{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T22:42:33Z","timestamp":1781908953072,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":43,"publisher":"ACM","license":[{"start":{"date-parts":[[2019,2,20]],"date-time":"2019-02-20T00:00:00Z","timestamp":1550620800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"CRISP one of six centers in JUMP a Semiconductor Research Corporation (SRC) program sponsored by DARPA"},{"name":"NSF\/Intel CAPA Award","award":["1723773"],"award-info":[{"award-number":["1723773"]}]},{"name":"DARPA Young Faculty Award","award":["D15AP00096"],"award-info":[{"award-number":["D15AP00096"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2019,2,20]]},"DOI":"10.1145\/3289602.3293910","type":"proceedings-article","created":{"date-parts":[[2019,2,22]],"date-time":"2019-02-22T22:12:13Z","timestamp":1550873533000},"page":"242-251","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":122,"title":["HeteroCL"],"prefix":"10.1145","author":[{"given":"Yi-Hsiang","family":"Lai","sequence":"first","affiliation":[{"name":"Cornell University, Ithaca, NY, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuze","family":"Chi","sequence":"additional","affiliation":[{"name":"University of California, Los Angeles, Los Angeles, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuwei","family":"Hu","sequence":"additional","affiliation":[{"name":"Cornell University, Ithaca, NY, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jie","family":"Wang","sequence":"additional","affiliation":[{"name":"University of California, Los Angeles, Los Angeles, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cody Hao","family":"Yu","sequence":"additional","affiliation":[{"name":"University of California, Los Angeles & Falcon Computing Solutions, Inc., Los Angeles, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuan","family":"Zhou","sequence":"additional","affiliation":[{"name":"Cornell University, Ithaca, NY, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jason","family":"Cong","sequence":"additional","affiliation":[{"name":"University of California, Los Angeles, Los Angeles, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhiru","family":"Zhang","sequence":"additional","affiliation":[{"name":"Cornell University, Ithaca, NY, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2019,2,20]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems. arXiv preprint arXiv:1603.04467","author":"Abadi M.","year":"2016","unstructured":"M. Abadi , A. Agarwal , P. Barham , E. Brevdo , Z. Chen , C. Citro , G. S. Corrado , A. Davis , J. Dean , M. Devin , TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems. arXiv preprint arXiv:1603.04467 , 2016 . M. Abadi, A. Agarwal, P. Barham, E. Brevdo, Z. Chen, C. Citro, G. S. Corrado, A. Davis, J. Dean, M. Devin, et al. TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems. arXiv preprint arXiv:1603.04467, 2016."},{"key":"e_1_3_2_1_2_1","volume-title":"A Scalable FPGA Architecture for Nonnegative Least Squares Problems. Int'l Conf. on Field Programmable Logic and Applications (FPL)","author":"Althoff A.","year":"2015","unstructured":"A. Althoff and R. Kastner . A Scalable FPGA Architecture for Nonnegative Least Squares Problems. Int'l Conf. on Field Programmable Logic and Applications (FPL) , 2015 . A. Althoff and R. Kastner. A Scalable FPGA Architecture for Nonnegative Least Squares Problems. Int'l Conf. on Field Programmable Logic and Applications (FPL), 2015."},{"key":"e_1_3_2_1_3_1","volume-title":"Tiramisu: A Code Optimization Framework for High Performance Systems. arXiv preprint arXiv:1804.10694","author":"Baghdadi R.","year":"2018","unstructured":"R. Baghdadi , J. Ray , M. B. Romdhane , E. Del Sozzo , P. Suriana , S. Kamil , and S. Amarasinghe . Tiramisu: A Code Optimization Framework for High Performance Systems. arXiv preprint arXiv:1804.10694 , 2018 . R. Baghdadi, J. Ray, M. B. Romdhane, E. Del Sozzo, P. Suriana, S. Kamil, and S. Amarasinghe. Tiramisu: A Code Optimization Framework for High Performance Systems. arXiv preprint arXiv:1804.10694, 2018."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/1941487.1941507"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/1950413.1950423"},{"key":"e_1_3_2_1_6_1","volume-title":"TVM: End-to-End Optimization Stack for Deep Learning. arXiv preprint arXiv:1802.04799","author":"Chen T.","year":"2018","unstructured":"T. Chen , T. Moreau , Z. Jiang , H. Shen , E. Yan , L. Wang , Y. Hu , L. Ceze , C. Guestrin , and A. Krishnamurthy . TVM: End-to-End Optimization Stack for Deep Learning. arXiv preprint arXiv:1802.04799 , 2018 . T. Chen, T. Moreau, Z. Jiang, H. Shen, E. Yan, L. Wang, Y. Hu, L. Ceze, C. Guestrin, and A. Krishnamurthy. TVM: End-to-End Optimization Stack for Deep Learning. arXiv preprint arXiv:1802.04799, 2018."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3240765.3240850"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2011.04.217"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2010.36"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/2593069.2596667"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/2934583.2953984"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2011.2110592"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3240765.3240838"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3195970.3195999"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2211477"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/2000064.2000108"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/2601097.2601174"},{"key":"e_1_3_2_1_18_1","volume-title":"Is High Level Synthesis Ready for Business? A Computational Finance Case Study. Int'l Conf. on Field Programmable Technology (FPT)","author":"Inggs G.","year":"2014","unstructured":"G. Inggs , S. Fleming , D. Thomas , and W. Luk . Is High Level Synthesis Ready for Business? A Computational Finance Case Study. Int'l Conf. on Field Programmable Technology (FPT) , 2014 . G. Inggs, S. Fleming, D. Thomas, and W. Luk. Is High Level Synthesis Ready for Business? A Computational Finance Case Study. Int'l Conf. on Field Programmable Technology (FPT), 2014."},{"key":"e_1_3_2_1_19_1","unstructured":"Intel. Xeon+FPGA Platform for the Data Center. https:\/\/www.ece.cmu.edu\/calcm\/carl\/lib\/exe\/fetch.php? media=carl15-gupta.pdf.  Intel. Xeon+FPGA Platform for the Data Center. https:\/\/www.ece.cmu.edu\/calcm\/carl\/lib\/exe\/fetch.php? media=carl15-gupta.pdf."},{"key":"e_1_3_2_1_20_1","volume-title":"Intel Math Kernel Library","year":"2007","unstructured":"Intel. Intel Math Kernel Library . 2007 . Intel. Intel Math Kernel Library. 2007."},{"key":"e_1_3_2_1_21_1","volume-title":"Intel High Level Synthesis Compiler User Guide","year":"2017","unstructured":"Intel. Intel High Level Synthesis Compiler User Guide . 2017 . Intel. Intel High Level Synthesis Compiler User Guide. 2017."},{"key":"e_1_3_2_1_22_1","volume-title":"Systems, Languages, and Applications","author":"Kjolstad F.","year":"2017","unstructured":"F. Kjolstad , S. Kamil , S. Chou , D. Lugato , and S. Amarasinghe . The Tensor Algebra Compiler. Intl'l Conf. on Object-Oriented Programming , Systems, Languages, and Applications , 2017 . F. Kjolstad, S. Kamil, S. Chou, D. Lugato, and S. Amarasinghe. The Tensor Algebra Compiler. Intl'l Conf. on Object-Oriented Programming, Systems, Languages, and Applications, 2017."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3192366.3192379"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2016.20"},{"key":"e_1_3_2_1_25_1","volume-title":"Sparse Matrix Proceedings","author":"Kung H.","year":"1979","unstructured":"H. Kung and C. E. Leiserson . Systolic Arrays (for VLSI) . Sparse Matrix Proceedings , 1979 . H. Kung and C. E. Leiserson. Systolic Arrays (for VLSI). Sparse Matrix Proceedings, 1979."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2015.2394802"},{"key":"e_1_3_2_1_28_1","volume-title":"VTA: An Open Hardware-Software Stack for Deep Learning. arXiv preprint arXiv:1807.04188","author":"Moreau T.","year":"2018","unstructured":"T. Moreau , T. Chen , Z. Jiang , L. Ceze , C. Guestrin , and A. Krishnamurthy . VTA: An Open Hardware-Software Stack for Deep Learning. arXiv preprint arXiv:1807.04188 , 2018 . T. Moreau, T. Chen, Z. Jiang, L. Ceze, C. Guestrin, and A. Krishnamurthy. VTA: An Open Hardware-Software Stack for Deep Learning. arXiv preprint arXiv:1807.04188, 2018."},{"key":"e_1_3_2_1_29_1","volume-title":"AWS Public Sector Summit","author":"Pellerin D.","year":"2017","unstructured":"D. Pellerin . Fpga accelerated computing using aws f1 instances . AWS Public Sector Summit , 2017 . D. Pellerin. Fpga accelerated computing using aws f1 instances. AWS Public Sector Summit, 2017."},{"key":"e_1_3_2_1_30_1","volume-title":"The Polyhedral Benchmark Suite. URL: http:\/\/www.cs.ucla.edu\/pouchet\/software\/polybench","author":"Pouchet L.-N.","year":"2012","unstructured":"L.-N. Pouchet . Polybench : The Polyhedral Benchmark Suite. URL: http:\/\/www.cs.ucla.edu\/pouchet\/software\/polybench , 2012 . L.-N. Pouchet. Polybench: The Polyhedral Benchmark Suite. URL: http:\/\/www.cs.ucla.edu\/pouchet\/software\/polybench, 2012."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3107953"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/2499370.2462176"},{"key":"e_1_3_2_1_33_1","volume-title":"Programmatic Control of a Compiler for Generating High-Performance Spatial Hardware. arXiv preprint arXiv:1711.07606","author":"Rong H.","year":"2017","unstructured":"H. Rong . Programmatic Control of a Compiler for Generating High-Performance Spatial Hardware. arXiv preprint arXiv:1711.07606 , 2017 . H. Rong. Programmatic Control of a Compiler for Generating High-Performance Spatial Hardware. arXiv preprint arXiv:1711.07606, 2017."},{"key":"e_1_3_2_1_34_1","volume-title":"Hot & Spicy: Improving Productivity with Python and HLS for FPGAs. IEEE Symp. on Field Programmable Custom Computing Machines (FCCM)","author":"Skalicky S.","year":"2018","unstructured":"S. Skalicky , J. Monson , A. Schmidt , and M. French . Hot & Spicy: Improving Productivity with Python and HLS for FPGAs. IEEE Symp. on Field Programmable Custom Computing Machines (FCCM) , 2018 . S. Skalicky, J. Monson, A. Schmidt, and M. French. Hot & Spicy: Improving Productivity with Python and HLS for FPGAs. IEEE Symp. on Field Programmable Custom Computing Machines (FCCM), 2018."},{"key":"e_1_3_2_1_35_1","volume-title":"A Study of Data Partitioning on OpenCL-Based FPGAs. Int'l Conf. on Field Programmable Logic and Applications (FPL)","author":"Wang Z.","year":"2015","unstructured":"Z. Wang , B. He , and W. Zhang . A Study of Data Partitioning on OpenCL-Based FPGAs. Int'l Conf. on Field Programmable Logic and Applications (FPL) , 2015 . Z. Wang, B. He, and W. Zhang. A Study of Data Partitioning on OpenCL-Based FPGAs. Int'l Conf. on Field Programmable Logic and Applications (FPL), 2015."},{"key":"e_1_3_2_1_36_1","volume-title":"Mol. Biol","author":"Waterman M.","year":"1981","unstructured":"M. Waterman . Identification of Common Molecular Subsequence . Mol. Biol , 1981 . M. Waterman. Identification of Common Molecular Subsequence. Mol. Biol, 1981."},{"key":"e_1_3_2_1_37_1","volume-title":"DLVM: A Modern Compiler Infrastructure for Deep Learning. arXiv preprint arXiv:1711.03016","author":"Wei R.","year":"2017","unstructured":"R. Wei , V. Adve , and L. Schwartz . DLVM: A Modern Compiler Infrastructure for Deep Learning. arXiv preprint arXiv:1711.03016 , 2017 . R. Wei, V. Adve, and L. Schwartz. DLVM: A Modern Compiler Infrastructure for Deep Learning. arXiv preprint arXiv:1711.03016, 2017."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3061639.3062207"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/1498765.1498785"},{"key":"e_1_3_2_1_40_1","volume-title":"Vivado Design Suite User Guide: High-Level Synthesis","author":"Xilinx Inc.","year":"2012","unstructured":"Xilinx Inc. Vivado Design Suite User Guide: High-Level Synthesis . 2012 . Xilinx Inc. Vivado Design Suite User Guide: High-Level Synthesis. 2012."},{"key":"e_1_3_2_1_41_1","volume-title":"HotCloud","author":"Zaharia M.","year":"2010","unstructured":"M. Zaharia , M. Chowdhury , M. J. Franklin , S. Shenker , and I. Stoica . Spark: Cluster Computing with Working Sets . HotCloud , 2010 . M. Zaharia, M. Chowdhury, M. J. Franklin, S. Shenker, and I. Stoica. Spark: Cluster Computing with Working Sets. HotCloud, 2010."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3020078.3021741"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3174243.3174255"}],"event":{"name":"FPGA '19: The 2019 ACM\/SIGDA International Symposium on Field-Programmable Gate Arrays","location":"Seaside CA USA","acronym":"FPGA '19","sponsor":["SIGDA ACM Special Interest Group on Design Automation"]},"container-title":["Proceedings of the 2019 ACM\/SIGDA International Symposium on Field-Programmable Gate Arrays"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3289602.3293910","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3289602.3293910","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T01:02:06Z","timestamp":1750208526000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3289602.3293910"}},"subtitle":["A Multi-Paradigm Programming Infrastructure for Software-Defined Reconfigurable Computing"],"short-title":[],"issued":{"date-parts":[[2019,2,20]]},"references-count":43,"alternative-id":["10.1145\/3289602.3293910","10.1145\/3289602"],"URL":"https:\/\/doi.org\/10.1145\/3289602.3293910","relation":{},"subject":[],"published":{"date-parts":[[2019,2,20]]},"assertion":[{"value":"2019-02-20","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}