Statements (23)
| Predicate | Object |
|---|---|
| gptkbp:instanceOf |
gptkb:technology
|
| gptkbp:documentedIn |
NVIDIA CUDA Toolkit Documentation
|
| gptkbp:enables |
efficient memory allocation
memory transfer between host and device |
| https://www.w3.org/2000/01/rdf-schema#label |
CUDA Memory Management
|
| gptkbp:importantFor |
performance optimization
data transfer speed |
| gptkbp:includes |
gptkb:cudaMemcpy
cudaFree cudaMalloc cudaMemset |
| gptkbp:relatedTo |
gptkb:NVIDIA_CUDA
|
| gptkbp:supports |
unified memory
zero-copy memory memory mapping pinned memory |
| gptkbp:usedBy |
CUDA developers
|
| gptkbp:usedFor |
GPU programming
|
| gptkbp:usedIn |
deep learning
high-performance computing scientific computing |
| gptkbp:bfsParent |
gptkb:CUDA_C++
|
| gptkbp:bfsLayer |
7
|