aclnnUnique

Applicable Products

Function

Function: Returns the unique elements in the input tensor.

Function Prototype

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

aclnnStatus aclnnUniqueGetWorkspaceSize(
  const aclTensor* self,
  bool             sorted,
  bool             returnInverse,
  aclTensor*       valueOut,
  aclTensor*       inverseOut,
  uint64_t*        workspaceSize,
  aclOpExecutor**  executor)

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

aclnnUniqueGetWorkspaceSize

• Parameters

  Parameter	Input/Output	Description	Instruction	Data Type	Data Format	Shape	Non-contiguous Tensor
  self	Input.	-	-	BOOL, FLOAT, FLOAT16, DOUBLE, UINT8, INT8, UINT16, INT16, INT32, UINT32, UINT64, INT64, BFLOAT16	ND	≤8	-
  sorted	Input	Indicates whether to sort valueOut in ascending order. If true, the output is sorted; if false, the output is unsorted.	-	-	-	-	-
  returnInverse	Input	Indicates whether to return the index of each element in the input data within valueOut.	-	-	-	-	-
  valueOut	Output	The first output tensor, containing the unique elements from the input tensor.		BOOL, FLOAT, FLOAT16, DOUBLE, UINT8, INT8, UINT16, INT16, INT32, UINT32, UINT64, INT64, BFLOAT16
  inverseOut	Output	The second output tensor, meaningful when returnInverse is True. Returns the position index of each element in self within valueOut.
  workspaceSize	Output	Returns the workspace size to be requested on the Device side.	-	-	-	-	-
  executor	Output	Returns the operator executor, which contains the operator computation process.	-	-	-	-	-

• Return Value

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

  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, valueOut, or inverseOut passed in is a null pointer.
  ACLNN_ERR_PARAM_INVALID	161002	The data type of self or valueOut is not within the supported range.
  		self is a non-contiguous tensor.
  		returnInverse is True and the shape of inverseOut is inconsistent with that of self.
  		returnInverse is True and the data type of inverseOut is not INT64.

aclnnUnique

• Parameters

  Parameter	Input/Output	Description
  workspace	Input	Address of the workspace memory applied for on the device.
  workspaceSize	Input	Size of the workspace applied for on the device, obtained through the first-phase API aclnnUniqueGetWorkspaceSize.
  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:

  • aclnnUnique defaults to a deterministic implementation.

  • Ascend 950PR/Ascend 950DT:

    • Due to differences in the deduplication algorithm implementation, when all of the following conditions are met, the operator ignores the value of the sorted input parameter and always sorts the output results in ascending order:

      • self input is 1D.

      • The data type of self is one of the following types: FLOAT, FLOAT16, UINT8, INT8, UINT16, INT16, INT32, UINT32, UINT64, INT64, BFLOAT16.

  • Atlas A2 training products/Atlas A2 inference products, Atlas A3 training products/Atlas A3 inference products: When the input self contains 0, the operator output includes both positive zero and negative zero, rather than outputting only one zero.

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.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 for 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);

  // Copy host-side data to 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);

  // 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.
  // Enter the deviceId based on the actual device.
  int32_t deviceId = 0;
  aclrtStream stream;
  auto ret = Init(deviceId, &stream);
  // Handle according to your needs.
  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.
  std::vector<int64_t> selfShape = {8};
  std::vector<int64_t> valueShape = {8};
  std::vector<int64_t> inverseShape = {8};
  void* selfDeviceAddr = nullptr;
  void* valueDeviceAddr = nullptr;
  void* inverseDeviceAddr = nullptr;
  aclTensor* self = nullptr;
  aclTensor* valueOut = nullptr;
  aclTensor* inverseOut = nullptr;
  std::vector<float> selfHostData = {1, 2, 3, 4, 5, 6, 7, 8};
  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};
  bool sorted = true;
  bool returnInverse = true;

  // 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);

  // 3. Call the CANN operator library API.
  uint64_t workspaceSize = 0;
  aclOpExecutor* executor;
  // Call the first-phase API of aclnnUnique.
  ret = aclnnUniqueGetWorkspaceSize(self, sorted, returnInverse, valueOut, inverseOut, &workspaceSize, &executor);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnUniqueGetWorkspaceSize 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 aclnnUnique.
  ret = aclnnUnique(workspaceAddr, workspaceSize, executor, stream);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnUnique 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. 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]);
  }
  std::vector<int64_t> resultData1(size, 0);
  ret = aclrtMemcpy(resultData1.data(), resultData1.size() * sizeof(resultData1[0]), inverseDeviceAddr, size * sizeof(int64_t),
                    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("result1[%ld] is: %f\n", i, resultData1[i]);
  }

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

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