aclnnBitwiseAndTensor

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: When the input is a BOOL-type tensor, performs a logical AND operation; when the input is an INT-type tensor, performs a bitwise AND operation.

• Formula:

  $$ou{t}_i=sel{f}_i\&othe{r}_i$$

Function Prototype

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

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

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

aclnnBitwiseAndTensorGetWorkspaceSize

• Parameters:

  Parameter	Input/Output	Description	Instruction	Data Type	Data Format	Dimension (shape)	Non-contiguous Tensor
  self (aclTensor*)	Input	self in the formula.	The data type needs to be consistent with other according to the data type deduction rules (see also conversion relationship). The shape needs to be consistent with other according to the broadcast relationship.	BOOL, INT8, INT16, INT32, INT64, UINT8, UINT16, UINT32, UINT64	ND	Not exceeding 8 dimensions	√
  other (aclTensor*)	Input	other in the formula.	The data type needs to be consistent with self following the data type deduction rules (see also conversion relationship). The shape needs to be consistent with self following the broadcast relationship.	BOOL, INT8, INT16, INT32, INT64, UINT8, UINT16, UINT32, UINT64	ND	Not exceeding 8 dimensions	√
  out (aclTensor*)	Output	out in the formula.	The data type needs to be a data type convertible after the deduction of self and other (see also conversion relationship). The shape needs to be the shape of self and other after broadcast.	BOOL, INT8, INT16, INT32, INT64, UINT8, UINT16, UINT32, UINT64	ND	Not exceeding 8 dimensions	√
  workspaceSize(uint64_t*)	Output	Returns the size of the workspace that needs to be applied on the Device side.	-	-	-	-	-
  executor (aclOpExecutor**)	Output	Returns the op executor, which contains the operator computation flow.	-	-	-	-	-

• Return value

  aclnnStatus: Returns the status 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	self, other, or out is a null pointer.
  ACLNN_ERR_PARAM_INVALID	161002	The data types of self and other are not supported.
  		The data types of self and other cannot be deduced.
  		The data type deduced from self and other cannot be converted to the data type of the specified output out.
  		The shapes of self and other cannot be broadcast.
  		The number of dimensions of self, other, or out exceeds 8.

aclnnBitwiseAndTensor

• Parameters:

  Parameter	Input/Output	Description
  workspace	Input	Workspace memory address applied on the Device side.
  workspaceSize	Input	Workspace size applied on the Device side, obtained by calling the first-phase API aclnnBitwiseAndTensorGetWorkspaceSize.
  executor	Input	op executor, which contains the computation flow of the operator.
  stream	Input	Stream for executing tasks.

• Return value

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

Constraints

• Deterministic computation:
  • aclnnBitwiseAndTensor 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_bitwise_and_tensor.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); aclFinalize(); return ret);
  ret = aclrtCreateStream(stream);
  CHECK_RET(ret == ACL_SUCCESS,
            LOG_PRINT("aclrtCreateStream failed. ERROR: %d\n", ret);
            aclrtResetDevice(deviceId); aclFinalize(); 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 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);

  // Calculate 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 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);
  // Process the check as needed.
  CHECK_RET(ret == 0, LOG_PRINT("Init acl failed. ERROR: %d\n", ret); return ret);
  // 2. Construct inputs and outputs. Customize the construction based on the API.
  std::vector<int64_t> selfShape = {4, 2};
  std::vector<int64_t> otherShape = {4, 2};
  std::vector<int64_t> outShape = {4, 2};
  void* selfDeviceAddr = nullptr;
  void* otherDeviceAddr = nullptr;
  void* outDeviceAddr = nullptr;
  aclTensor* self = nullptr;
  aclTensor* other = nullptr;
  aclTensor* out = nullptr;
  std::vector<int64_t> selfHostData = {0, 1, 2, 3, 4, 5, 6, 7};
  std::vector<int64_t> otherHostData = {1, 1, 2, 3, 3, 3, 4, 4};
  std::vector<int64_t> outHostData = {0, 0, 0, 0, 0, 0, 0, 0};
  // Create the self aclTensor.
  ret = CreateAclTensor(selfHostData, selfShape, &selfDeviceAddr, aclDataType::ACL_INT64, &self);
  CHECK_RET(ret == ACL_SUCCESS, return ret);
  // Create the other aclTensor.
  ret = CreateAclTensor(otherHostData, otherShape, &otherDeviceAddr, aclDataType::ACL_INT64, &other);
  CHECK_RET(ret == ACL_SUCCESS, return ret);
  // Create the out aclTensor.
  ret = CreateAclTensor(outHostData, outShape, &outDeviceAddr, aclDataType::ACL_INT64, &out);
  CHECK_RET(ret == ACL_SUCCESS, return ret);

  // 3. Call the CANN operator library API. Replace it with the specific API.
  uint64_t workspaceSize = 0;
  aclOpExecutor* executor;
  // Call the first-phase API of aclnnBitwiseAndTensor.
  ret = aclnnBitwiseAndTensorGetWorkspaceSize(self, other, out, &workspaceSize, &executor);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnBitwiseAndTensorGetWorkspaceSize failed. ERROR: %d\n", ret); return ret);
  // Allocate device memory based on the workspaceSize computed 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 aclnnBitwiseAndTensor.
  ret = aclnnBitwiseAndTensor(workspaceAddr, workspaceSize, executor, stream);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnBitwiseAndTensor failed. ERROR: %d\n", ret); return ret);
  // 4. (boilerplate) 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 memory. Modify it based on the specific API definition.
  auto size = GetShapeSize(outShape);
  std::vector<int64_t> resultData(size, 0);
  ret = aclrtMemcpy(resultData.data(), resultData.size() * sizeof(resultData[0]), outDeviceAddr, size * sizeof(int64_t),
                    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: %ld\n", i, resultData[i]);
  }

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

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