aclnnMaxPool3dWithArgmaxBackward

📄 View Source Code

Applicable Products

Function

Performs backward propagation of the forward max pooling operation aclnnMaxPool3dWithArgmax, backfilling gradients to the coordinates of the maximum value in each window, with accumulation at identical coordinates.

Function Prototype

Each operator is divided into a two-phase API. You must first call the "aclnnMaxPool3dWithArgmaxBackwardGetWorkspaceSize" API to obtain the workspace size required for computation and the executor that contains the operator computation process, and then call the "aclnnMaxPool3dWithArgmaxBackward" API to perform the computation.

aclnnStatus aclnnMaxPool3dWithArgmaxBackwardGetWorkspaceSize(
  const aclTensor   *gradOutput,
  const aclTensor   *self,
  const aclTensor   *indices,
  const aclIntArray *kernelSize,
  const aclIntArray *stride,
  const aclIntArray *padding,
  const aclIntArray *dilation,
  bool               ceilMode,
  aclTensor         *gradInput,
  uint64_t          *workspaceSize,
  aclOpExecutor     **executor)

aclnnStatus aclnnMaxPool3dWithArgmaxBackward(
  void          *workspace,
  uint64_t       workspaceSize,
  aclOpExecutor *executor,
  aclrtStream    stream)

aclnnMaxPool3dWithArgmaxBackwardGetWorkspaceSize

• Parameters:

  Parameter	Input/Output	Description	Instruction	Data Type	Data Format	Dimension (Shape)	Non-contiguous Tensor
  gradOutput	Input	Gradient output from the previous step during backward propagation.	Same shape as the forward output, and same data format as self.	FLOAT32, FLOAT16, BFLOAT16	ND	4-5	√
  self	Input	Input data of the forward pass.	-	FLOAT32, FLOAT16, BFLOAT16	ND	4-5	√
  indices	Input	Index positions of the maximum elements in the forward input.	-	INT32, INT64	ND	4-5	√
  kernelSize	Input	Sliding window size used in the pooling operation.	Length of 1 (kD = kH = kW) or 3 (kD, kH, kW).	INT64	-	-	-
  stride	Input	Stride of the sliding window.	Length of 0 (sD = kD, sH = kH, sW = kW), 1 (sD = sH = sW), or 3 (sD, sH, sW).	INT64	-	-	-
  padding	Input	Specifies the number of zero-padding layers in the D, H, and W directions of the input.	Length of 1 (padD = padH = padW) or 3 (padD, padH, padW).	INT64	-	-	-
  dilation	Input	Controls the spacing between elements in the window.	Length of 1 or 3, with a value of only 1.	INT64	-	-	-
  ceilMode	Input	Rounding method used when computing the output shape.	If True, rounds up when computing the output shape; if False, rounds down.	BOOL	-	-	-
  gradInput	Output	Gradient output from backward propagation.	The shape and data format are consistent with self.	BFLOAT16, FLOAT16, FLOAT32	ND	4-5	√
  workspaceSize	Output	Returns the workspace size to be requested on the Device side.	-	-	-	-	-
  executor	Output	Returns the operator executor, which contains the operator computation flow.	-	-	-	-	-

  • Atlas A3 training products/Atlas A3 inference products, Atlas A2 training products/Atlas A2 inference products: The INT64 data type is not supported for indices. depth height width cannot exceed the maximum int32 value.

• 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 or indices is a null pointer.
  ACLNN_ERR_PARAM_INVALID	161002	The data type of gradOutput, self, indices, or gradInput is not within the supported range.
  		The data format of gradOutput, self, indices, or gradInput is not within the supported range.
  		The shape of gradOutput is inconsistent with that of indices, or the shape of self is inconsistent with that of gradInput.
  		The length of kernelSize is neither 1 nor 3.
  		A value in kernelSize is less than or equal to 0.
  		The length of stride is not 0, 1, or 3.
  		A value in stride is less than or equal to 0.
  		The length of padding is not 1 or 3.
  		A value in padding is less than 0 or greater than kernelSize/2.
  		The length of dilation is not 1 or 3.
  		The platform is not supported.

aclnnMaxPool3dWithArgmaxBackward

• 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 aclnnMaxPool3dWithArgmaxBackwardGetWorkspaceSize.
  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:

  • aclnnMaxPool3dWithArgmaxBackward defaults to a non-deterministic implementation. Deterministic computation can be enabled through aclrtCtxSetSysParamOpt.

• Unsupported type description:

  • DOUBLE: The instruction does not support DOUBLE.

  • Whether empty tensors are supported: empty input yields empty output is not supported.

• Boundary value scenario description:

  • When the input is Inf, the output is Inf.

  • When the input is NaN, the output is NaN.

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_max_pool3d_with_argmax_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: 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 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 aclCreateTensor 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.
  // Fill in the deviceId based on your actual device.
  int32_t deviceId = 0;
  aclrtStream stream;
  auto ret = Init(deviceId, &stream);
  // Handle the check based on your needs.
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("Init acl failed. ERROR: %d\n", ret); return ret);

  // 2. Construct inputs and outputs. Customize the construction based on the API interface.
  std::vector<int64_t> gradOutShape = {1, 1, 1, 1, 1};
  std::vector<int64_t> selfShape = {1, 1, 2, 2, 2};
  std::vector<int64_t> indicesShape = {1, 1, 1, 1, 1};
  std::vector<int64_t> gradInShape = {1, 1, 2, 2, 2};
  std::vector<int64_t> kernelSizeData = {2, 2, 2};
  std::vector<int64_t> strideData = {2, 2, 2};
  std::vector<int64_t> paddingData = {0, 0, 0};
  std::vector<int64_t> dilationData = {1, 1, 1};
  void* gradOutDeviceAddr = nullptr;
  void* selfDeviceAddr = nullptr;
  void* indicesDeviceAddr = nullptr;
  void* gradInDeviceAddr = nullptr;
  aclTensor* gradOut = nullptr;
  aclTensor* self = nullptr;
  aclTensor* indices = nullptr;
  aclTensor* gradIn = nullptr;
  std::vector<float> gradOutHostData = {0.4757};
  std::vector<float> selfHostData = {0.0850, -0.5147, -0.0212, -0.5654, -0.3222, 0.5847, 1.7510, 0.9954};
  std::vector<int32_t> indicesHostData = {6};
  std::vector<float> gradInHostData = {0, 0, 0, 0, 0, 0, 0, 0};

  // Create gradOut aclTensor.
  ret = CreateAclTensor(gradOutHostData, gradOutShape, &gradOutDeviceAddr, aclDataType::ACL_FLOAT, &gradOut);
  CHECK_RET(ret == ACL_SUCCESS, return ret);
  // Create self aclTensor.
  ret = CreateAclTensor(selfHostData, selfShape, &selfDeviceAddr, aclDataType::ACL_FLOAT, &self);
  CHECK_RET(ret == ACL_SUCCESS, return ret);
  // Create the indices aclTensor.
  ret = CreateAclTensor(indicesHostData, indicesShape, &indicesDeviceAddr, aclDataType::ACL_INT32, &indices);
  CHECK_RET(ret == ACL_SUCCESS, return ret);
  // Create the gradIn aclTensor.
  ret = CreateAclTensor(gradInHostData, gradInShape, &gradInDeviceAddr, aclDataType::ACL_FLOAT, &gradIn);
  CHECK_RET(ret == ACL_SUCCESS, return ret);

  // Create the input array.
  aclIntArray* kernelSize = aclCreateIntArray(kernelSizeData.data(), 3);
  aclIntArray* stride = aclCreateIntArray(strideData.data(), 3);
  aclIntArray* padding = aclCreateIntArray(paddingData.data(), 3);
  aclIntArray* dilation = aclCreateIntArray(dilationData.data(), 3);
  const bool ceilMode = false;

  uint64_t workspaceSize = 0;
  aclOpExecutor* executor;

  // Example of aclnnMaxPool3dWithArgmaxBackward API call.
  // 3. Call the CANN operator library API. Replace it with the specific API name.
  // Call the aclnnMaxPool3dWithArgmaxBackwardGetWorkspaceSize first-phase API.
  ret = aclnnMaxPool3dWithArgmaxBackwardGetWorkspaceSize(gradOut, self, indices, kernelSize, stride, padding, dilation, ceilMode, gradIn, &workspaceSize, &executor);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnMaxPool3dWithArgmaxBackwardGetWorkspaceSize 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 aclnnMaxPool3dWithArgmaxBackward second-phase API.
  ret = aclnnMaxPool3dWithArgmaxBackward(workspaceAddr, workspaceSize, executor, stream);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnMaxPool3dWithArgmaxBackward 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(gradInShape);
  std::vector<float> resultData(size, 0);
  ret = aclrtMemcpy(resultData.data(), resultData.size() * sizeof(resultData[0]), gradInDeviceAddr,
                    size * sizeof(resultData[0]), ACL_MEMCPY_DEVICE_TO_HOST);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("copy gradIn 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(gradOut);
  aclDestroyTensor(self);
  aclDestroyTensor(indices);
  aclDestroyTensor(gradIn);

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