{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T22:30:00Z","timestamp":1730327400521,"version":"3.28.0"},"publisher-location":"New York, NY, USA","reference-count":70,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,4,27]]},"DOI":"10.1145\/3620665.3640381","type":"proceedings-article","created":{"date-parts":[[2024,4,22]],"date-time":"2024-04-22T14:18:06Z","timestamp":1713795486000},"page":"305-319","update-policy":"http:\/\/dx.doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Efficient Microsecond-scale Blind Scheduling with Tiny Quanta"],"prefix":"10.1145","author":[{"ORCID":"http:\/\/orcid.org\/0009-0004-1292-0696","authenticated-orcid":false,"given":"Zhihong","family":"Luo","sequence":"first","affiliation":[{"name":"UC Berkeley, Berkeley, California, USA"}]},{"ORCID":"http:\/\/orcid.org\/0009-0007-9268-9915","authenticated-orcid":false,"given":"Sam","family":"Son","sequence":"additional","affiliation":[{"name":"UC Berkeley, Berkeley, California, USA"}]},{"ORCID":"http:\/\/orcid.org\/0009-0001-9273-9835","authenticated-orcid":false,"given":"Dev","family":"Bali","sequence":"additional","affiliation":[{"name":"UC Berkeley, Berkeley, California, USA"}]},{"ORCID":"http:\/\/orcid.org\/0009-0003-8721-4895","authenticated-orcid":false,"given":"Emmanuel","family":"Amaro","sequence":"additional","affiliation":[{"name":"VMware Research, Palo Alto, California, United States of America"}]},{"ORCID":"http:\/\/orcid.org\/0000-0001-6590-8392","authenticated-orcid":false,"given":"Amy","family":"Ousterhout","sequence":"additional","affiliation":[{"name":"UC San Diego, San Diego, California, United States of America"}]},{"ORCID":"http:\/\/orcid.org\/0000-0002-0524-9425","authenticated-orcid":false,"given":"Sylvia","family":"Ratnasamy","sequence":"additional","affiliation":[{"name":"UC Berkeley, Berkeley, California, United States of America"}]},{"ORCID":"http:\/\/orcid.org\/0000-0002-1357-7533","authenticated-orcid":false,"given":"Scott","family":"Shenker","sequence":"additional","affiliation":[{"name":"ICSI AND UC Berkeley, Berkeley, California, United States of America"}]}],"member":"320","published-online":{"date-parts":[[2024,4,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.5555\/290940.290988"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/378795.378832"},{"volume-title":"Operating systems: Three easy pieces","year":"2018","author":"Arpaci-Dusseau Remzi H","key":"e_1_3_2_1_3_1","unstructured":"Remzi H Arpaci-Dusseau and Andrea C Arpaci-Dusseau. Operating systems: Three easy pieces. Arpaci-Dusseau Books, LLC, 2018."},{"volume-title":"Optimally profiling and tracing programs. ACM Transactions on Programming Languages and Systems (TOPLAS), 16(4):1319--1360","year":"1994","author":"Ball Thomas","key":"e_1_3_2_1_4_1","unstructured":"Thomas Ball and James R Larus. Optimally profiling and tracing programs. ACM Transactions on Programming Languages and Systems (TOPLAS), 16(4):1319--1360, 1994."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.1996.566449"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3015146"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2003.1196112"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3453483.3454107"},{"key":"e_1_3_2_1_9_1","first-page":"335","volume-title":"10th USENIX Symposium on Operating Systems Design and Implementation (OSDI 12)","author":"Belay Adam","year":"2012","unstructured":"Adam Belay, Andrea Bittau, Ali Mashtizadeh, David Terei, David Mazi\u00e8res, and Christos Kozyrakis. Dune: Safe user-level access to privileged cpu features. In 10th USENIX Symposium on Operating Systems Design and Implementation (OSDI 12), pages 335--348, 2012."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/1736020.1736029"},{"key":"e_1_3_2_1_11_1","first-page":"350","volume-title":"Proceedings of the IASTED Conference on Parallel and Distributed Computing and systems","volume":"14","author":"Beyls Kristof","year":"2001","unstructured":"Kristof Beyls and Erik D'Hollander. Reuse distance as a metric for cache behavior. In Proceedings of the IASTED Conference on Parallel and Distributed Computing and systems, volume 14, pages 350--360. Citeseer, 2001."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/1454115.1454128"},{"volume-title":"Mica: a pin tool for collecting microarchitecture-independent workload characteristics. https:\/\/github.com\/boegel\/MICA","year":"2023","key":"e_1_3_2_1_13_1","unstructured":"boegel. Mica: a pin tool for collecting microarchitecture-independent workload characteristics. https:\/\/github.com\/boegel\/MICA, 2023."},{"volume-title":"Performance of boost context switch. https:\/\/www.boost.org\/doc\/libs\/1_79_0\/libs\/context\/doc\/html\/context\/performance.html","year":"2022","key":"e_1_3_2_1_14_1","unstructured":"Boost. Performance of boost context switch. https:\/\/www.boost.org\/doc\/libs\/1_79_0\/libs\/context\/doc\/html\/context\/performance.html, 2022."},{"volume-title":"Performance of boost coroutine2. https:\/\/www.boost.org\/doc\/libs\/1_81_0\/libs\/coroutine2\/doc\/html\/coroutine2\/performance.html","year":"2022","key":"e_1_3_2_1_15_1","unstructured":"Boost. Performance of boost coroutine2. https:\/\/www.boost.org\/doc\/libs\/1_81_0\/libs\/coroutine2\/doc\/html\/coroutine2\/performance.html, 2022."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11134-006-7585-9"},{"key":"e_1_3_2_1_17_1","first-page":"645","volume-title":"2018 USENIX Annual Technical Conference (USENIX ATC 18)","author":"Boucher Sol","year":"2018","unstructured":"Sol Boucher, Anuj Kalia, David G Andersen, and Michael Kaminsky. Putting the\" micro\" back in microservice. In 2018 USENIX Annual Technical Conference (USENIX ATC 18), pages 645--650, 2018."},{"key":"e_1_3_2_1_18_1","first-page":"15","volume-title":"USENIX Annual Technical Conference, General Track","author":"Cantrill Bryan","year":"2004","unstructured":"Bryan Cantrill, Michael W Shapiro, and Adam H Leventhal. Dynamic instrumentation of production systems. In USENIX Annual Technical Conference, General Track, pages 15--28, 2004."},{"issue":"7","key":"e_1_3_2_1_19_1","first-page":"910","article-title":"Coroutines in lua","volume":"10","author":"De Moura Ana L\u00facia","year":"2004","unstructured":"Ana L\u00facia De Moura, Noemi Rodriguez, and Roberto Ierusalimschy. Coroutines in lua. Journal of Universal Computer Science, 10(7):910--925, 2004.","journal-title":"Journal of Universal Computer Science"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/1294261.1294281"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477132.3483571"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/781131.781159"},{"volume-title":"Compiler support for lightweight context switching. ACM Transactions on Architecture and Code Optimization (TACO), 9(4):1--25","year":"2013","author":"Dolan Stephen","key":"e_1_3_2_1_23_1","unstructured":"Stephen Dolan, Servesh Muralidharan, and David Gregg. Compiler support for lightweight context switching. ACM Transactions on Architecture and Code Optimization (TACO), 9(4):1--25, 2013."},{"volume-title":"https:\/\/www.dpdk.org\/","year":"2022","author":"DPDK.","key":"e_1_3_2_1_24_1","unstructured":"DPDK. Data plane development kit. https:\/\/www.dpdk.org\/, 2022."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/319151.319169"},{"volume-title":"AMD and VIA CPUs","year":"1996","author":"Fog Agner","key":"e_1_3_2_1_26_1","unstructured":"Agner Fog. Instruction tables: Lists of instruction latencies, throughputs and micro-operation breakdowns for Intel, AMD and VIA CPUs. Technical University of Denmark. Copyright \u00a9 1996 -- 2022. Last updated 2022-11-04."},{"key":"e_1_3_2_1_27_1","first-page":"281","volume-title":"14th USENIX Symposium on Operating Systems Design and Implementation (OSDI 20)","author":"Fried Joshua","year":"2020","unstructured":"Joshua Fried, Zhenyuan Ruan, Amy Ousterhout, and Adam Belay. Caladan: Mitigating interference at microsecond timescales. In 14th USENIX Symposium on Operating Systems Design and Implementation (OSDI 20), pages 281--297, 2020."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.5555\/3433701.3433771"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.peva.2007.06.012"},{"key":"e_1_3_2_1_30_1","first-page":"161","volume-title":"VEE 2016 - Proceedings of the 12th ACM SIGPLAN\/SIGOPS International Conference on Virtual Execution Environments","author":"Kyle","year":"2016","unstructured":"Kyle C. Hale and Peter A Dinda. Enabling hybrid parallel runtimes through kernel and virtualization support. In VEE 2016 - Proceedings of the 12th ACM SIGPLAN\/SIGOPS International Conference on Virtual Execution Environments, pages 161--175, March 2016."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9781139226424"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613136"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.5555\/866526"},{"key":"e_1_3_2_1_34_1","first-page":"345","volume-title":"16th USENIX Symposium on Networked Systems Design and Implementation (NSDI 19)","author":"Kaffes Kostis","year":"2019","unstructured":"Kostis Kaffes, Timothy Chong, Jack Tigar Humphries, Adam Belay, David Mazi\u00e8res, and Christos Kozyrakis. Shinjuku: Preemptive scheduling for \u03bcsecond-scale tail latency. In 16th USENIX Symposium on Networked Systems Design and Implementation (NSDI 19), pages 345--360, 2019."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CGO.2004.1281665"},{"volume-title":"Rhan Ha, Seongsoo Hong, Chang Yun Park, Minsuk Lee, and Chong Sang Kim. Analysis of cache-related preemption delay in fixed-priority preemptive scheduling","year":"1998","author":"Lee Chang-Gun","key":"e_1_3_2_1_36_1","unstructured":"Chang-Gun Lee, Hoosun Hahn, Yang-Min Seo, Sang Lyul Min, Rhan Ha, Seongsoo Hong, Chang Yun Park, Minsuk Lee, and Chong Sang Kim. Analysis of cache-related preemption delay in fixed-priority preemptive scheduling. IEEE transactions on computers, 47(6):700--713, 1998."},{"first-page":"2","volume-title":"Proceedings of the 2007 workshop on Experimental computer science","author":"Li Chuanpeng","key":"e_1_3_2_1_37_1","unstructured":"Chuanpeng Li, Chen Ding, and Kai Shen. Quantifying the cost of context switch. In Proceedings of the 2007 workshop on Experimental computer science, pages 2--es, 2007."},{"volume-title":"Towards fast, adaptive, and hardware-assisted user-space scheduling. arXiv preprint arXiv:2308.02896","year":"2023","author":"Li Yueying","key":"e_1_3_2_1_38_1","unstructured":"Yueying Li, Nikita Lazarev, David Koufaty, Yijun Yin, Andy Anderson, Zhiru Zhang, Edward Suh, Kostis Kaffes, and Christina Delimitrou. Towards fast, adaptive, and hardware-assisted user-space scheduling. arXiv preprint arXiv:2308.02896, 2023."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/71.491583"},{"volume-title":"Understanding the behavior and implications of context switch misses. ACM Transactions on Architecture and Code Optimization (TACO), 7(4):1--28","year":"2010","author":"Liu Fang","key":"e_1_3_2_1_40_1","unstructured":"Fang Liu and Yan Solihin. Understanding the behavior and implications of context switch misses. ACM Transactions on Architecture and Code Optimization (TACO), 7(4):1--28, 2010."},{"volume-title":"LLVM's analysis and transform passes. https:\/\/llvm.org\/docs\/Passes.html","year":"2022","author":"LLVM.","key":"e_1_3_2_1_41_1","unstructured":"LLVM. LLVM's analysis and transform passes. https:\/\/llvm.org\/docs\/Passes.html, 2022."},{"volume-title":"Vijay Janapa Reddi, and Kim Hazelwood. Pin: building customized program analysis tools with dynamic instrumentation. Acm sigplan notices, 40(6):190--200","year":"2005","author":"Luk Chi-Keung","key":"e_1_3_2_1_42_1","unstructured":"Chi-Keung Luk, Robert Cohn, Robert Muth, Harish Patil, Artur Klauser, Geoff Lowney, Steven Wallace, Vijay Janapa Reddi, and Kim Hazelwood. Pin: building customized program analysis tools with dynamic instrumentation. Acm sigplan notices, 40(6):190--200, 2005."},{"volume-title":"x86 user interrupts support. https:\/\/lwn.net\/Articles\/869140\/","year":"2021","author":"Mehta Sohil","key":"e_1_3_2_1_43_1","unstructured":"Sohil Mehta. x86 user interrupts support. https:\/\/lwn.net\/Articles\/869140\/, 2021."},{"volume-title":"https:\/\/rocksdb.org\/","year":"2022","key":"e_1_3_2_1_44_1","unstructured":"Meta. Rocksdb. https:\/\/rocksdb.org\/, 2022."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/71.963420"},{"volume-title":"Revisiting coroutines. ACM Transactions on Programming Languages and Systems (TOPLAS), 31(2):1--31","year":"2009","author":"De Moura Ana L\u00facia","key":"e_1_3_2_1_46_1","unstructured":"Ana L\u00facia De Moura and Roberto Ierusalimschy. Revisiting coroutines. ACM Transactions on Programming Languages and Systems (TOPLAS), 31(2):1--31, 2009."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.is.2014.04.003"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/944645.944698"},{"key":"e_1_3_2_1_49_1","unstructured":"Gor Nishanov. C++ extensions for coroutines. 2018."},{"key":"e_1_3_2_1_50_1","first-page":"385","volume-title":"Presented as part of the 10th USENIX Symposium on Networked Systems Design and Implementation (NSDI 13)","author":"Nishtala Rajesh","year":"2013","unstructured":"Rajesh Nishtala, Hans Fugal, Steven Grimm, Marc Kwiatkowski, Herman Lee, Harry C Li, Ryan McElroy, Mike Paleczny, Daniel Peek, Paul Saab, et al. Scaling memcache at facebook. In Presented as part of the 10th USENIX Symposium on Networked Systems Design and Implementation (NSDI 13), pages 385--398, 2013."},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.peva.2007.06.028"},{"key":"e_1_3_2_1_52_1","first-page":"361","volume-title":"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. Shenango: Achieving high {CPU} efficiency for latency-sensitive datacenter workloads. In 16th USENIX Symposium on Networked Systems Design and Implementation (NSDI 19), pages 361--378, 2019."},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.5555\/1594371.1594375"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1145\/3132747.3132780"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1145\/781027.781055"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2007.346181"},{"volume-title":"The boost C++ libraries. Boris Sch\u00e4ling","year":"2011","author":"Sch\u00e4ling Boris","key":"e_1_3_2_1_57_1","unstructured":"Boris Sch\u00e4ling. The boost C++ libraries. Boris Sch\u00e4ling, 2011."},{"issue":"10","key":"e_1_3_2_1_58_1","first-page":"1","article-title":"Approximate performance analysis of generalized join the shortest queue routing","volume":"3","author":"Selen Jori","year":"2016","unstructured":"Jori Selen, Ivo Adan, and Stella Kapodistria. Approximate performance analysis of generalized join the shortest queue routing. EAI Endorsed Transactions on Future Internet, 3(10), 1 2016.","journal-title":"EAI Endorsed Transactions on Future Internet"},{"key":"e_1_3_2_1_59_1","unstructured":"Hamed Seyedroudbari Srikar Vanavasam and Alexandros Daglis. Turbo: SmartNIC-enabled dynamic load balancing of \u03bcs-scale RPCs."},{"volume-title":"Modern processor design: fundamentals of superscalar processors","year":"2013","author":"Shen John Paul","key":"e_1_3_2_1_60_1","unstructured":"John Paul Shen and Mikko H Lipasti. Modern processor design: fundamentals of superscalar processors. Waveland Press, 2013."},{"volume-title":"https:\/\/www.tpc.org\/tpcc\/","year":"2022","author":"TPCC.","key":"e_1_3_2_1_61_1","unstructured":"TPCC. Tpc-c. https:\/\/www.tpc.org\/tpcc\/, 2022."},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1145\/2517349.2522713"},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2020.2980061"},{"volume-title":"Is tail-optimal scheduling possible? Operations research, 60(5):1249--1257","year":"2012","author":"Wierman Adam","key":"e_1_3_2_1_64_1","unstructured":"Adam Wierman and Bert Zwart. Is tail-optimal scheduling possible? Operations research, 60(5):1249--1257, 2012."},{"volume-title":"The worst-case execution-time problem---overview of methods and survey of tools. ACM Transactions on Embedded Computing Systems (TECS), 7(3):1--53","year":"2008","author":"Wilhelm Reinhard","key":"e_1_3_2_1_65_1","unstructured":"Reinhard Wilhelm, Jakob Engblom, Andreas Ermedahl, Niklas Holsti, Stephan Thesing, David Whalley, Guillem Bernat, Christian Ferdinand, Reinhold Heckmann, Tulika Mitra, Frank Mueller, Isabelle Puaut, Peter Puschner, Jan Staschulat, and Per Stenstrom. The worst-case execution-time problem---overview of methods and survey of tools. ACM Transactions on Embedded Computing Systems (TECS), 7(3):1--53, 2008."},{"volume-title":"Jaswinder Pal Singh, and Anoop Gupta. The splash-2 programs: Characterization and methodological considerations. ACM SIGARCH computer architecture news, 23(2):24--36","year":"1995","author":"Woo Steven Cameron","key":"e_1_3_2_1_66_1","unstructured":"Steven Cameron Woo, Moriyoshi Ohara, Evan Torrie, Jaswinder Pal Singh, and Anoop Gupta. The splash-2 programs: Characterization and methodological considerations. ACM SIGARCH computer architecture news, 23(2):24--36, 1995."},{"key":"e_1_3_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.1007\/BF01182931"},{"key":"e_1_3_2_1_68_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477132.3483569"},{"key":"e_1_3_2_1_69_1","doi-asserted-by":"publisher","DOI":"10.1145\/3453953.3453965"},{"key":"e_1_3_2_1_70_1","first-page":"1225","volume-title":"14th USENIX Symposium on Operating Systems Design and Implementation (OSDI 20)","author":"Zhu Hang","year":"2020","unstructured":"Hang Zhu, Kostis Kaffes, Zixu Chen, Zhenming Liu, Christos Kozyrakis, Ion Stoica, and Xin Jin. Racksched: A microsecond-scale scheduler for rack-scale computers. In 14th USENIX Symposium on Operating Systems Design and Implementation (OSDI 20), pages 1225--1240, 2020."}],"event":{"name":"ASPLOS '24: 29th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 2","sponsor":["SIGARCH ACM Special Interest Group on Computer Architecture","SIGOPS ACM Special Interest Group on Operating Systems","SIGPLAN ACM Special Interest Group on Programming Languages","SIGBED ACM Special Interest Group on Embedded Systems"],"location":"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 2"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3620665.3640381","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,1]],"date-time":"2024-05-01T13:57:05Z","timestamp":1714571825000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3620665.3640381"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,27]]},"references-count":70,"alternative-id":["10.1145\/3620665.3640381","10.1145\/3620665"],"URL":"https:\/\/doi.org\/10.1145\/3620665.3640381","relation":{},"subject":[],"published":{"date-parts":[[2024,4,27]]},"assertion":[{"value":"2024-04-27","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}