{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,25]],"date-time":"2026-04-25T15:05:27Z","timestamp":1777129527571,"version":"3.51.4"},"publisher-location":"Cham","reference-count":29,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030172268","type":"print"},{"value":"9783030172275","type":"electronic"}],"license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"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":[],"published-print":{"date-parts":[[2019]]},"DOI":"10.1007\/978-3-030-17227-5_15","type":"book-chapter","created":{"date-parts":[[2019,4,1]],"date-time":"2019-04-01T19:07:34Z","timestamp":1554145654000},"page":"199-213","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Evaluating LULESH Kernels on OpenCL FPGA"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7197-780X","authenticated-orcid":false,"given":"Zheming","family":"Jin","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7551-7122","authenticated-orcid":false,"given":"Hal","family":"Finkel","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,3,29]]},"reference":[{"key":"15_CR1","doi-asserted-by":"crossref","unstructured":"Huang, S., Manikandan, G.J., Ramachandran, A., Rupnow, K., Hwu, W.M.W., Chen, D.: Hardware acceleration of the pair-HMM algorithm for DNA variant calling. In: Proceedings of the 2017 ACM\/SIGDA International Symposium on Field-Programmable Gate Arrays, pp. 275\u2013284. ACM, February 2017","DOI":"10.1145\/3020078.3021749"},{"key":"15_CR2","doi-asserted-by":"crossref","unstructured":"Casper, J., Olukotun, K.: Hardware acceleration of database operations. In: Proceedings of the 2014 ACM\/SIGDA International Symposium on Field-Programmable Gate Arrays, pp. 151\u2013160. ACM, February 2014","DOI":"10.1145\/2554688.2554787"},{"key":"15_CR3","doi-asserted-by":"crossref","unstructured":"Inggs, G., Thomas, D., Luk, W.: A heterogeneous computing framework for computational finance. In: 2013 42nd International Conference on Parallel Processing (ICPP), pp. 688\u2013697. IEEE, October 2013","DOI":"10.1109\/ICPP.2013.82"},{"key":"15_CR4","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: 2013 18th Asia and South Pacific Design Automation Conference (ASP-DAC), pp. 297\u2013304. IEEE, January 2013","DOI":"10.1109\/ASPDAC.2013.6509612"},{"key":"15_CR5","doi-asserted-by":"crossref","unstructured":"Sharma, H., et al.: From high-level deep neural models to FPGAs. In: 2016 49th Annual IEEE\/ACM International Symposium on Microarchitecture (MICRO), pp. 1\u201312. IEEE, October 2016","DOI":"10.1109\/MICRO.2016.7783720"},{"key":"15_CR6","doi-asserted-by":"crossref","unstructured":"Kirsch, S., Rettig, F., Hutter, D., de Cuveland, J., Angelov, V., Lin-denstruth, V.: An FPGA-based high-speed, low-latency processing system for high-energy physics. In: 2010 International Conference on Field Programmable Logic and Applications (FPL), pp. 562\u2013567. IEEE, August 2010","DOI":"10.1109\/FPL.2010.110"},{"issue":"3","key":"15_CR7","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":"15_CR8","unstructured":"Intel FPGA SDK for OpenCL Cyclone V SoC Getting Started Guide. Intel (2017)"},{"key":"15_CR9","unstructured":"Intel FPGA SDK for OpenCL Stratix V Network Reference Platform Porting Guide. Intel (2017)"},{"key":"15_CR10","unstructured":"Intel FPGA SDK for OpenCL Arria 10 GX FPGA Development Kit Reference Platform Porting Guide. Intel (2017)"},{"key":"15_CR11","unstructured":"Loring Wirbel: Xilinx SDAccel Whitepaper. Xilinx (2014)"},{"key":"15_CR12","doi-asserted-by":"crossref","unstructured":"Karlin, I.: LULESH programming model and performance ports over-view (No. LLNL-TR-608824). Lawrence Livermore National Laboratory (LLNL), Livermore, CA (2012)","DOI":"10.2172\/1059462"},{"key":"15_CR13","unstructured":"CORAL Benchmark Codes. https:\/\/asc.llnl.gov\/CORAL-benchmarks\/"},{"key":"15_CR14","doi-asserted-by":"crossref","unstructured":"Bercea, G.T., et al.: Performance analysis of OpenMP on a GPU using a CORAL proxy application. In: Proceedings of the 6th International Workshop on Performance Modeling, Benchmarking, and Simulation of High Performance Computing Systems, p. 2. ACM, November 2015","DOI":"10.1145\/2832087.2832089"},{"key":"15_CR15","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"664","DOI":"10.1007\/978-3-319-75178-8_53","volume-title":"Euro-Par 2017: Parallel Processing Workshops","author":"Z Jin","year":"2018","unstructured":"Jin, Z., Finkel, H., Yoshii, K., Cappello, F.: Evaluation of a floating-point intensive kernel on FPGA. In: Heras, D.B., Boug\u00e9, L. (eds.) Euro-Par 2017. LNCS, vol. 10659, pp. 664\u2013675. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-319-75178-8_53"},{"key":"15_CR16","doi-asserted-by":"crossref","unstructured":"Le\u00f3n, E.A., Karlin, I.: Characterizing the impact of program optimizations on power and energy for explicit hydrodynamics. In: 2014 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW), pp. 773\u2013781. IEEE, May 2014","DOI":"10.1109\/IPDPSW.2014.89"},{"key":"15_CR17","doi-asserted-by":"crossref","unstructured":"Le\u00f3n, E.A., Karlin, I., Grant, R.E.: Optimizing explicit hydrodynamics for power, energy, and performance. In: 2015 IEEE International Conference on Cluster Computing (CLUSTER), pp. 11\u201321. IEEE, September 2015","DOI":"10.1109\/CLUSTER.2015.12"},{"key":"15_CR18","doi-asserted-by":"crossref","unstructured":"Wu, X., Taylor, V., Cook, J. Juedeman, T.: Performance and power characteristics and optimizations of hybrid MPI\/OpenMP LULESH miniapps under various workloads. In: Proceedings of the 5th International Workshop on Energy Efficient Supercomputing, p. 4. ACM, November 2017","DOI":"10.1145\/3149412.3149416"},{"key":"15_CR19","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"185","DOI":"10.1007\/978-3-319-27308-2_16","volume-title":"Euro-Par 2015: Parallel Processing Workshops","author":"R Lim","year":"2015","unstructured":"Lim, R., Malony, A., Norris, B., Chaimov, N.: Identifying optimization opportunities within kernel execution in GPU codes. In: Hunold, S., et al. (eds.) Euro-Par 2015. LNCS, vol. 9523, pp. 185\u2013196. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-27308-2_16"},{"key":"15_CR20","doi-asserted-by":"crossref","unstructured":"Sulyok, A.A., Balogh, G.D., Reguly, I.Z., Mudalige, G.R.: Improving locality of unstructured mesh algorithms on GPUs. arXiv preprint arXiv:1802.03749 (2018)","DOI":"10.1016\/j.jpdc.2019.07.011"},{"key":"15_CR21","doi-asserted-by":"crossref","unstructured":"Karlin, I., McGraw, J., Gallardo, E., Keasler, J., Leon, E.A., Still, B.: Memory and parallelism exploration using the LULESH proxy application. In: 2012 SC Companion: High Performance Computing, Networking, Storage and Analysis (SCC), pp. 1427\u20131428. IEEE, November 2012","DOI":"10.1109\/SC.Companion.2012.235"},{"key":"15_CR22","doi-asserted-by":"crossref","unstructured":"Lee, S., Vetter, J.S.: OpenARC: open accelerator research compiler for directive-based, efficient heterogeneous computing. In: Proceedings of the 23rd International Symposium on High-performance Parallel and Distributed Computing, pp. 115\u2013120. ACM, June 2014","DOI":"10.1145\/2600212.2600704"},{"key":"15_CR23","doi-asserted-by":"crossref","unstructured":"Lee, S., Kim, J., Vetter, J.S.: OpenACC to FPGA: a framework for directive-based high-performance reconfigurable computing. In: 2016 IEEE International Parallel and Distributed Processing Symposium, pp. 544\u2013554. IEEE, May 2016","DOI":"10.1109\/IPDPS.2016.28"},{"key":"15_CR24","doi-asserted-by":"crossref","unstructured":"Sommer, L., Korinth, J., Koch, A.: OpenMP device offloading to FPGA accelerators. In: 2017 IEEE 28th International Conference on Application-specific Systems, Architectures and Processors (ASAP), pp. 201\u2013205. IEEE, July 2017","DOI":"10.1109\/ASAP.2017.7995280"},{"key":"15_CR25","doi-asserted-by":"crossref","unstructured":"Gautier, Q., Althoff, A., Meng, P., Kastner, R.: Spector: an OpenCL FPGA benchmark suite. In: 2016 International Conference on Field-Programmable Technology (FPT), pp. 141\u2013148. IEEE, December 2016","DOI":"10.1109\/FPT.2016.7929519"},{"key":"15_CR26","doi-asserted-by":"crossref","unstructured":"Wang, Z., He, B., Zhang, W., Jiang, S.: A performance analysis framework for optimizing OpenCL applications on FPGAs. In: 2016 IEEE International Symposium on High Performance Computer Architecture (HPCA), pp. 114\u2013125. IEEE, March 2016","DOI":"10.1109\/HPCA.2016.7446058"},{"issue":"12","key":"15_CR27","doi-asserted-by":"publisher","first-page":"3547","DOI":"10.1109\/TPDS.2016.2537805","volume":"27","author":"Z Wang","year":"2016","unstructured":"Wang, Z., Zhang, S., He, B., Zhang, W.: Melia: a map reduce framework on OpenCL-based FPGAs. IEEE Trans. Parallel Distrib. Syst. 27(12), 3547\u20133560 (2016)","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"key":"15_CR28","unstructured":"Settle, S.O.: High-performance dynamic programming on FPGAs with OpenCL. In: Proceedings of the IEEE High Perform Extreme Computing Conference (HPEC), pp. 1\u20136, September 2013"},{"key":"15_CR29","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: 2013 18th Asia and South Pacific Design Automation Conference (ASP-DAC), pp. 297\u2013304. IEEE, January 2013","DOI":"10.1109\/ASPDAC.2013.6509612"}],"container-title":["Lecture Notes in Computer Science","Applied Reconfigurable Computing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-17227-5_15","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,11,22]],"date-time":"2019-11-22T17:36:34Z","timestamp":1574444194000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-17227-5_15"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030172268","9783030172275"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-17227-5_15","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019]]},"assertion":[{"value":"29 March 2019","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":"Darmstadt","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Germany","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2019","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9 April 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11 April 2019","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"arc2019","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.arc2019.tu-darmstadt.de\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"52","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"20","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"7","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"38% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"4.5","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"4","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}}]}}