Calling Built-in CANN Operators

#include <iostream>
#include <vector>
#include "acl/acl.h"
#include "aclnnop/aclnn_add.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) {
  // The initialization code is written in a fixed format.
  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);
  // Call aclrtMemcpy to copy the 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 consecutive tensors.
  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. (Fixed writing) Initialize the device/stream.
  // Set deviceId based on the actual device.
  int32_t deviceId = 0;
  aclrtStream stream;
  auto ret = Init(deviceId, &stream);
  // Use check as required.
  CHECK_RET(ret == 0, LOG_PRINT("Init acl failed. ERROR: %d\n", ret); return ret);

  //2. Construct the input and output 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;
  aclScalar* alpha = 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 = {0, 0, 0, 0, 0, 0, 0, 0};
  float alphaValue = 1.2f;
  // Create a self aclTensor.
  ret = CreateAclTensor(selfHostData, selfShape, &selfDeviceAddr, aclDataType::ACL_FLOAT, &self);
  CHECK_RET(ret == ACL_SUCCESS, return ret);
  // Create other aclTensor.
  ret = CreateAclTensor(otherHostData, otherShape, &otherDeviceAddr, aclDataType::ACL_FLOAT, &other);
  CHECK_RET(ret == ACL_SUCCESS, return ret);
  // create alpha aclScalar.
  alpha = aclCreateScalar(&alphaValue, aclDataType::ACL_FLOAT);
  CHECK_RET(alpha != nullptr, return ret);
  // Create 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, which needs to be changed to a specific operator API.
  uint64_t workspaceSize = 0;
  aclOpExecutor* executor;
  // Call the first-phase API of aclnnAdd.
  ret = aclnnAddGetWorkspaceSize(self, other, alpha, out, &workspaceSize, &executor);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnAddGetWorkspaceSize failed. ERROR: %d\n", ret); return ret);
  // Allocate device memory based on 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 aclnnAdd.
  ret = aclnnAdd(workspaceAddr, workspaceSize, executor, stream);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnAdd failed. ERROR: %d\n", ret); return ret);

 //4. Wait until the task execution is complete. This code is written in a fixed format.
  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. Modify the configuration based on the API definition.
  auto size = GetShapeSize(outShape);
  std::vector<float> resultData(size, 0);
  ret = aclrtMemcpy(resultData.data(), resultData.size() * sizeof(resultData[0]), outDeviceAddr, size * sizeof(float),
                    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 the configuration based on the API definition.
  aclDestroyTensor(self);
  aclDestroyTensor(other);
  aclDestroyScalar(alpha);
  aclDestroyTensor(out);

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

# CMake lowest version requirement
cmake_minimum_required(VERSION 3.14)

# Set the project name.
project(ACLNN_EXAMPLE)

# Compile options
add_compile_options(-std=c++11)

# Set compilation options.
set(CMAKE_RUNTIME_OUTPUT_DIRECTORY  "./bin")    
set(CMAKE_CXX_FLAGS_DEBUG "-fPIC -O0 -g -Wall")
set(CMAKE_CXX_FLAGS_RELEASE "-fPIC -O2 -Wall")

# Set the executable file name (for example, opapi_test) and specify the directory where the operator file (*.cpp) is stored.
add_executable(opapi_test
               test_add.cpp) 

# Set ASCEND_PATH (CANN package directory) and INCLUDE_BASE_DIR (header file directory).
if(NOT "$ENV{ASCEND_CUSTOM_PATH}" STREQUAL "")      
    set(ASCEND_PATH $ENV{ASCEND_CUSTOM_PATH})
else()
    set(ASCEND_PATH "/usr/local/Ascend/cann")
endif()
set(INCLUDE_BASE_DIR "${ASCEND_PATH}/include")
include_directories(
    ${INCLUDE_BASE_DIR}
    ${INCLUDE_BASE_DIR}/aclnn
)

#Set the link library file paths.
target_link_libraries(opapi_test PRIVATE
                      ${ASCEND_PATH}/lib64/libascendcl.so
                      ${ASCEND_PATH}/lib64/libnnopbase.so
                      ${ASCEND_PATH}/lib64/libopapi_${ops_project}.so)

# The executable file is in the bin folder of the directory where the CMakeLists file is located.
install(TARGETS opapi_test DESTINATION ${CMAKE_RUNTIME_OUTPUT_DIRECTORY})

#Set the link library file paths.
find_package(Threads REQUIRED)                        
target_link_libraries(opapi_test PRIVATE
                      ${ASCEND_PATH}/lib64/libascendcl.so
                      ${ASCEND_PATH}/lib64/libnnopbase.so
                      ${ASCEND_PATH}/lib64/libopapi_${ops_project}.so
                      ${ASCEND_PATH}/lib64/libhccl.so      #The HCCL file
                      ${CMAKE_THREAD_LIBS_INIT})            #The library file on which multithreading depends