Statements (23)
| Predicate | Object |
|---|---|
| gptkbp:instanceOf |
gptkb:personal_computer
|
| gptkbp:architecture |
NVLink-based
|
| gptkbp:connects |
multiple GPUs
|
| gptkbp:enables |
high-bandwidth GPU interconnect
multi-GPU scaling |
| https://www.w3.org/2000/01/rdf-schema#label |
Nvidia NVSwitch
|
| gptkbp:introducedIn |
2018
|
| gptkbp:manufacturer |
gptkb:Nvidia
|
| gptkbp:maxBandwidth |
up to 900 GB/s (per switch, depending on version)
|
| gptkbp:productType |
high-speed switch
|
| gptkbp:supports |
gptkb:NVLink
gptkb:NVLink_2.0 gptkb:NVLink_3.0 |
| gptkbp:usedFor |
gptkb:Nvidia_DGX_systems
gptkb:Nvidia_HGX_systems deep learning high-performance computing AI workloads |
| gptkbp:usedIn |
data centers
AI supercomputers |
| gptkbp:website |
https://www.nvidia.com/en-us/data-center/nvswitch/
|
| gptkbp:bfsParent |
gptkb:Nvidia
|
| gptkbp:bfsLayer |
5
|