c++ - is it possible for MurmurHash3 to produce a 64 bit hash where the upper 32 bits are all 0? -
looking @ https://github.com/aappleby/smhasher/blob/master/src/murmurhash3.cpp don't think wanted check.
the situation this, if have key of 1,2,3 or 4 bytes, reliable take numeric value of bytes instead of hashing 8 bytes, or cause collision keys greater 4 bytes hashed murmur3?
such property bad property hash function. shrinks function co-domain, increasing collision chance, seems unlikely.
moreover, this blog post provides inversion function murmurhash:
uint64 murmur_hash_64(const void * key, int len, uint64 seed) { const uint64 m = 0xc6a4a7935bd1e995ull; const int r = 47; uint64 h = seed ^ (len * m); const uint64 * data = (const uint64 *)key; const uint64 * end = data + (len / 8); while (data != end) { #ifdef platform_big_endian uint64 k = *data++; char *p = (char *)&k; char c; c = p[0]; p[0] = p[7]; p[7] = c; c = p[1]; p[1] = p[6]; p[6] = c; c = p[2]; p[2] = p[5]; p[5] = c; c = p[3]; p[3] = p[4]; p[4] = c; #else uint64 k = *data++; #endif 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(data2[6]) << 48; case 6: h ^= uint64(data2[5]) << 40; case 5: h ^= uint64(data2[4]) << 32; case 4: h ^= uint64(data2[3]) << 24; case 3: h ^= uint64(data2[2]) << 16; case 2: h ^= uint64(data2[1]) << 8; case 1: h ^= uint64(data2[0]); h *= m; }; h ^= h >> r; h *= m; h ^= h >> r; return h; } uint64 murmur_hash_64_inverse(uint64 h, uint64 seed) { const uint64 m = 0xc6a4a7935bd1e995ull; const uint64 minv = 0x5f7a0ea7e59b19bdull; // multiplicative inverse of m under % 2^64 const int r = 47; h ^= h >> r; h *= minv; h ^= h >> r; h *= minv; uint64 hforward = seed ^ (((uint64)8) * m); uint64 k = h ^ hforward; k *= minv; k ^= k >> r; k *= minv; #ifdef platform_big_endian char *p = (char *)&k; char c; c = p[0]; p[0] = p[7]; p[7] = c; c = p[1]; p[1] = p[6]; p[6] = c; c = p[2]; p[2] = p[5]; p[5] = c; c = p[3]; p[3] = p[4]; p[4] = c; #endif return k; }
you can find many inputs hash values <2^32
want.
your question reliability doesn't make sense: must ready handle collisions properly. practice, not recommend use plain integers or pointer values hash, can produce undesired patterns.
Comments
Post a Comment