NVIDIA Blackwell Platform Ushers in a New Era of AI Computing

At the GTC conference, NVIDIA unveiled the Blackwell platform, a groundbreaking advancement in accelerated computing designed to power the next generation of artificial intelligence. This new architecture promises to deliver real-time generative AI capabilities on massive trillion-parameter large language models, achieving up to a 25x reduction in cost and energy consumption compared to its predecessors.

Six Transformative Technologies

The Blackwell GPU architecture introduces six key technologies that will drive breakthroughs across various fields:

• World’s Most Powerful Chip: Featuring 208 billion transistors, the Blackwell GPUs are built on a custom-built 4NP TSMC process. These GPUs use a chip-to-chip link with a 10TB/second data transfer rate to function as a single, unified GPU.
• Second-Generation Transformer Engine: This engine, supported by new micro-tensor scaling support and advanced NVIDIA dynamic range management algorithms, will double compute capacity and facilitate larger model sizes with new 4-bit floating point AI inference capabilities.
• Fifth-Generation NVLink: This latest iteration of NVLink delivers 1.8TB/s bidirectional throughput per GPU. This groundbreaking speed enables seamless, high-speed communication for multitrillion-parameter and mixture-of-experts AI models that use up to 576 individual GPUs.
• RAS Engine: Blackwell-powered GPUs incorporate a dedicated engine for reliability, availability, and serviceability. Additionally, the Blackwell architecture leverages AI-based preventative maintenance to run diagnostics and predict reliability issues, helping to keep systems online for weeks or even months, which reduces operating costs.
• Secure AI: Advanced confidential computing capabilities are included to secure AI models and protect customer data. This security is achieved without impacting performance, with support for new native interface encryption protocols.
• Decompression Engine: A dedicated decompression engine supports the latest formats, accelerating database queries to deliver the highest performance in data analytics and data science.

A Massive Superchip: The NVIDIA GB200

The NVIDIA GB200 Grace Blackwell Superchip connects two NVIDIA B200 Tensor Core GPUs to the NVIDIA Grace CPU via a 900GB/s ultra-low-power NVLink chip-to-chip interconnect. For maximum performance, GB200-powered systems can connect to NVIDIA Quantum-X800 InfiniBand and Spectrum-X800 Ethernet platforms, which offer advanced networking at speeds up to 800Gb/s. The GB200 is a key component of the NVIDIA GB200 NVL72, a multi-node, liquid-cooled, rack-scale system designed for the most compute-intensive workloads. The system combines 36 Grace Blackwell Superchips, comprised of 72 Blackwell GPUs and 36 Grace CPUs, that are interconnected by fifth-generation NVLink. Furthermore, GB200 NVL72 also includes NVIDIA BlueField-3 data processing units to facilitate cloud network acceleration, composable storage, zero-trust security, and GPU compute elasticity in hyperscale AI clouds.

The GB200 NVL72 system provides up to a 30x performance improvement for large language model (LLM) inference workloads when compared to an equal number of NVIDIA H100 Tensor Core GPUs. The system also reduces cost and energy consumption by up to 25x. This platform functions as a single GPU with an AI performance of 1.4 exaflops and 30TB of fast memory and is a core building block for the DGX SuperPOD. In addition, NVIDIA offers the HGX B200, a server board that links eight B200 GPUs via NVLink for x86-based generative AI platforms.

Widespread Adoption and Partnerships

NVIDIA anticipates widespread adoption of the Blackwell platform from a diverse group of organizations, including:

• Cloud Service Providers: Amazon Web Services, Google Cloud, Microsoft Azure, and Oracle Cloud Infrastructure will offer Blackwell-powered instances immediately, along with NVIDIA Cloud Partner program companies like Applied Digital, CoreWeave, Crusoe, IBM Cloud, Lambda, and Nebius.
• AI Cloud Providers: Sovereign AI clouds will provide Blackwell-based cloud services and infrastructure, including Indosat Ooredoo Hutchinson, Nexgen Cloud, Oracle EU Sovereign Cloud, and the Oracle US, UK, and Australian Government Clouds.
• Server Manufacturers: Cisco, Dell, Hewlett Packard Enterprise, Lenovo, and Supermicro are expected to deliver a wide range of servers based on Blackwell products. Aivres, ASRock Rack, ASUS, Eviden, Foxconn, GIGABYTE, Inventec, Pegatron, QCT, Wistron, Wiwynn, and ZT Systems will also build servers based on Blackwell.
• Software Makers: Ansys, Cadence, and Synopsys, prominent engineering simulation leaders, will utilize Blackwell-based processors to accelerate their software for simulating electrical, mechanical, and manufacturing systems and parts.

Industry Leaders’ Perspectives

Key figures from leading tech companies have expressed their enthusiasm and support for the Blackwell platform:

• Sundar Pichai, CEO of Alphabet and Google: “As we enter the AI platform shift, we continue to invest deeply in infrastructure for our own products and services, and for our Cloud customers. We are fortunate to have a longstanding partnership with NVIDIA, and look forward to bringing the breakthrough capabilities of the Blackwell GPU to our Cloud customers and teams across Google, including Google DeepMind, to accelerate future discoveries.”
• Andy Jassy, president and CEO of Amazon: “Our deep collaboration with NVIDIA goes back more than 13 years, when we launched the world’s first GPU cloud instance on AWS… It’s why the new NVIDIA Blackwell GPU will run so well on AWS and the reason that NVIDIA chose AWS to co-develop Project Ceiba…Through this joint effort between AWS and NVIDIA engineers, we’re continuing to innovate together to make AWS the best place for anyone to run NVIDIA GPUs in the cloud.”
• Michael Dell, founder and CEO of Dell Technologies: “Generative AI is critical to creating smarter, more reliable and efficient systems. Dell Technologies and NVIDIA are working together to shape the future of technology. With the launch of Blackwell, we will continue to deliver the next-generation of accelerated products and services to our customers, providing them with the tools they need to drive innovation across industries.”
• Demis Hassabis, cofounder and CEO of Google DeepMind: “The transformative potential of AI is incredible, and it will help us solve some of the world’s most important scientific problems. Blackwell’s breakthrough technological capabilities will provide the critical compute needed to help the world’s brightest minds chart new scientific discoveries.”
• Mark Zuckerberg, founder and CEO of Meta: “AI already powers everything from our large language models to our content recommendations, ads, and safety systems, and it’s only going to get more important in the future. We’re looking forward to using NVIDIA’s Blackwell to help train our open-source Llama models and build the next generation of Meta AI and consumer products.”
• Satya Nadella, executive chairman and CEO of Microsoft: “We are committed to offering our customers the most advanced infrastructure to power their AI workloads. By bringing the GB200 Grace Blackwell processor to our datacenters globally, we are building on our long-standing history of optimizing NVIDIA GPUs for our cloud, as we make the promise of AI real for organizations everywhere.”
• Sam Altman, CEO of OpenAI: “Blackwell offers massive performance leaps, and will accelerate our ability to deliver leading-edge models. We’re excited to continue working with NVIDIA to enhance AI compute.”
• Larry Ellison, chairman and CTO of Oracle: “Oracle’s close collaboration with NVIDIA will enable qualitative and quantitative breakthroughs in AI, machine learning and data analytics…In order for customers to uncover more actionable insights, an even more powerful engine like Blackwell is needed, which is purpose-built for accelerated computing and generative AI.”
• Elon Musk, CEO of Tesla and xAI: “There is currently nothing better than NVIDIA hardware for AI.”

NVIDIA’s Blackwell platform is positioned to drive significant advancements in AI, offering unprecedented performance, efficiency, and security. The platform and NVIDIA are actively working with industry leaders in cloud computing to develop a future where generative AI is the norm.