{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/tactics-to-directly-map-cnn-graphs-on","title":"Tactics to Directly Map CNN graphs on Embedded FPGAs","arxiv_id":"1712.04322","date":"2017-11-20","proceeding":null,"authors":["Kamel Abdelouahab","Maxime Pelcat","Jocelyn Sérot","Cédric Bourrasset","François Berry","Jocelyn Serot"],"abstract":"Deep Convolutional Neural Networks (CNNs) are the state-of-the-art in image\nclassification. Since CNN feed forward propagation involves highly regular\nparallel computation, it benefits from a significant speed-up when running on\nfine grain parallel programmable logic devices. As a consequence, several\nstudies have proposed FPGA-based accelerators for CNNs. However, because of the\nlarge computationalpower required by CNNs, none of the previous studies has\nproposed a direct mapping of the CNN onto the physical resources of an FPGA,\nallocating each processing actor to its own hardware instance.In this paper, we\ndemonstrate the feasibility of the so called direct hardware mapping (DHM) and\ndiscuss several tactics we explore to make DHM usable in practice. As a proof\nof concept, we introduce the HADDOC2 open source tool, that automatically\ntransforms a CNN description into a synthesizable hardware description with\nplatform-independent direct hardware mapping.","url_abs":"http://arxiv.org/abs/1712.04322v1","url_pdf":"http://arxiv.org/pdf/1712.04322v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"tactics-to-directly-map-cnn-graphs-on","repo_url":"https://github.com/marph91/pocket-cnn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}