VacantInQue

Product Support

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

Function

Checks whether a queue is full.

Prototype

      
           __aicore__ inline bool VacantInQue()

Parameters

None

Restrictions

This API does not support inplace tensor operations, that is, the scenario where the depth of TQue is set to 0.

Returns

true: The queue is not full and the EnQue operation can be performed.
false: The queue is full and no more tensors can be added.

Example

      
       
         
         
           // Check whether the current queue is full based on VacantInQue and set the current queue depth to 4.
AscendC::TPipe pipe;
AscendC::TQueBind<AscendC::TPosition::VECOUT, AscendC::TPosition::GM, 4> que;
int num = 10;
int len = 1024;
pipe.InitBuffer(que, num, len);
bool ret = que.VacantInQue(); // The return is true.
AscendC::LocalTensor<half> tensor1 = que.AllocTensor<half>();
AscendC::LocalTensor<half> tensor2 = que.AllocTensor<half>();
AscendC::LocalTensor<half> tensor3 = que.AllocTensor<half>();
AscendC::LocalTensor<half> tensor4 = que.AllocTensor<half>();
AscendC::LocalTensor<half> tensor5 = que.AllocTensor<half>();
que.EnQue(tensor1);// Add tensor1 to the queue of VECOUT.
que.EnQue(tensor2);// Add tensor2 to the queue of VECOUT.
que.EnQue(tensor3);// Add tensor3 to the queue of VECOUT.
que.EnQue(tensor4);// Add tensor4 to the queue of VECOUT.
ret = que.VacantInQue(); // The return is false. An error is reported if the EnQue operation continues.

          

        

      
     

Parent topic: TQueBind