{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,30]],"date-time":"2025-12-30T23:40:24Z","timestamp":1767138024675,"version":"build-2238731810"},"publisher-location":"Cham","reference-count":12,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783319788890","type":"print"},{"value":"9783319788906","type":"electronic"}],"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_44","type":"book-chapter","created":{"date-parts":[[2018,4,7]],"date-time":"2018-04-07T04:52:40Z","timestamp":1523076760000},"page":"551-563","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["Exploring Functional Acceleration of OpenCL on FPGAs and GPUs Through Platform-Independent Optimizations"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9702-3070","authenticated-orcid":false,"given":"Umar Ibrahim","family":"Minhas","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6201-4270","authenticated-orcid":false,"given":"Roger","family":"Woods","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Georgios","family":"Karakonstantis","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,4,8]]},"reference":[{"issue":"9","key":"44_CR1","doi-asserted-by":"publisher","first-page":"647","DOI":"10.1038\/nrg2857","volume":"11","author":"EE Schadt","year":"2010","unstructured":"Schadt, E.E., et al.: Computational solutions to large-scale data management and analysis. Nat. Rev. Genet. 11(9), 647\u2013657 (2010)","journal-title":"Nat. Rev. Genet."},{"issue":"3","key":"44_CR2","doi-asserted-by":"publisher","first-page":"66","DOI":"10.1109\/MCSE.2010.69","volume":"12","author":"JE Stone","year":"2010","unstructured":"Stone, J.E., Gohara, D., Shi, G.: OpenCL - a parallel programming standard for heterogeneous computing systems. Comput. Sci. Eng. 12(3), 66\u201373 (2010)","journal-title":"Comput. Sci. Eng."},{"key":"44_CR3","unstructured":"Barr, J.: Developer preview \u2013 EC2 instances (F1) with programmable hardware. Amazon Web Services (2016)"},{"key":"44_CR4","doi-asserted-by":"crossref","unstructured":"Hill, K., et al.: Comparative analysis of OpenCL vs. HDL with image-processing kernels on Stratix-V FPGA. In: IEEE International Conference on ASAP (2015)","DOI":"10.1109\/ASAP.2015.7245733"},{"key":"44_CR5","doi-asserted-by":"crossref","unstructured":"Fang, J., Varbanescu, A.L., Sips, H.: A comprehensive performance comparison of CUDA and OpenCL. In: IEEE ICPP (2011)","DOI":"10.1109\/ICPP.2011.45"},{"key":"44_CR6","unstructured":"Rul, S., et al.: An experimental study on performance portability of OpenCL kernels. In: Symposium on Application Accelerators in High Performance Computing (2010)"},{"key":"44_CR7","doi-asserted-by":"crossref","unstructured":"Chen, D., Singh, D.: Fractal video compression in OpenCL: an evaluation of CPUs, GPUs, and FPGAs as acceleration platforms. In: ASP-DAC. IEEE (2013)","DOI":"10.1109\/ASPDAC.2013.6509612"},{"key":"44_CR8","doi-asserted-by":"crossref","unstructured":"Zohouri, H.R., et al.: Evaluating and optimizing OpenCL kernels for high performance computing with FPGAs. In: Proceedings of IEEE\/ACM Supercomputing Conference (2016)","DOI":"10.1109\/SC.2016.34"},{"key":"44_CR9","unstructured":"Berkeley Design Technology, Inc.: Floating-point DSP design flow and performance on Altera 28-nm FPGAs. In: Independent Analysis (2012)"},{"key":"44_CR10","doi-asserted-by":"crossref","unstructured":"Giefers, H., Polig, R., Hagleitner, C.: Analyzing the energy-efficiency of dense linear algebra kernels by power-profiling a hybrid CPU\/FPGA system. In: 25th International Conference on Application-Specific Systems, Architectures and Processors. IEEE (2014)","DOI":"10.1109\/ASAP.2014.6868642"},{"key":"44_CR11","doi-asserted-by":"publisher","first-page":"327","DOI":"10.1201\/b16721-25","volume-title":"GPU Pro 5","author":"Johan Gronqvist","year":"2014","unstructured":"Gronqvist, J., Lokhmotov, A.: Optimising OpenCL kernels for the ARM Mali-T600 GPUs. In: GPU Pro 5: Advanced Rendering Techniques, p. 327 (2014)"},{"key":"44_CR12","unstructured":"NVIDIA, CUDA: Basic Linear Algebra Subroutines (cuBLAS) library (2013)"}],"updated-by":[{"DOI":"10.1007\/978-3-319-78890-6_60","type":"erratum","label":"Erratum","source":"publisher","updated":{"date-parts":[[2018,6,5]],"date-time":"2018-06-05T00:00:00Z","timestamp":1528156800000}}],"container-title":["Lecture Notes in Computer Science","Applied Reconfigurable Computing. Architectures, Tools, and Applications"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-78890-6_44","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,20]],"date-time":"2019-05-20T03:39:43Z","timestamp":1558323583000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-78890-6_44"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783319788890","9783319788906"],"references-count":12,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-78890-6_44","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018]]},"assertion":[{"value":"8 April 2018","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ARC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Symposium on Applied Reconfigurable Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Santorini","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Greece","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":"2 May 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 May 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"arc2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/arc2018.esda-lab.cied.teiwest.gr\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}