mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/next/linux-next.git
synced 2024-12-29 17:22:07 +00:00
98988fc8e9
Import upstream zstd v1.5.5 to expose upstream's QAT integration.
Import from upstream commit 58b3ef79 [0]. This is one commit before the
tag v1.5.5-kernel [1], which is signed with upstream's signing key. The
next patch in the series imports from v1.5.5-kernel, and is included in
the series, rather than just importing directly from v1.5.5-kernel,
because it is a non-trivial patch applied to improve the kernel's
decompression speed. This commit contains 3 backported patches on top of
v1.5.5: Two from the Linux copy of zstd, and one from upstream's `dev`
branch.
In addition to keeping the kernel's copy of zstd up to date, this update
was requested by Intel to expose upstream zstd's external match provider
API to the kernel, which allows QAT to accelerate the LZ match finding
stage.
This commit was generated by:
export ZSTD=/path/to/repo/zstd/
export LINUX=/path/to/repo/linux/
cd "$ZSTD/contrib/linux-kernel"
git checkout v1.5.5-kernel~
make import LINUX="$LINUX"
I tested and benchmarked this commit on x86-64 with gcc-13.2.1 on an
Intel i9-9900K by running my benchmark scripts that benchmark zstd's
performance in btrfs and squashfs compressed filesystems. This commit
improves compression speed, especially for higher compression levels,
and regresses decompression speed. But the decompression speed
regression is addressed by the next patch in the series.
Component, Level, C. time delta, size delta, D. time delta
Btrfs , 1, -1.9%, +0.0%, +9.5%
Btrfs , 3, -5.6%, +0.0%, +7.4%
Btrfs , 5, -4.9%, +0.0%, +5.0%
Btrfs , 7, -5.7%, +0.0%, +5.2%
Btrfs , 9, -5.7%, +0.0%, +4.0%
Squashfs , 1, N/A, 0.0%, +11.6%
I also boot tested with a zstd compressed kernel on i386 and aarch64.
Link: 58b3ef79eb
Link: https://github.com/facebook/zstd/tree/v1.5.5-kernel
Signed-off-by: Nick Terrell <terrelln@fb.com>
626 lines
24 KiB
C
626 lines
24 KiB
C
// SPDX-License-Identifier: GPL-2.0+ OR BSD-3-Clause
|
|
/* ******************************************************************
|
|
* FSE : Finite State Entropy encoder
|
|
* Copyright (c) Meta Platforms, Inc. and affiliates.
|
|
*
|
|
* You can contact the author at :
|
|
* - FSE source repository : https://github.com/Cyan4973/FiniteStateEntropy
|
|
* - Public forum : https://groups.google.com/forum/#!forum/lz4c
|
|
*
|
|
* This source code is licensed under both the BSD-style license (found in the
|
|
* LICENSE file in the root directory of this source tree) and the GPLv2 (found
|
|
* in the COPYING file in the root directory of this source tree).
|
|
* You may select, at your option, one of the above-listed licenses.
|
|
****************************************************************** */
|
|
|
|
/* **************************************************************
|
|
* Includes
|
|
****************************************************************/
|
|
#include "../common/compiler.h"
|
|
#include "../common/mem.h" /* U32, U16, etc. */
|
|
#include "../common/debug.h" /* assert, DEBUGLOG */
|
|
#include "hist.h" /* HIST_count_wksp */
|
|
#include "../common/bitstream.h"
|
|
#define FSE_STATIC_LINKING_ONLY
|
|
#include "../common/fse.h"
|
|
#include "../common/error_private.h"
|
|
#define ZSTD_DEPS_NEED_MALLOC
|
|
#define ZSTD_DEPS_NEED_MATH64
|
|
#include "../common/zstd_deps.h" /* ZSTD_malloc, ZSTD_free, ZSTD_memcpy, ZSTD_memset */
|
|
#include "../common/bits.h" /* ZSTD_highbit32 */
|
|
|
|
|
|
/* **************************************************************
|
|
* Error Management
|
|
****************************************************************/
|
|
#define FSE_isError ERR_isError
|
|
|
|
|
|
/* **************************************************************
|
|
* Templates
|
|
****************************************************************/
|
|
/*
|
|
designed to be included
|
|
for type-specific functions (template emulation in C)
|
|
Objective is to write these functions only once, for improved maintenance
|
|
*/
|
|
|
|
/* safety checks */
|
|
#ifndef FSE_FUNCTION_EXTENSION
|
|
# error "FSE_FUNCTION_EXTENSION must be defined"
|
|
#endif
|
|
#ifndef FSE_FUNCTION_TYPE
|
|
# error "FSE_FUNCTION_TYPE must be defined"
|
|
#endif
|
|
|
|
/* Function names */
|
|
#define FSE_CAT(X,Y) X##Y
|
|
#define FSE_FUNCTION_NAME(X,Y) FSE_CAT(X,Y)
|
|
#define FSE_TYPE_NAME(X,Y) FSE_CAT(X,Y)
|
|
|
|
|
|
/* Function templates */
|
|
|
|
/* FSE_buildCTable_wksp() :
|
|
* Same as FSE_buildCTable(), but using an externally allocated scratch buffer (`workSpace`).
|
|
* wkspSize should be sized to handle worst case situation, which is `1<<max_tableLog * sizeof(FSE_FUNCTION_TYPE)`
|
|
* workSpace must also be properly aligned with FSE_FUNCTION_TYPE requirements
|
|
*/
|
|
size_t FSE_buildCTable_wksp(FSE_CTable* ct,
|
|
const short* normalizedCounter, unsigned maxSymbolValue, unsigned tableLog,
|
|
void* workSpace, size_t wkspSize)
|
|
{
|
|
U32 const tableSize = 1 << tableLog;
|
|
U32 const tableMask = tableSize - 1;
|
|
void* const ptr = ct;
|
|
U16* const tableU16 = ( (U16*) ptr) + 2;
|
|
void* const FSCT = ((U32*)ptr) + 1 /* header */ + (tableLog ? tableSize>>1 : 1) ;
|
|
FSE_symbolCompressionTransform* const symbolTT = (FSE_symbolCompressionTransform*) (FSCT);
|
|
U32 const step = FSE_TABLESTEP(tableSize);
|
|
U32 const maxSV1 = maxSymbolValue+1;
|
|
|
|
U16* cumul = (U16*)workSpace; /* size = maxSV1 */
|
|
FSE_FUNCTION_TYPE* const tableSymbol = (FSE_FUNCTION_TYPE*)(cumul + (maxSV1+1)); /* size = tableSize */
|
|
|
|
U32 highThreshold = tableSize-1;
|
|
|
|
assert(((size_t)workSpace & 1) == 0); /* Must be 2 bytes-aligned */
|
|
if (FSE_BUILD_CTABLE_WORKSPACE_SIZE(maxSymbolValue, tableLog) > wkspSize) return ERROR(tableLog_tooLarge);
|
|
/* CTable header */
|
|
tableU16[-2] = (U16) tableLog;
|
|
tableU16[-1] = (U16) maxSymbolValue;
|
|
assert(tableLog < 16); /* required for threshold strategy to work */
|
|
|
|
/* For explanations on how to distribute symbol values over the table :
|
|
* https://fastcompression.blogspot.fr/2014/02/fse-distributing-symbol-values.html */
|
|
|
|
#ifdef __clang_analyzer__
|
|
ZSTD_memset(tableSymbol, 0, sizeof(*tableSymbol) * tableSize); /* useless initialization, just to keep scan-build happy */
|
|
#endif
|
|
|
|
/* symbol start positions */
|
|
{ U32 u;
|
|
cumul[0] = 0;
|
|
for (u=1; u <= maxSV1; u++) {
|
|
if (normalizedCounter[u-1]==-1) { /* Low proba symbol */
|
|
cumul[u] = cumul[u-1] + 1;
|
|
tableSymbol[highThreshold--] = (FSE_FUNCTION_TYPE)(u-1);
|
|
} else {
|
|
assert(normalizedCounter[u-1] >= 0);
|
|
cumul[u] = cumul[u-1] + (U16)normalizedCounter[u-1];
|
|
assert(cumul[u] >= cumul[u-1]); /* no overflow */
|
|
} }
|
|
cumul[maxSV1] = (U16)(tableSize+1);
|
|
}
|
|
|
|
/* Spread symbols */
|
|
if (highThreshold == tableSize - 1) {
|
|
/* Case for no low prob count symbols. Lay down 8 bytes at a time
|
|
* to reduce branch misses since we are operating on a small block
|
|
*/
|
|
BYTE* const spread = tableSymbol + tableSize; /* size = tableSize + 8 (may write beyond tableSize) */
|
|
{ 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);
|
|
}
|
|
assert(n>=0);
|
|
pos += (size_t)n;
|
|
}
|
|
}
|
|
/* Spread symbols across the table. Lack of lowprob symbols means that
|
|
* we don't need variable sized inner loop, so we can unroll the loop and
|
|
* reduce branch misses.
|
|
*/
|
|
{ size_t position = 0;
|
|
size_t s;
|
|
size_t const unroll = 2; /* Experimentally determined optimal unroll */
|
|
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;
|
|
tableSymbol[uPosition] = spread[s + u];
|
|
}
|
|
position = (position + (unroll * step)) & tableMask;
|
|
}
|
|
assert(position == 0); /* Must have initialized all positions */
|
|
}
|
|
} else {
|
|
U32 position = 0;
|
|
U32 symbol;
|
|
for (symbol=0; symbol<maxSV1; symbol++) {
|
|
int nbOccurrences;
|
|
int const freq = normalizedCounter[symbol];
|
|
for (nbOccurrences=0; nbOccurrences<freq; nbOccurrences++) {
|
|
tableSymbol[position] = (FSE_FUNCTION_TYPE)symbol;
|
|
position = (position + step) & tableMask;
|
|
while (position > highThreshold)
|
|
position = (position + step) & tableMask; /* Low proba area */
|
|
} }
|
|
assert(position==0); /* Must have initialized all positions */
|
|
}
|
|
|
|
/* Build table */
|
|
{ U32 u; for (u=0; u<tableSize; u++) {
|
|
FSE_FUNCTION_TYPE s = tableSymbol[u]; /* note : static analyzer may not understand tableSymbol is properly initialized */
|
|
tableU16[cumul[s]++] = (U16) (tableSize+u); /* TableU16 : sorted by symbol order; gives next state value */
|
|
} }
|
|
|
|
/* Build Symbol Transformation Table */
|
|
{ unsigned total = 0;
|
|
unsigned s;
|
|
for (s=0; s<=maxSymbolValue; s++) {
|
|
switch (normalizedCounter[s])
|
|
{
|
|
case 0:
|
|
/* filling nonetheless, for compatibility with FSE_getMaxNbBits() */
|
|
symbolTT[s].deltaNbBits = ((tableLog+1) << 16) - (1<<tableLog);
|
|
break;
|
|
|
|
case -1:
|
|
case 1:
|
|
symbolTT[s].deltaNbBits = (tableLog << 16) - (1<<tableLog);
|
|
assert(total <= INT_MAX);
|
|
symbolTT[s].deltaFindState = (int)(total - 1);
|
|
total ++;
|
|
break;
|
|
default :
|
|
assert(normalizedCounter[s] > 1);
|
|
{ U32 const maxBitsOut = tableLog - ZSTD_highbit32 ((U32)normalizedCounter[s]-1);
|
|
U32 const minStatePlus = (U32)normalizedCounter[s] << maxBitsOut;
|
|
symbolTT[s].deltaNbBits = (maxBitsOut << 16) - minStatePlus;
|
|
symbolTT[s].deltaFindState = (int)(total - (unsigned)normalizedCounter[s]);
|
|
total += (unsigned)normalizedCounter[s];
|
|
} } } }
|
|
|
|
#if 0 /* debug : symbol costs */
|
|
DEBUGLOG(5, "\n --- table statistics : ");
|
|
{ U32 symbol;
|
|
for (symbol=0; symbol<=maxSymbolValue; symbol++) {
|
|
DEBUGLOG(5, "%3u: w=%3i, maxBits=%u, fracBits=%.2f",
|
|
symbol, normalizedCounter[symbol],
|
|
FSE_getMaxNbBits(symbolTT, symbol),
|
|
(double)FSE_bitCost(symbolTT, tableLog, symbol, 8) / 256);
|
|
} }
|
|
#endif
|
|
|
|
return 0;
|
|
}
|
|
|
|
|
|
|
|
#ifndef FSE_COMMONDEFS_ONLY
|
|
|
|
/*-**************************************************************
|
|
* FSE NCount encoding
|
|
****************************************************************/
|
|
size_t FSE_NCountWriteBound(unsigned maxSymbolValue, unsigned tableLog)
|
|
{
|
|
size_t const maxHeaderSize = (((maxSymbolValue+1) * tableLog
|
|
+ 4 /* bitCount initialized at 4 */
|
|
+ 2 /* first two symbols may use one additional bit each */) / 8)
|
|
+ 1 /* round up to whole nb bytes */
|
|
+ 2 /* additional two bytes for bitstream flush */;
|
|
return maxSymbolValue ? maxHeaderSize : FSE_NCOUNTBOUND; /* maxSymbolValue==0 ? use default */
|
|
}
|
|
|
|
static size_t
|
|
FSE_writeNCount_generic (void* header, size_t headerBufferSize,
|
|
const short* normalizedCounter, unsigned maxSymbolValue, unsigned tableLog,
|
|
unsigned writeIsSafe)
|
|
{
|
|
BYTE* const ostart = (BYTE*) header;
|
|
BYTE* out = ostart;
|
|
BYTE* const oend = ostart + headerBufferSize;
|
|
int nbBits;
|
|
const int tableSize = 1 << tableLog;
|
|
int remaining;
|
|
int threshold;
|
|
U32 bitStream = 0;
|
|
int bitCount = 0;
|
|
unsigned symbol = 0;
|
|
unsigned const alphabetSize = maxSymbolValue + 1;
|
|
int previousIs0 = 0;
|
|
|
|
/* Table Size */
|
|
bitStream += (tableLog-FSE_MIN_TABLELOG) << bitCount;
|
|
bitCount += 4;
|
|
|
|
/* Init */
|
|
remaining = tableSize+1; /* +1 for extra accuracy */
|
|
threshold = tableSize;
|
|
nbBits = tableLog+1;
|
|
|
|
while ((symbol < alphabetSize) && (remaining>1)) { /* stops at 1 */
|
|
if (previousIs0) {
|
|
unsigned start = symbol;
|
|
while ((symbol < alphabetSize) && !normalizedCounter[symbol]) symbol++;
|
|
if (symbol == alphabetSize) break; /* incorrect distribution */
|
|
while (symbol >= start+24) {
|
|
start+=24;
|
|
bitStream += 0xFFFFU << bitCount;
|
|
if ((!writeIsSafe) && (out > oend-2))
|
|
return ERROR(dstSize_tooSmall); /* Buffer overflow */
|
|
out[0] = (BYTE) bitStream;
|
|
out[1] = (BYTE)(bitStream>>8);
|
|
out+=2;
|
|
bitStream>>=16;
|
|
}
|
|
while (symbol >= start+3) {
|
|
start+=3;
|
|
bitStream += 3 << bitCount;
|
|
bitCount += 2;
|
|
}
|
|
bitStream += (symbol-start) << bitCount;
|
|
bitCount += 2;
|
|
if (bitCount>16) {
|
|
if ((!writeIsSafe) && (out > oend - 2))
|
|
return ERROR(dstSize_tooSmall); /* Buffer overflow */
|
|
out[0] = (BYTE)bitStream;
|
|
out[1] = (BYTE)(bitStream>>8);
|
|
out += 2;
|
|
bitStream >>= 16;
|
|
bitCount -= 16;
|
|
} }
|
|
{ int count = normalizedCounter[symbol++];
|
|
int const max = (2*threshold-1) - remaining;
|
|
remaining -= count < 0 ? -count : count;
|
|
count++; /* +1 for extra accuracy */
|
|
if (count>=threshold)
|
|
count += max; /* [0..max[ [max..threshold[ (...) [threshold+max 2*threshold[ */
|
|
bitStream += count << bitCount;
|
|
bitCount += nbBits;
|
|
bitCount -= (count<max);
|
|
previousIs0 = (count==1);
|
|
if (remaining<1) return ERROR(GENERIC);
|
|
while (remaining<threshold) { nbBits--; threshold>>=1; }
|
|
}
|
|
if (bitCount>16) {
|
|
if ((!writeIsSafe) && (out > oend - 2))
|
|
return ERROR(dstSize_tooSmall); /* Buffer overflow */
|
|
out[0] = (BYTE)bitStream;
|
|
out[1] = (BYTE)(bitStream>>8);
|
|
out += 2;
|
|
bitStream >>= 16;
|
|
bitCount -= 16;
|
|
} }
|
|
|
|
if (remaining != 1)
|
|
return ERROR(GENERIC); /* incorrect normalized distribution */
|
|
assert(symbol <= alphabetSize);
|
|
|
|
/* flush remaining bitStream */
|
|
if ((!writeIsSafe) && (out > oend - 2))
|
|
return ERROR(dstSize_tooSmall); /* Buffer overflow */
|
|
out[0] = (BYTE)bitStream;
|
|
out[1] = (BYTE)(bitStream>>8);
|
|
out+= (bitCount+7) /8;
|
|
|
|
return (out-ostart);
|
|
}
|
|
|
|
|
|
size_t FSE_writeNCount (void* buffer, size_t bufferSize,
|
|
const short* normalizedCounter, unsigned maxSymbolValue, unsigned tableLog)
|
|
{
|
|
if (tableLog > FSE_MAX_TABLELOG) return ERROR(tableLog_tooLarge); /* Unsupported */
|
|
if (tableLog < FSE_MIN_TABLELOG) return ERROR(GENERIC); /* Unsupported */
|
|
|
|
if (bufferSize < FSE_NCountWriteBound(maxSymbolValue, tableLog))
|
|
return FSE_writeNCount_generic(buffer, bufferSize, normalizedCounter, maxSymbolValue, tableLog, 0);
|
|
|
|
return FSE_writeNCount_generic(buffer, bufferSize, normalizedCounter, maxSymbolValue, tableLog, 1 /* write in buffer is safe */);
|
|
}
|
|
|
|
|
|
/*-**************************************************************
|
|
* FSE Compression Code
|
|
****************************************************************/
|
|
|
|
/* provides the minimum logSize to safely represent a distribution */
|
|
static unsigned FSE_minTableLog(size_t srcSize, unsigned maxSymbolValue)
|
|
{
|
|
U32 minBitsSrc = ZSTD_highbit32((U32)(srcSize)) + 1;
|
|
U32 minBitsSymbols = ZSTD_highbit32(maxSymbolValue) + 2;
|
|
U32 minBits = minBitsSrc < minBitsSymbols ? minBitsSrc : minBitsSymbols;
|
|
assert(srcSize > 1); /* Not supported, RLE should be used instead */
|
|
return minBits;
|
|
}
|
|
|
|
unsigned FSE_optimalTableLog_internal(unsigned maxTableLog, size_t srcSize, unsigned maxSymbolValue, unsigned minus)
|
|
{
|
|
U32 maxBitsSrc = ZSTD_highbit32((U32)(srcSize - 1)) - minus;
|
|
U32 tableLog = maxTableLog;
|
|
U32 minBits = FSE_minTableLog(srcSize, maxSymbolValue);
|
|
assert(srcSize > 1); /* Not supported, RLE should be used instead */
|
|
if (tableLog==0) tableLog = FSE_DEFAULT_TABLELOG;
|
|
if (maxBitsSrc < tableLog) tableLog = maxBitsSrc; /* Accuracy can be reduced */
|
|
if (minBits > tableLog) tableLog = minBits; /* Need a minimum to safely represent all symbol values */
|
|
if (tableLog < FSE_MIN_TABLELOG) tableLog = FSE_MIN_TABLELOG;
|
|
if (tableLog > FSE_MAX_TABLELOG) tableLog = FSE_MAX_TABLELOG;
|
|
return tableLog;
|
|
}
|
|
|
|
unsigned FSE_optimalTableLog(unsigned maxTableLog, size_t srcSize, unsigned maxSymbolValue)
|
|
{
|
|
return FSE_optimalTableLog_internal(maxTableLog, srcSize, maxSymbolValue, 2);
|
|
}
|
|
|
|
/* Secondary normalization method.
|
|
To be used when primary method fails. */
|
|
|
|
static size_t FSE_normalizeM2(short* norm, U32 tableLog, const unsigned* count, size_t total, U32 maxSymbolValue, short lowProbCount)
|
|
{
|
|
short const NOT_YET_ASSIGNED = -2;
|
|
U32 s;
|
|
U32 distributed = 0;
|
|
U32 ToDistribute;
|
|
|
|
/* Init */
|
|
U32 const lowThreshold = (U32)(total >> tableLog);
|
|
U32 lowOne = (U32)((total * 3) >> (tableLog + 1));
|
|
|
|
for (s=0; s<=maxSymbolValue; s++) {
|
|
if (count[s] == 0) {
|
|
norm[s]=0;
|
|
continue;
|
|
}
|
|
if (count[s] <= lowThreshold) {
|
|
norm[s] = lowProbCount;
|
|
distributed++;
|
|
total -= count[s];
|
|
continue;
|
|
}
|
|
if (count[s] <= lowOne) {
|
|
norm[s] = 1;
|
|
distributed++;
|
|
total -= count[s];
|
|
continue;
|
|
}
|
|
|
|
norm[s]=NOT_YET_ASSIGNED;
|
|
}
|
|
ToDistribute = (1 << tableLog) - distributed;
|
|
|
|
if (ToDistribute == 0)
|
|
return 0;
|
|
|
|
if ((total / ToDistribute) > lowOne) {
|
|
/* risk of rounding to zero */
|
|
lowOne = (U32)((total * 3) / (ToDistribute * 2));
|
|
for (s=0; s<=maxSymbolValue; s++) {
|
|
if ((norm[s] == NOT_YET_ASSIGNED) && (count[s] <= lowOne)) {
|
|
norm[s] = 1;
|
|
distributed++;
|
|
total -= count[s];
|
|
continue;
|
|
} }
|
|
ToDistribute = (1 << tableLog) - distributed;
|
|
}
|
|
|
|
if (distributed == maxSymbolValue+1) {
|
|
/* all values are pretty poor;
|
|
probably incompressible data (should have already been detected);
|
|
find max, then give all remaining points to max */
|
|
U32 maxV = 0, maxC = 0;
|
|
for (s=0; s<=maxSymbolValue; s++)
|
|
if (count[s] > maxC) { maxV=s; maxC=count[s]; }
|
|
norm[maxV] += (short)ToDistribute;
|
|
return 0;
|
|
}
|
|
|
|
if (total == 0) {
|
|
/* all of the symbols were low enough for the lowOne or lowThreshold */
|
|
for (s=0; ToDistribute > 0; s = (s+1)%(maxSymbolValue+1))
|
|
if (norm[s] > 0) { ToDistribute--; norm[s]++; }
|
|
return 0;
|
|
}
|
|
|
|
{ U64 const vStepLog = 62 - tableLog;
|
|
U64 const mid = (1ULL << (vStepLog-1)) - 1;
|
|
U64 const rStep = ZSTD_div64((((U64)1<<vStepLog) * ToDistribute) + mid, (U32)total); /* scale on remaining */
|
|
U64 tmpTotal = mid;
|
|
for (s=0; s<=maxSymbolValue; s++) {
|
|
if (norm[s]==NOT_YET_ASSIGNED) {
|
|
U64 const end = tmpTotal + (count[s] * rStep);
|
|
U32 const sStart = (U32)(tmpTotal >> vStepLog);
|
|
U32 const sEnd = (U32)(end >> vStepLog);
|
|
U32 const weight = sEnd - sStart;
|
|
if (weight < 1)
|
|
return ERROR(GENERIC);
|
|
norm[s] = (short)weight;
|
|
tmpTotal = end;
|
|
} } }
|
|
|
|
return 0;
|
|
}
|
|
|
|
size_t FSE_normalizeCount (short* normalizedCounter, unsigned tableLog,
|
|
const unsigned* count, size_t total,
|
|
unsigned maxSymbolValue, unsigned useLowProbCount)
|
|
{
|
|
/* Sanity checks */
|
|
if (tableLog==0) tableLog = FSE_DEFAULT_TABLELOG;
|
|
if (tableLog < FSE_MIN_TABLELOG) return ERROR(GENERIC); /* Unsupported size */
|
|
if (tableLog > FSE_MAX_TABLELOG) return ERROR(tableLog_tooLarge); /* Unsupported size */
|
|
if (tableLog < FSE_minTableLog(total, maxSymbolValue)) return ERROR(GENERIC); /* Too small tableLog, compression potentially impossible */
|
|
|
|
{ static U32 const rtbTable[] = { 0, 473195, 504333, 520860, 550000, 700000, 750000, 830000 };
|
|
short const lowProbCount = useLowProbCount ? -1 : 1;
|
|
U64 const scale = 62 - tableLog;
|
|
U64 const step = ZSTD_div64((U64)1<<62, (U32)total); /* <== here, one division ! */
|
|
U64 const vStep = 1ULL<<(scale-20);
|
|
int stillToDistribute = 1<<tableLog;
|
|
unsigned s;
|
|
unsigned largest=0;
|
|
short largestP=0;
|
|
U32 lowThreshold = (U32)(total >> tableLog);
|
|
|
|
for (s=0; s<=maxSymbolValue; s++) {
|
|
if (count[s] == total) return 0; /* rle special case */
|
|
if (count[s] == 0) { normalizedCounter[s]=0; continue; }
|
|
if (count[s] <= lowThreshold) {
|
|
normalizedCounter[s] = lowProbCount;
|
|
stillToDistribute--;
|
|
} else {
|
|
short proba = (short)((count[s]*step) >> scale);
|
|
if (proba<8) {
|
|
U64 restToBeat = vStep * rtbTable[proba];
|
|
proba += (count[s]*step) - ((U64)proba<<scale) > restToBeat;
|
|
}
|
|
if (proba > largestP) { largestP=proba; largest=s; }
|
|
normalizedCounter[s] = proba;
|
|
stillToDistribute -= proba;
|
|
} }
|
|
if (-stillToDistribute >= (normalizedCounter[largest] >> 1)) {
|
|
/* corner case, need another normalization method */
|
|
size_t const errorCode = FSE_normalizeM2(normalizedCounter, tableLog, count, total, maxSymbolValue, lowProbCount);
|
|
if (FSE_isError(errorCode)) return errorCode;
|
|
}
|
|
else normalizedCounter[largest] += (short)stillToDistribute;
|
|
}
|
|
|
|
#if 0
|
|
{ /* Print Table (debug) */
|
|
U32 s;
|
|
U32 nTotal = 0;
|
|
for (s=0; s<=maxSymbolValue; s++)
|
|
RAWLOG(2, "%3i: %4i \n", s, normalizedCounter[s]);
|
|
for (s=0; s<=maxSymbolValue; s++)
|
|
nTotal += abs(normalizedCounter[s]);
|
|
if (nTotal != (1U<<tableLog))
|
|
RAWLOG(2, "Warning !!! Total == %u != %u !!!", nTotal, 1U<<tableLog);
|
|
getchar();
|
|
}
|
|
#endif
|
|
|
|
return tableLog;
|
|
}
|
|
|
|
/* fake FSE_CTable, for rle input (always same symbol) */
|
|
size_t FSE_buildCTable_rle (FSE_CTable* ct, BYTE symbolValue)
|
|
{
|
|
void* ptr = ct;
|
|
U16* tableU16 = ( (U16*) ptr) + 2;
|
|
void* FSCTptr = (U32*)ptr + 2;
|
|
FSE_symbolCompressionTransform* symbolTT = (FSE_symbolCompressionTransform*) FSCTptr;
|
|
|
|
/* header */
|
|
tableU16[-2] = (U16) 0;
|
|
tableU16[-1] = (U16) symbolValue;
|
|
|
|
/* Build table */
|
|
tableU16[0] = 0;
|
|
tableU16[1] = 0; /* just in case */
|
|
|
|
/* Build Symbol Transformation Table */
|
|
symbolTT[symbolValue].deltaNbBits = 0;
|
|
symbolTT[symbolValue].deltaFindState = 0;
|
|
|
|
return 0;
|
|
}
|
|
|
|
|
|
static size_t FSE_compress_usingCTable_generic (void* dst, size_t dstSize,
|
|
const void* src, size_t srcSize,
|
|
const FSE_CTable* ct, const unsigned fast)
|
|
{
|
|
const BYTE* const istart = (const BYTE*) src;
|
|
const BYTE* const iend = istart + srcSize;
|
|
const BYTE* ip=iend;
|
|
|
|
BIT_CStream_t bitC;
|
|
FSE_CState_t CState1, CState2;
|
|
|
|
/* init */
|
|
if (srcSize <= 2) return 0;
|
|
{ size_t const initError = BIT_initCStream(&bitC, dst, dstSize);
|
|
if (FSE_isError(initError)) return 0; /* not enough space available to write a bitstream */ }
|
|
|
|
#define FSE_FLUSHBITS(s) (fast ? BIT_flushBitsFast(s) : BIT_flushBits(s))
|
|
|
|
if (srcSize & 1) {
|
|
FSE_initCState2(&CState1, ct, *--ip);
|
|
FSE_initCState2(&CState2, ct, *--ip);
|
|
FSE_encodeSymbol(&bitC, &CState1, *--ip);
|
|
FSE_FLUSHBITS(&bitC);
|
|
} else {
|
|
FSE_initCState2(&CState2, ct, *--ip);
|
|
FSE_initCState2(&CState1, ct, *--ip);
|
|
}
|
|
|
|
/* join to mod 4 */
|
|
srcSize -= 2;
|
|
if ((sizeof(bitC.bitContainer)*8 > FSE_MAX_TABLELOG*4+7 ) && (srcSize & 2)) { /* test bit 2 */
|
|
FSE_encodeSymbol(&bitC, &CState2, *--ip);
|
|
FSE_encodeSymbol(&bitC, &CState1, *--ip);
|
|
FSE_FLUSHBITS(&bitC);
|
|
}
|
|
|
|
/* 2 or 4 encoding per loop */
|
|
while ( ip>istart ) {
|
|
|
|
FSE_encodeSymbol(&bitC, &CState2, *--ip);
|
|
|
|
if (sizeof(bitC.bitContainer)*8 < FSE_MAX_TABLELOG*2+7 ) /* this test must be static */
|
|
FSE_FLUSHBITS(&bitC);
|
|
|
|
FSE_encodeSymbol(&bitC, &CState1, *--ip);
|
|
|
|
if (sizeof(bitC.bitContainer)*8 > FSE_MAX_TABLELOG*4+7 ) { /* this test must be static */
|
|
FSE_encodeSymbol(&bitC, &CState2, *--ip);
|
|
FSE_encodeSymbol(&bitC, &CState1, *--ip);
|
|
}
|
|
|
|
FSE_FLUSHBITS(&bitC);
|
|
}
|
|
|
|
FSE_flushCState(&bitC, &CState2);
|
|
FSE_flushCState(&bitC, &CState1);
|
|
return BIT_closeCStream(&bitC);
|
|
}
|
|
|
|
size_t FSE_compress_usingCTable (void* dst, size_t dstSize,
|
|
const void* src, size_t srcSize,
|
|
const FSE_CTable* ct)
|
|
{
|
|
unsigned const fast = (dstSize >= FSE_BLOCKBOUND(srcSize));
|
|
|
|
if (fast)
|
|
return FSE_compress_usingCTable_generic(dst, dstSize, src, srcSize, ct, 1);
|
|
else
|
|
return FSE_compress_usingCTable_generic(dst, dstSize, src, srcSize, ct, 0);
|
|
}
|
|
|
|
|
|
size_t FSE_compressBound(size_t size) { return FSE_COMPRESSBOUND(size); }
|
|
|
|
#endif /* FSE_COMMONDEFS_ONLY */
|