c - CUDA FFT 関数呼び出し中のエラー「code=2(CUFFT_ALLOC_FAILED)」

Question

CUDAを使ってGPSの信号を処理するプログラムを書いているので、fftを使う必要がありますが、エラーが発生しました。

 CUDA error at F:/clouddrive kingsoft/acc/accfinal/accfinal/acc.cu:341 code=2(CUF
FT_ALLOC_FAILED) "cufftPlan1d(&plan, new_size, CUFFT_C2C, 1)"

コードはここにあります。

 double fft_Ifft_Sum(Complex *h_signal,Complex *h_filter_kernel,double* list,bool firstEnter)
{
   double max=0;
    int new_size=samplesPerCode;
    int mem_size = sizeof(Complex) * new_size;

    // Allocate device memory for signal
    Complex *d_signal;
    checkCudaErrors(cudaMalloc((void **)&d_signal, mem_size));
    // Copy host memory to device
    checkCudaErrors(cudaMemcpy(d_signal, h_signal, mem_size,cudaMemcpyHostToDevice));

    // Allocate device memory for filter kernel
   if(firstEnter)
   { 
     checkCudaErrors(cudaFree(d_filter_kernel));
     checkCudaErrors(cudaMalloc((void **)&d_filter_kernel, mem_size));

     checkCudaErrors(cudaMemcpy(d_filter_kernel, h_filter_kernel, mem_size,
                               cudaMemcpyHostToDevice));
   }

    // CUFFT plan
    cufftHandle plan;
    checkCudaErrors(cufftPlan1d(&plan, new_size, CUFFT_C2C, 1));

    // Transform signal and kernel

    checkCudaErrors(cufftExecC2C(plan, (cufftComplex *)d_signal, (cufftComplex *)d_signal, CUFFT_FORWARD));

     ComplexPointwiseMulAndScale_p<<<1024, 1024>>>(d_signal, d_filter_kernel, new_size, 1.0f / new_size);   
// Check if kernel execution generated and error
    getLastCudaError("Kernel execution failed [ ComplexPointwiseMulAndScale ]");

    // Transform signal back
    //printf("Transforming signal back cufftExecC2C\n");
    checkCudaErrors(cufftExecC2C(plan, (cufftComplex *)d_signal, (cufftComplex *)d_signal, CUFFT_INVERSE));
    cudaThreadSynchronize();

    // Copy device memory to host
     Complex *h_convolved_signal = h_signal;
    checkCudaErrors(cudaMemcpy(h_convolved_signal, d_signal, mem_size,

                      cudaMemcpyDeviceToHost));
    // list=new double[new_size];
    for(int i=0;i<new_size;i++)
    {
        list[i]=h_convolved_signal[i].x*h_convolved_signal[i].x+h_convolved_signal[i].y*h_convolved_signal[i].y;
        if(list[i]>max)max=list[i];
    }


   return max;



    //Destroy CUFFT context
    checkCudaErrors(cufftDestroy(plan));

    // cleanup memory
    free(h_signal);
    free(h_filter_kernel);


    checkCudaErrors(cudaFree(d_signal));
    checkCudaErrors(cudaFree(d_filter_kernel));
    cudaDeviceReset();
}

この関数はメインで約1900回呼び出され、約1440回までスムーズに実行できますが、ここでエラーが発生します。理由がわかりません。ありがとう。