{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T13:14:35Z","timestamp":1776950075487,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":73,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,5,4]]},"DOI":"10.1145\/3777884.3796994","type":"proceedings-article","created":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T12:27:26Z","timestamp":1776947246000},"page":"192-207","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Variability-Guided Performance Optimization"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3709-1829","authenticated-orcid":false,"given":"Eitan","family":"Frachtenberg","sequence":"first","affiliation":[{"name":"Hewlett Packard Enterprise Labs, Milpitas, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6238-6709","authenticated-orcid":false,"given":"Viyom","family":"Mittal","sequence":"additional","affiliation":[{"name":"Hewlett Packard Enterprise Labs, Milpitas, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6981-581X","authenticated-orcid":false,"given":"Mohammed","family":"Baydoun","sequence":"additional","affiliation":[{"name":"American University of Beirut, Beirut, Lebanon"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8297-8525","authenticated-orcid":false,"given":"Aditya","family":"Dhakal","sequence":"additional","affiliation":[{"name":"Hewlett Packard Enterprise Labs, Milpitas, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3356-6898","authenticated-orcid":false,"given":"Izzat El","family":"Hajj","sequence":"additional","affiliation":[{"name":"American University of Beirut, Beirut, Lebanon"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9830-8588","authenticated-orcid":false,"given":"Dejan","family":"Milojicic","sequence":"additional","affiliation":[{"name":"Hewlett Packard Enterprise Labs, Milpitas, USA"}]}],"member":"320","published-online":{"date-parts":[[2026,5,3]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Bilge Acun. 2017. Mitigating variability in HPC systems and applications for performance and power efficiency. Ph.D. Dissertation. University of Illinois at Urbana-Champaign."},{"key":"e_1_3_2_1_2_1","volume-title":"14th Symposium on Networked Systems Design and Implementation (NSDI). USENIX, 469-482","author":"Alipourfard Omid","year":"2017","unstructured":"Omid Alipourfard, Hongqiang Harry Liu, Jianshu Chen, Shivaram Venkataraman, Minlan Yu, and Ming Zhang. 2017. CherryPick: Adaptively unearthing the best cloud configurations for big data analytics. In 14th Symposium on Networked Systems Design and Implementation (NSDI). USENIX, 469-482. https:\/\/www.usenix.org\/system\/files\/conference\/nsdi17\/nsdi17-alipourfard.pdf"},{"key":"e_1_3_2_1_3_1","volume-title":"Proceedings of the 48th International Conference on Parallel Processing. 1-10","author":"Ates Emre","year":"2019","unstructured":"Emre Ates, Yijia Zhang, Burak Aksar, Jim Brandt, Vitus J Leung, Manuel Egele, and Ayse K Coskun. 2019. HPAS: An HPC performance anomaly suite for reproducing performance variations. In Proceedings of the 48th International Conference on Parallel Processing. 1-10."},{"key":"e_1_3_2_1_4_1","first-page":"264","volume-title":"Proceedings of the 30th ACM International Conference on Architectural Support for Programming Languages and Operating Systems","volume":"1","author":"Roy Rohan Basu","year":"2025","unstructured":"Rohan Basu Roy, Vijay Gadepally, and Devesh Tiwari. 2025. DarwinGame: Playing Tournaments for Tuning Applications in Noisy Cloud Environments. In Proceedings of the 30th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 1. 264-279."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10009-017-0469-y"},{"key":"e_1_3_2_1_6_1","volume-title":"2019 IEEE 27th International Symposium on Modeling, Analysis, and Simulation of Computer and Telecommunication Systems (MASCOTS). IEEE, 249-255","author":"Bulej Lubom\u00edr","year":"2019","unstructured":"Lubom\u00edr Bulej, Vojt\u011bch Hork\u1ef3, and Petr Tuma. 2019. Initial experiments with duet benchmarking: Performance testing interference in the cloud. In 2019 IEEE 27th International Symposium on Modeling, Analysis, and Simulation of Computer and Telecommunication Systems (MASCOTS). IEEE, 249-255."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3358960.3379132"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2009.5306797"},{"key":"e_1_3_2_1_9_1","first-page":"217","volume-title":"11th USENIX Symposium on Operating Systems Design and Implementation (OSDI 14)","author":"Chow Michael","year":"2014","unstructured":"Michael Chow, David Meisner, Jason Flinn, Daniel Peek, and Thomas F Wenisch. 2014. The mystery machine: End-to-end performance analysis of large-scale internet services. In 11th USENIX Symposium on Operating Systems Design and Implementation (OSDI 14). 217-231."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/2812803"},{"key":"e_1_3_2_1_11_1","volume-title":"Proceedings of the SC'23 Workshops of the International Conference on High Performance Computing, Network, Storage, and Analysis. 1614-1622","author":"Cui Minyu","year":"2023","unstructured":"Minyu Cui, Nikela Papadopoulou, and Miquel Peric\u00e0s. 2023. Analysis and characterization of performance variability for openmp runtime. In Proceedings of the SC'23 Workshops of the International Conference on High Performance Computing, Network, Storage, and Analysis. 1614-1622."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3719276.3725184"},{"key":"e_1_3_2_1_13_1","volume-title":"2022 IEEE International Conference on Autonomic Computing and Self-Organizing Systems Companion (ACSOS-C). IEEE, 19-24","author":"Das Anwesha","year":"2022","unstructured":"Anwesha Das, Daniel Ratner, and Alex Aiken. 2022. Performance variability and causality in complex systems. In 2022 IEEE International Conference on Autonomic Computing and Self-Organizing Systems Companion (ACSOS-C). IEEE, 19-24."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2013.148"},{"key":"e_1_3_2_1_15_1","volume-title":"Slides from Linux Kongress","author":"De Melo Arnaldo Carvalho","unstructured":"Arnaldo Carvalho De Melo. 2010. The new linux'perf'tools. In Slides from Linux Kongress, Vol. 18. 1-42."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3570609"},{"key":"e_1_3_2_1_17_1","volume-title":"Proceedings of the ACM Symposium on Cloud Computing. 1-13","author":"Dean Daniel J","year":"2014","unstructured":"Daniel J Dean, Hiep Nguyen, Xiaohui Gu, Hui Zhang, Junghwan Rhee, Nipun Arora, and Geoff Jiang. 2014. Perfscope: Practical online server performance bug inference in production cloud computing infrastructures. In Proceedings of the ACM Symposium on Cloud Computing. 1-13."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/2499368.2451125"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/2644865.2541941"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/263580.263597"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3358960.3379124"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/1111583.1111594"},{"key":"e_1_3_2_1_23_1","volume-title":"GNU gprof. GNU Binutils. Available online: http:\/\/www. gnu.org\/software\/binutils (accessed on","author":"Fenlason Jay","year":"2018","unstructured":"Jay Fenlason and Richard Stallman. 1988. GNU gprof. GNU Binutils. Available online: http:\/\/www. gnu.org\/software\/binutils (accessed on 21 April 2018) (1988)."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/PDCAT.2011.18"},{"key":"e_1_3_2_1_25_1","volume-title":"AMD and VIA CPUs: An optimization guide for assembly programmers and compiler makers","author":"Fog Agner","unstructured":"Agner Fog. 2023. The microarchitecture of Intel, AMD and VIA CPUs: An optimization guide for assembly programmers and compiler makers. Copenhagen University College of Engineering. https:\/\/www.agner.org\/optimize\/microarchitecture.pdf"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1007\/11859802_7"},{"key":"e_1_3_2_1_27_1","volume-title":"complexity, and predictability in computer performance. arXiv preprint arXiv:1305.5408 (5","author":"Garland Joshua","year":"2013","unstructured":"Joshua Garland, Ryan James, and Elizabeth Bradley. 2013. Determinism, complexity, and predictability in computer performance. arXiv preprint arXiv:1305.5408 (5 2013). https:\/\/arxiv.org\/pdf\/1305.5408.pdf"},{"key":"e_1_3_2_1_28_1","unstructured":"gcc. [n.d.]. OMP_PROC_BINDING. https:\/\/gcc.gnu.org\/onlinedocs\/libgomp\/OMP_005fPROC_005fBIND.html"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"crossref","first-page":"776","DOI":"10.15837\/ijccc.2016.6.2554","article-title":"Lossless Compression of Data Tables in Mobile Devices by Using Co-clustering","volume":"11","author":"Han Bo","year":"2016","unstructured":"Bo Han and Bolang Li. 2016. Lossless Compression of Data Tables in Mobile Devices by Using Co-clustering. International Journal of Computers Communications & Control, Vol. 11, 6 (2016), 776-788.","journal-title":"International Journal of Computers Communications & Control"},{"key":"e_1_3_2_1_30_1","volume-title":"Proceedings of the 33rd ACM International Conference on the Foundations of Software Engineering. 400-410","author":"Henning S\u00f6ren","year":"2025","unstructured":"S\u00f6ren Henning, Adriano Vogel, Esteban Perez-Wohlfeil, Otmar Ertl, and Rick Rabiser. 2025. When Should I Run My Application Benchmark? Studying Cloud Performance Variability for the Case of Stream Processing Applications. In Proceedings of the 33rd ACM International Conference on the Foundations of Software Engineering. 400-410."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/1712605.1712640"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/2807591.2807644"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/2904111.2904113"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01316-z"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613165"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/2541883.2541894"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/1281700.1281702"},{"key":"e_1_3_2_1_38_1","volume-title":"Multi-Server Benchmarking for Latency-Critical Workloads. arXiv preprint arXiv:2505.03600","author":"Li Zhilin","year":"2025","unstructured":"Zhilin Li, Lucia Pons, Salvador Petit, Julio Sahuquillo, and Julio Pons. 2025. TailBench: Flexible Multi-Client, Multi-Server Benchmarking for Latency-Critical Workloads. arXiv preprint arXiv:2505.03600 (2025)."},{"key":"e_1_3_2_1_39_1","unstructured":"Tsung-Yi Lin Priya Goyal Ross Girshick Kaiming He and Piotr Doll\u00e1r. 2018. Focal Loss for Dense Object Detection. arXiv:1708.02002 [cs.CV] https:\/\/arxiv.org\/abs\/1708.02002"},{"key":"e_1_3_2_1_40_1","unstructured":"Linux. [n.d.]. Numactl Linux Man Page. https:\/\/linux.die.net\/man\/8\/numactl"},{"key":"e_1_3_2_1_41_1","first-page":"109","volume-title":"16th USENIX Symposium on Operating Systems Design and Implementation (OSDI 22)","author":"Lou Chang","year":"2022","unstructured":"Chang Lou, Cong Chen, Peng Huang, Yingnong Dang, Si Qin, Xinsheng Yang, Xukun Li, Qingwei Lin, and Murali Chintalapati. 2022. : a holistic service for dealing with memory leaks in production cloud infrastructure. In 16th USENIX Symposium on Operating Systems Design and Implementation (OSDI 22). 109-125."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3208104"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/CCGRID.2017.11"},{"key":"e_1_3_2_1_44_1","volume-title":"13th USENIX Symposium on Operating Systems Design and Implementation (OSDI). USENIX, 409-425","author":"Maricq Aleksander","year":"2018","unstructured":"Aleksander Maricq, Dmitry Duplyakin, Ivo Jimenez, Carlos Maltzahn, Ryan Stutsman, and Robert Ricci. 2018. Taming performance variability. In 13th USENIX Symposium on Operating Systems Design and Implementation (OSDI). USENIX, 409-425. https:\/\/www.usenix.org\/conference\/osdi18\/presentation\/maricq"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3319647.3325839"},{"key":"e_1_3_2_1_46_1","volume-title":"SHARP: A Distribution-Based Framework for Reproducible Performance Evaluation. In 2024 IEEE International Symposium on Workload Characterization (IISWC). IEEE, 82-93","author":"Mittal Viyom","year":"2024","unstructured":"Viyom Mittal, Pedro Bruel, Michalis Faloutsos, Dejan Milojicic, and Eitan Frachtenberg. 2024. SHARP: A Distribution-Based Framework for Reproducible Performance Evaluation. In 2024 IEEE International Symposium on Workload Characterization (IISWC). IEEE, 82-93."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/CCGrid57682.2023.00029"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS53621.2022.00040"},{"key":"e_1_3_2_1_49_1","unstructured":"Travis E Oliphant et al. 2006. Guide to numpy. Vol. 1. Trelgol Publishing USA."},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2019.2927908"},{"key":"e_1_3_2_1_51_1","volume-title":"Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems","author":"Paszke Adam","year":"2019","unstructured":"Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, et al., 2019. Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems, Vol. 32 (2019)."},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/3295500.3356217"},{"key":"e_1_3_2_1_53_1","unstructured":"Nikhila Ravi Valentin Gabeur Yuan-Ting Hu Ronghang Hu Chaitanya Ryali Tengyu Ma Haitham Khedr Roman R\u00e4dle Chloe Rolland Laura Gustafson et al. 2024. Sam 2: Segment anything in images and videos. arXiv preprint arXiv:2408.00714 (2024)."},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA45697.2020.00045"},{"key":"e_1_3_2_1_55_1","volume-title":"VTune performance analyzer essentials","author":"Reinders James","unstructured":"James Reinders. 2005. VTune performance analyzer essentials. Vol. 9. Intel Press Santa Clara."},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"crossref","first-page":"14978","DOI":"10.1007\/s11227-024-06040-w","article-title":"Analysis and prediction of performance variability in large-scale computing systems","volume":"80","author":"Beni Majid Salimi","year":"2024","unstructured":"Majid Salimi Beni, Sascha Hunold, and Biagio Cosenza. 2024. Analysis and prediction of performance variability in large-scale computing systems. The Journal of Supercomputing, Vol. 80, 10 (2024), 14978-15005.","journal-title":"The Journal of Supercomputing"},{"key":"e_1_3_2_1_57_1","unstructured":"Joel Scheuner. 2022. Performance Evaluation of Serverless Applications and Infrastructures. Ph.D. Dissertation."},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1002\/cpe.4692"},{"key":"e_1_3_2_1_59_1","unstructured":"Stability AI. 2025. Text-to-image generation using Stable Diffusion XL (stabilityai\/stable-diffusion-xl-base-1.0) with thermal management interventions on NVIDIA A100 GPU. https:\/\/huggingface.co\/stabilityai\/stable-diffusion-xl-base-1.0. Accessed: 2025-08-19."},{"key":"e_1_3_2_1_60_1","first-page":"27","article-title":"Parboil: A revised benchmark suite for scientific and commercial throughput computing","volume":"127","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 Wen-mei W Hwu. 2012. Parboil: A revised benchmark suite for scientific and commercial throughput computing. Center for Reliable and High-Performance Computing, Vol. 127 (2012), 27.","journal-title":"Center for Reliable and High-Performance Computing"},{"key":"e_1_3_2_1_61_1","volume-title":"Proceedings of the 23rd ACM SIGPLAN symposium on principles and practice of parallel programming. 124-136","author":"Tang Xiongchao","year":"2018","unstructured":"Xiongchao Tang, Jidong Zhai, Xuehai Qian, Bingsheng He, Wei Xue, and Wenguang Chen. 2018. Vsensor: Leveraging fixed-workload snippets of programs for performance variance detection. In Proceedings of the 23rd ACM SIGPLAN symposium on principles and practice of parallel programming. 124-136."},{"key":"e_1_3_2_1_62_1","volume-title":"High Performance Computing: 32nd International Conference, ISC High Performance. Springer, 355-373","author":"Tuncer Ozan","year":"2017","unstructured":"Ozan Tuncer, Emre Ates, Yijia Zhang, Ata Turk, Jim Brandt, Vitus J Leung, Manuel Egele, and Ayse K Coskun. 2017. Diagnosing performance variations in HPC applications using machine learning. In High Performance Computing: 32nd International Conference, ISC High Performance. Springer, 355-373. https:\/\/www.bu.edu\/peaclab\/files\/2020\/01\/isc.pdf"},{"key":"e_1_3_2_1_63_1","volume-title":"symposium on networked systems design and implementation (NSDI). ACM, 513-527","author":"Uta Alexandru","year":"2020","unstructured":"Alexandru Uta, Alexandru Custura, Dmitry Duplyakin, Ivo Jimenez, Jan Rellermeyer, Carlos Maltzahn, Robert Ricci, and Alexandru Iosup. 2020. Is big data performance reproducible in modern cloud networks?. In symposium on networked systems design and implementation (NSDI). ACM, 513-527. https:\/\/www.usenix.org\/system\/files\/nsdi20-paper-uta.pdf"},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1145\/379539.379590"},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1145\/2038642.2038650"},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.14778\/3523210.3523221"},{"key":"e_1_3_2_1_67_1","unstructured":"xapian.org. 2025. Xapian project. https:\/\/github.com\/xapian\/xapian. Accessed: 2025-08-19."},{"key":"e_1_3_2_1_68_1","doi-asserted-by":"publisher","DOI":"10.1093\/jrsssc\/qlae001"},{"key":"e_1_3_2_1_69_1","doi-asserted-by":"publisher","DOI":"10.1145\/3127479.3131614"},{"key":"e_1_3_2_1_70_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC41406.2024.00063"},{"key":"e_1_3_2_1_71_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2022.3181799"},{"key":"e_1_3_2_1_72_1","doi-asserted-by":"publisher","DOI":"10.1145\/34447545.3451182"},{"key":"e_1_3_2_1_73_1","volume-title":"Proceedings of the 27th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming. 150-162","author":"Zheng Liyan","year":"2022","unstructured":"Liyan Zheng, Jidong Zhai, Xiongchao Tang, Haojie Wang, Teng Yu, Yuyang Jin, Shuaiwen Leon Song, and Wenguang Chen. 2022. Vapro: Performance variance detection and diagnosis for production-run parallel applications. In Proceedings of the 27th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming. 150-162."}],"event":{"name":"ICPE '26: 17th ACM\/SPEC International Conference on Performance Engineering","location":"Florence Italy","sponsor":["SIGSOFT ACM Special Interest Group on Software Engineering","SIGMETRICS ACM Special Interest Group on Measurement and Evaluation","SPEC"]},"container-title":["Proceedings of the 17th ACM\/SPEC International Conference on Performance Engineering"],"original-title":[],"deposited":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T12:29:23Z","timestamp":1776947363000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3777884.3796994"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,3]]},"references-count":73,"alternative-id":["10.1145\/3777884.3796994","10.1145\/3777884"],"URL":"https:\/\/doi.org\/10.1145\/3777884.3796994","relation":{},"subject":[],"published":{"date-parts":[[2026,5,3]]},"assertion":[{"value":"2026-05-03","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}