NVIDIA Ampere architecture

GPTKB entity

Predicate	Object
gptkbp:instanceOf	gptkb:graphics_card
gptkbp:architecture	parallel computing
gptkbp:codename	gptkb:Ampere
gptkbp:developer	gptkb:NVIDIA
gptkbp:firstReleased	2020
https://www.w3.org/2000/01/rdf-schema#label	NVIDIA Ampere architecture
gptkbp:market	gptkb:cloud_service professional visualization consumer graphics AI and HPC
gptkbp:notableFeature	gptkb:Multi-Instance_GPU_(MIG) Second-generation Ray Tracing Cores Third-generation Tensor Cores FP16, TF32, INT8, INT4 support
gptkbp:predecessor	gptkb:NVIDIA_Turing_architecture
gptkbp:processNode	7 nm 8 nm
gptkbp:successor	gptkb:NVIDIA_Ada_Lovelace_architecture
gptkbp:supports	gptkb:Tensor_cores gptkb:OpenGL_4.6 gptkb:PCI_Express_4.0 gptkb:Vulkan_1.2 gptkb:NVIDIA_NVLink gptkb:CUDA_8.0 gptkb:DirectX_12_Ultimate gptkb:OpenCL_3.0 gptkb:PCIe_Gen_4 GDDR6 memory GDDR6X memory Ray tracing
gptkbp:transistorCount	28.3 billion (GA102) 54.2 billion (GA100)
gptkbp:usedIn	gptkb:NVIDIA_A100 gptkb:NVIDIA_Quadro_RTX_A6000 gptkb:NVIDIA_GeForce_RTX_30_series gptkb:NVIDIA_RTX_A6000 gptkb:NVIDIA_Tesla_A100
gptkbp:bfsParent	gptkb:NVLink
gptkbp:bfsLayer	6