{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,27]],"date-time":"2026-02-27T03:46:57Z","timestamp":1772164017769,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":60,"publisher":"ACM","license":[{"start":{"date-parts":[[2017,6,24]],"date-time":"2017-06-24T00:00:00Z","timestamp":1498262400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["CCF 13-02641 and CCF 16-19245"],"award-info":[{"award-number":["CCF 13-02641 and CCF 16-19245"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"name":"STARnet","award":["a Semiconductor Research Corporation program sponsored by MARCO and DARPA"],"award-info":[{"award-number":["a Semiconductor Research Corporation program sponsored by MARCO and DARPA"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2017,6,24]]},"DOI":"10.1145\/3079856.3080206","type":"proceedings-article","created":{"date-parts":[[2017,6,15]],"date-time":"2017-06-15T15:40:01Z","timestamp":1497541201000},"page":"161-174","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":29,"title":["Chasing Away RAts"],"prefix":"10.1145","author":[{"given":"Matthew D.","family":"Sinclair","sequence":"first","affiliation":[{"name":"University of Illinois at Urbana-Champaign"}]},{"given":"Johnathan","family":"Alsop","sequence":"additional","affiliation":[{"name":"University of Illinois at Urbana-Champaign"}]},{"given":"Sarita V.","family":"Adve","sequence":"additional","affiliation":[{"name":"University of Illinois at Urbana-Champaign"}]}],"member":"320","published-online":{"date-parts":[[2017,6,24]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/325164.325100"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/1787234.1787255"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","unstructured":"S. V. Adve and M. D. Hill. 1993. A Unified Formalization of Four Shared-Memory Models. TPDS Article 6 (June 1993) 613--624 pages. 10.1109\/71.242161","DOI":"10.1109\/71.242161"},{"key":"e_1_3_2_1_5_1","volume-title":"IEEE International Symposium on Performance Analysis of Systems and Software.","author":"Agarwal N.","unstructured":"N. Agarwal, T. Krishna, Li-Shiuan Peh, and N.K. Jha. 2009. GARNET: A Detailed On-chip Network Model Inside a Full-system Simulator. In IEEE International Symposium on Performance Analysis of Systems and Software."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/2627752"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2016.7783729"},{"key":"e_1_3_2_1_8_1","volume-title":"IEEE International Symposium on Performance Analysis of Systems and Software.","author":"Bakhoda Ali","unstructured":"Ali Bakhoda, George L. Yuan, Wilson W. L. Fung, Henry Wong, and Tor M. Aamodt. 2009. Analyzing CUDA Workloads Using a Detailed GPU Simulator. In IEEE International Symposium on Performance Analysis of Systems and Software."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/2837614.2837637"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-662-46669-8_12"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/2247684.2247688"},{"key":"e_1_3_2_1_12_1","unstructured":"Hans-J. Boehm. 2013. N3710: Specifying the absence of \"out of thin air\" results (LWG2265). (2013)."},{"key":"e_1_3_2_1_13_1","unstructured":"Hans-J. Boehm. 2013. N3786: Prohibiting \"out of thin air\" results in C++14. (2013)."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/1375581.1375591"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/2618128.2618134"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2012.6402918"},{"key":"e_1_3_2_1_17_1","unstructured":"C++. 2015. C++ Reference: Memory Order. http:\/\/en.cppreference.com\/w\/cpp\/atomic\/memory_order. (2015)."},{"key":"e_1_3_2_1_18_1","volume-title":"Pannotia: Understanding Irregular GPGPU Graph Applications. In IEEE International Symposium on Workload Characterization. 185--195","author":"Che Shuai","unstructured":"Shuai Che, B.M. Beckmann, S.K. Reinhardt, and K. Skadron. 2013. Pannotia: Understanding Irregular GPGPU Graph Applications. In IEEE International Symposium on Workload Characterization. 185--195."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2009.5306797"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2010.5650274"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/PACT.2011.21"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/2049662.2049663"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2011.159"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.5555\/17407.17406"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/2540708.2540743"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/2701618"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1016\/0743-7315(92)90052-O"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/325164.325102"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/2688500.2688501"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2015.15"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/2541940.2541981"},{"key":"e_1_3_2_1_33_1","unstructured":"HSA Foundation. 2015. HSA Platform System Architecture Specification. http:\/\/www.hsafoundation.com\/?ddownload=4944. (2015)."},{"key":"e_1_3_2_1_34_1","volume-title":"Intel Discloses Newest Microarchitecture and 14 Nanometer Manufacturing Process Technical Details. Intel Newsroom","author":"PR.","year":"2014","unstructured":"IntelPR. 2014. Intel Discloses Newest Microarchitecture and 14 Nanometer Manufacturing Process Technical Details. Intel Newsroom (2014)."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/2933575.2934536"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3009837.3009850"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/2749469.2750374"},{"key":"e_1_3_2_1_38_1","unstructured":"L. Howes and A. Munshi. 2015. The OpenCL Specification Version 2.0. Khronos Group. (2015)."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/2837614.2837643"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/2485922.2485964"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/1669112.1669172"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/1040305.1040336"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","unstructured":"M. M. K. Martin D. J. Sorin B. M. Beckmann M. R. Marty M. Xu A. R. Alameldeen K. E. Moore M. D. Hill and D. A. Wood. 2005. Multifacet's General Execution-driven Multiprocessor Simulator (GEMS) Toolset. SIGARCH Computer Architecture News (2005). 10.1145\/1105734.1105747","DOI":"10.1145\/1105734.1105747"},{"key":"e_1_3_2_1_44_1","volume-title":"Proceedings of the Dagstuhl Workshop on Compositional Verification Methods for Next-Generation Concurrency. 15","author":"McKenney Paul","year":"2015","unstructured":"Paul McKenney. 2015. Some Examples of Kernel-Hacker Informal Correctness Reasoning. In Proceedings of the Dagstuhl Workshop on Compositional Verification Methods for Next-Generation Concurrency. 15."},{"key":"e_1_3_2_1_45_1","unstructured":"Paul E. McKenney Torvald Riegel and Jeff Preshing. 2014. N4036: Towards Implementation and Use of memory_order_consume. (2014)."},{"key":"e_1_3_2_1_46_1","unstructured":"David S. Miller. 2016. Semantics and Behavior of Atomic and Bitmask Operations. (2016)."},{"key":"e_1_3_2_1_47_1","unstructured":"NVIDIA. 2010. CUDA SDK 3.1. (2010)."},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.5555\/1757112.1757137"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/2837614.2837616"},{"key":"e_1_3_2_1_50_1","unstructured":"Victor Podlozhnyuk. 2007. Histogram calculation in CUDA. (2007) 11 pages."},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/2851141.2851150"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1145\/2830772.2830821"},{"key":"e_1_3_2_1_54_1","volume-title":"Standard for Programming Language C++.","author":"Smith Richard","year":"2017","unstructured":"Richard Smith. 2017. N4659: Working Draft, Standard for Programming Language C++. (2017)."},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1145\/2464996.2467280"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1145\/2908080.2908114"},{"key":"e_1_3_2_1_57_1","volume-title":"Geng Daniel Liu, and WMW Hwu","author":"Stratton John A","year":"2012","unstructured":"John A Stratton, Christopher Rodrigues, I-Jui Sung, Nady Obeid, Li-Wen Chang, Nasser Anssari, Geng Daniel Liu, and WMW Hwu. 2012. Parboil: A Revised Benchmark Suite for Scientific and Commercial Throughput Computing. Technical Report. Department of ECE and CS, University of Illinois at Urbana-Champaign."},{"key":"e_1_3_2_1_58_1","volume-title":"Owens","author":"Stuart Jeff A.","year":"2011","unstructured":"Jeff A. Stuart and John D. Owens. 2011. Efficient Synchronization Primitives for GPUs. CoRR abs\/1110.4623 (2011)."},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1145\/2694344.2694356"},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1145\/2451116.2451119"},{"key":"e_1_3_2_1_61_1","volume-title":"Atomic Weapons: The C++ Memory Model and Modern Hardware. In C++ and Beyond.","author":"Sutter Herb","year":"2012","unstructured":"Herb Sutter. 2012. Atomic Weapons: The C++ Memory Model and Modern Hardware. In C++ and Beyond."},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1145\/2509136.2509532"},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1145\/2830772.2830774"}],"event":{"name":"ISCA '17: The 44th Annual International Symposium on Computer Architecture","location":"Toronto ON Canada","acronym":"ISCA '17","sponsor":["IEEE IEEE Computer Society Technical Committee on Design Automation","SIGARCH ACM Special Interest Group on Computer Architecture"]},"container-title":["Proceedings of the 44th Annual International Symposium on Computer Architecture"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3079856.3080206","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3079856.3080206","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3079856.3080206","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T23:37:15Z","timestamp":1750203435000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3079856.3080206"}},"subtitle":["Semantics and Evaluation for Relaxed Atomics on Heterogeneous Systems"],"short-title":[],"issued":{"date-parts":[[2017,6,24]]},"references-count":60,"alternative-id":["10.1145\/3079856.3080206","10.1145\/3079856"],"URL":"https:\/\/doi.org\/10.1145\/3079856.3080206","relation":{"is-identical-to":[{"id-type":"doi","id":"10.1145\/3140659.3080206","asserted-by":"object"}]},"subject":[],"published":{"date-parts":[[2017,6,24]]},"assertion":[{"value":"2017-06-24","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}