{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,4]],"date-time":"2024-09-04T17:54:17Z","timestamp":1725472457262},"publisher-location":"Berlin, Heidelberg","reference-count":21,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783540680673"},{"type":"electronic","value":"9783540680703"}],"license":[{"start":{"date-parts":[[2006,1,1]],"date-time":"2006-01-01T00:00:00Z","timestamp":1136073600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2006]]},"DOI":"10.1007\/11946441_74","type":"book-chapter","created":{"date-parts":[[2006,11,18]],"date-time":"2006-11-18T05:52:47Z","timestamp":1163829167000},"page":"818-832","source":"Crossref","is-referenced-by-count":12,"title":["Automatic Performance Optimization of the Discrete Fourier Transform on Distributed Memory Computers"],"prefix":"10.1007","author":[{"given":"Andreas","family":"Bonelli","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Franz","family":"Franchetti","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Juergen","family":"Lorenz","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Markus","family":"P\u00fcschel","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Christoph W.","family":"Ueberhuber","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"74_CR1","unstructured":"Adelmann, A., Bonelli, A., Petersen, W.P., Ueberhuber, C.W.: Communication efficiency of parallel 3D FFTs. In: VECPAR 2004, vol.\u00a0III, pp. 901\u2013907 (2004)"},{"key":"74_CR2","doi-asserted-by":"crossref","unstructured":"Baumgartner, G., Auer, A., Bernholdt, D.E., Bibireata, A., Choppella, V., Cociorva, D., Gao, X., Harrison, R.J., Hirata, S., Krishnamoorthy, S., Krishnan, S., Lam, C., Lu, Q., Nooijen, M., Pitzer, R.M., Ramanujam, J., Sadayappan, P., Sibiryakov, A.: Synthesis of high-performance parallel programs for a class of ab initio quantum chemistry models. In: [17], pp. 276\u2013292 (2005)","DOI":"10.1109\/JPROC.2004.840311"},{"key":"74_CR3","doi-asserted-by":"crossref","unstructured":"Blackford, L.S., Choi, J., Cleary, A., D\u2019Azevedo, E., Demmel, J., Dhillon, I., Dongarra, J., Hammarling, S., Henry, G., Petitet, A., Stanley, K., Walker, D., Whaley, R.C.: ScaLapack Users\u2019 Guide. SIAM, Philadelphia, PA (1997)","DOI":"10.1137\/1.9780898719642"},{"key":"74_CR4","doi-asserted-by":"publisher","first-page":"535","DOI":"10.1016\/B978-044450813-3\/50011-4","volume-title":"Handbook of Automated Reasoning, ch. 9","author":"N. Dershowitz","year":"2001","unstructured":"Dershowitz, N., Plaisted, D.A.: Rewriting. In: Robinson, A., Voronkov, A. (eds.) Handbook of Automated Reasoning, ch. 9, vol.\u00a01, pp. 535\u2013610. Elsevier, Amsterdam (2001)"},{"issue":"2\/3","key":"74_CR5","doi-asserted-by":"publisher","first-page":"457","DOI":"10.1147\/rd.492.0457","volume":"49","author":"M. Eleftheriou","year":"2005","unstructured":"Eleftheriou, M., Fitch, B., Rayshubskiy, A., Ward, T.C., Germain, R.: Scalable framework for 3D FFTs on the Blue Gene\/L supercomputer: Implementation and early performance measurements. IBM Journal of Research and Development\u00a049(2\/3), 457\u2013464 (2005)","journal-title":"IBM Journal of Research and Development"},{"key":"74_CR6","doi-asserted-by":"crossref","unstructured":"Faraj, A., Yuan, X.: Automatic generation and tuning of MPI collective communication routines. In: Proc.\u00a0International Conference on Supercomputing (ICS), pp. 393\u2013402 (2005)","DOI":"10.1145\/1088149.1088202"},{"key":"74_CR7","doi-asserted-by":"crossref","unstructured":"Franchetti, F., P\u00fcschel, M.: A SIMD vectorizing compiler for digital signal processing algorithms. In: Proc.\u00a0International Parallel and Distributed Processing Symposium (IPDPS), pp. 20\u201326 (2002)","DOI":"10.1109\/IPDPS.2002.1015494"},{"key":"74_CR8","doi-asserted-by":"crossref","unstructured":"Franchetti, F., Voronenko, Y., P\u00fcschel, M.: Loop merging for signal transforms. In: Proc.\u00a0Programming Language Design and Implementation (PLDI), pp. 315\u2013326 (2005)","DOI":"10.1145\/1064978.1065048"},{"key":"74_CR9","doi-asserted-by":"crossref","unstructured":"Franchetti, F., Voronenko, Y., P\u00fcschel, M.: FFT program generation for shared memory: SMP and multicore. In: Proc.\u00a0Supercomputing, SC (2006)","DOI":"10.1109\/SC.2006.31"},{"key":"74_CR10","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"363","DOI":"10.1007\/978-3-540-71351-7_28","volume-title":"High Performance Computing for Computational Science - VECPAR 2006","author":"F. Franchetti","year":"2007","unstructured":"Franchetti, F., Voronenko, Y., P\u00fcschel, M.: A rewriting system for the vectorization of signal transforms. In: Dayd\u00e9, M., Palma, J.M.L.M., Coutinho, \u00c1.L.G.A., Pacitti, E., Lopes, J.C. (eds.) VECPAR 2006. LNCS, vol.\u00a04395, pp. 363\u2013377. Springer, Heidelberg (2007) (On CD-ROM)"},{"key":"74_CR11","doi-asserted-by":"crossref","unstructured":"Frigo, M.: A fast Fourier transform compiler. In: Proc.\u00a0Programming Language Design and Implementation (PLDI), pp. 169\u2013180 (1999)","DOI":"10.1145\/301631.301661"},{"key":"74_CR12","first-page":"1381","volume-title":"Proc.\u00a0International Conference on\u00a0Acoustics, Speech, and Signal Processing (ICASSP)","author":"M. Frigo","year":"1998","unstructured":"Frigo, M., Johnson, S.G.: Fftw: An adaptive software architecture for the FFT. In: Proc.\u00a0International Conference on\u00a0Acoustics, Speech, and Signal Processing (ICASSP), vol.\u00a03, pp. 1381\u20131384. IEEE, Los Alamitos (1998)"},{"key":"74_CR13","doi-asserted-by":"crossref","unstructured":"Frigo, M., Johnson, S.G.: The design and implementation of Fftw3. In: [17], pp. 216\u2013231 (2005)","DOI":"10.1109\/JPROC.2004.840301"},{"key":"74_CR14","first-page":"1412","volume-title":"Proc.\u00a0Symposium on Applied Computing (SAC)","author":"G. Goumas","year":"2004","unstructured":"Goumas, G., Drosinos, N., Athanasaki, M., Koziris, N.: Automatic parallel code generation for tiled nested loops. In: Proc.\u00a0Symposium on Applied Computing (SAC), pp. 1412\u20131419. ACM Press, New York (2004)"},{"key":"74_CR15","doi-asserted-by":"crossref","unstructured":"Gygi, F., Draeger, E., de Supinski, B.R., Yates, R.K., Franchetti, F., Kral, S., Lorenz, J., Ueberhuber, C.W., Gunnels, J., Sexton, J.: Large-scale first-principles molecular dynamics simulations on the Blue Gene\/L platform using the Qbox code. In: Proc.\u00a0Supercomputing (SC), p. 24 (2005)","DOI":"10.2172\/883590"},{"key":"74_CR16","unstructured":"Johnson, J., Chen, K.: A self-adapting distributed memory package for fast signal transforms. In: Proc. International Parallel and Distributed Processing Symposium (IPDPS), p. 44a (2004)"},{"key":"74_CR17","doi-asserted-by":"crossref","unstructured":"Moura, J.M.F., P\u00fcschel, M., Padua, D., Dongarra, J. (eds.): Special Issue on Program Generation, Optimization, and Platform Adaptation, Proceedings of the IEEE\u00a093(2) (2005)","DOI":"10.1109\/JPROC.2004.840488"},{"key":"74_CR18","doi-asserted-by":"crossref","unstructured":"Pjesivac-Grbovic, J., Angskun, T., Bosilca, G., Fagg, G.E., Gabriel, E., Dongarra, J.: Performance analysis of MPI collective operations. Cluster Computing Journal, Special Issue on Performance Modeling and Evaluation of Parallel and Distributed Systems (accepted for publication, 2006)","DOI":"10.1007\/s10586-007-0012-0"},{"key":"74_CR19","doi-asserted-by":"crossref","unstructured":"P\u00fcschel, M., Moura, J.M.F., Johnson, J., Padua, D., Veloso, M., Singer, B.W., Xiong, J., Franchetti, F., Ga\u010di\u0107, A., Voronenko, Y., Chen, K., Johnson, R.W., Rizzolo, N.: Spiral: Code generation for DSP transforms. In: [17], pp. 232\u2013275 (2005)","DOI":"10.1109\/JPROC.2004.840306"},{"key":"74_CR20","unstructured":"Spiral web site, \n                      \n                        http:\/\/www.spiral.net"},{"key":"74_CR21","series-title":"Frontiers in Applied Mathematics","doi-asserted-by":"crossref","DOI":"10.1137\/1.9781611970999","volume-title":"Computational Frameworks for the Fast Fourier Transform","author":"C. Loan Van","year":"1992","unstructured":"Van Loan, C.: Computational Frameworks for the Fast Fourier Transform. Frontiers in Applied Mathematics, vol.\u00a010. Society for Industrial and Applied Mathematics (SIAM), Philadelphia (1992)"}],"container-title":["Lecture Notes in Computer Science","Parallel and Distributed Processing and Applications"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/11946441_74","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,19]],"date-time":"2019-05-19T12:53:43Z","timestamp":1558270423000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/11946441_74"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2006]]},"ISBN":["9783540680673","9783540680703"],"references-count":21,"URL":"https:\/\/doi.org\/10.1007\/11946441_74","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2006]]}}}