{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T04:42:20Z","timestamp":1777610540876,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":37,"publisher":"ACM","license":[{"start":{"date-parts":[[2011,11,12]],"date-time":"2011-11-12T00:00:00Z","timestamp":1321056000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2011,11,12]]},"DOI":"10.1145\/2063384.2063389","type":"proceedings-article","created":{"date-parts":[[2011,11,8]],"date-time":"2011-11-08T13:32:09Z","timestamp":1320759129000},"page":"1-12","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":30,"title":["Petaflop biofluidics simulations on a two million-core system"],"prefix":"10.1145","author":[{"given":"Massimo","family":"Bernaschi","sequence":"first","affiliation":[{"name":"CNR-IAC, Istituto Applicazioni, Calcolo, Consiglio Nazionale delle, Ricerche, Rome, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mauro","family":"Bisson","sequence":"additional","affiliation":[{"name":"Harvard University, Cambridge, MA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Toshio","family":"Endo","sequence":"additional","affiliation":[{"name":"Tokyo Institute of Technology, Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Satoshi","family":"Matsuoka","sequence":"additional","affiliation":[{"name":"Tokyo Institute of Technology, Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Massimiliano","family":"Fatica","sequence":"additional","affiliation":[{"name":"Nvidia Corp., Santa Clara, CA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Simone","family":"Melchionna","sequence":"additional","affiliation":[{"name":"CNR-IPCF, Istituto Processi, Chimico-Fisici, Consiglio Nazionale delle, Ricerche, Rome, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2011,11,12]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/5992.947108"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1137\/S0036142900369714"},{"key":"e_1_3_2_1_3_1","volume":"367","author":"Grinberg L.","year":"1896","unstructured":"L. Grinberg , T. Anor , E. Cheever , , Phil. Trans. Royal Soc. A , 367 1896 2371 (2009) L. Grinberg, T. Anor, E. Cheever, et al., Phil. Trans. Royal Soc. A, 367 1896 2371 (2009)","journal-title":"Phil. Trans. Royal Soc. A"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10955-005-8415-x"},{"key":"e_1_3_2_1_5_1","volume":"366","author":"Evans D. J. W.","unstructured":"D. J. W. Evans , P. V. Lawford , J. Gunn , D. Walker , D. R. Hose , R. H. Smallwood , B. Chopard , M. Krafczyk , J. Bernsdorf , A. Hoekstra , Phil. Trans. R. Soc. A 366 , 3343 (2008) D. J. W. Evans, P. V. Lawford, J. Gunn, D. Walker, D. R. Hose, R. H. Smallwood, B. Chopard, M. Krafczyk, J. Bernsdorf, A. Hoekstra, Phil. Trans. R. Soc. A 366, 3343 (2008)","journal-title":"Phil. Trans. R. Soc. A"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.0608546103"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.0811484106"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcp.2008.11.036"},{"key":"e_1_3_2_1_9_1","unstructured":"Scalable simulations up to 14 000 red blood cells were previously obtained with either boundary integral {10} or Lattice Boltzmann methods {11} on up to 64 thousands BlueGene\/P cores. More recently scalable simulations of blood flows were performed to scale up to 256 GPUs and up to 200 000 cores of the Cray Jaguar system {12}. This achievement used a very accurate representations of blood mostly targeting capillaries but with approximations that render the methods inapplicable to realistic vessel geometries and physiological flow conditions of high Reynolds number. Scalable simulations up to 14 000 red blood cells were previously obtained with either boundary integral {10} or Lattice Boltzmann methods {11} on up to 64 thousands BlueGene\/P cores. More recently scalable simulations of blood flows were performed to scale up to 256 GPUs and up to 200 000 cores of the Cray Jaguar system {12}. This achievement used a very accurate representations of blood mostly targeting capillaries but with approximations that render the methods inapplicable to realistic vessel geometries and physiological flow conditions of high Reynolds number."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1006\/jcph.1999.6384"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cpc.2010.02.005"},{"key":"e_1_3_2_1_12_1","volume-title":"Proceedings of Supercomputing 2010","author":"Rahimian A.","year":"2010","unstructured":"A. Rahimian , Proceedings of Supercomputing 2010 , New Orleans , 2010 . A. Rahimian, et al. Proceedings of Supercomputing 2010, New Orleans, 2010."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cpc.2009.04.001"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cpc.2009.10.017"},{"key":"e_1_3_2_1_15_1","volume-title":"Proc. IEEE\/ACM, SC2002 Conf. IEEE Press","author":"Phillips J. C.","year":"2002","unstructured":"J. C. Phillips , G. Zheng , S. Kumar , and L. V. Kal . Proc. IEEE\/ACM, SC2002 Conf. IEEE Press , 2002 . Technical Paper 277. J. C. Phillips, G. Zheng, S. Kumar, and L. V. Kal. Proc. IEEE\/ACM, SC2002 Conf. IEEE Press, 2002. Technical Paper 277."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.75.066707"},{"key":"e_1_3_2_1_17_1","volume-title":"DOI: 10.1002\/mats.201100012","author":"Melchionna S.","year":"2011","unstructured":"S. Melchionna , Macromol. Theory Sim ., DOI: 10.1002\/mats.201100012 ( 2011 ). 10.1002\/mats.201100012 S. Melchionna, Macromol. Theory Sim., DOI: 10.1002\/mats.201100012 (2011)."},{"key":"e_1_3_2_1_18_1","unstructured":"http:\/\/www.labri.fr\/perso\/pelegrin\/scotch\/ http:\/\/www.labri.fr\/perso\/pelegrin\/scotch\/"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1063\/1.869307"},{"key":"e_1_3_2_1_20_1","unstructured":"http:\/\/glaros.dtc.umn.edu\/gkhome\/views\/metis\/ http:\/\/glaros.dtc.umn.edu\/gkhome\/views\/metis\/"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1016\/0370-1573(92)90090-M"},{"key":"e_1_3_2_1_22_1","volume":"74","author":"Gay J. G.","unstructured":"J. G. Gay , B. J. Berne , J. Chem. Phys , 74 , 3316 (1981) J. G. Gay, B. J. Berne, J. Chem. Phys, 74, 3316 (1981)","journal-title":"J. Chem. Phys"},{"key":"e_1_3_2_1_23_1","unstructured":"http:\/\/www-03.ibm.com\/systems\/deepcomputing\/bluegene\/ http:\/\/www-03.ibm.com\/systems\/deepcomputing\/bluegene\/"},{"key":"e_1_3_2_1_24_1","volume-title":"DOI: 10.1002\/cpe.1466","author":"Bernaschi M.","year":"2009","unstructured":"M. Bernaschi , M. Fatica , S. Melchionna , S. Succi and E. Kaxiras , Concurrency and Computation: Practice and Experience , DOI: 10.1002\/cpe.1466 ( 2009 ). 10.1002\/cpe.1466 M. Bernaschi, M. Fatica, S. Melchionna, S. Succi and E. Kaxiras, Concurrency and Computation: Practice and Experience, DOI: 10.1002\/cpe.1466 (2009)."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cpc.2008.02.013"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1063\/1.474310"},{"key":"e_1_3_2_1_27_1","unstructured":"C. Chambreau J. Vetter \"mpiP: Lightweight Scalable MPI Profiling\" http:\/\/mpip.sourceforge.net\/ C. Chambreau J. Vetter \"mpiP: Lightweight Scalable MPI Profiling\" http:\/\/mpip.sourceforge.net\/"},{"key":"e_1_3_2_1_28_1","volume-title":"International Conference on Parallel and Distributed Computing Systems","author":"London K.","year":"2001","unstructured":"K. London , J. Dongarra , S. Moore , P. Mucci , K. Seymour , T. Spencer , International Conference on Parallel and Distributed Computing Systems , Dallas, TX , August 8-10, 2001 . K. London, J. Dongarra, S. Moore, P. Mucci, K. Seymour, T. Spencer, International Conference on Parallel and Distributed Computing Systems, Dallas, TX, August 8-10, 2001."},{"key":"e_1_3_2_1_29_1","unstructured":"http:\/\/oprofile.sourceforge.net. http:\/\/oprofile.sourceforge.net."},{"key":"e_1_3_2_1_30_1","volume-title":"Proceedings of Supercomputing 2010","author":"Peters A.","year":"2010","unstructured":"A. Peters , Proceedings of Supercomputing 2010 , New Orleans , 2010 . A. Peters et al., Proceedings of Supercomputing 2010, New Orleans, 2010."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.4208\/cicp.140810.021210a"},{"key":"e_1_3_2_1_32_1","volume-title":"Proceedings of International Conference for Mesoscopic Methods in Engineering and Science ICMMES07","author":"T\u00f6lke J.","year":"2007","unstructured":"J. T\u00f6lke , M. Krafczyk , In Proceedings of International Conference for Mesoscopic Methods in Engineering and Science ICMMES07 , Munich , 2007 . J. T\u00f6lke, M. Krafczyk, In Proceedings of International Conference for Mesoscopic Methods in Engineering and Science ICMMES07, Munich, 2007."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jnnfm.2004.07.017"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcp.2011.02.021"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"crossref","DOI":"10.1093\/oso\/9780198503989.001.0001","volume-title":"The Lattice Boltzmann Equation for Fluid Dynamics and Beyond","author":"Succi S.","year":"2001","unstructured":"S. Succi , The Lattice Boltzmann Equation for Fluid Dynamics and Beyond , Oxford University Press , USA , 2001 S. Succi, The Lattice Boltzmann Equation for Fluid Dynamics and Beyond, Oxford University Press, USA, 2001"},{"key":"e_1_3_2_1_36_1","unstructured":"The global geometry of the problem used for the present simulations is obtained from CT scans of the coronary arterial system of a real patient. Data acquisition was performed by a 320 x 0.5 mm CT scanner (Toshiba) and subsequently segmented into a stack of two-dimensional contours at a nominal resolution of 0.5 mm. The slice contours each consisting of 256 points are oversampled along the axial distance down to a slice-to-slice separation of 0.0125 mm and further smoothed out by appropriate interpolators. The resulting multi-branched geometrical structure is finally mapped into the Cartesian LB lattice ready for the simulation. Full details can be found in {14}. The global geometry of the problem used for the present simulations is obtained from CT scans of the coronary arterial system of a real patient. Data acquisition was performed by a 320 x 0.5 mm CT scanner (Toshiba) and subsequently segmented into a stack of two-dimensional contours at a nominal resolution of 0.5 mm. The slice contours each consisting of 256 points are oversampled along the axial distance down to a slice-to-slice separation of 0.0125 mm and further smoothed out by appropriate interpolators. The resulting multi-branched geometrical structure is finally mapped into the Cartesian LB lattice ready for the simulation. Full details can be found in {14}."},{"key":"e_1_3_2_1_37_1","unstructured":"Fluid boundary conditions are set up as follows. At the inlet a uniform flow profile with prescribed velocity is imposed and at the outlet ports a zero pressure difference from the inlet is maintained. The flow-pressure inflow\/outflow conditions are implemented via the Zou-He method to set up the LB populations in the proper way {19}. At rigid walls a standard mid-way bounce-back rule is applied to impose no-slip flow conditions. The fluid flow is initialized with zero speed and constant density across the entire domain. Particles are seeded at random positions and orientations and with null linear and angular velocity. In flow conditions RBC that exit from the outlet ports are reinjected in the inlet port in order to maintain a constant total hematocrit. The injected RBC have velocity given by the imposed inlet velocity random orientation and zero angular velocity. The RBCs are repelled by the wall via a GB pairwise potential acting between a RBC ellipsoid and a spherical particle positioned on a wall mesh node. Fluid boundary conditions are set up as follows. At the inlet a uniform flow profile with prescribed velocity is imposed and at the outlet ports a zero pressure difference from the inlet is maintained. The flow-pressure inflow\/outflow conditions are implemented via the Zou-He method to set up the LB populations in the proper way {19}. At rigid walls a standard mid-way bounce-back rule is applied to impose no-slip flow conditions. The fluid flow is initialized with zero speed and constant density across the entire domain. Particles are seeded at random positions and orientations and with null linear and angular velocity. In flow conditions RBC that exit from the outlet ports are reinjected in the inlet port in order to maintain a constant total hematocrit. The injected RBC have velocity given by the imposed inlet velocity random orientation and zero angular velocity. The RBCs are repelled by the wall via a GB pairwise potential acting between a RBC ellipsoid and a spherical particle positioned on a wall mesh node."}],"event":{"name":"SC '11: International Conference for High Performance Computing, Networking, Storage and Analysis","location":"Seattle Washington","acronym":"SC '11","sponsor":["SIGARCH ACM Special Interest Group on Computer Architecture","IEEE-CS Computer Society"]},"container-title":["Proceedings of 2011 International Conference for High Performance Computing, Networking, Storage and Analysis"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2063384.2063389","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/2063384.2063389","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T10:06:07Z","timestamp":1750241167000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2063384.2063389"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2011,11,12]]},"references-count":37,"alternative-id":["10.1145\/2063384.2063389","10.1145\/2063384"],"URL":"https:\/\/doi.org\/10.1145\/2063384.2063389","relation":{},"subject":[],"published":{"date-parts":[[2011,11,12]]},"assertion":[{"value":"2011-11-12","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}