aclnnMseLossOut

📄 View Source Code

Applicable Products

Function

• Description: Computes the mean squared error between each element in the input x and the target y. reduction specifies the reduction to apply to the output, supporting 'none', 'mean', and 'sum'. 'mean' indicates that the output will be reduced along axis 0 to compute the mean, and 'sum' indicates that the output will be reduced along axis 0 to compute the sum.

• Formula:

  When reduction is none,

  $$\ell(x, y) = L = \{l_1,\dots,l_N\}^\top, \quad l_n = \left( x_n - y_n \right)^2,$$

  where $x$ is self, $y$ is target, and $N$ is the batch size. If reduction is not none, then:

  $$\ell(x, y) = \begin{cases} \operatorname{mean}(L), & \text{if reduction} = \text{'mean';}\\ \operatorname{sum}(L), & \text{if reduction} = \text{'sum'.} \end{cases}$$

Function Prototype

Each operator is divided into a two-phase API. The "aclnnMseLossOutGetWorkspaceSize" API must be called first to obtain the workspace size required for computation and the executor that encapsulates the operator computation flow. Then, the "aclnnMseLossOut" API is called to perform the computation.

aclnnStatus aclnnMseLossOutGetWorkspaceSize(
    const aclTensor* self,
    const aclTensor* target,
    int64_t          reduction,
    aclTensor*       out,
    uint64_t*        workspaceSize,
    aclOpExecutor**  executor)

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

aclnnMseLossOutGetWorkspaceSize

• Parameters:

  Parameter	Input/Output	Description	Instruction	Data Type	Data Format	Dimension (Shape)	Non-contiguous Tensor
  self (aclTensor*)	Input	Input x in the formula.	The shape must satisfy the broadcast relationship with target. The data type and the data type of target satisfy the data type deduction rules (see Conversion Relationship).	FLOAT, FLOAT16, BFLOAT16	ND	1-8	√
  target (aclTensor*)	Input	Input y in the formula.	The shape must satisfy the broadcast relationship with self. The data type and self satisfy the data type deduction rules (see conversion relationship).	FLOAT, FLOAT16, BFLOAT16	ND	1-8	√
  reduction (int64_t)	Input	Specifies the reduction to apply to the output, i.e., the parameter reduction in the formula.	Supports 0 (none) | 1 (mean) | 2 (sum). 'none' means no reduction is applied. 'mean' means the sum of the output is divided by the number of elements in the output. 'sum' means the output is summed.	INT64	-	-	√
  out (aclTensor*)	Output	Output ℓ(x,y) in the formula.	The data type must be a convertible data type after deduction between self and target (see Conversion Relationship). When the value of reduction is 0, the shape of out is consistent with the shape after broadcast of self and target; when the value of reduction is not 0, the shape of out supports 0 dimensions.	FLOAT, FLOAT16, BFLOAT16	-	1-8	√
  workspaceSize (uint64_t*)	Output	Returns the workspace size to be applied on the Device side.	-	-	-	-	-
  executor (aclOpExecutor**)	Output	Returns the operator executor, which includes the computation process.	-	-	-	-	-

• 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 Value	Return Code	Description
  ACLNN_ERR_PARAM_NULLPTR	161001	The self, target, or out is a null pointer.
  ACLNN_ERR_PARAM_INVALID	161002	The data type of self, target, or out is not within the supported range.
  		The shapes of self and target cannot be broadcast.
  		The shape of self or target exceeds 8 dimensions.
  		The reduction value is not within the range of 0 to 2.
  		When the reduction value is 0, the shape of self and target after broadcast does not match the shape of out.
  		When the value of reduction is 1 or 2, the dimension of out is greater than 0.

aclnnMseLossOut

• Parameters:

  Parameter	Input/Output	Description
  workspace	Input	Memory address of the workspace applied on the Device side.
  workspaceSize	Input	Size of the workspace applied on the Device side, obtained from the first-phase API aclnnMseLossOutGetWorkspaceSize.
  executor	Input	Operator executor, which includes the computation flow of the operator.
  stream	Input	Stream that specifies the execution task.

• Return value

  aclnnStatus: return code. For details, see aclnn Return Code.

Constraints

• Deterministic computation:

  • aclnnMseLossOut 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_mse_loss_out.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 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 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 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. See the ACL API manual.
  // Set 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> selfShape = {2, 2};
  std::vector<int64_t> targetShape = {2, 2};
  std::vector<int64_t> outShape = {2};
  void* selfDeviceAddr = nullptr;
  void* targetDeviceAddr = nullptr;
  void* outDeviceAddr = nullptr;
  aclTensor* self = nullptr;
  aclTensor* target = nullptr;
  aclTensor* out = nullptr;
  std::vector<float> selfHostData = {0, 1, 2, 3};
  std::vector<float> targetHostData = {1, 1, 1, 1};
  std::vector<float> outHostData(2, 0);
  // Create the self aclTensor.
  ret = CreateAclTensor(selfHostData, selfShape, &selfDeviceAddr, aclDataType::ACL_FLOAT, &self);
  CHECK_RET(ret == ACL_SUCCESS, return ret);
  // Create the target aclTensor.
  ret = CreateAclTensor(targetHostData, targetShape, &targetDeviceAddr, aclDataType::ACL_FLOAT, &target);
  CHECK_RET(ret == ACL_SUCCESS, return ret);
  // Create the out aclTensor.
  ret = CreateAclTensor(outHostData, outShape, &outDeviceAddr, aclDataType::ACL_FLOAT, &out);
  CHECK_RET(ret == ACL_SUCCESS, return ret);
  // Create the reduction.
  int64_t reduction = 1;

  // 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 aclnnMseLossOut.
  ret = aclnnMseLossOutGetWorkspaceSize(self, target, reduction, out, &workspaceSize, &executor);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnMseLossOutGetWorkspaceSize 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 aclnnMseLossOut.
  ret = aclnnMseLossOut(workspaceAddr, workspaceSize, executor, stream);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnMseLossOut failed. ERROR: %d\n", ret); return ret);

  // 4. (Boilerplate) Synchronously 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 memory. 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. Destroy aclTensor and aclScalar. Modify based on the specific API definition.
  aclDestroyTensor(self);
  aclDestroyTensor(target);
  aclDestroyTensor(out);

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

  return 0;
}