我用C ++编写了一些测试代码来处理CSV文件。在Windows和Linux上编译并运行相同的代码会产生显着的性能:
CSV文件大小:~30MB
Windows性能(在Windows 8上): 80秒
Linux性能(在Ubuntu 4.4.0-72-generic上): 2秒
在这里输入代码
两个代码都在cmdline上运行。 Linux代码是使用支持C ++ 11的g ++构建的。 Windows代码是使用Visual Studio 2017构建的。
起初,我认为Linux上的计时器实现是错误的,所以我自己计时,结果是一样的。
有人能给我一些暗示这个巨大差异来自哪里?当我在调试器中运行windows时,我看到内存分配非常慢。但不确定这是否是主要原因。
附上代码和CSV
#include <iostream>
#include <vector>
#include <cstdio>
#include <string>
#include <fstream>
#include <sstream>
#include <chrono>
#include <unordered_map>
#include <algorithm>
#include <numeric>
#include <stdlib.h>
using namespace std;
class readCSV {
private:
vector<string> headers;
bool set_header = true;
string file_name;
unordered_map<string, vector<double>*> my_map;
unsigned int line_count = 1;
double duration;
public:
readCSV(string file, bool header)
:file_name(file), set_header(header), duration(0) {
parseCSV();
};
void parseCSV();
double find_duration() {
return duration / 1000.0;
}
vector<double> find_result(string names) {
vector <double> result;
unordered_map<string, vector<double>*>::iterator it = my_map.find(names);
if (it == my_map.end()) {
cout << "invalid query: " << names << endl;
exit;
}
cout << names << endl;
size_t size = it->second->size();
vector<double>* list = it->second;
double mean = 1.0 * accumulate(list->begin(), list->end(), 0.0) / size;
double sq_sum = inner_product(list->begin(), list->end(), list->begin(), 0.0);
double stdev = sqrt(sq_sum / size - mean * mean);
result.push_back(mean);
result.push_back(stdev);
return result;
}
~readCSV() {
//release memory to prevent leak
for (int i = 0; i < headers.size(); ++i) {
delete my_map.find(headers[i])->second;
}
}
};
void readCSV::parseCSV() {
ifstream file(file_name);
string line;
// log start time
long start = chrono::duration_cast<chrono::milliseconds>(
chrono::steady_clock::now().time_since_epoch()).count();
while (getline(file, line)) {
int count = 0;
string cell;
stringstream temp_line(line);
while (getline(temp_line, cell, ',')) {
unordered_map<string, vector<double>*>::iterator it;
if (line_count == 1) {
vector<double>* addr = new vector<double>();
if (set_header) {
cell.erase(remove(cell.begin(), cell.end(), '\"'), cell.end());
headers.push_back(cell);
my_map.insert(make_pair(cell, addr));
}
else {
string head = to_string(count);
headers.push_back(head);
my_map.insert(make_pair(head, addr));
}
count++;
continue;
}
it = my_map.find(headers[count]);
if (it != my_map.end()) {
double num = atof(cell.c_str());
it->second->push_back(num);
}
else {
cout << "CSV file corrupted!" << endl;
return;
}
count++;
}
line_count++;
}
//log finish time
long stop = chrono::duration_cast<chrono::milliseconds>(
chrono::steady_clock::now().time_since_epoch()).count();
duration = stop - start;
}
int main(int argc, char **argv) {
if (argc < 3) {
cout << "wrong argument" << endl;
return -1;
}
string filename(argv[1]);
string feature(argv[2]);
readCSV file(filename, true);
vector<double> result = file.find_result(feature);
cout << "duration is " << file.find_duration() << " seconds" << endl;
cout << "Mean is " << result[0] << " " << "STDev is " << result[1] << endl;
return 0;
}
CSV文件:
答案 0 :(得分:0)
您可能正在调试模式下编译VS版本。将编辑器顶部的组合框从“Debug”更改为“Release”并重新编译;你应该看到性能的显着提高。