Statements (28)
| Predicate | Object |
|---|---|
| gptkbp:instanceOf |
gptkb:graphics_card
|
| gptkbp:announced |
2022-03-22
|
| gptkbp:developedBy |
gptkb:NVIDIA
|
| gptkbp:feature |
gptkb:Confidential_Computing
gptkb:Multi-Instance_GPU_(MIG) gptkb:Transformer_Engine gptkb:NVLink_Switch_System DPX instructions Enhanced scalability |
| https://www.w3.org/2000/01/rdf-schema#label |
Hopper architecture
|
| gptkbp:marketedAs |
AI workloads
Data centers High Performance Computing |
| gptkbp:namedAfter |
gptkb:Grace_Hopper
|
| gptkbp:predecessor |
gptkb:Ampere_architecture
|
| gptkbp:processNode |
gptkb:TSMC_4N
|
| gptkbp:product |
gptkb:NVIDIA_H100
|
| gptkbp:successor |
Blackwell architecture
|
| gptkbp:supports |
gptkb:HBM3_memory
gptkb:NVLink_4.0 gptkb:PCIe_5.0 gptkb:Tensor_Cores FP8 precision |
| gptkbp:usedIn |
gptkb:NVIDIA_GH200_Grace_Hopper_Superchip
gptkb:NVIDIA_H100_PCIe gptkb:NVIDIA_H100_SXM |
| gptkbp:bfsParent |
gptkb:V3_Hopper
|
| gptkbp:bfsLayer |
7
|