aclnnLogSpace

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: Not supported
  • Atlas training products: Not supported

Function

  • Description: Creates a 1D tensor of size steps\text{steps}, whose values are evenly spaced on a logarithmic scale from basestart\text{base}^\text{start} to baseend\text{base}^\text{end}, inclusive of endpoints, with base\text{base} as the base.

  • Formula:

result=(basestart, base(start+end−startsteps−1), …, base(start+(steps−2)∗end−startsteps−1), baseend)\text{result} = \left(\text{base}^\text{start},\ \text{base}^{\left(\text{start} + \frac{\text{end} - \text{start}}{\text{steps} - 1}\right)},\ \ldots,\ \text{base}^{\left(\text{start} + (\text{steps} - 2) * \frac{\text{end} - \text{start}}{\text{steps} - 1}\right)},\ \text{base}^\text{end}\right)

Function Prototype

Each operator uses a two-phase API. First call "aclnnLogSpaceGetWorkspaceSize" to obtain the workspace size required for computation and the executor that contains the operator computation process, and then call "aclnnLogSpace" to perform the computation.

aclnnStatus aclnnLogSpaceGetWorkspaceSize(
  const aclScalar*    start,
  const aclScalar*    end,
  int64_t             steps,
  double              base,
  const aclTensor*    result,
  uint64_t*           workspaceSize,
  aclOpExecutor**     executor)
aclnnStatus aclnnLogSpace(
  void            *workspace,
  uint64_t         workspaceSize,
  aclOpExecutor   *executor,
  aclrtStream      stream)

aclnnLogSpaceGetWorkspaceSize

  • Parameters:

    Parameter Input/Output Description Instruction Data Type Data Format Dimensions(shape) Non-contiguous Tensor
    start (aclScalar*) Input First input of LogSpace, specifying the starting exponent of the log sequence. - FLOAT, FLOAT16, BFLOAT16, DOUBLE, UINT64, UINT32, UINT16, UINT8, INT64, INT32, INT16, INT8, BOOL ND - √
    end (aclScalar*) Input Second input of LogSpace, specifying the ending exponent of the log sequence. - FLOAT, FLOAT16, BFLOAT16, DOUBLE, UINT64, UINT32, UINT16, UINT8, INT64, INT32, INT16, INT8, BOOL ND - √
    steps (int64_t) Input Number of elements in the sequence. - int64_t - - -
    base (double) Input Base of the logarithmic space. - double - - -
    result (aclTensor*) Output Output of LogSpace, the logarithmically spaced sequence tensor. - FLOAT, FLOAT16, BFLOAT16 ND 1 √
    workspaceSize (uint64_t*) Output Returns the workspace size to be requested on the Device. - - - - -
    executor (aclOpExecutor**) Output Returns the op executor, which contains the operator computation process. - - - - -
  • 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 passed start, end, steps, or out is a null pointer.
    ACLNN_ERR_PARAM_INVALID 161002 The data type of out is not within the supported range.
    steps is less than 0.

aclnnLogSpace

  • Parameters:

    Parameter Input/Output Description
    workspace Input The workspace memory address allocated on the Device.
    workspaceSize Input The workspace size allocated on the Device, obtained by the first-phase API aclnnLogSpaceGetWorkspaceSize.
    executor Input Executor that contains the operator computation process.
    stream Input Stream for task execution.
  • Return value

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

Constraints

  • Deterministic computation:

    • aclnnLogSpace defaults to a deterministic implementation.

Example

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

#include <iostream>
#include <vector>
#include <math.h>
#include "acl/acl.h"
#include "aclnnop/aclnn_logspace.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 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 CreateOutputAclTensor(
    const std::vector<int64_t>& shape, void** deviceAddr, aclDataType dataType, aclTensor** tensor)
{
    auto size = GetShapeSize(shape) * sizeof(T);
    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);

    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];
    }
    *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 == 0, LOG_PRINT("Init acl failed. ERROR: %d\n", ret); return ret);

  // 2. Construct the input and output. Customize them as required by the API.
  void* outDeviceAddr = nullptr;
  aclScalar* start = nullptr;
  aclScalar* end = nullptr;
  aclTensor* out = nullptr;

  float startValue = 0.0f;  //Start exponent
  float endValue = 2.0f;    //End exponent
  int64_t steps = 5;    //Number of steps
  float base = 10.0;    //Base

  std::vector<int64_t> shape = {steps};

  // Create start aclScalar.
  start = aclCreateScalar(&startValue, aclDataType::ACL_FLOAT);
  CHECK_RET(start != nullptr, LOG_PRINT("create start scalar failed\n"); return -1);
  // Create end aclScalar.
  end = aclCreateScalar(&endValue, aclDataType::ACL_FLOAT);
  CHECK_RET(end != nullptr, LOG_PRINT("create end scalar failed\n"); return -1);
  // Create out aclTensor.
  ret = CreateOutputAclTensor<float>(shape, &outDeviceAddr, aclDataType::ACL_FLOAT, &out);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("create output tensor failed\n"); return ret);
  // 3. Call a CANN operator library API
  uint64_t workspaceSize = 0;
  aclOpExecutor* executor;
  // Call the aclnnLogSpace first-phase API
  ret = aclnnLogSpaceGetWorkspaceSize(start, end, steps, base, out, &workspaceSize, &executor);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnLogSpaceGetWorkspaceSize 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 > static_cast<uint64_t>(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 aclnnLogSpace second-phase API
  ret = aclnnLogSpace(workspaceAddr, workspaceSize, executor, stream);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnLogSpace failed. ERROR: %d\n", ret); return ret);

  // 4. Synchronize and wait for the 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 on device memory to the host
  auto size = GetShapeSize(shape);
  std::vector<float> resultData(size, 0);
  ret = aclrtMemcpy(resultData.data(), resultData.size() * sizeof(resultData[0]), outDeviceAddr,
                    size * sizeof(float), 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 aclTensor and aclScalar
  aclDestroyScalar(start);
  aclDestroyScalar(end);
  aclDestroyTensor(out);

  // 7. Release device resources. Modify as required by the specific API definition
  aclrtFree(outDeviceAddr);
  if (workspaceSize > static_cast<uint64_t>(0)) {
    aclrtFree(workspaceAddr);
  }
  aclrtDestroyStream(stream);
  aclrtResetDevice(deviceId);
  aclFinalize();

  return 0;
}