Statements (18)
Predicate | Object |
---|---|
gptkbp:instanceOf |
gptkb:technology
|
gptkbp:category |
GPU communication technology
|
gptkbp:compatibleWith |
gptkb:NVIDIA_GPUs
|
gptkbp:developedBy |
gptkb:NVIDIA
|
gptkbp:enables |
low-latency data transfer
direct memory access between GPUs |
gptkbp:firstReleased |
2010s
|
https://www.w3.org/2000/01/rdf-schema#label |
NVIDIA GPU Direct
|
gptkbp:improves |
data throughput
|
gptkbp:reduces |
CPU overhead
|
gptkbp:supports |
gptkb:CUDA
gptkb:InfiniBand gptkb:RDMA |
gptkbp:usedIn |
deep learning
high-performance computing scientific computing |
gptkbp:bfsParent |
gptkb:NVIDIA_A100_GPU
|
gptkbp:bfsLayer |
7
|