Description

NVIDIA NVLINK Bridge 2-WAY 3-SLOT x16 Increasing compute demands in AI and high-performance computing (HPC) including an emerging class of trillion-parameter models are driving a need for multi-node, multi-GPU systems with seamless, high-speed communication between every GPU. To build the most powerful, end-to-end computing platform that can meet the speed of business, a fast, scalable interconnect is needed.

NVLink bandwidth per GPU: Second Generation – 300GB/s, Third Generation – 600GB/s, Fourth Generation 900GB/s

Maximum Number of Links per GPU: Second Generation – 6, Third Generation – 12, Fourth Generation – 18

Supported NVIDIA Architectures: Second Generation – NVIDIA Volta architecture, Third Generation – NVIDIA Ampere Architecture, Fourth Generation – NVIDIA Hopper Architecture