diff --git a/src/backend/access/hash/hashfunc.c b/src/backend/access/hash/hashfunc.c index a127f3f8b1..b72df9b773 100644 --- a/src/backend/access/hash/hashfunc.c +++ b/src/backend/access/hash/hashfunc.c @@ -502,6 +502,226 @@ hash_any(register const unsigned char *k, register int keylen) } /* + * hash_any_extended() -- hash into a 64-bit value, using an optional seed + * k : the key (the unaligned variable-length array of bytes) + * len : the length of the key, counting by bytes + * seed : a 64-bit seed (0 means no seed) + * + * Returns a uint64 value. Otherwise similar to hash_any. + */ +Datum +hash_any_extended(register const unsigned char *k, register int keylen, + uint64 seed) +{ + register uint32 a, + b, + c, + len; + + /* Set up the internal state */ + len = keylen; + a = b = c = 0x9e3779b9 + len + 3923095; + + /* If the seed is non-zero, use it to perturb the internal state. */ + if (seed != 0) + { + /* + * In essence, the seed is treated as part of the data being hashed, + * but for simplicity, we pretend that it's padded with four bytes of + * zeroes so that the seed constitutes a 4-byte chunk. + */ + a += (uint32) (seed >> 32); + b += (uint32) seed; + mix(a, b, c); + } + + /* If the source pointer is word-aligned, we use word-wide fetches */ + if (((uintptr_t) k & UINT32_ALIGN_MASK) == 0) + { + /* Code path for aligned source data */ + register const uint32 *ka = (const uint32 *) k; + + /* handle most of the key */ + while (len >= 12) + { + a += ka[0]; + b += ka[1]; + c += ka[2]; + mix(a, b, c); + ka += 3; + len -= 12; + } + + /* handle the last 11 bytes */ + k = (const unsigned char *) ka; +#ifdef WORDS_BIGENDIAN + switch (len) + { + case 11: + c += ((uint32) k[10] << 8); + /* fall through */ + case 10: + c += ((uint32) k[9] << 16); + /* fall through */ + case 9: + c += ((uint32) k[8] << 24); + /* the lowest byte of c is reserved for the length */ + /* fall through */ + case 8: + b += ka[1]; + a += ka[0]; + break; + case 7: + b += ((uint32) k[6] << 8); + /* fall through */ + case 6: + b += ((uint32) k[5] << 16); + /* fall through */ + case 5: + b += ((uint32) k[4] << 24); + /* fall through */ + case 4: + a += ka[0]; + break; + case 3: + a += ((uint32) k[2] << 8); + /* fall through */ + case 2: + a += ((uint32) k[1] << 16); + /* fall through */ + case 1: + a += ((uint32) k[0] << 24); + /* case 0: nothing left to add */ + } +#else /* !WORDS_BIGENDIAN */ + switch (len) + { + case 11: + c += ((uint32) k[10] << 24); + /* fall through */ + case 10: + c += ((uint32) k[9] << 16); + /* fall through */ + case 9: + c += ((uint32) k[8] << 8); + /* the lowest byte of c is reserved for the length */ + /* fall through */ + case 8: + b += ka[1]; + a += ka[0]; + break; + case 7: + b += ((uint32) k[6] << 16); + /* fall through */ + case 6: + b += ((uint32) k[5] << 8); + /* fall through */ + case 5: + b += k[4]; + /* fall through */ + case 4: + a += ka[0]; + break; + case 3: + a += ((uint32) k[2] << 16); + /* fall through */ + case 2: + a += ((uint32) k[1] << 8); + /* fall through */ + case 1: + a += k[0]; + /* case 0: nothing left to add */ + } +#endif /* WORDS_BIGENDIAN */ + } + else + { + /* Code path for non-aligned source data */ + + /* handle most of the key */ + while (len >= 12) + { +#ifdef WORDS_BIGENDIAN + a += (k[3] + ((uint32) k[2] << 8) + ((uint32) k[1] << 16) + ((uint32) k[0] << 24)); + b += (k[7] + ((uint32) k[6] << 8) + ((uint32) k[5] << 16) + ((uint32) k[4] << 24)); + c += (k[11] + ((uint32) k[10] << 8) + ((uint32) k[9] << 16) + ((uint32) k[8] << 24)); +#else /* !WORDS_BIGENDIAN */ + a += (k[0] + ((uint32) k[1] << 8) + ((uint32) k[2] << 16) + ((uint32) k[3] << 24)); + b += (k[4] + ((uint32) k[5] << 8) + ((uint32) k[6] << 16) + ((uint32) k[7] << 24)); + c += (k[8] + ((uint32) k[9] << 8) + ((uint32) k[10] << 16) + ((uint32) k[11] << 24)); +#endif /* WORDS_BIGENDIAN */ + mix(a, b, c); + k += 12; + len -= 12; + } + + /* handle the last 11 bytes */ +#ifdef WORDS_BIGENDIAN + switch (len) /* all the case statements fall through */ + { + case 11: + c += ((uint32) k[10] << 8); + case 10: + c += ((uint32) k[9] << 16); + case 9: + c += ((uint32) k[8] << 24); + /* the lowest byte of c is reserved for the length */ + case 8: + b += k[7]; + case 7: + b += ((uint32) k[6] << 8); + case 6: + b += ((uint32) k[5] << 16); + case 5: + b += ((uint32) k[4] << 24); + case 4: + a += k[3]; + case 3: + a += ((uint32) k[2] << 8); + case 2: + a += ((uint32) k[1] << 16); + case 1: + a += ((uint32) k[0] << 24); + /* case 0: nothing left to add */ + } +#else /* !WORDS_BIGENDIAN */ + switch (len) /* all the case statements fall through */ + { + case 11: + c += ((uint32) k[10] << 24); + case 10: + c += ((uint32) k[9] << 16); + case 9: + c += ((uint32) k[8] << 8); + /* the lowest byte of c is reserved for the length */ + case 8: + b += ((uint32) k[7] << 24); + case 7: + b += ((uint32) k[6] << 16); + case 6: + b += ((uint32) k[5] << 8); + case 5: + b += k[4]; + case 4: + a += ((uint32) k[3] << 24); + case 3: + a += ((uint32) k[2] << 16); + case 2: + a += ((uint32) k[1] << 8); + case 1: + a += k[0]; + /* case 0: nothing left to add */ + } +#endif /* WORDS_BIGENDIAN */ + } + + final(a, b, c); + + /* report the result */ + return UInt64GetDatum(((uint64) b << 32) | c); +} + +/* * hash_uint32() -- hash a 32-bit value * * This has the same result as diff --git a/src/include/access/hash.h b/src/include/access/hash.h index 72fce3038c..383d7d67d3 100644 --- a/src/include/access/hash.h +++ b/src/include/access/hash.h @@ -322,6 +322,8 @@ extern bytea *hashoptions(Datum reloptions, bool validate); extern bool hashvalidate(Oid opclassoid); extern Datum hash_any(register const unsigned char *k, register int keylen); +extern Datum hash_any_extended(register const unsigned char *k, register int + keylen, uint64 seed); extern Datum hash_uint32(uint32 k); /* private routines */