{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T04:59:03Z","timestamp":1750309143066,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":55,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,2,17]],"date-time":"2024-02-17T00:00:00Z","timestamp":1708128000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,2,17]]},"DOI":"10.1145\/3640537.3641568","type":"proceedings-article","created":{"date-parts":[[2024,2,20]],"date-time":"2024-02-20T21:43:05Z","timestamp":1708465385000},"page":"100-112","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["BLQ: Light-Weight Locality-Aware Runtime for Blocking-Less Queuing"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7988-1431","authenticated-orcid":false,"given":"Qinzhe","family":"Wu","sequence":"first","affiliation":[{"name":"University of Texas at Austin, Austin, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7092-2401","authenticated-orcid":false,"given":"Ruihao","family":"Li","sequence":"additional","affiliation":[{"name":"University of Texas at Austin, Austin, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8651-7603","authenticated-orcid":false,"given":"Jonathan","family":"Beard","sequence":"additional","affiliation":[{"name":"Arm, Austin, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8747-5214","authenticated-orcid":false,"given":"Lizy","family":"John","sequence":"additional","affiliation":[{"name":"University of Texas at Austin, Austin, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,2,20]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1002\/9781119332015.ch13"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/18.32150"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2014.30"},{"key":"e_1_3_2_1_4_1","volume-title":"Operating Systems: Three Easy Pieces","author":"Arpaci-Dusseau R.H.","year":"2018","unstructured":"R.H. Arpaci-Dusseau and A.C. Arpaci-Dusseau. 2018. Operating Systems: Three Easy Pieces. CreateSpace Independent Publishing Platform. isbn:9781985086593 https:\/\/books.google.com\/books?id=0a-ouwEACAAJ"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2203.12533"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10885-8_6"},{"volume-title":"Proceedings of the Sixth International Workshop on Programming Models and Applications for Multicores and Manycores (PMAM \u201915)","author":"Beard Jonathan C.","key":"e_1_3_2_1_7_1","unstructured":"Jonathan C. Beard, Peng Li, and Roger D. Chamberlain. 2015. RaftLib: A C++ Template Library for High Performance Stream Parallel Processing. In Proceedings of the Sixth International Workshop on Programming Models and Applications for Multicores and Manycores (PMAM \u201915). Association for Computing Machinery, New York, NY, USA. 96\u2013105. isbn:9781450334044 https:\/\/doi.org\/10.1145\/2712386.2712400 10.1145\/2712386.2712400"},{"key":"e_1_3_2_1_8_1","unstructured":"boost. 2020. Class template queue. https:\/\/bit.ly\/37hAMHJ"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.7717\/peerj-cs.190"},{"key":"e_1_3_2_1_10_1","unstructured":"Go Community. 2024. Go Programming Language. https:\/\/go.dev\/"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/99.660313"},{"key":"e_1_3_2_1_12_1","volume-title":"Proceedings of the 1st Workshop on AutotuniNg and ADaptivity AppRoaches for Energy Efficient HPC Systems (ANDARE \u201917)","author":"Diavastos Andreas","year":"2017","unstructured":"Andreas Diavastos and Pedro Trancoso. 2017. Auto-Tuning Static Schedules for Task Data-Flow Applications. In Proceedings of the 1st Workshop on AutotuniNg and ADaptivity AppRoaches for Energy Efficient HPC Systems (ANDARE \u201917). Association for Computing Machinery, New York, NY, USA. Article 1, 6 pages. isbn:9781450353632 https:\/\/doi.org\/10.1145\/3152821.3152879 10.1145\/3152821.3152879"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3127068"},{"key":"e_1_3_2_1_14_1","volume-title":"Towards Scalable and Expressive Stream Packet Processing. In 2021 IEEE Global Communications Conference (GLOBECOM). 01\u201306","author":"Fais Alessandra","year":"2021","unstructured":"Alessandra Fais, Giuseppe Lettieri, Gregorio Procissi, and Stefano Giordano. 2021. Towards Scalable and Expressive Stream Packet Processing. In 2021 IEEE Global Communications Conference (GLOBECOM). 01\u201306. https:\/\/doi.org\/10.1109\/GLOBECOM46510.2021.9685436 10.1109\/GLOBECOM46510.2021.9685436"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-01743-8"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10422-5_35"},{"key":"e_1_3_2_1_17_1","unstructured":"Apache Foundation. 2024. Apache Storm. https:\/\/storm.apache.org\/index.html"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/1168857.1168877"},{"key":"e_1_3_2_1_19_1","volume-title":"Proceedings of the 10th International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS X). Association for Computing Machinery","author":"Gordon Michael I.","year":"2002","unstructured":"Michael I. Gordon, William Thies, Michal Karczmarek, Jasper Lin, Ali S. Meli, Andrew A. Lamb, Chris Leger, Jeremy Wong, Henry Hoffmann, David Maze, and Saman Amarasinghe. 2002. A Stream Compiler for Communication-Exposed Architectures. In Proceedings of the 10th International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS X). Association for Computing Machinery, New York, NY, USA. 291\u2013303. isbn:1581135742 https:\/\/doi.org\/10.1145\/605397.605428 10.1145\/605397.605428"},{"key":"e_1_3_2_1_20_1","volume-title":"2010 IEEE International Symposium on Parallel & Distributed Processing (IPDPS). IEEE Computer Society","author":"Guo Y.","year":"2010","unstructured":"Y. Guo, V. Cave, V. Sarkar, and J. Zhao. 2010. SLAW: A scalable locality-aware adaptive work-stealing scheduler. In 2010 IEEE International Symposium on Parallel & Distributed Processing (IPDPS). IEEE Computer Society, Los Alamitos, CA, USA. 1\u201312. https:\/\/doi.org\/10.1109\/IPDPS.2010.5470425 10.1109\/IPDPS.2010.5470425"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","unstructured":"M. Herlihy N. Shavit V. Luchangco and M. Spear. 2020. The Art of Multiprocessor Programming. Elsevier Science. isbn:9780123914064 https:\/\/doi.org\/10.1016\/c2011-0-06993-4 10.1016\/c2011-0-06993-4","DOI":"10.1016\/c2011-0-06993-4"},{"key":"e_1_3_2_1_22_1","unstructured":"Pieter Hintjens. 2010. ZeroMQ: the guide. http:\/\/zeromq.org"},{"key":"e_1_3_2_1_23_1","volume-title":"Proceedings of the ACM SIGOPS 28th Symposium on Operating Systems Principles CD-ROM","author":"Humphries Jack Tigar","year":"2021","unstructured":"Jack Tigar Humphries, Neel Natu, Ashwin Chaugule, Ofir Weisse, Barret Rhoden, Josh Don, Luigi Rizzo, Oleg Rombakh, Paul Jack Turner, and Christos Kozyrakis. 2021. ghOSt: Fast and Flexible User-Space Delegation of Linux Scheduling. In Proceedings of the ACM SIGOPS 28th Symposium on Operating Systems Principles CD-ROM. New York, NY, USA. 588\u2013604. https:\/\/doi.org\/10.1145\/3477132.3483542 10.1145\/3477132.3483542"},{"key":"e_1_3_2_1_24_1","unstructured":"M. Jones. 2018. Inside the Linux 2.6 Completely Fair Scheduler. https:\/\/developer.ibm.com\/tutorials\/l-completely-fair-scheduler\/"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/781498.781506"},{"volume-title":"Queueing Systems. Volume 1: Theory","author":"Kleinrock L.","key":"e_1_3_2_1_26_1","unstructured":"L. Kleinrock. 1975. Queueing Systems. Volume 1: Theory. Wiley-Interscience."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/PROC.1987.13876"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2010.5470368"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/hpca.2011.5749720"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2109.07047"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2941183"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-60939-9_2"},{"key":"e_1_3_2_1_33_1","volume-title":"Proceedings of the 18th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming (PPoPP \u201913)","author":"Morrison Adam","year":"2013","unstructured":"Adam Morrison and Yehuda Afek. 2013. Fast Concurrent Queues for X86 Processors. In Proceedings of the 18th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming (PPoPP \u201913). Association for Computing Machinery, New York, NY, USA. 103\u2013112. isbn:9781450319225 https:\/\/doi.org\/10.1145\/2442516.2442527 10.1145\/2442516.2442527"},{"key":"e_1_3_2_1_34_1","volume-title":"Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis. 1\u201312","author":"Nai Lifeng","year":"2015","unstructured":"Lifeng Nai, Yinglong Xia, Ilie G. Tanase, Hyesoon Kim, and Ching-Yung Lin. 2015. GraphBIG: understanding graph computing in the context of industrial solutions. In SC \u201915: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis. 1\u201312. https:\/\/doi.org\/10.1145\/2807591.2807626 10.1145\/2807591.2807626"},{"key":"e_1_3_2_1_35_1","volume-title":"2021 29th International Symposium on Modeling, Analysis, and Simulation of Computer and Telecommunication Systems (MASCOTS). 1\u20138. https:\/\/doi.org\/10","author":"Nookala Poornima","year":"2021","unstructured":"Poornima Nookala, Peter Dinda, Kyle C. Hale, Kyle Chard, and Ioan Raicu. 2021. Enabling Extremely Fine-grained Parallelism via Scalable Concurrent Queues on Modern Many-core Architectures. In 2021 29th International Symposium on Modeling, Analysis, and Simulation of Computer and Telecommunication Systems (MASCOTS). 1\u20138. https:\/\/doi.org\/10.1109\/MASCOTS53633.2021.9614292 10.1109\/MASCOTS53633.2021.9614292"},{"key":"e_1_3_2_1_36_1","volume-title":"Shenango: Achieving High CPU Efficiency for Latency-sensitive Datacenter Workloads. In 16th USENIX Symposium on Networked Systems Design and Implementation (NSDI 19)","author":"Ousterhout Amy","year":"2019","unstructured":"Amy Ousterhout, Joshua Fried, Jonathan Behrens, Adam Belay, and Hari Balakrishnan. 2019. Shenango: Achieving High CPU Efficiency for Latency-sensitive Datacenter Workloads. In 16th USENIX Symposium on Networked Systems Design and Implementation (NSDI 19). USENIX Association, Boston, MA. 361\u2013378. isbn:978-1-931971-49-2 https:\/\/www.usenix.org\/conference\/nsdi19\/presentation\/ousterhout"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2014.04.001"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/PACT.2011.9"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTER51413.2022.00026"},{"key":"e_1_3_2_1_40_1","volume-title":"2016 IEEE 34th International Conference on Computer Design (ICCD). 117\u2013124","author":"Sembrant Andreas","year":"2016","unstructured":"Andreas Sembrant, Erik Hagersten, and David Black-Schaffer. 2016. Data placement across the cache hierarchy: Minimizing data movement with reuse-aware placement. In 2016 IEEE 34th International Conference on Computer Design (ICCD). 117\u2013124. https:\/\/doi.org\/10.1109\/ICCD.2016.7753269 10.1109\/ICCD.2016.7753269"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compeleceng.2019.01.020"},{"key":"e_1_3_2_1_42_1","unstructured":"sstsimulator. 2020. Ember Communication Pattern Library. https:\/\/github.com\/sstsimulator\/ember"},{"key":"e_1_3_2_1_43_1","volume-title":"Proceedings of the Sixth ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming (PPOPP \u201997)","author":"Subhlok Jaspal","year":"1997","unstructured":"Jaspal Subhlok and Bwolen Yang. 1997. A New Model for Integrated Nested Task and Data Parallel Programming. In Proceedings of the Sixth ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming (PPOPP \u201997). Association for Computing Machinery, New York, NY, USA. 1\u201312. isbn:0897919068 https:\/\/doi.org\/10.1145\/263764.263768 10.1145\/263764.263768"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/1477926.1477930"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2018.2814602"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-45937-5_14"},{"volume-title":"Reuse Aware Data Placement Schemes for Multilevel Cache Hierarchies. Ph. D. Dissertation","author":"Wang Jiajun","key":"e_1_3_2_1_47_1","unstructured":"Jiajun Wang. 2019. Reuse Aware Data Placement Schemes for Multilevel Cache Hierarchies. Ph. D. Dissertation. The University of Texas at Austin. Austin TX."},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/2967938.2967954"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2008.4536359"},{"key":"e_1_3_2_1_50_1","unstructured":"Wikipedia. 2023. Message Queue. https:\/\/en.wikipedia.org\/wiki\/Message_queue"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","unstructured":"Markus Wittmann and Georg Hager. 2009. A Proof of Concept for Optimizing Task Parallelism by Locality Queues. https:\/\/doi.org\/10.48550\/arXiv.0902.1884 arxiv:arXiv:0902.1884.","DOI":"10.48550\/arXiv.0902.1884"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS49936.2021.00027"},{"key":"e_1_3_2_1_53_1","volume-title":"Proceedings of the 51st International Conference on Parallel Processing (ICPP \u201922)","author":"Wu Qinzhe","year":"2023","unstructured":"Qinzhe Wu, Ashen Ekanayake, Ruihao Li, Jonathan Beard, and Lizy John. 2023. SPAMeR: Speculative Push for Anticipated Message Requests in Multi-Core Systems. In Proceedings of the 51st International Conference on Parallel Processing (ICPP \u201922). Association for Computing Machinery, New York, NY, USA. Article 58, 12 pages. isbn:9781450397339 https:\/\/doi.org\/10.1145\/3545008.3545044 10.1145\/3545008.3545044"},{"key":"e_1_3_2_1_54_1","unstructured":"Xmcgcg. 2023. CPP copy_constructor. https:\/\/en.cppreference.com\/w\/cpp\/language\/copy_constructor"},{"key":"e_1_3_2_1_55_1","volume-title":"Revisiting the Design of Data Stream Processing Systems on Multi-Core Processors. In 2017 IEEE 33rd International Conference on Data Engineering (ICDE). 659\u2013670","author":"Zhang Shuhao","year":"2017","unstructured":"Shuhao Zhang, Bingsheng He, Daniel Dahlmeier, Amelie Chi Zhou, and Thomas Heinze. 2017. Revisiting the Design of Data Stream Processing Systems on Multi-Core Processors. In 2017 IEEE 33rd International Conference on Data Engineering (ICDE). 659\u2013670. https:\/\/doi.org\/10.1109\/ICDE.2017.119 10.1109\/ICDE.2017.119"}],"event":{"name":"CC '24: 33rd ACM SIGPLAN International Conference on Compiler Construction","sponsor":["SIGPLAN ACM Special Interest Group on Programming Languages"],"location":"Edinburgh United Kingdom","acronym":"CC '24"},"container-title":["Proceedings of the 33rd ACM SIGPLAN International Conference on Compiler Construction"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3640537.3641568","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3640537.3641568","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T22:50:24Z","timestamp":1750287024000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3640537.3641568"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,2,17]]},"references-count":55,"alternative-id":["10.1145\/3640537.3641568","10.1145\/3640537"],"URL":"https:\/\/doi.org\/10.1145\/3640537.3641568","relation":{},"subject":[],"published":{"date-parts":[[2024,2,17]]},"assertion":[{"value":"2024-02-20","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}