* 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 <cmath>
#include <stdint.h>
#include "acl/acl.h"
#include "aclnnop/aclnn_asin.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;
}
static inline float Float16ToFloat(uint16_t value)
{
unsigned int sign = (value >> 15) & 0x1;
unsigned int exponent = (value >> 10) & 0x1f;
unsigned int mantissa = value & 0x3ff;
float result;
if (exponent == 0) {
result = mantissa * 0.0000019073486328125f;
} else if (exponent == 31) {
result = (mantissa == 0) ? 1.0f / 0.0f : 0.0f / 0.0f;
} else {
result = (1.0f + mantissa * 0.0009765625f) * powf(2.0f, (int)exponent - 15);
}
return sign ? -result : result;
}
static inline uint16_t FloatToFloat16(float value)
{
uint32_t bits = *reinterpret_cast<uint32_t*>(&value);
uint16_t sign = (bits >> 16) & 0x8000;
int32_t exponent = ((bits >> 23) & 0xff) - 127 + 15;
uint32_t mantissa = bits & 0x7fffff;
if (exponent <= 0) {
return sign;
} else if (exponent >= 31) {
return sign | 0x7c00;
}
uint16_t fp16 = sign | (exponent << 10) | (mantissa >> 13);
return fp16;
}
void PrintOutResultFp16(std::vector<int64_t>& shape, void** deviceAddr, const std::vector<uint16_t>& selfHostData)
{
auto size = GetShapeSize(shape);
std::vector<uint16_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++) {
float inputFp32 = Float16ToFloat(selfHostData[i]);
float resultFp32 = Float16ToFloat(resultData[i]);
LOG_PRINT("asin input[%ld] is: %f (0x%04x), result[%ld] is: %f (0x%04x)\n",
i, inputFp32, selfHostData[i], i, resultFp32, 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 == ACL_SUCCESS, LOG_PRINT("Init acl failed. ERROR: %d\n", ret); return ret);
std::vector<int64_t> selfShape = {8, 8};
std::vector<uint16_t> selfHostData(64);
float inputVal = 0.5f;
uint16_t inputFp16 = FloatToFloat16(inputVal);
printf("Input value: %f, as float16: 0x%04x\n", inputVal, inputFp16);
for (int i = 0; i < 64; i++) {
selfHostData[i] = inputFp16;
}
aclTensor* self = nullptr;
void* selfDeviceAddr = nullptr;
ret = CreateAclTensor(selfHostData, selfShape, &selfDeviceAddr, aclDataType::ACL_FLOAT16, &self);
CHECK_RET(ret == ACL_SUCCESS, return ret);
aclTensor* out = nullptr;
void* outDeviceAddr = nullptr;
std::vector<uint16_t> outHostData(64, 0);
ret = CreateAclTensor(outHostData, selfShape, &outDeviceAddr, aclDataType::ACL_FLOAT16, &out);
CHECK_RET(ret == ACL_SUCCESS, return ret);
uint64_t workspaceSize = 0;
aclOpExecutor* executor;
ret = aclnnAsinGetWorkspaceSize(self, out, &workspaceSize, &executor);
CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnAsinGetWorkspaceSize failed. ERROR: %d\n", ret); return ret);
void* workspaceAddr = nullptr;
if (workspaceSize > static_cast<uint64_t>(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 = aclnnAsin(workspaceAddr, workspaceSize, executor, stream);
CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnAsin 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);
PrintOutResultFp16(selfShape, &outDeviceAddr, selfHostData);
aclDestroyTensor(self);
aclDestroyTensor(out);
aclrtFree(selfDeviceAddr);
aclrtFree(outDeviceAddr);
if (workspaceSize > static_cast<uint64_t>(0)) {
aclrtFree(workspaceAddr);
}
aclrtDestroyStream(stream);
aclrtResetDevice(deviceId);
aclFinalize();
return 0;
}