{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,27]],"date-time":"2026-06-27T03:48:18Z","timestamp":1782532098609,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":57,"publisher":"ACM","license":[{"start":{"date-parts":[[2020,8,17]],"date-time":"2020-08-17T00:00:00Z","timestamp":1597622400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2020,8,17]]},"DOI":"10.1145\/3404397.3404470","type":"proceedings-article","created":{"date-parts":[[2020,8,9]],"date-time":"2020-08-09T03:54:26Z","timestamp":1596945266000},"page":"1-11","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["Vector Forward Mode Automatic Differentiation on SIMD\/SIMT architectures"],"prefix":"10.1145","author":[{"given":"Jan","family":"H\u00fcckelheim","sequence":"first","affiliation":[{"name":"Argonne National Laboratory"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michel","family":"Schanen","sequence":"additional","affiliation":[{"name":"Argonne National Laboratory"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sri Hari Krishna","family":"Narayanan","sequence":"additional","affiliation":[{"name":"Argonne National Laboratory"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Paul","family":"Hovland","sequence":"additional","affiliation":[{"name":"Argonne National Laboratory"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2020,8,17]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"TensorFlow: A System for Large-Scale Machine Learning. In 12th USENIX Symposium on Operating Systems Design and Implementation (OSDI 16)","author":"Abadi Mart\u00edn","year":"2016"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2005.25"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1137\/0915020"},{"key":"e_1_3_2_1_4_1","first-page":"1","article-title":"Automatic differentiation in machine learning: a survey","volume":"18","author":"Baydin Atilim\u00a0Gunes","year":"2018","journal-title":"Journal of Marchine Learning Research"},{"key":"e_1_3_2_1_5_1","volume-title":"Effective Extensible Programming: Unleashing Julia on GPUs","author":"Besard Tim","year":"2018"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1155\/1992\/717832"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/109025.109067"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/99.537089"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"crossref","unstructured":"C. Bischof T. Knauff Jr. L. Green and K. Haigler. 1994. Parallel calculation of sensitivity derivatives for aircraft design using automatic differentiation. https:\/\/doi.org\/10.2514\/6.1994-4261  C. Bischof T. Knauff Jr. L. Green and K. Haigler. 1994. Parallel calculation of sensitivity derivatives for aircraft design using automatic differentiation. https:\/\/doi.org\/10.2514\/6.1994-4261","DOI":"10.2514\/6.1994-4261"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/377792.377842"},{"key":"e_1_3_2_1_11_1","unstructured":"Tianqi Chen Bing Xu Chiyuan Zhang and Carlos Guestrin. 2016. Training deep nets with sublinear memory cost. arXiv preprint arXiv:1604.06174(2016).  Tianqi Chen Bing Xu Chiyuan Zhang and Carlos Guestrin. 2016. Training deep nets with sublinear memory cost. arXiv preprint arXiv:1604.06174(2016)."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1137\/0720013"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2014.07.003"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1137\/120873558"},{"key":"e_1_3_2_1_16_1","series-title":"SIAM review 47, 4","volume-title":"What color is your Jacobian? Graph coloring for computing derivatives","author":"Gebremedhin Assefaw\u00a0Hadish","year":"2005"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/293686.293695"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"crossref","volume-title":"Recomputations in Reverse Mode AD","author":"Giering Ralf","DOI":"10.1007\/978-1-4613-0075-5_33"},{"key":"e_1_3_2_1_19_1","volume-title":"Recent Advances in Algorithmic Differentiation","author":"Giering Ralf"},{"key":"e_1_3_2_1_20_1","unstructured":"Michael Giles. 2007. LIBOR testcase. https:\/\/people.maths.ox.ac.uk\/gilesm\/codes\/libor_AD\/.  Michael Giles. 2007. LIBOR testcase. https:\/\/people.maths.ox.ac.uk\/gilesm\/codes\/libor_AD\/."},{"key":"e_1_3_2_1_21_1","unstructured":"Michael Giles and Paul Glasserman. 2005. Smoking Adjoints: fast evaluation of Greeks in Monte Carlo Calculations.  Michael Giles and Paul Glasserman. 2005. Smoking Adjoints: fast evaluation of Greeks in Monte Carlo Calculations."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.21314\/JCF.1999.037"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cpc.2015.10.027"},{"key":"e_1_3_2_1_25_1","volume-title":"Achieving logarithmic growth of temporal and spatial complexity in reverse automatic differentiation. Optimization Methods and software 1, 1","author":"Griewank Andreas","year":"1992"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/229473.229474"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/347837.347846"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"crossref","unstructured":"Andreas Griewank and Andrea Walther. 2008. Evaluating derivatives: principles and techniques of algorithmic differentiation. Vol.\u00a0105. Siam.  Andreas Griewank and Andrea Walther. 2008. Evaluating derivatives: principles and techniques of algorithmic differentiation. Vol.\u00a0105. Siam.","DOI":"10.1137\/1.9780898717761"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.5555\/1455489"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.5555\/1149000.1708228"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/2450153.2450158"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-19861-8_13"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/PICA.2001.932367"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/2560359"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3225058.3225138"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1080\/10556788.2018.1435654"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3337821.3337906"},{"key":"e_1_3_2_1_39_1","volume-title":"Checkmate: Breaking the Memory Wall with Optimal Tensor Rematerialization. arXiv preprint arXiv:1910.02653(2019).","author":"Jain Paras","year":"2019"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1002\/widm.1305"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1002\/fld.885"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"crossref","unstructured":"Uwe Naumann. 2012. The art of differentiating computer programs: an introduction to algorithmic differentiation. Vol.\u00a024. SIAM.  Uwe Naumann. 2012. The art of differentiating computer programs: an introduction to algorithmic differentiation. Vol.\u00a024. SIAM.","DOI":"10.1137\/1.9781611972078"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1007\/11428831_42"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"crossref","volume-title":"Numerical computing with IEEE floating point arithmetic","author":"Overton M.L.","DOI":"10.1137\/1.9780898718072"},{"key":"e_1_3_2_1_45_1","unstructured":"Adam Paszke Sam Gross Soumith Chintala Gregory Chanan Edward Yang Zachary DeVito Zeming Lin Alban Desmaison Luca Antiga and Adam Lerer. 2017. Automatic differentiation in PyTorch. (2017).  Adam Paszke Sam Gross Soumith Chintala Gregory Chanan Edward Yang Zachary DeVito Zeming Lin Alban Desmaison Luca Antiga and Adam Lerer. 2017. Automatic differentiation in PyTorch. (2017)."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1137\/15M1044679"},{"key":"e_1_3_2_1_47_1","unstructured":"Christopher Rackauckas Yingbo Ma Vaibhav Dixit Xingjian Guo Mike Innes Jarrett Revels Joakim Nyberg and Vijay Ivaturi. 2018. A comparison of automatic differentiation and continuous sensitivity analysis for derivatives of differential equation solutions. arXiv preprint arXiv:1812.01892(2018).  Christopher Rackauckas Yingbo Ma Vaibhav Dixit Xingjian Guo Mike Innes Jarrett Revels Joakim Nyberg and Vijay Ivaturi. 2018. A comparison of automatic differentiation and continuous sensitivity analysis for derivatives of differential equation solutions. arXiv preprint arXiv:1812.01892(2018)."},{"key":"e_1_3_2_1_48_1","unstructured":"Jarrett Revels Tim Besard Valentin Churavy Bjorn\u00a0De Sutter and Juan\u00a0Pablo Vielma. 2018. Dynamic Automatic Differentiation of GPU Broadcast Kernels. arxiv:1810.08297\u00a0[cs.MS]  Jarrett Revels Tim Besard Valentin Churavy Bjorn\u00a0De Sutter and Juan\u00a0Pablo Vielma. 2018. Dynamic Automatic Differentiation of GPU Broadcast Kernels. arxiv:1810.08297\u00a0[cs.MS]"},{"key":"e_1_3_2_1_49_1","unstructured":"J. Revels M. Lubin and T. Papamarkou. 2016. Forward-Mode Automatic Differentiation in Julia. arXiv:1607.07892 [cs.MS](2016). https:\/\/arxiv.org\/abs\/1607.07892  J. Revels M. Lubin and T. Papamarkou. 2016. Forward-Mode Automatic Differentiation in Julia. arXiv:1607.07892 [cs.MS](2016). https:\/\/arxiv.org\/abs\/1607.07892"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.3402\/tellusa.v45i5.15060"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-22750-0_19"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1080\/10556788.2018.1435651"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cpc.2010.06.043"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cpc.2005.01.011"},{"key":"e_1_3_2_1_55_1","volume-title":"Parboil: A revised benchmark suite for scientific and commercial throughput computing","author":"Stratton A","year":"2012"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2009.5161165"},{"key":"e_1_3_2_1_57_1","volume-title":"On the implementation of an interior-point filter line-search algorithm for large-scale nonlinear programming. Mathematical programming 106, 1","author":"W\u00e4chter Andreas","year":"2006"},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRS.2007.901301"},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1002\/fld.3844"},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1145\/3295500.3356210"}],"event":{"name":"ICPP '20: 49th International Conference on Parallel Processing","location":"Edmonton AB Canada","acronym":"ICPP '20"},"container-title":["49th International Conference on Parallel Processing - ICPP"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3404397.3404470","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3404397.3404470","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T22:38:59Z","timestamp":1750199939000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3404397.3404470"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,8,17]]},"references-count":57,"alternative-id":["10.1145\/3404397.3404470","10.1145\/3404397"],"URL":"https:\/\/doi.org\/10.1145\/3404397.3404470","relation":{},"subject":[],"published":{"date-parts":[[2020,8,17]]},"assertion":[{"value":"2020-08-17","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}