我的程序中有以下代码,我想使用 OpenMP 加速它。
...
for(i=curr_index; i < curr_index + rx_size; i+=2){
int64_t tgt = rcvq[i];
int64_t src = rcvq[i+1];
if (!TEST(tgt)) {
pred[tgt] = src;
newq[newq_count++] = tgt;
}
}
Run Code Online (Sandbox Code Playgroud)
目前,我有一个版本如下:
...
chunk = rx_sz / omp_nthreads;
#pragma omp parallel for num_threads(omp_nthreads)
for (ii = 0; ii < omp_nthreads; ii++) {
int start = curr_index + ii * chunk;
for (index = start; index < start + chunk; index +=2) {
int64_t tgt = rcvq[index];
int64_t src = rcvq[index+1];
if …Run Code Online (Sandbox Code Playgroud)