|
gptkbp:instance_of
|
gptkb:Graphics_Processing_Unit
|
|
gptkbp:architecture
|
gptkb:Turing
gptkb:Ampere
|
|
gptkbp:competitors
|
gptkb:Intel_Xe
AMD Radeon Instinct
|
|
gptkbp:cooling_system
|
Active cooling
Passive cooling
|
|
gptkbp:designed_for
|
High-performance computing
|
|
gptkbp:form_factor
|
gptkb:NVLink
gptkb:PCI_Express
|
|
gptkbp:has_ability
|
over 10 TFLOPS
|
|
https://www.w3.org/2000/01/rdf-schema#label
|
Tesla GPUs
|
|
gptkbp:manufacturer
|
gptkb:NVIDIA
|
|
gptkbp:market_share
|
Growing in cloud services
Leading in AI training
Significant in HPC
|
|
gptkbp:memory_type
|
GDDR6
|
|
gptkbp:notable_feature
|
gptkb:Tensor_Cores
Scalability
Low latency
Multi-GPU support
Virtualization support
High throughput
High bandwidth memory
ECC memory
NVLink support
|
|
gptkbp:notable_users
|
gptkb:Microsoft_Azure
gptkb:Amazon_Web_Services
gptkb:IBM
gptkb:Google
gptkb:Tesla,_Inc.
gptkb:Open_AI
gptkb:Facebook
NVIDIA itself
|
|
gptkbp:part_of
|
NVIDIA Cloud portfolio
NVIDIA Data Center portfolio
NVIDIA Deep Learning portfolio
NVIDIA AI portfolio
NVIDIA HPC portfolio
|
|
gptkbp:power_consumption
|
up to 300 watts
|
|
gptkbp:ram
|
up to 48 GB
|
|
gptkbp:release_year
|
gptkb:2010
|
|
gptkbp:successor
|
A100
V100
|
|
gptkbp:support
|
gptkb:Vulkan
gptkb:Direct_X
gptkb:CUDA
gptkb:Open_CL
|
|
gptkbp:target_market
|
gptkb:Scientific_research
gptkb:cloud_computing
Data centers
Rendering
Financial modeling
|
|
gptkbp:used_in
|
gptkb:Artificial_Intelligence
Deep learning
Machine learning
|
|
gptkbp:bfsParent
|
gptkb:NVIDIA
|
|
gptkbp:bfsLayer
|
4
|