Statements (19)
| Predicate | Object |
|---|---|
| gptkbp:instanceOf |
gptkb:personal_computer
|
| gptkbp:announced |
2022
|
| gptkbp:compatibleWith |
gptkb:PCIe_Gen5
|
| gptkbp:dataRate |
100 Gbps per lane
|
| gptkbp:developedBy |
gptkb:NVIDIA
|
| gptkbp:enables |
high-performance computing
AI workloads scalable GPU clusters |
| https://www.w3.org/2000/01/rdf-schema#label |
NVLink 5.0
|
| gptkbp:maximumBandwidthPerDirection |
50 GB/s
|
| gptkbp:numberOfLanesPerLink |
4
|
| gptkbp:successor |
gptkb:NVLink_4.0
|
| gptkbp:supports |
multi-GPU communication
|
| gptkbp:usedFor |
high-speed GPU interconnect
|
| gptkbp:usedIn |
gptkb:NVIDIA_DGX_H100
gptkb:NVIDIA_Grace_Hopper_Superchip gptkb:NVIDIA_H100 |
| gptkbp:bfsParent |
gptkb:Nvidia_Blackwell
|
| gptkbp:bfsLayer |
6
|