Reaching an optimal result in any task is often the result of balancing many factors, some of which may conflict with each other, to reach the best outcome for a particular set of circumstances. Chip design is one such area that behaves this way, with High-Level Synthesis (HLS) tools balancing hundreds of parameters simultaneously to achieve an optimal chip design for a given algorithm. Balancing this many parameters is a difficult task though and, out of necessity, a \u201cgood enough\u201d approach must often be taken. But now, by adding AI into the mix, a greater degree of intelligence can be brought to this delicate balancing process.<\/p>\n\n\n\n
In a recent podcast, host Spencer Acain was joined by Russell Klein, program director for Siemens EDA’s high-level synthesis team, to examine the ways in which AI can help bring greater intelligence to the process of compiling code \u2013 be that for HLS or any other language.<\/p>\n\n\n\n
Check out the full episode here<\/a> or keep reading for some of the highlights of that conversation.<\/p>\n\n\n\n AI makes smarter choices<\/strong><\/p>\n\n\n\n In HLS tools, like Siemens EDA\u2019s Catapult, there are many \u201cswitches that can be flipped under the hood\u201d Russ says that help balance the power, performance and area requirements of a final chip design. While an experienced designer can adjust these manually thanks to years of hard-won knowledge, most of them are processed automatically through heuristics in the compiler.<\/p>\n\n\n\n Compared to AI or machine learning algorithms, heuristics are hard coded, however, only able to produce a result of \u201cif X > Y, then A else B\u201d rather than picking the most appropriate choice for a given situation. In order to make an ideal choice though, context is required; what factors are the intended use case of this chip most sensitive too? Are there additional considerations that don\u2019t appear directly in the algorithm itself that might affect decisions made on the chip design? And other similar questions. Since a simple heuristic can\u2019t account for questions like this, Russ and his team are turning to AI.<\/p>\n\n\n\n Using AI in place of and in conjunction with existing heuristics allows for a degree of automated intelligence in this decision making processes. With hundreds of parameters and millions of combinations, it would be overwhelming for a human to consider every possibility manually yet a simple heuristic may miss obvious optimizations. By using an AI algorithm instead, it is possible to achieve the best of both worlds in many ways, allowing for key context to automatically inform machine-based decision making.<\/p>\n\n\n\n How AI will change chip design<\/strong><\/p>\n\n\n\n Beyond AI enhancing heuristics, Russ believes that this type of improvement is going to be the standard going forward when it comes to coding and design work, with AI both working in the background to bring intelligence into systems that previously relied on only hard coded rules as well as supporting end users to need less specialized training and experience to contribute at a high level.<\/p>\n\n\n\n The demand for high-end chips and other similarly advanced technologies is only increasing even as the tools and products themselves grow more complex. To meet this demand, leveraging AI will increasingly become a requirement since it offers the ability to both improve the tools and flatten the learning curve, helping existing users to be more productive while also supporting more rapid additions to the work force.<\/p>\n\n\n\n Already, integrated AI solutions can help answer user questions, recommend next steps and help navigate complex UI\u2019s, with technologies like this being added to powerful industry software, training the next generation of designers and engineers will become easier then ever, as the software itself becomes both mentor and partner in the design process.<\/p>\n\n\n\n Siemens Digital Industries Software<\/strong>\u00a0helps organizations of all sizes digitally transform using software, hardware and services from the Siemens Xcelerator<\/a> business platform. Siemens\u2019 software and the comprehensive digital twin enable companies to optimize their design, engineering and manufacturing processes to turn today\u2019s ideas into the sustainable products of the future. From chips to entire systems, from product to process, across all industries.\u00a0Siemens Digital Industries Software<\/a>\u00a0\u2013 Accelerating transformation.<\/p>\n","protected":false},"excerpt":{"rendered":" Reaching an optimal result in any task is often the result of balancing many factors, some of which may conflict…<\/p>\n","protected":false},"author":82958,"featured_media":12991,"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":[12,194,2,8374],"industry":[],"product":[],"coauthors":[2461],"class_list":["post-12990","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-news","tag-artificial-intelligence","tag-digital-transformation","tag-digitalization","tag-siemens-xcelerator"],"featured_image_url":"https:\/\/blogs.sw.siemens.com\/wp-content\/uploads\/sites\/19\/2026\/03\/EDA-CPU-brand-evolution-2023-1_medium.png","_links":{"self":[{"href":"https:\/\/blogs.sw.siemens.com\/thought-leadership\/wp-json\/wp\/v2\/posts\/12990","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/blogs.sw.siemens.com\/thought-leadership\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/blogs.sw.siemens.com\/thought-leadership\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/blogs.sw.siemens.com\/thought-leadership\/wp-json\/wp\/v2\/users\/82958"}],"replies":[{"embeddable":true,"href":"https:\/\/blogs.sw.siemens.com\/thought-leadership\/wp-json\/wp\/v2\/comments?post=12990"}],"version-history":[{"count":1,"href":"https:\/\/blogs.sw.siemens.com\/thought-leadership\/wp-json\/wp\/v2\/posts\/12990\/revisions"}],"predecessor-version":[{"id":12992,"href":"https:\/\/blogs.sw.siemens.com\/thought-leadership\/wp-json\/wp\/v2\/posts\/12990\/revisions\/12992"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/blogs.sw.siemens.com\/thought-leadership\/wp-json\/wp\/v2\/media\/12991"}],"wp:attachment":[{"href":"https:\/\/blogs.sw.siemens.com\/thought-leadership\/wp-json\/wp\/v2\/media?parent=12990"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/blogs.sw.siemens.com\/thought-leadership\/wp-json\/wp\/v2\/categories?post=12990"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/blogs.sw.siemens.com\/thought-leadership\/wp-json\/wp\/v2\/tags?post=12990"},{"taxonomy":"industry","embeddable":true,"href":"https:\/\/blogs.sw.siemens.com\/thought-leadership\/wp-json\/wp\/v2\/industry?post=12990"},{"taxonomy":"product","embeddable":true,"href":"https:\/\/blogs.sw.siemens.com\/thought-leadership\/wp-json\/wp\/v2\/product?post=12990"},{"taxonomy":"author","embeddable":true,"href":"https:\/\/blogs.sw.siemens.com\/thought-leadership\/wp-json\/wp\/v2\/coauthors?post=12990"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}
\n\n\n\n