{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,21]],"date-time":"2026-08-21T11:51:13Z","timestamp":1787313073854,"version":"build-2736575974"},"publisher-location":"New York, NY, USA","reference-count":64,"publisher":"ACM","license":[{"start":{"date-parts":[[2025,2,27]],"date-time":"2025-02-27T00:00:00Z","timestamp":1740614400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-sa\/4.0\/"}],"funder":[{"name":"CDSC industrial partners"},{"name":"NSF RTML","award":["CCF-1937599"],"award-info":[{"award-number":["CCF-1937599"]}]},{"name":"JUMP 2.0 - SRC and DARPA"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,2,27]]},"DOI":"10.1145\/3706628.3708878","type":"proceedings-article","created":{"date-parts":[[2025,2,26]],"date-time":"2025-02-26T12:22:11Z","timestamp":1740572531000},"page":"103-114","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":18,"title":["Stream-HLS: Towards Automatic Dataflow Acceleration"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8301-8411","authenticated-orcid":false,"given":"Suhail","family":"Basalama","sequence":"first","affiliation":[{"name":"University of California, Los Angeles, Los Angeles, California, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2887-6963","authenticated-orcid":false,"given":"Jason","family":"Cong","sequence":"additional","affiliation":[{"name":"University of California, Los Angeles, Los Angeles, California, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,2,27]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"2024. Circuit IR Compilers and Tools. https:\/\/circt.llvm.org\/."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3489517.3530629"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3570928"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3295500.3356173"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/N-SSC.2007.4785534"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/1375581.1375595"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/1950413.1950423"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CASES.2013.6662524"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3153032"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2016.7783710"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3656401"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3240765.3240850"},{"key":"e_1_3_2_1_13_1","volume-title":"2021 IEEE 29th Annual International Symposium on Field-Programmable Custom Computing Machines (FCCM). IEEE, 204--213","author":"Chi Yuze","year":"2021","unstructured":"Yuze Chi, Licheng Guo, Jason Lau, Young-kyu Choi, Jie Wang, and Jason Cong. 2021. Extending high-level synthesis for task-parallel programs. In 2021 IEEE 29th Annual International Symposium on Field-Programmable Custom Computing Machines (FCCM). IEEE, 204--213."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/2967938.2967969"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2018.022071131"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3530775"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3240765.3240838"},{"key":"e_1_3_2_1_18_1","volume-title":"SC20: International conference for high performance computing, networking, storage and analysis. IEEE, 1--13","author":"Matteis Tiziano De","year":"2020","unstructured":"Tiziano De Matteis, Johannes de Fine Licht, and Torsten Hoefler. 2020. FBLAS: Streaming linear algebra on FPGA. In SC20: International conference for high performance computing, networking, storage and analysis. IEEE, 1--13."},{"key":"e_1_3_2_1_19_1","volume-title":"Handbook of Thin Film Deposition","author":"Dennard Robert H","unstructured":"Robert H Dennard, Jin Cai, and Arvind Kumar. 2018. A perspective on today's scaling challenges and possible future directions. In Handbook of Thin Film Deposition. Elsevier, 3--18."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCD.2018.00040"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/2601097.2601174"},{"key":"e_1_3_2_1_23_1","volume-title":"Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861","author":"Howard Andrew G","year":"2017","unstructured":"Andrew G Howard, Menglong Zhu, Bo Chen, Dmitry Kalenichenko, Weijun Wang, Tobias Weyand, Marco Andreetto, and Hartwig Adam. 2017. Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861 (2017)."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2021.3123465"},{"key":"e_1_3_2_1_25_1","volume-title":"2021 IEEE 29th Annual International Symposium on Field-Programmable Custom Computing Machines (FCCM). IEEE, 186--194","author":"Huff Dillon","year":"2021","unstructured":"Dillon Huff, Steve Dai, and Pat Hanrahan. 2021. Clockwork: Resource-efficient static scheduling for multi-rate image processing applications on FPGAs. In 2021 IEEE 29th Annual International Symposium on Field-Programmable Custom Computing Machines (FCCM). IEEE, 186--194."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/MCAS.2021.3071631"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2021.3105574"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3140659.3080246"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3296979.3192379"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3289602.3293910"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3400302.3415644"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CGO.2004.1281665"},{"key":"e_1_3_2_1_33_1","volume-title":"MLIR: A compiler infrastructure for the end of Moore's law. arXiv preprint arXiv:2002.11054","author":"Lattner Chris","year":"2020","unstructured":"Chris Lattner, Mehdi Amini, Uday Bondhugula, Albert Cohen, Andy Davis, Jacques Pienaar, River Riddle, Tatiana Shpeisman, Nicolas Vasilache, and Oleksandr Zinenko. 2020. MLIR: A compiler infrastructure for the end of Moore's law. arXiv preprint arXiv:2002.11054 (2020)."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CGO51591.2021.9370308"},{"key":"e_1_3_2_1_35_1","unstructured":"llvm. 2023. Torch-MLIR Project. https:\/\/github.com\/llvm\/torch-mlir."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/FCCM48280.2020.00029"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3623278.3624767"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/PACT52795.2021.00011"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2017.2671881"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3385412.3385974"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3445814.3446712"},{"key":"e_1_3_2_1_42_1","unstructured":"Ampl Optimization. 2024. https:\/\/ampl.com\/."},{"key":"e_1_3_2_1_43_1","unstructured":"Gurobi Optimization. 2024. https:\/\/www.gurobi.com\/downloads\/ampl-andgurobi\/."},{"key":"e_1_3_2_1_44_1","volume-title":"Polybench: The polyhedral benchmark suite. URL: http:\/\/www.cs.ucla.edu\/pouchet\/software\/polybench","author":"Pouchet Louis-No\u00ebl","year":"2012","unstructured":"Louis-No\u00ebl Pouchet and Tomofumi Yuki. 2012. Polybench: The polyhedral benchmark suite. URL: http:\/\/www.cs.ucla.edu\/pouchet\/software\/polybench (2012)."},{"key":"e_1_3_2_1_45_1","volume-title":"Automatic Hardware Pragma Insertion in High-Level Synthesis: A Non-Linear Programming Approach. arXiv preprint arXiv:2405.12304","author":"Pouget St\u00e9phane","year":"2024","unstructured":"St\u00e9phane Pouget, Louis-No\u00ebl Pouchet, and Jason Cong. 2024. Automatic Hardware Pragma Insertion in High-Level Synthesis: A Non-Linear Programming Approach. arXiv preprint arXiv:2405.12304 (2024)."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/6.591665"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAD57390.2023.10323853"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3494534"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/3373376.3378495"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/3020078.3021744"},{"key":"e_1_3_2_1_51_1","volume-title":"Attention is all you need. Advances in Neural Information Processing Systems 30","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Lukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in Neural Information Processing Systems 30 (2017)."},{"key":"e_1_3_2_1_52_1","article-title":"Stacked denoising autoencoders: Learning useful representations in a deep network with a local denoising criterion","volume":"11","author":"Vincent Pascal","year":"2010","unstructured":"Pascal Vincent, Hugo Larochelle, Isabelle Lajoie, Yoshua Bengio, Pierre-Antoine Manzagol, and L\u00e9on Bottou. 2010. Stacked denoising autoencoders: Learning useful representations in a deep network with a local denoising criterion. Journal of machine learning research 11, 12 (2010).","journal-title":"Journal of machine learning research"},{"key":"e_1_3_2_1_53_1","volume-title":"The 2021 ACM\/SIGDA International Symposium on Field-Programmable Gate Arrays. 93--104","author":"Guo Licheng","year":"2021","unstructured":"JieWang, Licheng Guo, and Jason Cong. 2021. AutoSA: A polyhedral compiler for high-performance systolic arrays on FPGA. In The 2021 ACM\/SIGDA International Symposium on Field-Programmable Gate Arrays. 93--104."},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1145\/3020078.3021730"},{"key":"e_1_3_2_1_55_1","unstructured":"AMD Xilinx. [n. d.]. Alveo U280 Data Center Accelerator Card. https:\/\/www. xilinx.com\/publications\/product-briefs\/alveo-u280-product-brief.pdf."},{"key":"e_1_3_2_1_56_1","unstructured":"AMD Xilinx. 2023. Merlin. https:\/\/github.com\/Xilinx\/merlin-compiler."},{"key":"e_1_3_2_1_57_1","unstructured":"AMD Xilinx. 2023. Vitis High-Level Synthesis. https:\/\/www.xilinx.com\/products\/design-tools\/vitis.html."},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA53966.2022.00060"},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1145\/3617232.3624850"},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1145\/3603165.3607390"},{"key":"e_1_3_2_1_61_1","volume-title":"An Optimizing Framework on MLIR for Efficient FPGA-based Accelerator Generation. In 2024 IEEE International Symposium on High-Performance Computer Architecture (HPCA).","author":"Zhang Weichuang","year":"2024","unstructured":"Weichuang Zhang, Jieru Zhao, Guan Shen, Quan Chen, Chen Chen, and Minyi Guo. 2024. An Optimizing Framework on MLIR for Efficient FPGA-based Accelerator Generation. In 2024 IEEE International Symposium on High-Performance Computer Architecture (HPCA)."},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1145\/3431920.3439296"},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAD.2017.8203809"},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1109\/FPL57034.2022.00044"}],"event":{"name":"FPGA '25: The 2025 ACM\/SIGDA International Symposium on Field Programmable Gate Arrays","location":"Monterey CA USA","acronym":"FPGA '25","sponsor":["SIGDA ACM Special Interest Group on Design Automation"]},"container-title":["Proceedings of the 2025 ACM\/SIGDA International Symposium on Field Programmable Gate Arrays"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3706628.3708878","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3706628.3708878","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T21:53:21Z","timestamp":1755899601000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3706628.3708878"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2,27]]},"references-count":64,"alternative-id":["10.1145\/3706628.3708878","10.1145\/3706628"],"URL":"https:\/\/doi.org\/10.1145\/3706628.3708878","relation":{},"subject":[],"published":{"date-parts":[[2025,2,27]]},"assertion":[{"value":"2025-02-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}