aclnnCummax

Applicable Products

Product	Supported
Ascend 950PR/Ascend 950DT	×
Atlas A3 training products/Atlas A3 inference products	√
Atlas A2 training products/Atlas A2 inference products	√
Atlas 200I/500 A2 inference products	×
Atlas inference products	×
Atlas training products	√

Function

Description: Computes the cumulative maximum of self, and returns the maximum values along with their corresponding indices.
Formula:

valuesOut:
$valuesOut_{i} = max(self_{1}, self_{2}, self_{3}, ......, self_{i})$
indicesOut:
$indicesOut_{i} = argmax(self_{1}, self_{2}, self_{3}, ......, self_{i})$

Function Prototype

Each operator is divided into a two-phase API. The "aclnnCummaxGetWorkspaceSize" API must be called first to obtain the workspace size required for computation and the executor that encapsulates the operator computation flow. Then, the "aclnnCummax" API is called to perform the computation.

aclnnStatus aclnnCummaxGetWorkspaceSize(
  const aclTensor*    self,
  int64_t             dim,
  aclTensor*          valuesOut,
  aclTensor*          indicesOut,
  uint64_t*           workspaceSize,
  aclOpExecutor**     executor)

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

aclnnCummaxGetWorkspaceSize

Parameters:

Name	Input/Output	Description	Usage	Data Type	Data Format	Dimension (Shape)	Non-contiguous Tensor
self (aclTensor*)	Input	Input tensor.	The shape must be identical to those of `valuesOut` and `indicesOut`.	FLOAT16, FLOAT, DOUBLE, UINT8, INT8, INT16, INT32, INT64, BOOL, BFLOAT16	ND	[0,8]	√
dim (int64_t)	Input	Processing dimension.	When self.dim() = 0, the value range is [-1, 0]. When self.dim() > 0, the value range is [–self.dim(), self.dim() – 1).	int64_t	-	-	-
valuesOut (aclTensor*)	Output	Indicates the accumulated maximum value in self.	The shape must be the same as that of self and indicesOut.	FLOAT16, FLOAT, DOUBLE, UINT8, INT8, INT16, INT32, INT64, BOOL, BFLOAT16	ND	Maximum 8 dimensions	√
indicesOut (aclTensor*)	Output	Index corresponding to valuesOut.	The shape must be the same as those of self and valuesOut.	INT32 or INT64	ND	Maximum 8 dimensions	√
workspaceSize (uint64_t*)	Output	Size of the workspace to be allocated on the device.	-	-	-	-	-
executor (aclOpExecutor**)	Output	Operator executor, containing the operator computation process.	-	-	-	-	-

Atlas A3 training products/Atlas A3 inference products:the self and valuesOut data types do not support BFLOAT16.

Return value

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

The first-phase API performs input parameter validation and returns an error in the following scenarios:

Return Code	Error Code	Description
ACLNN_ERR_PARAM_NULLPTR	161001	self, valuesOut, or indicesOut is a null pointer.
ACLNN_ERR_PARAM_INVALID	161002	The data types of self, valuesOut, and indicesOut are not within the supported range.
		The shapes of self, valuesOut, and indicesOut are not within the supported range.
		When self.dim()=0, the dim parameter value is not within the range [-1, 0]; when self.dim()>0, the dim parameter value is not within the range [-self.dim(), self.dim()-1].

aclnnCummax

Parameters:

Parameter	Input/Output	Description
workspace	Input	Memory address of the workspace applied for on the Device side.
workspaceSize	Input	Size of the workspace applied for on the Device side, obtained from the first-phase API aclnnCummaxGetWorkspaceSize.
executor	Input	Operator executor that contains the operator computation flow.
stream	Input	Specifies the Stream for task execution.

Return value

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

Constraints

Deterministic computation:
- aclnnCummax defaults to a deterministic implementation.

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_cummax.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: 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 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);
  // Copy data from the host to the device memory by calling aclrtMemcpy.
  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];
  }

  // Create an aclTensor by calling aclCreateTensor.
  *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. Refer to 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 interface.
  std::vector<int64_t> selfShape = {2, 4};
  std::vector<int64_t> valuesOutShape = {2, 4};
  std::vector<int64_t> indicesOutShape = {2, 4};
  void* selfDeviceAddr = nullptr;
  void* valuesOutDeviceAddr = nullptr;
  void* indicesOutDeviceAddr = nullptr;
  aclTensor* self = nullptr;
  aclTensor* valuesOut = nullptr;
  aclTensor* indicesOut = nullptr;
  std::vector<float> selfHostData = {3.0, 3.0, 2.0, 1.0, 4.0, 2.0, 6.0, 7.0};
  std::vector<float> valuesOutHostData(8, 0.0);
  std::vector<int64_t> indicesOutHostData(8, 0);
  int64_t dim = 0;
  // Create the self aclTensor.
  ret = CreateAclTensor(selfHostData, selfShape, &selfDeviceAddr, aclDataType::ACL_FLOAT, &self);
  CHECK_RET(ret == ACL_SUCCESS, return ret);
  // Create the valuesOut aclTensor.
  ret = CreateAclTensor(valuesOutHostData, valuesOutShape, &valuesOutDeviceAddr, aclDataType::ACL_FLOAT, &valuesOut);
  CHECK_RET(ret == ACL_SUCCESS, return ret);
  // Create the indicesOut aclTensor.
  ret = CreateAclTensor(indicesOutHostData, indicesOutShape, &indicesOutDeviceAddr, aclDataType::ACL_INT64, &indicesOut);
  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 aclnnCummax.
  ret = aclnnCummaxGetWorkspaceSize(self, dim, valuesOut, indicesOut, &workspaceSize, &executor);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnCummaxGetWorkspaceSize 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 aclnnCummax.
  ret = aclnnCummax(workspaceAddr, workspaceSize, executor, stream);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnCummax failed. ERROR: %d\n", ret); return ret);

  // 4. (Boilerplate) Synchronize and wait for task completion.
  ret = aclrtSynchronizeStream(stream);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclrtSynchronizeStream failed. ERROR: %d\n", ret); return ret);

  // 5. Obtain the output values and copy the results from the device memory to the host. Modify this based on the specific API definition.
  // Obtain valuesOut.
  auto size = GetShapeSize(valuesOutShape);
  std::vector<float> resultData(size, 0);
  ret = aclrtMemcpy(resultData.data(), resultData.size() * sizeof(resultData[0]), valuesOutDeviceAddr,
                    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]);
  }
  // Obtain indicesOut.
  auto indicesSize = GetShapeSize(indicesOutShape);
  std::vector<int64_t> indicesResultData(indicesSize, 0);
  ret = aclrtMemcpy(indicesResultData.data(), indicesResultData.size() * sizeof(indicesResultData[0]), indicesOutDeviceAddr,
                    indicesSize * sizeof(indicesResultData[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 < indicesSize; i++) {
    LOG_PRINT("result[%ld] is: %ld\n", i, indicesResultData[i]);
  }

  // 6. Release aclTensor and aclScalar. Modify based on the specific API definition.
  aclDestroyTensor(self);
  aclDestroyTensor(valuesOut);
  aclDestroyTensor(indicesOut);
  // 7. Release device resources. Modify based on the specific API definition.
  aclrtFree(selfDeviceAddr);
  aclrtFree(valuesOutDeviceAddr);
  aclrtFree(indicesOutDeviceAddr);
  if (workspaceSize > 0) {
    aclrtFree(workspaceAddr);
  }
  aclrtDestroyStream(stream);
  aclrtResetDevice(deviceId);
  aclFinalize();
  return 0;
}