aclnnUniqueConsecutive

Applicable Products

Function

Description: Removes duplicate elements that follow each element. When dim is not empty, removes duplicate tensors that follow each tensor along the corresponding dimension.

Function Prototype

Each operator is divided into a two-phase API. The "aclnnUniqueConsecutiveGetWorkspaceSize" API must be called first to obtain the workspace size required for computation and the executor that encapsulates the operator computation flow. Then, the "aclnnUniqueConsecutive" API is called to perform the **computation.

aclnnStatus aclnnUniqueConsecutiveGetWorkspaceSize(
  const aclTensor* self,
  bool             returnInverse,
  bool             returnCounts,
  int64_t          dim,
  clTensor*        valueOut,
  aclTensor*       inverseOut,
  aclTensor*       countsOut,
  uint64_t*        workspaceSize,
  aclOpExecutor**  executor)

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

aclnnUniqueConsecutiveGetWorkspaceSize

• Parameters

  Parameter	Input/Output	Description	Instruction	Data Type	Data Format	Shape	Non-contiguous Tensor
  self	Input	-	-	FLOAT, FLOAT16, DOUBLE, INT8, INT16, INT32, INT64, UINT8, UINT16, UINT32, UINT64, COMPLEX64, COMPLEX128, BOOL, BFLOAT16	ND	≤8	-
  returnInverse	Input	Indicates whether to return the position indices of each element in self within valueOut. When set to True, the indices are returned; when set to False, they are not.	-	-	-	-	-
  returnCounts	Input	Specifies whether to return the number of consecutive occurrences of each element in valueOut within self. Returned when set to True, not returned when set to False.	-	-	-	-	-
  dim	Input	Indicates the dimension along which to remove duplicates.	-	-	-	-	-
  valueOut	Output	The first output tensor, which returns the result after removing consecutive duplicate elements.	-	FLOAT, FLOAT16, DOUBLE, INT8, INT16, INT32, INT64, UINT8, UINT16, UINT32, UINT64, COMPLEX64, COMPLEX128, BOOL, BFLOAT16.	-	-	-
  inverseOut	Output	The second output tensor. Meaningful when returnInverse is True. Returns the position index of each element in self within the corresponding element in valueOut.	-	INT64	ND	-	-
  countsOut	Output	The third output tensor, meaningful when returnCounts is True. Returns the number of consecutive occurrences of each element in valueOut within self.	-	INT64	ND	-	-
  workspaceSize	Output	Returns the workspace size to be allocated on the Device side.	-	-	-	-	-
  executor	Output	Returns the operator executor, which contains the operator computation flow.	-	-	-	-	-

• Return Value

  aclnnStatus: Return Status. See aclnn Return Code. The first-phase API performs input parameter validation and reports an error in the following scenarios:

  Return Value	Error Code	Description
  ACLNN_ERR_PARAM_NULLPTR	161001	The input self, valueOut, inverseOut, or countsOut is a null pointer.
  ACLNN_ERR_PARAM_INVALID	161002	The data type of self or valueOut is not within the supported range.
  		The data type of self is not within the supported range.
  		The data type of inverseOut or countsOut is not within the supported range.
  		The data types of inverseOut and countsOut are inconsistent.

aclnnUniqueConsecutive

• Parameters

  Parameter	Input/Output	Description
  workspace	Input	Specifies the workspace memory address applied for on the Device side.
  workspaceSize	Input	Specifies the workspace size applied for on the Device side, obtained through the first-phase API aclnnUniqueConsecutiveGetWorkspaceSize.
  executor	Input	Operator executor, which contains the operator computation flow.
  stream	Input	Specifies the stream for task execution.

• Return Value

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

Constraints

• Deterministic computation:

  • aclnnUniqueConsecutive defaults to a deterministic implementation.

Example

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

#include <iostream>
#include <vector>
#include "acl/acl.h"
#include "aclnnop/aclnn_unique_consecutive.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 shape_size = 1;
  for (auto i : shape) {
    shape_size *= i;
  }
  return shape_size;
}

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 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);

  // Copy data from the host to the device memory using aclrtMemcpy.
  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 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];
  }

  // Create an aclTensor using the aclCreateTensor API.
  *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.
  // Specify the deviceId based on your actual device.
  int32_t deviceId = 0;
  aclrtStream stream;
  auto ret = Init(deviceId, &stream);
  // Handle the check as needed.
  CHECK_RET(ret == 0, LOG_PRINT("Init acl failed. ERROR: %d\n", ret); return ret);
  // 2. Construct the input and output. Custom construction is required based on the API interface.
  std::vector<int64_t> selfShape = {4, 2};
  std::vector<int64_t> valueShape = {8};
  std::vector<int64_t> inverseShape = {4, 2};
  std::vector<int64_t> countsShape = {8};
  void* selfDeviceAddr = nullptr;
  void* valueDeviceAddr = nullptr;
  void* inverseDeviceAddr = nullptr;
  void* countsDeviceAddr = nullptr;
  aclTensor* self = nullptr;
  aclTensor* valueOut = nullptr;
  aclTensor* inverseOut = nullptr;
  aclTensor* countsOut = nullptr;
  std::vector<float> selfHostData = {0, 1, 1, 3, 3, 1, 1, 3};
  std::vector<float> valueHostData = {0, 0, 0, 0, 0, 0, 0, 0};
  std::vector<int64_t> inverseHostData = {0, 0, 0, 0, 0, 0, 0, 0};
  std::vector<int64_t> countsHostData = {0, 0, 0, 0, 0, 0, 0, 0};
  bool returnInverse = false;
  bool returnCounts = false;
  int64_t dim = 0;

  // Create the self aclTensor.
  ret = CreateAclTensor(selfHostData, selfShape, &selfDeviceAddr, aclDataType::ACL_FLOAT, &self);
  CHECK_RET(ret == ACL_SUCCESS, return ret);
  // Create the valueOut aclTensor.
  ret = CreateAclTensor(valueHostData, valueShape, &valueDeviceAddr, aclDataType::ACL_FLOAT, &valueOut);
  CHECK_RET(ret == ACL_SUCCESS, return ret);
  // Create the inverseOut aclTensor.
  ret = CreateAclTensor(inverseHostData, inverseShape, &inverseDeviceAddr, aclDataType::ACL_INT64, &inverseOut);
  CHECK_RET(ret == ACL_SUCCESS, return ret);
  // Create the countsOut aclTensor.
  ret = CreateAclTensor(countsHostData, countsShape, &countsDeviceAddr, aclDataType::ACL_INT64, &countsOut);
  CHECK_RET(ret == ACL_SUCCESS, return ret);

  // 3. Call the CANN operator library API.
  uint64_t workspaceSize = 0;
  aclOpExecutor* executor;
  // Call the first-phase API of aclnnUniqueConsecutive.
  ret = aclnnUniqueConsecutiveGetWorkspaceSize(self, returnInverse, returnCounts, dim, valueOut, inverseOut, countsOut, &workspaceSize, &executor);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnUniqueConsecutiveGetWorkspaceSize failed. ERROR: %d\n", ret); return ret);
  // Allocate 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 aclnnUniqueConsecutive.
  ret = aclnnUniqueConsecutive(workspaceAddr, workspaceSize, executor, stream);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnUniqueConsecutive failed. ERROR: %d\n", ret); return ret);
  // 4. (Boilerplate) Synchronously wait for task execution to finish.
  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 device memory to host memory. Modify based on the specific API definition.
  auto size = GetShapeSize(valueShape);
  std::vector<float> resultData(size, 0);
  ret = aclrtMemcpy(resultData.data(), resultData.size() * sizeof(resultData[0]), valueDeviceAddr, size * sizeof(float),
                    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 definition.
  aclDestroyTensor(self);
  aclDestroyTensor(valueOut);
  aclDestroyTensor(inverseOut);
  aclDestroyTensor(countsOut);
  return 0;

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