zstd-ruby 1.3.4.0 → 1.3.5.0

data/ext/zstdruby/libzstd/compress/zstd_opt.h

@@ -28,6 +28,13 @@ size_t ZSTD_compressBlock_btultra(
         ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
         ZSTD_compressionParameters const* cParams, void const* src, size_t srcSize);
 
+size_t ZSTD_compressBlock_btopt_dictMatchState(
+        ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
+        ZSTD_compressionParameters const* cParams, void const* src, size_t srcSize);
+size_t ZSTD_compressBlock_btultra_dictMatchState(
+        ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
+        ZSTD_compressionParameters const* cParams, void const* src, size_t srcSize);
+
 size_t ZSTD_compressBlock_btopt_extDict(
         ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
         ZSTD_compressionParameters const* cParams, void const* src, size_t srcSize);

data/ext/zstdruby/libzstd/compress/zstdmt_compress.c

@@ -37,18 +37,17 @@
 #define ZSTD_RESIZE_SEQPOOL 0
 
 /* ======   Debug   ====== */
-#if defined(ZSTD_DEBUG) && (ZSTD_DEBUG>=2)
+#if defined(DEBUGLEVEL) && (DEBUGLEVEL>=2) && !defined(_MSC_VER)
 
 #  include <stdio.h>
 #  include <unistd.h>
 #  include <sys/times.h>
-#  define DEBUGLOGRAW(l, ...) if (l<=ZSTD_DEBUG) { fprintf(stderr, __VA_ARGS__); }
 
 #  define DEBUG_PRINTHEX(l,p,n) {            \
     unsigned debug_u;                        \
     for (debug_u=0; debug_u<(n); debug_u++)  \
-        DEBUGLOGRAW(l, "%02X ", ((const unsigned char*)(p))[debug_u]); \
-    DEBUGLOGRAW(l, " \n");                   \
+        RAWLOG(l, "%02X ", ((const unsigned char*)(p))[debug_u]); \
+    RAWLOG(l, " \n");                        \
 }
 
 static unsigned long long GetCurrentClockTimeMicroseconds(void)
@@ -62,7 +61,7 @@ static unsigned long long GetCurrentClockTimeMicroseconds(void)
 
 #define MUTEX_WAIT_TIME_DLEVEL 6
 #define ZSTD_PTHREAD_MUTEX_LOCK(mutex) {          \
-    if (ZSTD_DEBUG >= MUTEX_WAIT_TIME_DLEVEL) {   \
+    if (DEBUGLEVEL >= MUTEX_WAIT_TIME_DLEVEL) {   \
         unsigned long long const beforeTime = GetCurrentClockTimeMicroseconds(); \
         ZSTD_pthread_mutex_lock(mutex);           \
         {   unsigned long long const afterTime = GetCurrentClockTimeMicroseconds(); \
@@ -160,6 +159,25 @@ static void ZSTDMT_setBufferSize(ZSTDMT_bufferPool* const bufPool, size_t const
     ZSTD_pthread_mutex_unlock(&bufPool->poolMutex);
 }
 
+
+static ZSTDMT_bufferPool* ZSTDMT_expandBufferPool(ZSTDMT_bufferPool* srcBufPool, U32 nbWorkers)
+{
+    unsigned const maxNbBuffers = 2*nbWorkers + 3;
+    if (srcBufPool==NULL) return NULL;
+    if (srcBufPool->totalBuffers >= maxNbBuffers) /* good enough */
+        return srcBufPool;
+    /* need a larger buffer pool */
+    {   ZSTD_customMem const cMem = srcBufPool->cMem;
+        size_t const bSize = srcBufPool->bufferSize;   /* forward parameters */
+        ZSTDMT_bufferPool* newBufPool;
+        ZSTDMT_freeBufferPool(srcBufPool);
+        newBufPool = ZSTDMT_createBufferPool(nbWorkers, cMem);
+        if (newBufPool==NULL) return newBufPool;
+        ZSTDMT_setBufferSize(newBufPool, bSize);
+        return newBufPool;
+    }
+}
+
 /** ZSTDMT_getBuffer() :
  *  assumption : bufPool must be valid
  * @return : a buffer, with start pointer and size
@@ -310,6 +328,10 @@ static void ZSTDMT_freeSeqPool(ZSTDMT_seqPool* seqPool)
     ZSTDMT_freeBufferPool(seqPool);
 }
 
+static ZSTDMT_seqPool* ZSTDMT_expandSeqPool(ZSTDMT_seqPool* pool, U32 nbWorkers)
+{
+    return ZSTDMT_expandBufferPool(pool, nbWorkers);
+}
 
 
 /* =====   CCtx Pool   ===== */
@@ -355,6 +377,18 @@ static ZSTDMT_CCtxPool* ZSTDMT_createCCtxPool(unsigned nbWorkers,
     return cctxPool;
 }
 
+static ZSTDMT_CCtxPool* ZSTDMT_expandCCtxPool(ZSTDMT_CCtxPool* srcPool,
+                                              unsigned nbWorkers)
+{
+    if (srcPool==NULL) return NULL;
+    if (nbWorkers <= srcPool->totalCCtx) return srcPool;   /* good enough */
+    /* need a larger cctx pool */
+    {   ZSTD_customMem const cMem = srcPool->cMem;
+        ZSTDMT_freeCCtxPool(srcPool);
+        return ZSTDMT_createCCtxPool(nbWorkers, cMem);
+    }
+}
+
 /* only works during initialization phase, not during compression */
 static size_t ZSTDMT_sizeof_CCtxPool(ZSTDMT_CCtxPool* cctxPool)
 {
@@ -425,12 +459,11 @@ typedef struct {
     ZSTD_window_t ldmWindow;  /* A thread-safe copy of ldmState.window */
 } serialState_t;
 
-static int ZSTDMT_serialState_reset(serialState_t* serialState, ZSTDMT_seqPool* seqPool, ZSTD_CCtx_params params)
+static int ZSTDMT_serialState_reset(serialState_t* serialState, ZSTDMT_seqPool* seqPool, ZSTD_CCtx_params params, size_t jobSize)
 {
     /* Adjust parameters */
     if (params.ldmParams.enableLdm) {
         DEBUGLOG(4, "LDM window size = %u KB", (1U << params.cParams.windowLog) >> 10);
-        params.ldmParams.windowLog = params.cParams.windowLog;
         ZSTD_ldm_adjustParameters(&params.ldmParams, &params.cParams);
         assert(params.ldmParams.hashLog >= params.ldmParams.bucketSizeLog);
         assert(params.ldmParams.hashEveryLog < 32);
@@ -453,7 +486,7 @@ static int ZSTDMT_serialState_reset(serialState_t* serialState, ZSTDMT_seqPool*
             serialState->params.ldmParams.hashLog -
             serialState->params.ldmParams.bucketSizeLog;
         /* Size the seq pool tables */
-        ZSTDMT_setNbSeq(seqPool, ZSTD_ldm_getMaxNbSeq(params.ldmParams, params.jobSize));
+        ZSTDMT_setNbSeq(seqPool, ZSTD_ldm_getMaxNbSeq(params.ldmParams, jobSize));
         /* Reset the window */
         ZSTD_window_clear(&serialState->ldmState.window);
         serialState->ldmWindow = serialState->ldmState.window;
@@ -473,6 +506,7 @@ static int ZSTDMT_serialState_reset(serialState_t* serialState, ZSTDMT_seqPool*
         memset(serialState->ldmState.bucketOffsets, 0, bucketSize);
     }
     serialState->params = params;
+    serialState->params.jobSize = (U32)jobSize;
     return 0;
 }
 
@@ -514,6 +548,7 @@ static void ZSTDMT_serialState_update(serialState_t* serialState,
             size_t error;
             assert(seqStore.seq != NULL && seqStore.pos == 0 &&
                    seqStore.size == 0 && seqStore.capacity > 0);
+            assert(src.size <= serialState->params.jobSize);
             ZSTD_window_update(&serialState->ldmState.window, src.start, src.size);
             error = ZSTD_ldm_generateSequences(
                 &serialState->ldmState, &seqStore,
@@ -602,13 +637,6 @@ void ZSTDMT_compressionJob(void* jobDescription)
     rawSeqStore_t rawSeqStore = ZSTDMT_getSeq(job->seqPool);
     buffer_t dstBuff = job->dstBuff;
 
-    /* Don't compute the checksum for chunks, since we compute it externally,
-     * but write it in the header.
-     */
-    if (job->jobID != 0) jobParams.fParams.checksumFlag = 0;
-    /* Don't run LDM for the chunks, since we handle it externally */
-    jobParams.ldmParams.enableLdm = 0;
-
     /* ressources */
     if (cctx==NULL) {
         job->cSize = ERROR(memory_allocation);
@@ -622,10 +650,22 @@ void ZSTDMT_compressionJob(void* jobDescription)
         }
         job->dstBuff = dstBuff;   /* this value can be read in ZSTDMT_flush, when it copies the whole job */
     }
+    if (jobParams.ldmParams.enableLdm && rawSeqStore.seq == NULL) {
+        job->cSize = ERROR(memory_allocation);
+        goto _endJob;
+    }
+
+    /* Don't compute the checksum for chunks, since we compute it externally,
+     * but write it in the header.
+     */
+    if (job->jobID != 0) jobParams.fParams.checksumFlag = 0;
+    /* Don't run LDM for the chunks, since we handle it externally */
+    jobParams.ldmParams.enableLdm = 0;
+
 
     /* init */
     if (job->cdict) {
-        size_t const initError = ZSTD_compressBegin_advanced_internal(cctx, NULL, 0, ZSTD_dct_auto, job->cdict, jobParams, job->fullFrameSize);
+        size_t const initError = ZSTD_compressBegin_advanced_internal(cctx, NULL, 0, ZSTD_dct_auto, ZSTD_dtlm_fast, job->cdict, jobParams, job->fullFrameSize);
         assert(job->firstJob);  /* only allowed for first job */
         if (ZSTD_isError(initError)) { job->cSize = initError; goto _endJob; }
     } else {  /* srcStart points at reloaded section */
@@ -637,6 +677,7 @@ void ZSTDMT_compressionJob(void* jobDescription)
         }   }
         {   size_t const initError = ZSTD_compressBegin_advanced_internal(cctx,
                                         job->prefix.start, job->prefix.size, ZSTD_dct_rawContent, /* load dictionary in "content-only" mode (no header analysis) */
+                                        ZSTD_dtlm_fast,
                                         NULL, /*cdict*/
                                         jobParams, pledgedSrcSize);
             if (ZSTD_isError(initError)) {
@@ -745,9 +786,9 @@ struct ZSTDMT_CCtx_s {
     ZSTD_CCtx_params params;
     size_t targetSectionSize;
     size_t targetPrefixSize;
-    roundBuff_t roundBuff;
+    int jobReady;        /* 1 => one job is already prepared, but pool has shortage of workers. Don't create a new job. */
     inBuff_t inBuff;
-    int jobReady;        /* 1 => one job is already prepared, but pool has shortage of workers. Don't create another one. */
+    roundBuff_t roundBuff;
     serialState_t serial;
     unsigned singleBlockingThread;
     unsigned jobIDMask;
@@ -798,6 +839,20 @@ static ZSTDMT_jobDescription* ZSTDMT_createJobsTable(U32* nbJobsPtr, ZSTD_custom
     return jobTable;
 }
 
+static size_t ZSTDMT_expandJobsTable (ZSTDMT_CCtx* mtctx, U32 nbWorkers) {
+    U32 nbJobs = nbWorkers + 2;
+    if (nbJobs > mtctx->jobIDMask+1) {  /* need more job capacity */
+        ZSTDMT_freeJobsTable(mtctx->jobs, mtctx->jobIDMask+1, mtctx->cMem);
+        mtctx->jobIDMask = 0;
+        mtctx->jobs = ZSTDMT_createJobsTable(&nbJobs, mtctx->cMem);
+        if (mtctx->jobs==NULL) return ERROR(memory_allocation);
+        assert((nbJobs != 0) && ((nbJobs & (nbJobs - 1)) == 0));  /* ensure nbJobs is a power of 2 */
+        mtctx->jobIDMask = nbJobs - 1;
+    }
+    return 0;
+}
+
+
 /* ZSTDMT_CCtxParam_setNbWorkers():
  * Internal use only */
 size_t ZSTDMT_CCtxParam_setNbWorkers(ZSTD_CCtx_params* params, unsigned nbWorkers)
@@ -924,6 +979,8 @@ size_t ZSTDMT_CCtxParam_setMTCtxParameter(ZSTD_CCtx_params* params,
         if ( (value > 0)  /* value==0 => automatic job size */
            & (value < ZSTDMT_JOBSIZE_MIN) )
             value = ZSTDMT_JOBSIZE_MIN;
+        if (value > ZSTDMT_JOBSIZE_MAX)
+            value = ZSTDMT_JOBSIZE_MAX;
         params->jobSize = value;
         return value;
     case ZSTDMT_p_overlapSectionLog :
@@ -950,6 +1007,21 @@ size_t ZSTDMT_setMTCtxParameter(ZSTDMT_CCtx* mtctx, ZSTDMT_parameter parameter,
     }
 }
 
+size_t ZSTDMT_getMTCtxParameter(ZSTDMT_CCtx* mtctx, ZSTDMT_parameter parameter, unsigned* value)
+{
+    switch (parameter) {
+    case ZSTDMT_p_jobSize:
+        *value = mtctx->params.jobSize;
+        break;
+    case ZSTDMT_p_overlapSectionLog:
+        *value = mtctx->params.overlapSizeLog;
+        break;
+    default:
+        return ERROR(parameter_unsupported);
+    }
+    return 0;
+}
+
 /* Sets parameters relevant to the compression job,
  * initializing others to default values. */
 static ZSTD_CCtx_params ZSTDMT_initJobCCtxParams(ZSTD_CCtx_params const params)
@@ -960,11 +1032,28 @@ static ZSTD_CCtx_params ZSTDMT_initJobCCtxParams(ZSTD_CCtx_params const params)
     jobParams.cParams = params.cParams;
     jobParams.fParams = params.fParams;
     jobParams.compressionLevel = params.compressionLevel;
-    jobParams.disableLiteralCompression = params.disableLiteralCompression;
 
     return jobParams;
 }
 
+
+/* ZSTDMT_resize() :
+ * @return : error code if fails, 0 on success */
+static size_t ZSTDMT_resize(ZSTDMT_CCtx* mtctx, unsigned nbWorkers)
+{
+    if (POOL_resize(mtctx->factory, nbWorkers)) return ERROR(memory_allocation);
+    CHECK_F( ZSTDMT_expandJobsTable(mtctx, nbWorkers) );
+    mtctx->bufPool = ZSTDMT_expandBufferPool(mtctx->bufPool, nbWorkers);
+    if (mtctx->bufPool == NULL) return ERROR(memory_allocation);
+    mtctx->cctxPool = ZSTDMT_expandCCtxPool(mtctx->cctxPool, nbWorkers);
+    if (mtctx->cctxPool == NULL) return ERROR(memory_allocation);
+    mtctx->seqPool = ZSTDMT_expandSeqPool(mtctx->seqPool, nbWorkers);
+    if (mtctx->seqPool == NULL) return ERROR(memory_allocation);
+    ZSTDMT_CCtxParam_setNbWorkers(&mtctx->params, nbWorkers);
+    return 0;
+}
+
+
 /*! 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. */
@@ -981,15 +1070,6 @@ void ZSTDMT_updateCParams_whileCompressing(ZSTDMT_CCtx* mtctx, const ZSTD_CCtx_p
     }
 }
 
-/* ZSTDMT_getNbWorkers():
- * @return nb threads currently active in mtctx.
- * mtctx must be valid */
-unsigned ZSTDMT_getNbWorkers(const ZSTDMT_CCtx* mtctx)
-{
-    assert(mtctx != NULL);
-    return mtctx->params.nbWorkers;
-}
-
 /* ZSTDMT_getFrameProgression():
  * tells how much data has been consumed (input) and produced (output) for current frame.
  * able to count progression inside worker threads.
@@ -1087,18 +1167,10 @@ static size_t ZSTDMT_compress_advanced_internal(
 
     assert(avgJobSize >= 256 KB);  /* condition for ZSTD_compressBound(A) + ZSTD_compressBound(B) <= ZSTD_compressBound(A+B), required to compress directly into Dst (no additional buffer) */
     ZSTDMT_setBufferSize(mtctx->bufPool, ZSTD_compressBound(avgJobSize) );
-    if (ZSTDMT_serialState_reset(&mtctx->serial, mtctx->seqPool, params))
+    if (ZSTDMT_serialState_reset(&mtctx->serial, mtctx->seqPool, params, avgJobSize))
         return ERROR(memory_allocation);
 
-    if (nbJobs > mtctx->jobIDMask+1) {  /* enlarge job table */
-        U32 jobsTableSize = nbJobs;
-        ZSTDMT_freeJobsTable(mtctx->jobs, mtctx->jobIDMask+1, mtctx->cMem);
-        mtctx->jobIDMask = 0;
-        mtctx->jobs = ZSTDMT_createJobsTable(&jobsTableSize, mtctx->cMem);
-        if (mtctx->jobs==NULL) return ERROR(memory_allocation);
-        assert((jobsTableSize != 0) && ((jobsTableSize & (jobsTableSize - 1)) == 0));  /* ensure jobsTableSize is a power of 2 */
-        mtctx->jobIDMask = jobsTableSize - 1;
-    }
+    CHECK_F( ZSTDMT_expandJobsTable(mtctx, nbJobs) );  /* only expands if necessary */
 
     {   unsigned u;
         for (u=0; u<nbJobs; u++) {
@@ -1221,17 +1293,18 @@ size_t ZSTDMT_initCStream_internal(
         const ZSTD_CDict* cdict, ZSTD_CCtx_params params,
         unsigned long long pledgedSrcSize)
 {
-    DEBUGLOG(4, "ZSTDMT_initCStream_internal (pledgedSrcSize=%u, nbWorkers=%u, cctxPool=%u, disableLiteralCompression=%i)",
-                (U32)pledgedSrcSize, params.nbWorkers, mtctx->cctxPool->totalCCtx, params.disableLiteralCompression);
-    /* params are supposed to be fully validated at this point */
+    DEBUGLOG(4, "ZSTDMT_initCStream_internal (pledgedSrcSize=%u, nbWorkers=%u, cctxPool=%u)",
+                (U32)pledgedSrcSize, params.nbWorkers, mtctx->cctxPool->totalCCtx);
+
+    /* params supposed partially fully validated at this point */
     assert(!ZSTD_isError(ZSTD_checkCParams(params.cParams)));
     assert(!((dict) && (cdict)));  /* either dict or cdict, not both */
-    assert(mtctx->cctxPool->totalCCtx == params.nbWorkers);
 
     /* init */
-    if (params.jobSize == 0) {
-        params.jobSize = 1U << ZSTDMT_computeTargetJobLog(params);
-    }
+    if (params.nbWorkers != mtctx->params.nbWorkers)
+        CHECK_F( ZSTDMT_resize(mtctx, params.nbWorkers) );
+
+    if (params.jobSize > 0 && params.jobSize < ZSTDMT_JOBSIZE_MIN) params.jobSize = ZSTDMT_JOBSIZE_MIN;
     if (params.jobSize > ZSTDMT_JOBSIZE_MAX) params.jobSize = ZSTDMT_JOBSIZE_MAX;
 
     mtctx->singleBlockingThread = (pledgedSrcSize <= ZSTDMT_JOBSIZE_MIN);  /* do not trigger multi-threading when srcSize is too small */
@@ -1270,7 +1343,9 @@ size_t ZSTDMT_initCStream_internal(
     mtctx->targetPrefixSize = (size_t)1 << ZSTDMT_computeOverlapLog(params);
     DEBUGLOG(4, "overlapLog=%u => %u KB", params.overlapSizeLog, (U32)(mtctx->targetPrefixSize>>10));
     mtctx->targetSectionSize = params.jobSize;
-    if (mtctx->targetSectionSize < ZSTDMT_JOBSIZE_MIN) mtctx->targetSectionSize = ZSTDMT_JOBSIZE_MIN;
+    if (mtctx->targetSectionSize == 0) {
+        mtctx->targetSectionSize = 1ULL << ZSTDMT_computeTargetJobLog(params);
+    }
     if (mtctx->targetSectionSize < mtctx->targetPrefixSize) mtctx->targetSectionSize = mtctx->targetPrefixSize;  /* job size must be >= overlap size */
     DEBUGLOG(4, "Job Size : %u KB (note : set to %u)", (U32)(mtctx->targetSectionSize>>10), params.jobSize);
     DEBUGLOG(4, "inBuff Size : %u KB", (U32)(mtctx->targetSectionSize>>10));
@@ -1312,7 +1387,7 @@ size_t ZSTDMT_initCStream_internal(
     mtctx->allJobsCompleted = 0;
     mtctx->consumed = 0;
     mtctx->produced = 0;
-    if (ZSTDMT_serialState_reset(&mtctx->serial, mtctx->seqPool, params))
+    if (ZSTDMT_serialState_reset(&mtctx->serial, mtctx->seqPool, params, mtctx->targetSectionSize))
         return ERROR(memory_allocation);
     return 0;
 }

data/ext/zstdruby/libzstd/compress/zstdmt_compress.h

@@ -95,6 +95,11 @@ typedef enum {
  * @return : 0, or an error code (which can be tested using ZSTD_isError()) */
 ZSTDLIB_API size_t ZSTDMT_setMTCtxParameter(ZSTDMT_CCtx* mtctx, ZSTDMT_parameter parameter, unsigned value);
 
+/* ZSTDMT_getMTCtxParameter() :
+ * Query the ZSTDMT_CCtx for a parameter value.
+ * @return : 0, or an error code (which can be tested using ZSTD_isError()) */
+ZSTDLIB_API size_t ZSTDMT_getMTCtxParameter(ZSTDMT_CCtx* mtctx, ZSTDMT_parameter parameter, unsigned* value);
+
 
 /*! ZSTDMT_compressStream_generic() :
  *  Combines ZSTDMT_compressStream() with optional ZSTDMT_flushStream() or ZSTDMT_endStream()
@@ -126,11 +131,6 @@ size_t ZSTDMT_CCtxParam_setNbWorkers(ZSTD_CCtx_params* params, unsigned nbWorker
  *  New parameters will be applied to next compression job. */
 void ZSTDMT_updateCParams_whileCompressing(ZSTDMT_CCtx* mtctx, const ZSTD_CCtx_params* cctxParams);
 
-/* ZSTDMT_getNbWorkers():
- * @return nb threads currently active in mtctx.
- * mtctx must be valid */
-unsigned ZSTDMT_getNbWorkers(const ZSTDMT_CCtx* mtctx);
-
 /* ZSTDMT_getFrameProgression():
  * tells how much data has been consumed (input) and produced (output) for current frame.
  * able to count progression inside worker threads.

data/ext/zstdruby/libzstd/decompress/huf_decompress.c

@@ -1,6 +1,7 @@
 /* ******************************************************************
-   Huffman decoder, part of New Generation Entropy library
-   Copyright (C) 2013-2016, Yann Collet.
+   huff0 huffman decoder,
+   part of Finite State Entropy library
+   Copyright (C) 2013-present, Yann Collet.
 
    BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php)
 
@@ -29,16 +30,15 @@
 
     You can contact the author at :
     - FSE+HUF source repository : https://github.com/Cyan4973/FiniteStateEntropy
-    - Public forum : https://groups.google.com/forum/#!forum/lz4c
 ****************************************************************** */
 
 /* **************************************************************
 *  Dependencies
 ****************************************************************/
 #include <string.h>     /* memcpy, memset */
-#include "bitstream.h"  /* BIT_* */
 #include "compiler.h"
-#include "fse.h"        /* header compression */
+#include "bitstream.h"  /* BIT_* */
+#include "fse.h"        /* to compress headers */
 #define HUF_STATIC_LINKING_ONLY
 #include "huf.h"
 #include "error_private.h"
@@ -48,7 +48,6 @@
 *  Error Management
 ****************************************************************/
 #define HUF_isError ERR_isError
-#define HUF_STATIC_ASSERT(c) { enum { HUF_static_assert = 1/(int)(!!(c)) }; }   /* use only *after* variable declarations */
 #define CHECK_F(f) { size_t const err_ = (f); if (HUF_isError(err_)) return err_; }
 
 
@@ -75,15 +74,15 @@ static DTableDesc HUF_getDTableDesc(const HUF_DTable* table)
 /*-***************************/
 /*  single-symbol decoding   */
 /*-***************************/
-typedef struct { BYTE byte; BYTE nbBits; } HUF_DEltX2;   /* single-symbol decoding */
+typedef struct { BYTE byte; BYTE nbBits; } HUF_DEltX1;   /* single-symbol decoding */
 
-size_t HUF_readDTableX2_wksp(HUF_DTable* DTable, const void* src, size_t srcSize, void* workSpace, size_t wkspSize)
+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_DEltX2* const dt = (HUF_DEltX2*)dtPtr;
+    HUF_DEltX1* const dt = (HUF_DEltX1*)dtPtr;
 
     U32* rankVal;
     BYTE* huffWeight;
@@ -96,7 +95,7 @@ size_t HUF_readDTableX2_wksp(HUF_DTable* DTable, const void* src, size_t srcSize
 
     if ((spaceUsed32 << 2) > wkspSize) return ERROR(tableLog_tooLarge);
 
-    HUF_STATIC_ASSERT(sizeof(DTableDesc) == sizeof(HUF_DTable));
+    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);
@@ -124,7 +123,7 @@ size_t HUF_readDTableX2_wksp(HUF_DTable* DTable, const void* src, size_t srcSize
             U32 const w = huffWeight[n];
             U32 const length = (1 << w) >> 1;
             U32 u;
-            HUF_DEltX2 D;
+            HUF_DEltX1 D;
             D.byte = (BYTE)n; D.nbBits = (BYTE)(tableLog + 1 - w);
             for (u = rankVal[w]; u < rankVal[w] + length; u++)
                 dt[u] = D;
@@ -134,17 +133,15 @@ size_t HUF_readDTableX2_wksp(HUF_DTable* DTable, const void* src, size_t srcSize
     return iSize;
 }
 
-size_t HUF_readDTableX2(HUF_DTable* DTable, const void* src, size_t srcSize)
+size_t HUF_readDTableX1(HUF_DTable* DTable, const void* src, size_t srcSize)
 {
     U32 workSpace[HUF_DECOMPRESS_WORKSPACE_SIZE_U32];
-    return HUF_readDTableX2_wksp(DTable, src, srcSize,
+    return HUF_readDTableX1_wksp(DTable, src, srcSize,
                                  workSpace, sizeof(workSpace));
 }
 
-typedef struct { U16 sequence; BYTE nbBits; BYTE length; } HUF_DEltX4;  /* double-symbols decoding */
-
 FORCE_INLINE_TEMPLATE BYTE
-HUF_decodeSymbolX2(BIT_DStream_t* Dstream, const HUF_DEltX2* dt, const U32 dtLog)
+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;
@@ -152,44 +149,44 @@ HUF_decodeSymbolX2(BIT_DStream_t* Dstream, const HUF_DEltX2* dt, const U32 dtLog
     return c;
 }
 
-#define HUF_DECODE_SYMBOLX2_0(ptr, DStreamPtr) \
-    *ptr++ = HUF_decodeSymbolX2(DStreamPtr, dt, dtLog)
+#define HUF_DECODE_SYMBOLX1_0(ptr, DStreamPtr) \
+    *ptr++ = HUF_decodeSymbolX1(DStreamPtr, dt, dtLog)
 
-#define HUF_DECODE_SYMBOLX2_1(ptr, DStreamPtr)  \
+#define HUF_DECODE_SYMBOLX1_1(ptr, DStreamPtr)  \
     if (MEM_64bits() || (HUF_TABLELOG_MAX<=12)) \
-        HUF_DECODE_SYMBOLX2_0(ptr, DStreamPtr)
+        HUF_DECODE_SYMBOLX1_0(ptr, DStreamPtr)
 
-#define HUF_DECODE_SYMBOLX2_2(ptr, DStreamPtr) \
+#define HUF_DECODE_SYMBOLX1_2(ptr, DStreamPtr) \
     if (MEM_64bits()) \
-        HUF_DECODE_SYMBOLX2_0(ptr, DStreamPtr)
+        HUF_DECODE_SYMBOLX1_0(ptr, DStreamPtr)
 
 HINT_INLINE size_t
-HUF_decodeStreamX2(BYTE* p, BIT_DStream_t* const bitDPtr, BYTE* const pEnd, const HUF_DEltX2* const dt, const U32 dtLog)
+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_SYMBOLX2_2(p, bitDPtr);
-        HUF_DECODE_SYMBOLX2_1(p, bitDPtr);
-        HUF_DECODE_SYMBOLX2_2(p, bitDPtr);
-        HUF_DECODE_SYMBOLX2_0(p, bitDPtr);
+        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_SYMBOLX2_0(p, bitDPtr);
+            HUF_DECODE_SYMBOLX1_0(p, bitDPtr);
 
     /* no more data to retrieve from bitstream, no need to reload */
     while (p < pEnd)
-        HUF_DECODE_SYMBOLX2_0(p, bitDPtr);
+        HUF_DECODE_SYMBOLX1_0(p, bitDPtr);
 
     return pEnd-pStart;
 }
 
 FORCE_INLINE_TEMPLATE size_t
-HUF_decompress1X2_usingDTable_internal_body(
+HUF_decompress1X1_usingDTable_internal_body(
           void* dst,  size_t dstSize,
     const void* cSrc, size_t cSrcSize,
     const HUF_DTable* DTable)
@@ -197,14 +194,14 @@ HUF_decompress1X2_usingDTable_internal_body(
     BYTE* op = (BYTE*)dst;
     BYTE* const oend = op + dstSize;
     const void* dtPtr = DTable + 1;
-    const HUF_DEltX2* const dt = (const HUF_DEltX2*)dtPtr;
+    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_decodeStreamX2(op, &bitD, oend, dt, dtLog);
+    HUF_decodeStreamX1(op, &bitD, oend, dt, dtLog);
 
     if (!BIT_endOfDStream(&bitD)) return ERROR(corruption_detected);
 
@@ -212,7 +209,7 @@ HUF_decompress1X2_usingDTable_internal_body(
 }
 
 FORCE_INLINE_TEMPLATE size_t
-HUF_decompress4X2_usingDTable_internal_body(
+HUF_decompress4X1_usingDTable_internal_body(
           void* dst,  size_t dstSize,
     const void* cSrc, size_t cSrcSize,
     const HUF_DTable* DTable)
@@ -224,7 +221,7 @@ HUF_decompress4X2_usingDTable_internal_body(
         BYTE* const ostart = (BYTE*) dst;
         BYTE* const oend = ostart + dstSize;
         const void* const dtPtr = DTable + 1;
-        const HUF_DEltX2* const dt = (const HUF_DEltX2*)dtPtr;
+        const HUF_DEltX1* const dt = (const HUF_DEltX1*)dtPtr;
 
         /* Init */
         BIT_DStream_t bitD1;
@@ -260,22 +257,22 @@ HUF_decompress4X2_usingDTable_internal_body(
         /* up to 16 symbols per loop (4 symbols per stream) in 64-bit mode */
         endSignal = BIT_reloadDStream(&bitD1) | BIT_reloadDStream(&bitD2) | BIT_reloadDStream(&bitD3) | BIT_reloadDStream(&bitD4);
         while ( (endSignal==BIT_DStream_unfinished) && (op4<(oend-3)) ) {
-            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);
+            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);
             BIT_reloadDStream(&bitD1);
             BIT_reloadDStream(&bitD2);
             BIT_reloadDStream(&bitD3);
@@ -291,191 +288,10 @@ HUF_decompress4X2_usingDTable_internal_body(
         /* note : op4 supposed 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;
-    }
-}
-
-
-FORCE_INLINE_TEMPLATE U32
-HUF_decodeSymbolX4(void* op, BIT_DStream_t* DStream, const HUF_DEltX4* 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_decodeLastSymbolX4(void* op, BIT_DStream_t* DStream, const HUF_DEltX4* 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_SYMBOLX4_0(ptr, DStreamPtr) \
-    ptr += HUF_decodeSymbolX4(ptr, DStreamPtr, dt, dtLog)
-
-#define HUF_DECODE_SYMBOLX4_1(ptr, DStreamPtr) \
-    if (MEM_64bits() || (HUF_TABLELOG_MAX<=12)) \
-        ptr += HUF_decodeSymbolX4(ptr, DStreamPtr, dt, dtLog)
-
-#define HUF_DECODE_SYMBOLX4_2(ptr, DStreamPtr) \
-    if (MEM_64bits()) \
-        ptr += HUF_decodeSymbolX4(ptr, DStreamPtr, dt, dtLog)
-
-HINT_INLINE size_t
-HUF_decodeStreamX4(BYTE* p, BIT_DStream_t* bitDPtr, BYTE* const pEnd,
-                const HUF_DEltX4* 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_SYMBOLX4_2(p, bitDPtr);
-        HUF_DECODE_SYMBOLX4_1(p, bitDPtr);
-        HUF_DECODE_SYMBOLX4_2(p, bitDPtr);
-        HUF_DECODE_SYMBOLX4_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_SYMBOLX4_0(p, bitDPtr);
-
-    while (p <= pEnd-2)
-        HUF_DECODE_SYMBOLX4_0(p, bitDPtr);   /* no need to reload : reached the end of DStream */
-
-    if (p < pEnd)
-        p += HUF_decodeLastSymbolX4(p, bitDPtr, dt, dtLog);
-
-    return p-pStart;
-}
-
-FORCE_INLINE_TEMPLATE size_t
-HUF_decompress1X4_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_DEltX4* const dt = (const HUF_DEltX4*)dtPtr;
-        DTableDesc const dtd = HUF_getDTableDesc(DTable);
-        HUF_decodeStreamX4(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_decompress4X4_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;
-        const void* const dtPtr = DTable+1;
-        const HUF_DEltX4* const dt = (const HUF_DEltX4*)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;
-        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) */
-        endSignal = BIT_reloadDStream(&bitD1) | BIT_reloadDStream(&bitD2) | BIT_reloadDStream(&bitD3) | BIT_reloadDStream(&bitD4);
-        for ( ; (endSignal==BIT_DStream_unfinished) & (op4<(oend-(sizeof(bitD4.bitContainer)-1))) ; ) {
-            HUF_DECODE_SYMBOLX4_2(op1, &bitD1);
-            HUF_DECODE_SYMBOLX4_2(op2, &bitD2);
-            HUF_DECODE_SYMBOLX4_2(op3, &bitD3);
-            HUF_DECODE_SYMBOLX4_2(op4, &bitD4);
-            HUF_DECODE_SYMBOLX4_1(op1, &bitD1);
-            HUF_DECODE_SYMBOLX4_1(op2, &bitD2);
-            HUF_DECODE_SYMBOLX4_1(op3, &bitD3);
-            HUF_DECODE_SYMBOLX4_1(op4, &bitD4);
-            HUF_DECODE_SYMBOLX4_2(op1, &bitD1);
-            HUF_DECODE_SYMBOLX4_2(op2, &bitD2);
-            HUF_DECODE_SYMBOLX4_2(op3, &bitD3);
-            HUF_DECODE_SYMBOLX4_2(op4, &bitD4);
-            HUF_DECODE_SYMBOLX4_0(op1, &bitD1);
-            HUF_DECODE_SYMBOLX4_0(op2, &bitD2);
-            HUF_DECODE_SYMBOLX4_0(op3, &bitD3);
-            HUF_DECODE_SYMBOLX4_0(op4, &bitD4);
-
-            endSignal = BIT_reloadDStream(&bitD1) | BIT_reloadDStream(&bitD2) | BIT_reloadDStream(&bitD3) | BIT_reloadDStream(&bitD4);
-        }
-
-        /* 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_decodeStreamX4(op1, &bitD1, opStart2, dt, dtLog);
-        HUF_decodeStreamX4(op2, &bitD2, opStart3, dt, dtLog);
-        HUF_decodeStreamX4(op3, &bitD3, opStart4, dt, dtLog);
-        HUF_decodeStreamX4(op4, &bitD4, oend,     dt, dtLog);
+        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);
@@ -493,7 +309,7 @@ typedef size_t (*HUF_decompress_usingDTable_t)(void *dst, size_t dstSize,
                                                const HUF_DTable *DTable);
 #if DYNAMIC_BMI2
 
-#define X(fn)                                                               \
+#define HUF_DGEN(fn)                                                               \
                                                                             \
     static size_t fn##_default(                                             \
                   void* dst,  size_t dstSize,                               \
@@ -522,7 +338,7 @@ typedef size_t (*HUF_decompress_usingDTable_t)(void *dst, size_t dstSize,
 
 #else
 
-#define X(fn)                                                               \
+#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)   \
     {                                                                       \
@@ -532,112 +348,114 @@ typedef size_t (*HUF_decompress_usingDTable_t)(void *dst, size_t dstSize,
 
 #endif
 
-X(HUF_decompress1X2_usingDTable_internal)
-X(HUF_decompress4X2_usingDTable_internal)
-X(HUF_decompress1X4_usingDTable_internal)
-X(HUF_decompress4X4_usingDTable_internal)
+HUF_DGEN(HUF_decompress1X1_usingDTable_internal)
+HUF_DGEN(HUF_decompress4X1_usingDTable_internal)
 
-#undef X
 
 
-size_t HUF_decompress1X2_usingDTable(
+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_decompress1X2_usingDTable_internal(dst, dstSize, cSrc, cSrcSize, DTable, /* bmi2 */ 0);
+    return HUF_decompress1X1_usingDTable_internal(dst, dstSize, cSrc, cSrcSize, DTable, /* bmi2 */ 0);
 }
 
-size_t HUF_decompress1X2_DCtx_wksp(HUF_DTable* DCtx, void* dst, size_t dstSize,
+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_readDTableX2_wksp(DCtx, cSrc, cSrcSize, workSpace, wkspSize);
+    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_decompress1X2_usingDTable_internal(dst, dstSize, ip, cSrcSize, DCtx, /* bmi2 */ 0);
+    return HUF_decompress1X1_usingDTable_internal(dst, dstSize, ip, cSrcSize, DCtx, /* bmi2 */ 0);
 }
 
 
-size_t HUF_decompress1X2_DCtx(HUF_DTable* DCtx, void* dst, size_t dstSize,
+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_decompress1X2_DCtx_wksp(DCtx, dst, dstSize, cSrc, cSrcSize,
+    return HUF_decompress1X1_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)
+size_t HUF_decompress1X1 (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);
+    HUF_CREATE_STATIC_DTABLEX1(DTable, HUF_TABLELOG_MAX);
+    return HUF_decompress1X1_DCtx (DTable, dst, dstSize, cSrc, cSrcSize);
 }
 
-size_t HUF_decompress4X2_usingDTable(
+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_decompress4X2_usingDTable_internal(dst, dstSize, cSrc, cSrcSize, DTable, /* bmi2 */ 0);
+    return HUF_decompress4X1_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,
+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_readDTableX2_wksp (dctx, cSrc, cSrcSize,
+    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_decompress4X2_usingDTable_internal(dst, dstSize, ip, cSrcSize, dctx, bmi2);
+    return HUF_decompress4X1_usingDTable_internal(dst, dstSize, ip, cSrcSize, dctx, bmi2);
 }
 
-size_t HUF_decompress4X2_DCtx_wksp(HUF_DTable* dctx, void* dst, size_t dstSize,
+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_decompress4X2_DCtx_wksp_bmi2(dctx, dst, dstSize, cSrc, cSrcSize, workSpace, wkspSize, 0);
+    return HUF_decompress4X1_DCtx_wksp_bmi2(dctx, dst, dstSize, cSrc, cSrcSize, workSpace, wkspSize, 0);
 }
 
 
-size_t HUF_decompress4X2_DCtx (HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize)
+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_decompress4X2_DCtx_wksp(dctx, dst, dstSize, cSrc, cSrcSize,
+    return HUF_decompress4X1_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)
+size_t HUF_decompress4X1 (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);
+    HUF_CREATE_STATIC_DTABLEX1(DTable, HUF_TABLELOG_MAX);
+    return HUF_decompress4X1_DCtx(DTable, dst, dstSize, cSrc, cSrcSize);
 }
 
 
 /* *************************/
 /* 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_fillDTableX4Level2() :
+
+/* HUF_fillDTableX2Level2() :
  * `rankValOrigin` must be a table of at least (HUF_TABLELOG_MAX + 1) U32 */
-static void HUF_fillDTableX4Level2(HUF_DEltX4* DTable, U32 sizeLog, const U32 consumed,
+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_DEltX4 DElt;
+    HUF_DEltX2 DElt;
     U32 rankVal[HUF_TABLELOG_MAX + 1];
 
     /* get pre-calculated rankVal */
@@ -672,10 +490,8 @@ static void HUF_fillDTableX4Level2(HUF_DEltX4* DTable, U32 sizeLog, const U32 co
     }   }
 }
 
-typedef U32 rankValCol_t[HUF_TABLELOG_MAX + 1];
-typedef rankValCol_t rankVal_t[HUF_TABLELOG_MAX];
 
-static void HUF_fillDTableX4(HUF_DEltX4* DTable, const U32 targetLog,
+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)
@@ -700,12 +516,12 @@ static void HUF_fillDTableX4(HUF_DEltX4* DTable, const U32 targetLog,
             int minWeight = nbBits + scaleLog;
             if (minWeight < 1) minWeight = 1;
             sortedRank = rankStart[minWeight];
-            HUF_fillDTableX4Level2(DTable+start, targetLog-nbBits, nbBits,
+            HUF_fillDTableX2Level2(DTable+start, targetLog-nbBits, nbBits,
                            rankValOrigin[nbBits], minWeight,
                            sortedList+sortedRank, sortedListSize-sortedRank,
                            nbBitsBaseline, symbol);
         } else {
-            HUF_DEltX4 DElt;
+            HUF_DEltX2 DElt;
             MEM_writeLE16(&(DElt.sequence), symbol);
             DElt.nbBits = (BYTE)(nbBits);
             DElt.length = 1;
@@ -717,7 +533,7 @@ static void HUF_fillDTableX4(HUF_DEltX4* DTable, const U32 targetLog,
     }
 }
 
-size_t HUF_readDTableX4_wksp(HUF_DTable* DTable, const void* src,
+size_t HUF_readDTableX2_wksp(HUF_DTable* DTable, const void* src,
                              size_t srcSize, void* workSpace,
                              size_t wkspSize)
 {
@@ -726,7 +542,7 @@ size_t HUF_readDTableX4_wksp(HUF_DTable* DTable, const void* src,
     U32 const maxTableLog = dtd.maxTableLog;
     size_t iSize;
     void* dtPtr = DTable+1;   /* force compiler to avoid strict-aliasing */
-    HUF_DEltX4* const dt = (HUF_DEltX4*)dtPtr;
+    HUF_DEltX2* const dt = (HUF_DEltX2*)dtPtr;
     U32 *rankStart;
 
     rankValCol_t* rankVal;
@@ -752,7 +568,7 @@ size_t HUF_readDTableX4_wksp(HUF_DTable* DTable, const void* src,
     rankStart = rankStart0 + 1;
     memset(rankStats, 0, sizeof(U32) * (2 * HUF_TABLELOG_MAX + 2 + 1));
 
-    HUF_STATIC_ASSERT(sizeof(HUF_DEltX4) == sizeof(HUF_DTable));   /* if compiler fails here, assertion is wrong */
+    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 ... */
 
@@ -806,7 +622,7 @@ size_t HUF_readDTableX4_wksp(HUF_DTable* DTable, const void* src,
                     rankValPtr[w] = rankVal0[w] >> consumed;
     }   }   }   }
 
-    HUF_fillDTableX4(dt, maxTableLog,
+    HUF_fillDTableX2(dt, maxTableLog,
                    sortedSymbol, sizeOfSort,
                    rankStart0, rankVal, maxW,
                    tableLog+1);
@@ -817,112 +633,296 @@ size_t HUF_readDTableX4_wksp(HUF_DTable* DTable, const void* src,
     return iSize;
 }
 
-size_t HUF_readDTableX4(HUF_DTable* DTable, const void* src, size_t srcSize)
+size_t HUF_readDTableX2(HUF_DTable* DTable, const void* src, size_t srcSize)
 {
   U32 workSpace[HUF_DECOMPRESS_WORKSPACE_SIZE_U32];
-  return HUF_readDTableX4_wksp(DTable, src, srcSize,
+  return HUF_readDTableX2_wksp(DTable, src, srcSize,
                                workSpace, sizeof(workSpace));
 }
 
-size_t HUF_decompress1X4_usingDTable(
+
+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;
+        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;
+        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) */
+        endSignal = BIT_reloadDStream(&bitD1) | BIT_reloadDStream(&bitD2) | BIT_reloadDStream(&bitD3) | BIT_reloadDStream(&bitD4);
+        for ( ; (endSignal==BIT_DStream_unfinished) & (op4<(oend-(sizeof(bitD4.bitContainer)-1))) ; ) {
+            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 = BIT_reloadDStream(&bitD1) | BIT_reloadDStream(&bitD2) | BIT_reloadDStream(&bitD3) | BIT_reloadDStream(&bitD4);
+        }
+
+        /* 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_decompress1X4_usingDTable_internal(dst, dstSize, cSrc, cSrcSize, DTable, /* bmi2 */ 0);
+    return HUF_decompress1X2_usingDTable_internal(dst, dstSize, cSrc, cSrcSize, DTable, /* bmi2 */ 0);
 }
 
-size_t HUF_decompress1X4_DCtx_wksp(HUF_DTable* DCtx, void* dst, size_t dstSize,
+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_readDTableX4_wksp(DCtx, cSrc, cSrcSize,
+    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_decompress1X4_usingDTable_internal(dst, dstSize, ip, cSrcSize, DCtx, /* bmi2 */ 0);
+    return HUF_decompress1X2_usingDTable_internal(dst, dstSize, ip, cSrcSize, DCtx, /* bmi2 */ 0);
 }
 
 
-size_t HUF_decompress1X4_DCtx(HUF_DTable* DCtx, void* dst, size_t dstSize,
+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_decompress1X4_DCtx_wksp(DCtx, dst, dstSize, cSrc, cSrcSize,
+    return HUF_decompress1X2_DCtx_wksp(DCtx, dst, dstSize, cSrc, cSrcSize,
                                        workSpace, sizeof(workSpace));
 }
 
-size_t HUF_decompress1X4 (void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize)
+size_t HUF_decompress1X2 (void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize)
 {
-    HUF_CREATE_STATIC_DTABLEX4(DTable, HUF_TABLELOG_MAX);
-    return HUF_decompress1X4_DCtx(DTable, dst, dstSize, cSrc, cSrcSize);
+    HUF_CREATE_STATIC_DTABLEX2(DTable, HUF_TABLELOG_MAX);
+    return HUF_decompress1X2_DCtx(DTable, dst, dstSize, cSrc, cSrcSize);
 }
 
-size_t HUF_decompress4X4_usingDTable(
+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_decompress4X4_usingDTable_internal(dst, dstSize, cSrc, cSrcSize, DTable, /* bmi2 */ 0);
+    return HUF_decompress4X2_usingDTable_internal(dst, dstSize, cSrc, cSrcSize, DTable, /* bmi2 */ 0);
 }
 
-static size_t HUF_decompress4X4_DCtx_wksp_bmi2(HUF_DTable* dctx, void* dst, size_t dstSize,
+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_readDTableX4_wksp(dctx, cSrc, cSrcSize,
+    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_decompress4X4_usingDTable_internal(dst, dstSize, ip, cSrcSize, dctx, bmi2);
+    return HUF_decompress4X2_usingDTable_internal(dst, dstSize, ip, cSrcSize, dctx, bmi2);
 }
 
-size_t HUF_decompress4X4_DCtx_wksp(HUF_DTable* dctx, void* dst, size_t dstSize,
+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_decompress4X4_DCtx_wksp_bmi2(dctx, dst, dstSize, cSrc, cSrcSize, workSpace, wkspSize, /* bmi2 */ 0);
+    return HUF_decompress4X2_DCtx_wksp_bmi2(dctx, dst, dstSize, cSrc, cSrcSize, workSpace, wkspSize, /* bmi2 */ 0);
 }
 
 
-size_t HUF_decompress4X4_DCtx(HUF_DTable* dctx, void* dst, size_t dstSize,
+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_decompress4X4_DCtx_wksp(dctx, dst, dstSize, cSrc, cSrcSize,
+    return HUF_decompress4X2_DCtx_wksp(dctx, dst, dstSize, cSrc, cSrcSize,
                                        workSpace, sizeof(workSpace));
 }
 
-size_t HUF_decompress4X4 (void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize)
+size_t HUF_decompress4X2 (void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize)
 {
-    HUF_CREATE_STATIC_DTABLEX4(DTable, HUF_TABLELOG_MAX);
-    return HUF_decompress4X4_DCtx(DTable, dst, dstSize, cSrc, cSrcSize);
+    HUF_CREATE_STATIC_DTABLEX2(DTable, HUF_TABLELOG_MAX);
+    return HUF_decompress4X2_DCtx(DTable, dst, dstSize, cSrc, cSrcSize);
 }
 
 
-/* ********************************/
-/* Generic decompression selector */
-/* ********************************/
+/* ***********************************/
+/* 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);
-    return dtd.tableType ? HUF_decompress1X4_usingDTable_internal(dst, maxDstSize, cSrc, cSrcSize, DTable, /* bmi2 */ 0) :
-                           HUF_decompress1X2_usingDTable_internal(dst, maxDstSize, cSrc, cSrcSize, DTable, /* bmi2 */ 0);
+    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);
 }
 
 size_t HUF_decompress4X_usingDTable(void* dst, size_t maxDstSize,
@@ -930,8 +930,8 @@ size_t HUF_decompress4X_usingDTable(void* dst, size_t maxDstSize,
                                     const HUF_DTable* DTable)
 {
     DTableDesc const dtd = HUF_getDTableDesc(DTable);
-    return dtd.tableType ? HUF_decompress4X4_usingDTable_internal(dst, maxDstSize, cSrc, cSrcSize, DTable, /* bmi2 */ 0) :
-                           HUF_decompress4X2_usingDTable_internal(dst, maxDstSize, cSrc, cSrcSize, DTable, /* bmi2 */ 0);
+    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);
 }
 
 
@@ -960,12 +960,12 @@ static const algo_time_t algoTime[16 /* Quantization */][3 /* single, double, qu
 /** HUF_selectDecoder() :
  *  Tells which decoder is likely to decode faster,
  *  based on a set of pre-computed metrics.
- * @return : 0==HUF_decompress4X2, 1==HUF_decompress4X4 .
+ * @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 KB);
+    assert(dstSize <= 128*1024);
     /* decoder timing evaluation */
     {   U32 const Q = (cSrcSize >= dstSize) ? 15 : (U32)(cSrcSize * 16 / dstSize);   /* Q < 16 */
         U32 const D256 = (U32)(dstSize >> 8);
@@ -980,7 +980,7 @@ typedef size_t (*decompressionAlgo)(void* dst, size_t dstSize, const void* cSrc,
 
 size_t HUF_decompress (void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize)
 {
-    static const decompressionAlgo decompress[2] = { HUF_decompress4X2, HUF_decompress4X4 };
+    static const decompressionAlgo decompress[2] = { HUF_decompress4X1, HUF_decompress4X2 };
 
     /* validation checks */
     if (dstSize == 0) return ERROR(dstSize_tooSmall);
@@ -1002,8 +1002,8 @@ size_t HUF_decompress4X_DCtx (HUF_DTable* dctx, void* dst, size_t dstSize, const
     if (cSrcSize == 1) { memset(dst, *(const BYTE*)cSrc, dstSize); return dstSize; }   /* RLE */
 
     {   U32 const algoNb = HUF_selectDecoder(dstSize, cSrcSize);
-        return algoNb ? HUF_decompress4X4_DCtx(dctx, dst, dstSize, cSrc, cSrcSize) :
-                        HUF_decompress4X2_DCtx(dctx, dst, dstSize, cSrc, cSrcSize) ;
+        return algoNb ? HUF_decompress4X2_DCtx(dctx, dst, dstSize, cSrc, cSrcSize) :
+                        HUF_decompress4X1_DCtx(dctx, dst, dstSize, cSrc, cSrcSize) ;
     }
 }
 
@@ -1025,8 +1025,8 @@ size_t HUF_decompress4X_hufOnly_wksp(HUF_DTable* dctx, void* dst,
     if (cSrcSize == 0) return ERROR(corruption_detected);
 
     {   U32 const algoNb = HUF_selectDecoder(dstSize, cSrcSize);
-        return algoNb ? HUF_decompress4X4_DCtx_wksp(dctx, dst, dstSize, cSrc, cSrcSize, workSpace, wkspSize):
-                        HUF_decompress4X2_DCtx_wksp(dctx, dst, dstSize, cSrc, cSrcSize, workSpace, wkspSize);
+        return algoNb ? HUF_decompress4X2_DCtx_wksp(dctx, dst, dstSize, cSrc, cSrcSize, workSpace, wkspSize):
+                        HUF_decompress4X1_DCtx_wksp(dctx, dst, dstSize, cSrc, cSrcSize, workSpace, wkspSize);
     }
 }
 
@@ -1041,9 +1041,9 @@ size_t HUF_decompress1X_DCtx_wksp(HUF_DTable* dctx, void* dst, size_t dstSize,
     if (cSrcSize == 1) { memset(dst, *(const BYTE*)cSrc, dstSize); return dstSize; }   /* RLE */
 
     {   U32 const algoNb = HUF_selectDecoder(dstSize, cSrcSize);
-        return algoNb ? HUF_decompress1X4_DCtx_wksp(dctx, dst, dstSize, cSrc,
+        return algoNb ? HUF_decompress1X2_DCtx_wksp(dctx, dst, dstSize, cSrc,
                                 cSrcSize, workSpace, wkspSize):
-                        HUF_decompress1X2_DCtx_wksp(dctx, dst, dstSize, cSrc,
+                        HUF_decompress1X1_DCtx_wksp(dctx, dst, dstSize, cSrc,
                                 cSrcSize, workSpace, wkspSize);
     }
 }
@@ -1060,27 +1060,27 @@ size_t HUF_decompress1X_DCtx(HUF_DTable* dctx, void* dst, size_t dstSize,
 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);
-    return dtd.tableType ? HUF_decompress1X4_usingDTable_internal(dst, maxDstSize, cSrc, cSrcSize, DTable, bmi2) :
-                           HUF_decompress1X2_usingDTable_internal(dst, maxDstSize, cSrc, cSrcSize, DTable, bmi2);
+    return dtd.tableType ? HUF_decompress1X2_usingDTable_internal(dst, maxDstSize, cSrc, cSrcSize, DTable, bmi2) :
+                           HUF_decompress1X1_usingDTable_internal(dst, maxDstSize, cSrc, cSrcSize, DTable, bmi2);
 }
 
-size_t HUF_decompress1X2_DCtx_wksp_bmi2(HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize, void* workSpace, size_t wkspSize, int bmi2)
+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_readDTableX2_wksp(dctx, cSrc, cSrcSize, workSpace, wkspSize);
+    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_decompress1X2_usingDTable_internal(dst, dstSize, ip, cSrcSize, dctx, bmi2);
+    return HUF_decompress1X1_usingDTable_internal(dst, dstSize, ip, cSrcSize, dctx, bmi2);
 }
 
 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);
-    return dtd.tableType ? HUF_decompress4X4_usingDTable_internal(dst, maxDstSize, cSrc, cSrcSize, DTable, bmi2) :
-                           HUF_decompress4X2_usingDTable_internal(dst, maxDstSize, cSrc, cSrcSize, DTable, bmi2);
+    return dtd.tableType ? HUF_decompress4X2_usingDTable_internal(dst, maxDstSize, cSrc, cSrcSize, DTable, bmi2) :
+                           HUF_decompress4X1_usingDTable_internal(dst, maxDstSize, cSrc, cSrcSize, DTable, bmi2);
 }
 
 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)
@@ -1090,7 +1090,7 @@ size_t HUF_decompress4X_hufOnly_wksp_bmi2(HUF_DTable* dctx, void* dst, size_t ds
     if (cSrcSize == 0) return ERROR(corruption_detected);
 
     {   U32 const algoNb = HUF_selectDecoder(dstSize, cSrcSize);
-        return algoNb ? HUF_decompress4X4_DCtx_wksp_bmi2(dctx, dst, dstSize, cSrc, cSrcSize, workSpace, wkspSize, bmi2) :
-                        HUF_decompress4X2_DCtx_wksp_bmi2(dctx, dst, dstSize, cSrc, cSrcSize, workSpace, wkspSize, bmi2);
+        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);
     }
 }