2

以下代码已从此处改编，以适用于使用 cufftPlan1d 的单个 1D 转换。最终，我想执行一个批处理就地 R2C 转换，但下面的代码使用单独的输入和输出数组执行单个转换。

如何调整此代码以就地执行转换，从而减少设备上分配的内存量？

感谢
Cuda 6.5 - 注意：我正在 MATLAB 2015a 中的 mexFunction 中运行代码

代码：

#include <stdlib.h>
#include <stdio.h>
#include <cuda_runtime.h>
#include <cufft.h>
#define DATASIZE 8
#define BATCH 1
#define gpuErrchk(ans) { gpuAssert((ans), __FILE__, __LINE__); }
inline void gpuAssert(cudaError_t code, const char *file, int line, bool  abort=true)
{
   if (code != cudaSuccess) 
   {
        fprintf(stderr,"GPUassert: %s %s %d\n", cudaGetErrorString(code), file, line);            
        if (abort) exit(code);
   }
}

void main(int argc, char **argv)
{   

// --- Host side input data allocation and initialization
cufftReal *hostInputData = (cufftReal*)malloc(DATASIZE*sizeof(cufftReal));
for (int j=0; j<DATASIZE; j++) hostInputData[j] = (cufftReal)(j + 1);

// --- Device side input data allocation and initialization
cufftReal *deviceInputData; 
gpuErrchk(cudaMalloc((void**)&deviceInputData, DATASIZE * sizeof(cufftReal)));
cudaMemcpy(deviceInputData, hostInputData, DATASIZE * sizeof(cufftReal), cudaMemcpyHostToDevice);

// --- Host side output data allocation
cufftComplex *hostOutputData = (cufftComplex*)malloc((DATASIZE / 2 + 1) * BATCH * sizeof(cufftComplex));

// --- Device side output data allocation
cufftComplex *deviceOutputData;   gpuErrchk(cudaMalloc((void**)&deviceOutputData, (DATASIZE / 2 + 1) * sizeof(cufftComplex)));

cufftResult cufftStatus;
cufftHandle handle;

cufftStatus = cufftPlan1d(&handle, DATASIZE, CUFFT_R2C, BATCH);
if (cufftStatus != cudaSuccess) { mexPrintf("cufftPlan1d failed!"); }       

cufftStatus = cufftExecR2C(handle,  deviceInputData, deviceOutputData);
if (cufftStatus != cudaSuccess) { mexPrintf("cufftExecR2C failed!"); }  

// --- Device->Host copy of the results
gpuErrchk(cudaMemcpy(hostOutputData, deviceOutputData, (DATASIZE / 2 + 1) * sizeof(cufftComplex), cudaMemcpyDeviceToHost));

for (int j=0; j<(DATASIZE / 2 + 1); j++)
        printf("%i %f %f\n", j, hostOutputData[j].x, hostOutputData[j].y);

cufftDestroy(handle);
gpuErrchk(cudaFree(deviceOutputData));
gpuErrchk(cudaFree(deviceInputData));

}
4

2 回答 2

0

该解决方案已经在另一个答案中给出：https ://stackoverflow.com/a/19208070/678093

对于您的示例，这意味着：

将输入分配为 cufftComplex：

cufftComplex *deviceInputData;
gpuErrchk(cudaMalloc((void**)&deviceInputData, DATASIZE * sizeof(cufftComplex)));
cudaMemcpy(deviceInputData, hostInputData, DATASIZE * sizeof(cufftReal), cudaMemcpyHostToDevice);

就地转换：

cufftStatus = cufftExecR2C(handle,  (cufftReal *)deviceInputData, deviceInputData);
gpuErrchk(cudaMemcpy(hostOutputData, deviceInputData, (DATASIZE / 2 + 1) * sizeof(cufftComplex), cudaMemcpyDeviceToHost));

顺便说一句：MATLAB 还包含 fft() 的 GPU 加速版本，也许这对您也有用： http: //de.mathworks.com/help/distcomp/run-built-in-functions-on-a- gpu.html#btjw5gk

于 2015-03-25T17:19:31.707 回答
0

这是我自己的完整解决方案，从 cufftReal 开始

void process(double *x, double *y, size_t n){
// --- Host side input data allocation and initialization
cufftReal *hostInputData = (cufftReal*)malloc(DATASIZE*sizeof(cufftReal));
for (int j=0; j<DATASIZE; j++) hostInputData[j] = (cufftReal)x[j];

// --- Device side input data allocation and initialization
cufftReal *deviceData; 
gpuErrchk(cudaMalloc((void**)&deviceData, (DATASIZE / 2 + 1) * BATCH * sizeof(cufftComplex)));
cudaMemcpy(deviceData, hostInputData, DATASIZE * sizeof(cufftReal), cudaMemcpyHostToDevice);

// --- Host side output data allocation
cufftComplex *hostOutputData = (cufftComplex*)malloc((DATASIZE / 2 + 1) * BATCH * sizeof(cufftComplex));

cufftResult cufftStatus;
cufftHandle handle;

cufftStatus = cufftPlan1d(&handle, DATASIZE, CUFFT_R2C, BATCH);
if (cufftStatus != cudaSuccess) { mexPrintf("cufftPlan1d failed!"); }       

cufftStatus = cufftExecR2C(handle,  deviceData, (cufftComplex*)deviceData);
if (cufftStatus != cudaSuccess) { mexPrintf("cufftExecR2C failed!"); }  

// --- Device->Host copy of the results
gpuErrchk(cudaMemcpy(hostOutputData, deviceData, (DATASIZE / 2 + 1) * sizeof(cufftComplex), cudaMemcpyDeviceToHost));

for (int j=0; j<(DATASIZE / 2 + 1); j++)
        mexPrintf("%i %f %f\n", j, hostOutputData[j].x, hostOutputData[j].y);

cufftDestroy(handle);
gpuErrchk(cudaFree(deviceData));}
于 2015-03-25T19:00:07.957 回答