Statements (19)
| Predicate | Object |
|---|---|
| gptkbp:instanceOf |
CUDA API function
|
| gptkbp:definedIn |
cuda_runtime_api.h
|
| gptkbp:documentation |
https://docs.nvidia.com/cuda/cuda-runtime-api/group__CUDART__MEMORY.html#group__CUDART__MEMORY_1g6e2e2c58e4458b4a5bc9aef12640add6
|
| https://www.w3.org/2000/01/rdf-schema#label |
cudaMemcpyPeer
|
| gptkbp:introducedIn |
CUDA 4.0
|
| gptkbp:parameter |
const void* src
size_t count void* dst int dstDevice int srcDevice |
| gptkbp:partOf |
gptkb:CUDA_Runtime_API
|
| gptkbp:relatedTo |
gptkb:cudaMemcpy
cudaMemcpyPeerAsync |
| gptkbp:requires |
Unified Virtual Addressing (UVA)
|
| gptkbp:result |
gptkb:cudaError_t
|
| gptkbp:threadSafe |
true
|
| gptkbp:usedFor |
device-to-device memory copy between different GPUs
|
| gptkbp:bfsParent |
gptkb:CUDA_Runtime
|
| gptkbp:bfsLayer |
7
|