- Description: Rounds off each tensor in the input tensor list with a specified precision. The rounding mode can be specified using roundMode. Compared with , this API changes the input parameter roundMode from aclTensor to aclScalar. You should select a proper API based on the actual situation.
- Formula:
Each operator has calls. First, aclnnForeachRoundOffNumberV2GetWorkspaceSize is called to obtain the input parameters and compute the required workspace size based on the process. Then, aclnnForeachRoundOffNumberV2 is called to perform computation.
[object Object]
[object Object]
Parameters
[object Object]Returns
[object Object]: status code. For details, see .The first-phase API implements input parameter verification. The following errors may be thrown.
[object Object]
- Deterministic computation:
- aclnnForeachRoundOffNumberV2 defaults to a deterministic implementation.
The following example is for reference only. For details, see .
[object Object]