在程序上使用openMP优化顺序运行后没有性能提升

Question

我尽可能地优化了我的顺序运行功能.当我使用openMP时,我发现性能没有任何好处.我在一个有1个内核的机器上和8个内核的机器上试过我的程序,性能是一样的.
年份设置为20,我有
1个核心:1秒.
8核:1秒.

随着年份设置为25我有
1核心:40秒.
8核心:40秒.

1核心机:我的笔记本电脑的intel核心2双核1.8 GHz,ubuntu linux
8核机器:3.25 GHz,ubuntu linux

我的程序枚举二叉树的所有可能路径,并在每个路径上做一些工作.所以我的循环大小呈指数级增长,我希望openMP线程的足迹为零.在我的循环中,我只减少一个变量.所有其他变量都是只读的.我只使用我写的函数,我认为它们是线程安全的.

我还在我的程序上运行Valgrind cachegrind.我不完全理解输出,但似乎没有缓存未命中或错误共享.

我编译

gcc -O3 -g3 -Wall -c -fmessage-length=0 -lm -fopenmp -ffast-math

我的完整程序如下.很抱歉发布了很多代码.我不熟悉openMP和C,如果不放弃主要任务,我就无法恢复更多代码.

使用openMP时如何提高性能？
它们是一些编译器标志还是C技巧会使程序运行得更快？

test.c的

#include <stdio.h>
#include <stdlib.h>
#include <math.h>
#include <omp.h>
#include "test.h"

int main(){

    printf("starting\n");
    int year=20;
    int tradingdate0=1;

    globalinit(year,tradingdate0);

    int i;
    float v=0;
    long n=pow(tradingdate0+1,year);
    #pragma omp parallel for reduction(+:v)
    for(i=0;i<n;i++)
        v+=pathvalue(i);

    globaldel();
    printf("finished\n");
    return 0;
}

//***function on which openMP is applied
float pathvalue(long pathindex) {
    float value = -ctx.firstpremium;
    float personalaccount = ctx.personalaccountat0;
    float account = ctx.firstpremium;
    int i;
    for (i = 0; i < ctx.year-1; i++) {
        value *= ctx.accumulationfactor;
        double index = getindex(i,pathindex);
        account = account * index;
        double death = fmaxf(account,ctx.guarantee[i]);
        value += qx(i) * death;
        if (haswithdraw(i)){
            double withdraw = personalaccount*ctx.allowed;
            value += px(i) * withdraw;
            personalaccount = fmaxf(personalaccount-withdraw,0);
            account = fmaxf(account-withdraw,0);
        }
    }

    //last year
    double index = getindex(ctx.year-1,pathindex);
    account = account * index;
    value+=fmaxf(account,ctx.guarantee[ctx.year-1]);

    return value * ctx.discountfactor;
}



int haswithdraw(int period){
    return 1;
}

float getindex(int period, long pathindex){
    int ndx = (pathindex/ctx.chunksize[period])%ctx.tradingdate;
    return ctx.stock[ndx];
}

float qx(int period){
    return 0;
}

float px(int period){
    return 1;
}

//****global
struct context ctx;

void globalinit(int year, int tradingdate0){
    ctx.year = year;
    ctx.tradingdate0 = tradingdate0;
    ctx.firstpremium = 1;
    ctx.riskfreerate = 0.06;
    ctx.volatility=0.25;
    ctx.personalaccountat0 = 1;
    ctx.allowed = 0.07;
    ctx.guaranteerate = 0.03;
    ctx.alpha=1;
    ctx.beta = 1;
    ctx.tradingdate=tradingdate0+1;
    ctx.discountfactor = exp(-ctx.riskfreerate * ctx.year);
    ctx.accumulationfactor = exp(ctx.riskfreerate);
    ctx.guaranteefactor = 1+ctx.guaranteerate;
    ctx.upmove=exp(ctx.volatility/sqrt(ctx.tradingdate0));
    ctx.downmove=1/ctx.upmove;

    ctx.stock=(float*)malloc(sizeof(float)*ctx.tradingdate);
    int i;
    for(i=0;i<ctx.tradingdate;i++)
        ctx.stock[i]=pow(ctx.upmove,ctx.tradingdate0-i)*pow(ctx.downmove,i);

    ctx.chunksize=(long*)malloc(sizeof(long)*ctx.year);
    for(i=0;i<year;i++)
        ctx.chunksize[i]=pow(ctx.tradingdate,ctx.year-i-1);

    ctx.guarantee=(float*)malloc(sizeof(float)*ctx.year);
    for(i=0;i<ctx.year;i++)
        ctx.guarantee[i]=ctx.beta*pow(ctx.guaranteefactor,i+1);
}

void globaldel(){
    free(ctx.stock);
    free(ctx.chunksize);
    free(ctx.guarantee);
}

test.h

float pathvalue(long pathindex);
int haswithdraw(int period);
float getindex(int period, long pathindex);
float qx(int period);
float px(int period);
//***global
struct context{
    int year;
    int tradingdate0;
    float firstpremium;
    float riskfreerate;
    float volatility;
    float personalaccountat0;
    float allowed;
    float guaranteerate;
    float alpha;
    float beta;
    int tradingdate;
    float discountfactor;
    float accumulationfactor;
    float guaranteefactor;
    float upmove;
    float downmove;
    float* stock;
    long* chunksize;
    float* guarantee;
};
struct context ctx;
void globalinit();
void globaldel();

编辑我将所有全局变量简化为常量.20年来,该计划运行速度提高了两倍(太棒了!).例如,我尝试设置线程数OMP_NUM_THREADS=4 ./test.但它并没有给我带来任何性能提升.
我的gcc可以有一些问题吗？

test.c的

#include <stdio.h>
#include <stdlib.h>
#include <time.h>
#include <math.h>
#include <omp.h>
#include "test.h"


int main(){

    starttimer();
    printf("starting\n");
    int i;
    float v=0;

    #pragma omp parallel for reduction(+:v)
    for(i=0;i<numberofpath;i++)
        v+=pathvalue(i);

    printf("v:%f\nfinished\n",v);
    endtimer();
    return 0;
}

//function on which openMP is applied
float pathvalue(long pathindex) {
    float value = -firstpremium;
    float personalaccount = personalaccountat0;
    float account = firstpremium;
    int i;
    for (i = 0; i < year-1; i++) {
        value *= accumulationfactor;
        double index = getindex(i,pathindex);
        account = account * index;
        double death = fmaxf(account,guarantee[i]);
        value += death;
        double withdraw = personalaccount*allowed;
        value += withdraw;
        personalaccount = fmaxf(personalaccount-withdraw,0);
        account = fmaxf(account-withdraw,0);
    }

    //last year
    double index = getindex(year-1,pathindex);
    account = account * index;
    value+=fmaxf(account,guarantee[year-1]);

    return value * discountfactor;
}



float getindex(int period, long pathindex){
    int ndx = (pathindex/chunksize[period])%tradingdate;
    return stock[ndx];
}

//timing
clock_t begin;

void starttimer(){
    begin = clock();
}

void endtimer(){
    clock_t end = clock();
    double elapsed = (double)(end - begin) / CLOCKS_PER_SEC;
    printf("\nelapsed: %f\n",elapsed);
}

test.h

float pathvalue(long pathindex);
int haswithdraw(int period);
float getindex(int period, long pathindex);
float qx(int period);
float px(int period);
//timing
void starttimer();
void endtimer();
//***constant
const int year= 20 ;
const int tradingdate0= 1 ;
const float firstpremium= 1 ;
const float riskfreerate= 0.06 ;
const float volatility= 0.25 ;
const float personalaccountat0= 1 ;
const float allowed= 0.07 ;
const float guaranteerate= 0.03 ;
const float alpha= 1 ;
const float beta= 1 ;
const int tradingdate= 2 ;
const int numberofpath= 1048576 ;
const float discountfactor= 0.301194211912 ;
const float accumulationfactor= 1.06183654655 ;
const float guaranteefactor= 1.03 ;
const float upmove= 1.28402541669 ;
const float downmove= 0.778800783071 ;
const float stock[2]={1.2840254166877414, 0.7788007830714049};
const long chunksize[20]={524288, 262144, 131072, 65536, 32768, 16384, 8192, 4096, 2048, 1024, 512, 256, 128, 64, 32, 16, 8, 4, 2, 1};
const float guarantee[20]={1.03, 1.0609, 1.092727, 1.1255088100000001, 1.1592740743, 1.1940522965290001, 1.2298738654248702, 1.2667700813876164, 1.304773183829245, 1.3439163793441222, 1.384233870724446, 1.4257608868461793, 1.4685337134515648, 1.512589724855112, 1.557967416600765, 1.6047064390987882, 1.6528476322717518, 1.7024330612399046, 1.7535060530771016, 1.8061112346694148};

Answer 1

即使您的程序受益于使用OpenMP,您也不会看到它,因为您正在测量错误的时间.

clock()返回在所有线程中花费的总CPU时间.如果你运行四个线程并且每个运行1/4的时间,仍然会返回相同的值,因为4*(1/4)= 1.你应该测量挂钟时间.clock()

更换到呼叫clock()与omp_get_wtime()或gettimeofday().它们都提供高精度的挂钟定时.

PS为什么周围有这么多人clock()用于计时？