aclnnEye

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

Returns a 2D tensor with ones on the diagonal and zeros elsewhere.

Function Prototype

Each operator uses a two-phase API. You must first call the "aclnnEyeGetWorkspaceSize" API to obtain the workspace size required for the computation and the executor that contains the computation process of the operator, and then call the "aclnnEye" API to perform the computation.

aclnnStatus aclnnEyeGetWorkspaceSize(
    int64_t             n,
    int64_t             m,
    aclTensor*          out,
    uint64_t*           workspaceSize,
    aclOpExecutor**     executor)

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

aclnnEyeGetWorkspaceSize

• Parameters:

  Parameter	Input/Output	Description	Instruction	Data Type	Data Format	Dimension (shape)	Non-contiguous Tensor
  n (int64_t)	Input	Size of the first dimension of the output 2D tensor.	Integer, value not less than 0.	int64_t	-	-	-
  m (int64_t)	Input	Size of the second dimension of the output 2D tensor.	Integer. The value must not be less than 0.	int64_t	-	-	-
  out (aclTensor*)	Output	Two-dimensional tensor with 1 on the diagonal and 0 elsewhere.	-	FLOAT16, FLOAT32, INT32, INT16, INT8, UINT8, INT64, BOOL, BFLOAT16	ND	2	-
  workspaceSize (uint64_t*)	Output	Returns the workspace size to be requested on the Device side.	-	-	-	-	-
  executor (aclOpExecutor**)	Output	Returns the op executor, which contains the operator computation process.	-	-	-	-	-

  • Atlas inference products, Atlas training products: The BFLOAT16 data type is 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	out is a null pointer.
  ACLNN_ERR_PARAM_INVALID	161002	The data type of out is not in the supported range.
  		The dimension of out is not 2.
  		The value of n or m is less than 0.
  		The shape of out is not (n, m).

aclnnEye

• Parameters:

  Parameter	Input/Output	Description
  workspace	Input	Workspace memory address requested on the device.
  workspaceSize	Input	Size of the workspace memory requested on the device, obtained by calling the first-phase API aclnnEyeGetWorkspaceSize.
  executor	Input	Executor of the op, containing the computation process of the operator.
  stream	Input	Stream for executing tasks.

• Return value

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

Constraints

• deterministic computation: aclnnEye 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 "acl/acl.h"
#include "aclnnop/aclnn_eye.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 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 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 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. For details, see the acl API manual.
  // 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. Customize the construction based on the API.
  std::vector<int64_t> outShape = {3, 3};
  void* outDeviceAddr = nullptr;
  aclTensor* out = nullptr;
  std::vector<float> outHostData(9, 0);
  int64_t n = 3;
  int64_t m = 3;
  // 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. Replace with the specific API name.
  uint64_t workspaceSize = 0;
  aclOpExecutor* executor;
  // Call the first-phase API of aclnnEye.
  ret = aclnnEyeGetWorkspaceSize(n, m, out, &workspaceSize, &executor);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnEyeGetWorkspaceSize 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 aclnnEye.
  ret = aclnnEye(workspaceAddr, workspaceSize, executor, stream);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnEye failed. ERROR: %d\n", ret); return ret);
  // 4. (Boilerplate) 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 from the device side to the host side. Modify it based on the specific 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]);
  }

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

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