Description: Pads the last dimension of the input tensor using replication of the input boundary.
Example:
[object Object]
Each operator has calls. First, [object Object] is called to obtain the workspace size required for computation and the executor that contains the operator computation process. Then, [object Object] is called to perform computation.
[object Object][object Object]
Parameters:
[object Object](aclTensor*, compute input): original input data to be padded, aclTensor on the device. The shape supports 2 or 3 dimensions, and the data type can be BFLOAT16, FLOAT16, FLOAT32, DOUBLE, INT8, INT16, INT32, INT64, UINT8, COMPLEX64, or COMPLEX128. are supported. The can be ND.[object Object](aclIntArray*, compute input): dimension to be padded in the input, aclIntArray on the host. The length is 2. The two values indicate the values to be padded on the left and right sides, respectively.[object Object](aclTensor*, compute output): output result after padding, aclTensor on the device. The shape supports 2 or 3 dimensions, and the data type can be BFLOAT16, FLOAT16, FLOAT32, DOUBLE, INT8, INT16, INT32, INT64, UINT8, COMPLEX64, or COMPLEX128. are supported. The can be ND. In the output shape, except the last dimension to be padded, the value of the last dimension of[object Object]must be the same as that of[object Object]. The value of the last dimension of[object Object]is equal to the value of the last dimension of[object Object]plus the first two values of padding.[object Object](uint64_t*, output): size of the workspace to be allocated on the device.[object Object](aclOpExecutor**, output): operator executor, containing the operator computation process.
Returns:
Parameters:
[object Object](void*, input): address of the workspace to be allocated on the device.[object Object](uint64_t, input): size of the workspace to be allocated on the device, which is obtained by calling[object Object].[object Object](aclOpExecutor*, input): operator executor, containing the operator computation process.[object Object](aclrtStream, input): stream for executing the task.
Returns:
- Deterministic compute:
[object Object]defaults to a deterministic implementation.
The following example is for reference only. For details, see .