zstdlib 0.14.0-x86-mingw32 → 0.15.0-x86-mingw32

data/ext/zstdlib_c/{zstd-1.5.6 → zstd-1.5.7}/lib/compress/zstd_compress_sequences.c

@@ -153,13 +153,13 @@ size_t ZSTD_crossEntropyCost(short const* norm, unsigned accuracyLog,
     return cost >> 8;
 }
 
-symbolEncodingType_e
+SymbolEncodingType_e
 ZSTD_selectEncodingType(
         FSE_repeat* repeatMode, unsigned const* count, unsigned const max,
         size_t const mostFrequent, size_t nbSeq, unsigned const FSELog,
         FSE_CTable const* prevCTable,
         short const* defaultNorm, U32 defaultNormLog,
-        ZSTD_defaultPolicy_e const isDefaultAllowed,
+        ZSTD_DefaultPolicy_e const isDefaultAllowed,
         ZSTD_strategy const strategy)
 {
     ZSTD_STATIC_ASSERT(ZSTD_defaultDisallowed == 0 && ZSTD_defaultAllowed != 0);
@@ -241,7 +241,7 @@ typedef struct {
 
 size_t
 ZSTD_buildCTable(void* dst, size_t dstCapacity,
-                FSE_CTable* nextCTable, U32 FSELog, symbolEncodingType_e type,
+                FSE_CTable* nextCTable, U32 FSELog, SymbolEncodingType_e type,
                 unsigned* count, U32 max,
                 const BYTE* codeTable, size_t nbSeq,
                 const S16* defaultNorm, U32 defaultNormLog, U32 defaultMax,
@@ -293,7 +293,7 @@ ZSTD_encodeSequences_body(
             FSE_CTable const* CTable_MatchLength, BYTE const* mlCodeTable,
             FSE_CTable const* CTable_OffsetBits, BYTE const* ofCodeTable,
             FSE_CTable const* CTable_LitLength, BYTE const* llCodeTable,
-            seqDef const* sequences, size_t nbSeq, int longOffsets)
+            SeqDef const* sequences, size_t nbSeq, int longOffsets)
 {
     BIT_CStream_t blockStream;
     FSE_CState_t  stateMatchLength;
@@ -387,7 +387,7 @@ ZSTD_encodeSequences_default(
             FSE_CTable const* CTable_MatchLength, BYTE const* mlCodeTable,
             FSE_CTable const* CTable_OffsetBits, BYTE const* ofCodeTable,
             FSE_CTable const* CTable_LitLength, BYTE const* llCodeTable,
-            seqDef const* sequences, size_t nbSeq, int longOffsets)
+            SeqDef const* sequences, size_t nbSeq, int longOffsets)
 {
     return ZSTD_encodeSequences_body(dst, dstCapacity,
                                     CTable_MatchLength, mlCodeTable,
@@ -405,7 +405,7 @@ ZSTD_encodeSequences_bmi2(
             FSE_CTable const* CTable_MatchLength, BYTE const* mlCodeTable,
             FSE_CTable const* CTable_OffsetBits, BYTE const* ofCodeTable,
             FSE_CTable const* CTable_LitLength, BYTE const* llCodeTable,
-            seqDef const* sequences, size_t nbSeq, int longOffsets)
+            SeqDef const* sequences, size_t nbSeq, int longOffsets)
 {
     return ZSTD_encodeSequences_body(dst, dstCapacity,
                                     CTable_MatchLength, mlCodeTable,
@@ -421,7 +421,7 @@ size_t ZSTD_encodeSequences(
             FSE_CTable const* CTable_MatchLength, BYTE const* mlCodeTable,
             FSE_CTable const* CTable_OffsetBits, BYTE const* ofCodeTable,
             FSE_CTable const* CTable_LitLength, BYTE const* llCodeTable,
-            seqDef const* sequences, size_t nbSeq, int longOffsets, int bmi2)
+            SeqDef const* sequences, size_t nbSeq, int longOffsets, int bmi2)
 {
     DEBUGLOG(5, "ZSTD_encodeSequences: dstCapacity = %u", (unsigned)dstCapacity);
 #if DYNAMIC_BMI2

data/ext/zstdlib_c/{zstd-1.5.6 → zstd-1.5.7}/lib/compress/zstd_compress_sequences.h

@@ -11,26 +11,27 @@
 #ifndef ZSTD_COMPRESS_SEQUENCES_H
 #define ZSTD_COMPRESS_SEQUENCES_H
 
+#include "zstd_compress_internal.h" /* SeqDef */
 #include "../common/fse.h" /* FSE_repeat, FSE_CTable */
-#include "../common/zstd_internal.h" /* symbolEncodingType_e, ZSTD_strategy */
+#include "../common/zstd_internal.h" /* SymbolEncodingType_e, ZSTD_strategy */
 
 typedef enum {
     ZSTD_defaultDisallowed = 0,
     ZSTD_defaultAllowed = 1
-} ZSTD_defaultPolicy_e;
+} ZSTD_DefaultPolicy_e;
 
-symbolEncodingType_e
+SymbolEncodingType_e
 ZSTD_selectEncodingType(
         FSE_repeat* repeatMode, unsigned const* count, unsigned const max,
         size_t const mostFrequent, size_t nbSeq, unsigned const FSELog,
         FSE_CTable const* prevCTable,
         short const* defaultNorm, U32 defaultNormLog,
-        ZSTD_defaultPolicy_e const isDefaultAllowed,
+        ZSTD_DefaultPolicy_e const isDefaultAllowed,
         ZSTD_strategy const strategy);
 
 size_t
 ZSTD_buildCTable(void* dst, size_t dstCapacity,
-                FSE_CTable* nextCTable, U32 FSELog, symbolEncodingType_e type,
+                FSE_CTable* nextCTable, U32 FSELog, SymbolEncodingType_e type,
                 unsigned* count, U32 max,
                 const BYTE* codeTable, size_t nbSeq,
                 const S16* defaultNorm, U32 defaultNormLog, U32 defaultMax,
@@ -42,7 +43,7 @@ size_t ZSTD_encodeSequences(
             FSE_CTable const* CTable_MatchLength, BYTE const* mlCodeTable,
             FSE_CTable const* CTable_OffsetBits, BYTE const* ofCodeTable,
             FSE_CTable const* CTable_LitLength, BYTE const* llCodeTable,
-            seqDef const* sequences, size_t nbSeq, int longOffsets, int bmi2);
+            SeqDef const* sequences, size_t nbSeq, int longOffsets, int bmi2);
 
 size_t ZSTD_fseBitCost(
     FSE_CTable const* ctable,

data/ext/zstdlib_c/{zstd-1.5.6 → zstd-1.5.7}/lib/compress/zstd_compress_superblock.c

@@ -51,7 +51,7 @@ ZSTD_compressSubBlock_literal(const HUF_CElt* hufTable,
     BYTE* const oend = ostart + dstSize;
     BYTE* op = ostart + lhSize;
     U32 const singleStream = lhSize == 3;
-    symbolEncodingType_e hType = writeEntropy ? hufMetadata->hType : set_repeat;
+    SymbolEncodingType_e hType = writeEntropy ? hufMetadata->hType : set_repeat;
     size_t cLitSize = 0;
 
     DEBUGLOG(5, "ZSTD_compressSubBlock_literal (litSize=%zu, lhSize=%zu, writeEntropy=%d)", litSize, lhSize, writeEntropy);
@@ -126,15 +126,15 @@ ZSTD_compressSubBlock_literal(const HUF_CElt* hufTable,
 }
 
 static size_t
-ZSTD_seqDecompressedSize(seqStore_t const* seqStore,
-                   const seqDef* sequences, size_t nbSeqs,
+ZSTD_seqDecompressedSize(SeqStore_t const* seqStore,
+                   const SeqDef* sequences, size_t nbSeqs,
                          size_t litSize, int lastSubBlock)
 {
     size_t matchLengthSum = 0;
     size_t litLengthSum = 0;
     size_t n;
     for (n=0; n<nbSeqs; n++) {
-        const ZSTD_sequenceLength seqLen = ZSTD_getSequenceLength(seqStore, sequences+n);
+        const ZSTD_SequenceLength seqLen = ZSTD_getSequenceLength(seqStore, sequences+n);
         litLengthSum += seqLen.litLength;
         matchLengthSum += seqLen.matchLength;
     }
@@ -162,7 +162,7 @@ ZSTD_seqDecompressedSize(seqStore_t const* seqStore,
 static size_t
 ZSTD_compressSubBlock_sequences(const ZSTD_fseCTables_t* fseTables,
                                 const ZSTD_fseCTablesMetadata_t* fseMetadata,
-                                const seqDef* sequences, size_t nbSeq,
+                                const SeqDef* sequences, size_t nbSeq,
                                 const BYTE* llCode, const BYTE* mlCode, const BYTE* ofCode,
                                 const ZSTD_CCtx_params* cctxParams,
                                 void* dst, size_t dstCapacity,
@@ -262,7 +262,7 @@ ZSTD_compressSubBlock_sequences(const ZSTD_fseCTables_t* fseTables,
  *            Or 0 if it failed to compress. */
 static size_t ZSTD_compressSubBlock(const ZSTD_entropyCTables_t* entropy,
                                     const ZSTD_entropyCTablesMetadata_t* entropyMetadata,
-                                    const seqDef* sequences, size_t nbSeq,
+                                    const SeqDef* sequences, size_t nbSeq,
                                     const BYTE* literals, size_t litSize,
                                     const BYTE* llCode, const BYTE* mlCode, const BYTE* ofCode,
                                     const ZSTD_CCtx_params* cctxParams,
@@ -327,7 +327,7 @@ static size_t ZSTD_estimateSubBlockSize_literal(const BYTE* literals, size_t lit
     return 0;
 }
 
-static size_t ZSTD_estimateSubBlockSize_symbolType(symbolEncodingType_e type,
+static size_t ZSTD_estimateSubBlockSize_symbolType(SymbolEncodingType_e type,
                         const BYTE* codeTable, unsigned maxCode,
                         size_t nbSeq, const FSE_CTable* fseCTable,
                         const U8* additionalBits,
@@ -426,7 +426,7 @@ static int ZSTD_needSequenceEntropyTables(ZSTD_fseCTablesMetadata_t const* fseMe
     return 0;
 }
 
-static size_t countLiterals(seqStore_t const* seqStore, const seqDef* sp, size_t seqCount)
+static size_t countLiterals(SeqStore_t const* seqStore, const SeqDef* sp, size_t seqCount)
 {
     size_t n, total = 0;
     assert(sp != NULL);
@@ -439,7 +439,7 @@ static size_t countLiterals(seqStore_t const* seqStore, const seqDef* sp, size_t
 
 #define BYTESCALE 256
 
-static size_t sizeBlockSequences(const seqDef* sp, size_t nbSeqs,
+static size_t sizeBlockSequences(const SeqDef* sp, size_t nbSeqs,
                 size_t targetBudget, size_t avgLitCost, size_t avgSeqCost,
                 int firstSubBlock)
 {
@@ -476,7 +476,7 @@ static size_t sizeBlockSequences(const seqDef* sp, size_t nbSeqs,
  *  Sub-blocks are all compressed, except the last one when beneficial.
  *  @return : compressed size of the super block (which features multiple ZSTD blocks)
  *            or 0 if it failed to compress. */
-static size_t ZSTD_compressSubBlock_multi(const seqStore_t* seqStorePtr,
+static size_t ZSTD_compressSubBlock_multi(const SeqStore_t* seqStorePtr,
                             const ZSTD_compressedBlockState_t* prevCBlock,
                             ZSTD_compressedBlockState_t* nextCBlock,
                             const ZSTD_entropyCTablesMetadata_t* entropyMetadata,
@@ -486,9 +486,9 @@ static size_t ZSTD_compressSubBlock_multi(const seqStore_t* seqStorePtr,
                             const int bmi2, U32 lastBlock,
                             void* workspace, size_t wkspSize)
 {
-    const seqDef* const sstart = seqStorePtr->sequencesStart;
-    const seqDef* const send = seqStorePtr->sequences;
-    const seqDef* sp = sstart; /* tracks progresses within seqStorePtr->sequences */
+    const SeqDef* const sstart = seqStorePtr->sequencesStart;
+    const SeqDef* const send = seqStorePtr->sequences;
+    const SeqDef* sp = sstart; /* tracks progresses within seqStorePtr->sequences */
     size_t const nbSeqs = (size_t)(send - sstart);
     const BYTE* const lstart = seqStorePtr->litStart;
     const BYTE* const lend = seqStorePtr->lit;
@@ -647,8 +647,8 @@ static size_t ZSTD_compressSubBlock_multi(const seqStore_t* seqStorePtr,
         op += cSize;
         /* We have to regenerate the repcodes because we've skipped some sequences */
         if (sp < send) {
-            const seqDef* seq;
-            repcodes_t rep;
+            const SeqDef* seq;
+            Repcodes_t rep;
             ZSTD_memcpy(&rep, prevCBlock->rep, sizeof(rep));
             for (seq = sstart; seq < sp; ++seq) {
                 ZSTD_updateRep(rep.rep, seq->offBase, ZSTD_getSequenceLength(seqStorePtr, seq).litLength == 0);
@@ -674,7 +674,7 @@ size_t ZSTD_compressSuperBlock(ZSTD_CCtx* zc,
           &zc->blockState.nextCBlock->entropy,
           &zc->appliedParams,
           &entropyMetadata,
-          zc->entropyWorkspace, ENTROPY_WORKSPACE_SIZE /* statically allocated in resetCCtx */), "");
+          zc->tmpWorkspace, zc->tmpWkspSize /* statically allocated in resetCCtx */), "");
 
     return ZSTD_compressSubBlock_multi(&zc->seqStore,
             zc->blockState.prevCBlock,
@@ -684,5 +684,5 @@ size_t ZSTD_compressSuperBlock(ZSTD_CCtx* zc,
             dst, dstCapacity,
             src, srcSize,
             zc->bmi2, lastBlock,
-            zc->entropyWorkspace, ENTROPY_WORKSPACE_SIZE /* statically allocated in resetCCtx */);
+            zc->tmpWorkspace, zc->tmpWkspSize /* statically allocated in resetCCtx */);
 }

data/ext/zstdlib_c/{zstd-1.5.6 → zstd-1.5.7}/lib/compress/zstd_cwksp.h

@@ -17,10 +17,7 @@
 #include "../common/allocations.h"  /* ZSTD_customMalloc, ZSTD_customFree */
 #include "../common/zstd_internal.h"
 #include "../common/portability_macros.h"
-
-#if defined (__cplusplus)
-extern "C" {
-#endif
+#include "../common/compiler.h" /* ZS2_isPower2 */
 
 /*-*************************************
 *  Constants
@@ -206,9 +203,9 @@ MEM_STATIC void ZSTD_cwksp_assert_internal_consistency(ZSTD_cwksp* ws) {
 /**
  * Align must be a power of 2.
  */
-MEM_STATIC size_t ZSTD_cwksp_align(size_t size, size_t const align) {
+MEM_STATIC size_t ZSTD_cwksp_align(size_t size, size_t align) {
     size_t const mask = align - 1;
-    assert((align & mask) == 0);
+    assert(ZSTD_isPower2(align));
     return (size + mask) & ~mask;
 }
 
@@ -222,7 +219,7 @@ MEM_STATIC size_t ZSTD_cwksp_align(size_t size, size_t const align) {
  * to figure out how much space you need for the matchState tables. Everything
  * else is though.
  *
- * Do not use for sizing aligned buffers. Instead, use ZSTD_cwksp_aligned_alloc_size().
+ * Do not use for sizing aligned buffers. Instead, use ZSTD_cwksp_aligned64_alloc_size().
  */
 MEM_STATIC size_t ZSTD_cwksp_alloc_size(size_t size) {
     if (size == 0)
@@ -234,12 +231,16 @@ MEM_STATIC size_t ZSTD_cwksp_alloc_size(size_t size) {
 #endif
 }
 
+MEM_STATIC size_t ZSTD_cwksp_aligned_alloc_size(size_t size, size_t alignment) {
+    return ZSTD_cwksp_alloc_size(ZSTD_cwksp_align(size, alignment));
+}
+
 /**
  * Returns an adjusted alloc size that is the nearest larger multiple of 64 bytes.
  * Used to determine the number of bytes required for a given "aligned".
  */
-MEM_STATIC size_t ZSTD_cwksp_aligned_alloc_size(size_t size) {
-    return ZSTD_cwksp_alloc_size(ZSTD_cwksp_align(size, ZSTD_CWKSP_ALIGNMENT_BYTES));
+MEM_STATIC size_t ZSTD_cwksp_aligned64_alloc_size(size_t size) {
+    return ZSTD_cwksp_aligned_alloc_size(size, ZSTD_CWKSP_ALIGNMENT_BYTES);
 }
 
 /**
@@ -262,7 +263,7 @@ MEM_STATIC size_t ZSTD_cwksp_slack_space_required(void) {
 MEM_STATIC size_t ZSTD_cwksp_bytes_to_align_ptr(void* ptr, const size_t alignBytes) {
     size_t const alignBytesMask = alignBytes - 1;
     size_t const bytes = (alignBytes - ((size_t)ptr & (alignBytesMask))) & alignBytesMask;
-    assert((alignBytes & alignBytesMask) == 0);
+    assert(ZSTD_isPower2(alignBytes));
     assert(bytes < alignBytes);
     return bytes;
 }
@@ -271,8 +272,12 @@ MEM_STATIC size_t ZSTD_cwksp_bytes_to_align_ptr(void* ptr, const size_t alignByt
  * Returns the initial value for allocStart which is used to determine the position from
  * which we can allocate from the end of the workspace.
  */
-MEM_STATIC void*  ZSTD_cwksp_initialAllocStart(ZSTD_cwksp* ws) {
-    return (void*)((size_t)ws->workspaceEnd & ~(ZSTD_CWKSP_ALIGNMENT_BYTES-1));
+MEM_STATIC void*  ZSTD_cwksp_initialAllocStart(ZSTD_cwksp* ws)
+{
+    char* endPtr = (char*)ws->workspaceEnd;
+    assert(ZSTD_isPower2(ZSTD_CWKSP_ALIGNMENT_BYTES));
+    endPtr = endPtr - ((size_t)endPtr % ZSTD_CWKSP_ALIGNMENT_BYTES);
+    return (void*)endPtr;
 }
 
 /**
@@ -287,7 +292,7 @@ ZSTD_cwksp_reserve_internal_buffer_space(ZSTD_cwksp* ws, size_t const bytes)
 {
     void* const alloc = (BYTE*)ws->allocStart - bytes;
     void* const bottom = ws->tableEnd;
-    DEBUGLOG(5, "cwksp: reserving %p %zd bytes, %zd bytes remaining",
+    DEBUGLOG(5, "cwksp: reserving [0x%p]:%zd bytes; %zd bytes remaining",
         alloc, bytes, ZSTD_cwksp_available_space(ws) - bytes);
     ZSTD_cwksp_assert_internal_consistency(ws);
     assert(alloc >= bottom);
@@ -404,7 +409,7 @@ MEM_STATIC void* ZSTD_cwksp_reserve_aligned_init_once(ZSTD_cwksp* ws, size_t byt
 {
     size_t const alignedBytes = ZSTD_cwksp_align(bytes, ZSTD_CWKSP_ALIGNMENT_BYTES);
     void* ptr = ZSTD_cwksp_reserve_internal(ws, alignedBytes, ZSTD_cwksp_alloc_aligned_init_once);
-    assert(((size_t)ptr & (ZSTD_CWKSP_ALIGNMENT_BYTES-1))== 0);
+    assert(((size_t)ptr & (ZSTD_CWKSP_ALIGNMENT_BYTES-1)) == 0);
     if(ptr && ptr < ws->initOnceStart) {
         /* We assume the memory following the current allocation is either:
          * 1. Not usable as initOnce memory (end of workspace)
@@ -424,11 +429,12 @@ MEM_STATIC void* ZSTD_cwksp_reserve_aligned_init_once(ZSTD_cwksp* ws, size_t byt
 /**
  * Reserves and returns memory sized on and aligned on ZSTD_CWKSP_ALIGNMENT_BYTES (64 bytes).
  */
-MEM_STATIC void* ZSTD_cwksp_reserve_aligned(ZSTD_cwksp* ws, size_t bytes)
+MEM_STATIC void* ZSTD_cwksp_reserve_aligned64(ZSTD_cwksp* ws, size_t bytes)
 {
-    void* ptr = ZSTD_cwksp_reserve_internal(ws, ZSTD_cwksp_align(bytes, ZSTD_CWKSP_ALIGNMENT_BYTES),
-                                            ZSTD_cwksp_alloc_aligned);
-    assert(((size_t)ptr & (ZSTD_CWKSP_ALIGNMENT_BYTES-1))== 0);
+    void* const ptr = ZSTD_cwksp_reserve_internal(ws,
+                        ZSTD_cwksp_align(bytes, ZSTD_CWKSP_ALIGNMENT_BYTES),
+                        ZSTD_cwksp_alloc_aligned);
+    assert(((size_t)ptr & (ZSTD_CWKSP_ALIGNMENT_BYTES-1)) == 0);
     return ptr;
 }
 
@@ -474,7 +480,7 @@ MEM_STATIC void* ZSTD_cwksp_reserve_table(ZSTD_cwksp* ws, size_t bytes)
 #endif
 
     assert((bytes & (ZSTD_CWKSP_ALIGNMENT_BYTES-1)) == 0);
-    assert(((size_t)alloc & (ZSTD_CWKSP_ALIGNMENT_BYTES-1))== 0);
+    assert(((size_t)alloc & (ZSTD_CWKSP_ALIGNMENT_BYTES-1)) == 0);
     return alloc;
 }
 
@@ -520,6 +526,20 @@ MEM_STATIC void* ZSTD_cwksp_reserve_object(ZSTD_cwksp* ws, size_t bytes)
 
     return alloc;
 }
+/**
+ * with alignment control
+ * Note : should happen only once, at workspace first initialization
+ */
+MEM_STATIC void* ZSTD_cwksp_reserve_object_aligned(ZSTD_cwksp* ws, size_t byteSize, size_t alignment)
+{
+    size_t const mask = alignment - 1;
+    size_t const surplus = (alignment > sizeof(void*)) ? alignment - sizeof(void*) : 0;
+    void* const start = ZSTD_cwksp_reserve_object(ws, byteSize + surplus);
+    if (start == NULL) return NULL;
+    if (surplus == 0) return start;
+    assert(ZSTD_isPower2(alignment));
+    return (void*)(((size_t)start + surplus) & ~mask);
+}
 
 MEM_STATIC void ZSTD_cwksp_mark_tables_dirty(ZSTD_cwksp* ws)
 {
@@ -577,7 +597,8 @@ MEM_STATIC void ZSTD_cwksp_clean_tables(ZSTD_cwksp* ws) {
  * Invalidates table allocations.
  * All other allocations remain valid.
  */
-MEM_STATIC void ZSTD_cwksp_clear_tables(ZSTD_cwksp* ws) {
+MEM_STATIC void ZSTD_cwksp_clear_tables(ZSTD_cwksp* ws)
+{
     DEBUGLOG(4, "cwksp: clearing tables!");
 
 #if ZSTD_ADDRESS_SANITIZER && !defined (ZSTD_ASAN_DONT_POISON_WORKSPACE)
@@ -741,8 +762,4 @@ MEM_STATIC void ZSTD_cwksp_bump_oversized_duration(
     }
 }
 
-#if defined (__cplusplus)
-}
-#endif
-
 #endif /* ZSTD_CWKSP_H */

data/ext/zstdlib_c/{zstd-1.5.6 → zstd-1.5.7}/lib/compress/zstd_double_fast.c

@@ -15,7 +15,7 @@
 
 static
 ZSTD_ALLOW_POINTER_OVERFLOW_ATTR
-void ZSTD_fillDoubleHashTableForCDict(ZSTD_matchState_t* ms,
+void ZSTD_fillDoubleHashTableForCDict(ZSTD_MatchState_t* ms,
                               void const* end, ZSTD_dictTableLoadMethod_e dtlm)
 {
     const ZSTD_compressionParameters* const cParams = &ms->cParams;
@@ -53,7 +53,7 @@ void ZSTD_fillDoubleHashTableForCDict(ZSTD_matchState_t* ms,
 
 static
 ZSTD_ALLOW_POINTER_OVERFLOW_ATTR
-void ZSTD_fillDoubleHashTableForCCtx(ZSTD_matchState_t* ms,
+void ZSTD_fillDoubleHashTableForCCtx(ZSTD_MatchState_t* ms,
                               void const* end, ZSTD_dictTableLoadMethod_e dtlm)
 {
     const ZSTD_compressionParameters* const cParams = &ms->cParams;
@@ -87,7 +87,7 @@ void ZSTD_fillDoubleHashTableForCCtx(ZSTD_matchState_t* ms,
         }   }
 }
 
-void ZSTD_fillDoubleHashTable(ZSTD_matchState_t* ms,
+void ZSTD_fillDoubleHashTable(ZSTD_MatchState_t* ms,
                         const void* const end,
                         ZSTD_dictTableLoadMethod_e dtlm,
                         ZSTD_tableFillPurpose_e tfp)
@@ -103,7 +103,7 @@ void ZSTD_fillDoubleHashTable(ZSTD_matchState_t* ms,
 FORCE_INLINE_TEMPLATE
 ZSTD_ALLOW_POINTER_OVERFLOW_ATTR
 size_t ZSTD_compressBlock_doubleFast_noDict_generic(
-        ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
+        ZSTD_MatchState_t* ms, SeqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
         void const* src, size_t srcSize, U32 const mls /* template */)
 {
     ZSTD_compressionParameters const* cParams = &ms->cParams;
@@ -142,9 +142,14 @@ size_t ZSTD_compressBlock_doubleFast_noDict_generic(
     const BYTE* matchl0; /* the long match for ip */
     const BYTE* matchs0; /* the short match for ip */
     const BYTE* matchl1; /* the long match for ip1 */
+    const BYTE* matchs0_safe; /* matchs0 or safe address */
 
     const BYTE* ip = istart; /* the current position */
     const BYTE* ip1; /* the next position */
+    /* Array of ~random data, should have low probability of matching data
+     * we load from here instead of from tables, if matchl0/matchl1 are
+     * invalid indices. Used to avoid unpredictable branches. */
+    const BYTE dummy[] = {0x12,0x34,0x56,0x78,0x9a,0xbc,0xde,0xf0,0xe2,0xb4};
 
     DEBUGLOG(5, "ZSTD_compressBlock_doubleFast_noDict_generic");
 
@@ -191,24 +196,29 @@ size_t ZSTD_compressBlock_doubleFast_noDict_generic(
 
             hl1 = ZSTD_hashPtr(ip1, hBitsL, 8);
 
-            if (idxl0 > prefixLowestIndex) {
+            /* idxl0 > prefixLowestIndex is a (somewhat) unpredictable branch.
+             * However expression below complies into conditional move. Since
+             * match is unlikely and we only *branch* on idxl0 > prefixLowestIndex
+             * if there is a match, all branches become predictable. */
+            {   const BYTE*  const matchl0_safe = ZSTD_selectAddr(idxl0, prefixLowestIndex, matchl0, &dummy[0]);
+
                 /* check prefix long match */
-                if (MEM_read64(matchl0) == MEM_read64(ip)) {
+                if (MEM_read64(matchl0_safe) == MEM_read64(ip) && matchl0_safe == matchl0) {
                     mLength = ZSTD_count(ip+8, matchl0+8, iend) + 8;
                     offset = (U32)(ip-matchl0);
                     while (((ip>anchor) & (matchl0>prefixLowest)) && (ip[-1] == matchl0[-1])) { ip--; matchl0--; mLength++; } /* catch up */
                     goto _match_found;
-                }
-            }
+            }   }
 
             idxl1 = hashLong[hl1];
             matchl1 = base + idxl1;
 
-            if (idxs0 > prefixLowestIndex) {
-                /* check prefix short match */
-                if (MEM_read32(matchs0) == MEM_read32(ip)) {
-                    goto _search_next_long;
-                }
+            /* Same optimization as matchl0 above */
+            matchs0_safe = ZSTD_selectAddr(idxs0, prefixLowestIndex, matchs0, &dummy[0]);
+
+            /* check prefix short match */
+            if(MEM_read32(matchs0_safe) == MEM_read32(ip) && matchs0_safe == matchs0) {
+                  goto _search_next_long;
             }
 
             if (ip1 >= nextStep) {
@@ -242,21 +252,23 @@ _cleanup:
 
 _search_next_long:
 
-        /* check prefix long +1 match */
-        if (idxl1 > prefixLowestIndex) {
-            if (MEM_read64(matchl1) == MEM_read64(ip1)) {
+        /* short match found: let's check for a longer one */
+        mLength = ZSTD_count(ip+4, matchs0+4, iend) + 4;
+        offset = (U32)(ip - matchs0);
+
+        /* check long match at +1 position */
+        if ((idxl1 > prefixLowestIndex) && (MEM_read64(matchl1) == MEM_read64(ip1))) {
+            size_t const l1len = ZSTD_count(ip1+8, matchl1+8, iend) + 8;
+            if (l1len > mLength) {
+                /* use the long match instead */
                 ip = ip1;
-                mLength = ZSTD_count(ip+8, matchl1+8, iend) + 8;
+                mLength = l1len;
                 offset = (U32)(ip-matchl1);
-                while (((ip>anchor) & (matchl1>prefixLowest)) && (ip[-1] == matchl1[-1])) { ip--; matchl1--; mLength++; } /* catch up */
-                goto _match_found;
+                matchs0 = matchl1;
             }
         }
 
-        /* if no long +1 match, explore the short match we found */
-        mLength = ZSTD_count(ip+4, matchs0+4, iend) + 4;
-        offset = (U32)(ip - matchs0);
-        while (((ip>anchor) & (matchs0>prefixLowest)) && (ip[-1] == matchs0[-1])) { ip--; matchs0--; mLength++; } /* catch up */
+        while (((ip>anchor) & (matchs0>prefixLowest)) && (ip[-1] == matchs0[-1])) { ip--; matchs0--; mLength++; } /* complete backward */
 
         /* fall-through */
 
@@ -314,7 +326,7 @@ _match_stored:
 FORCE_INLINE_TEMPLATE
 ZSTD_ALLOW_POINTER_OVERFLOW_ATTR
 size_t ZSTD_compressBlock_doubleFast_dictMatchState_generic(
-        ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
+        ZSTD_MatchState_t* ms, SeqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
         void const* src, size_t srcSize,
         U32 const mls /* template */)
 {
@@ -335,7 +347,7 @@ size_t ZSTD_compressBlock_doubleFast_dictMatchState_generic(
     const BYTE* const ilimit = iend - HASH_READ_SIZE;
     U32 offset_1=rep[0], offset_2=rep[1];
 
-    const ZSTD_matchState_t* const dms = ms->dictMatchState;
+    const ZSTD_MatchState_t* const dms = ms->dictMatchState;
     const ZSTD_compressionParameters* const dictCParams = &dms->cParams;
     const U32* const dictHashLong  = dms->hashTable;
     const U32* const dictHashSmall = dms->chainTable;
@@ -392,7 +404,7 @@ size_t ZSTD_compressBlock_doubleFast_dictMatchState_generic(
         hashLong[h2] = hashSmall[h] = curr;   /* update hash tables */
 
         /* check repcode */
-        if (((U32)((prefixLowestIndex-1) - repIndex) >= 3 /* intentional underflow */)
+        if ((ZSTD_index_overlap_check(prefixLowestIndex, repIndex))
             && (MEM_read32(repMatch) == MEM_read32(ip+1)) ) {
             const BYTE* repMatchEnd = repIndex < prefixLowestIndex ? dictEnd : iend;
             mLength = ZSTD_count_2segments(ip+1+4, repMatch+4, iend, repMatchEnd, prefixLowest) + 4;
@@ -401,14 +413,12 @@ size_t ZSTD_compressBlock_doubleFast_dictMatchState_generic(
             goto _match_stored;
         }
 
-        if (matchIndexL > prefixLowestIndex) {
+        if ((matchIndexL >= prefixLowestIndex) && (MEM_read64(matchLong) == MEM_read64(ip))) {
             /* check prefix long match */
-            if (MEM_read64(matchLong) == MEM_read64(ip)) {
-                mLength = ZSTD_count(ip+8, matchLong+8, iend) + 8;
-                offset = (U32)(ip-matchLong);
-                while (((ip>anchor) & (matchLong>prefixLowest)) && (ip[-1] == matchLong[-1])) { ip--; matchLong--; mLength++; } /* catch up */
-                goto _match_found;
-            }
+            mLength = ZSTD_count(ip+8, matchLong+8, iend) + 8;
+            offset = (U32)(ip-matchLong);
+            while (((ip>anchor) & (matchLong>prefixLowest)) && (ip[-1] == matchLong[-1])) { ip--; matchLong--; mLength++; } /* catch up */
+            goto _match_found;
         } else if (dictTagsMatchL) {
             /* check dictMatchState long match */
             U32 const dictMatchIndexL = dictMatchIndexAndTagL >> ZSTD_SHORT_CACHE_TAG_BITS;
@@ -423,7 +433,7 @@ size_t ZSTD_compressBlock_doubleFast_dictMatchState_generic(
         }   }
 
         if (matchIndexS > prefixLowestIndex) {
-            /* check prefix short match */
+            /* short match  candidate */
             if (MEM_read32(match) == MEM_read32(ip)) {
                 goto _search_next_long;
             }
@@ -453,14 +463,12 @@ _search_next_long:
             hashLong[hl3] = curr + 1;
 
             /* check prefix long +1 match */
-            if (matchIndexL3 > prefixLowestIndex) {
-                if (MEM_read64(matchL3) == MEM_read64(ip+1)) {
-                    mLength = ZSTD_count(ip+9, matchL3+8, iend) + 8;
-                    ip++;
-                    offset = (U32)(ip-matchL3);
-                    while (((ip>anchor) & (matchL3>prefixLowest)) && (ip[-1] == matchL3[-1])) { ip--; matchL3--; mLength++; } /* catch up */
-                    goto _match_found;
-                }
+            if ((matchIndexL3 >= prefixLowestIndex) && (MEM_read64(matchL3) == MEM_read64(ip+1))) {
+                mLength = ZSTD_count(ip+9, matchL3+8, iend) + 8;
+                ip++;
+                offset = (U32)(ip-matchL3);
+                while (((ip>anchor) & (matchL3>prefixLowest)) && (ip[-1] == matchL3[-1])) { ip--; matchL3--; mLength++; } /* catch up */
+                goto _match_found;
             } else if (dictTagsMatchL3) {
                 /* check dict long +1 match */
                 U32 const dictMatchIndexL3 = dictMatchIndexAndTagL3 >> ZSTD_SHORT_CACHE_TAG_BITS;
@@ -513,7 +521,7 @@ _match_stored:
                 const BYTE* repMatch2 = repIndex2 < prefixLowestIndex ?
                         dictBase + repIndex2 - dictIndexDelta :
                         base + repIndex2;
-                if ( ((U32)((prefixLowestIndex-1) - (U32)repIndex2) >= 3 /* intentional overflow */)
+                if ( (ZSTD_index_overlap_check(prefixLowestIndex, repIndex2))
                    && (MEM_read32(repMatch2) == MEM_read32(ip)) ) {
                     const BYTE* const repEnd2 = repIndex2 < prefixLowestIndex ? dictEnd : iend;
                     size_t const repLength2 = ZSTD_count_2segments(ip+4, repMatch2+4, iend, repEnd2, prefixLowest) + 4;
@@ -540,7 +548,7 @@ _match_stored:
 
 #define ZSTD_GEN_DFAST_FN(dictMode, mls)                                                                 \
     static size_t ZSTD_compressBlock_doubleFast_##dictMode##_##mls(                                      \
-            ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],                          \
+            ZSTD_MatchState_t* ms, SeqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],                          \
             void const* src, size_t srcSize)                                                             \
     {                                                                                                    \
         return ZSTD_compressBlock_doubleFast_##dictMode##_generic(ms, seqStore, rep, src, srcSize, mls); \
@@ -558,7 +566,7 @@ ZSTD_GEN_DFAST_FN(dictMatchState, 7)
 
 
 size_t ZSTD_compressBlock_doubleFast(
-        ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
+        ZSTD_MatchState_t* ms, SeqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
         void const* src, size_t srcSize)
 {
     const U32 mls = ms->cParams.minMatch;
@@ -578,7 +586,7 @@ size_t ZSTD_compressBlock_doubleFast(
 
 
 size_t ZSTD_compressBlock_doubleFast_dictMatchState(
-        ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
+        ZSTD_MatchState_t* ms, SeqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
         void const* src, size_t srcSize)
 {
     const U32 mls = ms->cParams.minMatch;
@@ -600,7 +608,7 @@ size_t ZSTD_compressBlock_doubleFast_dictMatchState(
 static
 ZSTD_ALLOW_POINTER_OVERFLOW_ATTR
 size_t ZSTD_compressBlock_doubleFast_extDict_generic(
-        ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
+        ZSTD_MatchState_t* ms, SeqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
         void const* src, size_t srcSize,
         U32 const mls /* template */)
 {
@@ -651,7 +659,7 @@ size_t ZSTD_compressBlock_doubleFast_extDict_generic(
         size_t mLength;
         hashSmall[hSmall] = hashLong[hLong] = curr;   /* update hash table */
 
-        if ((((U32)((prefixStartIndex-1) - repIndex) >= 3) /* intentional underflow : ensure repIndex doesn't overlap dict + prefix */
+        if (((ZSTD_index_overlap_check(prefixStartIndex, repIndex))
             & (offset_1 <= curr+1 - dictStartIndex)) /* note: we are searching at curr+1 */
           && (MEM_read32(repMatch) == MEM_read32(ip+1)) ) {
             const BYTE* repMatchEnd = repIndex < prefixStartIndex ? dictEnd : iend;
@@ -719,7 +727,7 @@ size_t ZSTD_compressBlock_doubleFast_extDict_generic(
                 U32 const current2 = (U32)(ip-base);
                 U32 const repIndex2 = current2 - offset_2;
                 const BYTE* repMatch2 = repIndex2 < prefixStartIndex ? dictBase + repIndex2 : base + repIndex2;
-                if ( (((U32)((prefixStartIndex-1) - repIndex2) >= 3)   /* intentional overflow : ensure repIndex2 doesn't overlap dict + prefix */
+                if ( ((ZSTD_index_overlap_check(prefixStartIndex, repIndex2))
                     & (offset_2 <= current2 - dictStartIndex))
                   && (MEM_read32(repMatch2) == MEM_read32(ip)) ) {
                     const BYTE* const repEnd2 = repIndex2 < prefixStartIndex ? dictEnd : iend;
@@ -749,7 +757,7 @@ ZSTD_GEN_DFAST_FN(extDict, 6)
 ZSTD_GEN_DFAST_FN(extDict, 7)
 
 size_t ZSTD_compressBlock_doubleFast_extDict(
-        ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
+        ZSTD_MatchState_t* ms, SeqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
         void const* src, size_t srcSize)
 {
     U32 const mls = ms->cParams.minMatch;