NVLink Fabric: Advancing Multi-GPU Processing
NVlink is the world’s first high-speed GPU interconnect that can be used for data and control code transfers in processor systems between CPUs and GPUs and solely between GPUs. NVLink specific a point-to-point connections data rates of 20 and 25 Gbit/s (NVLink/NVLink2) per data lane per direction. Total data rates in sysems are 160 and 300 GByte (NVLink/NVLink2) for the total system sum of input and output data streams.
NVIDIA Quadro GV100 and NVLink
The new Quadro GV100 packs 7.4 TFLOPS double-precision, 14.8 TFLOPS single-precision and 118.5 TFLOPS deep learning performance, and is equipped with 32GB of high-bandwidth memory capacity. Two GV100 cards can be combined using NVIDIA NVLink interconnect technology to scale memory and performance, creating a massive visual computing solution in a single workstation chassis.
» Click here to learn more about the NVIDIA Quadro GV100
Related NVLink Bridge Products
NVIDIA Quadro GP100 (VCQGP100-PB) Powered by Pascal GPU architecture, the NVIDIA Quadro GP100 is equipped with the most advanced visualization and simulation capabilities to meet the needs of the most demanding professional workflows.
NVIDIA NVLink Bridge (NVLINK-2W2S-KIT) Connect a pair of Quadro GP100 cards with NVLink to increase the effective memory footprint and scale application performance by enabling GPU-to-GPU data transfers at rates up to 80 GB/s (bidirectional).