NVIDIA Hopper architecture

GPTKB entity

Predicate	Object
gptkbp:instanceOf	gptkb:graphics_card
gptkbp:announced	2022
gptkbp:architecture_type	monolithic
gptkbp:developer	gptkb:NVIDIA
gptkbp:first_product	gptkb:NVIDIA_H100
gptkbp:memory_bandwidth	up to 3 TB/s
gptkbp:namedAfter	gptkb:Grace_Hopper
gptkbp:notableFeature	gptkb:Transformer_Engine gptkb:multi-instance_GPU_(MIG) DPX instructions confidential computing
gptkbp:predecessor	gptkb:NVIDIA_Ampere_architecture
gptkbp:process_node	gptkb:TSMC_4N
gptkbp:release_product	gptkb:NVIDIA_GH200_Grace_Hopper_Superchip gptkb:NVIDIA_H100_PCIe gptkb:NVIDIA_H100_SXM
gptkbp:successor	gptkb:NVIDIA_Blackwell_architecture
gptkbp:supports	gptkb:HBM3_memory gptkb:NVLink_4.0 gptkb:PCIe_5.0 gptkb:Tensor_Cores FP8 precision
gptkbp:targetMarket	data centers high-performance computing AI acceleration
gptkbp:transistor_count	80 billion (H100)
gptkbp:bfsParent	gptkb:NVLink gptkb:Multi-Instance_GPU_(MIG) gptkb:NVLink_4.0 gptkb:second-generation_Transformer_Engine gptkb:NVIDIA_RISC-V_controllers
gptkbp:bfsLayer	7
https://www.w3.org/2000/01/rdf-schema#label	NVIDIA Hopper architecture