{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T23:42:34Z","timestamp":1743118954663,"version":"3.40.3"},"publisher-location":"Cham","reference-count":33,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031460760"},{"type":"electronic","value":"9783031460777"}],"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\/978-3-031-46077-7_7","type":"book-chapter","created":{"date-parts":[[2023,11,6]],"date-time":"2023-11-06T11:01:58Z","timestamp":1699268518000},"page":"91-106","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Characterization of\u00a0a\u00a0Coherent Hardware Accelerator Framework for\u00a0SoCs"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5323-0761","authenticated-orcid":false,"given":"Guillem","family":"L\u00f3pez-Parad\u00eds","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7696-9473","authenticated-orcid":false,"given":"Balaji","family":"Venu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2869-668X","authenticated-orcid":false,"given":"Adri\u00e1","family":"Armejach","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9848-8758","authenticated-orcid":false,"given":"Miquel","family":"Moret\u00f3","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,11,7]]},"reference":[{"key":"7_CR1","unstructured":"Compute Express Link, CXL Consortium White Paper. https:\/\/docs.wixstatic.com\/ugd\/0c1418_d9878707bbb7427786b70c3c91d5fbd1.pdf"},{"key":"7_CR2","unstructured":"Compute Library by Arm. https:\/\/github.com\/ARM-software\/ComputeLibrary"},{"key":"7_CR3","unstructured":"Enabling hardware accelerator and SoC design space exploration. https:\/\/community.arm.com\/arm-research\/b\/articles\/posts\/enabling-hardware-accelerator-and-soc-design-space-exploration"},{"key":"7_CR4","unstructured":"An Introduction to CCIX White Paper. https:\/\/www.ccixconsortium.com\/wp-content\/uploads\/2019\/11\/CCIX-White-Paper-Rev111219.pdf"},{"key":"7_CR5","unstructured":"PCI Express Base Specification Revision 6.0, PCI-SIG. https:\/\/pcisig.com\/specifications"},{"key":"7_CR6","doi-asserted-by":"publisher","unstructured":"Alsop, J., Sinclair, M., Adve, S.: Spandex: a flexible interface for efficient heterogeneous coherence. In: 2018 ACM\/IEEE 45th Annual International Symposium on Computer Architecture (ISCA), pp. 261\u2013274 (2018). https:\/\/doi.org\/10.1109\/ISCA.2018.00031","DOI":"10.1109\/ISCA.2018.00031"},{"key":"7_CR7","doi-asserted-by":"publisher","unstructured":"Choi, B., et al.: DeNovo: rethinking the memory hierarchy for disciplined parallelism. In: 2011 International Conference on Parallel Architectures and Compilation Techniques, pp. 155\u2013166 (2011). https:\/\/doi.org\/10.1109\/PACT.2011.21","DOI":"10.1109\/PACT.2011.21"},{"key":"7_CR8","doi-asserted-by":"publisher","unstructured":"Choi, Y.K., Cong, J., Fang, Z., Hao, Y., Reinman, G., Wei, P.: A quantitative analysis on microarchitectures of modern CPU-FPGA platforms. In: Proceedings of the 53rd Annual Design Automation Conference, DAC 2016, Association for Computing Machinery, New York (2016). https:\/\/doi.org\/10.1145\/2897937.2897972","DOI":"10.1145\/2897937.2897972"},{"key":"7_CR9","doi-asserted-by":"publisher","unstructured":"Choi, Y.K., Cong, J., Fang, Z., Hao, Y., Reinman, G., Wei, P.: In-depth analysis on microarchitectures of modern heterogeneous CPU-FPGA platforms. ACM Trans. Reconfigurable Technol. Syst. 12(1) (2019). https:\/\/doi.org\/10.1145\/3294054","DOI":"10.1145\/3294054"},{"issue":"7","key":"7_CR10","doi-asserted-by":"publisher","first-page":"48","DOI":"10.1145\/3361682","volume":"63","author":"WJ Dally","year":"2020","unstructured":"Dally, W.J., Turakhia, Y., Han, S.: Domain-specific hardware accelerators. Commun. ACM 63(7), 48\u201357 (2020). https:\/\/doi.org\/10.1145\/3361682","journal-title":"Commun. ACM"},{"issue":"2","key":"7_CR11","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1109\/MM.2017.37","volume":"37","author":"D Foley","year":"2017","unstructured":"Foley, D., Danskin, J.: Ultra-performance pascal GPU and NVLink interconnect. IEEE Micro 37(2), 7\u201317 (2017). https:\/\/doi.org\/10.1109\/MM.2017.37","journal-title":"IEEE Micro"},{"issue":"6","key":"7_CR12","doi-asserted-by":"publisher","first-page":"36","DOI":"10.1109\/MM.2018.2877288","volume":"38","author":"D Giri","year":"2018","unstructured":"Giri, D., Mantovani, P., Carloni, L.P.: Accelerators and coherence: an SoC perspective. IEEE Micro 38(6), 36\u201345 (2018). https:\/\/doi.org\/10.1109\/MM.2018.2877288","journal-title":"IEEE Micro"},{"key":"7_CR13","doi-asserted-by":"publisher","unstructured":"Hao, Y., Fang, Z., Reinman, G., Cong, J.: Supporting address translation for accelerator-centric architectures. In: 2017 IEEE International Symposium on High Performance Computer Architecture (HPCA), pp. 37\u201348 (2017). https:\/\/doi.org\/10.1109\/HPCA.2017.19","DOI":"10.1109\/HPCA.2017.19"},{"issue":"12","key":"7_CR14","doi-asserted-by":"publisher","first-page":"36","DOI":"10.1145\/3460970","volume":"64","author":"MD Hill","year":"2021","unstructured":"Hill, M.D., Reddi, V.J.: Accelerator-level parallelism. Commun. ACM 64(12), 36\u201338 (2021). https:\/\/doi.org\/10.1145\/3460970","journal-title":"Commun. ACM"},{"key":"7_CR15","doi-asserted-by":"publisher","unstructured":"Ito, M., Ohara, M.: A power-efficient FPGA accelerator: systolic array with cache-coherent interface for pair-HMM algorithm. In: 2016 IEEE Symposium in Low-Power and High-Speed Chips (COOL CHIPS XIX), pp. 1\u20133 (2016). https:\/\/doi.org\/10.1109\/CoolChips.2016.7503681","DOI":"10.1109\/CoolChips.2016.7503681"},{"key":"7_CR16","doi-asserted-by":"publisher","unstructured":"Jouppi, N.P., et al.: In-datacenter performance analysis of a tensor processing unit (2017). https:\/\/doi.org\/10.1145\/3079856.3080246","DOI":"10.1145\/3079856.3080246"},{"key":"7_CR17","doi-asserted-by":"publisher","unstructured":"Kelm, J.H., Johnson, D.R., Tuohy, W., Lumetta, S.S., Patel, S.J.: Cohesion: a hybrid memory model for accelerators. In: Proceedings of the 37th Annual International Symposium on Computer Architecture, ISCA 2010, pp. 429\u2013440. Association for Computing Machinery, New York (2010). https:\/\/doi.org\/10.1145\/1815961.1816019","DOI":"10.1145\/1815961.1816019"},{"key":"7_CR18","doi-asserted-by":"publisher","unstructured":"Kumar, S., Shriraman, A., Vedula, N.: Fusion: design tradeoffs in coherent cache hierarchies for accelerators. In: Proceedings of the 42nd Annual International Symposium on Computer Architecture, ISCA 2015, pp. 733\u2013745. Association for Computing Machinery, New York (2015). https:\/\/doi.org\/10.1145\/2749469.2750421","DOI":"10.1145\/2749469.2750421"},{"key":"7_CR19","doi-asserted-by":"publisher","unstructured":"L\u00f3pez-Parad\u00eds, G., Armejach, A., Moret\u00f3, M.: Gem5 + RTL: a framework to enable RTL models inside a full-system simulator. In: Proceedings of the 50th International Conference on Parallel Processing, ICPP 2021, Association for Computing Machinery, New York (2021). https:\/\/doi.org\/10.1145\/3472456.3472461","DOI":"10.1145\/3472456.3472461"},{"key":"7_CR20","doi-asserted-by":"publisher","unstructured":"Min, S.W., Huang, S., El-Hadedy, M., Xiong, J., Chen, D., Hwu, W.M.: Analysis and optimization of i\/o cache coherency strategies for SoC-FPGA device. In: 2019 29th International Conference on Field Programmable Logic and Applications (FPL), pp. 301\u2013306 (2019). https:\/\/doi.org\/10.1109\/FPL.2019.00055","DOI":"10.1109\/FPL.2019.00055"},{"issue":"5","key":"7_CR21","doi-asserted-by":"publisher","first-page":"4368","DOI":"10.1109\/TIE.2017.2766581","volume":"65","author":"RF Molanes","year":"2018","unstructured":"Molanes, R.F., Rodr\u00edguez-Andina, J.J., Fari\u00f1a, J.: Performance characterization and design guidelines for efficient processor-FPGA communication in cyclone V FPSoCs. IEEE Trans. Ind. Electron. 65(5), 4368\u20134377 (2018). https:\/\/doi.org\/10.1109\/TIE.2017.2766581","journal-title":"IEEE Trans. Ind. Electron."},{"key":"7_CR22","doi-asserted-by":"publisher","unstructured":"Molanes, R.F., Salgado, F., Fari\u00f1a, J., Rodr\u00edguez-Andina, J.J.: Characterization of FPGA-master arm communication delays in cyclone V devices. In: IECON 2015\u201341st Annual Conference of the IEEE Industrial Electronics Society (2015). https:\/\/doi.org\/10.1109\/IECON.2015.7392759","DOI":"10.1109\/IECON.2015.7392759"},{"key":"7_CR23","doi-asserted-by":"publisher","unstructured":"Papamarcos, M.S., Patel, J.H.: A low-overhead coherence solution for multiprocessors with private cache memories. In: Proceedings of the 11th Annual International Symposium on Computer Architecture, ISCA 1984, pp. 348\u2013354. Association for Computing Machinery, New York (1984). https:\/\/doi.org\/10.1145\/800015.808204","DOI":"10.1145\/800015.808204"},{"key":"7_CR24","doi-asserted-by":"publisher","unstructured":"Powell, A., Silage, D.: Statistical performance of the ARM cortex A9 accelerator coherency port in the xilinx zynq SoC for real-time applications. In: 2015 International Conference on ReConFigurable Computing and FPGAs (ReConFig), pp. 1\u20136 (2015). https:\/\/doi.org\/10.1109\/ReConFig.2015.7393362","DOI":"10.1109\/ReConFig.2015.7393362"},{"key":"7_CR25","doi-asserted-by":"publisher","unstructured":"Putnam, A., et al.: A reconfigurable fabric for accelerating large-scale datacenter services. In: 2014 ACM\/IEEE 41st International Symposium on Computer Architecture (ISCA) (2014). https:\/\/doi.org\/10.1109\/ISCA.2014.6853195","DOI":"10.1109\/ISCA.2014.6853195"},{"key":"7_CR26","doi-asserted-by":"publisher","unstructured":"Reagen, B., Adolf, R., Shao, Y.S., Wei, G.Y., Brooks, D.: MachSuite: benchmarks for accelerator design and customized architectures. In: 2014 IEEE International Symposium on Workload Characterization (IISWC), pp. 110\u2013119 (2014). https:\/\/doi.org\/10.1109\/IISWC.2014.6983050d","DOI":"10.1109\/IISWC.2014.6983050"},{"key":"7_CR27","doi-asserted-by":"publisher","unstructured":"Sadri, M., Weis, C., Wehn, N., Benini, L.: Energy and performance exploration of accelerator coherency port using Xilinx ZYNQ. In: Proceedings of the 10th FPGAworld Conference, FPGAworld 2013, pp. 1\u20138. Association for Computing Machinery, New York (2013). https:\/\/doi.org\/10.1145\/2513683.2513688","DOI":"10.1145\/2513683.2513688"},{"key":"7_CR28","unstructured":"Shao, Y.S., Xi, S., Srinivasan, V., Wei, G.Y., Brooks, D.: Toward cache-friendly hardware accelerators, p. 6 (2015)"},{"key":"7_CR29","doi-asserted-by":"publisher","unstructured":"Shao, Y.S., Xi, S.L., Srinivasan, V., Wei, G.Y., Brooks, D.: Co-designing accelerators and SoC interfaces using gem5-Aladdin. In: 2016 49th Annual IEEE\/ACM International Symposium on Microarchitecture (MICRO), pp. 1\u201312 (2016). https:\/\/doi.org\/10.1109\/MICRO.2016.7783751","DOI":"10.1109\/MICRO.2016.7783751"},{"key":"7_CR30","doi-asserted-by":"publisher","unstructured":"Sklyarov, V., Skliarova, I., Silva, J., Sudnitson, A.: Analysis and comparison of attainable hardware acceleration in all programmable systems-on-chip. In: 2015 Euromicro Conference on Digital System Design, pp. 345\u2013352 (2015). https:\/\/doi.org\/10.1109\/DSD.2015.45","DOI":"10.1109\/DSD.2015.45"},{"key":"7_CR31","doi-asserted-by":"publisher","unstructured":"Stuecheli, J., Blaner, B., Johns, C.R., Siegel, M.S.: CAPI: a coherent accelerator processor interface. IBM J. Res. Dev. 59(1), 7:1\u20137:7 (2015). https:\/\/doi.org\/10.1147\/JRD.2014.2380198","DOI":"10.1147\/JRD.2014.2380198"},{"key":"7_CR32","doi-asserted-by":"publisher","unstructured":"Tamimi, S., Stock, F., Koch, A., Bernhardt, A., Petrov, I.: An evaluation of using CCIX for cache-coherent host-FPGA interfacing. In: 2022 IEEE 30th Annual International Symposium on Field-Programmable Custom Computing Machines (FCCM), pp. 1\u20139 (2022). https:\/\/doi.org\/10.1109\/FCCM53951.2022.9786103","DOI":"10.1109\/FCCM53951.2022.9786103"},{"key":"7_CR33","doi-asserted-by":"publisher","unstructured":"Zuckerman, J., Giri, D., Kwon, J., Mantovani, P., Carloni, L.P.: Cohmeleon: learning-based orchestration of accelerator coherence in heterogeneous SoCs. In: MICRO-54: 54th Annual IEEE\/ACM International Symposium on Microarchitecture, MICRO 2021, pp. 350\u2013365. Association for Computing Machinery, New York (2021). https:\/\/doi.org\/10.1145\/3466752.3480065","DOI":"10.1145\/3466752.3480065"}],"container-title":["Lecture Notes in Computer Science","Embedded Computer Systems: Architectures, Modeling, and Simulation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-46077-7_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,6]],"date-time":"2023-11-06T11:02:40Z","timestamp":1699268560000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-46077-7_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031460760","9783031460777"],"references-count":33,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-46077-7_7","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":"7 November 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"SAMOS","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Embedded Computer Systems","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Samos","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":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 July 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6 July 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"samos2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/samos-conference.com\/wp\/","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":"Softconf","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"45","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":"11","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":"7","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":"24% - 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":"2","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)"}}]}}