|
gptkbp:instance_of
|
gptkb:Graphics_Processing_Unit
|
|
gptkbp:application
|
gptkb:simulation
gptkb:AI_technology
financial modeling
machine learning inference
rendering
scientific computing
big data analytics
machine learning training
deep learning inference
deep learning training
|
|
gptkbp:architecture
|
gptkb:CUDA
|
|
gptkbp:cooling_system
|
active cooling
|
|
gptkbp:designed_for
|
high-performance computing
|
|
gptkbp:form_factor
|
gptkb:PCI_Express
|
|
gptkbp:has_ability
|
6.0
|
|
https://www.w3.org/2000/01/rdf-schema#label
|
NVIDIA Tesla series
|
|
gptkbp:interface
|
PCIe 4.0
|
|
gptkbp:latest_version
|
gptkb:Tesla_A100
|
|
gptkbp:manufacturing_process
|
7nm
|
|
gptkbp:memory_type
|
GDDR6
|
|
gptkbp:model
|
gptkb:Tesla_C870
|
|
gptkbp:performance
|
TFLOPS
|
|
gptkbp:power_consumption
|
300 W
|
|
gptkbp:produced_by
|
gptkb:NVIDIA_Corporation
|
|
gptkbp:ram
|
up to 80 GB
|
|
gptkbp:release_year
|
gptkb:2007
|
|
gptkbp:successor
|
gptkb:NVIDIA_A100
|
|
gptkbp:supports
|
gptkb:NVIDIA_DGX_systems
gptkb:NVIDIA_Deep_Stream
gptkb:NVIDIA_Jarvis
gptkb:NVIDIA_Merlin
gptkb:NVIDIA_Tensor_RT
gptkb:NVLink
gptkb:NVIDIA_HPC_SDK
gptkb:NVIDIA_NGC
gptkb:NVIDIA_RAPIDS
gptkb:machine_learning
gptkb:NVIDIA_Clara
deep learning
multi-GPU configurations
virtualization
AI workloads
Tensor cores
ECC memory
high bandwidth memory
mixed precision training
FP16 operations
INT8 operations
FP32 operations
INT4 operations
|
|
gptkbp:target_market
|
data centers
|
|
gptkbp:uses
|
parallel processing
CUDA cores
|
|
gptkbp:bfsParent
|
gptkb:NVIDIA's_CUDA_platform
gptkb:NVIDIA's_GPU_architecture
gptkb:NVIDIA_graphics_card
|
|
gptkbp:bfsLayer
|
6
|