{"id":40399,"date":"2021-04-08T13:19:35","date_gmt":"2021-04-08T10:19:35","guid":{"rendered":"https:\/\/forklog.com\/en\/?p=40399"},"modified":"2025-08-30T13:57:48","modified_gmt":"2025-08-30T10:57:48","slug":"researchers-speed-up-neural-network-training-on-cpus-by-up-to-15x","status":"publish","type":"post","link":"https:\/\/u1f987.com\/en\/researchers-speed-up-neural-network-training-on-cpus-by-up-to-15x\/","title":{"rendered":"Researchers speed up neural network training on CPUs by up to 15x"},"content":{"rendered":"<p>Researchers at Rice University have developed a sublinear deep-learning mechanism (SLIDE) that runs on a central processor and trains neural networks 4\u201315 times faster than platforms equipped with graphical processing units. The university&#8217;s official site <a href=\\\"https:\/\/news.rice.edu\/2021\/04\/07\/rice-intel-optimize-ai-training-for-commodity-hardware-2\/\\\" target=\\\"_blank\\\" rel=\\\"noreferrer noopener nofollow\\\">reports<\/a>.<\/p>\n<p>In 2019, the research team reframed neural network training from matrix multiplication into a search problem that can be solved with hash tables.<\/p>\n<p>Subsequently, the researchers improved the algorithm\u2019s performance using vectorization accelerators and memory-optimization techniques in modern CPUs.<\/p>\n<blockquote class=\\\"wp-block-quote is-layout-flow wp-block-quote-is-layout-flow\\\">\n<p>&#8220;If you are not fixated on matrix multiplication, you can harness the power of modern processors and train artificial intelligence models 4\u201315 times faster,&#8221; said Shabnam Dagagi, co-author of the study.<\/p>\n<\/blockquote>\n<p>The project lead, Anshumali Srinivastava, associate professor of computer science, argues that using central-processing units instead of graphical accelerators will significantly reduce the cost of training neural networks.<\/p>\n<p>He added that companies spend millions of dollars per week just on training and fine-tuning AI models.<\/p>\n<p>At the end of March Arm<a href=\"https:\/\/u1f987.com\/en\/news\/robots-see-through-walls-military-adopts-microsoft-hololens-headsets-and-other-ai-news\"> introduced<\/a> the ninth generation of its mobile-processor architecture, with manufacturers focusing their efforts on boosting AI algorithm performance.<\/p>\n<p>In February 2021, the Chinese IT giant Baidu<a href=\"https:\/\/u1f987.com\/en\/news\/anthony-levandowski-closes-his-church-of-ai-ai-algorithm-predicts-covid-19-mortality-and-other-ai-news\"> held talks with investors<\/a>, who could invest funds in its new business producing AI processors for autonomous vehicles.<\/p>\n<p>Subscribe to ForkLog news on Telegram: <a href=\\\"https:\/\/t.me\/forklogAI\\\" target=\\\"_blank\\\" rel=\\\"noreferrer noopener nofollow\\\">ForkLog AI<\/a> \u2014 all the news from the AI world!<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Researchers at Rice University have developed a sublinear deep-learning mechanism (SLIDE) that runs on a central processor and trains neural networks 4\u201315 times faster than platforms with graphical accelerators.<\/p>\n","protected":false},"author":1,"featured_media":26216,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"select":"1","news_style_id":"1","cryptorium_level":"","_short_excerpt_text":"","creation_source":"","_metatest_mainpost_news_update":false,"footnotes":""},"categories":[3],"tags":[438],"class_list":["post-40399","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-news-and-analysis","tag-artificial-intelligence"],"aioseo_notices":[],"amp_enabled":true,"views":"30","promo_type":"1","layout_type":"1","short_excerpt":"","is_update":"","_links":{"self":[{"href":"https:\/\/u1f987.com\/en\/wp-json\/wp\/v2\/posts\/40399","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/u1f987.com\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/u1f987.com\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/u1f987.com\/en\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/u1f987.com\/en\/wp-json\/wp\/v2\/comments?post=40399"}],"version-history":[{"count":1,"href":"https:\/\/u1f987.com\/en\/wp-json\/wp\/v2\/posts\/40399\/revisions"}],"predecessor-version":[{"id":40400,"href":"https:\/\/u1f987.com\/en\/wp-json\/wp\/v2\/posts\/40399\/revisions\/40400"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/u1f987.com\/en\/wp-json\/wp\/v2\/media\/26216"}],"wp:attachment":[{"href":"https:\/\/u1f987.com\/en\/wp-json\/wp\/v2\/media?parent=40399"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/u1f987.com\/en\/wp-json\/wp\/v2\/categories?post=40399"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/u1f987.com\/en\/wp-json\/wp\/v2\/tags?post=40399"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}