aclnnInplaceNormalTensor

📄 View Source Code

Applicable Products

Function

Fills the tensor with elements from a normal distribution parameterized by mean and std. Random numbers are drawn from a discrete normal distribution with the given mean and standard deviation std to fill the selfRef tensor. The mean is a base type float that contains the mean of the normal distribution associated with each output element. std is a base type float that contains the standard deviation of the normal distribution associated with each output element. The random number offset of this API is the sum of the offsetTensor value and offset.

Function Prototype

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

aclnnStatus aclnnInplaceNormalTensorGetWorkspaceSize(
  const aclTensor* selfRef,
  float            mean,
  float            std,
  const aclTensor* seedTensor,
  const aclTensor* offsetTensor,
  int64_t          offset,
  uint64_t*        workspaceSize,
  aclOpExecutor**  executor)

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

aclnnInplaceNormalTensorGetWorkspaceSize

• Parameters:

  Parameter	Input/Output	Description	Instruction	Data Type	Data Format	Dimension (Shape)	Non-Contiguous Tensor
  selfRef	Input/Output	Input/output tensor.	-	FLOAT32, FLOAT16, BFLOAT16, INT32, INT16, INT8, UINT8, INT64, BOOL, DOUBLE	ND	0-8 dimensions	√
  mean	Input	Represents the random mean.	-	-	-	-	-
  std	Input	Represents the standard deviation of the random numbers.	-	-	-	-	-
  seedTensor	Input.	Sets the seed value of the random number generator.	-	INT64	ND	[1]	√
  offsetTensor	Input	Specifies the offset of the random number operator as the accumulation result with the scalar offset.	-	INT64	ND	[1]	√
  offset	Input	Serves as the accumulator for offsetTensor.	-	-	-	-	-
  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 Codes.

  The first-phase API performs input parameter validation and returns an error in the following scenarios:

  Return Value	Error Code	Description
  ACLNN_ERR_PARAM_NULLPTR	161001	The input selfRef is a null pointer.
  ACLNN_ERR_PARAM_INVALID	161002	The data type of selfRef is not within the supported range.
  		The data types of std and mean do not meet the API input requirements.

aclnnInplaceNormalTensor

• Parameter Description:

  Parameter	Input/Output	Description
  workspace	Input	Device-side workspace memory address.
  workspaceSize	Input	Size of the device-side workspace, obtained by the first-phase API aclnnInplaceNormalTensorGetWorkspaceSize.
  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 Codes.

Constraints

None.

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_normal.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 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);
  // Call aclrtMemcpy to copy host-side data to device-side 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);

  // Compute the strides of the 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 the aclCreateTensor API 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. Refer to the ACL API manual.
  // Fill in the 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. Custom construction is required based on the API.
  std::vector<int64_t> selfShape = {2, 2};
  std::vector<int64_t> seedShape = {1};
  std::vector<int64_t> offsetShape = {1};
  float mean = 2.;
  float std = 1.;
  void* seedDeviceAddr = nullptr;
  aclTensor* seed = nullptr;
  void* offsetDeviceAddr = nullptr;
  aclTensor* offset = nullptr;
  int64_t offset2 = 102;
  void* selfDeviceAddr = nullptr;
  aclTensor* selfRef = nullptr;
  std::vector<float> selfHostData = {0.0, 0.0, 0.0, 0.0};
  std::vector<int64_t> seedHostData = {0};
  std::vector<int64_t> offsetHostData = {392};

  // Create self aclTensor.
  ret = CreateAclTensor(selfHostData, selfShape, &selfDeviceAddr, aclDataType::ACL_FLOAT, &selfRef);
  CHECK_RET(ret == ACL_SUCCESS, return ret);
  // Create seed aclTensor.
  ret = CreateAclTensor(seedHostData, seedShape, &seedDeviceAddr, aclDataType::ACL_INT64, &seed);
  CHECK_RET(ret == ACL_SUCCESS, return ret);
  // Create offset aclTensor.
  ret = CreateAclTensor(offsetHostData, offsetShape, &offsetDeviceAddr, aclDataType::ACL_INT64, &offset);
  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 aclnnInplaceNormalTensor.
  ret = aclnnInplaceNormalTensorGetWorkspaceSize(selfRef, mean, std, seed, offset, offset2, &workspaceSize, &executor);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnInplaceNormalTensorGetWorkspaceSize 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 aclnnInplaceNormalTensor.
  ret = aclnnInplaceNormalTensor(workspaceAddr, workspaceSize, executor, stream);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnInplaceNormalTensor 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 device-side memory to host-side memory. Modify based on the specific API definition.
  auto size = GetShapeSize(selfShape);
  std::vector<float> resultData(size, 0);
  ret = aclrtMemcpy(resultData.data(), resultData.size() * sizeof(resultData[0]), selfDeviceAddr,
                    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(selfRef);
  aclDestroyTensor(seed);
  aclDestroyTensor(offset);

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

  return 0;
}