aclnnSlice

📄 View Source Code

Applicable Products

Function

Extracts a sub-tensor $out$ from the input tensor $self$ along the specified dimension $dim$ based on the given range $[start, end]$ and stride $step$. $start$ and $end$ can take values outside $[0, self.shape[dim]]$. After being specified, they are converted to valid values using the following formula, assuming self.shape[dim] = N:

$out.shape$ differs from $self.shape$ only along the dim axis, and remains the same along other axes:

Function Prototype

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

aclnnStatus aclnnSliceGetWorkspaceSize(
    const aclTensor *self,
    int64_t         dim,
    int64_t         start,
    int64_t         end,
    int64_t         step,
    aclTensor       *out,
    uint64_t        *workspaceSize,
    aclOpExecutor   **executor)

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

aclnnSliceGetWorkspaceSize

• Parameters:

  Parameter	Input/Output	Description	Instruction	Data Type	Data Format	Dimension (Shape)	Non-contiguous Tensor
  self (aclTensor*)	Input.	Tensor self in the formula.	The data type of self must be the same as that of out.	FLOAT, FLOAT16, BFLOAT16, INT32, INT64, INT8, UINT8, BOOL	ND	1-8	√
  dim (int64_t)	Input	The parameter dim in the formula, which specifies the dimension.	The value range is [-self.dim(), self.dim() - 1].	INT64	ND	-	-
  start (int64_t)	Input	Tensor start in the formula, representing the starting index of the slice position.	-	INT64	ND	-	√
  end (int64_t)	Input	Tensor end in the formula, indicating the end index of the slice position.	-	INT64	ND	-	√
  step (int64_t)	Input	Tensor step in the formula, specifying the stride of the slice.	The value range must be greater than 0.	INT64	ND	-	√
  out (aclTensor*)	Output	Tensor out in the formula.	The shape satisfies the deduction rules in the formula.	Same as self.	ND	1-8	√
  workspaceSize (uint64_t*)	Output	Returns the workspace size to be allocated on the Device side.	-	-	-	-	-
  executor（aclOpExecutor**）	Output	Returns the op executor, which contains the operator computation flow.	-	-	-	-	-

  • Atlas training products: The BFLOAT16 data type is not supported.

• 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 Code	Error Code	Description
  ACLNN_ERR_PARAM_NULLPTR	161001	When the input self or out is a null pointer.
  ACLNN_ERR_PARAM_INVALID	161002	The data type of self or out is not within the supported range.
  		The shape dimension of self is 0 or greater than 8.
  		The value of dim is not within [-self.dim(), self.dim() - 1].
  		step is less than or equal to 0.
  		The data types of self and out are inconsistent.
  		The shape of out does not satisfy the deduction rules in the formula.

aclnnSlice

• 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, which is obtained by the first-phase API aclnnSliceGetWorkspaceSize.
  executor	Input	Operator executor, which contains the operator computation process.
  stream	Input	Stream that executes the task.

• Return value

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

Constraints

None.

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_slice.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 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);
  // Call aclrtMemcpy to copy host-side data to the device-side 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 input and output. Custom construction is required based on the API.
  std::vector<int64_t> selfShape = {4, 2};
  std::vector<int64_t> outShape = {2, 2};
  void* selfDeviceAddr = nullptr;
  void* outDeviceAddr = nullptr;
  aclTensor* self = nullptr;
  aclTensor* out = nullptr;
  std::vector<float> selfHostData = {0, 1, 2, 3, 4, 5, 6, 7};
  std::vector<float> outHostData = {0, 0, 0, 0};
  int64_t dim = 0;
  int64_t start = 1;
  int64_t end = 3;
  int64_t step = 1;
  // Create the self aclTensor.
  ret = CreateAclTensor(selfHostData, selfShape, &selfDeviceAddr, aclDataType::ACL_FLOAT, &self);
  CHECK_RET(ret == ACL_SUCCESS, return ret);
  // Create the out aclTensor.
  ret = CreateAclTensor(outHostData, outShape, &outDeviceAddr, aclDataType::ACL_FLOAT, &out);
  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 aclnnSlice first-phase API.
  ret = aclnnSliceGetWorkspaceSize(self, dim, start, end, step, out, &workspaceSize, &executor);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnSliceGetWorkspaceSize 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 aclnnSlice second-phase API.
  ret = aclnnSlice(workspaceAddr, workspaceSize, executor, stream);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnSlice failed. ERROR: %d\n", ret); return ret);

  // 4. (Boilerplate) Synchronously wait for the task 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 the device memory to the host memory. Modify based on the specific 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]);
  }

  // 6. Release the aclTensor. Modify based on the specific API definition.
  aclDestroyTensor(self);
  aclDestroyTensor(out);

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