{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T14:23:01Z","timestamp":1742912581141,"version":"3.40.3"},"publisher-location":"Cham","reference-count":22,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319788890"},{"type":"electronic","value":"9783319788906"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"unspecified","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\/978-3-319-78890-6_10","type":"book-chapter","created":{"date-parts":[[2018,4,7]],"date-time":"2018-04-07T04:52:40Z","timestamp":1523076760000},"page":"119-131","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Achieving Efficient Realization of Kalman Filter on CGRA Through Algorithm-Architecture Co-design"],"prefix":"10.1007","author":[{"given":"Farhad","family":"Merchant","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tarun","family":"Vatwani","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anupam","family":"Chattopadhyay","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Soumyendu","family":"Raha","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"S. K.","family":"Nandy","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ranjani","family":"Narayan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,4,8]]},"reference":[{"key":"10_CR1","doi-asserted-by":"crossref","unstructured":"Baluni, A., Merchant, F., Nandy, S.K., Balakrishnan, S.: A fully pipelined modular multiple precision floating point multiplier with vector support. In: 2011 International Symposium on Electronic System Design, pp. 45\u201350, December 2011","DOI":"10.1109\/ISED.2011.14"},{"issue":"1","key":"10_CR2","first-page":"012057","volume":"608","author":"G Cerati","year":"2015","unstructured":"Cerati, G., Elmer, P., Lantz, S., MacNeill, I., McDermott, K., Riley, D., Tadel, M., Wittich, P., W\u00fcrthwein, F., Yagil, A.: Traditional tracking with kalman filter on parallel architectures. J. Phys.: Conf. Ser. 608(1), 012057 (2015)","journal-title":"J. Phys.: Conf. Ser."},{"issue":"7","key":"10_CR3","doi-asserted-by":"publisher","first-page":"592","DOI":"10.1016\/j.sysarc.2014.06.002","volume":"60","author":"S Das","year":"2014","unstructured":"Das, S., Madhu, K.T., Madhu, K., Krishna, M., Sivanandan, N., Merchant, F., Natarajan, S., Biswas, I., Pulli, A., Nandy, S.K., Narayan, R.: A framework for post-silicon realization of arbitrary instruction extensions on reconfigurable data-paths. J. Syst. Archit. - Embed. Syst. Des. 60(7), 592\u2013614 (2014)","journal-title":"J. Syst. Archit. - Embed. Syst. Des."},{"key":"10_CR4","doi-asserted-by":"crossref","unstructured":"Gentleman, W.M., Kung, H.T.: Matrix triangularization by systolic arrays. In: SPIE Proceedings, vol. 298, pp. 19\u201326 (1982)","DOI":"10.1117\/12.932507"},{"issue":"4","key":"10_CR5","doi-asserted-by":"publisher","first-page":"352","DOI":"10.1145\/98267.98290","volume":"16","author":"NJ Higham","year":"1990","unstructured":"Higham, N.J.: Exploiting fast matrix multiplication within the level 3 BLAS. ACM Trans. Math. Softw. 16(4), 352\u2013368 (1990)","journal-title":"ACM Trans. Math. Softw."},{"issue":"7","key":"10_CR6","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1109\/MC.2008.209","volume":"41","author":"MD Hill","year":"2008","unstructured":"Hill, M.D., Marty, M.R.: Amdahl\u2019s law in the multicore era. Computer 41(7), 33\u201338 (2008)","journal-title":"Computer"},{"key":"10_CR7","doi-asserted-by":"crossref","unstructured":"Johnson, B., Thomas, N., Rani, J.S.: An FPGA based high throughput discrete Kalman filter architecture for real-time image denoising. In: 2017 30th International Conference on VLSI Design and 2017 16th International Conference on Embedded Systems (VLSID), January 2017","DOI":"10.1109\/VLSID.2017.26"},{"key":"10_CR8","doi-asserted-by":"crossref","unstructured":"Mahadurkar, M., Merchant, F., Maity, A., Vatwani, K., Munje, I., Gopalan, N., Nandy, S.K., Narayan, R.: Co-exploration of NLA kernels and specification of compute elements in distributed memory CGRAs. In: XIVth International Conference on Embedded Computer Systems: Architectures, Modeling, and Simulation, SAMOS 2014, Agios Konstantinos, Samos, Greece, 14\u201317 July 2014, pp. 225\u2013232 (2014)","DOI":"10.1109\/SAMOS.2014.6893215"},{"key":"10_CR9","doi-asserted-by":"crossref","unstructured":"Merchant, F., Maity, A., Mahadurkar, M., Vatwani, K., Munje, I., Krishna, M., Nalesh, S., Gopalan, N., Raha, S., Nandy, S.K., Narayan, R.: Micro-architectural enhancements in distributed memory CGRAs for LU and QR factorizations. In: 2015 28th International Conference on VLSI Design (VLSID), pp. 153\u2013158, January 2015","DOI":"10.1109\/VLSID.2015.31"},{"issue":"99","key":"10_CR10","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TPDS.2018.2803820","volume":"PP","author":"FA Merchant","year":"2018","unstructured":"Merchant, F.A., Vatwani, T., Chattopadhyay, A., Raha, S., Nandy, S.K., Narayan, R.: Efficient realization of householder transform through algorithm-architecture co-design for acceleration of QR factorization. IEEE Trans. Parallel Distrib. Syst. PP(99), 1 (2018)","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"key":"10_CR11","doi-asserted-by":"crossref","unstructured":"Merchant, F., Chattopadhyay, A., Garga, G., Nandy, S.K., Narayan, R., Gopalan, N.: Efficient QR decomposition using low complexity column-wise givens rotation (CGR). In: 2014 27th International Conference on VLSI Design and 2014 13th International Conference on Embedded Systems, Mumbai, India, 5\u20139 January 2014, pp. 258\u2013263 (2014)","DOI":"10.1109\/VLSID.2014.51"},{"issue":"3\u20134","key":"10_CR12","first-page":"1","volume":"27","author":"F Merchant","year":"2017","unstructured":"Merchant, F., Chattopadhyay, A., Raha, S., Nandy, S.K., Narayan, R.: Accelerating BLAS and LAPACK via efficient floating point architecture design. Parallel Process. Lett. 27(3\u20134), 1\u201317 (2017)","journal-title":"Parallel Process. Lett."},{"key":"10_CR13","doi-asserted-by":"crossref","unstructured":"Merchant, F., Choudhary, N., Nandy, S.K., Narayan, R.: Efficient realization of table look-up based double precision floating point arithmetic. In: 29th International Conference on VLSI Design and 15th International Conference on Embedded Systems, VLSID 2016, Kolkata, India, 4\u20138 January 2016, pp. 415\u2013420 (2016)","DOI":"10.1109\/VLSID.2016.113"},{"key":"10_CR14","doi-asserted-by":"crossref","unstructured":"Merchant, F., Vatwani, T., Chattopadhyay, A., Raha, S., Nandy, S.K., Narayan, R.: Achieving efficient QR factorization by algorithm-architecture co-design of householder transformation. In: 29th International Conference on VLSI Design and 15th International Conference on Embedded Systems, VLSID 2016, Kolkata, India, 4\u20138 January 2016, pp. 98\u2013103 (2016)","DOI":"10.1109\/VLSID.2016.109"},{"issue":"2","key":"10_CR15","doi-asserted-by":"publisher","first-page":"129","DOI":"10.1109\/12.2142","volume":"37","author":"JG Nash","year":"1988","unstructured":"Nash, J.G., Hansen, S.: Modified Faddeeva algorithm for concurrent execution of linear algebraic operations. IEEE Trans. Comput. 37(2), 129\u2013137 (1988)","journal-title":"IEEE Trans. Comput."},{"key":"10_CR16","doi-asserted-by":"crossref","unstructured":"R\u00e1kossy, Z.E., Merchant, F., Acosta Aponte, A., Nandy, S.K., Chattopadhyay, A.: Efficient and scalable CGRA-based implementation of column-wise givens rotation. In: ASAP, pp. 188\u2013189 (2014)","DOI":"10.1109\/ASAP.2014.6868659"},{"key":"10_CR17","doi-asserted-by":"crossref","unstructured":"R\u00e1kossy, Z.E., Merchant, F., Acosta Aponte, A., Nandy, S.K., Chattopadhyay, A.: Scalable and energy-efficient reconfigurable accelerator for column-wise givens rotation. In: 22nd International Conference on Very Large Scale Integration, VLSI-SoC, Playa del Carmen, Mexico, 6\u20138 October 2014, pp. 1\u20136 (2014)","DOI":"10.1109\/VLSI-SoC.2014.7004166"},{"issue":"17","key":"10_CR18","doi-asserted-by":"publisher","first-page":"5749","DOI":"10.1109\/JSEN.2017.2726529","volume":"17","author":"F Sandhu","year":"2017","unstructured":"Sandhu, F., Selamat, H., Alavi, S.E., Behtaji Siahkal Mahalleh, V.: FPGA-based implementation of kalman filter for real-time estimation of tire velocity and acceleration. IEEE Sens. J. 17(17), 5749\u20135758 (2017)","journal-title":"IEEE Sens. J."},{"key":"10_CR19","unstructured":"Smith, B.J.: R package magma: matrix algebra on GPU and multicore architectures, version 0.2.2, 3 September 2010. http:\/\/cran.r-project.org\/package=magma"},{"issue":"7\u20138","key":"10_CR20","doi-asserted-by":"publisher","first-page":"847","DOI":"10.1016\/0094-5765(77)90017-0","volume":"4","author":"CL Thornton","year":"1977","unstructured":"Thornton, C.L., Bierman, G.J.: Givens transformation techniques for kalman filtering. Acta Astronaut. 4(7\u20138), 847\u2013863 (1977)","journal-title":"Acta Astronaut."},{"key":"10_CR21","doi-asserted-by":"crossref","unstructured":"Wang, Q., Zhang, X., Zhang, Y., Yi, Q.: AUGEM: automatically generate high performance dense linear algebra kernels on x86 CPUs. In: Proceedings of the International Conference on High Performance Computing, Networking, Storage and Analysis, SC 2013, pp. 25:1\u201325:12. ACM, New York (2013)","DOI":"10.1145\/2503210.2503219"},{"issue":"6","key":"10_CR22","doi-asserted-by":"publisher","first-page":"4802","DOI":"10.1109\/TVT.2016.2546957","volume":"65","author":"G Zhong","year":"2016","unstructured":"Zhong, G., Niar, S., Prakash, A., Mitra, T.: Design of multiple-target tracking system on heterogeneous system-on-chip devices. IEEE Trans. Veh. Technol. 65(6), 4802\u20134812 (2016)","journal-title":"IEEE Trans. Veh. Technol."}],"container-title":["Lecture Notes in Computer Science","Applied Reconfigurable Computing. Architectures, Tools, and Applications"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-78890-6_10","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,10,14]],"date-time":"2019-10-14T13:17:17Z","timestamp":1571059037000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-78890-6_10"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783319788890","9783319788906"],"references-count":22,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-78890-6_10","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2018]]}}}