NVIDIA has launched its next-generation of AI supercomputer chips that will likely play a large role in future breakthroughs in deep learning and large language models (LLMs) like OpenAI's GPT-4, the company announced. The technology represents a significant leap over the last generation and is poised to be used in data centers and supercomputers -- working on tasks like weather and climate prediction, drug discovery, quantum computing and more. The key product is the HGX H200 GPU based on NVIDIA's "Hopper" architecture, a replacement for the popular H100 GPU. It's the company's first chip to use HBM3e memory that's faster and has more capacity, thus making it better suited for large language models. "With HBM3e, the NVIDIA H200 delivers 141GB of memory at 4.8 terabytes per second, nearly double the capacity and 2.4x more bandwidth compared with its predecessor, the NVIDIA A100," the company wrote.

In recent years, advances in AI have produced algorithms for everything from image recognition to instantaneous translation. But when it comes to applying these advances in the real world, we're only just getting started. A new product from Nvidia announced today at GTC -- a $99 AI computer called the Jetson Nano -- should help speed that process. The Nano is the latest in Nvidia's line of Jetson embedded computing boards, used to provide the brains for robots and other AI-powered devices. Plug one of these into your latest creation, and it'll be able to handle tasks like object recognition and autonomous navigation without relying on cloud processing power.

It seems like Nvidia announces the fastest GPU in history multiple times a year, and that's exactly what's happened again today; the Titan V is "the most powerful PC GPU ever created," in Nvidia's words. It represents a more significant leap than most products that have made that claim, however, as it's the first consumer-grade GPU based around Nvidia's new Volta architecture. That said, a liberal definition of the word "consumer" is in order here -- the Titan V sells for $2,999 and is focused around AI and scientific simulation processing. Nvidia claims up to 110 teraflops of performance from its 21.1 billion transistors, with 12GB of HBM2 memory, 5120 CUDA cores, and 640 "tensor cores" that are said to offer up to 9 times the deep-learning performance of its predecessor. Also it comes in gold and black, which looks pretty cool.

The sophisticated neural networks underlying systems like Google's Deep Dream and all manner of interesting experiments require a great deal of computing power. NVIDIA proposes to put all that horsepower in a single box, specially engineered to meet the needs of AI researchers. NVIDIA already has GPUs specializing in deep learning applications, so this was a logical next step. It's called the DGX-1, and it's basically a fancy enclosure for an 8-GPU supercomputing cluster. There are 8 Tesla P100 cards in there with 16 GB of RAM each, plus 7 TB of storage for all the raw data you'll be training your networks on.