c - 为什么这个 OCaml 程序比我的 C 程序快?

标签 c performance ocaml

我写了一个基本的Hippity Hop使用 C、Python 和 OCaml 编写程序。诚然,这可能不是这三种语言的一个很好的基准。但是我得到的结果是这样的:

  • Python:0.350 秒
  • C:0.050 秒
  • 解释 OCaml:.040 秒
  • 编译的 OCaml:.010

Python 的性能并没有让我感到惊讶,但我对 OCaml 的速度(尤其是解释版本)的速度感到相当震惊。为了进行比较,我将发布 C 版本和 OCaml 版本。

C

#include <stdio.h>
#include <stdlib.h>
#include <assert.h>

long get_count(char *name);

int main(int argc, char *argv[])
{
  if (argc != 2){
    printf("Filename must be specified as a positional argument.\n");
    exit(EXIT_FAILURE);
  }

  long count_no = get_count(argv[1]);

  int i;
  for (i = 1; i <= count_no; i++){
    if (((i % 3) == 0) && ((i % 5) == 0)){
      printf("Hop\n");
      continue;
    }
    if ((i % 3) == 0){
      printf("Hoppity\n");
    }
    if ((i % 5) == 0){
      printf("Hophop\n");
    }
  }
  return 0;
}

long get_count(char *name){
  FILE *fileptr = fopen(name, "r");
  if (!fileptr){
    printf("Unable to open file %s.\n", name);
    exit(EXIT_FAILURE);
  }
  size_t text_len = 20;
  char *file_text = calloc(text_len, sizeof(char));
  while (!feof(fileptr)){
    fread(file_text, sizeof(char), text_len, fileptr);
    assert(!ferror(fileptr));
    text_len += 20;
    file_text = realloc(file_text, text_len * sizeof(char));
  }
  long file_as_int = strtol(file_text, NULL, 10);

  free(file_text);
  return file_as_int;
}

OCaml

open String;;

let trim str =
  if str = "" then "" else
  let search_pos init p next =
    let rec search i =
      if p i then raise(Failure "empty") else
      match str.[i] with
      | ' ' | '\n' | '\r' | '\t' -> search (next i)
      | _ -> i
    in
    search init
  in
  let len = String.length str in
  try
    let left = search_pos 0 (fun i -> i >= len) (succ)
    and right = search_pos (len - 1) (fun i -> i < 0) (pred)
    in
    String.sub str left (right - left + 1)
  with
  | Failure "empty" -> ""
;;

let rec iterate_over_numbers curr_num max_num =
  (
   if curr_num <= max_num then (
     if ((curr_num mod 3) == 0) && ((curr_num mod 5) == 0) then 
       print_endline "Hop"
     else if (curr_num mod 3) == 0 then 
       print_endline "Hoppity"
     else if (curr_num mod 5) == 0 then
       print_endline "Hophop";
     iterate_over_numbers (curr_num + 1) max_num
   ))
;;


let fname = Sys.argv.(1);;
let infile = open_in fname;;
let file_text = trim (input_line infile);;
close_in infile;;
let input_number = int_of_string file_text;;
iterate_over_numbers 1 input_number;;

但我很想知道为什么会得到这些结果。我是不是在我的 C 程序中做了一些愚蠢的事情,或者这只是 OCaml 更快的事情?在我看来,解释程序运行速度比 C 版本快一点,而编译程序运行速度是 C 版本的 5 倍,这在我看来有点奇怪。

最佳答案

您的 C 代码不等同于 OCaml 代码 - 您在 OCaml 中使用了“else if”以避免不得不重新计算模数。

“读取长整数”中有大量代码。为什么不直接使用 fscanf();它会自动跳过空白和所有这些,并避免你执行 malloc() 等。我不经常推荐使用 fscanf(),但这看起来像是一个设置它 - 单行,两边可能有空格,没有有趣的东西。


好奇害死猫 - 但在这种情况下,不是豹子。

我下载了适用于 MacOS X Intel 的 OCaml 3.11.1,并将问题中的 OCaml 代码复制到 xxx.ml (OCaml) 中,并将其编译成目标文件 xxx(使用“ocamlc -o xxx xxx.ml”);我将 C 代码逐字复制到 yyy.c 中,并使用 fscanf()fclose() 创建了一个变体 zzz.c,并使用“gcc -O -o”编译了它们yyy yyy.c”和“gcc -O -o zzz zzz.c”。我创建了一个文件“file3”,其中包含:“987654”加上换行符。我创建了一个 shell 脚本 runthem.sh,如图所示。请注意,'time' 是一个讨厌的命令,它认为它的输出必须转到 stderr,即使您不希望它这样做 - 您必须非常努力地工作才能将输出放在您想要的位置。 (range 命令生成给定范围内的数字,包括在内 - 因此每个程序 11 个值。)

Osiris JL: cat runthem.sh
for prog in "ocaml xxx.ml" ./xxx ./yyy ./zzz
do
    for iter in $(range 0 10)
    do
        r=$(sh -c "time $prog file3 >/dev/null" 2>&1)
        echo $prog: $r
    done
done
Osiris JL: 

我在运行 Leopard (10.5.8) 的现代 MacBook Pro(3 GHz Core 2 Duo 等,4GB RAM)上运行了所有这些。我得到的时间显示为:

Osiris JL: sh runthem.sh
ocaml xxx.ml: real 0m0.961s user 0m0.524s sys 0m0.432s
ocaml xxx.ml: real 0m0.953s user 0m0.516s sys 0m0.430s
ocaml xxx.ml: real 0m0.959s user 0m0.517s sys 0m0.431s
ocaml xxx.ml: real 0m0.951s user 0m0.517s sys 0m0.430s
ocaml xxx.ml: real 0m0.952s user 0m0.516s sys 0m0.431s
ocaml xxx.ml: real 0m0.952s user 0m0.514s sys 0m0.431s
ocaml xxx.ml: real 0m0.951s user 0m0.515s sys 0m0.431s
ocaml xxx.ml: real 0m0.959s user 0m0.515s sys 0m0.431s
ocaml xxx.ml: real 0m0.950s user 0m0.515s sys 0m0.431s
ocaml xxx.ml: real 0m0.956s user 0m0.516s sys 0m0.431s
ocaml xxx.ml: real 0m0.952s user 0m0.514s sys 0m0.432s
./xxx: real 0m0.928s user 0m0.494s sys 0m0.430s
./xxx: real 0m0.938s user 0m0.494s sys 0m0.430s
./xxx: real 0m0.927s user 0m0.494s sys 0m0.430s
./xxx: real 0m0.928s user 0m0.492s sys 0m0.430s
./xxx: real 0m0.928s user 0m0.493s sys 0m0.430s
./xxx: real 0m0.927s user 0m0.493s sys 0m0.430s
./xxx: real 0m0.928s user 0m0.492s sys 0m0.430s
./xxx: real 0m0.933s user 0m0.497s sys 0m0.428s
./xxx: real 0m0.926s user 0m0.494s sys 0m0.429s
./xxx: real 0m0.921s user 0m0.492s sys 0m0.428s
./xxx: real 0m0.925s user 0m0.494s sys 0m0.428s
./yyy: real 0m0.027s user 0m0.026s sys 0m0.001s
./yyy: real 0m0.031s user 0m0.026s sys 0m0.002s
./yyy: real 0m0.028s user 0m0.026s sys 0m0.001s
./yyy: real 0m0.029s user 0m0.026s sys 0m0.002s
./yyy: real 0m0.028s user 0m0.026s sys 0m0.001s
./yyy: real 0m0.029s user 0m0.026s sys 0m0.002s
./yyy: real 0m0.028s user 0m0.026s sys 0m0.001s
./yyy: real 0m0.031s user 0m0.026s sys 0m0.002s
./yyy: real 0m0.028s user 0m0.026s sys 0m0.001s
./yyy: real 0m0.030s user 0m0.026s sys 0m0.002s
./yyy: real 0m0.028s user 0m0.026s sys 0m0.001s
./zzz: real 0m0.030s user 0m0.027s sys 0m0.002s
./zzz: real 0m0.029s user 0m0.027s sys 0m0.001s
./zzz: real 0m0.030s user 0m0.027s sys 0m0.002s
./zzz: real 0m0.029s user 0m0.027s sys 0m0.001s
./zzz: real 0m0.030s user 0m0.027s sys 0m0.002s
./zzz: real 0m0.029s user 0m0.027s sys 0m0.001s
./zzz: real 0m0.030s user 0m0.027s sys 0m0.002s
./zzz: real 0m0.029s user 0m0.027s sys 0m0.001s
./zzz: real 0m0.030s user 0m0.027s sys 0m0.002s
./zzz: real 0m0.029s user 0m0.027s sys 0m0.001s
./zzz: real 0m0.030s user 0m0.027s sys 0m0.002s
Osiris JL:

我没有看到 OCaml 代码比 C 代码运行得更快。我在读取的文件中用较小的数字运行测试,结果同样有利于 C 代码:

停止编号:345

ocaml xxx.ml: real 0m0.027s user 0m0.020s sys 0m0.005s
ocaml xxx.ml: real 0m0.021s user 0m0.016s sys 0m0.005s
ocaml xxx.ml: real 0m0.025s user 0m0.016s sys 0m0.004s
ocaml xxx.ml: real 0m0.020s user 0m0.015s sys 0m0.003s
ocaml xxx.ml: real 0m0.022s user 0m0.016s sys 0m0.004s
ocaml xxx.ml: real 0m0.019s user 0m0.015s sys 0m0.003s
ocaml xxx.ml: real 0m0.021s user 0m0.016s sys 0m0.004s
ocaml xxx.ml: real 0m0.020s user 0m0.015s sys 0m0.004s
ocaml xxx.ml: real 0m0.021s user 0m0.016s sys 0m0.004s
ocaml xxx.ml: real 0m0.020s user 0m0.015s sys 0m0.004s
ocaml xxx.ml: real 0m0.021s user 0m0.016s sys 0m0.004s
./xxx: real 0m0.003s user 0m0.001s sys 0m0.002s
./xxx: real 0m0.003s user 0m0.001s sys 0m0.001s
./xxx: real 0m0.003s user 0m0.001s sys 0m0.001s
./xxx: real 0m0.002s user 0m0.001s sys 0m0.001s
./xxx: real 0m0.003s user 0m0.001s sys 0m0.001s
./xxx: real 0m0.005s user 0m0.001s sys 0m0.002s
./xxx: real 0m0.003s user 0m0.001s sys 0m0.002s
./xxx: real 0m0.003s user 0m0.001s sys 0m0.001s
./xxx: real 0m0.003s user 0m0.001s sys 0m0.001s
./xxx: real 0m0.003s user 0m0.001s sys 0m0.001s
./xxx: real 0m0.003s user 0m0.001s sys 0m0.001s
./yyy: real 0m0.002s user 0m0.000s sys 0m0.001s
./yyy: real 0m0.003s user 0m0.000s sys 0m0.001s
./yyy: real 0m0.002s user 0m0.000s sys 0m0.001s
./yyy: real 0m0.002s user 0m0.000s sys 0m0.001s
./yyy: real 0m0.002s user 0m0.000s sys 0m0.001s
./yyy: real 0m0.002s user 0m0.000s sys 0m0.001s
./yyy: real 0m0.002s user 0m0.000s sys 0m0.001s
./yyy: real 0m0.001s user 0m0.000s sys 0m0.001s
./yyy: real 0m0.002s user 0m0.000s sys 0m0.001s
./yyy: real 0m0.002s user 0m0.000s sys 0m0.001s
./yyy: real 0m0.003s user 0m0.000s sys 0m0.002s
./zzz: real 0m0.002s user 0m0.000s sys 0m0.001s
./zzz: real 0m0.002s user 0m0.000s sys 0m0.001s
./zzz: real 0m0.002s user 0m0.000s sys 0m0.001s
./zzz: real 0m0.002s user 0m0.000s sys 0m0.001s
./zzz: real 0m0.002s user 0m0.000s sys 0m0.001s
./zzz: real 0m0.002s user 0m0.000s sys 0m0.001s
./zzz: real 0m0.001s user 0m0.000s sys 0m0.001s
./zzz: real 0m0.002s user 0m0.000s sys 0m0.001s
./zzz: real 0m0.003s user 0m0.000s sys 0m0.002s
./zzz: real 0m0.002s user 0m0.000s sys 0m0.001s
./zzz: real 0m0.002s user 0m0.000s sys 0m0.001s

站号:87654

ocaml xxx.ml: real 0m0.102s user 0m0.059s sys 0m0.041s
ocaml xxx.ml: real 0m0.102s user 0m0.059s sys 0m0.040s
ocaml xxx.ml: real 0m0.101s user 0m0.060s sys 0m0.040s
ocaml xxx.ml: real 0m0.103s user 0m0.059s sys 0m0.041s
ocaml xxx.ml: real 0m0.102s user 0m0.059s sys 0m0.041s
ocaml xxx.ml: real 0m0.101s user 0m0.059s sys 0m0.041s
ocaml xxx.ml: real 0m0.102s user 0m0.059s sys 0m0.040s
ocaml xxx.ml: real 0m0.103s user 0m0.059s sys 0m0.040s
ocaml xxx.ml: real 0m0.101s user 0m0.059s sys 0m0.040s
ocaml xxx.ml: real 0m0.102s user 0m0.059s sys 0m0.040s
ocaml xxx.ml: real 0m0.105s user 0m0.059s sys 0m0.041s
./xxx: real 0m0.092s user 0m0.044s sys 0m0.038s
./xxx: real 0m0.087s user 0m0.044s sys 0m0.039s
./xxx: real 0m0.085s user 0m0.044s sys 0m0.038s
./xxx: real 0m0.084s user 0m0.044s sys 0m0.038s
./xxx: real 0m0.085s user 0m0.044s sys 0m0.039s
./xxx: real 0m0.086s user 0m0.045s sys 0m0.039s
./xxx: real 0m0.085s user 0m0.044s sys 0m0.039s
./xxx: real 0m0.085s user 0m0.044s sys 0m0.038s
./xxx: real 0m0.084s user 0m0.044s sys 0m0.038s
./xxx: real 0m0.084s user 0m0.044s sys 0m0.039s
./xxx: real 0m0.083s user 0m0.044s sys 0m0.038s
./yyy: real 0m0.004s user 0m0.003s sys 0m0.001s
./yyy: real 0m0.004s user 0m0.003s sys 0m0.001s
./yyy: real 0m0.004s user 0m0.003s sys 0m0.001s
./yyy: real 0m0.004s user 0m0.003s sys 0m0.001s
./yyy: real 0m0.005s user 0m0.003s sys 0m0.001s
./yyy: real 0m0.005s user 0m0.003s sys 0m0.001s
./yyy: real 0m0.004s user 0m0.003s sys 0m0.001s
./yyy: real 0m0.004s user 0m0.003s sys 0m0.001s
./yyy: real 0m0.004s user 0m0.003s sys 0m0.001s
./yyy: real 0m0.004s user 0m0.003s sys 0m0.001s
./yyy: real 0m0.006s user 0m0.003s sys 0m0.002s
./zzz: real 0m0.004s user 0m0.003s sys 0m0.001s
./zzz: real 0m0.004s user 0m0.003s sys 0m0.001s
./zzz: real 0m0.004s user 0m0.003s sys 0m0.001s
./zzz: real 0m0.004s user 0m0.003s sys 0m0.001s
./zzz: real 0m0.004s user 0m0.003s sys 0m0.001s
./zzz: real 0m0.005s user 0m0.003s sys 0m0.002s
./zzz: real 0m0.004s user 0m0.003s sys 0m0.001s
./zzz: real 0m0.004s user 0m0.003s sys 0m0.001s
./zzz: real 0m0.004s user 0m0.003s sys 0m0.001s
./zzz: real 0m0.004s user 0m0.003s sys 0m0.001s
./zzz: real 0m0.005s user 0m0.003s sys 0m0.001s

显然,YMMV - 但 OCaml 似乎比 C 慢很多,但如果给定文件中的数字足够小,则启动和文件读取将主导进程时间。

C 时序,尤其是在较小的数字上,非常快,以至于它们并不那么可靠。

关于c - 为什么这个 OCaml 程序比我的 C 程序快?,我们在Stack Overflow上找到一个类似的问题: https://stackoverflow.com/questions/1586423/

相关文章:

c# - 生成 CPU 缓存未命中时的性能

map - OCaml 有通用的 map()/reduce() 函数吗?

c - 如何在 C 中填充二维结构数组?

c - 需要帮助用 C 打开 sqlite3 数据库

c - 如何将 C_FLOAT 数组传递给 Fortran 子例程

c# - 如何消除此循环矢量化的数组边界检查?

mysql - 将mysql慢查询日志更改为public_html路径

arrays - Ocaml 中的数组操作

module - OCaml 中的未绑定(bind)模块

c - CodeBlocks 13.12 上的 Valgrind