aclnnFrac&aclnnInplaceFrac

Supported Products

Product	Supported
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: Calculates the decimal part of each element in the input tensor and then outputs the result.
Formula:
$out_{i}=input_{i} - \lfloor \vert input_{i} \vert \rfloor * sgn(input_{i})$
$sgn(\cdot)$ is a sign function, which extracts the sign of $input_{i}$ .

Prototype

aclnnFrac and aclnnInplaceFrac implement the same function in different ways. Select a proper operator based on your requirements.
- aclnnFrac: An output tensor object needs to be created to store the computation result.
- aclnnInplaceFrac: 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, aclnnFracGetWorkspaceSize or aclnnInplaceFracGetWorkspaceSize is called to obtain the workspace size required for computation and the executor that contains the operator computation process. Then, aclnnFrac or aclnnInplaceFrac is called to perform computation.
- aclnnStatus aclnnFracGetWorkspaceSize(const aclTensor* input, aclTensor* out, uint64_t* workspaceSize, aclOpExecutor** executor)
- aclnnStatus aclnnFrac(void* workspace, uint64_t workspaceSize, aclOpExecutor* executor, aclrtStream stream)
- aclnnStatus aclnnInplaceFracGetWorkspaceSize(aclTensor* inputRef, uint64_t* workspaceSize, aclOpExecutor** executor)
- aclnnStatus aclnnInplaceFrac(void* workspace, uint64_t workspaceSize, aclOpExecutor* executor, aclrtStream stream)

aclnnFracGetWorkspaceSize

Parameters:
- input (aclTensor*, compute input): input in the formula, aclTensor on the device. The shape can have 0 to 8 dimensions, and the shapes of input and out must be the same. Non-contiguous tensors are supported. The data format can be ND. The data type must be the same as that of out.
  - Atlas training products: The data type can be FLOAT16, FLOAT, UINT8, INT8, INT16, INT32, or INT64.
  - Atlas A2 training products/Atlas A2 inference products and Atlas A3 training products/Atlas A3 inference products: The data type can be FLOAT16, FLOAT, UINT8, INT8, INT16, INT32, INT64, or BFLOAT16.
- out (aclTensor*, compute output): out in the formula, aclTensor on the device. The shape can have 0 to 8D, and the shapes of input and out must be the same. Non-contiguous tensors are supported. The data format can be ND. The data type must be the same as that of out.
  - Atlas training products: The data type can be FLOAT16, FLOAT, UINT8, INT8, INT16, INT32, or INT64.
  - Atlas A2 training products/Atlas A2 inference products and Atlas A3 training products/Atlas A3 inference products: The data type can be FLOAT16, FLOAT, UINT8, INT8, INT16, INT32, INT64, or BFLOAT16.
- 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 performs input parameter validation. The following errors may be returned:
 161001 (ACLNN_ERR_PARAM_NULLPTR): 1. The passed input or out is a null pointer.
 161002 (ACLNN_ERR_PARAM_INVALID): 1. The data type of input or out is not supported.
                                     2. The shapes of input and out are inconsistent.
                                     3. The data types of input and out are inconsistent.
                                     4. The shape of input or out is greater than 8D.

aclnnFrac

Parameters:
- workspace (void*, input): memory 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 aclnnFracGetWorkspaceSize.
- 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.

aclnnInplaceFracGetWorkspaceSize

Parameters:
- inputRef (aclTensor*, compute input): aclTensor on the device. The shape can be 0 to 8D. Non-contiguous tensors are supported. The data format can be ND.
  - Atlas training products: The data type can be FLOAT16, FLOAT, UINT8, INT8, INT16, INT32, or INT64.
  - Atlas A2 training products/Atlas A2 inference products and Atlas A3 training products/Atlas A3 inference products: The data type can be FLOAT16, FLOAT, UINT8, INT8, INT16, INT32, INT64, or BFLOAT16.
- 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 performs input parameter validation. The following errors may be returned:
 161001 (ACLNN_ERR_PARAM_NULLPTR): 1. The passed inputRef is a null pointer.
 161002 (ACLNN_ERR_PARAM_INVALID): 1. The data type of inputRef is not supported.
                                     2. The shape of inputRef is greater than 8D.

aclnnInplaceFrac

Parameters:
- workspace (void *, input): memory 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 aclnnInplaceFracGetWorkspaceSize.
- 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 computation:
- aclnnFrac and aclnnInplaceFrac default to a deterministic implementation.

Calling Example

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

#include <iostream>
#include <vector>
#include "acl/acl.h"
#include "aclnnop/aclnn_frac.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) 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 device 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 data to the device 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 the strides of the 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 the device and stream. For details, see the ACL API manual.
  // Set the device ID based on the actual device.
  int32_t deviceId = 0;
  aclrtStream stream;
  auto ret = Init(deviceId, &stream);
  // Perform the check as required.
  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 = {4, 2};
  std::vector<int64_t> outShape = {4, 2};
  void* selfDeviceAddr = nullptr;
  void* outDeviceAddr = nullptr;
  aclTensor* self = nullptr;
  aclTensor* out = nullptr;
  std::vector<float> selfHostData = {0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8};
  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);

  // aclnnFrac API calling example
  // 3. Call the CANN operator library API.
  // Call the first-phase API of aclnnFrac.
  uint64_t workspaceSize = 0;
  aclOpExecutor* executor;
  ret = aclnnFracGetWorkspaceSize(self, out, &workspaceSize, &executor);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnFracGetWorkspaceSize 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 aclnnFrac.
  ret = aclnnFrac(workspaceAddr, workspaceSize, executor, stream);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnFrac failed. ERROR: %d\n", ret); return ret);

  // 4. (Boilerplate) 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 memory 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]);
  }

  // aclnnInplace API calling example
  LOG_PRINT("\ntest aclnnInplaceFrac\n");
  // 3. Call the CANN operator library API.
  // Call the first-phase API of aclnnInplaceFrac.
  uint64_t inplaceWorkspaceSize = 0;
  aclOpExecutor* inplaceExecutor;
  ret = aclnnInplaceFracGetWorkspaceSize(self, &inplaceWorkspaceSize, &inplaceExecutor);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnInplaceFracGetWorkspaceSize failed. ERROR: %d\n", ret); return ret);
  // Allocate device memory based on workspaceSize computed by the first-phase API.
  void* inplaceWorkspaceAddr = nullptr;
  if (inplaceWorkspaceSize > 0) {
    ret = aclrtMalloc(&inplaceWorkspaceAddr, inplaceWorkspaceSize, 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 aclnnInplaceFrac.
  ret = aclnnInplaceFrac(inplaceWorkspaceAddr, inplaceWorkspaceSize, inplaceExecutor, stream);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnInplaceFrac failed. ERROR: %d\n", ret); return ret);

  // 4. (Boilerplate) 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 memory to the host. Modify the code based on the API definition.
  size = GetShapeSize(outShape);
  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. Destroy aclTensor. Modify the code based on the API definition.
  aclDestroyTensor(self);
  aclDestroyTensor(out);

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