{"id":187,"date":"2019-07-16T16:32:00","date_gmt":"2019-07-16T20:32:00","guid":{"rendered":"https:\/\/blogs.sw.siemens.com\/hlsdesign-verification\/?p=187"},"modified":"2021-07-15T16:33:09","modified_gmt":"2021-07-15T20:33:09","slug":"power-is-limiting-machine-learning-deployments","status":"publish","type":"post","link":"https:\/\/blogs.stage.sw.siemens.com\/hlsdesign-verification\/2019\/07\/16\/power-is-limiting-machine-learning-deployments\/","title":{"rendered":"Power Is Limiting Machine Learning Deployments"},"content":{"rendered":"\n<p>Excerpt from article: \u201c<a href=\"https:\/\/semiengineering.com\/power-limitations-of-machine-learning\/\" target=\"_blank\" rel=\"noreferrer noopener\">Power Is Limiting Machine Learning Deployments<\/a>\u201d<\/p>\n\n\n\n<blockquote class=\"wp-block-quote is-layout-flow wp-block-quote-is-layout-flow\"><p>The total amount of power consumed for machine learning tasks is staggering. Until a few years ago we did not have computers powerful enough to run many of the algorithms, but the repurposing of the GPU gave the industry the horsepower that it needed.<\/p><p>The problem is that the GPU is not well suited to the task, and most of the power consumed is waste. While&nbsp;<a href=\"https:\/\/semiengineering.com\/knowledge_centers\/artificial-intelligence\/machine-learning\/\" target=\"_blank\" rel=\"noopener\">machine learning<\/a>&nbsp;has provided many benefits, much bigger gains will come from pushing machine learning to the edge. To get there, power must be addressed.<\/p><p>\u201cYou read about how datacenters may consume 5% of the energy today,\u201d says Ron Lowman, product marketing manager for Artificial Intelligence at&nbsp;<a href=\"https:\/\/semiengineering.com\/entities\/synopsys-inc\/\" target=\"_blank\" rel=\"noopener\">Synopsys<\/a>. \u201cThis may move to over 20% or even as high as 40%. There is a dramatic reason to reduce chipset power consumption for the datacenter or to move it to the edge.\u201d<\/p><p>Learning is compute-intensive. \u201cThere are two parts to learning,\u201d says Mike Fingeroff, high-level synthesis technologist at <a href=\"https:\/\/semiengineering.com\/entities\/mentor-a-siemens-business\/\" target=\"_blank\" rel=\"noreferrer noopener\">Siemens EDA<\/a>. \u201cFirst, the training includes running the feed-forward (inference engine) part of the network. Then, the back-propagation of the error to adjust the weights uses gradient descent algorithms that require massive amounts of matrix manipulations.\u201d<\/p><\/blockquote>\n\n\n\n<p>Read the entire article on <a href=\"https:\/\/semiengineering.com\/power-limitations-of-machine-learning\/\" target=\"_blank\" rel=\"noreferrer noopener\">SemiEngineering<\/a> originally published on July 16th, 2019.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Excerpt from article: \u201cPower Is Limiting Machine Learning Deployments\u201d The total amount of power consumed for machine learning tasks is&#8230;<\/p>\n","protected":false},"author":77876,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"spanish_translation":"","french_translation":"","german_translation":"","italian_translation":"","polish_translation":"","japanese_translation":"","chinese_translation":"","footnotes":""},"categories":[1],"tags":[302,324,402],"industry":[],"product":[176],"coauthors":[349],"class_list":["post-187","post","type-post","status-publish","format-standard","hentry","category-news","tag-machine-learning","tag-ml","tag-power","product-powerpro"],"_links":{"self":[{"href":"https:\/\/blogs.stage.sw.siemens.com\/hlsdesign-verification\/wp-json\/wp\/v2\/posts\/187","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/blogs.stage.sw.siemens.com\/hlsdesign-verification\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/blogs.stage.sw.siemens.com\/hlsdesign-verification\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/blogs.stage.sw.siemens.com\/hlsdesign-verification\/wp-json\/wp\/v2\/users\/77876"}],"replies":[{"embeddable":true,"href":"https:\/\/blogs.stage.sw.siemens.com\/hlsdesign-verification\/wp-json\/wp\/v2\/comments?post=187"}],"version-history":[{"count":2,"href":"https:\/\/blogs.stage.sw.siemens.com\/hlsdesign-verification\/wp-json\/wp\/v2\/posts\/187\/revisions"}],"predecessor-version":[{"id":189,"href":"https:\/\/blogs.stage.sw.siemens.com\/hlsdesign-verification\/wp-json\/wp\/v2\/posts\/187\/revisions\/189"}],"wp:attachment":[{"href":"https:\/\/blogs.stage.sw.siemens.com\/hlsdesign-verification\/wp-json\/wp\/v2\/media?parent=187"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/blogs.stage.sw.siemens.com\/hlsdesign-verification\/wp-json\/wp\/v2\/categories?post=187"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/blogs.stage.sw.siemens.com\/hlsdesign-verification\/wp-json\/wp\/v2\/tags?post=187"},{"taxonomy":"industry","embeddable":true,"href":"https:\/\/blogs.stage.sw.siemens.com\/hlsdesign-verification\/wp-json\/wp\/v2\/industry?post=187"},{"taxonomy":"product","embeddable":true,"href":"https:\/\/blogs.stage.sw.siemens.com\/hlsdesign-verification\/wp-json\/wp\/v2\/product?post=187"},{"taxonomy":"author","embeddable":true,"href":"https:\/\/blogs.stage.sw.siemens.com\/hlsdesign-verification\/wp-json\/wp\/v2\/coauthors?post=187"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}