{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T18:27:28Z","timestamp":1773772048572,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":27,"publisher":"ACM","license":[{"start":{"date-parts":[[2006,6,28]],"date-time":"2006-06-28T00:00:00Z","timestamp":1151452800000},"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":[[2006,6,28]]},"DOI":"10.1145\/1183401.1183431","type":"proceedings-article","created":{"date-parts":[[2007,1,17]],"date-time":"2007-01-17T01:15:56Z","timestamp":1168996556000},"page":"199-208","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":64,"title":["STAR-MPI"],"prefix":"10.1145","author":[{"given":"Ahmad","family":"Faraj","sequence":"first","affiliation":[{"name":"Florida State University, Tallahassee, FL"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xin","family":"Yuan","sequence":"additional","affiliation":[{"name":"Florida State University, Tallahassee, FL"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"David","family":"Lowenthal","sequence":"additional","affiliation":[{"name":"University of Georgia, Athens, GA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2006,6,28]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/263580.263662"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/71.642949"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/1088149.1088202"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2005.288"},{"key":"e_1_3_2_1_5_1","volume-title":"Bandwidth Efficient All-to-All Broadcast on Switched Clusters.\" The 2005 IEEE International Conference on Cluster Computing","author":"Faraj A.","year":"2005","unstructured":"A. Faraj and X. Yuan . \" Bandwidth Efficient All-to-All Broadcast on Switched Clusters.\" The 2005 IEEE International Conference on Cluster Computing , Boston, MA , Sept 27--30, 2005 . A. Faraj and X. Yuan. \"Bandwidth Efficient All-to-All Broadcast on Switched Clusters.\" The 2005 IEEE International Conference on Cluster Computing, Boston, MA, Sept 27--30, 2005."},{"key":"e_1_3_2_1_6_1","first-page":"1381","article-title":"FFTW: An Adaptive Software Architecture for the FFT","volume":"3","author":"Frigo M.","year":"1998","unstructured":"M. Frigo and S. Johnson . \" FFTW: An Adaptive Software Architecture for the FFT .\" In Proceedings of the International Conference on Acoustics, Speech, and Signal Processing (ICASSP) , volume 3 , page 1381 , 1998 . M. Frigo and S. Johnson. \"FFTW: An Adaptive Software Architecture for the FFT.\" In Proceedings of the International Conference on Acoustics, Speech, and Signal Processing (ICASSP), volume 3, page 1381, 1998.","journal-title":"Proceedings of the International Conference on Acoustics, Speech, and Signal Processing (ICASSP)"},{"key":"e_1_3_2_1_7_1","volume-title":"Argonne National Labratory","author":"Gropp William","year":"1999","unstructured":"William Gropp and Ewing Lusk , \" Reproducible Measurements of MPI Performance Characteristics .\" Technical Report ANL\/MCS-P755--0699 , Argonne National Labratory , Argonne, IL , June 1999 . William Gropp and Ewing Lusk, \"Reproducible Measurements of MPI Performance Characteristics.\" Technical Report ANL\/MCS-P755--0699, Argonne National Labratory, Argonne, IL, June 1999."},{"key":"e_1_3_2_1_8_1","unstructured":"FFTW. http:\/\/www.fftw.org.  FFTW. http:\/\/www.fftw.org."},{"key":"e_1_3_2_1_9_1","unstructured":"LAM\/MPI Parallel Computing. http:\/\/www.lam-mpi.org.  LAM\/MPI Parallel Computing. http:\/\/www.lam-mpi.org."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1006\/jpdc.1996.1264"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/781498.781514"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/301104.301116"},{"key":"e_1_3_2_1_13_1","unstructured":"LAMMPS\n  : Molecular Dynamics Simulator Available at http:\/\/www.cs.sandia.gov\/sjplimp\/lammps.html.  LAMMPS: Molecular Dynamics Simulator Available at http:\/\/www.cs.sandia.gov\/sjplimp\/lammps.html."},{"key":"e_1_3_2_1_14_1","volume-title":"July","author":"Forum The MPI","year":"1997","unstructured":"The MPI Forum . The MPI-2: Extensions to the Message Passing Interface , July 1997 . Available at http:\/\/www.mpi-forum.org\/docs\/mpi-20-html\/ mpi2-report.html. The MPI Forum. The MPI-2: Extensions to the Message Passing Interface, July 1997. Available at http:\/\/www.mpi-forum.org\/docs\/mpi-20-html\/ mpi2-report.html."},{"key":"e_1_3_2_1_15_1","unstructured":"MPICH - A Portable Implementation of MPI. Available at http:\/\/www.mcs.anl.gov\/mpi\/mpich.  MPICH - A Portable Implementation of MPI. Available at http:\/\/www.mcs.anl.gov\/mpi\/mpich."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/369028.369106"},{"key":"e_1_3_2_1_17_1","unstructured":"Parallel N-Body Simulations Available at http:\/\/www.cs.cmu.edu\/scan-dal\/alg\/nbody.html.  Parallel N-Body Simulations Available at http:\/\/www.cs.cmu.edu\/scan-dal\/alg\/nbody.html."},{"key":"e_1_3_2_1_18_1","volume-title":"Pipelined Broadcast on Ethernet Switched Clusters.\" The 20th IEEE International Parallel & Distributed Processing Symposium (IPDPS)","author":"Patarasuk P.","year":"2006","unstructured":"P. Patarasuk , A. Faraj , and X. Yuan . \" Pipelined Broadcast on Ethernet Switched Clusters.\" The 20th IEEE International Parallel & Distributed Processing Symposium (IPDPS) , Rhodes Island , Greece, April 25--29, 2006 . P. Patarasuk, A. Faraj, and X. Yuan. \"Pipelined Broadcast on Ethernet Switched Clusters.\" The 20th IEEE International Parallel & Distributed Processing Symposium (IPDPS), Rhodes Island, Greece, April 25--29, 2006."},{"key":"e_1_3_2_1_19_1","unstructured":"Pittsburg Supercomputing Center Available at http:\/\/www.psc.edu\/machines\/tcs\/lemieux.html.  Pittsburg Supercomputing Center Available at http:\/\/www.psc.edu\/machines\/tcs\/lemieux.html."},{"key":"e_1_3_2_1_20_1","unstructured":"R. Rabenseifner \"A new optimized MPI reduce and allreduce algorithms.\" Available at http:\/\/www.hlrs.de\/organization\/par\/services\/models\/mpi\/myreduce.html 1997.  R. Rabenseifner \"A new optimized MPI reduce and allreduce algorithms.\" Available at http:\/\/www.hlrs.de\/organization\/par\/services\/models\/mpi\/myreduce.html 1997."},{"key":"e_1_3_2_1_21_1","first-page":"77","volume-title":"First results on CRAY T3E900--512,\" In Proceedings of the Message Passing Interface Developer's and User's Conference","author":"Rabenseinfner R.","year":"1999","unstructured":"R. Rabenseinfner , \" Automatic MPI counter profiling of all users : First results on CRAY T3E900--512,\" In Proceedings of the Message Passing Interface Developer's and User's Conference , pages 77 -- 85 , 1999 . R. Rabenseinfner, \"Automatic MPI counter profiling of all users: First results on CRAY T3E900--512,\" In Proceedings of the Message Passing Interface Developer's and User's Conference, pages 77--85, 1999."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1142\/S0129183199000139"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/331532.331555"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/363911.363920"},{"key":"e_1_3_2_1_25_1","volume-title":"Argonne National Laboratory","author":"Thakur R.","year":"2004","unstructured":"R. Thakur , R. Rabenseifner , and W. Gropp . Optimizing of Collective Communication Operations in MPICH. ANL\/MCS-P1140--0304, Mathematics and Computer Science Division , Argonne National Laboratory , March 2004 . R. Thakur, R. Rabenseifner, and W. Gropp. Optimizing of Collective Communication Operations in MPICH. ANL\/MCS-P1140--0304, Mathematics and Computer Science Division, Argonne National Laboratory, March 2004."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.5555\/370049.370055"},{"key":"e_1_3_2_1_27_1","volume-title":"SuperComputing'98: High Performance Networking and Computing","author":"Whaley R. C.","year":"1998","unstructured":"R. C. Whaley and J. Dongarra . Automatically tuned linear algebra software . In SuperComputing'98: High Performance Networking and Computing , 1998 . R. C. Whaley and J. Dongarra. Automatically tuned linear algebra software. In SuperComputing'98: High Performance Networking and Computing, 1998."}],"event":{"name":"ICS06: International Conference on Supercomputing 2006","location":"Cairns Queensland Australia","acronym":"ICS06","sponsor":["ACM Association for Computing Machinery","SIGARCH ACM Special Interest Group on Computer Architecture"]},"container-title":["Proceedings of the 20th annual international conference on Supercomputing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/1183401.1183431","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/1183401.1183431","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T15:14:36Z","timestamp":1750259676000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/1183401.1183431"}},"subtitle":["self tuned adaptive routines for MPI collective operations"],"short-title":[],"issued":{"date-parts":[[2006,6,28]]},"references-count":27,"alternative-id":["10.1145\/1183401.1183431","10.1145\/1183401"],"URL":"https:\/\/doi.org\/10.1145\/1183401.1183431","relation":{},"subject":[],"published":{"date-parts":[[2006,6,28]]},"assertion":[{"value":"2006-06-28","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}