in lib/decompress/zstd_decompress_block.c [445:562]
void ZSTD_buildFSETable_body(ZSTD_seqSymbol* dt,
const short* normalizedCounter, unsigned maxSymbolValue,
const U32* baseValue, const U8* nbAdditionalBits,
unsigned tableLog, void* wksp, size_t wkspSize)
{
ZSTD_seqSymbol* const tableDecode = dt+1;
U32 const maxSV1 = maxSymbolValue + 1;
U32 const tableSize = 1 << tableLog;
U16* symbolNext = (U16*)wksp;
BYTE* spread = (BYTE*)(symbolNext + MaxSeq + 1);
U32 highThreshold = tableSize - 1;
/* Sanity Checks */
assert(maxSymbolValue <= MaxSeq);
assert(tableLog <= MaxFSELog);
assert(wkspSize >= ZSTD_BUILD_FSE_TABLE_WKSP_SIZE);
(void)wkspSize;
/* Init, lay down lowprob symbols */
{ ZSTD_seqSymbol_header DTableH;
DTableH.tableLog = tableLog;
DTableH.fastMode = 1;
{ S16 const largeLimit= (S16)(1 << (tableLog-1));
U32 s;
for (s=0; s<maxSV1; s++) {
if (normalizedCounter[s]==-1) {
tableDecode[highThreshold--].baseValue = s;
symbolNext[s] = 1;
} else {
if (normalizedCounter[s] >= largeLimit) DTableH.fastMode=0;
assert(normalizedCounter[s]>=0);
symbolNext[s] = (U16)normalizedCounter[s];
} } }
ZSTD_memcpy(dt, &DTableH, sizeof(DTableH));
}
/* Spread symbols */
assert(tableSize <= 512);
/* Specialized symbol spreading for the case when there are
* no low probability (-1 count) symbols. When compressing
* small blocks we avoid low probability symbols to hit this
* case, since header decoding speed matters more.
*/
if (highThreshold == tableSize - 1) {
size_t const tableMask = tableSize-1;
size_t const step = FSE_TABLESTEP(tableSize);
/* First lay down the symbols in order.
* We use a uint64_t to lay down 8 bytes at a time. This reduces branch
* misses since small blocks generally have small table logs, so nearly
* all symbols have counts <= 8. We ensure we have 8 bytes at the end of
* our buffer to handle the over-write.
*/
{
U64 const add = 0x0101010101010101ull;
size_t pos = 0;
U64 sv = 0;
U32 s;
for (s=0; s<maxSV1; ++s, sv += add) {
int i;
int const n = normalizedCounter[s];
MEM_write64(spread + pos, sv);
for (i = 8; i < n; i += 8) {
MEM_write64(spread + pos + i, sv);
}
pos += n;
}
}
/* Now we spread those positions across the table.
* The benefit of doing it in two stages is that we avoid the
* variable size inner loop, which caused lots of branch misses.
* Now we can run through all the positions without any branch misses.
* We unroll the loop twice, since that is what empirically worked best.
*/
{
size_t position = 0;
size_t s;
size_t const unroll = 2;
assert(tableSize % unroll == 0); /* FSE_MIN_TABLELOG is 5 */
for (s = 0; s < (size_t)tableSize; s += unroll) {
size_t u;
for (u = 0; u < unroll; ++u) {
size_t const uPosition = (position + (u * step)) & tableMask;
tableDecode[uPosition].baseValue = spread[s + u];
}
position = (position + (unroll * step)) & tableMask;
}
assert(position == 0);
}
} else {
U32 const tableMask = tableSize-1;
U32 const step = FSE_TABLESTEP(tableSize);
U32 s, position = 0;
for (s=0; s<maxSV1; s++) {
int i;
int const n = normalizedCounter[s];
for (i=0; i<n; i++) {
tableDecode[position].baseValue = s;
position = (position + step) & tableMask;
while (position > highThreshold) position = (position + step) & tableMask; /* lowprob area */
} }
assert(position == 0); /* position must reach all cells once, otherwise normalizedCounter is incorrect */
}
/* Build Decoding table */
{
U32 u;
for (u=0; u<tableSize; u++) {
U32 const symbol = tableDecode[u].baseValue;
U32 const nextState = symbolNext[symbol]++;
tableDecode[u].nbBits = (BYTE) (tableLog - ZSTD_highbit32(nextState) );
tableDecode[u].nextState = (U16) ( (nextState << tableDecode[u].nbBits) - tableSize);
assert(nbAdditionalBits[symbol] < 255);
tableDecode[u].nbAdditionalBits = nbAdditionalBits[symbol];
tableDecode[u].baseValue = baseValue[symbol];
}
}
}