{"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/characterising-across-stack-optimisations-for","title":"Characterising Across-Stack Optimisations for Deep Convolutional Neural Networks","arxiv_id":"1809.07196","date":"2018-09-19","proceeding":null,"authors":["Jack Turner","José Cano","Valentin Radu","Elliot J. Crowley","Michael O'Boyle","Amos Storkey"],"abstract":"Convolutional Neural Networks (CNNs) are extremely computationally demanding,\npresenting a large barrier to their deployment on resource-constrained devices.\nSince such systems are where some of their most useful applications lie (e.g.\nobstacle detection for mobile robots, vision-based medical assistive\ntechnology), significant bodies of work from both machine learning and systems\ncommunities have attempted to provide optimisations that will make CNNs\navailable to edge devices. In this paper we unify the two viewpoints in a Deep\nLearning Inference Stack and take an across-stack approach by implementing and\nevaluating the most common neural network compression techniques (weight\npruning, channel pruning, and quantisation) and optimising their parallel\nexecution with a range of programming approaches (OpenMP, OpenCL) and hardware\narchitectures (CPU, GPU). We provide comprehensive Pareto curves to instruct\ntrade-offs under constraints of accuracy, execution time, and memory space.","url_abs":"http://arxiv.org/abs/1809.07196v1","url_pdf":"http://arxiv.org/pdf/1809.07196v1.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":"characterising-across-stack-optimisations-for","repo_url":"https://github.com/jack-willturner/characterising-neural-compression","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":null,"task_name":"CPU"},{"task_slug":null,"task_name":"GPU"},{"task_slug":"neural-network-compression","task_name":"Neural Network Compression"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}