1943_CR9","first-page":"2015","volume":"1949","author":"TD Economon","year":"2015","unstructured":"Economon TD, Palacios F, Alonso JJ, Bansal G, Mudigere D, Deshpande A, Heinecke A, Smelyanskiy M (2015) Towards high-performance optimizations of the unstructured open-source su2 suite. AIAA SciTech AIAA Pap 1949:2015","journal-title":"AIAA SciTech AIAA Pap"},{"key":"1943_CR10","volume-title":"Towards a Systematic Exploration of the Optimization Space for Many-Core Processors","author":"J Fang","year":"2014","unstructured":"Fang J (2014) Towards a Systematic Exploration of the Optimization Space for Many-Core Processors. Delft University of Technology, Delft"},{"key":"1943_CR11","doi-asserted-by":"crossref","unstructured":"Fang J, Sips H, Zhang L, Xu C, Che Y, Varbanescu AL (2014) Test-driving intel xeon phi. In: Proceedings of the 5th ACM\/SPEC international conference on Performance engineering. ACM, pp 137\u2013148","DOI":"10.1145\/2568088.2576799"},{"issue":"1","key":"1943_CR12","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1016\/S1000-9361(11)60359-2","volume":"25","author":"W Gang","year":"2012","unstructured":"Gang W, Jiang Y, Zhengyin Y (2012) An improved lu-sgs implicit scheme for high reynolds number flow computations on hybrid unstructured mesh. Chin J Aeronaut 25(1):33\u201341","journal-title":"Chin J Aeronaut"},{"key":"1943_CR13","doi-asserted-by":"crossref","unstructured":"Li D, Xu C, Wang Y, Song Z, Xiong M, Gao X, Deng X (2015) Parallelizing and optimizing large-scale 3d multi-phase flow simulations on the tianhe-2 supercomputer. Practice and Experience, Concurrency and Computation","DOI":"10.1002\/cpe.3717"},{"key":"1943_CR14","first-page":"92","volume":"1","author":"R Li","year":"2008","unstructured":"Li R, Wang X, Zhao W (2008) A multigrid block lu-sgs algorithm for euler equations on unstructured grids. Numer Math Theory Methods Appl 1:92\u2013112","journal-title":"Numer Math Theory Methods Appl"},{"key":"1943_CR15","doi-asserted-by":"crossref","first-page":"43","DOI":"10.1016\/j.compfluid.2014.11.019","volume":"110","author":"W Liu","year":"2015","unstructured":"Liu W, Zhang L, Zhong Y, Wang Y, Che Y, Xu C, Cheng X (2015) Cfd high-order accurate scheme jacobian-free newton krylov method. Comput Fluids 110:43\u201347","journal-title":"Comput Fluids"},{"key":"1943_CR16","first-page":"2003","volume":"273","author":"H Luo","year":"2003","unstructured":"Luo H, Sharov D, Baum JD, L\u00f6hner R (2003) Parallel unstructured grid gmres+ lu-sgs method for turbulent flows. AIAA Pap 273:2003","journal-title":"AIAA Pap"},{"key":"1943_CR17","unstructured":"Otero E, Eliasson P (2011) Convergence acceleration of the cfd code edge by lu-sgs. In: 3rd CEAS European Air & Space Conference. CEAS\/AIDAA, pp 606\u2013611"},{"key":"1943_CR18","unstructured":"Parsani M, Van den Abeele K, Lacor C (2007) Implicit lu-sgs time integration algorithm for high-order spectral volume method with p-multigrid strategy. In: West-East High-Speed Flow Field Conference, Moscow, Russia"},{"key":"1943_CR19","first-page":"2000","volume":"927","author":"D Sharov","year":"2000","unstructured":"Sharov D, Luo H, Baum JD, L\u00f6hner R (2000) Implementation of unstructured grid gmres+ lu-sgs method on shared-memory, cache-based parallel computers. AIAA Pap 927:2000","journal-title":"AIAA Pap"},{"issue":"2\u20134","key":"1943_CR20","first-page":"760","volume":"5","author":"Y Sun","year":"2009","unstructured":"Sun Y, Wang Z, Liu Y (2009) Efficient implicit non-linear lu-sgs approach for compressible flow computation using high-order spectral difference method. commun. Comput Phys 5(2\u20134):760\u2013778","journal-title":"Comput Phys"},{"issue":"1","key":"1943_CR21","first-page":"36","volume":"43","author":"YX Wang","year":"2015","unstructured":"Wang YX, Zhang LL, Che YG, Xu CF, Liu W, Cheng XH (2015) Efficient parallel computing and performance tuning for multi-block structured grid cfd applications on tianhe supercomputer. Tien Tzu Hsueh Pao\/acta Electronica Sinica 43(1):36\u201344","journal-title":"Tien Tzu Hsueh Pao\/acta Electronica Sinica"},{"key":"1943_CR22","doi-asserted-by":"crossref","first-page":"275","DOI":"10.1016\/j.jcp.2014.08.024","volume":"278","author":"C Xu","year":"2014","unstructured":"Xu C, Deng X, Zhang L, Fang J, Wang G, Jiang Y, Cao W, Che Y, Wang Y, Wang Z et al (2014) Collaborating cpu and gpu for large-scale high-order cfd simulations with complex grids on the tianhe-1a supercomputer. J Comput Phys 278:275\u2013297","journal-title":"J Comput Phys"},{"key":"1943_CR23","doi-asserted-by":"crossref","unstructured":"Yamamoto S, Sasao Y, Sato S, Sano K (2007) Parallel-implicit computation of three-dimensional multistage stator-rotor cascade flows with condensation. In: Proc. 18th AIAA Computational Fluid Dynamics Conference, AIAA Paper, vol 4460, p 2007","DOI":"10.2514\/6.2007-4460"},{"issue":"9","key":"1943_CR24","doi-asserted-by":"crossref","first-page":"1025","DOI":"10.2514\/3.10007","volume":"26","author":"S Yoon","year":"1988","unstructured":"Yoon S, Jameson A (1988) Lower-upper symmetric-gauss-seidel method for the euler and navier-stokes equations. AIAA J 26(9):1025\u20131026","journal-title":"AIAA J"},{"key":"1943_CR25","unstructured":"Yoon S, Jost G, Chang S (2005) Parallelization of gauss-seidel relaxation for real gas flow. Tech. rep., NAS Technical Report, NAS-05-011"},{"issue":"7","key":"1943_CR26","doi-asserted-by":"crossref","first-page":"891","DOI":"10.1016\/j.compfluid.2003.10.004","volume":"33","author":"L Zhang","year":"2004","unstructured":"Zhang L, Wang Z (2004) A block lu-sgs implicit dual time-stepping algorithm for hybrid dynamic meshes. Comput Fluids 33(7):891\u2013916","journal-title":"Comput Fluids"}],"container-title":["The Journal of Supercomputing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11227-016-1943-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-016-1943-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-016-1943-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,9,16]],"date-time":"2019-09-16T16:55:59Z","timestamp":1568652959000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11227-016-1943-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,12,16]]},"references-count":26,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2017,6]]}},"alternative-id":["1943"],"URL":"https:\/\/doi.org\/10.1007\/s11227-016-1943-0","relation":{},"ISSN":["0920-8542","1573-0484"],"issn-type":[{"value":"0920-8542","type":"print"},{"value":"1573-0484","type":"electronic"}],"subject":[],"published":{"date-parts":[[2016,12,16]]}}}