{"id":42378,"date":"2021-08-23T09:35:48","date_gmt":"2021-08-23T09:35:48","guid":{"rendered":"http:\/\/icloud.pe\/blog\/?guid=c9d9cc93b0e826339753fdfc108c8e0a"},"modified":"2021-08-23T09:35:48","modified_gmt":"2021-08-23T09:35:48","slug":"ibm-unveils-on-chip-ai-accelerator-for-fraud-detection","status":"publish","type":"post","link":"https:\/\/icloud.pe\/blog\/ibm-unveils-on-chip-ai-accelerator-for-fraud-detection\/","title":{"rendered":"IBM unveils on-chip AI accelerator for fraud detection"},"content":{"rendered":"<p><span class=\"field field-name-field-author field-type-node-reference field-label-hidden\"><br \/>\n      <span class=\"field-item even\"><a href=\"https:\/\/www.cloudpro.co.uk\/authors\/bobby-hellard\">Bobby Hellard<\/a><\/span><br \/>\n  <\/span><\/p>\n<div class=\"field field-name-field-published-date field-type-datetime field-label-hidden\">\n<div class=\"field-items\">\n<div class=\"field-item even\"><span class=\"date-display-single\">23 Aug, 2021<\/span><\/div>\n<\/p><\/div>\n<\/div>\n<p class=\"short-teaser\">\n<a href=\"https:\/\/www.cloudpro.co.uk\/\" title=\"\" class=\"combined-link\"><\/a><\/p>\n<div class=\"field field-name-body\">\n<p><a href=\"https:\/\/www.itpro.co.uk\/tags\/ibm\" >IBM<\/a>\u00a0has unveiled its\u00a0long-awaited &#8216;Telum&#8217;\u00a0chip, built with AI inference acceleration that will allow for\u00a0<a href=\"https:\/\/www.itpro.co.uk\/tags\/fraud\" >fraud<\/a>\u00a0detection while a transaction is occurring.<\/p>\n<p>The new processor was showcased at the annual Hot Chips conference with the\u00a0first Telum-based system planned for 2022.\u00a0<\/p>\n<p><!--wysiwyg_see-related_plugin--><\/p>\n<p><span class=\"pullquote\"><span class=\"pullquote\"><\/span><\/span><\/p>\n<p>Telum is IBM&#8217;s first processor to contain &#8220;on-chip&#8221;\u00a0<a href=\"https:\/\/www.itpro.co.uk\/hardware\/358665\/ibm-unveils-the-worlds-first-quad-core-ai-accelerator-chip\" >acceleration for artificial intelligence (AI)\u00a0inference<\/a>. The tech giant spent three years developing the &#8220;breakthrough&#8221; hardware, which is designed to help customers across banking, finance, trading, insurance applications and customer interactions.\u00a0<\/p>\n<p>The processor is designed to enable applications to run efficiently where the data resides, differentiating it from traditional\u00a0<a href=\"https:\/\/www.itpro.co.uk\/startups-0\/30484\/workday-creates-startup-fund-for-enterprise-ai\" >enterprise AI<\/a>\u00a0approaches that tend to require significant memory and data movement capabilities to handle inferencing. With the accelerator in close proximity to mission-critical data and applications, however, IBM suggests that enterprises can conduct high volume inferencing for real time-sensitive transactions without invoking off-platform AI solutions, which could potentially impact performance.\u00a0<\/p>\n<p>&#8220;Today, businesses typically apply detection techniques to catch fraud after it occurs, a process that can be time-consuming and compute-intensive due to the limitations of today&#8217;s technology, particularly when fraud analysis and detection is conducted far away from mission-critical transactions and data,&#8221;\u00a0<a href=\"https:\/\/newsroom.ibm.com\/2021-08-23-IBM-Unveils-On-Chip-Accelerated-Artificial-Intelligence-Processor\" >IBM said<\/a>.\u00a0<\/p>\n<p>&#8220;Due to latency requirements, complex fraud detection often cannot be completed in real-time &#8211; meaning a bad actor could have already successfully purchased goods with a stolen credit card before the retailer is aware fraud has taken place.&#8221;<\/p>\n<p>The chip was built on 7nm extreme ultraviolet tech, created by Samsung, and features eight processor cores that have a &#8220;deep-scalar out-of-order instruction pipeline&#8221; running with more than 5GHz clock frequency. IBM said that these were optimised for the demands of heterogeneous enterprise-class workloads.<\/p>\n<p>It features a completely redesigned cache and chip-interconnection infrastructure that provides 32MB\u00a0<a href=\"https:\/\/www.itpro.co.uk\/hardware\/30353\/what-is-cache-memory\" >cache<\/a>\u00a0per core that can scale to 32 Telum chips. The dual-chip module design contains 22 billion transistors and 19 miles of wire on 17 metal layers. <\/p>\n<\/p><\/div>\n","protected":false},"excerpt":{"rendered":"<p>      Bobby Hellard<\/p>\n<p>        23 Aug, 2021    <\/p>\n<p>      IBM\u00a0has unveiled its\u00a0long-awaited &#8216;Telum&#8217;\u00a0chip, built with AI inference acceleration that will allow for\u00a0fraud\u00a0detection while a transaction is occurring.<br \/>\nThe new processor was showcased at the&#8230;<\/p>\n","protected":false},"author":403,"featured_media":0,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[],"tags":[],"class_list":["post-42378","post","type-post","status-publish","format-standard","hentry"],"_links":{"self":[{"href":"https:\/\/icloud.pe\/blog\/wp-json\/wp\/v2\/posts\/42378","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/icloud.pe\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/icloud.pe\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/icloud.pe\/blog\/wp-json\/wp\/v2\/users\/403"}],"replies":[{"embeddable":true,"href":"https:\/\/icloud.pe\/blog\/wp-json\/wp\/v2\/comments?post=42378"}],"version-history":[{"count":1,"href":"https:\/\/icloud.pe\/blog\/wp-json\/wp\/v2\/posts\/42378\/revisions"}],"predecessor-version":[{"id":42379,"href":"https:\/\/icloud.pe\/blog\/wp-json\/wp\/v2\/posts\/42378\/revisions\/42379"}],"wp:attachment":[{"href":"https:\/\/icloud.pe\/blog\/wp-json\/wp\/v2\/media?parent=42378"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/icloud.pe\/blog\/wp-json\/wp\/v2\/categories?post=42378"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/icloud.pe\/blog\/wp-json\/wp\/v2\/tags?post=42378"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}