{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,27]],"date-time":"2026-02-27T03:48:13Z","timestamp":1772164093893,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":89,"publisher":"ACM","license":[{"start":{"date-parts":[[2018,3,19]],"date-time":"2018-03-19T00:00:00Z","timestamp":1521417600000},"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-1533560,CCF-1453853"],"award-info":[{"award-number":["CCF-1533560,CCF-1453853"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2018,3,19]]},"DOI":"10.1145\/3173162.3173181","type":"proceedings-article","created":{"date-parts":[[2018,3,22]],"date-time":"2018-03-22T11:15:40Z","timestamp":1521717340000},"page":"432-447","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":15,"title":["Unconventional Parallelization of Nondeterministic Applications"],"prefix":"10.1145","author":[{"given":"Enrico A.","family":"Deiana","sequence":"first","affiliation":[{"name":"Northwestern University, Evanston, IL, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vincent","family":"St-Amour","sequence":"additional","affiliation":[{"name":"Northwestern University, Evanston, IL, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peter A.","family":"Dinda","sequence":"additional","affiliation":[{"name":"Northwestern University, Evanston, IL, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nikos","family":"Hardavellas","sequence":"additional","affiliation":[{"name":"Northwestern University, Evanston, IL, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Simone","family":"Campanoni","sequence":"additional","affiliation":[{"name":"Northwestern University, Evanston, IL, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2018,3,19]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/1669112.1669131"},{"key":"e_1_3_2_1_2_1","volume-title":"Perfect Pipelining: A New Loop Parallelization Technique European Symposium on Programming (ESOP).","author":"Aiken Alexander","year":"1988"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"crossref","unstructured":"Riad Akram Mohammad Mejbah Ul Alam and Abdullah Muzahid. 2016. Approximate Lock: Trading off Accuracy for Performance by Skipping Critical Sections International Symposium on Software Reliability Engineering (ISSRE).  Riad Akram Mohammad Mejbah Ul Alam and Abdullah Muzahid. 2016. Approximate Lock: Trading off Accuracy for Performance by Skipping Critical Sections International Symposium on Software Reliability Engineering (ISSRE).","DOI":"10.1109\/ISSRE.2016.49"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/1274971.1275011"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/1542476.1542481"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/2628071.2628092"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"crossref","unstructured":"Jason Ansel Yee Lok Wong Cy Chan Marek Olszewski Alan Edelman and Saman Amarasinghe. 2011. Language and Compiler Support for Auto-tuning Variable-accuracy Algorithms Code Generation and Optimization (CGO).   Jason Ansel Yee Lok Wong Cy Chan Marek Olszewski Alan Edelman and Saman Amarasinghe. 2011. Language and Compiler Support for Auto-tuning Variable-accuracy Algorithms Code Generation and Optimization (CGO).","DOI":"10.1109\/CGO.2011.5764677"},{"key":"e_1_3_2_1_8_1","unstructured":"Christian Bienia. 2011. Benchmarking Modern Multiprocessors. Ph.D. Dissertation. bibinfoschoolPrinceton University.   Christian Bienia. 2011. Benchmarking Modern Multiprocessors. Ph.D. Dissertation. bibinfoschoolPrinceton University."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/1454115.1454128"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/263580.263662"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/1854273.1854350"},{"key":"e_1_3_2_1_12_1","unstructured":"Shekhar Borkar Robert Cohn George Cox Sha Gleason Thomas Gross H. T. Kung Monica Lam Brian Moore Craig Peterson John Pieper Linda Rankin P. S. Tseng Jim Sutton John Urbanski and Jon Webb. 1988. iWarp: An Integrated Solution to High-Speed Parallel Computing International Conference on Supercomputing (ICS).   Shekhar Borkar Robert Cohn George Cox Sha Gleason Thomas Gross H. T. Kung Monica Lam Brian Moore Craig Peterson John Pieper Linda Rankin P. S. Tseng Jim Sutton John Urbanski and Jon Webb. 1988. iWarp: An Integrated Solution to High-Speed Parallel Computing International Conference on Supercomputing (ICS)."},{"key":"e_1_3_2_1_13_1","unstructured":"Gary Bradski and Adrian Kaehler. 2008. Learning OpenCV: Computer vision with the OpenCV library. \"O'Reilly Media Inc.\".  Gary Bradski and Adrian Kaehler. 2008. Learning OpenCV: Computer vision with the OpenCV library. \"O'Reilly Media Inc.\"."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/192724.192750"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.5555\/2665671.2665705"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"crossref","unstructured":"Simone Campanoni Glenn Holloway Gu-Yeon Wei and David Brooks. 2015. HELIX-UP: Relaxing Program Semantics to Unleash Parallelization Code Generation and Optimization (CGO).   Simone Campanoni Glenn Holloway Gu-Yeon Wei and David Brooks. 2015. HELIX-UP: Relaxing Program Semantics to Unleash Parallelization Code Generation and Optimization (CGO).","DOI":"10.1109\/CGO.2015.7054203"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/2259016.2259028"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"crossref","volume-title":"HELIX: Making the Extraction of Thread-Level Parallelism Mainstream International Symposium on Microarchitecture (MICRO).","author":"Campanoni S.","DOI":"10.1145\/2259016.2259028"},{"key":"e_1_3_2_1_19_1","unstructured":"Shawn D. Casey. 2011. How to Determine the Effectiveness of Hyper-Threading Technology with an Application. https:\/\/goo.gl\/ycuL6E. (2011). Accessed: 2018-01--14.  Shawn D. Casey. 2011. How to Determine the Effectiveness of Hyper-Threading Technology with an Application. https:\/\/goo.gl\/ycuL6E. (2011). Accessed: 2018-01--14."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2009.34"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/71.503771"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/71.770138"},{"key":"e_1_3_2_1_23_1","volume-title":"Project Adam: Building an Efficient and Scalable Deep Learning Training System. Operating Systems Design and Implementation (OSDI).","author":"Chilimbi Trishul M","year":"2014"},{"key":"e_1_3_2_1_24_1","volume-title":"Active Harmony: Towards Automated Performance Tuning Supercomputing Conference (SC).","author":"Tuapucs Cristian"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/115372.115320"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/99.660313"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.1979.4766909"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/318789.318807"},{"key":"e_1_3_2_1_29_1","unstructured":"Matthias Felleisen Robert Bruce Findler Matthew Flatt Shriram Krishnamurthi Eli Barzilay Jay McCarthy and Sam Tobin-Hochstadt. 2015. The Racket Manifesto. In Summit on Advances in Programming Languages (SNAPL).  Matthias Felleisen Robert Bruce Findler Matthew Flatt Shriram Krishnamurthi Eli Barzilay Jay McCarthy and Sam Tobin-Hochstadt. 2015. The Racket Manifesto. In Summit on Advances in Programming Languages (SNAPL)."},{"key":"e_1_3_2_1_30_1","volume-title":"International Symposium on Microarchitecture (MICRO).","author":"Frigo Matteo"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/291069.291058"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/277830.277840"},{"key":"e_1_3_2_1_33_1","volume-title":"Haswell: The fourth-generation intel core processor International Symposium on Microarchitecture (MICRO).","author":"Hammarlund P.","year":"2014"},{"key":"e_1_3_2_1_34_1","volume-title":"The Stanford Hydra CMP. In International Symposium on Microarchitecture (MICRO).","author":"Hammond Lance","year":"2000"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/1772954.1772975"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2011.108"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/1950365.1950390"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/1772954.1772973"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"crossref","unstructured":"A.R. Hurson Joford T. LimKrishna M. and KaviBen Lee. 1997. Parallelization of DOALL and DOACROSS Loops - A Survey Advances in Computers.  A.R. Hurson Joford T. LimKrishna M. and KaviBen Lee. 1997. Parallelization of DOALL and DOACROSS Loops - A Survey Advances in Computers.","DOI":"10.1016\/S0065-2458(08)60706-8"},{"key":"e_1_3_2_1_40_1","volume-title":"Optimizing Sparse Matrix Computations for Register Reuse in SPARSITY International Conference on Computational Sciences (ICCS).","author":"Im Eun-Jin"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2012.12"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/1229428.1229474"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/CGO.2009.18"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1002\/cpe.1844"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/2259016.2259029"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/1250734.1250759"},{"key":"e_1_3_2_1_47_1","volume-title":"LLVM: A compilation framework for lifelong program analysis & transformation Code Generation and Optimization (CGO).","author":"Lattner Chris","year":"2004"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"crossref","unstructured":"Hung Q Le GL Guthrie DE Williams Maged M Michael BG Frey William J Starke Cathy May Rei Odaira and Takuya Nakaike. 2015. Transactional memory support in the IBM POWER8 processor IBM Journal of Research and Development.  Hung Q Le GL Guthrie DE Williams Maged M Michael BG Frey William J Starke Cathy May Rei Odaira and Takuya Nakaike. 2015. Transactional memory support in the IBM POWER8 processor IBM Journal of Research and Development.","DOI":"10.1147\/JRD.2014.2380199"},{"key":"e_1_3_2_1_49_1","volume-title":"Thread and Memory Placement on NUMA Systems: Asymmetry Matters. USENIX Annual Technical Conference (USENIX ATC).","author":"Lepers Baptiste","year":"2015"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/1629395.1629407"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/1122971.1122997"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/181181.181265"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1145\/1542476.1542495"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2009.5160991"},{"key":"e_1_3_2_1_55_1","unstructured":"Jiayuan Meng Anand Raghunathan Srimat T. Chakradhar and Surendra Byna. 2010. Exploiting the forgiving nature of applications for scalable parallel execution International Symposium on Parallel and Distributed Processing (IPDPS).  Jiayuan Meng Anand Raghunathan Srimat T. Chakradhar and Surendra Byna. 2010. Exploiting the forgiving nature of applications for scalable parallel execution International Symposium on Parallel and Distributed Processing (IPDPS)."},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1145\/2465787.2465790"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1145\/1806799.1806808"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2005.13"},{"key":"e_1_3_2_1_59_1","article-title":"Intel Threading Building Blocks. In","author":"Pheatt Chuck","year":"2008","journal-title":"J. Comput. Sci. Coll."},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1145\/2451116.2451162"},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1145\/2628071.2628077"},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1145\/1993498.1993501"},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1145\/1736020.1736030"},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1145\/1356058.1356074"},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1145\/2414729.2414737"},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.1145\/1297027.1297055"},{"key":"e_1_3_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2013.6522341"},{"key":"e_1_3_2_1_68_1","doi-asserted-by":"publisher","DOI":"10.1145\/2540708.2540711"},{"key":"e_1_3_2_1_69_1","doi-asserted-by":"publisher","DOI":"10.1145\/980152.980156"},{"key":"e_1_3_2_1_70_1","doi-asserted-by":"publisher","DOI":"10.1145\/237090.237144"},{"key":"e_1_3_2_1_71_1","doi-asserted-by":"publisher","DOI":"10.1145\/2025113.2025133"},{"key":"e_1_3_2_1_72_1","doi-asserted-by":"publisher","DOI":"10.1145\/223982.224451"},{"key":"e_1_3_2_1_73_1","unstructured":"Sharanyan Srikanthan Sandhya Dwarkadas and Kai Shen. 2015. Data Sharing or Resource Contention: Toward Performance Transparency on Multicore Systems USENIX Annual Technical Conference (USENIX ATC).   Sharanyan Srikanthan Sandhya Dwarkadas and Kai Shen. 2015. Data Sharing or Resource Contention: Toward Performance Transparency on Multicore Systems USENIX Annual Technical Conference (USENIX ATC)."},{"key":"e_1_3_2_1_74_1","unstructured":"Sharanyan Srikanthan Sandhya Dwarkadas and Kai Shen. 2016. Coherence stalls or latency tolerance: informed CPU scheduling for socket and core sharing USENIX Annual Technical Conference (USENIX ATC).   Sharanyan Srikanthan Sandhya Dwarkadas and Kai Shen. 2016. Coherence stalls or latency tolerance: informed CPU scheduling for socket and core sharing USENIX Annual Technical Conference (USENIX ATC)."},{"key":"e_1_3_2_1_75_1","unstructured":"J. Steffan and T Mowry. 1998. The Potential for Using Thread-Level Data Speculation to Facilitate Automatic Parallelization. In High-Performance Computer Architecture (HPCA).   J. Steffan and T Mowry. 1998. The Potential for Using Thread-Level Data Speculation to Facilitate Automatic Parallelization. In High-Performance Computer Architecture (HPCA)."},{"key":"e_1_3_2_1_76_1","doi-asserted-by":"publisher","DOI":"10.1145\/1082469.1082471"},{"key":"e_1_3_2_1_77_1","doi-asserted-by":"crossref","unstructured":"John E. Stone David Gohara and Guochun Shi. 2010. OpenCL: A Parallel Programming Standard for Heterogeneous Computing Systems IEEE Des. Test.  John E. Stone David Gohara and Guochun Shi. 2010. OpenCL: A Parallel Programming Standard for Heterogeneous Computing Systems IEEE Des. Test.","DOI":"10.1109\/MCSE.2010.69"},{"key":"e_1_3_2_1_78_1","doi-asserted-by":"publisher","DOI":"10.1145\/2872362.2872402"},{"key":"e_1_3_2_1_79_1","doi-asserted-by":"publisher","DOI":"10.1145\/1542476.1542496"},{"key":"e_1_3_2_1_80_1","doi-asserted-by":"publisher","DOI":"10.1145\/1993498.1993555"},{"key":"e_1_3_2_1_81_1","unstructured":"Antonio Valles M Gillespie and G Drysdale. 2009. Performance Insights to Intel\u00ae Hyper-Threading Technology. http:\/\/software.intel.com\/en-us\/articles\/performance-insights-to-intel-hyper-threading-technology. (2009). Accessed: 2017-07-01.  Antonio Valles M Gillespie and G Drysdale. 2009. Performance Insights to Intel\u00ae Hyper-Threading Technology. http:\/\/software.intel.com\/en-us\/articles\/performance-insights-to-intel-hyper-threading-technology. (2009). Accessed: 2017-07-01."},{"key":"e_1_3_2_1_82_1","doi-asserted-by":"publisher","DOI":"10.1145\/2660193.2660227"},{"key":"e_1_3_2_1_83_1","doi-asserted-by":"publisher","DOI":"10.1109\/CGO.2009.33"},{"key":"e_1_3_2_1_84_1","doi-asserted-by":"publisher","DOI":"10.1145\/1542275.1542302"},{"key":"e_1_3_2_1_85_1","volume-title":"On-Chip Interconnection Architecture of the Tile Processor International Symposium on Microarchitecture (MICRO).","author":"Wentzlaff David","year":"2007"},{"key":"e_1_3_2_1_86_1","volume-title":"Automatically Tuned Linear Algebra Software. In Supercomputing Conference (SC).","author":"Clint Whaley R."},{"key":"e_1_3_2_1_87_1","doi-asserted-by":"publisher","DOI":"10.1109\/71.926166"},{"key":"e_1_3_2_1_88_1","doi-asserted-by":"publisher","DOI":"10.1145\/1369396.1369399"},{"key":"e_1_3_2_1_89_1","doi-asserted-by":"crossref","unstructured":"Hongtao Zhong Mojtaba Mehrara Steven A. Lieberman and Scott A. Mahlke. 2008. Uncovering hidden loop level parallelism in sequential applications High-Performance Computer Architecture (HPCA).  Hongtao Zhong Mojtaba Mehrara Steven A. Lieberman and Scott A. Mahlke. 2008. Uncovering hidden loop level parallelism in sequential applications High-Performance Computer Architecture (HPCA).","DOI":"10.1109\/HPCA.2008.4658647"}],"event":{"name":"ASPLOS '18: Architectural Support for Programming Languages and Operating Systems","location":"Williamsburg VA USA","acronym":"ASPLOS '18","sponsor":["SIGPLAN ACM Special Interest Group on Programming Languages","SIGOPS ACM Special Interest Group on Operating Systems","SIGARCH ACM Special Interest Group on Computer Architecture","SIGBED ACM Special Interest Group on Embedded Systems"]},"container-title":["Proceedings of the Twenty-Third International Conference on Architectural Support for Programming Languages and Operating Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3173162.3173181","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3173162.3173181","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3173162.3173181","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T23:02:50Z","timestamp":1750201370000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3173162.3173181"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,3,19]]},"references-count":89,"alternative-id":["10.1145\/3173162.3173181","10.1145\/3173162"],"URL":"https:\/\/doi.org\/10.1145\/3173162.3173181","relation":{"is-identical-to":[{"id-type":"doi","id":"10.1145\/3296957.3173181","asserted-by":"object"}]},"subject":[],"published":{"date-parts":[[2018,3,19]]},"assertion":[{"value":"2018-03-19","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}