🇨🇳cnBeta (Full RSS)•較早收集於 6m
黃仁勳宴請SK海力士HBM4工程師慶生

💡NVIDIA CEO woos HBM4 team—vital supply chain signal for AI infrastructure builds.
⚡ 30-Second TL;DR
有什麼變化
2月14日在聖塔克拉拉99 Chicken舉行
為什麼重要
此親民舉動突顯NVIDIA對SK海力士HBM供應的依賴,對Blackwell及未來AI GPU效能至關重要。可能緩解AI資料中心記憶體短缺疑慮。
下一步行動
Track SK Hynix Q1 earnings for HBM4 yield updates impacting NVIDIA GPU supply.
誰應關注:Enterprise & Security Teams
關鍵要點
- •2月14日在聖塔克拉拉99 Chicken舉行
- •30位SK海力士DRAM/HBM4核心工程師
- •黃仁勳親自為賓客倒酒
- •彰顯NVIDIA與SK海力士緊密合作
🧠 深度解析
背景與延伸:來自公開資料,非原文內容。引用 6 個來源。
🔑 增強重點摘要
- •SK Hynix secured 70% of NVIDIA's HBM4 orders for the Vera Rubin platform, utilizing 12-layer and 16-layer stacks.[1]
- •HBM4 features a 2048-bit I/O interface doubling HBM3E's bandwidth, custom logic die via TSMC 12nm/5nm processes, and 30-micrometer thinned dies for 16-high stacks.[1]
- •SK Hynix began HBM development in 2009, co-developed first TSV HBM with AMD in 2014, and released HBM3 in 2021 with mass production in 2022.[3][4]
🛠️ 技術深入
- •HBM4 doubles bus width to 2048-bit I/O from HBM3E's 1024-bit, enabling >2.0 TB/s per stack at lower clocks for improved power efficiency.[1]
- •Replaces DRAM base die with TSMC 12nm/5nm logic die integrating memory controllers and PHY, reducing latency by ~20%.[1]
- •16-high stacks achieved by thinning DRAM dies to 30 micrometers while maintaining 775-micrometer height limit.[1]
- •Power usage 40% more efficient than prior gen, >10 Gbps speed, capable of processing over 400 Full HD 5GB movies per second per stack.[3]
🔮 前景展望AI analysis grounded in cited sources
SK Hynix HBM4 will enable real-time training of trillion-parameter AI models
HBM4's high throughput and efficiency address energy costs prohibitive in current hardware for Vera Rubin platform.[1]
⏳ 時間線
2009
SK Hynix begins HBM development ahead of industry.
2014
Co-develops first TSV HBM with AMD.
2021-10
Develops world's first HBM3.
2022-06
Begins HBM3 mass production for NVIDIA.
2025-03
Delivers HBM4 samples to NVIDIA.
2026-01
Secures 70% of NVIDIA HBM4 orders for Vera Rubin.
📎 來源 (6)
Factual claims are grounded in the sources below. Forward-looking analysis is AI-generated interpretation.
- markets.chroniclejournal.com — Tokenring 2026 1 30 Sk Hynix Emerges As Indisputable AI Memory King with 70 Share of Nvidias Hbm4 Orders for Vera Rubin Platform
- technetbooks.com — Jensen Huang Nvidia AI Infrastructure
- Tom's Hardware — High Bandwidth Memory Future of AI One Team Spirit Sk Hynix
- news.skhynix.com — The Story of Sk Hynixs Hbm Development
- gurufocus.com — Nvidia and Sk Group Discuss Hbm4 Supply and AI Collaboration
- techinvestments.io — History and Outlook of the Memory
📰
AI 週報
閱讀本週精選 AI 大事摘要 →
👉相關動態
AI 策展新聞聚合。所有內容版權歸原始發布者所有。
原始來源: cnBeta (Full RSS) ↗
每週 AI 簡報
每週一封,可隨時退訂。
