Documentation
Download

aclnnCos&aclnnInplaceCos

📄 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: Performs the cosine operation on each element of the input matrix and outputs the result.

  • Formula:

outi=cos(inputi)out_{i}=cos(input_{i})

Prototype

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

    • aclnnCos: An output tensor object needs to be created to store the computation result.
    • aclnnInplaceCos: No output tensor object needs to be created, and the computation result is stored in the memory of the input tensor.

  • Each operator has two-phase API calls. First, aclnnCosGetWorkspaceSize or aclnnInplaceCosGetWorkspaceSize is called to obtain the workspace size required for computation and the executor that contains the operator computation process. Then, aclnnCos or aclnnInplaceCos is called to perform computation.

aclnnStatus aclnnCosGetWorkspaceSize(
  const aclTensor *input, 
  aclTensor       *out, 
  uint64_t        *workspaceSize, 
  aclOpExecutor  **executor)
aclnnStatus aclnnCos(
  void             *workspace, 
  uint64_t          workspaceSize, 
  aclOpExecutor    *executor, 
  const aclrtStream stream)
aclnnStatus aclnnInplaceCosGetWorkspaceSize(
  aclTensor      *inputRef, 
  uint64_t       *workspaceSize, 
  aclOpExecutor **executor)
aclnnStatus aclnnInplaceCos(
  void             *workspace, 
  uint64_t          workspaceSize, 
  aclOpExecutor    *executor, 
  const aclrtStream stream)

aclnnCosGetWorkspaceSize

  • Parameters

    Name Input/Output Description Usage Notes Data Type Data Format Dimension (Shape) Non-contiguous Tensor
    input Input Input tensor.
    • If the type is INT8, INT16, INT32, INT64, UINT8, or BOOL, the data type is converted to FLOAT for computation, and the computation result is converted to the data type of out.
    • The number of non-contiguous tensor dimensions must not exceed 8, and the shape must be identical to that of out.
    		 INT8, INT16, INT32, INT64, UINT8, BOOL, FLOAT, FLOAT16, DOUBLE, COMPLEX64, COMPLEX128, BFLOAT16 ND - √
    out Output Output tensor. The number of non-contiguous tensor dimensions must not exceed 8, and the shape must be identical to that of input. FLOAT, FLOAT16, DOUBLE, COMPLEX64, COMPLEX128, BFLOAT16 ND - √
    workspaceSize Output Size of the workspace required to be allocated on the device. - - - - -
    executor Output Operator executor, containing the operator computation process. - - - - -
    • Atlas 200I/500 A2 inference products, Atlas inference products, and Atlas training products: The data type cannot be BFLOAT16.

  • Returns

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

    The first-phase API implements input parameter validation. The following error codes may be returned.

    Return Error Code Description
    ACLNN_ERR_PARAM_NULLPTR 161001 The passed input or output is a null pointer.
    ACLNN_ERR_PARAM_INVALID 161002 The data type of input or out is not supported.
    The shapes of input and out are inconsistent.
    The number of dimensions of input or out exceeds 8.

aclnnCos

  • Parameters

    Name Input/Output Description
    workspace Input Address of the workspace to be allocated on the device.
    workspaceSize Input Size of the workspace to be allocated on the device, which is obtained by calling the first-phase API aclnnCosGetWorkspaceSize.
    executor Input Operator executor, containing the operator computation process.
    stream Input Stream for executing the task.

  • Returns

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

aclnnInplaceCosGetWorkspaceSize

  • Parameters

    Name Input/Output Description Usage Notes Data Type Data Format Dimension (Shape) Non-contiguous Tensor
    inputRef Input/Output Input or output tensor. The number of non-contiguous tensor dimensions must not exceed 8. FLOAT, FLOAT16, DOUBLE, COMPLEX64, COMPLEX128, BFLOAT16 ND - √
    workspaceSize Output Size of the workspace required to be allocated on the device. - - - - -
    executor Output Operator executor, containing the operator computation process. - - - - -
    • Atlas 200I/500 A2 inference products, Atlas inference products, and Atlas training products: The data type cannot be BFLOAT16.

  • Returns

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

    The first-phase API implements input parameter validation. The following error codes may be returned.

    Return Error Code Description
    ACLNN_ERR_PARAM_NULLPTR 161001 The passed inputRef is a null pointer.
    ACLNN_ERR_PARAM_INVALID 161002 The data type of inputRef is not supported.
    The number of dimensions of inputRef exceeds 8.

aclnnInplaceCos

  • Parameters

    Name Input/Output Description
    workspace Input Address of the workspace to be allocated on the device.
    workspaceSize Input Size of the workspace to be allocated on the device, which is obtained by calling the first-phase API aclnnInplaceCosGetWorkspaceSize.
    executor Input Operator executor, containing the operator computation process.
    stream Input Stream for executing the task.

  • Returns

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

Constraints

  • Deterministic computation:

    • aclnnCos and aclnnInplaceCos default to a deterministic implementation.

  • Atlas training products, Atlas A2 training products/Atlas A2 inference products, and Atlas A3 training products/Atlas A3 inference products: The input values of the FLOAT, FLOAT16, and BFLOAT16 data types must be within the range of [-10^7, 10^7] to meet precision requirements. If this range is exceeded, precision is not guaranteed and you are advised to use the CPU for computation.

  • Atlas inference products and Atlas 200I/500 A2 inference products: The input values of the FLOAT and FLOAT16 data types must be within the range of [-65504, 65504] to meet precision requirements. If this range is exceeded, precision is not guaranteed and you are advised to use the CPU for computation.

Example

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

#include <iostream>
#include <vector>
#include "acl/acl.h"
#include "aclnnop/aclnn_cos.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) Initialize resources.
  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 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);

  // Call aclrtMemcpy to copy host data 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);

  // Compute 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) Initialize the device and stream. For details, see the AscendCL API manual.
  // Set the device ID based on the actual device.
  int32_t deviceId = 0;
  aclrtStream stream;
  auto ret = Init(deviceId, &stream);
  // Handle the check as required.
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("Init acl 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<float> selfHostData = {0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8};
  std::vector<float> outHostData = {0, 0, 0, 0, 0, 0, 0, 0};
  // Create a self aclTensor.
  ret = CreateAclTensor(selfHostData, selfShape, &selfDeviceAddr, aclDataType::ACL_FLOAT, &self);
  CHECK_RET(ret == ACL_SUCCESS, return ret);
  // Create an out aclTensor.
  ret = CreateAclTensor(outHostData, outShape, &outDeviceAddr, aclDataType::ACL_FLOAT, &out);
  CHECK_RET(ret == ACL_SUCCESS, return ret);

  uint64_t workspaceSize = 0;
  aclOpExecutor* executor;

  // aclnnCos API call example
  LOG_PRINT("test aclnnCos\n");

  // 3. Call the CANN operator library API. Replace it with the actual API name.
  // Call the first-phase API of aclnnCos.
  ret = aclnnCosGetWorkspaceSize(self, out, &workspaceSize, &executor);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnCosGetWorkspaceSize failed. ERROR: %d\n", ret); return ret);
  // Allocate device memory based on 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 second-phase API of aclnnCos.
  ret = aclnnCos(workspaceAddr, workspaceSize, executor, stream);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnCos failed. ERROR: %d\n", ret); return ret);

  // 4. (Boilerplate) Synchronize the stream and wait for the task 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. Modify the code based on the 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]);
  }

  // aclnnInplaceCos API call example
  LOG_PRINT("\ntest aclnnInplaceCos\n");

  // 3. Call the CANN operator library API. Replace it with the actual API name.
  // Call the first-phase API of aclnnInplaceCos.
  ret = aclnnInplaceCosGetWorkspaceSize(self, &workspaceSize, &executor);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnInplaceCosGetWorkspaceSize failed. ERROR: %d\n", ret); return ret);
  // Allocate device memory based on workspaceSize computed 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 aclnnInplaceCos.
  ret = aclnnInplaceCos(workspaceAddr, workspaceSize, executor, stream);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnInplaceCos failed. ERROR: %d\n", ret); return ret);

  // 4. (Boilerplate) Synchronize the stream and wait for the task 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. Modify the code based on the API definition.
  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 aclTensors. Modify the code based on the API definition.
  aclDestroyTensor(self);
  aclDestroyTensor(out);

  // 7. Release device resources.
  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