{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,19]],"date-time":"2026-01-19T07:33:09Z","timestamp":1768807989695,"version":"3.49.0"},"reference-count":29,"publisher":"Springer Science and Business Media LLC","issue":"12","license":[{"start":{"date-parts":[[2013,5,19]],"date-time":"2013-05-19T00:00:00Z","timestamp":1368921600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Computing"],"published-print":{"date-parts":[[2013,12]]},"DOI":"10.1007\/s00607-013-0324-2","type":"journal-article","created":{"date-parts":[[2013,5,18]],"date-time":"2013-05-18T08:00:43Z","timestamp":1368864043000},"page":"1121-1136","source":"Crossref","is-referenced-by-count":61,"title":["MPI + MPI: a new hybrid approach to parallel programming with MPI plus shared memory"],"prefix":"10.1007","volume":"95","author":[{"given":"Torsten","family":"Hoefler","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"James","family":"Dinan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Darius","family":"Buntinas","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pavan","family":"Balaji","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Brian","family":"Barrett","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ron","family":"Brightwell","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"William","family":"Gropp","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vivek","family":"Kale","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rajeev","family":"Thakur","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2013,5,19]]},"reference":[{"key":"324_CR1","unstructured":"MPI Forum (2012) MPI: a message-passing interface standard. version 3.0"},{"issue":"2,3","key":"324_CR2","first-page":"83","volume":"9","author":"L Smith","year":"2001","unstructured":"Smith L, Bull M (2001) Development of mixed mode MPI\/OpenMP applications. Sci Program 9(2,3):83\u201398","journal-title":"Sci Program"},{"key":"324_CR3","doi-asserted-by":"crossref","unstructured":"Rabenseifner R, Hager G, Jost G (2009) Hybrid MPI\/OpenMP parallel programming on clusters of multi-core SMP nodes. In: Proceedings of the 17th Euromicro international conference on parallel, distributed and network-based processing","DOI":"10.1109\/PDP.2009.43"},{"key":"324_CR4","unstructured":"Demaine E (1997) A threads-only MPI implementation for the development of parallel programs. In: Proceedings of the 11th international symposium on HPC systems. pp 153\u2013163"},{"key":"324_CR5","unstructured":"Bhargava P (1997) MPI-LITE: multithreading support for MPI. http:\/\/pcl.cs.ucla.edu\/projects\/sesame\/mpi_lite\/mpi_lite.html"},{"key":"324_CR6","doi-asserted-by":"crossref","unstructured":"Shen K, Tang H, Yang T (1999) Adaptive two-level thread management for fast MPI execution on shared memory machines. In: Proceedings of the ACM\/IEEE conference on supercomputing","DOI":"10.1145\/331532.331581"},{"key":"324_CR7","doi-asserted-by":"crossref","first-page":"673","DOI":"10.1145\/363911.363920","volume":"22","author":"H Tang","year":"2000","unstructured":"Tang H, Shen K, Yang T (2000) Program transformation and runtime support for threaded MPI execution on shared memory machines. ACM Trans Program Lang Syst 22:673\u2013700","journal-title":"ACM Trans Program Lang Syst"},{"key":"324_CR8","unstructured":"P\u00e9rachec M, Carribault P, Jourdren H (2009) MPC-MPI: an MPI implementation reducing the overall memory consumption. In: Proceedings of EuroPVM\/MPI 2009, Springer, pp 94\u2013103"},{"key":"324_CR9","unstructured":"Shirley D (2000) Enhancing MPI applications through selective use of shared memory on SMPs. In: Proceedings of the 1st SIAM conference on CSE"},{"key":"324_CR10","unstructured":"Los Alamos National Laboratory (2001) Unified parallel software users\u2019 guide and reference manual. http:\/\/public.lanl.gov\/ups\/Doc_Directory\/UserGuide\/UserGuide.pdf"},{"key":"324_CR11","doi-asserted-by":"crossref","unstructured":"Hoefler T, Dinan J, Buntinas D, Balaji P, Barrett B, Brightwell R, Gropp W, Kale V, Thakur R (2012) Leveraging MPIs one-sided communication interface for shared-memory programming. In: Tr\u00e4ff J, Benkner S, Dongarra J (eds) Recent advances in the message passing interface. vol 7490, pp 132\u2013141","DOI":"10.1007\/978-3-642-33518-1_18"},{"issue":"4","key":"324_CR12","doi-asserted-by":"crossref","first-page":"521","DOI":"10.1016\/S0167-8191(00)00072-7","volume":"27","author":"JR Taft","year":"2001","unstructured":"Taft JR (2001) Achieving 60 GFLOP\/s on the production CFD code OVERFLOW-MLP. Parallel Comput 27(4):521\u2013536","journal-title":"Parallel Comput"},{"key":"324_CR13","doi-asserted-by":"crossref","unstructured":"Boehm HJ (2005) Threads cannot be implemented as a library. In: Proceedings of the 2005 ACM SIGPLAN conference on programming language design and implementation. PLDI \u201905, New York, NY, USA, ACM pp 261\u2013268","DOI":"10.1145\/1065010.1065042"},{"issue":"2","key":"324_CR14","doi-asserted-by":"crossref","first-page":"48","DOI":"10.1145\/2076450.2076465","volume":"55","author":"HJ Boehm","year":"2012","unstructured":"Boehm HJ, Adve SV (2012) You do not know jack about shared variables or memory models. Commun. ACM 55(2):48\u201354","journal-title":"Commun. ACM"},{"key":"324_CR15","volume-title":"Compilers: principles, techniques, and tools","author":"AV Aho","year":"1986","unstructured":"Aho AV, Sethi R, Ullman JD (1986) Compilers: principles, techniques, and tools. Addison-Wesley Longman Publishing Co. Inc., Boston"},{"key":"324_CR16","doi-asserted-by":"crossref","unstructured":"Manson J, Pugh W, Adve SV (2005) The Java memory model. In: Proceedings of the 32nd ACM SIGPLAN-SIGACT symposium on principles of programming languages. POPL \u201905, New York, ACM pp 378\u2013391","DOI":"10.1145\/1040305.1040336"},{"issue":"6","key":"324_CR17","doi-asserted-by":"crossref","first-page":"68","DOI":"10.1145\/1379022.1375591","volume":"43","author":"HJ Boehm","year":"2008","unstructured":"Boehm HJ, Adve SV (2008) Foundations of the C++ concurrency memory model. SIGPLAN Not 43(6):68\u201378","journal-title":"SIGPLAN Not"},{"issue":"5","key":"324_CR18","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1109\/MC.2006.180","volume":"39","author":"EA Lee","year":"2006","unstructured":"Lee EA (2006) The problem with threads. Computer 39(5):33\u201342","journal-title":"Computer"},{"key":"324_CR19","unstructured":"Heroux MA, Brightwell R, Wolf MM (2011) Bi-modal MPI and MPI+threads computing on scalable multicore systems. IJHPCA (Submitted)"},{"key":"324_CR20","unstructured":"Sandia National Laboratories (2012) Mantevo project. http:\/\/www.mantevo.org"},{"key":"324_CR21","doi-asserted-by":"crossref","unstructured":"Saad Y (2003) Iterative methods for sparse linear systems. Society for Industrial and Applied Mathematics","DOI":"10.1137\/1.9780898718003"},{"issue":"1","key":"324_CR22","doi-asserted-by":"crossref","first-page":"123","DOI":"10.1137\/0911008","volume":"11","author":"JH Saltz","year":"1990","unstructured":"Saltz JH (1990) Aggregation methods for solving sparse triangular systems on multiprocessors. SIAM J Sci Stat Comput 11(1):123\u2013144","journal-title":"SIAM J Sci Stat Comput"},{"key":"324_CR23","unstructured":"Wolf MM, Heroux MA, Boman EG (2010) Factors impacting performance of multithreaded sparse triangular solve. Technical report SAND2010-0331 presented at VECPAR\u201910"},{"issue":"1","key":"324_CR24","first-page":"012057","volume":"125","author":"KP Esler","year":"2008","unstructured":"Esler KP, Kim J, Ceperley DM, Purwanto W, Walter EJ, Krakauer H, Zhang S, Kent PRC, Hennig RG, Umrigar C, Bajdich M, Koloren J, Mitas L, Srinivasan A (2008) Quantum monte carlo algorithms for electronic structure at the petascale; the endstation project. J Phys 125(1):012057","journal-title":"J Phys"},{"issue":"9","key":"324_CR25","doi-asserted-by":"crossref","first-page":"3390","DOI":"10.1016\/j.jcp.2009.01.017","volume":"228","author":"LK Wagner","year":"2009","unstructured":"Wagner LK, Bajdich M, Mitas L (2009) Qwalk: a quantum monte carlo program for electronic structure. J Comput Phys 228(9):3390\u20133404","journal-title":"J Comput Phys"},{"key":"324_CR26","unstructured":"Esler KP Einspline libaray. Online: http:\/\/einspline.svn.sourceforge.net\/"},{"key":"324_CR27","doi-asserted-by":"crossref","unstructured":"Niu Q, Dinan J, Tirukkovalur S, Mitas L, Wagner L, Sadayappan P (2012) A global address space approach to automated data management for parallel quantum Monte Carlo applications. In: Proceedings 19th international conference on high performance computing. HiPC\u201912","DOI":"10.1109\/HiPC.2012.6507509"},{"issue":"12","key":"324_CR28","doi-asserted-by":"crossref","first-page":"1121","DOI":"10.1002\/1096-9128(200010)12:12<1121::AID-CPE531>3.0.CO;2-N","volume":"12","author":"L Smith","year":"2000","unstructured":"Smith L, Kent P (2000) Development and performance of a mixed OpenMP\/MPI quantum Monte Carlo code. Concurr Pract Exp 12(12):1121\u20131129","journal-title":"Concurr Pract Exp"},{"issue":"1","key":"324_CR29","doi-asserted-by":"crossref","first-page":"40","DOI":"10.1109\/MCSE.2010.122","volume":"14","author":"KP Esler","year":"2012","unstructured":"Esler KP, Kim J, Ceperley DM, Shulenburger L (2012) Accelerating quantum Monte Carlo simulations of real materials on GPU clusters. Comput Sci Eng 14(1):40\u201351","journal-title":"Comput Sci Eng"}],"container-title":["Computing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00607-013-0324-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s00607-013-0324-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00607-013-0324-2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,7,13]],"date-time":"2019-07-13T23:15:45Z","timestamp":1563059745000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s00607-013-0324-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,5,19]]},"references-count":29,"journal-issue":{"issue":"12","published-print":{"date-parts":[[2013,12]]}},"alternative-id":["324"],"URL":"https:\/\/doi.org\/10.1007\/s00607-013-0324-2","relation":{},"ISSN":["0010-485X","1436-5057"],"issn-type":[{"value":"0010-485X","type":"print"},{"value":"1436-5057","type":"electronic"}],"subject":[],"published":{"date-parts":[[2013,5,19]]}}}