storage, networking and security. Vera Rubin NVL link 72 3.6% exoflops of compute 260 tab per second of all toall NVLink bandwidth the engine supercharging the era of Aentic AI. The Vera CPU rack designed for orchestration and Aentic workflows.The STX rack AI native storage built with Bluefield 4 scale out with Spectrum X co-acked optics increasing energy efficiency and resiliency and an incredible new addition the Gro 3 LPX rack tightly connected to Vera Rubin Gro's LPU's massive onchip SRAM a token accele ...

Those were the daysX Freeze (@XFreeze):Jensen Huang just told the story of how Elon Musk became NVIDIA’s very first customer for their powerful AI supercomputer - when literally nobody else in the world wanted it“When I announced this thing, nobody wanted to buy it. Not one purchase orderExcept for ElonHe was at https://t.co/fxyLaop1mi ...

Summary of NVIDIA Conference Call on Co-package Silicon Photonic Switch for Gigawatt AI Factories Company and Industry - **Company**: NVIDIA (NasdaqGS: NVDA) - **Industry**: AI Supercomputing and Data Center Infrastructure Core Points and Arguments 1. **AI Supercomputer Infrastructure**: The presentation emphasized the evolution of data centers into AI supercomputers, where multiple computing elements are interconnected to handle AI workloads effectively [3][4] 2. **Scale-Up and Scale-Out Networks**: NVIDIA's infrastructure includes NVLink for scale-up (connecting H100 GPUs) and Spectrum-X Ethernet for scale-out (connecting multiple racks) to form a large data center capable of running distributed AI workloads [4][5] 3. **Context Memory Storage**: The integration of BlueField DPUs for context memory storage is crucial for meeting the storage requirements of inferencing workloads [6] 4. **Scale Across Infrastructure**: The need to connect multiple data centers is addressed through Spectrum-X Ethernet, enabling a single computing engine to support large-scale AI factories [7] 5. **Spectrum-X Ethernet Design**: This Ethernet technology is specifically designed for AI workloads, focusing on high performance and low jitter, which is essential for distributed computing [9][10] 6. **Performance Improvements**: Spectrum-X Ethernet has shown a 3x improvement in expert dispatch performance and a 1.4x increase in training performance, ensuring all GPUs work synchronously [12][13] 7. **Power Consumption and Efficiency**: The optical connectivity in data centers can consume up to 10% of computing resources, and reducing this power consumption is vital for enhancing compute capability [14] 8. **Co-package Optics Introduction**: Co-package optics integrates the optical engine within the switch, significantly reducing power consumption by up to 5x and increasing the resiliency of the data center [15][18] 9. **Optical Engine Design**: The optical engine consists of a photonic IC and electronic IC, designed to improve signal integrity and reliability [20][21] 10. **Deployment Timeline**: Co-package optics deployments are expected to begin in 2026, with initial partners including CoreWeave, Lambda, and Texas Advanced Computing Center [26] Additional Important Content 1. **Reliability Issues**: Previous optical networks faced reliability issues due to human handling of external transceivers. Co-package optics mitigates this by integrating the optical engine within the switch, reducing human touch and increasing reliability [27][29] 2. **Collaboration with TSMC**: The partnership with TSMC focuses on creating a reliable packaging process for co-package optics, which is crucial for mass production [30][31] 3. **Flexibility of Co-package Optics**: Unlike traditional pluggable optics, co-package optics offers a unified technology that can cover various distances within and between data centers, reducing the need for multiple transceivers [37][38] 4. **Adoption Challenges**: Hyperscalers may be cautious about adopting co-package optics due to concerns over the initial investment and the transition from pluggable optics, but the benefits in power efficiency and resiliency are expected to drive adoption [39][40] 5. **Future Innovations**: Continuous innovation is anticipated in switch design, optical network density, and overall data center efficiency, with a focus on larger radix switches and improved cooling solutions [54][55] This summary encapsulates the key points discussed during the NVIDIA conference call, highlighting the advancements in AI supercomputing infrastructure and the introduction of co-package optics technology.

Uh Korea is going to be um uh growing tremendously in semiconductors in the coming years and the reason for that as you know uh Samsung and SK helped me invent the AI supercomputer. Without the HBM memory there is no AI supercomputer and over the next decade uh memory technology and semiconductor growth here in Korea will be very significant with with with respect to China. Uh, China is now 0% of our business.We used to have 95% share of the AI business in China. Now we're at 0% share. And I'm disappointed ...

The live reaction of @elonmusk and Jensen HuangCreated by Grok imagine https://t.co/EbIMohZeHhTesla Owners Silicon Valley (@teslaownersSV):BREAKING: . NVIDIA CEO Jensen Huang kicks off the rollout of DGX Spark, the world’s smallest AI supercomputer, with a hand-delivery to Elon Musk https://t.co/6eJp6wL92P ...

NVIDIA accelerated computing starts with DGX, the world's AI supercomputer, the engine behind the large language model breakthrough. IHand delivered the world's first DGX to open AI. Since then, half of the Fortune 100 companies have installed DGX AI supercomputers. DGX has become the essential instrument of AI. The GPU of DGX is eight H100 modules.H100 has a transformer engine designed to process models like the amazing chat GPT which stands for generative pre-trained transformers. The eight H100 modules a ...

>> Amazon Web Services unveiling a new chip intended to take on Nvidia. Of course, in those cloud wars. Kristina Partsinevelos joins us now.She's in Austin, Texas and has more for us this morning. Christina. >> David, this is where AWS chips are born. This is Annapurna Labs.It's owned by AWS. And like you said today they are announcing their new graviton four chip will offer 600GB per second of networking bandwidth. So this is a CPU and really shows how their custom chip strategy is competing against, you k ...

Blackwell B200 Super Chip Manufacturing - Blackwell B200 超级芯片由 12 英寸晶圆上的 2000 亿个晶体管构建而成 [1] - 每个晶圆被划分为单独的 Blackwell 芯片，经过测试和分类，将好的芯片分离出来 [2] - 32 个 Blackwell 芯片和 128 个 HBM 堆栈通过芯片基板工艺连接到定制的硅中介层晶圆上 [2] - 组装完成后，经过烘烤、模塑和固化，形成 Blackwell B200 超级芯片，并在 125° 的烤箱中进行压力测试 [3] - Grace Blackwell PCB 上通过机器人昼夜不停地放置超过 10,000 个组件 [3] Interconnect and Communication - MVLink 开创性高速链路，可连接多个 GPU 并扩展为大型虚拟 GPU [5] - MVLink 交换机托盘由 MVLink 交换机芯片构建，提供每秒 14.4 万亿字节的全互连带宽 [5] - MVLink 主干形成定制的盲插背板，通过 5,000 根铜缆连接所有 72 个 Blackwell 或 144 个 GPU 芯片，形成一个巨大的 GPU，提供每秒 130 万亿字节的全互连带宽 [5] - Connect X7 Super Nix 用于实现横向扩展通信，Bluefield 3 DPU 用于卸载和加速网络、存储和安全任务 [4] System Integration and Scale - 总计 120 万个组件、200 万米铜缆和 130 万亿个晶体管，总重量接近 2 吨 [5] - 定制的液冷铜块用于将芯片保持在最佳温度 [4] - 所有部件集成到 GB200 计算托盘中，最终组装成机架规模的 AI 超级计算机 [4][5] Vision - Blackwell 不仅仅是一项技术奇迹，更是全球协作和创新的力量的证明，推动着塑造我们未来各地的发现和解决方案 [6]