--- title: Towards fearless SIMD, 7 years later | daily.dev description: A deep-dive revisiting the state of SIMD programming in Rust seven years after an earlier influential post on the topic. The author, working on the... canonical: https://daily.dev/posts/towards-fearless-simd-7-years-later-tq0m1xyys twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Towards fearless SIMD, 7 years later | daily.dev og:description: A deep-dive revisiting the state of SIMD programming in Rust seven years after an earlier influential post on the topic. The author, working on the... og:url: https://daily.dev/posts/towards-fearless-simd-7-years-later-tq0m1xyys og:image: https://api.daily.dev/og/posts/tq0m1xyYs.png og:image:alt: Towards fearless SIMD, 7 years later 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. # Towards fearless SIMD, 7 years later **[Linebender](https://daily.dev/sources/linebender)** · 12 min read · 0 upvotes · 0 comments ## Summary A deep-dive revisiting the state of SIMD programming in Rust seven years after an earlier influential post on the topic. The author, working on the Linebender/Vello CPU/GPU hybrid renderer, walks through a sigmoid function example implemented via hand-written intrinsics, the pulp crate, and a new fearless_simd prototype. Topics covered include the unsafe nature of SIMD intrinsics, the unsolved multiversioning/runtime dispatch problem, comparisons to C++'s Highway library, FP16 support gaps, AVX-512's controversial history and AVX10's future, std::simd's portability tradeoffs, and upcoming language features like target_feature 1.1 (landing in Rust 1.86) and RFC 3525 for safer SIMD ergonomics. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### When does target_feature 1.1 ship in Rust and what does it change? Target_feature 1.1 is scheduled to ship in Rust 1.86. It relaxes the original target_feature rule that required unsafe to call any function annotated with #[target_feature], instead allowing functions already under a target_feature gate to safely call other functions gated with the same feature, reducing unnecessary unsafe blocks in SIMD code. _Rust developers tracking SIMD safety improvements can follow language changes like this one on daily.dev._ ### Why are all SIMD intrinsics in Rust marked unsafe even when used correctly? SIMD intrinsics are marked unsafe because CPU support for specific SIMD features varies, and executing an unsupported instruction is undefined behavior that can crash the chip, ignore the instruction, or behave unexpectedly. Without a mechanism to verify the CPU supports the feature at the call site, the compiler cannot guarantee safety, so intrinsics remain unsafe by default. _Developers weighing safe SIMD abstractions against raw intrinsics can track this tradeoff discussion on daily.dev._ ### What is the multiversioning problem in SIMD programming and how does the Highway C++ library solve it? Multiversioning is the need to compile multiple versions of SIMD code for different CPU capabilities and dispatch to the best one at runtime, since target hardware is often unknown at compile time. The C++ Highway library solves this well and is used in JPEG-XL codecs; Rust currently lacks an equivalent, though crates like multiversion, rust-target-feature-dispatch, and pulp attempt partial solutions. _Engineers comparing SIMD dispatch strategies across languages can follow these Rust ecosystem efforts on daily.dev._ ## Similar posts on daily.dev - [SIMD programming in pure Rust](https://daily.dev/posts/simd-programming-in-pure-rust-idnkdlsse) · Hacker News · 2 upvotes · 0 comments - [fearless\_simd v0.7: 64-bit integers, improved generics, SSE2, and upcoming v1.0](https://daily.dev/posts/fearless-simd-v0-7-64-bit-integers-improved-generics-sse2-and-upcoming-v1-0-aors3lfex) · Lobsters · 0 upvotes · 0 comments --- Tags: [#performance](https://daily.dev/tags/performance), [#rust](https://daily.dev/tags/rust) [View this post on daily.dev](https://daily.dev/posts/towards-fearless-simd-7-years-later-tq0m1xyys) ```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":"Towards fearless SIMD, 7 years later","url":"https://daily.dev/posts/towards-fearless-simd-7-years-later-tq0m1xyys","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/towards-fearless-simd-7-years-later-tq0m1xyys"},"datePublished":"2026-08-31T05:54:36.402Z","dateModified":"2026-08-31T05:55:44.826Z","description":"A deep-dive revisiting the state of SIMD programming in Rust seven years after an earlier influential post on the topic. The author, working on the...","image":"https://media.daily.dev/image/upload/s--P4t4XyoV--/f_auto/v1722860399/public/Placeholder%2001","thumbnailUrl":"https://media.daily.dev/image/upload/s--P4t4XyoV--/f_auto/v1722860399/public/Placeholder%2001","isAccessibleForFree":true,"articleSection":"Linebender","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":"Linebender","logo":"https://media.daily.dev/image/upload/logos/placeholder.jpg","url":"https://daily.dev/sources/linebender"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/towards-fearless-simd-7-years-later-tq0m1xyys","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"performance,rust","timeRequired":"PT12M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Linebender","item":"https://daily.dev/sources/linebender"},{"@type":"ListItem","position":3,"name":"Towards fearless SIMD, 7 years later"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/towards-fearless-simd-7-years-later-tq0m1xyys#faq","mainEntity":[{"@type":"Question","name":"When does target_feature 1.1 ship in Rust and what does it change?","acceptedAnswer":{"@type":"Answer","text":"Target_feature 1.1 is scheduled to ship in Rust 1.86. It relaxes the original target_feature rule that required unsafe to call any function annotated with #[target_feature], instead allowing functions already under a target_feature gate to safely call other functions gated with the same feature, reducing unnecessary unsafe blocks in SIMD code. Rust developers tracking SIMD safety improvements can follow language changes like this one on daily.dev."}},{"@type":"Question","name":"Why are all SIMD intrinsics in Rust marked unsafe even when used correctly?","acceptedAnswer":{"@type":"Answer","text":"SIMD intrinsics are marked unsafe because CPU support for specific SIMD features varies, and executing an unsupported instruction is undefined behavior that can crash the chip, ignore the instruction, or behave unexpectedly. Without a mechanism to verify the CPU supports the feature at the call site, the compiler cannot guarantee safety, so intrinsics remain unsafe by default. Developers weighing safe SIMD abstractions against raw intrinsics can track this tradeoff discussion on daily.dev."}},{"@type":"Question","name":"What is the multiversioning problem in SIMD programming and how does the Highway C++ library solve it?","acceptedAnswer":{"@type":"Answer","text":"Multiversioning is the need to compile multiple versions of SIMD code for different CPU capabilities and dispatch to the best one at runtime, since target hardware is often unknown at compile time. The C++ Highway library solves this well and is used in JPEG-XL codecs; Rust currently lacks an equivalent, though crates like multiversion, rust-target-feature-dispatch, and pulp attempt partial solutions. Engineers comparing SIMD dispatch strategies across languages can follow these Rust ecosystem efforts on daily.dev."}}]} ```