- Description: Adds the specified scalar value to each tensor in the tensor list. Compared with , this API modifies the structure type of the input parameter scalar from aclTensor to aclScalar. Select the appropriate API based on actual requirements.
- Formula:
Each operator has calls. First, aclnnForeachAddScalarV2GetWorkspaceSize is called to obtain the input parameters and compute the required workspace size based on the process. Then, aclnnForeachAddScalarV2 is called to perform computation.
[object Object]
[object Object]
Parameters
[object Object][object Object]Atlas A2 training products/Atlas A2 inference products[object Object] and [object Object]Atlas A3 training products/Atlas A3 inference products[object Object]:
The data type of
[object Object]depends on that of[object Object]:- When
[object Object]is of the FLOAT32 or BFLOAT16 type, the data type must be FLOAT32 or DOUBLE. - When
[object Object]is of the FLOAT16 type, the data type must be FLOAT16 or DOUBLE. - When
[object Object]is of the INT32 type, the data type must be INT32 or INT64.
- When
Ascend 950PR/Ascend 950DT:
- The maximum number of tensors supported by the input parameter
[object Object]is 50. - The data type of
[object Object]depends on that of[object Object]:- When the data type of
[object Object]is BFLOAT16 or FLOAT32, the data type can be FLOAT32 or DOUBLE. - When the data type of
[object Object]is FLOAT16, the data type can be FLOAT16, FLOAT32, or DOUBLE. - When
[object Object]is of the INT32 type, the data type must be INT32 or INT64.
- When the data type of
- The maximum number of tensors supported by the output parameter
[object Object]is 50.
- The maximum number of tensors supported by the input parameter
Return Value
[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:
- aclnnForeachAddScalarV2 defaults to a deterministic implementation.
The following example is for reference only. For details, see .
[object Object]