{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T15:57:27Z","timestamp":1780675047259,"version":"3.54.1"},"reference-count":37,"publisher":"Springer Science and Business Media LLC","issue":"10","license":[{"start":{"date-parts":[[2021,1,22]],"date-time":"2021-01-22T00:00:00Z","timestamp":1611273600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,22]],"date-time":"2021-01-22T00:00:00Z","timestamp":1611273600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Sign Process Syst"],"published-print":{"date-parts":[[2021,10]]},"DOI":"10.1007\/s11265-020-01630-2","type":"journal-article","created":{"date-parts":[[2021,1,22]],"date-time":"2021-01-22T18:40:40Z","timestamp":1611340840000},"page":"1159-1171","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":13,"title":["Floating Point CGRA based Ultra-Low Power DSP Accelerator"],"prefix":"10.1007","volume":"93","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1202-837X","authenticated-orcid":false,"given":"Rohit","family":"Prasad","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7550-2641","authenticated-orcid":false,"given":"Satyajit","family":"Das","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8122-1192","authenticated-orcid":false,"given":"Kevin J. M.","family":"Martin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7222-5271","authenticated-orcid":false,"given":"Philippe","family":"Coussy","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2021,1,22]]},"reference":[{"issue":"11","key":"1630_CR1","doi-asserted-by":"publisher","first-page":"3300","DOI":"10.1109\/TCAD.2020.3022015","volume":"39","author":"M Balasubramanian","year":"2020","unstructured":"Balasubramanian, M., & Shrivastava, A. (2020). Crimson: compute-intensive loop acceleration by randomized iterative modulo scheduling and optimized mapping on CGRAs. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 39(11), 3300\u20133310. https:\/\/doi.org\/10.1109\/TCAD.2020.3022015.","journal-title":"IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems"},{"key":"1630_CR2","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 of the 3rd international conference on reconfigurable computing: architectures, tools and applications, ARC\u201907. http:\/\/dl.acm.org\/citation.cfm?id=1764631.1764633 (pp. 1\u201313). Berlin: Springer.","DOI":"10.1007\/978-3-540-71431-6_1"},{"issue":"6","key":"1630_CR3","doi-asserted-by":"publisher","first-page":"1095","DOI":"10.1109\/TCAD.2018.2834397","volume":"38","author":"S Das","year":"2018","unstructured":"Das, S., Martin, K. J., Rossi, D., Coussy, P., & Benini, L. (2018). An energy-efficient integrated programmable array accelerator and compilation flow for near-sensor ultralow power processing. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 38(6), 1095\u20131108.","journal-title":"IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems"},{"key":"1630_CR4","doi-asserted-by":"publisher","unstructured":"Das, S., Peyret, T., Martin, K., Corre, G., Thevenin, M., & Coussy, P. (2016). A scalable design approach to efficiently map applications on cgras. In 2016 IEEE computer society annual symposium on VLSI (ISVLSI) (pp. 655\u2013660), DOI https:\/\/doi.org\/10.1109\/ISVLSI.2016.54, (to appear in print).","DOI":"10.1109\/ISVLSI.2016.54"},{"key":"1630_CR5","doi-asserted-by":"crossref","unstructured":"Das, S., Rossi, D., Martin, K. J. M., Coussy, P., & Benini, L. (2017). A 142mops\/mw integrated programmable array accelerator for smart visual processing. In 2017 IEEE International symposium on circuits and systems (ISCAS). IEEE (pp. 1\u20134).","DOI":"10.1109\/ISCAS.2017.8050238"},{"key":"1630_CR6","doi-asserted-by":"crossref","unstructured":"De Sutter, B., Raghavan, P., & Lambrechts, A. (2010). Coarse-grained reconfigurable array architectures. In Bhattacharyya, S.S., Deprettere, E.F., Leupers, R., & Takala, J. (Eds.) Handbook of signal processing systems. Springer US (pp. 449\u2013484).","DOI":"10.1007\/978-1-4419-6345-1_17"},{"key":"1630_CR7","doi-asserted-by":"publisher","unstructured":"Dinda, P., Bernat, A., & Hetland, C. (2020). Spying on the floating point behavior of existing, unmodified scientific applications. In Proceedings of the 29th international symposium on high-performance parallel and distributed computing, HPDC \u201920. Association for Computing Machinery, New York, NY, USA (pp. 5\u201316), DOI https:\/\/doi.org\/10.1145\/3369583.3392673, (to appear in print).","DOI":"10.1145\/3369583.3392673"},{"key":"1630_CR8","unstructured":"Exynos 5 Octa (5430): Samsung 2014. Retrieved from (2014). https:\/\/www.samsung.com\/semiconductor\/minisite\/exynos\/products\/mobileprocessor\/exynos-5-octa-5430\/."},{"issue":"10","key":"1630_CR9","doi-asserted-by":"publisher","first-page":"2700","DOI":"10.1109\/TVLSI.2017.2654506","volume":"25","author":"M Gautschi","year":"2017","unstructured":"Gautschi, M., Schiavone, P. D., Traber, A., Loi, I., Pullini, A., Rossi, D., Flamand, E., G\u00fcrkaynak, F. K., & Benini, L. (2017). Near-threshold risc-v core with dsp extensions for scalable iot endpoint devices. IEEE Transactions on Very Large Scale Integration (VLSI) Systems, 25(10), 2700\u20132713. https:\/\/doi.org\/10.1109\/TVLSI.2017.2654506.","journal-title":"IEEE Transactions on Very Large Scale Integration (VLSI) Systems"},{"key":"1630_CR10","doi-asserted-by":"crossref","unstructured":"Golub, G. H., & Van der Vorst, H. A. (2001). Eigenvalue computation in the 20th century. In Numerical analysis: historical developments in the 20th century. Elsevier (pp. 209\u2013239).","DOI":"10.1016\/B978-0-444-50617-7.50010-0"},{"issue":"5","key":"1630_CR11","doi-asserted-by":"publisher","first-page":"38","DOI":"10.1109\/MM.2012.51","volume":"32","author":"V Govindaraju","year":"2012","unstructured":"Govindaraju, V., Ho, C. H., Nowatzki, T., Chhugani, J., Satish, N., Sankaralingam, K., & Kim, C. (2012). Dyser: unifying functionality and parallelism specialization for energy-efficient computing. IEEE Micro, 32(5), 38\u201351.","journal-title":"IEEE Micro"},{"key":"1630_CR12","unstructured":"IEEE: IEEE standard for floating-point arithmetic. IEEE Std 754-2008 pp. 1\u201370 (2008)."},{"key":"1630_CR13","unstructured":"Intel 2016: Retrieved from https:\/\/newsroom.intel.com\/news-releases\/intel-tsinghua-university-and-montage-technology-collaborate-to-bring-indigenous-data-center-solutions-to-china\/https:\/\/newsroom.intel.com\/news-releases\/intel-tsinghua-university-and-montage-technology-collaborate-to-bring-indigenous-data-center-solutions-to-china\/https:\/\/newsroom.intel.com\/news-releases\/intel-tsinghua-university-and-montage-technology-collaborate-to-bring-indigenous-data-center-solutions-to-china\/."},{"issue":"2","key":"1630_CR14","doi-asserted-by":"publisher","first-page":"35","DOI":"10.1109\/40.918001","volume":"21","author":"B Khailany","year":"2001","unstructured":"Khailany, B., Dally, W. J., Kapasi, U. J., Mattson, P., Namkoong, J., Owens, J. D., Towles, B., Chang, A., & Rixner, S. (2001). Imagine: media processing with streams. IEEE Micro, 21(2), 35\u201346. https:\/\/doi.org\/10.1109\/40.918001.","journal-title":"IEEE Micro"},{"key":"1630_CR15","doi-asserted-by":"crossref","unstructured":"Kim, S., Park, Y. H., Kim, J., Kim, M., Lee, W., & Lee, S. (2015). Flexible video processing platform for 8k uhd tv. In Hot chips symposium (p. 1).","DOI":"10.1109\/HOTCHIPS.2015.7477475"},{"issue":"4","key":"1630_CR16","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1109\/MSP.2019.2903715","volume":"36","author":"J Le Kernec","year":"2019","unstructured":"Le Kernec, J., Fioranelli, F., Ding, C., Zhao, H., Sun, L., Hong, H., Lorandel, J., & Romain, O. (2019). Radar signal processing for sensing in assisted living: the challenges associated with real-time implementation of emerging algorithms. IEEE Signal Processing Magazine, 36(4), 29\u201341.","journal-title":"IEEE Signal Processing Magazine"},{"key":"1630_CR17","doi-asserted-by":"publisher","unstructured":"Lee, D., Jo, M., Han, K., & Choi, K. (2009). Flora: coarse-grained reconfigurable architecture with floating-point operation capability. In 2009 International conference on field-programmable technology (pp. 376\u2013379), DOI https:\/\/doi.org\/10.1109\/FPT.2009.5377609, (to appear in print).","DOI":"10.1109\/FPT.2009.5377609"},{"issue":"2\u20133","key":"1630_CR18","doi-asserted-by":"publisher","first-page":"147","DOI":"10.1023\/A:1008189221436","volume":"24","author":"MH Lee","year":"2000","unstructured":"Lee, M. H., Singh, H., Lu, G., Bagherzadeh, N., Kurdahi, F. J., Eliseu Filho, M., & Alves, V. C. (2000). Design and implementation of the morphosys reconfigurable computing processor. Journal of VLSI Signal Processing Systems for Signal, Image and Video Technology, 24(2\u20133), 147\u2013164.","journal-title":"Journal of VLSI Signal Processing Systems for Signal, Image and Video Technology"},{"issue":"4","key":"1630_CR19","doi-asserted-by":"publisher","first-page":"341","DOI":"10.1007\/BF02575586","volume":"9","author":"G Levi","year":"1973","unstructured":"Levi, G. (1973). A note on the derivation of maximal common subgraphs of two directed or undirected graphs. Calcolo, 9(4), 341\u2013352.","journal-title":"Calcolo"},{"issue":"12","key":"1630_CR20","doi-asserted-by":"publisher","first-page":"2271","DOI":"10.1109\/TCAD.2018.2878183","volume":"38","author":"D Liu","year":"2018","unstructured":"Liu, D., Yin, S., Luo, G., Shang, J., Liu, L., Wei, S., Feng, Y., & Zhou, S. (2018). Data-flow graph mapping optimization for cgra with deep reinforcement learning. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 38(12), 2271\u20132283.","journal-title":"IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems"},{"key":"1630_CR21","doi-asserted-by":"publisher","unstructured":"Montagna, F., Benatti, S., & Rossi, D. (2017). Flexible, scalable and energy efficient bio-signals processing on the pulp platform: a case study on seizure detection. Journal of Low Power Electronics and Applications, 7(2). https:\/\/doi.org\/10.3390\/jlpea7020016, http:\/\/www.mdpi.com\/2079-9268\/7\/2\/16.","DOI":"10.3390\/jlpea7020016"},{"key":"1630_CR22","unstructured":"Nicol, C. (2017). A coarse grain reconfigurable array (CGRA) for statically scheduled data flow computing. Wave Computing White Paper. https:\/\/wavecomp.ai\/wp-content\/uploads\/2018\/12\/WP_CGRA.pdf."},{"key":"1630_CR23","unstructured":"PACT: Retrieved from http:\/\/www.pactxpp.com\/."},{"key":"1630_CR24","doi-asserted-by":"crossref","unstructured":"Peyret, T., Corre, G., Thevenin, M., Martin, K., & Coussy, P. (2014). Efficient application mapping on cgras based on backward simultaneous scheduling\/binding and dynamic graph transformations. In 2014 IEEE 25th international conference on application-specific systems, architectures and processors (pp. 169\u2013172).","DOI":"10.1109\/ASAP.2014.6868652"},{"key":"1630_CR25","doi-asserted-by":"crossref","unstructured":"Prabhakar, R., Zhang, Y., Koeplinger, D., Feldman, M., Zhao, T., Hadjis, S., Pedram, A., Kozyrakis, C., & Olukotun, K. (2017). Plasticine: a reconfigurable architecture for parallel patterns. In 2017 ACM\/IEEE 44th annual international symposium on computer architecture (ISCA). IEEE (pp. 389\u2013402).","DOI":"10.1145\/3079856.3080256"},{"key":"1630_CR26","doi-asserted-by":"crossref","unstructured":"Prasad, R., Das, S., Martin, K. J. M., Tagliavini, G., Coussy, P., Benini, L., & Rossi, D. (2020). Transpire: an energy-efficient transprecision floating-point programmable architecture. In 2020 Design, automation test in Europe conference exhibition (DATE) (pp. 1067\u20131072).","DOI":"10.23919\/DATE48585.2020.9116408"},{"issue":"7","key":"1630_CR27","doi-asserted-by":"publisher","first-page":"1970","DOI":"10.1109\/JSSC.2019.2912307","volume":"54","author":"A Pullini","year":"2019","unstructured":"Pullini, A., Rossi, D., Loi, I., Tagliavini, G., & Benini, L. (2019). Mr.wolf: an energy-precision scalable parallel ultra low power soc for iot edge processing. IEEE Journal of Solid-State Circuits, 54 (7), 1970\u20131981. https:\/\/doi.org\/10.1109\/JSSC.2019.2912307.","journal-title":"IEEE Journal of Solid-State Circuits"},{"key":"1630_CR28","unstructured":"PULP Platform: Open hardware, the way it should be! https:\/\/pulp-platform.org\/."},{"key":"1630_CR29","unstructured":"PULP SDK: PULP software development kit and tools. https:\/\/pulp-platform.org\/docs\/hipeac\/AndreasKurth_pulp_tools.pdf."},{"key":"1630_CR30","doi-asserted-by":"crossref","unstructured":"Rahimi, A., Loi, I., Kakoee, M. R., & Benini, L. (2011). A fully-synthesizable single-cycle interconnection network for shared-l1 processor clusters. In Design, automation & test in Europe conference & exhibition (DATE), 2011. IEEE (pp. 1\u2013 6).","DOI":"10.1109\/DATE.2011.5763085"},{"key":"1630_CR31","doi-asserted-by":"crossref","unstructured":"Rossi, D., Conti, F., Marongiu, A., Pullini, A., Loi, I., Gautschi, M., Tagliavini, G., Capotondi, A., Flatresse, P., & Benini, L. (2015). Pulp: a parallel ultra low power platform for next generation iot applications. In 2015 IEEE Hot chips 27 symposium (HCS) (pp. 1\u201339).","DOI":"10.1109\/HOTCHIPS.2015.7477325"},{"key":"1630_CR32","doi-asserted-by":"crossref","unstructured":"Sato, T., Watanabe, H., & Shiba, K. (2005). Implementation of dynamically reconfigurable processor dapdna-2. In 2005 IEEE VLSI-TSA International symposium on VLSI design, automation and test, 2005.(VLSI-TSA-DAT). IEEE (pp. 323\u2013 324).","DOI":"10.1109\/VDAT.2005.1500086"},{"key":"1630_CR33","doi-asserted-by":"crossref","unstructured":"Suzuki, M., Hasegawa, Y., Yamada, Y., Kaneko, N., Deguchi, K., Amano, H., Anjo, K., Motomura, M., Wakabayashi, K., Toi, T., & et al. (2004). Stream applications on the dynamically reconfigurable processor. In Proceedings. 2004 IEEE international conference on field-programmable technology (IEEE cat. no. 04EX921). IEEE (pp. 137\u2013144).","DOI":"10.1109\/FPT.2004.1393261"},{"key":"1630_CR34","doi-asserted-by":"crossref","unstructured":"Voitsechov, D., & Etsion, Y. (2018). Inter-thread communication in multithreaded, reconfigurable coarse-grain arrays. arXiv:1801.05178.","DOI":"10.1109\/MICRO.2018.00013"},{"key":"1630_CR35","doi-asserted-by":"crossref","unstructured":"Walker, M. J., & Anderson, J. H. (2019). Generic connectivity-based cgra mapping via integer linear programming. In 2019 IEEE 27th annual international symposium on field-programmable custom computing machines (FCCM). IEEE (pp. 65\u201373).","DOI":"10.1109\/FCCM.2019.00019"},{"key":"1630_CR36","unstructured":"Wilkinson, J. H., & Reinsch, C. (2012). Handbook for automatic computation: Volume II: linear algebra, vol. 186. Springer Science & Business Media."},{"key":"1630_CR37","doi-asserted-by":"publisher","unstructured":"Yin, S., Liu, D., Sun, L., Liu, L., & Wei, S. (2017). Dfgnet: mapping dataflow graph onto cgra by a deep learning approach. In 2017 IEEE international symposium on circuits and systems (ISCAS) (pp. 1\u20134), DOI https:\/\/doi.org\/10.1109\/ISCAS.2017.8050274, (to appear in print).","DOI":"10.1109\/ISCAS.2017.8050274"}],"container-title":["Journal of Signal Processing Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11265-020-01630-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11265-020-01630-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11265-020-01630-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,10,19]],"date-time":"2021-10-19T20:21:44Z","timestamp":1634674904000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11265-020-01630-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,1,22]]},"references-count":37,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2021,10]]}},"alternative-id":["1630"],"URL":"https:\/\/doi.org\/10.1007\/s11265-020-01630-2","relation":{},"ISSN":["1939-8018","1939-8115"],"issn-type":[{"value":"1939-8018","type":"print"},{"value":"1939-8115","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,1,22]]},"assertion":[{"value":"17 July 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 November 2020","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 December 2020","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 January 2021","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}