{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,26]],"date-time":"2026-04-26T14:33:33Z","timestamp":1777214013582,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":50,"publisher":"ACM","license":[{"start":{"date-parts":[[2020,3,9]],"date-time":"2020-03-09T00:00:00Z","timestamp":1583712000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Stanford SystemX"},{"name":"DSSoC DARPA grant"},{"name":"Stanford AHA affiliates program"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2020,3,9]]},"DOI":"10.1145\/3373376.3378514","type":"proceedings-article","created":{"date-parts":[[2020,3,13]],"date-time":"2020-03-13T22:37:01Z","timestamp":1584139021000},"page":"369-383","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":188,"title":["Interstellar"],"prefix":"10.1145","author":[{"given":"Xuan","family":"Yang","sequence":"first","affiliation":[{"name":"Stanford University, Stanford, CA, USA"}]},{"given":"Mingyu","family":"Gao","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}]},{"given":"Qiaoyi","family":"Liu","sequence":"additional","affiliation":[{"name":"Stanford University, Stanford, CA, USA"}]},{"given":"Jeff","family":"Setter","sequence":"additional","affiliation":[{"name":"Stanford University, Stanford, CA, USA"}]},{"given":"Jing","family":"Pu","sequence":"additional","affiliation":[{"name":"Stanford University, Stanford, CA, USA"}]},{"given":"Ankita","family":"Nayak","sequence":"additional","affiliation":[{"name":"Stanford University, Stanford, CA, China"}]},{"given":"Steven","family":"Bell","sequence":"additional","affiliation":[{"name":"Stanford University, Stanford, CA, USA"}]},{"given":"Kaidi","family":"Cao","sequence":"additional","affiliation":[{"name":"Stanford University, Stanford, CA, USA"}]},{"given":"Heonjae","family":"Ha","sequence":"additional","affiliation":[{"name":"Stanford University, Stanford, CA, USA"}]},{"given":"Priyanka","family":"Raina","sequence":"additional","affiliation":[{"name":"Stanford University, Stanford, CA, USA"}]},{"given":"Christos","family":"Kozyrakis","sequence":"additional","affiliation":[{"name":"Stanford University, Google, Stanford, CA, USA"}]},{"given":"Mark","family":"Horowitz","sequence":"additional","affiliation":[{"name":"Stanford University, Stanford, CA, USA"}]}],"member":"320","published-online":{"date-parts":[[2020,3,13]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"ARM ML Processor. https:\/\/developer.arm.com\/products\/processors\/machine-learning\/arm-ml-processor\/.  ARM ML Processor. https:\/\/developer.arm.com\/products\/processors\/machine-learning\/arm-ml-processor\/."},{"key":"e_1_3_2_1_2_1","unstructured":"NVDLA. http:\/\/nvdla.org\/.  NVDLA. http:\/\/nvdla.org\/."},{"key":"e_1_3_2_1_3_1","unstructured":"Tensilica customizable processor IP. http:\/\/ip.cadence.com\/ipportfolio\/tensilica-ip.  Tensilica customizable processor IP. http:\/\/ip.cadence.com\/ipportfolio\/tensilica-ip."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2016.11"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.5555\/3195638.3195664"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/2541940.2541967"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/JETCAS.2019.2910232"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2016.40"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC.2016.7418007"},{"key":"e_1_3_2_1_10_1","first-page":"609","volume-title":"47th Annual ACM\/IEEE International Symposium on Microarchitecture (MICRO)","author":"Chen Yunji","year":"2014","unstructured":"Yunji Chen , Tao Luo , Shaoli Liu , Shijin Zhang , Liqiang He , Jia Wang , Ling Li , Tianshi Chen , Zhiwei Xu , Ninghui Sun , and Olivier Temam . DaDianNao : A machine-learning supercomputer . In 47th Annual ACM\/IEEE International Symposium on Microarchitecture (MICRO) , pages 609 -- 622 , 2014 . Yunji Chen, Tao Luo, Shaoli Liu, Shijin Zhang, Liqiang He, Jia Wang, Ling Li, Tianshi Chen, Zhiwei Xu, Ninghui Sun, and Olivier Temam. DaDianNao: A machine-learning supercomputer. In 47th Annual ACM\/IEEE International Symposium on Microarchitecture (MICRO), pages 609--622, 2014."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2016.13"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/2749469.2750389"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2011.5981829"},{"key":"e_1_3_2_1_14_1","volume-title":"22nd ACM International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS)","author":"Gao Mingyu","year":"2017","unstructured":"Mingyu Gao , Jing Pu , Xuan Yang , Mark Horowitz , and Christos Kozyrakis . TETRIS : Scalable and efficient neural network acceleration with 3D memory . In 22nd ACM International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS) , 2017 . Mingyu Gao, Jing Pu, Xuan Yang, Mark Horowitz, and Christos Kozyrakis. TETRIS: Scalable and efficient neural network acceleration with 3D memory. In 22nd ACM International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS), 2017."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3297858.3304014"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2014.106"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2016.30"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.2006.18.7.1527"},{"key":"e_1_3_2_1_19_1","volume-title":"Mobilenets: Efficient convolutional neural networks for mobile vision applications. CoRR, abs\/1704.04861","author":"Howard Andrew G.","year":"2017","unstructured":"Andrew G. Howard , Menglong Zhu , Bo Chen , Dmitry Kalenichenko , Weijun Wang , Tobias Weyand , Marco Andreetto , and Hartwig Adam . Mobilenets: Efficient convolutional neural networks for mobile vision applications. CoRR, abs\/1704.04861 , 2017 . Andrew G. Howard, Menglong Zhu, Bo Chen, Dmitry Kalenichenko, Weijun Wang, Tobias Weyand, Marco Andreetto, and Hartwig Adam. Mobilenets: Efficient convolutional neural networks for mobile vision applications. CoRR, abs\/1704.04861, 2017."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080246"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2016.41"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3061639.3062228"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3352460.3358252"},{"key":"e_1_3_2_1_24_1","volume-title":"MAESTRO: an open-source infrastructure for modeling dataflows within deep learning accelerators. CoRR, abs\/1805.02566","author":"Kwon Hyoukjun","year":"2018","unstructured":"Hyoukjun Kwon , Michael Pellauer , and Tushar Krishna . MAESTRO: an open-source infrastructure for modeling dataflows within deep learning accelerators. CoRR, abs\/1805.02566 , 2018 . Hyoukjun Kwon, Michael Pellauer, and Tushar Krishna. MAESTRO: an open-source infrastructure for modeling dataflows within deep learning accelerators. CoRR, abs\/1805.02566, 2018."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3173162.3173176"},{"key":"e_1_3_2_1_26_1","first-page":"1","volume-title":"2016 26th International Conference on Field Programmable Logic and Applications (FPL)","author":"Li Huimin","year":"2016","unstructured":"Huimin Li , Xitian Fan , Li Jiao , Wei Cao , Xuegong Zhou , and Lingli Wang . A high performance FPGA-based accelerator for large-scale convolutional neural networks . In 2016 26th International Conference on Field Programmable Logic and Applications (FPL) , pages 1 -- 9 , Aug 2016 . Huimin Li, Xitian Fan, Li Jiao, Wei Cao, Xuegong Zhou, and Lingli Wang. A high performance FPGA-based accelerator for large-scale convolutional neural networks. In 2016 26th International Conference on Field Programmable Logic and Applications (FPL), pages 1--9, Aug 2016."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2017.29"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/2694344.2694364"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2007.30"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2019.00042"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080254"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3107953"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/2847263.2847265"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/2491956.2462176"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.5555\/3195638.3195659"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/FPL.2016.7577315"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080221"},{"key":"e_1_3_2_1_38_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 . Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 , 2014 . Karen Simonyan and Andrew Zisserman. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556, 2014."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2018.00016"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/2847263.2847276"},{"key":"e_1_3_2_1_41_1","volume-title":"Sequence to sequence learning with neural networks. CoRR, abs\/1409.3215","author":"Sutskever Ilya","year":"2014","unstructured":"Ilya Sutskever , Oriol Vinyals , and Quoc V. Le . Sequence to sequence learning with neural networks. CoRR, abs\/1409.3215 , 2014 . Ilya Sutskever, Oriol Vinyals, and Quoc V. Le. Sequence to sequence learning with neural networks. CoRR, abs\/1409.3215, 2014."},{"key":"e_1_3_2_1_42_1","volume-title":"Going deeper with convolutions. arXiv preprint arXiv:1409.4842","author":"Szegedy Christian","year":"2014","unstructured":"Christian Szegedy , Wei Liu , Yangqing Jia , Pierre Sermanet , Scott Reed , Dragomir Anguelov , Dumitru Erhan , Vincent Vanhoucke , and Andrew Rabinovich . Going deeper with convolutions. arXiv preprint arXiv:1409.4842 , 2014 . Christian Szegedy, Wei Liu, Yangqing Jia, Pierre Sermanet, Scott Reed, Dragomir Anguelov, Dumitru Erhan, Vincent Vanhoucke, and Andrew Rabinovich. Going deeper with convolutions. arXiv preprint arXiv:1409.4842, 2014."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3061639.3062207"},{"key":"e_1_3_2_1_45_1","unstructured":"Xuan Yang Jing Pu Blaine Burton Rister Nikhil Bhagdikar Stephen Richardson Shahar Kvatinsky Jonathan Ragan-Kelley Ardavan Pedram and Mark Horowitz. A systematic approach to blocking convolutional neural networks. arXiv preprint arXiv:1606.04209 2016.  Xuan Yang Jing Pu Blaine Burton Rister Nikhil Bhagdikar Stephen Richardson Shahar Kvatinsky Jonathan Ragan-Kelley Ardavan Pedram and Mark Horowitz. A systematic approach to blocking convolutional neural networks. arXiv preprint arXiv:1606.04209 2016."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080215"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/2684746.2689060"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3020078.3021727"},{"key":"e_1_3_2_1_49_1","first-page":"1","volume-title":"49th Annual IEEE\/ACM International Symposium on Microarchitecture (MICRO)","author":"Zhang Shijin","year":"2016","unstructured":"Shijin Zhang , Zidong Du , Lei Zhang , Huiying Lan , Shaoli Liu , Ling Li , Qi Guo , Tianshi Chen , and Yunji Chen . Cambricon-X : An accelerator for sparse neural networks . In 49th Annual IEEE\/ACM International Symposium on Microarchitecture (MICRO) , pages 1 -- 12 , 2016 . Shijin Zhang, Zidong Du, Lei Zhang, Huiying Lan, Shaoli Liu, Ling Li, Qi Guo, Tianshi Chen, and Yunji Chen. Cambricon-X: An accelerator for sparse neural networks. In 49th Annual IEEE\/ACM International Symposium on Microarchitecture (MICRO), pages 1--12, 2016."},{"key":"e_1_3_2_1_50_1","volume-title":"Jan Koutn'i k, and J\u00fc rgen Schmidhuber. Recurrent highway networks. CoRR, abs\/1607.03474","author":"Zilly Julian G.","year":"2016","unstructured":"Julian G. Zilly , Rupesh Kumar Srivastava , Jan Koutn'i k, and J\u00fc rgen Schmidhuber. Recurrent highway networks. CoRR, abs\/1607.03474 , 2016 . Julian G. Zilly, Rupesh Kumar Srivastava, Jan Koutn'i k, and J\u00fc rgen Schmidhuber. Recurrent highway networks. CoRR, abs\/1607.03474, 2016."},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/2435264.2435271"}],"event":{"name":"ASPLOS '20: Architectural Support for Programming Languages and Operating Systems","location":"Lausanne Switzerland","acronym":"ASPLOS '20","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-Fifth International Conference on Architectural Support for Programming Languages and Operating Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3373376.3378514","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3373376.3378514","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T22:38:16Z","timestamp":1750199896000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3373376.3378514"}},"subtitle":["Using Halide's Scheduling Language to Analyze DNN Accelerators"],"short-title":[],"issued":{"date-parts":[[2020,3,9]]},"references-count":50,"alternative-id":["10.1145\/3373376.3378514","10.1145\/3373376"],"URL":"https:\/\/doi.org\/10.1145\/3373376.3378514","relation":{},"subject":[],"published":{"date-parts":[[2020,3,9]]},"assertion":[{"value":"2020-03-13","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}