aclnnPolar

Applicable Products

Function

• Operator function: Converts the polar coordinates corresponding to the absolute value input and angle into Cartesian coordinates, producing a complex tensor out.

• Formula:

  $$out = abs*cos(angle) + abs*sin(angle)*j$$

Function Prototype

Each operator is divided into a two-phase API. You must first call the "aclnnPolarGetWorkspaceSize" API to obtain the workspace size required for computation and the executor that encapsulates the operator computation flow, and then call the "aclnnPolar" API to perform the computation.

• aclnnStatus aclnnPolarGetWorkspaceSize(const aclTensor* input, const aclTensor* angle, aclTensor* out,uint64_t* workspaceSize, aclOpExecutor** executor)

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

aclnnPolarGetWorkspaceSize

• Parameters:

• input (aclTensor*, computation input): Input tensor, representing abs in the formula. The data type supports FLOAT. Non-contiguous tensors are supported. The data format supports ND. The maximum dimension is 8.

• angle (aclTensor*, computation input): Input tensor, representing angle in the formula. The data type must be the same as input. Non-contiguous tensors are supported. The data format supports ND. The dimensions must be consistent with input.

• out (aclTensor*, computation output): Output tensor, representing out in the formula. The data type supports COMPLEX64. Non-contiguous tensors are supported. The data format supports ND. The dimensions must be consistent with input.

• workspaceSize (uint64_t*, output parameter): Returns the workspace size to be allocated on the Device side.

  • executor (aclOpExecutor**, output parameter): Returns the op executor, which includes computation.

• Return value

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

The first-phase API completes input parameter validation and reports an error in the following scenarios:
Returns 161001 (ACLNN_ERR_PARAM_NULLPTR): 1. input, angle, or out passed is a null pointer.
Returns 161002 (ACLNN_ERR_PARAM_INVALID): 1. The Data Type of input and angle is not within the supported range.
                                      2. The Data Types of input and angle are inconsistent.
                                      3. The Data Type of out is not COMPLEX64.
                                      4. The number of dimensions of input, angle, or out exceeds 8 or they are inconsistent.

aclnnPolar

• Parameters:

  • workspace (void*, input parameter): Device-side allocated workspace memory address.

  • workspaceSize (uint64_t, input parameter): Device-side allocated workspace size, obtained from the first-phase API aclnnPolarGetWorkspaceSize.

  • executor (aclOpExecutor*, input parameter): Op executor, which includes the computation process of the operator.

  • stream (aclrtStream, input parameter): Stream on which the task is executed.

• Return value

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

Constraints

• Deterministic computation:

  • aclnnPolar 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_polar.h"
#include <complex>

#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);
  // 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);

  // 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. 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> inputShape = {1, 2};
  std::vector<int64_t> angleShape = {1, 2};
  std::vector<int64_t> outShape = {1, 2};
  void* inputDeviceAddr = nullptr;
  void* angleDeviceAddr = nullptr;
  void* outDeviceAddr = nullptr;
  aclTensor* input = nullptr;
  aclTensor* angle = nullptr;
  aclTensor* out = nullptr;
  std::vector<float> inputHostData = {1, 2};
  std::vector<float> angleHostData = {1, 2};
  std::vector<std::complex<float>> outHostData = {1, 2};
  // Create the input aclTensor.
  ret = CreateAclTensor(inputHostData, inputShape, &inputDeviceAddr, aclDataType::ACL_FLOAT, &input);
  CHECK_RET(ret == ACL_SUCCESS, return ret);
  // Create the angle aclTensor.
  ret = CreateAclTensor(angleHostData, angleShape, &angleDeviceAddr, aclDataType::ACL_FLOAT, &angle);
  CHECK_RET(ret == ACL_SUCCESS, return ret);
  // Create the out aclTensor.
  ret = CreateAclTensor(outHostData, outShape, &outDeviceAddr, aclDataType::ACL_COMPLEX64, &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 aclnnPolar.
  ret = aclnnPolarGetWorkspaceSize(input, angle, out, &workspaceSize, &executor);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnPolarGetWorkspaceSize failed. ERROR: %d\n", ret); return ret);
  // Allocate device memory based on the workspaceSize computed 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 aclnnPolar second-phase API.
  ret = aclnnPolar(workspaceAddr, workspaceSize, executor, stream);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnPolar 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 values and copy the results from the device memory to the host memory. Modify based on the specific API definition.
  auto size = GetShapeSize(outShape);
  std::vector<std::complex<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++) {
   //The first number in the output is the real part, and the second number is the imaginary part.
   std::cout << "result[" << i << "]: " <<resultData[i] << std::endl;
  }

  // 6. Release aclTensor and aclIntArray. Modify based on the specific API definition.
  aclDestroyTensor(input);
  aclDestroyTensor(angle);
  aclDestroyTensor(out);

  // 7. Release device resources.
  aclrtFree(inputDeviceAddr);
  aclrtFree(angleDeviceAddr);
  aclrtFree(outDeviceAddr);
  if (workspaceSize > 0) {
    aclrtFree(workspaceAddr);
  }
  aclrtDestroyStream(stream);
  aclrtResetDevice(deviceId);
  aclFinalize();

  return 0;
}