{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2022,3,30]],"date-time":"2022-03-30T12:07:35Z","timestamp":1648642055592},"reference-count":37,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2015,2,17]],"date-time":"2015-02-17T00:00:00Z","timestamp":1424131200000},"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":["J Sign Process Syst"],"published-print":{"date-parts":[[2016,10]]},"DOI":"10.1007\/s11265-015-0974-8","type":"journal-article","created":{"date-parts":[[2015,2,17]],"date-time":"2015-02-17T09:57:48Z","timestamp":1424167068000},"page":"45-66","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["A Dynamic Modulo Scheduling with Binary Translation: Loop optimization with software compatibility"],"prefix":"10.1007","volume":"85","author":[{"given":"Ricardo","family":"Ferreira","sequence":"first","affiliation":[]},{"given":"Waldir","family":"Denver","sequence":"additional","affiliation":[]},{"given":"Monica","family":"Pereira","sequence":"additional","affiliation":[]},{"given":"Stephan","family":"Wong","sequence":"additional","affiliation":[]},{"given":"Carlos A.","family":"Lisb\u020fa","sequence":"additional","affiliation":[]},{"given":"Luigi","family":"Carro","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2015,2,17]]},"reference":[{"key":"974_CR1","unstructured":"Ahn, M., Yoon, J.W., Paek, Y., Kim, Y., Kiemb, M., Choi, K. (2006). A spatial mapping algorithm for heterogeneous coarse-grained reconfigurable architectures. In: Proceedings DATE, pp. 363\u2013368."},{"issue":"3s","key":"974_CR2","doi-asserted-by":"crossref","first-page":"107:1","DOI":"10.1145\/2517087","volume":"13","author":"O Arnold","year":"2014","unstructured":"Arnold, O., Matus, E., Noethen, B., Winter, M., Limberg, T., Fettweis, G. (2014). Tomahawk: Parallelism and heterogeneity in communications signal processing mpsocs. ACM Transactions on Embedded Computing Systems, 13(3s), 107:1\u2013107:241.","journal-title":"ACM Transactions on Embedded Computing Systems"},{"key":"974_CR3","doi-asserted-by":"crossref","unstructured":"Beck, A.C.S., Rutzig, M.B., Gaydadjiev, G., Carro, L. (2008). Transparent reconfigurable acceleration for heterogeneous embedded applications. In: Proceedings of the Conference on Design, Automation and Test in Europe, pp. 1208\u20131213.","DOI":"10.1109\/DATE.2008.4484843"},{"key":"974_CR4","doi-asserted-by":"crossref","unstructured":"Bispo, J., Paulino, N., Cardoso, J.M., Ferreira, J.C. (2013). Transparent runtime migration of loop-based traces of processor instructions to reconfigurable processing units. International Journal of Reconfigurable Computing","DOI":"10.1155\/2013\/340316"},{"key":"974_CR5","unstructured":"Bispo, J., Paulino, N., Ferreira, J., Cardoso, J. (2012). Transparent trace-based binary acceleration for reconfigurable hw\/sw systems. IEEE Transactions on Industrial Informatics."},{"issue":"1-2","key":"974_CR6","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1007\/s11265-014-0891-2","volume":"77","author":"S Boppu","year":"2014","unstructured":"Boppu, S., Hannig, F., Teich, J. (2014). Compact code generation for tightly-coupled processor arrays. Journal of Signal Processing Systems, 77(1-2), 5\u201329.","journal-title":"Journal of Signal Processing Systems"},{"key":"974_CR7","doi-asserted-by":"crossref","unstructured":"Bouwens, F., Berekovic, M., Kanstein, A., Gaydadjiev, G. (2007). Architectural exploration of the adres coarse-grained reconfigurable array. In Proceedings ARC pp. 1\u201313.","DOI":"10.1007\/978-3-540-71431-6_1"},{"key":"974_CR8","doi-asserted-by":"crossref","unstructured":"Chen, L., & Mitra, T. (2012). Graph minor approach for application mapping on cgras. In: Proceedings FPT.","DOI":"10.1109\/FPT.2012.6412149"},{"key":"974_CR9","doi-asserted-by":"crossref","unstructured":"De Sutter, B., Coene, P., Vander Aa, T., Mei, B. (2008). Placement-and-routing-based register allocation for coarse-grained reconfigurable arrays. In Proceedings LCTES (pp. 151\u2013160).","DOI":"10.1145\/1375657.1375678"},{"key":"974_CR10","doi-asserted-by":"crossref","unstructured":"Ferreira, R., Duarte, V., Meireles, W., Pereira, M., Carro, L., Wong, S. (2013). A just-in-time modulo scheduling for virtual coarse-grained reconfigurable architectures. In SAMOS XIII.","DOI":"10.1109\/SAMOS.2013.6621122"},{"key":"974_CR11","doi-asserted-by":"crossref","unstructured":"Ferreira, R., Vendramini, J.G., Mucida, L., Pereira, M.M., Carro, L. (2011). An fpga-based heterogeneous coarse-grained dynamically reconfigurable architecture. In: Proceedings CASES.","DOI":"10.1145\/2038698.2038728"},{"key":"974_CR12","doi-asserted-by":"crossref","unstructured":"Friedman, S., Carroll, A., Van Essen, B., Ylvisaker, B., Ebeling, C., Hauck, S. (2009). Spr: an architecture-adaptive cgra mapping tool. In: Proceeding of the ACM\/SIGDA international symposium on field programmable gate arrays, FPGA \u201909 (pp. 191\u2013200). New York: ACM","DOI":"10.1145\/1508128.1508158"},{"key":"974_CR13","doi-asserted-by":"crossref","unstructured":"Goel, N., Kumar, A., Panda, P.R. (2014). Shared-port register file architecture for low-energy vliw processors. ACM Transactions Architectural Code Optimization, 11(1).","DOI":"10.1145\/2533397"},{"key":"974_CR14","doi-asserted-by":"crossref","unstructured":"Hamzeh, M., Shrivastava, A., Vrudhula, S. (2012). Epimap: Using epimorphism to map applications on CGRAs. In Proceeding of DAC conference (pp. 1280\u20131287).","DOI":"10.1145\/2228360.2228600"},{"key":"974_CR15","doi-asserted-by":"crossref","unstructured":"Hamzeh, M., Shrivastava, A., Vrudhula, S. (2014). Branch-aware loop mapping on CGRAs. In Proceeding of DAC conference on design automation conference (pp. 1\u20136). ACM.","DOI":"10.1109\/DAC.2014.6881434"},{"key":"974_CR16","doi-asserted-by":"crossref","unstructured":"Hamzeh, M., Shrivastava, A., Vrudhula, S.B. (2013). Regimap: register-aware application mapping on coarse-grained reconfigurable architectures (CGRAs). In Proceeding of DAC conference (p. 18).","DOI":"10.1145\/2463209.2488756"},{"key":"974_CR17","doi-asserted-by":"crossref","unstructured":"Hartenstein, R. (2001). Coarse grain reconfigurable architecture (embedded tutorial). In: Proceedings of the 2001 asia and south pacific design automation conference, ASP-DAC \u201901.","DOI":"10.1145\/370155.370535"},{"key":"974_CR18","doi-asserted-by":"crossref","unstructured":"Hatanaka, A., & Bagherzadeh, N. (2007). A modulo scheduling algorithm for a coarse-grain reconfigurable array template. In IPDPS 2007 (pp. 1\u20138).","DOI":"10.1109\/IPDPS.2007.370371"},{"key":"974_CR19","doi-asserted-by":"crossref","unstructured":"Hoogerbrugge, J., & Corporaal, H. (1994). Register file port requirements of transport triggered architectures. In: Proceedings of the 27th annual international symposium on microarchitecture. (pp. 191\u2013195). ACM.","DOI":"10.1109\/MICRO.1994.717458"},{"key":"974_CR20","unstructured":"J\u00e4\u00e4skel\u00e4inen, P., Kultala, H., Viitanen, T., Takala, J. (2014). Code density and energy efficiency of exposed datapath architectures. Journal of Signal Processing Systems, 1\u201316."},{"key":"974_CR21","doi-asserted-by":"publisher","unstructured":"Kim, Y., Lee, J., Shrivastava, A., Yoon, J., Cho, D., Paek, Y. (2011). High throughput data mapping for coarse-grained reconfigurable architectures. IEEE Transactions on CAD of International Circuits and Systems, 30 (11), 1599 \u20131609. doi: 10.1109\/TCAD.2011.2161217 .","DOI":"10.1109\/TCAD.2011.2161217"},{"key":"974_CR22","unstructured":"Laboratories, & H.P. (2014). Vex toolchain. http:\/\/www.hpl.hp.com\/downloads\/vex\/ ."},{"issue":"5","key":"974_CR23","doi-asserted-by":"crossref","first-page":"637","DOI":"10.1109\/TCAD.2010.2098571","volume":"30","author":"G Lee","year":"2011","unstructured":"Lee, G., Choi, K., Dutt, N. (2011). Mapping multi-domain applications onto coarse-grained reconfigurable architectures. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 30(5), 637\u2013650.","journal-title":"IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems"},{"issue":"3","key":"974_CR24","doi-asserted-by":"crossref","first-page":"209","DOI":"10.1007\/s11265-007-0061-x","volume":"51","author":"TJ Lin","year":"2008","unstructured":"Lin, T.J., Chen, S.K., Kuo, Y.T., Liu, C.W., Hsiao, P.C. (2008). Design and implementation of a high-performance and complexity-effective vliw dsp for multimedia applications. Journal of Signal Processing Systems, 51(3), 209\u2013223.","journal-title":"Journal of Signal Processing Systems"},{"key":"974_CR25","doi-asserted-by":"crossref","unstructured":"Loeffler, C., Ligtenberg, A., Moschytz, G.S. (1989). Practical fast 1-d dct algorithms with 11 multiplications. IEEE international conference on acoustics, speech, and signal processing, 1989. ICASSP-89 (pp. 988\u2013991).","DOI":"10.1109\/ICASSP.1989.266596"},{"issue":"3","key":"974_CR26","doi-asserted-by":"crossref","first-page":"109","DOI":"10.1109\/MSP.2007.361608","volume":"24","author":"M McCool","year":"2007","unstructured":"McCool, M. (2007). Signal processing and general-purpose computing and gpus [exploratory dsp]. IEEE Signal Processing Magazine, 24(3), 109\u2013114.","journal-title":"IEEE Signal Processing Magazine"},{"key":"974_CR27","unstructured":"Mei, B., Vernalde, S., Verkest, D., De Man, H., Lauwereins, R. (2002). Dresc: a retargetable compiler for coarse-grained reconfigurable architectures. In Proceedings FPT pp. 166\u2013173."},{"key":"974_CR28","doi-asserted-by":"crossref","unstructured":"Mei, B., Vernalde, S., Verkest, D., Man, H.D., Lauwereins, R. (2003). Exploiting loop-level parallelism on coarse-grained reconfigurable architectures using modulo scheduling. In: Proceedings DATE.","DOI":"10.1049\/ip-cdt:20030833"},{"key":"974_CR29","doi-asserted-by":"crossref","unstructured":"Oh, T., Egger, B., Park, H., Mahlke, S. (2009). Recurrence cycle aware modulo scheduling for coarse-grained reconfigurable architectures. In Proceedings LCTES pp. 21\u201330.","DOI":"10.1145\/1542452.1542456"},{"issue":"4","key":"974_CR30","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1145\/1926367.1926374","volume":"38","author":"JK Paek","year":"2011","unstructured":"Paek, J.K., Choi, K., Lee, J. (2011). Binary acceleration using coarse-grained reconfigurable architecture. SIGARCH Computers Architecture News, 38(4), 33\u201339.","journal-title":"SIGARCH Computers Architecture News"},{"key":"974_CR31","doi-asserted-by":"crossref","unstructured":"Park, H., Fan, K., Kudlur, M., Mahlke, S. (2006). Modulo graph embedding: mapping applications onto coarse-grained reconfigurable architectures. In Proceedings CASES (pp. 136\u2013146).","DOI":"10.1145\/1176760.1176778"},{"key":"974_CR32","doi-asserted-by":"crossref","unstructured":"Park, H., Fan, K., Mahlke, S.A., Oh, T., Kim, H., Kim, H.s. (2008). Edge-centric modulo scheduling for coarse-grained reconfigurable architectures. In: Proceedings PACT.","DOI":"10.1145\/1454115.1454140"},{"key":"974_CR33","doi-asserted-by":"crossref","unstructured":"Park, H., Park, Y., Mahlke, S. (2009). Polymorphic pipeline array: a flexible multicore accelerator with virtualized execution for mobile multimedia applications. In Proceedings MICRO (pp. 370\u2013380).","DOI":"10.1145\/1669112.1669160"},{"key":"974_CR34","doi-asserted-by":"crossref","unstructured":"Rau, B.R. (1994). Iterative modulo scheduling: an algorithm for software pipelining loops. In Proceedings MICRO (pp. 63\u201374).","DOI":"10.1145\/192724.192731"},{"key":"974_CR35","unstructured":"Wong, S., Van As, T., Brown, G. (2008). \u03c1-vex: A reconfigurable and extensible softcore vliw processor. In International conference on field-programmable technology FPT (pp. 369\u2013372). IEEE."},{"key":"974_CR36","doi-asserted-by":"crossref","unstructured":"Yoon, J., Shrivastava, A., Park, S., Ahn, M., Jeyapaul, R., Paek, Y. (2008). Spkm: A novel graph drawing based algorithm for application mapping onto coarse-grained reconfigurable architectures. In Proceedings ASPDAC (pp. 776\u2013782).","DOI":"10.1109\/ASPDAC.2008.4484056"},{"key":"974_CR37","doi-asserted-by":"crossref","unstructured":"Zhou, L., Liu, H., Zhang, J. (2013). Loop acceleration by cluster-based cgra. IEICE Electronics Express, 10(16).","DOI":"10.1587\/elex.10.20130506"}],"container-title":["Journal of Signal Processing Systems"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11265-015-0974-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11265-015-0974-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11265-015-0974-8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,6,1]],"date-time":"2019-06-01T12:22:27Z","timestamp":1559391747000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11265-015-0974-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,2,17]]},"references-count":37,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2016,10]]}},"alternative-id":["974"],"URL":"https:\/\/doi.org\/10.1007\/s11265-015-0974-8","relation":{},"ISSN":["1939-8018","1939-8115"],"issn-type":[{"value":"1939-8018","type":"print"},{"value":"1939-8115","type":"electronic"}],"subject":[],"published":{"date-parts":[[2015,2,17]]}}}