Specifying Requirements

Setting up synchronization resources begins by determining the requirements of each endpoint. The producer and consumers must query the NVIDIA drivers they will use with the appropriate APIs to obtain separate NvSciSyncAttrList handles representing the requirements for signaling (writing to) and waiting for (reading from) synchronization objects.

If an endpoint directly writes to or reads from the stream packets with the CPU instead of using an NVIDIA API, it does not generate fences and does not need synchronization signaling requirements. It needs to perform CPU waits for fences from the other endpoint and must create a waiting requirement attribute list with the NeedCpuAccess flag set.

In some cases, an application endpoint may require that packets it receives are available immediately, without waiting for a fence. This case does not require synchronization waiting requirement attributes. Instead, the other endpoint is notified of CPU wait before sending the packets.

Once an endpoint determins its signal and wait requirements for synchronization objects, it stores the signal requirements locally and passes the wait requirements, one NvSciSyncAttrList per packet element, to the other endpoint through the stream. It passes an NvSciSyncAttrList with the wait requirement attribute, if fences are supported, into the endpoint block by calling NvSciStreamBlockElementWaiterAttrSet(). If the waiter for the element referenced by elemIndex does not support fences, NULL pointer is passed. The function call is the same for both producer and consumer endpoints. Ownership of the sync attribute handle remains with the caller. The stream creates a duplicate before the function returns.

NvSciError
NvSciStreamBlockElementWaiterAttrSet(
    NvSciStreamBlock  const block,
    Uint32_t          const elemIndex,
    NvSciSyncAttrList const waitSyncAttrList
)