[英]C++ difference in behavior between if statement setting condition to true and or-ing a condition in loop
我当时正在为CS类开发Datalog解释器,但遇到一个奇怪的问题,即我的Rule评估花了太多时间才能完成。 看完我的代码后,我在下面进行了两项修改,以固定我的评估以正确的通过次数执行:
//original form
bool addedFacts = false;
for (X x: xs) {
addedFacts = addedFacts || set.insert(x).second;
}
//modified form
bool addedFacts = false;
for (X x: xs) {
if (set.insert(x).second) {
addedFacts = true;
}
}
对我来说,这两个代码结构在逻辑上是等效的。 是否存在一个原因,一个人执行正确,一个人执行错误/效率低下? 这是一个正在发生的问题的可构建示例:
#include <iostream>
#include <set>
#include <vector>
using std::set;
using std::vector;
using std::cout;
using std::endl;
const int CAP = 100;
class Rule {
public:
int factor;
Rule(int factor) {
this->factor = factor;
}
bool evaluateInefficient(set<int>& facts) {
vector<int> data;
bool addedFacts = false;
for (int fact : facts) {
data.push_back(fact);
}
for (int datum : data) {
int newFact = datum * factor;
if (newFact < CAP) {
addedFacts = addedFacts || facts.insert(newFact).second;
}
}
return addedFacts;
}
bool evaluate(set<int>& facts) {
vector<int> data;
bool addedFacts = false;
for (int fact : facts) {
data.push_back(fact);
}
for (int datum : data) {
int newFact = datum * factor;
if (newFact < CAP) {
if (facts.insert(newFact).second) {
addedFacts = true;
}
}
}
return addedFacts;
}
};
int doublyInefficient(vector<Rule>& rules) {
set<int> facts;
facts.insert(1);
bool addedFacts = true;
int passes = 0;
while (addedFacts) {
passes++;
addedFacts = false;
for (Rule rule : rules) {
addedFacts = addedFacts || rule.evaluateInefficient(facts);
}
}
return passes;
}
int singlyInefficient(vector<Rule>& rules) {
set<int> facts;
facts.insert(1);
bool addedFacts = true;
int passes = 0;
while (addedFacts) {
passes++;
addedFacts = false;
for (Rule rule : rules) {
addedFacts = addedFacts || rule.evaluate(facts);
}
}
return passes;
}
int efficient(vector<Rule>& rules) {
set<int> facts;
facts.insert(1);
bool addedFacts = true;
int passes = 0;
while (addedFacts) {
passes++;
addedFacts = false;
for (Rule rule : rules) {
if (rule.evaluate(facts)) {
addedFacts = true;
}
}
}
return passes;
}
int main(int argc, char* argv[]) {
//build the rules
vector<Rule> rules;
rules.push_back(Rule(2));
rules.push_back(Rule(3));
rules.push_back(Rule(5));
rules.push_back(Rule(7));
rules.push_back(Rule(11));
rules.push_back(Rule(13));
//Show three different codes that should (in my mind) take the same amount of passes over the rules but don't
cout << "Facts populated after " << doublyInefficient(rules) << " passes through the Rules." << endl;
cout << "Facts populated after " << singlyInefficient(rules) << " passes through the Rules." << endl;
cout << "Facts populated after " << efficient(rules) << " passes through the Rules." << endl;
getchar();
}
在Visual Studio 2017上以调试和发布模式(32位)运行时,我得到以下输出。据我所知,代码未进行优化。
Facts populated after 61 passes through the Rules.
Facts populated after 17 passes through the Rules.
Facts populated after 7 passes through the Rules.
addedFacts = addedFacts || set.insert(x).second;
和
if (set.insert(x).second) {
addedFacts = true;
}
绝对不是同一回事。 第一段代码等效于:
if (!addedFacts) {
addedFacts = set.insert(x).second;
}
!addedFacts
检查有很大的不同。
由于短路评估而产生差异:考虑形式为(expr1 || expr2)
的表达式。 短路意味着如果expr1
计算为true
,则表达式expr2
根本不会得到评估(参见此在线c ++标准草案 ,重点是我的):
5.15逻辑或运算符
|| 操作员组从左到右。 操作数都在上下文中转换为bool(Clause [conv])。 如果两个操作数中的任何一个为true,则返回true,否则返回false。 与|,||不同 保证从左到右的评估; 此外,如果第一个操作数的值为true,则不计算第二个操作数的值 。
因此,在您的表达式中添加了addedFacts || set.insert(x).second
addedFacts || set.insert(x).second
,从addedFacts
第一次变为true
的点开始,将不再执行表达式set.insert(x).second
。 我想这是“错误”的行为,因为您的set
将不包含相应的x
。
声明:本站的技术帖子网页,遵循CC BY-SA 4.0协议,如果您需要转载,请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.