--- title: FFmpeg Lands Latest AVX-512 Optimization: 1.372x Faster... description: FFmpeg developer Niklas Haas has added AVX-512 VPERMB (Vector Permute Byte) instruction support to FFmpeg's libswscale library, enabling full cross-lane byte... canonical: https://daily.dev/posts/ffmpeg-lands-latest-avx-512-optimization-1-372x-faster-in-pixel-format-conversion-ciayyw4zi twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: FFmpeg Lands Latest AVX-512 Optimization: 1.372x Faster In Pixel Format Conversion | daily.dev og:description: FFmpeg developer Niklas Haas has added AVX-512 VPERMB (Vector Permute Byte) instruction support to FFmpeg's libswscale library, enabling full cross-lane byte... og:url: https://daily.dev/posts/ffmpeg-lands-latest-avx-512-optimization-1-372x-faster-in-pixel-format-conversion-ciayyw4zi og:image: https://api.daily.dev/og/posts/CIaYyW4ZI.png og:image:alt: FFmpeg Lands Latest AVX-512 Optimization: 1.372x Faster In Pixel Format Conversion 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. # FFmpeg Lands Latest AVX-512 Optimization: 1.372x Faster In Pixel Format Conversion **[Phoronix](https://daily.dev/sources/phoronix)** · 1 min read · 2 upvotes · 0 comments ## Summary FFmpeg developer Niklas Haas has added AVX-512 VPERMB (Vector Permute Byte) instruction support to FFmpeg's libswscale library, enabling full cross-lane byte permutation for more efficient video scaling and pixel format conversion. The optimization delivers a 1.372x speedup for RGB24 to RGBA 1920x1080 conversions on AVX-512-capable processors, including AMD Zen 4+ and select Intel Xeon CPUs. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### How much faster is FFmpeg's pixel format conversion with the new AVX-512 optimization? RGBA24 to RGBA 1920x1080 conversion runs 1.372x faster after FFmpeg developer Niklas Haas extended libswscale to use AVX-512's VPERMB (Vector Permute Byte) instruction. VPERMB enables full cross-lane byte permutation, improving performance especially for non-lane-aligned conversion scenarios on AVX-512-capable CPUs. _Track low-level performance wins like this FFmpeg AVX-512 optimization by following media processing updates on daily.dev._ ### Which CPUs benefit from FFmpeg's new AVX-512 VPERMB optimization in libswscale? AMD Zen 4 and newer CPUs, along with Intel Xeon and other select Intel processors supporting AVX-512, benefit from this optimization. The improvement comes from using the VPERMB instruction in FFmpeg's libswscale for more efficient video scaling and pixel format conversion. _Developers optimizing media pipelines for specific CPU architectures can follow AVX-512 developments on daily.dev._ ## Similar posts on daily.dev - [FFmpeg Introduces Vulkan Acceleration For Apple ProRes Video Decoding](https://daily.dev/posts/ffmpeg-introduces-vulkan-acceleration-for-apple-prores-video-decoding-hqfpur3sh) · Phoronix · 0 upvotes · 0 comments - [FFmpeg 8.1 Released With Experimental xHE-AAC MPS212, More Vulkan Acceleration](https://daily.dev/posts/ffmpeg-8-1-released-with-experimental-xhe-aac-mps212-more-vulkan-acceleration-yklasxtd0) · Phoronix · 0 upvotes · 0 comments - [Video Encoding and Decoding with Vulkan Compute Shaders in FFmpeg](https://daily.dev/posts/video-encoding-and-decoding-with-vulkan-compute-shaders-in-ffmpeg-wmurcqryk) · Khronos · 0 upvotes · 0 comments - [Vector Vibing to speed up Opus encode by 20%](https://daily.dev/posts/vector-vibing-to-speed-up-opus-encode-by-20--3thskyanw) · WebRTC Hacks · 2 upvotes · 0 comments --- Tags: [#backend](https://daily.dev/tags/backend) [View this post on daily.dev](https://daily.dev/posts/ffmpeg-lands-latest-avx-512-optimization-1-372x-faster-in-pixel-format-conversion-ciayyw4zi) ```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":"FFmpeg Lands Latest AVX-512 Optimization: 1.372x Faster In Pixel Format Conversion","url":"https://daily.dev/posts/ffmpeg-lands-latest-avx-512-optimization-1-372x-faster-in-pixel-format-conversion-ciayyw4zi","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/ffmpeg-lands-latest-avx-512-optimization-1-372x-faster-in-pixel-format-conversion-ciayyw4zi"},"datePublished":"2026-07-19T11:16:23.666Z","dateModified":"2026-09-13T20:29:44.882Z","description":"FFmpeg developer Niklas Haas has added AVX-512 VPERMB (Vector Permute Byte) instruction support to FFmpeg's libswscale library, enabling full cross-lane byte...","image":"https://media.daily.dev/image/upload/s--58gMhC4P--/f_auto/v1722860399/public/Placeholder%2012","thumbnailUrl":"https://media.daily.dev/image/upload/s--58gMhC4P--/f_auto/v1722860399/public/Placeholder%2012","isAccessibleForFree":true,"articleSection":"Phoronix","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":"Phoronix","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/6a26ba379dd64932830aa0c9803dd7ee","url":"https://daily.dev/sources/phoronix"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/ffmpeg-lands-latest-avx-512-optimization-1-372x-faster-in-pixel-format-conversion-ciayyw4zi","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":2},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"backend","timeRequired":"PT1M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Phoronix","item":"https://daily.dev/sources/phoronix"},{"@type":"ListItem","position":3,"name":"FFmpeg Lands Latest AVX-512 Optimization: 1.372x Faster In Pixel Format Conversion"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/ffmpeg-lands-latest-avx-512-optimization-1-372x-faster-in-pixel-format-conversion-ciayyw4zi#faq","mainEntity":[{"@type":"Question","name":"How much faster is FFmpeg's pixel format conversion with the new AVX-512 optimization?","acceptedAnswer":{"@type":"Answer","text":"RGBA24 to RGBA 1920x1080 conversion runs 1.372x faster after FFmpeg developer Niklas Haas extended libswscale to use AVX-512's VPERMB (Vector Permute Byte) instruction. VPERMB enables full cross-lane byte permutation, improving performance especially for non-lane-aligned conversion scenarios on AVX-512-capable CPUs. Track low-level performance wins like this FFmpeg AVX-512 optimization by following media processing updates on daily.dev."}},{"@type":"Question","name":"Which CPUs benefit from FFmpeg's new AVX-512 VPERMB optimization in libswscale?","acceptedAnswer":{"@type":"Answer","text":"AMD Zen 4 and newer CPUs, along with Intel Xeon and other select Intel processors supporting AVX-512, benefit from this optimization. The improvement comes from using the VPERMB instruction in FFmpeg's libswscale for more efficient video scaling and pixel format conversion. Developers optimizing media pipelines for specific CPU architectures can follow AVX-512 developments on daily.dev."}}]} ```