[object Object]

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

• Description: Obtains the inverse matrix of an array.
• Formula:$${A}^{-1}A = A{A}^{-1} = {I}_{n}$$ A is the input tensor, ${A}^{-1}$ is the inverse of A, and ${I}_{n}$ is an n-dimensional matrix.

[object Object]

Each operator has calls. First, aclnnInverseGetWorkspaceSize is called to obtain the workspace size required for computation and the executor that contains the operator computation process. Then, aclnnInverse is called to perform computation.

• [object Object]
• [object Object]

[object Object]

• Parameters:

  • self (aclTensor*, compute input): aclTensor on the device. The data type can be FLOAT, DOUBLE, COMPLEX64, COMPLEX128, or FLOAT16. The shape must be at least two-dimensional, and the last two dimensions must be of the same size. are supported. The supports ND. Data dimensions cannot exceed eight dimensions.
  • out (aclTensor *, compute output): aclTensor on the device. The data type can be FLOAT, DOUBLE, COMPLEX64, COMPLEX128, or FLOAT16. The data type must be convertible from that of self. The shape must be the same as that of self. are supported. The supports ND. Data dimensions cannot exceed eight dimensions.
  • workspaceSize (uint64_t *, output): size of the workspace to be allocated on the device.
  • executor (aclOpExecutor **, output): operator executor, containing the operator computation process.

• Returns:

  aclnnStatus: status code. For details, see .

[object Object]

• Parameters:

  • workspace (void *, input): address of the workspace to be allocated on the device.
  • workspaceSize (uint64_t, input): size of the workspace to be allocated on the device, which is obtained by the first-phase API aclnnInverseGetWorkspaceSize.
  • executor (aclOpExecutor *, input): operator executor, containing the operator computation process.
  • stream (aclrtStream, input): stream for executing the task.

• Returns:

  aclnnStatus: status code. For details, see .

[object Object]

• Deterministic compute:
  • aclnnInverse defaults to a deterministic implementation.

[object Object]

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