{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T16:11:14Z","timestamp":1783181474963,"version":"3.54.6"},"publisher-location":"New York, NY, USA","reference-count":29,"publisher":"ACM","license":[{"start":{"date-parts":[[2017,6,18]],"date-time":"2017-06-18T00:00:00Z","timestamp":1497744000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2017,6,18]]},"DOI":"10.1145\/3061639.3062207","type":"proceedings-article","created":{"date-parts":[[2017,6,13]],"date-time":"2017-06-13T12:18:42Z","timestamp":1497356322000},"page":"1-6","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":334,"title":["Automated Systolic Array Architecture Synthesis for High Throughput CNN Inference on FPGAs"],"prefix":"10.1145","author":[{"given":"Xuechao","family":"Wei","sequence":"first","affiliation":[{"name":"Center for Energy-efficient Computing and Applications, School of EECS, Peking University, China and Falcon Computing Solutions, Inc, Los Angeles, CA, USA and Falcon Computing, Solutions Inc."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cody Hao","family":"Yu","sequence":"additional","affiliation":[{"name":"Computer Science Department, University of California, Los Angeles, CA, USA and Falcon Computing Solutions, Inc, Los Angeles, CA, USA and Falcon Computing, Solutions Inc."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Falcon Computing Solutions, Inc, Los Angeles, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Youxiang","family":"Chen","sequence":"additional","affiliation":[{"name":"Falcon Computing Solutions, Inc, Los Angeles, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuxin","family":"Wang","sequence":"additional","affiliation":[{"name":"Falcon Computing Solutions, Inc, Los Angeles, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Han","family":"Hu","sequence":"additional","affiliation":[{"name":"Falcon Computing Solutions, Inc, Los Angeles, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yun","family":"Liang","sequence":"additional","affiliation":[{"name":"Center for Energy-efficient Computing and Applications, School of EECS, Peking University, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jason","family":"Cong","sequence":"additional","affiliation":[{"name":"Center for Energy-efficient Computing and Applications, School of EECS, Peking University, China and Computer Science Department, University of California, Los Angeles, CA, USA and Falcon Computing Solutions, Inc, Los Angeles, CA, USA and Falcon Computing Solutions Inc. and Peking University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2017,6,18]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/1854273.1854309"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/ASAP.2009.25"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/1815961.1815993"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"crossref","unstructured":"C. Farabet et al. \"CNP: An FPGA-based processor for Convolutional Networks \" in FPL 2009.  C. Farabet et al. \"CNP: An FPGA-based processor for Convolutional Networks \" in FPL 2009.","DOI":"10.1109\/FPL.2009.5272559"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"crossref","unstructured":"M. Peemen et al. \"Memory-centric accelerator design for Convolutional Neural Networks \" in ICCD 2013.  M. Peemen et al. \"Memory-centric accelerator design for Convolutional Neural Networks \" in ICCD 2013.","DOI":"10.1109\/ICCD.2013.6657019"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/2684746.2689060"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/2847263.2847276"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"crossref","unstructured":"S. I. Venieris et al. \"fpgaConvNet: A Framework for Mapping Convolutional Neural Networks on FPGAs \" in FCCM 2016.  S. I. Venieris et al. \"fpgaConvNet: A Framework for Mapping Convolutional Neural Networks on FPGAs \" in FCCM 2016.","DOI":"10.1109\/FCCM.2016.22"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/2847263.2847265"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/2966986.2967011"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3020078.3021736"},{"key":"e_1_3_2_1_12_1","unstructured":"Intel Arria 10.  Intel Arria 10."},{"key":"e_1_3_2_1_13_1","unstructured":"Xilinx Ultrascale Architecture.  Xilinx Ultrascale Architecture."},{"key":"e_1_3_2_1_14_1","unstructured":"H. T. Kung et al. Algorithms for VLSI Processor Arrays 1979.  H. T. Kung et al. Algorithms for VLSI Processor Arrays 1979."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/2684746.2689147"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"crossref","unstructured":"A. C. Jacob et al. \"Design of Throughput-Optimized Arrays from Recurrence Abstractions \" in ASAP 2010.  A. C. Jacob et al. \"Design of Throughput-Optimized Arrays from Recurrence Abstractions \" in ASAP 2010.","DOI":"10.1109\/ASAP.2010.5540753"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3020078.3021738"},{"key":"e_1_3_2_1_18_1","unstructured":"A. Krizhevsky et al. \"ImageNet Classification with Deep Convolutional Neural Networks \" in NIPS 2012.   A. Krizhevsky et al. \"ImageNet Classification with Deep Convolutional Neural Networks \" in NIPS 2012."},{"key":"e_1_3_2_1_19_1","unstructured":"K. Simonyan et al. \"Very Deep Convolutional Networks for Large-Scale Image Recognition \" arXiv 2014.  K. Simonyan et al. \"Very Deep Convolutional Networks for Large-Scale Image Recognition \" arXiv 2014."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"crossref","unstructured":"C. Szegedy et al. \"Going Deeper with Convolutions \" arXiv 2014.  C. Szegedy et al. \"Going Deeper with Convolutions \" arXiv 2014.","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654889"},{"key":"e_1_3_2_1_22_1","unstructured":"D. L. Kuck Structure of Computers and Computations. John Wiley & Sons Inc. 1978.   D. L. Kuck Structure of Computers and Computations. John Wiley & Sons Inc. 1978."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"crossref","unstructured":"S. Verdoolaege \"Isl: An Integer Set Library for the Polyhedral Model \" in ICMS 2010.   S. Verdoolaege \"Isl: An Integer Set Library for the Polyhedral Model \" in ICMS 2010.","DOI":"10.1007\/978-3-642-15582-6_49"},{"key":"e_1_3_2_1_24_1","unstructured":"Intel SDK for OpenCL Applications.  Intel SDK for OpenCL Applications."},{"key":"e_1_3_2_1_25_1","unstructured":"ROSE Compiler Infrastructure.  ROSE Compiler Infrastructure."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3020078.3021698"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"crossref","unstructured":"S. Winograd Arithmetic Complexity of Computations 1980.  S. Winograd Arithmetic Complexity of Computations 1980.","DOI":"10.1137\/1.9781611970364"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3020078.3021727"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"crossref","unstructured":"L. Lu et al. \"Evaluating Fast Algorithms for Convolutional Neural Networks on FPGAs \" in FCCM 2017.  L. Lu et al. \"Evaluating Fast Algorithms for Convolutional Neural Networks on FPGAs \" in FCCM 2017.","DOI":"10.1109\/FCCM.2017.64"}],"event":{"name":"DAC '17: The 54th Annual Design Automation Conference 2017","location":"Austin TX USA","acronym":"DAC '17","sponsor":["EDAC Electronic Design Automation Consortium","SIGDA ACM Special Interest Group on Design Automation","IEEE-CEDA","SIGBED ACM Special Interest Group on Embedded Systems"]},"container-title":["Proceedings of the 54th Annual Design Automation Conference 2017"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3061639.3062207","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3061639.3062207","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T03:36:34Z","timestamp":1750217794000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3061639.3062207"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,6,18]]},"references-count":29,"alternative-id":["10.1145\/3061639.3062207","10.1145\/3061639"],"URL":"https:\/\/doi.org\/10.1145\/3061639.3062207","relation":{},"subject":[],"published":{"date-parts":[[2017,6,18]]},"assertion":[{"value":"2017-06-18","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}