extzstd 0.0.3.CONCEPT → 0.3.1

data/contrib/zstd/lib/compress/zstdmt_compress.h

@@ -0,0 +1,192 @@
+/*
+ * Copyright (c) 2016-2020, Yann Collet, Facebook, Inc.
+ * All rights reserved.
+ *
+ * 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.
+ */
+
+ #ifndef ZSTDMT_COMPRESS_H
+ #define ZSTDMT_COMPRESS_H
+
+ #if defined (__cplusplus)
+ extern "C" {
+ #endif
+
+
+/* Note : This is an internal API.
+ *        These APIs used to be exposed with ZSTDLIB_API,
+ *        because it used to be the only way to invoke MT compression.
+ *        Now, it's recommended to use ZSTD_compress2 and ZSTD_compressStream2()
+ *        instead.
+ *
+ *        If you depend on these APIs and can't switch, then define
+ *        ZSTD_LEGACY_MULTITHREADED_API when making the dynamic library.
+ *        However, we may completely remove these functions in a future
+ *        release, so please switch soon.
+ *
+ *        This API requires ZSTD_MULTITHREAD to be defined during compilation,
+ *        otherwise ZSTDMT_createCCtx*() will fail.
+ */
+
+#ifdef ZSTD_LEGACY_MULTITHREADED_API
+#  define ZSTDMT_API ZSTDLIB_API
+#else
+#  define ZSTDMT_API
+#endif
+
+/* ===   Dependencies   === */
+#include <stddef.h>                /* size_t */
+#define ZSTD_STATIC_LINKING_ONLY   /* ZSTD_parameters */
+#include "../zstd.h"            /* ZSTD_inBuffer, ZSTD_outBuffer, ZSTDLIB_API */
+
+
+/* ===   Constants   === */
+#ifndef ZSTDMT_NBWORKERS_MAX
+#  define ZSTDMT_NBWORKERS_MAX 200
+#endif
+#ifndef ZSTDMT_JOBSIZE_MIN
+#  define ZSTDMT_JOBSIZE_MIN (1 MB)
+#endif
+#define ZSTDMT_JOBLOG_MAX   (MEM_32bits() ? 29 : 30)
+#define ZSTDMT_JOBSIZE_MAX  (MEM_32bits() ? (512 MB) : (1024 MB))
+
+
+/* ===   Memory management   === */
+typedef struct ZSTDMT_CCtx_s ZSTDMT_CCtx;
+/* Requires ZSTD_MULTITHREAD to be defined during compilation, otherwise it will return NULL. */
+ZSTDMT_API ZSTDMT_CCtx* ZSTDMT_createCCtx(unsigned nbWorkers);
+/* Requires ZSTD_MULTITHREAD to be defined during compilation, otherwise it will return NULL. */
+ZSTDMT_API ZSTDMT_CCtx* ZSTDMT_createCCtx_advanced(unsigned nbWorkers,
+                                                    ZSTD_customMem cMem);
+ZSTDMT_API size_t ZSTDMT_freeCCtx(ZSTDMT_CCtx* mtctx);
+
+ZSTDMT_API size_t ZSTDMT_sizeof_CCtx(ZSTDMT_CCtx* mtctx);
+
+
+/* ===   Simple one-pass compression function   === */
+
+ZSTDMT_API size_t ZSTDMT_compressCCtx(ZSTDMT_CCtx* mtctx,
+                                       void* dst, size_t dstCapacity,
+                                 const void* src, size_t srcSize,
+                                       int compressionLevel);
+
+
+
+/* ===   Streaming functions   === */
+
+ZSTDMT_API size_t ZSTDMT_initCStream(ZSTDMT_CCtx* mtctx, int compressionLevel);
+ZSTDMT_API size_t ZSTDMT_resetCStream(ZSTDMT_CCtx* mtctx, unsigned long long pledgedSrcSize);  /**< if srcSize is not known at reset time, use ZSTD_CONTENTSIZE_UNKNOWN. Note: for compatibility with older programs, 0 means the same as ZSTD_CONTENTSIZE_UNKNOWN, but it will change in the future to mean "empty" */
+
+ZSTDMT_API size_t ZSTDMT_nextInputSizeHint(const ZSTDMT_CCtx* mtctx);
+ZSTDMT_API size_t ZSTDMT_compressStream(ZSTDMT_CCtx* mtctx, ZSTD_outBuffer* output, ZSTD_inBuffer* input);
+
+ZSTDMT_API size_t ZSTDMT_flushStream(ZSTDMT_CCtx* mtctx, ZSTD_outBuffer* output);   /**< @return : 0 == all flushed; >0 : still some data to be flushed; or an error code (ZSTD_isError()) */
+ZSTDMT_API size_t ZSTDMT_endStream(ZSTDMT_CCtx* mtctx, ZSTD_outBuffer* output);     /**< @return : 0 == all flushed; >0 : still some data to be flushed; or an error code (ZSTD_isError()) */
+
+
+/* ===   Advanced functions and parameters  === */
+
+ZSTDMT_API size_t ZSTDMT_compress_advanced(ZSTDMT_CCtx* mtctx,
+                                          void* dst, size_t dstCapacity,
+                                    const void* src, size_t srcSize,
+                                    const ZSTD_CDict* cdict,
+                                          ZSTD_parameters params,
+                                          int overlapLog);
+
+ZSTDMT_API size_t ZSTDMT_initCStream_advanced(ZSTDMT_CCtx* mtctx,
+                                        const void* dict, size_t dictSize,   /* dict can be released after init, a local copy is preserved within zcs */
+                                        ZSTD_parameters params,
+                                        unsigned long long pledgedSrcSize);  /* pledgedSrcSize is optional and can be zero == unknown */
+
+ZSTDMT_API size_t ZSTDMT_initCStream_usingCDict(ZSTDMT_CCtx* mtctx,
+                                        const ZSTD_CDict* cdict,
+                                        ZSTD_frameParameters fparams,
+                                        unsigned long long pledgedSrcSize);  /* note : zero means empty */
+
+/* ZSTDMT_parameter :
+ * List of parameters that can be set using ZSTDMT_setMTCtxParameter() */
+typedef enum {
+    ZSTDMT_p_jobSize,     /* Each job is compressed in parallel. By default, this value is dynamically determined depending on compression parameters. Can be set explicitly here. */
+    ZSTDMT_p_overlapLog,  /* Each job may reload a part of previous job to enhance compression ratio; 0 == no overlap, 6(default) == use 1/8th of window, >=9 == use full window. This is a "sticky" parameter : its value will be re-used on next compression job */
+    ZSTDMT_p_rsyncable    /* Enables rsyncable mode. */
+} ZSTDMT_parameter;
+
+/* ZSTDMT_setMTCtxParameter() :
+ * allow setting individual parameters, one at a time, among a list of enums defined in ZSTDMT_parameter.
+ * The function must be called typically after ZSTD_createCCtx() but __before ZSTDMT_init*() !__
+ * Parameters not explicitly reset by ZSTDMT_init*() remain the same in consecutive compression sessions.
+ * @return : 0, or an error code (which can be tested using ZSTD_isError()) */
+ZSTDMT_API size_t ZSTDMT_setMTCtxParameter(ZSTDMT_CCtx* mtctx, ZSTDMT_parameter parameter, int value);
+
+/* ZSTDMT_getMTCtxParameter() :
+ * Query the ZSTDMT_CCtx for a parameter value.
+ * @return : 0, or an error code (which can be tested using ZSTD_isError()) */
+ZSTDMT_API size_t ZSTDMT_getMTCtxParameter(ZSTDMT_CCtx* mtctx, ZSTDMT_parameter parameter, int* value);
+
+
+/*! ZSTDMT_compressStream_generic() :
+ *  Combines ZSTDMT_compressStream() with optional ZSTDMT_flushStream() or ZSTDMT_endStream()
+ *  depending on flush directive.
+ * @return : minimum amount of data still to be flushed
+ *           0 if fully flushed
+ *           or an error code
+ *  note : needs to be init using any ZSTD_initCStream*() variant */
+ZSTDMT_API size_t ZSTDMT_compressStream_generic(ZSTDMT_CCtx* mtctx,
+                                                ZSTD_outBuffer* output,
+                                                ZSTD_inBuffer* input,
+                                                ZSTD_EndDirective endOp);
+
+
+/* ========================================================
+ * ===  Private interface, for use by ZSTD_compress.c   ===
+ * ===  Not exposed in libzstd. Never invoke directly   ===
+ * ======================================================== */
+
+ /*! ZSTDMT_toFlushNow()
+  *  Tell how many bytes are ready to be flushed immediately.
+  *  Probe the oldest active job (not yet entirely flushed) and check its output buffer.
+  *  If return 0, it means there is no active job,
+  *  or, it means oldest job is still active, but everything produced has been flushed so far,
+  *  therefore flushing is limited by speed of oldest job. */
+size_t ZSTDMT_toFlushNow(ZSTDMT_CCtx* mtctx);
+
+/*! ZSTDMT_CCtxParam_setMTCtxParameter()
+ *  like ZSTDMT_setMTCtxParameter(), but into a ZSTD_CCtx_Params */
+size_t ZSTDMT_CCtxParam_setMTCtxParameter(ZSTD_CCtx_params* params, ZSTDMT_parameter parameter, int value);
+
+/*! ZSTDMT_CCtxParam_setNbWorkers()
+ *  Set nbWorkers, and clamp it.
+ *  Also reset jobSize and overlapLog */
+size_t ZSTDMT_CCtxParam_setNbWorkers(ZSTD_CCtx_params* params, unsigned nbWorkers);
+
+/*! ZSTDMT_updateCParams_whileCompressing() :
+ *  Updates only a selected set of compression parameters, to remain compatible with current frame.
+ *  New parameters will be applied to next compression job. */
+void ZSTDMT_updateCParams_whileCompressing(ZSTDMT_CCtx* mtctx, const ZSTD_CCtx_params* cctxParams);
+
+/*! ZSTDMT_getFrameProgression():
+ *  tells how much data has been consumed (input) and produced (output) for current frame.
+ *  able to count progression inside worker threads.
+ */
+ZSTD_frameProgression ZSTDMT_getFrameProgression(ZSTDMT_CCtx* mtctx);
+
+
+/*! ZSTDMT_initCStream_internal() :
+ *  Private use only. Init streaming operation.
+ *  expects params to be valid.
+ *  must receive dict, or cdict, or none, but not both.
+ *  @return : 0, or an error code */
+size_t ZSTDMT_initCStream_internal(ZSTDMT_CCtx* zcs,
+                    const void* dict, size_t dictSize, ZSTD_dictContentType_e dictContentType,
+                    const ZSTD_CDict* cdict,
+                    ZSTD_CCtx_params params, unsigned long long pledgedSrcSize);
+
+
+#if defined (__cplusplus)
+}
+#endif
+
+#endif   /* ZSTDMT_COMPRESS_H */

data/contrib/zstd/lib/decompress/huf_decompress.c

@@ -0,0 +1,1248 @@
+/* ******************************************************************
+ * huff0 huffman decoder,
+ * part of Finite State Entropy library
+ * Copyright (c) 2013-2020, Yann Collet, Facebook, Inc.
+ *
+ *  You can contact the author at :
+ *  - FSE+HUF source repository : https://github.com/Cyan4973/FiniteStateEntropy
+ *
+ * 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.
+****************************************************************** */
+
+/* **************************************************************
+*  Dependencies
+****************************************************************/
+#include <string.h>     /* memcpy, memset */
+#include "../common/compiler.h"
+#include "../common/bitstream.h"  /* BIT_* */
+#include "../common/fse.h"        /* to compress headers */
+#define HUF_STATIC_LINKING_ONLY
+#include "../common/huf.h"
+#include "../common/error_private.h"
+
+/* **************************************************************
+*  Macros
+****************************************************************/
+
+/* These two optional macros force the use one way or another of the two
+ * Huffman decompression implementations. You can't force in both directions
+ * at the same time.
+ */
+#if defined(HUF_FORCE_DECOMPRESS_X1) && \
+    defined(HUF_FORCE_DECOMPRESS_X2)
+#error "Cannot force the use of the X1 and X2 decoders at the same time!"
+#endif
+
+
+/* **************************************************************
+*  Error Management
+****************************************************************/
+#define HUF_isError ERR_isError
+
+
+/* **************************************************************
+*  Byte alignment for workSpace management
+****************************************************************/
+#define HUF_ALIGN(x, a)         HUF_ALIGN_MASK((x), (a) - 1)
+#define HUF_ALIGN_MASK(x, mask) (((x) + (mask)) & ~(mask))
+
+
+/* **************************************************************
+*  BMI2 Variant Wrappers
+****************************************************************/
+#if DYNAMIC_BMI2
+
+#define HUF_DGEN(fn)                                                        \
+                                                                            \
+    static size_t fn##_default(                                             \
+                  void* dst,  size_t dstSize,                               \
+            const void* cSrc, size_t cSrcSize,                              \
+            const HUF_DTable* DTable)                                       \
+    {                                                                       \
+        return fn##_body(dst, dstSize, cSrc, cSrcSize, DTable);             \
+    }                                                                       \
+                                                                            \
+    static TARGET_ATTRIBUTE("bmi2") size_t fn##_bmi2(                       \
+                  void* dst,  size_t dstSize,                               \
+            const void* cSrc, size_t cSrcSize,                              \
+            const HUF_DTable* DTable)                                       \
+    {                                                                       \
+        return fn##_body(dst, dstSize, cSrc, cSrcSize, DTable);             \
+    }                                                                       \
+                                                                            \
+    static size_t fn(void* dst, size_t dstSize, void const* cSrc,           \
+                     size_t cSrcSize, HUF_DTable const* DTable, int bmi2)   \
+    {                                                                       \
+        if (bmi2) {                                                         \
+            return fn##_bmi2(dst, dstSize, cSrc, cSrcSize, DTable);         \
+        }                                                                   \
+        return fn##_default(dst, dstSize, cSrc, cSrcSize, DTable);          \
+    }
+
+#else
+
+#define HUF_DGEN(fn)                                                        \
+    static size_t fn(void* dst, size_t dstSize, void const* cSrc,           \
+                     size_t cSrcSize, HUF_DTable const* DTable, int bmi2)   \
+    {                                                                       \
+        (void)bmi2;                                                         \
+        return fn##_body(dst, dstSize, cSrc, cSrcSize, DTable);             \
+    }
+
+#endif
+
+
+/*-***************************/
+/*  generic DTableDesc       */
+/*-***************************/
+typedef struct { BYTE maxTableLog; BYTE tableType; BYTE tableLog; BYTE reserved; } DTableDesc;
+
+static DTableDesc HUF_getDTableDesc(const HUF_DTable* table)
+{
+    DTableDesc dtd;
+    memcpy(&dtd, table, sizeof(dtd));
+    return dtd;
+}
+
+
+#ifndef HUF_FORCE_DECOMPRESS_X2
+
+/*-***************************/
+/*  single-symbol decoding   */
+/*-***************************/
+typedef struct { BYTE byte; BYTE nbBits; } HUF_DEltX1;   /* single-symbol decoding */
+
+size_t HUF_readDTableX1_wksp(HUF_DTable* DTable, const void* src, size_t srcSize, void* workSpace, size_t wkspSize)
+{
+    U32 tableLog = 0;
+    U32 nbSymbols = 0;
+    size_t iSize;
+    void* const dtPtr = DTable + 1;
+    HUF_DEltX1* const dt = (HUF_DEltX1*)dtPtr;
+
+    U32* rankVal;
+    BYTE* huffWeight;
+    size_t spaceUsed32 = 0;
+
+    rankVal = (U32 *)workSpace + spaceUsed32;
+    spaceUsed32 += HUF_TABLELOG_ABSOLUTEMAX + 1;
+    huffWeight = (BYTE *)((U32 *)workSpace + spaceUsed32);
+    spaceUsed32 += HUF_ALIGN(HUF_SYMBOLVALUE_MAX + 1, sizeof(U32)) >> 2;
+
+    if ((spaceUsed32 << 2) > wkspSize) return ERROR(tableLog_tooLarge);
+
+    DEBUG_STATIC_ASSERT(sizeof(DTableDesc) == sizeof(HUF_DTable));
+    /* memset(huffWeight, 0, sizeof(huffWeight)); */   /* is not necessary, even though some analyzer complain ... */
+
+    iSize = HUF_readStats(huffWeight, HUF_SYMBOLVALUE_MAX + 1, rankVal, &nbSymbols, &tableLog, src, srcSize);
+    if (HUF_isError(iSize)) return iSize;
+
+    /* Table header */
+    {   DTableDesc dtd = HUF_getDTableDesc(DTable);
+        if (tableLog > (U32)(dtd.maxTableLog+1)) return ERROR(tableLog_tooLarge);   /* DTable too small, Huffman tree cannot fit in */
+        dtd.tableType = 0;
+        dtd.tableLog = (BYTE)tableLog;
+        memcpy(DTable, &dtd, sizeof(dtd));
+    }
+
+    /* Calculate starting value for each rank */
+    {   U32 n, nextRankStart = 0;
+        for (n=1; n<tableLog+1; n++) {
+            U32 const current = nextRankStart;
+            nextRankStart += (rankVal[n] << (n-1));
+            rankVal[n] = current;
+    }   }
+
+    /* fill DTable */
+    {   U32 n;
+        size_t const nEnd = nbSymbols;
+        for (n=0; n<nEnd; n++) {
+            size_t const w = huffWeight[n];
+            size_t const length = (1 << w) >> 1;
+            size_t const uStart = rankVal[w];
+            size_t const uEnd = uStart + length;
+            size_t u;
+            HUF_DEltX1 D;
+            D.byte = (BYTE)n;
+            D.nbBits = (BYTE)(tableLog + 1 - w);
+            rankVal[w] = (U32)uEnd;
+            if (length < 4) {
+                /* Use length in the loop bound so the compiler knows it is short. */
+                for (u = 0; u < length; ++u)
+                    dt[uStart + u] = D;
+            } else {
+                /* Unroll the loop 4 times, we know it is a power of 2. */
+                for (u = uStart; u < uEnd; u += 4) {
+                    dt[u + 0] = D;
+                    dt[u + 1] = D;
+                    dt[u + 2] = D;
+                    dt[u + 3] = D;
+    }   }   }   }
+    return iSize;
+}
+
+size_t HUF_readDTableX1(HUF_DTable* DTable, const void* src, size_t srcSize)
+{
+    U32 workSpace[HUF_DECOMPRESS_WORKSPACE_SIZE_U32];
+    return HUF_readDTableX1_wksp(DTable, src, srcSize,
+                                 workSpace, sizeof(workSpace));
+}
+
+FORCE_INLINE_TEMPLATE BYTE
+HUF_decodeSymbolX1(BIT_DStream_t* Dstream, const HUF_DEltX1* dt, const U32 dtLog)
+{
+    size_t const val = BIT_lookBitsFast(Dstream, dtLog); /* note : dtLog >= 1 */
+    BYTE const c = dt[val].byte;
+    BIT_skipBits(Dstream, dt[val].nbBits);
+    return c;
+}
+
+#define HUF_DECODE_SYMBOLX1_0(ptr, DStreamPtr) \
+    *ptr++ = HUF_decodeSymbolX1(DStreamPtr, dt, dtLog)
+
+#define HUF_DECODE_SYMBOLX1_1(ptr, DStreamPtr)  \
+    if (MEM_64bits() || (HUF_TABLELOG_MAX<=12)) \
+        HUF_DECODE_SYMBOLX1_0(ptr, DStreamPtr)
+
+#define HUF_DECODE_SYMBOLX1_2(ptr, DStreamPtr) \
+    if (MEM_64bits()) \
+        HUF_DECODE_SYMBOLX1_0(ptr, DStreamPtr)
+
+HINT_INLINE size_t
+HUF_decodeStreamX1(BYTE* p, BIT_DStream_t* const bitDPtr, BYTE* const pEnd, const HUF_DEltX1* const dt, const U32 dtLog)
+{
+    BYTE* const pStart = p;
+
+    /* up to 4 symbols at a time */
+    while ((BIT_reloadDStream(bitDPtr) == BIT_DStream_unfinished) & (p < pEnd-3)) {
+        HUF_DECODE_SYMBOLX1_2(p, bitDPtr);
+        HUF_DECODE_SYMBOLX1_1(p, bitDPtr);
+        HUF_DECODE_SYMBOLX1_2(p, bitDPtr);
+        HUF_DECODE_SYMBOLX1_0(p, bitDPtr);
+    }
+
+    /* [0-3] symbols remaining */
+    if (MEM_32bits())
+        while ((BIT_reloadDStream(bitDPtr) == BIT_DStream_unfinished) & (p < pEnd))
+            HUF_DECODE_SYMBOLX1_0(p, bitDPtr);
+
+    /* no more data to retrieve from bitstream, no need to reload */
+    while (p < pEnd)
+        HUF_DECODE_SYMBOLX1_0(p, bitDPtr);
+
+    return pEnd-pStart;
+}
+
+FORCE_INLINE_TEMPLATE size_t
+HUF_decompress1X1_usingDTable_internal_body(
+          void* dst,  size_t dstSize,
+    const void* cSrc, size_t cSrcSize,
+    const HUF_DTable* DTable)
+{
+    BYTE* op = (BYTE*)dst;
+    BYTE* const oend = op + dstSize;
+    const void* dtPtr = DTable + 1;
+    const HUF_DEltX1* const dt = (const HUF_DEltX1*)dtPtr;
+    BIT_DStream_t bitD;
+    DTableDesc const dtd = HUF_getDTableDesc(DTable);
+    U32 const dtLog = dtd.tableLog;
+
+    CHECK_F( BIT_initDStream(&bitD, cSrc, cSrcSize) );
+
+    HUF_decodeStreamX1(op, &bitD, oend, dt, dtLog);
+
+    if (!BIT_endOfDStream(&bitD)) return ERROR(corruption_detected);
+
+    return dstSize;
+}
+
+FORCE_INLINE_TEMPLATE size_t
+HUF_decompress4X1_usingDTable_internal_body(
+          void* dst,  size_t dstSize,
+    const void* cSrc, size_t cSrcSize,
+    const HUF_DTable* DTable)
+{
+    /* Check */
+    if (cSrcSize < 10) return ERROR(corruption_detected);  /* strict minimum : jump table + 1 byte per stream */
+
+    {   const BYTE* const istart = (const BYTE*) cSrc;
+        BYTE* const ostart = (BYTE*) dst;
+        BYTE* const oend = ostart + dstSize;
+        BYTE* const olimit = oend - 3;
+        const void* const dtPtr = DTable + 1;
+        const HUF_DEltX1* const dt = (const HUF_DEltX1*)dtPtr;
+
+        /* Init */
+        BIT_DStream_t bitD1;
+        BIT_DStream_t bitD2;
+        BIT_DStream_t bitD3;
+        BIT_DStream_t bitD4;
+        size_t const length1 = MEM_readLE16(istart);
+        size_t const length2 = MEM_readLE16(istart+2);
+        size_t const length3 = MEM_readLE16(istart+4);
+        size_t const length4 = cSrcSize - (length1 + length2 + length3 + 6);
+        const BYTE* const istart1 = istart + 6;  /* jumpTable */
+        const BYTE* const istart2 = istart1 + length1;
+        const BYTE* const istart3 = istart2 + length2;
+        const BYTE* const istart4 = istart3 + length3;
+        const size_t segmentSize = (dstSize+3) / 4;
+        BYTE* const opStart2 = ostart + segmentSize;
+        BYTE* const opStart3 = opStart2 + segmentSize;
+        BYTE* const opStart4 = opStart3 + segmentSize;
+        BYTE* op1 = ostart;
+        BYTE* op2 = opStart2;
+        BYTE* op3 = opStart3;
+        BYTE* op4 = opStart4;
+        DTableDesc const dtd = HUF_getDTableDesc(DTable);
+        U32 const dtLog = dtd.tableLog;
+        U32 endSignal = 1;
+
+        if (length4 > cSrcSize) return ERROR(corruption_detected);   /* overflow */
+        CHECK_F( BIT_initDStream(&bitD1, istart1, length1) );
+        CHECK_F( BIT_initDStream(&bitD2, istart2, length2) );
+        CHECK_F( BIT_initDStream(&bitD3, istart3, length3) );
+        CHECK_F( BIT_initDStream(&bitD4, istart4, length4) );
+
+        /* up to 16 symbols per loop (4 symbols per stream) in 64-bit mode */
+        for ( ; (endSignal) & (op4 < olimit) ; ) {
+            HUF_DECODE_SYMBOLX1_2(op1, &bitD1);
+            HUF_DECODE_SYMBOLX1_2(op2, &bitD2);
+            HUF_DECODE_SYMBOLX1_2(op3, &bitD3);
+            HUF_DECODE_SYMBOLX1_2(op4, &bitD4);
+            HUF_DECODE_SYMBOLX1_1(op1, &bitD1);
+            HUF_DECODE_SYMBOLX1_1(op2, &bitD2);
+            HUF_DECODE_SYMBOLX1_1(op3, &bitD3);
+            HUF_DECODE_SYMBOLX1_1(op4, &bitD4);
+            HUF_DECODE_SYMBOLX1_2(op1, &bitD1);
+            HUF_DECODE_SYMBOLX1_2(op2, &bitD2);
+            HUF_DECODE_SYMBOLX1_2(op3, &bitD3);
+            HUF_DECODE_SYMBOLX1_2(op4, &bitD4);
+            HUF_DECODE_SYMBOLX1_0(op1, &bitD1);
+            HUF_DECODE_SYMBOLX1_0(op2, &bitD2);
+            HUF_DECODE_SYMBOLX1_0(op3, &bitD3);
+            HUF_DECODE_SYMBOLX1_0(op4, &bitD4);
+            endSignal &= BIT_reloadDStreamFast(&bitD1) == BIT_DStream_unfinished;
+            endSignal &= BIT_reloadDStreamFast(&bitD2) == BIT_DStream_unfinished;
+            endSignal &= BIT_reloadDStreamFast(&bitD3) == BIT_DStream_unfinished;
+            endSignal &= BIT_reloadDStreamFast(&bitD4) == BIT_DStream_unfinished;
+        }
+
+        /* check corruption */
+        /* note : should not be necessary : op# advance in lock step, and we control op4.
+         *        but curiously, binary generated by gcc 7.2 & 7.3 with -mbmi2 runs faster when >=1 test is present */
+        if (op1 > opStart2) return ERROR(corruption_detected);
+        if (op2 > opStart3) return ERROR(corruption_detected);
+        if (op3 > opStart4) return ERROR(corruption_detected);
+        /* note : op4 supposed already verified within main loop */
+
+        /* finish bitStreams one by one */
+        HUF_decodeStreamX1(op1, &bitD1, opStart2, dt, dtLog);
+        HUF_decodeStreamX1(op2, &bitD2, opStart3, dt, dtLog);
+        HUF_decodeStreamX1(op3, &bitD3, opStart4, dt, dtLog);
+        HUF_decodeStreamX1(op4, &bitD4, oend,     dt, dtLog);
+
+        /* check */
+        { U32 const endCheck = BIT_endOfDStream(&bitD1) & BIT_endOfDStream(&bitD2) & BIT_endOfDStream(&bitD3) & BIT_endOfDStream(&bitD4);
+          if (!endCheck) return ERROR(corruption_detected); }
+
+        /* decoded size */
+        return dstSize;
+    }
+}
+
+
+typedef size_t (*HUF_decompress_usingDTable_t)(void *dst, size_t dstSize,
+                                               const void *cSrc,
+                                               size_t cSrcSize,
+                                               const HUF_DTable *DTable);
+
+HUF_DGEN(HUF_decompress1X1_usingDTable_internal)
+HUF_DGEN(HUF_decompress4X1_usingDTable_internal)
+
+
+
+size_t HUF_decompress1X1_usingDTable(
+          void* dst,  size_t dstSize,
+    const void* cSrc, size_t cSrcSize,
+    const HUF_DTable* DTable)
+{
+    DTableDesc dtd = HUF_getDTableDesc(DTable);
+    if (dtd.tableType != 0) return ERROR(GENERIC);
+    return HUF_decompress1X1_usingDTable_internal(dst, dstSize, cSrc, cSrcSize, DTable, /* bmi2 */ 0);
+}
+
+size_t HUF_decompress1X1_DCtx_wksp(HUF_DTable* DCtx, void* dst, size_t dstSize,
+                                   const void* cSrc, size_t cSrcSize,
+                                   void* workSpace, size_t wkspSize)
+{
+    const BYTE* ip = (const BYTE*) cSrc;
+
+    size_t const hSize = HUF_readDTableX1_wksp(DCtx, cSrc, cSrcSize, workSpace, wkspSize);
+    if (HUF_isError(hSize)) return hSize;
+    if (hSize >= cSrcSize) return ERROR(srcSize_wrong);
+    ip += hSize; cSrcSize -= hSize;
+
+    return HUF_decompress1X1_usingDTable_internal(dst, dstSize, ip, cSrcSize, DCtx, /* bmi2 */ 0);
+}
+
+
+size_t HUF_decompress1X1_DCtx(HUF_DTable* DCtx, void* dst, size_t dstSize,
+                              const void* cSrc, size_t cSrcSize)
+{
+    U32 workSpace[HUF_DECOMPRESS_WORKSPACE_SIZE_U32];
+    return HUF_decompress1X1_DCtx_wksp(DCtx, dst, dstSize, cSrc, cSrcSize,
+                                       workSpace, sizeof(workSpace));
+}
+
+size_t HUF_decompress1X1 (void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize)
+{
+    HUF_CREATE_STATIC_DTABLEX1(DTable, HUF_TABLELOG_MAX);
+    return HUF_decompress1X1_DCtx (DTable, dst, dstSize, cSrc, cSrcSize);
+}
+
+size_t HUF_decompress4X1_usingDTable(
+          void* dst,  size_t dstSize,
+    const void* cSrc, size_t cSrcSize,
+    const HUF_DTable* DTable)
+{
+    DTableDesc dtd = HUF_getDTableDesc(DTable);
+    if (dtd.tableType != 0) return ERROR(GENERIC);
+    return HUF_decompress4X1_usingDTable_internal(dst, dstSize, cSrc, cSrcSize, DTable, /* bmi2 */ 0);
+}
+
+static size_t HUF_decompress4X1_DCtx_wksp_bmi2(HUF_DTable* dctx, void* dst, size_t dstSize,
+                                   const void* cSrc, size_t cSrcSize,
+                                   void* workSpace, size_t wkspSize, int bmi2)
+{
+    const BYTE* ip = (const BYTE*) cSrc;
+
+    size_t const hSize = HUF_readDTableX1_wksp (dctx, cSrc, cSrcSize,
+                                                workSpace, wkspSize);
+    if (HUF_isError(hSize)) return hSize;
+    if (hSize >= cSrcSize) return ERROR(srcSize_wrong);
+    ip += hSize; cSrcSize -= hSize;
+
+    return HUF_decompress4X1_usingDTable_internal(dst, dstSize, ip, cSrcSize, dctx, bmi2);
+}
+
+size_t HUF_decompress4X1_DCtx_wksp(HUF_DTable* dctx, void* dst, size_t dstSize,
+                                   const void* cSrc, size_t cSrcSize,
+                                   void* workSpace, size_t wkspSize)
+{
+    return HUF_decompress4X1_DCtx_wksp_bmi2(dctx, dst, dstSize, cSrc, cSrcSize, workSpace, wkspSize, 0);
+}
+
+
+size_t HUF_decompress4X1_DCtx (HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize)
+{
+    U32 workSpace[HUF_DECOMPRESS_WORKSPACE_SIZE_U32];
+    return HUF_decompress4X1_DCtx_wksp(dctx, dst, dstSize, cSrc, cSrcSize,
+                                       workSpace, sizeof(workSpace));
+}
+size_t HUF_decompress4X1 (void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize)
+{
+    HUF_CREATE_STATIC_DTABLEX1(DTable, HUF_TABLELOG_MAX);
+    return HUF_decompress4X1_DCtx(DTable, dst, dstSize, cSrc, cSrcSize);
+}
+
+#endif /* HUF_FORCE_DECOMPRESS_X2 */
+
+
+#ifndef HUF_FORCE_DECOMPRESS_X1
+
+/* *************************/
+/* double-symbols decoding */
+/* *************************/
+
+typedef struct { U16 sequence; BYTE nbBits; BYTE length; } HUF_DEltX2;  /* double-symbols decoding */
+typedef struct { BYTE symbol; BYTE weight; } sortedSymbol_t;
+typedef U32 rankValCol_t[HUF_TABLELOG_MAX + 1];
+typedef rankValCol_t rankVal_t[HUF_TABLELOG_MAX];
+
+
+/* HUF_fillDTableX2Level2() :
+ * `rankValOrigin` must be a table of at least (HUF_TABLELOG_MAX + 1) U32 */
+static void HUF_fillDTableX2Level2(HUF_DEltX2* DTable, U32 sizeLog, const U32 consumed,
+                           const U32* rankValOrigin, const int minWeight,
+                           const sortedSymbol_t* sortedSymbols, const U32 sortedListSize,
+                           U32 nbBitsBaseline, U16 baseSeq)
+{
+    HUF_DEltX2 DElt;
+    U32 rankVal[HUF_TABLELOG_MAX + 1];
+
+    /* get pre-calculated rankVal */
+    memcpy(rankVal, rankValOrigin, sizeof(rankVal));
+
+    /* fill skipped values */
+    if (minWeight>1) {
+        U32 i, skipSize = rankVal[minWeight];
+        MEM_writeLE16(&(DElt.sequence), baseSeq);
+        DElt.nbBits   = (BYTE)(consumed);
+        DElt.length   = 1;
+        for (i = 0; i < skipSize; i++)
+            DTable[i] = DElt;
+    }
+
+    /* fill DTable */
+    {   U32 s; for (s=0; s<sortedListSize; s++) {   /* note : sortedSymbols already skipped */
+            const U32 symbol = sortedSymbols[s].symbol;
+            const U32 weight = sortedSymbols[s].weight;
+            const U32 nbBits = nbBitsBaseline - weight;
+            const U32 length = 1 << (sizeLog-nbBits);
+            const U32 start = rankVal[weight];
+            U32 i = start;
+            const U32 end = start + length;
+
+            MEM_writeLE16(&(DElt.sequence), (U16)(baseSeq + (symbol << 8)));
+            DElt.nbBits = (BYTE)(nbBits + consumed);
+            DElt.length = 2;
+            do { DTable[i++] = DElt; } while (i<end);   /* since length >= 1 */
+
+            rankVal[weight] += length;
+    }   }
+}
+
+
+static void HUF_fillDTableX2(HUF_DEltX2* DTable, const U32 targetLog,
+                           const sortedSymbol_t* sortedList, const U32 sortedListSize,
+                           const U32* rankStart, rankVal_t rankValOrigin, const U32 maxWeight,
+                           const U32 nbBitsBaseline)
+{
+    U32 rankVal[HUF_TABLELOG_MAX + 1];
+    const int scaleLog = nbBitsBaseline - targetLog;   /* note : targetLog >= srcLog, hence scaleLog <= 1 */
+    const U32 minBits  = nbBitsBaseline - maxWeight;
+    U32 s;
+
+    memcpy(rankVal, rankValOrigin, sizeof(rankVal));
+
+    /* fill DTable */
+    for (s=0; s<sortedListSize; s++) {
+        const U16 symbol = sortedList[s].symbol;
+        const U32 weight = sortedList[s].weight;
+        const U32 nbBits = nbBitsBaseline - weight;
+        const U32 start = rankVal[weight];
+        const U32 length = 1 << (targetLog-nbBits);
+
+        if (targetLog-nbBits >= minBits) {   /* enough room for a second symbol */
+            U32 sortedRank;
+            int minWeight = nbBits + scaleLog;
+            if (minWeight < 1) minWeight = 1;
+            sortedRank = rankStart[minWeight];
+            HUF_fillDTableX2Level2(DTable+start, targetLog-nbBits, nbBits,
+                           rankValOrigin[nbBits], minWeight,
+                           sortedList+sortedRank, sortedListSize-sortedRank,
+                           nbBitsBaseline, symbol);
+        } else {
+            HUF_DEltX2 DElt;
+            MEM_writeLE16(&(DElt.sequence), symbol);
+            DElt.nbBits = (BYTE)(nbBits);
+            DElt.length = 1;
+            {   U32 const end = start + length;
+                U32 u;
+                for (u = start; u < end; u++) DTable[u] = DElt;
+        }   }
+        rankVal[weight] += length;
+    }
+}
+
+size_t HUF_readDTableX2_wksp(HUF_DTable* DTable,
+                       const void* src, size_t srcSize,
+                             void* workSpace, size_t wkspSize)
+{
+    U32 tableLog, maxW, sizeOfSort, nbSymbols;
+    DTableDesc dtd = HUF_getDTableDesc(DTable);
+    U32 const maxTableLog = dtd.maxTableLog;
+    size_t iSize;
+    void* dtPtr = DTable+1;   /* force compiler to avoid strict-aliasing */
+    HUF_DEltX2* const dt = (HUF_DEltX2*)dtPtr;
+    U32 *rankStart;
+
+    rankValCol_t* rankVal;
+    U32* rankStats;
+    U32* rankStart0;
+    sortedSymbol_t* sortedSymbol;
+    BYTE* weightList;
+    size_t spaceUsed32 = 0;
+
+    rankVal = (rankValCol_t *)((U32 *)workSpace + spaceUsed32);
+    spaceUsed32 += (sizeof(rankValCol_t) * HUF_TABLELOG_MAX) >> 2;
+    rankStats = (U32 *)workSpace + spaceUsed32;
+    spaceUsed32 += HUF_TABLELOG_MAX + 1;
+    rankStart0 = (U32 *)workSpace + spaceUsed32;
+    spaceUsed32 += HUF_TABLELOG_MAX + 2;
+    sortedSymbol = (sortedSymbol_t *)workSpace + (spaceUsed32 * sizeof(U32)) / sizeof(sortedSymbol_t);
+    spaceUsed32 += HUF_ALIGN(sizeof(sortedSymbol_t) * (HUF_SYMBOLVALUE_MAX + 1), sizeof(U32)) >> 2;
+    weightList = (BYTE *)((U32 *)workSpace + spaceUsed32);
+    spaceUsed32 += HUF_ALIGN(HUF_SYMBOLVALUE_MAX + 1, sizeof(U32)) >> 2;
+
+    if ((spaceUsed32 << 2) > wkspSize) return ERROR(tableLog_tooLarge);
+
+    rankStart = rankStart0 + 1;
+    memset(rankStats, 0, sizeof(U32) * (2 * HUF_TABLELOG_MAX + 2 + 1));
+
+    DEBUG_STATIC_ASSERT(sizeof(HUF_DEltX2) == sizeof(HUF_DTable));   /* if compiler fails here, assertion is wrong */
+    if (maxTableLog > HUF_TABLELOG_MAX) return ERROR(tableLog_tooLarge);
+    /* memset(weightList, 0, sizeof(weightList)); */  /* is not necessary, even though some analyzer complain ... */
+
+    iSize = HUF_readStats(weightList, HUF_SYMBOLVALUE_MAX + 1, rankStats, &nbSymbols, &tableLog, src, srcSize);
+    if (HUF_isError(iSize)) return iSize;
+
+    /* check result */
+    if (tableLog > maxTableLog) return ERROR(tableLog_tooLarge);   /* DTable can't fit code depth */
+
+    /* find maxWeight */
+    for (maxW = tableLog; rankStats[maxW]==0; maxW--) {}  /* necessarily finds a solution before 0 */
+
+    /* Get start index of each weight */
+    {   U32 w, nextRankStart = 0;
+        for (w=1; w<maxW+1; w++) {
+            U32 current = nextRankStart;
+            nextRankStart += rankStats[w];
+            rankStart[w] = current;
+        }
+        rankStart[0] = nextRankStart;   /* put all 0w symbols at the end of sorted list*/
+        sizeOfSort = nextRankStart;
+    }
+
+    /* sort symbols by weight */
+    {   U32 s;
+        for (s=0; s<nbSymbols; s++) {
+            U32 const w = weightList[s];
+            U32 const r = rankStart[w]++;
+            sortedSymbol[r].symbol = (BYTE)s;
+            sortedSymbol[r].weight = (BYTE)w;
+        }
+        rankStart[0] = 0;   /* forget 0w symbols; this is beginning of weight(1) */
+    }
+
+    /* Build rankVal */
+    {   U32* const rankVal0 = rankVal[0];
+        {   int const rescale = (maxTableLog-tableLog) - 1;   /* tableLog <= maxTableLog */
+            U32 nextRankVal = 0;
+            U32 w;
+            for (w=1; w<maxW+1; w++) {
+                U32 current = nextRankVal;
+                nextRankVal += rankStats[w] << (w+rescale);
+                rankVal0[w] = current;
+        }   }
+        {   U32 const minBits = tableLog+1 - maxW;
+            U32 consumed;
+            for (consumed = minBits; consumed < maxTableLog - minBits + 1; consumed++) {
+                U32* const rankValPtr = rankVal[consumed];
+                U32 w;
+                for (w = 1; w < maxW+1; w++) {
+                    rankValPtr[w] = rankVal0[w] >> consumed;
+    }   }   }   }
+
+    HUF_fillDTableX2(dt, maxTableLog,
+                   sortedSymbol, sizeOfSort,
+                   rankStart0, rankVal, maxW,
+                   tableLog+1);
+
+    dtd.tableLog = (BYTE)maxTableLog;
+    dtd.tableType = 1;
+    memcpy(DTable, &dtd, sizeof(dtd));
+    return iSize;
+}
+
+size_t HUF_readDTableX2(HUF_DTable* DTable, const void* src, size_t srcSize)
+{
+  U32 workSpace[HUF_DECOMPRESS_WORKSPACE_SIZE_U32];
+  return HUF_readDTableX2_wksp(DTable, src, srcSize,
+                               workSpace, sizeof(workSpace));
+}
+
+
+FORCE_INLINE_TEMPLATE U32
+HUF_decodeSymbolX2(void* op, BIT_DStream_t* DStream, const HUF_DEltX2* dt, const U32 dtLog)
+{
+    size_t const val = BIT_lookBitsFast(DStream, dtLog);   /* note : dtLog >= 1 */
+    memcpy(op, dt+val, 2);
+    BIT_skipBits(DStream, dt[val].nbBits);
+    return dt[val].length;
+}
+
+FORCE_INLINE_TEMPLATE U32
+HUF_decodeLastSymbolX2(void* op, BIT_DStream_t* DStream, const HUF_DEltX2* dt, const U32 dtLog)
+{
+    size_t const val = BIT_lookBitsFast(DStream, dtLog);   /* note : dtLog >= 1 */
+    memcpy(op, dt+val, 1);
+    if (dt[val].length==1) BIT_skipBits(DStream, dt[val].nbBits);
+    else {
+        if (DStream->bitsConsumed < (sizeof(DStream->bitContainer)*8)) {
+            BIT_skipBits(DStream, dt[val].nbBits);
+            if (DStream->bitsConsumed > (sizeof(DStream->bitContainer)*8))
+                /* ugly hack; works only because it's the last symbol. Note : can't easily extract nbBits from just this symbol */
+                DStream->bitsConsumed = (sizeof(DStream->bitContainer)*8);
+    }   }
+    return 1;
+}
+
+#define HUF_DECODE_SYMBOLX2_0(ptr, DStreamPtr) \
+    ptr += HUF_decodeSymbolX2(ptr, DStreamPtr, dt, dtLog)
+
+#define HUF_DECODE_SYMBOLX2_1(ptr, DStreamPtr) \
+    if (MEM_64bits() || (HUF_TABLELOG_MAX<=12)) \
+        ptr += HUF_decodeSymbolX2(ptr, DStreamPtr, dt, dtLog)
+
+#define HUF_DECODE_SYMBOLX2_2(ptr, DStreamPtr) \
+    if (MEM_64bits()) \
+        ptr += HUF_decodeSymbolX2(ptr, DStreamPtr, dt, dtLog)
+
+HINT_INLINE size_t
+HUF_decodeStreamX2(BYTE* p, BIT_DStream_t* bitDPtr, BYTE* const pEnd,
+                const HUF_DEltX2* const dt, const U32 dtLog)
+{
+    BYTE* const pStart = p;
+
+    /* up to 8 symbols at a time */
+    while ((BIT_reloadDStream(bitDPtr) == BIT_DStream_unfinished) & (p < pEnd-(sizeof(bitDPtr->bitContainer)-1))) {
+        HUF_DECODE_SYMBOLX2_2(p, bitDPtr);
+        HUF_DECODE_SYMBOLX2_1(p, bitDPtr);
+        HUF_DECODE_SYMBOLX2_2(p, bitDPtr);
+        HUF_DECODE_SYMBOLX2_0(p, bitDPtr);
+    }
+
+    /* closer to end : up to 2 symbols at a time */
+    while ((BIT_reloadDStream(bitDPtr) == BIT_DStream_unfinished) & (p <= pEnd-2))
+        HUF_DECODE_SYMBOLX2_0(p, bitDPtr);
+
+    while (p <= pEnd-2)
+        HUF_DECODE_SYMBOLX2_0(p, bitDPtr);   /* no need to reload : reached the end of DStream */
+
+    if (p < pEnd)
+        p += HUF_decodeLastSymbolX2(p, bitDPtr, dt, dtLog);
+
+    return p-pStart;
+}
+
+FORCE_INLINE_TEMPLATE size_t
+HUF_decompress1X2_usingDTable_internal_body(
+          void* dst,  size_t dstSize,
+    const void* cSrc, size_t cSrcSize,
+    const HUF_DTable* DTable)
+{
+    BIT_DStream_t bitD;
+
+    /* Init */
+    CHECK_F( BIT_initDStream(&bitD, cSrc, cSrcSize) );
+
+    /* decode */
+    {   BYTE* const ostart = (BYTE*) dst;
+        BYTE* const oend = ostart + dstSize;
+        const void* const dtPtr = DTable+1;   /* force compiler to not use strict-aliasing */
+        const HUF_DEltX2* const dt = (const HUF_DEltX2*)dtPtr;
+        DTableDesc const dtd = HUF_getDTableDesc(DTable);
+        HUF_decodeStreamX2(ostart, &bitD, oend, dt, dtd.tableLog);
+    }
+
+    /* check */
+    if (!BIT_endOfDStream(&bitD)) return ERROR(corruption_detected);
+
+    /* decoded size */
+    return dstSize;
+}
+
+FORCE_INLINE_TEMPLATE size_t
+HUF_decompress4X2_usingDTable_internal_body(
+          void* dst,  size_t dstSize,
+    const void* cSrc, size_t cSrcSize,
+    const HUF_DTable* DTable)
+{
+    if (cSrcSize < 10) return ERROR(corruption_detected);   /* strict minimum : jump table + 1 byte per stream */
+
+    {   const BYTE* const istart = (const BYTE*) cSrc;
+        BYTE* const ostart = (BYTE*) dst;
+        BYTE* const oend = ostart + dstSize;
+        BYTE* const olimit = oend - (sizeof(size_t)-1);
+        const void* const dtPtr = DTable+1;
+        const HUF_DEltX2* const dt = (const HUF_DEltX2*)dtPtr;
+
+        /* Init */
+        BIT_DStream_t bitD1;
+        BIT_DStream_t bitD2;
+        BIT_DStream_t bitD3;
+        BIT_DStream_t bitD4;
+        size_t const length1 = MEM_readLE16(istart);
+        size_t const length2 = MEM_readLE16(istart+2);
+        size_t const length3 = MEM_readLE16(istart+4);
+        size_t const length4 = cSrcSize - (length1 + length2 + length3 + 6);
+        const BYTE* const istart1 = istart + 6;  /* jumpTable */
+        const BYTE* const istart2 = istart1 + length1;
+        const BYTE* const istart3 = istart2 + length2;
+        const BYTE* const istart4 = istart3 + length3;
+        size_t const segmentSize = (dstSize+3) / 4;
+        BYTE* const opStart2 = ostart + segmentSize;
+        BYTE* const opStart3 = opStart2 + segmentSize;
+        BYTE* const opStart4 = opStart3 + segmentSize;
+        BYTE* op1 = ostart;
+        BYTE* op2 = opStart2;
+        BYTE* op3 = opStart3;
+        BYTE* op4 = opStart4;
+        U32 endSignal = 1;
+        DTableDesc const dtd = HUF_getDTableDesc(DTable);
+        U32 const dtLog = dtd.tableLog;
+
+        if (length4 > cSrcSize) return ERROR(corruption_detected);   /* overflow */
+        CHECK_F( BIT_initDStream(&bitD1, istart1, length1) );
+        CHECK_F( BIT_initDStream(&bitD2, istart2, length2) );
+        CHECK_F( BIT_initDStream(&bitD3, istart3, length3) );
+        CHECK_F( BIT_initDStream(&bitD4, istart4, length4) );
+
+        /* 16-32 symbols per loop (4-8 symbols per stream) */
+        for ( ; (endSignal) & (op4 < olimit); ) {
+#if defined(__clang__) && (defined(__x86_64__) || defined(__i386__))
+            HUF_DECODE_SYMBOLX2_2(op1, &bitD1);
+            HUF_DECODE_SYMBOLX2_1(op1, &bitD1);
+            HUF_DECODE_SYMBOLX2_2(op1, &bitD1);
+            HUF_DECODE_SYMBOLX2_0(op1, &bitD1);
+            HUF_DECODE_SYMBOLX2_2(op2, &bitD2);
+            HUF_DECODE_SYMBOLX2_1(op2, &bitD2);
+            HUF_DECODE_SYMBOLX2_2(op2, &bitD2);
+            HUF_DECODE_SYMBOLX2_0(op2, &bitD2);
+            endSignal &= BIT_reloadDStreamFast(&bitD1) == BIT_DStream_unfinished;
+            endSignal &= BIT_reloadDStreamFast(&bitD2) == BIT_DStream_unfinished;
+            HUF_DECODE_SYMBOLX2_2(op3, &bitD3);
+            HUF_DECODE_SYMBOLX2_1(op3, &bitD3);
+            HUF_DECODE_SYMBOLX2_2(op3, &bitD3);
+            HUF_DECODE_SYMBOLX2_0(op3, &bitD3);
+            HUF_DECODE_SYMBOLX2_2(op4, &bitD4);
+            HUF_DECODE_SYMBOLX2_1(op4, &bitD4);
+            HUF_DECODE_SYMBOLX2_2(op4, &bitD4);
+            HUF_DECODE_SYMBOLX2_0(op4, &bitD4);
+            endSignal &= BIT_reloadDStreamFast(&bitD3) == BIT_DStream_unfinished;
+            endSignal &= BIT_reloadDStreamFast(&bitD4) == BIT_DStream_unfinished;
+#else
+            HUF_DECODE_SYMBOLX2_2(op1, &bitD1);
+            HUF_DECODE_SYMBOLX2_2(op2, &bitD2);
+            HUF_DECODE_SYMBOLX2_2(op3, &bitD3);
+            HUF_DECODE_SYMBOLX2_2(op4, &bitD4);
+            HUF_DECODE_SYMBOLX2_1(op1, &bitD1);
+            HUF_DECODE_SYMBOLX2_1(op2, &bitD2);
+            HUF_DECODE_SYMBOLX2_1(op3, &bitD3);
+            HUF_DECODE_SYMBOLX2_1(op4, &bitD4);
+            HUF_DECODE_SYMBOLX2_2(op1, &bitD1);
+            HUF_DECODE_SYMBOLX2_2(op2, &bitD2);
+            HUF_DECODE_SYMBOLX2_2(op3, &bitD3);
+            HUF_DECODE_SYMBOLX2_2(op4, &bitD4);
+            HUF_DECODE_SYMBOLX2_0(op1, &bitD1);
+            HUF_DECODE_SYMBOLX2_0(op2, &bitD2);
+            HUF_DECODE_SYMBOLX2_0(op3, &bitD3);
+            HUF_DECODE_SYMBOLX2_0(op4, &bitD4);
+            endSignal = (U32)LIKELY(
+                        (BIT_reloadDStreamFast(&bitD1) == BIT_DStream_unfinished)
+                      & (BIT_reloadDStreamFast(&bitD2) == BIT_DStream_unfinished)
+                      & (BIT_reloadDStreamFast(&bitD3) == BIT_DStream_unfinished)
+                      & (BIT_reloadDStreamFast(&bitD4) == BIT_DStream_unfinished));
+#endif
+        }
+
+        /* check corruption */
+        if (op1 > opStart2) return ERROR(corruption_detected);
+        if (op2 > opStart3) return ERROR(corruption_detected);
+        if (op3 > opStart4) return ERROR(corruption_detected);
+        /* note : op4 already verified within main loop */
+
+        /* finish bitStreams one by one */
+        HUF_decodeStreamX2(op1, &bitD1, opStart2, dt, dtLog);
+        HUF_decodeStreamX2(op2, &bitD2, opStart3, dt, dtLog);
+        HUF_decodeStreamX2(op3, &bitD3, opStart4, dt, dtLog);
+        HUF_decodeStreamX2(op4, &bitD4, oend,     dt, dtLog);
+
+        /* check */
+        { U32 const endCheck = BIT_endOfDStream(&bitD1) & BIT_endOfDStream(&bitD2) & BIT_endOfDStream(&bitD3) & BIT_endOfDStream(&bitD4);
+          if (!endCheck) return ERROR(corruption_detected); }
+
+        /* decoded size */
+        return dstSize;
+    }
+}
+
+HUF_DGEN(HUF_decompress1X2_usingDTable_internal)
+HUF_DGEN(HUF_decompress4X2_usingDTable_internal)
+
+size_t HUF_decompress1X2_usingDTable(
+          void* dst,  size_t dstSize,
+    const void* cSrc, size_t cSrcSize,
+    const HUF_DTable* DTable)
+{
+    DTableDesc dtd = HUF_getDTableDesc(DTable);
+    if (dtd.tableType != 1) return ERROR(GENERIC);
+    return HUF_decompress1X2_usingDTable_internal(dst, dstSize, cSrc, cSrcSize, DTable, /* bmi2 */ 0);
+}
+
+size_t HUF_decompress1X2_DCtx_wksp(HUF_DTable* DCtx, void* dst, size_t dstSize,
+                                   const void* cSrc, size_t cSrcSize,
+                                   void* workSpace, size_t wkspSize)
+{
+    const BYTE* ip = (const BYTE*) cSrc;
+
+    size_t const hSize = HUF_readDTableX2_wksp(DCtx, cSrc, cSrcSize,
+                                               workSpace, wkspSize);
+    if (HUF_isError(hSize)) return hSize;
+    if (hSize >= cSrcSize) return ERROR(srcSize_wrong);
+    ip += hSize; cSrcSize -= hSize;
+
+    return HUF_decompress1X2_usingDTable_internal(dst, dstSize, ip, cSrcSize, DCtx, /* bmi2 */ 0);
+}
+
+
+size_t HUF_decompress1X2_DCtx(HUF_DTable* DCtx, void* dst, size_t dstSize,
+                              const void* cSrc, size_t cSrcSize)
+{
+    U32 workSpace[HUF_DECOMPRESS_WORKSPACE_SIZE_U32];
+    return HUF_decompress1X2_DCtx_wksp(DCtx, dst, dstSize, cSrc, cSrcSize,
+                                       workSpace, sizeof(workSpace));
+}
+
+size_t HUF_decompress1X2 (void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize)
+{
+    HUF_CREATE_STATIC_DTABLEX2(DTable, HUF_TABLELOG_MAX);
+    return HUF_decompress1X2_DCtx(DTable, dst, dstSize, cSrc, cSrcSize);
+}
+
+size_t HUF_decompress4X2_usingDTable(
+          void* dst,  size_t dstSize,
+    const void* cSrc, size_t cSrcSize,
+    const HUF_DTable* DTable)
+{
+    DTableDesc dtd = HUF_getDTableDesc(DTable);
+    if (dtd.tableType != 1) return ERROR(GENERIC);
+    return HUF_decompress4X2_usingDTable_internal(dst, dstSize, cSrc, cSrcSize, DTable, /* bmi2 */ 0);
+}
+
+static size_t HUF_decompress4X2_DCtx_wksp_bmi2(HUF_DTable* dctx, void* dst, size_t dstSize,
+                                   const void* cSrc, size_t cSrcSize,
+                                   void* workSpace, size_t wkspSize, int bmi2)
+{
+    const BYTE* ip = (const BYTE*) cSrc;
+
+    size_t hSize = HUF_readDTableX2_wksp(dctx, cSrc, cSrcSize,
+                                         workSpace, wkspSize);
+    if (HUF_isError(hSize)) return hSize;
+    if (hSize >= cSrcSize) return ERROR(srcSize_wrong);
+    ip += hSize; cSrcSize -= hSize;
+
+    return HUF_decompress4X2_usingDTable_internal(dst, dstSize, ip, cSrcSize, dctx, bmi2);
+}
+
+size_t HUF_decompress4X2_DCtx_wksp(HUF_DTable* dctx, void* dst, size_t dstSize,
+                                   const void* cSrc, size_t cSrcSize,
+                                   void* workSpace, size_t wkspSize)
+{
+    return HUF_decompress4X2_DCtx_wksp_bmi2(dctx, dst, dstSize, cSrc, cSrcSize, workSpace, wkspSize, /* bmi2 */ 0);
+}
+
+
+size_t HUF_decompress4X2_DCtx(HUF_DTable* dctx, void* dst, size_t dstSize,
+                              const void* cSrc, size_t cSrcSize)
+{
+    U32 workSpace[HUF_DECOMPRESS_WORKSPACE_SIZE_U32];
+    return HUF_decompress4X2_DCtx_wksp(dctx, dst, dstSize, cSrc, cSrcSize,
+                                       workSpace, sizeof(workSpace));
+}
+
+size_t HUF_decompress4X2 (void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize)
+{
+    HUF_CREATE_STATIC_DTABLEX2(DTable, HUF_TABLELOG_MAX);
+    return HUF_decompress4X2_DCtx(DTable, dst, dstSize, cSrc, cSrcSize);
+}
+
+#endif /* HUF_FORCE_DECOMPRESS_X1 */
+
+
+/* ***********************************/
+/* Universal decompression selectors */
+/* ***********************************/
+
+size_t HUF_decompress1X_usingDTable(void* dst, size_t maxDstSize,
+                                    const void* cSrc, size_t cSrcSize,
+                                    const HUF_DTable* DTable)
+{
+    DTableDesc const dtd = HUF_getDTableDesc(DTable);
+#if defined(HUF_FORCE_DECOMPRESS_X1)
+    (void)dtd;
+    assert(dtd.tableType == 0);
+    return HUF_decompress1X1_usingDTable_internal(dst, maxDstSize, cSrc, cSrcSize, DTable, /* bmi2 */ 0);
+#elif defined(HUF_FORCE_DECOMPRESS_X2)
+    (void)dtd;
+    assert(dtd.tableType == 1);
+    return HUF_decompress1X2_usingDTable_internal(dst, maxDstSize, cSrc, cSrcSize, DTable, /* bmi2 */ 0);
+#else
+    return dtd.tableType ? HUF_decompress1X2_usingDTable_internal(dst, maxDstSize, cSrc, cSrcSize, DTable, /* bmi2 */ 0) :
+                           HUF_decompress1X1_usingDTable_internal(dst, maxDstSize, cSrc, cSrcSize, DTable, /* bmi2 */ 0);
+#endif
+}
+
+size_t HUF_decompress4X_usingDTable(void* dst, size_t maxDstSize,
+                                    const void* cSrc, size_t cSrcSize,
+                                    const HUF_DTable* DTable)
+{
+    DTableDesc const dtd = HUF_getDTableDesc(DTable);
+#if defined(HUF_FORCE_DECOMPRESS_X1)
+    (void)dtd;
+    assert(dtd.tableType == 0);
+    return HUF_decompress4X1_usingDTable_internal(dst, maxDstSize, cSrc, cSrcSize, DTable, /* bmi2 */ 0);
+#elif defined(HUF_FORCE_DECOMPRESS_X2)
+    (void)dtd;
+    assert(dtd.tableType == 1);
+    return HUF_decompress4X2_usingDTable_internal(dst, maxDstSize, cSrc, cSrcSize, DTable, /* bmi2 */ 0);
+#else
+    return dtd.tableType ? HUF_decompress4X2_usingDTable_internal(dst, maxDstSize, cSrc, cSrcSize, DTable, /* bmi2 */ 0) :
+                           HUF_decompress4X1_usingDTable_internal(dst, maxDstSize, cSrc, cSrcSize, DTable, /* bmi2 */ 0);
+#endif
+}
+
+
+#if !defined(HUF_FORCE_DECOMPRESS_X1) && !defined(HUF_FORCE_DECOMPRESS_X2)
+typedef struct { U32 tableTime; U32 decode256Time; } algo_time_t;
+static const algo_time_t algoTime[16 /* Quantization */][3 /* single, double, quad */] =
+{
+    /* single, double, quad */
+    {{0,0}, {1,1}, {2,2}},  /* Q==0 : impossible */
+    {{0,0}, {1,1}, {2,2}},  /* Q==1 : impossible */
+    {{  38,130}, {1313, 74}, {2151, 38}},   /* Q == 2 : 12-18% */
+    {{ 448,128}, {1353, 74}, {2238, 41}},   /* Q == 3 : 18-25% */
+    {{ 556,128}, {1353, 74}, {2238, 47}},   /* Q == 4 : 25-32% */
+    {{ 714,128}, {1418, 74}, {2436, 53}},   /* Q == 5 : 32-38% */
+    {{ 883,128}, {1437, 74}, {2464, 61}},   /* Q == 6 : 38-44% */
+    {{ 897,128}, {1515, 75}, {2622, 68}},   /* Q == 7 : 44-50% */
+    {{ 926,128}, {1613, 75}, {2730, 75}},   /* Q == 8 : 50-56% */
+    {{ 947,128}, {1729, 77}, {3359, 77}},   /* Q == 9 : 56-62% */
+    {{1107,128}, {2083, 81}, {4006, 84}},   /* Q ==10 : 62-69% */
+    {{1177,128}, {2379, 87}, {4785, 88}},   /* Q ==11 : 69-75% */
+    {{1242,128}, {2415, 93}, {5155, 84}},   /* Q ==12 : 75-81% */
+    {{1349,128}, {2644,106}, {5260,106}},   /* Q ==13 : 81-87% */
+    {{1455,128}, {2422,124}, {4174,124}},   /* Q ==14 : 87-93% */
+    {{ 722,128}, {1891,145}, {1936,146}},   /* Q ==15 : 93-99% */
+};
+#endif
+
+/** HUF_selectDecoder() :
+ *  Tells which decoder is likely to decode faster,
+ *  based on a set of pre-computed metrics.
+ * @return : 0==HUF_decompress4X1, 1==HUF_decompress4X2 .
+ *  Assumption : 0 < dstSize <= 128 KB */
+U32 HUF_selectDecoder (size_t dstSize, size_t cSrcSize)
+{
+    assert(dstSize > 0);
+    assert(dstSize <= 128*1024);
+#if defined(HUF_FORCE_DECOMPRESS_X1)
+    (void)dstSize;
+    (void)cSrcSize;
+    return 0;
+#elif defined(HUF_FORCE_DECOMPRESS_X2)
+    (void)dstSize;
+    (void)cSrcSize;
+    return 1;
+#else
+    /* decoder timing evaluation */
+    {   U32 const Q = (cSrcSize >= dstSize) ? 15 : (U32)(cSrcSize * 16 / dstSize);   /* Q < 16 */
+        U32 const D256 = (U32)(dstSize >> 8);
+        U32 const DTime0 = algoTime[Q][0].tableTime + (algoTime[Q][0].decode256Time * D256);
+        U32 DTime1 = algoTime[Q][1].tableTime + (algoTime[Q][1].decode256Time * D256);
+        DTime1 += DTime1 >> 3;  /* advantage to algorithm using less memory, to reduce cache eviction */
+        return DTime1 < DTime0;
+    }
+#endif
+}
+
+
+typedef size_t (*decompressionAlgo)(void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize);
+
+size_t HUF_decompress (void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize)
+{
+#if !defined(HUF_FORCE_DECOMPRESS_X1) && !defined(HUF_FORCE_DECOMPRESS_X2)
+    static const decompressionAlgo decompress[2] = { HUF_decompress4X1, HUF_decompress4X2 };
+#endif
+
+    /* validation checks */
+    if (dstSize == 0) return ERROR(dstSize_tooSmall);
+    if (cSrcSize > dstSize) return ERROR(corruption_detected);   /* invalid */
+    if (cSrcSize == dstSize) { memcpy(dst, cSrc, dstSize); return dstSize; }   /* not compressed */
+    if (cSrcSize == 1) { memset(dst, *(const BYTE*)cSrc, dstSize); return dstSize; }   /* RLE */
+
+    {   U32 const algoNb = HUF_selectDecoder(dstSize, cSrcSize);
+#if defined(HUF_FORCE_DECOMPRESS_X1)
+        (void)algoNb;
+        assert(algoNb == 0);
+        return HUF_decompress4X1(dst, dstSize, cSrc, cSrcSize);
+#elif defined(HUF_FORCE_DECOMPRESS_X2)
+        (void)algoNb;
+        assert(algoNb == 1);
+        return HUF_decompress4X2(dst, dstSize, cSrc, cSrcSize);
+#else
+        return decompress[algoNb](dst, dstSize, cSrc, cSrcSize);
+#endif
+    }
+}
+
+size_t HUF_decompress4X_DCtx (HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize)
+{
+    /* validation checks */
+    if (dstSize == 0) return ERROR(dstSize_tooSmall);
+    if (cSrcSize > dstSize) return ERROR(corruption_detected);   /* invalid */
+    if (cSrcSize == dstSize) { memcpy(dst, cSrc, dstSize); return dstSize; }   /* not compressed */
+    if (cSrcSize == 1) { memset(dst, *(const BYTE*)cSrc, dstSize); return dstSize; }   /* RLE */
+
+    {   U32 const algoNb = HUF_selectDecoder(dstSize, cSrcSize);
+#if defined(HUF_FORCE_DECOMPRESS_X1)
+        (void)algoNb;
+        assert(algoNb == 0);
+        return HUF_decompress4X1_DCtx(dctx, dst, dstSize, cSrc, cSrcSize);
+#elif defined(HUF_FORCE_DECOMPRESS_X2)
+        (void)algoNb;
+        assert(algoNb == 1);
+        return HUF_decompress4X2_DCtx(dctx, dst, dstSize, cSrc, cSrcSize);
+#else
+        return algoNb ? HUF_decompress4X2_DCtx(dctx, dst, dstSize, cSrc, cSrcSize) :
+                        HUF_decompress4X1_DCtx(dctx, dst, dstSize, cSrc, cSrcSize) ;
+#endif
+    }
+}
+
+size_t HUF_decompress4X_hufOnly(HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize)
+{
+    U32 workSpace[HUF_DECOMPRESS_WORKSPACE_SIZE_U32];
+    return HUF_decompress4X_hufOnly_wksp(dctx, dst, dstSize, cSrc, cSrcSize,
+                                         workSpace, sizeof(workSpace));
+}
+
+
+size_t HUF_decompress4X_hufOnly_wksp(HUF_DTable* dctx, void* dst,
+                                     size_t dstSize, const void* cSrc,
+                                     size_t cSrcSize, void* workSpace,
+                                     size_t wkspSize)
+{
+    /* validation checks */
+    if (dstSize == 0) return ERROR(dstSize_tooSmall);
+    if (cSrcSize == 0) return ERROR(corruption_detected);
+
+    {   U32 const algoNb = HUF_selectDecoder(dstSize, cSrcSize);
+#if defined(HUF_FORCE_DECOMPRESS_X1)
+        (void)algoNb;
+        assert(algoNb == 0);
+        return HUF_decompress4X1_DCtx_wksp(dctx, dst, dstSize, cSrc, cSrcSize, workSpace, wkspSize);
+#elif defined(HUF_FORCE_DECOMPRESS_X2)
+        (void)algoNb;
+        assert(algoNb == 1);
+        return HUF_decompress4X2_DCtx_wksp(dctx, dst, dstSize, cSrc, cSrcSize, workSpace, wkspSize);
+#else
+        return algoNb ? HUF_decompress4X2_DCtx_wksp(dctx, dst, dstSize, cSrc,
+                            cSrcSize, workSpace, wkspSize):
+                        HUF_decompress4X1_DCtx_wksp(dctx, dst, dstSize, cSrc, cSrcSize, workSpace, wkspSize);
+#endif
+    }
+}
+
+size_t HUF_decompress1X_DCtx_wksp(HUF_DTable* dctx, void* dst, size_t dstSize,
+                                  const void* cSrc, size_t cSrcSize,
+                                  void* workSpace, size_t wkspSize)
+{
+    /* validation checks */
+    if (dstSize == 0) return ERROR(dstSize_tooSmall);
+    if (cSrcSize > dstSize) return ERROR(corruption_detected);   /* invalid */
+    if (cSrcSize == dstSize) { memcpy(dst, cSrc, dstSize); return dstSize; }   /* not compressed */
+    if (cSrcSize == 1) { memset(dst, *(const BYTE*)cSrc, dstSize); return dstSize; }   /* RLE */
+
+    {   U32 const algoNb = HUF_selectDecoder(dstSize, cSrcSize);
+#if defined(HUF_FORCE_DECOMPRESS_X1)
+        (void)algoNb;
+        assert(algoNb == 0);
+        return HUF_decompress1X1_DCtx_wksp(dctx, dst, dstSize, cSrc,
+                                cSrcSize, workSpace, wkspSize);
+#elif defined(HUF_FORCE_DECOMPRESS_X2)
+        (void)algoNb;
+        assert(algoNb == 1);
+        return HUF_decompress1X2_DCtx_wksp(dctx, dst, dstSize, cSrc,
+                                cSrcSize, workSpace, wkspSize);
+#else
+        return algoNb ? HUF_decompress1X2_DCtx_wksp(dctx, dst, dstSize, cSrc,
+                                cSrcSize, workSpace, wkspSize):
+                        HUF_decompress1X1_DCtx_wksp(dctx, dst, dstSize, cSrc,
+                                cSrcSize, workSpace, wkspSize);
+#endif
+    }
+}
+
+size_t HUF_decompress1X_DCtx(HUF_DTable* dctx, void* dst, size_t dstSize,
+                             const void* cSrc, size_t cSrcSize)
+{
+    U32 workSpace[HUF_DECOMPRESS_WORKSPACE_SIZE_U32];
+    return HUF_decompress1X_DCtx_wksp(dctx, dst, dstSize, cSrc, cSrcSize,
+                                      workSpace, sizeof(workSpace));
+}
+
+
+size_t HUF_decompress1X_usingDTable_bmi2(void* dst, size_t maxDstSize, const void* cSrc, size_t cSrcSize, const HUF_DTable* DTable, int bmi2)
+{
+    DTableDesc const dtd = HUF_getDTableDesc(DTable);
+#if defined(HUF_FORCE_DECOMPRESS_X1)
+    (void)dtd;
+    assert(dtd.tableType == 0);
+    return HUF_decompress1X1_usingDTable_internal(dst, maxDstSize, cSrc, cSrcSize, DTable, bmi2);
+#elif defined(HUF_FORCE_DECOMPRESS_X2)
+    (void)dtd;
+    assert(dtd.tableType == 1);
+    return HUF_decompress1X2_usingDTable_internal(dst, maxDstSize, cSrc, cSrcSize, DTable, bmi2);
+#else
+    return dtd.tableType ? HUF_decompress1X2_usingDTable_internal(dst, maxDstSize, cSrc, cSrcSize, DTable, bmi2) :
+                           HUF_decompress1X1_usingDTable_internal(dst, maxDstSize, cSrc, cSrcSize, DTable, bmi2);
+#endif
+}
+
+#ifndef HUF_FORCE_DECOMPRESS_X2
+size_t HUF_decompress1X1_DCtx_wksp_bmi2(HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize, void* workSpace, size_t wkspSize, int bmi2)
+{
+    const BYTE* ip = (const BYTE*) cSrc;
+
+    size_t const hSize = HUF_readDTableX1_wksp(dctx, cSrc, cSrcSize, workSpace, wkspSize);
+    if (HUF_isError(hSize)) return hSize;
+    if (hSize >= cSrcSize) return ERROR(srcSize_wrong);
+    ip += hSize; cSrcSize -= hSize;
+
+    return HUF_decompress1X1_usingDTable_internal(dst, dstSize, ip, cSrcSize, dctx, bmi2);
+}
+#endif
+
+size_t HUF_decompress4X_usingDTable_bmi2(void* dst, size_t maxDstSize, const void* cSrc, size_t cSrcSize, const HUF_DTable* DTable, int bmi2)
+{
+    DTableDesc const dtd = HUF_getDTableDesc(DTable);
+#if defined(HUF_FORCE_DECOMPRESS_X1)
+    (void)dtd;
+    assert(dtd.tableType == 0);
+    return HUF_decompress4X1_usingDTable_internal(dst, maxDstSize, cSrc, cSrcSize, DTable, bmi2);
+#elif defined(HUF_FORCE_DECOMPRESS_X2)
+    (void)dtd;
+    assert(dtd.tableType == 1);
+    return HUF_decompress4X2_usingDTable_internal(dst, maxDstSize, cSrc, cSrcSize, DTable, bmi2);
+#else
+    return dtd.tableType ? HUF_decompress4X2_usingDTable_internal(dst, maxDstSize, cSrc, cSrcSize, DTable, bmi2) :
+                           HUF_decompress4X1_usingDTable_internal(dst, maxDstSize, cSrc, cSrcSize, DTable, bmi2);
+#endif
+}
+
+size_t HUF_decompress4X_hufOnly_wksp_bmi2(HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize, void* workSpace, size_t wkspSize, int bmi2)
+{
+    /* validation checks */
+    if (dstSize == 0) return ERROR(dstSize_tooSmall);
+    if (cSrcSize == 0) return ERROR(corruption_detected);
+
+    {   U32 const algoNb = HUF_selectDecoder(dstSize, cSrcSize);
+#if defined(HUF_FORCE_DECOMPRESS_X1)
+        (void)algoNb;
+        assert(algoNb == 0);
+        return HUF_decompress4X1_DCtx_wksp_bmi2(dctx, dst, dstSize, cSrc, cSrcSize, workSpace, wkspSize, bmi2);
+#elif defined(HUF_FORCE_DECOMPRESS_X2)
+        (void)algoNb;
+        assert(algoNb == 1);
+        return HUF_decompress4X2_DCtx_wksp_bmi2(dctx, dst, dstSize, cSrc, cSrcSize, workSpace, wkspSize, bmi2);
+#else
+        return algoNb ? HUF_decompress4X2_DCtx_wksp_bmi2(dctx, dst, dstSize, cSrc, cSrcSize, workSpace, wkspSize, bmi2) :
+                        HUF_decompress4X1_DCtx_wksp_bmi2(dctx, dst, dstSize, cSrc, cSrcSize, workSpace, wkspSize, bmi2);
+#endif
+    }
+}