|
gptkbp:instanceOf
|
gptkb:personal_computer
|
|
gptkbp:enables
|
faster data transfer between GPUs
scalable GPU clusters
high-bandwidth memory sharing
|
|
https://www.w3.org/2000/01/rdf-schema#label
|
NVIDIA NVLink
|
|
gptkbp:introducedIn
|
gptkb:NVIDIA_Pascal_architecture
2016
|
|
gptkbp:manufacturer
|
gptkb:NVIDIA
|
|
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
CPU-GPU interconnect
|
|
gptkbp:replacedBy
|
PCI Express (in some use cases)
|
|
gptkbp:successor
|
gptkb:NVIDIA_SLI
|
|
gptkbp:supports
|
gptkb:NVLink_Bridge
multi-GPU configurations
|
|
gptkbp:supportsProtocol
|
point-to-point interconnect
|
|
gptkbp:usedIn
|
gptkb:NVIDIA_A100
gptkb:NVIDIA_Tesla_V100
gptkb:NVIDIA_DGX-1
gptkb:NVIDIA_HGX_systems
gptkb:NVIDIA_Tesla_P100
gptkb:NVIDIA_DGX_systems
gptkb:NVIDIA_Ampere_architecture
gptkb:NVIDIA_DGX-2
gptkb:NVIDIA_DGX_A100
gptkb:NVIDIA_DGX_H100
gptkb:NVIDIA_H100
gptkb:NVIDIA_Hopper_architecture
gptkb:NVIDIA_NVSwitch
gptkb:NVIDIA_Quadro_GPUs
gptkb:NVIDIA_Quadro_GV100
gptkb:NVIDIA_Tesla_GPUs
gptkb:NVIDIA_Turing_architecture
gptkb:NVIDIA_Volta_architecture
gptkb:NVIDIA_Quadro_RTX_8000
gptkb:NVIDIA_RTX_A6000
gptkb:NVIDIA_Tesla_A100
gptkb:IBM_POWER10_processors
gptkb:IBM_POWER9_processors
gptkb:NVIDIA_NVSwitch_systems
gptkb:NVIDIA_Quadro_RTX_5000
gptkb:NVIDIA_Quadro_RTX_6000
gptkb:NVIDIA_RTX_6000_Ada
gptkb:NVIDIA_Tesla_H100
gptkb:NVIDIA_Titan_RTX
|
|
gptkbp:website
|
https://www.nvidia.com/en-us/data-center/nvlink/
|
|
gptkbp:bfsParent
|
gptkb:A5000
gptkb:DGX_H100
gptkb:IBM_Power_System_AC922
gptkb:NVIDIA_Ampere_architecture
gptkb:NVIDIA_DGX_H100
gptkb:NVIDIA_Grace_CPU
gptkb:NVIDIA_SLI
gptkb:GeForce_RTX_2080_Ti
|
|
gptkbp:bfsLayer
|
7
|