如何在 Ruby C API 中有效地合并两个哈希值?

发布于 2024-08-02 02:08:44 字数 338 浏览 5 评论 0原文

我正在为 Ruby 编写一个 C 扩展,它确实需要合并两个哈希值,但是 rb_hash_merge() 函数在 Ruby 1.8.6 中是静态的。 我尝试改为使用:

rb_funcall(hash1, rb_intern("merge"), 1, hash2);

但这太慢了,并且在此应用程序中性能非常关键。

有谁知道如何在考虑到效率和速度的情况下执行此合并?

(请注意,我尝试简单地查看 rb_hash_merge() 的源代码并复制它,但它充满了其他静态函数,这些函数本身也充满了更多静态函数,因此似乎几乎不可能解开......我需要另一种方法)

I am writing a C extension for Ruby that really needs to merge two hashes, however the rb_hash_merge() function is STATIC in Ruby 1.8.6. I have tried instead to use:

rb_funcall(hash1, rb_intern("merge"), 1, hash2);

but this is much too slow, and performance is very critical in this application.

Does anyone know how to go about performing this merge with efficiency and speed in mind?

(Note I have tried simply looking at the source for rb_hash_merge() and replicating it but it is RIDDLED with other static functions, which are themselves riddled with yet more static functions so it seems almost impossible to disentangle...i need another way)

如果你对这篇内容有疑问,欢迎到本站社区发帖提问 参与讨论,获取更多帮助,或者扫码二维码加入 Web 技术交流群。

扫码二维码加入Web技术交流群

发布评论

需要 登录 才能够评论, 你可以免费 注册 一个本站的账号。

评论(1

寂寞清仓 2024-08-09 02:08:44

好吧,看起来可能无法在已发布的 API 中进行优化。

测试代码:

#extconf.rb
require 'mkmf'
dir_config("hello")
create_makefile("hello")


// hello.c
#include "ruby.h"

static VALUE rb_mHello;
static VALUE rb_cMyCalc;

static void calc_mark(void *f) { }
static void calc_free(void *f) { }
static VALUE calc_alloc(VALUE klass) { return Data_Wrap_Struct(klass, calc_mark, calc_free, NULL); }

static VALUE calc_init(VALUE obj) { return Qnil; }

static VALUE calc_merge(VALUE obj, VALUE h1, VALUE h2) {
  return rb_funcall(h1, rb_intern("merge"), 1, h2);
}

static VALUE
calc_merge2(VALUE obj, VALUE h1, VALUE h2)
{
  VALUE h3 = rb_hash_new();
  VALUE keys;
  VALUE akey;
  keys = rb_funcall(h1, rb_intern("keys"), 0);
  while (akey = rb_each(keys)) {
    rb_hash_aset(h3, akey, rb_hash_aref(h1, akey));
  }
  keys = rb_funcall(h2, rb_intern("keys"), 0);
  while (akey = rb_each(keys)) {
    rb_hash_aset(h3, akey, rb_hash_aref(h2, akey));
  }
  return h3;
}

static VALUE
calc_merge3(VALUE obj, VALUE h1, VALUE h2)
{
  VALUE keys;
  VALUE akey;
  keys = rb_funcall(h1, rb_intern("keys"), 0);
  while (akey = rb_each(keys)) {
    rb_hash_aset(h2, akey, rb_hash_aref(h1, akey));
  }
  return h2;
}

void
Init_hello()
{
  rb_mHello = rb_define_module("Hello");
  rb_cMyCalc = rb_define_class_under(rb_mHello, "Calculator", rb_cObject);
  rb_define_alloc_func(rb_cMyCalc, calc_alloc);
  rb_define_method(rb_cMyCalc, "initialize", calc_init, 0);
  rb_define_method(rb_cMyCalc, "merge", calc_merge, 2);
  rb_define_method(rb_cMyCalc, "merge2", calc_merge, 2);
  rb_define_method(rb_cMyCalc, "merge3", calc_merge, 2);
}


# test.rb
require "hello"

h1 = Hash.new()
h2 = Hash.new()

1.upto(100000) { |x| h1[x] = x+1; }
1.upto(100000) { |x| h2["#{x}-12"] = x+1; }

c = Hello::Calculator.new()

puts c.merge(h1, h2).keys.length if ARGV[0] == "1"
puts c.merge2(h1, h2).keys.length if ARGV[0] == "2"
puts c.merge3(h1, h2).keys.length if ARGV[0] == "3"

现在是测试结果:

$ time ruby test.rb

real    0m1.021s
user    0m0.940s
sys     0m0.080s
$ time ruby test.rb 1
200000

real    0m1.224s
user    0m1.148s
sys     0m0.076s
$ time ruby test.rb 2
200000

real    0m1.219s
user    0m1.132s
sys     0m0.084s
$ time ruby test.rb 3
200000

real    0m1.220s
user    0m1.128s
sys     0m0.092s

所以看起来我们可以在 0.2 秒的操作上最多减少约 0.004 秒。

鉴于除了设置值之外可能没有那么多,因此可能没有那么多空间进行进一步优化。 也许尝试破解 ruby​​ 源代码本身 - 但那时您不再真正开发“扩展”,而是更改语言,因此它可能行不通。

如果散列连接是您需要在 C 部分中多次执行的操作 - 那么可能使用内部数据结构并仅在最后一遍将它们导出到 Ruby 散列中将是优化事物的唯一方法。

ps 代码的初始框架借自这个优秀的教程< /a>

Ok, looks like might be not possible to optimize within the published API.

Test code:

#extconf.rb
require 'mkmf'
dir_config("hello")
create_makefile("hello")


// hello.c
#include "ruby.h"

static VALUE rb_mHello;
static VALUE rb_cMyCalc;

static void calc_mark(void *f) { }
static void calc_free(void *f) { }
static VALUE calc_alloc(VALUE klass) { return Data_Wrap_Struct(klass, calc_mark, calc_free, NULL); }

static VALUE calc_init(VALUE obj) { return Qnil; }

static VALUE calc_merge(VALUE obj, VALUE h1, VALUE h2) {
  return rb_funcall(h1, rb_intern("merge"), 1, h2);
}

static VALUE
calc_merge2(VALUE obj, VALUE h1, VALUE h2)
{
  VALUE h3 = rb_hash_new();
  VALUE keys;
  VALUE akey;
  keys = rb_funcall(h1, rb_intern("keys"), 0);
  while (akey = rb_each(keys)) {
    rb_hash_aset(h3, akey, rb_hash_aref(h1, akey));
  }
  keys = rb_funcall(h2, rb_intern("keys"), 0);
  while (akey = rb_each(keys)) {
    rb_hash_aset(h3, akey, rb_hash_aref(h2, akey));
  }
  return h3;
}

static VALUE
calc_merge3(VALUE obj, VALUE h1, VALUE h2)
{
  VALUE keys;
  VALUE akey;
  keys = rb_funcall(h1, rb_intern("keys"), 0);
  while (akey = rb_each(keys)) {
    rb_hash_aset(h2, akey, rb_hash_aref(h1, akey));
  }
  return h2;
}

void
Init_hello()
{
  rb_mHello = rb_define_module("Hello");
  rb_cMyCalc = rb_define_class_under(rb_mHello, "Calculator", rb_cObject);
  rb_define_alloc_func(rb_cMyCalc, calc_alloc);
  rb_define_method(rb_cMyCalc, "initialize", calc_init, 0);
  rb_define_method(rb_cMyCalc, "merge", calc_merge, 2);
  rb_define_method(rb_cMyCalc, "merge2", calc_merge, 2);
  rb_define_method(rb_cMyCalc, "merge3", calc_merge, 2);
}


# test.rb
require "hello"

h1 = Hash.new()
h2 = Hash.new()

1.upto(100000) { |x| h1[x] = x+1; }
1.upto(100000) { |x| h2["#{x}-12"] = x+1; }

c = Hello::Calculator.new()

puts c.merge(h1, h2).keys.length if ARGV[0] == "1"
puts c.merge2(h1, h2).keys.length if ARGV[0] == "2"
puts c.merge3(h1, h2).keys.length if ARGV[0] == "3"

Now the test results:

$ time ruby test.rb

real    0m1.021s
user    0m0.940s
sys     0m0.080s
$ time ruby test.rb 1
200000

real    0m1.224s
user    0m1.148s
sys     0m0.076s
$ time ruby test.rb 2
200000

real    0m1.219s
user    0m1.132s
sys     0m0.084s
$ time ruby test.rb 3
200000

real    0m1.220s
user    0m1.128s
sys     0m0.092s

So it looks like we might shave off at maximum ~0.004s on a 0.2s operation.

Given that there's probably not that much besides setting the values, there might not be that much space for further optimizations. Maybe try to hack the ruby source itself - but at that point you no longer really develop "extension" but rather change the language, so it probably won't work.

If the join of hashes is something that you need to do many times in the C part - then probably using the internal data structures and only exporting them into Ruby hash in the final pass would be the only way of optimizing things.

p.s. The initial skeleton for the code borrowed from this excellent tutorial

~没有更多了~
我们使用 Cookies 和其他技术来定制您的体验包括您的登录状态等。通过阅读我们的 隐私政策 了解更多相关信息。 单击 接受 或继续使用网站,即表示您同意使用 Cookies 和您的相关数据。
原文