{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,8]],"date-time":"2026-01-08T02:31:20Z","timestamp":1767839480491,"version":"3.49.0"},"publisher-location":"Cham","reference-count":30,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031320408","type":"print"},{"value":"9783031320415","type":"electronic"}],"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\/978-3-031-32041-5_15","type":"book-chapter","created":{"date-parts":[[2023,5,10]],"date-time":"2023-05-10T21:56:29Z","timestamp":1683755789000},"page":"279-296","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["A Study on\u00a0the\u00a0Performance Implications of\u00a0AArch64 Atomics"],"prefix":"10.1007","author":[{"given":"Ricardo","family":"Jesus","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mich\u00e8le","family":"Weiland","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,5,10]]},"reference":[{"key":"15_CR1","doi-asserted-by":"publisher","unstructured":"Alessandrini, V.: Concurrent access to shared data. In: Shared Memory Application Programming, pp. 101\u2013127. Morgan Kaufmann, Boston (2016). https:\/\/doi.org\/10.1016\/B978-0-12-803761-4.00005-8","DOI":"10.1016\/B978-0-12-803761-4.00005-8"},{"key":"15_CR2","unstructured":"Arm Limited: ARMv8-A Memory Systems. Document ID 100941_0100_en (2017)"},{"key":"15_CR3","unstructured":"Arm Limited: Arm Neoverse V1 Core. DDI 101427, 0101-05 (2021)"},{"key":"15_CR4","unstructured":"Arm Limited: Do near or far atomics give the best performance on Neoverse systems? (2021). https:\/\/developer.arm.com\/documentation\/ka004706\/1-0"},{"key":"15_CR5","unstructured":"Arm Limited: Arm Architecture Reference Manual for A-profile architecture. DDI 0487 H.a (2022)"},{"key":"15_CR6","unstructured":"Arm Limited: Arm\u00ae Architecture Reference Manual Supplement Armv9, for Armv9-A architecture profile. DDI 0608 B.a (2022)"},{"key":"15_CR7","unstructured":"Arm Limited: Overview of Arm Transactional Memory Extension. Document ID 102873_0100_en (2022)"},{"key":"15_CR8","unstructured":"Arm Limited: Synchronization Benchmarks (2022). https:\/\/github.com\/ARM-software\/synchronization-benchmarks"},{"key":"15_CR9","doi-asserted-by":"publisher","unstructured":"Chabbi, M., Fagan, M., Mellor-Crummey, J.: High performance locks for multi-level NUMA systems. In: Proceedings of the 20th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming, pp. 215\u2013226. ACM, San Francisco (2015). https:\/\/doi.org\/10.1145\/2688500.2688503","DOI":"10.1145\/2688500.2688503"},{"key":"15_CR10","unstructured":"Cownie, J.: Atomics in AArch64 (2021). https:\/\/cpufun.substack.com\/p\/atomics-in-aarch64"},{"key":"15_CR11","doi-asserted-by":"publisher","unstructured":"David, T., Guerraoui, R., Trigonakis, V.: Everything you always wanted to know about synchronization but were afraid to ask. In: Proceedings of the Twenty-Fourth ACM Symposium on Operating Systems Principles, pp. 33\u201348. ACM, Farminton Pennsylvania (2013). https:\/\/doi.org\/10.1145\/2517349.2522714","DOI":"10.1145\/2517349.2522714"},{"key":"15_CR12","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"595","DOI":"10.1007\/978-3-642-40047-6_60","volume-title":"Euro-Par 2013 Parallel Processing","author":"D Dice","year":"2013","unstructured":"Dice, D., Hendler, D., Mirsky, I.: Lightweight contention management for efficient compare-and-swap operations. In: Wolf, F., Mohr, B., an Mey, D. (eds.) Euro-Par 2013. LNCS, vol. 8097, pp. 595\u2013606. Springer, Heidelberg (2013). https:\/\/doi.org\/10.1007\/978-3-642-40047-6_60"},{"key":"15_CR13","unstructured":"Fujitsu Limited: A64FX Microarchitecture Manual. Revision 1.6 (2021). https:\/\/github.com\/fujitsu\/A64FX"},{"key":"15_CR14","unstructured":"Herlihy, M., Shavit, N., Luchangco, V., Spear, M.: The Art of Multiprocessor Programming. MA, second edn, Morgan Kaufmann, Cambridge (2021)"},{"key":"15_CR15","doi-asserted-by":"publisher","unstructured":"Hornung, R., Hones, H.: RAJA Performance Suite. Lawrence Livermore National Laboratory (LLNL), Livermore, CA (United States) (2017). https:\/\/doi.org\/10.11578\/DC.20201001.36","DOI":"10.11578\/DC.20201001.36"},{"key":"15_CR16","unstructured":"Intel Corporation: Intel\u00ae 64 and IA-32 Architectures Software Developer\u2019s Manual, Volume 3A: System Programming Guide, Part 1. Order Number 253668\u2013077US (2022)"},{"key":"15_CR17","doi-asserted-by":"publisher","unstructured":"Klemm, M., Cownie, J.: 6 mutual exclusion and atomicity. In: High Performance Parallel Runtimes: Design and Implementation, pp. 146\u2013193. De Gruyter Oldenbourg, Berlin(2021). https:\/\/doi.org\/10.1515\/9783110632729-006","DOI":"10.1515\/9783110632729-006"},{"key":"15_CR18","doi-asserted-by":"crossref","unstructured":"Klemm, M., Cownie, J.: High Performance Parallel Runtimes: Design and Implementation. De Gruyter Textbook, De Gruyter Oldenbourg, Berlin (2021)","DOI":"10.1515\/9783110632729"},{"key":"15_CR19","doi-asserted-by":"crossref","unstructured":"Makreshanski, D., Levandoski, J., Stutsman, R.: To lock, swap, or elide: on the interplay of hardware transactional memory and lock-free indexing. Proc. VLDB Endowment 8(11), 1298\u20131309 (2015).https:\/\/doi.org\/10.14778\/2809974.2809990","DOI":"10.14778\/2809974.2809990"},{"issue":"1","key":"15_CR20","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1145\/103727.103729","volume":"9","author":"JM Mellor-Crummey","year":"1991","unstructured":"Mellor-Crummey, J.M., Scott, M.L.: Algorithms for scalable synchronization on shared-memory multiprocessors. ACM Trans. Comput. Syst. 9(1), 21\u201365 (1991). https:\/\/doi.org\/10.1145\/103727.103729","journal-title":"ACM Trans. Comput. Syst."},{"key":"15_CR21","doi-asserted-by":"publisher","unstructured":"Michael, M.M., Scott, M.L.: Simple, fast, and practical non-blocking and blocking concurrent queue algorithms. In: Proceedings of the Fifteenth Annual ACM Symposium on Principles of Distributed Computing - PODC 1996, pp. 267\u2013275. ACM Press, Philadelphia, Pennsylvania (1996). https:\/\/doi.org\/10.1145\/248052.248106","DOI":"10.1145\/248052.248106"},{"issue":"3","key":"15_CR22","doi-asserted-by":"publisher","first-page":"48","DOI":"10.1109\/MCG.2016.48","volume":"36","author":"K Moreland","year":"2016","unstructured":"Moreland, K., et al.: VTK-m: accelerating the visualization toolkit for massively threaded architectures. IEEE Comput. Graph. Appl. 36(3), 48\u201358 (2016). https:\/\/doi.org\/10.1109\/MCG.2016.48","journal-title":"IEEE Comput. Graph. Appl."},{"key":"15_CR23","doi-asserted-by":"publisher","unstructured":"Morrison, A., Afek, Y.: Fast concurrent queues for x86 processors. In: Proceedings of the 18th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming - PPoPP 2013, p. 103. ACM Press, Shenzhen (2013). https:\/\/doi.org\/10.1145\/2442516.2442527","DOI":"10.1145\/2442516.2442527"},{"key":"15_CR24","doi-asserted-by":"publisher","unstructured":"Oberhauser, J., et al.: VSync: push-button verification and optimization for synchronization primitives on weak memory models. In: Proceedings of the 26th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, pp. 530\u2013545. ACM, Virtual USA (2021). https:\/\/doi.org\/10.1145\/3445814.3446748","DOI":"10.1145\/3445814.3446748"},{"key":"15_CR25","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"240","DOI":"10.1007\/978-3-030-91014-3_17","volume-title":"Networked Systems","author":"J Oberhauser","year":"2021","unstructured":"Oberhauser, J., Oberhauser, L., Paolillo, A., Behrens, D., Fu, M., Vafeiadis, V.: Verifying and optimizing the HMCS lock for Arm servers. In: Echihabi, K., Meyer, R. (eds.) NETYS 2021. LNCS, vol. 12754, pp. 240\u2013260. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-91014-3_17"},{"key":"15_CR26","unstructured":"Pardos, V.S.: Characterization and Modeling of Atomic Memory Operations in Arm Based Architectures. Master\u2019s thesis, Universitat Polit\u00e8cnica de Catalunya, BarcelonaTech (2022). https:\/\/upcommons.upc.edu\/handle\/2117\/363728"},{"key":"15_CR27","doi-asserted-by":"publisher","unstructured":"Sakalis, C., Leonardsson, C., Kaxiras, S., Ros, A.: Splash-3: a properly synchronized benchmark suite for contemporary research. In: 2016 IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS), pp. 101\u2013111. IEEE, Uppsala (2016). https:\/\/doi.org\/10.1109\/ISPASS.2016.7482078","DOI":"10.1109\/ISPASS.2016.7482078"},{"key":"15_CR28","doi-asserted-by":"publisher","unstructured":"Schweizer, H., Besta, M., Hoefler, T.: Evaluating the cost of atomic operations on modern architectures. In: 2015 International Conference on Parallel Architecture and Compilation (PACT), pp. 445\u2013456. IEEE, San Francisco (2015). https:\/\/doi.org\/10.1109\/PACT.2015.24","DOI":"10.1109\/PACT.2015.24"},{"key":"15_CR29","doi-asserted-by":"publisher","unstructured":"Williams, B., Leidel, J., Wang, X., Donofrio, D., Chen, Y.: CircusTent: a benchmark suite for atomic memory operations. In: The International Symposium on Memory Systems, pp. 144\u2013157. ACM, Washington (2020). https:\/\/doi.org\/10.1145\/3422575.3422789","DOI":"10.1145\/3422575.3422789"},{"key":"15_CR30","doi-asserted-by":"publisher","unstructured":"Wu, H., Becchi, M.: Evaluating thread coarsening and low-cost synchronization on intel xeon phi. In: 2020 IEEE International Parallel and Distributed Processing Symposium (IPDPS), pp. 1018\u20131029. IEEE, New Orleans (2020). https:\/\/doi.org\/10.1109\/IPDPS47924.2020.00108","DOI":"10.1109\/IPDPS47924.2020.00108"}],"container-title":["Lecture Notes in Computer Science","High Performance Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-32041-5_15","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,10]],"date-time":"2023-05-10T22:02:17Z","timestamp":1683756137000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-32041-5_15"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031320408","9783031320415"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-32041-5_15","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"10 May 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ISC High Performance","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on High Performance Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hamburg","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":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21 May 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25 May 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"38","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"supercomputing2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.isc-hpc.com\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Linklings","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"78","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":"21","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":"27% - 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":"3.74","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":"4.49","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":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}