Add salt into row hash (#3528 part 2) (#3533)

Part 2 of #3528

Adds hash salt that helps to avoid regressions where consecutive compressions use the same tag space with similar data (running zstd -b5e7 enwik8 -B128K reproduces this regression).
This commit is contained in:
Yonatan Komornik
2023-03-13 15:34:13 -07:00
committed by GitHub
parent 9420bce8a4
commit 91f4c23e63
4 changed files with 104 additions and 48 deletions
+39 -12
View File
@@ -228,6 +228,8 @@ struct ZSTD_matchState_t {
U32 rowHashLog; /* For row-based matchfinder: Hashlog based on nb of rows in the hashTable.*/
BYTE* tagTable; /* For row-based matchFinder: A row-based table containing the hashes and head index. */
U32 hashCache[ZSTD_ROW_HASH_CACHE_SIZE]; /* For row-based matchFinder: a cache of hashes to improve speed */
U64 hashSalt; /* For row-based matchFinder: salts the hash for re-use of tag table */
U32 hashSaltEntropy; /* For row-based matchFinder: collects entropy for salt generation */
U32* hashTable;
U32* hashTable3;
@@ -787,28 +789,35 @@ ZSTD_count_2segments(const BYTE* ip, const BYTE* match,
* Hashes
***************************************/
static const U32 prime3bytes = 506832829U;
static U32 ZSTD_hash3(U32 u, U32 h) { assert(h <= 32); return ((u << (32-24)) * prime3bytes) >> (32-h) ; }
MEM_STATIC size_t ZSTD_hash3Ptr(const void* ptr, U32 h) { return ZSTD_hash3(MEM_readLE32(ptr), h); } /* only in zstd_opt.h */
static U32 ZSTD_hash3(U32 u, U32 h, U32 s) { assert(h <= 32); return (((u << (32-24)) * prime3bytes) ^ s) >> (32-h) ; }
MEM_STATIC size_t ZSTD_hash3Ptr(const void* ptr, U32 h) { return ZSTD_hash3(MEM_readLE32(ptr), h, 0); } /* only in zstd_opt.h */
MEM_STATIC size_t ZSTD_hash3PtrS(const void* ptr, U32 h, U32 s) { return ZSTD_hash3(MEM_readLE32(ptr), h, s); }
static const U32 prime4bytes = 2654435761U;
static U32 ZSTD_hash4(U32 u, U32 h) { assert(h <= 32); return (u * prime4bytes) >> (32-h) ; }
static size_t ZSTD_hash4Ptr(const void* ptr, U32 h) { return ZSTD_hash4(MEM_readLE32(ptr), h); }
static U32 ZSTD_hash4(U32 u, U32 h, U32 s) { assert(h <= 32); return ((u * prime4bytes) ^ s) >> (32-h) ; }
static size_t ZSTD_hash4Ptr(const void* ptr, U32 h) { return ZSTD_hash4(MEM_readLE32(ptr), h, 0); }
static size_t ZSTD_hash4PtrS(const void* ptr, U32 h, U32 s) { return ZSTD_hash4(MEM_readLE32(ptr), h, s); }
static const U64 prime5bytes = 889523592379ULL;
static size_t ZSTD_hash5(U64 u, U32 h) { assert(h <= 64); return (size_t)(((u << (64-40)) * prime5bytes) >> (64-h)) ; }
static size_t ZSTD_hash5Ptr(const void* p, U32 h) { return ZSTD_hash5(MEM_readLE64(p), h); }
static size_t ZSTD_hash5(U64 u, U32 h, U64 s) { assert(h <= 64); return (size_t)((((u << (64-40)) * prime5bytes) ^ s) >> (64-h)) ; }
static size_t ZSTD_hash5Ptr(const void* p, U32 h) { return ZSTD_hash5(MEM_readLE64(p), h, 0); }
static size_t ZSTD_hash5PtrS(const void* p, U32 h, U64 s) { return ZSTD_hash5(MEM_readLE64(p), h, s); }
static const U64 prime6bytes = 227718039650203ULL;
static size_t ZSTD_hash6(U64 u, U32 h) { assert(h <= 64); return (size_t)(((u << (64-48)) * prime6bytes) >> (64-h)) ; }
static size_t ZSTD_hash6Ptr(const void* p, U32 h) { return ZSTD_hash6(MEM_readLE64(p), h); }
static size_t ZSTD_hash6(U64 u, U32 h, U64 s) { assert(h <= 64); return (size_t)((((u << (64-48)) * prime6bytes) ^ s) >> (64-h)) ; }
static size_t ZSTD_hash6Ptr(const void* p, U32 h) { return ZSTD_hash6(MEM_readLE64(p), h, 0); }
static size_t ZSTD_hash6PtrS(const void* p, U32 h, U64 s) { return ZSTD_hash6(MEM_readLE64(p), h, s); }
static const U64 prime7bytes = 58295818150454627ULL;
static size_t ZSTD_hash7(U64 u, U32 h) { assert(h <= 64); return (size_t)(((u << (64-56)) * prime7bytes) >> (64-h)) ; }
static size_t ZSTD_hash7Ptr(const void* p, U32 h) { return ZSTD_hash7(MEM_readLE64(p), h); }
static size_t ZSTD_hash7(U64 u, U32 h, U64 s) { assert(h <= 64); return (size_t)((((u << (64-56)) * prime7bytes) ^ s) >> (64-h)) ; }
static size_t ZSTD_hash7Ptr(const void* p, U32 h) { return ZSTD_hash7(MEM_readLE64(p), h, 0); }
static size_t ZSTD_hash7PtrS(const void* p, U32 h, U64 s) { return ZSTD_hash7(MEM_readLE64(p), h, s); }
static const U64 prime8bytes = 0xCF1BBCDCB7A56463ULL;
static size_t ZSTD_hash8(U64 u, U32 h) { assert(h <= 64); return (size_t)(((u) * prime8bytes) >> (64-h)) ; }
static size_t ZSTD_hash8Ptr(const void* p, U32 h) { return ZSTD_hash8(MEM_readLE64(p), h); }
static size_t ZSTD_hash8(U64 u, U32 h, U64 s) { assert(h <= 64); return (size_t)((((u) * prime8bytes) ^ s) >> (64-h)) ; }
static size_t ZSTD_hash8Ptr(const void* p, U32 h) { return ZSTD_hash8(MEM_readLE64(p), h, 0); }
static size_t ZSTD_hash8PtrS(const void* p, U32 h, U64 s) { return ZSTD_hash8(MEM_readLE64(p), h, s); }
MEM_STATIC FORCE_INLINE_ATTR
size_t ZSTD_hashPtr(const void* p, U32 hBits, U32 mls)
@@ -828,6 +837,24 @@ size_t ZSTD_hashPtr(const void* p, U32 hBits, U32 mls)
}
}
MEM_STATIC FORCE_INLINE_ATTR
size_t ZSTD_hashPtrSalted(const void* p, U32 hBits, U32 mls, const U64 hashSalt) {
/* Although some of these hashes do support hBits up to 64, some do not.
* To be on the safe side, always avoid hBits > 32. */
assert(hBits <= 32);
switch(mls)
{
default:
case 4: return ZSTD_hash4PtrS(p, hBits, (U32)hashSalt);
case 5: return ZSTD_hash5PtrS(p, hBits, hashSalt);
case 6: return ZSTD_hash6PtrS(p, hBits, hashSalt);
case 7: return ZSTD_hash7PtrS(p, hBits, hashSalt);
case 8: return ZSTD_hash8PtrS(p, hBits, hashSalt);
}
}
/** ZSTD_ipow() :
* Return base^exponent.
*/