T parallel_accumulate(Iterator first, Iterator last, T init)
{
unsigned long const length = std::distance(first, last);
if (!length) {
return init;
}
unsigned long const block_size = 25;
unsigned long const num_blocks = (length + block_size - 1) / block_size;
std::vector<std::future<T> > futures(num_blocks - 1);
thread_pool pool;
Iterator block_start = first;
for (unsigned long i = 0; i < (num_threads - 1); ++i) {
Iterator block_end = block_start;
std::advance(block_end, block_size);
futures[i] = pool.submit(accumulate_block<Iterator, T>());
block_start = block_end;
}
T last_result = accumulate_block()(block_start, last);
T result = init;
for (unsigned long i = 0; i < (num_blocks - 1); ++i) {
result += futures[i].get();
}
result += last_result;
return result;
}
T parallel_accumulate(Iterator first,Iterator last,T init)
{
unsigned long const length=std::distance(first,last);
if(!length)
return init;
unsigned long const min_per_thread=25;
unsigned long const max_threads=
(length+min_per_thread-1)/min_per_thread;
unsigned long const hardware_threads=
std::thread::hardware_concurrency();
unsigned long const num_threads=
std::min(hardware_threads!=0?hardware_threads:2,max_threads);
unsigned long const block_size=length/num_threads;
std::vector<std::future<T> > futures(num_threads-1);
std::vector<std::thread> threads(num_threads-1);
Iterator block_start=first;
for(unsigned long i=0;i<(num_threads-1);++i)
{
Iterator block_end=block_start;
std::advance(block_end,block_size);
std::packaged_task<T(Iterator,Iterator)> task(
accumulate_block<Iterator,T>());
futures[i]=task.get_future();
threads[i]=std::thread(std::move(task),block_start,block_end);
block_start=block_end;
}
T last_result=accumulate_block()(block_start,last);
std::for_each(threads.begin(),threads.end(),
std::mem_fn(&std::thread::join));
T result=init;
for(unsigned long i=0;i<(num_threads-1);++i)
{
result+=futures[i].get();
}
result += last_result;
return result;
}
