{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T06:17:42Z","timestamp":1730269062993,"version":"3.28.0"},"reference-count":28,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2014,5]]},"DOI":"10.1109\/ipdps.2014.113","type":"proceedings-article","created":{"date-parts":[[2014,8,20]],"date-time":"2014-08-20T15:15:40Z","timestamp":1408547740000},"page":"1083-1092","source":"Crossref","is-referenced-by-count":12,"title":["Improving Communication Performance and Scalability of Native Applications on Intel Xeon Phi Coprocessor Clusters"],"prefix":"10.1109","author":[{"given":"Karthikeyan","family":"Vaidyanathan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kiran","family":"Pamnany","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dhiraj D.","family":"Kalamkar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alexander","family":"Heinecke","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mikhail","family":"Smelyanskiy","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jongsoo","family":"Park","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daehyun","family":"Kim","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Aniruddha","family":"Shet G.","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bharat","family":"Kaul","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Balint","family":"Joo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pradeep","family":"Dubey","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"19","article-title":"A framework for low-communication 1- d FFT","author":"tak peter tang","year":"2012","journal-title":"Proceedings of the Conference on High Performance Computing Networking, Storage and Analysis - SC '09"},{"key":"17","doi-asserted-by":"publisher","DOI":"10.1147\/rd.416.0737"},{"year":"2012","key":"18"},{"key":"15","doi-asserted-by":"crossref","DOI":"10.22323\/1.164.0020","article-title":"The BlueGene\/Q supercomputer","author":"boyle","year":"2012","journal-title":"Proceedings of Science Lattice Field Theory"},{"key":"16","doi-asserted-by":"publisher","DOI":"10.6028\/jres.049.044"},{"key":"13","doi-asserted-by":"publisher","DOI":"10.1145\/2503210.2503242"},{"key":"14","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2010.40"},{"key":"11","first-page":"297","volume":"19","author":"cooley","year":"1965","journal-title":"An Algorithm for the Machine Computation of Complex Fourier Series"},{"key":"12","article-title":"Design and implementation of the linpack benchmark for single and multi-node systems based on intel(r) xeon phi(tm) coprocessor","author":"heinecke","year":"2013","journal-title":"Proceedings of IPDPS International Parallel and Distributed Processing Symposium"},{"journal-title":"Principles and Practices of Interconnection Networks","year":"2004","author":"dally","key":"21"},{"key":"20","first-page":"216","volume":"93","author":"frigo","year":"2005","journal-title":"The Design and Implementation of fftw3"},{"year":"0","key":"22"},{"key":"23","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTR.2003.1253341"},{"key":"24","article-title":"Zero-copy MPI derived datatype communication over infiniBand","author":"santhanaraman","year":"2004","journal-title":"Proceedings of EuroPVM\/MPI Conference"},{"key":"25","doi-asserted-by":"publisher","DOI":"10.1007\/11846802_36"},{"key":"26","doi-asserted-by":"publisher","DOI":"10.1016\/j.nuclphysbps.2004.11.254"},{"key":"27","article-title":"Parallel Zero-Copy Algorithms for Fast Fourier Transform and Conjugate Gradient using MPI Datatypes","author":"hoefler","year":"2010","journal-title":"Proceedings of EuroMPI Conference"},{"key":"28","article-title":"Application Experiences on a Cluster Supercomputer Equipped with Intel Xeon Phi Coprocessors","author":"hadri","year":"2013","journal-title":"Supercomputing Lab"},{"journal-title":"Titan Supercomputer","year":"0","key":"3"},{"journal-title":"Tianhe-2 Petaflop Supercomputer","year":"0","key":"2"},{"journal-title":"HPL - a Portable Implementation of the High-Performance Linpack Benchmark for Distributed-Memory Computers","year":"0","author":"petitet","key":"10"},{"journal-title":"Toward Exascale Computing","year":"2010","key":"1"},{"key":"7","article-title":"Multiple DAPL* provider support for intel xeon phi coprocessor with intel mpi library","author":"chuvelev","year":"2013","journal-title":"Proceedings of International Conference on Parallel Computing"},{"journal-title":"Nvidia Tesla GPU Accelerators for Servers","year":"0","key":"6"},{"journal-title":"Intel Xeon Phi Coprocessor","year":"0","key":"5"},{"year":"0","key":"4"},{"key":"9","article-title":"Lattice QCD on intel xeon phi","author":"joo","year":"2013","journal-title":"Proceedings of ISC13 International Conference for Super Computing"},{"key":"8","doi-asserted-by":"publisher","DOI":"10.1145\/2503210.2503288"}],"event":{"name":"2014 IEEE International Parallel & Distributed Processing Symposium (IPDPS)","start":{"date-parts":[[2014,5,19]]},"location":"Phoenix, AZ, USA","end":{"date-parts":[[2014,5,23]]}},"container-title":["2014 IEEE 28th International Parallel and Distributed Processing Symposium"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6875427\/6877223\/06877337.pdf?arnumber=6877337","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,12,24]],"date-time":"2020-12-24T18:43:19Z","timestamp":1608835399000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/6877337\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,5]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/ipdps.2014.113","relation":{},"subject":[],"published":{"date-parts":[[2014,5]]}}}