Statements (19)
| 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
|
| 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
gptkb:Nvidia_A100_Tensor_Core_GPU |
| gptkbp:bfsLayer |
8
|
| https://www.w3.org/2000/01/rdf-schema#label |
NVIDIA GPU Direct
|