aclnnCummin

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 minimum of self, and returns the values along with their corresponding indices.
Formula:

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

Function Prototype

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

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

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

aclnnCumminGetWorkspaceSize

Parameters:

Name	Input/Output	Description	Usage	Data Type	Data Format	Dimension (Shape)	Non-contiguous Tensor
self (aclTensor*)	Input	Input tensor.	The data type can be converted to that of valuesOut.	FLOAT, DOUBLE, UINT8, INT8, INT16, INT32, INT64, FLOAT16, BFLOAT16, BOOL	ND	No more than 8 dimensions.	√
dim (int64_t)	Input	Dimension along which the operation is performed.	The value range is [–self.dim(), self.dim()–1).	INT64	-	-	-
valuesOut (aclTensor*)	Output	Output tensor of the accumulated minimum value.	The data type and shape must be the same as those of self.	FLOAT, DOUBLE, UINT8, INT8, INT16, INT32, INT64, FLOAT16, BFLOAT16, BOOL	ND	No more than 8 dimensions.	√
indicesOut (aclTensor*)	Output	Output tensor of the index corresponding to the accumulated minimum value.	The data type can be INT32 or INT64, and the shape must be the same as that of self.	INT32, INT64	ND	No more than 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 inference products, Atlas 200I/500 A2 inference products, and Atlas training products: The data type cannot be 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	The self, valuesOut, and indicesOut parameters are null pointers.
ACLNN_ERR_PARAM_INVALID	161002	The data type of the parameters self, valuesOut, and indicesOut is not within the supported range.
		The shapes of the parameters self, valuesOut, and indicesOut are inconsistent.
		When self.dim()=0, the value range of the parameter dim is not within [-1, 0]; when self.dim()>0, the value range of the parameter dim is not within [-self.dim(), self.dim()-1].
		The data type of the parameter self cannot be converted to the data type of valuesOut.
		The dimension of the self, valuesOut, and indicesOut parameters exceeds 8.

aclnnCummin

Parameters:

Parameter	Input/Output	Description
workspace	Input	Specifies the workspace memory address allocated on the Device side.
workspaceSize	Input	Specifies the workspace size allocated on the Device side, obtained from the first-phase API aclnnCumminGetWorkspaceSize.
executor	Input	Operator executor, which contains the operator computation process.
stream	Input	Specifies the stream that executes the task.

Return value

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

Constraints

Deterministic computation:
- aclnnCummin defaults to a deterministic implementation.
When the input self data type is int32, due to instruction feature constraints, precision is guaranteed only when values are within [-16777215, 16777215].

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_cummin.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: 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 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 data from the host to the device.
  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 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 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) Initialize the device/stream. See the ACL API manual.
  // Fill in the deviceId based on your 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 aclnnCummin.
  ret = aclnnCumminGetWorkspaceSize(self, dim, valuesOut, indicesOut, &workspaceSize, &executor);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnCumminGetWorkspaceSize 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 aclnnCummin.
  ret = aclnnCummin(workspaceAddr, workspaceSize, executor, stream);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnCummin failed. ERROR: %d\n", ret); return ret);

  // 4. (Boilerplate) Synchronize and 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 memory. Modify based on the specific API definition.
  auto valuesSize = GetShapeSize(valuesOutShape);
  std::vector<float> valuesResultData(valuesSize, 0);
  ret = aclrtMemcpy(valuesResultData.data(), valuesResultData.size() * sizeof(valuesResultData[0]), valuesOutDeviceAddr,
                    valuesSize * sizeof(valuesResultData[0]), ACL_MEMCPY_DEVICE_TO_HOST);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("copy values result from device to host failed. ERROR: %d\n", ret); return ret);

  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 indices result from device to host failed. ERROR: %d\n", ret); return ret);

  LOG_PRINT("Values result:\n");
  for (int64_t i = 0; i < valuesSize; i++) {
    LOG_PRINT("valuesResult[%ld] is: %f\n", i, valuesResultData[i]);
  }

  LOG_PRINT("Indices result:\n");
  for (int64_t i = 0; i < indicesSize; i++) {
    LOG_PRINT("indicesResult[%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;
}