{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T01:43:07Z","timestamp":1787017387549,"version":"build-2736575974"},"publisher-location":"New York, NY, USA","reference-count":38,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,2,17]],"date-time":"2023-02-17T00:00:00Z","timestamp":1676592000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100000781","name":"European Research Council","doi-asserted-by":"publisher","award":["101002047"],"award-info":[{"award-number":["101002047"]}],"id":[{"id":"10.13039\/501100000781","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100010661","name":"Horizon 2020 Framework Programme","doi-asserted-by":"publisher","award":["955606"],"award-info":[{"award-number":["955606"]}],"id":[{"id":"10.13039\/100010661","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Swiss National Science Foundation","award":["185778"],"award-info":[{"award-number":["185778"]}]},{"name":"Platform for Advanced Scientific Computing","award":["DaCeMI"],"award-info":[{"award-number":["DaCeMI"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,2,17]]},"DOI":"10.1145\/3579990.3580018","type":"proceedings-article","created":{"date-parts":[[2023,2,22]],"date-time":"2023-02-22T05:27:10Z","timestamp":1677043630000},"page":"173-185","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":7,"title":["Bridging Control-Centric and Data-Centric Optimization"],"prefix":"10.1145","author":[{"given":"Tal","family":"Ben-Nun","sequence":"first","affiliation":[{"name":"ETH Zurich, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Berke","family":"Ates","sequence":"additional","affiliation":[{"name":"ETH Zurich, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alexandru","family":"Calotoiu","sequence":"additional","affiliation":[{"name":"ETH Zurich, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Torsten","family":"Hoefler","sequence":"additional","affiliation":[{"name":"ETH Zurich, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2023,2,22]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2012.71"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","unstructured":"Tal Ben-Nun Berke Ates Alexandru Calotoiu and Torsten Hoefler. 2023. Data availability artifact. https:\/\/doi.org\/10.5281\/zenodo.7519936 10.5281\/zenodo.7519936","DOI":"10.5281\/zenodo.7519936"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3295500.3356173"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.5555\/3571885.3571982"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","unstructured":"Alexey Bochkovskiy Chien-Yao Wang and Hong-Yuan Mark Liao. 2020. YOLOv4: Optimal Speed and Accuracy of Object Detection. https:\/\/doi.org\/10.48550\/arXiv.2004.10934","DOI":"10.48550\/arXiv.2004.10934"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3524059.3532389"},{"key":"e_1_3_2_1_7_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:\/\/doi.org\/10.48550\/arXiv.1802.04799"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CGO51591.2021.9370315"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/24039.24041"},{"key":"e_1_3_2_1_10_1","unstructured":"Khronos Group. 2022. SYCL. https:\/\/www.khronos.org\/sycl\/"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3469030"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/1272998.1273005"},{"key":"e_1_3_2_1_13_1","volume-title":"Proceedings of Machine Learning and Systems, A. Smola, A. Dimakis, and I. Stoica (Eds.). 3, 711\u2013732","author":"Ivanov Andrei","year":"2021","unstructured":"Andrei Ivanov, Nikoli Dryden, Tal Ben-Nun, Shigang Li, and Torsten Hoefler. 2021. Data Movement Is All You Need: A Case Study on Optimizing Transformers. In Proceedings of Machine Learning and Systems, A. Smola, A. Dimakis, and I. Stoica (Eds.). 3, 711\u2013732. https:\/\/doi.org\/10.48550\/arXiv.2007.00072"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","unstructured":"Navdeep Katel Vivek Khandelwal and Uday Bondhugula. 2021. High Performance GPU Code Generation for Matrix-Matrix Multiplication using MLIR: Some Early Results. https:\/\/doi.org\/10.48550\/arXiv.2108.13191 arxiv:2108.13191.","DOI":"10.48550\/arXiv.2108.13191"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3133901"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3178487.3178493"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3409964.3461796"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CGO.2004.1281665"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CGO51591.2021.9370308"},{"key":"e_1_3_2_1_20_1","volume-title":"Java Virtual Machine Specification","author":"Lindholm Tim","year":"2014","unstructured":"Tim Lindholm and Frank Yellin. 1999. Java Virtual Machine Specification (2nd ed.). Addison-Wesley Longman Publishing Co., Inc., USA. isbn:0201432943","edition":"2"},{"key":"e_1_3_2_1_21_1","unstructured":"LLVM Project. 2022. Circuit IR Compilers and Tools (CIRCT). https:\/\/github.com\/llvm\/circt"},{"key":"e_1_3_2_1_22_1","volume-title":"Flang: FORTRAN front end. https:\/\/github.com\/llvm\/llvm-project\/tree\/main\/flang","author":"Project LLVM","year":"2022","unstructured":"LLVM Project. 2022. Flang: FORTRAN front end. https:\/\/github.com\/llvm\/llvm-project\/tree\/main\/flang"},{"key":"e_1_3_2_1_23_1","volume-title":"Proceedings of the 31st British Machine Vision Conference (BMVC). https:\/\/doi.org\/10","author":"Misra Diganta","year":"2020","unstructured":"Diganta Misra. 2020. Mish: A Self Regularized Non-Monotonic Activation Function. In Proceedings of the 31st British Machine Vision Conference (BMVC). https:\/\/doi.org\/10.48550\/arXiv.1908.08681"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/PACT52795.2021.00011"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/2517349.2522738"},{"key":"e_1_3_2_1_26_1","unstructured":"NVIDIA Corporation. 2022. cuBLAS: Basic Linear Algebra on NVIDIA GPUs. https:\/\/developer.nvidia.com\/cublas"},{"key":"e_1_3_2_1_27_1","unstructured":"L. N. Pouchet. 2016. PolyBench: The Polyhedral Benchmark suite. https:\/\/sourceforge.net\/projects\/polybench"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3524059.3532364"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3385412.3386024"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2019.2960333"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3529538.3529992"},{"key":"e_1_3_2_1_32_1","volume-title":"Tools for High Performance Computing","author":"Terpstra Dan","year":"2009","unstructured":"Dan Terpstra, Heike Jagode, Haihang You, and Jack Dongarra. 2010. Collecting Performance Data with PAPI-C. In Tools for High Performance Computing 2009, Matthias S. M\u00fcller, Michael M. Resch, Alexander Schulz, and Wolfgang E. Nagel (Eds.). Springer Berlin Heidelberg, Berlin, Heidelberg. 157\u2013173. isbn:978-3-642-11261-4"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2017.2703149"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1802.04730"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/2851141.2851145"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/1806596.1806640"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3295500.3357156"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3476176"}],"event":{"name":"CGO '23: 21st ACM\/IEEE International Symposium on Code Generation and Optimization","location":"Montr\u00e9al QC Canada","acronym":"CGO '23","sponsor":["SIGMICRO ACM Special Interest Group on Microarchitectural Research and Processing","SIGPLAN ACM Special Interest Group on Programming Languages","IEEE-CS Computer Society"]},"container-title":["Proceedings of the 21st ACM\/IEEE International Symposium on Code Generation and Optimization"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3579990.3580018","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3579990.3580018","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T14:08:19Z","timestamp":1750169299000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3579990.3580018"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,2,17]]},"references-count":38,"alternative-id":["10.1145\/3579990.3580018","10.1145\/3579990"],"URL":"https:\/\/doi.org\/10.1145\/3579990.3580018","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"}}]}}