NVLink

GPTKB entity

Statements (52)
Predicate Object
gptkbp:instanceOf gptkb:personal_computer
gptkbp:announced 2014
gptkbp:connects gptkb:NVSwitch
GPUs
CPUs (in some systems)
gptkbp:developedBy gptkb:NVIDIA
gptkbp:enables faster data transfer between GPUs
scalable GPU memory pooling
https://www.w3.org/2000/01/rdf-schema#label NVLink
gptkbp:introducedIn gptkb:NVIDIA_Pascal_architecture
gptkbp:memoryBusWidth up to 25 GB/s per lane (NVLink 2.0)
up to 50 GB/s per lane (NVLink 3.0)
gptkbp:purpose high-speed GPU interconnect
gptkbp:replacedBy PCI Express (in some use cases)
gptkbp:successor gptkb:NVIDIA_SLI
gptkbp:supports multi-GPU communication
gptkbp:supportsProtocol point-to-point interconnect
gptkbp:usedIn gptkb:Lawrence_Livermore_National_Laboratory
gptkb:Oak_Ridge_National_Laboratory
gptkb:Summit_supercomputer
gptkb:NVIDIA_Omniverse
gptkb:Sierra_supercomputer
gptkb:NVIDIA_DGX_systems
gptkb:NVIDIA_A100_GPU
gptkb:NVIDIA_Ampere_architecture
gptkb:NVIDIA_Clara_platform
gptkb:NVIDIA_DGX-2
gptkb:NVIDIA_DGX_A100
gptkb:NVIDIA_DGX_H100
gptkb:NVIDIA_DGX_Station
gptkb:NVIDIA_Grace_CPU
gptkb:NVIDIA_Grace_Hopper_Superchip
gptkb:NVIDIA_H100_GPU
gptkb:NVIDIA_HGX_platform
gptkb:NVIDIA_Hopper_architecture
gptkb:NVIDIA_NVSwitch
gptkb:NVIDIA_P100_GPU
gptkb:NVIDIA_Quadro_GPUs
gptkb:NVIDIA_RTX_3090
gptkb:NVIDIA_RTX_6000
gptkb:NVIDIA_Selene_supercomputer
gptkb:NVIDIA_Tesla_GPUs
gptkb:NVIDIA_Turing_architecture
gptkb:NVIDIA_V100_GPU
gptkb:NVIDIA_Volta_architecture
data centers
high-performance computing
supercomputers
AI workloads
gptkbp:bfsParent gptkb:NVIDIA_Tesla_V100
gptkb:graphics_card
gptkbp:bfsLayer 5