perflab实验报告

1、课程实验报告 课 程 名 称： 计算机组成与结构 实验项目名称： perflab-handout 专 业 班 级： 姓 名： 学 号： 指 导 教 师： 杨科华 完 成 时 间： 2016 年 5 月 27 日信息科学与工程学院实验题目：perflab程序性能调优实验目的：理解编译器，学习程序优化，从优化程序代码和程序执行速度两方面着手。实验要求：本次实验，要求针对每个函数、每个人均至少写出3种优化版本、并根据driver报告的结果进行性能分析实验环境: ubuntu-15.10、 x32系统 、VMware workstation实验内容及操作步骤：将下载下来的 kernels.c 中的 r

2、otate、smooth 函数进行优化。rotate函数的作用是将图像逆时针旋转90，smooth函数的作用是对于图像中的每一个像素点，取它和周围的像素点的平均值，让图片变得模糊。下面对代码进行逐一优化。源代码的CPE测试：1.Naive_rotate 1)源代码:char naive_rotate_descr = naive_rotate: Naive baseline implementation;void naive_rotate(int dim, pixel *src, pixel *dst) int i, j; for (i = 0; i dim; i+)for (j = 0; j

3、dim; j+) dstRIDX(dim-1-j, i, dim) = srcRIDX(i, j, dim);2）分析：这段代码的作用就是用一个双层循环将所有的像素进行行列调位、导致整幅图画进行了 90 度旋转。然而分析一下代码就能发现一个十分简单的优化方法：因为在最内层循环中，j的值每次都会改变，所以每执行一次赋值就要计算一次dim-1-j，算多了自然就慢了。我们可以利用简单的数学技巧改写公式，将赋值语句改成dstRIDX(i, j, dim) = srcRIDX(j, dim-i-1, dim); 这样就不用每次都计算了。3）优化代码1如下：char naive_rotate_descr2

4、 = naive_rotate2: only change the place of i and j;void naive_rotate2(int dim, pixel *src, pixel *dst) int i, j; for (i = 0; i dim; i+) for (j = 0; j dim; j+) dstRIDX(i, j, dim) = srcRIDX(j, dim-i-1, dim);/i change less 优化结果如下：这是一种最为简单的优化方案，由图可知，速度提升不大，性能优化结果也不是很好。再分析源代码，从 cache 友好性来分析，这个代码的效率机会很低，

5、所以按照 cache 的大小， 应在存储的时候进行 32 个像素依次存储 （列 存储）。做到 cache 友好这样就可以可以大幅度提高效率。4）优化代码2如下：char rotate_descr2 = rotate2: version2breakinto4*4blocks; void rotate2(int dim, pixel *src, pixel*dst) int i, j,ii,jj; for(ii=0; ii dim; ii+=4)for(jj=0; jj dim; jj+=4)for(i=ii; i ii+4; i+)for(j=jj; j jj+4; j+) dstRIDX(di

6、m-1-j,i,dim) = srcRIDX(i,j,dim); 优化结果如下：用分块的方式，进行优化。将整个程序分成4*4的小块，提高空间局部性5）优化代码3如下：char rotate_descr3 = rotate3: version3 break into 32*32 blocks;void rotate3(int dim, pixel *src, pixel *dst) int i, j,ii,jj; for(ii=0; ii dim; ii+=32)for(jj=0; jj dim; jj+=32)for(i=ii; i ii+32; i+)for(j=jj; j jj+32; j

7、+) dstRIDX(dim-1-j,i,dim) = srcRIDX(i,j,dim); 优化结果如下：分成32*32块，提高空间局部性6）优化代码4如下：char rotate_descr4 = rotate4: Current working version,using pointer rather than computing address;void rotate4(int dim, pixel *src, pixel *dst) int i; int j; int tmp1=dim*dim; int tmp2=dim *31; int tmp3=tmp1-dim; int tmp4

8、=tmp1+32; int tmp5=dim+31; dst+=tmp3; for(i=0; i dim; i+=32) for(j=0;jdim;j+) *dst=*src; dst+;src+=dim; *dst=*src; dst+;src+=dim; *dst=*src; dst+;src+=dim; *dst=*src; dst+;src+=dim; *dst=*src; dst+;src+=dim; *dst=*src; dst+;src+=dim; *dst=*src; dst+;src+=dim; *dst=*src; dst+;src+=dim; *dst=*src; dst

9、+;src+=dim; *dst=*src; dst+;src+=dim; *dst=*src; dst+;src+=dim; *dst=*src; dst+;src+=dim; *dst=*src; dst+;src+=dim; *dst=*src; dst+;src+=dim; *dst=*src; dst+;src+=dim; *dst=*src; dst+;src+=dim; *dst=*src; dst+;src+=dim; *dst=*src; dst+;src+=dim; *dst=*src; dst+;src+=dim; *dst=*src; dst+;src+=dim; *d

10、st=*src; dst+;src+=dim; *dst=*src; dst+;src+=dim; *dst=*src; dst+;src+=dim; *dst=*src; dst+;src+=dim; *dst=*src; dst+;src+=dim; *dst=*src; dst+;src+=dim; *dst=*src; dst+;src+=dim; *dst=*src; dst+;src+=dim; *dst=*src; dst+;src+=dim; *dst=*src; dst+;src+=dim; *dst=*src; dst+;src+=dim; *dst=*src; src+;

11、 src-=tmp2; dst-=tmp5; src+=tmp2; dst+=tmp4; 优化结果如下：用循环展开，分成32路并行来写2.Naive_smooth1)源代码char naive_smooth_descr = naive_smooth: Naive baseline implementation;void naive_smooth(int dim, pixel *src, pixel *dst) int i, j; for (i = 0; i dim; i+)for (j = 0; j dim; j+) dstRIDX(i, j, dim) = avg(dim, i, j, sr

12、c);CPES性能如下：2）分析这段代码很多次地调用 avg 函数，而 avg 函数内也频繁调用 initialize_pixel_sum 、 accumulate_sum、assign_sum_to_pixel 这几个函数，且含有 2 层 for 循环。虽然会以损害程序的模块性为代价，但消除函数调用的时间开销，得到的代码运行速度会快得多。所以，需要改写代码，不调用 avg 函数。 3）优化代码1如下：char smooth_descr1 = smooth1: with less func call and grossly simplified calculation for central

13、parts;void smooth1(int dim, pixel *src, pixel *dst) int i, j, ii, jj; pixel_sum sum; pixel current_pixel, cp; for (j = 0; j dim; j+) dstRIDX(0, j, dim) = avg(dim, 0, j, src); dstRIDX(dim-1, j, dim) = avg(dim, dim-1, j, src); for (i = 0; i dim; i+) dstRIDX(i, 0, dim) = avg(dim, i, 0, src); dstRIDX(i,

14、 dim-1, dim) = avg(dim, i, dim-1, src); for (i = 1; i dim-1; i+) for (j = 1; j dim-1; j+) sum.red = sum.green = sum.blue = 0; for(ii = max(i-1, 0); ii = min(i+1, dim-1); ii+) for(jj = max(j-1, 0); jj 2; dstRIDX(0,0,dim).blue=(srcRIDX(0,0,dim).blue+srcRIDX(1,0,dim).blue+srcRIDX(0,1,dim).blue+srcRIDX(

15、1,1,dim).blue)2; dstRIDX(0,0,dim).green=(srcRIDX(0,0,dim).green+srcRIDX(1,0,dim).green+srcRIDX(0,1,dim).green+srcRIDX(1,1,dim).green)2; dstRIDX(0,dim-1,dim).red=(srcRIDX(0,dim-1,dim).red+srcRIDX(1,dim-1,dim).red+srcRIDX(0,dim-2,dim).red+srcRIDX(1,dim-2,dim).red)2; dstRIDX(0,dim-1,dim).blue=(srcRIDX(

16、0,dim-1,dim).blue+srcRIDX(1,dim-1,dim).blue+srcRIDX(0,dim-2,dim).blue+srcRIDX(1,dim-2,dim).blue)2; dstRIDX(0,dim-1,dim).green=(srcRIDX(0,dim-1,dim).green+srcRIDX(1,dim-1,dim).green+srcRIDX(0,dim-2,dim).green+srcRIDX(1,dim-2,dim).green)2; dstRIDX(dim-1,0,dim).red=(srcRIDX(dim-1,0,dim).red+srcRIDX(dim

17、-2,0,dim).red+srcRIDX(dim-1,1,dim).red+srcRIDX(dim-2,1,dim).red)2; dstRIDX(dim-1,0,dim).blue=(srcRIDX(dim-1,0,dim).blue+srcRIDX(dim-2,0,dim).blue+srcRIDX(dim-1,1,dim).blue+srcRIDX(dim-2,1,dim).blue)2; dstRIDX(dim-1,0,dim).green=(srcRIDX(dim-1,0,dim).green+srcRIDX(dim-2,0,dim).green+srcRIDX(dim-1,1,d

18、im).green+srcRIDX(dim-2,1,dim).green)2; dstRIDX(dim-1,dim-1,dim).red=(srcRIDX(dim-1,dim-1,dim).red+srcRIDX(dim-1,dim-2,dim).red+srcRIDX(dim-2,dim-1,dim).red+srcRIDX(dim-2,dim-2,dim).red)2; dstRIDX(dim-1,dim-1,dim).blue=(srcRIDX(dim-1,dim-1,dim).blue+srcRIDX(dim-1,dim-2,dim).blue+srcRIDX(dim-2,dim-1,

19、dim).blue+srcRIDX(dim-2,dim-2,dim).blue)2; dstRIDX(dim-1,dim-1,dim).green=(srcRIDX(dim-1,dim-1,dim).green+srcRIDX(dim-1,dim-2,dim).green+srcRIDX(dim-2,dim-1,dim).green+srcRIDX(dim-2,dim-2,dim).green)2; /boarderfor(i=1;idim-1;i+) dstRIDX(i,0,dim).red=(srcRIDX(i,0,dim).red+srcRIDX(i-1,0,dim).red+srcRI

20、DX(i-1,1,dim).red+srcRIDX(i,1,dim).red+srcRIDX(i+1,0,dim).red+srcRIDX(i+1,1,dim).red)/6; dstRIDX(i,0,dim).blue=(srcRIDX(i,0,dim).blue+srcRIDX(i-1,0,dim).blue+srcRIDX(i-1,1,dim).blue+srcRIDX(i,1,dim).blue+srcRIDX(i+1,0,dim).blue+srcRIDX(i+1,1,dim).blue)/6; dstRIDX(i,0,dim).green=(srcRIDX(i,0,dim).gre

21、en+srcRIDX(i-1,0,dim).green+srcRIDX(i-1,1,dim).green+srcRIDX(i,1,dim).green+srcRIDX(i+1,0,dim).green+srcRIDX(i+1,1,dim).green)/6;for(i=1;idim-1;i+) dstRIDX(i,dim-1,dim).red=(srcRIDX(i,dim-1,dim).red+srcRIDX(i-1,dim-1,dim).red+srcRIDX(i-1,dim-2,dim).red+srcRIDX(i,dim-2,dim).red+srcRIDX(i+1,dim-1,dim)

22、.red+srcRIDX(i+1,dim-2,dim).red)/6; dstRIDX(i,dim-1,dim).blue=(srcRIDX(i,dim-1,dim).blue+srcRIDX(i-1,dim-1,dim).blue+srcRIDX(i-1,dim-2,dim).blue+srcRIDX(i,dim-2,dim).blue+srcRIDX(i+1,dim-1,dim).blue+srcRIDX(i+1,dim-2,dim).blue)/6; dstRIDX(i,dim-1,dim).green=(srcRIDX(i,dim-1,dim).green+srcRIDX(i-1,di

23、m-1,dim).green+srcRIDX(i-1,dim-2,dim).green+srcRIDX(i,dim-2,dim).green+srcRIDX(i+1,dim-1,dim).green+srcRIDX(i+1,dim-2,dim).green)/6; for(j=1;jdim-1;j+) dstRIDX(0,j,dim).red=(srcRIDX(0,j,dim).red+srcRIDX(0,j-1,dim).red+srcRIDX(1,j-1,dim).red+srcRIDX(1,j,dim).red+srcRIDX(0,j+1,dim).red+srcRIDX(1,j+1,d

24、im).red)/6; dstRIDX(0,j,dim).blue=(srcRIDX(0,j,dim).blue+srcRIDX(0,j-1,dim).blue+srcRIDX(1,j-1,dim).blue+srcRIDX(1,j,dim).blue+srcRIDX(0,j+1,dim).blue+srcRIDX(1,j+1,dim).blue)/6; dstRIDX(0,j,dim).green=(srcRIDX(0,j,dim).green+srcRIDX(0,j-1,dim).green+srcRIDX(1,j-1,dim).green+srcRIDX(1,j,dim).green+s

25、rcRIDX(0,j+1,dim).green+srcRIDX(1,j+1,dim).green)/6; for(j=1;jdim-1;j+) dstRIDX(dim-1,j,dim).red=(srcRIDX(dim-1,j,dim).red+srcRIDX(dim-1,j+1,dim).red+srcRIDX(dim-1,j-1,dim).red+srcRIDX(dim-2,j,dim).red+srcRIDX(dim-2,j+1,dim).red+srcRIDX(dim-2,j-1,dim).red)/6; dstRIDX(dim-1,j,dim).blue=(srcRIDX(dim-1

26、,j,dim).blue+srcRIDX(dim-1,j+1,dim).blue+srcRIDX(dim-1,j-1,dim).blue+srcRIDX(dim-2,j,dim).blue+srcRIDX(dim-2,j+1,dim).blue+srcRIDX(dim-2,j-1,dim).blue)/6; dstRIDX(dim-1,j,dim).green=(srcRIDX(dim-1,j,dim).green+srcRIDX(dim-1,j+1,dim).green+srcRIDX(dim-1,j-1,dim).green+srcRIDX(dim-2,j,dim).green+srcRI

27、DX(dim-2,j+1,dim).green+srcRIDX(dim-2,j-1,dim).green)/6; /common for(i=1;idim-1;i+) for(j=1;jdim-1;j+) dstRIDX(i,j,dim).red=(srcRIDX(i,j,dim).red+srcRIDX(i+1,j,dim).red+srcRIDX(i-1,j,dim).red+srcRIDX(i,j-1,dim).red+srcRIDX(i+1,j-1,dim).red+srcRIDX(i-1,j-1,dim).red+srcRIDX(i,j+1,dim).red+srcRIDX(i+1,

28、j+1,dim).red+srcRIDX(i-1,j+1,dim).red)/9; dstRIDX(i,j,dim).blue=(srcRIDX(i,j,dim).blue+srcRIDX(i+1,j,dim).blue+srcRIDX(i-1,j,dim).blue+srcRIDX(i,j-1,dim).blue+srcRIDX(i+1,j-1,dim).blue+srcRIDX(i-1,j-1,dim).blue+srcRIDX(i,j+1,dim).blue+srcRIDX(i+1,j+1,dim).blue+srcRIDX(i-1,j+1,dim).blue)/9; dstRIDX(i,j,