Load more dictionary positions into table if empty

If the hash table is empty load positions into the hash table
that we would otherwise skip.

| Level | Data Set     | Improvement |
|-------|--------------|-------------|
| 1     | github       | 0.44%       |
| 1     | hg-changelog | 0.13%       |
| 1     | hg-commands  | 1.28%       |
| 1     | hg-manifest  | 0.70%       |
| 3     | github       | 0.74%       |
| 3     | hg-changelog | 0.87%       |
| 3     | hg-commands  | 1.74%       |
| 3     | hg-manifest  | 0.23%       |
This commit is contained in:
Nick Terrell 2018-01-12 12:26:47 -08:00
parent 04c00f9388
commit 9a211d1f05
2 changed files with 28 additions and 9 deletions

View File

@ -21,12 +21,23 @@ void ZSTD_fillDoubleHashTable(ZSTD_CCtx* cctx, const void* end, const U32 mls)
const BYTE* const base = cctx->base;
const BYTE* ip = base + cctx->nextToUpdate;
const BYTE* const iend = ((const BYTE*)end) - HASH_READ_SIZE;
const size_t fastHashFillStep = 3;
const U32 fastHashFillStep = 3;
while(ip <= iend) {
hashSmall[ZSTD_hashPtr(ip, hBitsS, mls)] = (U32)(ip - base);
hashLarge[ZSTD_hashPtr(ip, hBitsL, 8)] = (U32)(ip - base);
ip += fastHashFillStep;
/* Always insert every fastHashFillStep position into the hash tables.
* Insert the other positions into the large hash table if their entry
* is empty.
*/
for (; ip + fastHashFillStep - 1 <= iend; ip += fastHashFillStep) {
U32 const current = (U32)(ip - base);
U32 i;
for (i = 0; i < fastHashFillStep; ++i) {
size_t const smHash = ZSTD_hashPtr(ip + i, hBitsS, mls);
size_t const lgHash = ZSTD_hashPtr(ip + i, hBitsL, 8);
if (i == 0)
hashSmall[smHash] = current + i;
if (i == 0 || hashLarge[lgHash] == 0)
hashLarge[lgHash] = current + i;
}
}
}

View File

@ -19,11 +19,19 @@ void ZSTD_fillHashTable (ZSTD_CCtx* zc, const void* end, const U32 mls)
const BYTE* const base = zc->base;
const BYTE* ip = base + zc->nextToUpdate;
const BYTE* const iend = ((const BYTE*)end) - HASH_READ_SIZE;
const size_t fastHashFillStep = 3;
const U32 fastHashFillStep = 3;
while(ip <= iend) {
hashTable[ZSTD_hashPtr(ip, hBits, mls)] = (U32)(ip - base);
ip += fastHashFillStep;
/* Always insert every fastHashFillStep position into the hash table.
* Insert the other positions if their hash entry is empty.
*/
for (; ip + fastHashFillStep - 1 <= iend; ip += fastHashFillStep) {
U32 const current = (U32)(ip - base);
U32 i;
for (i = 0; i < fastHashFillStep; ++i) {
size_t const hash = ZSTD_hashPtr(ip + i, hBits, mls);
if (i == 0 || hashTable[hash] == 0)
hashTable[hash] = current + i;
}
}
}