{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T15:40:58Z","timestamp":1780674058239,"version":"3.54.1"},"reference-count":45,"publisher":"Association for Computing Machinery (ACM)","issue":"1","license":[{"start":{"date-parts":[[2022,12,20]],"date-time":"2022-12-20T00:00:00Z","timestamp":1671494400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100000001","name":"NSF","doi-asserted-by":"publisher","award":["CCF-1723773"],"award-info":[{"award-number":["CCF-1723773"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100008457","name":"University of Virginia","doi-asserted-by":"publisher","award":["GI18518.156870"],"award-info":[{"award-number":["GI18518.156870"]}],"id":[{"id":"10.13039\/100008457","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100002418","name":"Intel Corporation","doi-asserted-by":"publisher","award":["36888881"],"award-info":[{"award-number":["36888881"]}],"id":[{"id":"10.13039\/100002418","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["Commun. ACM"],"published-print":{"date-parts":[[2023,1]]},"abstract":"<jats:p>Creating a programming environment and compilation flow that empowers programmers to create their own DSAs efficiently and affordably on FPGAs.<\/jats:p>","DOI":"10.1145\/3524108","type":"journal-article","created":{"date-parts":[[2022,12,20]],"date-time":"2022-12-20T19:47:37Z","timestamp":1671565657000},"page":"74-85","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":24,"title":["Democratizing Domain-Specific Computing"],"prefix":"10.1145","volume":"66","author":[{"given":"Yuze","family":"Chi","sequence":"first","affiliation":[{"name":"University of California Los Angeles, Los Angeles, CA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weikang","family":"Qiao","sequence":"additional","affiliation":[{"name":"University of California Los Angeles, Los Angeles, CA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Atefeh","family":"Sohrabizadeh","sequence":"additional","affiliation":[{"name":"University of California Los Angeles, Los Angeles, CA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jie","family":"Wang","sequence":"additional","affiliation":[{"name":"University of California Los Angeles, Los Angeles, CA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jason","family":"Cong","sequence":"additional","affiliation":[{"name":"University of California Los Angeles, Los Angeles, CA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2022,12,20]]},"reference":[{"key":"e_1_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3489517.3530629"},{"key":"e_1_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/1941487.1941507"},{"key":"e_1_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICFPT51103.2020.00011"},{"key":"e_1_2_1_4_1","volume-title":"Proceedings of the 2019 ACM\/SIGDA Intern. Symp. on Field-Programmable Gate Arrays, 104--109","author":"Chen Z.","unstructured":"Chen , Z. , Blair , H.T. , and Cong , J . LANMC: LSTM-assisted non-rigid motion correction on FPGA for calcium image stabilization . In Proceedings of the 2019 ACM\/SIGDA Intern. Symp. on Field-Programmable Gate Arrays, 104--109 . Chen, Z., Blair, H.T., and Cong, J. LANMC: LSTM-assisted non-rigid motion correction on FPGA for calcium image stabilization. In Proceedings of the 2019 ACM\/SIGDA Intern. Symp. on Field-Programmable Gate Arrays, 104--109."},{"key":"e_1_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/DAC18072.2020.9218680"},{"key":"e_1_2_1_6_1","volume-title":"2018 IEEE\/ACM Intern. Conf. on Computer-Aided Design, 1--8.","author":"Chi Y.","unstructured":"Chi , Y. , Cong , J. , Wei , P. , and Zhou , P . SODA: Stencil with optimized dataflow architecture . In 2018 IEEE\/ACM Intern. Conf. on Computer-Aided Design, 1--8. Chi, Y., Cong, J., Wei, P., and Zhou, P. SODA: Stencil with optimized dataflow architecture. In 2018 IEEE\/ACM Intern. Conf. on Computer-Aided Design, 1--8."},{"key":"e_1_2_1_7_1","volume-title":"2021 IEEE 29th Annual Intern. Symp. on Field-Programmable Custom Computing Machines, 204--213","author":"Chi Y.","unstructured":"Chi , Y. et al. Extending high-level synthesis for task-parallel programs . In 2021 IEEE 29th Annual Intern. Symp. on Field-Programmable Custom Computing Machines, 204--213 . Chi, Y. et al. Extending high-level synthesis for task-parallel programs. In 2021 IEEE 29th Annual Intern. Symp. on Field-Programmable Custom Computing Machines, 204--213."},{"key":"e_1_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS49936.2021.00077"},{"key":"e_1_2_1_9_1","volume-title":"2014 51st ACM\/EDAC\/IEEE Design Automation Conference, 1--6.","author":"Cong J.","unstructured":"Cong , J. et al. Accelerator-rich architectures: Opportunities and progresses . In 2014 51st ACM\/EDAC\/IEEE Design Automation Conference, 1--6. Cong, J. et al. Accelerator-rich architectures: Opportunities and progresses. In 2014 51st ACM\/EDAC\/IEEE Design Automation Conference, 1--6."},{"key":"e_1_2_1_10_1","volume-title":"Proceedings of the 2012 ACM\/IEEE Intern. Symp. on Low Power Electronics and Design, 379--384","author":"Cong J.","unstructured":"Cong , J. et al. CHARM: A composable heterogeneous accelerator-rich microprocessor . In Proceedings of the 2012 ACM\/IEEE Intern. Symp. on Low Power Electronics and Design, 379--384 . Cong, J. et al. CHARM: A composable heterogeneous accelerator-rich microprocessor. In Proceedings of the 2012 ACM\/IEEE Intern. Symp. on Low Power Electronics and Design, 379--384."},{"key":"e_1_2_1_11_1","volume-title":"Proceedings of the 2016 Intern. Symp. on Low Power Electronics and Design, 154--155","author":"Cong","unstructured":"Cong ., J., Huang , M. , Pan , P. , Wu , D. , and Zhang , P . Software infrastructure for enabling FPGA-based accelerations in data centers . In Proceedings of the 2016 Intern. Symp. on Low Power Electronics and Design, 154--155 . Cong., J., Huang, M., Pan, P., Wu, D., and Zhang, P. Software infrastructure for enabling FPGA-based accelerations in data centers. In Proceedings of the 2016 Intern. Symp. on Low Power Electronics and Design, 154--155."},{"key":"e_1_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3530775"},{"key":"e_1_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2011.2110592"},{"key":"e_1_2_1_14_1","first-page":"2","article-title":"Customizable domain-specific computing","volume":"28","author":"Cong J.","year":"2010","unstructured":"Cong , J. , Sarkar , V. , Reinman , G. , and Bui , A . Customizable domain-specific computing . IEEE Design & Test of Computers 28 , 2 ( 2010 ), 6--15. Cong, J., Sarkar, V., Reinman, G., and Bui, A. Customizable domain-specific computing. IEEE Design & Test of Computers 28, 2 (2010), 6--15.","journal-title":"IEEE Design & Test of Computers"},{"key":"e_1_2_1_15_1","volume-title":"2018 55th ACM\/ESDA\/IEEE Design Automation Conf., 1--6.","author":"Cong J.","unstructured":"Cong , J. , Wei , P. , Yu , C.H. , and Zhang , P . Automated accelerator generation and optimization with composable, parallel and pipeline architecture . In 2018 55th ACM\/ESDA\/IEEE Design Automation Conf., 1--6. Cong, J., Wei, P., Yu, C.H., and Zhang, P. Automated accelerator generation and optimization with composable, parallel and pipeline architecture. In 2018 55th ACM\/ESDA\/IEEE Design Automation Conf., 1--6."},{"key":"e_1_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3361682"},{"key":"e_1_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.1974.1050511"},{"key":"e_1_2_1_18_1","volume-title":"2011 38th Annual Intern. Symp. on Computer Architecture, 365--376","author":"Esmaeilzadeh H.","unstructured":"Esmaeilzadeh , H. et al. Dark silicon and the end of multicore scaling . In 2011 38th Annual Intern. Symp. on Computer Architecture, 365--376 . Esmaeilzadeh, H. et al. Dark silicon and the end of multicore scaling. In 2011 38th Annual Intern. Symp. on Computer Architecture, 365--376."},{"key":"e_1_2_1_19_1","volume-title":"2018 ACM\/IEEE 45th Annual Intern. Symp. on Computer Architecture, 1--14","author":"Fowers J.","unstructured":"Fowers , J. et al. A configurable cloud-scale DNN processor for real-time AI . In 2018 ACM\/IEEE 45th Annual Intern. Symp. on Computer Architecture, 1--14 . Fowers, J. et al. A configurable cloud-scale DNN processor for real-time AI. In 2018 ACM\/IEEE 45th Annual Intern. Symp. on Computer Architecture, 1--14."},{"key":"e_1_2_1_20_1","volume-title":"et al. Gemmini: An agile systolic array generator enabling systematic evaluations of deep-learning architectures. (2019)","author":"Genc H.","year":"1911","unstructured":"Genc , H. et al. Gemmini: An agile systolic array generator enabling systematic evaluations of deep-learning architectures. (2019) ; arXiv preprint arXiv: 1911 .09925 Genc, H. et al. Gemmini: An agile systolic array generator enabling systematic evaluations of deep-learning architectures. (2019); arXiv preprint arXiv:1911.09925"},{"key":"e_1_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3282307"},{"key":"e_1_2_1_22_1","volume-title":"2021 ACM\/SIGDA Intern. Symp. on Field-Programmable Gate Arrays, 145--146","author":"Huff D.","unstructured":"Huff , D. , Dai , S. , and Hanrahan , P . Clockwork: Resource-efficient static scheduling for multi-rate image processing applications on FPGAs . 2021 ACM\/SIGDA Intern. Symp. on Field-Programmable Gate Arrays, 145--146 . Huff, D., Dai, S., and Hanrahan, P. Clockwork: Resource-efficient static scheduling for multi-rate image processing applications on FPGAs. 2021 ACM\/SIGDA Intern. Symp. on Field-Programmable Gate Arrays, 145--146."},{"key":"e_1_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080246"},{"key":"e_1_2_1_24_1","volume-title":"Proceedings of the 2019 ACM\/SIGDA Intern. Symp. on Field-Programmable Gate Arrays, 242--251","author":"Lai Y-H","unstructured":"Lai , Y-H . et al. HeteroCL: A multi-paradigm programming infrastructure for software-defined reconfigurable computing . In Proceedings of the 2019 ACM\/SIGDA Intern. Symp. on Field-Programmable Gate Arrays, 242--251 . Lai, Y-H. et al. HeteroCL: A multi-paradigm programming infrastructure for software-defined reconfigurable computing. In Proceedings of the 2019 ACM\/SIGDA Intern. Symp. on Field-Programmable Gate Arrays, 242--251."},{"key":"e_1_2_1_25_1","volume-title":"et al. MLIR: A compiler infrastructure for the end of Moore's law. (2020)","author":"Lattner C.","year":"2002","unstructured":"Lattner , C. et al. MLIR: A compiler infrastructure for the end of Moore's law. (2020) ; arXiv preprint arXiv: 2002 .11054. Lattner, C. et al. MLIR: A compiler infrastructure for the end of Moore's law. (2020); arXiv preprint arXiv:2002.11054."},{"key":"e_1_2_1_26_1","volume-title":"Proceedings of the 2020 ACM\/SIGDA Intern. Symp. on Field-Programmable Gate Arrays, 51--57","author":"Li J.","unstructured":"Li , J. , Chi , Y. , and Cong , J . HeteroHalide: From image processing DSL to efficient FPGA acceleration . In Proceedings of the 2020 ACM\/SIGDA Intern. Symp. on Field-Programmable Gate Arrays, 51--57 . Li, J., Chi, Y., and Cong, J. HeteroHalide: From image processing DSL to efficient FPGA acceleration. In Proceedings of the 2020 ACM\/SIGDA Intern. Symp. on Field-Programmable Gate Arrays, 51--57."},{"key":"e_1_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201308"},{"key":"e_1_2_1_28_1","first-page":"6","article-title":"A survey of coarse-grained reconfigurable architecture and design: Taxonomy, challenges, and applications","volume":"52","author":"Liu L.","year":"2019","unstructured":"Liu , L. . A survey of coarse-grained reconfigurable architecture and design: Taxonomy, challenges, and applications . ACM Computing Surveys 52 , 6 ( 2019 ), 1--39. Liu, L. et al. A survey of coarse-grained reconfigurable architecture and design: Taxonomy, challenges, and applications. ACM Computing Surveys 52, 6 (2019), 1--39.","journal-title":"ACM Computing Surveys"},{"key":"e_1_2_1_29_1","volume-title":"2022 55th Annual IEEE\/ACM Intern. Symp. on Microarchitecture.","author":"Liu S.","unstructured":"Liu , S. et al. OverGen: Improving FPGA usability through domain-specific overlay generation . 2022 55th Annual IEEE\/ACM Intern. Symp. on Microarchitecture. Liu, S. et al. OverGen: Improving FPGA usability through domain-specific overlay generation. 2022 55th Annual IEEE\/ACM Intern. Symp. on Microarchitecture."},{"key":"e_1_2_1_30_1","volume-title":"Semiconductor design and manufacturing: Achieving leading-edge capabilities. (August 20","author":"McKinsey","year":"2020","unstructured":"McKinsey . Semiconductor design and manufacturing: Achieving leading-edge capabilities. (August 20 , 2020 ); http:\/\/bit.ly\/3g64PJr. McKinsey. Semiconductor design and manufacturing: Achieving leading-edge capabilities. (August 20, 2020); http:\/\/bit.ly\/3g64PJr."},{"key":"e_1_2_1_31_1","volume-title":"29th IEEE Annual Intern. Symp. on Field-Programmable Custom Computing Machines (May","author":"Qiao W.","year":"2021","unstructured":"Qiao , W. et al. FANS: FPGA-accelerated near-storage sorting . In 29th IEEE Annual Intern. Symp. on Field-Programmable Custom Computing Machines (May 2021 ), 106--114; http:\/\/bit.ly\/3X7cBDl. Qiao, W. et al. FANS: FPGA-accelerated near-storage sorting. In 29th IEEE Annual Intern. Symp. on Field-Programmable Custom Computing Machines (May 2021), 106--114; http:\/\/bit.ly\/3X7cBDl."},{"key":"e_1_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/2185520.2185528"},{"key":"e_1_2_1_33_1","volume-title":"2014 IEEE Intern. Symp. on Workload Characterization, 110--119","author":"Reagen B.","unstructured":"Reagen , B. Adolf , R. , Shao , Y.S. , Wei , G-Y. , and Brooks , D . Machsuite: Benchmarks for accelerator design and customized architectures . In 2014 IEEE Intern. Symp. on Workload Characterization, 110--119 . Reagen, B. Adolf, R., Shao, Y.S., Wei, G-Y., and Brooks, D. Machsuite: Benchmarks for accelerator design and customized architectures. In 2014 IEEE Intern. Symp. on Workload Characterization, 110--119."},{"key":"e_1_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISLPED.2013.6629329"},{"key":"e_1_2_1_35_1","unstructured":"Rong H. Programmatic control of a compiler for generating high-performance spatial hardware. (2017); arXiv preprint arXiv:1711.07606  Rong H. Programmatic control of a compiler for generating high-performance spatial hardware. (2017); arXiv preprint arXiv:1711.07606"},{"key":"e_1_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA45697.2020.00033"},{"key":"e_1_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2019.2943570"},{"key":"e_1_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3489517.3530409"},{"key":"e_1_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3494534"},{"key":"e_1_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15582-6_49"},{"key":"e_1_2_1_41_1","volume-title":"Proceedings of the 2021 ACM\/SIGDA Intern. Symp. on Field-Programmable Gate Arrays, 93--104","author":"Wang J.","unstructured":"Wang , J. , Guo , L. , and Cong , J . AutoSA: A polyhedral compiler for high-performance systolic arrays on FPGA . In Proceedings of the 2021 ACM\/SIGDA Intern. Symp. on Field-Programmable Gate Arrays, 93--104 . Wang, J., Guo, L., and Cong, J. AutoSA: A polyhedral compiler for high-performance systolic arrays on FPGA. In Proceedings of the 2021 ACM\/SIGDA Intern. Symp. on Field-Programmable Gate Arrays, 93--104."},{"key":"e_1_2_1_42_1","volume-title":"2017 IEEE Intern. Parallel and Distributed Processing Symp. 72--81","author":"Wang J.","unstructured":"Wang , J. , Xie , X. , and Cong , J . Communication optimization on GPU: A case study of sequence alignment algorithms . In 2017 IEEE Intern. Parallel and Distributed Processing Symp. 72--81 . Wang, J., Xie, X., and Cong, J. Communication optimization on GPU: A case study of sequence alignment algorithms. In 2017 IEEE Intern. Parallel and Distributed Processing Symp. 72--81."},{"key":"e_1_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/2684746.2689060"},{"key":"e_1_2_1_44_1","volume-title":"2021 ACM\/SIGDA Intern. Symp. on Field-Programmable Gate Arrays, 171--182","author":"Zhang Y.","unstructured":"Zhang , Y. et al. FracBNN: Accurate and FPGA-efficient binary neural networks with fractional activations . 2021 ACM\/SIGDA Intern. Symp. on Field-Programmable Gate Arrays, 171--182 . Zhang, Y. et al. FracBNN: Accurate and FPGA-efficient binary neural networks with fractional activations. 2021 ACM\/SIGDA Intern. Symp. on Field-Programmable Gate Arrays, 171--182."},{"key":"e_1_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3295500.3356210"}],"container-title":["Communications of the ACM"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3524108","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3524108","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3524108","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:31:05Z","timestamp":1750188665000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3524108"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12,20]]},"references-count":45,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2023,1]]}},"alternative-id":["10.1145\/3524108"],"URL":"https:\/\/doi.org\/10.1145\/3524108","relation":{},"ISSN":["0001-0782","1557-7317"],"issn-type":[{"value":"0001-0782","type":"print"},{"value":"1557-7317","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,12,20]]},"assertion":[{"value":"2022-12-20","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}