GetTensorCountInQue

Function Usage

Queries the number of enqueued tensors in a queue.

Prototype

1
__aicore__ inline int32_t GetTensorCountInQue()

Parameters

None

Availability

Atlas Training Series Product

Precautions

None

Returns

Number of enqueued tensors in the queue

Example

1
2
3
4
5
6
7
8
9
// Use GetTensorCountInQue to query the number of enqueued tensors in the queue. Currently, the AllocTensor API is used to allocate memory and add the memory to the queue. The value of num is 1.
AscendC::TPipe pipe;
AscendC::TQueBind<AscendC::TPosition::VECOUT, AscendC::TPosition::GM, 4> que;
int num = 4;
int len = 1024;
pipe.InitBuffer(que, num, len);
AscendC::LocalTensor<half> tensor1 = que.AllocTensor<half>();
que.EnQue(tensor1);// Add the tensor to the queue of VECOUT.
int32_t numb = que.GetTensorCountInQue();