{"id":128006,"date":"2023-09-19T23:40:06","date_gmt":"2023-09-19T23:40:06","guid":{"rendered":"https:\/\/blogs.nvidia.com\/?p=66948"},"modified":"2023-09-19T23:40:06","modified_gmt":"2023-09-19T23:40:06","slug":"oracle-cloud-infrastructure-offers-new-nvidia-gpu-accelerated-compute-instances","status":"publish","type":"post","link":"https:\/\/webdomino.net\/index.php\/nvidia\/oracle-cloud-infrastructure-offers-new-nvidia-gpu-accelerated-compute-instances\/","title":{"rendered":"Oracle Cloud Infrastructure Offers New NVIDIA GPU-Accelerated Compute Instances"},"content":{"rendered":"

With generative AI<\/a> and large language models<\/a> (LLMs) driving groundbreaking innovations, the computational demands for training and inference are skyrocketing.<\/p>\n

These modern-day generative AI applications demand full-stack accelerated compute, starting with state-of-the-art infrastructure that can handle massive workloads with speed and accuracy. To help meet this need, Oracle Cloud Infrastructure today announced general availability of NVIDIA H100 Tensor Core GPUs<\/a> on OCI Compute<\/a>, with NVIDIA L40S GPUs<\/a> coming soon.<\/p>\n

NVIDIA H100 Tensor Core GPU Instance on OCI<\/strong><\/h2>\n

The OCI Compute bare-metal instances with NVIDIA H100 GPUs, powered by the NVIDIA Hopper architecture<\/a>, enable an order-of-magnitude leap for large-scale AI and high-performance computing, with unprecedented performance, scalability and versatility for every workload.<\/p>\n

Organizations using NVIDIA H100 GPUs obtain up to a 30x increase in AI inference performance<\/a> and a 4x boost in AI training<\/a> compared with tapping the NVIDIA A100 Tensor Core GPU<\/a>. The H100 GPU is designed for resource-intensive computing tasks, including training LLMs and inference while running them.<\/p>\n

The BM.GPU.H100.8 OCI Compute shape includes eight NVIDIA H100 GPUs, each with 80GB of HBM2 GPU memory. Between the eight GPUs, 3.2TB\/s of bisectional bandwidth enables each GPU to communicate directly with all seven other GPUs via NVIDIA NVSwitch and NVLink 4.0 technology<\/a>. The shape includes 16 local NVMe drives with a capacity of 3.84TB each and also includes 4th Gen Intel Xeon CPU processors with 112 cores, as well as 2TB of system memory.<\/p>\n

In a nutshell, this shape is optimized for organizations\u2019 most challenging workloads.<\/p>\n

Depending on timelines and sizes of workloads, OCI Supercluster<\/a> allows organizations to scale their NVIDIA H100 GPU usage from a single node to up to tens of thousands of H100 GPUs over a high-performance, ultra-low-latency network.<\/p>\n

NVIDIA L40S GPU Instance on OCI<\/strong><\/h2>\n

The NVIDIA L40S GPU, based on the NVIDIA Ada Lovelace architecture<\/a>, is a universal GPU for the data center, delivering breakthrough multi-workload acceleration for LLM inference and training, visual computing and video applications. The OCI Compute bare-metal instances with NVIDIA L40S GPUs will be available for early access later this year, with general availability coming early in 2024.<\/p>\n

These instances will offer an alternative to the NVIDIA H100 and A100 GPU instances for tackling smaller- to medium-sized AI workloads, as well as for graphics and video compute tasks. The NVIDIA L40S GPU achieves up to a 20% performance boost<\/a> for generative AI workloads and as much as a 70% improvement in fine-tuning AI models<\/a> compared with the NVIDIA A100.<\/p>\n

The BM.GPU.L40S.4 OCI Compute shape includes four NVIDIA L40S GPUs, along with the latest-generation Intel Xeon CPU with up to 112 cores, 1TB of system memory, 15.36TB of low-latency NVMe local storage for caching data and 400GB\/s of cluster network bandwidth. This instance was created to tackle a wide range of use cases, ranging from LLM training, fine-tuning and inference to NVIDIA Omniverse<\/a> workloads and industrial digitalization, 3D graphics and rendering, video transcoding and FP32 HPC.<\/p>\n

NVIDIA and OCI: Enterprise AI<\/strong><\/h2>\n

This collaboration between OCI and NVIDIA will enable organizations of all sizes to join the generative AI revolution by providing them with state-of-the-art NVIDIA H100 and L40S GPU-accelerated infrastructure.<\/p>\n

Access to NVIDIA GPU-accelerated instances may not be enough, however. Unlocking the maximum potential of NVIDIA GPUs on OCI Compute means having an optimal software layer. NVIDIA AI Enterprise<\/a> streamlines the development and deployment of enterprise-grade accelerated AI software with open-source containers and frameworks optimized for the underlying NVIDIA GPU infrastructure, all with the help of support services<\/a>.<\/p>\n

To learn more, join NVIDIA at Oracle Cloud World<\/a> in the AI Pavillion, attend this session<\/a> on the new OCI instances on Wednesday, Sept. 20, and visit these web pages on Oracle Cloud Infrastructure<\/a>, OCI Compute<\/a>, how Oracle approaches AI<\/a> and the NVIDIA AI Platform<\/a>.<\/p>\n<\/div>","protected":false},"excerpt":{"rendered":"

With generative AI and large language models (LLMs) driving groundbreaking innovations, the computational demands for training and inference are skyrocketing. These modern-day generative AI applications demand full-stack accelerated compute, starting with state-of-the-art infrastructure that can handle massive workloads with speed and accuracy. To help meet this need, Oracle Cloud Infrastructure today announced general availability of Read article ><\/a><\/p>\n","protected":false},"author":266,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"_mi_skip_tracking":false,"_monsterinsights_sitenote_active":false,"_monsterinsights_sitenote_note":"","_monsterinsights_sitenote_category":0,"footnotes":""},"categories":[343],"tags":[4223,35,847,432,12142,52],"yoast_head":"\nOracle Cloud Infrastructure Offers New NVIDIA GPU-Accelerated Compute Instances - WebDomino.NET<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"http:\/\/webdomino.net\/index.php\/nvidia\/oracle-cloud-infrastructure-offers-new-nvidia-gpu-accelerated-compute-instances\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Oracle Cloud Infrastructure Offers New NVIDIA GPU-Accelerated Compute Instances - WebDomino.NET\" \/>\n<meta property=\"og:description\" content=\"With generative AI and large language models (LLMs) driving groundbreaking innovations, the computational demands for training and inference are skyrocketing. These modern-day generative AI applications demand full-stack accelerated compute, starting with state-of-the-art infrastructure that can handle massive workloads with speed and accuracy. To help meet this need, Oracle Cloud Infrastructure today announced general availability of Read article >\" \/>\n<meta property=\"og:url\" content=\"http:\/\/webdomino.net\/index.php\/nvidia\/oracle-cloud-infrastructure-offers-new-nvidia-gpu-accelerated-compute-instances\/\" \/>\n<meta property=\"og:site_name\" content=\"WebDomino.NET\" \/>\n<meta property=\"article:published_time\" content=\"2023-09-19T23:40:06+00:00\" \/>\n<meta name=\"author\" content=\"Dave Salvator\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"Dave Salvator\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"3 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"http:\/\/webdomino.net\/index.php\/nvidia\/oracle-cloud-infrastructure-offers-new-nvidia-gpu-accelerated-compute-instances\/\",\"url\":\"http:\/\/webdomino.net\/index.php\/nvidia\/oracle-cloud-infrastructure-offers-new-nvidia-gpu-accelerated-compute-instances\/\",\"name\":\"Oracle Cloud Infrastructure Offers New NVIDIA GPU-Accelerated Compute Instances - WebDomino.NET\",\"isPartOf\":{\"@id\":\"https:\/\/webdomino.net\/#website\"},\"datePublished\":\"2023-09-19T23:40:06+00:00\",\"dateModified\":\"2023-09-19T23:40:06+00:00\",\"author\":{\"@id\":\"https:\/\/webdomino.net\/#\/schema\/person\/310dae90f82d7d270510022746aa300c\"},\"breadcrumb\":{\"@id\":\"http:\/\/webdomino.net\/index.php\/nvidia\/oracle-cloud-infrastructure-offers-new-nvidia-gpu-accelerated-compute-instances\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"http:\/\/webdomino.net\/index.php\/nvidia\/oracle-cloud-infrastructure-offers-new-nvidia-gpu-accelerated-compute-instances\/\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"http:\/\/webdomino.net\/index.php\/nvidia\/oracle-cloud-infrastructure-offers-new-nvidia-gpu-accelerated-compute-instances\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\/\/webdomino.net\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Oracle Cloud Infrastructure Offers New NVIDIA GPU-Accelerated Compute Instances\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/webdomino.net\/#website\",\"url\":\"https:\/\/webdomino.net\/\",\"name\":\"WebDomino.NET\",\"description\":\"Global NEWS WordPress site\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/webdomino.net\/?s={search_term_string}\"},\"query-input\":\"required name=search_term_string\"}],\"inLanguage\":\"en-US\"},{\"@type\":\"Person\",\"@id\":\"https:\/\/webdomino.net\/#\/schema\/person\/310dae90f82d7d270510022746aa300c\",\"name\":\"Dave Salvator\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/webdomino.net\/#\/schema\/person\/image\/\",\"url\":\"https:\/\/secure.gravatar.com\/avatar\/60146dd4624401222bdbdfebf7cd1c66?s=96&d=mm&r=g\",\"contentUrl\":\"https:\/\/secure.gravatar.com\/avatar\/60146dd4624401222bdbdfebf7cd1c66?s=96&d=mm&r=g\",\"caption\":\"Dave Salvator\"},\"sameAs\":[\"https:\/\/nvidianews.nvidia.com\"],\"url\":\"https:\/\/webdomino.net\/index.php\/author\/dave-salvator\/\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Oracle Cloud Infrastructure Offers New NVIDIA GPU-Accelerated Compute Instances - WebDomino.NET","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"http:\/\/webdomino.net\/index.php\/nvidia\/oracle-cloud-infrastructure-offers-new-nvidia-gpu-accelerated-compute-instances\/","og_locale":"en_US","og_type":"article","og_title":"Oracle Cloud Infrastructure Offers New NVIDIA GPU-Accelerated Compute Instances - WebDomino.NET","og_description":"With generative AI and large language models (LLMs) driving groundbreaking innovations, the computational demands for training and inference are skyrocketing. These modern-day generative AI applications demand full-stack accelerated compute, starting with state-of-the-art infrastructure that can handle massive workloads with speed and accuracy. To help meet this need, Oracle Cloud Infrastructure today announced general availability of Read article >","og_url":"http:\/\/webdomino.net\/index.php\/nvidia\/oracle-cloud-infrastructure-offers-new-nvidia-gpu-accelerated-compute-instances\/","og_site_name":"WebDomino.NET","article_published_time":"2023-09-19T23:40:06+00:00","author":"Dave Salvator","twitter_misc":{"Written by":"Dave Salvator","Est. reading time":"3 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"http:\/\/webdomino.net\/index.php\/nvidia\/oracle-cloud-infrastructure-offers-new-nvidia-gpu-accelerated-compute-instances\/","url":"http:\/\/webdomino.net\/index.php\/nvidia\/oracle-cloud-infrastructure-offers-new-nvidia-gpu-accelerated-compute-instances\/","name":"Oracle Cloud Infrastructure Offers New NVIDIA GPU-Accelerated Compute Instances - WebDomino.NET","isPartOf":{"@id":"https:\/\/webdomino.net\/#website"},"datePublished":"2023-09-19T23:40:06+00:00","dateModified":"2023-09-19T23:40:06+00:00","author":{"@id":"https:\/\/webdomino.net\/#\/schema\/person\/310dae90f82d7d270510022746aa300c"},"breadcrumb":{"@id":"http:\/\/webdomino.net\/index.php\/nvidia\/oracle-cloud-infrastructure-offers-new-nvidia-gpu-accelerated-compute-instances\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["http:\/\/webdomino.net\/index.php\/nvidia\/oracle-cloud-infrastructure-offers-new-nvidia-gpu-accelerated-compute-instances\/"]}]},{"@type":"BreadcrumbList","@id":"http:\/\/webdomino.net\/index.php\/nvidia\/oracle-cloud-infrastructure-offers-new-nvidia-gpu-accelerated-compute-instances\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/webdomino.net\/"},{"@type":"ListItem","position":2,"name":"Oracle Cloud Infrastructure Offers New NVIDIA GPU-Accelerated Compute Instances"}]},{"@type":"WebSite","@id":"https:\/\/webdomino.net\/#website","url":"https:\/\/webdomino.net\/","name":"WebDomino.NET","description":"Global NEWS WordPress site","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/webdomino.net\/?s={search_term_string}"},"query-input":"required name=search_term_string"}],"inLanguage":"en-US"},{"@type":"Person","@id":"https:\/\/webdomino.net\/#\/schema\/person\/310dae90f82d7d270510022746aa300c","name":"Dave Salvator","image":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/webdomino.net\/#\/schema\/person\/image\/","url":"https:\/\/secure.gravatar.com\/avatar\/60146dd4624401222bdbdfebf7cd1c66?s=96&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/60146dd4624401222bdbdfebf7cd1c66?s=96&d=mm&r=g","caption":"Dave Salvator"},"sameAs":["https:\/\/nvidianews.nvidia.com"],"url":"https:\/\/webdomino.net\/index.php\/author\/dave-salvator\/"}]}},"_links":{"self":[{"href":"https:\/\/webdomino.net\/index.php\/wp-json\/wp\/v2\/posts\/128006"}],"collection":[{"href":"https:\/\/webdomino.net\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/webdomino.net\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/webdomino.net\/index.php\/wp-json\/wp\/v2\/users\/266"}],"replies":[{"embeddable":true,"href":"https:\/\/webdomino.net\/index.php\/wp-json\/wp\/v2\/comments?post=128006"}],"version-history":[{"count":1,"href":"https:\/\/webdomino.net\/index.php\/wp-json\/wp\/v2\/posts\/128006\/revisions"}],"predecessor-version":[{"id":128007,"href":"https:\/\/webdomino.net\/index.php\/wp-json\/wp\/v2\/posts\/128006\/revisions\/128007"}],"wp:attachment":[{"href":"https:\/\/webdomino.net\/index.php\/wp-json\/wp\/v2\/media?parent=128006"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/webdomino.net\/index.php\/wp-json\/wp\/v2\/categories?post=128006"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/webdomino.net\/index.php\/wp-json\/wp\/v2\/tags?post=128006"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}