FFT_1D
C2C
C2C_1D算子调用示例：
#include <iostream>
#include <vector>
#include "asdsip.h"
#include "acl/acl.h"
#include "aclnn/acl_meta.h"
using namespace AsdSip;
#define CHECK_RET(cond, return_expr) \
do { \
if (!(cond)) { \
return_expr; \
} \
} while (0)
#define LOG_PRINT(message, ...) \
do { \
printf(message, ##__VA_ARGS__); \
} while (0)
#define ASD_STATUS_CHECK(err) \
do { \
AsdSip::AspbStatus err_ = (err); \
if (err_ != AsdSip::NO_ERROR) { \
std::cout << "Execute failed." << std::endl; \
exit(-1); \
} \
} 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)
{
// 固定写法，AscendCL初始化
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);
// 调用aclrtMalloc申请device侧内存
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);
// 调用aclrtMemcpy将host侧数据复制到device侧内存上
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);
// 计算连续tensor的strides
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];
}
// 调用aclCreateTensor接口创建aclTensor
*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);
// 创造tensor的Host侧数据
int batch = 32, Nfft = 128; // c2c dft
// int batch = 32, Nfft = 8192; // c2c fftb
// int batch = 32, Nfft = 15000; // c2c mixed
// int batch = 32, Nfft = 32768; // c2c fftn
// int batch = 32, Nfft = 199 * 199; // core any
const int64_t tensorInSize = batch * Nfft;
std::vector<int64_t> selfShape = {batch, Nfft};
std::vector<int64_t> outShape = {batch, Nfft};
std::vector<std::complex<float>> inputHostData(tensorInSize, std::complex<float>(0, 0));
for (int i = 0; i < tensorInSize; i++) {
inputHostData[i] = std::complex<float>(i, i + 1);
}
std::vector<std::complex<float>> outHostData(tensorInSize, std::complex<float>(0, 0));
void *inputDeviceAddr = nullptr;
void *outDeviceAddr = nullptr;
aclTensor *input = nullptr;
aclTensor *out = nullptr;
ret = CreateAclTensor(inputHostData, selfShape, &inputDeviceAddr, aclDataType::ACL_COMPLEX64, &input);
CHECK_RET(ret == ACL_SUCCESS, return ret);
ret = CreateAclTensor(outHostData, outShape, &outDeviceAddr, aclDataType::ACL_COMPLEX64, &out);
CHECK_RET(ret == ACL_SUCCESS, return ret);
asdFftHandle handle;
asdFftCreate(handle);
asdFftMakePlan1D(handle, Nfft, asdFftType::ASCEND_FFT_C2C, asdFftDirection::ASCEND_FFT_FORWARD, batch);
size_t work_size;
asdFftGetWorkspaceSize(handle, work_size);
void *workspaceAddr = nullptr;
if (work_size > 0) {
ret = aclrtMalloc(&workspaceAddr, static_cast<int64_t>(work_size), ACL_MEM_MALLOC_HUGE_FIRST);
CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("allocate workspace failed. ERROR: %d\n", ret); return ret);
}
asdFftSetWorkspace(handle, (uint8_t *)workspaceAddr);
asdFftSetStream(handle, stream);
ASD_STATUS_CHECK(asdFftExecC2C(handle, input, out));
ret = aclrtSynchronizeStream(stream);
CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclrtSynchronizeStream failed. ERROR: %d\n", ret); return ret);
asdFftDestroy(handle);
auto size = GetShapeSize(outShape);
std::vector<std::complex<float>> outData(size, 0);
ret = aclrtMemcpy(outData.data(),
outData.size() * sizeof(outData[0]),
outDeviceAddr,
size * sizeof(outData[0]),
ACL_MEMCPY_DEVICE_TO_HOST);
// 打印输出tensor值中前16个
for (int64_t i = 0; i < 16; i++) {
std::cout << static_cast<std::complex<float>>(outData[i]) << "\t";
}
std::cout << "\nend result" << std::endl;
std::cout << "Execute successfully." << std::endl;
aclDestroyTensor(input);
aclDestroyTensor(out);
aclrtFree(inputDeviceAddr);
aclrtFree(outDeviceAddr);
if (work_size > 0) {
aclrtFree(workspaceAddr);
}
aclrtDestroyStream(stream);
aclrtResetDevice(deviceId);
aclFinalize();
return 0;
}
C2R
C2R_1D算子调用示例：
#include <iostream>
#include <vector>
#include "asdsip.h"
#include "acl/acl.h"
#include "aclnn/acl_meta.h"
using namespace AsdSip;
#define CHECK_RET(cond, return_expr) \
do { \
if (!(cond)) { \
return_expr; \
} \
} while (0)
#define LOG_PRINT(message, ...) \
do { \
printf(message, ##__VA_ARGS__); \
} while (0)
#define ASD_STATUS_CHECK(err) \
do { \
AsdSip::AspbStatus err_ = (err); \
if (err_ != AsdSip::NO_ERROR) { \
std::cout << "Execute failed." << std::endl; \
exit(-1); \
} \
} 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)
{
// 固定写法，AscendCL初始化
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);
// 调用aclrtMalloc申请device侧内存
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);
// 调用aclrtMemcpy将host侧数据复制到device侧内存上
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);
// 计算连续tensor的strides
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];
}
// 调用aclCreateTensor接口创建aclTensor
*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);
// 创造tensor的Host侧数据
int batch = 32, Nfft = 128;
// int batch = 32, Nfft = 8192;
// int batch = 8, Nfft = 567;
// int batch = 32, Nfft = 997;
// int batch = 32, Nfft = 15000;
// 创造tensor的Host侧数据
// int batch = 32, Nfft = 199 * 199;
const int64_t inSignal = Nfft / 2 + 1;
const int64_t outSignal = Nfft;
const int64_t tensorInSize = batch * inSignal;
const int64_t tensorOutSize = batch * outSignal;
std::vector<int64_t> selfShape = {batch, inSignal};
std::vector<int64_t> outShape = {batch, outSignal};
std::vector<std::complex<float>> inputHostData(tensorInSize, std::complex<float>(0, 0));
for (int i = 0; i < tensorInSize; i++) {
inputHostData[i] = std::complex<float>(i, i + 1);
}
std::vector<float> outHostData(tensorOutSize, 0);
void *inputDeviceAddr = nullptr;
void *outDeviceAddr = nullptr;
aclTensor *input = nullptr;
aclTensor *out = nullptr;
ret = CreateAclTensor(inputHostData, selfShape, &inputDeviceAddr, aclDataType::ACL_COMPLEX64, &input);
CHECK_RET(ret == ACL_SUCCESS, return ret);
ret = CreateAclTensor(outHostData, outShape, &outDeviceAddr, aclDataType::ACL_FLOAT, &out);
CHECK_RET(ret == ACL_SUCCESS, return ret);
asdFftHandle handle;
asdFftCreate(handle);
asdFftMakePlan1D(handle, Nfft, asdFftType::ASCEND_FFT_C2R, asdFftDirection::ASCEND_FFT_FORWARD, batch);
size_t work_size;
asdFftGetWorkspaceSize(handle, work_size);
void *workspaceAddr = nullptr;
if (work_size > 0) {
ret = aclrtMalloc(&workspaceAddr, static_cast<int64_t>(work_size), ACL_MEM_MALLOC_HUGE_FIRST);
CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("allocate workspace failed. ERROR: %d\n", ret); return ret);
}
asdFftSetWorkspace(handle, (uint8_t *)workspaceAddr);
asdFftSetStream(handle, stream);
ASD_STATUS_CHECK(asdFftExecC2R(handle, input, out));
ret = aclrtSynchronizeStream(stream);
CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclrtSynchronizeStream failed. ERROR: %d\n", ret); return ret);
asdFftDestroy(handle);
auto size = GetShapeSize(outShape);
std::vector<float> outData(size, 0);
ret = aclrtMemcpy(outData.data(),
outData.size() * sizeof(outData[0]),
outDeviceAddr,
size * sizeof(outData[0]),
ACL_MEMCPY_DEVICE_TO_HOST);
// 打印输出tensor值中前16个
for (int64_t i = 0; i < 16; i++) {
std::cout << static_cast<float>(outData[i]) << "\t";
}
std::cout << "\nend result" << std::endl;
std::cout << "Execute successfully." << std::endl;
aclDestroyTensor(input);
aclDestroyTensor(out);
aclrtFree(inputDeviceAddr);
aclrtFree(outDeviceAddr);
if (work_size > 0) {
aclrtFree(workspaceAddr);
}
aclrtDestroyStream(stream);
aclrtResetDevice(deviceId);
aclFinalize();
return 0;
}
R2C
R2C_1D算子调用示例：
#include <iostream>
#include <vector>
#include "asdsip.h"
#include "acl/acl.h"
#include "aclnn/acl_meta.h"
using namespace AsdSip;
#define CHECK_RET(cond, return_expr) \
do { \
if (!(cond)) { \
return_expr; \
} \
} while (0)
#define LOG_PRINT(message, ...) \
do { \
printf(message, ##__VA_ARGS__); \
} while (0)
#define ASD_STATUS_CHECK(err) \
do { \
AsdSip::AspbStatus err_ = (err); \
if (err_ != AsdSip::NO_ERROR) { \
std::cout << "Execute failed." << std::endl; \
exit(-1); \
} \
} 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)
{
// 固定写法，AscendCL初始化
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);
// 调用aclrtMalloc申请device侧内存
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);
// 调用aclrtMemcpy将host侧数据复制到device侧内存上
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);
// 计算连续tensor的strides
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];
}
// 调用aclCreateTensor接口创建aclTensor
*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);
// 创造tensor的Host侧数据
int batch = 32, Nfft = 256;
// int batch = 32, Nfft = 199 * 199;
const int64_t inSignal = Nfft;
const int64_t outSignal = Nfft / 2 + 1;
const int64_t tensorInSize = batch * inSignal;
const int64_t tensorOutSize = batch * outSignal;
std::vector<int64_t> selfShape = {batch, inSignal};
std::vector<int64_t> outShape = {batch, outSignal};
std::vector<float> inputHostData(tensorInSize, 0);
for (int i = 0; i < tensorInSize; i++) {
inputHostData[i] = i;
}
std::vector<std::complex<float>> outHostData(tensorOutSize, std::complex<float>(0, 0));
void *inputDeviceAddr = nullptr;
void *outDeviceAddr = nullptr;
aclTensor *input = nullptr;
aclTensor *out = nullptr;
ret = CreateAclTensor(inputHostData, selfShape, &inputDeviceAddr, aclDataType::ACL_FLOAT, &input);
CHECK_RET(ret == ACL_SUCCESS, return ret);
ret = CreateAclTensor(outHostData, outShape, &outDeviceAddr, aclDataType::ACL_COMPLEX64, &out);
CHECK_RET(ret == ACL_SUCCESS, return ret);
asdFftHandle handle;
asdFftCreate(handle);
asdFftMakePlan1D(handle, Nfft, asdFftType::ASCEND_FFT_R2C, asdFftDirection::ASCEND_FFT_FORWARD, batch);
size_t work_size;
asdFftGetWorkspaceSize(handle, work_size);
void *workspaceAddr = nullptr;
if (work_size > 0) {
ret = aclrtMalloc(&workspaceAddr, static_cast<int64_t>(work_size), ACL_MEM_MALLOC_HUGE_FIRST);
CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("allocate workspace failed. ERROR: %d\n", ret); return ret);
}
asdFftSetWorkspace(handle, (uint8_t *)workspaceAddr);
asdFftSetStream(handle, stream);
ASD_STATUS_CHECK(asdFftExecR2C(handle, input, out));
ret = aclrtSynchronizeStream(stream);
CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclrtSynchronizeStream failed. ERROR: %d\n", ret); return ret);
asdFftDestroy(handle);
auto size = GetShapeSize(outShape);
std::vector<std::complex<float>> outData(size, 0);
ret = aclrtMemcpy(outData.data(),
outData.size() * sizeof(outData[0]),
outDeviceAddr,
size * sizeof(outData[0]),
ACL_MEMCPY_DEVICE_TO_HOST);
// 打印输出tensor值中前16个
for (int64_t i = 0; i < 16; i++) {
std::cout << static_cast<std::complex<float>>(outData[i]) << "\t";
}
std::cout << "\nend result" << std::endl;
std::cout << "Execute successfully." << std::endl;
aclDestroyTensor(input);
aclDestroyTensor(out);
aclrtFree(inputDeviceAddr);
aclrtFree(outDeviceAddr);
if (work_size > 0) {
aclrtFree(workspaceAddr);
}
aclrtDestroyStream(stream);
aclrtResetDevice(deviceId);
aclFinalize();
return 0;
}
父主题： FFT