aclnnMaxN

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: Computes the element-wise maximum across the corresponding elements of each input tensor in the input tensor list.

• Formula:

$$ou{t}_i=max(input{0}_i,input{1}_i,...)$$

Function Prototype

Each operator uses a two-phase API. Call the "aclnnMaxNGetWorkspaceSize" API first to obtain the workspace size required for the computation and the executor that contains the operator computation process, and then call the "aclnnMaxN" API to execute the computation.

aclnnStatus aclnnMaxNGetWorkspaceSize(
  const aclTensorList*     tensors,
  aclTensor*               out,
  uint64_t*                workspaceSize,
  aclOpExecutor**          executor)

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

aclnnMaxNGetWorkspaceSize

• Parameters:

  Parameter	Input/Output	Description	Instruction	Data Type	Data Format	Dimensions (shape)	Non-contiguous Tensor
  self (aclTensorList*)	Input	The input in the formula.	The shapes of the tensors in tensors must satisfy the broadcast relationship with each other. The dtypes of the tensors in tensors must be the same.	FLOAT16, FLOAT, INT8, UINT8, INT32, INT64, BFLOAT16	ND	0-8	√
  out (aclTensor*)	Output	The out in the formula.	The dtype must be the same as the dtype of the tensors in tensors. The shape must be the shape of all tensors in the input tensor list after broadcast.	FLOAT16, FLOAT, INT8, UINT8, INT32, INT64, BFLOAT16	ND	0-8	√
  workspaceSize (uint64_t*)	Output	Returns the workspace size to be allocated on the device.	-	-	-	-	-
  executor (aclOpExecutor**)	Output	Returns the op executor, which contains the operator computation flow.	-	-	-	-	-

  • Atlas inference products and Atlas training products: The BFLOAT16 data type is not supported.
  • Atlas A3 products, Atlas A2 products, Atlas training products, Atlas inference products: UINT8 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:

  Return Value	Error Code	Description
  ACLNN_ERR_PARAM_NULLPTR	161001	Null pointer passed for tensors or out.
  ACLNN_ERR_PARAM_INVALID	161002	The data type of a tensor in the tensors list or out is not within the supported range.
  		The data types of tensors in the tensors list and out are inconsistent.
  		The shapes of tensors in the tensors list and out do not comply with the broadcast rules, or the shape after broadcast is inconsistent with out.
  		The maximum dimension of a tensor in the tensors list exceeds 8.

aclnnMaxN

• Parameters:

  Parameter	Input/Output	Description
  workspace	Input	Pointer to the workspace memory allocated on the device.
  workspaceSize	Input	Size of the workspace memory allocated on the device, obtained by calling the first-phase API aclnnMaxNGetWorkspaceSize.
  executor	Input	op executor, which contains 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:
  • aclnnMaxN 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_maxn.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); 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 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 aclCreateTensor 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) Device/stream initialization. For details, see the acl API list.
  // 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 inputs and outputs as required by the API.
  std::vector<int64_t> selfShape1 = {2, 3};
  std::vector<int64_t> selfShape2 = {1, 3};
  std::vector<int64_t> outShape = {2, 3};
  void* input1DeviceAddr = nullptr;
  void* input2DeviceAddr = nullptr;
  void* outDeviceAddr = nullptr;
  aclTensor* input1 = nullptr;
  aclTensor* input2 = nullptr;
  aclTensor* out = nullptr;
  std::vector<float> input1HostData = {11, 12, 13, 4, 5, 6};
  std::vector<float> input2HostData = {7, 8, 9};
  std::vector<float> outHostData(6, 0);

  // Create input1 aclTensor.
  ret = CreateAclTensor(input1HostData, selfShape1, &input1DeviceAddr, aclDataType::ACL_FLOAT, &input1);
  CHECK_RET(ret == ACL_SUCCESS, return ret);

  // Create input2 aclTensor.
  ret = CreateAclTensor(input2HostData, selfShape2, &input2DeviceAddr, aclDataType::ACL_FLOAT, &input2);
  CHECK_RET(ret == ACL_SUCCESS, return ret);

  // Create out aclTensor.
  ret = CreateAclTensor(outHostData, outShape, &outDeviceAddr, aclDataType::ACL_FLOAT, &out);
  CHECK_RET(ret == ACL_SUCCESS, return ret);

  std::vector<aclTensor*> tmp{input1, input2};
  aclTensorList* tensorList = aclCreateTensorList(tmp.data(), tmp.size());

  // 3. Call the CANN operator library API. Replace it with the actual API name.
  uint64_t workspaceSize = 0;
  aclOpExecutor* executor;
  // Call the first-phase API of aclnnMaxN.
  ret = aclnnMaxNGetWorkspaceSize(tensorList, out, &workspaceSize, &executor);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnMaxNGetWorkspaceSize 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 aclnnMaxN.
  ret = aclnnMaxN(workspaceAddr, workspaceSize, executor, stream);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnMaxN failed. ERROR: %d\n", ret); return ret);

  // 4. (boilerplate) Wait synchronously 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 device memory 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 and aclScalar. Modify it based on the specific API definition.
  aclDestroyTensorList(tensorList);
  aclDestroyTensor(out);


  // 7. Release device resources. Modify it based on the specific API definition.
  aclrtFree(input1DeviceAddr);
  aclrtFree(input2DeviceAddr);
  aclrtFree(outDeviceAddr);
  if (workspaceSize > 0) {
    aclrtFree(workspaceAddr);
  }
  aclrtDestroyStream(stream);
  aclrtResetDevice(deviceId);
  aclFinalize();

  return 0;
}