{"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/developing-synthesis-flows-without-human","title":"Developing Synthesis Flows Without Human Knowledge","arxiv_id":"1804.05714","date":"2018-04-16","proceeding":null,"authors":["Cunxi Yu","Houping Xiao","Giovanni De Micheli"],"abstract":"Design flows are the explicit combinations of design transformations,\nprimarily involved in synthesis, placement and routing processes, to accomplish\nthe design of Integrated Circuits (ICs) and System-on-Chip (SoC). Mostly, the\nflows are developed based on the knowledge of the experts. However, due to the\nlarge search space of design flows and the increasing design complexity,\ndeveloping Intellectual Property (IP)-specific synthesis flows providing high\nQuality of Result (QoR) is extremely challenging. This work presents a fully\nautonomous framework that artificially produces design-specific synthesis flows\nwithout human guidance and baseline flows, using Convolutional Neural Network\n(CNN). The demonstrations are made by successfully designing logic synthesis\nflows of three large scaled designs.","url_abs":"http://arxiv.org/abs/1804.05714v3","url_pdf":"http://arxiv.org/pdf/1804.05714v3.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":"developing-synthesis-flows-without-human","repo_url":"https://github.com/ycunxi/FLowGen-CNNs-DAC18","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"developing-synthesis-flows-without-human","repo_url":"https://github.com/lydiawunan/lostin","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1804.05714","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}