aclnnAbs

Applicable Products

  • Ascend 950PR&950DT products: Supported
  • Atlas A3 products: Supported
  • Atlas A2 products: Supported
  • Atlas 200I/500 A2 inference products: Not supported
  • Atlas inference products: Supported
  • Atlas training products: Supported

Function

  • Description: Computes the absolute value for each element of the input tensor.

  • Formula:

out=∣self∣out=|self|

Function Prototype

Each operator uses a two-phase API. Call the "aclnnAbsGetWorkspaceSize" API first to obtain the workspace size required for the computation and the executor that contains the operator computation process, and then call the "aclnnAbs" API to execute the computation.

aclnnStatus aclnnAbsGetWorkspaceSize(
  const aclTensor *self,
  aclTensor       *out,
  uint64_t        *workspaceSize,
  aclOpExecutor  **executor)
aclnnStatus aclnnAbs(
  void              *workspace,
  uint64_t           workspaceSize,
  aclOpExecutor     *executor,
  const aclrtStream  stream)

aclnnAbsGetWorkspaceSize

  • Parameters:

    Parameter Input/Output Description Instruction Data Type Data Format Shape Non-contiguous Tensor
    self Input Input parameter for the abs computation, which is self in the formula. - FLOAT, FLOAT16, DOUBLE, BFLOAT16, INT8, INT16, INT32, INT64, UINT8, BOOL, COMPLEX32, COMPLEX64 ND 0-8 √
    out Output Output parameter for the abs computation, which is out in the formula. Same shape as self. FLOAT, FLOAT16, DOUBLE, BFLOAT16, INT8, INT16, INT32, INT64, UINT8, BOOL ND 0-8 √
    workspaceSize Output Returns the size of the workspace to be allocated on the device. - - - - -
    executor Output Returns the op executor, which contains the operator computation flow. - - - - -
    • Atlas training products and Atlas inference products: BFLOAT16, COMPLEX32, and COMPLEX64 are not supported.
  • Return value

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

    The first-phase API performs input parameter validation and returns an error in the following scenarios:

    Error Code Error Code Description
    ACLNN_ERR_PARAM_NULLPTR 161001 The input tensor is a null pointer.
    ACLNN_ERR_PARAM_INVALID 161002 The data type and data format of self are not within the supported range.
    The number of dimensions of self exceeds 8.
    The shapes of self and out are inconsistent.
    If self is a real number, the data types of self and out are inconsistent. If self is COMPLEX64, the data type of out is not FLOAT32. If self is COMPLEX32, the data type of out is not FLOAT16.

aclnnAbs

  • Parameters:

    Parameter Input/Output Description
    workspace Input Workspace memory address allocated on the Device side.
    workspaceSize Input Workspace size allocated on the Device side, obtained by calling the first-phase API aclnnAbsGetWorkspaceSize.
    executor Input op executor, which contains the operator computation process.
    stream Input Stream for executing tasks.
  • Return value

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

Constraints

  • Deterministic computation:
    • aclnnAbs defaults to a deterministic implementation.

Example

The following sample code is for reference only. For details about compiling and running, see Compile and Run Samples.

#include <iostream>
#include <vector>
#include "acl/acl.h"
#include "aclnnop/aclnn_abs.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;
}

void PrintOutResult(std::vector<int64_t> &shape, void** deviceAddr) {
  auto size = GetShapeSize(shape);
  std::vector<float> resultData(size, 0);
  auto ret = aclrtMemcpy(resultData.data(), resultData.size() * sizeof(resultData[0]),
                         *deviceAddr, 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);
  for (int64_t i = 0; i < size; i++) {
    LOG_PRINT("result[%ld] is: %f\n", i, resultData[i]);
  }
}

int Init(int32_t deviceId, aclrtStream* stream) {
  // Boilerplate, 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 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 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);

  // 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) Initialize the device/stream. For details, see the acl API documentation.
  // 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. Custom construction is required based on the API.
  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 = {1, -1, -1, -2, 2, -2, -3, 3};
  std::vector<float> outHostData = {1, -1, -1, -2, 2, -2, -3, 3};

  ret = CreateAclTensor(selfHostData, selfShape, &selfDeviceAddr, aclDataType::ACL_FLOAT, &self);
  CHECK_RET(ret == ACL_SUCCESS, return ret);
  ret = CreateAclTensor(outHostData, outShape, &outDeviceAddr, aclDataType::ACL_FLOAT, &out);
  CHECK_RET(ret == ACL_SUCCESS, return ret);

  // 3. Call the CANN operator library API. Change it to the specific API name.
  uint64_t workspaceSize = 0;
  aclOpExecutor* executor;

  // Call the first-phase API of aclnnAbs.
  ret = aclnnAbsGetWorkspaceSize(self, out, &workspaceSize, &executor);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnAbsGetWorkspaceSize failed. ERROR: %d.\n[ERROR msg]%s", ret, aclGetRecentErrMsg()); 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[ERROR msg]%s", ret, aclGetRecentErrMsg()); return ret);
  }

  // Call the second-phase API of aclnnAbs.
  ret = aclnnAbs(workspaceAddr, workspaceSize, executor, stream);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnAbs failed. ERROR: %d.\n[ERROR msg]%s", ret, aclGetRecentErrMsg()); return ret);

  // 4. (boilerplate) Synchronously wait for the task execution to complete.
  ret = aclrtSynchronizeStream(stream);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclrtSynchronizeStream failed. ERROR: %d.\n[ERROR msg]%s", ret, aclGetRecentErrMsg()); return ret);

  // 5. Obtain the output value and copy the result from the device side to the host side. Modify it based on the definition of the specific API.
  PrintOutResult(outShape, &outDeviceAddr);

  // 6. Release aclTensor. Modify it based on the definition of the specific API.
  aclDestroyTensor(self);
  aclDestroyTensor(out);

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

  return 0;
}