aclSetTensorAddr

// Create the input and output aclTensor and aclTensorList.
std::vector<int64_t> shape = {1, 2, 3};
aclTensor tensor1 = aclCreateTensor(shape.data(), shape.size(), aclDataType::ACL_FLOAT,
nullptr, 0, aclFormat::ACL_FORMAT_ND, shape.data(), shape.size(), nullptr);
aclTensor tensor2 = aclCreateTensor(shape.data(), shape.size(), aclDataType::ACL_FLOAT,
nullptr, 0, aclFormat::ACL_FORMAT_ND, shape.data(), shape.size(), nullptr);
aclTensor tensor3 = aclCreateTensor(shape.data(), shape.size(), aclDataType::ACL_FLOAT,
nullptr, 0, aclFormat::ACL_FORMAT_ND, shape.data(), shape.size(), nullptr);
aclTensor output = aclCreateTensor(shape.data(), shape.size(), aclDataType::ACL_FLOAT,
nullptr, 0, aclFormat::ACL_FORMAT_ND, shape.data(), shape.size(), nullptr);
aclTensor *list[] = {tensor1, tensor2};
auto tensorList = aclCreateTensorList(list, 2);
uint64_t workspace_size = 0;
aclOpExecutor *executor;
// The AddCustom operator has two inputs (aclTensorList and aclTensor) and one output (aclTensor).
// Call the first-phase API.
aclnnAddCustomGetWorkspaceSize(tensorList, tensor3, output, &workspace_size, &executor);
// Set the executor to be reusable.
aclSetAclOpExecutorRepeatable(executor);  
void *addr;
aclSetTensorAddr(executor, 0, tensor1, addr); // Update the device address of the first aclTensor in the input tensor list.
aclSetTensorAddr(executor, 1, tensor2, addr); // Update the device address of the second aclTensor in the input tensor list.
aclSetTensorAddr(executor, 2, tensor3, addr); // Update the device address of the input aclTensor.
aclSetTensorAddr(executor, 3, output, addr); // Update the device address of the output aclTensor.
.......
// Call the second-phase API.
aclnnAddCustom(workspace, workspace_size, executor, stream);
// Clear the executor.
aclDestroyAclOpExecutor(executor);