|
gptkbp:instanceOf
|
gptkb:graphics_card
|
|
gptkbp:announced
|
gptkb:GTC_2020
|
|
gptkbp:architecture
|
parallel computing
|
|
gptkbp:codename
|
gptkb:Ampere
|
|
gptkbp:developer
|
gptkb:Nvidia
|
|
gptkbp:fabricationProcess
|
7 nm
8 nm
|
|
gptkbp:firstReleased
|
2020
|
|
gptkbp:hasConcept
|
gptkb:GA102
gptkb:GA104
gptkb:GA106
gptkb:GA107
gptkb:GA108
gptkb:GA100
|
|
https://www.w3.org/2000/01/rdf-schema#label
|
Nvidia Ampere
|
|
gptkbp:market
|
gptkb:cloud_service
professional visualization
consumer graphics
|
|
gptkbp:memoryBusWidth
|
up to 384-bit
|
|
gptkbp:memoryType
|
gptkb:GDDR6X
gptkb:GDDR6
|
|
gptkbp:notableProduct
|
gptkb:Nvidia_A100
gptkb:GeForce_RTX_3060
gptkb:GeForce_RTX_3070
gptkb:GeForce_RTX_3090
gptkb:GeForce_RTX_3080
gptkb:RTX_A6000
|
|
gptkbp:predecessor
|
gptkb:Nvidia_Turing
|
|
gptkbp:processNode
|
gptkb:TSMC_7nm
gptkb:Samsung_8N
|
|
gptkbp:successor
|
gptkb:Nvidia_Ada_Lovelace
|
|
gptkbp:supports
|
gptkb:Tensor_cores
gptkb:PCI_Express_4.0
gptkb:CUDA
gptkb:OpenGL
gptkb:DLSS
gptkb:DirectX_12_Ultimate
gptkb:Vulkan
GDDR6 memory
GDDR6X memory
Ray tracing
|
|
gptkbp:transistorCount
|
28.3 billion (GA102)
54.2 billion (GA100)
|
|
gptkbp:usedIn
|
gptkb:Nvidia_A100
gptkb:Nvidia_GeForce_RTX_30_series
gptkb:Nvidia_RTX_A6000
|
|
gptkbp:VRAM
|
24 GB (RTX 3090)
up to 80 GB (A100)
|
|
gptkbp:bfsParent
|
gptkb:Nvidia_Hopper
|
|
gptkbp:bfsLayer
|
6
|