{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:16:37Z","timestamp":1750220197808,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":37,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,5,17]],"date-time":"2022-05-17T00:00:00Z","timestamp":1652745600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"U.S. Office of the Under Secretary of Defense for Research and Engineering (OUSD(R&E))","award":["FA8750-15-2-0119"],"award-info":[{"award-number":["FA8750-15-2-0119"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,5,17]]},"DOI":"10.1145\/3528416.3530251","type":"proceedings-article","created":{"date-parts":[[2022,5,5]],"date-time":"2022-05-05T02:16:59Z","timestamp":1651717019000},"page":"244-250","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["Towards neural architecture-aware exploration of compiler optimizations in a deep learning {graph} compiler"],"prefix":"10.1145","author":[{"given":"Gaurav","family":"Verma","sequence":"first","affiliation":[{"name":"Stony Brook University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Swetang","family":"Finviya","sequence":"additional","affiliation":[{"name":"Stony Brook University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Abid M.","family":"Malik","sequence":"additional","affiliation":[{"name":"Brookhaven National Laboratory"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Murali","family":"Emani","sequence":"additional","affiliation":[{"name":"Argonne National Laboratory"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Barbara","family":"Chapman","sequence":"additional","affiliation":[{"name":"Stony Brook University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2022,5,17]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Deep learning using rectified linear units (relu). arXiv preprint arXiv","author":"Agarap Abien Fred","year":"1803","unstructured":"Abien Fred Agarap. 2018. Deep learning using rectified linear units (relu). arXiv preprint arXiv: 1803.08375 (2018)."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"crossref","unstructured":"Amir Hossein Ashouri Andrea Bignoli Gianluca Palermo and Cristina Silvano. 2016. Predictive modeling methodology for compiler phase-ordering. In Proceedings of the 7th Workshop on Parallel Programming and Run-Time Management Techniques for Many-core Architectures and the 5th Workshop on Design Tools and Architectures For Multicore Embedded Computing Platforms. 7--12.","DOI":"10.1145\/2872421.2872424"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3124452"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3197978"},{"key":"e_1_3_2_1_5_1","unstructured":"Tianqi Chen Thierry Moreau Ziheng Jiang Lianmin Zheng Eddie Yan Haichen Shen Meghan Cowan Leyuan Wang Yuwei Hu Luis Ceze et al. 2018. {TVM}: An automated end-to-end optimizing compiler for deep learning. In 13th {USENIX} Symposium on Operating Systems Design and Implementation ({OSDI} 18). 578--594."},{"key":"e_1_3_2_1_6_1","unstructured":"Standard Performance Evaluation Corporation. 1995--2022. SPECint95 Benchmark Suite. Retrieved 20220208 from https:\/\/www.spec.org\/cpu95\/CINT95\/index.html"},{"key":"e_1_3_2_1_7_1","volume-title":"Performant Compiler Optimization Environments for AI Research. arXiv.2109.08267","author":"Cummins Chris","year":"2021","unstructured":"Chris Cummins, Bram Wasti, Jiadong Guo, Brandon Cui, Jason Ansel, Sahir Gomez, Somya Jain, Jia Liu, Olivier Teytaud, Benoit Steiner, Yuandong Tian, and Hugh Leather. 2021. CompilerGym: Robust, Performant Compiler Optimization Environments for AI Research. arXiv.2109.08267 (2021)."},{"key":"e_1_3_2_1_8_1","unstructured":"Scott Cyphers Arjun K Bansal Anahita Bhiwandiwalla Jayaram Bobba Matthew Brookhart Avijit Chakraborty Will Constable Christian Convey Leona Cook Omar Kanawi et al. 2018. Intel ngraph: An intermediate representation compiler and executor for deep learning. arXiv preprint arXiv 1801.08058 (2018)."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_2_1_10_1","volume-title":"Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805","author":"Devlin Jacob","year":"2018","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/1880043.1880047"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3207719.3207727"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/1062261.1062293"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/FCCM.2019.00049"},{"key":"e_1_3_2_1_16_1","volume-title":"2nd International Workshop on GCC Research Opportunities (GROW'10)","author":"Huang Yuanjie","year":"2010","unstructured":"Yuanjie Huang, Liang Peng, Chengyong Wu, Yuriy Kashnikov, J\u00f6rn Rennecke, and Grigori Fursin. 2010. Transforming GCC into a research-friendly environment: plugins for optimization tuning and reordering, function cloning and program instrumentation. In 2nd International Workshop on GCC Research Opportunities (GROW'10)."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.5555\/2555729.2555736"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3458744.3473355"},{"key":"e_1_3_2_1_19_1","unstructured":"Alex Krizhevsky Geoffrey Hinton et al. 2009. Learning multiple layers of features from tiny images. (2009)."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/1509864.1509865"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/2883614"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CEC.2014.6900634"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CINTI.2013.6705166"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/2764967.2764978"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/2980930.2907959"},{"key":"e_1_3_2_1_28_1","volume-title":"Compiler phase ordering as an orthogonal approach for reducing energy consumption. arXiv preprint arXiv","author":"Nobre Ricardo","year":"1807","unstructured":"Ricardo Nobre, Lu\u00eds Reis, and Joao MP Cardoso. 2018. Compiler phase ordering as an orthogonal approach for reducing energy consumption. arXiv preprint arXiv 1807.00638 (2018)."},{"key":"e_1_3_2_1_29_1","unstructured":"NVIDIA. v2021.2.2.0. Nsight Compute Command Line Profiler. Retrieved 20220208 from https:\/\/docs.nvidia.com\/nsight-compute\/NsightComputeCli\/index.html"},{"key":"e_1_3_2_1_30_1","unstructured":"NVIDIA. v2021.3.2.4. NVIDIA Nsight Systems. Retrieved 20220208 from https:\/\/docs.nvidia.com\/nsight-systems\/"},{"key":"e_1_3_2_1_31_1","unstructured":"NVIDIA. v8.0.1. TensorRT. https:\/\/developer.nvidia.com\/tensorrt"},{"key":"e_1_3_2_1_32_1","volume-title":"Know what you don't know: Unanswerable questions for SQuAD. arXiv preprint arXiv","author":"Rajpurkar Pranav","year":"1806","unstructured":"Pranav Rajpurkar, Robin Jia, and Percy Liang. 2018. Know what you don't know: Unanswerable questions for SQuAD. arXiv preprint arXiv 1806.03822 (2018)."},{"key":"e_1_3_2_1_33_1","volume-title":"Glow: Graph lowering compiler techniques for neural networks. arXiv preprint arXiv","author":"Rotem Nadav","year":"2018","unstructured":"Nadav Rotem, Jordan Fix, Saleem Abdulrasool, Garret Catron, Summer Deng, Roman Dzhabarov, Nick Gibson, James Hegeman, Meghan Lele, Roman Levenstein, et al. 2018. Glow: Graph lowering compiler techniques for neural networks. arXiv preprint arXiv 1805.00907 (2018)."},{"key":"e_1_3_2_1_34_1","volume-title":"XLA : Compiling Machine Learning for Peak Performance.","author":"Sabne Amit","year":"2020","unstructured":"Amit Sabne. 2020. XLA : Compiling Machine Learning for Peak Performance."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"e_1_3_2_1_36_1","volume-title":"Attention is all you need. Advances in neural information processing systems 30","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW52791.2021.00128"}],"event":{"name":"CF '22: 19th ACM International Conference on Computing Frontiers","sponsor":["SIGMICRO ACM Special Interest Group on Microarchitectural Research and Processing"],"location":"Turin Italy","acronym":"CF '22"},"container-title":["Proceedings of the 19th ACM International Conference on Computing Frontiers"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3528416.3530251","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3528416.3530251","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:02:42Z","timestamp":1750186962000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3528416.3530251"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,17]]},"references-count":37,"alternative-id":["10.1145\/3528416.3530251","10.1145\/3528416"],"URL":"https:\/\/doi.org\/10.1145\/3528416.3530251","relation":{},"subject":[],"published":{"date-parts":[[2022,5,17]]},"assertion":[{"value":"2022-05-17","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}