{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:09:18Z","timestamp":1750219758862,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":39,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,4,27]],"date-time":"2024-04-27T00:00:00Z","timestamp":1714176000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100000781","name":"European Research Council","doi-asserted-by":"publisher","award":["819134"],"award-info":[{"award-number":["819134"]}],"id":[{"id":"10.13039\/501100000781","id-type":"DOI","asserted-by":"publisher"}]},{"name":"European Union NextGenerationEU\/PRTR","award":["TED2021-130233B-C33"],"award-info":[{"award-number":["TED2021-130233B-C33"]}]},{"name":"RDF A way of making Europe","award":["PID2022-136315OB-I00"],"award-info":[{"award-number":["PID2022-136315OB-I00"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,4,27]]},"DOI":"10.1145\/3622781.3674176","type":"proceedings-article","created":{"date-parts":[[2025,4,10]],"date-time":"2025-04-10T15:31:01Z","timestamp":1744299061000},"page":"17-30","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Bounding Speculative Execution of Atomic Regions to a Single Retry"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8445-615X","authenticated-orcid":false,"given":"Eduardo Jos\u00e9","family":"G\u00f3mez-Hern\u00e1ndez","sequence":"first","affiliation":[{"name":"Computer Engineering Department, University of Murcia, Murcia, Spain"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3731-9301","authenticated-orcid":false,"given":"Juan M.","family":"Cebrian","sequence":"additional","affiliation":[{"name":"Computer Engineering Department, University of Murcia, Murcia, Spain"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8267-0232","authenticated-orcid":false,"given":"Stefanos","family":"Kaxiras","sequence":"additional","affiliation":[{"name":"Department of Information Technology, Uppsala University, Uppsala, Sweden"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5757-1064","authenticated-orcid":false,"given":"Alberto","family":"Ros","sequence":"additional","affiliation":[{"name":"Computer Engineering Department, University of Murcia, Murcia, Spain"}]}],"member":"320","published-online":{"date-parts":[[2025,4,10]]},"reference":[{"key":"e_1_3_2_1_1_1","first-page":"33","volume-title":"Int'l Symp. on Performance Analysis of Systems and Software (ISPASS)","author":"Agarwal Niket","year":"2009","unstructured":"Niket Agarwal, Tushar Krishna, Li-Shiuan Peh, and Niraj K. Jha. GARNET: A detailed on-chip network model inside a full-system simulator. In Int'l Symp. on Performance Analysis of Systems and Software (ISPASS), pages 33--42, April 2009."},{"key":"e_1_3_2_1_2_1","first-page":"14","volume-title":"49th Int'l Symp. on Computer Architecture (ISCA)","author":"Asgharzadeh Ashkan","year":"2022","unstructured":"Ashkan Asgharzadeh, Juan M. Cebrian, Arthur Perais, Stefanos Kaxiras, and Alberto Ros. Free atomics: hardware atomic operations without fences. In 49th Int'l Symp. on Computer Architecture (ISCA), pages 14--26, 2022."},{"issue":"3","key":"e_1_3_2_1_3_1","doi-asserted-by":"crossref","first-page":"404","DOI":"10.1109\/TPDS.2008.105","article-title":"The design of openmp tasks","volume":"20","author":"Ayguad\u00e9 Eduard","year":"2008","unstructured":"Eduard Ayguad\u00e9, Nawal Copty, Alejandro Duran, Jay Hoeflinger, Yuan Lin, Federico Massaioli, Xavier Teruel, Priya Unnikrishnan, and Guansong Zhang. The design of openmp tasks. IEEE Transactions on Parallel and Distributed systems, 20(3):404--418, 2008.","journal-title":"IEEE Transactions on Parallel and Distributed systems"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"crossref","first-page":"278","DOI":"10.1145\/3503221.3508433","volume-title":"Proceedings of the 27th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming","author":"Ben-David Naama","year":"2022","unstructured":"Naama Ben-David, Guy E Blelloch, and Yuanhao Wei. Lock-free locks revisited. In Proceedings of the 27th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming, pages 278--293, 2022."},{"issue":"2","key":"e_1_3_2_1_5_1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/2024716.2024718","article-title":"The gem5 simulator","volume":"39","author":"Binkert Nathan","year":"2011","unstructured":"Nathan Binkert, Bradford Beckmann, Gabriel Black, Steven K. Reinhardt, Ali Saidi, Arkaprava Basu, Joel Hestness, Derek R. Hower, Tushar Krishna, Somayeh Sardashti, Rathijit Sen, Korey Sewell, Muhammad Shoaib, Nilay Vaish, Mark D. Hill, and David A. Wood. The gem5 simulator. ACM SIGARCH Computer Architecture News, 39(2):1--7, May 2011.","journal-title":"ACM SIGARCH Computer Architecture News"},{"key":"e_1_3_2_1_6_1","first-page":"54","volume-title":"Transact 2014 Workshop. ACM","author":"Calciu Irina","year":"2014","unstructured":"Irina Calciu, Tatiana Shpeisman, Gilles Pokam, and Maurice Herlihy. Improved single global lock fallback for best-effort hardware transactional memory. In Transact 2014 Workshop. ACM, page 54, 2014."},{"key":"e_1_3_2_1_7_1","first-page":"21","volume-title":"Proceedings of the Seventeenth Annual ACM Symposium on Parallelism in Algorithms and Architectures, SPAA '05","author":"Chase David","year":"2005","unstructured":"David Chase and Yossi Lev. Dynamic circular work-stealing deque. In Proceedings of the Seventeenth Annual ACM Symposium on Parallelism in Algorithms and Architectures, SPAA '05, page 21--28, New York, USA, 2005. Association for Computing Machinery."},{"key":"e_1_3_2_1_8_1","volume-title":"Introduction to Algorithms","author":"Cormen Thomas H.","year":"2009","unstructured":"Thomas H. Cormen, Charles E. Leiserson, Ronald L. Rivest, and Clifford Stein. Introduction to Algorithms, Third Edition. The MIT Press, 3rd edition, 2009."},{"key":"e_1_3_2_1_9_1","volume-title":"Improving parallelism in hardware transactional memory. ACM Trans. Archit. Code Optim., 15(1), mar","author":"Dice Dave","year":"2018","unstructured":"Dave Dice, Maurice Herlihy, and Alex Kogan. Improving parallelism in hardware transactional memory. ACM Trans. Archit. Code Optim., 15(1), mar 2018."},{"key":"e_1_3_2_1_10_1","volume-title":"Seer: Probabilistic scheduling for hardware transactional memory. ACM Trans. Comput. Syst., 35(3), nov","author":"Diegues Nuno","year":"2017","unstructured":"Nuno Diegues, Paolo Romano, and Stoyan Garbatov. Seer: Probabilistic scheduling for hardware transactional memory. ACM Trans. Comput. Syst., 35(3), nov 2017."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"crossref","first-page":"216","DOI":"10.1145\/1007912.1007945","volume-title":"Proceedings of the Sixteenth Annual ACM Symposium on Parallelism in Algorithms and Architectures","author":"Doherty Simon","year":"2004","unstructured":"Simon Doherty, David L. Detlefs, Lindsay Groves, Christine H. Flood, Victor Luchangco, Paul A. Martin, Mark Moir, Nir Shavit, and Guy L. Steele. Dcas is not a silver bullet for nonblocking algorithm design. In Proceedings of the Sixteenth Annual ACM Symposium on Parallelism in Algorithms and Architectures, page 216--224, 2004."},{"key":"e_1_3_2_1_12_1","volume-title":"A practical wait-free multi-word compare-and-swap operation","author":"Feldman Steven","year":"2013","unstructured":"Steven Feldman, Pierre Laborde, and Damian Dechev. A practical wait-free multi-word compare-and-swap operation. 2013."},{"key":"e_1_3_2_1_13_1","article-title":"A wait-free multi-word compare-and-swap operation","author":"Feldman Steven","year":"2014","unstructured":"Steven Feldman, Pierre Laborde, and Damian Dechev. A wait-free multi-word compare-and-swap operation. International Journal of Parallel Programming, August 2014.","journal-title":"International Journal of Parallel Programming"},{"key":"e_1_3_2_1_14_1","volume-title":"Instruction latencies, throughputs and micro-operation breakdowns.","author":"Fog Agner","year":"2023","unstructured":"Agner Fog. Instruction Tables. Instruction latencies, throughputs and micro-operation breakdowns. Available at http:\/\/www.agner.org\/optimize\/instruction_tables.pdf (accessed on 30 Nov. 2023)."},{"key":"e_1_3_2_1_15_1","first-page":"46","volume-title":"45th Int'l Symp. on Computer Architecture (ISCA)","author":"Gogte Vaibhav","year":"2018","unstructured":"Vaibhav Gogte, Stephan Diestelhorst, William Wang, Satish Narayanasamy, Peter M. Chen, and Thomas F. Wenisch. Persistency for synchronization-free regions. In 45th Int'l Symp. on Computer Architecture (ISCA), pages 46--61, June 2018."},{"key":"e_1_3_2_1_16_1","first-page":"337","volume-title":"Stefanos Kaxiras, and Alberto Ros. Efficient, distributed, and non-speculative multi-address atomic operations. In 54th IEEE\/ACM Int'l Symp. on Microarchitecture (MICRO)","author":"G\u00f3mez-Hern\u00e1ndez Eduardo Jos\u00e9","year":"2021","unstructured":"Eduardo Jos\u00e9 G\u00f3mez-Hern\u00e1ndez, Juan M. Cebrian, J. Rub\u00e9n Titos Gil, Stefanos Kaxiras, and Alberto Ros. Efficient, distributed, and non-speculative multi-address atomic operations. In 54th IEEE\/ACM Int'l Symp. on Microarchitecture (MICRO), pages 337--349, October 2021."},{"key":"e_1_3_2_1_17_1","first-page":"1","volume-title":"11th Int'l Conf. on Architectural Support for Programming Language and Operating Systems (ASPLOS)","author":"Hammond Lance","year":"2004","unstructured":"Lance Hammond, Brian D. Carlstrom, Vicky Wong, Ben Hertzberg, Mike Chen, Christos Kozyrakis, and Kunle Olukotun. Programming with transactional coherence and consistency (TCC). In 11th Int'l Conf. on Architectural Support for Programming Language and Operating Systems (ASPLOS), pages 1--13, October 2004."},{"key":"e_1_3_2_1_18_1","first-page":"300","volume-title":"Proceedings of the 15th International Conference on Distributed Computing, DISC '01","author":"Harris Timothy L.","year":"2001","unstructured":"Timothy L. Harris. A pragmatic implementation of non-blocking linked-lists. In Proceedings of the 15th International Conference on Distributed Computing, DISC '01, pages 300--314, Berlin, Heidelberg, 2001. Springer-Verlag."},{"key":"e_1_3_2_1_19_1","first-page":"289","volume-title":"20st Int'l Symp. on Computer Architecture (ISCA)","author":"Herlihy Maurice","year":"1993","unstructured":"Maurice Herlihy and J. Eliot B. Moss. Transactional memory: Architectural support for lock-free data structures. In 20st Int'l Symp. on Computer Architecture (ISCA), pages 289--300, May 1993."},{"key":"e_1_3_2_1_20_1","volume-title":"The Art of Multiprocessor Programming","author":"Herlihy Maurice","year":"2008","unstructured":"Maurice Herlihy and Nir Shavit. The Art of Multiprocessor Programming. Morgan Kaufmann Publishers Inc., San Francisco, USA, 2008."},{"key":"e_1_3_2_1_21_1","volume-title":"Intel\u00ae 64 and IA-32 Architectures Software Developer's Manual. Number 325462-081US","author":"Intel Corporation","year":"2023","unstructured":"Intel Corporation. Intel\u00ae 64 and IA-32 Architectures Software Developer's Manual. Number 325462-081US. September 2023."},{"key":"e_1_3_2_1_23_1","volume-title":"Bitcoin network dataset. Available (archived) at: https:\/\/web.archive.org\/web\/20200502094144\/https:\/\/senseable2015-6.mit.edu\/bitcoin\/ (accessed on","author":"Kondor Daniel","year":"2023","unstructured":"Daniel Kondor. Bitcoin network dataset. Available (archived) at: https:\/\/web.archive.org\/web\/20200502094144\/https:\/\/senseable2015-6.mit.edu\/bitcoin\/ (accessed on 30 Nov. 2023)."},{"key":"e_1_3_2_1_24_1","unstructured":"Shubham Lagwankar. A lock-free work-stealing deque. https:\/\/github.com\/ssbl\/concurrent-deque."},{"issue":"8","key":"e_1_3_2_1_25_1","doi-asserted-by":"crossref","first-page":"69","DOI":"10.1145\/2517327.2442524","article-title":"Correct and efficient work-stealing for weak memory models","volume":"48","author":"L\u00ea Nhat Minh","year":"2013","unstructured":"Nhat Minh L\u00ea, Antoniu Pop, Albert Cohen, and Francesco Zappa Nardelli. Correct and efficient work-stealing for weak memory models. ACM SIGPLAN Notices, 48(8):69--80, 2013.","journal-title":"ACM SIGPLAN Notices"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"crossref","unstructured":"Sheng Li Jung Ho Ahn Richard D. Strong Jay B. Brockman Dean M. Tullsen and Norman P. Jouppi. Mcpat: An integrated power area and timing modeling framework for multicore and manycore architectures. In 42nd IEEE\/ACM Int'l Symp. on Microarchitecture (MICRO) pages 469--480 December 2009.","DOI":"10.1145\/1669112.1669172"},{"key":"e_1_3_2_1_27_1","first-page":"383","volume-title":"Proceedings of the 19th International Conference on Architectural Support for Programming Languages and Operating Systems, ASPLOS '14","author":"Litz Heiner","year":"2014","unstructured":"Heiner Litz, David Cheriton, Amin Firoozshahian, Omid Azizi, and John P. Stevenson. Si-tm: reducing transactional memory abort rates through snapshot isolation. In Proceedings of the 19th International Conference on Architectural Support for Programming Languages and Operating Systems, ASPLOS '14, page 383--398, New York, NY, USA, 2014. Association for Computing Machinery."},{"key":"e_1_3_2_1_28_1","volume-title":"Efficient correction of anomalies in snapshot isolation transactions. ACM Trans. Archit. Code Optim., 11(4), jan","author":"Litz Heiner","year":"2015","unstructured":"Heiner Litz, Ricardo J. Dias, and David R. Cheriton. Efficient correction of anomalies in snapshot isolation transactions. ACM Trans. Archit. Code Optim., 11(4), jan 2015."},{"key":"e_1_3_2_1_29_1","first-page":"814","volume-title":"2017 IEEE International Symposium on Parallel and Distributed Processing with Applications and 2017 IEEE International Conference on Ubiquitous Computing and Communications (ISPA\/IUCC)","author":"Lu Kun","year":"2017","unstructured":"Kun Lu, Changhao Yan, Hai Zhou, Dian Zhou, and Xuan Zeng. A novel n-retry transactional memory model for multi-thread programming. In 2017 IEEE International Symposium on Parallel and Distributed Processing with Applications and 2017 IEEE International Conference on Ubiquitous Computing and Communications (ISPA\/IUCC), pages 814--821. IEEE, 2017."},{"key":"e_1_3_2_1_30_1","first-page":"35","volume-title":"Int'l Symp. on Workload Characterization (IISWC)","author":"Minh Chi Cao","year":"2008","unstructured":"Chi Cao Minh, JaeWoong Chung, Christos Kozyrakis, and Kunle Olukotun. STAMP: Stanford transactional applications for multi-processing. In Int'l Symp. on Workload Characterization (IISWC), pages 35--46, September 2008."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"crossref","first-page":"469","DOI":"10.1109\/RTSS52674.2021.00049","volume-title":"2021 IEEE Real-Time Systems Symposium (RTSS)","author":"Nord Claire","year":"2021","unstructured":"Claire Nord, Shai Caspin, Catherine E Nemitz, Howard Shrobe, Hamed Okhravi, James H Anderson, Nathan Burow, and Bryan C Ward. Tortis: Retry-free software transactional memory for real-time systems. In 2021 IEEE Real-Time Systems Symposium (RTSS), pages 469--481. IEEE, 2021."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"crossref","first-page":"192","DOI":"10.1109\/PACT.2019.00023","volume-title":"2019 28th International Conference on Parallel Architectures and Compilation Techniques (PACT)","author":"Park Sunjae","year":"2019","unstructured":"Sunjae Park, Christopher J. Hughes, and Milos Prvulovic. Forgive-tm: Supporting lazy conflict detection in eager hardware transactional memory. In 2019 28th International Conference on Parallel Architectures and Compilation Techniques (PACT), pages 192--204, 2019."},{"key":"e_1_3_2_1_33_1","first-page":"918","volume-title":"Proceedings of the Conference on Design, Automation & Test in Europe (DATE)","author":"Patel Srishty","year":"2017","unstructured":"Srishty Patel, Rajshekar Kalayappan, Ishani Mahajan, and Smruti R. Sarangi. A hardware implementation of the mcas synchronization primitive. In Proceedings of the Conference on Design, Automation & Test in Europe (DATE), pages 918--921, 2017."},{"key":"e_1_3_2_1_34_1","first-page":"97","volume-title":"Proceedings 33","author":"Piatka Christian","year":"2020","unstructured":"Christian Piatka, Rico Amslinger, Florian Haas, Sebastian Weis, Sebastian Altmeyer, and Theo Ungerer. Investigating transactional memory for high performance embedded systems. In Architecture of Computing Systems-ARCS 2020: 33rd International Conference, Aachen, Germany, May 25--28, 2020, Proceedings 33, pages 97--108. Springer, 2020."},{"key":"e_1_3_2_1_35_1","first-page":"294","volume-title":"34th IEEE\/ACM Int'l Symp. on Microarchitecture (MICRO)","author":"Rajwar Ravi","year":"2001","unstructured":"Ravi Rajwar and James R. Goodman. Speculative lock elision: Enabling highly concurrent multithreaded execution. In 34th IEEE\/ACM Int'l Symp. on Microarchitecture (MICRO), pages 294--305, December 2001."},{"key":"e_1_3_2_1_36_1","volume-title":"Transactional lock-free execution of lock-based programs. 37(10):5--17, oct","author":"Rajwar Ravi","year":"2002","unstructured":"Ravi Rajwar and James R. Goodman. Transactional lock-free execution of lock-based programs. 37(10):5--17, oct 2002."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"crossref","first-page":"246","DOI":"10.1109\/MICRO.2008.4771795","volume-title":"2008 41st IEEE\/ACM International Symposium on Microarchitecture","author":"Ramadan Hany E.","year":"2008","unstructured":"Hany E. Ramadan, Christopher J. Rossbach, and Emmett Witchel. Dependence-aware transactional memory for increased concurrency. In 2008 41st IEEE\/ACM International Symposium on Microarchitecture, pages 246--257, 2008."},{"key":"e_1_3_2_1_38_1","first-page":"221","volume-title":"45th Int'l Symp. on Computer Architecture (ISCA)","author":"Ros Alberto","year":"2018","unstructured":"Alberto Ros and Stefanos Kaxiras. Non-speculative store coalescing in total store order. In 45th Int'l Symp. on Computer Architecture (ISCA), pages 221--234, June 2018."},{"issue":"4","key":"e_1_3_2_1_39_1","doi-asserted-by":"crossref","first-page":"58","DOI":"10.1109\/88.260295","article-title":"Multiple reservations and the oklahoma update","volume":"1","author":"Stone Janice M.","year":"1993","unstructured":"Janice M. Stone, Harold S. Stone, Philip Heidelberger, and John Turek. Multiple reservations and the oklahoma update. IEEE Parallel & Distributed Technology: Systems & Applications, 1(4):58--71, November 1993.","journal-title":"IEEE Parallel & Distributed Technology: Systems & Applications"},{"key":"e_1_3_2_1_40_1","first-page":"577","volume-title":"21st Int'l Symp. on High-Performance Computer Architecture (HPCA)","author":"Xi Sam","year":"2015","unstructured":"Sam Xi, Hans Jacobson, Pradip Bose, Gu-Yeon Wei, and David Brooks. Quantifying sources of error in McPAT and potential impacts on architectural studies. In 21st Int'l Symp. on High-Performance Computer Architecture (HPCA), pages 577--589, 2015."}],"event":{"name":"ASPLOS '24: 29th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 4","sponsor":["SIGOPS ACM Special Interest Group on Operating Systems","SIGPLAN ACM Special Interest Group on Programming Languages","SIGARCH ACM Special Interest Group on Computer Architecture","SIGBED ACM Special Interest Group on Embedded Systems"],"location":"Hilton La Jolla Torrey Pines La Jolla CA USA","acronym":"ASPLOS '24"},"container-title":["Proceedings of the 29th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 4"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3622781.3674176","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3622781.3674176","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:37:03Z","timestamp":1750178223000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3622781.3674176"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,27]]},"references-count":39,"alternative-id":["10.1145\/3622781.3674176","10.1145\/3622781"],"URL":"https:\/\/doi.org\/10.1145\/3622781.3674176","relation":{},"subject":[],"published":{"date-parts":[[2024,4,27]]},"assertion":[{"value":"2025-04-10","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}