我正在为 memcpy 函数做一个优化任务,我在这里找到了这个链接。如何提高 memcpy 的性能
由于我不熟悉多线程编程,所以不知道如何将下面的代码插入到原来的main函数中?如何将原问题中的代码修改成多线程memcpy项目?我的意思是,如何为这个多线程项目创建一个完整的memcpy
项目。在原始 main 函数中插入类似startCopyThreads
or stopCopyThreads
or函数的地方在哪里?mt_memcpy
#define NUM_CPY_THREADS 4
HANDLE hCopyThreads[NUM_CPY_THREADS] = {0};
HANDLE hCopyStartSemaphores[NUM_CPY_THREADS] = {0};
HANDLE hCopyStopSemaphores[NUM_CPY_THREADS] = {0};
typedef struct
{
int ct;
void * src, * dest;
size_t size;
} mt_cpy_t;
mt_cpy_t mtParamters[NUM_CPY_THREADS] = {0};
DWORD WINAPI thread_copy_proc(LPVOID param)
{
mt_cpy_t * p = (mt_cpy_t * ) param;
while(1)
{
WaitForSingleObject(hCopyStartSemaphores[p->ct], INFINITE);
memcpy(p->dest, p->src, p->size);
ReleaseSemaphore(hCopyStopSemaphores[p->ct], 1, NULL);
}
return 0;
}
int startCopyThreads()
{
for(int ctr = 0; ctr < NUM_CPY_THREADS; ctr++)
{
hCopyStartSemaphores[ctr] = CreateSemaphore(NULL, 0, 1, NULL);
hCopyStopSemaphores[ctr] = CreateSemaphore(NULL, 0, 1, NULL);
mtParamters[ctr].ct = ctr;
hCopyThreads[ctr] = CreateThread(0, 0, thread_copy_proc, &mtParamters[ctr], 0, NULL);
}
return 0;
}
void * mt_memcpy(void * dest, void * src, size_t bytes)
{
//set up parameters
for(int ctr = 0; ctr < NUM_CPY_THREADS; ctr++)
{
mtParamters[ctr].dest = (char *) dest + ctr * bytes / NUM_CPY_THREADS;
mtParamters[ctr].src = (char *) src + ctr * bytes / NUM_CPY_THREADS;
mtParamters[ctr].size = (ctr + 1) * bytes / NUM_CPY_THREADS - ctr * bytes / NUM_CPY_THREADS;
}
//release semaphores to start computation
for(int ctr = 0; ctr < NUM_CPY_THREADS; ctr++)
ReleaseSemaphore(hCopyStartSemaphores[ctr], 1, NULL);
//wait for all threads to finish
WaitForMultipleObjects(NUM_CPY_THREADS, hCopyStopSemaphores, TRUE, INFINITE);
return dest;
}
int stopCopyThreads()
{
for(int ctr = 0; ctr < NUM_CPY_THREADS; ctr++)
{
TerminateThread(hCopyThreads[ctr], 0);
CloseHandle(hCopyStartSemaphores[ctr]);
CloseHandle(hCopyStopSemaphores[ctr]);
}
return 0;
}