aclnnForeachSqrt

📄 View Source Code

Applicable Products

Function

• Description: Performs square root operation on each tensor in the input tensor list.

• Formula:

  $$x = [{x_0}, {x_1}, ... {x_{n-1}}]\\ y = [{y_0}, {y_1}, ... {y_{n-1}}]\\$$ $$y_i =\sqrt{x_i} (i=0,1,...n-1)$$

Function Prototype

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

aclnnStatus aclnnForeachSqrtGetWorkspaceSize(
  const aclTensorList    *x,
  const aclTensorList    *out,
  uint64_t               *workspaceSize,
  aclOpExecutor         **executor)

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

aclnnForeachSqrtGetWorkspaceSize

• Parameters

  Parameter	Input/Output	Description	Instruction	Data Type	Data Format	Dimension (Shape)	Non-Contiguous Tensor
  x (aclTensorList*)	Input	List of input tensors for the square root operation, corresponding to `x` in the formula.	Empty tensors are supported. All tensors in this parameter must have the same data type.	FLOAT32, FLOAT16, BFLOAT16	ND	0-8	√
  out (aclTensorList*)	Output	Indicates the output tensor list for the square root operation, corresponding to `y` in the formula.	Supports empty tensors. All tensors in this parameter have the same data type. The data type and data format are consistent with those of the input parameter `x`.	FLOAT32, FLOAT16, 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 process.	-	-	-	-	-

  • Atlas A2 training products/Atlas A2 inference products, Atlas A3 training products/Atlas A3 inference products: The shape size of input parameter x is less than or equal to the shape size of output out.

  • Ascend 950PR/Ascend 950DT: The shape size of input parameter x is the same as the shape size of output out. The maximum number of tensors supported by both input parameter x and output out is 50.

• 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 x or out is a null pointer.
  ACLNN_ERR_PARAM_INVALID	161002	The data type of x or out is not supported.
  		The data types of x and out are inconsistent.
  ACLNN_ERR_PARAM_INVALID	561002	The shapes of x and out do not satisfy the constraints.
  		The data types of tensors in x or out are inconsistent.
  		A tensor in x or out has more than 8 dimensions.

aclnnForeachSqrt

• Parameters

  Parameter	Input/Output	Description
  workspace	Input	Address of the workspace memory applied on the device side.
  workspaceSize	Input	Size of the workspace applied on the device side, obtained from the first-phase API aclnnForeachSqrtGetWorkspaceSize.
  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:

  • aclnnForeachSqrt 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_foreach_sqrt.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 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 data to 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);

  // 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 aclCreateTensor.
  *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 inputs and outputs. Customize the construction based on the API interface.
  std::vector<int64_t> selfShape1 = {2, 3};
  std::vector<int64_t> selfShape2 = {1, 3};
  std::vector<int64_t> outShape1 = {2, 3};
  std::vector<int64_t> outShape2 = {1, 3};
  void* input1DeviceAddr = nullptr;
  void* input2DeviceAddr = nullptr;
  void* out1DeviceAddr = nullptr;
  void* out2DeviceAddr = nullptr;
  aclTensor* input1 = nullptr;
  aclTensor* input2 = nullptr;
  aclTensor* out1 = nullptr;
  aclTensor* out2 = nullptr;
  std::vector<float> input1HostData = {1, 2, 3, 4, 5, 6};
  std::vector<float> input2HostData = {7, 8, 9};
  std::vector<float> out1HostData(6, 0);
  std::vector<float> out2HostData(3, 0);

  // Create the input1 aclTensor.
  ret = CreateAclTensor(input1HostData, selfShape1, &input1DeviceAddr, aclDataType::ACL_FLOAT, &input1);
  CHECK_RET(ret == ACL_SUCCESS, return ret);

  // Create the input2 aclTensor.
  ret = CreateAclTensor(input2HostData, selfShape2, &input2DeviceAddr, aclDataType::ACL_FLOAT, &input2);
  CHECK_RET(ret == ACL_SUCCESS, return ret);

  // Create the out1 aclTensor.
  ret = CreateAclTensor(out1HostData, outShape1, &out1DeviceAddr, aclDataType::ACL_FLOAT, &out1);
  CHECK_RET(ret == ACL_SUCCESS, return ret);

  // Create the out2 aclTensor.
  ret = CreateAclTensor(out2HostData, outShape2, &out2DeviceAddr, aclDataType::ACL_FLOAT, &out2);
  CHECK_RET(ret == ACL_SUCCESS, return ret);

  std::vector<aclTensor*> tempInput{input1, input2};
  aclTensorList* tensorListInput = aclCreateTensorList(tempInput.data(), tempInput.size());
  std::vector<aclTensor*> tempOutput{out1, out2};
  aclTensorList* tensorListOutput = aclCreateTensorList(tempOutput.data(), tempOutput.size());

  // 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 aclnnForeachSqrt.
  ret = aclnnForeachSqrtGetWorkspaceSize(tensorListInput, tensorListOutput, &workspaceSize, &executor);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnForeachSqrtGetWorkspaceSize failed. ERROR: %d\n", ret); return ret);
  // Allocate 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 aclnnForeachSqrt.
  ret = aclnnForeachSqrt(workspaceAddr, workspaceSize, executor, stream);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnForeachSqrt 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 memory. Modify based on the specific API definition.
  auto size = GetShapeSize(outShape1);
  std::vector<float> out1Data(size, 0);
  ret = aclrtMemcpy(out1Data.data(), out1Data.size() * sizeof(out1Data[0]), out1DeviceAddr,
                    size * sizeof(out1Data[0]), ACL_MEMCPY_DEVICE_TO_HOST);
  for (int64_t i = 0; i < size; i++) {
    LOG_PRINT("out1 result[%ld] is: %f\n", i, out1Data[i]);
  }

  size = GetShapeSize(outShape2);
  std::vector<float> out2Data(size, 0);
  ret = aclrtMemcpy(out2Data.data(), out2Data.size() * sizeof(out2Data[0]), out2DeviceAddr,
                    size * sizeof(out2Data[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("out2 result[%ld] is: %f\n", i, out2Data[i]);
  }

  // 6. Release aclTensor. Modify based on the specific API definition.
  aclDestroyTensorList(tensorListInput);
  aclDestroyTensorList(tensorListOutput);

  // 7. Release device resources. Modify based on the specific API definition.
  aclrtFree(input1DeviceAddr);
  aclrtFree(input2DeviceAddr);
  aclrtFree(out1DeviceAddr);
  aclrtFree(out2DeviceAddr);
  if (workspaceSize > 0) {
    aclrtFree(workspaceAddr);
  }
  aclrtDestroyStream(stream);
  aclrtResetDevice(deviceId);
  aclFinalize();
  return 0;
}