{"id":2709,"date":"2025-11-25T16:00:00","date_gmt":"2025-11-25T09:00:00","guid":{"rendered":"https:\/\/dgway.com\/blog_E\/?p=2709"},"modified":"2025-11-24T14:19:12","modified_gmt":"2025-11-24T07:19:12","slug":"reach-3000-mb-s-nvme-ssd-with-full-filesystem-access-on-petalinux","status":"publish","type":"post","link":"https:\/\/dgway.com\/blog_E\/2025\/11\/25\/reach-3000-mb-s-nvme-ssd-with-full-filesystem-access-on-petalinux\/","title":{"rendered":"Reach 3000++ MB\/s NVMe SSD with Full Filesystem Access on PetaLinux"},"content":{"rendered":"\n<h3 class=\"wp-block-heading\">High-Speed Storage for Next-Gen Embedded &amp; Edge Applications<\/h3>\n\n\n\n<p class=\"wp-block-paragraph\">Modern embedded systems demand more performance than ever \u2014 <strong>real-time data logging<\/strong>, <strong>edge AI<\/strong>, <strong>embedded servers<\/strong>, and <strong>high-bandwidth video streaming<\/strong> all require storage that can keep up. Traditional storage interfaces simply can\u2019t deliver the throughput and low latency needed.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">That\u2019s why <strong>NVMe over PCIe<\/strong> has become the new gold standard. But integrating NVMe into embedded systems \u2014 especially those using Linux \u2014 often becomes complex and time-consuming.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">\ud83d\udc49 <strong>We solved that.<\/strong><\/p>\n\n\n\n<p class=\"wp-block-paragraph\">With <strong>rmNVMe-IP + PetaLinux<\/strong>, you can now achieve <strong>3000++ MB\/s<\/strong> read\/write speed <em>with full filesystem access<\/em>, seamless Linux integration, and proven performance on AMD Zynq UltraScale+ platforms like the <strong>ZCU106<\/strong>.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">\ud83c\udfa5 <a href=\"https:\/\/youtu.be\/1Z4e61EFQrQ\" target=\"_blank\" rel=\"noreferrer noopener\">Watch the full demo on YouTube<\/a><\/p>\n\n\n\n<figure class=\"wp-block-embed is-type-video is-provider-youtube wp-block-embed-youtube wp-embed-aspect-16-9 wp-has-aspect-ratio\"><div class=\"wp-block-embed__wrapper\">\n<iframe loading=\"lazy\" title=\"Reach 3000++ MB\/s NVMe SSD with Full Filesystem Access on PetaLinux\" width=\"680\" height=\"383\" src=\"https:\/\/www.youtube.com\/embed\/1Z4e61EFQrQ?feature=oembed\" frameborder=\"0\" allow=\"accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share\" referrerpolicy=\"strict-origin-when-cross-origin\" allowfullscreen><\/iframe>\n<\/div><\/figure>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<h3 class=\"wp-block-heading\">\u26a1 Why This Matters for Engineers &amp; Embedded Developers<\/h3>\n\n\n\n<p class=\"wp-block-paragraph\">Modern FPGA-based systems face challenges such as: \u2013 Sustaining <strong>3000+ MB\/s<\/strong> for high-speed data logging \u2013 Delivering <strong>high random-access I\/O<\/strong> for AI inference \u2013 Maintaining <strong>simultaneous read\/write<\/strong> operations \u2013 Ensuring full compatibility with <strong>Linux block devices<\/strong>, filesystems, and custom applications<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">Our solution solves all of these with a <strong>hardware-accelerated NVMe engine<\/strong> plus a customized <strong>rmNVMe driver<\/strong> running on PetaLinux.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\">\ud83e\udde9 What\u2019s Inside the Solution?<\/h3>\n\n\n\n<h3 class=\"wp-block-heading\">\u2714 Hardware Layer<\/h3>\n\n\n\n<ul class=\"wp-block-list\">\n<li>Custom <strong>DMA engine<\/strong><\/li>\n\n\n\n<li>Full NVMe command support via <strong>rmNVMe-IP<\/strong><\/li>\n\n\n\n<li>Stable performance across all workload types<\/li>\n<\/ul>\n\n\n\n<h3 class=\"wp-block-heading\">\u2714 Software Layer<\/h3>\n\n\n\n<ul class=\"wp-block-list\">\n<li>PetaLinux with <strong>rmNVMe driver<\/strong><\/li>\n\n\n\n<li>ext4 filesystem support<\/li>\n\n\n\n<li>FIO performance testing<\/li>\n\n\n\n<li>Custom io_uring user applications<\/li>\n<\/ul>\n\n\n\n<p class=\"wp-block-paragraph\">This creates a <strong>fast, reliable bridge<\/strong> between your embedded platform and NVMe SSD \u2014 ideal for real-world industrial, automotive, military, and edge computing use cases.<\/p>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<h3 class=\"wp-block-heading\">\u2699\ufe0f Live Demo Highlights<\/h3>\n\n\n\n<ul class=\"wp-block-list\">\n<li>\u2714\ufe0f NVMe SSD recognized instantly on PetaLinux<\/li>\n\n\n\n<li>\u2714\ufe0f Formatted &amp; mounted with full ext4 filesystem<\/li>\n\n\n\n<li>\u2714\ufe0f Tested with FIO \u2014 delivering <strong>3000+ MB\/s<\/strong> read\/write<\/li>\n\n\n\n<li>\u2714\ufe0f Stable performance on mixed workloads<\/li>\n\n\n\n<li>\u2714\ufe0f Custom app example using <strong>io_uring<\/strong> for ultra-efficient async I\/O<\/li>\n<\/ul>\n\n\n\n<p class=\"wp-block-paragraph\">This proves not only peak performance but also <strong>flexible integration for real industrial workloads.<\/strong><\/p>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<h3 class=\"wp-block-heading\">\ud83e\udde9 Build Custom Applications Easily<\/h3>\n\n\n\n<p class=\"wp-block-paragraph\">Whether you\u2019re building:<\/p>\n\n\n\n<div class=\"wp-block-columns is-layout-flex wp-container-core-columns-is-layout-8f761849 wp-block-columns-is-layout-flex\">\n<div class=\"wp-block-column is-layout-flow wp-block-column-is-layout-flow\"><div class=\"wp-block-image\">\n<figure class=\"aligncenter size-large\"><img loading=\"lazy\" decoding=\"async\" width=\"1024\" height=\"573\" src=\"https:\/\/dgway.com\/blog_E\/wp-content\/uploads\/2025\/11\/Real-time_Data_Logging-1024x573.jpg\" alt=\"Digital data visualization showing real-time analytics and system metrics, representing high-performance NVMe SSD throughput exceeding 3000 MB\/s with full filesystem access on PetaLinux for embedded data-logging applications.\" class=\"wp-image-2716\" srcset=\"https:\/\/dgway.com\/blog_E\/wp-content\/uploads\/2025\/11\/Real-time_Data_Logging-1024x573.jpg 1024w, https:\/\/dgway.com\/blog_E\/wp-content\/uploads\/2025\/11\/Real-time_Data_Logging-300x168.jpg 300w, https:\/\/dgway.com\/blog_E\/wp-content\/uploads\/2025\/11\/Real-time_Data_Logging-768x430.jpg 768w, https:\/\/dgway.com\/blog_E\/wp-content\/uploads\/2025\/11\/Real-time_Data_Logging-1536x860.jpg 1536w, https:\/\/dgway.com\/blog_E\/wp-content\/uploads\/2025\/11\/Real-time_Data_Logging.jpg 1600w\" sizes=\"auto, (max-width: 1024px) 100vw, 1024px\" \/><figcaption class=\"wp-element-caption\">Real-time data logging<\/figcaption><\/figure>\n<\/div><\/div>\n\n\n\n<div class=\"wp-block-column is-layout-flow wp-block-column-is-layout-flow\"><div class=\"wp-block-image\">\n<figure class=\"aligncenter size-large\"><img loading=\"lazy\" decoding=\"async\" width=\"1024\" height=\"573\" src=\"https:\/\/dgway.com\/blog_E\/wp-content\/uploads\/2025\/11\/Edge_AI_and_inference_processing-1024x573.jpg\" alt=\"An AI chip on a circuit board, representing high-performance Edge AI and inference workloads powered by NVMe SSD speeds exceeding 3000 MB\/s with full filesystem access on PetaLinux.\" class=\"wp-image-2717\" srcset=\"https:\/\/dgway.com\/blog_E\/wp-content\/uploads\/2025\/11\/Edge_AI_and_inference_processing-1024x573.jpg 1024w, https:\/\/dgway.com\/blog_E\/wp-content\/uploads\/2025\/11\/Edge_AI_and_inference_processing-300x168.jpg 300w, https:\/\/dgway.com\/blog_E\/wp-content\/uploads\/2025\/11\/Edge_AI_and_inference_processing-768x430.jpg 768w, https:\/\/dgway.com\/blog_E\/wp-content\/uploads\/2025\/11\/Edge_AI_and_inference_processing-1536x860.jpg 1536w, https:\/\/dgway.com\/blog_E\/wp-content\/uploads\/2025\/11\/Edge_AI_and_inference_processing.jpg 1600w\" sizes=\"auto, (max-width: 1024px) 100vw, 1024px\" \/><figcaption class=\"wp-element-caption\">Edge AI and inference processing<\/figcaption><\/figure>\n<\/div><\/div>\n<\/div>\n\n\n\n<div class=\"wp-block-columns is-layout-flex wp-container-core-columns-is-layout-8f761849 wp-block-columns-is-layout-flex\">\n<div class=\"wp-block-column is-layout-flow wp-block-column-is-layout-flow\"><div class=\"wp-block-image\">\n<figure class=\"aligncenter size-large\"><img loading=\"lazy\" decoding=\"async\" width=\"1024\" height=\"573\" src=\"https:\/\/dgway.com\/blog_E\/wp-content\/uploads\/2025\/11\/Embedded_servers-1024x573.jpg\" alt=\"Server racks with a cloud of interconnected digital icons representing embedded server workloads, symbolizing high-speed NVMe SSD performance exceeding 3000 MB\/s with full filesystem access on PetaLinux for embedded server applications.\" class=\"wp-image-2718\" srcset=\"https:\/\/dgway.com\/blog_E\/wp-content\/uploads\/2025\/11\/Embedded_servers-1024x573.jpg 1024w, https:\/\/dgway.com\/blog_E\/wp-content\/uploads\/2025\/11\/Embedded_servers-300x168.jpg 300w, https:\/\/dgway.com\/blog_E\/wp-content\/uploads\/2025\/11\/Embedded_servers-768x430.jpg 768w, https:\/\/dgway.com\/blog_E\/wp-content\/uploads\/2025\/11\/Embedded_servers-1536x860.jpg 1536w, https:\/\/dgway.com\/blog_E\/wp-content\/uploads\/2025\/11\/Embedded_servers.jpg 1600w\" sizes=\"auto, (max-width: 1024px) 100vw, 1024px\" \/><figcaption class=\"wp-element-caption\">Embedded servers<\/figcaption><\/figure>\n<\/div><\/div>\n\n\n\n<div class=\"wp-block-column is-layout-flow wp-block-column-is-layout-flow\"><div class=\"wp-block-image\">\n<figure class=\"aligncenter size-large\"><img loading=\"lazy\" decoding=\"async\" width=\"1024\" height=\"573\" src=\"https:\/\/dgway.com\/blog_E\/wp-content\/uploads\/2025\/11\/High-resolution_video_recording_and_streaming-1024x573.jpg\" alt=\"Professional cinema camera in a studio environment representing high-resolution video recording and real-time streaming workflows powered by NVMe SSD performance exceeding 3000 MB\/s with full filesystem access on PetaLinux.\" class=\"wp-image-2719\" srcset=\"https:\/\/dgway.com\/blog_E\/wp-content\/uploads\/2025\/11\/High-resolution_video_recording_and_streaming-1024x573.jpg 1024w, https:\/\/dgway.com\/blog_E\/wp-content\/uploads\/2025\/11\/High-resolution_video_recording_and_streaming-300x168.jpg 300w, https:\/\/dgway.com\/blog_E\/wp-content\/uploads\/2025\/11\/High-resolution_video_recording_and_streaming-768x430.jpg 768w, https:\/\/dgway.com\/blog_E\/wp-content\/uploads\/2025\/11\/High-resolution_video_recording_and_streaming-1536x860.jpg 1536w, https:\/\/dgway.com\/blog_E\/wp-content\/uploads\/2025\/11\/High-resolution_video_recording_and_streaming.jpg 1600w\" sizes=\"auto, (max-width: 1024px) 100vw, 1024px\" \/><figcaption class=\"wp-element-caption\">High-resolution video recording and streaming<\/figcaption><\/figure>\n<\/div><\/div>\n<\/div>\n\n\n\n<p class=\"wp-block-paragraph\">Our framework lets you deploy <strong>fast, reliable, Linux-compatible NVMe storage<\/strong> without PCIe complexity.<\/p>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<h2 class=\"wp-block-heading\">\u2705 Select the Right NVMe Solution for Your Requirement<\/h2>\n\n\n<div class=\"wp-block-image\">\n<figure class=\"aligncenter size-large\"><img loading=\"lazy\" decoding=\"async\" width=\"1024\" height=\"341\" src=\"https:\/\/dgway.com\/blog_E\/wp-content\/uploads\/2025\/11\/image-5-1024x341.jpeg\" alt=\"Comparison chart highlighting the differences between rmNVMe-IP and NVMe-IP, showing device type, design target, performance focus, and operation support to help engineers select the right NVMe solution for achieving 3000+ MB\/s performance with full filesystem access on PetaLinux.\" class=\"wp-image-2710\" srcset=\"https:\/\/dgway.com\/blog_E\/wp-content\/uploads\/2025\/11\/image-5-1024x341.jpeg 1024w, https:\/\/dgway.com\/blog_E\/wp-content\/uploads\/2025\/11\/image-5-300x100.jpeg 300w, https:\/\/dgway.com\/blog_E\/wp-content\/uploads\/2025\/11\/image-5-768x256.jpeg 768w, https:\/\/dgway.com\/blog_E\/wp-content\/uploads\/2025\/11\/image-5.jpeg 1200w\" sizes=\"auto, (max-width: 1024px) 100vw, 1024px\" \/><figcaption class=\"wp-element-caption\">Compare rmNVMe-IP vs NVMe-IP OPtimal Performance<\/figcaption><\/figure>\n<\/div>\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<h3 class=\"wp-block-heading\">\ud83d\udccc Summary: Why rmNVMe-IP + PetaLinux Is a Game Changer<\/h3>\n\n\n\n<ul class=\"wp-block-list\">\n<li>\u26a1 Over <strong>3000 MB\/s throughput<\/strong><\/li>\n\n\n\n<li>\ud83d\udcc1 Full Linux filesystem support (EXT4)<\/li>\n\n\n\n<li>\ud83c\udf10 Standard tools: lsblk, FIO, mount, io_uring<\/li>\n\n\n\n<li>\ud83d\ude80 Flexible for any embedded workload<\/li>\n\n\n\n<li>\ud83c\udfaf Simplifies complex NVMe integration via PCIe<\/li>\n\n\n\n<li>\ud83e\udde9 Runs on popular FPGA\/Adaptive SoC platforms<\/li>\n<\/ul>\n\n\n\n<p class=\"wp-block-paragraph\">If you&#8217;re building tomorrow\u2019s high-performance embedded system, <strong>this is the storage layer you\u2019ve been waiting for.<\/strong><\/p>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<h2 class=\"wp-block-heading\">\ud83d\udce9 Ready to accelerate your embedded storage system?<\/h2>\n\n\n\n<p class=\"wp-block-paragraph\">\ud83d\udc49 <a href=\"https:\/\/dgway.com\/contact.html\" target=\"_blank\" rel=\"noreferrer noopener\"><strong>Contact Us<\/strong><\/a><strong> <\/strong>Let\u2019s discuss your next project and explore how our rmNVMe IP solutions can empower your storage.<\/p>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<h3 class=\"wp-block-heading\">\ud83c\udd93 Free Evaluation<\/h3>\n\n\n\n<p class=\"wp-block-paragraph\">Explore rmNVMe-IP with our free evaluation package:<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li><a href=\"https:\/\/dgway.com\/download\/download_form.html?d=rrmNVMeIP_Petalinux_ZCU106_AB17.zip\" target=\"_blank\" rel=\"noreferrer noopener\">rmNVMe IP on PetaLinux (AMD)<\/a><\/li>\n\n\n\n<li><a href=\"https:\/\/dgway.com\/download\/download_form.html?d=rmNVMeIPG5Test_Config_AGLI.zip\" target=\"_blank\" rel=\"noreferrer noopener\">rmNVMe-IP (Gen5) (Altera)<\/a><\/li>\n<\/ul>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<h3 class=\"wp-block-heading\">\ud83d\udcd8 Product Page<\/h3>\n\n\n\n<p class=\"wp-block-paragraph\">Learn more about the rmNVMe-IP core and supported reference designs:<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li><a href=\"https:\/\/dgway.com\/rmNVMe-IP_X_E.html\" target=\"_blank\" rel=\"noreferrer noopener\">AMD rmNVMe-IP Product Page<\/a><\/li>\n\n\n\n<li><a href=\"https:\/\/dgway.com\/rmNVMe-IP_A_E.html\" target=\"_blank\" rel=\"noreferrer noopener\">Altera rmNVMe-IP Product Page<\/a><\/li>\n<\/ul>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<h3 class=\"wp-block-heading\">\ud83d\udcc4 Technical Documents for AMD<\/h3>\n\n\n\n<ul class=\"wp-block-list\">\n<li>rmNVMe on PetaLinux: <a href=\"https:\/\/dgway.com\/products\/IP\/NVMe-IP\/rmNVMeIP-PetaLinux-instruction-amd\/\" target=\"_blank\" rel=\"noreferrer noopener\">Instruction<\/a><\/li>\n<\/ul>\n\n\n\n<h3 class=\"wp-block-heading\">\ud83d\udcc4 Technical Documents for Altera<\/h3>\n\n\n\n<ul class=\"wp-block-list\">\n<li>rmNVMe-IP (Gen5): <a href=\"https:\/\/dgway.com\/products\/IP\/NVMe-IP\/dg_rmnvme_ip_data_sheet_g5_intel\/\" target=\"_blank\" rel=\"noreferrer noopener\">Datasheet<\/a> | <a href=\"https:\/\/dgway.com\/products\/IP\/NVMe-IP\/dg_rmnvmeip_refdesign_g5_intel\/\" target=\"_blank\" rel=\"noreferrer noopener\">Reference Design<\/a><\/li>\n<\/ul>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<h3 class=\"wp-block-heading\">\ud83e\udd1d Official Partner Platform Availability<\/h3>\n\n\n\n<p class=\"wp-block-paragraph\">rmNVMe-IP is now available through the official FPGA partner ecosystems (<a href=\"https:\/\/www.amd.com\/en\/search\/partner\/embedded-partner-solutions.html\/7554\" target=\"_blank\" rel=\"noreferrer noopener\">AMD<\/a>). Integrate faster with certified, production-ready IP.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>High-Speed Storage for Next-Gen Embedded &amp; Edge Applications Modern embedded systems demand more performance than ever \u2014 real-time data logging, edge AI, embedded servers, and high-bandwidth video streaming all require storage that can keep up. Traditional storage interfaces simply can\u2019t deliver the throughput and low latency needed. That\u2019s why NVMe over PCIe has become the new gold standard. But integrating&#46;&#46;&#46;<\/p>\n","protected":false},"author":1,"featured_media":2715,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[6],"tags":[871,867,863,271,865,868,411,148,870,855,866,875,857,854,859,861,872,873],"class_list":["post-2709","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-storage","tag-data-transfer-acceleration","tag-data-intensive-applications","tag-edge-ai","tag-edge-computing","tag-embedded-servers","tag-fio-benchmark","tag-fpga-storage-solution","tag-fpga-based-solutions","tag-high-throughput-ssd","tag-high-performance-storage","tag-high-resolution-video-recording","tag-linux-compatibility","tag-linux-filesystem","tag-nvme-ssd","tag-nvme-ip","tag-pcie-gen4","tag-soc-platform","tag-storage-performance-tuning"],"_links":{"self":[{"href":"https:\/\/dgway.com\/blog_E\/wp-json\/wp\/v2\/posts\/2709","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/dgway.com\/blog_E\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/dgway.com\/blog_E\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/dgway.com\/blog_E\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/dgway.com\/blog_E\/wp-json\/wp\/v2\/comments?post=2709"}],"version-history":[{"count":1,"href":"https:\/\/dgway.com\/blog_E\/wp-json\/wp\/v2\/posts\/2709\/revisions"}],"predecessor-version":[{"id":2720,"href":"https:\/\/dgway.com\/blog_E\/wp-json\/wp\/v2\/posts\/2709\/revisions\/2720"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/dgway.com\/blog_E\/wp-json\/wp\/v2\/media\/2715"}],"wp:attachment":[{"href":"https:\/\/dgway.com\/blog_E\/wp-json\/wp\/v2\/media?parent=2709"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/dgway.com\/blog_E\/wp-json\/wp\/v2\/categories?post=2709"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/dgway.com\/blog_E\/wp-json\/wp\/v2\/tags?post=2709"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}