我想使用约 FFT
元素的数组的Intel MKL
来计算3D 300×200×200
。此3D数组以列式方式存储为double
类型的一维数组:
for( int k = 0; k < nk; k++ ) // Loop through the height.
for( int j = 0; j < nj; j++ ) // Loop through the rows.
for( int i = 0; i < ni; i++ ) // Loop through the columns.
{
ijk = i + ni * j + ni * nj * k;
my3Darray[ ijk ] = 1.0;
}
我想对输入数组执行not-in-place
FFT并防止它被修改(我需要稍后在我的代码中使用它)然后执行反向计算in-place
。我也希望零填充。
我的问题是:
FFT
函数使用的数组的大小?以下是我对此问题的尝试,对于任何评论,建议或暗示,我都会非常感谢。
#include <stdio.h>
#include "mkl.h"
int max(int a, int b, int c)
{
int m = a;
(m < b) && (m = b);
(m < c) && (m = c);
return m;
}
void FFT3D_R2C( // Real to Complex 3D FFT.
double *in, int nRowsIn , int nColsIn , int nHeightsIn ,
double *out )
{
int n = max( nRowsIn , nColsIn , nHeightsIn );
// Round up to the next highest power of 2.
unsigned int N = (unsigned int) n; // compute the next highest power of 2 of 32-bit n.
N--;
N |= N >> 1;
N |= N >> 2;
N |= N >> 4;
N |= N >> 8;
N |= N >> 16;
N++;
/* Strides describe data layout in real and conjugate-even domain. */
MKL_LONG rs[4], cs[4];
// DFTI descriptor.
DFTI_DESCRIPTOR_HANDLE fft_desc = 0;
// Variables needed for out-of-place computations.
MKL_Complex16 *in_fft = new MKL_Complex16 [ N*N*N ];
MKL_Complex16 *out_fft = new MKL_Complex16 [ N*N*N ];
double *out_ZeroPadded = new double [ N*N*N ];
/* Compute strides */
rs[3] = 1; cs[3] = 1;
rs[2] = (N/2+1)*2; cs[2] = (N/2+1);
rs[1] = N*(N/2+1)*2; cs[1] = N*(N/2+1);
rs[0] = 0; cs[0] = 0;
// Create DFTI descriptor.
MKL_LONG sizes[] = { N, N, N };
DftiCreateDescriptor( &fft_desc, DFTI_DOUBLE, DFTI_REAL, 3, sizes );
// Configure DFTI descriptor.
DftiSetValue( fft_desc, DFTI_CONJUGATE_EVEN_STORAGE, DFTI_COMPLEX_COMPLEX );
DftiSetValue( fft_desc, DFTI_PLACEMENT, DFTI_NOT_INPLACE ); // Out-of-place transformation.
DftiSetValue( fft_desc, DFTI_INPUT_STRIDES , rs );
DftiSetValue( fft_desc, DFTI_OUTPUT_STRIDES , cs );
DftiCommitDescriptor( fft_desc );
DftiComputeForward ( fft_desc, in , in_fft );
// Change strides to compute backward transform.
DftiSetValue ( fft_desc, DFTI_INPUT_STRIDES , cs);
DftiSetValue ( fft_desc, DFTI_OUTPUT_STRIDES, rs);
DftiCommitDescriptor( fft_desc );
DftiComputeBackward ( fft_desc, out_fft, out_ZeroPadded );
// Printing the zero padded 3D FFT result.
for( long long i = 0; i < (long long)N*N*N; i++ )
printf("%f\n", out_ZeroPadded[i] );
/* I don't know how to take out the zero padded results and
save the actual result in the variable named "out" */
DftiFreeDescriptor ( &fft_desc );
delete[] in_fft;
delete[] out_ZeroPadded ;
}
int main()
{
int n = 10;
double *a = new double [n*n*n]; // This array is real.
double *afft = new double [n*n*n];
// Fill the array with some 'real' numbers.
for( int i = 0; i < n*n*n; i++ )
a[ i ] = 1.0;
// Calculate FFT.
FFT3D_R2C( a, n, n, n, afft );
printf("FFT results:\n");
for( int i = 0; i < n*n*n; i++ )
printf( "%15.8f\n", afft[i] );
delete[] a;
delete[] afft;
return 0;
}
答案 0 :(得分:0)
2大小的力量
Nx,Ny,Nz
为输入矩阵的大小和nx,ny,nz
大小
for (nx=1;nx<Nx;nx<<=1);
for (ny=1;ny<Ny;ny<<=1);
for (nz=1;nz<Nz;nz<<=1);
现在将memset零填充为零,然后复制矩阵线
N^3
而不是nx*ny*nz
会导致大幅减速nx,ny,nz
彼此不相近输出很复杂
a
是输入实矩阵afft
输出复杂矩阵double *afft = new double [2*nx*ny*nz];
"\r\n"
行之后可以查看3D DFFT
double lin[2*max(nx,ny,nz)];