// rtoa-pgatram-openmp.cpp. Crude first attempt at an OpenMp version.
// Compile with:
//   g++ -o rtoa-pgatram-openmp -std=c++20 -fopenmp -Wall -O3 rtoa-pgatram-openmp.cpp
// or:
//   clang++ -o rtoa-pgatram-openmp -std=c++20 -fopenmp -Wall -O3 rtoa-pgatram-openmp.cpp
// or:
//   g++ -o rtoa-pgatram-openmp -std=c++20 -fopenmp -Wall -O3 -I "$HOME/local-fast_io/fast_io/include" rtoa-pgatram-openmp.cpp
// to use the locally installed fast_io header-only library

#include <cctype>
#include <cstring>
#include <string>
#include <vector>
#include <numeric>

#ifdef _OPENMP
#include <omp.h>
#endif

#include <chrono>
#include <thread>

#include <iostream>
#include <iomanip>

// See [id://11149504] for more info on the fast_io C++ library
#include <fast_io.h>

// ----------------------------------------------------------------------------

typedef std::chrono::high_resolution_clock high_resolution_clock;
typedef std::chrono::high_resolution_clock::time_point time_point;
typedef std::chrono::milliseconds milliseconds;

double elaspe_time(
   time_point cend,
   time_point cstart)
{
   return double (
      std::chrono::duration_cast<milliseconds>(cend - cstart).count()
   ) * 1e-3;
}

// ----------------------------------------------------------------------------

// Longest roman numeral is MMMDCCCLXXXVIII (3888) of length 15
// XXX: I'm off by one somewhere because 3888 fails with
// MAX_STR_LEN_L of 16 but works with 17
#define MAX_STR_LEN_L 17

// The basic idea is to keep this struct small and without pointers to
// improve data locality/cache performance when traversing the vector
struct str_type {
   char slen;
   char str[MAX_STR_LEN_L];
};

using vec_str_type = std::vector<str_type>;
using vec_int_type = std::vector<int>;

// Read an input file of Roman Numerals and append them to a list
static void read_input_file(
   const char*    fname,       //  in: file name containing a list of Roman Numerals
   vec_str_type&  vec_ret)     // out: a vector of Roman Numeral strings
{
   FILE* fh;
   str_type line;
   fh = ::fopen(fname, "r");
   if ( fh == NULL ) {
      std::cerr << "Error opening '" << fname << "' : " << strerror(errno) << "\n";
      return;
   }
   while ( ::fgets( line.str, MAX_STR_LEN_L, fh ) != NULL ) {
      line.slen = ::strlen(line.str) - 1;    // -1 to strip trailing newline
      vec_ret.emplace_back(line);
   }
   ::fclose(fh);
}

// ---------------------------------------------------------------
// Though there are less than 256 initializers in this ascii table,
// the others are guaranteed by ANSI C to be initialized to zero.
static const int romtab[256] = {
    0,0,0,0,0,0,   0,   0,   0,   0,  //  00- 09
    0,0,0,0,0,0,   0,   0,   0,   0,  //  10- 19
    0,0,0,0,0,0,   0,   0,   0,   0,  //  20- 29
    0,0,0,0,0,0,   0,   0,   0,   0,  //  30- 39
    0,0,0,0,0,0,   0,   0,   0,   0,  //  40- 49
    0,0,0,0,0,0,   0,   0,   0,   0,  //  50- 59
    0,0,0,0,0,0,   0, 100, 500,   0,  //  60- 69
    0,0,0,1,0,0,  50,1000,   0,   0,  //  70- 79
    0,0,0,0,0,0,   5,   0,  10,   0,  //  80- 89
    0,0,0,0,0,0,   0,   0,   0, 100,  //  90- 99
  500,0,0,0,0,1,   0,   0,  50,1000,  // 100-109
    0,0,0,0,0,0,   0,   0,   5,   0,  // 110-119
   10,0,0,0,0,0,   0,   0,   0,   0   // 120-129
};

// Return the arabic number for a roman letter c.
// Return zero if the roman letter c is invalid.
inline int urtoa(int c) { return romtab[c]; }

inline int accfn(int t, char c) {
  return t + urtoa(c) - t % urtoa(c) * 2;
}

inline int roman_to_dec(const str_type& st) {
   return std::accumulate( st.str, st.str + st.slen, 0, accfn );
}

int main(int argc, char* argv[])
{
   if (argc < 2) {
      std::cerr << "usage: rtoa-pgatram-openmp file...\n";
      return 1;
   }

#ifdef _OPENMP
   std::cerr << "use OpenMP\n";
#else
   std::cerr << "don't use OpenMP\n";
#endif

   // Get the list of input files from the command line
   int    nfiles = argc - 1;
   char** fname  = &argv[1];

   std::cerr << std::setprecision(3) << std::setiosflags(std::ios::fixed);
   time_point cstart1, cend1, cstart2, cend2;

#ifdef _OPENMP
   // Determine the number of threads.
   const char* env_nthrs = std::getenv("NUM_THREADS");
   int nthrs = (env_nthrs && strlen(env_nthrs)) ? ::atoi(env_nthrs) : std::thread::hardware_concurrency();
   omp_set_dynamic(false);
   omp_set_num_threads(nthrs);
#else
   int nthrs = 1;
#endif

   // Read the input files into roman_list
   vec_str_type roman_list;
   roman_list.reserve(3999000 * 4);
   cstart1 = high_resolution_clock::now();

   // Run parallel, depending on the number of threads
   if ( nthrs == 1 || nfiles == 1 ) {
      for (int i = 0; i < nfiles; ++i)
         read_input_file( fname[i], roman_list );
   }
#ifdef _OPENMP
   else {
      #pragma omp parallel for schedule(static, 1)
      for (int i = 0; i < nfiles; ++i) {
         vec_str_type locvec;
         read_input_file( fname[i], locvec );
         #pragma omp critical
         {
            // Append local vector
            roman_list.insert( roman_list.end(), locvec.begin(), locvec.end() );
         }
      }
   }
#endif

   cend1 = high_resolution_clock::now();
   double ctaken1 = elaspe_time(cend1, cstart1);
   std::cerr << "read_input_files  : " << roman_list.size() << " items\n";
   std::cerr << "read file time    : " << std::setw(8) << ctaken1 << " secs\n";

   // Convert roman to decimal
   cstart2 = high_resolution_clock::now();
   for ( auto const& r : roman_list ) {
      // std::cout << roman_to_dec(r) << '\n';
      fast_io::io::println( roman_to_dec(r) );
   }
   cend2 = high_resolution_clock::now();
   double ctaken2 = elaspe_time(cend2, cstart2);
   std::cerr << "roman_to_dec time : " << std::setw(8) << ctaken2 << " secs\n";

   double ctaken = elaspe_time(cend2, cstart1);
   std::cerr << "total time        : " << std::setw(8) << ctaken   << " secs\n";

   return 0;
}

##</code><code>##

$ time NUM_THREADS=1 ./rtoa-pgatram-openmp t1.txt t1.txt t1.txt t1.txt >s.tmp
use OpenMP
read_input_files  : 15996000 items
read file time    :    0.700 secs
roman_to_dec time :    0.556 secs
total time        :    1.256 secs

real    0m1.278s
user    0m0.928s
sys     0m0.350s

##</code><code>##

$ time NUM_THREADS=4 ./rtoa-pgatram-openmp t1.txt t1.txt t1.txt t1.txt >s.tmp
use OpenMP
read_input_files  : 15996000 items
read file time    :    0.405 secs
roman_to_dec time :    0.568 secs
total time        :    0.974 secs

real    0m0.995s
user    0m1.439s
sys     0m0.539s

$ cmp f.tmp s.tmp