The B200 GPU packs 208 billion transistors and offers up to 20 petaflops of FP4 performance. It also includes a fast second-generation transformer engine featuring FP8 precision.
What just happened? At the Nvidia GTC 2024 conference on Monday, the company unveiled its Blackwell GPU platform that it says is designed for generative AI processing. The next-gen lineup includes the B200 GPU and GB200 Grace «superchip» that offer all the grunt needed by LLM inference workloads while substantially reducing energy consumption.
The B200 GPU packs 208 billion transistors and offers up to 20 petaflops of FP4 performance. It also includes a fast second-generation transformer engine featuring FP8 precision. The GB200 Grace combines two of these B200 chips with an Nvidia Grace CPU and connects them over an NVLink Chip-to-Chip (C2C) interface that delivers 900 GB/s of bidirectional bandwidth.
