{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T11:40:16Z","timestamp":1755776416693,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":48,"publisher":"ACM","license":[{"start":{"date-parts":[[2025,3,30]],"date-time":"2025-03-30T00:00:00Z","timestamp":1743292800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-sa\/4.0\/"}],"funder":[{"name":"The National Key R&D Program of China","award":["2022YFB4501600"],"award-info":[{"award-number":["2022YFB4501600"]}]},{"name":"The Strategic Priority Research Program of the Chinese Academy of Sciences","award":["XDB0660300, XDB0660301, XDB0660302"],"award-info":[{"award-number":["XDB0660300, XDB0660301, XDB0660302"]}]},{"name":"CAS Project for Young Scientists in Basic Research","award":["YSBR-029"],"award-info":[{"award-number":["YSBR-029"]}]},{"name":"The NSF of China","award":["U22A2028, 62302483, 62222214, 62341411, 62102399, 62302478, 62302482, 62302480, 62302481"],"award-info":[{"award-number":["U22A2028, 62302483, 62222214, 62341411, 62102399, 62302478, 62302482, 62302480, 62302481"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,3,30]]},"DOI":"10.1145\/3676641.3716262","type":"proceedings-article","created":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T16:47:32Z","timestamp":1743094052000},"page":"672-688","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Mosaic: Exploiting Instruction-Level Parallelism on Deep Learning Accelerators with\n            <i>iTex<\/i>\n            Tessellation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0373-411X","authenticated-orcid":false,"given":"Jianxing","family":"Xu","sequence":"first","affiliation":[{"name":"University of Science and Technology of China, Hefei, China, SKL of Processors, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China, and Cambricon Technologies, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7775-2724","authenticated-orcid":false,"given":"Yuanbo","family":"Wen","sequence":"additional","affiliation":[{"name":"SKL of Processors, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-3931-9222","authenticated-orcid":false,"given":"Zikang","family":"Liu","sequence":"additional","affiliation":[{"name":"SKL of Processors, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China, University of Chinese Academy of Sciences, Beijing, China, and Cambricon Technologies, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-1830-4483","authenticated-orcid":false,"given":"Ruibai","family":"Xu","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China, SKL of Processors, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China, and Cambricon Technologies, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-7123-1913","authenticated-orcid":false,"given":"Tingfeng","family":"Ruan","sequence":"additional","affiliation":[{"name":"SKL of Processors, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China, University of Chinese Academy of Sciences, Beijing, China, and Cambricon Technologies, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9956-7039","authenticated-orcid":false,"given":"Jun","family":"Bi","sequence":"additional","affiliation":[{"name":"SKL of Processors, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8691-8549","authenticated-orcid":false,"given":"Rui","family":"Zhang","sequence":"additional","affiliation":[{"name":"SKL of Processors, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2370-0072","authenticated-orcid":false,"given":"Di","family":"Huang","sequence":"additional","affiliation":[{"name":"SKL of Processors, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3458-1555","authenticated-orcid":false,"given":"Xinkai","family":"Song","sequence":"additional","affiliation":[{"name":"SKL of Processors, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-9823-2573","authenticated-orcid":false,"given":"Yifan","family":"Hao","sequence":"additional","affiliation":[{"name":"SKL of Processors, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9979-0561","authenticated-orcid":false,"given":"Xing","family":"Hu","sequence":"additional","affiliation":[{"name":"SKL of Processors, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7603-4210","authenticated-orcid":false,"given":"Zidong","family":"Du","sequence":"additional","affiliation":[{"name":"SKL of Processors, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-1345-9484","authenticated-orcid":false,"given":"Chongqing","family":"Zhao","sequence":"additional","affiliation":[{"name":"Tencent, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9658-5127","authenticated-orcid":false,"given":"Jiang","family":"Jie","sequence":"additional","affiliation":[{"name":"Tencent, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2530-5874","authenticated-orcid":false,"given":"Qi","family":"Guo","sequence":"additional","affiliation":[{"name":"SKL of Processors, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,3,30]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"4th Gen Xeon Scalable Processors. https:\/\/www.intel.com\/content\/www\/us\/en\/products\/docs\/processors\/xeon-accelerated\/4th-genxeon-scalable-processors.html."},{"key":"e_1_3_2_1_2_1","unstructured":"Accelerate Fast Math with Intel\u00ae oneAPI Math Kernel Library. http: \/\/software.intel.com\/en-us\/intel-mkl."},{"key":"e_1_3_2_1_3_1","unstructured":"Basic Linear Algebra on NVIDIA GPUs. https:\/\/developer.nvidia.com\/ cublas."},{"key":"e_1_3_2_1_4_1","unstructured":"CuAssembler: An unofficial CUDA assembler. https:\/\/github.com\/cloudcores\/CuAssembler."},{"key":"e_1_3_2_1_5_1","unstructured":"CUDA Templates for Linear Algebra Subroutines. https:\/\/github.com\/ NVIDIA\/cutlass."},{"key":"e_1_3_2_1_6_1","unstructured":"Intel\u00ae Extension for PyTorch. https:\/\/www.intel.com\/content\/www\/us\/en\/developer\/tools\/oneapi\/ai-analytics-toolkit.html."},{"key":"e_1_3_2_1_7_1","unstructured":"Introducing Meta Llama 3: The most capable openly available LLM to date. https:\/\/ai.meta.com\/blog\/meta-llama-3\/."},{"key":"e_1_3_2_1_8_1","unstructured":"Maxwell Architecture. https:\/\/developer.nvidia.com\/maxwellcompute- architecture\/."},{"key":"e_1_3_2_1_9_1","unstructured":"OpenAI. https:\/\/openai.com\/."},{"key":"e_1_3_2_1_10_1","unstructured":"Marah Abdin Sam Ade Jacobs Ammar Ahmad Awan Jyoti Aneja Ahmed Awadallah Hany Awadalla Nguyen Bach Amit Bahree Arash Bakhtiari Jianmin Bao Harkirat Behl Alon Benhaim Misha Bilenko Johan Bjorck S\u00e9bastien Bubeck Qin Cai Martin Cai Caio C\u00e9sar Teodoro Mendes Weizhu Chen Vishrav Chaudhary Dong Chen Dongdong Chen Yen-Chun Chen Yi-Ling Chen Parul Chopra Xiyang Dai Allie Del Giorno Gustavo de Rosa Matthew Dixon Ronen Eldan Victor Fragoso Dan Iter Mei Gao Min Gao Jianfeng Gao Amit Garg Abhishek Goswami Suriya Gunasekar Emman Haider Junheng Hao Russell J. Hewett Jamie Huynh Mojan Javaheripi Xin Jin Piero Kauffmann Nikos Karampatziakis Dongwoo Kim Mahoud Khademi Lev Kurilenko James R. Lee Yin Tat Lee Yuanzhi Li Yunsheng Li Chen Liang Lars Liden Ce Liu Mengchen Liu Weishung Liu Eric Lin Zeqi Lin Chong Luo Piyush Madan Matt Mazzola Arindam Mitra Hardik Modi Anh Nguyen Brandon Norick Barun Patra Daniel Perez-Becker Thomas Portet Reid Pryzant Heyang Qin Marko Radmilac Corby Rosset Sambudha Roy Olatunji Ruwase Olli Saarikivi Amin Saied Adil Salim Michael Santacroce Shital Shah Ning Shang Hiteshi Sharma Swadheen Shukla Xia Song Masahiro Tanaka Andrea Tupini XinWang Lijuan Wang Chunyu Wang YuWang Rachel Ward Guanhua Wang Philipp Witte Haiping Wu Michael Wyatt Bin Xiao Can Xu Jiahang Xu Weijian Xu Sonali Yadav Fan Yang Jianwei Yang Ziyi Yang Yifan Yang Donghan Yu Lu Yuan Chengruidong Zhang Cyril Zhang Jianwen Zhang Li Lyna Zhang Yi Zhang Yue Zhang Yunan Zhang and Xiren Zhou. Phi-3 technical report: A highly capable language model locally on your phone 2024."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3620665.3640366"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CGO.2019.8661197"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3582016.3582061"},{"key":"e_1_3_2_1_14_1","volume-title":"A survey on evaluation of large language models. ACM Trans. Intell. Syst. Technol., 15(3), mar","author":"Chang Yupeng","year":"2024","unstructured":"Yupeng Chang, Xu Wang, Jindong Wang, Yuan Wu, Linyi Yang, Kaijie Zhu, Hao Chen, Xiaoyuan Yi, Cunxiang Wang, Yidong Wang, Wei Ye, Yue Zhang, Yi Chang, Philip S. Yu, Qiang Yang, and Xing Xie. A survey on evaluation of large language models. ACM Trans. Intell. Syst. Technol., 15(3), mar 2024."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA59077.2024.00011"},{"key":"e_1_3_2_1_16_1","first-page":"579","volume-title":"Proceedings of the 13th USENIX Conference on Operating Systems Design and Implementation, OSDI'18","author":"Chen Tianqi","year":"2018","unstructured":"Tianqi Chen, Thierry Moreau, Ziheng Jiang, Lianmin Zheng, Eddie Yan, Meghan Cowan, Haichen Shen, Leyuan Wang, Yuwei Hu, Luis Ceze, Carlos Guestrin, and Arvind Krishnamurthy. Tvm: an automated end-to-end optimizing compiler for deep learning. In Proceedings of the 13th USENIX Conference on Operating Systems Design and Implementation, OSDI'18, page 579--594, USA, 2018. USENIX Association."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.5555\/3327144.3327258"},{"key":"e_1_3_2_1_18_1","first-page":"269","volume-title":"Proceedings of the 19th International Conference on Architectural Support for Programming Languages and Operating Systems, ASPLOS '14","author":"Chen Tianshi","year":"2014","unstructured":"Tianshi Chen, Zidong Du, Ninghui Sun, Jia Wang, Chengyong Wu, Yunji Chen, and Olivier Temam. Diannao: a small-footprint highthroughput accelerator for ubiquitous machine-learning. In Proceedings of the 19th International Conference on Architectural Support for Programming Languages and Operating Systems, ASPLOS '14, page 269--284, New York, NY, USA, 2014. Association for Computing Machinery."},{"key":"e_1_3_2_1_19_1","unstructured":"NVIDIA Corporation. NVIDIA V100 TENSOR CORE GPU. https: \/\/www.nvidia.com\/en-us\/data-center\/v100\/."},{"key":"e_1_3_2_1_20_1","volume-title":"Adam Procter, and Tristan J. Webb. Intel ngraph: An intermediate representation, compiler, and executor for deep learning","author":"Cyphers Scott","year":"2018","unstructured":"Scott Cyphers, Arjun K. Bansal, Anahita Bhiwandiwalla, Jayaram Bobba, Matthew Brookhart, Avijit Chakraborty, Will Constable, Christian Convey, Leona Cook, Omar Kanawi, Robert Kimball, Jason Knight, Nikolay Korovaiko, Varun Kumar, Yixing Lao, Christopher R. Lishka, Jaikrishnan Menon, Jennifer Myers, Sandeep Aswath Narayana, Adam Procter, and Tristan J. Webb. Intel ngraph: An intermediate representation, compiler, and executor for deep learning, 2018."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2012.48"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3575693.3576933"},{"volume-title":"Tensorflow xla. https:\/\/www.tensorflow.org\/xla","year":"2023","key":"e_1_3_2_1_23_1","unstructured":"Google. Tensorflow xla. https:\/\/www.tensorflow.org\/xla, 2023."},{"key":"e_1_3_2_1_24_1","first-page":"302","volume-title":"Proceedings of the 28th ACM International Conference on Architectural Support for Programming Languages and Operating Systems","volume":"3","author":"Hagedorn Bastian","year":"2023","unstructured":"Bastian Hagedorn, Bin Fan, Hanfeng Chen, Cris Cecka, Michael Garland, and Vinod Grover. Graphene: An ir for optimized tensor computations on gpus. In Proceedings of the 28th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 3, ASPLOS 2023, page 302--313, New York, NY, USA, 2023. Association for Computing Machinery."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISVLSI54635.2022.00051"},{"key":"e_1_3_2_1_26_1","volume-title":"Large multilingual models pivot zero-shot multimodal learning across languages","author":"Hu Jinyi","year":"2024","unstructured":"Jinyi Hu, Yuan Yao, Chongyi Wang, Shan Wang, Yinxu Pan, Qianyu Chen, Tianyu Yu, Hanghao Wu, Yue Zhao, Haoye Zhang, Xu Han, Yankai Lin, Jiao Xue, Dahai Li, Zhiyuan Liu, and Maosong Sun. Large multilingual models pivot zero-shot multimodal learning across languages, 2024."},{"key":"e_1_3_2_1_27_1","volume-title":"September","author":"Intel Corporation","year":"2023","unstructured":"Intel Corporation. 4th gen intel\u00ae xeon\u00ae scalable processors product brief. https:\/\/www.intel.com\/content\/dam\/www\/central-libraries\/us\/ en\/documents\/2023-09\/4th-gen-xeon-revised-product-brief.pdf, September 2023. Accessed: 2024-06-24."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/2830772.2830784"},{"key":"e_1_3_2_1_29_1","first-page":"7b","article-title":"Diego de las Casas, Florian Bressand, Gianna Lengyel, Guillaume Lample, Lucile Saulnier, L\u00e9lio Renard Lavaud, Marie-Anne Lachaux, Pierre Stock, Teven Le Scao, Thibaut Lavril, Thomas Wang, Timoth\u00e9e Lacroix, and William El Sayed","author":"Jiang Albert Q.","year":"2023","unstructured":"Albert Q. Jiang, Alexandre Sablayrolles, Arthur Mensch, Chris Bamford, Devendra Singh Chaplot, Diego de las Casas, Florian Bressand, Gianna Lengyel, Guillaume Lample, Lucile Saulnier, L\u00e9lio Renard Lavaud, Marie-Anne Lachaux, Pierre Stock, Teven Le Scao, Thibaut Lavril, Thomas Wang, Timoth\u00e9e Lacroix, and William El Sayed. Mistral 7b, 2023.","journal-title":"Mistral"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080246"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4684-2001-2_9"},{"key":"e_1_3_2_1_32_1","volume-title":"Gauthier-Villars","author":"Knuth Donald E","year":"1970","unstructured":"Donald E Knuth. The analysis of algorithms. In Actes du Congres International des Mathematiciens (ICM). Gauthier-Villars, Paris, 1970."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CGO51591.2021.9370308"},{"key":"e_1_3_2_1_34_1","volume-title":"Visual instruction tuning. Advances in neural information processing systems, 36","author":"Liu Haotian","year":"2024","unstructured":"Haotian Liu, Chunyuan Li, Qingyang Wu, and Yong Jae Lee. Visual instruction tuning. Advances in neural information processing systems, 36, 2024."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW.2018.00091"},{"key":"e_1_3_2_1_36_1","unstructured":"NVIDIA Corporation. Whitepaper: NVIDIA Tesla V100 GPU Architecture. http:\/\/images.nvidia.com\/content\/volta-architecture\/pdf\/voltaarchitecture-whitepaper.pdf 2017."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/2491956.2462176"},{"key":"e_1_3_2_1_38_1","volume-title":"Glow: Graph lowering compiler techniques for neural networks","author":"Rotem Nadav","year":"2019","unstructured":"Nadav Rotem, Jordan Fix, Saleem Abdulrasool, Garret Catron, Summer Deng, Roman Dzhabarov, Nick Gibson, James Hegeman, Meghan Lele, Roman Levenstein, Jack Montgomery, Bert Maher, Satish Nadathur, Jakob Olesen, Jongsoo Park, Artem Rakhov, Misha Smelyanskiy, and Man Wang. Glow: Graph lowering compiler techniques for neural networks, 2019."},{"key":"e_1_3_2_1_39_1","unstructured":"Baptiste Rozi\u00e8re Jonas Gehring Fabian Gloeckle Sten Sootla Itai Gat Xiaoqing Ellen Tan Yossi Adi Jingyu Liu Romain Sauvestre Tal Remez J\u00e9r\u00e9my Rapin Artyom Kozhevnikov Ivan Evtimov Joanna Bitton Manish Bhatt Cristian Canton Ferrer Aaron Grattafiori Wenhan Xiong Alexandre D\u00e9fossez Jade Copet Faisal Azhar Hugo Touvron Louis Martin Nicolas Usunier Thomas Scialom and Gabriel Synnaeve. Code llama: Open foundation models for code 2024."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2017.2761740"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3315508.3329973"},{"key":"e_1_3_2_1_42_1","unstructured":"Hugo Touvron Louis Martin Kevin Stone Peter Albert Amjad Almahairi Yasmine Babaei Nikolay Bashlykov Soumya Batra Prajjwal Bhargava Shruti Bhosale Dan Bikel Lukas Blecher Cristian Canton Ferrer Moya Chen Guillem Cucurull David Esiobu Jude Fernandes Jeremy Fu Wenyin Fu Brian Fuller Cynthia Gao Vedanuj Goswami Naman Goyal Anthony Hartshorn Saghar Hosseini Rui Hou Hakan Inan Marcin Kardas Viktor Kerkez Madian Khabsa Isabel Kloumann Artem Korenev Punit Singh Koura Marie-Anne Lachaux Thibaut Lavril Jenya Lee Diana Liskovich Yinghai Lu Yuning Mao Xavier Martinet Todor Mihaylov Pushkar Mishra Igor Molybog Yixin Nie Andrew Poulton Jeremy Reizenstein Rashi Rungta Kalyan Saladi Alan Schelten Ruan Silva Eric Michael Smith Ranjan Subramanian Xiaoqing Ellen Tan Binh Tang Ross Taylor Adina Williams Jian Xiang Kuan Puxin Xu Zheng Yan Iliyan Zarov Yuchen Zhang Angela Fan Melanie Kambadur Sharan Narang Aurelien Rodriguez Robert Stojnic Sergey Edunov and Thomas Scialom. Llama 2: Open foundation and fine-tuned chat models 2023."},{"key":"e_1_3_2_1_43_1","volume-title":"Tensor comprehensions: Frameworkagnostic high-performance machine learning abstractions","author":"Vasilache Nicolas","year":"2018","unstructured":"Nicolas Vasilache, Oleksandr Zinenko, Theodoros Theodoridis, Priya Goyal, Zachary DeVito, William S. Moses, Sven Verdoolaege, Andrew Adams, and Albert Cohen. Tensor comprehensions: Frameworkagnostic high-performance machine learning abstractions, 2018."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.34133\/icomputing.0040"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCD53106.2021.00054"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/3453483.3454106"},{"key":"e_1_3_2_1_47_1","first-page":"863","volume-title":"Proceedings of 14th USENIX Symposium on Operating Systems Design and Implementation (OSDI)","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 Gonzalez, and Ion Stoica. Ansor: Generating high-performance tensor programs for deep learning. In Proceedings of 14th USENIX Symposium on Operating Systems Design and Implementation (OSDI), pages 863--879, 2020."},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3373376.3378508"}],"event":{"name":"ASPLOS '25: 30th ACM International Conference on Architectural Support for Programming Languages and Operating Systems","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"],"location":"Rotterdam Netherlands","acronym":"ASPLOS '25"},"container-title":["Proceedings of the 30th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 2"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3676641.3716262","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3676641.3716262","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T11:12:09Z","timestamp":1755774729000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3676641.3716262"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,30]]},"references-count":48,"alternative-id":["10.1145\/3676641.3716262","10.1145\/3676641"],"URL":"https:\/\/doi.org\/10.1145\/3676641.3716262","relation":{},"subject":[],"published":{"date-parts":[[2025,3,30]]},"assertion":[{"value":"2025-03-30","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}