#include <windows.h>
#include <stdio.h>
#include <time.h>
#include <process.h>

typedef struct {
	void *protected;
	int loops;
} args;

void lock( void *protected ) {

	while( _interlockedbittestandset64( (__int64*)protected, 0 ) ) {
		Sleep( 1 );
	}
}

void unlock( void *protected ) {
	_interlockedbittestandreset64( (__int64*)protected, 0 );
}

void worker( void *arg ) {
    args *a = (args*)arg;
    int i = 0;

    for( i=0; i < a->loops; ++i ) {
		lock( a->protected );
		*( (int*)a->protected ) += 2;
		unlock( a->protected );
	}
	return;
}

void main( int argc, char **argv ) {
    int i = 0, nThreads = 4;
    clock_t start, finish;
    double elapsed;
    uintptr_t threads[32];
    int shared = 0;
	args a = { (void *)&shared, 1000000 };;

    if( argc > 1 ) nThreads = atol( argv[1] );
    if( argc > 2 ) a.loops = atol( argv[2] );

	printf( "threads:%d loops:%d\n", nThreads, a.loops );

    start = clock();
    for( i=0; i < nThreads; ++i )
		threads[ i ] = _beginthread( &worker, 0, &a );

	WaitForMultipleObjects( nThreads, (HANDLE*)&threads, 1, INFINITE );
	finish = clock();

	elapsed = (double)(finish - start) / CLOCKS_PER_SEC;

	printf( "count: %lu time:%.6f\n", shared, elapsed );

}