{"id":583042,"date":"2026-07-13T08:39:16","date_gmt":"2026-07-13T08:39:16","guid":{"rendered":"https:\/\/www.europesays.com\/ie\/583042\/"},"modified":"2026-07-13T08:39:16","modified_gmt":"2026-07-13T08:39:16","slug":"chinas-optical-chip-breakthrough-boosts-ai-speed-100-fold-using-fraction-of-compute-power","status":"publish","type":"post","link":"https:\/\/www.europesays.com\/ie\/583042\/","title":{"rendered":"China\u2019s optical chip breakthrough boosts AI speed 100-fold using fraction of compute power"},"content":{"rendered":"<p>Chinese researchers have developed a new all-optical interconnect system linking standard electronic chips, boosting <a target=\"_self\" class=\"e1yy41x40 ef9u0v01 css-1ankfgb ecgc78b0\" href=\"https:\/\/www.scmp.com\/topics\/artificial-intelligence?module=inline&amp;pgtype=article\" title=\"\" data-qa=\"BaseLink-renderAnchor-StyledAnchor\" rel=\"nofollow noopener\">AI<\/a> distributed inference speeds by over 100 times while using just one-ninth of the typical computational resources.<\/p>\n<p datatype=\"p\" data-qa=\"Component-Component\" class=\"e8zc9q40 css-1c6uqr6 ec74h0k1\">AI models are permeating ever more applications, expanding the industry\u2019s appetite for computational power. The conventional response has been to pile on more GPUs and build ever-larger data centres in a seemingly endless race for energy and brute force.<\/p>\n<p>But a new study from <a target=\"_self\" class=\"e1yy41x40 ef9u0v01 css-1ankfgb ecgc78b0\" href=\"https:\/\/www.scmp.com\/topics\/peking-university?module=inline&amp;pgtype=article\" title=\"\" data-qa=\"BaseLink-renderAnchor-StyledAnchor\" rel=\"nofollow noopener\">Peking University<\/a> suggests a radically different path: by optically linking chips with specific algorithms, they boost inference speeds by a factor of over 100 while slashing compute needs to just one-ninth.<\/p>\n<p datatype=\"p\" data-qa=\"Component-Component\" class=\"e8zc9q40 css-1c6uqr6 ec74h0k1\">The work was published in the journal National Science Review, and its corresponding authors include Shu Haowen and Wang Xingjun from Peking University.<\/p>\n<p>The team\u2019s \u201cLego\u201d building blocks were field-programmable gate array (FPGA) chips: programmable devices widely used in fields that demand high parallel-processing ability, such as missile guidance, <a target=\"_self\" class=\"e1yy41x40 ef9u0v01 css-1ankfgb ecgc78b0\" href=\"https:\/\/www.scmp.com\/topics\/self-driving-cars-autonomous-vehicles?module=inline&amp;pgtype=article\" title=\"\" data-qa=\"BaseLink-renderAnchor-StyledAnchor\" rel=\"nofollow noopener\">autonomous driving<\/a> and data centres.<\/p>\n<p>Space computing: what is it, why move computing into orbit and where does China stand?<\/p>\n<p datatype=\"p\" data-qa=\"Component-Component\" class=\"e8zc9q40 css-1c6uqr6 ec74h0k1\">The \u201cjoints\u201d connecting these FPGAs are two custom-designed communication hardware components. The first is a silicon photonic transceiver chip running at 400 gigabits per second, responsible for converting electrical signals to optical and vice versa.<\/p>\n","protected":false},"excerpt":{"rendered":"Chinese researchers have developed a new all-optical interconnect system linking standard electronic chips, boosting AI distributed inference speeds&hellip;\n","protected":false},"author":2,"featured_media":583043,"comment_status":"","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"footnotes":"","_share_on_mastodon":"0"},"categories":[261],"tags":[291,247736,289,290,2625,247733,444,18,247735,20102,19,17,51959,247734,24390,247732,24393,247737,82],"class_list":["post-583042","post","type-post","status-publish","format-standard","has-post-thumbnail","category-artificial-intelligence","tag-ai","tag-ai-processing-speed","tag-artificial-intelligence","tag-artificialintelligence","tag-chinese-scientists","tag-computational-power","tag-data-centres","tag-eire","tag-fpga-chips","tag-gpu","tag-ie","tag-ireland","tag-national-science-review","tag-optical-modules","tag-peking-university","tag-professor-shu-haowen","tag-professor-wang-xingjun","tag-silicon-photonic-transceiver-chip","tag-technology"],"share_on_mastodon":{"url":"","error":""},"_links":{"self":[{"href":"https:\/\/www.europesays.com\/ie\/wp-json\/wp\/v2\/posts\/583042","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.europesays.com\/ie\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.europesays.com\/ie\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.europesays.com\/ie\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/www.europesays.com\/ie\/wp-json\/wp\/v2\/comments?post=583042"}],"version-history":[{"count":0,"href":"https:\/\/www.europesays.com\/ie\/wp-json\/wp\/v2\/posts\/583042\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.europesays.com\/ie\/wp-json\/wp\/v2\/media\/583043"}],"wp:attachment":[{"href":"https:\/\/www.europesays.com\/ie\/wp-json\/wp\/v2\/media?parent=583042"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.europesays.com\/ie\/wp-json\/wp\/v2\/categories?post=583042"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.europesays.com\/ie\/wp-json\/wp\/v2\/tags?post=583042"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}