[object Object]

[object Object][object Object]undefined[object Object]

• Description: Returns a new tensor with Boolean elements and determines whether the given values of [object Object] and [object Object] are close to each other, and returns [object Object] if the values are close to each other and returns [object Object] otherwise.
• Formula: Returns a new tensor [object Object] of type [object Object], indicating whether each element of the input [object Object] is close to the corresponding element of the input [object Object]. Closeness is defined as:$$\left | self_{i}-other_{i}\right | \le atol + rtol\times \left | other_{i} \right |$$ When both [object Object] and [object Object] are finite values, the foregoing formula is true. When both [object Object] and [object Object] are non-finite, the result is [object Object] only if they are equal. When [object Object] is [object Object], [object Object] is considered to be closed. When [object Object] is [object Object], [object Object] is considered not to be closed.

[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]

[object Object]

• Parameters:

  • [object Object] (aclTensor*, compute input): aclTensor on the device of [object Object] in the formula. are supported. The dtype must be the same as that of [object Object]. The [object Object] and [object Object] must meet the broadcast relationship. The can be ND, and the data is less than or equal to 8D.
    • [object Object]Atlas inference products[object Object] and [object Object]Atlas training products[object Object]: The data type can be FLOAT, FLOAT16, INT32, INT64, INT16, INT8, UINT8, BOOL, or DOUBLE.
    • [object Object]Atlas A3 training products/Atlas A3 inference products[object Object] and [object Object]Atlas A2 training products/Atlas A2 inference products[object Object]: The data type can be FLOAT, FLOAT16, INT32, INT64, INT16, INT8, UINT8, BOOL, DOUBLE, or BFLOAT16.
  • [object Object] (aclTensor*, compute input): aclTensor on the device. The data type can be FLOAT, FLOAT16, INT32, or BFLOAT16. [non-contiguous tensors] (../common/non_contiguous_tensor.md) are supported, the dtype must be the same as that of [object Object]. The [object Object] and [object Object] must meet the broadcast relationship. The can be ND, and the data is less than or equal to 8D.
  • [object Object] (double, compute input): [object Object] in the formula, indicating the relative tolerance. The data type can be DOUBLE.
  • [object Object] (double, compute input): [object Object] in the formula, indicating the absolute difference. The data type can be DOUBLE.
  • [object Object] (bool, compute input): [object Object] in the formula, indicating the comparison of two NaN values. If the value is [object Object], two [object Object] values are considered equal. If the value is [object Object], two [object Object] values are considered unequal. The data type can be BOOL.
  • [object Object] (aclTensor*, computation output): [object Object] in the formula, the calculation result, which indicates whether the elements in the two inputs are close. [object Object] on the device. The data type is BOOL. are supported. Its [object Object] should be the same as that of [object Object]. The can be ND. The shape is the same as that of [object Object], and the data is not greater than 8D.
  • [object Object] (uint64_t*, compute output): size of the workspace to be allocated on the device.
  • [object Object] (aclOpExecutor**, compute output): operator executor, containing the operator computation process.

• Returns:

  [object Object]: status code. For details, see .

[object Object]

• 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 the first-phase API [object Object].
  • [object Object] (aclOpExecutor*, input): operator executor, containing the operator computation process.
  • [object Object] (aclrtStream, input): stream for executing the task.

• Returns

  [object Object]: status code. For details, see .

[object Object]

• Deterministic computation:
  • [object Object] defaults to a deterministic implementation.

[object Object]

The following example is for reference only. For details, see .