c++ - Strange output for a simple OpenMP program on Multi2sim v4.0.1 -

i'm trying run simple program using openmp

the program follows

#include <iostream> #include <fstream> #include <vector> #include <omp.h> #include <algorithm> #include <math.h> #include <map> #include <string> #include <ctime> using namespace std;  #define num 10    void openmp() {     omp_set_num_threads(1);     int sum =0;     #pragma omp parallel shared(sum)     {         (int i=0;i<100;i++)         {             sum++;         }     }     cout<<"sum = "<<sum<<endl;  } int main() {     cout<<"open mp \n";     openmp(); return 0; } 

now when compile using

g++ test.cpp -fopenmp -o test

and run on ubuntu terminal

./test

the output correct - think - follows

open mp  sum = 100 

but when try run using multi2sim using these 2 files given instructor

multicore-config:

[ general ] cores = 4 threads = 1 

multicore-mem-config:

[cachegeometry geo-l1] sets = 256 assoc = 2 blocksize = 64 latency = 2 policy = lru ports = 2  [cachegeometry geo-l2] sets = 512 assoc = 4 blocksize = 64 latency = 20 policy = lru ports = 4  [module mod-l1-0] type = cache geometry = geo-l1 lownetwork = net-l1-l2  lowmodules = mod-l2  [module mod-l1-1] type = cache geometry = geo-l1 lownetwork = net-l1-l2  lowmodules = mod-l2  [module mod-l2] type = cache geometry = geo-l2 highnetwork = net-l1-l2  lownetwork = net-l2-mm lowmodules = mod-mm  [module mod-mm] type = mainmemory blocksize = 256 latency = 200 highnetwork = net-l2-mm  [network net-l2-mm] defaultinputbuffersize = 1024  defaultoutputbuffersize = 1024 defaultbandwidth = 256   [network net-l1-l2] defaultinputbuffersize = 1024  defaultoutputbuffersize = 1024 defaultbandwidth = 256   [entry core-0] arch = x86 core = 0 thread = 0 datamodule = mod-l1-0 instmodule = mod-l1-0  [entry core-1] arch = x86 core = 1 thread = 0 datamodule = mod-l1-0 instmodule = mod-l1-0  [entry core-2] arch = x86 core = 2 thread = 0 datamodule = mod-l1-0 instmodule = mod-l1-0  [entry core-3] arch = x86 core = 3 thread = 0 datamodule = mod-l1-0 instmodule = mod-l1-0 

and using instruction in ubuntu terminal

m2s --x86-config multicore-config.txt --mem-config multicore-mem-config.txt --x86-sim detailed test 

i output

; multi2sim 4.0.1 - simulation framework cpu-gpu heterogeneous computing ; please use command 'm2s --help' list of command-line options. ; last compilation: may  8 2013 10:01:31  open mp  sum = 83  ; ; simulation statistics summary ;  [ general ] time = 53.17 simend = contextsfinished cycles = 3691870  [ x86 ] simtype = detailed time = 53.15 contexts = 4 memory = 37056512 emulatedinstructions = 3292450 emulatedinstructionspersecond = 61943 cycles = 3691558 cyclespersecond = 69452 fastforwardinstructions = 0 committedinstructions = 2081157 committedinstructionspercycle = 0.5638 committedmicroinstructions = 3113721 committedmicroinstructionspercycle = 0.8435 branchpredictionaccuracy = 0.9375 

why output in multi2sim 83 while output in normal run 100

also why take time run on multi2sim ?

any appreciated.

i don't know m2s, case culprit is:

#pragma omp parallel shared(sum)     {         (int i=0;i<100;i++)         {             sum++; // concurrent access shared variable!!!         }     } 

in first test fact explicitly set number of threads 1:

omp_set_num_threads(1); 

saves race conditions. suggest trying with:

#pragma omp parallel shared(sum) reduction(+:sum) (int i=0;i<100;i++) {             sum++; }     

to see if can obtain desired behavior.