|
gptkbp:instanceOf
|
AI supercomputer
|
|
gptkbp:coreCount
|
2
|
|
gptkbp:dimensions
|
868 x 444 x 1310 mm
|
|
gptkbp:formFactor
|
rack-mounted
|
|
gptkbp:GPU
|
gptkb:NVIDIA_Tesla_V100
|
|
gptkbp:GPUArchitecture
|
gptkb:Volta
|
|
https://www.w3.org/2000/01/rdf-schema#label
|
NVIDIA DGX-2
|
|
gptkbp:manufacturer
|
gptkb:NVIDIA
|
|
gptkbp:maxFP16Performance
|
2 PFLOPS
|
|
gptkbp:maxFP32Performance
|
512 TFLOPS
|
|
gptkbp:maxFP64Performance
|
64 TFLOPS
|
|
gptkbp:network
|
8x 100 Gb/s InfiniBand
|
|
gptkbp:numberOfGPUs
|
16
|
|
gptkbp:NVSwitch
|
12
|
|
gptkbp:operatingSystem
|
gptkb:Ubuntu_Linux
|
|
gptkbp:powerSource
|
10 kW
|
|
gptkbp:predecessor
|
gptkb:NVIDIA_DGX-1
|
|
gptkbp:priceRange
|
$399,000
|
|
gptkbp:processor
|
gptkb:Intel_Xeon_Platinum_8168
|
|
gptkbp:purpose
|
AI research
deep learning
|
|
gptkbp:RAM
|
1.5 TB
|
|
gptkbp:releaseDate
|
2018
|
|
gptkbp:storage
|
30 TB NVMe SSD
|
|
gptkbp:successor
|
gptkb:NVIDIA_DGX_A100
|
|
gptkbp:supports
|
gptkb:NVIDIA_TensorRT
gptkb:NVIDIA_cuDNN
gptkb:NVIDIA_CUDA
gptkb:NCCL
|
|
gptkbp:targetMarket
|
gptkb:business
universities
research institutions
|
|
gptkbp:totalGPUmemory
|
512 GB
|
|
gptkbp:weight
|
350 kg
|
|
gptkbp:bfsParent
|
gptkb:NVLink
gptkb:NVIDIA_DGX_systems
gptkb:DGX
|
|
gptkbp:bfsLayer
|
6
|