{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T17:43:15Z","timestamp":1781545395837,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":55,"publisher":"ACM","license":[{"start":{"date-parts":[[2020,6,29]],"date-time":"2020-06-29T00:00:00Z","timestamp":1593388800000},"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":[[2020,6,29]]},"DOI":"10.1145\/3394277.3401846","type":"proceedings-article","created":{"date-parts":[[2020,6,18]],"date-time":"2020-06-18T23:03:38Z","timestamp":1592521418000},"page":"1-11","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":32,"title":["Extreme-Scale Task-Based Cholesky Factorization Toward Climate and Weather Prediction Applications"],"prefix":"10.1145","author":[{"given":"Qinglei","family":"Cao","sequence":"first","affiliation":[{"name":"University of Tennessee"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Pei","sequence":"additional","affiliation":[{"name":"University of Tennessee"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kadir","family":"Akbudak","sequence":"additional","affiliation":[{"name":"King Abdullah University of Science and Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aleksandr","family":"Mikhalev","sequence":"additional","affiliation":[{"name":"King Abdullah University of Science and Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"George","family":"Bosilca","sequence":"additional","affiliation":[{"name":"University of Tennessee"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hatem","family":"Ltaief","sequence":"additional","affiliation":[{"name":"King Abdullah University of Science and Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"David","family":"Keyes","sequence":"additional","affiliation":[{"name":"King Abdullah University of Science and Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jack","family":"Dongarra","sequence":"additional","affiliation":[{"name":"University of Tennessee, the Oak, Ridge National Laboratory and the University of Manchester, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2020,6,29]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2018.2850749"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"crossref","unstructured":"S. Abdulah H. Ltaief Y. Sun M. G. Genton and D. E. Keyes. 2018. Parallel Approximation of the Maximum Likelihood Estimation for the Prediction of Large-Scale Geostatistics Simulations. In 2018 IEEE International Conference on Cluster Computing (CLUSTER). IEEE 98--108.  S. Abdulah H. Ltaief Y. Sun M. G. Genton and D. E. Keyes. 2018. Parallel Approximation of the Maximum Likelihood Estimation for the Prediction of Large-Scale Geostatistics Simulations. In 2018 IEEE International Conference on Cluster Computing (CLUSTER). IEEE 98--108.","DOI":"10.1109\/CLUSTER.2018.00089"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"crossref","unstructured":"E. Agullo O. Aumage M. Faverge N. Furmento F. Pruvost M. Sergent and S. Thibault. 2017. Achieving High Performance on Supercomputers with a Sequential Task-based Programming Model. IEEE Transactions on Parallel and Distributed Systems (2017).  E. Agullo O. Aumage M. Faverge N. Furmento F. Pruvost M. Sergent and S. Thibault. 2017. Achieving High Performance on Supercomputers with a Sequential Task-based Programming Model. IEEE Transactions on Parallel and Distributed Systems (2017).","DOI":"10.1109\/TPDS.2017.2766064"},{"key":"e_1_3_2_1_4_1","volume-title":"Numerical Linear Algebra on Emerging Architectures: The PLASMA and MAGMA Projects. Journal of Physics: Conference Series 180","author":"Agullo E.","year":"2009","unstructured":"E. Agullo , J. Demmel , J. Dongarra , B. Hadri , J. Kurzak , J. Langou , H. Ltaief , P. Luszczek , and S. Tomov . 2009 . Numerical Linear Algebra on Emerging Architectures: The PLASMA and MAGMA Projects. Journal of Physics: Conference Series 180 ( 2009 ). E. Agullo, J. Demmel, J. Dongarra, B. Hadri, J. Kurzak, J. Langou, H. Ltaief, P. Luszczek, and S. Tomov. 2009. Numerical Linear Algebra on Emerging Architectures: The PLASMA and MAGMA Projects. Journal of Physics: Conference Series 180 (2009)."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"crossref","unstructured":"K. Akbudak H. Ltaief A. Mikhalev A. Charara A. Esposito and D. E. Keyes. 2018. Exploiting Data Sparsity for Large-Scale Matrix Computations. In Euro-Par 2018: Parallel Processing M. Aldinucci L. Padovani and M. Torquati (Eds.). Springer International Publishing Cham 721--734.  K. Akbudak H. Ltaief A. Mikhalev A. Charara A. Esposito and D. E. Keyes. 2018. Exploiting Data Sparsity for Large-Scale Matrix Computations. In Euro-Par 2018: Parallel Processing M. Aldinucci L. Padovani and M. Torquati (Eds.). Springer International Publishing Cham 721--734.","DOI":"10.1007\/978-3-319-96983-1_51"},{"key":"e_1_3_2_1_6_1","volume-title":"Tile Low Rank Cholesky Factorization for Climate\/Weather Modeling Applications on Manycore Architectures. In 32nd International Conference on High Performance","author":"Akbudak K.","unstructured":"K. Akbudak , H. Ltaief , A. Mikhalev , and D. Keyes . 2017 . Tile Low Rank Cholesky Factorization for Climate\/Weather Modeling Applications on Manycore Architectures. In 32nd International Conference on High Performance , Frankfurt, Germany. Springer International Publishing, 22--40. K. Akbudak, H. Ltaief, A. Mikhalev, and D. Keyes. 2017. Tile Low Rank Cholesky Factorization for Climate\/Weather Modeling Applications on Manycore Architectures. In 32nd International Conference on High Performance, Frankfurt, Germany. Springer International Publishing, 22--40."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10915-013-9714-z"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1137\/120903476"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3242094"},{"key":"e_1_3_2_1_10_1","volume-title":"MUMPS: A General Purpose Distributed Memory Sparse Solver","author":"Amestoy P. R.","year":"2001","unstructured":"P. R. Amestoy , I. S. Duff , J.-Y. L'Excellent , and J. Koster . 2001 . MUMPS: A General Purpose Distributed Memory Sparse Solver . Springer Berlin Heidelberg , Berlin, Heidelberg , 121--130. https:\/\/doi.org\/10.1007\/3-540-70734-4_16 10.1007\/3-540-70734-4_16 P. R. Amestoy, I. S. Duff, J.-Y. L'Excellent, and J. Koster. 2001. MUMPS: A General Purpose Distributed Memory Sparse Solver. Springer Berlin Heidelberg, Berlin, Heidelberg, 121--130. https:\/\/doi.org\/10.1007\/3-540-70734-4_16"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcp.2015.10.012"},{"key":"e_1_3_2_1_12_1","volume-title":"LAPACK User's Guide","author":"Anderson E.","unstructured":"E. Anderson , Z. Bai , C. H. Bischof , L. Susan Blackford , J. W. Demmel , J.J. Dongarra , J. J. Du Croz , A. Greenbaum , S. Hammarling , A. McKenney , and D. C Sorensen . 1999. LAPACK User's Guide ( 3 rd ed.). SIAM , Philadelphia . E. Anderson, Z. Bai, C. H. Bischof, L. Susan Blackford, J. W. Demmel, J.J. Dongarra, J. J. Du Croz, A. Greenbaum, S. Hammarling, A. McKenney, and D. C Sorensen. 1999. LAPACK User's Guide (3rd ed.). SIAM, Philadelphia.","edition":"3"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1002\/cpe.1631"},{"key":"e_1_3_2_1_14_1","volume-title":"Legion: Expressing Locality and Independence with Logical Regions. In International Conference for High Performance Computing, Networking, Storage and Analysis, SC.","author":"Bauer M.","unstructured":"M. Bauer , S. Treichler , E. Slaughter , and A. Aiken . 2012 . Legion: Expressing Locality and Independence with Logical Regions. In International Conference for High Performance Computing, Networking, Storage and Analysis, SC. M. Bauer, S. Treichler, E. Slaughter, and A. Aiken. 2012. Legion: Expressing Locality and Independence with Logical Regions. In International Conference for High Performance Computing, Networking, Storage and Analysis, SC."},{"key":"e_1_3_2_1_15_1","series-title":"Lecture Notes in Computational Science and Engineering","volume-title":"Hierarchical Matrices: A Means to Efficiently Solve Elliptic Boundary Value Problems","author":"Bebendorf M.","unstructured":"M. Bebendorf . 2008. Hierarchical Matrices: A Means to Efficiently Solve Elliptic Boundary Value Problems . Lecture Notes in Computational Science and Engineering , Vol. 63 . Springer . 269 pages. M. Bebendorf. 2008. Hierarchical Matrices: A Means to Efficiently Solve Elliptic Boundary Value Problems. Lecture Notes in Computational Science and Engineering, Vol. 63. Springer. 269 pages."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/1131322.1131332"},{"key":"#cr-split#-e_1_3_2_1_17_1.1","doi-asserted-by":"crossref","unstructured":"L.S. Blackford J. Choi A. Cleary E.F. D'Azevedo J.W. Demmel I.S. Dhillon J.J. Dongarra S. Hammarling G. Henry A. Petitet K. Stanley D.W. Walker and R.C. Whaley. 1997. ScaLAPACK Users' Guide. Society for Industrial and Applied Mathematics Philadelphia. https:\/\/doi.org\/10.1137\/1.9780898719642 10.1137\/1.9780898719642","DOI":"10.1137\/1.9780898719642"},{"key":"#cr-split#-e_1_3_2_1_17_1.2","doi-asserted-by":"crossref","unstructured":"L.S. Blackford J. Choi A. Cleary E.F. D'Azevedo J.W. Demmel I.S. Dhillon J.J. Dongarra S. Hammarling G. Henry A. Petitet K. Stanley D.W. Walker and R.C. Whaley. 1997. ScaLAPACK Users' Guide. Society for Industrial and Applied Mathematics Philadelphia. https:\/\/doi.org\/10.1137\/1.9780898719642","DOI":"10.1137\/1.9780898719642"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.5555\/889664"},{"key":"e_1_3_2_1_19_1","volume-title":"Flexible Development of Dense Linear Algebra Algorithms on Massively Parallel Architectures with DPLASMA. In IPDPS Workshops. IEEE, 1432--1441","author":"Bosilca G.","unstructured":"G. Bosilca , A. Bouteiller , A. Danalis , M. Faverge , A. Haidar , T. H\u00e9rault , J. Kurzak , J. Langou , P. Lemarinier , H. Ltaief , P. Luszczek , A. YarKhan , and J. Dongarra . 2011 . Flexible Development of Dense Linear Algebra Algorithms on Massively Parallel Architectures with DPLASMA. In IPDPS Workshops. IEEE, 1432--1441 . http:\/\/ieeexplore.ieee.org\/xpl\/mostRecentIssue.jsp?punumber=6008655 G. Bosilca, A. Bouteiller, A. Danalis, M. Faverge, A. Haidar, T. H\u00e9rault, J. Kurzak, J. Langou, P. Lemarinier, H. Ltaief, P. Luszczek, A. YarKhan, and J. Dongarra. 2011. Flexible Development of Dense Linear Algebra Algorithms on Massively Parallel Architectures with DPLASMA. In IPDPS Workshops. IEEE, 1432--1441. http:\/\/ieeexplore.ieee.org\/xpl\/mostRecentIssue.jsp?punumber=6008655"},{"key":"e_1_3_2_1_20_1","first-page":"1","article-title":"PaRSEC: A Programming Paradigm Exploiting Heterogeneity for Enhancing Scalability","volume":"99","author":"Bosilca G.","year":"2013","unstructured":"G. Bosilca , A. Bouteiller , A. Danalis , M. Faverge , T. Herault , and J. Dongarra . 2013 . PaRSEC: A Programming Paradigm Exploiting Heterogeneity for Enhancing Scalability . Computing in Science and Engineering 99 (2013), 1 . G. Bosilca, A. Bouteiller, A. Danalis, M. Faverge, T. Herault, and J. Dongarra. 2013. PaRSEC: A Programming Paradigm Exploiting Heterogeneity for Enhancing Scalability. Computing in Science and Engineering 99 (2013), 1.","journal-title":"Computing in Science and Engineering"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/MCSE.2013.98"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1016\/0010-4655(91)90151-A"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"crossref","unstructured":"Q. Cao Y. Pei T. Herault K. Akbudak A. Mikhalev G. Bosilca H. Ltaief D. Keyes and J. Dongarra. 2019. Performance Analysis of Tile Low-Rank Cholesky Factorization Using PaRSEC Instrumentation Tools. In 2019 IEEE\/ACM International Workshop on Programming and Performance Visualization Tools (ProTools) at SC19. IEEE 25--32.  Q. Cao Y. Pei T. Herault K. Akbudak A. Mikhalev G. Bosilca H. Ltaief D. Keyes and J. Dongarra. 2019. Performance Analysis of Tile Low-Rank Cholesky Factorization Using PaRSEC Instrumentation Tools. In 2019 IEEE\/ACM International Workshop on Programming and Performance Visualization Tools (ProTools) at SC19. IEEE 25--32.","DOI":"10.1109\/ProTools49597.2019.00009"},{"key":"e_1_3_2_1_24_1","volume-title":"SPAA '07: Proceedings of the nineteenth annual ACM symposium on Parallel algorithms and architectures","author":"Chan E.","unstructured":"E. Chan , E.S. Quintana-Ort\u00ed , G. Quintana-Ort\u00ed , and R. van de Geijn . 2007. Super-matrix Out-of-order Scheduling of Matrix Operations for SMP And Multi-core Architectures . In SPAA '07: Proceedings of the nineteenth annual ACM symposium on Parallel algorithms and architectures . ACM , New York, NY, USA , 116--125. https:\/\/doi.org\/10.1145\/1248377.1248397 10.1145\/1248377.1248397 E. Chan, E.S. Quintana-Ort\u00ed, G. Quintana-Ort\u00ed, and R. van de Geijn. 2007. Super-matrix Out-of-order Scheduling of Matrix Operations for SMP And Multi-core Architectures. In SPAA '07: Proceedings of the nineteenth annual ACM symposium on Parallel algorithms and architectures. ACM, New York, NY, USA, 116--125. https:\/\/doi.org\/10.1145\/1248377.1248397"},{"key":"e_1_3_2_1_25_1","volume-title":"Proceedings of WOLFHPC 2014: 4th International Workshop on DSLs and High-Level Frameworks for High Performance Computing, 21--30","author":"Danalis A.","year":"2014","unstructured":"A. Danalis , G. Bosilca , A. Bouteiller , T. Herault , and J. Dongarra . 2014. PTG: An Abstraction for Unhindered Parallelism . Proceedings of WOLFHPC 2014: 4th International Workshop on DSLs and High-Level Frameworks for High Performance Computing, 21--30 . https:\/\/doi.org\/10.1109\/WOLFHPC. 2014 .8 10.1109\/WOLFHPC.2014.8 A. Danalis, G. Bosilca, A. Bouteiller, T. Herault, and J. Dongarra. 2014. PTG: An Abstraction for Unhindered Parallelism. Proceedings of WOLFHPC 2014: 4th International Workshop on DSLs and High-Level Frameworks for High Performance Computing, 21--30. https:\/\/doi.org\/10.1109\/WOLFHPC.2014.8"},{"key":"e_1_3_2_1_26_1","volume-title":"Proceedings - 24th Euromicro International Conference on Parallel, Distributed, and Network-Based Processing, PDP 2016, 364--368","author":"Dokulil J.","year":"2016","unstructured":"J. Dokulil , M. Sandrieser , and S. Benkner . 2016. Implementing the Open Community Runtime for Shared-Memory and Distributed-Memory Systems . Proceedings - 24th Euromicro International Conference on Parallel, Distributed, and Network-Based Processing, PDP 2016, 364--368 . https:\/\/doi.org\/10.1109\/PDP. 2016 .81 10.1109\/PDP.2016.81 J. Dokulil, M. Sandrieser, and S. Benkner. 2016. Implementing the Open Community Runtime for Shared-Memory and Distributed-Memory Systems. Proceedings - 24th Euromicro International Conference on Parallel, Distributed, and Network-Based Processing, PDP 2016, 364--368. https:\/\/doi.org\/10.1109\/PDP.2016.81"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10766-009-0101-1"},{"key":"e_1_3_2_1_28_1","volume-title":"Impact of Noise on Scaling of Collectives: An Empirical Evaluation. In HiPC'06: Proceedings of International Conference on High Performance Computing (LNCS), Springer (Ed.)","volume":"4297","author":"Garg R.","unstructured":"R. Garg and P. De . 2006 . Impact of Noise on Scaling of Collectives: An Empirical Evaluation. In HiPC'06: Proceedings of International Conference on High Performance Computing (LNCS), Springer (Ed.) , Vol. 4297 . 460--471. R. Garg and P. De. 2006. Impact of Noise on Scaling of Collectives: An Empirical Evaluation. In HiPC'06: Proceedings of International Conference on High Performance Computing (LNCS), Springer (Ed.), Vol. 4297. 460--471."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1080\/10618600.2019.1652616"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1016\/0021-9991(87)90140-9"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1137\/090771806"},{"key":"e_1_3_2_1_32_1","volume-title":"Proceedings of the 8th Workshop on Latest Advances in Scalable Algorithms for Large-Scale Systems (ScalA '17)","author":"Hoque R.","unstructured":"R. Hoque , T. Herault , G. Bosilca , and J. Dongarra . 2017. Dynamic Task Discovery in PaRSEC: A Data-flow Task-based Runtime . In Proceedings of the 8th Workshop on Latest Advances in Scalable Algorithms for Large-Scale Systems (ScalA '17) . ACM, New York, NY, USA, Article 6, 8 pages. https:\/\/doi.org\/10.1145\/3148226.3148233 10.1145\/3148226.3148233 R. Hoque, T. Herault, G. Bosilca, and J. Dongarra. 2017. Dynamic Task Discovery in PaRSEC: A Data-flow Task-based Runtime. In Proceedings of the 8th Workshop on Latest Advances in Scalable Algorithms for Large-Scale Systems (ScalA '17). ACM, New York, NY, USA, Article 6, 8 pages. https:\/\/doi.org\/10.1145\/3148226.3148233"},{"key":"e_1_3_2_1_33_1","unstructured":"H. Jagode A. Danalis and J. Dongarra. 2017. Accelerating NWChem Coupled Cluster through Dataflow-Based Execution. The International Journal of High Performance Computing Applications (01--2017 2017) 1--13.  H. Jagode A. Danalis and J. Dongarra. 2017. Accelerating NWChem Coupled Cluster through Dataflow-Based Execution. The International Journal of High Performance Computing Applications (01--2017 2017) 1--13."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00791-014-0226-7"},{"key":"e_1_3_2_1_35_1","volume-title":"IEEE International Parallel & Distributed Processing Symposium Workshops (IPDPSW). 29--38","author":"Lacoste X.","year":"2014","unstructured":"X. Lacoste , M. Faverge , G. Bosilca , P. Ramet , and S. Thibault . 2014. Taking Advantage of Hybrid Systems for Sparse Direct Solvers via Task-Based Runtimes . In IEEE International Parallel & Distributed Processing Symposium Workshops (IPDPSW). 29--38 . https:\/\/doi.org\/10.1109\/IPDPSW. 2014 .9 10.1109\/IPDPSW.2014.9 X. Lacoste, M. Faverge, G. Bosilca, P. Ramet, and S. Thibault. 2014. Taking Advantage of Hybrid Systems for Sparse Direct Solvers via Task-Based Runtimes. In IEEE International Parallel & Distributed Processing Symposium Workshops (IPDPSW). 29--38. https:\/\/doi.org\/10.1109\/IPDPSW.2014.9"},{"key":"e_1_3_2_1_36_1","volume-title":"Real-Time Massively Distributed Multi-object Adaptive Optics Simulations for the European Extremely Large Telescope. In IEEE International Parallel and Distributed Processing Symposium (IPDPS). 75--84","author":"Ltaief H.","unstructured":"H. Ltaief , A. Charara , D. Gratadour , N. Doucet , B. Hadri , E. Gendron , S. Feki , and D. Keyes . 2018 . Real-Time Massively Distributed Multi-object Adaptive Optics Simulations for the European Extremely Large Telescope. In IEEE International Parallel and Distributed Processing Symposium (IPDPS). 75--84 . H. Ltaief, A. Charara, D. Gratadour, N. Doucet, B. Hadri, E. Gendron, S. Feki, and D. Keyes. 2018. Real-Time Massively Distributed Multi-object Adaptive Optics Simulations for the European Extremely Large Telescope. In IEEE International Parallel and Distributed Processing Symposium (IPDPS). 75--84."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2017.05.164"},{"key":"e_1_3_2_1_39_1","volume-title":"A Computer Oriented Geodetic Data Base and a New Technique in File Sequencing","author":"Morton G.M.","unstructured":"G.M. Morton . 1966. A Computer Oriented Geodetic Data Base and a New Technique in File Sequencing . International Business Machines Company , New York . G.M. Morton. 1966. A Computer Oriented Geodetic Data Base and a New Technique in File Sequencing. International Business Machines Company, New York."},{"key":"e_1_3_2_1_40_1","unstructured":"OpenMP. 2013. OpenMP 4.0 Complete Specifications. http:\/\/www.openmp.org\/wp-content\/uploads\/OpenMP4.0.0.pdf  OpenMP. 2013. OpenMP 4.0 Complete Specifications. http:\/\/www.openmp.org\/wp-content\/uploads\/OpenMP4.0.0.pdf"},{"key":"e_1_3_2_1_41_1","volume-title":"Horizons of Quantum Chemistry","author":"Parr R.G.","unstructured":"R.G. Parr . 1980. Density Functional Theory of Atoms and Molecules . In Horizons of Quantum Chemistry , Kenichi Fukui and Bernard Pullman (Eds.). Springer Netherlands , Dordrecht , 5--15. R.G. Parr. 1980. Density Functional Theory of Atoms and Molecules. In Horizons of Quantum Chemistry, Kenichi Fukui and Bernard Pullman (Eds.). Springer Netherlands, Dordrecht, 5--15."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1007\/BF01199438"},{"key":"e_1_3_2_1_43_1","volume-title":"PAW-ATM Workshop at SC19","author":"Pei Y.","unstructured":"Y. Pei , G. Bosilca , I. Yamazaki , A. Ida , and J. Dongarra . 2019. Evaluation of Programming Models to Address Load Imbalance on Distributed Multi-Core CPUs: A Case Study with Block Low-Rank Factorization . In PAW-ATM Workshop at SC19 . ACM, ACM, Denver, CO. Y. Pei, G. Bosilca, I. Yamazaki, A. Ida, and J. Dongarra. 2019. Evaluation of Programming Models to Address Load Imbalance on Distributed Multi-Core CPUs: A Case Study with Block Low-Rank Factorization. In PAW-ATM Workshop at SC19. ACM, ACM, Denver, CO."},{"key":"e_1_3_2_1_44_1","volume-title":"Intel Threading Building Blocks Outfitting C++ for Multi-core Processor Parallelism","author":"Reinders J.","unstructured":"J. Reinders . 2010. Intel Threading Building Blocks Outfitting C++ for Multi-core Processor Parallelism . O'Reilly Media . J. Reinders. 2010. Intel Threading Building Blocks Outfitting C++ for Multi-core Processor Parallelism. O'Reilly Media."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/2930660"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.spasta.2013.06.003"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1080\/10618600.2014.975230"},{"key":"e_1_3_2_1_48_1","volume-title":"Proc. 6th Swedish Workshop on Multi-Core Computing","author":"Tillenius M.","unstructured":"M. Tillenius , E. Larsson , E. Lehto , and N. Flyer . 2013. A Task Parallel Implementation of a Scattered Node Stencil-based Solver for the Shallow Water Equations . In Proc. 6th Swedish Workshop on Multi-Core Computing . Halmstad University, 33--36. M. Tillenius, E. Larsson, E. Lehto, and N. Flyer. 2013. A Task Parallel Implementation of a Scattered Node Stencil-based Solver for the Shallow Water Equations. In Proc. 6th Swedish Workshop on Multi-Core Computing. Halmstad University, 33--36."},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"crossref","unstructured":"S.J. Treichler. 2014. Realm: Performance Portability through Composable Asynchrony. Ph.D. Dissertation. Stanford University.  S.J. Treichler. 2014. Realm: Performance Portability through Composable Asynchrony. Ph.D. Dissertation. Stanford University.","DOI":"10.1145\/2628071.2628084"},{"key":"e_1_3_2_1_50_1","volume-title":"ICS '05: Proceedings of the 19th Annual International Conference on Supercomputing. ACM Press","author":"Tsafrir D.","unstructured":"D. Tsafrir , Y. Etsion , D.G. Feitelson , and S. Kirkpatrick . 2005. System Noise, OS Clock Ticks, and Fine-grained Parallel Applications . In ICS '05: Proceedings of the 19th Annual International Conference on Supercomputing. ACM Press , New York, NY, USA, 303--312. D. Tsafrir, Y. Etsion, D.G. Feitelson, and S. Kirkpatrick. 2005. System Noise, OS Clock Ticks, and Fine-grained Parallel Applications. In ICS '05: Proceedings of the 19th Annual International Conference on Supercomputing. ACM Press, New York, NY, USA, 303--312."},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1007\/BF02575706"},{"key":"e_1_3_2_1_52_1","volume-title":"Proceedings of the 32Nd International Conference on International Conference on Machine Learning -","volume":"37","author":"Wilson A. G.","unstructured":"A. G. Wilson and H. Nickisch . 2015. Kernel Interpolation for Scalable Structured Gaussian Processes (KISS-GP) . In Proceedings of the 32Nd International Conference on International Conference on Machine Learning - Volume 37 (ICML'15). JMLR.org, 1775--1784. http:\/\/dl.acm.org\/citation.cfm?id=3045118.3045307 A. G. Wilson and H. Nickisch. 2015. Kernel Interpolation for Scalable Structured Gaussian Processes (KISS-GP). In Proceedings of the 32Nd International Conference on International Conference on Machine Learning - Volume 37 (ICML'15). JMLR.org, 1775--1784. http:\/\/dl.acm.org\/citation.cfm?id=3045118.3045307"},{"key":"e_1_3_2_1_53_1","volume-title":"Hierarchical DAG Scheduling for Hybrid Distributed Systems. In 2015 IEEE International Parallel and Distributed Processing Symposium. 156--165","author":"Wu W.","unstructured":"W. Wu , A. Bouteiller , G. Bosilca , M. Faverge , and J. Dongarra . 2015 . Hierarchical DAG Scheduling for Hybrid Distributed Systems. In 2015 IEEE International Parallel and Distributed Processing Symposium. 156--165 . W. Wu, A. Bouteiller, G. Bosilca, M. Faverge, and J. Dongarra. 2015. Hierarchical DAG Scheduling for Hybrid Distributed Systems. In 2015 IEEE International Parallel and Distributed Processing Symposium. 156--165."},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1137\/110831982"},{"key":"e_1_3_2_1_55_1","volume-title":"Proceedings of the International Conference for High Performance Computing, Networking, Storage, and Analysis (SC '18)","author":"Yu C.D.","unstructured":"C.D. Yu , S. Reiz , and G. Biros . 2018. Distributed-memory Hierarchical Compression of Dense SPD Matrices . In Proceedings of the International Conference for High Performance Computing, Networking, Storage, and Analysis (SC '18) . IEEE Press, Piscataway, NJ, USA, Article 15, 15 pages. C.D. Yu, S. Reiz, and G. Biros. 2018. Distributed-memory Hierarchical Compression of Dense SPD Matrices. In Proceedings of the International Conference for High Performance Computing, Networking, Storage, and Analysis (SC '18). IEEE Press, Piscataway, NJ, USA, Article 15, 15 pages."}],"event":{"name":"PASC '20: Platform for Advanced Scientific Computing Conference","location":"Geneva Switzerland","acronym":"PASC '20","sponsor":["SIGHPC ACM Special Interest Group on High Performance Computing, Special Interest Group on High Performance Computing","CSCS Swiss National Supercomputing Centre","ETH Zurich Federal Institute of Technology - University of Zurich"]},"container-title":["Proceedings of the Platform for Advanced Scientific Computing Conference"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3394277.3401846","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3394277.3401846","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T22:01:41Z","timestamp":1750197701000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3394277.3401846"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,6,29]]},"references-count":55,"alternative-id":["10.1145\/3394277.3401846","10.1145\/3394277"],"URL":"https:\/\/doi.org\/10.1145\/3394277.3401846","relation":{},"subject":[],"published":{"date-parts":[[2020,6,29]]},"assertion":[{"value":"2020-06-29","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}