97a5ffb9Add on 18 days agoHistory

aclnnEqual

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: Checks whether two tensors have the same size and elements. Returns a value of the Bool type.
Formula:
$o u t = (s e l f = = o t h e r) ? T r u e : F a l s e$

Function Prototype

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

aclnnStatus aclnnEqualGetWorkspaceSize(
  const aclTensor* self,
  const aclTensor* other,
  aclTensor*       out,
  uint64_t*        workspaceSize,
  aclOpExecutor**  executor)

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

aclnnEqualGetWorkspaceSize

Parameters:

Parameter	Input/Output	Description	Instruction	Data Type	Data Format	Dimensions (shape)	Non-contiguous Tensor
self	Input	Represents the first input.	The data types of self and other must conform to the data type deduction rules (see deduction relationship).	FLOAT16, FLOAT, INT32, INT8, UINT8, BOOL, DOUBLE, INT64, INT16, UINT16, UINT32, UINT64, BFLOAT16	ND	-	√
other	Input	Represents the second input.	The data types of other and self must satisfy the data type deduction rules (see deduction relationship).	FLOAT16, FLOAT, INT32, INT8, UINT8, BOOL, DOUBLE, INT64, INT16, UINT16, UINT32, UINT64, BFLOAT16	ND	-	√
out	Output	Represents the output. The output is a one-dimensional tensor with one element of the BOOL data type.	-	-	-	-	-
workspaceSize	Output	Returns the workspace size to be applied for on the Device.	-	-	-	-	-
executor	Output	Returns the op executor, which contains the operator computation flow.	-	-	-	-	-

Atlas training products and Atlas inference 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	The self or other parameter is a null pointer.
ACLNN_ERR_PARAM_INVALID	161002	The deduced data type of self or other is not within the supported range.
		The dimension of self, other, or out is greater than 8.
		The shape of out is not [1].

aclnnEqual

Parameters:

Parameter	Input/Output	Description
workspace	Input	Workspace memory address allocated on the Device.
workspaceSize	Input	Size of the workspace allocated on the Device, obtained by calling the first-phase API aclnnEqualGetWorkspaceSize.
executor	Input	op executor, containing the operator computation flow.
stream	Input	Stream for executing tasks.

Return value

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

Constraints

Deterministic computation:
- aclnnEqual defaults to a deterministic implementation.
A large computation workload may cause operator execution timeout (aicore error, with errorStr set to: timeout or trap error). This occurs when the merged size of the last two axes is less than 16 and the merged size of the preceding axes is extremely large.

Example

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

#include <iostream>
#include <vector>
#include "acl/acl.h"
#include "aclnnop/aclnn_equal.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 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 apply for 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 host data to 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(), shape.size(), aclFormat::ACL_FORMAT_ND, shape.data(),
      shape.size(), *deviceAddr);
  return 0;
}

aclError InitAcl(int32_t deviceId, aclrtStream* stream)
{
  auto ret = Init(deviceId, stream);
  CHECK_RET(ret == 0, LOG_PRINT("Init acl failed. ERROR: %d\n", ret); return ret);
  return ACL_SUCCESS;
}

aclError CreateInputs(
    std::vector<int64_t>& selfShape, std::vector<int64_t>& otherShape, std::vector<int64_t>& outShape,
    void** selfDeviceAddr, void** otherDeviceAddr, void** outDeviceAddr, aclTensor** self, aclTensor** other,
    aclTensor** out)
{
  std::vector<double> selfHostData = {0, 1, 2, 3, 4, 5, 6, 7};
  std::vector<double> otherHostData = {0, 1, 2, 3, 4, 5, 6, 7};
  std::vector<char> outHostData = {0};

  auto ret = CreateAclTensor(selfHostData, selfShape, selfDeviceAddr, aclDataType::ACL_DOUBLE, self);
  CHECK_RET(ret == ACL_SUCCESS, return ret);

  ret = CreateAclTensor(otherHostData, otherShape, otherDeviceAddr, aclDataType::ACL_DOUBLE, other);
  CHECK_RET(ret == ACL_SUCCESS, return ret);

  ret = CreateAclTensor(outHostData, outShape, outDeviceAddr, aclDataType::ACL_BOOL, out);
  CHECK_RET(ret == ACL_SUCCESS, return ret);

  return ACL_SUCCESS;
}

aclError ExecOpApi(
    aclTensor* self, aclTensor* other, aclTensor* out, void** workspaceAddrOut, uint64_t& workspaceSize,
    void* outDeviceAddr, std::vector<int64_t>& outShape, aclrtStream stream)
{
  aclOpExecutor* executor;

  auto ret = aclnnEqualGetWorkspaceSize(self, other, out, &workspaceSize, &executor);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnEqualGetWorkspaceSize failed. ERROR: %d\n", ret); return ret);

  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);
  }
  *workspaceAddrOut = workspaceAddr;

  ret = aclnnEqual(workspaceAddr, workspaceSize, executor, stream);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnEqual failed. ERROR: %d\n", ret); return ret);

  ret = aclrtSynchronizeStream(stream);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclrtSynchronizeStream failed. ERROR: %d\n", ret); return ret);

  auto size = GetShapeSize(outShape);
  std::vector<char> resultData(size, 0);

  ret = aclrtMemcpy(
      resultData.data(), resultData.size() * sizeof(resultData[0]), outDeviceAddr, size * sizeof(char),
      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: %d\n", i, resultData[i]);
  }

  return ACL_SUCCESS;
}

int main()
{
  int32_t deviceId = 0;
  aclrtStream stream;

  auto ret = InitAcl(deviceId, &stream);
  CHECK_RET(ret == ACL_SUCCESS, return ret);

  std::vector<int64_t> selfShape = {4, 2};
  std::vector<int64_t> otherShape = {4, 2};
  std::vector<int64_t> outShape = {1};

  void* selfDeviceAddr = nullptr;
  void* otherDeviceAddr = nullptr;
  void* outDeviceAddr = nullptr;

  aclTensor* self = nullptr;
  aclTensor* other = nullptr;
  aclTensor* out = nullptr;

  ret = CreateInputs(
      selfShape, otherShape, outShape, &selfDeviceAddr, &otherDeviceAddr, &outDeviceAddr, &self, &other, &out);
  CHECK_RET(ret == ACL_SUCCESS, return ret);

  uint64_t workspaceSize = 0;
  void* workspaceAddr = nullptr;

  ret = ExecOpApi(self, other, out, &workspaceAddr, workspaceSize, outDeviceAddr, outShape, stream);
  CHECK_RET(ret == ACL_SUCCESS, return ret);

  // Release resources.
  aclDestroyTensor(self);
  aclDestroyTensor(other);
  aclDestroyTensor(out);

  aclrtFree(selfDeviceAddr);
  aclrtFree(otherDeviceAddr);
  aclrtFree(outDeviceAddr);

  if (workspaceSize > 0) {
    aclrtFree(workspaceAddr);
  }

  aclrtDestroyStream(stream);
  aclrtResetDevice(deviceId);
  aclFinalize();
  return 0;
}