--- 格式版本: 2 标题: "AI Workloads Spur Competition in Networking Chips" 原文链接: "https://www.datacenterknowledge.com/data-center-chips/ai-workloads-spur-competition-in-networking-chips" 发布日期: "2026-08-17" 发布时间校准状态: "found" 发布时间需复核: "否" 发布时间来源: "llm:scrape:strict_markdown_body" 发布时间证据: "AUG 17, 2026" 发布时间校准原因: "标题附近明确标注的日期，且与发现时间一致，是最可能的文章发布时间" 发布时间校准置信度: "1" 发布时间候选数量: 9 发布时间严格候选数量: 9 发布时间原页读取状态: "" 发布时间未找到原因: "" 发布时间校准时间: "2026-08-17T20:58:50+08:00" 发布时间仲裁状态: "confirmed" 发布时间仲裁尝试次数: 1 发布时间仲裁耗时毫秒: 30375 发现时间: "2026-08-17T20:36:37+08:00" 入库时间: "2026-08-17T12:59:18.847Z" 来源平台: "Data Center Knowledge 搜索" 搜索渠道: "source_template" 搜索词: "https://www.datacenterknowledge.com/search?q=Marvell" 匹配关键词: - "Marvell" - "AI" - "performance" - "latency" - "bandwidth" 相关厂家: - "NVIDIA" - "Google" - "Broadcom" 相关专家: [] 内容类型: "网页" 抓取工具: "CDP Render" 清洗工具: "CDP Text + Defuddle/Readability 正文提取" 原始附件: [] AI优质: "否" AI打分: 43 AI分档: "非优质" AI质检状态: "不通过" AI打分理由: "搜索入口页，正文不完整且发布日期旧（2023年7月），仅泛泛讨论AI网络芯片竞争，缺乏超节点/AI Rack直接相关的技术细节、架构或商业部署信号。" AI质检模型: "ali-deepseek-v4-flash" AI质检时间: "2026-08-17T20:59:27+08:00" AI主题相关性: 10 AI来源权威性: 10 AI新颖性: 5 AI技术细节: 10 AI商业部署信号: 5 AI完整性: 3 AI摘要: "思科发布Silicon One G200和G202网络芯片，用于支持AI/ML工作负载，与博通、英伟达和Marvell竞争。思科称该芯片可使AI/ML集群减少40%交换机、50%光模块和33%网络层；" AI摘要模型: "ali-deepseek-v4-flash" AI摘要时间: "2026-09-07T03:23:01.850Z" 采集批次: "2026年8月17日19点06分47秒" 采集批次ID: "20260817-190647-603" 去重键: "https://www.datacenterknowledge.com/data-center-chips/ai-workloads-spur-competition-in-networking-chips" --- An Informa TechTarget Publication NEWSLETTER SIGN-UP DATA CENTER CHIPS INFRASTRUCTURE DATA CENTER HARDWARE NEWS AI Workloads Spur Competition in Networking Chips Cisco announced the Silicon One G200 and G202 networking chips that support AI ML workloads. How are Broadcom, NVIDIA, and others keeping up? Brian T. Horowitz July 18, 2023 2 Min Read ALAMY Networking vendors are competing in a tight market to produce networking chips that can handle artificial intelligence (AI) and machine learning (ML) workloads. Late last month, Cisco announced its Silicon One G200 and G202 ASICs, pitting it against offerings from Broadcom, NVIDIA, and Marvell. A recent IDC forecast shows how companies plan to spend more on AI. The research firm predicts that global spending on AI will climb to $154 billion in 2023 and at least $300 billion by 2026. In addition, by 2027, almost 1 in 5 Ethernet switch ports that data centers purchase will be related to AI/ML and accelerated computing, according to a report by research firm 650 Group. How Cisco Networking Chips Improve Workload Time Cisco says the Silicon One G200 and G202 ASICs carry out AI and ML tasks with 40% fewer switches at 51.2Tbps. They enable customers to build a 32K 400G GPUs AI/ML cluster on a two-layer network with 50% less optics and 33% less networking layers, according to the company. The G200 and G202 are the fourth generation of the company's Silicon One chips, which are designed to offer unified routing and switching. "Cisco provides a converged architecture that can be used across routing, switching, and AI/ML networks," Cisco fellow Rakesh Chopra told Network Computing. The ultralow latency, high performance, and advanced load balancing allow the networking chips to handle AI/ML workloads, according to Chopra. In addition, enhanced Ethernet-based capabilities also make these workloads possible. “Fully scheduled and enhanced Ethernet are ways to improve the performance of an Ethernet-based network and significantly reduce job completion time,” Chopra said. “With enhanced Ethernet, customers can reduce their job completion time by 1.57x, making their AI/ML jobs complete quicker and with less power.” Cisco says the G200 and G202 also incorporate load balancing, better fault isolation, and a fully shared buffer, which allow a network to support optical performance for AI/ML workloads. How Chipmakers Are Tackling AI Networking vendors are rolling out networking chips with higher bandwidth and radix, which are the number of devices in which they can connect to be able to carry out AI tasks, according to Chopra. They are also enabling GPUs to communicate without interference, eliminating bottlenecks for AI/ML workloads, he said. Read the rest of this article on Network Computing. About the Author Brian T. Horowitz Want more Data Center Knowledge stories in your Google search results? ADD US NOW Subscribe to the Data Center Knowledge Newsletter Get analysis and expert insight on the latest in data center business and technology delivered to your inbox daily. NEWSLETTER SIGN-UP Recommendations SPONSORED The AI era is defined by pushing the frontiers of what’s possible AUG 17, 2026 DATA CENTER CONSTRUCTION New Data Center Developments: June 2026 by James Walker JUN 03, 2026 ENERGY & POWER SUPPLY Why Data Centers Are Turning to Behind-the-Meter Power by Jack Vaughan APR 15, 2026 COOLING Data Center Cooling Methods: Costs vs. Efficiency vs. Sustainability by Christopher Tozzi OCT 31, 2025 Editor's Choice DATA CENTER SITE SELECTION Virginia Report Finds Groundwater Running Dry for New Data Centers JUL 30, 2026 PHYSICAL SECURITY Data Centers Under Fire: Do Facilities Need Counter-Drone Defenses? JUL 30, 2026 OUTAGES Fault in Data Center Alley Triggered 3 GW Load Drop JUL 23, 2026 ENERGY & POWER SUPPLY DOE: AI Data Centers Are Transforming America’s Transmission Map JUL 24, 2026 SUSTAINABILITY After the AI Rush, Can Data Centers Reclaim Sustainability? JUL 23, 2026 Want more Data Center Knowledge stories in your Google search results? Subscribe to the Data Center Knowledge Newsletter Get analysis and expert insight on the latest in data center business and technology delivered to your inbox daily. NEWSLETTER SIGN-UP Industry Voices SPONSORED CONTENT The AI era is defined by pushing the frontiers of what’s possible AUG 17, 2026 DATA CENTER SITE SELECTION Land Banking Explained: A Novel Strategy for Data Center Expansion AUG 14, 2026 DATA CENTER WORLD POWER Join the entire data center ecosystem September 21 – 23, 2026, at the Gaylord Texan Resort & Convention Center in Dallas, TX.  LEARN MORE Discover More InformationWeek Data Center World AFCOM Working With Us About Us Meet Our Writers Reprints Advertise Contact Us Join Us NEWSLETTER SIGN-UP Follow Us Copyright © 2026 TechTarget, Inc. d/b/a Informa TechTarget. This website is owned and operated by Informa TechTarget, part of a global network that informs, influences and connects the world’s technology buyers and sellers. All copyright resides with them. Informa PLC’s registered office is 5 Howick Place, London SW1P 1WG. Registered in England and Wales. TechTarget, Inc.’s registered office is 275 Grove St. Newton, MA 02466. Home| CCPA: Do not sell my personal info| Cookies| Privacy| Terms Your Privacy Choices