aclnnAdaptiveAvgPool3d

📄 View Source Code

Applicable Products

Function

Performs 3D adaptive average pooling on the tensor self given the specified 3D output shape information (outputSize). Unlike aclnnAvgPool3d, aclnnAdaptiveAvgPool3d only requires specifying the output size, and it automatically derives the kernel size and corresponding stride.

Function Prototype

Each operator is divided into a two-phase API. The "aclnnAdaptiveAvgPool3dGetWorkspaceSize" API must be called first to obtain the workspace size required for computation and the executor that encapsulates the operator computation flow. Then, the "aclnnAdaptiveAvgPool3d" API is called to perform the computation.

aclnnStatus aclnnAdaptiveAvgPool3dGetWorkspaceSize(
  const aclTensor   *self,
  const aclIntArray *outputSize,
  aclTensor         *out,
  uint64_t          *workspaceSize,
  aclOpExecutor     **executor)

aclnnStatus aclnnAdaptiveAvgPool3d(
  void          *workspace,
  uint64_t       workspaceSize,
  aclOpExecutor *executor,
  aclrtStream    stream)

aclnnAdaptiveAvgPool3dGetWorkspaceSize

• Parameters:

  Parameter	Input/Output	Description	Instruction	Data Type	Data Format	Dimension (Shape)	Non-Contiguous Tensor
  self	Input	Represents the target tensor to be computed.	-	FLOAT32, FLOAT16, BFLOAT16	NCDHW, ND	4-5	√
  outputSize	Input	Specifies the output shape size in the DHW dimensions.	The array length is always 3.	INT64	-	-	-
  out	Output	Output tensor, with the same data type as self.	The shape of out must be consistent with the shape derived from the shape of self and outputSize.	FLOAT32, FLOAT16, BFLOAT16	NCDHW, ND	4-5	√
  workspaceSize	output	Returns the workspace size to be applied for on the Device side.	-	-	-	-	-
  executor	Output	Returns the op executor, which contains the operator computation flow.	-	-	-	-	-

  • Atlas inference products: The data type of the parameters self and out does not support BFLOAT16.

• 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 Code	Error Code	Description
  ACLNN_ERR_PARAM_NULLPTR	161001	The passed self, outputSize, or out is a null pointer.
  ACLNN_ERR_PARAM_INVALID	161002	The data type or data format of self is not within the supported range.
  		The data types of self and out are inconsistent.
  		The dimension of self is not 4 or 5.
  		A dimension of the shape of self or out is not greater than 0.
  		The length of outputSize is not 3.
  		The NC dimensions of self and out are inconsistent.
  		The shape of out is inconsistent with the shape derived from the shape of self and outputSize.

aclnnAdaptiveAvgPool3d

• Parameters:

  Parameter	Input/Output	Description
  workspace	Input	Address of the workspace memory applied on the device side.
  workspaceSize	Input	Size of the workspace applied on the device side, obtained through the first-phase API aclnnAdaptiveAvgPool3dGetWorkspaceSize.
  executor	Input	Op executor, which contains the operator computation flow.
  stream	Input	Specifies the stream on which the task is executed.

• Return value

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

Constraints

• Deterministic computation:

  • aclnnAdaptiveAvgPool3d defaults to a deterministic implementation.

• Shape description:

  • self.shape = (N, C, Din, Hin, Win) or (C, Din, Hin, Win)

  • outputSize = [Dout, Hout, Wout]

  • out.shape = (N, C, Dout, Hout, Wout) or (C, Dout, Hout, Wout)

Example

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

#include <cstdio>
#include <iostream>
#include <vector>
#include "acl/acl.h"
#include "aclnnop/aclnn_adaptive_avg_pool3d.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: 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-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 the 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 your 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. Customize the construction based on the API.
  std::vector<int64_t> inputShape = {2, 1, 2, 2, 4};
  std::vector<int64_t> outShape = {2, 1, 2, 2, 2};
  std::vector<int64_t> outSize = {2, 2, 2};
  void* inputDeviceAddr = nullptr;
  void* outDeviceAddr = nullptr;
  aclTensor* input = nullptr;
  aclTensor* out = nullptr;
  aclIntArray* outputSize = aclCreateIntArray(outSize.data(), 3);
  std::vector<float> inputHostData = {1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16};
  std::vector<float> outHostData(16, 0);

  // Create the input aclTensor.
  ret = CreateAclTensor(inputHostData, inputShape, &inputDeviceAddr, aclDataType::ACL_FLOAT, &input);
  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 first-phase API of aclnnAdaptiveAvgPool3d.
  ret = aclnnAdaptiveAvgPool3dGetWorkspaceSize(input, outputSize, out, &workspaceSize, &executor);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnAdaptiveAvgPool3dGetWorkspaceSize 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 aclnnAdaptiveAvgPool3d.
  ret = aclnnAdaptiveAvgPool3d(workspaceAddr, workspaceSize, executor, stream);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnAdaptiveAvgPool3d failed. ERROR: %d\n", ret); return ret);

  // 4. (Boilerplate) Wait for the task execution to complete synchronously.
  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 aclTensor. Modify based on the specific API definition.
  aclDestroyTensor(input);
  aclDestroyTensor(out);

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

  return 0;
}