aclnnStridedSliceAssignV2

📄 View Source Code

Applicable Products

Function

StridedSliceAssign is a tensor slice assignment operation that assigns the content of the inputValue tensor to a specified position in the target tensor varRef.

Function Prototype

Each operator is divided into a two-phase API. You must first call the aclnnStridedSliceAssignV2GetWorkspaceSize API to obtain the workspace size required for computation and the executor that contains the operator computation process, and then call the aclnnStridedSliceAssignV2 API to perform the computation.

aclnnStatus aclnnStridedSliceAssignV2GetWorkspaceSize(
    aclTensor         *varRef,
    const aclTensor   *inputValue,
    const aclIntArray *begin,
    const aclIntArray *end,
    const aclIntArray *strides,
    const aclIntArray *axesOptional,
    uint64_t          *workspaceSize,
    aclOpExecutor    **executor)

aclnnStatus aclnnStridedSliceAssignV2(
    void          *workspace,
    uint64_t       workspaceSize,
    aclOpExecutor *executor,
    aclrtStream    stream)

aclnnStridedSliceAssignV2GetWorkspaceSize

• Parameters:

  Parameter	Input/Output	Description	Instruction	Data Type	Data Format	Dimension (Shape)	Non-Contiguous Tensor
  varRef (aclTensor*)	Input/Output	Input tensor.	-	FLOAT16, FLOAT, BFLOAT16, INT32, INT64, DOUBLE, INT8	ND	1-8	√
  inputValue (aclTensor*)	Input	Input axis.	The shape must be consistent with the slice shape computed from varRef.	FLOAT16, FLOAT, BFLOAT16, INT32, INT64, DOUBLE, INT8	ND	-	√
  begin (aclIntArray*)	Input	Start index of the slice position.	-	INT64	ND	-	-
  end (aclIntArray*)	Input	End index of the slice position.	-	INT64	ND	-	-
  strides (aclIntArray*)	Input	Slice stride.	strides must be positive, and the stride corresponding to the last dimension of varRef must be 1.	INT64	ND	-	-
  axesOptinal（aclIntArray*）	Input	Optional parameter, the axis of the slice.	-	INT64	ND	-	-
  workspaceSize (uint64_t*)	Output	Returns the workspace size to be requested on the Device side.	-	-	-	-	-
  (aclOpExecutor**)	Output	Returns the op executor, which contains the operator computation flow.	-	-	-	-	-

• Return value

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

  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, out, or dim parameter is a null pointer.
  ACLNN_ERR_PARAM_INVALID	161002	The data types of the input and output are not within the supported range.

aclnnStridedSliceAssignV2

• Parameters:

  Parameter	Input/Output	Description
  workspace	Input	Address of the workspace memory applied for on the Device side.
  workspaceSize	Input	Size of the workspace applied for on the Device side, obtained from the first-phase API aclnnStridedSliceAssignV2GetWorkspaceSize.
  executor	Input	Operator executor, which contains the operator computation process.
  stream	Input	The stream for executing the task.

• Return value

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

Constraints

• Deterministic computation:

  • aclnnStridedSliceAssignV2 defaults to a deterministic implementation. The formula for the i-th dimension of inputValue's shape is: $inputValueShape[i] = \lceil\frac{end[i] - begin[i]}{strides[i]} \rceil$, where $\lceil x\rceil$ represents rounding up $x$. $end$ and $begin$ are values adjusted by special values. The adjustment method is: when $end[i] < 0$, $end[i]=varShape[i] + end[i]$; if $end[i] < 0$ still holds, then $end[i] = 0$; when $end[i] > varShape[i]$, $end[i] = varShape[i]$. The same applies to $begin$.

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_strided_slice_assign_v2.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 data from the host to the device memory by calling 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 by calling 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. For details, see the ACL API list.
  // Enter 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. Customize the construction based on the API.
  std::vector<int64_t> varRefShape = {4, 3};
  std::vector<int64_t> inputValueShape = {2, 2};
  std::vector<int64_t> sliceShape = {2};

  void* varRefDeviceAddr = nullptr;
  void* inputValueDeviceAddr = nullptr;

  aclTensor* varRef = nullptr;
  aclTensor* inputValue = nullptr;

  std::vector<float> varRefHostData = {0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11};
  std::vector<float> inputValueHostData = {-1, -2, -3, -4};
  std::vector<int64_t> beginData = {1, 0};
  std::vector<int64_t> endData = {4, 2};
  std::vector<int64_t> stridesData = {2, 1};
  std::vector<int64_t> axesData = {0, 1};

  // Create varRef aclTensor.
  ret = CreateAclTensor(varRefHostData, varRefShape, &varRefDeviceAddr, aclDataType::ACL_FLOAT, &varRef);
  CHECK_RET(ret == ACL_SUCCESS, return ret);
  // Create inputValue aclTensor.
  ret = CreateAclTensor(inputValueHostData, inputValueShape, &inputValueDeviceAddr, aclDataType::ACL_FLOAT, &inputValue);
  CHECK_RET(ret == ACL_SUCCESS, return ret);
  // Create begin aclIntArray.
  aclIntArray *begin = aclCreateIntArray(beginData.data(), beginData.size());
  // Create the end aclIntArray.
  aclIntArray *end = aclCreateIntArray(endData.data(), endData.size());
  // Create the strides aclIntArray.
  aclIntArray *strides = aclCreateIntArray(stridesData.data(), stridesData.size());
  // Create the axes aclTensor.
  aclIntArray *axes = aclCreateIntArray(axesData.data(), axesData.size());

  // 3. Call the CANN operator library API. Replace with the specific API.
  uint64_t workspaceSize = 0;
  aclOpExecutor* executor;
  // Call the first-phase API of aclnnStridedSliceAssignV2.
  ret = aclnnStridedSliceAssignV2GetWorkspaceSize(varRef, inputValue, begin, end, strides, axes, &workspaceSize, &executor);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnStridedSliceAssignV2GetWorkspaceSize 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 aclnnStridedSliceAssignV2.
  ret = aclnnStridedSliceAssignV2(workspaceAddr, workspaceSize, executor, stream);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnStridedSliceAssignV2 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 side memory to the host side. Modify based on the specific API definition.
  auto size = GetShapeSize(varRefShape);
  std::vector<float> resultData(size, 0);
  ret = aclrtMemcpy(resultData.data(), resultData.size() * sizeof(resultData[0]), varRefDeviceAddr, 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(varRef);
  aclDestroyTensor(inputValue);
  aclDestroyIntArray(begin);
  aclDestroyIntArray(end);
  aclDestroyIntArray(strides);
  aclDestroyIntArray(axes);

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