{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T16:54:49Z","timestamp":1774630489459,"version":"3.50.1"},"publisher-location":"Cham","reference-count":38,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031725661","type":"print"},{"value":"9783031725678","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[[2024]]},"DOI":"10.1007\/978-3-031-72567-8_4","type":"book-chapter","created":{"date-parts":[[2024,9,19]],"date-time":"2024-09-19T16:19:25Z","timestamp":1726762765000},"page":"49-63","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Integrating Multi-FPGA Acceleration to\u00a0OpenMP Distributed Computing"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6482-8745","authenticated-orcid":false,"given":"Pedro Henrique","family":"Rosso","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3480-0570","authenticated-orcid":false,"given":"Lucian","family":"Petrica","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7929-0191","authenticated-orcid":false,"given":"Nusrat Jahan","family":"Lisa","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1140-4513","authenticated-orcid":false,"given":"Marcio","family":"Pereira","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9539-6874","authenticated-orcid":false,"given":"Sandro","family":"Rigo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1214-3431","authenticated-orcid":false,"given":"Herv\u00e9","family":"Yviquel","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1743-8004","authenticated-orcid":false,"given":"Vanderlei","family":"Bonato","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5374-2521","authenticated-orcid":false,"given":"Emilio","family":"Francesquini","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4869-5190","authenticated-orcid":false,"given":"Guido","family":"Araujo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,9,16]]},"reference":[{"key":"4_CR1","unstructured":"OpenMP Cluster - FPGA Artifacts. https:\/\/gitlab.com\/phrosso\/researchartifacts\/-\/tree\/master"},{"key":"4_CR2","unstructured":"OpenMP Cluster - FPGA Repository. https:\/\/gitlab.com\/ompcluster\/llvm-project\/-\/tree\/fpga\/alveo-plugin"},{"key":"4_CR3","unstructured":"Accelerating sensor signal processing with the Alveo U55C card (2022). https:\/\/www.xilinx.com\/content\/dam\/xilinx\/publications\/solution-briefs\/sensor-signal-processing-solution-brief.pdf. Accessed 03 Nov 2023"},{"key":"4_CR4","unstructured":"Color blindness (2023). https:\/\/www.nei.nih.gov\/learn-about-eye-health\/eye-conditions-and-diseases\/color-blindness. Accessed 26 Oct 2023"},{"key":"4_CR5","unstructured":"HACC ETH Zurich Cluster (2023). https:\/\/www.amd-haccs.io\/ethz.html. Accessed 03 Nov 2023"},{"key":"4_CR6","unstructured":"Amazon Web Services: Amazon EC2 F1 instances (2019). https:\/\/aws.amazon.com\/ec2\/instance-types\/f1. Accessed 26 Oct 2023"},{"key":"4_CR7","doi-asserted-by":"publisher","unstructured":"Antao, S.F., et al.: Offloading support for OpenMP in clang and LLVM. In: 2016 Third Workshop on the LLVM Compiler Infrastructure in HPC (LLVM-HPC), pp. 1\u201311 (2016). https:\/\/doi.org\/10.1109\/LLVM-HPC.2016.006","DOI":"10.1109\/LLVM-HPC.2016.006"},{"key":"4_CR8","doi-asserted-by":"crossref","unstructured":"Bosch, J., et al.: Application acceleration on fpgas with ompss@ fpga. In: 2018 International Conference on Field-Programmable Technology (FPT), pp. 70\u201377. IEEE (2018)","DOI":"10.1109\/FPT.2018.00021"},{"key":"4_CR9","doi-asserted-by":"crossref","unstructured":"Cardwell, D., Song, F.: An extended roofline model with communication-awareness for distributed-memory HPC systems. In: Proceedings of the International Conference on High Performance Computing in Asia-Pacific Region, pp. 26\u201335 (2019)","DOI":"10.1145\/3293320.3293321"},{"key":"4_CR10","doi-asserted-by":"publisher","unstructured":"Caulfield, A.M., et al.: A cloud-scale acceleration architecture. In: 2016 49th Annual IEEE\/ACM International Symposium on Microarchitecture (MICRO), pp. 1\u201313 (2016). https:\/\/doi.org\/10.1109\/MICRO.2016.7783710","DOI":"10.1109\/MICRO.2016.7783710"},{"key":"4_CR11","doi-asserted-by":"crossref","unstructured":"Ceissler, C., Nepomuceno, R., Pereira, M., Araujo, G.: Automatic offloading of cluster accelerators. In: 2018 IEEE 26th Annual International Symposium on Field-Programmable Custom Computing Machines (FCCM), pp. 224\u2013224. IEEE (2018)","DOI":"10.1109\/FCCM.2018.00058"},{"key":"4_CR12","doi-asserted-by":"crossref","unstructured":"Choi, J., Brown, S., Anderson, J.: From software threads to parallel hardware in high-level synthesis for FPGAs. In: 2013 International Conference on Field-Programmable Technology (FPT), pp. 270\u2013277. IEEE (2013)","DOI":"10.1109\/FPT.2013.6718365"},{"key":"4_CR13","doi-asserted-by":"crossref","unstructured":"Cilardo, A., Gallo, L., Mazzeo, A., Mazzocca, N.: Efficient and scalable OpenMP-based system-level design. In: 2013 Design, Automation & Test in Europe Conference & Exhibition (DATE), pp. 988\u2013991. IEEE (2013)","DOI":"10.7873\/DATE.2013.206"},{"issue":"02","key":"4_CR14","doi-asserted-by":"publisher","first-page":"173","DOI":"10.1142\/S0129626411000151","volume":"21","author":"A Duran","year":"2011","unstructured":"Duran, A., et al.: Ompss: a proposal for programming heterogeneous multi-core architectures. Parallel Process. Lett. 21(02), 173\u2013193 (2011)","journal-title":"Parallel Process. Lett."},{"key":"4_CR15","unstructured":"Esmaeilzadeh, H., Blem, E., Sankaralingam, R.S.A.K., Burger, D.: Retrospective: dark silicon and the end of multicore scaling"},{"key":"4_CR16","doi-asserted-by":"crossref","unstructured":"Filgueras, A., et al.: OmpSs@ Zynq all-programmable SoC ecosystem. In: Proceedings of the 2014 ACM\/SIGDA International Symposium on Field-Programmable Gate Arrays, pp. 137\u2013146 (2014)","DOI":"10.1145\/2554688.2554777"},{"key":"4_CR17","series-title":"LNCSE","doi-asserted-by":"publisher","first-page":"96","DOI":"10.1007\/978-3-540-73750-6_4","volume-title":"Principal Manifolds for Data Visualization and Dimension Reduction","author":"AN Gorban","year":"2008","unstructured":"Gorban, A.N., Zinovyev, A.Y.: Elastic maps and nets for approximating principal manifolds and their application to microarray data visualization. In: Gorban, A.N., K\u00e9gl, B., Wunsch, D.C., Zinovyev, A.Y. (eds.) Principal Manifolds for Data Visualization and Dimension Reduction. LNCSE, vol. 58, pp. 96\u2013130. Springer, Heidelberg (2008). https:\/\/doi.org\/10.1007\/978-3-540-73750-6_4"},{"key":"4_CR18","unstructured":"Halstead, M.H.: Elements of Software Science (Operating and programming systems series). Elsevier Science Inc. (1977)"},{"key":"4_CR19","doi-asserted-by":"crossref","unstructured":"de\u00a0Haro, J.M., et al.: OmpSs@ cloudFPGA: an FPGA task-based programming model with message passing. In: 2022 IEEE International Parallel and Distributed Processing Symposium (IPDPS), pp. 828\u2013838. IEEE (2022)","DOI":"10.1109\/IPDPS53621.2022.00085"},{"key":"4_CR20","doi-asserted-by":"publisher","unstructured":"He, Z., Parravicini, D., Petrica, L., O\u2019Brien, K., Alonso, G., Blott, M.: ACCL: FPGA-accelerated collectives over 100 Gbps TCP-IP. In: 2021 IEEE\/ACM International Workshop on Heterogeneous High-Performance Reconfigurable Computing (H2RC), pp. 33\u201343 (2021). https:\/\/doi.org\/10.1109\/H2RC54759.2021.00009","DOI":"10.1109\/H2RC54759.2021.00009"},{"key":"4_CR21","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"},{"key":"4_CR22","doi-asserted-by":"crossref","unstructured":"Kadosh, T., Hasabnis, N., Mattson, T., Pinter, Y., Oren, G.: Quantifying OpenMP: statistical insights into usage and adoption. arXiv preprint arXiv:2308.08002 (2023)","DOI":"10.1109\/HPEC58863.2023.10363459"},{"key":"4_CR23","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/978-3-319-31596-6_1","volume-title":"The Dark Side of Silicon","author":"A Kanduri","year":"2017","unstructured":"Kanduri, A., Rahmani, A.M., Liljeberg, P., Hemani, A., Jantsch, A., Tenhunen, H.: A perspective on dark silicon. In: Rahmani, A.M., Liljeberg, P., Hemani, A., Jantsch, A., Tenhunen, H. (eds.) The Dark Side of Silicon, pp. 3\u201320. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-31596-6_1"},{"key":"4_CR24","doi-asserted-by":"crossref","unstructured":"Knaust, M., Mayer, F., Steinke, T.: OpenMP to FPGA offloading prototype using OpenCL SDK. In: 2019 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW), pp. 387\u2013390. IEEE (2019)","DOI":"10.1109\/IPDPSW.2019.00072"},{"key":"4_CR25","doi-asserted-by":"publisher","unstructured":"Lattner, C., Adve, V.: LLVM: a compilation framework for lifelong program analysis & transformation. In: International Symposium on Code Generation and Optimization, 2004. CGO 2004, pp. 75\u201386 (2004). https:\/\/doi.org\/10.1109\/CGO.2004.1281665","DOI":"10.1109\/CGO.2004.1281665"},{"issue":"4","key":"4_CR26","doi-asserted-by":"publisher","first-page":"882","DOI":"10.3390\/electronics12040882","volume":"12","author":"E Liel\u0101murs","year":"2023","unstructured":"Liel\u0101murs, E., Cvetkovs, A., Novickis, R., Ozols, K.: Infrared image pre-processing and IR\/RGB registration with FPGA implementation. Electronics 12(4), 882 (2023)","journal-title":"Electronics"},{"key":"4_CR27","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1007\/978-3-030-99372-6_6","volume-title":"Languages and Compilers for Parallel Computing","author":"F Mayer","year":"2022","unstructured":"Mayer, F., Brandner, J., Hellmann, M., Schwarzer, J., Philippsen, M.: The ORKA-HPC compiler\u2014practical OpenMP for\u00a0FPGAs. In: Li, X., Chandrasekaran, S. (eds.) LCPC 2021. LNCS, vol. 13181, pp. 83\u201397. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-030-99372-6_6"},{"key":"4_CR28","doi-asserted-by":"crossref","unstructured":"Nepomuceno, R., Sterle, R., Valarini, G., Pereira, M., Yviquel, H., Araujo, G.: Enabling openMP task parallelism on multi-FPGAs. In: 2021 IEEE 29th Annual International Symposium on Field-Programmable Custom Computing Machines (FCCM), pp. 260\u2013260. IEEE (2021)","DOI":"10.1109\/FCCM51124.2021.00047"},{"key":"4_CR29","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"128","DOI":"10.1007\/978-3-319-98521-3_9","volume-title":"Evolving OpenMP for Evolving Architectures","author":"SJ Pennycook","year":"2018","unstructured":"Pennycook, S.J., Sewall, J.D., Duran, A.: Supporting function variants in OpenMP. In: de Supinski, B.R., Valero-Lara, P., Martorell, X., Mateo Bellido, S., Labarta, J. (eds.) IWOMP 2018. LNCS, vol. 11128, pp. 128\u2013142. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-319-98521-3_9"},{"key":"4_CR30","doi-asserted-by":"crossref","unstructured":"Podobas, A., Brorsson, M.: Empowering openMP with automatically generated hardware. In: 2016 International Conference on Embedded Computer Systems: Architectures, Modeling and Simulation (SAMOS), pp. 245\u2013252. IEEE (2016)","DOI":"10.1109\/SAMOS.2016.7818354"},{"key":"4_CR31","unstructured":"Rosso, P.H.D.F.: Recolora\u00e7\u00e3o de imagens para dicromatas baseada em mapas el\u00e1sticos (2018). https:\/\/repositorio.ufsc.br\/handle\/123456789\/192338. Accessed 26 Oct 2023"},{"key":"4_CR32","doi-asserted-by":"crossref","unstructured":"Slaughter, E., et\u00a0al.: Task bench: a parameterized benchmark for evaluating parallel runtime performance. In: SC20: International Conference for High Performance Computing, Networking, Storage and Analysis, pp. 1\u201315. IEEE (2020)","DOI":"10.1109\/SC41405.2020.00066"},{"key":"4_CR33","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 (2017)","DOI":"10.1109\/ASAP.2017.7995280"},{"key":"4_CR34","doi-asserted-by":"publisher","unstructured":"Strickland, M.: FPGA accelerated HPC and data analytics. In: 2018 International Conference on Field-Programmable Technology (FPT), pp. 21\u201321 (2018). https:\/\/doi.org\/10.1109\/FPT.2018.00009","DOI":"10.1109\/FPT.2018.00009"},{"issue":"10","key":"4_CR35","first-page":"4003","volume":"69","author":"L Xuan","year":"2022","unstructured":"Xuan, L., Un, K.F., Lam, C.S., Martins, R.P.: An FPGA-based energy-efficient reconfigurable depthwise separable convolution accelerator for image recognition. IEEE Trans. Circuits Syst. II Express Briefs 69(10), 4003\u20134007 (2022)","journal-title":"IEEE Trans. Circuits Syst. II Express Briefs"},{"key":"4_CR36","series-title":"CCIS","doi-asserted-by":"publisher","first-page":"227","DOI":"10.1007\/978-3-031-23606-8_14","volume-title":"SMC 2022","author":"AR Young","year":"2023","unstructured":"Young, A.R., Miniskar, N.R., Liu, F., Blokland, W., Vetter, J.S.: Adrastea: an efficient FPGA design environment for heterogeneous scientific computing and machine learning. In: Doug, K., Al, G., Pophale, S., Liu, H., Parete-Koon, S. (eds.) SMC 2022. CCIS, vol. 1690, pp. 227\u2013243. Springer, Cham (2023). https:\/\/doi.org\/10.1007\/978-3-031-23606-8_14"},{"key":"4_CR37","doi-asserted-by":"crossref","unstructured":"Yviquel, H., et\u00a0al.: The OpenMP cluster programming model. In: Workshop Proceedings of the 51st International Conference on Parallel Processing, pp. 1\u201311 (2022)","DOI":"10.1145\/3547276.3548444"},{"key":"4_CR38","doi-asserted-by":"crossref","unstructured":"Zhu, Y., He, Z., Jiang, W., Zeng, K., Zhou, J., Alonso, G.: Distributed recommendation inference on FPGA clusters. In: 2021 31st International Conference on Field-Programmable Logic and Applications (FPL), pp. 279\u2013285. IEEE (2021)","DOI":"10.1109\/FPL53798.2021.00057"}],"container-title":["Lecture Notes in Computer Science","Advancing OpenMP for Future Accelerators"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72567-8_4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,19]],"date-time":"2024-09-19T16:20:00Z","timestamp":1726762800000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72567-8_4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031725661","9783031725678"],"references-count":38,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72567-8_4","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"16 September 2024","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":"Perth, WA","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Australia","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 September 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iwomp2024","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"}}]}}