Statements (97)
| Predicate | Object |
|---|---|
| gptkbp:instance_of |
gptkb:networking
|
| gptkbp:competes_with |
gptkb:PCI_Express
|
| gptkbp:connects |
multiple GPUs
|
| gptkbp:developed_by |
gptkb:NVIDIA
|
| gptkbp:enables |
faster data transfer
scalable multi-GPU systems |
| gptkbp:first_introduced |
gptkb:2016
|
| https://www.w3.org/2000/01/rdf-schema#label |
NVLink
|
| gptkbp:is_a |
high-speed interconnect
|
| gptkbp:is_available_in |
gptkb:NVIDIA_RTX_A6000
gptkb:NVIDIA_Quadro_GPUs gptkb:NVIDIA_RTX_series gptkb:NVIDIA_Tesla_GPUs gptkb:NVIDIA_Ge_Force_GPUs gptkb:NVIDIA_A100_Tensor_Core_GPUs gptkb:NVIDIA_H100_Tensor_Core_GPUs |
| gptkbp:is_based_on |
coherent memory access
|
| gptkbp:is_compatible_with |
gptkb:NVIDIA's_CUDA_platform
gptkb:NVIDIA's_DGX_Station gptkb:NVIDIA's_Ge_Force_RTX_30_series gptkb:NVIDIA_GPUs NVIDIA's DGX systems |
| gptkbp:is_designed_for |
low latency
data-intensive applications high throughput AI workloads scalable performance |
| gptkbp:is_designed_to |
enhance performance
reduce bottlenecks |
| gptkbp:is_implemented_in |
gptkb:NVIDIA_Tesla_GPUs
gptkb:NVIDIA_Ampere_architecture gptkb:NVIDIA_Volta_architecture NVIDIA Hopper architecture |
| gptkbp:is_integrated_with |
gptkb:NVIDIA's_Omniverse_platform
gptkb:NVIDIA's_Tensor_RT NVIDIA's NVSwitch |
| gptkbp:is_optimized_for |
parallel processing
|
| gptkbp:is_part_of |
gptkb:NVIDIA's_Hopper_architecture
gptkb:NVIDIA's_Ampere_architecture gptkb:NVIDIA's_GPU_architecture gptkb:NVIDIA's_Volta_architecture NVIDIA's edge computing solutions NVIDIA's AI infrastructure NVIDIA's cloud services NVIDIA's data center solutions NVIDIA's enterprise solutions NVIDIA's software ecosystem NVIDIA's next-generation architectures NVIDIA's research initiatives NVIDIA's gaming solutions NVIDIA's automotive solutions NVIDIA's hardware ecosystem NVIDIA's professional visualization solutions NVIDIA's autonomous machines NVIDIA's development tools NVIDIA's healthcare solutions NVIDIA's robotics solutions NVIDIA's smart cities initiatives NVIDIA's NVSwitch technology |
| gptkbp:is_supported_by |
gptkb:NVIDIA's_AI_Enterprise_software_suite
gptkb:NVIDIA's_DGX_A100_system gptkb:NVIDIA_DGX_systems NVIDIA's software stack CUDA programming model NVIDIA's driver software NVIDIA's libraries NVIDIA's SDKs |
| gptkbp:is_used_for |
gptkb:virtual_reality
deep learning high-performance computing big data analytics real-time rendering graphics rendering virtual reality applications AI workloads scientific simulations deep learning training |
| gptkbp:is_used_in |
gptkb:vehicles
gptkb:cloud_computing gptkb:machine_learning data centers machine learning applications big data analytics cloud computing environments supercomputers scientific simulations |
| gptkbp:is_utilized_in |
financial modeling
supercomputers |
| gptkbp:offers |
lower latency
|
| gptkbp:provides |
high bandwidth
|
| gptkbp:ram |
up to 300 GB/s
|
| gptkbp:supports |
multi-GPU configurations
GPU-to-GPU communication |
| gptkbp:used_in |
gptkb:NVIDIA_GPUs
high-performance computing |
| gptkbp:bfsParent |
gptkb:NVIDIA
|
| gptkbp:bfsLayer |
4
|