相关疑难解决方法(0)

我正在调查矢量化对程序性能的影响.在这方面,我写了以下代码:

#include <stdio.h>
#include <sys/time.h>
#include <stdlib.h>

#define LEN 10000000

int main(){

    struct timeval stTime, endTime;

    double* a = (double*)malloc(LEN*sizeof(*a));
    double* b = (double*)malloc(LEN*sizeof(*b));
    double* c = (double*)malloc(LEN*sizeof(*c));

    int k;
    for(k = 0; k < LEN; k++){
        a[k] = rand();
        b[k] = rand();
    }

    gettimeofday(&stTime, NULL);

    for(k = 0; k < LEN; k++)
        c[k] = a[k] * b[k];

    gettimeofday(&endTime, NULL);

    FILE* fh = fopen("dump", "w");
    for(k = 0; k < LEN; k++)
        fprintf(fh, "c[%d] = %f\t", k, c[k]);
    fclose(fh);

    double …

我有以下代码使用预先计算的内存表进行Sin/Cos函数.在下面的示例中,该表具有1024*128项,涵盖从0到2pi的所有Sin/Cos值.我知道我可以使用Sin/Cos对称并只保留1/4的值,但是在计算值时我会有更多'ifs'.

private const double PI2 = Math.PI * 2.0; 
private const int TABLE_SIZE = 1024 * 128;
private const double TABLE_SIZE_D = (double)TABLE_SIZE;
private const double FACTOR = TABLE_SIZE_D / PI2;

private static double[] _CosineDoubleTable;
private static double[] _SineDoubleTable;

设置转换表

private static void InitializeTrigonometricTables(){
   _CosineDoubleTable = new double[TABLE_SIZE];
   _SineDoubleTable = new double[TABLE_SIZE];

   for (int i = 0; i < TABLE_SIZE; i++){
      double Angle = ((double)i / TABLE_SIZE_D) * PI2;
      _SineDoubleTable[i] = Math.Sin(Angle);
      _CosineDoubleTable[i] = Math.Cos(Angle);
   }
}

价值是弧度的两倍.

Value %= …