--- 格式版本: 2 标题: "NVIDIA, Intel and Partners Supercharge AI Computing Efficiency | NVIDIA Blog" 原文链接: "https://blogs.nvidia.com/blog/intel-partners-ai-computing-efficiency/" 发布日期: "2026-06-30" 发布时间校准状态: "found" 发布时间来源: "llm:strict_original_body" 发布时间证据: "time class=related-news-date nvidia-article-date datetime=2026-06-30T08:00:57-07:00: Jun 30, 2026" 发布时间校准原因: "该日期位于标题下方，且带有 nvidia-article-date 类名，符合文章发布时间的特征。" 发布时间校准置信度: "1" 发布时间候选数量: 36 发布时间严格候选数量: 12 发布时间原页读取状态: "原页面来自已抓取 HTML" 发布时间未找到原因: "候选日期无效或 LLM 未确认" 发布时间校准时间: "2026-07-20T11:29:34+08:00" 发现时间: "2026-07-20T09:24:55+08:00" 入库时间: "2026-07-20T03:35:16.126Z" 来源平台: "NVIDIA Blog 搜索" 搜索渠道: "source_template" 搜索词: "https://blogs.nvidia.com/?s=PCIe%20switch" 匹配关键词: - "PCIe switch" - "GPU" 相关厂家: - "NVIDIA" - "QCT" 相关专家: [] 内容类型: "网页" 抓取工具: "AgentKey Scrape" 清洗工具: "AgentKey Markdown + LLM 正文裁剪" 原始附件: [] AI优质: "否" AI打分: 58 AI分档: "召回候选" AI质检状态: "不通过" AI打分理由: "NVIDIA官方发布，但内容聚焦DGX H100系统与Intel 4代至强CPU的能效提升，未涉及超节点/AI Rack/机柜级架构、供电散热或高速互连细节，技术展开偏通用，正文较短且缺乏量产部署具体信号。" AI质检模型: "qwen3.6-plus" AI质检时间: "2026-07-20T11:35:16+08:00" AI主题相关性: 12 AI来源权威性: 14 AI新颖性: 10 AI技术细节: 10 AI商业部署信号: 8 AI完整性: 4 图片摘要: - "★ ./assets/img-83d2f103.jpg | diagram | 展示大规模 AI 集群物理架构，包含密集计算节点与互连线缆，体现高性能数据中心的拓扑布局。" - "★ ./assets/img-1f6575f1.png | diagram | 展示 GPU 与 Vera CPU 的互连架构与任务协同，体现异构计算中的数据流与处理路径。" - "✓ ./assets/img-3511966c.jpg | photo | NVIDIA 园区外景实拍，展示品牌标识，作为合作伙伴生态与基础设施建设的背景配图。" - "✓ ./assets/img-e47e99dc.png | infographic | AI 推理软件栈概念图，以发光立方体象征高效能计算核心，展示降低 Token 成本的技术愿景。" 采集批次: "2026年7月20日9点23分34秒" 采集批次ID: "20260720-092334-062" 去重键: "https://blogs.nvidia.com/blog/intel-partners-ai-computing-efficiency" --- AI is at the heart of humanity’s most transformative innovations — from developing COVID vaccines at unprecedented speeds and diagnosing cancer to powering autonomous vehicles and understanding climate change. Virtually every industry will benefit from adopting [AI computing](https://blogs.nvidia.com/blog/what-is-ai-computing/), but the technology has become more resource intensive as neural networks have increased in complexity. To avoid placing unsustainable demands on electricity generation to run this computing infrastructure, the underlying technology must be as efficient as possible. Accelerated computing powered by NVIDIA GPUs and the NVIDIA AI platform offer the efficiency that enables data centers to sustainably drive the next generation of breakthroughs. And now, timed with the launch of 4th Gen Intel Xeon Scalable processors, NVIDIA and its partners have kicked off a new generation of accelerated computing systems that are built for energy-efficient AI. When combined with [NVIDIA H100 Tensor Core GPUs](https://www.nvidia.com/en-us/data-center/h100/), these systems can deliver dramatically higher performance, greater scale and higher efficiency than the prior generation, providing more computation and problem-solving per watt. The new Intel CPUs will be used in [NVIDIA DGX H100 systems](https://www.nvidia.com/en-us/data-center/dgx-h100/), as well as in more than 60 servers featuring H100 GPUs from NVIDIA partners around the world. ## Supercharging Speed, Efficiency and Savings for Enterprise AI The coming NVIDIA and Intel-powered systems will help enterprises run workloads an average of 25x more efficiently than traditional CPU-only data center servers. This incredible performance per watt means less power is needed to get jobs done, which helps ensure the power available to data centers is used as efficiently as possible to supercharge the most important work. Compared to prior-generation accelerated systems, this new generation of NVIDIA-accelerated servers speed training and inference to boost [energy efficiency](https://blogs.nvidia.com/blog/what-is-green-computing/) by 3.5x – which translates into real cost savings, with AI data centers delivering over 3x lower total cost of ownership. ## New 4th Gen Intel Xeon CPUs Move More Data to Accelerate NVIDIA AI Among the features of the new 4th Gen Intel Xeon CPU is support for PCIe Gen 5, which can double the data transfer rates from CPU to NVIDIA GPUs and networking. Increased PCIe lanes allow for a greater density of GPUs and high-speed networking within each server. Faster memory bandwidth also improves the performance of data-intensive workloads such as AI, while networking speeds — up to 400 gigabits per second (Gbps) per connection — support faster data transfers between servers and storage. NVIDIA DGX H100 systems and servers from NVIDIA partners with H100 PCIe GPUs come with a license for [NVIDIA AI Enterprise](https://www.nvidia.com/en-in/data-center/products/ai-enterprise/), an end-to-end, secure, cloud-native suite of AI development and deployment software, providing a complete platform for excellence in efficient enterprise AI. ## NVIDIA DGX H100 Systems Supercharge Efficiency for Supersize AI As the fourth generation of the world’s premier purpose-built AI infrastructure, NVIDIA DGX H100 systems provide a fully optimized platform powered by the operating system of the accelerated data center, [NVIDIA Base Command](https://www.nvidia.com/en-us/data-center/base-command/) software. Each DGX H100 system features eight NVIDIA H100 GPUs, 10 [NVIDIA ConnectX-7](https://nvdam.widen.net/s/vmnr5rmhrl/infiniband-ethernet-datasheet-connectx-7-ds-nv-us-2544471) network adapters and dual 4th Gen Intel Xeon Scalable processors to deliver the performance required to build large [generative AI](https://www.nvidia.com/en-us/glossary/data-science/generative-ai/) models, [large language models](https://blogs.nvidia.com/blog/what-are-large-language-models-used-for/), [recommender systems](https://blogs.nvidia.com/blog/whats-a-recommender-system/) and more. Combined with NVIDIA networking, this architecture supercharges efficient computing at scale by delivering up to 9x more performance than the previous generation and 20x to 40x more performance than unaccelerated X86 dual-socket servers for AI training and HPC workloads. If a language model previously required 40 days to train on a cluster of X86-only servers, the NVIDIA DGX H100 using Intel Xeon CPUs and ConnectX-7 powered networking could complete the same work in as little as 1-2 days. NVIDIA DGX H100 systems are the building blocks of an enterprise-ready, turnkey [NVIDIA DGX SuperPOD](https://www.nvidia.com/en-us/data-center/dgx-superpod/), which delivers up to [one exaflop](https://blogs.nvidia.com/blog/what-is-an-exaflop/) of AI performance, providing a leap in efficiency for large-scale enterprise AI deployment. ## NVIDIA Partners Boost Data Center Efficiency For AI data center workloads, NVIDIA H100 GPUs enable enterprises to build and deploy applications more efficiently. Bringing a new generation of performance and energy efficiency to enterprises worldwide, a broad portfolio of systems with H100 GPUs and 4th Gen Intel Xeon Scalable CPUs are coming soon from NVIDIA partners, including ASUS, Atos, Cisco, Dell Technologies, Fujitsu, GIGABYTE, Hewlett Packard Enterprise, Lenovo, QCT and Supermicro. As the bellwether of the efficiency gains to come, the [Flatiron Institute’s Lenovo ThinkSystem with NVIDIA H100 GPUs](https://blogs.nvidia.com/blog/green/) tops the latest Green500 list — and NVIDIA technologies power 23 of the top 30 systems on the list. The Flatiron system uses prior-generation Intel CPUs, so even more efficiency is expected from the systems now coming to market. Additionally, connecting servers with NVIDIA ConnectX-7 networking and Intel 4th Gen Xeon Scalable processors will increase efficiency and reduce infrastructure and power consumption. NVIDIA ConnectX-7 adapters support PCIe Gen 5 and 400 Gbps per connection using Ethernet or InfiniBand, doubling networking throughput between servers and to storage. The adapters support advanced networking, storage and security offloads. ConnectX-7 reduces the number of cables and switch ports needed, saving 17% or more on electricity needed for the networking of large GPU-accelerated HPC and AI clusters and contributing to the better energy efficiency of these new servers. ## NVIDIA AI Enterprise Software Delivers Full-Stack AI Solution These next-generation systems also deliver a leap forward in operational efficiency as they’re optimized for the [NVIDIA AI Enterprise software suite](https://blogs.nvidia.com/blog/ai-enterprise-software-3/). Running on NVIDIA H100, NVIDIA AI Enterprise accelerates the data science pipeline and streamlines the development and deployment of predictive AI models to automate essential processes and gain rapid insights from data. With an extensive library of full-stack software, including AI workflows of reference applications, frameworks, pretrained models and infrastructure optimization, the software provides an ideal foundation for scaling enterprise AI success. To try out NVIDIA H100 running AI workflows and frameworks supported in NVIDIA AI Enterprise, sign up for [NVIDIA LaunchPad](https://www.nvidia.com/en-us/launchpad/) free of charge. [Watch NVIDIA founder and CEO Jensen Huang](https://www.youtube.com/watch?v=-OhKhT4r4mo) speak at the 4th Gen Intel Xeon Scalable processor launch event. ![Why Performance per Watt Is the Ultimate Metric for AI Infrastructure Efficiency](./assets/img-83d2f103.jpg) ![AI Innovators Adopt NVIDIA Vera — Why Max Single-Threaded CPU at Scale Matters](./assets/img-1f6575f1.png) ![NVIDIA Unlocks AI Compute at Scale, Inviting Partners to Power the AI Infrastructure Buildout](./assets/img-3511966c.jpg) ![How NVIDIA’s Inference Software Stack Powers the Lowest Token Cost](./assets/img-e47e99dc.png)