【发布时间】：2010-10-20 23:42:35
【问题描述】：
有没有办法加速这个一维卷积？我试图使 dy 缓存高效 但使用 g++ 和 -O3 编译时性能较差。
我正在与 [-1. , 0., 1] 在两个方向。 不是家庭作业。
#include<iostream>
#include<cstdlib>
#include<sys/time.h>
void print_matrix( int height, int width, float *matrix){
for (int j=0; j < height; j++){
for (int i=0; i < width; i++){
std::cout << matrix[j * width + i] << ",";
}
std::cout << std::endl;
}
}
void fill_matrix( int height, int width, float *matrix){
for (int j=0; j < height; j++){
for (int i=0; i < width; i++){
matrix[j * width + i] = ((float)rand() / (float)RAND_MAX) ;
}
}
}
#define RESTRICT __restrict__
void dx_matrix( int height, int width, float * RESTRICT in_matrix, float * RESTRICT out_matrix, float *min, float *max){
//init min,max
*min = *max = -1.F * in_matrix[0] + in_matrix[1];
for (int j=0; j < height; j++){
float* row = in_matrix + j * width;
for (int i=1; i < width-1; i++){
float res = -1.F * row[i-1] + row[i+1]; /* -1.F * value + 0.F * value + 1.F * value; */
if (res > *max ) *max = res;
if (res < *min ) *min = res;
out_matrix[j * width + i] = res;
}
}
}
void dy_matrix( int height, int width, float * RESTRICT in_matrix, float * RESTRICT out_matrix, float *min, float *max){
//init min,max
*min = *max = -1.F * in_matrix[0] + in_matrix[ width + 1];
for (int j=1; j < height-1; j++){
for (int i=0; i < width; i++){
float res = -1.F * in_matrix[ (j-1) * width + i] + in_matrix[ (j+1) * width + i] ;
if (res > *max ) *max = res;
if (res < *min ) *min = res;
out_matrix[j * width + i] = res;
}
}
}
double now (void)
{
struct timeval tv;
gettimeofday(&tv, NULL);
return (double)tv.tv_sec + (double)tv.tv_usec / 1000000.0;
}
int main(int argc, char **argv){
int width, height;
float *in_matrix;
float *out_matrix;
if(argc < 3){
std::cout << argv[0] << "usage: width height " << std::endl;
return -1;
}
srand(123);
width = atoi(argv[1]);
height = atoi(argv[2]);
std::cout << "Width:"<< width << " Height:" << height << std::endl;
if (width < 3){
std::cout << "Width too short " << std::endl;
return -1;
}
if (height < 3){
std::cout << "Height too short " << std::endl;
return -1;
}
in_matrix = (float *) malloc( height * width * sizeof(float));
out_matrix = (float *) malloc( height * width * sizeof(float));
fill_matrix(height, width, in_matrix);
//print_matrix(height, width, in_matrix);
float min, max;
double a = now();
dx_matrix(height, width, in_matrix, out_matrix, &min, &max);
std::cout << "dx min:" << min << " max:" << max << std::endl;
dy_matrix(height, width, in_matrix, out_matrix, &min, &max);
double b = now();
std::cout << "dy min:" << min << " max:" << max << std::endl;
std::cout << "time: " << b-a << " sec" << std::endl;
return 0;
}
【问题讨论】：
-
快速卷积通常使用 FFT 完成，因为卷积是一个 O(n log n) 操作，而在时域中它是 O(n*n) - 当序列具有显着长度时，这是一个巨大的差异.如果你有一个针对长信号的小卷积核，我会利用自然并行性并将其线程化到可用内核上。
标签： c++ performance optimization convolution