|
gptkbp:instanceOf
|
gptkb:personal_computer
|
|
gptkbp:announced
|
2014
|
|
gptkbp:compatibleWith
|
gptkb:NVIDIA_RTX_40_series
|
|
gptkbp:competitor
|
gptkb:AMD_Infinity_Fabric
|
|
gptkbp:connects
|
CPUs and GPUs (in some systems)
|
|
gptkbp:developedBy
|
gptkb:NVIDIA
|
|
gptkbp:enables
|
faster data transfer between GPUs
|
|
https://www.w3.org/2000/01/rdf-schema#label
|
NVLink (SLI)
|
|
gptkbp:introducedIn
|
gptkb:NVIDIA_Pascal_architecture
|
|
gptkbp:memoryBusWidth
|
up to 25 GB/s per lane (NVLink 2.0)
up to 50 GB/s per link (NVLink 3.0)
|
|
gptkbp:purpose
|
high-speed GPU interconnect
|
|
gptkbp:relatedTo
|
gptkb:NVSwitch
gptkb:PCI_Express
gptkb:SLI
|
|
gptkbp:replacedBy
|
PCI Express for GPU-to-GPU communication
|
|
gptkbp:successor
|
gptkb:SLI
|
|
gptkbp:supports
|
multi-GPU configurations
|
|
gptkbp:supportsProtocol
|
point-to-point interconnect
|
|
gptkbp:usedFor
|
deep learning
high-performance computing
AI workloads
scientific simulations
|
|
gptkbp:usedIn
|
gptkb:NVIDIA_A100
gptkb:NVIDIA_GPUs
gptkb:NVIDIA_DGX_systems
gptkb:NVIDIA_NVSwitch
gptkb:NVIDIA_RTX_3090
gptkb:NVIDIA_V100
NVIDIA data center products
|
|
gptkbp:bfsParent
|
gptkb:Nvidia_RTX_3090
|
|
gptkbp:bfsLayer
|
7
|