Documentation
Download

aclnnAcos&aclnnInplaceAcos

📄 View source code

Supported Products

ProductSupported
Atlas A3 training products/Atlas A3 inference products√
Atlas A2 training products/Atlas A2 inference products√
Atlas 200I/500 A2 inference products×
Atlas inference products√
Atlas training products√

Function Description

  • Description: Performs the arc cosine operation on each element of the input matrix and outputs the result.

  • Formula:

    outi=cos−1(inputi)out_{i}=cos^{-1}(input_{i})

Prototype

  • aclnnAcos and aclnnInplaceAcos implement the same function in different ways. Select a proper operator based on your requirements.

    • aclnnAcos: An output tensor object needs to be created to store the computation result.
    • aclnnInplaceAcos: No output tensor object needs to be created, and the computation result is written in place to the input tensor's memory.

  • Each operator has two-phase API calls. First, aclnnAcosGetWorkspaceSize or aclnnInplaceAcosGetWorkspaceSize is called to obtain the workspace size required for computation and the executor covering the operator computation process. Then, aclnnAcos or aclnnInplaceAcos is called to perform computation.

    • aclnnStatus aclnnAcosGetWorkspaceSize(const aclTensor* input, aclTensor* out, uint64_t* workspaceSize, aclOpExecutor** executor)
    • aclnnStatus aclnnAcos(void* workspace, uint64_t workspaceSize, aclOpExecutor* executor, const aclrtStream stream)
    • aclnnStatus aclnnInplaceAcosGetWorkspaceSize(aclTensor *inputRef, uint64_t *workspaceSize, aclOpExecutor **executor)
    • aclnnStatus aclnnInplaceAcos(void *workspace, uint64_t workspaceSize, aclOpExecutor *executor, const aclrtStream stream)

aclnnAcosGetWorkspaceSize

  • Parameters:

    • input (aclTensor*, computation input): aclTensor on the device. When its data type is INT8, INT16, INT32, INT64, UINT8, or BOOL, the data type is cast to FLOAT32 for computation, and the output is of the FLOAT32 type. It supports non-contiguous tensors. Its data format can be ND. For a non-contiguous tensor, its dimensions cannot exceed 8, and its shape must be the same as that of out.
      • Atlas A2 training products/Atlas A2 inference products and Atlas A3 training products/Atlas A3 inference products: The data type can be INT8, INT16, INT32, INT64, UINT8, BOOL, FLOAT, BFLOAT16, FLOAT16, or DOUBLE.
      • Atlas training products and Atlas inference products: The data type can be INT8, INT16, INT32, INT64, UINT8, BOOL, FLOAT, FLOAT16, or DOUBLE.
    • out (aclTensor*, computation output): aclTensor on the device. It supports non-contiguous tensors. Its data format can be ND. For a non-contiguous tensor, its dimensions cannot exceed 8, and its shape must be the same as that the input tensor.
      • Atlas A2 training products/Atlas A2 inference products and Atlas A3 training products/Atlas A3 inference products: The data type can be FLOAT, BFLOAT16, FLOAT16, or DOUBLE.

      Atlas training products and Atlas inference products: The data type can be FLOAT, FLOAT16, or DOUBLE.

    • workspaceSize (uint64_t*, output): size of the workspace to be allocated on the device.
    • executor (aclOpExecutor**, output): operator executor, covering the operator computation process.

  • Returns:

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

   The first-phase API implements input parameter verification. The following errors may be thrown:
 161001 (ACLNN_ERR_PARAM_NULLPTR): 1. The input or out parameter is a null pointer.
 161002 (ACLNN_ERR_PARAM_INVALID): 1. The data type of input or out is not supported.
                                      2. The shapes of input and out are inconsistent.
                                      3. The input or out parameter has more than 8 dimensions.

aclnnAcos

  • Parameters:

    • workspace (void*, input): address of the workspace to be allocated on the device.
    • workspaceSize (uint64_t, input): size of the workspace to be allocated on the device, which is obtained by calling aclnnAcosGetWorkspaceSize.
    • executor (aclOpExecutor*, input): operator executor, covering the operator computation process.
    • stream (aclrtStream, input): stream for executing the task.

  • Returns:

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

aclnnInplaceAcosGetWorkspaceSize

  • Parameters:

    • inputRef (aclTensor*, computation input/output): input/output tensor, that is, input and out in the formula. It is the aclTensor on the device. It supports non-contiguous tensors. Its data format can be ND. For a non-contiguous tensor, its dimensions cannot exceed 8.
      • Atlas A2 training products/Atlas A2 inference products and Atlas A3 training products/Atlas A3 inference products: The data type can be FLOAT, BFLOAT16, FLOAT16, or DOUBLE.

      Atlas training products and Atlas inference products: The data type can be FLOAT, FLOAT16, or DOUBLE.

    • workspaceSize (uint64_t*, input): size of the workspace to be allocated on the device.
    • executor (aclOpExecutor**, input): operator executor, covering the operator computation process.

  • Returns:

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

   The first-phase API implements input parameter verification. The following errors may be thrown:
 161001 (ACLNN_ERR_PARAM_NULLPTR): 1. inputRef is a null pointer.
 161002 (ACLNN_ERR_PARAM_INVALID): 1. The data type of inputRef is not supported.
                                      2. inputRef has more than 8 dimensions.

aclnnInplaceAcos

  • Parameters:

    • workspace (void*, input): address of the workspace to be allocated on the device.
    • workspaceSize (uint64_t, input): size of the workspace to be allocated on the device, which is obtained by calling aclnnInplaceAcosGetWorkspaceSize.
    • executor (aclOpExecutor*, input): operator executor, covering the operator computation process.
    • stream (aclrtStream, input): stream for executing the task.

  • Returns:

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

Constraints

  • Deterministic computation:
    • aclnnAcos and aclnnInplaceAcos each default to a deterministic implementation.

Example

The following example is for reference only. For details, see Compilation and Running Sample.

#include <iostream>
#include <vector>
#include "math.h"
#include "acl/acl.h"
#include "aclnnop/aclnn_acos.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 code 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 allocate memory on the device.
  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 the data from the host to the device.
  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 aclCreateTensor 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 code for device/stream initialization. For details, see the ACL API manual.
  // Set the device ID in use.
  int32_t deviceId = 0;
  aclrtStream stream;
  auto ret = Init(deviceId, &stream);
  // Customize the error handling as needed.
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("Init failed. ERROR: %d\n", ret); return ret);

  // 2. Construct the inputs and outputs based on the API definition.
  std::vector<int64_t> selfShape = {4, 2};
  std::vector<int64_t> outShape = {4, 2};
  void* selfDeviceAddr = nullptr;
  void* outDeviceAddr = nullptr;
  aclTensor* self = nullptr;
  aclTensor* out = nullptr;
  std::vector<double> selfHostData = {1, -1, 0, 0.5, -1.732/2, 12, NAN, -INFINITY};
  std::vector<double> outHostData = {0, 0, 0, 0, 0, 0, 0, 0};
  // Create a self aclTensor.
  ret = CreateAclTensor(selfHostData, selfShape, &selfDeviceAddr, aclDataType::ACL_DOUBLE, &self);
  CHECK_RET(ret == ACL_SUCCESS, return ret);
  // Create an out aclTensor.
  ret = CreateAclTensor(outHostData, outShape, &outDeviceAddr, aclDataType::ACL_DOUBLE, &out);
  CHECK_RET(ret == ACL_SUCCESS, return ret);

  uint64_t workspaceSize = 0;
  aclOpExecutor* executor;

  // aclnnAcos API call example
  // 3. Call the CANN operator library API.
  // Call the first-phase API of aclnnAcos.
  ret = aclnnAcosGetWorkspaceSize(self, out, &workspaceSize, &executor);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnAcosGetWorkspaceSize 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 aclnnAcos.
  ret = aclnnAcos(workspaceAddr, workspaceSize, executor, stream);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnAcos failed. ERROR: %d\n", ret); return ret);

  // 4. (Boilerplate code) Wait until the task execution is 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 to the host. Modify the code based on the API definition.
  auto size = GetShapeSize(outShape);
  std::vector<double> 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("%ld acos(%lf) = %lf\n", i, selfHostData[i], resultData[i]);
  }

  // aclnnInplaceAcos API call example
  // 3. Call the CANN operator library API.
  LOG_PRINT("\ntest aclnnInplaceAcos\n");
  // Call the first-phase API of aclnnInplaceAcos.
  ret = aclnnInplaceAcosGetWorkspaceSize(self, &workspaceSize, &executor);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnInplaceAcosGetWorkspaceSize failed. ERROR: %d\n", ret); return ret);
  // Allocate device memory based on the workspaceSize calculated by the first-phase API.
  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 aclnnInplaceAcos.
  ret = aclnnInplaceAcos(workspaceAddr, workspaceSize, executor, stream);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnInplaceAcos failed. ERROR: %d\n", ret); return ret);
  // 4. (Boilerplate code) Wait until the task execution is 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 to the host.
  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("%ld acos(%f) = %f\n", i, selfHostData[i], resultData[i]);
  }


  // 6. Destroy aclTensor. Modify the code based on the API definition.
  aclDestroyTensor(self);
  aclDestroyTensor(out);

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

  return 0;
}
This site uses cookies to improve your browsing experience. By continuing to browse this site, you agree to our use of cookies.View Details