{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T05:12:14Z","timestamp":1783746734260,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":40,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T00:00:00Z","timestamp":1783900800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["2211315"],"award-info":[{"award-number":["2211315"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["2119069"],"award-info":[{"award-number":["2119069"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["2211508"],"award-info":[{"award-number":["2211508"]}],"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":[[2026,7,13]]},"DOI":"10.1145\/3806645.3807578","type":"proceedings-article","created":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T04:21:11Z","timestamp":1783743671000},"page":"98-111","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Enabling Floating Point Virtualization With Tiny Numbers"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-1429-6217","authenticated-orcid":false,"given":"Kevin","family":"Hayes","sequence":"first","affiliation":[{"name":"Northwestern University, Evanston, Illinois, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5315-5987","authenticated-orcid":false,"given":"Peter","family":"Dinda","sequence":"additional","affiliation":[{"name":"Northwestern University, Evanston, Illinois, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,13]]},"reference":[{"key":"e_1_3_3_2_2_2","unstructured":"Capstone: The ultimate disassembler 2021."},{"key":"e_1_3_3_2_3_2","doi-asserted-by":"crossref","unstructured":"Arnold M.\u00a0G. Bailey T.\u00a0A. Cowles J.\u00a0R. and Cupal J.\u00a0J. Redundant logarithmic arithmetic. IEEE Transactions on Computers 39 8 (Aug. 1990) 1077\u20131086.","DOI":"10.1109\/12.57046"},{"key":"e_1_3_3_2_4_2","unstructured":"Bailey D. Barszcz E. Barton J. Browning D. Carter R. Dagum L. Fatoohi R. Fineberg S. Frederickson P. Lasinksi T. Schreiber R. Simon H. Venkatakrishnan V. and Weeratunga S. The nas parallel benchmarks (nas 1). Tech. Rep. RNR-94-007 NASA March 1994."},{"key":"e_1_3_3_2_5_2","unstructured":"Bellard F. Libbf: The tiny big float library. Available at https:\/\/bellard.org\/libbf\/ 2017."},{"key":"e_1_3_3_2_6_2","doi-asserted-by":"crossref","unstructured":"Boehm H.-J. Towards an api for the real numbers. In Proceedings of the 41st ACM SIGPLAN Conference on Programming Language Design and Implementation (PLDI) (June 2020).","DOI":"10.1145\/3385412.3386037"},{"key":"e_1_3_3_2_7_2","doi-asserted-by":"crossref","unstructured":"Bryan G.\u00a0L. Norman M.\u00a0L. O\u2019Shea B.\u00a0W. Abel T. Wise J.\u00a0H. Turk M.\u00a0J. Reynolds D.\u00a0R. Collins D.\u00a0C. Wang P. Skillman S.\u00a0W. Smith B. Harkness R.\u00a0P. Bordner J. Kim J.-h. Kuhlen M. Xu H. Goldbaum N. Hummels C. Kritsuk A.\u00a0G. Tasker E. Skory S. Simpson C.\u00a0M. Hahn O. Oishi J.\u00a0S. So G.\u00a0C. Zhao F. Cen R. Li Y. and The Enzo Collaboration. ENZO: An Adaptive Mesh Refinement Code for Astrophysics. The Astrophysical Journal 211 2 (March 2014) 19.","DOI":"10.1088\/0067-0049\/211\/2\/19"},{"key":"e_1_3_3_2_8_2","unstructured":"Cherkaev A. The secret life of a nan. https:\/\/anniecherkaev.com\/the-secret-life-of-nan March 2018."},{"key":"e_1_3_3_2_9_2","doi-asserted-by":"crossref","unstructured":"Courbet C. Nsan: A floating-point numerical sanitizer. In Proceedings of the 30th ACM SIGPLAN International Conference on Compiler Construction (CC) (March 2021).","DOI":"10.1145\/3446804.3446848"},{"key":"e_1_3_3_2_10_2","doi-asserted-by":"crossref","unstructured":"Dettmers T. Pagnoni A. Holtzman A. and Zettlemoyer L. Qlora: efficient finetuning of quantized llms. In Proceedings of the 37th International Conference on Neural Information Processing Systems (NIPS 2023) (2023).","DOI":"10.52202\/075280-0441"},{"key":"e_1_3_3_2_11_2","doi-asserted-by":"crossref","unstructured":"Devaney R.An Introduction to Chaotic Dynamical Systems. 10 2021.","DOI":"10.1201\/9780429280801"},{"key":"e_1_3_3_2_12_2","unstructured":"Developers L.\u00a0K. Linux kernel documentation: Livepatch."},{"key":"e_1_3_3_2_13_2","unstructured":"Developers L.\u00a0K. Linux kernel documentation: preempt_notifier_register."},{"key":"e_1_3_3_2_14_2","doi-asserted-by":"crossref","unstructured":"Dinda P. Wanninger N. Ma J. Bernat A. Bernat C. Ghosh S. Kraemer C. and Elmasry Y. FPVM: Towards a floating point virtual machine. In Proceedings of the 31st ACM Symposium on High-performance Parallel and Distributed Computing (HPDC) (June 2022).","DOI":"10.1145\/3502181.3531469"},{"key":"e_1_3_3_2_15_2","doi-asserted-by":"crossref","unstructured":"Fousse L. Hanrot G. Lef\u00e8vre V. P\u00e9lissier P. and Zimmermann P. Mpfr: A multiple-precision binary floating-point library with correct rounding. ACM Transactions on Mathematical Software (TOMS) 33 2 (June 2007).","DOI":"10.1145\/1236463.1236468"},{"key":"e_1_3_3_2_16_2","unstructured":"Gustafson J.The End of Error: Unum Computing. Chapman and Hall\/CRC 2015."},{"key":"e_1_3_3_2_17_2","unstructured":"Hallsby K. Strand L. Wanninger N. Dhiantravan N. and Dinda P. Architecture-independent floating point spying and an architecture for floating point spying. Tech. Rep. NWU-CS-2025-27 Department of Computer Science Northwestern University July 2025."},{"key":"e_1_3_3_2_18_2","doi-asserted-by":"crossref","unstructured":"Hickey T. Ju Q. and Van\u00a0Emden M.\u00a0H. Interval arithmetic: From principles to implementation. Journal of the ACM 48 5 (Sept. 2001) 1038\u20131068.","DOI":"10.1145\/502102.502106"},{"key":"e_1_3_3_2_19_2","doi-asserted-by":"publisher","unstructured":"Hoerold F. Ivanov I.\u00a0R. Dhruv A. Moses W.\u00a0S. Dubey A. Wahib M. and Domke J. Raptor: Practical numerical profiling of scientific applications. arXiv:https:\/\/arXiv.org\/abs\/2507.04647v2 September 2025. v1 is July 2025; DOI is 10.48550\/arXiv.2507.04647.","DOI":"10.48550\/arXiv.2507.04647"},{"key":"e_1_3_3_2_20_2","doi-asserted-by":"crossref","unstructured":"Hoerold F. Ivanov I.\u00a0R. Dhruv A. Moses W.\u00a0S. Dubey A. Wahib M. and Domke J. Raptor: Practical numerical profiling of scientific applications. In Proceedings of the International Conference on High Performance Computing Networking Storage and Analysis (SC 2025) (November 2025). To Appear.","DOI":"10.1145\/3712285.3759810"},{"key":"e_1_3_3_2_21_2","unstructured":"IEEE Floating Point Working Group. IEEE standard for binary floating-point arithmetic. ANSI\/IEEE Std 754-1985 (1985)."},{"key":"e_1_3_3_2_22_2","unstructured":"IEEE Floating Point Working Group. IEEE standard for floating-point arithmetic. IEEE Std 754-2008 (Aug 2008) 1\u201370."},{"key":"e_1_3_3_2_23_2","unstructured":"IEEE Floating Point Working Group. IEEE standard for floating-point arithmetic. IEEE Std 754-2019 (Revision of IEEE 754-2008) (July 2019) 1\u201384."},{"key":"e_1_3_3_2_24_2","unstructured":"Jin H. Frumkin M. and Yan J. The open mp implementation of nas parallel benchmarks and its performance (nas 3). Tech. Rep. NAS-99-011 NASA March 1999. OpenMP 3.0 version available at https:\/\/github.com\/benchmark-subsetting\/NPB3.0-omp-C."},{"key":"e_1_3_3_2_25_2","doi-asserted-by":"crossref","unstructured":"Jost T. Durand Y. Fabre C. Cohen A. and P\u00e9trot F. Vp float: First class treatment for variable precision floating point arithmetic. In Proceedings of the ACM International Conference on Parallel Architectures and Compilation Techniques (PACT) (September 2020).","DOI":"10.1145\/3410463.3414660"},{"key":"e_1_3_3_2_26_2","doi-asserted-by":"crossref","unstructured":"Jost T.\u00a0T. Durand Y. Fabre C. Cohen A. and P\u00e9rrot F. Seamless compiler integration of variable precision floating-point arithmetic. In 2021 IEEE\/ACM International Symposium on Code Generation and Optimization (CGO) (February-March 2021).","DOI":"10.1109\/CGO51591.2021.9370331"},{"key":"e_1_3_3_2_27_2","unstructured":"Kahan W. A critique of john l. gustafson\u2019s the end of error\u2014unum computation and his a radical approach to computation with real numbers. In Proceedings of the 23rd IEEE Symposium on Computer Arithmetic (ARITH) (July 2016)."},{"key":"e_1_3_3_2_28_2","unstructured":"Kalamkar D. Mudigere D. Mellempudi N. Das D. Banerjee K. Avancha S. Vooturi D.\u00a0T. Jammalamadaka N. Huang J. Yuen H. Yang J. Park J. Heinecke A. Georganas E. Srinivasan S. Kundu A. Smelyanskiy M. Kaul B. and Kundu P.\u00a0D. A study of BFLOAT16 for deep learning training. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1905.12322 May 2019."},{"key":"e_1_3_3_2_29_2","unstructured":"CVE-2018-3665. Available from RedHat CVE-ID CVE-2018-3665. June\u00a012 2018."},{"key":"e_1_3_3_2_30_2","unstructured":"x86\/fpu: Finish excising \u2019eagerfpu\u2019. Commit to the Linux kernel."},{"key":"e_1_3_3_2_31_2","doi-asserted-by":"crossref","unstructured":"Matula D.\u00a0W. and Kornerup P. Finite precision rational arithmetic: Slash number systems. IEEE Transactions on Computers C-34 1 (Jan 1985) 3\u201318.","DOI":"10.1109\/TC.1985.1676511"},{"key":"e_1_3_3_2_32_2","unstructured":"Micikevicius P. Stosic D. Burgess N. Cornea M. Dubey P. Grisenthwaite R. Ha S. Heinecke A. Judd P. Kamalu J. Mellempudi N. Oberman S. Shoeybi M. Siu M. and Wu H. Fp8 formats for deep learning 2022."},{"key":"e_1_3_3_2_33_2","doi-asserted-by":"crossref","unstructured":"Moon F.\u00a0C.Chaotic and Fractal Dynamics: An Introduction for Applied Scientists and Engineers. John Wiley and Sons Inc. 1992.","DOI":"10.1002\/9783527617500"},{"key":"e_1_3_3_2_34_2","unstructured":"Omni OpenMP Compiler Group University of Versailles Saint Quentin en Yvlines. Nas parallel benchmarks 3.0\u2014unofficial openmp c version. https:\/\/github.com\/benchmark-subsetting\/NPB3.0-omp-C 2014."},{"key":"e_1_3_3_2_35_2","doi-asserted-by":"crossref","unstructured":"Popek G. and Goldberg R. Formal requirements for virtualizable third generation architectures. Communications of the ACM (July 1974) 413\u2013421.","DOI":"10.1145\/361011.361073"},{"key":"e_1_3_3_2_36_2","doi-asserted-by":"crossref","unstructured":"Rubio-Gonz\u00e1lez C. Nguyen C. Nguyen H.\u00a0D. Demmel J. Kahan W. Sen K. Bailey D.\u00a0H. Iancu C. and Hough D. Precimonious: Tuning assistant for floating-point precision. In Proceedings of the International Conference on High Performance Computing Networking Storage and Analysis (Supercomputing) (2013).","DOI":"10.1145\/2503210.2503296"},{"key":"e_1_3_3_2_37_2","unstructured":"Walker J. Fbench: Floating point benchmarks. https:\/\/www.fourmilab.ch\/fbench\/ September 2021."},{"key":"e_1_3_3_2_38_2","unstructured":"Walker J. Ffbench: Fast fourier transform benchmark. https:\/\/www.fourmilab.ch\/fbench\/ffbench.html January 2025."},{"key":"e_1_3_3_2_39_2","doi-asserted-by":"crossref","unstructured":"Wanninger N. Dhiantravan N. and Dinda P. Virtualization so light it floats!: Accelerating floating point virtualization. In Proceedings of the 34th ACM Symposium on High-performance Parallel and Distributed Computing (HPDC) (July 2025).","DOI":"10.1145\/3731545.3731584"},{"key":"e_1_3_3_2_40_2","unstructured":"Wingo A. Value representation in javascript implementations. http:\/\/wingolog.org\/archives\/2011\/05\/18\/value-representation-in-javascript-implementations May 2011."},{"key":"e_1_3_3_2_41_2","doi-asserted-by":"crossref","unstructured":"Zhu F. Gong R. Yu F. Liu X. Wang Y. Li Z. Yang X. and Yan J. Towards unified int8 training for convolutional neural network. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2020) (June 2020).","DOI":"10.1109\/CVPR42600.2020.00204"}],"event":{"name":"HPDC '26: 35th International Symposium on High-Performance Parallel and Distributed Computing","location":"Cleveland USA","acronym":"HPDC '26","sponsor":["SIGHPC ACM Special Interest Group on High Performance Computing, Special Interest Group on High Performance Computing","SIGARCH ACM Special Interest Group on Computer Architecture"]},"container-title":["Proceedings of the 35th International Symposium on High-Performance Parallel and Distributed Computing"],"original-title":[],"deposited":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T04:22:21Z","timestamp":1783743741000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3806645.3807578"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,13]]},"references-count":40,"alternative-id":["10.1145\/3806645.3807578","10.1145\/3806645"],"URL":"https:\/\/doi.org\/10.1145\/3806645.3807578","relation":{},"subject":[],"published":{"date-parts":[[2026,7,13]]},"assertion":[{"value":"2026-07-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}