NVIDIA has pioneered accelerated computing to tackle challenges that otherwise can’t be solved. Our work in AI and computer graphics is transforming industries valued at more than $100 trillion, from gaming to healthcare to transportation, and profoundly impacting society. The New Engine for the World’s AI Infrastructure Makes Order-of-Magnitude Performance Leap. With the ability to securely scale diverse workloads in every data center—from small enterprise to exascale high-performance computing (HPC) and trillion-parameter AI—Hopper lets brilliant innovators fulfill their life's work at the fastest pace in human history. Built with over 80 billion transistors using a cutting edge TSMC 4N process, Hopper features five groundbreaking innovations that fuel the NVIDIA H100 Tensor Core GPU and combine to deliver an incredible 30X speedup over the prior generation on AI inference of NVIDIA Megatron 530B chatbot, the world’s largest generative language model. The NVIDIA Hopper architecture advances Tensor Core Technology with the Transformer Engine, designed to accelerate the training of AI models. Hopper Tensor Cores have the capability to apply mixed FP8 and FP16 precisions to dramatically accelerate AI calculations for transformers. Hopper also triples the floating-point operations per second (FLOPS) for TF32, FP64, FP16, and INT8 precisions over the prior generation. Combined with Transformer Engine and fourth-generation NVIDIA® NVLink®, Hopper Tensor Cores power an order-of-magnitude speedup on HPC and AI workloads.