我遇到了一个让我抓狂的段错误问题。
这是代码:
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;
}
当我对蝴蝶使用 printf 时,会出现段错误。我正在打印蝴蝶的值,因为我想确保所有计算都正确完成。
我做错了什么?
注意:
范围采用以下值 (1024,256,64,16,4,1)
x 实数 float 组
y 虚数 float 组
数组大小为 4096
我正在使用 Intel 内在函数,因此一次加载 4 个值。
最佳答案
根据 MSDN (https://msdn.microsoft.com/en-us/library/ayeb3ayc.aspx):
You should not access the __m128 fields directly. You can, however, see these types in the debugger. A variable of type __m128 maps to the XMM[0-7] registers.
因此,您可能会遇到上述警告试图避免的情况。
关于c - 未知的段错误问题,我们在Stack Overflow上找到一个类似的问题: https://stackoverflow.com/questions/38786989/