{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T04:20:55Z","timestamp":1743049255151,"version":"3.40.3"},"publisher-location":"Cham","reference-count":34,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031407437"},{"type":"electronic","value":"9783031407444"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023]]},"DOI":"10.1007\/978-3-031-40744-4_10","type":"book-chapter","created":{"date-parts":[[2023,8,30]],"date-time":"2023-08-30T23:03:28Z","timestamp":1693436608000},"page":"147-162","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Multipurpose Cacheing to\u00a0Accelerate OpenMP Target Regions on\u00a0FPGAs"],"prefix":"10.1007","author":[{"given":"Julian","family":"Brandner","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Florian","family":"Mayer","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michael","family":"Philippsen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,9,1]]},"reference":[{"key":"10_CR1","doi-asserted-by":"publisher","unstructured":"Adler, M., Fleming, K.E., Parashar, A., Pellauer, M., Emer, J.: Leap scratchpads: automatic memory and cache management for reconfigurable logic. In: Proceedings of the International Symposium Field Programmable Gate Arrays (FPGA 2011), Monterey, CA, pp. 25\u201328, February 2011. https:\/\/doi.org\/10.1145\/1950413.1950421. Accessed 11 May 2023","DOI":"10.1145\/1950413.1950421"},{"key":"10_CR2","unstructured":"Arvind: Bluespec: a language for hardware design, simulation, synthesis and verification invited talk. In: Proceedings of the ACM and IEEE International Conference on Formal Methods and Models for Co-Design (MEMOCODE 2003), Mont Saint-Michel, France, pp. 249. IEEE Computer Society, June 2003"},{"key":"10_CR3","doi-asserted-by":"publisher","unstructured":"Asano, S., Maruyama, T., Yamaguchi, Y.: Performance comparison of FPGA, GPU and CPU in image processing. In: Proceedings of the International Conference on Field Programmable Logic and Applications (FPL 2009), Prague, Czech Republic, pp. 126\u2013131, September 2009. https:\/\/doi.org\/10.1109\/FPL.2009.5272532. Accessed 11 May 2023","DOI":"10.1109\/FPL.2009.5272532"},{"key":"10_CR4","doi-asserted-by":"publisher","unstructured":"Brandner, J., Mayer, F., Philippsen, M.: Reducing OpenMP to FPGA round-trip times with predictive modelling. In: Klemm, M., de Supinski, B.R., Klinkenberg, J., Neth, B. (eds.) IWOMP 2022. LNCS, vol. 13527, pp. 94\u2013108. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-15922-0_7. Accessed 11 May 2023","DOI":"10.1007\/978-3-031-15922-0_7"},{"key":"10_CR5","doi-asserted-by":"publisher","unstructured":"Castells-Rufas, D., et al.: Opencl-based FPGA accelerator for semi-global approximate string matching using diagonal bit-vectors. In: Proceedings of the International Conference on Field Programmable Logic and Applications (FPL 2021), Dresden, Germany, pp. 174\u2013178, May 2021. https:\/\/doi.org\/10.1109\/FPL53798.2021.00036. Accessed 11 May 2023","DOI":"10.1109\/FPL53798.2021.00036"},{"key":"10_CR6","doi-asserted-by":"publisher","unstructured":"Chen, R., Siriyal, S., Prasanna, V.: Energy and memory efficient mapping of bitonic sorting on FPGA. In: Proceedings of the International Symposium Field Programmable Gate Arrays (FPGA 2015), Monterey, CA, pp. 240\u2013249, February 2015. https:\/\/doi.org\/10.1145\/2684746.2689068. Accessed 11 May 2023","DOI":"10.1145\/2684746.2689068"},{"key":"10_CR7","doi-asserted-by":"publisher","unstructured":"Cheng, S., Lin, M., Liu, H.J., Scott, S., Wawrzynek, J.: Exploiting memory-level parallelism in reconfigurable accelerators. In: Proceedings of the International Symposium Field-Programmable Custom Computing Machines (FCCM 2012), Toronto, Canada, pp. 157\u2013160, April 2012. https:\/\/doi.org\/10.1109\/FCCM.2012.35. Accessed 11 May 2023","DOI":"10.1109\/FCCM.2012.35"},{"key":"10_CR8","doi-asserted-by":"publisher","unstructured":"Choi, J., Nam, K., Canis, A., Anderson, J., Brown, S., Czajkowski, T.: Impact of cache architecture and interface on performance and area of FPGA-based processor\/parallel-accelerator systems. In: Proceedings of the International Symposium Field-Programmable Custom Computing Machines (FCCM 2012), Toronto, Canada, pp. 17\u201324, April 2012. https:\/\/doi.org\/10.1109\/FCCM.2012.13. Accessed 11 May 2023","DOI":"10.1109\/FCCM.2012.13"},{"key":"10_CR9","doi-asserted-by":"publisher","unstructured":"Escobar, F.A., Kolar, A., Harb, N., Vinci Dos Santos, F., Valderrama, C.: Scalable shared-memory architecture to solve the knapsack 0\/1 problem. Microprocessors Microsyst. 50(3), 189\u2013201 (2017). https:\/\/doi.org\/10.1016\/j.micpro.2017.04.001. Accessed 11 May 2023","DOI":"10.1016\/j.micpro.2017.04.001"},{"key":"10_CR10","doi-asserted-by":"publisher","unstructured":"F\u00e4rber, C., Schwemmer, R., Machen, J., Neufeld, N.: Particle identification on an FPGA accelerated compute platform for the LHCb upgrade. IEEE Trans. Nuclear Sci. 64(7), 1994\u20131999 (2017). https:\/\/doi.org\/10.1109\/TNS.2017.2715900. Accessed 11 May 2023","DOI":"10.1109\/TNS.2017.2715900"},{"key":"10_CR11","doi-asserted-by":"publisher","unstructured":"Hematian, A., Chuprat, S., Manaf, A.A., Parsazadeh, N.: Zero-delay FPGA-based odd-even sorting network. In: Proceedings of the IEEE Symposium Computers Informatics (ISCI 2013), Langkawi, Malaysia, pp. 128\u2013131, April 2013. https:\/\/doi.org\/10.1109\/ISCI.2013.6612389. Accessed 11 May 2023","DOI":"10.1109\/ISCI.2013.6612389"},{"key":"10_CR12","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"265","DOI":"10.1007\/978-3-030-58144-2_17","volume-title":"OpenMP: Portable Multi-Level Parallelism on Modern Systems","author":"J Huthmann","year":"2020","unstructured":"Huthmann, J., Sommer, L., Podobas, A., Koch, A., Sano, K.: OpenMP device offloading to FPGAs using the nymble infrastructure. In: Milfeld, K., de Supinski, B.R., Koesterke, L., Klinkenberg, J. (eds.) IWOMP 2020. LNCS, vol. 12295, pp. 265\u2013279. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58144-2_17 Accessed 11 May 2023"},{"key":"10_CR13","doi-asserted-by":"publisher","unstructured":"Knaust, M., Mayer, F., Steinke, T.: OpenMP to FPGA offloading prototype using OpenCL SDK. In: Proceedings of the International Workshop High-Level Parallel Programing Models and Supportive Environment (HIPS 2019), Rio de Janeiro, Brazil, pp. 387\u2013390, May 2019. https:\/\/doi.org\/10.1109\/IPDPSW.2019.00072 (Accessed on May 11, 2023)","DOI":"10.1109\/IPDPSW.2019.00072"},{"key":"10_CR14","doi-asserted-by":"crossref","unstructured":"Korinth, J., Hofmann, J., Heinz, C., Koch, A.: The TaPaSCo open-source toolflow for the automated composition of task-based parallel reconfigurable computing systems. In: Proceedings of the International Symposium Applied Reconfigurable Computing, (ARC 2019), Darmstadt, Germany, pp. 214\u2013229, April 2019","DOI":"10.1007\/978-3-030-17227-5_16"},{"key":"10_CR15","doi-asserted-by":"publisher","unstructured":"Lipu, A.R., Amin, R., Islam Mondal, M.N., Mamun, M.A.: Exploiting parallelism for faster implementation of bubble sort algorithm using FPGA. In: Proceedings of the International Conference Electrical, Computer Telecommunication Engineering (ICECTE 2016), Rajshahi, Bangladesh, pp. 1\u20134, December 2016. https:\/\/doi.org\/10.1109\/ICECTE.2016.7879576. Accessed 11 May 2023","DOI":"10.1109\/ICECTE.2016.7879576"},{"key":"10_CR16","doi-asserted-by":"publisher","unstructured":"Ma, L., Lavagno, L., Lazarescu, M.T., Arif, A.: Acceleration by inline cache for memory-intensive algorithms on FPGA via high-level synthesis. IEEE Access 5, 18953\u201318974 (2017). https:\/\/doi.org\/10.1109\/ACCESS.2017.2750923. Accessed 11 May 2023","DOI":"10.1109\/ACCESS.2017.2750923"},{"key":"10_CR17","doi-asserted-by":"publisher","unstructured":"Matthews, E., Doyle, N.C., Shannon, L.: Design space exploration of l1 data caches for FPGA-based multiprocessor systems. In: Proceedings of the International Symposium Field Programmable Gate Arrays (FPGA 2015), Monterey, CA, pp. 156\u2013159, February 2015. https:\/\/doi.org\/10.1145\/2684746.2689083 (Accessed on May 11, 2023)","DOI":"10.1145\/2684746.2689083"},{"key":"10_CR18","doi-asserted-by":"publisher","unstructured":"Mayer, F., Brandner, J., Hellmann, M., Schwarzer, J., Philippsen, M.: The ORKA-HPC compiler\u2013practical OpenMP for FPGAs. In: Proceedings of the International Workshop Languages and Compilers for Parallel Computing (LCPC 2021). LNCS, Newark, DE, vol. 13181, pp. 83\u201397, October 2021. https:\/\/doi.org\/10.1007\/978-3-030-99372-6_6. Accessed 11 May 2023","DOI":"10.1007\/978-3-030-99372-6_6"},{"key":"10_CR19","doi-asserted-by":"publisher","unstructured":"Mayer, F., Brandner, J., Philippsen, M.: Employing polyhedral methods to reduce data movement in FPGA stencil codes. In: Mendis, C., Rauchwerger, L. (eds) LCPC 2022. LNCS, vol. 13829, pp. 47\u201363. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-31445-2_4. Accessed 11 May 2023","DOI":"10.1007\/978-3-031-31445-2_4"},{"key":"10_CR20","doi-asserted-by":"publisher","unstructured":"Mayer, F., Knaust, M., Philippsen, M.: OpenMP on FPGAs-a survey. In: Proceedings of the International Workshop OpenMP (IWOMP 2019), Auckland, New Zealand, pp. 94\u2013108, August 2019. https:\/\/doi.org\/10.1007\/978-3-030-28596-8_7. Accessed 11 May 2023","DOI":"10.1007\/978-3-030-28596-8_7"},{"key":"10_CR21","doi-asserted-by":"publisher","unstructured":"McEvoy, R.P., Crowe, F.M., Murphy, C.C., Marnane, W.P.: Optimisation of the SHA-2 family of hash functions on FPGAs. In: Proceedings of the IEEE Computer Society Annual Symposium Emerging VLSI Technologies and Architectures (ISVLSI 2006), Karlsruhe, Germany, pp. 317\u2013322, March 2006. https:\/\/doi.org\/10.1109\/ISVLSI.2006.70, Accessed 11 May 2023","DOI":"10.1109\/ISVLSI.2006.70"},{"key":"10_CR22","doi-asserted-by":"publisher","unstructured":"Meher, P.K., Chandrasekaran, S., Amira, A.: FPGA realization of FIR filters by efficient and flexible systolization using distributed arithmetic. IEEE Trans. Signal Processing 56(7), 3009\u20133017 (2008). https:\/\/doi.org\/10.1109\/TSP.2007.914926. Accessed 11 May 2023","DOI":"10.1109\/TSP.2007.914926"},{"key":"10_CR23","doi-asserted-by":"publisher","unstructured":"Moss, D.J., et al.: A customizable matrix multiplication framework for the Intel HARPv2 Xeon+FPGA platform: a deep learning case study. In: Proceedings of the International Symposium Field Programmable Gate Arrays (FPGA 2018), Monterey, CA, pp. 107\u2013116, February 2018. https:\/\/doi.org\/10.1145\/3174243.3174258. Accessed 11 May 2023","DOI":"10.1145\/3174243.3174258"},{"key":"10_CR24","doi-asserted-by":"publisher","unstructured":"Nepomuceno, R., Sterle, R., Valarini, G., Pereira, M., Yviquel, H., Araujo, G.: Enabling OpenMP task parallelism on multi-FPGAs. arXiv:2103.10573 [cs.DC], March 2021. https:\/\/doi.org\/10.1109\/FCCM51124.2021.00047. Accessed 11 May 2023","DOI":"10.1109\/FCCM51124.2021.00047"},{"key":"10_CR25","doi-asserted-by":"publisher","unstructured":"Nibbelink, K., Rajopadhye, S., McConnell, R.: 0\/1 knapsack on hardware: a complete solution. In: Proceedings of the International Conference on Application-Specific Systems, Architectures and Processors (ASAP 2007), Montr\u00e9al, Canada, pp. 160\u2013167, July 2007. https:\/\/doi.org\/10.1109\/ASAP.2007.4429974. Accessed 11 May 2023","DOI":"10.1109\/ASAP.2007.4429974"},{"key":"10_CR26","doi-asserted-by":"publisher","unstructured":"Park, S.Y., Meher, P.K.: Efficient FPGA and ASIC realizations of a DA-based reconfigurable FIR digital filter. IEEE Trans. Circuits and Systems II: Express Briefs 61(7), 511\u2013515 (2014). https:\/\/doi.org\/10.1109\/TCSII.2014.2324418. Accessed 11 May 2023","DOI":"10.1109\/TCSII.2014.2324418"},{"key":"10_CR27","doi-asserted-by":"crossref","unstructured":"Pouchet, L.N., Zhang, P., Sadayappan, P., Cong, J.: Polyhedral-based data reuse optimization for configurable computing. In: Proceedings of the International Symposium Field Programmable Gate Arrays (FPGA 2013), Montery, CA, pp. 29\u201338, February 2013","DOI":"10.1145\/2435264.2435273"},{"key":"10_CR28","doi-asserted-by":"publisher","unstructured":"Putnam, A., et al.: Performance and power of cache-based reconfigurable computing. SIGARCH Comput. Archit. News 37(3), 395\u2013405 (2009). https:\/\/doi.org\/10.1145\/1555815.1555804. Accessed 11 May 2023","DOI":"10.1145\/1555815.1555804"},{"key":"10_CR29","doi-asserted-by":"publisher","unstructured":"Qasaimeh, M., Denolf, K., Lo, J., Vissers, K., Zambreno, J., Jones, P.H.: Comparing energy efficiency of CPU, GPU and FPGA implementations for vision kernels. In: Proceedings of the IEEE International Conference on Embedded Software and Systems (ICESS 2019), Las Vegas, NV, pp. 1\u20138, June 2019. https:\/\/doi.org\/10.1109\/ICESS.2019.8782524. Accessed 11 May 2023","DOI":"10.1109\/ICESS.2019.8782524"},{"key":"10_CR30","doi-asserted-by":"publisher","unstructured":"Sklyarov, V., Skliarova, I.: High-performance implementation of regular and easily scalable sorting networks on an FPGA. Microprocessors and Microsystems 38(5), 470\u2013484 (2014). https:\/\/doi.org\/10.1016\/j.micpro.2014.03.003. Accessed 11 May 2023","DOI":"10.1016\/j.micpro.2014.03.003"},{"key":"10_CR31","unstructured":"SPEC: SPEC CPU 2006. https:\/\/www.spec.org\/cpu2006\/. Accessed 11 May 2023"},{"key":"10_CR32","doi-asserted-by":"publisher","unstructured":"Wang, K., Nurmi, J.: Using OpenCL to rapidly prototype FPGA designs. In: Proceedings of the IEEE Nordic Circuits and Systems Conference (NORCAS 2016), Copenhagen, Denmark, pp. 1\u20136, November 2016. https:\/\/doi.org\/10.1109\/NORCHIP.2016.7792907. Accessed 11 May 2023","DOI":"10.1109\/NORCHIP.2016.7792907"},{"key":"10_CR33","doi-asserted-by":"publisher","unstructured":"Winterstein, F., Fleming, K., Yang, H.J., Wickerson, J., Constantinides, G.: Custom-sized caches in application-specific memory hierarchies. In: Proceedings of the International Conference on Field Programmable Technology (FPT 2015), pp. 144\u2013151 (2015). https:\/\/doi.org\/10.1109\/FPT.2015.7393141. Accessed 11 May 2023","DOI":"10.1109\/FPT.2015.7393141"},{"key":"10_CR34","doi-asserted-by":"crossref","unstructured":"Yoshimi, M., Nishikawa, Y., Miki, M., Hiroyasu, T., Amano, H., Mencer, O.: A performance evaluation of CUBE: One-dimensional 512 FPGA cluster. In: Proceedings of the International Symposium Applied Reconfigurable Computing (ARC 2010), Bangkok, Thailand, pp. 372\u2013381, March 2010","DOI":"10.1007\/978-3-642-12133-3_36"}],"container-title":["Lecture Notes in Computer Science","OpenMP: Advanced Task-Based, Device and Compiler Programming"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-40744-4_10","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,30]],"date-time":"2023-08-30T23:04:21Z","timestamp":1693436661000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-40744-4_10"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031407437","9783031407444"],"references-count":34,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-40744-4_10","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"1 September 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"IWOMP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Workshop on OpenMP","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Bristol","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"United Kingdom","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 September 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 September 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iwomp2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.iwomp.org","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 (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"20","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"15","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"75% - 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 (provided by the conference organizers)"}},{"value":"4","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"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 (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}