{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T11:29:52Z","timestamp":1778585392820,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":33,"publisher":"ACM","license":[{"start":{"date-parts":[[2013,11,17]],"date-time":"2013-11-17T00:00:00Z","timestamp":1384646400000},"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":[[2013,11,17]]},"DOI":"10.1145\/2503210.2503242","type":"proceedings-article","created":{"date-parts":[[2013,10,30]],"date-time":"2013-10-30T12:55:22Z","timestamp":1383137722000},"page":"1-12","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":20,"title":["Tera-scale 1D FFT with low-communication algorithm and Intel\u00ae Xeon Phi\u2122 coprocessors"],"prefix":"10.1145","author":[{"given":"Jongsoo","family":"Park","sequence":"first","affiliation":[{"name":"Parallel Computing Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ganesh","family":"Bikshandi","sequence":"additional","affiliation":[{"name":"Parallel Computing Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Karthikeyan","family":"Vaidyanathan","sequence":"additional","affiliation":[{"name":"Parallel Computing Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ping Tak Peter","family":"Tang","sequence":"additional","affiliation":[{"name":"Software and Service Group, Intel Corporation"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pradeep","family":"Dubey","sequence":"additional","affiliation":[{"name":"Parallel Computing Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daehyun","family":"Kim","sequence":"additional","affiliation":[{"name":"Parallel Computing Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2013,11,17]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Intel\u00ae Xeon Phi#8482; Coprocessor Instruction Set Architecture Reference Manual.  Intel\u00ae Xeon Phi#8482; Coprocessor Instruction Set Architecture Reference Manual."},{"key":"e_1_3_2_1_2_1","unstructured":"HPC Challenge Benchmark Results. http:\/\/icl.cs.utk.edu\/hpcc\/hpcc_results.cgi.  HPC Challenge Benchmark Results. http:\/\/icl.cs.utk.edu\/hpcc\/hpcc_results.cgi."},{"key":"e_1_3_2_1_3_1","unstructured":"RIKEN Next-Generation Supercomputer R&D Center. http:\/\/www.nsc.riken.jp\/index-eng.html.  RIKEN Next-Generation Supercomputer R&D Center. http:\/\/www.nsc.riken.jp\/index-eng.html."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/HOTI.2011.21"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/BF00162341"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1137\/090769156"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/1810085.1810128"},{"key":"e_1_3_2_1_8_1","volume-title":"Global Signal Processing Expo","author":"Chow Alex Chunghen","year":"2005","unstructured":"Alex Chunghen Chow , Gordon C. Fossum , and Daniel A. Brokenshire . A Programming Example: Large FFT on the Cell Broadband Engine . In Global Signal Processing Expo , 2005 . Alex Chunghen Chow, Gordon C. Fossum, and Daniel A. Brokenshire. A Programming Example: Large FFT on the Cell Broadband Engine. In Global Signal Processing Expo, 2005."},{"issue":"2","key":"e_1_3_2_1_9_1","first-page":"297","volume":"19","author":"Cooley James W.","year":"1965","unstructured":"James W. Cooley and John W . Tukey. An Algorithm for the Machine Computation of Complex Fourier Series. Mathematics of Computation , 19 ( 2 ): 297 -- 301 , 1965 . James W. Cooley and John W. Tukey. An Algorithm for the Machine Computation of Complex Fourier Series. Mathematics of Computation, 19(2):297--301, 1965.","journal-title":"Tukey. An Algorithm for the Machine Computation of Complex Fourier Series. Mathematics of Computation"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2010.38"},{"key":"e_1_3_2_1_11_1","volume-title":"Encyclopedia of Parallel Computing","author":"Franchetti Franz","year":"2011","unstructured":"Franz Franchetti and Markus P\u00fcschel . Encyclopedia of Parallel Computing , chapter Fast Fourier Transform. Springer , 2011 . Franz Franchetti and Markus P\u00fcschel. Encyclopedia of Parallel Computing, chapter Fast Fourier Transform. Springer, 2011."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2009.934155"},{"key":"e_1_3_2_1_13_1","first-page":"216","volume":"93","author":"Frigo Matteo","year":"2005","unstructured":"Matteo Frigo and Steven G . Johnson. The Design and Implementation of FFTW. Proceedings of the IEEE , 93 : 216 -- 231 , 2005 . Matteo Frigo and Steven G. Johnson. The Design and Implementation of FFTW. Proceedings of the IEEE, 93:216--231, 2005.","journal-title":"Johnson. The Design and Implementation of FFTW. Proceedings of the IEEE"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.5555\/1413370.1413373"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2013.113"},{"key":"e_1_3_2_1_16_1","volume-title":"International Supercomputing Conference (ISC), accepted for publication","author":"Joo Balint","year":"2013","unstructured":"Balint Joo , Dhiraj D. Kalamkar , Karthikeyan Vaidyanathan , Mikhail Smelyanskiy , Kiran Pamnany , Victor W Lee , Pradeep Dubey , and William Watson III. Lattice QCD on Intel R Xeon Phi coprocessors . In International Supercomputing Conference (ISC), accepted for publication , 2013 . Balint Joo, Dhiraj D. Kalamkar, Karthikeyan Vaidyanathan, Mikhail Smelyanskiy, Kiran Pamnany, Victor W Lee, Pradeep Dubey, and William Watson III. Lattice QCD on Intel R Xeon Phi coprocessors. In International Supercomputing Conference (ISC), accepted for publication, 2013."},{"key":"e_1_3_2_1_17_1","volume-title":"ExaScale Computing Study: Technology Challenges in Achieving Exascale Systems","author":"Kogge Peter","year":"2008","unstructured":"Peter Kogge , Keren Bergman , Shekhar Borkar , Dan Campbell , William Carlson , William Dally , Monty Denneau , Paul Franzon , William Harrod , Kerry Hill , Jon Hiller , Sherman Karp , Stephen Keckler , Dean Klein , Robert Lucas , Mark Richards , Al Scarpelli , Steven Scott , Allan Snavely , Thomas Sterling , R. Stanley Williams , and Katherine Yelick . ExaScale Computing Study: Technology Challenges in Achieving Exascale Systems . 2008 . www.cse.nd.edu\/Reports\/2008\/TR-2008-13.pdf. Peter Kogge, Keren Bergman, Shekhar Borkar, Dan Campbell, William Carlson, William Dally, Monty Denneau, Paul Franzon, William Harrod, Kerry Hill, Jon Hiller, Sherman Karp, Stephen Keckler, Dean Klein, Robert Lucas, Mark Richards, Al Scarpelli, Steven Scott, Allan Snavely, Thomas Sterling, R. Stanley Williams, and Katherine Yelick. ExaScale Computing Study: Technology Challenges in Achieving Exascale Systems. 2008. www.cse.nd.edu\/Reports\/2008\/TR-2008-13.pdf."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"crossref","DOI":"10.1137\/1.9781611970999","volume-title":"Computational Frameworks for the Fast Fourier Transforms","author":"Loan Charles Van","year":"1992","unstructured":"Charles Van Loan . Computational Frameworks for the Fast Fourier Transforms . SIAM , 1992 . Charles Van Loan. Computational Frameworks for the Fast Fourier Transforms. SIAM, 1992."},{"key":"e_1_3_2_1_19_1","unstructured":"John D. McCalpin. STREAM: Sustainable Memory Bandwidth in High Performance Computers. http:\/\/www.cs.virginia.edu\/stream.  John D. McCalpin. STREAM: Sustainable Memory Bandwidth in High Performance Computers. http:\/\/www.cs.virginia.edu\/stream."},{"key":"e_1_3_2_1_20_1","volume-title":"Prospects for scalable 3D FFTs on heterogeneous exascale systems","author":"McClanahan Chris","year":"2011","unstructured":"Chris McClanahan , Kent Czechowski , Casey Battaglino , Kartik Iyer , P.-K. Yeung , and Richard Vuduc . Prospects for scalable 3D FFTs on heterogeneous exascale systems . 2011 . Chris McClanahan, Kent Czechowski, Casey Battaglino, Kartik Iyer, P.-K. Yeung, and Richard Vuduc. Prospects for scalable 3D FFTs on heterogeneous exascale systems. 2011."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/SSST.2006.1619115"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/SSST.2005.1460927"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.5555\/2388996.2389056"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-8659.2007.01012.x"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"crossref","unstructured":"Jongsoo Park Ping Tak Peter Tang Mikhail Smelyanskiy Daehyun Kim and Thomas Benson. Efficient Backprojection-based Synthetic Aperture Radar Computation with Many-core Processors. In International Conference for High Performance Computing Networking Storage and Analysis (SC) 2012.   Jongsoo Park Ping Tak Peter Tang Mikhail Smelyanskiy Daehyun Kim and Thomas Benson. Efficient Backprojection-based Synthetic Aperture Radar Computation with Many-core Processors. In International Conference for High Performance Computing Networking Storage and Analysis (SC) 2012.","DOI":"10.1109\/SC.2012.53"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/1807167.1807207"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2010.48"},{"key":"e_1_3_2_1_28_1","volume-title":"A Parallel 3-D FFT Algorithm on Clusters of Vector SMPs","author":"Takahashi Daisuke","year":"2000","unstructured":"Daisuke Takahashi . A Parallel 3-D FFT Algorithm on Clusters of Vector SMPs , 2000 . Daisuke Takahashi. A Parallel 3-D FFT Algorithm on Clusters of Vector SMPs, 2000."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-8191(03)00039-5"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.5555\/646667.700022"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCC.2012.53"},{"key":"e_1_3_2_1_32_1","volume-title":"International Conference for High Performance Computing, Networking, Storage and Analysis (SC)","author":"Peter Tang Ping Tak","year":"2012","unstructured":"Ping Tak Peter Tang , Jongsoo Park , Daehyun Kim , and Vladimir Petrov . A Framework for Low-Communication 1-D FFT . In International Conference for High Performance Computing, Networking, Storage and Analysis (SC) , 2012 . Ping Tak Peter Tang, Jongsoo Park, Daehyun Kim, and Vladimir Petrov. A Framework for Low-Communication 1-D FFT. In International Conference for High Performance Computing, Networking, Storage and Analysis (SC), 2012."},{"key":"e_1_3_2_1_33_1","volume-title":"High Performance Compilers for Parallel Computing","author":"Wolfe Michael","year":"1996","unstructured":"Michael Wolfe . High Performance Compilers for Parallel Computing . Addison-Wesley , 1996 . Michael Wolfe. High Performance Compilers for Parallel Computing. Addison-Wesley, 1996."}],"event":{"name":"SC13: International Conference for High Performance Computing, Networking, Storage and Analysis","location":"Denver Colorado","acronym":"SC13","sponsor":["SIGHPC ACM Special Interest Group on High Performance Computing, Special Interest Group on High Performance Computing","SIGARCH ACM Special Interest Group on Computer Architecture","IEEE-CS Computer Society"]},"container-title":["Proceedings of the International Conference on High Performance Computing, Networking, Storage and Analysis"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2503210.2503242","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/2503210.2503242","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T08:18:55Z","timestamp":1750234735000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2503210.2503242"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,11,17]]},"references-count":33,"alternative-id":["10.1145\/2503210.2503242","10.1145\/2503210"],"URL":"https:\/\/doi.org\/10.1145\/2503210.2503242","relation":{},"subject":[],"published":{"date-parts":[[2013,11,17]]},"assertion":[{"value":"2013-11-17","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}