这是我的第一个问题，所以我会尽量详细。我正在努力在 CUDA 6.5 中实现降噪算法。我的代码基于这个 Matlab 实现： http: //pastebin.com/HLVq48C1。
我很想使用新的 cuFFT 设备回调功能，但我被困在cufftXtSetCallback上。每次我的 cufftResult 都是CUFFT_NOT_IMPLEMENTED (14)。即使 nVidia 提供的示例也以同样的方式失败......我的设备回调测试代码：
__device__ void noiseStampCallback(void *dataOut,
size_t offset,
cufftComplex element,
void *callerInfo,
void *sharedPointer) {
element.x = offset;
element.y = 2;
((cufftComplex*)dataOut)[offset] = element;
}
__device__ cufftCallbackStoreC noiseStampCallbackPtr = noiseStampCallback;
我的代码的CUDA部分：
cufftHandle forwardFFTPlan;//RtC
//find how many windows there are
int batch = targetFile->getNbrOfNoiseWindows();
size_t worksize;
cufftCreate(&forwardFFTPlan);
cufftMakePlan1d(forwardFFTPlan, WINDOW, CUFFT_R2C, batch, &worksize); //WINDOW = 2048
//host memory, allocate
float *h_wave;
cufftComplex *h_complex_waveSpec;
unsigned int m_num_real_elems = batch*WINDOW*2;
h_wave = (float*)malloc(m_num_real_elems * sizeof(float));
h_complex_waveSpec = (cufftComplex*)malloc((m_num_real_elems/2+1)*sizeof(cufftComplex));
//init
memset(h_wave, 0, sizeof(float) * m_num_real_elems); //last window won't probably be full of file data, so fill memory with 0
memset(h_complex_waveSpec, 0, sizeof(cufftComplex) * (m_num_real_elems/2+1));
targetFile->getNoiseFile(h_wave); //fill h_wave with samples from sound file
//device memory, allocate, copy from host
float *d_wave;
cufftComplex *d_complex_waveSpec;
cudaMalloc((void**)&d_wave, m_num_real_elems * sizeof(float));
cudaMalloc((void**)&d_complex_waveSpec, (m_num_real_elems/2+1) * sizeof(cufftComplex));
cudaMemcpy(d_wave, h_wave, m_num_real_elems * sizeof(float), cudaMemcpyHostToDevice);
//prepare callback
cufftCallbackStoreC hostNoiseStampCallbackPtr;
cudaMemcpyFromSymbol(&hostNoiseStampCallbackPtr,
noiseStampCallbackPtr,
sizeof(hostNoiseStampCallbackPtr));
cufftResult status = cufftXtSetCallback(forwardFFTPlan,
(void **)&hostNoiseStampCallbackPtr,
CUFFT_CB_ST_COMPLEX,
NULL);
//always return status 14 - CUFFT_NOT_IMPLEMENTED
//run forward plan
cufftResult result = cufftExecR2C(forwardFFTPlan, d_wave, d_complex_waveSpec);
//result seems to be okay without cufftXtSetCallback
我知道我只是 CUDA 的初学者。我的问题是：
如何正确调用 cufftXtSetCallback 或导致此错误的原因是什么？