gptkbp:instanceOf
|
computing platform
|
gptkbp:announced
|
2017
|
gptkbp:compatibleWith
|
gptkb:NVIDIA_A100
gptkb:NVIDIA_H100
gptkb:NVIDIA_V100
|
gptkbp:designedFor
|
high-performance computing
AI workloads
|
gptkbp:developedBy
|
gptkb:NVIDIA
|
gptkbp:features
|
modular design
high-speed interconnects
scalable architecture
liquid cooling (in some models)
high-bandwidth memory
multi-GPU support
air cooling
|
https://www.w3.org/2000/01/rdf-schema#label
|
NVIDIA HGX platform
|
gptkbp:marketedAs
|
gptkb:machine_learning
deep learning
scientific computing
enterprise AI
|
gptkbp:supports
|
gptkb:Ethernet
gptkb:InfiniBand
gptkb:NVLink
gptkb:PCIe
gptkb:NVIDIA_GPUs
gptkb:NVIDIA_NVSwitch
|
gptkbp:usedBy
|
gptkb:Atos
gptkb:Baidu
gptkb:Fujitsu
gptkb:Hewlett_Packard_Enterprise
gptkb:IBM
gptkb:OpenAI
gptkb:Tesla
gptkb:Supermicro
gptkb:Penguin_Computing
gptkb:Google_Cloud
gptkb:Oracle_Cloud
gptkb:Cray
gptkb:Alibaba
gptkb:Lenovo
gptkb:Amazon_Web_Services
gptkb:Dell_Technologies
gptkb:Meta
gptkb:Microsoft_Azure
gptkb:Tencent
gptkb:Inspur
gptkb:ASUS
gptkb:QCT
Gigabyte
HPC clusters
|
gptkbp:usedFor
|
gptkb:simulation
autonomous vehicles
robotics
scientific research
inference
data analytics
training large language models
|
gptkbp:usedIn
|
cloud computing
data centers
supercomputers
|
gptkbp:bfsParent
|
gptkb:NVLink
|
gptkbp:bfsLayer
|
6
|