aclnnSigmoidBackward

Applicable Products

Product	Supported
Ascend 950PR/Ascend 950DT	√
Atlas A3 training products/Atlas A3 inference products	√
Atlas A2 training products/Atlas A2 inference products	√
Atlas 200I/500 A2 inference products	×
Atlas inference products	√
Atlas training products	√

Function

Description: Completes the backward propagation of Sigmoid, and computes the gradient input of Sigmoid based on the Sigmoid backward propagation gradient and the forward output.
Formula:
$out = {\frac{1} {1+{e}^{-input}}}$ $grad\_input = grad\_output * \sigma(x) * (1 - \sigma(x))$

Where $\sigma(x)$ is the forward output of the Sigmoid function, and $\sigma(x)*(1-\sigma(x))$ is the derivative of the Sigmoid function.

Function Prototype

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

aclnnStatus aclnnSigmoidBackwardGetWorkspaceSize(
  const aclTensor    *gradOutput,
  const aclTensor    *output,
  aclTensor          *gradInput,
  uint64_t           *workspaceSize,
  aclOpExecutor     **executor)

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

aclnnSigmoidBackwardGetWorkspaceSize

Parameters:

Parameter	Input/Output	Description	Instruction	Data Type	Data Format	Dimension (shape)	Non-contiguous Tensor
gradOutput (aclTensor*)	Input	Gradient of the loss function with respect to the Sigmoid output, i.e., grad_output in the formula.	Supports empty tensors. The shape must satisfy the broadcast relationship with output.	FLOAT, FLOAT16, BFLOAT16, DOUBLE, COMPLEX64, COMPLEX128	ND	1-8	√
output (aclTensor*)	Input	Output of the forward Sigmoid, i.e., out in the formula.	Supports empty tensors. The shape must satisfy the broadcast relationship with gradOutput	FLOAT, FLOAT16, BFLOAT16, DOUBLE, COMPLEX64, COMPLEX128	ND	1-8	√
gradInput (aclTensor*)	Output	Gradient value of self, corresponding to grad_input in the formula.	The shape must satisfy the broadcast relationship with gradOutput and output. The data type must be a data type to which gradOutput and output can be converted (see Conversion Relationship).	FLOAT, FLOAT16, BFLOAT16, DOUBLE, COMPLEX64, COMPLEX128	ND	1-8	√
workspaceSize (uint64_t*)	Output	Returns the workspace size to be applied for on the Device side.	-	-	-	-	-
executor (aclOpExecutor**)	Output	Returns the op executor, which contains the operator computation flow.	-	-	-	-	-

Atlas inference products and Atlas training products: FLOAT, FLOAT16, DOUBLE, COMPLEX64, and COMPLEX128 are supported.

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 gradOutput, output, or gradInput is a null pointer.
ACLNN_ERR_PARAM_INVALID	161002	The data type or data format of gradOutput, output, or gradInput is not within the supported range.
		The shapes of gradOutput and output do not meet the broadcast condition.
		The shape of gradInput is inconsistent with the broadcast result of gradOutput and output.
		The shape dimension of gradOutput or output exceeds 8.

aclnnSigmoidBackward

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 aclnnSigmoidBackwardGetWorkspaceSize.
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:
- aclnnSigmoidBackward defaults to a deterministic implementation.

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_sigmoid_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-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 host-side data to device-side 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 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. Refer to the acl API manual.
  // Fill in 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. Customize the construction based on the API.
  std::vector<int64_t> gradOutputShape = {2, 2};
  std::vector<int64_t> outputShape = {2, 2};
  std::vector<int64_t> gradInputShape = {2, 2};
  void* gradOutputDeviceAddr = nullptr;
  void* outputDeviceAddr = nullptr;
  void* gradInputDeviceAddr = nullptr;
  aclTensor* gradOutput = nullptr;
  aclTensor* output = nullptr;
  aclTensor* gradInput = nullptr;
  std::vector<float> gradOutputHostData = {1, 1, 1, 1};
  std::vector<float> outputHostData = {1, 2, 3, 4};
  std::vector<float> gradInputHostData(4, 0);
  // Create gradOutput aclTensor.
  ret = CreateAclTensor(gradOutputHostData, gradOutputShape, &gradOutputDeviceAddr, aclDataType::ACL_FLOAT, &gradOutput);
  CHECK_RET(ret == ACL_SUCCESS, return ret);
  // Create output aclTensor.
  ret = CreateAclTensor(outputHostData, outputShape, &outputDeviceAddr, aclDataType::ACL_FLOAT, &output);
  CHECK_RET(ret == ACL_SUCCESS, return ret);
  // Create gradInput aclTensor.
  ret = CreateAclTensor(gradInputHostData, gradInputShape, &gradInputDeviceAddr, aclDataType::ACL_FLOAT, &gradInput);
  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 aclnnSigmoidBackward.
  ret = aclnnSigmoidBackwardGetWorkspaceSize(gradOutput, output, gradInput, &workspaceSize, &executor);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnSigmoidBackwardGetWorkspaceSize 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 aclnnSigmoidBackward.
  ret = aclnnSigmoidBackward(workspaceAddr, workspaceSize, executor, stream);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnSigmoidBackward failed. ERROR: %d\n", ret); return ret);

  // 4. (Boilerplate) Synchronously wait for the 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 memory to the host memory. Modify this based on the specific API definition.
  auto size = GetShapeSize(gradInputShape);
  std::vector<float> resultData(size, 0);
  ret = aclrtMemcpy(resultData.data(), resultData.size() * sizeof(resultData[0]), gradInputDeviceAddr,
                    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(gradOutput);
  aclDestroyTensor(output);
  aclDestroyTensor(gradInput);
  // 7. Release device resources. Set parameters based on the specific API definition.
  aclrtFree(gradOutputDeviceAddr);
  aclrtFree(outputDeviceAddr);
  aclrtFree(gradInputDeviceAddr);
  if (workspaceSize > 0) {
    aclrtFree(workspaceAddr);
  }
  aclrtDestroyStream(stream);
  aclrtResetDevice(deviceId);
  aclFinalize();
  return 0;
}