Hopper

E790551

Hopper is an NVIDIA GPU architecture designed for high-performance computing and AI workloads, featuring advanced capabilities such as enhanced Tensor Core acceleration.

All labels observed (1)

Label Occurrences
Hopper canonical 2

How this entity was disambiguated

Statements (47)

Predicate Object
instanceOf GPU microarchitecture
announcedBy NVIDIA Corporation
architectureGeneration NVIDIA Hopper architecture
codename Hopper
designedFor data center GPUs
developer NVIDIA
linked to: NVIDIA Corporation
feature DPX instructions
FP8 precision support
HBM3 memory support
NVLink support
PCIe Gen5 support
Transformer Engine
confidential computing capabilities
enhanced Tensor Cores
enhanced sparsity support
fourth-generation Tensor Cores
improved energy efficiency
improved mixed-precision performance
large-scale parallelism
multi-instance GPU (MIG)
marketSegment AI supercomputing
cloud computing
enterprise computing
memoryType High Bandwidth Memory
linked to: HBM2
namedAfter Grace Hopper
optimizationFor data analytics
large language models
recommendation systems
scientific simulation
predecessor Ampere
successor Blackwell
supportsComputationType BF16
FP16
FP32
FP64
FP8
INT8
TF32
supportsParallelProgrammingModel CUDA
linked to: NVIDIA CUDA

CUDA Graphs
NVIDIA NCCL
linked to: NCCL
targetApplicationDomain artificial intelligence
deep learning
high-performance computing
machine learning
usedInProduct NVIDIA H100 Tensor Core GPU
linked to: NVIDIA H100

NVIDIA H200 Tensor Core GPU

How these facts were elicited

Referenced by (2)

Full triples — surface form annotated when it differs from this entity's canonical label.

Hopper codename Hopper