{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T16:11:52Z","timestamp":1776442312766,"version":"3.51.2"},"publisher-location":"New York, NY, USA","reference-count":57,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,8,12]],"date-time":"2024-08-12T00:00:00Z","timestamp":1723420800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100000015","name":"DOE U.S. Department of Energy","doi-asserted-by":"publisher","award":["17-SC-20-SC"],"award-info":[{"award-number":["17-SC-20-SC"]}],"id":[{"id":"10.13039\/100000015","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,8,12]]},"DOI":"10.1145\/3673038.3673046","type":"proceedings-article","created":{"date-parts":[[2024,8,8]],"date-time":"2024-08-08T18:29:01Z","timestamp":1723141741000},"page":"576-586","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["BrickDL: Graph-Level Optimizations for DNNs with Fine-Grained Data Blocking on GPUs"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6813-0536","authenticated-orcid":false,"given":"Mahesh","family":"Lakshminarasimhan","sequence":"first","affiliation":[{"name":"University of Utah, United States of America"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3058-7573","authenticated-orcid":false,"given":"Mary","family":"Hall","sequence":"additional","affiliation":[{"name":"University of Utah, United States of America"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8327-5717","authenticated-orcid":false,"given":"Samuel","family":"Williams","sequence":"additional","affiliation":[{"name":"Lawrence Berkeley National Laboratory, United States of America"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4596-0289","authenticated-orcid":false,"given":"Oscar","family":"Antepara","sequence":"additional","affiliation":[{"name":"Lawrence Berkeley National Laboratory, United States of America"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,8,12]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"2023. NVIDIA TensorRT SDK. https:\/\/developer.nvidia.com\/tensorrt"},{"key":"e_1_3_2_1_2_1","unstructured":"2023. PyTorch TorchScript. https:\/\/pytorch.org\/docs\/stable\/jit.html"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2016.7783725"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1155\/2009\/382638"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/2686745.2686749"},{"key":"e_1_3_2_1_6_1","volume-title":"13th USENIX Symposium on Operating Systems Design and Implementation (OSDI 18)","author":"Chen Tianqi","year":"2018","unstructured":"Tianqi Chen, Thierry Moreau, Ziheng Jiang, Lianmin Zheng, Eddie Yan, Haichen Shen, Meghan Cowan, Leyuan Wang, Yuwei Hu, Luis Ceze, 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\u2013594."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3087556.3087586"},{"key":"e_1_3_2_1_8_1","series-title":"SIAM review 51, 1","volume-title":"Optimization and performance modeling of stencil computations on modern microprocessors","author":"Datta Kaushik","year":"2009","unstructured":"Kaushik Datta, Shoaib Kamil, Samuel Williams, Leonid Oliker, John Shalf, and Katherine Yelick. 2009. Optimization and performance modeling of stencil computations on modern microprocessors. SIAM review 51, 1 (2009), 129\u2013159."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2008.5222004"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3575693.3575702"},{"key":"e_1_3_2_1_11_1","volume-title":"Proceedings of Machine Learning and Systems, A.\u00a0Smola, A.\u00a0Dimakis, and I.\u00a0Stoica (Eds.). Vol.\u00a03. 167\u2013180","author":"Ding Yaoyao","year":"2021","unstructured":"Yaoyao Ding, Ligeng Zhu, Zhihao Jia, Gennady Pekhimenko, and Song Han. 2021. IOS: Inter-Operator Scheduler for CNN Acceleration. In Proceedings of Machine Learning and Systems, A.\u00a0Smola, A.\u00a0Dimakis, and I.\u00a0Stoica (Eds.). Vol.\u00a03. 167\u2013180."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2019.00031"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/1088149.1088197"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3582016.3582018"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2017.373"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.3990527"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/12.40842"},{"key":"e_1_3_2_1_19_1","volume-title":"A strategy for high performance in computational fluid dynamics","author":"Jayaraj Jagan","unstructured":"Jagan Jayaraj. 2013. A strategy for high performance in computational fluid dynamics. University of Minnesota."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3341301.3359630"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/1178597.1178605"},{"key":"e_1_3_2_1_22_1","volume-title":"Exascale Deep Learning for Climate Analytics. In SC18: International Conference for High Performance Computing, Networking, Storage and Analysis. IEEE, 649\u2013660","author":"Kurth Thorsten","year":"2018","unstructured":"Thorsten Kurth, Sean Treichler, Joshua Romero, Mayur Mudigonda, Nathan Luehr, Everett Phillips, Ankur Mahesh, Michael Matheson, Jack Deslippe, Massimiliano Fatica, 2018. Exascale Deep Learning for Climate Analytics. In SC18: International Conference for High Performance Computing, Networking, Storage and Analysis. IEEE, 649\u2013660."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CGO51591.2021.9370308"},{"key":"e_1_3_2_1_24_1","volume-title":"14th USENIX Symposium on Operating Systems Design and Implementation (OSDI 20)","author":"Ma Lingxiao","year":"2020","unstructured":"Lingxiao Ma, Zhiqiang Xie, Zhi Yang, Jilong Xue, Youshan Miao, Wei Cui, Wenxiang Hu, Fan Yang, Lintao Zhang, and Lidong Zhou. 2020. Rammer: Enabling holistic deep learning compiler optimizations with { rTasks}. In 14th USENIX Symposium on Operating Systems Design and Implementation (OSDI 20). 881\u2013897."},{"key":"e_1_3_2_1_25_1","unstructured":"John McCalpin and David Wonnacott. 1998. Time skewing: A value-based approach to optimizing for memory locality. Technical Report. Rutgers University."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2010.2"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3453483.3454083"},{"key":"e_1_3_2_1_28_1","volume-title":"Yolov3: An incremental improvement. arXiv preprint arXiv:1804.02767","author":"Redmon Joseph","year":"2018","unstructured":"Joseph Redmon and Ali Farhadi. 2018. Yolov3: An incremental improvement. arXiv preprint arXiv:1804.02767 (2018)."},{"key":"e_1_3_2_1_29_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. (2020)."},{"key":"e_1_3_2_1_30_1","volume-title":"Maximizing Performance Through Memory Hierarchy-Driven Data Layout Transformations. In 2022 IEEE\/ACM Workshop on Memory Centric High Performance Computing (MCHPC). IEEE, 1\u201310","author":"Sepanski Benjamin","year":"2022","unstructured":"Benjamin Sepanski, Tuowen Zhao, Hans Johansen, and Samuel Williams. 2022. Maximizing Performance Through Memory Hierarchy-Driven Data Layout Transformations. In 2022 IEEE\/ACM Workshop on Memory Centric High Performance Computing (MCHPC). IEEE, 1\u201310."},{"key":"e_1_3_2_1_31_1","first-page":"208","article-title":"Nimble: Efficiently compiling dynamic neural networks for model inference","volume":"3","author":"Shen Haichen","year":"2021","unstructured":"Haichen Shen, Jared Roesch, Zhi Chen, Wei Chen, Yong Wu, Mu Li, Vin Sharma, Zachary Tatlock, and Yida Wang. 2021. Nimble: Efficiently compiling dynamic neural networks for model inference. Proceedings of Machine Learning and Systems 3 (2021), 208\u2013222.","journal-title":"Proceedings of Machine Learning and Systems"},{"key":"e_1_3_2_1_32_1","volume-title":"Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556","author":"Simonyan Karen","year":"2014","unstructured":"Karen Simonyan and Andrew Zisserman. 2014. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11231"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3519939.3523448"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/2688500.2688514"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3315508.3329973"},{"key":"e_1_3_2_1_37_1","volume-title":"15th USENIX Symposium on Operating Systems Design and Implementation (OSDI 21)","author":"Wang Haojie","year":"2021","unstructured":"Haojie Wang, Jidong Zhai, Mingyu Gao, Zixuan Ma, Shizhi Tang, Liyan Zheng, Yuanzhi Li, Kaiyuan Rong, Yuanyong Chen, and Zhihao Jia. 2021. { PET} : Optimizing tensor programs with partially equivalent transformations and automated corrections. In 15th USENIX Symposium on Operating Systems Design and Implementation (OSDI 21). 37\u201354."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/COMPSAC.2009.82"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2012.85"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/1128022.1128027"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1007\/BF01407876"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2000.845979"},{"key":"e_1_3_2_1_43_1","first-page":"204","article-title":"Bolt: Bridging the gap between auto-tuners and hardware-native performance","volume":"4","author":"Xing Jiarong","year":"2022","unstructured":"Jiarong Xing, Leyuan Wang, Shang Zhang, Jack Chen, Ang Chen, and Yibo Zhu. 2022. Bolt: Bridging the gap between auto-tuners and hardware-native performance. Proceedings of Machine Learning and Systems 4 (2022), 204\u2013216.","journal-title":"Proceedings of Machine Learning and Systems"},{"key":"e_1_3_2_1_44_1","unstructured":"Bing Xu Ying Zhang Hao Lu Yang Chen Terry Chen Mike Iovine Mu-Chu Lee and Zhijing Li. 2022. AITemplate. https:\/\/github.com\/facebookincubator\/AITemplate"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3497776.3517766"},{"key":"e_1_3_2_1_46_1","first-page":"255","article-title":"Equality saturation for tensor graph superoptimization","volume":"3","author":"Yang Yichen","year":"2021","unstructured":"Yichen Yang, Phitchaya Phothilimthana, Yisu Wang, Max Willsey, Sudip Roy, and Jacques Pienaar. 2021. Equality saturation for tensor graph superoptimization. Proceedings of Machine Learning and Systems 3 (2021), 255\u2013268.","journal-title":"Proceedings of Machine Learning and Systems"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/WOLFHPC.2016.08"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.75"},{"key":"e_1_3_2_1_49_1","first-page":"1","article-title":"Apollo: Automatic partition-based operator fusion through layer by layer optimization","volume":"4","author":"Zhao Jie","year":"2022","unstructured":"Jie Zhao, Xiong Gao, Ruijie Xia, Zhaochuang Zhang, Deshi Chen, Lei Chen, Renwei Zhang, Zhen Geng, Bin Cheng, and Xuefeng Jin. 2022. Apollo: Automatic partition-based operator fusion through layer by layer optimization. Proceedings of Machine Learning and Systems 4 (2022), 1\u201319.","journal-title":"Proceedings of Machine Learning and Systems"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/3295500.3356210"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/3437801.3441598"},{"key":"e_1_3_2_1_52_1","volume-title":"Delivering Performance-portable Stencil Computations on CPUs and GPUs Using Bricks. In 2018 IEEE\/ACM International Workshop on Performance, Portability and Productivity in HPC (P3HPC). IEEE, 59\u201370","author":"Zhao Tuowen","year":"2018","unstructured":"Tuowen Zhao, Samuel Williams, Mary Hall, and Hans Johansen. 2018. Delivering Performance-portable Stencil Computations on CPUs and GPUs Using Bricks. In 2018 IEEE\/ACM International Workshop on Performance, Portability and Productivity in HPC (P3HPC). IEEE, 59\u201370."},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2018.2858384"},{"key":"e_1_3_2_1_54_1","volume-title":"Ansor: Generating High-Performance Tensor Programs for Deep Learning. In 14th USENIX symposium on operating systems design and implementation (OSDI 20)","author":"Zheng Lianmin","year":"2020","unstructured":"Lianmin Zheng, Chengfan Jia, Minmin Sun, Zhao Wu, Cody\u00a0Hao Yu, Ameer Haj-Ali, Yida Wang, Jun Yang, Danyang Zhuo, Koushik Sen, 2020. Ansor: Generating High-Performance Tensor Programs for Deep Learning. In 14th USENIX symposium on operating systems design and implementation (OSDI 20). 863\u2013879."},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1145\/3373376.3378508"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503222.3507723"},{"key":"e_1_3_2_1_57_1","volume-title":"16th USENIX Symposium on Operating Systems Design and Implementation (OSDI 22)","author":"Zhu Hongyu","year":"2022","unstructured":"Hongyu Zhu, Ruofan Wu, Yijia Diao, Shanbin Ke, Haoyu Li, Chen Zhang, Jilong Xue, Lingxiao Ma, Yuqing Xia, Wei Cui, 2022. { ROLLER} : Fast and efficient tensor compilation for deep learning. In 16th USENIX Symposium on Operating Systems Design and Implementation (OSDI 22). 233\u2013248."}],"event":{"name":"ICPP '24: the 53rd International Conference on Parallel Processing","location":"Gotland Sweden","acronym":"ICPP '24"},"container-title":["Proceedings of the 53rd International Conference on Parallel Processing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3673038.3673046","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/abs\/10.1145\/3673038.3673046","content-type":"text\/html","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3673038.3673046","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3673038.3673046","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,23]],"date-time":"2025-09-23T17:30:41Z","timestamp":1758648641000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3673038.3673046"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,12]]},"references-count":57,"alternative-id":["10.1145\/3673038.3673046","10.1145\/3673038"],"URL":"https:\/\/doi.org\/10.1145\/3673038.3673046","relation":{},"subject":[],"published":{"date-parts":[[2024,8,12]]},"assertion":[{"value":"2024-08-12","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}