的main.c

Question

前言

最近，我将OpenMP实施到我们小组的项目代码中。主要运行两个for循环;外部控制'运行'，而内部控制'运行'。生成完全独立于不同的运行，但在同一次运行中依赖于其他代。

这个想法是并行化外部循环，即“运行”循环，同时让每个线程在分配给它的任何特定运行编号上保持世代的进化。

问题

当设置OMP_THREADS = 1时，即让程序只用一个线程运行时，它会顺利运行。如果此数字更高，我会收到以下错误：

Unhandled exception at 0x00F5C4C3 in projectc.exe: 0xC0000005: Access violation writing location 0x00000072.

以下内容出现在Visual Studio的“Autos”部分中：

（注意：t，t->active_cells和t->cellx为“错误红色”，其余为白色时出现此错误）

如果我将default(none)更改为外部循环上方default(shared)的{{1}}，则移除#pragma，t和s从bn（这些是在外部文件中初始化的结构），然后程序在冻结之前在每个线程上正常运行一代（虽然CPU活动显示两个线程仍然以与之前相同的强度运行）。

尝试解决方案

我无法弄清楚出了什么问题。在外部循环之外尝试一个简单的threadprivate当然不起作用，但我也尝试将所有main声明为#pragma omp parallel for，将外部循环声明为#pragma omp parallel。还尝试了其他一些微妙的方法，这使我得出结论，它必须与线程之间共享变量的方式有关...因为所有运行，所以线程都是独立的，所有这些都是变量可以设置为私有;虽然您在#pragma omp for中看到了一些重叠。

代码附于下方。

的main.c

shared(..)

结构

/* General Includes */
#include <stdio.h> 
#include <stdlib.h>
#include <string.h>
#include <time.h>
#include <omp.h>

/* Project Includes */
#include "main.h"
#include "randgen.h"
#include "board7.h"
#include "tissue.h"
#include "io.h"

#define BitFlp(arg,posn) ((arg) ^ (1L << (posn)))
#define BitClr(arg,posn) ((arg) & ~(1L << (posn)))

#define display_dbg 1 //Controls whether print statements in main.c are displayed.
#define display_time 1 //Controls whether timing print statements are executed.
#define BILLION 1000000000L;

#define num_runs 10 //Controls number of runs per simulation
#define num_gens 4000//Controls number of generations per run

#define OMP_THREADS 1 // Max number of threads used if OpenMP is enabled

int n, i, r, j, z, x, sxa, y, flagb, m;
int j1, j2;
char a;
int max_fit_gen, collect_data, lb_run, w, rn, sx;
float f, max_fitness;
tissuen *fx;
input_vec dx;
calookup ra;

#pragma omp threadprivate(n, r, j, x, z, sxa, y, flagb, m, \
        j1, j2, a, max_fit_gen, collect_data, lb_run, w, \
    rn, sx, f, max_fitness, fx, dx, ra, run_data, t, s, bn)

int main(int argc, char *argv[])
{

    int* p = 0x00000000;   // pointer to NULL
        char sa[256];
    char ss[10];
    long randn;
    boardtable ba;
    srand((unsigned)time(NULL));
    init_mm();
    randn = number_range(1, 100);

    #ifdef OS_WINDOWS
    // Timing parameters
        LARGE_INTEGER clk_freq;
    LARGE_INTEGER t1, t2, t3;
    #endif

    #ifdef OS_UNIX
    struct timespec clk_freq, t1, t2, t3;
    #endif

    double avg_gen_time, avg_run_time, run_time, sim_time, est_run_time, est_sim_time;

    // File System and IO Parameters
    char cwd[FILENAME_MAX];
    getcwd(&cwd, sizeof(cwd));
    char curState[FILENAME_MAX];
    char recState[FILENAME_MAX];
    char recMode[FILENAME_MAX];
    char curGen[FILENAME_MAX];
    char curRun[FILENAME_MAX];
    char genTmp[FILENAME_MAX];

    strcpy(curState, cwd);
    strcpy(recState, cwd);
    strcpy(recMode, cwd);
    strcpy(curGen, cwd);
    strcpy(curRun, cwd);
    strcpy(genTmp, cwd);

    #ifdef OS_WINDOWS
    strcat(curState, "\\current.txt");
    strcat(recState, "\\recover.txt");
    strcat(recMode, "\\recovermode.txt");
    strcat(curGen, "\\gen.txt");
    strcat(curRun, "\\run");
    strcat(genTmp, "\\tmp\\gentmp");
    #endif

    #ifdef OS_UNIX
    strcat(curState, "/current.txt");
    strcat(recState, "/recover.txt");
    strcat(recMode, "/recovermode.txt");
    strcat(curGen, "/gen.txt");
    strcat(curRun, "/run");
    strcat(genTmp, "/tmp/gentmp");
    #endif

    //Read current EA run variables (i.e. current run number, generation, recover mode status)
    z = readorcreate(curState);
    x = readorcreate(recState);
    sxa = readorcreate(recMode);
    y = readorcreate(curGen);

    //Initialize simulation parameters
    s.count = 0;

    s.x[0] = 0;
    s.y[0] = 0;

    s.addvec[0] = 0;

    s.bestnum = 0;
    s.countb = 0;
    s.count = 0;
    initialize_sim_param(&s, 0, 200);

    collect_data = 0;

    //Build a collection of experiment initial conditions
    buildboardcollection7(&bn);

    //Determine clock frequency.
    #ifdef OS_WINDOWS
    if (display_time)   get_frequency(&clk_freq);
    #endif

    #ifdef OS_UNIX
    if (display_time)   get_frequency(CLOCK_REALTIME, &clk_freq);
    #endif


//Start simulation timer
    #ifdef OS_WINDOWS
    if (display_time)   read_clock(&t1);
    #endif

    #ifdef OS_UNIX
    if (display_time)   read_clock(CLOCK_REALTIME, &t1);
    #endif

#pragma omp parallel for schedule(static) default(none) num_threads(OMP_THREADS) \
            private(sa, ss, randn, ba, t2, t3, avg_gen_time, avg_run_time, sim_time, \
        run_time, est_run_time, est_sim_time) \
            shared(i, cwd, recMode, curRun, curGen, curState, genTmp, clk_freq, t1)
for (i = z; i < num_runs; i++)
{


    // randomly initialize content of  tissue population
    initialize_tissue_pop_s2(&(t.tgen[0]), &s);
    initialize_tissue_pop_s2(&(t.tgen[1]), &s);

    max_fit_gen = 0;
    max_fitness = 0.0;
    flagb = 0;

    if ((i == z) && (x == 1))
    {
        w = y;
    }
    else
    {
        w = 0;
    }

    rn = 200;
    j1 = 0;

    s.run_num = i;
    s.maxfitness = 0.0;

    //Start run timer
        #ifdef OS_WINDOWS
    if (display_time)   read_clock(&t2);
        #endif

        #ifdef OS_UNIX
    if (display_time)   read_clock(CLOCK_REALTIME, &t2);
        #endif

        #if defined(_OPENMP)
    printf("\n ======================================= \n");
    printf("  OpenMP Status Message \n");
    printf("\n --------------------------------------- \n");
    printf("| RUN %d : \n", i);
    printf("|   New Thread Process (Thread %d) \n", omp_get_thread_num());
    printf("|   Available Threads: %d of %d \n", omp_get_num_threads(), omp_get_max_threads());
    printf(" ======================================= \n\n");
        #endif

    for (j = w; j < num_gens; j++)
    {

        // Flips on lightboard data collection. See board7.h.
        if (enable_collection == 1) {
            if ((i >= run_collect) && (j >= gen_collect)) { collect_data = 1; }
        }

        sx = readcurrent(recMode);

        // Pseudo loop code. Uses bit flipping to cycle through boards.
        j2 = ~(j1)& 1;
        if (display_dbg)    printf("start evaluation...\n");

        // evaluate tissue
        // Most of the problems in the code happen here.
        evaluatepopulation_tissueb(&(t.tgen[j1]), &ra, &bn, &s, j, i);
        if (display_dbg)    printf("\n");

        // display fitness stats to screen
        printmaxfitness(&(t.tgen[j1]), i, j, j1, &cwd);

        if (display_dbg)    printf("start tournament...\n");

        // Perform tournament selection and have children ready for evaluation
        // Rarely have to touch. Figure out best parents. Crossover operator.
        // Create a subgroup. Randomly pick individuals from the population.
        // Pick fittest individuals out of the random group.
        // 2 parents and 2 children. Children replace parents.
        tournamentsel_tissueb(&(t.tgen[j1]), &(t.tgen[j2]), &s);

        printf("Tournament selection complete.\n");

        // keep track of best fitness during run
        if (t.tgen[j1].fit_max > max_fitness)
        {
            max_fitness = t.tgen[j1].fit_max;
            max_fit_gen = j;
        }

        if ((t.tgen[j1].fit_max > 99.0) && (flagb == 0))
        {
            flagb = 1;
            run_data.fit90[i] = t.tgen[j1].fit_max;
            run_data.gen90[i] = j;
        }

        sa[0] = 0;
        strcat(sa, curRun);
        sprintf(ss, "%d", i);
        strcat(sa, ss);
        strcat(sa, ".txt");

        printf("Write fitness epc...\n");

        // write fitness stats to file
        writefitnessepc(sa, &(t), j1, j);

        printf("Write fitness complete.\n");

        // trunk for saving population to disk
        if (sx != 0)
        {
            sa[0] = 0;
            strcat(sa, genTmp);
            sprintf(ss, "%d", 1);
            strcat(sa, ss);
            strcat(sa, ".txt");

            if (display_dbg)    printf("Saving Current Run\n");
        }

        //update current generation to file
        writecurrent(curGen, j + 1);

        if (display_time && j > 0 && (j % 10 == 0 || j % (num_gens - 1) == 0))
        {
            #ifdef OS_WINDOWS
            read_clock(&t3);
            sim_time = (t3.QuadPart - t1.QuadPart) / clk_freq.QuadPart;
            run_time = (t3.QuadPart - t2.QuadPart) / clk_freq.QuadPart;
            #endif

            #ifdef OS_UNIX
            read_clock(CLOCK_REALTIME, &t3);
            sim_time = (double)(t3.tv_sec - t1.tv_sec);
            run_time = (double)(t3.tv_sec - t2.tv_sec);
            #endif

            avg_gen_time = run_time / (j + 1);
            est_run_time = avg_gen_time * (num_gens - j);
            avg_run_time = est_run_time + run_time;
            est_sim_time = (est_run_time * (num_runs - i)) / (i + 1);
            printf("\n============= Timing Data =============\n");
            printf("Time in Simulation: %.2fs\n", sim_time);
            printf("Time in Run: %.2fs\n", run_time);
            printf("Est. Time to Complete Run: %.2fs\n", est_run_time);
            printf("Est. Time to Complete Simulation: %.2fs\n\n", est_sim_time);
            printf("Average Time Per Generation: %.2fs/gen\n", avg_gen_time);
            printf("Average Time Per Run: %.2fs/run\n", avg_run_time);
            printf("=======================================\n\n");

            if (j % (num_gens - 1) == 0) {

            }
        }

            //Display Position Board
            //displayboardl(&bn.board[0]);

            j1 = j2;
        }
    }
}

Answer 1

代码对于正确的测试而言太大了，使用全局变量确实无法弄清楚数据依赖性。不过我可以发表一些评论：

shared被声明为private，而它是并行化循环的索引。这是错的！如果在omp for循环中确实存在一个您真正想要shared的变量，那么它就是循环索引。我在C和C ++的OpenMP标准中没有发现任何明确的内容，而对于Fortran，循环索引（以及所有封闭循环中的循环索引）是隐式私有化的。尽管如此，英特尔编译器在尝试显式声明sharedi.cc(11): warning #2555: static control variable for parallel loop for ( i=0; i<10; i++ ) { ^ sharedi.cc(10): error: index variable "i" of for statement following an OpenMP for pragma must be private #pragma omp parallel for shared(i) schedule(static) ^ compilation aborted for sharedi.cc (code 2)这样的索引时会出错：
```
private
```
通过平均时间，gcc版本5.1.0不会为相同的代码发出任何警告或错误，并且表现为变量已被声明为i ...我倾向于找到英特尔的编译器行为更合理，但我不能100％确定哪一个是正确的。但我所知道的是，声明shared private绝对是一个非常糟糕的主意（甚至是AFAIC的错误）。所以我觉得这是一个灰色区域，你的编译器可能会或者可能不会做一个明智的工作，这本身就可以解释你的大部分问题。
您似乎将数据输出到文件中，这些名称可能会跨线程冲突。小心一点，因为你最终会弄得一团糟......
您的打印很可能全部搞砸了。我不知道你对此有多重视，但这不会是现在的写作方式。

总而言之，您的代码只是纠结于我，以便清楚地了解正在发生的事情。尝试至少解决我提到的两个第一点，它可能足以让它“ work ”。但是，我不能鼓励你清理代码和摆脱全局变量。同样，尽量只在源代码中尽可能地声明变量，因为这样可以减少为OpenMP声明它们{{1}}的需要，并且可以大大提高可读性。

祝你好好调试。

OpenMP：访问冲突和其他错误

前言

问题

尝试解决方案

的main.c

结构

1 个答案: