{"id":200435,"date":"2025-10-14T22:38:09","date_gmt":"2025-10-14T22:38:09","guid":{"rendered":"https:\/\/www.newsbeep.com\/uk\/200435\/"},"modified":"2025-10-14T22:38:09","modified_gmt":"2025-10-14T22:38:09","slug":"gpus-edge-computing-and-the-push-for-energy-smart-ai-college-of-engineering-applied-science","status":"publish","type":"post","link":"https:\/\/www.newsbeep.com\/uk\/200435\/","title":{"rendered":"GPUs, edge computing, and the push for energy-smart AI \u2013 College of Engineering &#038; Applied Science"},"content":{"rendered":"<p>Originally designed for video games, graphics processing units (GPUs) now power much of today\u2019s AI \u2013 from voice assistants to self-driving cars. Unlike regular computer chips, GPUs have thousands of small cores that handle many simple tasks at once.<\/p>\n<p>GPUs that are built into larger devices process data locally \u2013 at single locations \u2013 called \u201cthe edge.\u201d This approach saves power, speeds results, and keeps information more private because it doesn\u2019t have to be sent to the cloud, said Roger Shen, assistant professor of electrical engineering.<\/p>\n<p>Edge computing can handle small, local AI models that later can contribute to larger shared models through a process called \u201cfederated learning,\u201d while preserving data security.<\/p>\n<p><img loading=\"lazy\" decoding=\"async\" width=\"300\" height=\"300\" src=\"https:\/\/www.newsbeep.com\/uk\/wp-content\/uploads\/2025\/10\/GPU.jpg\" alt=\"top view of a Graphics Processing Unit (GPU)\" class=\"wp-image-25955\"  \/>A GPU, just larger than the palm of your hand, was created for gaming, but can perform many simple, repetitive tasks simultaneously, accelerating mathematical calculations. They can be deployed at individual locations where they can process AI \u201cat the edge\u201d \u2013 right were the data is generated. <\/p>\n<p>Another key to energy savings is through better-tailored algorithms, Shen said.<\/p>\n<p>A tradeoff<\/p>\n<p>Efficient algorithms can reduce the number of calculations needed and handle larger data sets without overwhelming servers.<\/p>\n<p>\u201cMy focus is on the algorithm side,\u201d Shen said. \u201cThis provides a promising solution to the energy consumption issue because an embedded system is simpler \u2013 it\u2019s just focused on a specific task.\u201d<\/p>\n<p>There\u2019s always a tradeoff, Shen noted. Using less power often means a model is less precise. But not every task requires perfection. In manufacturing, for example, AI may only need to decide a yes-or-no question: \u201cIs this part defective or not?\u201d<\/p>\n<p>In such a case, a small loss in accuracy is inconsequential and worth the savings in speed and energy.<\/p>\n<p>Embedded AI processing can flag defects in real time and prevent breakdowns before they happen, shaping the next wave of smart manufacturing.<\/p>\n<p>Shen has seen the payoff firsthand. Working with battery manufacturer Clarios, his team used machine learning to analyze why individual cells that passed inspection sometimes failed when assembled into packs.<\/p>\n<p>\u201cOur job was to dig into those production data to see if there was some circumstance that explained why they weren\u2019t playing well together,\u201d Shen said.<\/p>\n","protected":false},"excerpt":{"rendered":"Originally designed for video games, graphics processing units (GPUs) now power much of today\u2019s AI \u2013 from voice&hellip;\n","protected":false},"author":2,"featured_media":200436,"comment_status":"","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[21],"tags":[4323,86,56,54,55],"class_list":{"0":"post-200435","1":"post","2":"type-post","3":"status-publish","4":"format-standard","5":"has-post-thumbnail","7":"category-computing","8":"tag-computing","9":"tag-technology","10":"tag-uk","11":"tag-united-kingdom","12":"tag-unitedkingdom"},"_links":{"self":[{"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/posts\/200435","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/comments?post=200435"}],"version-history":[{"count":0,"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/posts\/200435\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/media\/200436"}],"wp:attachment":[{"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/media?parent=200435"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/categories?post=200435"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/tags?post=200435"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}