* Copyright (c) 2026 Huawei Technologies Co., Ltd.
* This program is free software, you can redistribute it and/or modify it under the terms and conditions of
* CANN Open Software License Agreement Version 2.0 (the "License").
* Please refer to the License for details. You may not use this file except in compliance with the License.
* THIS SOFTWARE IS PROVIDED ON AN "AS IS" BASIS, WITHOUT WARRANTIES OF ANY KIND, EITHER EXPRESS OR IMPLIED,
* INCLUDING BUT NOT LIMITED TO NON-INFRINGEMENT, MERCHANTABILITY, OR FITNESS FOR A PARTICULAR PURPOSE.
* See LICENSE in the root of the software repository for the full text of the License.
*/
#include <iostream>
#include <vector>
#include "acl/acl.h"
#include "aclnnop/aclnn_silent_check.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;
}
void PrintOutResult(std::vector<int64_t>& shape, void** deviceAddr)
{
auto size = GetShapeSize(shape);
std::vector<int32_t> resultData(size, 0);
auto ret = aclrtMemcpy(resultData.data(), resultData.size() * sizeof(resultData[0]), *deviceAddr,
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);
for (int64_t i = 0; i < size; i++) {
LOG_PRINT("result[%ld] is: %d\n", i, resultData[i]);
}
}
int Init(int32_t deviceId, aclrtStream* stream)
{
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);
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);
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);
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];
}
*tensor = aclCreateTensor(shape.data(), shape.size(), dataType, strides.data(), 0, aclFormat::ACL_FORMAT_ND,
shape.data(), shape.size(), *deviceAddr);
return 0;
}
int main()
{
int32_t deviceId = 0;
aclrtStream stream;
auto ret = Init(deviceId, &stream);
CHECK_RET(ret == 0, LOG_PRINT("Init acl failed. ERROR: %d\n", ret); return ret);
std::vector<int64_t> valShape = {};
std::vector<int64_t> inputGradShape = {4, 2};
std::vector<int64_t> sfdaShape = {3};
std::vector<int64_t> stepShape = {1};
std::vector<int64_t> resultShape = {1};
void* valDeviceAddr = nullptr;
void* inputGradDeviceAddr = nullptr;
void* sfdaDeviceAddr = nullptr;
void* stepDeviceAddr = nullptr;
void* resultDeviceAddr = nullptr;
aclTensor* val = nullptr;
aclTensor* inputGrad = nullptr;
aclTensor* sfda = nullptr;
aclTensor* step = nullptr;
aclTensor* result = nullptr;
std::vector<float> valHostData = {160.0};
std::vector<float> inputGradHostData = {0, 1, 2, 3, 4, 5, 6, 7};
std::vector<float> sfdaHostData = {70.0, 200.0, 400.0};
std::vector<int64_t> stepHostData = {7};
std::vector<int32_t> resultHostData = {0};
int32_t c_min_steps = 7;
float c_thresh_l1 = 1000000;
float c_coeff_l1 = 100000;
float c_thresh_l2 = 10000;
float c_coeff_l2 = 5000;
int32_t npu_asd_detect = 3;
ret = CreateAclTensor(valHostData, valShape, &valDeviceAddr, aclDataType::ACL_FLOAT, &val);
CHECK_RET(ret == ACL_SUCCESS, return ret);
ret = CreateAclTensor(inputGradHostData, inputGradShape, &inputGradDeviceAddr, aclDataType::ACL_FLOAT, &inputGrad);
CHECK_RET(ret == ACL_SUCCESS, return ret);
ret = CreateAclTensor(sfdaHostData, sfdaShape, &sfdaDeviceAddr, aclDataType::ACL_FLOAT, &sfda);
CHECK_RET(ret == ACL_SUCCESS, return ret);
ret = CreateAclTensor(stepHostData, stepShape, &stepDeviceAddr, aclDataType::ACL_INT64, &step);
CHECK_RET(ret == ACL_SUCCESS, return ret);
ret = CreateAclTensor(resultHostData, resultShape, &resultDeviceAddr, aclDataType::ACL_INT32, &result);
if (result == nullptr) {
std::cout << "result is nullptr!" << std::endl;
return 0;
}
CHECK_RET(ret == ACL_SUCCESS, return ret);
uint64_t workspaceSize = 0;
aclOpExecutor* executor;
ret = aclnnSilentCheckGetWorkspaceSize(val, inputGrad, sfda, step, c_min_steps, c_thresh_l1, c_coeff_l1,
c_thresh_l2, c_coeff_l2, npu_asd_detect, result, &workspaceSize, &executor);
CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnSilentCheckGetWorkspaceSize failed. ERROR: %d\n", ret); return ret);
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);
}
ret = aclnnSilentCheck(workspaceAddr, workspaceSize, executor, stream);
CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnSilentCheck failed. ERROR: %d\n", ret); return ret);
ret = aclrtSynchronizeStream(stream);
CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclrtSynchronizeStream failed. ERROR: %d\n", ret); return ret);
PrintOutResult(resultShape, &resultDeviceAddr);
aclDestroyTensor(val);
aclDestroyTensor(inputGrad);
aclDestroyTensor(sfda);
aclDestroyTensor(step);
aclDestroyTensor(result);
aclrtFree(valDeviceAddr);
aclrtFree(inputGradDeviceAddr);
aclrtFree(sfdaDeviceAddr);
aclrtFree(stepDeviceAddr);
aclrtFree(resultDeviceAddr);
if (workspaceSize > 0) {
aclrtFree(workspaceAddr);
}
aclrtDestroyStream(stream);
aclrtResetDevice(deviceId);
aclFinalize();
return 0;
}