{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T07:44:29Z","timestamp":1740123869855,"version":"3.37.3"},"reference-count":35,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2017,5,10]],"date-time":"2017-05-10T00:00:00Z","timestamp":1494374400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"FP7 FASTER","award":["#287804","#287804"],"award-info":[{"award-number":["#287804","#287804"]}]},{"DOI":"10.13039\/501100007601","name":"Horizon 2020","doi-asserted-by":"publisher","award":["671653"],"award-info":[{"award-number":["671653"]}],"id":[{"id":"10.13039\/501100007601","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Parallel Prog"],"published-print":{"date-parts":[[2018,12]]},"DOI":"10.1007\/s10766-017-0494-1","type":"journal-article","created":{"date-parts":[[2017,5,10]],"date-time":"2017-05-10T03:19:01Z","timestamp":1494386341000},"page":"1185-1219","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["The Case for Polymorphic Registers in Dataflow Computing"],"prefix":"10.1007","volume":"46","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3329-3773","authenticated-orcid":false,"given":"C\u0103t\u0103lin Bogdan","family":"Ciobanu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Georgi","family":"Gaydadjiev","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Christian","family":"Pilato","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Donatella","family":"Sciuto","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2017,5,10]]},"reference":[{"issue":"2","key":"494_CR1","doi-asserted-by":"crossref","first-page":"10","DOI":"10.1109\/MM.2006.41","volume":"26","author":"M Gschwind","year":"2006","unstructured":"Gschwind, M., Hofstee, H., Flachs, B., Hopkin, M., Watanabe, Y., Yamazaki, T.: Synergistic processing in Cell\u2019s Multicore Architecture. IEEE Micro 26(2), 10\u201324 (2006)","journal-title":"IEEE Micro"},{"key":"494_CR2","unstructured":"Maxeler MaxWorkstation. http:\/\/www.maxeler.com\/products\/desktop\/"},{"key":"494_CR3","doi-asserted-by":"crossref","unstructured":"Tomas, C., Cazzola, L., Oriato, D., Pell, O., Theis, D., Satta, G., Bonomi, E.: Acceleration of the anisotropic PSPI imaging algorithm with Dataflow Engines. In: Society of Exploration Geophysicists (SEG) Technical Program Expanded Abstracts, pp. 1\u20135 (2012)","DOI":"10.1190\/segam2012-1282.1"},{"issue":"1","key":"494_CR4","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1155\/2009\/382983","volume":"2009","author":"H Fu","year":"2009","unstructured":"Fu, H., Osborne, W., Clapp, R., Mencer, O., Luk, W.: Accelerating seismic computations using customized number representations on FPGAs. EURASIP J. Embed. Syst. 2009(1), 1\u201313 (2009)","journal-title":"EURASIP J. Embed. Syst."},{"key":"494_CR5","unstructured":"Ciobanu, C.: Customizable Register Files for Multidimensional SIMD Architectures. PhD Thesis, Delft University of Technology, Delft, March (2013)"},{"key":"494_CR6","unstructured":"The LLVM Compiler Infrastructure. http:\/\/llvm.org"},{"issue":"5","key":"494_CR7","doi-asserted-by":"crossref","first-page":"16","DOI":"10.1109\/MM.2010.79","volume":"30","author":"A Ramirez","year":"2010","unstructured":"Ramirez, A., Cabarcas, F., Juurlink, B., Alvarez Mesa, M., Sanchez, F., Azevedo, A., Meenderinck, C., Ciobanu, C., Isaza, S., Gaydadjiev, G.: The SARC architecture. IEEE Micro 30(5), 16\u201329 (2010)","journal-title":"IEEE Micro"},{"key":"494_CR8","doi-asserted-by":"crossref","unstructured":"Ciobanu, C., Kuzmanov, G.K., Ramirez, A., Gaydadjiev, G.N.: A Polymorphic Register File for matrix operations. In: Proceedings of SAMOS, pp. 241\u2013249. July (2010)","DOI":"10.1109\/ICSAMOS.2010.5642059"},{"key":"494_CR9","doi-asserted-by":"crossref","unstructured":"Ciobanu, C., Kuzmanov, G.K., Gaydadjiev, G.N.: On implementability of Polymorphic Register Files. In: Proceedings of ReCoSoC, pp. 1\u20136 (2012)","DOI":"10.1109\/ReCoSoC.2012.6322873"},{"key":"494_CR10","doi-asserted-by":"crossref","unstructured":"Ciobanu, C., Kuzmanov, G.K., Gaydadjiev, G.N.: Scalability study of Polymorphic Register Files. In: Proceedings of DSD, pp. 803\u2013808 (2012)","DOI":"10.1109\/DSD.2012.116"},{"key":"494_CR11","doi-asserted-by":"crossref","unstructured":"Ciobanu, C., Martorell, X., Kuzmanov, G.K., Ramirez, A., Gaydadjiev, G.N.: Scalability evaluation of a Polymorphic Register File: a CG case study. In: Proceedings of ARCS, pp. 13\u201325 (2011)","DOI":"10.1007\/978-3-642-19137-4_2"},{"key":"494_CR12","doi-asserted-by":"crossref","unstructured":"Ciobanu, C., Gaydadjiev, G.: Separable 2D Convolution with Polymorphic Register Files. In: Proceedings of ARCS, pp. 317\u2013328 (2013)","DOI":"10.1007\/978-3-642-36424-2_27"},{"issue":"5","key":"494_CR13","doi-asserted-by":"crossref","first-page":"363","DOI":"10.1109\/TC.1982.1676014","volume":"C\u201331","author":"D Kuck","year":"1982","unstructured":"Kuck, D., Stokes, R.: The Burroughs Scientific Processor (BSP). IEEE Trans. Comput. C\u201331(5), 363\u2013376 (1982)","journal-title":"IEEE Trans. Comput."},{"key":"494_CR14","doi-asserted-by":"crossref","unstructured":"Juurlink, B., Cheresiz, D., Vassiliadis, S., Wijshoff, H.A.G.: Implementation and Evaluation of the Complex Streamed Instruction Set. In: Proceedings of PACT, pp. 73\u201382 (2001)","DOI":"10.1109\/PACT.2001.953289"},{"key":"494_CR15","doi-asserted-by":"crossref","unstructured":"Panda, D., Hwang, K.: Reconfigurable Vector Register Windows for fast matrix computation on the orthogonal multiprocessor. In: Proceedings of ASAP, pp. 202\u2013213, 5\u20137 (1990)","DOI":"10.1109\/ASAP.1990.145457"},{"key":"494_CR16","doi-asserted-by":"crossref","unstructured":"Corbal, J., Espasa, R., Valero, M.: MOM: a matrix SIMD Instruction Set Architecture for multimedia applications. In: Proceedings of the ACM\/IEEE SC99 Conference, pp. 1\u201312 (1999)","DOI":"10.1145\/331532.331547"},{"key":"494_CR17","doi-asserted-by":"crossref","unstructured":"Shahbahrami, A., Juurlink, B., Vassiliadis, S.: Matrix Register File and extended subwords: two techniques for embedded media processors. In: Computing Frontiers \u201905, pp. 171\u2013180. May (2005)","DOI":"10.1145\/1062261.1062291"},{"key":"494_CR18","doi-asserted-by":"crossref","unstructured":"Derby, J.H., Montoye, R.K., Moreira, J.: VICTORIA: VMX indirect compute technology oriented towards in-line acceleration. In: Proceedings of CF, pp. 303\u2013312 (2006)","DOI":"10.1145\/1128022.1128062"},{"key":"494_CR19","doi-asserted-by":"crossref","unstructured":"Park, J., Park, S.-B., Balfour, J.D., Black-Schaffer, D., Kozyrakis, C., Dally, W.J.: Register Pointer Architecture for efficient embedded processors. In: Proceedings of DATE, pp. 600\u2013605 (2007)","DOI":"10.1109\/DATE.2007.364659"},{"key":"494_CR20","doi-asserted-by":"crossref","unstructured":"Osburn, J., Anderson, W., Rosenberg, R., Lanzagorta, M.: Early experiences on the NRL Cray XD1. In: HPCMP Users Group Conference, pp. 347\u2013353 (2006)","DOI":"10.1109\/HPCMP-UGC.2006.21"},{"key":"494_CR21","unstructured":"Cray XR1 Reconfigurable Processing Blade. http:\/\/www.cray.com\/Assets\/PDF\/products\/xt\/CrayXR1Blade"},{"key":"494_CR22","unstructured":"SGI Altix 4700. http:\/\/www.sgi.com\/products\/servers\/?\/4000\/configs.html"},{"key":"494_CR23","doi-asserted-by":"crossref","unstructured":"Stojanovic, S., Bojic, D., Bojovic, M., Valero, M., Milutinovic, V.: An overview of selected hybrid and reconfigurable architectures. In: Proceedings of ICIT, pp. 444\u2013449 (2012)","DOI":"10.1109\/ICIT.2012.6209978"},{"issue":"2","key":"494_CR24","doi-asserted-by":"crossref","first-page":"70","DOI":"10.1109\/MM.2010.36","volume":"30","author":"TM Brewer","year":"2010","unstructured":"Brewer, T.M.: Instruction set innovations for the convey HC-1 computer. IEEE Micro 30(2), 70\u201379 (2010)","journal-title":"IEEE Micro"},{"issue":"10","key":"494_CR25","doi-asserted-by":"crossref","first-page":"1591","DOI":"10.1109\/TCAD.2015.2513673","volume":"35","author":"R Nane","year":"2016","unstructured":"Nane, R., Sima, V.-M., Pilato, C., Choi, J., Fort, B., Canis, A., Chen, Y.T., Hsiao, H., Brown, S., Ferrandi, F., Anderson, J., Bertels, K.: A survey and evaluation of FPGA High-Level Synthesis tools. IEEE Trans. Comput.-Aided Des. Integr. Circuits Syst. 35(10), 1591\u20131604 (2016)","journal-title":"IEEE Trans. Comput.-Aided Des. Integr. Circuits Syst."},{"key":"494_CR26","doi-asserted-by":"crossref","unstructured":"Villarreal, J., Park, A., Najjar, W., Halstead, R.: Designing modular hardware accelerators in C with ROCCC 2.0. In: Proceedings of FCCM, pp. 127\u2013134 (2010)","DOI":"10.1109\/FCCM.2010.28"},{"issue":"3","key":"494_CR27","first-page":"435","volume":"36","author":"C Pilato","year":"2017","unstructured":"Pilato, C., Mantovani, P., Di Guglielmo, G., Carloni, L.P.: System-level optimization of accelerator local memory for heterogeneous systems-on-chip. IEEE Trans. Comput.-Aided Des. Integr. Circuits Syst. 36(3), 435\u2013448 (2017)","journal-title":"IEEE Trans. Comput.-Aided Des. Integr. Circuits Syst."},{"issue":"2","key":"494_CR28","doi-asserted-by":"crossref","first-page":"56","DOI":"10.1109\/MM.2010.41","volume":"30","author":"J Nickolls","year":"2010","unstructured":"Nickolls, J., Dally, W.: The GPU computing era. IEEE Micro 30(2), 56\u201369 (2010)","journal-title":"IEEE Micro"},{"issue":"4","key":"494_CR29","doi-asserted-by":"crossref","first-page":"13","DOI":"10.1109\/MM.2008.57","volume":"28","author":"M Garland","year":"2008","unstructured":"Garland, M., Le Grand, S., Nickolls, J., Anderson, J., Hardwick, J., Morton, S., Phillips, E., Zhang, Y., Volkov, V.: Parallel computing experiences with CUDA. IEEE Micro 28(4), 13\u201327 (2008)","journal-title":"IEEE Micro"},{"key":"494_CR30","unstructured":"Xilinx Zynq-7000 All Programmable SoC User Guide. http:\/\/www.xilinx.com\/support\/documentation\/user_guides\/ug585-Zynq-7000-TRM"},{"key":"494_CR31","unstructured":"Balart, J., Duran, A., Gonzlez, M., Martorell, X., Ayguad, E., Labarta, J.: Nanos mercurium: a research compiler for openmp. In: European Workshop on OpenMP (EWOMP\u201904), pp. 103\u2013109 (2004)"},{"key":"494_CR32","unstructured":"Podlozhnyuk, V.: Image convolution with CUDA. http:\/\/developer.download.nvidia.com\/compute\/cuda\/1.1-Beta\/x86_64_website\/projects\/convolutionSeparable\/doc\/convolutionSeparable"},{"key":"494_CR33","doi-asserted-by":"crossref","unstructured":"Eichenberger, A.E., et al.: Using advanced compiler technology to exploit the performance of the Cell Broadband Engine Architecture. In: IBM Systems Journal, pp. 59\u201384 (2006)","DOI":"10.1147\/sj.451.0059"},{"key":"494_CR34","unstructured":"TESLA C2050 \/ C2070 GPU Computing Processor. Supercomputing at 1\/10th of the cost. www.nvidia.com\/docs\/IO\/43395\/NV_DS_Tesla_C2050_C2070_jul10_lores"},{"key":"494_CR35","doi-asserted-by":"crossref","unstructured":"Ciobanu, C., Kuzmanov, G.K., Gaydadjiev, G.N.: Scalability study of Polymorphic Register Files. In: Proceedings of DSD, pp. 803\u2013808 (2012)","DOI":"10.1109\/DSD.2012.116"}],"container-title":["International Journal of Parallel Programming"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10766-017-0494-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10766-017-0494-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10766-017-0494-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,9,24]],"date-time":"2019-09-24T00:20:03Z","timestamp":1569284403000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10766-017-0494-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,5,10]]},"references-count":35,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2018,12]]}},"alternative-id":["494"],"URL":"https:\/\/doi.org\/10.1007\/s10766-017-0494-1","relation":{},"ISSN":["0885-7458","1573-7640"],"issn-type":[{"type":"print","value":"0885-7458"},{"type":"electronic","value":"1573-7640"}],"subject":[],"published":{"date-parts":[[2017,5,10]]}}}