{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T10:13:43Z","timestamp":1777371223299,"version":"3.51.4"},"reference-count":37,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2014,9,26]],"date-time":"2014-09-26T00:00:00Z","timestamp":1411689600000},"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":["Int J Parallel Prog"],"published-print":{"date-parts":[[2015,12]]},"DOI":"10.1007\/s10766-014-0323-8","type":"journal-article","created":{"date-parts":[[2014,9,25]],"date-time":"2014-09-25T10:29:23Z","timestamp":1411640963000},"page":"1078-1102","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["BPLG: A Tuned Butterfly Processing Library for GPU Architectures"],"prefix":"10.1007","volume":"43","author":[{"given":"J.","family":"Lobeiras","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"M.","family":"Amor","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"R.","family":"Doallo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2014,9,26]]},"reference":[{"key":"323_CR1","unstructured":"Khronos OpenCL Working Group: The OpenCL specification (2011)"},{"key":"323_CR2","unstructured":"NVIDIA: CUDA C Best Practices Guide (SDK Document.). V5.0. (2012)"},{"key":"323_CR3","volume-title":"C++ Templates: The Complete Guide","author":"D Vandevoorde","year":"2002","unstructured":"Vandevoorde, D., Josuttis, N.M.: C++ Templates: The Complete Guide. Addison-Wesley, Boston (2002)"},{"key":"323_CR4","doi-asserted-by":"crossref","unstructured":"Bell, N.: Thrust: a productivity-oriented library for CUDA. In: GPU Computing Gems, Jade Edition. Morgan Kaufmann (2011)","DOI":"10.1016\/B978-0-12-385963-1.00026-5"},{"key":"323_CR5","unstructured":"Sander B.,: Bolt: A C++ Templater Library for HSA. Presented in AMD Fusion Developer Summit \u201912 (2012)"},{"key":"323_CR6","volume-title":"Inside the FFT Black Box: Serial and Parallel Fast Fourier Transform Algorithms. Computational Mathematics Series","author":"E Chu","year":"2000","unstructured":"Chu, E., George, A.: Inside the FFT Black Box: Serial and Parallel Fast Fourier Transform Algorithms. Computational Mathematics Series. CRC Press, Boca Raton (2000)"},{"key":"323_CR7","doi-asserted-by":"crossref","unstructured":"Hartley, R.V.L.: A more symmetrical Fourier analysis applied to transmission problems. In: Proc. of the Institute of Radio Engineers (IRE), vol. 30(3), pp. 144\u2013150 (1942)","DOI":"10.1109\/JRPROC.1942.234333"},{"issue":"1","key":"323_CR8","doi-asserted-by":"crossref","first-page":"90","DOI":"10.1109\/T-C.1974.223784","volume":"C\u201323","author":"N Ahmed","year":"1974","unstructured":"Ahmed, N., Natarajan, T., Rao, K.R.: Discrete cosine transform. IEEE Trans. Comput. C\u201323(1), 90\u201393 (1974)","journal-title":"IEEE Trans. Comput."},{"key":"323_CR9","doi-asserted-by":"crossref","unstructured":"Lobeiras, J., Amor, M., Doallo, R.: SPLG: a tuned signal processing library for GPU architectures. In: International Symposium on Computer Architecture and High Performance Computing (SBAC-PAD 2013), vol. 1, pp. 184\u2013191 (2013)","DOI":"10.1109\/SBAC-PAD.2013.30"},{"issue":"2","key":"323_CR10","doi-asserted-by":"crossref","first-page":"216","DOI":"10.1109\/JPROC.2004.840301","volume":"93","author":"M Frigo","year":"2005","unstructured":"Frigo, M., Johnson, S.G.: The design and implementation of FFTW3. Proc. IEEE 93(2), 216\u2013231 (2005)","journal-title":"Proc. IEEE"},{"key":"323_CR11","unstructured":"Intel: Intel Integrated Performance Primitives for Intel Architecture, Reference Manual. Volume 1: Signal Processing (2012)"},{"key":"323_CR12","doi-asserted-by":"crossref","unstructured":"P\u00fcschel, M., Moura, J.M.F., Johnson, J., Padua, D., Veloso, M., Singer, B., Xiong, J., Franchetti, F., Gacic, A., Voronenko, Y., Chen, K., Johnson, R.W., Rizzolo, N.: SPIRAL: code generation for DSP transforms. In: Proc. of the IEEE, on \u201cProgram Generation, Optimization, and Platform Adaptation\u201d, vol. 93(2), pp. 232\u2013275 (2005)","DOI":"10.1109\/JPROC.2004.840306"},{"key":"323_CR13","doi-asserted-by":"crossref","unstructured":"Govindaraju, N., Lloyd, B., Dotsenko, Y., Smith, B., Manferdelli, J.: High performance discrete Fourier transforms on graphics processors. In: Proc. of the 2008 ACM\/IEEE conference on Supercomputing (SC \u201908), pp. 2:1\u20132:12. IEEE Press (2008)","DOI":"10.1109\/SC.2008.5213922"},{"key":"323_CR14","unstructured":"Volkov, V., Kazian, B.: Fitting FFT onto the G80 Architecture. University of California, Berkeley, Tech. rep. (2009)"},{"key":"323_CR15","doi-asserted-by":"crossref","unstructured":"Nukada, A., Matsuoka, S.: Auto-tuning 3-D FFT Library for CUDA GPUs. In: Proc. of the Conference on High Performance Computing Networking, Storage and Analysis (SC \u201909), pp. 1\u201310 (2009)","DOI":"10.1145\/1654059.1654090"},{"key":"323_CR16","doi-asserted-by":"crossref","unstructured":"Chen, Y., Cui, X., Mei, H.: Large-scale FFT on GPU clusters. In: ICS \u201910: Proc. of the 24th ACM Intl. Conference on Supercomputing, pp. 315\u2013324 (2010)","DOI":"10.1145\/1810085.1810128"},{"key":"323_CR17","doi-asserted-by":"crossref","unstructured":"Dotsenko, Y., Baghsorkhi, S.S., Lloyd, B., Govindaraju, N.K.: Auto-tuning of fast Fourier transform on graphics processors. In: Principles and Practice of Parallel Programming (PPoPP \u201911), pp. 257\u2013266 (2011)","DOI":"10.1145\/1941553.1941589"},{"issue":"1","key":"323_CR18","doi-asserted-by":"crossref","first-page":"90","DOI":"10.1007\/s11390-013-1314-8","volume":"28","author":"Y Li","year":"2013","unstructured":"Li, Y., Zhang, Y., Liu, Y., Long, G., Jia, H.: MPFFT: an auto-tuning FFT library for OpenCL GPUs. J. Comput. Sci. Technol. 28(1), 90\u2013105 (2013)","journal-title":"J. Comput. Sci. Technol."},{"key":"323_CR19","unstructured":"NVIDIA: CUDA CUFFT Library. V5.0. (2012)"},{"key":"323_CR20","unstructured":"AMD: AMD Math Libraries, OpenCL Fast Fourier Transform (clAmdFft) (2012)"},{"key":"323_CR21","doi-asserted-by":"crossref","unstructured":"Wang B., \u00c1lvarez-Mesa M., Ching C., Juurlink B.: An optimized parallel IDCT on graphics processing units. In: 18th International Conference on Parallel Processing Workshops (EuroPar \u201912), pp. 155\u2013164. Springer, Berlin (2013)","DOI":"10.1007\/978-3-642-36949-0_18"},{"issue":"1","key":"323_CR22","first-page":"512","volume":"2","author":"M Guptda","year":"2012","unstructured":"Guptda, M., Garg, A.K.: Analysis of image compression algorithm using DCT. Int. J. Eng. Res. Appl. (IJERA) 2(1), 512\u2013521 (2012)","journal-title":"Int. J. Eng. Res. Appl. (IJERA)"},{"issue":"2","key":"323_CR23","doi-asserted-by":"crossref","first-page":"475","DOI":"10.1007\/s11042-012-1028-x","volume":"64","author":"CG Kim","year":"2013","unstructured":"Kim, C.G., Choi, Y.S.: A high performance parallel DCT with OpenCL on heterogeneous computing environment. Multimed. Tools Appl. 64(2), 475\u2013489 (2013)","journal-title":"Multimed. Tools Appl."},{"issue":"5","key":"323_CR24","first-page":"23","volume":"10","author":"M Panella","year":"2012","unstructured":"Panella, M., Basset, L.: An efficient GPU implementation of modified discrete cosine transform using CUDA. Int. J. Comput. Sci. Inf. Secur. 10(5), 23\u201330 (2012)","journal-title":"Int. J. Comput. Sci. Inf. Secur."},{"key":"323_CR25","unstructured":"Thomas, L.H.: Elliptic Problems in Linear Differential Equations over a Network. Columbia University, Tech. rep. (1949)"},{"issue":"2","key":"323_CR26","doi-asserted-by":"crossref","first-page":"177","DOI":"10.1016\/j.parco.2005.07.005","volume":"32","author":"E Polizzi","year":"2006","unstructured":"Polizzi, E., Sameh, A.H.: A parallel hybrid banded system solver: the SPIKE algorithm. Parallel Comput. 32(2), 177\u2013194 (2006)","journal-title":"Parallel Comput."},{"key":"323_CR27","unstructured":"Intel: Intel Math Kernel Library, Reference Manual. V10.2. (2009)"},{"issue":"1","key":"323_CR28","doi-asserted-by":"crossref","first-page":"22","DOI":"10.1109\/TPDS.2010.61","volume":"22","author":"D G\u00f6ddeke","year":"2011","unstructured":"G\u00f6ddeke, D., Strzodka, R.: Cyclic reduction tridiagonal solvers on GPUs applied to mixed precision multigrid. IEEE Trans. Parallel Distrib. Syst. (TPDS) 22(1), 22\u201332 (2011). (Special Issue on HPC with Accelerators)","journal-title":"IEEE Trans. Parallel Distrib. Syst. (TPDS)"},{"key":"323_CR29","doi-asserted-by":"crossref","unstructured":"Chang, L.-W., Stratton, J.A., Kim, H.-S., Hwu, W.W.: A scalable, numerically stable, high-performance tridiagonal solver using GPUs. In: Proceedings of the International Conference on High Performance Computing, Networking, Storage and Analysis (SC\u201912), pp. 27:1\u201327:11. IEEE Computer Society Press (2012)","DOI":"10.1109\/SC.2012.12"},{"key":"323_CR30","doi-asserted-by":"crossref","unstructured":"Kim, H.-S., Wu, S., Chang, L.-W., Hwu, W.W.: A scalable tridiagonal solver for GPU. In: Intl. Conf. on Parallel Processing, pp. 444\u2013453. IEEE Comp. Society (2011)","DOI":"10.1109\/ICPP.2011.41"},{"key":"323_CR31","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Cohen, J., Owens, J.D.: Fast tridiagonal solvers on the GPU. In: Proceedings of the 15th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming (PPoPP 2010), pp. 127\u2013136 (2010)","DOI":"10.1145\/1693453.1693472"},{"key":"323_CR32","unstructured":"CUDA Data Parallel Primitives Library. V2.1. (2013)"},{"key":"323_CR33","unstructured":"NVIDIA: CUSPARSE Library. V5.0. (2012)"},{"key":"323_CR34","doi-asserted-by":"crossref","unstructured":"Wang, X., Mou, Z.G.: A divide-and-conquer method of solving tridiagonal systems on hypercube massively parallel computers. In: IEEE Symposium on Parallel and Distributed Processing, pp. 810\u2013817 (1991)","DOI":"10.1109\/SPDP.1991.218237"},{"issue":"90","key":"323_CR35","doi-asserted-by":"crossref","first-page":"297","DOI":"10.1090\/S0025-5718-1965-0178586-1","volume":"19","author":"JW Cooley","year":"1965","unstructured":"Cooley, J.W., Tukey, J.W.: An algorithm for the machine calculation of complex fourier series. Math. Comput. 19(90), 297\u2013301 (1965)","journal-title":"Math. Comput."},{"key":"323_CR36","doi-asserted-by":"crossref","unstructured":"Stockham, T.G.: High-speed convolution and correlation. In: Proceedings of the Spring Joint Computer Conference, pp. 229\u2013233 (1966)","DOI":"10.1145\/1464182.1464209"},{"key":"323_CR37","volume-title":"The Regularized Fast Hartley Transform. Signals and Communication Technology","author":"J Keith","year":"2010","unstructured":"Keith, J.: The Regularized Fast Hartley Transform. Signals and Communication Technology. Springer, Berlin (2010)"}],"container-title":["International Journal of Parallel Programming"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10766-014-0323-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10766-014-0323-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10766-014-0323-8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,4]],"date-time":"2025-05-04T20:27:12Z","timestamp":1746390432000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10766-014-0323-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,9,26]]},"references-count":37,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2015,12]]}},"alternative-id":["323"],"URL":"https:\/\/doi.org\/10.1007\/s10766-014-0323-8","relation":{},"ISSN":["0885-7458","1573-7640"],"issn-type":[{"value":"0885-7458","type":"print"},{"value":"1573-7640","type":"electronic"}],"subject":[],"published":{"date-parts":[[2014,9,26]]}}}