{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:11:12Z","timestamp":1750219872237,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":42,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,6,18]],"date-time":"2023-06-18T00:00:00Z","timestamp":1687046400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["IIS-2008295"],"award-info":[{"award-number":["IIS-2008295"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,6,18]]},"DOI":"10.1145\/3592980.3595301","type":"proceedings-article","created":{"date-parts":[[2023,6,14]],"date-time":"2023-06-14T03:07:44Z","timestamp":1686712064000},"page":"77-81","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["AMULET: Adaptive Matrix-Multiplication-Like Tasks"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-5789-2026","authenticated-orcid":false,"given":"Junyoung","family":"Kim","sequence":"first","affiliation":[{"name":"Computer Science, Columbia University, US"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9397-6990","authenticated-orcid":false,"given":"Kenneth A","family":"Ross","sequence":"additional","affiliation":[{"name":"Computer Science, Columbia University, US"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-1334-6317","authenticated-orcid":false,"given":"Eric","family":"Sedlar","sequence":"additional","affiliation":[{"name":"Oracle Labs, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-3156-2475","authenticated-orcid":false,"given":"Lukas","family":"Stadler","sequence":"additional","affiliation":[{"name":"Oracle Labs, Austria"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,6,18]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"2021. Intel C\/C++ compilers complete adoption of LLVM. Retrieved 2023-03-02 from https:\/\/www.intel.com\/content\/www\/us\/en\/developer\/articles\/technical\/adoption-of-llvm-complete-icx.html"},{"key":"e_1_3_2_1_2_1","unstructured":"2021. Intel\u00ae oneAPI Math Kernel Library. Retrieved 2022-03-02 from https:\/\/www.intel.com\/content\/www\/us\/en\/develop\/documentation\/get-started-with-mkl-for-dpcpp\/top.html"},{"key":"e_1_3_2_1_3_1","unstructured":"2022. OpenBLAS. Retrieved 2023-03-02 from http:\/\/www.openblas.net\/"},{"key":"e_1_3_2_1_4_1","unstructured":"2022. XLA. Retrieved 2023-03-02 from https:\/\/www.tensorflow.org\/xla"},{"key":"e_1_3_2_1_5_1","unstructured":"2023. Intel oneAPI DPC++\/C++ Compiler. Retrieved 2023-03-02 from https:\/\/www.intel.com\/content\/www\/us\/en\/developer\/tools\/oneapi\/dpc-compiler.html#gs.nyazv0"},{"key":"e_1_3_2_1_6_1","unstructured":"2023. NumPy. Retrieved 2023-03-02 from https:\/\/numpy.org\/"},{"key":"e_1_3_2_1_7_1","volume-title":"Proceedings of the 12th USENIX Conference on Operating Systems Design and Implementation","author":"Abadi Mart\u00edn","year":"2016","unstructured":"Mart\u00edn Abadi, Paul Barham, Jianmin Chen, Zhifeng Chen, Andy Davis, Jeffrey Dean, Matthieu Devin, Sanjay Ghemawat, Geoffrey Irving, Michael Isard, Manjunath Kudlur, Josh Levenberg, Rajat Monga, Sherry Moore, Derek\u00a0G. Murray, Benoit Steiner, Paul Tucker, Vijay Vasudevan, Pete Warden, Martin Wicke, Yuan Yu, and Xiaoqiang Zheng. 2016. TensorFlow: A System for Large-Scale Machine Learning. In Proceedings of the 12th USENIX Conference on Operating Systems Design and Implementation (Savannah, GA, USA) (OSDI\u201916). USENIX Association, USA, 265\u2013283."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/29873.29875"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/1514894.1514909"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/342009.335420"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3317550.3321441"},{"key":"e_1_3_2_1_12_1","volume-title":"Proceedings of the 13th USENIX Conference on Operating Systems Design and Implementation","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. 2018. TVM: An Automated End-to-End Optimizing Compiler for Deep Learning. In Proceedings of the 13th USENIX Conference on Operating Systems Design and Implementation (Carlsbad, CA, USA) (OSDI\u201918). USENIX Association, USA, 579\u2013594."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3318464.3380607"},{"volume-title":"Adaptive query processing","author":"Deshpande Amol","key":"e_1_3_2_1_14_1","unstructured":"Amol Deshpande, Zachary Ives, and Vijayshankar Raman. 2007. Adaptive query processing. Now Publishers Inc."},{"key":"e_1_3_2_1_15_1","volume-title":"Communication-Optimal Tilings for Projective Nested Loops with Arbitrary Bounds. CoRR abs\/2003.00119","author":"Dinh Grace","year":"2020","unstructured":"Grace Dinh and James Demmel. 2020. Communication-Optimal Tilings for Projective Nested Loops with Arbitrary Bounds. CoRR abs\/2003.00119 (2020). arXiv:2003.00119https:\/\/arxiv.org\/abs\/2003.00119"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2021.3136457"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2018.2873289"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1998.681704"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/1356052.1356053"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3514221.3517869"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2018.00052"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3341301.3359630"},{"volume-title":"Proc. 3rd Symp. on Programming Language Implementation and Logic Programming. Springer LCNS, 195\u2013206","author":"Ke\u00dfler W.","key":"e_1_3_2_1_23_1","unstructured":"C.\u00a0W. Ke\u00dfler, W.\u00a0J. Paul, and T. Rauber. 1991. A Randomized Heuristic Approach to Register Allocation. In Proc. 3rd Symp. on Programming Language Implementation and Logic Programming. Springer LCNS, 195\u2013206."},{"key":"e_1_3_2_1_24_1","volume-title":"AMULET: Adaptive Matrix-Multiplication-Like Tasks. arxiv:2305.08872\u00a0[cs.PL]","author":"Kim Junyoung","year":"2023","unstructured":"Junyoung Kim, Kenneth Ross, Eric Sedlar, and Lukas Stadler. 2023. AMULET: Adaptive Matrix-Multiplication-Like Tasks. arxiv:2305.08872\u00a0[cs.PL]"},{"key":"e_1_3_2_1_25_1","unstructured":"Vishal Mehta. 2019. Getting started with tensor cores in HPC. Retrieved 2022-08-22 from https:\/\/on-demand.gputechconf.com\/supercomputing\/2019\/pdf\/sc1909-getting-started-with-tensor-cores-for-hpc.pdf"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/1454115.1454119"},{"key":"e_1_3_2_1_27_1","volume-title":"9th Biennial Conference on Innovative Data Systems Research, CIDR","author":"Pirk Holger","year":"2019","unstructured":"Holger Pirk, Jana Giceva, and Peter\u00a0R. Pietzuch. 2019. Thriving in the No Man\u2019s Land between Compilers and Databases. In 9th Biennial Conference on Innovative Data Systems Research, CIDR 2019, Asilomar, CA, USA, January 13-16, 2019, Online Proceedings. www.cidrdb.org. http:\/\/cidrdb.org\/cidr2019\/papers\/p91-pirk-cidr19.pdf"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/2463676.2465292"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/800125.804049"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CGO.2015.7054190"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.5555\/3049832.3049846"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/HiPC.2011.6152742"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/2764454"},{"key":"e_1_3_2_1_34_1","volume-title":"Tensor Comprehensions: Framework-Agnostic High-Performance Machine Learning Abstractions. arxiv:1802.04730\u00a0[cs.PL]","author":"Vasilache Nicolas","year":"2018","unstructured":"Nicolas Vasilache, Oleksandr Zinenko, Theodoros Theodoridis, Priya Goyal, Zachary DeVito, William\u00a0S. Moses, Sven Verdoolaege, Andrew Adams, and Albert Cohen. 2018. Tensor Comprehensions: Framework-Agnostic High-Performance Machine Learning Abstractions. arxiv:1802.04730\u00a0[cs.PL]"},{"key":"e_1_3_2_1_35_1","unstructured":"[35] Carl Vondrick. 2021. personal communication."},{"volume-title":"Proceedings of the 1998 ACM\/IEEE Conference on Supercomputing","author":"R.","key":"e_1_3_2_1_36_1","unstructured":"R.\u00a0Clint Whaley and Jack\u00a0J. Dongarra. 1998. Automatically Tuned Linear Algebra Software. In Proceedings of the 1998 ACM\/IEEE Conference on Supercomputing (San Jose, CA) (SC \u201998). IEEE Computer Society, USA, 1\u201327."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/2384716.2384723"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/2509578.2509581"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/2509578.2509581"},{"key":"e_1_3_2_1_40_1","unstructured":"Xuan Yang Jing Pu Blaine\u00a0Burton Rister Nikhil Bhagdikar Stephen Richardson Shahar Kvatinsky Jonathan Ragan-Kelley Ardavan Pedram and Mark Horowitz. 2016. A Systematic Approach to Blocking Convolutional Neural Networks. arxiv:1606.04209\u00a0[cs.DC]"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.14778\/3447689.3447697"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3205289.3205306"}],"event":{"name":"SIGMOD\/PODS '23: International Conference on Management of Data","sponsor":["SIGMOD ACM Special Interest Group on Management of Data"],"location":"Seattle WA USA","acronym":"SIGMOD\/PODS '23"},"container-title":["Proceedings of the 19th International Workshop on Data Management on New Hardware"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3592980.3595301","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/abs\/10.1145\/3592980.3595301","content-type":"text\/html","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3592980.3595301","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3592980.3595301","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:48:01Z","timestamp":1750178881000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3592980.3595301"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,18]]},"references-count":42,"alternative-id":["10.1145\/3592980.3595301","10.1145\/3592980"],"URL":"https:\/\/doi.org\/10.1145\/3592980.3595301","relation":{},"subject":[],"published":{"date-parts":[[2023,6,18]]},"assertion":[{"value":"2023-06-18","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}