aclnnMinimum

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 minimum value of each element in two tensors and returns a new tensor.

  • Formula:

    outi=min⁡(selfi,otheri)\text{out}_i = \min(\text{self}_i, \text{other}_i)

Function Prototype

Each operator uses a two-phase API. First, call the "aclnnMinimumGetWorkspaceSize" API to obtain the workspace size required for the computation and the executor containing the operator computation process. Then, call the "aclnnMinimum" API to perform the computation.

aclnnStatus aclnnMinimumGetWorkspaceSize(
  const aclTensor *self,
  const aclTensor *other,
  aclTensor       *out,
  uint64_t        *workspaceSize,
  aclOpExecutor  **executor)
aclnnStatus aclnnMinimum(
  void           *workspace,
  uint64_t        workspaceSize,
  aclOpExecutor  *executor,
  aclrtStream     stream)

aclnnMinimumGetWorkspaceSize

  • Parameters:

    Parameter Input/Output Description Instruction Data Type Data Format Dimension (shape) Non-contiguous Tensor
    self (aclTensor*) Input The first input tensor. The data type must comply with the data type deduction rules together with the data type of other, and the shape must meet the broadcast relationship with other. FLOAT, FLOAT16, DOUBLE, INT32, INT64, INT16, INT8, UINT8, BOOL, BFLOAT16 ND - √
    other (aclTensor*) Input The second input tensor. The data type must conform to the data type deduction rules with self. The shape must conform to the broadcast relationship with self. FLOAT, FLOAT16, DOUBLE, INT32, INT64, INT16, INT8, UINT8, BOOL, BFLOAT16 ND - √
    out (aclTensor*) Output Output tensor. The data type must be convertible to the data type deduced from self and other. The shape must be the shape after self and other are broadcast. FLOAT, FLOAT16, DOUBLE, INT32, INT64, INT16, INT8, UINT8, BOOL, BFLOAT16 ND - √
    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 training products, Atlas inference products: The data types of self, other, and out do not support BOOL or BFLOAT16.
  • 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 When self, other, or out is a null pointer.
    ACLNN_ERR_PARAM_INVALID 161002 The data type of self or other is out of the supported range.
    The data types of self and other cannot be deduced.
    The deduced data type cannot be converted to the type of the specified output out.
    The shapes of self and other cannot be broadcast.

aclnnMinimum

  • Parameters:

    Parameter Input/Output Description
    workspace Input Workspace memory address allocated on the Device.
    workspaceSize Input Size of the workspace memory allocated on the Device, obtained by the first-phase API aclnnMinimumGetWorkspaceSize.
    executor Input op executor that contains the operator computation flow.
    stream Input Stream that executes the task.
  • Return value

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

Constraints

  • Deterministic computation:
    • aclnnMinimum defaults to a deterministic implementation.

Example

The sample code is as follows and is for reference only. For details about compiling and running the sample, see Compile and Run Samples.

#include <iostream>
#include <vector>
#include "acl/acl.h"
#include "aclnnop/aclnn_minimum.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); 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 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 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. 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);
  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.
  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<float> selfHostData = {0, 1, 2, 3, 4, 5, 6, 7};
  std::vector<float> otherHostData = {1, 1, 1, 2, 2, 2, 3, 3};
  std::vector<float> outHostData(8, 0);
  // Create the self aclTensor.
  ret = CreateAclTensor(selfHostData, selfShape, &selfDeviceAddr, aclDataType::ACL_FLOAT, &self);
  CHECK_RET(ret == ACL_SUCCESS, return ret);
  // Create the other aclTensor.
  ret = CreateAclTensor(otherHostData, otherShape, &otherDeviceAddr, aclDataType::ACL_FLOAT, &other);
  CHECK_RET(ret == ACL_SUCCESS, return ret);
  // Create the out aclTensor.
  ret = CreateAclTensor(outHostData, outShape, &outDeviceAddr, aclDataType::ACL_FLOAT, &out);
  CHECK_RET(ret == ACL_SUCCESS, return ret);

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

  // 4. (Boilerplate) Wait synchronously for the task execution to finish
  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 in device memory to host memory. 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.
  aclDestroyTensor(self);
  aclDestroyTensor(other);
  aclDestroyTensor(out);

  // 7. Release 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;
}