aclnnLinspace

📄 View Source Code

Applicable Products

Function

• Description: Generates an evenly spaced sequence of values. Creates a one-dimensional vector of size steps, with values linearly and uniformly distributed from start to end (inclusive).

• Formula:

Function Prototype

Each operator is divided into a two-phase API. The "aclnnLinspaceGetWorkspaceSize" API must be called first to obtain the workspace size required for computation and the executor that encapsulates the operator computation flow. Then, the "aclnnLinspace" API is called to perform the computation.

• aclnnStatus aclnnLinspaceGetWorkspaceSize(const aclScalar *start, const aclScalar *end, int64_t steps, aclTensor *out, uint64_t *workspaceSize, aclOpExecutor **executor)

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

aclnnLinspaceGetWorkspaceSize

• Parameters:

  Parameter	Input/Output	Description	Instruction	Data Type	Data Format	Dimension	Non-contiguous Tensor
  start (aclScalar*)	Input	start in the formula.	-	INT8, INT16, INT32, INT64, UINT8, BOOL, FLOAT, FLOAT16, DOUBLE, BFLOAT16	-	-	-
  end (aclScalar*)	Input	Specifies the end value in the formula.	-	INT8, INT16, INT32, INT64, UINT8, BOOL, FLOAT, FLOAT16, DOUBLE, BFLOAT16	-	-	-
  steps (int64_t)	Input	Specifies the number of elements to generate.	The value of steps must be greater than or equal to 0.	-	-	-	-
  out (aclTensor*)	Output	The out in the formula.	The number of elements in out must be consistent with steps. An empty tensor is not supported.	INT8, INT16, INT32, UINT8, FLOAT, FLOAT16, DOUBLE, BFLOAT16	ND	0-8	-
  workspaceSize (uint64_t*)	Output	Returns the workspace size to be applied for on the Device side.	-	-	-	-	-
  executor (aclOpExecutor**)	Output	Returns the operator executor, which contains the operator computation process.	-	-	-	-	-

• Return value

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

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

  Return Value	Error Code	Description
  ACLNN_ERR_PARAM_NULLPTR	161001	The input 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.
  		The value of steps is less than 0.
  		The number of elements in out is inconsistent with steps.

aclnnLinspace

• Parameters:

  Parameter	Input/Output	Description
  workspace	Input	Address of the workspace applied for on the Device side.
  workspaceSize	Input	Size of the workspace applied for on the Device side, obtained through the first-phase API aclnnLinspaceGetWorkspaceSize.
  executor	Input	Operator executor that contains the operator computation process.
  stream	Input	Specifies the stream for task execution.

• Return value

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

Constraints

• Deterministic computation:

  • aclnnLinspace 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_linspace.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 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 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 the 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);

  // Compute 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. See the ACL API manual.
  // Enter the deviceId based on your 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. Custom construction is required based on the API.
  std::vector<int64_t> outShape = {8};
  void* outDeviceAddr = nullptr;
  aclScalar* start = nullptr;
  aclScalar* end = nullptr;
  aclScalar* steps = nullptr;
  aclTensor* out = nullptr;
  std::vector<float> outHostData = {0, 0, 0, 0, 0, 0, 0, 0};
  float startValue = 0.0f;
  float endValue = 1.0f;
  int64_t stepsValue = 8;

  // Create the start aclScalar.
  start = aclCreateScalar(&startValue, aclDataType::ACL_FLOAT);
  CHECK_RET(start != nullptr, return ret);
  // Create the end aclScalar.
  end = aclCreateScalar(&endValue, aclDataType::ACL_FLOAT);
  CHECK_RET(end != nullptr, return ret);
  // Create the steps aclScalar.
  steps = aclCreateScalar(&stepsValue, aclDataType::ACL_INT64);
  CHECK_RET(steps != nullptr, return ret);
  // Create the out aclTensor.
  ret = CreateAclTensor(outHostData, outShape, &outDeviceAddr, aclDataType::ACL_FLOAT, &out);
  CHECK_RET(ret == ACL_SUCCESS, return ret);

  // 3. Call the CANN operator library API.
  uint64_t workspaceSize = 0;
  aclOpExecutor* executor;
  // Call the first-phase API of aclnnLinspace.
  ret = aclnnLinspaceGetWorkspaceSize(start, end, stepsValue, out, &workspaceSize, &executor);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnLinspaceGetWorkspaceSize 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 aclnnLinspace.
  ret = aclnnLinspace(workspaceAddr, workspaceSize, executor, stream);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnLinspace failed. ERROR: %d\n", ret); return ret);

  // 4. Synchronously 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 from the device memory to the host side.
  auto size = GetShapeSize(outShape);
  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 based on the specific API definition.
  aclrtFree(outDeviceAddr);
  if (workspaceSize > 0) {
    aclrtFree(workspaceAddr);
  }
  aclrtDestroyStream(stream);
  aclrtResetDevice(deviceId);
  aclFinalize();

  return 0;
}