{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T14:29:35Z","timestamp":1743085775743,"version":"3.40.3"},"publisher-location":"Cham","reference-count":41,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030024642"},{"type":"electronic","value":"9783030024659"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"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":[[2018]]},"DOI":"10.1007\/978-3-030-02465-9_22","type":"book-chapter","created":{"date-parts":[[2019,1,24]],"date-time":"2019-01-24T20:06:48Z","timestamp":1548360408000},"page":"329-346","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Comparing Controlflow and Dataflow for Tensor Calculus: Speed, Power, Complexity, and MTBF"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6459-0087","authenticated-orcid":false,"given":"Milos","family":"Kotlar","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9380-5232","authenticated-orcid":false,"given":"Veljko","family":"Milutinovic","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,1,25]]},"reference":[{"key":"22_CR1","unstructured":"Abadi, M., et al.: TensorFlow: a system for large-scale machine learning. In: OSDI, vol. 16, pp. 265\u2013283 (2016)"},{"issue":"1","key":"22_CR2","first-page":"2773","volume":"15","author":"A Anandkumar","year":"2014","unstructured":"Anandkumar, A., Ge, R., Hsu, D., Kakade, S.M., Telgarsky, M.: Tensor decompositions for learning latent variable models. J. Mach. Learn. Res. 15(1), 2773\u20132832 (2014)","journal-title":"J. Mach. Learn. Res."},{"key":"22_CR3","doi-asserted-by":"crossref","unstructured":"Auth, C., et al.: A 10 nm high performance and low-power CMOS technology featuring 3rd generation FinFET transistors, Self-Aligned Quad Patterning, contact over active gate and cobalt local interconnects. In: 2017 IEEE International on Electron Devices Meeting (IEDM), p. 29-1. IEEE (2017)","DOI":"10.1109\/IEDM.2017.8268472"},{"issue":"1","key":"22_CR4","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1007\/s007800050032","volume":"2","author":"OE Barndorff-Nielsen","year":"1997","unstructured":"Barndorff-Nielsen, O.E.: Processes of normal inverse Gaussian type. Finan. Stochast. 2(1), 41\u201368 (1997)","journal-title":"Finan. Stochast."},{"key":"22_CR5","doi-asserted-by":"crossref","unstructured":"Baskin, C., Liss, N., Mendelson, A., Zheltonozhskii, E.: Streaming architecture for large-scale quantized neural networks on an FPGA-based dataflow platform. arXiv preprint \n                      arXiv:1708.00052\n                      \n                     (2017)","DOI":"10.1109\/IPDPSW.2018.00032"},{"key":"22_CR6","unstructured":"Brillouin, L.: Tensors in mechanics and elasficify (1964)"},{"key":"22_CR7","doi-asserted-by":"crossref","unstructured":"Coppersmith, D., Winograd, S.: Matrix multiplication via arithmetic progressions. In: Proceedings of the Nineteenth Annual ACM Symposium on Theory of Computing, p. 16. ACM (1987)","DOI":"10.1145\/28395.28396"},{"issue":"2","key":"22_CR8","doi-asserted-by":"publisher","first-page":"430","DOI":"10.17706\/IJCEE.2017.9.2.430-438","volume":"9","author":"T Dobravec","year":"2017","unstructured":"Dobravec, T., Bulic, P.: Comparing CPU and GPU implementations of a simple matrix multiplication algorithm. Int. J. Comput. Electr. Eng. 9(2), 430\u2013439 (2017)","journal-title":"Int. J. Comput. Electr. Eng."},{"key":"22_CR9","volume-title":"Relativity: The Special and The General Theory","author":"A Einstein","year":"2015","unstructured":"Einstein, A.: Relativity: The Special and The General Theory. Princeton University Press, Princeton (2015)"},{"issue":"1","key":"22_CR10","doi-asserted-by":"publisher","first-page":"333","DOI":"10.1137\/0613024","volume":"13","author":"JR Gilbert","year":"1992","unstructured":"Gilbert, J.R., Moler, C., Schreiber, R.: Sparse matrices in MATLAB: design and implementation. SIAM J. Matrix Anal. Appl. 13(1), 333\u2013356 (1992)","journal-title":"SIAM J. Matrix Anal. Appl."},{"issue":"5","key":"22_CR11","doi-asserted-by":"publisher","first-page":"403","DOI":"10.1007\/BF02163027","volume":"14","author":"GH Golub","year":"1970","unstructured":"Golub, G.H., Reinsch, C.: Singular value decomposition and least squares solutions. Numerische Mathematik 14(5), 403\u2013420 (1970)","journal-title":"Numerische Mathematik"},{"issue":"6","key":"22_CR12","doi-asserted-by":"publisher","first-page":"45","DOI":"10.1145\/2512329","volume":"60","author":"CJ Hillar","year":"2013","unstructured":"Hillar, C.J., Lim, L.H.: Most tensor problems are NP-hard. J. ACM (JACM) 60(6), 45 (2013)","journal-title":"J. ACM (JACM)"},{"issue":"5","key":"22_CR13","doi-asserted-by":"publisher","first-page":"1460","DOI":"10.1016\/j.jcss.2011.12.025","volume":"78","author":"D Hsu","year":"2012","unstructured":"Hsu, D., Kakade, S.M., Zhang, T.: A spectral algorithm for learning hidden Markov models. J. Comput. Syst. Sci. 78(5), 1460\u20131480 (2012)","journal-title":"J. Comput. Syst. Sci."},{"key":"22_CR14","doi-asserted-by":"crossref","unstructured":"Blagojevic, V., et al.: A systematic approach to generation of new ideas for PhD research in computing. In: Advances in Computers, vol. 104, pp. 1\u201319. Elsevier (2016)","DOI":"10.1016\/bs.adcom.2016.09.001"},{"key":"22_CR15","doi-asserted-by":"crossref","unstructured":"Milutinovic, V., et al.: A new course on R&D project management in computer science and engineering: subjects taught, rationales behind, and lessons learned. In: Advances in Computers, vol. 106, pp. 1\u201319. Elsevier (2017)","DOI":"10.1016\/bs.adcom.2017.04.001"},{"key":"22_CR16","doi-asserted-by":"crossref","unstructured":"Stojanovic, S., Bojic, D., Bojovic, M.: An overview of selected heterogeneous and reconfigurable architectures. In: Advances in Computers, vol. 96, pp. 1\u201345. Elsevier (2015)","DOI":"10.1016\/bs.adcom.2014.11.003"},{"key":"22_CR17","unstructured":"Janzamin, M., Sedghi, H., Anandkumar, A.: Beating the perils of non-convexity: guaranteed training of neural networks using tensor methods. arXiv preprint \n                      arXiv:1506.08473\n                      \n                     (2015)"},{"key":"22_CR18","volume-title":"Matrix Computation","author":"A Jennings","year":"1992","unstructured":"Jennings, A., McKeown, J.J.: Matrix Computation. Wiley, Hoboken (1992)"},{"issue":"4","key":"22_CR19","doi-asserted-by":"publisher","first-page":"249","DOI":"10.1049\/iet-cdt.2011.0132","volume":"6","author":"\u017d Jovanovi\u0107","year":"2012","unstructured":"Jovanovi\u0107, \u017d., Milutinovi\u0107, V.: FPGA accelerator for floating-point matrix multiplication. IET Comput. Digit. Tech. 6(4), 249\u2013256 (2012)","journal-title":"IET Comput. Digit. Tech."},{"key":"22_CR20","doi-asserted-by":"crossref","unstructured":"Kaisler, S., Armour, F., Espinosa, J.A., Money, W.: Big data: issues and challenges moving forward. In: 2013 46th Hawaii International Conference on System Sciences (HICSS), pp. 995\u20131004. IEEE (2013)","DOI":"10.1109\/HICSS.2013.645"},{"key":"22_CR21","unstructured":"Kanellos, M.: 152,000 smart devices every minute in 2025: IDC outlines the future of smart things. Forbes.com (2016)"},{"key":"22_CR22","doi-asserted-by":"crossref","unstructured":"Karatzoglou, A., Amatriain, X., Baltrunas, L., Oliver, N.: Multiverse recommendation: n-dimensional tensor factorization for context-aware collaborative filtering. In: Proceedings of the Fourth ACM Conference on Recommender systems, pp. 79\u201386. ACM (2010)","DOI":"10.1145\/1864708.1864727"},{"issue":"3","key":"22_CR23","doi-asserted-by":"publisher","first-page":"308","DOI":"10.1145\/355841.355847","volume":"5","author":"CL Lawson","year":"1979","unstructured":"Lawson, C.L., Hanson, R.J., Kincaid, D.R., Krogh, F.T.: Basic linear algebra subprograms for FORTRAN usage. ACM Trans. Math. Softw. (TOMS) 5(3), 308\u2013323 (1979)","journal-title":"ACM Trans. Math. Softw. (TOMS)"},{"key":"22_CR24","doi-asserted-by":"publisher","DOI":"10.1137\/1.9780898719512","volume-title":"Matrix Analysis and Applied Linear Algebra","author":"CD Meyer","year":"2000","unstructured":"Meyer, C.D.: Matrix Analysis and Applied Linear Algebra, vol. 71. SIAM, Philadelphia (2000)"},{"key":"22_CR25","first-page":"1","volume":"11","author":"E Miller","year":"2009","unstructured":"Miller, E., Ladenheim, S., Martin, C.: Higher order tensor operations and their applications. TCNJ J. Stud. Sch. 11, 1\u201315 (2009)","journal-title":"TCNJ J. Stud. Sch."},{"key":"22_CR26","unstructured":"Milutinovic, D., Milutinovic, V., Soucek, B.: The honeycomb architecture (1987)"},{"key":"22_CR27","unstructured":"Milutinovic, V., et al.: Splitting spatial and temporal localities for entropy minimiation. Tutorial of the IEEE ISCA (1995)"},{"issue":"5","key":"22_CR28","doi-asserted-by":"publisher","first-page":"538","DOI":"10.1109\/26.1469","volume":"36","author":"V Milutinovic","year":"1988","unstructured":"Milutinovic, V.: A comparison of suboptimal detection algorithms applied to the additive mix of orthogonal sinusoidal signals. IEEE Trans. Commun. 36(5), 538\u2013543 (1988)","journal-title":"IEEE Trans. Commun."},{"key":"22_CR29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-66125-4","volume-title":"DataFlow Supercomputing Essentials","author":"V Milutinovic","year":"2017","unstructured":"Milutinovic, V., Kotlar, M., Stojanovic, M., Dundic, I., Trifunovic, N., Babovic, Z.: DataFlow Supercomputing Essentials. Springer, Cham (2017). \n                      https:\/\/doi.org\/10.1007\/978-3-319-66125-4"},{"key":"22_CR30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-16229-4","volume-title":"Guide to DataFlow Supercomputing","author":"V Milutinovi\u0107","year":"2015","unstructured":"Milutinovi\u0107, V., Salom, J., Trifunovi\u0107, N., Giorgi, R.: Guide to DataFlow Supercomputing. Springer, Cham (2015). \n                      https:\/\/doi.org\/10.1007\/978-3-319-16229-4"},{"key":"22_CR31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-66128-5","volume-title":"DataFlow Supercomputing Essentials","author":"V Milutinovic","year":"2017","unstructured":"Milutinovic, V., Salom, J., Veljovic, D., Korolija, N., Markovic, D., Petrovic, L.: DataFlow Supercomputing Essentials. Springer, Cham (2017). \n                      https:\/\/doi.org\/10.1007\/978-3-319-66128-5"},{"key":"22_CR32","doi-asserted-by":"crossref","unstructured":"Nurvitadhi, E., et al.: Can FPGAS beat GPUS in accelerating next-generation deep neural networks? In: Proceedings of the 2017 ACM\/SIGDA International Symposium on Field-Programmable Gate Arrays, pp. 5\u201314. ACM (2017)","DOI":"10.1145\/3020078.3021740"},{"key":"22_CR33","unstructured":"Rupp, K., et al.: Years of microprocessor trend data. \n                      http:\/\/www.karlrupp.net\/wp-content\/uploads\/2015.06\/40-years-processor-trend.png\n                      \n                     (40)"},{"key":"22_CR34","first-page":"012022","volume":"78","author":"B Schroeder","year":"2007","unstructured":"Schroeder, B., Gibson, G.A.: Understanding failures in petascale computers. J. Phys.: Conf. Ser. 78, 012022 (2007)","journal-title":"J. Phys.: Conf. Ser."},{"issue":"1","key":"22_CR35","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s40537-015-0038-8","volume":"3","author":"N Trifunovic","year":"2016","unstructured":"Trifunovic, N., Milutinovic, V., et al.: The AppGallery.Maxeler.com for bigdata supercomputing. J. Big Data 3(1), 1\u20139 (2016)","journal-title":"J. Big Data"},{"issue":"1","key":"22_CR36","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1186\/s40537-014-0010-z","volume":"2","author":"N Trifunovic","year":"2015","unstructured":"Trifunovic, N., Milutinovic, V., Salom, J., Kos, A.: Paradigm shift in big data SuperComputing: DataFlow vs. ControlFlow. J. Big Data 2(1), 4 (2015)","journal-title":"J. Big Data"},{"issue":"1","key":"22_CR37","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2983387","volume":"49","author":"R Trobec","year":"2016","unstructured":"Trobec, R., Vasiljevic, R., Tomasevic, M., Milutinovic, V., et al.: Interconnection networks for petacomputing. ACM Comput. Surv. 49(1), 1\u201324 (2016)","journal-title":"ACM Comput. Surv."},{"key":"22_CR38","unstructured":"Tuffley, D.: Google\u2019s release of TensorFlow could be a gamechanger in the future of AI (2015)"},{"key":"22_CR39","doi-asserted-by":"crossref","unstructured":"Voss, N., Bacis, M., Mencer, O., Gaydadjiev, G., Luk, W.: Convolutional neural networks on dataflow engines. In: 2017 IEEE International Conference on Computer Design (ICCD), pp. 435\u2013438. IEEE (2017)","DOI":"10.1109\/ICCD.2017.77"},{"key":"22_CR40","doi-asserted-by":"crossref","unstructured":"Wu, K.C., Tsai, Y.W.: Structured ASIC, evolution or revolution? In: Proceedings of the 2004 International Symposium on Physical Design, pp. 103\u2013106. ACM (2004)","DOI":"10.1145\/981066.981088"},{"issue":"6","key":"22_CR41","doi-asserted-by":"publisher","first-page":"929","DOI":"10.1109\/TPAMI.2005.110","volume":"27","author":"J Ye","year":"2005","unstructured":"Ye, J., Li, Q.: A two-stage linear discriminant analysis via QR-decomposition. IEEE Trans. Pattern Anal. Mach. Intell. 27(6), 929\u2013941 (2005)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."}],"container-title":["Lecture Notes in Computer Science","High Performance Computing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-02465-9_22","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,20]],"date-time":"2019-05-20T05:02:57Z","timestamp":1558328577000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-02465-9_22"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030024642","9783030024659"],"references-count":41,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-02465-9_22","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2018]]},"assertion":[{"value":"25 January 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ISC High Performance","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on High Performance Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Frankfurt","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Germany","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2018","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24 June 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 June 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"33","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"supercomputing2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.isc-hpc.com\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}