{"rewrite":{"id":"r_0485e85741db5d8a5816bf0e","clusterId":"c_dc01b7bd52a0bf9a9a51f831","slug":"amd-and-intel-move-pytorch-x86-optimization-into-onednn","model":"deepseek-v4-1-flash","headline":"AMD and Intel Move PyTorch x86 Optimization Into oneDNN","summary":"AMD and Intel said they will fold PyTorch optimization work for x86 CPUs into the open-source library oneDNN, making it the default acceleration path for both companies' processors. AMD will integrate its ZenDNN library into oneDNN and has joined the Unified Acceleration Foundation as a steering member. The two companies are also working together on AI Compute Extensions, a next-generation x86 instruction set aimed at matrix multiplication.","whyItMatters":"A single default library removes the split optimization path that forced PyTorch developers to choose between AMD and Intel CPUs, and it puts both companies behind one instruction set plan for AI workloads.","webCardHtml":"\u003cp\u003eThe change reaches past existing code. AMD and Intel are also working on AI Compute Extensions, an instruction set intended to speed up matrix multiplication, the core operation in deep learning workloads. PyTorch is expected to reach those features through future oneDNN updates.\u003c/p\u003e\u003cp\u003eAMD\u0026#39;s entry into the Unified Acceleration Foundation as a steering member gives it a formal role in the body that manages oneDNN, so the arrangement has a venue for continued joint development rather than a one-time handoff. Jeff McVeigh, VP and GM of Intel\u0026#39;s Data Center Strategy Programs, said developers should not have to be aware of separate software paths to get the best performance out of x86 CPUs. Robert Hormuth, Corporate VP of Architecture \u0026amp; Strategy at AMD, stressed the value of the industry uniting around common foundational technology.\u003c/p\u003e","blueskyPost":"AMD and Intel will merge PyTorch x86 optimization into oneDNN, with AMD folding ZenDNN into the shared library and taking a steering seat at the Unified Acceleration Foundation. Both are also drafting AI Compute Extensions for matrix math.","twitterPost":"AMD and Intel will consolidate PyTorch x86 optimization in oneDNN: AMD brings ZenDNN into the library and joins the Unified Acceleration Foundation as a steering member. The two are also co-developing AI Compute Extensions for matrix multiplication.","threadsPost":null,"newsletterBlurb":"AMD and Intel agreed to make oneDNN the default PyTorch acceleration library for x86 CPUs, ending the split where developers weighed separate optimization paths per vendor. AMD will move its ZenDNN work into oneDNN and has joined the Unified Acceleration Foundation as a steering member. The two are also cooperating on AI Compute Extensions, an x86 instruction set for matrix multiplication.","attributionJson":"[{\"source\":\"ASCII.jp\",\"url\":\"https://ascii.jp/elem/000/004/446/4446223/?rss\",\"title\":\"AMD and Intel Collaborate on PyTorch x86 Optimization, Integrating into \\\"oneDNN\\\" to Eliminate Ecosystem Fragmentation\"}]","lintFlagsJson":null,"lintHits":0,"costUsd":0,"inputTokens":4932,"outputTokens":730,"status":"published","repairAttempts":0,"nextRepairAt":null,"factsAttemptedAt":1793148570,"createdAt":"2026-10-28T00:44:15.000Z","publishedAt":"2026-10-28T00:48:26.000Z","updatedAt":"2026-10-28T00:48:26.000Z"},"cluster":{"id":"c_dc01b7bd52a0bf9a9a51f831","canonicalTitle":"AMDとインテルがPyTorchのx86最適化で協業、「oneDNN」に統合してエコシステムの分断解消へ","representativeArticleId":"a_9bcf228db34fa81525ab39ff","sourceCount":1,"writtenSourceCount":1,"writeAttempts":0,"isSolo":true,"entitiesJson":"{\"anime_titles\":[],\"manga_titles\":[],\"work_titles\":[],\"studios\":[\"AMD\",\"Intel\"],\"people\":[],\"type\":\"business\",\"domain\":\"other\",\"is_roundup\":false}","contentType":"news","status":"published","firstSeenAt":"2026-10-28T00:00:00.000Z","lastSeenAt":"2026-10-28T00:00:00.000Z","updatedAt":"2026-10-28T00:48:24.000Z"},"attribution":[{"source":"ASCII.jp","url":"https://ascii.jp/elem/000/004/446/4446223/?rss","title":"AMDとインテルがPyTorchのx86最適化で協業、「oneDNN」に統合してエコシステムの分断解消へ"}],"entities":{"anime_titles":[],"manga_titles":[],"work_titles":[],"studios":["AMD","Intel"],"people":[],"type":"business","domain":"other","is_roundup":false},"keyFacts":["AMD and Intel will integrate PyTorch x86 CPU optimization work into the open-source oneDNN library.","AMD will integrate its ZenDNN optimization library into oneDNN as the default x86 acceleration path.","AMD has joined the Unified Acceleration Foundation, which manages oneDNN, as a steering member.","AMD and Intel are cooperating on AI Compute Extensions, an x86 instruction set for matrix multiplication.","The effort follows recommendations from the x86 Ecosystem Advisory Group."],"pageLinks":{"healthSlugs":["amd","intel"],"storySlugs":[],"entities":[{"slug":"amd","supported":1,"disputed":0,"contradicted":0,"unverified":5,"overall":"green","story_count":7,"has_dossier":true},{"slug":"intel","supported":0,"disputed":0,"contradicted":0,"unverified":5,"overall":"unverified","story_count":5,"has_dossier":true}],"stories":[],"entitiesOk":true,"storiesOk":true}}