aclnnIndex

📄 View Source Code

Applicable Products

Function

• Description: Extracts data from the input x at the coordinates specified by indices.

• Formula:

  $$out = self[indices]$$

Function Prototype

Each operator uses a two-phase API. You must first call the "aclnnIndexGetWorkspaceSize" API to obtain the input parameters and calculate the required workspace size based on the process, and then call the "aclnnIndex" API to perform the computation.

aclnnStatus aclnnIndexGetWorkspaceSize(
 const aclTensor*     self,
 const aclTensorList* indices,
 aclTensor*           out,
 uint64_t*            workspaceSize,
 aclOpExecutor**      executor)

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

aclnnIndexGetWorkspaceSize

• Parameters

  Parameter	Input/Output	Description	Instruction	Data Type	Data Format	Dimension (Shape)	Non-contiguous Tensor
  self	Input	Input tensor.	-	FLOAT, FLOAT16, BFLOAT16, DOUBLE, INT32, INT64, INT16, INT8, UINT8, BOOL	ND	1-8	√
  indices	Input	Index.	The index data in index does not support out-of-bounds access.	INT32, INT64, BOOL	ND	1-8	√
  out	Output	Output tensor.	-	Same as self.	ND	1-8	-
  workspaceSize	Output	Size of the workspace to be applied for on the Device.	-	-	-	-	-
  executor	Output	Returns the operator executor, which contains the operator computation process.	-	-	-	-	-

  • Atlas training products and Atlas inference products: The BFLOAT16 data type is not supported.

• Return Value

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

  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 passed self is a null pointer.
  ACLNN_ERR_PARAM_INVALID	161002	The data types of self and out are not within the supported range.
  		The data types of self and out are inconsistent.

aclnnIndex

• Parameters

  Parameter	Input/Output	Description
  workspace	Input	Address of the workspace memory applied for on the Device side.
  workspaceSize	Input	Size of the workspace applied for on the Device side, obtained from the first-phase API aclnnIndexGetWorkspaceSize.
  executor	Input	Operator executor that contains the operator computation flow.
  stream	Input	Stream that executes the task.

• Return Value

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

Constraints

• Deterministic computation:

  • aclnnIndex defaults to a deterministic implementation.

• When self is a non-zero-dimensional tensor, the number of tensors in indices must be less than or equal to the number of dimensions of self. When self is a zero-dimensional tensor, indices can contain only one tensor.

• The shapes of the tensors in indices must be identical or satisfy the broadcast relationship. The values in each tensor must not exceed the size of the corresponding dimension in self; otherwise, unpredictable behavior such as out-of-bounds access may occur.

• When indices are of the bool type, the shape of each tensor in indices must be exactly the same as the shape of the corresponding dimension in self, and the shapes of the new tensors generated by filtering each tensor through its own boolean indices must satisfy the broadcast relationship.

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_index.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 shape_size = 1;
  for (auto i : shape) {
    shape_size *= i;
  }
  return shape_size;
}

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-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.
  // Set the deviceId based on the actual device.
  int32_t deviceId = 0;
  aclrtStream stream;
  auto ret = Init(deviceId, &stream);
  // Handle the check based on your requirements.
  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> selfShape = {3, 4};
  std::vector<int64_t> indexShape = {1};
  std::vector<int64_t> outShape = {1};
  void* selfDeviceAddr = nullptr;
  void* indexOneDeviceAddr = nullptr;
  void* indexTwoDeviceAddr = nullptr;
  void* outDeviceAddr = nullptr;
  aclTensor* self = nullptr;
  aclTensor* indexOne = nullptr;
  aclTensor* indexTwo = nullptr;
  aclTensor* out = nullptr;
  std::vector<float> selfHostData = {1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12};
  std::vector<int64_t> indexOneHostData = {0};
  std::vector<int64_t> indexTwoHostData = {2};
  std::vector<float> outHostData = {0};
  // Create the self aclTensor.
  ret = CreateAclTensor(selfHostData, selfShape, &selfDeviceAddr, aclDataType::ACL_FLOAT, &self);
  CHECK_RET(ret == ACL_SUCCESS, return ret);
  // Create the index aclTensor.
  ret = CreateAclTensor(indexOneHostData, indexShape, &indexOneDeviceAddr, aclDataType::ACL_INT64, &indexOne);
  CHECK_RET(ret == ACL_SUCCESS, return ret);
  ret = CreateAclTensor(indexTwoHostData, indexShape, &indexTwoDeviceAddr, aclDataType::ACL_INT64, &indexTwo);
  CHECK_RET(ret == ACL_SUCCESS, return ret);
  aclTensor* indices[] = {indexOne, indexTwo};
  auto indexTensorList = aclCreateTensorList(indices, 2);
  // 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 operator API.
  uint64_t workspaceSize = 0;
  aclOpExecutor* executor;
  // Call the first-phase API of aclnnIndex.
  ret = aclnnIndexGetWorkspaceSize(self, indexTensorList, out, &workspaceSize, &executor);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnIndexGetWorkspaceSize failed. ERROR: %d\n", ret); return ret);
  // Apply for 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 aclnnIndex.
  ret = aclnnIndex(workspaceAddr, workspaceSize, executor, stream);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnIndex failed. ERROR: %d\n", ret); return ret);

  // 4. (boilerplate) Synchronously wait for 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. Modify 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(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. Modify based on the specific API definition.
  aclDestroyTensor(self);
  aclDestroyTensorList(indexTensorList);
  aclDestroyTensor(out);

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