NVIDIA Blackwell, a new computing platform, allows enterprises to design and execute real-time generative AI on trillion-parameter big language models at up to 25x lower cost and energy usage than its predecessor.
Six transformative accelerated computing technologies in the Blackwell GPU architecture will enable breakthroughs in data processing,
engineering simulation, electronic design automation, computer-aided drug design, quantum computing, and generative AI, all emerging NVIDIA industries.
“For three decades we’ve pursued accelerated computing to enable transformative breakthroughs like deep learning and AI,”
said NVIDIA founder and CEO Jensen Huang. “Generative AI defines our era. Blackwell drives this new industrial revolution.
Working with the world's most dynamic organizations, we'll achieve AI's promise for every industry.”
AWS, Dell Technologies, Google, Meta, Microsoft, OpenAI, Oracle, Tesla, and xAI are likely to embrace Blackwell.
A 900GB/s ultra-low-power NVLink chip-to-chip interconnect links two NVIDIA B200 Tensor Core GPUs to the NVIDIA Grace CPU in the NVIDIA GB200 Grace Blackwell Superchip.