Question

Recently, I was asked in a interview to implement a string reverse function using threads. I came up with most part of the solution below. Got selected or not is a different story :-). I tried to run the below solution on my home PC running Windows 8 consumer preview. The compiler is VC11 Beta.

The question is, the multi-threaded code is always either as fast or 1 millisecond slower than the sequential code. The input I gave is a text file of size 32.4 MB. Is there a way to make the multi-threaded code faster ? Or is it that the input given is too less to make any difference ?

EDIT

I only wrote void Reverse(char* str, int beg, int end, int rbegin, int rend); and
void CustomReverse(char* str); methods in the interview. All the other code is written at home.

 template<typename Function>
    void TimeIt(Function&& fun, const char* caption)
    {
        clock_t start = clock();     
        fun();     
        clock_t ticks = clock()-start;     
        std::cout << std::setw(30) << caption          << ": "          << (double)ticks/CLOCKS_PER_SEC << "\n"; 
    }

    void Reverse(char* str)
    {


        assert(str != NULL);
        for ( int i = 0, j = strlen(str) - 1; i < j; ++i, --j)
        {
            if ( str[i] != str[j])
            {
                std::swap(str[i], str[j]);
            }
        }

    }

     void Reverse(char* str, int beg, int end, int rbegin, int rend)
        {
            for ( ; beg <= end && rbegin >= rend; ++beg, --rbegin)
            {
                if ( str[beg] != str[rbegin])
                {
                    char temp = str[beg];
                    str[beg] = str[rbegin];
                    str[rbegin] = temp;
                }
            }
        }

        void CustomReverse(char* str)
        {
            int len = strlen(str);
            const int MAX_THREADS = std::thread::hardware_concurrency();
            std::vector<std::thread> threads;

            threads.reserve(MAX_THREADS);

            const int CHUNK = len / MAX_THREADS > (4096) ? (4096) : len / MAX_THREADS;

            /*std::cout << "len:" << len << "\n";
            std::cout << "MAX_THREADS:" << MAX_THREADS << "\n";
            std::cout << "CHUNK:" << CHUNK << "\n";*/

        for ( int i = 0, j = len - 1; i < j; )
                {
                    if (i + CHUNK < j && j - CHUNK > i )
                    {
                        for ( int k = 0; k < MAX_THREADS && (i + CHUNK < j && j - CHUNK > i ); ++k)
                        {                                                
                             threads.push_back( std::thread([=, &str]() { Reverse(str, i,    
                                                    i + CHUNK, j, j - CHUNK); }));
                            i += CHUNK + 1;
                            j -= CHUNK + 1;
                        }


                        for ( auto& th : threads)
                        {
                            th.join();
                        }

                        threads.clear();
                    }
                    else
                    {          
                                        char temp = str[i];
                                        str[i] = str[j];
                                        str[j] = str[i];
                        i++;
                        j--;
                    }
                }
            }


        void Write(std::ostream&& os, const std::string& str)
        {
           os << str << "\n";
        }

        void CustomReverseDemo(int argc, char** argv)
        {
            std::ifstream inpfile;
            for ( int i = 0; i < argc; ++i)
                std::cout << argv[i] << "\n";

            inpfile.open(argv[1], std::ios::in);

            std::ostringstream oss;
            std::string line;

            if (! inpfile.is_open())
            {
                return;
            }
            while (std::getline(inpfile, line))
            {
                oss << line;
            }

            std::string seq(oss.str());
            std::string par(oss.str());

            std::cout << "Reversing now\n";

            TimeIt( [&] { CustomReverse(&par[0]); }, "Using parallel code\n");  
            TimeIt( [&] { Reverse(&seq[0]) ;}, "Using Sequential Code\n");
            TimeIt( [&] { Reverse(&seq[0]) ;}, "Using Sequential Code\n");
            TimeIt( [&] { CustomReverse(&par[0]); }, "Using parallel code\n");      



            Write(std::ofstream("sequential.txt"), seq);
            Write(std::ofstream("Parallel.txt"), par);
        }

        int main(int argc, char* argv[])
        {
            CustomReverseDemo(argc, argv);
        }

Answer 1

I tried to write the program with same functionality:
My effort of "Reversing a string using threads"

I have tested that with 2 core processor with VC11 Beta and mingw(gcc 4.8) on Windows 7

Testing results:

VC11 Beta:

7 Mb file:

Debug

Simple reverse: 0.468

Async reverse : 0.275

Release

Simple reverse: 0.006

Async reverse : 0.014

98 Mb file:

Debug

Simple reverse: 5.982

Async reverse : 3.091

Release

Simple reverse: 0.063

Async reverse : 0.079

782 Mb file

Release

Simple reverse: 0.567

Async reverse : 0.689

Mingw:

782 Mb file

Release

Simple reverse: 0.583

Async reverse : 0.566

As you can see multi-threaded code wins only in debug build. But in release compiler makes optimization and uses all cores even in case of single-threaded code.

So trust your compiler =)