{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,22]],"date-time":"2025-02-22T17:10:28Z","timestamp":1740244228602,"version":"3.37.3"},"publisher-location":"Berlin, Heidelberg","reference-count":29,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783540254249"},{"type":"electronic","value":"9783540318545"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2005]]},"DOI":"10.1007\/11403937_3","type":"book-chapter","created":{"date-parts":[[2010,7,5]],"date-time":"2010-07-05T20:46:11Z","timestamp":1278362771000},"page":"23-36","source":"Crossref","is-referenced-by-count":1,"title":["Automatically Tuned FFTs for BlueGene\/L\u2019s Double FPU"],"prefix":"10.1007","author":[{"given":"Franz","family":"Franchetti","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Stefan","family":"Kral","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":"3_CR1","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"543","DOI":"10.1007\/978-3-540-45209-6_79","volume-title":"Euro-Par 2003 Parallel Processing","author":"G.S. Alm\u00e1si","year":"2003","unstructured":"Alm\u00e1si, G.S., Bellofatto, R., Brunheroto, J.R., Ca\u015fcaval, C., Casta\u00f1os, J.G., Ceze, L., Crumley, P., Erway, C.C., Gagliano, J., Lieber, D., Martorell, X., Moreira, J.E., Sanomiya, A., Strauss, K.: An overview of the blue gene\/L system software organization. In: Kosch, H., B\u00f6sz\u00f6rm\u00e9nyi, L., Hellwagner, H. (eds.) Euro-Par 2003. LNCS, vol.\u00a02790, pp. 543\u2013555. Springer, Heidelberg (2003)"},{"key":"3_CR2","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"399","DOI":"10.1007\/3-540-44905-1_25","volume-title":"Languages and Compilers for Parallel Computing","author":"R.J. Fisher","year":"2000","unstructured":"Fisher, R.J., Dietz, H.G.: The scc compiler: SWARing at MMX and 3DNow. In: Carter, L., Ferrante, J. (eds.) LCPC 1999. LNCS, vol.\u00a01863, pp. 399\u2013414. Springer, Heidelberg (2000)"},{"key":"3_CR3","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"290","DOI":"10.1007\/3-540-48319-5_19","volume-title":"Languages and Compilers for Parallel Computing","author":"R.J. Fisher","year":"1999","unstructured":"Fisher, R.J., Dietz, H.G.: Compiling for SIMD within a register. In: Carter, L., Ferrante, J., Sehr, D., Chatterjee, S., Prins, J.F., Li, Z., Yew, P.-C. (eds.) LCPC 1998. LNCS, vol.\u00a01656, pp. 290\u2013304. Springer, Heidelberg (1999)"},{"unstructured":"Franchetti, F.: A portable short vector version of fftw. In: Proc. Fourth IMACS Symposium on Mathematical Modelling (MATHMOD 2003), vol.\u00a02, pp. 1539\u20131548 (2003)","key":"3_CR4"},{"key":"3_CR5","first-page":"1109","volume":"2","author":"F. Franchetti","year":"2001","unstructured":"Franchetti, F., Karner, H., Kral, S., Ueberhuber, C.W.: Architecture independent short vector FFTs. In: Proc.\u00a0ICASSP, vol.\u00a02, pp. 1109\u20131112 (2001)","journal-title":"Proc.\u00a0ICASSP"},{"doi-asserted-by":"crossref","unstructured":"Franchetti, F., Kral, S., Lorenz, J., Ueberhuber, C.W.: Efficient Utilization of SIMD Extensions. In: IEEE Proceedings Special Issue on Program Generation, Optimization, and Platform Adaption (to appear)","key":"3_CR6","DOI":"10.1109\/JPROC.2004.840491"},{"doi-asserted-by":"crossref","unstructured":"Franchetti, F., P\u00fcschel, M.: A SIMD Vectorizing Compiler for Digital Signal Processing Algorithms. In: Proc.\u00a0IPDPS, pp. 20\u201326 (2002)","key":"3_CR7","DOI":"10.1109\/IPDPS.2002.1015494"},{"doi-asserted-by":"crossref","unstructured":"Franchetti, F., P\u00fcschel, M.: Short vector code generation and adaptation for DSP algorithms. In: Proceedings of the International Conerence on Acoustics, Speech, and Signal Processing, Conference Proceedings (ICASSP 2003), vol.\u00a02, pp. 537\u2013540 (2003)","key":"3_CR8","DOI":"10.1109\/ICASSP.2003.1202422"},{"doi-asserted-by":"crossref","unstructured":"Franchetti, F., P\u00fcschel, M.: Short vector code generation for the discrete Fourier transform. In: Proceedings of the 17th International Parallel and Distributed Processing Symposium (IPDPS 2003), pp. 58\u201367 (2003)","key":"3_CR9","DOI":"10.1109\/IPDPS.2003.1213153"},{"key":"3_CR10","doi-asserted-by":"publisher","first-page":"169","DOI":"10.1145\/301618.301661","volume-title":"Proceedings of the ACM SIGPLAN 1999 Conference on Programming Language Design and Implementation","author":"M. Frigo","year":"1999","unstructured":"Frigo, M.: A fast Fourier transform compiler. In: Proceedings of the ACM SIGPLAN 1999 Conference on Programming Language Design and Implementation, pp. 169\u2013180. ACM Press, New York (1999)"},{"unstructured":"Frigo, M., Kral, S.: The Advanced FFT Program Generator genfft. In:aurora Technical Report TR2001-2003, vol.\u00a03 (2001)","key":"3_CR11"},{"doi-asserted-by":"crossref","unstructured":"Frigo, M., Johnson, S.G.: fftw: An Adaptive Software Architecture for the FFT. In: ICASSP 1998, vol.\u00a03, pp. 1381\u20131384 (1998)","key":"3_CR12","DOI":"10.1109\/ICASSP.1998.681704"},{"unstructured":"Intel. Corporation, Intel. C\/C++ compiler user\u2019s guide (2002)","key":"3_CR13"},{"doi-asserted-by":"crossref","unstructured":"Johnson, J., Johnson, R.W., Rodriguez, D., Tolimieri, R.: A methodology for designing, modifying, and implementing Fourier transform algorithms on various architectures. In: IEEE Trans. on Circuits and Systems, vol.\u00a09, pp. 449\u2013500 (1990)","key":"3_CR14","DOI":"10.1007\/BF01189337"},{"key":"3_CR15","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"251","DOI":"10.1007\/978-3-540-45209-6_39","volume-title":"Euro-Par 2003 Parallel Processing","author":"S. Kral","year":"2003","unstructured":"Kral, S., Franchetti, F., Lorenz, J., Ueberhuber, C.: SIMD vectorization of straight line FFT code. In: Kosch, H., B\u00f6sz\u00f6rm\u00e9nyi, L., Hellwagner, H. (eds.) Euro-Par 2003. LNCS, vol.\u00a02790, pp. 251\u2013260. Springer, Heidelberg (2003)"},{"key":"3_CR16","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"crossref","first-page":"217","DOI":"10.1007\/b13482","volume-title":"Proceedings of the 13th International Conference on Compiler Construction LNCS 2790","author":"S. Kral","year":"2003","unstructured":"Kral, S., Franchetti, F., Lorenz, J., Ueberhuber, C.: FFT compiler techniques. In: Kosch, H., B\u00f6sz\u00f6rm\u00e9nyi, L., Hellwagner, H. (eds.) Euro-Par 2003. LNCS, vol.\u00a02790, pp. 217\u2013231. Springer, Heidelberg (2003)"},{"unstructured":"Lamson, S.: Sciport (1995), Available: http:\/\/www.netlib.org\/scilib\/","key":"3_CR17"},{"issue":"5","key":"3_CR18","doi-asserted-by":"publisher","first-page":"145","DOI":"10.1145\/358438.349320","volume":"35","author":"S. Larsen","year":"2000","unstructured":"Larsen, S., Amarasinghe, S.: Exploiting superword level parallelism with multimedia instruction sets. ACM SIGPLAN Notices\u00a035(5), 145\u2013156 (2000)","journal-title":"ACM SIGPLAN Notices"},{"issue":"4","key":"3_CR19","doi-asserted-by":"publisher","first-page":"794","DOI":"10.1145\/362652.362661","volume":"5","author":"R. Leupers","year":"2000","unstructured":"Leupers, R., Bashford, S.: Graph-based code selection techniques for embedded processors. ACM Transactions on Design Automation of Electronic Systems\u00a05(4), 794\u2013814 (2000)","journal-title":"ACM Transactions on Design Automation of Electronic Systems"},{"unstructured":"Lorenz, J., Kral, S., Franchetti, F., Ueberhuber, C.W.: Vectorization Techniques for BlueGene\/L\u2019s Double FPU. IBM Journal of Research and Development (to appear)","key":"3_CR20"},{"doi-asserted-by":"crossref","unstructured":"Lorenz, M., Wehmeyer, L., Draeger, T.: Energy aware compilation for DSPs with SIMD instructions. In: Proceedings of the 2002 Joint Conference on Languages, Compilers, and Tools for Embedded Systems & Software and Compilers for Embedded Systems (LCTES\u201902-SCOPES 2002), pp. 94\u2013101 (2002)","key":"3_CR21","DOI":"10.1145\/513829.513847"},{"doi-asserted-by":"crossref","unstructured":"Mirkovic, D., Johnsson, S.L.: Automatic Performance Tuning in the UHFFT Library. In: Proc. ICCS 2001, pp. 71\u201380 (2001)","key":"3_CR22","DOI":"10.1007\/3-540-45545-0_17"},{"key":"3_CR23","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1177\/1094342004041291","volume":"18","author":"M. P\u00fcschel","year":"2004","unstructured":"P\u00fcschel, M., Singer, B., Xiong, J., Moura, J.M.F., Johnson, J., Padua, D., Veloso, M., Johnson, R.W.: Spiral: A generator for platform-adapted libraries of signal processing algorithms. Journal on High Performance Computing and Applications, special issue on Automatic Performance Tuning\u00a018, 21\u201345 (2004)","journal-title":"Journal on High Performance Computing and Applications, special issue on Automatic Performance Tuning"},{"issue":"4","key":"3_CR24","doi-asserted-by":"publisher","first-page":"363","DOI":"10.1023\/A:1007559022013","volume":"28","author":"N. Sreraman","year":"2000","unstructured":"Sreraman, N., Govindarajan, R.: A vectorizing compiler for multimedia extensions. International Journal of Parallel Programming\u00a028(4), 363\u2013400 (2000)","journal-title":"International Journal of Parallel Programming"},{"key":"3_CR25","doi-asserted-by":"publisher","first-page":"45","DOI":"10.1016\/S0167-8191(84)90413-7","volume":"1","author":"P.N. Swarztrauber","year":"1984","unstructured":"Swarztrauber, P.N.: FFT algorithms for vector computers. Parallel Comput.\u00a01, 45\u201363 (1984)","journal-title":"Parallel Comput"},{"doi-asserted-by":"crossref","unstructured":"Van Loan, C.F.: Computational Frameworks for the Fast Fourier Transform. Ser. Frontiers in Applied Mathematics, vol. 10. Society for Industrial and Applied Mathematics, Philadelphia (1992)","key":"3_CR26","DOI":"10.1137\/1.9781611970999"},{"key":"3_CR27","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1016\/S0167-8191(00)00087-9","volume":"27","author":"R.C. Whaley","year":"2001","unstructured":"Whaley, R.C., Petitet, A., Dongarra, J.J.: Automated empirical optimizations of software and the atlas project. Parallel Comput.\u00a027, 3\u201335 (2001)","journal-title":"Parallel Comput"},{"doi-asserted-by":"crossref","unstructured":"Xiong, J., Johnson, J., Johnson, R., Padua, D.: SPL: A Language and Compiler for DSP Algorithms. In: Proceedings of the Conference on Programming Languages Design and Implementation (PLDI), pp. 298\u2013308 (2001)","key":"3_CR28","DOI":"10.1145\/378795.378860"},{"key":"3_CR29","volume-title":"Supercompilers for Parallel and Vector Computers","author":"H. Zima","year":"1991","unstructured":"Zima, H., Chapman, B.: Supercompilers for Parallel and Vector Computers. ACM Press, New York (1991)"}],"container-title":["Lecture Notes in Computer Science","High Performance Computing for Computational Science - VECPAR 2004"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/11403937_3.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,22]],"date-time":"2025-02-22T16:43:21Z","timestamp":1740242601000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/11403937_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2005]]},"ISBN":["9783540254249","9783540318545"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/11403937_3","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2005]]}}}