{"id":25940,"date":"2025-10-14T14:41:14","date_gmt":"2025-10-14T19:41:14","guid":{"rendered":"https:\/\/uwm.edu\/engineering\/?p=25940"},"modified":"2025-11-14T14:19:34","modified_gmt":"2025-11-14T20:19:34","slug":"gpus-edge-computing-and-the-push-for-energy-smart-ai","status":"publish","type":"post","link":"https:\/\/uwm.edu\/engineering\/gpus-edge-computing-and-the-push-for-energy-smart-ai\/","title":{"rendered":"GPUs, edge computing, and the push for energy-smart AI"},"content":{"rendered":"\n<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\n\n\n<p>GPUs that are built into larger devices process data locally \u2013 at single locations \u2013 called &#8220;the edge.&#8221; This approach saves power, speeds results, and keeps information more private because it doesn&#8217;t have to be sent to the cloud, said Roger Shen, assistant professor of electrical engineering.<\/p>\n\n\n\n<p>Edge computing can handle small, local AI models that later can contribute to larger shared models through a process called &#8220;federated learning,&#8221; while preserving data security.<\/p>\n\n\n\n<div class=\"uwm-p-notice uwm-p-notice--warning\"><div class=\"uwm-p-notice--content\"><div class=\"uwm-p-notice--title\">Making Waves of Impact<\/div><div class=\"uwm-p-notice--message\">See how computing on the &#8216;edge,&#8217; rather than in the cloud, offers speed, data privacy, and efficiency.<\/div><\/div><\/div>\n\n\n\n<figure class=\"alignleft uwm-c-img--left\"><img loading=\"lazy\" decoding=\"async\" width=\"300\" height=\"300\" src=\"https:\/\/uwm.edu\/engineering\/wp-content\/uploads\/sites\/537\/2025\/10\/GPU.jpg\" alt=\"top view of a Graphics Processing Unit (GPU)\" class=\"wp-image-25955\" srcset=\"https:\/\/uwm.edu\/engineering\/wp-content\/uploads\/sites\/537\/2025\/10\/GPU.jpg 300w, https:\/\/uwm.edu\/engineering\/wp-content\/uploads\/sites\/537\/2025\/10\/GPU-150x150.jpg 150w\" sizes=\"auto, (max-width: 300px) 100vw, 300px\" \/><figcaption>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 &#8220;at the edge&#8221; &#8211; right were the data is generated. <\/figcaption><\/figure>\n\n\n\n<p>Another key to energy savings is through better-tailored algorithms, Shen said.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\" id=\"h-a-tradeoff\"><strong>A tradeoff<\/strong><strong><\/strong><\/h3>\n\n\n\n<p>Efficient algorithms can reduce the number of calculations needed and handle larger data sets without overwhelming servers.<\/p>\n\n\n\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\n\n\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\n\n\n<p>In such a case, a small loss in accuracy is inconsequential and worth the savings in speed and energy.<\/p>\n\n\n\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\n\n\n<p>Shen has seen the payoff firsthand while working with a local company. <\/p>\n\n\n\n<p>\u201cOur job was to dig into their production data to see if there was some circumstance that explained their problem,&#8221; he said.<\/p>\n\n\n\n<p><\/p>\n","protected":false},"excerpt":{"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. GPUs &hellip;<\/p>\n","protected":false},"author":836,"featured_media":25942,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":"","uwm_wg_additional_authors":[]},"categories":[156,25],"tags":[165],"class_list":["post-25940","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-ai","category-news","tag-smarter-systems"],"yoast_head":"<!-- This site is optimized with the Yoast SEO Premium plugin v27.3 (Yoast SEO v27.3) - https:\/\/yoast.com\/product\/yoast-seo-premium-wordpress\/ -->\n<title>College of Engineering &amp; Applied Science<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/uwm.edu\/engineering\/gpus-edge-computing-and-the-push-for-energy-smart-ai\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"GPUs, edge computing, and the push for energy-smart AI\" \/>\n<meta property=\"og:description\" content=\"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. GPUs &hellip;\" \/>\n<meta property=\"og:url\" content=\"https:\/\/uwm.edu\/engineering\/gpus-edge-computing-and-the-push-for-energy-smart-ai\/\" \/>\n<meta property=\"og:site_name\" content=\"College of Engineering &amp; Applied Science\" \/>\n<meta property=\"article:published_time\" content=\"2025-10-14T19:41:14+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2025-11-14T20:19:34+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/uwm.edu\/engineering\/wp-content\/uploads\/sites\/537\/2025\/10\/Shen.CSI_.jpg\" \/>\n\t<meta property=\"og:image:width\" content=\"750\" \/>\n\t<meta property=\"og:image:height\" content=\"500\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/jpeg\" \/>\n<meta name=\"author\" content=\"Laura Otto\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"Laura Otto\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"2 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"Article\",\"@id\":\"https:\\\/\\\/uwm.edu\\\/engineering\\\/gpus-edge-computing-and-the-push-for-energy-smart-ai\\\/#article\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/uwm.edu\\\/engineering\\\/gpus-edge-computing-and-the-push-for-energy-smart-ai\\\/\"},\"author\":{\"name\":\"Laura Otto\",\"@id\":\"https:\\\/\\\/uwm.edu\\\/engineering\\\/#\\\/schema\\\/person\\\/2f360a26f3df4ff8f31b58e43d772565\"},\"headline\":\"GPUs, edge computing, and the push for energy-smart AI\",\"datePublished\":\"2025-10-14T19:41:14+00:00\",\"dateModified\":\"2025-11-14T20:19:34+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\\\/\\\/uwm.edu\\\/engineering\\\/gpus-edge-computing-and-the-push-for-energy-smart-ai\\\/\"},\"wordCount\":368,\"image\":{\"@id\":\"https:\\\/\\\/uwm.edu\\\/engineering\\\/gpus-edge-computing-and-the-push-for-energy-smart-ai\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/uwm.edu\\\/engineering\\\/wp-content\\\/uploads\\\/sites\\\/537\\\/2025\\\/10\\\/Shen.CSI_.jpg\",\"keywords\":[\"Smarter Systems\"],\"articleSection\":[\"AI\",\"News\"],\"inLanguage\":\"en-US\"},{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/uwm.edu\\\/engineering\\\/gpus-edge-computing-and-the-push-for-energy-smart-ai\\\/\",\"url\":\"https:\\\/\\\/uwm.edu\\\/engineering\\\/gpus-edge-computing-and-the-push-for-energy-smart-ai\\\/\",\"name\":\"GPUs, edge computing, and the push for energy-smart AI - College of Engineering &amp; Applied Science\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/uwm.edu\\\/engineering\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/uwm.edu\\\/engineering\\\/gpus-edge-computing-and-the-push-for-energy-smart-ai\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/uwm.edu\\\/engineering\\\/gpus-edge-computing-and-the-push-for-energy-smart-ai\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/uwm.edu\\\/engineering\\\/wp-content\\\/uploads\\\/sites\\\/537\\\/2025\\\/10\\\/Shen.CSI_.jpg\",\"datePublished\":\"2025-10-14T19:41:14+00:00\",\"dateModified\":\"2025-11-14T20:19:34+00:00\",\"author\":{\"@id\":\"https:\\\/\\\/uwm.edu\\\/engineering\\\/#\\\/schema\\\/person\\\/2f360a26f3df4ff8f31b58e43d772565\"},\"breadcrumb\":{\"@id\":\"https:\\\/\\\/uwm.edu\\\/engineering\\\/gpus-edge-computing-and-the-push-for-energy-smart-ai\\\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/uwm.edu\\\/engineering\\\/gpus-edge-computing-and-the-push-for-energy-smart-ai\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/uwm.edu\\\/engineering\\\/gpus-edge-computing-and-the-push-for-energy-smart-ai\\\/#primaryimage\",\"url\":\"https:\\\/\\\/uwm.edu\\\/engineering\\\/wp-content\\\/uploads\\\/sites\\\/537\\\/2025\\\/10\\\/Shen.CSI_.jpg\",\"contentUrl\":\"https:\\\/\\\/uwm.edu\\\/engineering\\\/wp-content\\\/uploads\\\/sites\\\/537\\\/2025\\\/10\\\/Shen.CSI_.jpg\",\"width\":750,\"height\":500,\"caption\":\"Roger Shen, assistant professor, electrical engineering, specializes in optimizing AI processing algorithms so that they use less data and make fewer calculations without losing much accuracy. This can be useful in a factory setting for automated decision-making involving products coming off the production line. Here, he's at the production line testbed at 51ÁÔÆæ's Connected Systems Institute.\"},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/uwm.edu\\\/engineering\\\/gpus-edge-computing-and-the-push-for-energy-smart-ai\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/uwm.edu\\\/engineering\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"GPUs, edge computing, and the push for energy-smart AI\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/uwm.edu\\\/engineering\\\/#website\",\"url\":\"https:\\\/\\\/uwm.edu\\\/engineering\\\/\",\"name\":\"College of Engineering &amp; Applied Science\",\"description\":\"\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/uwm.edu\\\/engineering\\\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-US\"},{\"@type\":\"Person\",\"@id\":\"https:\\\/\\\/uwm.edu\\\/engineering\\\/#\\\/schema\\\/person\\\/2f360a26f3df4ff8f31b58e43d772565\",\"name\":\"Laura Otto\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/7a25d6450ea441d1a0a92cfcac5c88d413d72cb7a72eb8721a3c4bc0b8b290f0?s=96&d=mm&r=g\",\"url\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/7a25d6450ea441d1a0a92cfcac5c88d413d72cb7a72eb8721a3c4bc0b8b290f0?s=96&d=mm&r=g\",\"contentUrl\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/7a25d6450ea441d1a0a92cfcac5c88d413d72cb7a72eb8721a3c4bc0b8b290f0?s=96&d=mm&r=g\",\"caption\":\"Laura Otto\"},\"url\":\"https:\\\/\\\/uwm.edu\\\/engineering\\\/author\\\/llhuntuwm-edu\\\/\"}]}<\/script>\n<!-- \/ Yoast SEO Premium plugin. -->","yoast_head_json":{"title":"College of Engineering &amp; Applied Science","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/uwm.edu\/engineering\/gpus-edge-computing-and-the-push-for-energy-smart-ai\/","og_locale":"en_US","og_type":"article","og_title":"GPUs, edge computing, and the push for energy-smart AI","og_description":"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. GPUs &hellip;","og_url":"https:\/\/uwm.edu\/engineering\/gpus-edge-computing-and-the-push-for-energy-smart-ai\/","og_site_name":"College of Engineering &amp; Applied Science","article_published_time":"2025-10-14T19:41:14+00:00","article_modified_time":"2025-11-14T20:19:34+00:00","og_image":[{"width":750,"height":500,"url":"https:\/\/uwm.edu\/engineering\/wp-content\/uploads\/sites\/537\/2025\/10\/Shen.CSI_.jpg","type":"image\/jpeg"}],"author":"Laura Otto","twitter_card":"summary_large_image","twitter_misc":{"Written by":"Laura Otto","Est. reading time":"2 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/uwm.edu\/engineering\/gpus-edge-computing-and-the-push-for-energy-smart-ai\/#article","isPartOf":{"@id":"https:\/\/uwm.edu\/engineering\/gpus-edge-computing-and-the-push-for-energy-smart-ai\/"},"author":{"name":"Laura Otto","@id":"https:\/\/uwm.edu\/engineering\/#\/schema\/person\/2f360a26f3df4ff8f31b58e43d772565"},"headline":"GPUs, edge computing, and the push for energy-smart AI","datePublished":"2025-10-14T19:41:14+00:00","dateModified":"2025-11-14T20:19:34+00:00","mainEntityOfPage":{"@id":"https:\/\/uwm.edu\/engineering\/gpus-edge-computing-and-the-push-for-energy-smart-ai\/"},"wordCount":368,"image":{"@id":"https:\/\/uwm.edu\/engineering\/gpus-edge-computing-and-the-push-for-energy-smart-ai\/#primaryimage"},"thumbnailUrl":"https:\/\/uwm.edu\/engineering\/wp-content\/uploads\/sites\/537\/2025\/10\/Shen.CSI_.jpg","keywords":["Smarter Systems"],"articleSection":["AI","News"],"inLanguage":"en-US"},{"@type":"WebPage","@id":"https:\/\/uwm.edu\/engineering\/gpus-edge-computing-and-the-push-for-energy-smart-ai\/","url":"https:\/\/uwm.edu\/engineering\/gpus-edge-computing-and-the-push-for-energy-smart-ai\/","name":"GPUs, edge computing, and the push for energy-smart AI - College of Engineering &amp; Applied Science","isPartOf":{"@id":"https:\/\/uwm.edu\/engineering\/#website"},"primaryImageOfPage":{"@id":"https:\/\/uwm.edu\/engineering\/gpus-edge-computing-and-the-push-for-energy-smart-ai\/#primaryimage"},"image":{"@id":"https:\/\/uwm.edu\/engineering\/gpus-edge-computing-and-the-push-for-energy-smart-ai\/#primaryimage"},"thumbnailUrl":"https:\/\/uwm.edu\/engineering\/wp-content\/uploads\/sites\/537\/2025\/10\/Shen.CSI_.jpg","datePublished":"2025-10-14T19:41:14+00:00","dateModified":"2025-11-14T20:19:34+00:00","author":{"@id":"https:\/\/uwm.edu\/engineering\/#\/schema\/person\/2f360a26f3df4ff8f31b58e43d772565"},"breadcrumb":{"@id":"https:\/\/uwm.edu\/engineering\/gpus-edge-computing-and-the-push-for-energy-smart-ai\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/uwm.edu\/engineering\/gpus-edge-computing-and-the-push-for-energy-smart-ai\/"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/uwm.edu\/engineering\/gpus-edge-computing-and-the-push-for-energy-smart-ai\/#primaryimage","url":"https:\/\/uwm.edu\/engineering\/wp-content\/uploads\/sites\/537\/2025\/10\/Shen.CSI_.jpg","contentUrl":"https:\/\/uwm.edu\/engineering\/wp-content\/uploads\/sites\/537\/2025\/10\/Shen.CSI_.jpg","width":750,"height":500,"caption":"Roger Shen, assistant professor, electrical engineering, specializes in optimizing AI processing algorithms so that they use less data and make fewer calculations without losing much accuracy. This can be useful in a factory setting for automated decision-making involving products coming off the production line. Here, he's at the production line testbed at 51ÁÔÆæ's Connected Systems Institute."},{"@type":"BreadcrumbList","@id":"https:\/\/uwm.edu\/engineering\/gpus-edge-computing-and-the-push-for-energy-smart-ai\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/uwm.edu\/engineering\/"},{"@type":"ListItem","position":2,"name":"GPUs, edge computing, and the push for energy-smart AI"}]},{"@type":"WebSite","@id":"https:\/\/uwm.edu\/engineering\/#website","url":"https:\/\/uwm.edu\/engineering\/","name":"College of Engineering &amp; Applied Science","description":"","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/uwm.edu\/engineering\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"},{"@type":"Person","@id":"https:\/\/uwm.edu\/engineering\/#\/schema\/person\/2f360a26f3df4ff8f31b58e43d772565","name":"Laura Otto","image":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/secure.gravatar.com\/avatar\/7a25d6450ea441d1a0a92cfcac5c88d413d72cb7a72eb8721a3c4bc0b8b290f0?s=96&d=mm&r=g","url":"https:\/\/secure.gravatar.com\/avatar\/7a25d6450ea441d1a0a92cfcac5c88d413d72cb7a72eb8721a3c4bc0b8b290f0?s=96&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/7a25d6450ea441d1a0a92cfcac5c88d413d72cb7a72eb8721a3c4bc0b8b290f0?s=96&d=mm&r=g","caption":"Laura Otto"},"url":"https:\/\/uwm.edu\/engineering\/author\/llhuntuwm-edu\/"}]}},"meta_fields":{"_edit_lock":["1763151587:836"],"_edit_last":["836"],"feat_img_video":[""],"feat_img_gallery":[""],"feat_img_caption":["feat-img-caption-on"],"breadcrumbs_display":["breadcrumbs-on"],"otp_nav_display":["otp-on-mobile"],"post_layout":["post-layout-theme"],"_yoast_wpseo_primary_category":["25"],"_yoast_wpseo_content_score":["60"],"_yoast_wpseo_focuskeywords":[""],"_yoast_wpseo_keywordsynonyms":[""],"_yoast_wpseo_estimated-reading-time-minutes":["2"],"_thumbnail_id":["25942"],"_yoast_indexnow_last_ping":["1763151574"],"_uwm_wg_content_review_log":["a:1:{i:0;a:5:{s:11:\"reviewer_id\";i:0;s:6:\"status\";s:5:\"reset\";s:10:\"entry_date\";s:19:\"2026-03-01 02:11:11\";s:16:\"priority_content\";s:0:\"\";s:4:\"note\";s:43:\"Content review reset at start of new cycle.\";}}"]},"_links":{"self":[{"href":"https:\/\/uwm.edu\/engineering\/wp-json\/wp\/v2\/posts\/25940","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/uwm.edu\/engineering\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/uwm.edu\/engineering\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/uwm.edu\/engineering\/wp-json\/wp\/v2\/users\/836"}],"replies":[{"embeddable":true,"href":"https:\/\/uwm.edu\/engineering\/wp-json\/wp\/v2\/comments?post=25940"}],"version-history":[{"count":8,"href":"https:\/\/uwm.edu\/engineering\/wp-json\/wp\/v2\/posts\/25940\/revisions"}],"predecessor-version":[{"id":26820,"href":"https:\/\/uwm.edu\/engineering\/wp-json\/wp\/v2\/posts\/25940\/revisions\/26820"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/uwm.edu\/engineering\/wp-json\/wp\/v2\/media\/25942"}],"wp:attachment":[{"href":"https:\/\/uwm.edu\/engineering\/wp-json\/wp\/v2\/media?parent=25940"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/uwm.edu\/engineering\/wp-json\/wp\/v2\/categories?post=25940"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/uwm.edu\/engineering\/wp-json\/wp\/v2\/tags?post=25940"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}