{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,26]],"date-time":"2025-09-26T13:16:28Z","timestamp":1758892588146,"version":"3.37.3"},"reference-count":25,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2021,1,3]],"date-time":"2021-01-03T00:00:00Z","timestamp":1609632000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,3]],"date-time":"2021-01-03T00:00:00Z","timestamp":1609632000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100001659","name":"Deutsche Forschungsgemeinschaft","doi-asserted-by":"publisher","award":["146371743"],"award-info":[{"award-number":["146371743"]}],"id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Parallel Prog"],"published-print":{"date-parts":[[2021,8]]},"DOI":"10.1007\/s10766-020-00688-6","type":"journal-article","created":{"date-parts":[[2021,1,3]],"date-time":"2021-01-03T18:02:30Z","timestamp":1609696950000},"page":"570-599","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["DynaCo: Dynamic Coherence Management for Tiled Manycore Architectures"],"prefix":"10.1007","volume":"49","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1427-9511","authenticated-orcid":false,"given":"Akshay","family":"Srivatsa","sequence":"first","affiliation":[]},{"given":"Mostafa","family":"Mansour","sequence":"additional","affiliation":[]},{"given":"Sven","family":"Rheindt","sequence":"additional","affiliation":[]},{"given":"Dirk","family":"Gabriel","sequence":"additional","affiliation":[]},{"given":"Thomas","family":"Wild","sequence":"additional","affiliation":[]},{"given":"Andreas","family":"Herkersdorf","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,1,3]]},"reference":[{"key":"688_CR1","doi-asserted-by":"publisher","unstructured":"Fleisch, B., Popek, G.: Mirage: a coherent distributed shared memory design. In: Proceedings of the Twelfth ACM Symposium on Operating Systems Principles, pp. 211\u2013223. SOSP \u201989, Association for Computing Machinery, New York (1989). https:\/\/doi.org\/10.1145\/74850.74871","DOI":"10.1145\/74850.74871"},{"key":"688_CR2","doi-asserted-by":"publisher","unstructured":"Bennett, J.K., Carter, J.B., Zwaenepoel, W.: Munin: distributed shared memory based on type-specific memory coherence. In: Proceedings of the Second ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming, pp. 168\u2013176. PPOPP \u201990, Association for Computing Machinery, New York (1990). https:\/\/doi.org\/10.1145\/99163.99182","DOI":"10.1145\/99163.99182"},{"key":"688_CR3","doi-asserted-by":"publisher","unstructured":"de Dinechin, B.D.: Kalray mppa$$\\textregistered$$: massively parallel processor array: revisiting dsp acceleration with the kalray mppa manycore processor. In: 2015 IEEE Hot Chips 27 Symposium, pp. 1\u201327 (2015). https:\/\/doi.org\/10.1109\/HOTCHIPS.2015.7477332","DOI":"10.1109\/HOTCHIPS.2015.7477332"},{"issue":"3","key":"688_CR4","doi-asserted-by":"publisher","first-page":"63","DOI":"10.1109\/2.121510","volume":"25","author":"D Lenoski","year":"1992","unstructured":"Lenoski, D., Laudon, J., Gharachorloo, K., Weber, W., Gupta, A., Hennessy, J., Horowitz, M., Lam, M.S.: The stanford dash multiprocessor. Computer 25(3), 63\u201379 (1992)","journal-title":"Computer"},{"issue":"5","key":"688_CR5","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1109\/MM.2007.4378780","volume":"27","author":"D Wentzlaff","year":"2007","unstructured":"Wentzlaff, D., Griffin, P., Hoffmann, H., Bao, L., Edwards, B., Ramey, C., Mattina, M., Miao, C.C., Brown III, J.F., Agarwal, A.: On-chip interconnection architecture of the tile processor. IEEE Micro. 27(5), 15\u201331 (2007)","journal-title":"IEEE Micro."},{"key":"688_CR6","doi-asserted-by":"publisher","unstructured":"Kessler, R.E.: The cavium 32 core octeon ii 68xx. In: 2011 IEEE Hot Chips 23 Symposium (HCS), pp. 1\u201333 (2011). https:\/\/doi.org\/10.1109\/HOTCHIPS.2011.7477487","DOI":"10.1109\/HOTCHIPS.2011.7477487"},{"key":"688_CR7","doi-asserted-by":"crossref","unstructured":"Srivatsa, A., Rheindt, S., Wild, T., Herkersdorf, A.: Region based cache coherence for tiled mpsocs. In: 2017 30th IEEE International System-on-Chip Conference (SOCC), pp. 286\u2013291 (2017)","DOI":"10.1109\/SOCC.2017.8226059"},{"key":"688_CR8","doi-asserted-by":"publisher","unstructured":"Southern, G., Renau, J.: Analysis of parsec workload scalability. In: IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS), pp. 133\u2013142 (2016). https:\/\/doi.org\/10.1109\/ISPASS.2016.7482081","DOI":"10.1109\/ISPASS.2016.7482081"},{"key":"688_CR9","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1007\/978-3-030-27562-4_2","volume-title":"Embedded Computer Systems: Architectures, Modeling, and Simulation","author":"A Srivatsa","year":"2019","unstructured":"Srivatsa, A., Rheindt, S., Gabriel, D., Wild, T., Herkersdorf, A.: Cod: coherence-on-demand-runtime adaptable working set coherence for dsm-based manycore architectures. In: Pnevmatikatos, D.N., Pelcat, M., Jung, M. (eds.) Embedded Computer Systems: Architectures, Modeling, and Simulation, pp. 18\u201333. Springer, Cham (2019)"},{"key":"688_CR10","doi-asserted-by":"publisher","unstructured":"Eggers, S.J., Katz, R.H.: Evaluating the performance of four snooping cache coherency protocols. In: Proceedings of the 16th Annual International Symposium on Computer Architecture, pp. 2\u201315. ISCA \u201989, Association for Computing Machinery, New York (1989). https:\/\/doi.org\/10.1145\/74925.74927","DOI":"10.1145\/74925.74927"},{"issue":"3","key":"688_CR11","doi-asserted-by":"publisher","first-page":"418","DOI":"10.1109\/5.747863","volume":"87","author":"J Hennessy","year":"1999","unstructured":"Hennessy, J., Heinrich, M., Gupta, A.: Cache-coherent distributed shared memory: perspectives on its development and future challenges. Proc. IEEE 87(3), 418\u2013429 (1999). https:\/\/doi.org\/10.1109\/5.747863","journal-title":"Proc. IEEE"},{"key":"688_CR12","unstructured":"Gupta, A., dietrich Weber, W., Mowry, T.: Reducing memory and traffic requirements for scalable directory-based cache coherence schemes. In: International Conference on Parallel Processing, pp. 312\u2013321 (1990)"},{"key":"688_CR13","doi-asserted-by":"crossref","unstructured":"Yao, Y., Wang, G., Ge, Z., Mitra, T., Chen, W., Zhang, N.: Selectdirectory: a selective directory for cache coherence in many-core architectures. In: 2015 Design, Automation Test in Europe Conference Exhibition (DATE), pp. 175\u2013180 (2015)","DOI":"10.7873\/DATE.2015.0438"},{"key":"688_CR14","doi-asserted-by":"crossref","unstructured":"Ferdman, M., Lotfi-Kamran, P., Balet, K., Falsafi, B.: Cuckoo directory: a scalable directory for many-core systems. In: 2011 IEEE 17th International Symposium on High Performance Computer Architecture, pp. 169\u2013180 (2011)","DOI":"10.1109\/HPCA.2011.5749726"},{"key":"688_CR15","doi-asserted-by":"publisher","unstructured":"Chaiken, D., Kubiatowicz, J., Agarwal, A.: Limitless Directories: A Scalable Cache Coherence Scheme, pp. 224\u2013234. ASPLOS IV, ACM, New York (1991). https:\/\/doi.org\/10.1145\/106972.106995","DOI":"10.1145\/106972.106995"},{"issue":"2","key":"688_CR16","doi-asserted-by":"publisher","first-page":"34","DOI":"10.1109\/MM.2016.25","volume":"36","author":"A Sodani","year":"2016","unstructured":"Sodani, A., Gramunt, R., Corbal, J., Kim, H., Vinod, K., Chinthamani, S., Hutsell, S., Agarwal, R., Liu, Y.: Knights landing: Second-generation intel xeon phi product. IEEE Micro 36(2), 34\u201346 (2016)","journal-title":"IEEE Micro"},{"key":"688_CR17","doi-asserted-by":"publisher","unstructured":"Fu, Y., Nguyen, T.M., Wentzlaff, D.: Coherence domain restriction on large scale systems. In: 48th International Symposium on Microarchitecture, pp. 686\u2013698. MICRO-48, ACM, New York (2015). https:\/\/doi.org\/10.1145\/2830772.2830832","DOI":"10.1145\/2830772.2830832"},{"key":"688_CR18","doi-asserted-by":"publisher","unstructured":"Teich, J., Henkel, J., Herkersdorf, A., Schmitt-Landsiedel, D., Schr\u00f6der-Preikschat, W., Snelting, G.: Invasive computing: an overview. In: Multiprocessor System-on-Chip: Hardware Design and Tool Integration. https:\/\/doi.org\/10.1007\/978-1-4419-6460-1_11","DOI":"10.1007\/978-1-4419-6460-1_11"},{"issue":"6","key":"688_CR19","doi-asserted-by":"publisher","first-page":"651","DOI":"10.1109\/12.286299","volume":"43","author":"J Torrellas","year":"1994","unstructured":"Torrellas, J., Lam, H.S., Hennessy, J.L.: False sharing and spatial locality in multiprocessor caches. IEEE Trans. Comput. 43(6), 651\u2013663 (1994). https:\/\/doi.org\/10.1109\/12.286299","journal-title":"IEEE Trans. Comput."},{"key":"688_CR20","doi-asserted-by":"publisher","unstructured":"Jeremiassen, T.E., Eggers, S.J.: Reducing false sharing on shared memory multiprocessors through compile time data transformations. In: Proceedings of the Fifth ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming, pp. 179\u2013188. PPOPP \u201995, Association for Computing Machinery, New York (1995). https:\/\/doi.org\/10.1145\/209936.209955","DOI":"10.1145\/209936.209955"},{"key":"688_CR21","doi-asserted-by":"publisher","unstructured":"Liu, T., Tian, C., Hu, Z., Berger, E.D.: Predator: predictive false sharing detection. In: Proceedings of the 19th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming, pp. 3\u201314. PPoPP \u201914, Association for Computing Machinery, New York (2014). https:\/\/doi.org\/10.1145\/2555243.2555244","DOI":"10.1145\/2555243.2555244"},{"key":"688_CR22","doi-asserted-by":"publisher","unstructured":"Liu, T., Liu, X.: Cheetah: detecting false sharing efficiently and effectively. In: Proceedings of the 2016 International Symposium on Code Generation and Optimization, pp. 1\u201311. CGO \u201916, Association for Computing Machinery, New York (2016). https:\/\/doi.org\/10.1145\/2854038.2854039","DOI":"10.1145\/2854038.2854039"},{"issue":"10","key":"688_CR23","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1145\/2076021.2048070","volume":"46","author":"T Liu","year":"2011","unstructured":"Liu, T., Berger, E.D.: Sheriff: precise detection and automatic mitigation of false sharing. SIGPLAN Not. 46(10), 3\u201318 (2011). https:\/\/doi.org\/10.1145\/2076021.2048070","journal-title":"SIGPLAN Not."},{"key":"688_CR24","doi-asserted-by":"publisher","unstructured":"Freeh, V.W., Andrews, G.R.: Dynamically controlling false sharing in distributed shared memory. In: Proceedings of 5th IEEE International Symposium on High Performance Distributed Computing, pp. 403\u2013411 (1996). https:\/\/doi.org\/10.1109\/HPDC.1996.546211","DOI":"10.1109\/HPDC.1996.546211"},{"key":"688_CR25","doi-asserted-by":"publisher","unstructured":"Waliullah, M., Stenstrom, P.: Classification and elimination of conflicts in hardware transactional memory systems. In: 2011 23rd International Symposium on Computer Architecture and High Performance Computing, pp. 96\u2013103 (2011). https:\/\/doi.org\/10.1109\/SBAC-PAD.2011.18","DOI":"10.1109\/SBAC-PAD.2011.18"}],"container-title":["International Journal of Parallel Programming"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10766-020-00688-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10766-020-00688-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10766-020-00688-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,6,29]],"date-time":"2021-06-29T22:03:18Z","timestamp":1625004198000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10766-020-00688-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,1,3]]},"references-count":25,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2021,8]]}},"alternative-id":["688"],"URL":"https:\/\/doi.org\/10.1007\/s10766-020-00688-6","relation":{},"ISSN":["0885-7458","1573-7640"],"issn-type":[{"type":"print","value":"0885-7458"},{"type":"electronic","value":"1573-7640"}],"subject":[],"published":{"date-parts":[[2021,1,3]]},"assertion":[{"value":"1 April 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 November 2020","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 January 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Compliance with Ethical Standards"}},{"value":"The authors would like to thank Sai Varun Brahmadevara, Li-Yu Peng and Miguel Montoya Rendon for their contributions as master and internship students at the Chair of Integrated Systems, TUM. We would also like to thank Sebastian Maier at the Computer Science 4 department, FAU, Erlangen-Nuremberg for his OS support.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}