{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,11]],"date-time":"2024-09-11T04:15:55Z","timestamp":1726028155410},"publisher-location":"Singapore","reference-count":25,"publisher":"Springer Singapore","isbn-type":[{"type":"print","value":"9789811361937"},{"type":"electronic","value":"9789811361944"}],"license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019]]},"DOI":"10.1007\/978-981-13-6194-4_8","type":"book-chapter","created":{"date-parts":[[2019,5,14]],"date-time":"2019-05-14T12:07:03Z","timestamp":1557835623000},"page":"137-168","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Fast Fourier Transform in Large-Scale Systems"],"prefix":"10.1007","author":[{"given":"Daisuke","family":"Takahashi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,5,15]]},"reference":[{"key":"8_CR1","unstructured":"2DECOMP & FFT\u2014Library for 2D Pencil Decomposition and Distributed FFTs. \n                http:\/\/www.2decomp.org\/"},{"key":"8_CR2","unstructured":"TOP500 Supercomputer Sites. \n                http:\/\/www.top500.org\/"},{"key":"8_CR3","doi-asserted-by":"publisher","first-page":"58","DOI":"10.1016\/j.parco.2012.12.002","volume":"39","author":"O Ayala","year":"2013","unstructured":"O. Ayala, L.P. Wang, Parallel implementation and scalability analysis of 3D fast Fourier transform using 2D domain decomposition. Parallel Comput. 39, 58\u201377 (2013)","journal-title":"Parallel Comput."},{"key":"8_CR4","doi-asserted-by":"publisher","first-page":"23","DOI":"10.1007\/BF00162341","volume":"4","author":"DH Bailey","year":"1990","unstructured":"D.H. Bailey, FFTs in external or hierarchical memory. J. Supercomput. 4, 23\u201335 (1990)","journal-title":"J. Supercomput."},{"key":"8_CR5","doi-asserted-by":"publisher","first-page":"45","DOI":"10.1109\/TAU.1967.1161899","volume":"15","author":"WT Cochran","year":"1967","unstructured":"W.T. Cochran, J.W. Cooley, D.L. Favin, H.D. Helms, R.A. Kaenel, W.W. Lang, G.C. Maling, D.E. Nelson, C.M. Rader, P.D. Welch, What is the fast Fourier transform? IEEE Trans. Audio Electroacoust. 15, 45\u201355 (1967)","journal-title":"IEEE Trans. Audio Electroacoust."},{"key":"8_CR6","doi-asserted-by":"publisher","first-page":"297","DOI":"10.1090\/S0025-5718-1965-0178586-1","volume":"19","author":"JW Cooley","year":"1965","unstructured":"J.W. Cooley, J.W. Tukey, An algorithm for the machine calculation of complex Fourier series. Math. Comput. 19, 297\u2013301 (1965)","journal-title":"Math. Comput."},{"key":"8_CR7","doi-asserted-by":"publisher","first-page":"457","DOI":"10.1147\/rd.492.0457","volume":"49","author":"M Eleftheriou","year":"2005","unstructured":"M. Eleftheriou, B.G. Fitch, A. Rayshubskiy, T.J.C. Ward, R.S. Germain, Scalable framework for 3D FFTs on the Blue Gene\/L supercomputer: implementation and early performance measurements. IBM J. Res. Dev. 49, 457\u2013464 (2005)","journal-title":"IBM J. Res. Dev."},{"key":"8_CR8","doi-asserted-by":"publisher","first-page":"531","DOI":"10.1016\/j.cpc.2006.12.006","volume":"176","author":"B Fang","year":"2007","unstructured":"B. Fang, Y. Deng, G. Martyna, Performance of the 3D FFT on the 6D network torus QCDOC parallel supercomputer. Comput. Phys. Commun. 176, 531\u2013538 (2007)","journal-title":"Comput. Phys. Commun."},{"key":"8_CR9","unstructured":"A. Faraj, X. Yuan, Automatic generation and tuning of MPI collective communication routines, in Proceedings of 19th ACM International Conference on Supercomputing (ICS\u201905) (2005), pp. 393\u2013402"},{"key":"8_CR10","doi-asserted-by":"publisher","first-page":"216","DOI":"10.1109\/JPROC.2004.840301","volume":"93","author":"M Frigo","year":"2005","unstructured":"M. Frigo, S.G. Johnson, The design and implementation of FFTW3. Proc. IEEE 93, 216\u2013231 (2005)","journal-title":"Proc. IEEE"},{"key":"8_CR11","doi-asserted-by":"crossref","unstructured":"R. Kumar, A. Mamidala, D.K. Panda, Scaling all-to-all collective on multi-core systems, in Proceedings of 2008 IEEE International Parallel and Distributed Processing Symposium (IPDPS 2008) (2008)","DOI":"10.1109\/IPDPS.2008.4536141"},{"key":"8_CR12","unstructured":"MVAPICH: MPI over InfiniBand and iWARP. \n                http:\/\/mvapich.cse.ohio-state.edu\/"},{"key":"8_CR13","unstructured":"NVIDIA Corporation, CUFFT Library User\u2019s Guide (2017). \n                http:\/\/docs.nvidia.com\/cuda\/pdf\/CUFFT_Library.pdf"},{"key":"8_CR14","doi-asserted-by":"publisher","first-page":"C192","DOI":"10.1137\/11082748X","volume":"34","author":"D Pekurovsky","year":"2012","unstructured":"D. Pekurovsky, P3DFFT: a framework for parallel computations of Fourier transforms in three dimensions. SIAM J. Sci. Comput. 34, C192\u2013C209 (2012)","journal-title":"SIAM J. Sci. Comput."},{"key":"8_CR15","unstructured":"The Portland Group, CUDA Fortran Programming Guide and Reference (2017). \n                http:\/\/www.pgroup.com\/doc\/pgicudaforug.pdf"},{"key":"8_CR16","doi-asserted-by":"publisher","first-page":"232","DOI":"10.1109\/JPROC.2004.840306","volume":"93","author":"M P\u00fcschel","year":"2005","unstructured":"M. P\u00fcschel, J.M.F. Moura, J.R. Johnson, D. Padua, M.M. Veloso, B.W. Singer, J. Xiong, F. Franchetti, A. Ga\u010di\u0107, Y. Voronenko, K. Chen, R.W. Johnson, N. Rizzolo, SPIRAL: code generation for DSP transforms. Proc. IEEE 93, 232\u2013275 (2005)","journal-title":"Proc. IEEE"},{"issue":"3","key":"8_CR17","doi-asserted-by":"publisher","first-page":"250","DOI":"10.1109\/TASSP.1977.1162951","volume":"25","author":"G. Rivard","year":"1977","unstructured":"G.E. Rivard, Direct fast Fourier transform of bivariate functions. IEEE Trans. Acoust. Speech Signal Process. ASSP-25, 250\u2013252 (1977)","journal-title":"IEEE Transactions on Acoustics, Speech, and Signal Processing"},{"key":"8_CR18","doi-asserted-by":"publisher","first-page":"93","DOI":"10.1109\/TAU.1969.1162042","volume":"17","author":"RC Singleton","year":"1969","unstructured":"R.C. Singleton, An algorithm for computing the mixed radix fast Fourier transform. IEEE Trans. Audio Electroacoust. 17, 93\u2013103 (1969)","journal-title":"IEEE Trans. Audio Electroacoust."},{"key":"8_CR19","doi-asserted-by":"crossref","unstructured":"D. Takahashi, A blocking algorithm for parallel 1-D FFT on shared-memory parallel computers, in Proceedings of 6th International Conference on Applied Parallel Computing (PARA 2002). Lecture Notes in Computer Science, vol. 2367 (Springer, 2002), pp. 380\u2013389","DOI":"10.1007\/3-540-48051-X_38"},{"key":"8_CR20","doi-asserted-by":"crossref","unstructured":"D. Takahashi, Automatic tuning for parallel FFTs, in Software Automatic Tuning: From Concepts to State-of-the-Art Results, ed. by K. Naono, K. Teranishi, J. Cavazos, R. Suda (Springer, 2010), pp. 49\u201367","DOI":"10.1007\/978-1-4419-6935-4_4"},{"key":"8_CR21","doi-asserted-by":"crossref","unstructured":"D. Takahashi, An implementation of parallel 3-D FFT with 2-D decomposition on a massively parallel cluster of multi-core processors, in Proceedings of 8th International Conference on Parallel Processing and Applied Mathematics (PPAM 2009), Part I, Workshop on Memory Issues on Multi- and Manycore Platforms. Lecture Notes in Computer Science, vol. 6067 (Springer, 2010), pp. 606\u2013614","DOI":"10.1007\/978-3-642-14390-8_63"},{"key":"8_CR22","unstructured":"D. Takahashi, Implementation of parallel 1-D FFT on GPU clusters, in Proceedings of 2013 IEEE 16th International Conference on Computational Science and Engineering (CSE 2013) (2013), pp. 174\u2013180"},{"key":"8_CR23","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/0021-9991(83)90013-X","volume":"52","author":"C Temperton","year":"1983","unstructured":"C. Temperton, Self-sorting mixed-radix fast Fourier transforms. J. Comput. Phys. 52, 1\u201323 (1983)","journal-title":"J. Comput. Phys."},{"key":"8_CR24","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611970999","volume-title":"Computational Frameworks for the Fast Fourier Transform","author":"C Loan Van","year":"1992","unstructured":"C. Van Loan, Computational Frameworks for the Fast Fourier Transform (SIAM Press, Philadelphia, PA, 1992)"},{"key":"8_CR25","doi-asserted-by":"publisher","first-page":"257","DOI":"10.1007\/s00450-011-0171-3","volume":"26","author":"H Wang","year":"2011","unstructured":"H. Wang, S. Potluri, M. Luo, A.K. Singh, S. Sur, D.K. Panda, MVAPICH2-GPU: optimized GPU to GPU communication for infiniband clusters. Comput. Sci.\u2014Res. Dev. 26, 257\u2013266 (2011)","journal-title":"Comput. Sci.\u2014Res. Dev."}],"container-title":["The Art of High Performance Computing for Computational Science, Vol. 1"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-13-6194-4_8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,14]],"date-time":"2019-05-14T12:07:36Z","timestamp":1557835656000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-981-13-6194-4_8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9789811361937","9789811361944"],"references-count":25,"URL":"https:\/\/doi.org\/10.1007\/978-981-13-6194-4_8","relation":{},"subject":[],"published":{"date-parts":[[2019]]},"assertion":[{"value":"15 May 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}}]}}