|
gptkbp:instanceOf
|
gptkb:graphics_card
|
|
gptkbp:announced
|
March 2022
|
|
gptkbp:architecture
|
Data center GPU
|
|
gptkbp:competitor
|
gptkb:Intel_Ponte_Vecchio
AMD Instinct MI200 series
|
|
gptkbp:first_product
|
gptkb:NVIDIA_H100
|
|
https://www.w3.org/2000/01/rdf-schema#label
|
NVIDIA Hopper GPUs
|
|
gptkbp:manufacturer
|
gptkb:NVIDIA
|
|
gptkbp:memoryType
|
gptkb:HBM2e
gptkb:HBM3
|
|
gptkbp:namedAfter
|
gptkb:Grace_Hopper
|
|
gptkbp:notableFeature
|
gptkb:Confidential_Computing
gptkb:Multi-Instance_GPU_(MIG)
gptkb:Transformer_Engine
DPX instructions
|
|
gptkbp:notableProduct
|
gptkb:NVIDIA_GH200_Grace_Hopper_Superchip
gptkb:NVIDIA_H100_PCIe
gptkb:NVIDIA_H100_SXM
NVIDIA H100 NVL
|
|
gptkbp:predecessor
|
gptkb:NVIDIA_Ampere_GPUs
|
|
gptkbp:processNode
|
gptkb:TSMC_4N
|
|
gptkbp:releaseYear
|
2022
|
|
gptkbp:successor
|
NVIDIA Blackwell GPUs
|
|
gptkbp:supports
|
gptkb:CUDA
gptkb:NVIDIA_AI_Enterprise
gptkb:NVLink
gptkb:HBM3_memory
gptkb:NVIDIA_cuDNN
gptkb:NVIDIA_NVSwitch
gptkb:PCIe_Gen5
gptkb:NVIDIA_NCCL
gptkb:NVLink_Switch_System
gptkb:Tensor_Cores
Virtualization
FP16 precision
FP8 precision
INT8 precision
Secure Multi-Tenancy
BF16 precision
FP32 precision
FP64 precision
NVIDIA CUDA-X AI
PCIe form factor
SXM5 form factor
Sparsity acceleration
|
|
gptkbp:targetMarket
|
gptkb:artificial_intelligence
High-performance computing
|
|
gptkbp:usedIn
|
gptkb:NVIDIA_HGX_H100
gptkb:NVIDIA_DGX_H100
gptkb:NVIDIA_L40
|
|
gptkbp:bfsParent
|
gptkb:TensorFloat-32
|
|
gptkbp:bfsLayer
|
7
|