aclnnThresholdBackward

📄 View Source Code

Applicable Products

Function

• Description: Computes the backward propagation of aclnnThreshold.

• Formula:

  $$output = \begin{cases} gradOutput(i) & \text{if } self(i) > threshold \\ 0 & \text{otherwise} \end{cases}$$

Function Prototype

Each operator is divided into a two-phase API. You must first call the "aclnnThresholdBackwardGetWorkspaceSize" API to obtain the input parameters and calculate the required workspace size based on the process, and then call the "aclnnThresholdBackward" API to perform the computation.

aclnnStatus aclnnThresholdBackwardGetWorkspaceSize(
  const aclTensor *gradOutput,
  const aclTensor *self,
  const aclScalar *threshold,
  aclTensor       *out,
  uint64_t        *workspaceSize,
  aclOpExecutor  **executor)

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

aclnnThresholdBackwardGetWorkspaceSize

• Parameters:

  Parameter	Input/Output	Description	Instruction	Data Type	Data Format	Dimension (Shape)	Non-contiguous Tensor
  gradOutput (aclTensor*)	Input	gradOutput in the formula.	Supports empty tensors. The dtype must be consistent with self. The shape must satisfy the broadcast relationship with self.	FLOAT, BFLOAT16, FLOAT16, INT32, INT8, UINT8, INT64	ND	0-8	√
  self (aclTensor*)	Input	self in the formula.	The data type of the input must satisfy the data type deduction rule with the data type of gradOutput (see Deduction Relationship).	FLOAT, BFLOAT16, FLOAT16, INT32, INT8, UINT8, INT64	ND	0-8	√
  threshold (aclScalar*)	Input	threshold in the formula.	Supports empty tensors. The dtype must be the same as that of gradOutput The shape must satisfy the broadcast relationship with gradOutput	FLOAT, BFLOAT16, FLOAT16, INT32, INT8, UINT8, INT64	ND	0-8	√
  out (aclTensor*)	Output	The out in the formula.	The dtype must be the same as self. The shape must be equal to the shape after broadcasting self and gradOutput	FLOAT, BFLOAT16, FLOAT16, INT32, INT8, UINT8, INT64	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 process.	-	-	-	-	-

  • Atlas A2 training products/Atlas A2 inference products, Atlas A3 training products/Atlas A3 inference products: The INT64 data type is not supported.

  • Atlas inference products and Atlas training products: The BFLOAT16 and INT64 data types are not supported.

  • Ascend 950PR/Ascend 950DT: This product is supported only when the value is 0.0.

• 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 or self is a null pointer.
  ACLNN_ERR_PARAM_INVALID	161002	The data type of gradOutput or self is not within the supported range.
  		The shape of gradOutput or self exceeds 8 dimensions.
  		The data types of gradOutput, out, and self are inconsistent.

aclnnThresholdBackward

• Parameters:

  Parameter	Input/Output	Description
  workspace	Input	Address of the workspace applied on the device.
  workspaceSize	Input	Size of the workspace applied on the device, obtained through the first-phase API aclnnThresholdBackwardGetWorkspaceSize.
  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:

  • aclnnThresholdBackward 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_threshold_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 data from the host to the 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);

  // Compute 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 using 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.
  // Set 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> selfShape = {2, 2};
  std::vector<int64_t> gradOutputShape = {2, 2};
  std::vector<int64_t> outShape = {2, 2};
  void* selfDeviceAddr = nullptr;
  void* gradOutputDeviceAddr = nullptr;
  void* outDeviceAddr = nullptr;
  aclTensor* self = nullptr;
  aclTensor* gradOutput = nullptr;
  aclScalar* threshold = nullptr;
  aclTensor* out = nullptr;
  std::vector<float> selfHostData = {0.2, 1.2, 2.2, 3.2};
  std::vector<float> gradOutputHostData = {4.5, 4.4, 4.3, 4.2};
  std::vector<float> outHostData = {0.0, 0.0, 0.0, 0.0};
  float thresholdValue = 1.0f;
  // Create the self aclTensor.
  ret = CreateAclTensor(selfHostData, selfShape, &selfDeviceAddr, aclDataType::ACL_FLOAT, &self);
  CHECK_RET(ret == ACL_SUCCESS, return ret);
  // Create the gradOutput aclTensor.
  ret = CreateAclTensor(gradOutputHostData, gradOutputShape, &gradOutputDeviceAddr, aclDataType::ACL_FLOAT, &gradOutput);
  CHECK_RET(ret == ACL_SUCCESS, return ret);
  // Create the threshold aclScalar.
  threshold = aclCreateScalar(&thresholdValue, aclDataType::ACL_FLOAT);
  CHECK_RET(threshold != nullptr, 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 actual API name.
  uint64_t workspaceSize = 0;
  aclOpExecutor* executor;
  // Call the first-phase API of aclnnThresholdBackward.
  ret = aclnnThresholdBackwardGetWorkspaceSize(gradOutput, self, threshold, out, &workspaceSize, &executor);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnThresholdBackwardGetWorkspaceSize 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 aclnnThresholdBackward.
  ret = aclnnThresholdBackward(workspaceAddr, workspaceSize, executor, stream);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnThresholdBackward failed. ERROR: %d\n", ret); return ret);

  // 4. (Boilerplate) Wait synchronously 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 side memory to the host side. 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 and aclScalar. Modify based on the specific API definition.
  aclDestroyTensor(self);
  aclDestroyTensor(gradOutput);
  aclDestroyScalar(threshold);
  aclDestroyTensor(out);

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