|
gptkbp:instanceOf
|
gptkb:graphics_card
|
|
gptkbp:architecture
|
gptkb:Volta
gptkb:Hopper
gptkb:Ampere
gptkb:Pascal
gptkb:Turing
|
|
gptkbp:designedFor
|
data centers
|
|
gptkbp:firstReleased
|
2016
|
|
https://www.w3.org/2000/01/rdf-schema#label
|
Nvidia Data Center GPU
|
|
gptkbp:manufacturer
|
gptkb:Nvidia
|
|
gptkbp:marketedAs
|
gptkb:business
AI research
supercomputing
cloud service providers
|
|
gptkbp:notableProduct
|
gptkb:Nvidia_A100
gptkb:Nvidia_H100
gptkb:Nvidia_T4
gptkb:Nvidia_V100
Nvidia H200
Nvidia L40
|
|
gptkbp:parentCompany
|
gptkb:Nvidia_Corporation
|
|
gptkbp:productType
|
gptkb:Nvidia_A100
gptkb:Nvidia_H100
gptkb:Nvidia_T4
gptkb:Nvidia_V100
Nvidia A10
Nvidia A30
Nvidia A40
Nvidia H200
Nvidia L40
Nvidia P100
|
|
gptkbp:supports
|
gptkb:CUDA
gptkb:NVLink
gptkb:PCIe
gptkb:HBM3_memory
gptkb:Multi-Instance_GPU_(MIG)
gptkb:NVSwitch
gptkb:HBM2_memory
gptkb:Tensor_Cores
FP16
INT8
FP32
FP64
|
|
gptkbp:usedFor
|
gptkb:machine_learning
cloud computing
deep learning
high performance computing
AI workloads
|
|
gptkbp:bfsParent
|
gptkb:Nvidia_Tesla
|
|
gptkbp:bfsLayer
|
6
|