introduced ext_wksp variants of count to reduce stack memory usage

lib/common/fse.h

@@ -294,8 +294,31 @@ If there is an error, the function will return an error code, which can be teste
 /* *****************************************
 *  FSE advanced API
 *******************************************/
+/* FSE_count_wksp() :
+ * Same as FSE_count(), but using an externally provided scratch buffer.
+ * `workSpace` size must be table of >= `1024` unsigned
+ */
+size_t FSE_count_wksp(unsigned* count, unsigned* maxSymbolValuePtr,
+                 const void* source, size_t sourceSize, unsigned* workSpace);
+
+/** FSE_countFast() :
+ *  same as FSE_count(), but blindly trusts that all byte values within src are <= *maxSymbolValuePtr
+ */
 size_t FSE_countFast(unsigned* count, unsigned* maxSymbolValuePtr, const void* src, size_t srcSize);
-/**< same as FSE_count(), but blindly trusts that all byte values within src are <= *maxSymbolValuePtr  */
+
+/* FSE_countFast_wksp() :
+ * Same as FSE_countFast(), but using an externally provided scratch buffer.
+ * `workSpace` must be a table of minimum `1024` unsigned
+ */
+size_t FSE_countFast_wksp(unsigned* count, unsigned* maxSymbolValuePtr, const void* src, size_t srcSize, unsigned* workSpace);
+
+/*! FSE_count_simple
+ * Same as FSE_countFast(), but does not use any additional memory (not even on stack).
+ * This function is unsafe, and will segfault if any value within `src` is `> *maxSymbolValuePtr` (presuming it's also the size of `count`).
+*/
+size_t FSE_count_simple(unsigned* count, unsigned* maxSymbolValuePtr, const void* src, size_t srcSize);
+
+
 
 unsigned FSE_optimalTableLog_internal(unsigned maxTableLog, size_t srcSize, unsigned maxSymbolValue, unsigned minus);
 /**< same as FSE_optimalTableLog(), which used `minus==2` */
@@ -334,13 +357,9 @@ size_t FSE_decompress_wksp(void* dst, size_t dstCapacity, const void* cSrc, size
 *******************************************/
 /*!
    This API consists of small unitary functions, which highly benefit from being inlined.
-   You will want to enable link-time-optimization to ensure these functions are properly inlined in your binary.
+   Hence their body are included in next section.
-   Visual seems to do it automatically.
-   For gcc or clang, you'll need to add -flto flag at compilation and linking stages.
-   If none of these solutions is applicable, include "fse.c" directly.
 */
-typedef struct
+typedef struct {
-{
     ptrdiff_t   value;
     const void* stateTable;
     const void* symbolTT;
@@ -400,8 +419,7 @@ If there is an error, it returns an errorCode (which can be tested using FSE_isE
 /* *****************************************
 *  FSE symbol decompression API
 *******************************************/
-typedef struct
+typedef struct {
-{
     size_t      state;
     const void* table;   /* precise table may vary, depending on U16 */
 } FSE_DState_t;

lib/common/huf.h

@@ -90,6 +90,11 @@ const char* HUF_getErrorName(size_t code);   /**< provides error code string (us
 *   Same as HUF_compress(), but offers direct control over `maxSymbolValue` and `tableLog` */
 size_t HUF_compress2 (void* dst, size_t dstSize, const void* src, size_t srcSize, unsigned maxSymbolValue, unsigned tableLog);
 
+/** HUF_compress4X_wksp() :
+*   Same as HUF_compress2(), but uses externally allocated `workSpace`, which must be a table of <= 1024 unsigned */
+size_t HUF_compress4X_wksp (void* dst, size_t dstSize, const void* src, size_t srcSize, unsigned maxSymbolValue, unsigned tableLog, unsigned* workSpace);
+
+
 
 #ifdef HUF_STATIC_LINKING_ONLY
 
@@ -208,12 +213,13 @@ size_t HUF_decompress4X4_usingDTable(void* dst, size_t maxDstSize, const void* c
 /* single stream variants */
 
 size_t HUF_compress1X (void* dst, size_t dstSize, const void* src, size_t srcSize, unsigned maxSymbolValue, unsigned tableLog);
+size_t HUF_compress1X_wksp (void* dst, size_t dstSize, const void* src, size_t srcSize, unsigned maxSymbolValue, unsigned tableLog, unsigned* workSpace);  /**< `workSpace` must be a table of at least 1024 unsigned */
 size_t HUF_compress1X_usingCTable(void* dst, size_t dstSize, const void* src, size_t srcSize, const HUF_CElt* CTable);
 
 size_t HUF_decompress1X2 (void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize);   /* single-symbol decoder */
 size_t HUF_decompress1X4 (void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize);   /* double-symbol decoder */
 
-size_t HUF_decompress1X_usingDTable(void* dst, size_t maxDstSize, const void* cSrc, size_t cSrcSize, const HUF_DTable* DTable);
+size_t HUF_decompress1X_usingDTable(void* dst, size_t maxDstSize, const void* cSrc, size_t cSrcSize, const HUF_DTable* DTable);   /**< automatic selection of sing or double symbol decoder, based on DTable */
 size_t HUF_decompress1X2_usingDTable(void* dst, size_t maxDstSize, const void* cSrc, size_t cSrcSize, const HUF_DTable* DTable);
 size_t HUF_decompress1X4_usingDTable(void* dst, size_t maxDstSize, const void* cSrc, size_t cSrcSize, const HUF_DTable* DTable);
 

lib/compress/fse_compress.c

@@ -308,14 +308,14 @@ size_t FSE_writeNCount (void* buffer, size_t bufferSize, const short* normalized
 *  Counting histogram
 ****************************************************************/
 /*! FSE_count_simple
-    This function just counts byte values within `src`,
+    This function counts byte values within `src`, and store the histogram into table `count`.
-    and store the histogram into table `count`.
+    It doesn't use any additional memory.
-    This function is unsafe : it doesn't check that all values within `src` can fit into `count`.
+    But this function is unsafe : it doesn't check that all values within `src` can fit into `count`.
     For this reason, prefer using a table `count` with 256 elements.
     @return : count of most numerous element
 */
-static size_t FSE_count_simple(unsigned* count, unsigned* maxSymbolValuePtr,
+size_t FSE_count_simple(unsigned* count, unsigned* maxSymbolValuePtr,
-                               const void* src, size_t srcSize)
+                        const void* src, size_t srcSize)
 {
     const BYTE* ip = (const BYTE*)src;
     const BYTE* const end = ip + srcSize;
@@ -409,31 +409,41 @@ static size_t FSE_count_parallel_wksp(
     return (size_t)max;
 }
 
-
+/* FSE_countFast_wksp() :
-static size_t FSE_count_parallel(unsigned* count, unsigned* maxSymbolValuePtr,
+ * Same as FSE_countFast(), but using an externally provided scratch buffer.
-                                const void* source, size_t sourceSize,
+ * `workSpace` size must be table of >= `1024` unsigned */
-                                unsigned checkMax)
+size_t FSE_countFast_wksp(unsigned* count, unsigned* maxSymbolValuePtr,
+                     const void* source, size_t sourceSize, unsigned* workSpace)
 {
-    U32 tmpCounters[1024];
+    if (sourceSize < 1500) return FSE_count_simple(count, maxSymbolValuePtr, source, sourceSize);
-    return FSE_count_parallel_wksp(count, maxSymbolValuePtr, source, sourceSize, checkMax, tmpCounters);
+    return FSE_count_parallel_wksp(count, maxSymbolValuePtr, source, sourceSize, 0, workSpace);
 }
 
-
 /* fast variant (unsafe : won't check if src contains values beyond count[] limit) */
 size_t FSE_countFast(unsigned* count, unsigned* maxSymbolValuePtr,
                      const void* source, size_t sourceSize)
 {
-    if (sourceSize < 1500) return FSE_count_simple(count, maxSymbolValuePtr, source, sourceSize);
+    unsigned tmpCounters[1024];
-    return FSE_count_parallel(count, maxSymbolValuePtr, source, sourceSize, 0);
+    return FSE_countFast_wksp(count, maxSymbolValuePtr, source, sourceSize, tmpCounters);
+}
+
+/* FSE_count_wksp() :
+ * Same as FSE_count(), but using an externally provided scratch buffer.
+ * `workSpace` size must be table of >= `1024` unsigned */
+size_t FSE_count_wksp(unsigned* count, unsigned* maxSymbolValuePtr,
+                 const void* source, size_t sourceSize, unsigned* workSpace)
+{
+    if (*maxSymbolValuePtr < 255)
+        return FSE_count_parallel_wksp(count, maxSymbolValuePtr, source, sourceSize, 1, workSpace);
+    *maxSymbolValuePtr = 255;
+    return FSE_countFast_wksp(count, maxSymbolValuePtr, source, sourceSize, workSpace);
 }
 
 size_t FSE_count(unsigned* count, unsigned* maxSymbolValuePtr,
-                 const void* source, size_t sourceSize)
+                 const void* src, size_t srcSize)
 {
-    if (*maxSymbolValuePtr < 255)
+    unsigned tmpCounters[1024];
-        return FSE_count_parallel(count, maxSymbolValuePtr, source, sourceSize, 1);
+    return FSE_count_wksp(count, maxSymbolValuePtr, src, srcSize, tmpCounters);
-    *maxSymbolValuePtr = 255;
-    return FSE_countFast(count, maxSymbolValuePtr, source, sourceSize);
 }
 
 
@@ -764,7 +774,7 @@ size_t FSE_compress_usingCTable (void* dst, size_t dstSize,
 
 size_t FSE_compressBound(size_t size) { return FSE_COMPRESSBOUND(size); }
 
-#define CHECK_E_F(e, f) size_t const e = f; if (FSE_isError(e)) return f
+#define CHECK_E_F(e, f) size_t const e = f; if (ERR_isError(e)) return f
 #define CHECK_F(f)   { CHECK_E_F(_var_err__, f); }
 
 /* FSE_compress_wksp() :
@@ -773,9 +783,6 @@ size_t FSE_compressBound(size_t size) { return FSE_COMPRESSBOUND(size); }
  */
 size_t FSE_compress_wksp (void* dst, size_t dstSize, const void* src, size_t srcSize, unsigned maxSymbolValue, unsigned tableLog, void* workSpace, size_t wkspSize)
 {
-    const BYTE* const istart = (const BYTE*) src;
-    const BYTE* ip = istart;
-
     BYTE* const ostart = (BYTE*) dst;
     BYTE* op = ostart;
     BYTE* const oend = ostart + dstSize;
@@ -794,14 +801,14 @@ size_t FSE_compress_wksp (void* dst, size_t dstSize, const void* src, size_t src
     if (!tableLog) tableLog = FSE_DEFAULT_TABLELOG;
 
     /* Scan input and build symbol stats */
-    {   CHECK_E_F(maxCount, FSE_count(count, &maxSymbolValue, ip, srcSize) );
+    {   CHECK_E_F(maxCount, FSE_count(count, &maxSymbolValue, src, srcSize) );
         if (maxCount == srcSize) return 1;   /* only a single symbol in src : rle */
         if (maxCount == 1) return 0;         /* each symbol present maximum once => not compressible */
         if (maxCount < (srcSize >> 7)) return 0;   /* Heuristic : not compressible enough */
     }
 
     tableLog = FSE_optimalTableLog(tableLog, srcSize, maxSymbolValue);
-    CHECK_F( FSE_normalizeCount (norm, tableLog, count, srcSize, maxSymbolValue) );
+    CHECK_F( FSE_normalizeCount(norm, tableLog, count, srcSize, maxSymbolValue) );
 
     /* Write table description header */
     {   CHECK_E_F(nc_err, FSE_writeNCount(op, oend-op, norm, maxSymbolValue, tableLog) );
@@ -810,7 +817,7 @@ size_t FSE_compress_wksp (void* dst, size_t dstSize, const void* src, size_t src
 
     /* Compress */
     CHECK_F( FSE_buildCTable_wksp(CTable, norm, maxSymbolValue, tableLog, scratchBuffer, scratchBufferSize) );
-    {   CHECK_E_F(cSize, FSE_compress_usingCTable(op, oend - op, ip, srcSize, CTable) );
+    {   CHECK_E_F(cSize, FSE_compress_usingCTable(op, oend - op, src, srcSize, CTable) );
         if (cSize == 0) return 0;   /* not enough space for compressed data */
         op += cSize;
     }

lib/compress/huf_compress.c

@@ -56,6 +56,8 @@
 *  Error Management
 ****************************************************************/
 #define HUF_STATIC_ASSERT(c) { enum { HUF_static_assert = 1/(int)(!!(c)) }; }   /* use only *after* variable declarations */
+#define CHECK_E_F(e, f) size_t const e = f; if (ERR_isError(e)) return f
+#define CHECK_F(f)   { CHECK_E_F(_var_err__, f); }
 
 
 /* **************************************************************
@@ -70,18 +72,60 @@ unsigned HUF_optimalTableLog(unsigned maxTableLog, size_t srcSize, unsigned maxS
 /* *******************************************************
 *  HUF : Huffman block compression
 *********************************************************/
+/* HUF_compressWeights() :
+ * Same as FSE_compress(), but dedicated to huff0's weights compression.
+ * The use case needs much less stack memory.
+ * Note : all elements within weightTable are supposed to be <= HUF_TABLELOG_MAX.
+ */
+#define MAX_FSE_TABLELOG_FOR_HUFF_HEADER 6
+size_t HUF_compressWeights (void* dst, size_t dstSize, const void* weightTable, size_t wtSize)
+{
+    BYTE* const ostart = (BYTE*) dst;
+    BYTE* op = ostart;
+    BYTE* const oend = ostart + dstSize;
+
+    U32 maxSymbolValue = HUF_TABLELOG_MAX;
+    U32 tableLog = MAX_FSE_TABLELOG_FOR_HUFF_HEADER;
+
+    FSE_CTable CTable[FSE_CTABLE_SIZE_U32(MAX_FSE_TABLELOG_FOR_HUFF_HEADER, HUF_TABLELOG_MAX)];
+    BYTE scratchBuffer[1<<MAX_FSE_TABLELOG_FOR_HUFF_HEADER];
+
+    U32 count[HUF_TABLELOG_MAX+1];
+    S16 norm[HUF_TABLELOG_MAX+1];
+
+    /* init conditions */
+    if (wtSize <= 1) return 0;  /* Not compressible */
+
+    /* Scan input and build symbol stats */
+    {   CHECK_E_F(maxCount, FSE_count_simple(count, &maxSymbolValue, weightTable, wtSize) );
+        if (maxCount == wtSize) return 1;   /* only a single symbol in src : rle */
+        if (maxCount == 1) return 0;         /* each symbol present maximum once => not compressible */
+    }
+
+    tableLog = FSE_optimalTableLog(tableLog, wtSize, maxSymbolValue);
+    CHECK_F( FSE_normalizeCount(norm, tableLog, count, wtSize, maxSymbolValue) );
+
+    /* Write table description header */
+    {   CHECK_E_F(hSize, FSE_writeNCount(op, oend-op, norm, maxSymbolValue, tableLog) );
+        op += hSize;
+    }
+
+    /* Compress */
+    CHECK_F( FSE_buildCTable_wksp(CTable, norm, maxSymbolValue, tableLog, scratchBuffer, sizeof(scratchBuffer)) );
+    {   CHECK_E_F(cSize, FSE_compress_usingCTable(op, oend - op, weightTable, wtSize, CTable) );
+        if (cSize == 0) return 0;   /* not enough space for compressed data */
+        op += cSize;
+    }
+
+    return op-ostart;
+}
+
+
 struct HUF_CElt_s {
   U16  val;
   BYTE nbBits;
 };   /* typedef'd to HUF_CElt within "huf.h" */
 
-typedef struct nodeElt_s {
-    U32 count;
-    U16 parent;
-    BYTE byte;
-    BYTE nbBits;
-} nodeElt;
-
 /*! HUF_writeCTable() :
     `CTable` : huffman tree to save, using huf representation.
     @return : size of saved CTable */
@@ -91,8 +135,6 @@ size_t HUF_writeCTable (void* dst, size_t maxDstSize,
     BYTE bitsToWeight[HUF_TABLELOG_MAX + 1];   /* precomputed conversion table */
     BYTE huffWeight[HUF_SYMBOLVALUE_MAX];
     BYTE* op = (BYTE*)dst;
-#define MAX_FSE_TABLELOG_FOR_HUFF_HEADER 6
-    FSE_CTable scratchBuffer[FSE_WKSP_SIZE_U32(MAX_FSE_TABLELOG_FOR_HUFF_HEADER, HUF_TABLELOG_MAX)];
     U32 n;
 
      /* check conditions */
@@ -106,18 +148,17 @@ size_t HUF_writeCTable (void* dst, size_t maxDstSize,
         huffWeight[n] = bitsToWeight[CTable[n].nbBits];
 
     /* attempt weights compression by FSE */
-    {   size_t const size = FSE_compress_wksp(op+1, maxDstSize-1, huffWeight, maxSymbolValue, HUF_TABLELOG_MAX, MAX_FSE_TABLELOG_FOR_HUFF_HEADER, scratchBuffer, sizeof(scratchBuffer));
+    {   CHECK_E_F(hSize, HUF_compressWeights(op+1, maxDstSize-1, huffWeight, maxSymbolValue) );
-        if (FSE_isError(size)) return size;
+        if ((hSize>1) & (hSize < maxSymbolValue/2)) {   /* FSE compressed */
-        if ((size>1) & (size < maxSymbolValue/2)) {   /* FSE compressed */
+            op[0] = (BYTE)hSize;
-            op[0] = (BYTE)size;
+            return hSize+1;
-            return size+1;
     }   }
 
-    /* raw values */
+    /* write raw values as 4-bits (max : 15) */
     if (maxSymbolValue > (256-128)) return ERROR(GENERIC);   /* should not happen : likely means source cannot be compressed */
     if (((maxSymbolValue+1)/2) + 1 > maxDstSize) return ERROR(dstSize_tooSmall);   /* not enough space within dst buffer */
     op[0] = (BYTE)(128 /*special case*/ + (maxSymbolValue-1));
-    huffWeight[maxSymbolValue] = 0;   /* to be sure it doesn't cause issue in final combination */
+    huffWeight[maxSymbolValue] = 0;   /* to be sure it doesn't cause msan issue in final combination */
     for (n=0; n<maxSymbolValue; n+=2)
         op[(n/2)+1] = (BYTE)((huffWeight[n] << 4) + huffWeight[n+1]);
     return ((maxSymbolValue+1)/2) + 1;
@@ -126,16 +167,13 @@ size_t HUF_writeCTable (void* dst, size_t maxDstSize,
 
 size_t HUF_readCTable (HUF_CElt* CTable, U32 maxSymbolValue, const void* src, size_t srcSize)
 {
-    BYTE huffWeight[HUF_SYMBOLVALUE_MAX + 1];
+    BYTE huffWeight[HUF_SYMBOLVALUE_MAX + 1];   /* init not required, even though some static analyzer may complain */
     U32 rankVal[HUF_TABLELOG_ABSOLUTEMAX + 1];   /* large enough for values from 0 to 16 */
     U32 tableLog = 0;
-    size_t readSize;
     U32 nbSymbols = 0;
-    /*memset(huffWeight, 0, sizeof(huffWeight));*/   /* is not necessary, even though some analyzer complain ... */
 
     /* get symbol weights */
-    readSize = HUF_readStats(huffWeight, HUF_SYMBOLVALUE_MAX+1, rankVal, &nbSymbols, &tableLog, src, srcSize);
+    CHECK_E_F(readSize, HUF_readStats(huffWeight, HUF_SYMBOLVALUE_MAX+1, rankVal, &nbSymbols, &tableLog, src, srcSize));
-    if (HUF_isError(readSize)) return readSize;
 
     /* check result */
     if (tableLog > HUF_TABLELOG_MAX) return ERROR(tableLog_tooLarge);
@@ -175,6 +213,13 @@ size_t HUF_readCTable (HUF_CElt* CTable, U32 maxSymbolValue, const void* src, si
 }
 
 
+typedef struct nodeElt_s {
+    U32 count;
+    U16 parent;
+    BYTE byte;
+    BYTE nbBits;
+} nodeElt;
+
 static U32 HUF_setMaxHeight(nodeElt* huffNode, U32 lastNonNull, U32 maxNbBits)
 {
     const U32 largestBits = huffNode[lastNonNull].nbBits;
@@ -280,6 +325,9 @@ static void HUF_sort(nodeElt* huffNode, const U32* count, U32 maxSymbolValue)
 }
 
 
+/** HUF_buildCTable() :
+ *  Note : count is used before tree is written, so they can safely overlap
+ */
 #define STARTNODE (HUF_SYMBOLVALUE_MAX+1)
 size_t HUF_buildCTable (HUF_CElt* tree, const U32* count, U32 maxSymbolValue, U32 maxNbBits)
 {
@@ -420,32 +468,28 @@ size_t HUF_compress4X_usingCTable(void* dst, size_t dstSize, const void* src, si
     if (srcSize < 12) return 0;   /* no saving possible : too small input */
     op += 6;   /* jumpTable */
 
-    {   size_t const cSize = HUF_compress1X_usingCTable(op, oend-op, ip, segmentSize, CTable);
+    {   CHECK_E_F(cSize, HUF_compress1X_usingCTable(op, oend-op, ip, segmentSize, CTable) );
-        if (HUF_isError(cSize)) return cSize;
         if (cSize==0) return 0;
         MEM_writeLE16(ostart, (U16)cSize);
         op += cSize;
     }
 
     ip += segmentSize;
-    {   size_t const cSize = HUF_compress1X_usingCTable(op, oend-op, ip, segmentSize, CTable);
+    {   CHECK_E_F(cSize, HUF_compress1X_usingCTable(op, oend-op, ip, segmentSize, CTable) );
-        if (HUF_isError(cSize)) return cSize;
         if (cSize==0) return 0;
         MEM_writeLE16(ostart+2, (U16)cSize);
         op += cSize;
     }
 
     ip += segmentSize;
-    {   size_t const cSize = HUF_compress1X_usingCTable(op, oend-op, ip, segmentSize, CTable);
+    {   CHECK_E_F(cSize, HUF_compress1X_usingCTable(op, oend-op, ip, segmentSize, CTable) );
-        if (HUF_isError(cSize)) return cSize;
         if (cSize==0) return 0;
         MEM_writeLE16(ostart+4, (U16)cSize);
         op += cSize;
     }
 
     ip += segmentSize;
-    {   size_t const cSize = HUF_compress1X_usingCTable(op, oend-op, ip, iend-ip, CTable);
+    {   CHECK_E_F(cSize, HUF_compress1X_usingCTable(op, oend-op, ip, iend-ip, CTable) );
-        if (HUF_isError(cSize)) return cSize;
         if (cSize==0) return 0;
         op += cSize;
     }
@@ -454,18 +498,21 @@ size_t HUF_compress4X_usingCTable(void* dst, size_t dstSize, const void* src, si
 }
 
 
+/* `workSpace` must a table of at least 1024 unsigned */
 static size_t HUF_compress_internal (
                 void* dst, size_t dstSize,
                 const void* src, size_t srcSize,
                 unsigned maxSymbolValue, unsigned huffLog,
-                unsigned singleStream)
+                unsigned singleStream, unsigned* workSpace)
 {
     BYTE* const ostart = (BYTE*)dst;
     BYTE* const oend = ostart + dstSize;
     BYTE* op = ostart;
 
-    U32 count[HUF_SYMBOLVALUE_MAX+1];
+    union {
-    HUF_CElt CTable[HUF_SYMBOLVALUE_MAX+1];
+        U32 count[HUF_SYMBOLVALUE_MAX+1];
+        HUF_CElt CTable[HUF_SYMBOLVALUE_MAX+1];
+    } table;   /* `count` can overlap with `CTable`; saves 1 KB */
 
     /* checks & inits */
     if (!srcSize) return 0;  /* Uncompressed (note : 1 means rle, so first byte must be correct) */
@@ -476,30 +523,27 @@ static size_t HUF_compress_internal (
     if (!huffLog) huffLog = HUF_TABLELOG_DEFAULT;
 
     /* Scan input and build symbol stats */
-    {   size_t const largest = FSE_count (count, &maxSymbolValue, (const BYTE*)src, srcSize);
+    {   CHECK_E_F(largest, FSE_count_wksp (table.count, &maxSymbolValue, (const BYTE*)src, srcSize, workSpace) );
-        if (HUF_isError(largest)) return largest;
         if (largest == srcSize) { *ostart = ((const BYTE*)src)[0]; return 1; }   /* single symbol, rle */
         if (largest <= (srcSize >> 7)+1) return 0;   /* Fast heuristic : not compressible enough */
     }
 
     /* Build Huffman Tree */
     huffLog = HUF_optimalTableLog(huffLog, srcSize, maxSymbolValue);
-    {   size_t const maxBits = HUF_buildCTable (CTable, count, maxSymbolValue, huffLog);
+    {   CHECK_E_F(maxBits, HUF_buildCTable (table.CTable, table.count, maxSymbolValue, huffLog) );
-        if (HUF_isError(maxBits)) return maxBits;
         huffLog = (U32)maxBits;
     }
 
     /* Write table description header */
-    {   size_t const hSize = HUF_writeCTable (op, dstSize, CTable, maxSymbolValue, huffLog);
+    {   CHECK_E_F(hSize, HUF_writeCTable (op, dstSize, table.CTable, maxSymbolValue, huffLog) );
-        if (HUF_isError(hSize)) return hSize;
         if (hSize + 12 >= srcSize) return 0;   /* not useful to try compression */
         op += hSize;
     }
 
     /* Compress */
     {   size_t const cSize = (singleStream) ?
-                            HUF_compress1X_usingCTable(op, oend - op, src, srcSize, CTable) :   /* single segment */
+                            HUF_compress1X_usingCTable(op, oend - op, src, srcSize, table.CTable) :   /* single segment */
-                            HUF_compress4X_usingCTable(op, oend - op, src, srcSize, CTable);
+                            HUF_compress4X_usingCTable(op, oend - op, src, srcSize, table.CTable);
         if (HUF_isError(cSize)) return cSize;
         if (cSize==0) return 0;   /* uncompressible */
         op += cSize;
@@ -513,21 +557,36 @@ static size_t HUF_compress_internal (
 }
 
 
+size_t HUF_compress1X_wksp (void* dst, size_t dstSize,
+                      const void* src, size_t srcSize,
+                      unsigned maxSymbolValue, unsigned huffLog, unsigned* workSpace)
+{
+    return HUF_compress_internal(dst, dstSize, src, srcSize, maxSymbolValue, huffLog, 1 /* single stream */, workSpace);
+}
+
 size_t HUF_compress1X (void* dst, size_t dstSize,
                  const void* src, size_t srcSize,
                  unsigned maxSymbolValue, unsigned huffLog)
 {
-    return HUF_compress_internal(dst, dstSize, src, srcSize, maxSymbolValue, huffLog, 1);
+    unsigned workSpace[1024];
+    return HUF_compress1X_wksp(dst, dstSize, src, srcSize, maxSymbolValue, huffLog, workSpace);
+}
+
+size_t HUF_compress4X_wksp (void* dst, size_t dstSize,
+                      const void* src, size_t srcSize,
+                      unsigned maxSymbolValue, unsigned huffLog, unsigned* workSpace)
+{
+    return HUF_compress_internal(dst, dstSize, src, srcSize, maxSymbolValue, huffLog, 0 /* 4 streams */, workSpace);
 }
 
 size_t HUF_compress2 (void* dst, size_t dstSize,
                 const void* src, size_t srcSize,
                 unsigned maxSymbolValue, unsigned huffLog)
 {
-    return HUF_compress_internal(dst, dstSize, src, srcSize, maxSymbolValue, huffLog, 0);
+    unsigned workSpace[1024];
+    return HUF_compress4X_wksp(dst, dstSize, src, srcSize, maxSymbolValue, huffLog, workSpace);
 }
 
-
 size_t HUF_compress (void* dst, size_t maxDstSize, const void* src, size_t srcSize)
 {
     return HUF_compress2(dst, maxDstSize, src, (U32)srcSize, 255, HUF_TABLELOG_DEFAULT);

lib/compress/zstd_compress.c

@@ -82,6 +82,7 @@ struct ZSTD_CCtx_s
     FSE_CTable offcodeCTable  [FSE_CTABLE_SIZE_U32(OffFSELog, MaxOff)];
     FSE_CTable matchlengthCTable[FSE_CTABLE_SIZE_U32(MLFSELog, MaxML)];
     FSE_CTable litlengthCTable  [FSE_CTABLE_SIZE_U32(LLFSELog, MaxLL)];
+    unsigned tmpCounters[1024];
 };
 
 ZSTD_CCtx* ZSTD_createCCtx(void)
@@ -470,8 +471,8 @@ static size_t ZSTD_compressLiterals (ZSTD_CCtx* zc,
         singleStream = 1;
         cLitSize = HUF_compress1X_usingCTable(ostart+lhSize, dstCapacity-lhSize, src, srcSize, zc->hufTable);
     } else {
-        cLitSize = singleStream ? HUF_compress1X(ostart+lhSize, dstCapacity-lhSize, src, srcSize, 255, 11)
+        cLitSize = singleStream ? HUF_compress1X_wksp(ostart+lhSize, dstCapacity-lhSize, src, srcSize, 255, 11, zc->tmpCounters)
-                                : HUF_compress2 (ostart+lhSize, dstCapacity-lhSize, src, srcSize, 255, 11);
+                                : HUF_compress4X_wksp(ostart+lhSize, dstCapacity-lhSize, src, srcSize, 255, 11, zc->tmpCounters);
     }
 
     if ((cLitSize==0) | (cLitSize >= srcSize - minGain))
@@ -594,7 +595,7 @@ size_t ZSTD_compressSequences(ZSTD_CCtx* zc,
 
     /* CTable for Literal Lengths */
     {   U32 max = MaxLL;
-        size_t const mostFrequent = FSE_countFast(count, &max, llCodeTable, nbSeq);
+        size_t const mostFrequent = FSE_countFast_wksp(count, &max, llCodeTable, nbSeq, zc->tmpCounters);
         if ((mostFrequent == nbSeq) && (nbSeq > 2)) {
             *op++ = llCodeTable[0];
             FSE_buildCTable_rle(CTable_LitLength, (BYTE)max);
@@ -618,7 +619,7 @@ size_t ZSTD_compressSequences(ZSTD_CCtx* zc,
 
     /* CTable for Offsets */
     {   U32 max = MaxOff;
-        size_t const mostFrequent = FSE_countFast(count, &max, ofCodeTable, nbSeq);
+        size_t const mostFrequent = FSE_countFast_wksp(count, &max, ofCodeTable, nbSeq, zc->tmpCounters);
         if ((mostFrequent == nbSeq) && (nbSeq > 2)) {
             *op++ = ofCodeTable[0];
             FSE_buildCTable_rle(CTable_OffsetBits, (BYTE)max);
@@ -642,7 +643,7 @@ size_t ZSTD_compressSequences(ZSTD_CCtx* zc,
 
     /* CTable for MatchLengths */
     {   U32 max = MaxML;
-        size_t const mostFrequent = FSE_countFast(count, &max, mlCodeTable, nbSeq);
+        size_t const mostFrequent = FSE_countFast_wksp(count, &max, mlCodeTable, nbSeq, zc->tmpCounters);
         if ((mostFrequent == nbSeq) && (nbSeq > 2)) {
             *op++ = *mlCodeTable;
             FSE_buildCTable_rle(CTable_MatchLength, (BYTE)max);