Documentation
Download
文档中心
aclnnSwishBackward

aclnnSoftshrinkBackward

📄 View Source Code

Applicable Products

ProductSupported
Ascend 950PR/Ascend 950DTNo
Atlas A3 training products/Atlas A3 inference productsYes
Atlas A2 training products/Atlas A2 inference productsYes
Atlas 200I/500 A2 inference productsNo
Atlas inference productsNo
Atlas training productsYes

Function

  • Description: Completes the backward API of the Softshrink function.

  • Formula:

    • Softshrink forward computation formula:

      Softshrink(x)={x−λ, if x>λx+λ, if x<−λSoftshrink(x)= \begin{cases} x - {\lambda}, \ if \ x > {\lambda}\\ x + {\lambda}, \ if \ x < -{\lambda} \end{cases}

    • Softshrink backward propagation formula:

      gradInput={gradOutput, if x>λgradOutput, if x<−λ0, otherwisegradInput= \begin{cases} gradOutput, \ if \ x > \lambda \\ gradOutput, \ if \ x <-\lambda \\ 0, \ otherwise \end{cases}

Function Prototype

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

aclnnStatus aclnnSoftshrinkBackwardGetWorkspaceSize(
  const aclTensor* gradOutput,
  const aclTensor* self,
  const aclScalar* lambda,
  aclTensor*       gradInput,
  uint64_t*        workspaceSize,
  aclOpExecutor**  executor)
aclnnStatus aclnnSoftshrinkBackward(
  void*             workspace,
  uint64_t          workspaceSize,
  aclOpExecutor*    executor,
  const aclrtStream stream)

aclnnSoftshrinkBackwardGetWorkspaceSize

  • Parameters:

    Parameter Input/Output Description Instruction Data Type Data Format Dimension (Shape) Non-Contiguous Tensor
    gradOutput (aclTensor*) Input Gradient output from the previous step during backward propagation, serving as the input to this backward operator, represented as gradOutput in the formula.
    • Supports empty tensors.
    • The shape satisfies the broadcast relationship with self.
    • gradOutput, self, and gradInput have the same data type.
    		 FLOAT16, FLOAT, BFLOAT16 ND 0-8 √
    self (aclTensor*) Input Forward input value, i.e., x in the formula.
    • Supports empty tensors.
    • The shape and gradOutput satisfy the broadcast relationship.
    • The data type must be consistent with gradOutput
    		 FLOAT16, FLOAT, BFLOAT16 ND 0-8 √
    lambda (aclScalar*) Input Input λ in the formula. The data type supports common numeric types, such as FLOAT, and the value range must be greater than or equal to 0. - - - -
    gradInput（aclTensor*） Output Output parameter, corresponding to gradInput in the formula.
    • Supports empty tensors.
    • The shape must be consistent with the broadcast result of self and gradOutput
    • The shape and data type of gradInput are the same as those of self.
    		 FLOAT16, FLOAT, BFLOAT16 ND 0-8 √
    workspaceSize (uint64_t*) Output Returns the workspace size to be requested on the Device side. - - - - -
    executor (aclOpExecutor**) Output Returns the operator executor, which contains the operator computation flow. - - - - -
    • Atlas training products: The data type supports FLOAT16 and FLOAT.

  • 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, self, lambda, or gradInput is a null pointer.
    ACLNN_ERR_PARAM_INVALID 161002 The data types of gradOutput, self, and gradInput are not within the supported range.
    The shapes of self and gradOutput do not satisfy the broadcast rule.
    lambda is less than 0.
    The shape of gradInput is inconsistent with the broadcast result of self and gradOutput
    The dimensions of gradOutput, self, and gradInput are greater than 8.

aclnnSoftshrinkBackward

  • Parameters:

    Parameter Input/Output Description
    workspace Input Address of the workspace memory applied on the device.
    workspaceSize Input Size of the workspace applied on the device, obtained by the first-phase API aclnnSoftshrinkBackwardGetWorkspaceSize.
    executor Input Operator executor that 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:

    • aclnnSoftshrinkBackward 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_softshrink_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 shape_size = 1;
  for (auto i : shape) {
    shape_size *= i;
  }
  return shape_size;
}

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 data from the host to the device memory by calling 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. See the ACL API manual.
  // Set deviceId based on the actual device.
  int32_t deviceId = 0;
  aclrtStream stream;
  auto ret = Init(deviceId, &stream);
  // Handle based on your own needs.
  CHECK_RET(ret == 0, 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 = {4, 2};
  std::vector<int64_t> selfShape = {4, 2};
  std::vector<int64_t> gradInputShape = {4, 2};
  void* gradOutputDeviceAddr = nullptr;
  void* selfDeviceAddr = nullptr;
  void* gradInputDeviceAddr = nullptr;
  aclTensor* gradOutput = nullptr;
  aclTensor* self = nullptr;
  aclTensor* gradInput = nullptr;
  aclScalar* lambda = nullptr;
  std::vector<float> gradOutputHostData = {0, 1, 2, 3, 4, 5, 6, 7};
  std::vector<float> selfHostData = {1, 1, 1, 2, 1, 2, 3, 3};
  std::vector<float> gradInputHostData = {0, 0, 0, 0, 0, 0, 0, 0};
  float lambdaValue = 1.2f;
  // Create the gradOutput aclTensor.
  ret = CreateAclTensor(gradOutputHostData, gradOutputShape, &gradOutputDeviceAddr, aclDataType::ACL_FLOAT, &gradOutput);
  CHECK_RET(ret == ACL_SUCCESS, return ret);
  // Create the self aclTensor.
  ret = CreateAclTensor(selfHostData, selfShape, &selfDeviceAddr, aclDataType::ACL_FLOAT, &self);
  CHECK_RET(ret == ACL_SUCCESS, return ret);
  // lambda aclScalar
  lambda = aclCreateScalar(&lambdaValue, aclDataType::ACL_FLOAT);
  CHECK_RET(lambda != nullptr, return ret);
  // Create the 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.
  uint64_t workspaceSize = 0;
  aclOpExecutor* executor;
  // Call the first-phase API of aclnnSoftshrinkBackward.
  ret = aclnnSoftshrinkBackwardGetWorkspaceSize(gradOutput, self, lambda, gradInput, &workspaceSize, &executor);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnSoftshrinkBackwardGetWorkspaceSize 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 aclnnSoftshrinkBackward.
  ret = aclnnSoftshrinkBackward(workspaceAddr, workspaceSize, executor, stream);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnSoftshrinkBackward 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 memory to the host side. Modify 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(float),
                    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 and aclScalar. Modify based on the specific API definition.
  aclDestroyTensor(gradOutput);
  aclDestroyTensor(self);
  aclDestroyScalar(lambda);
  aclDestroyTensor(gradInput);

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

  return 0;
}
This site uses cookies to improve your browsing experience. By continuing to browse this site, you agree to our use of cookies.View Details