aclnnAdaptiveAvgPool3dBackward

Applicable Products

📄 View Source Code

Function

Backward computation of aclnnAdaptiveAvgPool3d.

Function Prototype

Each operator is divided into a two-phase API. First call the "aclnnAdaptiveAvgPool3dBackwardGetWorkspaceSize" API to obtain the workspace size required for computation and the executor that contains the operator computation process, and then call the "aclnnAdaptiveAvgPool3dBackward" API to perform the computation.

aclnnStatus aclnnAdaptiveAvgPool3dBackwardGetWorkspaceSize(
  const aclTensor   *gradOutput,
  const aclTensor   *self,
  aclTensor         *out,
  uint64_t          *workspaceSize,
  aclOpExecutor     **executor)

aclnnStatus aclnnAdaptiveAvgPool3dBackward(
  void          *workspace,
  uint64_t       workspaceSize,
  aclOpExecutor *executor,
  aclrtStream    stream)

aclnnAdaptiveAvgPool3dBackwardGetWorkspaceSize

• Parameters:

  Parameter	Input/Output	Description	Instruction	Data Type	Data Format	Shape	Non-Contiguous Tensor
  gradOutput	Input	Gradient of the current node.	The data type is the same as self, and the NC dimensions are consistent with self.	FLOAT32, FLOAT16, BFLOAT16	NCDHW, ND	4-5	√
  self	Input	Leaf node.	-	FLOAT32, FLOAT16, BFLOAT16	NCDHW, ND	4-5	√
  out	Output	Gradient corresponding to the input leaf node.	-	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 operator 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 Code	Return Code	Description
  ACLNN_ERR_PARAM_NULLPTR	161001	The passed gradOutput, self, or out is a null pointer.
  ACLNN_ERR_PARAM_INVALID	161002	The data types and data formats of gradOutput and self are not within the supported range.
  		The data types of gradOutput, self, and out are inconsistent.
  		The number of dimensions of gradOutput, self, and out is not equal to 4 or 5.
  		The shapes of gradOutput, self, and out do not match.
  		A dimension of the shape of gradOutput or self is not greater than 0.
  		The data formats of gradOutput and self are inconsistent.
  		The NC dimensions are inconsistent.

aclnnAdaptiveAvgPool3dBackward

• 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 through the first-phase API aclnnAdaptiveAvgPool3dBackwardGetWorkspaceSize.
  executor	Input	Operator executor, which contains the operator computation flow.
  stream	Input	Stream that executes the task.

• Return value

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

Constraints

• Deterministic computation:

  • aclnnAdaptiveAvgPool3dBackward defaults to a non-deterministic implementation. It supports enabling deterministic computation through aclrtCtxSetSysParamOpt.

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 "math.h"
#include "acl/acl.h"
#include "aclnnop/aclnn_adaptive_avg_pool3d_backward.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 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 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];
  }

  // Create an aclTensor by calling aclCreateTensor.
  *tensor = aclCreateTensor(shape.data(), shape.size(), dataType, strides.data(), 0, aclFormat::ACL_FORMAT_ND,
                            shape.data(), shape.size(), *deviceAddr);
  return 0;
}

int main() {
  // 1. Initialize the device/stream. See the ACL API manual.
  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.
  std::vector<int64_t> yGradShape = {2, 2, 1, 1, 2};
  std::vector<int64_t> xShape = {2, 2, 1, 1, 4};
  std::vector<int64_t> xGradShape = {2, 2, 1, 1, 4};
  void* yGradDeviceAddr = nullptr;
  void* xDeviceAddr = nullptr;
  void* xGradDeviceAddr = nullptr;
  aclTensor* yGrad = nullptr;
  aclTensor* x = nullptr;
  aclTensor* xGrad = nullptr;
  std::vector<float> yGradHostData = {1, 2, 3, 4, 5, 6, 7, 8};
  std::vector<float> xHostData(GetShapeSize(xShape), 1);
  std::vector<float> xGradHostData(16, 0);
  // Create yGrad aclTensor.
  ret = CreateAclTensor(yGradHostData, yGradShape, &yGradDeviceAddr, aclDataType::ACL_FLOAT, &yGrad);
  CHECK_RET(ret == ACL_SUCCESS, return ret);
  // Create x aclTensor.
  ret = CreateAclTensor(xHostData, xShape, &xDeviceAddr, aclDataType::ACL_FLOAT, &x);
  CHECK_RET(ret == ACL_SUCCESS, return ret);
  // Create xGrad aclTensor.
  ret = CreateAclTensor(xGradHostData, xGradShape, &xGradDeviceAddr, aclDataType::ACL_FLOAT, &xGrad);
  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 aclnnAdaptiveAvgPool3dBackward.
  ret = aclnnAdaptiveAvgPool3dBackwardGetWorkspaceSize(yGrad, x, xGrad, &workspaceSize, &executor);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnAdaptiveAvgPool3dBackwardGetWorkspaceSize failed. ERROR: %d\n", ret); return ret);
  // Allocate 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 aclnnAdaptiveAvgPool3dBackward second-phase API.
  ret = aclnnAdaptiveAvgPool3dBackward(workspaceAddr, workspaceSize, executor, stream);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnAdaptiveAvgPool3dBackward failed. ERROR: %d\n", ret); return ret);

  // 4. 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 device memory to host memory.
  auto size = GetShapeSize(xGradShape);
  std::vector<float> resultData(size, 0);
  ret = aclrtMemcpy(resultData.data(), resultData.size() * sizeof(resultData[0]), xGradDeviceAddr,
                    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.
  aclDestroyTensor(yGrad);
  aclDestroyTensor(x);
  aclDestroyTensor(xGrad);

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

  return 0;
}