[英]Why is using a std::multiset as a priority queue faster than using a std::priority_queue?
[英]Why is the STL priority_queue not much faster than multiset in this case?
我正在比較STL(g ++)priority_queue的性能,發現push和pop沒有我想象的那么快。 請參閱以下代碼:
#include <set>
#include <queue>
using namespace std;
typedef multiset<int> IntSet;
void testMap()
{
srand( 0 );
IntSet iSet;
for ( size_t i = 0; i < 1000; ++i )
{
iSet.insert(rand());
}
for ( size_t i = 0; i < 100000; ++i )
{
int v = *(iSet.begin());
iSet.erase( iSet.begin() );
v = rand();
iSet.insert(v);
}
}
typedef priority_queue<int> IntQueue;
void testPriorityQueue()
{
srand(0);
IntQueue q;
for ( size_t i = 0; i < 1000; ++i )
{
q.push(rand());
}
for ( size_t i = 0; i < 100000; ++i )
{
int v = q.top();
q.pop();
v = rand();
q.push(v);
}
}
int main(int,char**)
{
testMap();
testPriorityQueue();
}
我編譯了這個-O3,然后運行了valgrind --tool = callgrind,KCachegrind testMap占用了總CPU的54%testPriorityQueue占用了44%的CPU
(沒有-O3 testMap比testPriorityQueue快很多)調用testPriorityQueue似乎大部分時間的函數被調用
void std::__adjust_heap<__gbe_cxx::__normal_iterator<int*, std::vector<int, std::allocator<int> > >, long, int, std::less<int> >
該函數似乎是從pop()調用中調用的。
這個功能究竟做了什么? 有沒有辦法通過使用不同的容器或分配器來避免它?
我已經實現了一個優先級隊列,當使用-O3編譯時,該隊列似乎運行得更快。 也許只是因為編譯器能夠在STL情況下內聯更多?
#include <set>
#include <queue>
#include <vector>
#include <iostream>
using namespace std;
typedef multiset<int> IntSet;
#define TIMES 10000000
void testMap()
{
srand( 0 );
IntSet iSet;
for ( size_t i = 0; i < 1000; ++i ) {
iSet.insert(rand());
}
for ( size_t i = 0; i < TIMES; ++i ) {
int v = *(iSet.begin());
iSet.erase( iSet.begin() );
v = rand();
iSet.insert(v);
}
}
typedef priority_queue<int> IntQueue;
void testPriorityQueue()
{
srand(0);
IntQueue q;
for ( size_t i = 0; i < 1000; ++i ) {
q.push( rand() );
}
for ( size_t i = 0; i < TIMES; ++i ) {
int v = q.top();
q.pop();
v = rand();
q.push(v);
}
}
template <class T>
class fast_priority_queue
{
public:
fast_priority_queue()
:size(1) {
mVec.resize(1); // first element never used
}
void push( const T& rT ) {
mVec.push_back( rT );
size_t s = size++;
while ( s > 1 ) {
T* pTr = &mVec[s];
s = s / 2;
if ( mVec[s] > *pTr ) {
T tmp = mVec[s];
mVec[s] = *pTr;
*pTr = tmp;
} else break;
}
}
const T& top() const {
return mVec[1];
}
void pop() {
mVec[1] = mVec.back();
mVec.pop_back();
--size;
size_t s = 1;
size_t n = s*2;
T& rT = mVec[s];
while ( n < size ) {
if ( mVec[n] < rT ) {
T tmp = mVec[n];
mVec[n] = rT;
rT = tmp;
s = n;
n = 2 * s;
continue;
}
++n;
if ( mVec[n] < rT ) {
T tmp = mVec[n];
mVec[n] = rT;
rT = tmp;
s = n;
n = 2 * s;
continue;
}
break;
}
}
size_t size;
vector<T> mVec;
};
typedef fast_priority_queue<int> MyQueue;
void testMyPriorityQueue()
{
srand(0);
MyQueue q;
for ( size_t i = 0; i < 1000; ++i ) {
q.push( rand() );
}
for ( size_t i = 0; i < TIMES; ++i ) {
int v = q.top();
q.pop();
v = rand();
q.push(v);
}
}
int main(int,char**)
{
clock_t t1 = clock();
testMyPriorityQueue();
clock_t t2 = clock();
testMap();
clock_t t3 = clock();
testPriorityQueue();
clock_t t4 = clock();
cout << "fast_priority_queue: " << t2 - t1 << endl;
cout << "std::multiset: " << t3 - t2 << endl;
cout << "std::priority_queue: " << t4 - t3 << endl;
}
當用64位Linux上的g ++ 4.1.2標志:-O3編譯時,這給了我:
fast_priority_queue: 260000
std::multiset: 620000
std::priority_queue: 490000
聲明:本站的技術帖子網頁,遵循CC BY-SA 4.0協議,如果您需要轉載,請注明本站網址或者原文地址。任何問題請咨詢:yoyou2525@163.com.