A parallel nonlinear multigrid solver for unsteady incompressible flow simulation on multi-GPU cluster

A nonlinear multigrid solver for solutions of unsteady three-dimensional incompressible viscous flow working on multi-GPU cluster is developed. The solver consists of a full approximation scheme (FAS) V-cycle scheme to accelerate the computation, in which the artificial compressibility method based...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	Journal of computational physics Ročník 414; s. 109447
Hlavní autoři:	Shi, Xiaolei, Agrawal, Tanmay, Lin, Chao-An, Hwang, Feng-Nan, Chiu, Tzu-Hsuan
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	Cambridge Elsevier Inc 01.08.2020 Elsevier Science Ltd
Témata:	Artificial compressibility method Clusters Compressibility Computational fluid dynamics Computational physics Computer simulation Dual-time stepping FAS V-cycle scheme Flow simulation Fluid flow Incompressible flow Laminar flow Multi-GPU Navier-Stokes equations Three dimensional flow Viscous flow Incompressible flow FAS V-cycle scheme Dual-time stepping Artificial compressibility method Multi-GPU Navier-Stokes equations
ISSN:	0021-9991, 1090-2716
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Abstract	A nonlinear multigrid solver for solutions of unsteady three-dimensional incompressible viscous flow working on multi-GPU cluster is developed. The solver consists of a full approximation scheme (FAS) V-cycle scheme to accelerate the computation, in which the artificial compressibility method based Navier-Stokes solver is used as a smoother. Multi-stream overlapping strategies are designed to assist multi-GPU computations. The numerical procedure is validated by computing 3D laminar and turbulent flows within a lid-driven cubic cavity. The predicted results compare favorably with previous benchmark solutions and measurements, both in mean and turbulent quantities. For the performance of the FAS V-cycle scheme, up to two orders of magnitude speedups are reported, and the relationship between work unit (WU) and total grid number N is O(N0.3) under the deepest FAS V-cycle. A detailed evaluation of the GPU implementation is carried out employing the Roofline model and the scalability analysis. •A parallel nonlinear multigrid solver for unsteady incompressible flow simulation is implemented on multi-GPU cluster.•The artificial compressibility method based Navier-Stokes solver is used as a smoother for multigrid.•For FAS Lev. 7, 250 speedups over its single grid counterpart is reported.•The work unit scales with the total grid number N at O(N0.3) under the deepest FAS V-cycle.•A detailed evaluation of the GPU implementation is carried out employing the Roofline model and the scalability analysis.
AbstractList	A nonlinear multigrid solver for solutions of unsteady three-dimensional incompressible viscous flow working on multi-GPU cluster is developed. The solver consists of a full approximation scheme (FAS) V-cycle scheme to accelerate the computation, in which the artificial compressibility method based Navier-Stokes solver is used as a smoother. Multi-stream overlapping strategies are designed to assist multi-GPU computations. The numerical procedure is validated by computing 3D laminar and turbulent flows within a lid-driven cubic cavity. The predicted results compare favorably with previous benchmark solutions and measurements, both in mean and turbulent quantities. For the performance of the FAS V-cycle scheme, up to two orders of magnitude speedups are reported, and the relationship between work unit (WU) and total grid number N is O (N0.3) under the deepest FAS V-cycle. A detailed evaluation of the GPU implementation is carried out employing the Roofline model and the scalability analysis. A nonlinear multigrid solver for solutions of unsteady three-dimensional incompressible viscous flow working on multi-GPU cluster is developed. The solver consists of a full approximation scheme (FAS) V-cycle scheme to accelerate the computation, in which the artificial compressibility method based Navier-Stokes solver is used as a smoother. Multi-stream overlapping strategies are designed to assist multi-GPU computations. The numerical procedure is validated by computing 3D laminar and turbulent flows within a lid-driven cubic cavity. The predicted results compare favorably with previous benchmark solutions and measurements, both in mean and turbulent quantities. For the performance of the FAS V-cycle scheme, up to two orders of magnitude speedups are reported, and the relationship between work unit (WU) and total grid number N is O(N0.3) under the deepest FAS V-cycle. A detailed evaluation of the GPU implementation is carried out employing the Roofline model and the scalability analysis. •A parallel nonlinear multigrid solver for unsteady incompressible flow simulation is implemented on multi-GPU cluster.•The artificial compressibility method based Navier-Stokes solver is used as a smoother for multigrid.•For FAS Lev. 7, 250 speedups over its single grid counterpart is reported.•The work unit scales with the total grid number N at O(N0.3) under the deepest FAS V-cycle.•A detailed evaluation of the GPU implementation is carried out employing the Roofline model and the scalability analysis.
ArticleNumber	109447
Author	Chiu, Tzu-Hsuan Shi, Xiaolei Agrawal, Tanmay Hwang, Feng-Nan Lin, Chao-An
Author_xml	– sequence: 1 givenname: Xiaolei orcidid: 0000-0003-1901-2354 surname: Shi fullname: Shi, Xiaolei email: xiaoleishi.th@gmail.com organization: Department of Power Mechanical Engineering, National Tsing Hua University, Hsinchu 30013, Taiwan – sequence: 2 givenname: Tanmay orcidid: 0000-0002-0777-2527 surname: Agrawal fullname: Agrawal, Tanmay email: tanmayagrawal7@gmail.com organization: Department of Power Mechanical Engineering, National Tsing Hua University, Hsinchu 30013, Taiwan – sequence: 3 givenname: Chao-An orcidid: 0000-0002-2861-7913 surname: Lin fullname: Lin, Chao-An email: calin@pme.nthu.edu.tw organization: Department of Power Mechanical Engineering, National Tsing Hua University, Hsinchu 30013, Taiwan – sequence: 4 givenname: Feng-Nan surname: Hwang fullname: Hwang, Feng-Nan email: hwangf@math.ncu.edu.tw organization: Department of Mathematics, National Central University, Taoyuan 32001, Taiwan – sequence: 5 givenname: Tzu-Hsuan surname: Chiu fullname: Chiu, Tzu-Hsuan email: nemovten608@gmail.com organization: Department of Power Mechanical Engineering, National Tsing Hua University, Hsinchu 30013, Taiwan
BookMark	eNp9kE1LAzEQhoNUsK3-AG8Bz1uT7Ec3eCpFq1DQgz2HNDuRLOlmTXYr_fdmu548FEIygfeZYZ4ZmjSuAYTuKVlQQovHelGrdsEIG_48y5ZXaBoLkrAlLSZoSgijCeec3qBZCDUhpMyzcor0CrfSS2vB4tjSmgakx4fedubLmwoHZ4_gsXYe903oQFYnbBrlDq2HEMzeAtbW_eBgIiM74xocz5lPNh87rGwfKX-LrrW0Ae7-3jnavTx_rl-T7fvmbb3aJipleZdkHDIGHCSv1HAxzYgqskpyyUlZljnhKss5o0u9p0xXMVtADooVUuW60OkcPYx9W---ewidqF3vmzhSsCglJWmW5jFFx5TyLgQPWrTeHKQ_CUrEoFPUIuoUg04x6ozM8h-jTHdeuPPS2Ivk00hCXPxowIugDDQKKuNBdaJy5gL9CzbNk1Y
CitedBy_id	crossref_primary_10_1080_10618562_2023_2202391 crossref_primary_10_1016_j_camwa_2022_04_013 crossref_primary_10_1093_jom_ufad015 crossref_primary_10_1007_s10494_025_00689_w
Cites_doi	10.1006/jcph.1998.6067 10.1016/0021-9991(87)90190-2 10.1006/jcph.1997.5716 10.1090/S0025-5718-1977-0431719-X 10.1145/1498765.1498785 10.1016/j.jcp.2005.01.020 10.1080/10618562.2013.829915 10.2514/3.50867 10.1147/rd.112.0215 10.1002/fld.1709 10.1063/1.857491 10.1016/j.compfluid.2014.12.010 10.1016/j.compfluid.2012.01.021 10.1016/j.compfluid.2010.12.011 10.1016/j.jcp.2008.08.027 10.1016/0021-9991(88)90007-1 10.1006/jcph.1997.5859 10.1109/JPROC.2008.917757 10.1016/0021-9991(85)90148-2 10.1016/j.compfluid.2011.02.005 10.2514/3.12303 10.1016/j.cpc.2018.03.026 10.1016/j.compfluid.2018.03.008 10.1109/MCSE.2012.37 10.1016/j.compfluid.2013.05.021 10.1063/1.5026947 10.2514/3.10627 10.1016/j.jcp.2016.03.016 10.1016/j.compfluid.2013.10.035 10.1115/1.1366680
ContentType	Journal Article
Copyright	2020 Elsevier Inc. Copyright Elsevier Science Ltd. Aug 1, 2020
Copyright_xml	– notice: 2020 Elsevier Inc. – notice: Copyright Elsevier Science Ltd. Aug 1, 2020
DBID	AAYXX CITATION 7SC 7SP 7U5 8FD JQ2 L7M L~C L~D
DOI	10.1016/j.jcp.2020.109447
DatabaseName	CrossRef Computer and Information Systems Abstracts Electronics & Communications Abstracts Solid State and Superconductivity Abstracts Technology Research Database ProQuest Computer Science Collection Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional
DatabaseTitle	CrossRef Technology Research Database Computer and Information Systems Abstracts – Academic Electronics & Communications Abstracts ProQuest Computer Science Collection Computer and Information Systems Abstracts Solid State and Superconductivity Abstracts Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Professional
DatabaseTitleList	Technology Research Database
DeliveryMethod	fulltext_linktorsrc
Discipline	Applied Sciences
EISSN	1090-2716
ExternalDocumentID	10_1016_j_jcp_2020_109447 S0021999120302217
GroupedDBID	--K --M -~X .~1 0R~ 1B1 1RT 1~. 1~5 4.4 457 4G. 5GY 5VS 6OB 7-5 71M 8P~ 9JN AABNK AACTN AAEDT AAEDW AAIAV AAIKJ AAKOC AALRI AAOAW AAQFI AAXUO AAYFN ABBOA ABFRF ABJNI ABMAC ABNEU ABYKQ ACBEA ACDAQ ACFVG ACGFO ACGFS ACNCT ACRLP ACZNC ADBBV ADEZE AEBSH AEFWE AEKER AENEX AFKWA AFTJW AGHFR AGUBO AGYEJ AHHHB AHZHX AIALX AIEXJ AIKHN AITUG AIVDX AJOXV ALMA_UNASSIGNED_HOLDINGS AMFUW AMRAJ AOUOD AXJTR BKOJK BLXMC CS3 DM4 DU5 EBS EFBJH EFLBG EO8 EO9 EP2 EP3 F5P FDB FEDTE FIRID FNPLU FYGXN G-Q GBLVA GBOLZ HLZ HVGLF IHE J1W K-O KOM LG5 LX9 LZ4 M37 M41 MO0 N9A O-L O9- OAUVE OGIMB OZT P-8 P-9 P2P PC. Q38 RNS ROL RPZ SDF SDG SDP SES SPC SPCBC SPD SSQ SSV SSZ T5K TN5 UPT YQT ZMT ZU3 ~02 ~G- 29K 6TJ 8WZ 9DU A6W AAQXK AATTM AAXKI AAYWO AAYXX ABFNM ABWVN ABXDB ACLOT ACNNM ACRPL ACVFH ADCNI ADFGL ADIYS ADJOM ADMUD ADNMO AEIPS AEUPX AFFNX AFJKZ AFPUW AGQPQ AIGII AIIUN AKBMS AKRWK AKYEP ANKPU APXCP ASPBG AVWKF AZFZN BBWZM CAG CITATION COF D-I EFKBS EJD FGOYB G-2 HME HMV HZ~ NDZJH R2- SBC SEW SHN SPG T9H UQL WUQ ZY4 ~HD 7SC 7SP 7U5 8FD JQ2 L7M L~C L~D
ID	FETCH-LOGICAL-c325t-49e42e9ea9dcea9d2f20c64da9a90888509c459217fb12fd2e96e5ec26ac5f6f3
ISICitedReferencesCount	10
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000536532800008&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	0021-9991
IngestDate	Sun Nov 09 06:43:09 EST 2025 Tue Nov 18 21:39:29 EST 2025 Sat Nov 29 03:10:28 EST 2025 Fri Feb 23 02:47:59 EST 2024
IsPeerReviewed	true
IsScholarly	true
Keywords	Incompressible flow FAS V-cycle scheme Dual-time stepping Artificial compressibility method Multi-GPU Navier-Stokes equations
Language	English
LinkModel	OpenURL
MergedId	FETCHMERGED-LOGICAL-c325t-49e42e9ea9dcea9d2f20c64da9a90888509c459217fb12fd2e96e5ec26ac5f6f3
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
ORCID	0000-0003-1901-2354 0000-0002-0777-2527 0000-0002-2861-7913
PQID	2447303435
PQPubID	2047462
ParticipantIDs	proquest_journals_2447303435 crossref_primary_10_1016_j_jcp_2020_109447 crossref_citationtrail_10_1016_j_jcp_2020_109447 elsevier_sciencedirect_doi_10_1016_j_jcp_2020_109447
PublicationCentury	2000
PublicationDate	2020-08-01 2020-08-00 20200801
PublicationDateYYYYMMDD	2020-08-01
PublicationDate_xml	– month: 08 year: 2020 text: 2020-08-01 day: 01
PublicationDecade	2020
PublicationPlace	Cambridge
PublicationPlace_xml	– name: Cambridge
PublicationTitle	Journal of computational physics
PublicationYear	2020
Publisher	Elsevier Inc Elsevier Science Ltd
Publisher_xml	– name: Elsevier Inc – name: Elsevier Science Ltd
References	Bailey, Lucas, Williams (br0380) 2010 Davani, Marti, Pourghassemi, Liu, Chandramowlishwaran (br0050) 2017 Oyarzun, Borrell, Gorobets, Oliva (br0110) 2014; 92 Gilmanov, Sotiropoulos (br0150) 2005; 207 Ku, Hirsh, Taylor (br0310) 1987; 70 Candler, Wright, McDonald (br0410) 1994; 32 Koseff, Street, Gresho, Upson, Humphrey, To (br0320) 1983 Owens, Houston, Luebke, Green, Stone, Phillips (br0010) 2008; 96 Darwish, Sraj, Moukalled (br0230) 2009; 228 Gorobets, Trias, Oliva (br0130) 2013; 88 Abe, Kawamura, Matsuo (br0350) 2001; 123 Pratap Vanka, Shinn, Sahu (br0280) 2011 Hong, Huang, Lin, Lin (br0040) 2015; 110 Tesla (br0290) 2017 (br0300) 2012 Cox, Liang, Plesniak (br0430) 2016; 314 Briggs, Henson, McCormick (br0210) 2000 Lo Jung, Williams, Straalen, Ligocki, Cordery, Wright, Hall, Oliker (br0390) 2015 Liu, Zheng, Sung (br0220) 1998; 139 Tanno, Morinishi, Satofuka, Watanabe (br0420) 2011; 45 Deleon, Jacobsen, Senocak (br0100) 2013; 15 Rogers, Kwak, Kiris (br0160) 1991; 29 Hsu, Hwang, Wei, Lai, Lin (br0240) 2011; 45 Chorin (br0140) 1997; 135 Chandar, Sitaraman, Mavriplis (br0030) 2013; 27 Prasad, Perng, Koseff (br0330) 1988 Soh, Goodrich (br0260) 1988; 79 Prasad, Koseff (br0340) 1989; 1 Ofenbeck, Steinmann, Cabezas, Spampinato, Püschel (br0400) 2014 Wang, Aoki (br0020) 2011; 37 Diaz, Solovchuk, Sheu (br0070) 2018; 173 Brandt (br0180) 1977; 31 Louda, Kozel, Příhoda (br0170) 2008; 56 Zhu, Phillips, Spandan, Donners, Ruetsch, Romero, Ostilla-Mónico, Yang, Lohse, Verzicco, Fatica, Stevens (br0060) 2018; 229 Kim, Moin (br0080) 1985; 59 Brandt (br0190) 1980; 18 Brandt, Livne (br0200) 2011; vol. 67 Owolabi, Lin (br0360) 2018; 30 Courant, Friedrichs, Lewy (br0270) 1967; 11 Zaspel, Griebel (br0120) 2013; 80 Jacobsen, Senocak (br0090) 2011 Drikakis, Iliev, Vassileva (br0250) 1998; 146 Williams, Waterman, Patterson (br0370) 2009; 52 Davani (10.1016/j.jcp.2020.109447_br0050) 2017 Oyarzun (10.1016/j.jcp.2020.109447_br0110) 2014; 92 Williams (10.1016/j.jcp.2020.109447_br0370) 2009; 52 Ofenbeck (10.1016/j.jcp.2020.109447_br0400) 2014 Prasad (10.1016/j.jcp.2020.109447_br0330) 1988 Prasad (10.1016/j.jcp.2020.109447_br0340) 1989; 1 Wang (10.1016/j.jcp.2020.109447_br0020) 2011; 37 Zhu (10.1016/j.jcp.2020.109447_br0060) 2018; 229 Rogers (10.1016/j.jcp.2020.109447_br0160) 1991; 29 Briggs (10.1016/j.jcp.2020.109447_br0210) 2000 Hsu (10.1016/j.jcp.2020.109447_br0240) 2011; 45 Owens (10.1016/j.jcp.2020.109447_br0010) 2008; 96 Ku (10.1016/j.jcp.2020.109447_br0310) 1987; 70 Soh (10.1016/j.jcp.2020.109447_br0260) 1988; 79 Diaz (10.1016/j.jcp.2020.109447_br0070) 2018; 173 Gilmanov (10.1016/j.jcp.2020.109447_br0150) 2005; 207 Koseff (10.1016/j.jcp.2020.109447_br0320) 1983 Kim (10.1016/j.jcp.2020.109447_br0080) 1985; 59 Louda (10.1016/j.jcp.2020.109447_br0170) 2008; 56 Drikakis (10.1016/j.jcp.2020.109447_br0250) 1998; 146 Owolabi (10.1016/j.jcp.2020.109447_br0360) 2018; 30 Tesla (10.1016/j.jcp.2020.109447_br0290) 2017 Liu (10.1016/j.jcp.2020.109447_br0220) 1998; 139 Zaspel (10.1016/j.jcp.2020.109447_br0120) 2013; 80 Candler (10.1016/j.jcp.2020.109447_br0410) 1994; 32 Hong (10.1016/j.jcp.2020.109447_br0040) 2015; 110 Abe (10.1016/j.jcp.2020.109447_br0350) 2001; 123 Pratap Vanka (10.1016/j.jcp.2020.109447_br0280) 2011 Cox (10.1016/j.jcp.2020.109447_br0430) 2016; 314 Brandt (10.1016/j.jcp.2020.109447_br0190) 1980; 18 Chorin (10.1016/j.jcp.2020.109447_br0140) 1997; 135 Brandt (10.1016/j.jcp.2020.109447_br0180) 1977; 31 Brandt (10.1016/j.jcp.2020.109447_br0200) 2011; vol. 67 Chandar (10.1016/j.jcp.2020.109447_br0030) 2013; 27 Gorobets (10.1016/j.jcp.2020.109447_br0130) 2013; 88 Tanno (10.1016/j.jcp.2020.109447_br0420) 2011; 45 Deleon (10.1016/j.jcp.2020.109447_br0100) 2013; 15 Courant (10.1016/j.jcp.2020.109447_br0270) 1967; 11 Jacobsen (10.1016/j.jcp.2020.109447_br0090) 2011 Bailey (10.1016/j.jcp.2020.109447_br0380) 2010 Darwish (10.1016/j.jcp.2020.109447_br0230) 2009; 228 (10.1016/j.jcp.2020.109447_br0300) 2012 Lo Jung (10.1016/j.jcp.2020.109447_br0390) 2015
References_xml	– volume: 96 start-page: 879 year: 2008 end-page: 899 ident: br0010 article-title: Gpu computing publication-title: Proc. IEEE – volume: 110 start-page: 1 year: 2015 end-page: 8 ident: br0040 article-title: Scalable multi-relaxation-time lattice Boltzmann simulations on multi-GPU cluster publication-title: Comput. Fluids – volume: 139 start-page: 35 year: 1998 end-page: 57 ident: br0220 article-title: Preconditioned multigrid methods for unsteady incompressible flows publication-title: J. Comput. Phys. – start-page: 76 year: 2014 end-page: 85 ident: br0400 article-title: Applying the roofline model publication-title: IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS) – volume: 80 start-page: 356 year: 2013 end-page: 364 ident: br0120 article-title: Solving incompressible two-phase flows on multi-GPU clusters publication-title: Comput. Fluids – year: 2000 ident: br0210 article-title: A Multigrid Tutorial – year: 2011 ident: br0090 article-title: A full-depth amalgamated parallel 3D geometric multigrid solver for GPU clusters publication-title: 49th AIAA Aerospace Sciences Meeting – volume: 123 start-page: 382 year: 2001 end-page: 393 ident: br0350 article-title: Direct numerical simulation of a fully developed turbulent channel flow with respect to the reynolds number dependence publication-title: J. Fluids Eng. – start-page: 129 year: 2015 end-page: 148 ident: br0390 article-title: Roofline Model Toolkit: A Practical Yool for Architectural and Program Analysis – volume: 135 start-page: 118 year: 1997 end-page: 125 ident: br0140 article-title: A numerical method for solving incompressible viscous flow problems publication-title: J. Comput. Phys. – volume: 1 start-page: 208 year: 1989 end-page: 218 ident: br0340 article-title: Reynolds number and end wall effects on a lid-driven cavity flow publication-title: Phys. Fluids A, Fluid Dyn. – volume: 92 start-page: 244 year: 2014 end-page: 252 ident: br0110 article-title: MPi-CUDA sparse matrix–vector multiplication for the conjugate gradient method with an approximate inverse preconditioner publication-title: Comput. Fluids – volume: 27 start-page: 268 year: 2013 end-page: 282 ident: br0030 article-title: A GPU-based incompressible Navier—Stokes solver on moving overset grids publication-title: Int. J. Comput. Fluid Dyn. – volume: vol. 67 year: 2011 ident: br0200 article-title: Multigrid techniques. 1984 guide with applications to fluid dynamics publication-title: revised ed. – volume: 314 start-page: 414 year: 2016 end-page: 435 ident: br0430 article-title: A high-order solver for unsteady incompressible navier–stokes equations using the flux reconstruction method on unstructured grids with implicit dual time stepping publication-title: J. Comput. Phys. – start-page: 288 year: 1988 end-page: 295 ident: br0330 article-title: Some Observations on the Influence of Longitudinal Vortices in a Lid-Driven Cavity Flow – volume: 52 start-page: 65 year: 2009 end-page: 76 ident: br0370 article-title: Roofline: an insightful visual performance model for multicore architectures publication-title: Commun. ACM – volume: 45 start-page: 138 year: 2011 end-page: 146 ident: br0240 article-title: A parallel multilevel preconditioned iterative pressure Poisson solver for the large-eddy simulation of turbulent flow inside a duct publication-title: Comput. Fluids – volume: 45 start-page: 162 year: 2011 end-page: 167 ident: br0420 article-title: Calculation by artificial compressibility method and virtual flux method on gpu publication-title: Comput. Fluids – volume: 37 start-page: 521 year: 2011 end-page: 535 ident: br0020 article-title: Multi-GPU performance of incompressible flow computation by lattice Boltzmann method on GPU cluster publication-title: Parallel Comput. – year: 2011 ident: br0280 article-title: Computational fluid dynamics using graphics processing units: challenges and opportunities publication-title: ASME 2011 International Mechanical Engineering Congress and Exposition, IMECE, 2011, vol. 6 – volume: 31 start-page: 333 year: 1977 end-page: 390 ident: br0180 article-title: Multi-level adaptive solutions to boundary-value problems publication-title: Math. Comput. – volume: 228 start-page: 180 year: 2009 end-page: 201 ident: br0230 article-title: A coupled finite volume solver for the solution of incompressible flows on unstructured grids publication-title: J. Comput. Phys. – volume: 70 start-page: 439 year: 1987 end-page: 462 ident: br0310 article-title: A pseudospectral method for solution of the three-dimensional incompressible navier-stokes equations publication-title: J. Comput. Phys. – volume: 79 start-page: 113 year: 1988 end-page: 134 ident: br0260 article-title: Unsteady solution of incompressible Navier–Stokes equations publication-title: J. Comput. Phys. – volume: 207 start-page: 457 year: 2005 end-page: 492 ident: br0150 article-title: A hybrid Cartesian/immersed boundary method for simulating flows with 3D, geometrically complex, moving bodies publication-title: J. Comput. Phys. – year: 1983 ident: br0320 article-title: Three-Dimensional Lid-Driven Cavity Flow: Experiment and Simulation – volume: 32 start-page: 2380 year: 1994 end-page: 2386 ident: br0410 article-title: Data-parallel lower-upper relaxation method for reacting flows publication-title: AIAA J. – volume: 173 start-page: 195 year: 2018 end-page: 205 ident: br0070 article-title: High-performance multi-GPU solver for describing nonlinear acoustic waves in homogeneous thermoviscous media publication-title: Comput. Fluids – volume: 30 year: 2018 ident: br0360 article-title: Marginally turbulent couette flow in a spanwise confined passage of square cross section publication-title: Phys. Fluids – volume: 15 start-page: 26 year: 2013 end-page: 33 ident: br0100 article-title: Large-eddy simulations of turbulent incompressible flows on GPU clusters publication-title: Comput. Sci. Eng. – year: 2017 ident: br0050 article-title: Unsteady Navier-Stokes computations on GPU architectures publication-title: 23rd AIAA Computational Fluid Dynamics Conferences – year: 2017 ident: br0290 article-title: V100 GPU Architecture – volume: 56 start-page: 1399 year: 2008 end-page: 1407 ident: br0170 article-title: Numerical solution of 2D and 3D viscous incompressible steady and unsteady flows using artificial compressibility method publication-title: Int. J. Numer. Methods Fluids – volume: 229 start-page: 199 year: 2018 end-page: 210 ident: br0060 article-title: AFiD-GPU: a versatile Navier—Stokes solver for wall-bounded turbulent flows on GPU clusters publication-title: Comput. Phys. Commun. – volume: 11 start-page: 215 year: 1967 end-page: 234 ident: br0270 article-title: On the partial difference equations of mathematical physics publication-title: IBM J. Res. Dev. – volume: 59 start-page: 308 year: 1985 end-page: 323 ident: br0080 article-title: Application of a fractional-step method to incompressible Navier–Stokes equations publication-title: J. Comput. Phys. – volume: 88 start-page: 764 year: 2013 end-page: 772 ident: br0130 article-title: A parallel MPI+OpenMP+OpenCL algorithm for hybrid supercomputations of incompressible flows publication-title: Comput. Fluids – year: 2012 ident: br0300 article-title: Developing a Linux Kernel Module Using RDMA for GPUdirect: Application Guide – volume: 18 start-page: 1165 year: 1980 end-page: 1172 ident: br0190 article-title: Multilevel adaptive computations in fluid dynamics publication-title: AIAA J. – volume: 146 start-page: 301 year: 1998 end-page: 321 ident: br0250 article-title: A nonlinear multigrid method for the three-dimensional incompressible Navier—Stokes equations publication-title: J. Comput. Phys. – year: 2010 ident: br0380 article-title: Performance Tuning of Scientific Applications – volume: 29 start-page: 603 year: 1991 end-page: 610 ident: br0160 article-title: Steady and unsteady solutions of the incompressible Navier–Stokes equations publication-title: AIAA J. – volume: 146 start-page: 301 year: 1998 ident: 10.1016/j.jcp.2020.109447_br0250 article-title: A nonlinear multigrid method for the three-dimensional incompressible Navier—Stokes equations publication-title: J. Comput. Phys. doi: 10.1006/jcph.1998.6067 – volume: 70 start-page: 439 year: 1987 ident: 10.1016/j.jcp.2020.109447_br0310 article-title: A pseudospectral method for solution of the three-dimensional incompressible navier-stokes equations publication-title: J. Comput. Phys. doi: 10.1016/0021-9991(87)90190-2 – volume: 135 start-page: 118 year: 1997 ident: 10.1016/j.jcp.2020.109447_br0140 article-title: A numerical method for solving incompressible viscous flow problems publication-title: J. Comput. Phys. doi: 10.1006/jcph.1997.5716 – volume: 31 start-page: 333 year: 1977 ident: 10.1016/j.jcp.2020.109447_br0180 article-title: Multi-level adaptive solutions to boundary-value problems publication-title: Math. Comput. doi: 10.1090/S0025-5718-1977-0431719-X – year: 1983 ident: 10.1016/j.jcp.2020.109447_br0320 – volume: 52 start-page: 65 year: 2009 ident: 10.1016/j.jcp.2020.109447_br0370 article-title: Roofline: an insightful visual performance model for multicore architectures publication-title: Commun. ACM doi: 10.1145/1498765.1498785 – volume: 207 start-page: 457 year: 2005 ident: 10.1016/j.jcp.2020.109447_br0150 article-title: A hybrid Cartesian/immersed boundary method for simulating flows with 3D, geometrically complex, moving bodies publication-title: J. Comput. Phys. doi: 10.1016/j.jcp.2005.01.020 – start-page: 76 year: 2014 ident: 10.1016/j.jcp.2020.109447_br0400 article-title: Applying the roofline model – volume: 27 start-page: 268 year: 2013 ident: 10.1016/j.jcp.2020.109447_br0030 article-title: A GPU-based incompressible Navier—Stokes solver on moving overset grids publication-title: Int. J. Comput. Fluid Dyn. doi: 10.1080/10618562.2013.829915 – volume: 18 start-page: 1165 year: 1980 ident: 10.1016/j.jcp.2020.109447_br0190 article-title: Multilevel adaptive computations in fluid dynamics publication-title: AIAA J. doi: 10.2514/3.50867 – volume: 11 start-page: 215 year: 1967 ident: 10.1016/j.jcp.2020.109447_br0270 article-title: On the partial difference equations of mathematical physics publication-title: IBM J. Res. Dev. doi: 10.1147/rd.112.0215 – start-page: 129 year: 2015 ident: 10.1016/j.jcp.2020.109447_br0390 – volume: 56 start-page: 1399 year: 2008 ident: 10.1016/j.jcp.2020.109447_br0170 article-title: Numerical solution of 2D and 3D viscous incompressible steady and unsteady flows using artificial compressibility method publication-title: Int. J. Numer. Methods Fluids doi: 10.1002/fld.1709 – start-page: 288 year: 1988 ident: 10.1016/j.jcp.2020.109447_br0330 – volume: 1 start-page: 208 year: 1989 ident: 10.1016/j.jcp.2020.109447_br0340 article-title: Reynolds number and end wall effects on a lid-driven cavity flow publication-title: Phys. Fluids A, Fluid Dyn. doi: 10.1063/1.857491 – volume: 110 start-page: 1 year: 2015 ident: 10.1016/j.jcp.2020.109447_br0040 article-title: Scalable multi-relaxation-time lattice Boltzmann simulations on multi-GPU cluster publication-title: Comput. Fluids doi: 10.1016/j.compfluid.2014.12.010 – volume: 80 start-page: 356 year: 2013 ident: 10.1016/j.jcp.2020.109447_br0120 article-title: Solving incompressible two-phase flows on multi-GPU clusters publication-title: Comput. Fluids doi: 10.1016/j.compfluid.2012.01.021 – volume: 45 start-page: 138 year: 2011 ident: 10.1016/j.jcp.2020.109447_br0240 article-title: A parallel multilevel preconditioned iterative pressure Poisson solver for the large-eddy simulation of turbulent flow inside a duct publication-title: Comput. Fluids doi: 10.1016/j.compfluid.2010.12.011 – volume: 228 start-page: 180 year: 2009 ident: 10.1016/j.jcp.2020.109447_br0230 article-title: A coupled finite volume solver for the solution of incompressible flows on unstructured grids publication-title: J. Comput. Phys. doi: 10.1016/j.jcp.2008.08.027 – year: 2011 ident: 10.1016/j.jcp.2020.109447_br0090 article-title: A full-depth amalgamated parallel 3D geometric multigrid solver for GPU clusters – volume: 79 start-page: 113 year: 1988 ident: 10.1016/j.jcp.2020.109447_br0260 article-title: Unsteady solution of incompressible Navier–Stokes equations publication-title: J. Comput. Phys. doi: 10.1016/0021-9991(88)90007-1 – year: 2012 ident: 10.1016/j.jcp.2020.109447_br0300 – volume: 139 start-page: 35 year: 1998 ident: 10.1016/j.jcp.2020.109447_br0220 article-title: Preconditioned multigrid methods for unsteady incompressible flows publication-title: J. Comput. Phys. doi: 10.1006/jcph.1997.5859 – year: 2017 ident: 10.1016/j.jcp.2020.109447_br0290 – volume: 96 start-page: 879 year: 2008 ident: 10.1016/j.jcp.2020.109447_br0010 article-title: Gpu computing publication-title: Proc. IEEE doi: 10.1109/JPROC.2008.917757 – year: 2010 ident: 10.1016/j.jcp.2020.109447_br0380 – volume: 59 start-page: 308 year: 1985 ident: 10.1016/j.jcp.2020.109447_br0080 article-title: Application of a fractional-step method to incompressible Navier–Stokes equations publication-title: J. Comput. Phys. doi: 10.1016/0021-9991(85)90148-2 – volume: 45 start-page: 162 issue: 1 year: 2011 ident: 10.1016/j.jcp.2020.109447_br0420 article-title: Calculation by artificial compressibility method and virtual flux method on gpu publication-title: Comput. Fluids doi: 10.1016/j.compfluid.2011.02.005 – year: 2000 ident: 10.1016/j.jcp.2020.109447_br0210 – volume: 32 start-page: 2380 year: 1994 ident: 10.1016/j.jcp.2020.109447_br0410 article-title: Data-parallel lower-upper relaxation method for reacting flows publication-title: AIAA J. doi: 10.2514/3.12303 – volume: 37 start-page: 521 year: 2011 ident: 10.1016/j.jcp.2020.109447_br0020 article-title: Multi-GPU performance of incompressible flow computation by lattice Boltzmann method on GPU cluster publication-title: Parallel Comput. – volume: 229 start-page: 199 year: 2018 ident: 10.1016/j.jcp.2020.109447_br0060 article-title: AFiD-GPU: a versatile Navier—Stokes solver for wall-bounded turbulent flows on GPU clusters publication-title: Comput. Phys. Commun. doi: 10.1016/j.cpc.2018.03.026 – volume: 173 start-page: 195 year: 2018 ident: 10.1016/j.jcp.2020.109447_br0070 article-title: High-performance multi-GPU solver for describing nonlinear acoustic waves in homogeneous thermoviscous media publication-title: Comput. Fluids doi: 10.1016/j.compfluid.2018.03.008 – volume: 15 start-page: 26 year: 2013 ident: 10.1016/j.jcp.2020.109447_br0100 article-title: Large-eddy simulations of turbulent incompressible flows on GPU clusters publication-title: Comput. Sci. Eng. doi: 10.1109/MCSE.2012.37 – year: 2017 ident: 10.1016/j.jcp.2020.109447_br0050 article-title: Unsteady Navier-Stokes computations on GPU architectures – volume: 88 start-page: 764 year: 2013 ident: 10.1016/j.jcp.2020.109447_br0130 article-title: A parallel MPI+OpenMP+OpenCL algorithm for hybrid supercomputations of incompressible flows publication-title: Comput. Fluids doi: 10.1016/j.compfluid.2013.05.021 – year: 2011 ident: 10.1016/j.jcp.2020.109447_br0280 article-title: Computational fluid dynamics using graphics processing units: challenges and opportunities – volume: 30 year: 2018 ident: 10.1016/j.jcp.2020.109447_br0360 article-title: Marginally turbulent couette flow in a spanwise confined passage of square cross section publication-title: Phys. Fluids doi: 10.1063/1.5026947 – volume: 29 start-page: 603 year: 1991 ident: 10.1016/j.jcp.2020.109447_br0160 article-title: Steady and unsteady solutions of the incompressible Navier–Stokes equations publication-title: AIAA J. doi: 10.2514/3.10627 – volume: vol. 67 year: 2011 ident: 10.1016/j.jcp.2020.109447_br0200 article-title: Multigrid techniques. 1984 guide with applications to fluid dynamics – volume: 314 start-page: 414 year: 2016 ident: 10.1016/j.jcp.2020.109447_br0430 article-title: A high-order solver for unsteady incompressible navier–stokes equations using the flux reconstruction method on unstructured grids with implicit dual time stepping publication-title: J. Comput. Phys. doi: 10.1016/j.jcp.2016.03.016 – volume: 92 start-page: 244 year: 2014 ident: 10.1016/j.jcp.2020.109447_br0110 article-title: MPi-CUDA sparse matrix–vector multiplication for the conjugate gradient method with an approximate inverse preconditioner publication-title: Comput. Fluids doi: 10.1016/j.compfluid.2013.10.035 – volume: 123 start-page: 382 year: 2001 ident: 10.1016/j.jcp.2020.109447_br0350 article-title: Direct numerical simulation of a fully developed turbulent channel flow with respect to the reynolds number dependence publication-title: J. Fluids Eng. doi: 10.1115/1.1366680
SSID	ssj0008548
Score	2.4027872
Snippet	A nonlinear multigrid solver for solutions of unsteady three-dimensional incompressible viscous flow working on multi-GPU cluster is developed. The solver...
SourceID	proquest crossref elsevier
SourceType	Aggregation Database Enrichment Source Index Database Publisher
StartPage	109447
SubjectTerms	Artificial compressibility method Clusters Compressibility Computational fluid dynamics Computational physics Computer simulation Dual-time stepping FAS V-cycle scheme Flow simulation Fluid flow Incompressible flow Laminar flow Multi-GPU Navier-Stokes equations Three dimensional flow Viscous flow
Title	A parallel nonlinear multigrid solver for unsteady incompressible flow simulation on multi-GPU cluster
URI	https://dx.doi.org/10.1016/j.jcp.2020.109447 https://www.proquest.com/docview/2447303435
Volume	414
WOSCitedRecordID	wos000536532800008&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText	1
inHoldings	1
isFullTextHit
isPrint
journalDatabaseRights	– providerCode: PRVESC databaseName: Elsevier SD Freedom Collection Journals 2021 customDbUrl: eissn: 1090-2716 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0008548 issn: 0021-9991 databaseCode: AIEXJ dateStart: 19950101 isFulltext: true titleUrlDefault: https://www.sciencedirect.com providerName: Elsevier
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV3da9swEBdZuoe97HusWzf0sKcZlVSWP_RoRrdujFBYCnkzsiwHB9cpdtL0ff_4Tl8OTVnZBoMggpFsc_ezdDr97g6hD6oskkrEKSmiMCasrCgppEhIBKZsyZR2vElTbCKZTtP5nJ-PRj99LMx1k7RtenPDr_6rquEaKFuHzv6FuoebwgX4D0qHFtQO7R8pPgt0Ou-mUU3Q2jwYorO8wUVXaye55kIbduGmNSrWkX-aWW4YsTqQqmpW26CvL11lL32eYMaTL-cXgWw2vaf03jVqpSkS4R2M1m0yWO0_TAHhYF6LVaPqAWqLTmxN2YFgJtrLHanne-0JASuSDRg-2zoPNwh9QaYO3M5vQXesOedM8wE1t_ieljHCbQGvY2Xn5AmfEJrYkEw_aTMbenpnAbC-iOXxUupkpNSky2I2p-deXm19TK1zMJxQmOco7MweoAOaRDwdo4Ps6-n827CgpxGzC7p7N384bmiCew_6nXmzt9Ab62X2FD12GsKZhcszNFLtc_TEbUGwm-D7F6jKsEcPHtCDB_Rgix4M6MEePfg2erBGD96hB8NvQA926HmJLj6fzj6dEVeKg8iQRmvCuGJUcSV4KXVDKzqRMSsFF5ool4LZKVnEQYpVcUKrEvrGKlKSxkJGVVyFr9AY3lq9RjiEHTKVPFGxgAWj5CkroXtalDxUVaTEIZp4CebS5anX5VKa3BMSlzkIPddCz63QD9HHYciVTdJyX2fm1ZI7K9Najzlg6L5hR16Fufva-xxsY1ghQ9hyvPm3u75Fj3bfxhEar7uNeoceyut13XfvHRB_Ab_er1U
linkProvider	Elsevier
openUrl	ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=A+parallel+nonlinear+multigrid+solver+for+unsteady+incompressible+flow+simulation+on+multi-GPU+cluster&rft.jtitle=Journal+of+computational+physics&rft.au=Shi%2C+Xiaolei&rft.au=Agrawal%2C+Tanmay&rft.au=Lin%2C+Chao-An&rft.au=Hwang%2C+Feng-Nan&rft.date=2020-08-01&rft.pub=Elsevier+Inc&rft.issn=0021-9991&rft.eissn=1090-2716&rft.volume=414&rft_id=info:doi/10.1016%2Fj.jcp.2020.109447&rft.externalDocID=S0021999120302217
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0021-9991&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0021-9991&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0021-9991&client=summon