Statements (28)
| Predicate | Object |
|---|---|
| gptkbp:instanceOf |
gptkb:graphics_card
|
| gptkbp:announced |
March 2022
|
| gptkbp:architecture |
Data center GPU
|
| gptkbp:developedBy |
gptkb:NVIDIA
|
| https://www.w3.org/2000/01/rdf-schema#label |
Hopper (GPU)
|
| gptkbp:marketedAs |
Supercomputing
Cloud computing Enterprise |
| gptkbp:memoryType |
gptkb:HBM3
|
| gptkbp:namedAfter |
gptkb:Grace_Hopper
|
| gptkbp:notableFeature |
gptkb:Confidential_Computing
gptkb:Multi-Instance_GPU_(MIG) gptkb:Transformer_Engine DPX instructions |
| gptkbp:predecessor |
Ampere (GPU)
|
| gptkbp:processNode |
gptkb:TSMC_4N
|
| gptkbp:product |
gptkb:NVIDIA_GH200_Grace_Hopper_Superchip
gptkb:NVIDIA_H100 gptkb:NVIDIA_H100_Tensor_Core_GPU |
| gptkbp:releaseYear |
2022
|
| gptkbp:successor |
Blackwell (GPU)
|
| gptkbp:supports |
gptkb:NVLink_4.0
gptkb:PCIe_5.0 FP8 precision |
| gptkbp:usedIn |
AI workloads
High-performance computing |
| gptkbp:bfsParent |
gptkb:NVIDIA_Grace_Hopper_Superchip
|
| gptkbp:bfsLayer |
6
|