google sparse hash with murmur hash function

问题

How to use murmur hash function in google sparse hash map? Could you please give me step by step instructions on how to use murmur hash function? I'm using visual c++.

Currently I'm using std::hash hash function in google sparse hash map. Is there any performance difference between the goole sparse hash maps which are implemented using std::hash and murmur hash?

回答1:

You need to provide hash function to sparse_hash_map template. I've checked https://sites.google.com/site/murmurhash/; it's interface is different than std::hash<>, so you'll need to write adapter class. Here's a working example (keep in mind that adapter only covers some cases):

#include <iostream>
#include <sparsehash/sparse_hash_map>

using google::sparse_hash_map;      // namespace where class lives by default
using namespace std;

// 64-bit hash for 64-bit platforms
// copied from https://sites.google.com/site/murmurhash/
uint64_t MurmurHash64A ( const void * key, int len, unsigned int seed )
{
  const uint64_t m = 0xc6a4a7935bd1e995;
  const int r = 47;

  uint64_t h = seed ^ (len * m);

  const uint64_t * data = (const uint64_t *)key;
  const uint64_t * end = data + (len/8);

  while(data != end)
  {
    uint64_t k = *data++;

    k *= m; 
    k ^= k >> r; 
    k *= m; 

    h ^= k;
    h *= m; 
  }

  const unsigned char * data2 = (const unsigned char*)data;

  switch(len & 7)
  {
  case 7: h ^= uint64_t(data2[6]) << 48;
  case 6: h ^= uint64_t(data2[5]) << 40;
  case 5: h ^= uint64_t(data2[4]) << 32;
  case 4: h ^= uint64_t(data2[3]) << 24;
  case 3: h ^= uint64_t(data2[2]) << 16;
  case 2: h ^= uint64_t(data2[1]) << 8;
  case 1: h ^= uint64_t(data2[0]);
          h *= m;
  };

  h ^= h >> r;
  h *= m;
  h ^= h >> r;

  return h;
} 

// simple hash adapter for types without pointers
template<typename T> 
struct MurmurHasher {
    size_t operator()(const T& t) const {
        return MurmurHash64A(&t, sizeof(t), 0);
    }    
};

// specialization for strings
template<> 
struct MurmurHasher<string> {
    size_t operator()(const string& t) const {
        return MurmurHash64A(t.c_str(), t.size(), 0);
    }    
};

struct eqstr
{
  bool operator()(const char* s1, const char* s2) const
  {
    return (s1 == s2) || (s1 && s2 && strcmp(s1, s2) == 0);
  }
};

int main()
{
  sparse_hash_map<const char*, int, MurmurHasher<const char*>, eqstr> months;

  months["january"] = 31;
  months["february"] = 28;
  months["march"] = 31;
  months["april"] = 30;
  months["may"] = 31;
  months["june"] = 30;
  months["july"] = 31;
  months["august"] = 31;
  months["september"] = 30;
  months["october"] = 31;
  months["november"] = 30;
  months["december"] = 31;

  cout << "september -> " << months["september"] << endl;
  cout << "april     -> " << months["april"] << endl;
  cout << "june      -> " << months["june"] << endl;
  cout << "november  -> " << months["november"] << endl;

  sparse_hash_map<string, int, MurmurHasher<string>> years;
  years["2012"] = 366;
  cout << "2012      -> " << years["2012"] << endl;
}

Performance will probably depend on your data patterns, so you should do the tests yourself.

来源：https://stackoverflow.com/questions/14094104/google-sparse-hash-with-murmur-hash-function

标签

visual-c++

hashmap

murmurhash