FetchEventID

Applicability

Product	Supported
Atlas A3 training products/Atlas A3 inference products	√
Atlas A2 training products/Atlas A2 inference products	√
Atlas 200I/500 A2 inference products	x
Atlas inference product's AI Core	√
Atlas inference product's Vector Core	x
Atlas training products	√

Function

Obtains available TEventIDs based on HardEvent (hardware synchronization event). This API does not allocate TEventIDs, but provides available TEventIDs.

Prototype

template <HardEvent evt>
__aicore__ inline TEventID FetchEventID()
__aicore__ inline TEventID FetchEventID(HardEvent evt)

Parameters

Parameter	Input/Output	Description
evt	Input	Parameter of the HardEvent hardware synchronization type. For details about this type, see the description of synchronization types in the SetFlag/WaitFlag(ISASI).

Parameter

Input/Output

Description

evt

Input

Parameter of the HardEvent hardware synchronization type.

For details about this type, see the description of synchronization types in the SetFlag/WaitFlag(ISASI).

Restrictions

Compared with AllocEventID, FetchEventID is suitable for scenarios requiring temporary ID usage, as it does not occupy the ID after acquisition. In some complex application scenarios, you need to ensure that the usage is correct. For example, if SetFlag and WaitFlag are called consecutively in the same pipeline and the two IDs are obtained using FetchEventID, undefined behaviors such as program suspension may occur because the two IDs are the same. In this case, AllocEventID is recommended.

Returns

TEventID

Example

AscendC::TEventID eventIdVToS = GetTPipePtr()->FetchEventID(AscendC::HardEvent::V_S); //The scalar needs to wait for vector synchronization and the HardEvent ID is required.
AscendC::SetFlag<AscendC::HardEvent::V_S>(eventIdVToS);
AscendC::WaitFlag<AscendC::HardEvent::V_S>(eventIdVToS);

Parent topic: TPipe