zstdlib 0.13.0-x86-linux

data/ext/zstdlib_c/zstd-1.5.6/lib/compress/hist.c

@@ -0,0 +1,181 @@
+/* ******************************************************************
+ * hist : Histogram functions
+ * part of Finite State Entropy project
+ * Copyright (c) Meta Platforms, Inc. and affiliates.
+ *
+ *  You can contact the author at :
+ *  - FSE source repository : https://github.com/Cyan4973/FiniteStateEntropy
+ *  - Public forum : https://groups.google.com/forum/#!forum/lz4c
+ *
+ * This source code is licensed under both the BSD-style license (found in the
+ * LICENSE file in the root directory of this source tree) and the GPLv2 (found
+ * in the COPYING file in the root directory of this source tree).
+ * You may select, at your option, one of the above-listed licenses.
+****************************************************************** */
+
+/* --- dependencies --- */
+#include "../common/mem.h"             /* U32, BYTE, etc. */
+#include "../common/debug.h"           /* assert, DEBUGLOG */
+#include "../common/error_private.h"   /* ERROR */
+#include "hist.h"
+
+
+/* --- Error management --- */
+unsigned HIST_isError(size_t code) { return ERR_isError(code); }
+
+/*-**************************************************************
+ *  Histogram functions
+ ****************************************************************/
+unsigned HIST_count_simple(unsigned* count, unsigned* maxSymbolValuePtr,
+                           const void* src, size_t srcSize)
+{
+    const BYTE* ip = (const BYTE*)src;
+    const BYTE* const end = ip + srcSize;
+    unsigned maxSymbolValue = *maxSymbolValuePtr;
+    unsigned largestCount=0;
+
+    ZSTD_memset(count, 0, (maxSymbolValue+1) * sizeof(*count));
+    if (srcSize==0) { *maxSymbolValuePtr = 0; return 0; }
+
+    while (ip<end) {
+        assert(*ip <= maxSymbolValue);
+        count[*ip++]++;
+    }
+
+    while (!count[maxSymbolValue]) maxSymbolValue--;
+    *maxSymbolValuePtr = maxSymbolValue;
+
+    {   U32 s;
+        for (s=0; s<=maxSymbolValue; s++)
+            if (count[s] > largestCount) largestCount = count[s];
+    }
+
+    return largestCount;
+}
+
+typedef enum { trustInput, checkMaxSymbolValue } HIST_checkInput_e;
+
+/* HIST_count_parallel_wksp() :
+ * store histogram into 4 intermediate tables, recombined at the end.
+ * this design makes better use of OoO cpus,
+ * and is noticeably faster when some values are heavily repeated.
+ * But it needs some additional workspace for intermediate tables.
+ * `workSpace` must be a U32 table of size >= HIST_WKSP_SIZE_U32.
+ * @return : largest histogram frequency,
+ *           or an error code (notably when histogram's alphabet is larger than *maxSymbolValuePtr) */
+static size_t HIST_count_parallel_wksp(
+                                unsigned* count, unsigned* maxSymbolValuePtr,
+                                const void* source, size_t sourceSize,
+                                HIST_checkInput_e check,
+                                U32* const workSpace)
+{
+    const BYTE* ip = (const BYTE*)source;
+    const BYTE* const iend = ip+sourceSize;
+    size_t const countSize = (*maxSymbolValuePtr + 1) * sizeof(*count);
+    unsigned max=0;
+    U32* const Counting1 = workSpace;
+    U32* const Counting2 = Counting1 + 256;
+    U32* const Counting3 = Counting2 + 256;
+    U32* const Counting4 = Counting3 + 256;
+
+    /* safety checks */
+    assert(*maxSymbolValuePtr <= 255);
+    if (!sourceSize) {
+        ZSTD_memset(count, 0, countSize);
+        *maxSymbolValuePtr = 0;
+        return 0;
+    }
+    ZSTD_memset(workSpace, 0, 4*256*sizeof(unsigned));
+
+    /* by stripes of 16 bytes */
+    {   U32 cached = MEM_read32(ip); ip += 4;
+        while (ip < iend-15) {
+            U32 c = cached; cached = MEM_read32(ip); ip += 4;
+            Counting1[(BYTE) c     ]++;
+            Counting2[(BYTE)(c>>8) ]++;
+            Counting3[(BYTE)(c>>16)]++;
+            Counting4[       c>>24 ]++;
+            c = cached; cached = MEM_read32(ip); ip += 4;
+            Counting1[(BYTE) c     ]++;
+            Counting2[(BYTE)(c>>8) ]++;
+            Counting3[(BYTE)(c>>16)]++;
+            Counting4[       c>>24 ]++;
+            c = cached; cached = MEM_read32(ip); ip += 4;
+            Counting1[(BYTE) c     ]++;
+            Counting2[(BYTE)(c>>8) ]++;
+            Counting3[(BYTE)(c>>16)]++;
+            Counting4[       c>>24 ]++;
+            c = cached; cached = MEM_read32(ip); ip += 4;
+            Counting1[(BYTE) c     ]++;
+            Counting2[(BYTE)(c>>8) ]++;
+            Counting3[(BYTE)(c>>16)]++;
+            Counting4[       c>>24 ]++;
+        }
+        ip-=4;
+    }
+
+    /* finish last symbols */
+    while (ip<iend) Counting1[*ip++]++;
+
+    {   U32 s;
+        for (s=0; s<256; s++) {
+            Counting1[s] += Counting2[s] + Counting3[s] + Counting4[s];
+            if (Counting1[s] > max) max = Counting1[s];
+    }   }
+
+    {   unsigned maxSymbolValue = 255;
+        while (!Counting1[maxSymbolValue]) maxSymbolValue--;
+        if (check && maxSymbolValue > *maxSymbolValuePtr) return ERROR(maxSymbolValue_tooSmall);
+        *maxSymbolValuePtr = maxSymbolValue;
+        ZSTD_memmove(count, Counting1, countSize);   /* in case count & Counting1 are overlapping */
+    }
+    return (size_t)max;
+}
+
+/* HIST_countFast_wksp() :
+ * Same as HIST_countFast(), but using an externally provided scratch buffer.
+ * `workSpace` is a writable buffer which must be 4-bytes aligned,
+ * `workSpaceSize` must be >= HIST_WKSP_SIZE
+ */
+size_t HIST_countFast_wksp(unsigned* count, unsigned* maxSymbolValuePtr,
+                          const void* source, size_t sourceSize,
+                          void* workSpace, size_t workSpaceSize)
+{
+    if (sourceSize < 1500) /* heuristic threshold */
+        return HIST_count_simple(count, maxSymbolValuePtr, source, sourceSize);
+    if ((size_t)workSpace & 3) return ERROR(GENERIC);  /* must be aligned on 4-bytes boundaries */
+    if (workSpaceSize < HIST_WKSP_SIZE) return ERROR(workSpace_tooSmall);
+    return HIST_count_parallel_wksp(count, maxSymbolValuePtr, source, sourceSize, trustInput, (U32*)workSpace);
+}
+
+/* HIST_count_wksp() :
+ * Same as HIST_count(), but using an externally provided scratch buffer.
+ * `workSpace` size must be table of >= HIST_WKSP_SIZE_U32 unsigned */
+size_t HIST_count_wksp(unsigned* count, unsigned* maxSymbolValuePtr,
+                       const void* source, size_t sourceSize,
+                       void* workSpace, size_t workSpaceSize)
+{
+    if ((size_t)workSpace & 3) return ERROR(GENERIC);  /* must be aligned on 4-bytes boundaries */
+    if (workSpaceSize < HIST_WKSP_SIZE) return ERROR(workSpace_tooSmall);
+    if (*maxSymbolValuePtr < 255)
+        return HIST_count_parallel_wksp(count, maxSymbolValuePtr, source, sourceSize, checkMaxSymbolValue, (U32*)workSpace);
+    *maxSymbolValuePtr = 255;
+    return HIST_countFast_wksp(count, maxSymbolValuePtr, source, sourceSize, workSpace, workSpaceSize);
+}
+
+#ifndef ZSTD_NO_UNUSED_FUNCTIONS
+/* fast variant (unsafe : won't check if src contains values beyond count[] limit) */
+size_t HIST_countFast(unsigned* count, unsigned* maxSymbolValuePtr,
+                     const void* source, size_t sourceSize)
+{
+    unsigned tmpCounters[HIST_WKSP_SIZE_U32];
+    return HIST_countFast_wksp(count, maxSymbolValuePtr, source, sourceSize, tmpCounters, sizeof(tmpCounters));
+}
+
+size_t HIST_count(unsigned* count, unsigned* maxSymbolValuePtr,
+                 const void* src, size_t srcSize)
+{
+    unsigned tmpCounters[HIST_WKSP_SIZE_U32];
+    return HIST_count_wksp(count, maxSymbolValuePtr, src, srcSize, tmpCounters, sizeof(tmpCounters));
+}
+#endif

data/ext/zstdlib_c/zstd-1.5.6/lib/compress/hist.h

@@ -0,0 +1,75 @@
+/* ******************************************************************
+ * hist : Histogram functions
+ * part of Finite State Entropy project
+ * Copyright (c) Meta Platforms, Inc. and affiliates.
+ *
+ *  You can contact the author at :
+ *  - FSE source repository : https://github.com/Cyan4973/FiniteStateEntropy
+ *  - Public forum : https://groups.google.com/forum/#!forum/lz4c
+ *
+ * This source code is licensed under both the BSD-style license (found in the
+ * LICENSE file in the root directory of this source tree) and the GPLv2 (found
+ * in the COPYING file in the root directory of this source tree).
+ * You may select, at your option, one of the above-listed licenses.
+****************************************************************** */
+
+/* --- dependencies --- */
+#include "../common/zstd_deps.h"   /* size_t */
+
+
+/* --- simple histogram functions --- */
+
+/*! HIST_count():
+ *  Provides the precise count of each byte within a table 'count'.
+ * 'count' is a table of unsigned int, of minimum size (*maxSymbolValuePtr+1).
+ *  Updates *maxSymbolValuePtr with actual largest symbol value detected.
+ * @return : count of the most frequent symbol (which isn't identified).
+ *           or an error code, which can be tested using HIST_isError().
+ *           note : if return == srcSize, there is only one symbol.
+ */
+size_t HIST_count(unsigned* count, unsigned* maxSymbolValuePtr,
+                  const void* src, size_t srcSize);
+
+unsigned HIST_isError(size_t code);  /**< tells if a return value is an error code */
+
+
+/* --- advanced histogram functions --- */
+
+#define HIST_WKSP_SIZE_U32 1024
+#define HIST_WKSP_SIZE    (HIST_WKSP_SIZE_U32 * sizeof(unsigned))
+/** HIST_count_wksp() :
+ *  Same as HIST_count(), but using an externally provided scratch buffer.
+ *  Benefit is this function will use very little stack space.
+ * `workSpace` is a writable buffer which must be 4-bytes aligned,
+ * `workSpaceSize` must be >= HIST_WKSP_SIZE
+ */
+size_t HIST_count_wksp(unsigned* count, unsigned* maxSymbolValuePtr,
+                       const void* src, size_t srcSize,
+                       void* workSpace, size_t workSpaceSize);
+
+/** HIST_countFast() :
+ *  same as HIST_count(), but blindly trusts that all byte values within src are <= *maxSymbolValuePtr.
+ *  This function is unsafe, and will segfault if any value within `src` is `> *maxSymbolValuePtr`
+ */
+size_t HIST_countFast(unsigned* count, unsigned* maxSymbolValuePtr,
+                      const void* src, size_t srcSize);
+
+/** HIST_countFast_wksp() :
+ *  Same as HIST_countFast(), but using an externally provided scratch buffer.
+ * `workSpace` is a writable buffer which must be 4-bytes aligned,
+ * `workSpaceSize` must be >= HIST_WKSP_SIZE
+ */
+size_t HIST_countFast_wksp(unsigned* count, unsigned* maxSymbolValuePtr,
+                           const void* src, size_t srcSize,
+                           void* workSpace, size_t workSpaceSize);
+
+/*! HIST_count_simple() :
+ *  Same as HIST_countFast(), this function is unsafe,
+ *  and will segfault if any value within `src` is `> *maxSymbolValuePtr`.
+ *  It is also a bit slower for large inputs.
+ *  However, it does not need any additional memory (not even on stack).
+ * @return : count of the most frequent symbol.
+ *  Note this function doesn't produce any error (i.e. it must succeed).
+ */
+unsigned HIST_count_simple(unsigned* count, unsigned* maxSymbolValuePtr,
+                           const void* src, size_t srcSize);