![]() |
VisionWorks Toolkit ReferenceDecember 18, 2015 | 1.2 Release |
Adds various extensions to the vx_node
object.
This section describes different extensions and features to the standard Object: Node.
Enumerations | |
enum | nvx_node_attribute_e { NVX_NODE_ATTRIBUTE_CUDA_STREAM = VX_ATTRIBUTE_BASE(VX_ID_NVIDIA, VX_TYPE_NODE) + 0x0 } |
The extended node attributes list. More... | |
enum nvx_node_attribute_e |
The extended node attributes list.
Enumerator | |
---|---|
NVX_NODE_ATTRIBUTE_CUDA_STREAM |
Gets the CUDA stream object associated with the current node. This attribute is read-only and is only meaningful when queried from a kernel processing callback. To ensure a correct execution, user custom kernels for the GPU target must use this attribute to enqueue their own CUDA kernels to the CUDA stream, provided by the framework, or to synchronize with it, if they use own streams.
|