如何将此代码重写为 sse 内部函数

How to rewrite this code to sse intrinsics

本文关键字：sse 内部函数 重写 代码      更新时间：2023-10-16

我是 sse 内联函数中的新手，希望得到一些提示，以帮助使用此 9，因为这对我来说还很模糊）

我有这样的代码 

for(int k=0; k<=n-4; k+=4) 
 { 
  int xc0 = 512 + ((idx + k*iddx)>>6); 
  int yc0 = 512 + ((idy + k*iddy)>>6); 
  int xc1 = 512 + ((idx + (k+1)*iddx)>>6); 
  int yc1 = 512 + ((idy + (k+1)*iddy)>>6); 
  int xc2 = 512 + ((idx + (k+2)*iddx)>>6); 
  int yc2 = 512 + ((idy + (k+2)*iddy)>>6); 
  int xc3 = 512 + ((idx + (k+3)*iddx)>>6); 
  int yc3 = 512 + ((idy + (k+3)*iddy)>>6); 
  unsigned color0 =  working_buffer[yc0*working_buffer_size_x + xc0]; 
  unsigned color1 =  working_buffer[yc1*working_buffer_size_x + xc1]; 
  unsigned color2 =  working_buffer[yc2*working_buffer_size_x + xc2]; 
  unsigned color3 =  working_buffer[yc3*working_buffer_size_x + xc3]; 
  int adr = base_adr + k; 
  frame_bitmap[adr]  = color0; 
  frame_bitmap[adr+1]= color1; 
  frame_bitmap[adr+2]= color2; 
  frame_bitmap[adr+3]= color3; 
 }

这里都是 int/unsigned，这是循环的关键部分，不确定整数 SSE 是否会在速度上有所帮助，但想知道它是否会起作用？ Someopne可以帮忙吗？

（我使用 mingw32）

我的sse有点生疏，但你应该做的是：

xmm0: [k, k+1, k+2, k+3] //xc0, xc1,....
xmm1: [k, k+1, k+2, k+3] //yc0, yc1,....
//initialize before the loop
xmm2: [512, 512, 512, 512]
xmm3: [idx, idx, idx, idx]
xmm4: [iddx, iddx, iddx, iddx]
xmm5: [idy, idy, idy, idy]
xmm6: [iddy, iddy, iddy, iddy]
xmm7: [working_buffer_size_x, working_buffer_size_x, working_buffer_size_x, working_buffer_size_x]

计算：

xmm0 * xmm4
xmm0 + xmm3
xmm0 >> 6
xmm0 + xmm2
xmm0: [xc0, xc1, xc2, xc3]
///////////////////////////////
xmm1 * xmm6
xmm1 + xmm5
xmm1 >> 6
xmm1 + xmm2
xmm1: [yc0, yc1, yc2, yc3]
xmm1 * xmm7
xmm1 + xmm0

现在xmm1是：

xmm1: [yc0*working_buffer_size_x + xc0, yc1*working_buffer_size_x + xc1, yc2*working_buffer_size_x + xc2, yc3*working_buffer_size_x + xc3]

您在每个循环（working_buffer、frame_bitmap数组）中读取和写入内存，这些操作比计算本身慢得多，因此速度提高不会像您预期的那么多。

编辑

您需要对齐working_buffer和frame_bitmap阵列，并且 SSE4.1：

#include <emmintrin.h>
#include <smmintrin.h> //SSE4.1
int a[4] __attribute__((aligned(16)));
__m128i xmm0, xmm1, xmm2, xmm3, xmm4, xmm5, xmm6, xmm7;
xmm2 = _mm_set1_epi32(512);
xmm3 = _mm_set1_epi32(idx);
xmm4 = _mm_set1_epi32(iddx);
xmm5 = _mm_set1_epi32(idy);
xmm6 = _mm_set1_epi32(iddy);
xmm7 = _mm_set1_epi32(working_buffer_size_x);
for(k = 0; k <= n - 4; k +=4){
    xmm0 = _mm_set_epi32(k + 3, k + 2, k + 1, k);
    xmm1 = _mm_set_epi32(k + 3, k + 2, k + 1, k);
    //xmm0 * xmm4
    xmm0 = _mm_mullo_epi32(xmm0, xmm4);
    //xmm0 + xmm3
    xmm0 = _mm_add_epi32(xmm0, xmm3);
    //xmm0 >> 6
    xmm0 = _mm_srai_epi32(xmm0, 6);
    //xmm0 + xmm2
    xmm0 = _mm_add_epi32(xmm0, xmm2);

    //xmm1 * xmm6
    xmm1 = _mm_mullo_epi32(xmm1, xmm6);
    //xmm1 + xmm5
    xmm1 = _mm_add_epi32(xmm1, xmm5);
    //xmm1 >> 6
    xmm1 = _mm_srai_epi32(xmm1, 6);
    //xmm1 + xmm2
    xmm1 = _mm_add_epi32(xmm1, xmm2);

    //xmm1 * xmm7
    xmm1 = _mm_mullo_epi32(xmm1, xmm7);
    //xmm1 + xmm0
    xmm1 = _mm_add_epi32(xmm1, xmm0);

    //a[0] = yc0*working_buffer_size_x + xc0
    //a[1] = yc1*working_buffer_size_x + xc1
    //a[2] = yc2*working_buffer_size_x + xc2
    //a[3] = yc3*working_buffer_size_x + xc3
    _mm_store_si128((__m128i *)&a[0], xmm1);
    unsigned color0 =  working_buffer[ a[0] ]; 
    unsigned color1 =  working_buffer[ a[1] ]; 
    unsigned color2 =  working_buffer[ a[2] ]; 
    unsigned color3 =  working_buffer[ a[3] ]; 
    int adr = base_adr + k; 
    frame_bitmap[adr]  = color0; 
    frame_bitmap[adr+1]= color1; 
    frame_bitmap[adr+2]= color2; 
    frame_bitmap[adr+3]= color3; 
}

您可以通过避免使用直接操作内存的汇编来_mm_store_si128((__m128i *)&a[0], xmm1);或int adr = base_adr + k;来进一步优化它。

相关文章：