aclnnNanToNum&aclnnInplaceNanToNum

Applicable Products

Product	Supported
Ascend 950PR/Ascend 950DT	√
Atlas A3 training products/Atlas A3 inference products	√
Atlas A2 training products/Atlas A2 inference products	√
Atlas 200I/500 A2 inference products	×
Atlas inference products	×
Atlas training products	×

Function

Description: Replaces NaN, positive infinity, and negative infinity values in the input with the values specified by nan, posinf, and neginf, respectively.
Formula:
$\text{out}_i = \begin{cases} \text{nan} & \text{if } \text{self}_i \text{ is NaN} \\ \text{posinf} & \text{if } \text{self}_i \text{ is } +\infty \\ \text{neginf} & \text{if } \text{self}_i \text{ is } -\infty \\ \text{self}_i & \text{otherwise} \end{cases}$

Function Prototype

aclnnNanToNum and aclnnInplaceNanToNum implement the same functionality. The differences in usage are as follows. Select the appropriate operator based on your actual scenario.
- aclnnNanToNum: Requires creating a new output tensor object to store the computation result.
- aclnnInplaceNanToNum: Does not require creating a new output tensor object. The computation result is stored directly in the memory of the input tensor.

Each operator is divided into a two-phase API. You must first call the "aclnnNanToNumGetWorkspaceSize" or "aclnnInplaceNanToNumGetWorkspaceSize" API to obtain the workspace size required for computation and the executor that includes the operator computation process, and then call the "aclnnNanToNum" or "aclnnInplaceNanToNum" API to execute the computation.

aclnnStatus aclnnNanToNumGetWorkspaceSize(
  const aclTensor *self,
  float            nan,
  float            posinf,
  float            neginf,
  aclTensor       *out,
  uint64_t        *workspaceSize,
  aclOpExecutor  **executor)

aclnnStatus aclnnNanToNum(
  void*          workspace,
  uint64_t       workspaceSize,
  aclOpExecutor *executor,
  aclrtStream    stream)

aclnnStatus aclnnInplaceNanToNumGetWorkspaceSize(
  aclTensor      *selfRef,
  float           nan,
  float           posinf,
  float           neginf,
  uint64_t       *workspaceSize,
  aclOpExecutor **executor)

aclnnStatus aclnnInplaceNanToNum(
  void*          workspace,
  uint64_t       workspaceSize,
  aclOpExecutor *executor,
  aclrtStream    stream)

aclnnNanToNumGetWorkspaceSize

Parameters:

Parameter	Input/Output	Description	Instruction	Data Type	Data Format	Dimension (Shape)	Non-contiguous Tensor
self (aclTensor*)	Input	Input tensor.	-	FLOAT16、FLOAT32、INT8、INT16、INT32、INT64、UINT8、BOOL、BFLOAT16	ND	Not greater than 8.	√
nan (float)	Input.	Replaces NaN values in tensor elements.	-	FLOAT	-	-	-
posinf (float)	Input	Replaces the positive infinite values in the tensor elements.	-	FLOAT	-	-	-
neginf (float)	Input	Replaces the negative infinite values in tensor elements.	-	FLOAT	-	-	-
out (aclTensor*)	Output	Output tensor.	The shape is the same as self, and the data format must be consistent with self.	FLOAT16, FLOAT32, INT8, INT16, INT32, INT64, UINT8, BOOL, BFLOAT16	ND	Same as self.	√
workspaceSize (uint64_t*)	Output	Returns the workspace size to be applied on the Device side.	-	-	-	-	-
executor (aclOpExecutor**)	Output	Returns the op executor, which includes the calculation process.	-	-	-	-	-

Return value

aclnnStatus: return code. For details, see aclnn Return Codes.

The first-phase API performs input parameter validation and returns an error in the following scenarios:

Return Value	Error Code	Description
ACLNN_ERR_PARAM_NULLPTR	161001	The self or out passed in is a null pointer.
ACLNN_ERR_PARAM_INVALID	161002	The data type or data format of self is not within the supported range.
		The data types of self and out are inconsistent.
		The shapes of self and out are inconsistent.
		The dimension of self is greater than 8.

aclnnNanToNum

Parameters:

Parameter	Input/Output	Description
workspace	Input	Memory address of the workspace applied on the Device side.
workspaceSize	Input	Size of the workspace applied on the Device side, obtained from the first-phase API aclnnNanToNumGetWorkspaceSize.
executor	Input	Operator executor, which includes the operator calculation process.
stream	Input	Specifies the stream for task execution.

Return value

aclnnStatus: return code. For details, see aclnn Return Codes.

aclnnInplaceNanToNumGetWorkspaceSize

Parameters:

Parameter	Input/Output	Description	Instruction	Data Type	Data Format	Dimension (shape)	Non-contiguous Tensor
selfRef (aclTensor*)	Input/Output	Input/output tensor.	-	FLOAT16、FLOAT32、INT8、INT16、INT32、INT64、UINT8、BOOL、BFLOAT16	ND	Not greater than 8.	√
nan (float)	Input	Replaces the NaN values in tensor elements.	-	FLOAT	-	-	-
posinf (float)	Input	Replaces the positive infinite values in tensor elements.	-	FLOAT	-	-	-
neginf (float)	Input	Replaces negative infinity values in tensor elements.	-	FLOAT	-	-	-
workspaceSize（uint64_t*）	Output	Returns the workspace size to be applied for on the Device side.	-	-	-	-	-
executor (aclOpExecutor**)	Output	Returns the op executor, which includes the calculation process of the operator.	-	-	-	-	-

Return value

aclnnStatus: return code. For details, see aclnn Return Codes.

The first-phase API performs input parameter validation and returns an error in the following scenarios:

Return Value	Error Code	Description
ACLNN_ERR_PARAM_NULLPTR	161001	The passed selfRef is a null pointer.
ACLNN_ERR_PARAM_INVALID	161002	The data type and data format of selfRef are not within the supported range.
ACLNN_ERR_PARAM_INVALID	161002	The number of dimensions of selfRef exceeds 8.

aclnnInplaceNanToNum

Parameters:

Parameter	Input/Output	Description
workspace	Input	Address of the workspace memory applied on the device side.
workspaceSize	Input	Size of the workspace applied on the device side, obtained through the first-phase API aclnnInplaceNanToNumGetWorkspaceSize.
executor	Input	Operator executor, which includes the operator calculation process.
stream	Input	Specifies the stream that executes the task.

Return value

aclnnStatus: return code. For details, see aclnn Return Codes.

Constraints

Deterministic computation:
- aclnnNanToNum & aclnnInplaceNanToNum default to a deterministic implementation.

Example

The following provides example code for reference only. For details about compilation and running, see Compile and Run Samples.

Example of aclnnNanToNum API Call

#include <iostream>
#include <vector>
#include "acl/acl.h"
#include "aclnnop/aclnn_nan_to_num.h"

#define CHECK_RET(cond, return_expr) \
  do {                               \
    if (!(cond)) {                   \
      return_expr;                   \
    }                                \
  } while (0)

#define LOG_PRINT(message, ...)     \
  do {                              \
    printf(message, ##__VA_ARGS__); \
  } while (0)

int64_t GetShapeSize(const std::vector<int64_t>& shape) {
  int64_t shapeSize = 1;
  for (auto i : shape) {
    shapeSize *= i;
  }
  return shapeSize;
}

int Init(int32_t deviceId, aclrtStream* stream) {
  // Boilerplate: resource initialization.
  auto ret = aclInit(nullptr);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclInit failed. ERROR: %d\n", ret); return ret);
  ret = aclrtSetDevice(deviceId);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclrtSetDevice failed. ERROR: %d\n", ret); return ret);
  ret = aclrtCreateStream(stream);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclrtCreateStream failed. ERROR: %d\n", ret); return ret);
  return 0;
}

template <typename T>
int CreateAclTensor(const std::vector<T>& hostData, const std::vector<int64_t>& shape, void** deviceAddr,
                    aclDataType dataType, aclTensor** tensor) {
  auto size = GetShapeSize(shape) * sizeof(T);
  // Call aclrtMalloc to apply for device-side memory.
  auto ret = aclrtMalloc(deviceAddr, size, ACL_MEM_MALLOC_HUGE_FIRST);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclrtMalloc failed. ERROR: %d\n", ret); return ret);
  // Call aclrtMemcpy to copy data from the host side to the device side.
  ret = aclrtMemcpy(*deviceAddr, size, hostData.data(), size, ACL_MEMCPY_HOST_TO_DEVICE);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclrtMemcpy failed. ERROR: %d\n", ret); return ret);

  // Calculate the strides of a contiguous tensor.
  std::vector<int64_t> strides(shape.size(), 1);
  for (int64_t i = shape.size() - 2; i >= 0; i--) {
    strides[i] = shape[i + 1] * strides[i + 1];
  }

  // Call the aclCreateTensor API to create an aclTensor.
  *tensor = aclCreateTensor(shape.data(), shape.size(), dataType, strides.data(), 0, aclFormat::ACL_FORMAT_ND,
                            shape.data(), shape.size(), *deviceAddr);
  return 0;
}

int main() {
  // 1. (Boilerplate) Initialize the device/stream. See the ACL API manual.
  // Set deviceId based on the actual device.
  int32_t deviceId = 0;
  aclrtStream stream;
  auto ret = Init(deviceId, &stream);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("Init acl failed. ERROR: %d\n", ret); return ret);

  // 2. Construct the input and output. Customize the construction based on the API definition.
  std::vector<int64_t> selfShape = {2, 3};
  std::vector<int64_t> outShape = {2, 3};
  void* selfDeviceAddr = nullptr;
  void* outDeviceAddr = nullptr;
  aclTensor* self = nullptr;
  aclTensor* out = nullptr;
  float nanValue = 0;
  float posInfValue = 1.0;
  float negInfValue = -1.0;
  std::vector<float> selfHostData = {0, 1, 2, 3, 4, 0, 1, -1};
  std::vector<float> outHostData = {0, 0, 0, 0, 0, 0, 0, 0};
  // Create the self aclTensor.
  ret = CreateAclTensor(selfHostData, selfShape, &selfDeviceAddr, aclDataType::ACL_FLOAT, &self);
  CHECK_RET(ret == ACL_SUCCESS, return ret);
  // Create the out aclTensor.
  ret = CreateAclTensor(outHostData, outShape, &outDeviceAddr, aclDataType::ACL_FLOAT, &out);
  CHECK_RET(ret == ACL_SUCCESS, return ret);

  // 3. Call the CANN operator library API. Replace with the specific API name.
  uint64_t workspaceSize = 0;
  aclOpExecutor* executor;
  // Call the first-phase API of aclnnNanToNum.
  ret = aclnnNanToNumGetWorkspaceSize(self, nanValue, posInfValue, negInfValue, out, &workspaceSize,
                                     &executor);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnNanToNumGetWorkspaceSize failed. ERROR: %d\n", ret); return ret);
  // Apply for device memory based on the workspaceSize calculated by the first-phase API.
  void* workspaceAddr = nullptr;
  if (workspaceSize > 0) {
    ret = aclrtMalloc(&workspaceAddr, workspaceSize, ACL_MEM_MALLOC_HUGE_FIRST);
    CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("allocate workspace failed. ERROR: %d\n", ret); return ret);
  }
  // Call the second-phase API of aclnnNanToNum.
  ret = aclnnNanToNum(workspaceAddr, workspaceSize, executor, stream);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnNanToNum failed. ERROR: %d\n", ret); return ret);

  // 4. (boilerplate) Synchronize and wait for task execution to complete.
  ret = aclrtSynchronizeStream(stream);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclrtSynchronizeStream failed. ERROR: %d\n", ret); return ret);

  // 5. Obtain the output value and copy the result from the device memory to the host memory, based on the specific API definition.
  auto size = GetShapeSize(outShape);
  std::vector<float> resultData(size, 0);
  ret = aclrtMemcpy(resultData.data(), resultData.size() * sizeof(resultData[0]), outDeviceAddr,
                    size * sizeof(resultData[0]), ACL_MEMCPY_DEVICE_TO_HOST);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("copy result from device to host failed. ERROR: %d\n", ret); return ret);
  for (int64_t i = 0; i < size; i++) {
    LOG_PRINT("result[%ld] is: %f\n", i, resultData[i]);
  }

  // 6. Release aclTensor and aclScalar, based on the specific API definition.
  aclDestroyTensor(self);
  aclDestroyTensor(out);

  // 7. Release device resources. Modify based on the specific API interface definition.
  aclrtFree(selfDeviceAddr);
  aclrtFree(outDeviceAddr);
  if (workspaceSize > 0) {
    aclrtFree(workspaceAddr);
  }
  aclrtDestroyStream(stream);
  aclrtResetDevice(deviceId);
  aclFinalize();
  return 0;
}

Sample code for calling the aclnnInplaceNanToNum API:

#include <iostream>
#include <vector>
#include "acl/acl.h"
#include "aclnnop/aclnn_nan_to_num.h"

#define CHECK_RET(cond, return_expr) \
  do {                               \
    if (!(cond)) {                   \
      return_expr;                   \
    }                                \
  } while (0)

#define LOG_PRINT(message, ...)     \
  do {                              \
    printf(message, ##__VA_ARGS__); \
  } while (0)

int64_t GetShapeSize(const std::vector<int64_t>& shape) {
  int64_t shapeSize = 1;
  for (auto i : shape) {
    shapeSize *= i;
  }
  return shapeSize;
}

int Init(int32_t deviceId, aclrtStream* stream) {
  // Boilerplate: resource initialization.
  auto ret = aclInit(nullptr);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclInit failed. ERROR: %d\n", ret); return ret);
  ret = aclrtSetDevice(deviceId);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclrtSetDevice failed. ERROR: %d\n", ret); return ret);
  ret = aclrtCreateStream(stream);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclrtCreateStream failed. ERROR: %d\n", ret); return ret);
  return 0;
}

template <typename T>
int CreateAclTensor(const std::vector<T>& hostData, const std::vector<int64_t>& shape, void** deviceAddr,
                    aclDataType dataType, aclTensor** tensor) {
  auto size = GetShapeSize(shape) * sizeof(T);
  // Call aclrtMalloc to apply for device-side memory.
  auto ret = aclrtMalloc(deviceAddr, size, ACL_MEM_MALLOC_HUGE_FIRST);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclrtMalloc failed. ERROR: %d\n", ret); return ret);
  // Call aclrtMemcpy to copy host-side data to device-side memory.
  ret = aclrtMemcpy(*deviceAddr, size, hostData.data(), size, ACL_MEMCPY_HOST_TO_DEVICE);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclrtMemcpy failed. ERROR: %d\n", ret); return ret);

  // Compute strides for a contiguous tensor.
  std::vector<int64_t> strides(shape.size(), 1);
  for (int64_t i = shape.size() - 2; i >= 0; i--) {
    strides[i] = shape[i + 1] * strides[i + 1];
  }

  // Call aclCreateTensor to create an aclTensor.
  *tensor = aclCreateTensor(shape.data(), shape.size(), dataType, strides.data(), 0, aclFormat::ACL_FORMAT_ND,
                            shape.data(), shape.size(), *deviceAddr);
  return 0;
}

int main() {
  // 1. (Boilerplate) Initialize device/stream. See the acl API manual.
  // Fill in deviceId based on your actual device.
  int32_t deviceId = 0;
  aclrtStream stream;
  auto ret = Init(deviceId, &stream);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("Init acl failed. ERROR: %d\n", ret); return ret);

  // 2. Construct input and output. Customize based on the API definition.
  std::vector<int64_t> selfShape = {2, 3};
  void* selfDeviceAddr = nullptr;
  aclTensor* self = nullptr;
  float nanValue = 0;
  float posInfValue = 1.0;
  float negInfValue = -1.0;
  std::vector<float> selfHostData = {0, 1, 2, 3, 4, 0, 1, -1};
  // Create self aclTensor.
  ret = CreateAclTensor(selfHostData, selfShape, &selfDeviceAddr, aclDataType::ACL_FLOAT, &self);
  CHECK_RET(ret == ACL_SUCCESS, return ret);

  // 3. Call the CANN operator library API. Modify to the specific API name.
  uint64_t workspaceSize = 0;
  aclOpExecutor* executor;
  // Call the first-phase API of aclnnInplaceNanToNum.
  ret = aclnnInplaceNanToNumGetWorkspaceSize(self, nanValue, posInfValue, negInfValue, &workspaceSize, &executor);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnInplaceNanToNumGetWorkspaceSize failed. ERROR: %d\n", ret); return ret);
  // Apply for device memory based on the workspaceSize computed by the first-phase API.
  void* workspaceAddr = nullptr;
  if (workspaceSize > 0) {
    ret = aclrtMalloc(&workspaceAddr, workspaceSize, ACL_MEM_MALLOC_HUGE_FIRST);
    CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("allocate workspace failed. ERROR: %d\n", ret); return ret);
  }
  // Call the second-phase API of aclnnInplaceNanToNum.
  ret = aclnnInplaceNanToNum(workspaceAddr, workspaceSize, executor, stream);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnInplaceNanToNum failed. ERROR: %d\n", ret); return ret);

  // 4. (Boilerplate) Synchronize and wait for task execution to complete.
  ret = aclrtSynchronizeStream(stream);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclrtSynchronizeStream failed. ERROR: %d\n", ret); return ret);

  // 5. Obtain the output value. Copy the result from device-side memory to host side. Modify based on the specific API interface definition.
  auto size = GetShapeSize(selfShape);
  std::vector<float> resultData(size, 0);
  ret = aclrtMemcpy(resultData.data(), resultData.size() * sizeof(resultData[0]), selfDeviceAddr,
                    size * sizeof(resultData[0]), ACL_MEMCPY_DEVICE_TO_HOST);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("copy result from device to host failed. ERROR: %d\n", ret); return ret);
  for (int64_t i = 0; i < size; i++) {
    LOG_PRINT("result[%ld] is: %f\n", i, resultData[i]);
  }

  // 6. Release aclTensor and aclScalar. Modify based on the specific API interface definition.
  aclDestroyTensor(self);

  // 7. Release device resources. Modify based on the specific API interface definition.
  aclrtFree(selfDeviceAddr);
  if (workspaceSize > 0) {
    aclrtFree(workspaceAddr);
  }
  aclrtDestroyStream(stream);
  aclrtResetDevice(deviceId);
  aclFinalize();
  return 0;
}```