--- title: Is x86 ready to ACE it? | daily.dev description: The x86 Ecosystem Advisory Group has published a whitepaper and specification for ACE, a new AMX accelerator type targeting AI/ML matrix multiplication... canonical: https://daily.dev/posts/is-x86-ready-to-ace-it--mwjwunws8 twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Is x86 ready to ACE it? | daily.dev og:description: The x86 Ecosystem Advisory Group has published a whitepaper and specification for ACE, a new AMX accelerator type targeting AI/ML matrix multiplication... og:url: https://daily.dev/posts/is-x86-ready-to-ace-it--mwjwunws8 og:image: https://api.daily.dev/og/posts/MwJWunWS8.png og:image:alt: Is x86 ready to ACE it? og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # Is x86 ready to ACE it? **[Hacker News](https://daily.dev/sources/hn)** · 18 min read · 0 upvotes · 0 comments ## Summary The x86 Ecosystem Advisory Group has published a whitepaper and specification for ACE, a new AMX accelerator type targeting AI/ML matrix multiplication workloads. Unlike AMX's TMUL which uses inner products, ACE uses outer product instructions and takes inputs from AVX-512 vector registers rather than tile registers, enabling larger effective tile sizes and reduced cache bandwidth demands. The piece compares ACE to Arm's SME2 across several dimensions: data type conversion/de-quantization flexibility, block scaling support for low-precision FP8 formats, and tile size efficiency. ACE leverages AVX-512's fixed 512-bit width for flexible lookup-table-based quantization, while SME2 uses a dedicated ZT0 register. Both extensions support microscaling formats for FP8. Bandwidth analysis shows ACE improves on AMX TMUL and approaches SME efficiency. No hardware implementations of ACE exist yet, but Intel and AMD may target their next CPU generations. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Similar posts on daily.dev - [Intel Posts Initial GCC Compiler Patches For AI Compute Extensions "ACE"](https://daily.dev/posts/intel-posts-initial-gcc-compiler-patches-for-ai-compute-extensions-ace--lhqzhusiq) · Phoronix · 0 upvotes · 0 comments - [Mysterious 16-Tile & 32-Tile AMX Implementations Talked Up For More Performance](https://daily.dev/posts/mysterious-16-tile-32-tile-amx-implementations-talked-up-for-more-performance-ixmyjg9w2) · Phoronix · 0 upvotes · 0 comments - [Accelerating On-Device ML Inference with ExecuTorch and Arm SME2 – PyTorch](https://daily.dev/posts/accelerating-on-device-ml-inference-with-executorch-and-arm-sme2-pytorch-wdi856qzn) · PyTorch · 0 upvotes · 0 comments - [GCC 17 Compiler Merges Initial Support For Intel/AMD AI Compute Extensions "ACE"](https://daily.dev/posts/gcc-17-compiler-merges-initial-support-for-intel-amd-ai-compute-extensions-ace--zwwfphik0) · Phoronix · 0 upvotes · 0 comments --- Tags: [#hardware](https://daily.dev/tags/hardware) [View this post on daily.dev](https://daily.dev/posts/is-x86-ready-to-ace-it--mwjwunws8) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"Is x86 ready to ACE it?","url":"https://daily.dev/posts/is-x86-ready-to-ace-it--mwjwunws8","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/is-x86-ready-to-ace-it--mwjwunws8"},"datePublished":"2026-07-14T08:37:26.350Z","dateModified":"2026-08-24T06:57:50.718Z","description":"The x86 Ecosystem Advisory Group has published a whitepaper and specification for ACE, a new AMX accelerator type targeting AI/ML matrix multiplication...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/c497830f96caa70f7abf170571d11f22?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/c497830f96caa70f7abf170571d11f22?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"Hacker News","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"Hacker News","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/hn","url":"https://daily.dev/sources/hn"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/is-x86-ready-to-ace-it--mwjwunws8","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"hardware","timeRequired":"PT18M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Hacker News","item":"https://daily.dev/sources/hn"},{"@type":"ListItem","position":3,"name":"Is x86 ready to ACE it?"}]} ```