{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,28]],"date-time":"2024-09-28T04:24:00Z","timestamp":1727497440152},"publisher-location":"New York, NY, USA","reference-count":27,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,2,17]]},"DOI":"10.1145\/3579990.3580025","type":"proceedings-article","created":{"date-parts":[[2023,2,22]],"date-time":"2023-02-22T10:27:10Z","timestamp":1677061630000},"page":"212-223","update-policy":"http:\/\/dx.doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Flexer: Out-of-Order Scheduling for Multi-NPUs"],"prefix":"10.1145","author":[{"given":"Hyemi","family":"Min","sequence":"first","affiliation":[{"name":"Seoul National University, South Korea"}]},{"given":"Jungyoon","family":"Kwon","sequence":"additional","affiliation":[{"name":"Seoul National University, South Korea"}]},{"given":"Bernhard","family":"Egger","sequence":"additional","affiliation":[{"name":"Seoul National University, South Korea"}]}],"member":"320","published-online":{"date-parts":[[2023,2,22]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/2541940.2541967"},{"key":"e_1_3_2_1_2_1","volume-title":"TVM: An Automated End-to-End Optimizing Compiler for Deep Learning. In 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, Carlos Guestrin, and Arvind Krishnamurthy. 2018. TVM: An Automated End-to-End Optimizing Compiler for Deep Learning. In 13th USENIX Symposium on Operating Systems Design and Implementation (OSDI 18). USENIX Association, Carlsbad, CA. 578\u2013594. isbn:978-1-939133-08-3 https:\/\/www.usenix.org\/conference\/osdi18\/presentation\/chen"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2016.2616357"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.23919\/DATE51398.2021.9473965"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3240765.3240838"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3358198"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3297858.3304014"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO50266.2020.00062"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","unstructured":"Barend Harris Inpyo Bae and Bernhard Egger. 2018. Architectures and algorithms for on-device user customization of CNNs. Integration issn:0167-9260 https:\/\/doi.org\/10.1016\/j.vlsi.2018.11.001 10.1016\/j.vlsi.2018.11.001","DOI":"10.1016\/j.vlsi.2018.11.001"},{"key":"e_1_3_2_1_10_1","volume-title":"Deep Residual Learning for Image Recognition. CoRR, abs\/1512.03385","author":"He Kaiming","year":"2015","unstructured":"Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. 2015. Deep Residual Learning for Image Recognition. CoRR, abs\/1512.03385 (2015), arxiv:1512.03385. arxiv:1512.03385"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA52012.2021.00050"},{"key":"e_1_3_2_1_12_1","volume-title":"SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and < 1MB model size. CoRR, abs\/1602.07360","author":"Iandola Forrest N.","year":"2016","unstructured":"Forrest N. Iandola, Matthew W. Moskewicz, Khalid Ashraf, Song Han, William J. Dally, and Kurt Keutzer. 2016. SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and < 1MB model size. CoRR, abs\/1602.07360 (2016), arxiv:1602.07360. arxiv:1602.07360"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO50266.2020.00058"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3400302.3415639"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.23919\/DATE.2018.8342033"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3020078.3021736"},{"key":"e_1_3_2_1_17_1","volume-title":"Faster, Stronger. CoRR, abs\/1612.08242","author":"Redmon Joseph","year":"2016","unstructured":"Joseph Redmon and Ali Farhadi. 2016. YOLO9000: Better, Faster, Stronger. CoRR, abs\/1612.08242 (2016), arxiv:1612.08242. arxiv:1612.08242"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3352460.3358302"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2016.7783720"},{"key":"e_1_3_2_1_20_1","unstructured":"Karen Simonyan and Andrew Zisserman. 2014. Very Deep Convolutional Networks for Large-Scale Image Recognition. arxiv:1409.1556."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CGO53902.2022.9741281"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3373376.3378514"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/2684746.2689060"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403105"},{"key":"e_1_3_2_1_25_1","volume-title":"Ameer Haj-Ali, Yida Wang, Jun Yang, Danyang Zhuo, Koushik Sen, Joseph E. Gonzalez, and Ion Stoica.","author":"Zheng Lianmin","year":"2020","unstructured":"Lianmin Zheng, Chengfan Jia, Minmin Sun, Zhao Wu, Cody Hao Yu, Ameer Haj-Ali, Yida Wang, Jun Yang, Danyang Zhuo, Koushik Sen, Joseph E. Gonzalez, and Ion Stoica. 2020. Ansor: Generating High-Performance Tensor Programs for Deep Learning. USENIX Association, USA. isbn:978-1-939133-19-9"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3373376.3378508"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA53966.2022.00042"}],"event":{"name":"CGO '23: 21st ACM\/IEEE International Symposium on Code Generation and Optimization","sponsor":["SIGMICRO ACM Special Interest Group on Microarchitectural Research and Processing","SIGPLAN ACM Special Interest Group on Programming Languages","IEEE-CS Computer Society"],"location":"Montr\u00e9al QC Canada","acronym":"CGO '23"},"container-title":["Proceedings of the 21st ACM\/IEEE International Symposium on Code Generation and Optimization"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3579990.3580025","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,27]],"date-time":"2024-09-27T14:56:56Z","timestamp":1727449016000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3579990.3580025"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,2,17]]},"references-count":27,"alternative-id":["10.1145\/3579990.3580025","10.1145\/3579990"],"URL":"https:\/\/doi.org\/10.1145\/3579990.3580025","relation":{},"subject":[],"published":{"date-parts":[[2023,2,17]]},"assertion":[{"value":"2023-02-22","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}