Documentation
Download

aclnnNanToNum&aclnnInplaceNanToNum

📄 View source code

Supported Products

ProductSupported
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

Operator function: Replaces NaN, positive infinity, and negative infinity in the input with the values specified by nan, posinf, and neginf, respectively.

Prototype

  • aclnnNanToNum and aclnnInplaceNanToNum implement the same function in different ways. Select a proper operator based on your requirements.

    • aclnnNanToNum: An output tensor object needs to be created to store the computation result.
    • aclnnInplaceNanToNum: No output tensor object needs to be created, and the computation result is stored in the memory of the input tensor.

  • Each operator has two-phase API calls. First, aclnnNanToNumGetWorkspaceSize or aclnnInplaceNanToNumGetWorkspaceSize is called to obtain the workspace size required for computation and the executor that contains the operator computation process. Then, aclnnNanToNum or aclnnInplaceNanToNum is called to perform 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:

    • self (aclTensor*, computation input): input tensor. Non-contiguous tensors are supported. The data format can be ND. The data type can be FLOAT16, FLOAT32, INT8, INT16, INT32, INT64, UINT8, BOOL, or BFLOAT16.
    • out (aclTensor*, computation output): output tensor. The shape is the same as that of self. The data format can be ND, and must be the same as that of self. The data type can be FLOAT16, FLOAT32, INT8, INT16, INT32, INT64, UINT8, BOOL, or BFLOAT16.
    • nan (float, computation input): input parameter, which replaces the NaN value of the tensor element. The data type can be FLOAT.
    • posinf (float, computation input): input parameter, which replaces the positive infinity value of the tensor element. The data type can be FLOAT.
    • neginf (float, computation input): input parameter, which replaces the negative infinity value of the tensor element. The data type can be FLOAT.
    • 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 aclnn Return Codes.

   The first-phase API implements input parameter verification. The following errors may be thrown.
 161001 ACLNN_ERR_PARAM_NULLPTR: 1. The input self or out is a null pointer.
 161002 ACLNN_ERR_PARAM_INVALID: 1. The data type and format of self are not supported.
                                2. The data types of self and out are inconsistent.
                                3. The shapes of self and out are inconsistent.
                                4. The dimensions of self are greater than 8.

aclnnNanToNum

  • 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 calling the first-phase API aclnnNanToNumGetWorkspaceSize.
    • 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 aclnn Return Codes.

aclnnInplaceNanToNumGetWorkspaceSize

  • Parameters:

    • selfRef (aclTensor *, computation input | computation output): input and output tensor. Non-contiguous tensors are supported. The data format supports ND. The data type can be FLOAT16, FLOAT32, INT8, INT16, INT32, INT64, UINT8, BOOL, or BFLOAT16.
    • nan (float, computation input): input parameter, which replaces the NaN value of the tensor element. The data type can be FLOAT.
    • posinf (float, computation input): input parameter, which replaces the positive infinity value of the tensor element. The data type can be FLOAT.
    • neginf (float, computation input): input parameter, which replaces the negative infinity value of the tensor element. The data type can be FLOAT.
    • 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 aclnn Return Codes.

   The first-phase API implements input parameter verification. The following errors may be thrown.
 161001 ACLNN_ERR_PARAM_NULLPTR: 1. The input selfRef is a null pointer.
 161002 ACLNN_ERR_PARAM_INVALID: 1. The data type and format of selfRef are not supported.
                                 2. The dimensions of selfRef are greater than 8.

aclnnInplaceNanToNum

  • 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 aclnnInplaceNanToNumGetWorkspaceSize.
    • 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 aclnn Return Codes.

Constraints

  • Deterministic computing:
    • aclnnNanToNum&aclnnInplaceNanToNum defaults to a deterministic implementation.

Example

The following example is for reference only. For details, see Compilation and Running Sample.

aclnnNanToNum sample code:

#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) {
  // (Fixed writing) Initialize resources.
  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 allocate memory on the device.
  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 the data on the host to the memory on the device.
  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 consecutive tensors.
  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. (Fixed writing) Initialize the device and stream. For details, 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 inputs and outputs 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 a self aclTensor.
  ret = CreateAclTensor(selfHostData, selfShape, &selfDeviceAddr, aclDataType::ACL_FLOAT, &self);
  CHECK_RET(ret == ACL_SUCCESS, return ret);
  // Create an 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, which needs to be replaced with the actual API.
  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);
  // Allocate device memory based on 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 aclnnNanToNum.
  ret = aclnnNanToNum(workspaceAddr, workspaceSize, executor, stream);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnNanToNum failed. ERROR: %d\n", ret); return ret);

  // 4. (Fixed writing) Wait until the task execution is 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 to the host. Modify the code based on the 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. Modify the configuration based on the API definition.
  aclDestroyTensor(self);
  aclDestroyTensor(out);

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

aclnnInplaceNanToNum sample code:

#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) {
  // (Fixed writing) Initialize resources.
  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 allocate memory on the device.
  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 the data on the host to the memory on the device.
  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 consecutive tensors.
  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. (Fixed writing) Initialize the device and stream. For details, 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 inputs and outputs 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 a 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, which needs to be replaced with the actual API.
  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);
  // Allocate device memory based on 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. (Fixed writing) Wait until the task execution is 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 to the host. Modify the code based on the API 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 the configuration based on the API definition.
  aclDestroyTensor(self);

  // 7. Release device resources. Modify the configuration based on the API definition.
  aclrtFree(selfDeviceAddr);
  if (workspaceSize > 0) {
    aclrtFree(workspaceAddr);
  }
  aclrtDestroyStream(stream);
  aclrtResetDevice(deviceId);
  aclFinalize();
  return 0;
}
This site uses cookies to improve your browsing experience. By continuing to browse this site, you agree to our use of cookies.View Details