{"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/standing-on-the-shoulders-of-giants-hardware","title":"Standing on the Shoulders of Giants: Hardware and Neural Architecture Co-Search with Hot Start","arxiv_id":"2007.09087","date":"2020-07-17","proceeding":null,"authors":["Weiwen Jiang","Lei Yang","Sakyasingha Dasgupta","Jingtong Hu","Yiyu Shi"],"abstract":"Hardware and neural architecture co-search that automatically generates Artificial Intelligence (AI) solutions from a given dataset is promising to promote AI democratization; however, the amount of time that is required by current co-search frameworks is in the order of hundreds of GPU hours for one target hardware. This inhibits the use of such frameworks on commodity hardware. The root cause of the low efficiency in existing co-search frameworks is the fact that they start from a \"cold\" state (i.e., search from scratch). In this paper, we propose a novel framework, namely HotNAS, that starts from a \"hot\" state based on a set of existing pre-trained models (a.k.a. model zoo) to avoid lengthy training time. As such, the search time can be reduced from 200 GPU hours to less than 3 GPU hours. In HotNAS, in addition to hardware design space and neural architecture search space, we further integrate a compression space to conduct model compressing during the co-search, which creates new opportunities to reduce latency but also brings challenges. One of the key challenges is that all of the above search spaces are coupled with each other, e.g., compression may not work without hardware design support. To tackle this issue, HotNAS builds a chain of tools to design hardware to support compression, based on which a global optimizer is developed to automatically co-search all the involved search spaces. Experiments on ImageNet dataset and Xilinx FPGA show that, within the timing constraint of 5ms, neural architectures generated by HotNAS can achieve up to 5.79% Top-1 and 3.97% Top-5 accuracy gain, compared with the existing ones.","url_abs":"https://arxiv.org/abs/2007.09087v1","url_pdf":"https://arxiv.org/pdf/2007.09087v1.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":"standing-on-the-shoulders-of-giants-hardware","repo_url":"https://github.com/weiwenjiang/hotNAS-CODES20","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":null,"task_name":"GPU"},{"task_slug":"architecture-search","task_name":"Neural Architecture Search"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2007.09087","atlas_url":"https://app.syntology.ai/?focus=2007.09087","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.09087"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/weiwenjiang/hotNAS-CODES20","reach":null}],"summary":{"ran_violates":1,"ran_draft_wrong":1},"by_repo_kind":{"listed":{"samples":2,"ran":2,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":2,"samples":[{"code_sha256_prefix":"ad6032db8403f07d","entry":"is_same","repo":"weiwenjiang/hotNAS-CODES20","repo_kind":"listed","path":"Interface/CONV_PM_IF.py","file_url":"https://github.com/weiwenjiang/hotNAS-CODES20/blob/HEAD/Interface/CONV_PM_IF.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ad6032db8403f07d"}},{"code_sha256_prefix":"7a60943814ee5081","entry":"tell_conv_type","repo":"weiwenjiang/hotNAS-CODES20","repo_kind":"listed","path":"Interface/CONV_PM_IF.py","file_url":"https://github.com/weiwenjiang/hotNAS-CODES20/blob/HEAD/Interface/CONV_PM_IF.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"7a60943814ee5081"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}