我有一個分段故障問題,讓我發瘋。未知分段故障問題
這是代碼:
for (k = 0; k < range; k=k+4)
{
int k1,k2,kfactor,k1factor,k2factor;
__m128 bfly0_rv, bfly1_rv, bfly2_rv, bfly3_rv;
__m128 bfly0_iv, bfly1_iv, bfly2_iv, bfly3_iv;
__m128 x_n2_vec, x_N2_vec, x_N2_2_vec, x_N2_3_vec;
__m128 y_n2_vec, y_N2_vec, y_N2_2_vec, y_N2_3_vec;
///////////
//factors//
///////////
k1=2*k;
k2=3*k;
kfactor = k * factor;
k1factor = k1 * factor;
k2factor = k2 * factor;
//printf("%d \t %d \t %d \n",kfactor,k1factor,k2factor);
//////////////
//Load input//
//////////////
//real parts//
__M128_MM_LOAD_PS(x_n2_vec,&x[n2]);
__M128_MM_LOAD_PS(x_N2_vec,&x[N2]);
__M128_MM_LOAD_PS(x_N2_2_vec,&x[N2_2]);
__M128_MM_LOAD_PS(x_N2_3_vec,&x[N2_3]);
//imaginary parts//
__M128_MM_LOAD_PS(y_n2_vec,&y[n2]);
__M128_MM_LOAD_PS(y_N2_vec,&y[N2]);
__M128_MM_LOAD_PS(y_N2_2_vec,&y[N2_2]);
__M128_MM_LOAD_PS(y_N2_3_vec,&y[N2_3]);
///////////////
//butterflies//
///////////////
//additions//
//Butterfly 0//
__M128_MM_ADD_PS(bfly0_rv,x_n2_vec,x_N2_vec)
__M128_MM_ADD_PS(bfly0_rv,bfly0_rv,x_N2_2_vec)
__M128_MM_ADD_PS(bfly0_rv,bfly0_rv,x_N2_3_vec)
__M128_MM_ADD_PS(bfly0_iv,y_n2_vec,y_N2_vec)
__M128_MM_ADD_PS(bfly0_iv,bfly0_iv,y_N2_2_vec)
__M128_MM_ADD_PS(bfly0_iv,bfly0_iv,y_N2_3_vec)
//Butterfly 1//
__M128_MM_ADD_PS(bfly1_rv,x_n2_vec,y_N2_vec)
__M128_MM_SUB_PS(bfly1_rv,bfly1_rv,x_N2_2_vec)
__M128_MM_SUB_PS(bfly1_rv,bfly1_rv,y_N2_3_vec)
__M128_MM_SUB_PS(bfly1_iv,y_n2_vec,x_N2_vec)
__M128_MM_SUB_PS(bfly1_iv,bfly1_iv,y_N2_2_vec)
__M128_MM_ADD_PS(bfly1_iv,bfly1_iv,x_N2_3_vec)
//Butterfly 2//
__M128_MM_SUB_PS(bfly2_rv,x_n2_vec,x_N2_vec)
__M128_MM_ADD_PS(bfly2_rv,bfly2_rv,x_N2_2_vec)
__M128_MM_SUB_PS(bfly2_rv,bfly2_rv,x_N2_3_vec)
__M128_MM_SUB_PS(bfly2_iv,y_n2_vec,y_N2_vec)
__M128_MM_ADD_PS(bfly2_iv,bfly2_iv,y_N2_2_vec)
__M128_MM_SUB_PS(bfly2_iv,bfly2_iv,y_N2_3_vec)
//Butterfly 3//
__M128_MM_SUB_PS(bfly3_rv,x_n2_vec,y_N2_vec)
__M128_MM_SUB_PS(bfly3_rv,bfly3_rv,x_N2_2_vec)
__M128_MM_ADD_PS(bfly3_rv,bfly3_rv,y_N2_3_vec)
__M128_MM_ADD_PS(bfly3_iv,y_n2_vec,x_N2_vec)
__M128_MM_SUB_PS(bfly3_iv,bfly3_iv,y_N2_2_vec)
__M128_MM_SUB_PS(bfly3_iv,bfly3_iv,x_N2_3_vec)
printf("%f \t %f \t %f \t %f \t %f \t %f \t %f \t %f \n",bfly0_rv[0],bfly0_iv[0],bfly1_rv[0],bfly1_iv[0],bfly2_rv[0],bfly2_iv[0],bfly3_rv[0],bfly3_iv[0]);
printf("%f \t %f \t %f \t %f \t %f \t %f \t %f \t %f \n",bfly0_rv[1],bfly0_iv[1],bfly1_rv[1],bfly1_iv[1],bfly2_rv[1],bfly2_iv[1],bfly3_rv[1],bfly3_iv[1]);
printf("%f \t %f \t %f \t %f \t %f \t %f \t %f \t %f \n",bfly0_rv[2],bfly0_iv[2],bfly1_rv[2],bfly1_iv[2],bfly2_rv[2],bfly2_iv[2],bfly3_rv[2],bfly3_iv[2]);
printf("%f \t %f \t %f \t %f \t %f \t %f \t %f \t %f \n",bfly0_rv[3],bfly0_iv[3],bfly1_rv[3],bfly1_iv[3],bfly2_rv[3],bfly2_iv[3],bfly3_rv[3],bfly3_iv[3]);
n2 = n2 + 4;
N2 = N2 + 4;
N2_2 = N2_2 + 4;
N2_3 = N2_3 + 4;
}
分割的故障出現時,我使用的蝴蝶中的printf。我正在打印蝴蝶的值,因爲我想確保所有計算都正確完成。
我做錯了什麼?
注意:
範圍正在採取以下值(1024,256,64,16,4,1)
X陣列浮子的實數
y虛構陣列
陣列大小爲40 96
我使用的是英特爾內部函數,所以我一次加載4個值。
嘗試將其降低爲仍然存在段錯誤的[mcve]。它不必執行FFT,只需使用一對內在函數並嘗試打印它們即可。 –