aclnnRopeWithSinCosCacheV2

📄 View Source Code

Applicable Products

Function

• Description: To improve performance, the inference network passes sin and cos inputs through a cache to perform rotary position embedding computation. Compared with the aclnnRopeWithSinCosCache API, this API adds the cacheMode parameter to indicate how cos and sin are concatenated:

  • When cacheMode=0, the implementation is the same as aclnnRopeWithSinCosCache, using segmented concatenation of cos and sin.

  • When cacheMode=1, cos and sin are concatenated in an interleaved manner.

• Formula:

  1. mrope mode: The shape of positions is [m, numTokens], where m is the number of elements in mropeSection, supporting 3 or 4:
  $$cosSin[i] = cosSinCache[positions[i]]$$ $$cos, sin = cosSin.chunk(2, dim=-1)$$

  (1) When cacheMode is 0:

  • The number of elements in mropeSection is 3:

    $$cos0 = cos[0, :, :mropeSection[0]]$$ $$cos1 = cos[1, :, mropeSection[0]:(mropeSection[0] + mropeSection[1])]$$ $$cos2 = cos[2, :, (mropeSection[0] + mropeSection[1]):(mropeSection[0] + mropeSection[1] + mropeSection[2])]$$ $$cos = torch.cat((cos0, cos1, cos2), dim=-1)$$ $$sin0 = sin[0, :, :mropeSection[0]]$$ $$sin1 = sin[1, :, mropeSection[0]:(mropeSection[0] + mropeSection[1])]$$ $$sin2 = sin[2, :, (mropeSection[0] + mropeSection[1]):(mropeSection[0] + mropeSection[1] + mropeSection[2])]$$ $$sin= torch.cat((sin0, sin1, sin2), dim=-1)$$ $$queryRot = query[..., :rotaryDim]$$ $$queryPass = query[..., rotaryDim:]$$

  • The number of elements in mropeSection is 4:

    $$cos = torch.cat([m[i]\ for\ i, m\ in\ enumerate(cos.split(mropeSection, dim=-1))], dim=-1)$$ $$sin = torch.cat([m[i]\ for\ i, m\ in\ enumerate(sin.split(mropeSection, dim=-1))], dim=-1)$$ $$queryRot = query[..., :rotaryDim]$$ $$queryPass = query[..., rotaryDim:]$$

  (2) cacheMode is 1:

  $$cosTmp = cos$$ $$cos [..., 1:mropeSection[1] * 3:3] = cosTmp[1, ..., 1:mropeSection[1] * 3:3]$$ $$cos[..., 2:mropeSection[1] * 3:3] = cosTmp[2, ..., 2:mropeSection[1] * 3:3]$$ $$sinTmp = sin$$ $$sin[..., 1:mropeSection[1] * 3:3] = sinTmp [1, ..., 1:mropeSection[1] * 3:3]$$ $$sin[..., 2:mropeSection[1] * 3:3] = sinTmp [2, ..., 2:mropeSection[1] * 3:3]$$ $$queryRot = query[..., :rotaryDim]$$ $$queryPass = query[..., rotaryDim:]$$

  (1) rotate_half (GPT-NeoX style) computation mode:

  $$x1, x2 = torch.chunk(queryRot, 2, dim=-1)$$ $$o1[i] = x1[i] * cos[i] - x2[i] * sin[i]$$ $$o2[i] = x2[i] * cos[i] + x1[i] * sin[i]$$ $$queryRot = torch.cat((o1, o2), dim=-1)$$ $$query = torch.cat((queryRot, queryPass), dim=-1)$$

  (2) rotate_interleaved (GPT-J style) computation mode:

  $$x1 = queryRot[..., ::2]$$ $$x2 = queryRot[..., 1::2]$$ $$o1[i] = x1[i] * cos[i] - x2[i] * sin[i]$$ $$o2[i] = x2[i] * cos[i] + x1[i] * sin[i]$$ $$queryRot = torch.stack((o1, o2), dim=-1)$$ $$query = torch.cat((queryRot, queryPass), dim=-1)$$
  2. rope mode: The shape of positions is [numTokens]:
  $$cosSin[i] = cosSinCache[positions[i]]$$ $$cos, sin = cosSin.chunk(2, dim=-1)$$ $$queryRot = query[..., :rotaryDim]$$ $$queryPass = query[..., rotaryDim:]$$

  (1) rotate_half (GPT-NeoX style) computation mode:

  $$x1, x2 = torch.chunk(queryRot, 2, dim=-1)$$ $$o1[i] = x1[i] * cos[i] - x2[i] * sin[i]$$ $$o2[i] = x2[i] * cos[i] + x1[i] * sin[i]$$ $$queryRot = torch.cat((o1, o2), dim=-1)$$ $$query = torch.cat((queryRot, queryPass), dim=-1)$$

  (2) rotate_interleaved (GPT-J style) computation mode:

  $$x1 = queryRot[..., ::2]$$ $$x2 = queryRot[..., 1::2]$$ $$o1[i] = x1[i] * cos[i] - x2[i] * sin[i]$$ $$o2[i] = x2[i] * cos[i] + x1[i] * sin[i]$$ $$queryRot = torch.stack((o1, o2), dim=-1)$$ $$query = torch.cat((queryRot, queryPass), dim=-1)$$

Function Prototype

Each operator is divided into a two-phase API. You must first call the "aclnnRopeWithSinCosCacheV2GetWorkspaceSize" API to obtain the workspace size required for computation and the executor that contains the operator computation process, and then call the "aclnnRopeWithSinCosCacheV2" API to perform the computation.

aclnnStatus aclnnRopeWithSinCosCacheV2GetWorkspaceSize(
    const aclTensor   *positions,
    const aclTensor   *queryIn,
    const aclTensor   *keyIn,
    const aclTensor   *cosSinCache,
    const aclIntArray *mropeSection,
    int64_t            headSize,
    bool               isNeoxStyle,
    int64_t            cacheMode,
    aclTensor         *queryOut,
    aclTensor         *keyOut,
    uint64_t          *workspaceSize,
    aclOpExecutor     **executor)

aclnnStatus aclnnRopeWithSinCosCacheV2(
    void          *workspace,
    uint64_t       workspaceSize,
    aclOpExecutor *executor,
    aclrtStream    stream)

aclnnRopeWithSinCosCacheV2GetWorkspaceSize

• Parameters:

  Parameter	Input/Output	Description	Instruction	Data Type	Data Format	Dimension (Shape)	Non-contiguous Tensor
  positions	Input	positions in the formula, used to select the positional encoding tensor.	Empty tensors are not supported. In rope mode, the shape is (numTokens). In mrope mode, the shape is (3, numTokens) or (4, numTokens).	INT64	ND	1-2	√
  queryIn	Input	The query in the formula, which is the first tensor to undergo rotary position encoding.	Empty tensors are not supported. Must be a 2D tensor with shape (numTokens, numQHeads*headSize).	BFLOAT16, FLOAT16, FLOAT32	ND	2	√
  keyIn	Input	The second tensor on which rotary position encoding is to be performed.	Empty tensors are not supported. Must be a 2D tensor with shape (numTokens, numKHeads*headSize).	BFLOAT16, FLOAT16, FLOAT32	ND	2	√
  cosSinCache	Input	Represents the position encoding tensor involved in the computation.	Empty tensors are not supported. Must be a 2D tensor with the shape (maxSeqLen, rotaryDim), where maxSeqLen indicates the maximum sequence length processed by the model, and rotaryDim indicates the dimension of the rotary position embedding.	BFLOAT16, FLOAT16, FLOAT32	ND	2	√
  mropeSection	Input	mropeSection in the formula, used to integrate the input position encoding tensor information in mrope mode.	Inputting the mropeSection attribute indicates that mrope mode is enabled. If mrope mode is not enabled (i.e., rope mode), the input is nullptr.	aclIntArray	-	-	-
  headSize	Input	Dimension size of each attention head.	-	INT64	-	-	-
  isNeoxStyle	Input	Indicates whether to use the GPT-NeoX computation mode.	true indicates the GPT-NeoX style computation mode. false indicates the GPT-J style computation mode.	BOOL	-	-	-
  cacheMode	Input	Indicates whether to concatenate cos and sin in a segmented or interleaved manner.	0 indicates segmented. 1 indicates interleaved.	INT64	-	-	-
  queryOut	Output	Result of applying rotary position encoding to query.	The data type is the same as query. Must be a 2D tensor with shape (numTokens, numQHeads*headSize).	FLOAT32, FLOAT16, BFLOAT16	ND	2	×
  keyOut	Output	Result of applying rotary position encoding to key.	Has the same data type as key. Must be a 2D tensor with shape (numTokens, numKHeads*headSize).	FLOAT32, FLOAT16, BFLOAT16	ND	2	×
  workspaceSize	Output	Returns the workspace size that the user needs to apply for on the Device side.	-	-	-	-	-
  executor	Output	Returns the op executor, which contains the operator computation flow.	-	-	-	-	-

• 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	A required input, required output, or required attribute passed in is a null pointer.
  ACLNN_ERR_PARAM_INVALID	161002	The data type or data format of the input or output is not within the supported range.
  ACLNN_ERR_INNER_TILING_ERROR	561002	The shape information of multiple input tensors does not match.
  		The shape information between the input attributes and the input tensors does not match.
  ACLNN_ERR_INNER_TILING_ERROR	361001	query or key is not 64B-aligned.
  		rotaryDim > headSize.

aclnnRopeWithSinCosCacheV2

• Parameters:

  Parameter	Input/Output	Description
  workspace	Input	Workspace memory address applied for on the Device side.
  workspaceSize	Input	Workspace size applied for on the Device side, obtained from the first-phase API aclnnRopeWithSinCosCacheV2GetWorkspaceSize.
  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:

  • aclnnRopeWithSinCosCacheV2 defaults to a deterministic implementation.

• queryIn, keyIn, and cosSinCache only support 2-dimensional shape input.

• The data types of queryIn, keyIn, and cosSinCache inputs must be consistent.

• headSize: Must be a multiple of 32 when the data type is BFLOAT16 or FLOAT16, and a multiple of 16 when the data type is FLOAT32.

• rotaryDim: Always less than or equal to headSize; must be a multiple of 32 when the data type is BFLOAT16 or FLOAT16, and a multiple of 16 when the data type is FLOAT32; in mrope mode, the cumulative sum of all elements in mropeSection must equal half of the rotaryDim value.

• The value of the input tensor positions must be less than maxSeqLen of dimension 0 of cosSinCache.

• In mrope mode, mropeSection: Currently supports only [16, 24, 24], [24, 20, 20], [8, 12, 12], and [16, 16, 16, 16].

• In mrope mode, cacheMode supports only 0 and 1. When mropeSection is [16, 16, 16, 16], only 0 is supported.

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/level2/aclnn_rope_with_sin_cos_cache_v2.h"
#include <iostream>

#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;
}

void PrintOutResult(std::vector<int64_t> &shape, void **deviceAddr) {
  auto size = GetShapeSize(shape);
  std::vector<float> resultData(size, 0);
  auto ret = aclrtMemcpy(
      resultData.data(), resultData.size() * sizeof(resultData[0]), *deviceAddr,
      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 );
  for (int64_t i = 0; i < size; i++) {
    LOG_PRINT("mean result[%ld] is: %f\n", i, resultData[i]);
  }
}

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 allocate memory on the device side.
  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 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);

  // 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);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("Init acl failed. ERROR: %d\n", ret);
            return ret);

  // 2. Construct the inputs and outputs. Customize the construction based on the API interface.
  std::vector<int64_t> positionsShape = {2};
  std::vector<int64_t> queryInShape = {2, 64};
  std::vector<int64_t> keyInShape = {2, 64};
  std::vector<int64_t> cosSinCacheShape = {2, 32};
  std::vector<int64_t> queryOutShape = {2, 64};
  std::vector<int64_t> keyOutShape = {2, 64};
  void* positionsDeviceAddr = nullptr;
  void* queryInDeviceAddr = nullptr;
  void* keyInDeviceAddr = nullptr;
  void* cosSinCacheDeviceAddr = nullptr;
  void* queryOutDeviceAddr = nullptr;
  void* keyOutDeviceAddr = nullptr;

  aclTensor* positions = nullptr;
  aclTensor* queryIn = nullptr;
  aclTensor* keyIn = nullptr;
  aclTensor* cosSinCache = nullptr;
  int64_t headSize = 32;
  bool isNeoxStyle = true;
  int64_t cacheMode = 1;
  aclTensor *queryOut = nullptr;
  aclTensor *keyOut = nullptr;

  std::vector<int64_t> positionsHostData = {0, 1};
  std::vector<float> queryInHostData = {74, 54, 84, 125, 23, 78, 37, 72, 27, 98, 34, 107, 29, 23, 54, 60, 70, 49,
                                        119, 54, 29, 54, 41, 99, 27, 62, 5, 46, 108, 39, 24, 123, 33, 82, 6, 40, 88,
                                        24, 6, 116, 38, 119, 110, 5, 30, 79, 87, 18, 29, 100, 90, 24, 21, 93, 63, 68,
                                        34, 112, 119, 48, 74, 43, 85, 64, 14, 49, 128, 59, 18, 37, 123, 76, 14, 63, 10,
                                        39, 107, 124, 79, 16, 17, 76, 80, 47, 90, 41, 58, 82, 75, 80, 69, 37, 74, 36, 54,
                                        26, 32, 54, 13, 100, 105, 15, 13, 69, 122, 26, 94, 59, 29, 14, 60, 8, 24, 17, 45,
                                        33, 107, 122, 63, 111, 75, 128, 68, 31, 105, 6, 82, 99};
  std::vector<float> keyInHostData = {112, 32, 66, 114, 69, 31, 117, 122, 77, 57, 78, 119, 115, 25, 54, 27, 122, 65, 15, 85,
                                      33, 16, 36, 6, 95, 15, 43, 6, 66, 91, 14, 101, 78, 51, 110, 74, 56, 30, 127, 61, 53, 29,
                                      32, 65, 114, 77, 26, 116, 89, 38, 75, 14, 96, 91, 87, 34, 25, 42, 57, 26, 51, 43, 23, 42,
                                      40, 17, 98, 117, 53, 75, 68, 75, 38, 41, 115, 76, 67, 22, 76, 10, 24, 46, 85, 54, 61, 114,
                                      10, 59, 6, 123, 58, 10, 115, 9, 13, 58, 66, 120, 23, 30, 83, 13, 11, 76, 18, 82, 57, 4,
                                      117, 105, 8, 73, 127, 5, 91, 56, 12, 125, 20, 3, 104, 40, 46, 18, 89, 63, 99, 104};
  std::vector<float> cosSinCacheHostData = {112, 32, 66, 114, 69, 31, 117, 122, 77, 57, 78, 119, 115, 25, 54, 27, 122, 65, 15, 85,
                                      33, 16, 36, 6, 95, 15, 43, 6, 66, 91, 14, 101, 78, 51, 110, 74, 56, 30, 127, 61, 53, 29,
                                      32, 65, 114, 77, 26, 116, 89, 38, 75, 14, 96, 91, 87, 34, 25, 42, 57, 26, 51, 43, 23, 42};
  std::vector<float> queryOutHostData = {0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0};
  std::vector<float> keyOutHostData = {0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0};

  ret = CreateAclTensor(positionsHostData, positionsShape,
                        &positionsDeviceAddr, aclDataType::ACL_INT64,
                        &positions);
  CHECK_RET(ret == ACL_SUCCESS, return ret);
  ret = CreateAclTensor(queryInHostData, queryInShape, &queryInDeviceAddr,
                      aclDataType::ACL_FLOAT, &queryIn);
  CHECK_RET(ret == ACL_SUCCESS, return ret);
  ret = CreateAclTensor(keyInHostData, keyInShape, &keyInDeviceAddr,
                      aclDataType::ACL_FLOAT, &keyIn);
  CHECK_RET(ret == ACL_SUCCESS, return ret);
  ret = CreateAclTensor(cosSinCacheHostData, cosSinCacheShape, &cosSinCacheDeviceAddr,
                      aclDataType::ACL_FLOAT, &cosSinCache);
  CHECK_RET(ret == ACL_SUCCESS, return ret);

  ret = CreateAclTensor(queryOutHostData, queryOutShape, &queryOutDeviceAddr, aclDataType::ACL_FLOAT,
                        &queryOut);
  CHECK_RET(ret == ACL_SUCCESS, return ret);
  ret = CreateAclTensor(keyOutHostData, keyOutShape, &keyOutDeviceAddr, aclDataType::ACL_FLOAT,
                        &keyOut);
  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 aclnnRopeWithSinCosCacheV2.
  ret = aclnnRopeWithSinCosCacheV2GetWorkspaceSize(positions, queryIn, keyIn, cosSinCache, nullptr, headSize, isNeoxStyle, cacheMode,
                                               queryOut, keyOut, &workspaceSize, &executor);
  CHECK_RET(
      ret == ACL_SUCCESS,
      LOG_PRINT("aclnnRopeWithSinCosCacheV2GetWorkspaceSize 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 aclnnRopeWithSinCosCacheV2.
  ret = aclnnRopeWithSinCosCacheV2(workspaceAddr, workspaceSize, executor, stream);
  CHECK_RET(ret == ACL_SUCCESS,
            LOG_PRINT("aclnnRopeWithSinCosCacheV2 failed. ERROR: %d\n", ret);
            return ret);

  // 4. (Boilerplate) Synchronously 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 device memory to host memory. Modify based on the specific API definition.
  PrintOutResult(queryOutShape, &queryOutDeviceAddr);
  PrintOutResult(keyOutShape, &keyOutDeviceAddr);

  // 6. Release aclTensor and aclScalar. Modify based on the specific API definition.
  aclDestroyTensor(positions);
  aclDestroyTensor(queryIn);
  aclDestroyTensor(keyIn);
  aclDestroyTensor(cosSinCache);
  aclDestroyTensor(queryOut);
  aclDestroyTensor(keyOut);

  // 7. Release device resources.
  aclrtFree(positionsDeviceAddr);
  aclrtFree(queryInDeviceAddr);
  aclrtFree(keyInDeviceAddr);
  aclrtFree(cosSinCacheDeviceAddr);
  aclrtFree(queryOutDeviceAddr);
  aclrtFree(keyOutDeviceAddr);

  if (workspaceSize > 0) {
    aclrtFree(workspaceAddr);
  }
  aclrtDestroyStream(stream);
  aclrtResetDevice(deviceId);
  aclFinalize();

  return 0;
}