multi_compress 0.2.0 → 0.2.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: b07dc7022c50225ee44cd8956e0182ac483f4f4e9bcc2f48cfc0c14b8ef74b31
-  data.tar.gz: 42e399c199fb48cab2ad7eefc129149d8754d8df0b2255abb5b75f140fe9bf80
+  metadata.gz: ae5350e9b46caeca01531ebf9dad7f603bcf1a5ef6d5c3e2638ff248ad3a4bab
+  data.tar.gz: 71eb14838de738d6590bdb33f31eca25e89a236c35b3ba54a1e01d10cfc88fe3
 SHA512:
-  metadata.gz: 8b123a2f7cee46ca4d61052c5e4b75403e327ab269ebee9d7b35db9f610affc51dfdfcc3118c1cd0949b134146ade9afdaa1ef79a1387af8843478e73fc0f74d
-  data.tar.gz: '0574149cfcb0fba8c38690286149c0bbd0b057ab4b615a157ea2e0c63a687a963317988da3a25d1f9c686389f2b2db07064b4de51ac799b4b0b5ce5f75132d5e'
+  metadata.gz: 02c084372c04faf4b75ea6bddb0b95a63cc580ed897099e97dbff2b61ce33a2b2aa1ba50143e01badd7d109e87ce8d88b3429dc35aadb4448f41fb451530323f
+  data.tar.gz: 46579de5cf8264c15c24cc6330e01407dd59ad8501c17e35a43d3e762c29fcd06e88c3181656619d87744198247857041f2207b525dfa4a6aa33f705bd990e86

data/CHANGELOG.md

@@ -1,5 +1,9 @@
 # Changelog
 
+## [0.2.1] — 2026-04-15
+- Change version zstd "1.5.6" -> "1.5.7".
+- Micro optimization.
+
 ## [0.2.0] — 2026-04-15
 
 ### Added

data/ext/multi_compress/extconf.rb

@@ -163,9 +163,14 @@ else
   vpath_dirs = configure_vendored_libraries(VENDOR_DIR)
 end
 
-$CFLAGS += " -O2"
+$CFLAGS += " -O3"
 $CFLAGS += " -DXXH_NAMESPACE=MULTICOMPRESS_"
 
+case RUBY_PLATFORM
+when /x86_64|amd64|aarch64|arm64/
+  $CFLAGS += " -DBROTLI_BUILD_LITTLE_ENDIAN"
+end
+
 have_header("ruby/fiber/scheduler.h")
 
 have_library("pthread") unless RUBY_PLATFORM.include?("darwin")

data/ext/multi_compress/vendor/zstd/lib/Makefile

@@ -63,6 +63,8 @@ CPPFLAGS_DYNLIB  += -DZSTD_MULTITHREAD # dynamic library build defaults to multi
 LDFLAGS_DYNLIB   += -pthread
 CPPFLAGS_STATICLIB +=                  # static library build defaults to single-threaded
 
+# pkg-config Libs.private points to LDFLAGS_DYNLIB
+PCLIB := $(LDFLAGS_DYNLIB)
 
 ifeq ($(findstring GCC,$(CCVER)),GCC)
 decompress/zstd_decompress_block.o : CFLAGS+=-fno-tree-vectorize
@@ -71,13 +73,15 @@ endif
 
 # macOS linker doesn't support -soname, and use different extension
 # see : https://developer.apple.com/library/mac/documentation/DeveloperTools/Conceptual/DynamicLibraries/100-Articles/DynamicLibraryDesignGuidelines.html
-ifeq ($(UNAME), Darwin)
+UNAME_TARGET_SYSTEM ?= $(UNAME)
+
+ifeq ($(UNAME_TARGET_SYSTEM), Darwin)
   SHARED_EXT = dylib
   SHARED_EXT_MAJOR = $(LIBVER_MAJOR).$(SHARED_EXT)
   SHARED_EXT_VER = $(LIBVER).$(SHARED_EXT)
   SONAME_FLAGS = -install_name $(LIBDIR)/libzstd.$(SHARED_EXT_MAJOR) -compatibility_version $(LIBVER_MAJOR) -current_version $(LIBVER)
 else
-  ifeq ($(UNAME), AIX)
+  ifeq ($(UNAME_TARGET_SYSTEM), AIX)
     SONAME_FLAGS =
   else
     SONAME_FLAGS = -Wl,-soname=libzstd.$(SHARED_EXT).$(LIBVER_MAJOR)
@@ -186,12 +190,15 @@ lib : libzstd.a libzstd
 %-mt : CPPFLAGS_DYNLIB  := -DZSTD_MULTITHREAD
 %-mt : CPPFLAGS_STATICLIB := -DZSTD_MULTITHREAD
 %-mt : LDFLAGS_DYNLIB   := -pthread
+%-mt : PCLIB :=
+%-mt : PCMTLIB := $(LDFLAGS_DYNLIB)
 %-mt : %
 	@echo multi-threaded build completed
 
 %-nomt : CPPFLAGS_DYNLIB  :=
 %-nomt : LDFLAGS_DYNLIB   :=
 %-nomt : CPPFLAGS_STATICLIB :=
+%-nomt : PCLIB :=
 %-nomt : %
 	@echo single-threaded build completed
 
@@ -261,7 +268,7 @@ clean:
 #-----------------------------------------------------------------------------
 # make install is validated only for below listed environments
 #-----------------------------------------------------------------------------
-ifneq (,$(filter $(UNAME),Linux Darwin GNU/kFreeBSD GNU OpenBSD FreeBSD NetBSD DragonFly SunOS Haiku AIX MSYS_NT CYGWIN_NT))
+ifneq (,$(filter Linux Darwin GNU/kFreeBSD GNU OpenBSD FreeBSD NetBSD DragonFly SunOS Haiku AIX MSYS_NT% CYGWIN_NT%,$(UNAME)))
 
 lib: libzstd.pc
 
@@ -292,13 +299,21 @@ PCLIBPREFIX := $(if $(findstring $(LIBDIR),$(PCLIBDIR)),,$${exec_prefix})
 # to PREFIX, rather than as a resolved value.
 PCEXEC_PREFIX := $(if $(HAS_EXPLICIT_EXEC_PREFIX),$(EXEC_PREFIX),$${prefix})
 
-ifneq (,$(filter $(UNAME),FreeBSD NetBSD DragonFly))
+
+ifneq ($(MT),)
+  PCLIB :=
+  PCMTLIB := $(LDFLAGS_DYNLIB)
+else
+  PCLIB := $(LDFLAGS_DYNLIB)
+endif
+
+ifneq (,$(filter FreeBSD NetBSD DragonFly,$(UNAME)))
   PKGCONFIGDIR ?= $(PREFIX)/libdata/pkgconfig
 else
   PKGCONFIGDIR ?= $(LIBDIR)/pkgconfig
 endif
 
-ifneq (,$(filter $(UNAME),SunOS))
+ifneq (,$(filter SunOS,$(UNAME)))
   INSTALL ?= ginstall
 else
   INSTALL ?= install
@@ -308,6 +323,10 @@ INSTALL_PROGRAM ?= $(INSTALL)
 INSTALL_DATA    ?= $(INSTALL) -m 644
 
 
+# pkg-config library define.
+# For static single-threaded library declare -pthread in Libs.private
+# For static multi-threaded library declare -pthread in Libs and Cflags
+.PHONY: libzstd.pc
 libzstd.pc: libzstd.pc.in
 	@echo creating pkgconfig
 	@sed \
@@ -316,7 +335,8 @@ libzstd.pc: libzstd.pc.in
 	        -e 's|@INCLUDEDIR@|$(PCINCPREFIX)$(PCINCDIR)|' \
 	        -e 's|@LIBDIR@|$(PCLIBPREFIX)$(PCLIBDIR)|' \
 	        -e 's|@VERSION@|$(VERSION)|' \
-	        -e 's|@LIBS_PRIVATE@|$(LDFLAGS_DYNLIB)|' \
+	        -e 's|@LIBS_MT@|$(PCMTLIB)|' \
+	        -e 's|@LIBS_PRIVATE@|$(PCLIB)|' \
 	        $< >$@
 
 .PHONY: install

data/ext/multi_compress/vendor/zstd/lib/README.md

@@ -27,12 +27,16 @@ Enabling multithreading requires 2 conditions :
 
 For convenience, we provide a build target to generate multi and single threaded libraries:
 - Force enable multithreading on both dynamic and static libraries by appending `-mt` to the target, e.g. `make lib-mt`.
+  Note that the `.pc` generated on calling `make lib-mt` will already include the require Libs and Cflags.
 - Force disable multithreading on both dynamic and static libraries by appending `-nomt` to the target, e.g. `make lib-nomt`.
 - By default, as mentioned before, dynamic library is multithreaded, and static library is single-threaded, e.g. `make lib`.
 
 When linking a POSIX program with a multithreaded version of `libzstd`,
 note that it's necessary to invoke the `-pthread` flag during link stage.
 
+The `.pc` generated from `make install` or `make install-pc` always assume a single-threaded static library
+is compiled. To correctly generate a `.pc` for the multi-threaded static library, set `MT=1` as ENV variable.
+
 Multithreading capabilities are exposed
 via the [advanced API defined in `lib/zstd.h`](https://github.com/facebook/zstd/blob/v1.4.3/lib/zstd.h#L351).
 
@@ -145,6 +149,13 @@ The file structure is designed to make this selection manually achievable for an
   will expose the deprecated `ZSTDMT` API exposed by `zstdmt_compress.h` in
   the shared library, which is now hidden by default.
 
+- The build macro `STATIC_BMI2` can be set to 1 to force usage of `bmi2` instructions.
+  It is generally not necessary to set this build macro,
+  because `STATIC_BMI2` will be automatically set to 1
+  on detecting the presence of the corresponding instruction set in the compilation target.
+  It's nonetheless available as an optional manual toggle for better control,
+  and can also be used to forcefully disable `bmi2` instructions by setting it to 0.
+
 - The build macro `DYNAMIC_BMI2` can be set to 1 or 0 in order to generate binaries
   which can detect at runtime the presence of BMI2 instructions, and use them only if present.
   These instructions contribute to better performance, notably on the decoder side.

data/ext/multi_compress/vendor/zstd/lib/common/bits.h

@@ -28,27 +28,29 @@ MEM_STATIC unsigned ZSTD_countTrailingZeros32_fallback(U32 val)
 MEM_STATIC unsigned ZSTD_countTrailingZeros32(U32 val)
 {
     assert(val != 0);
-#   if defined(_MSC_VER)
-#       if STATIC_BMI2 == 1
-            return (unsigned)_tzcnt_u32(val);
-#       else
-            if (val != 0) {
-                unsigned long r;
-                _BitScanForward(&r, val);
-                return (unsigned)r;
-            } else {
-                /* Should not reach this code path */
-                __assume(0);
-            }
-#       endif
-#   elif defined(__GNUC__) && (__GNUC__ >= 4)
-        return (unsigned)__builtin_ctz(val);
-#   else
-        return ZSTD_countTrailingZeros32_fallback(val);
-#   endif
+#if defined(_MSC_VER)
+#  if STATIC_BMI2
+    return (unsigned)_tzcnt_u32(val);
+#  else
+    if (val != 0) {
+        unsigned long r;
+        _BitScanForward(&r, val);
+        return (unsigned)r;
+    } else {
+        __assume(0); /* Should not reach this code path */
+    }
+#  endif
+#elif defined(__GNUC__) && (__GNUC__ >= 4)
+    return (unsigned)__builtin_ctz(val);
+#elif defined(__ICCARM__)
+    return (unsigned)__builtin_ctz(val);
+#else
+    return ZSTD_countTrailingZeros32_fallback(val);
+#endif
 }
 
-MEM_STATIC unsigned ZSTD_countLeadingZeros32_fallback(U32 val) {
+MEM_STATIC unsigned ZSTD_countLeadingZeros32_fallback(U32 val)
+{
     assert(val != 0);
     {
         static const U32 DeBruijnClz[32] = {0, 9, 1, 10, 13, 21, 2, 29,
@@ -67,86 +69,89 @@ MEM_STATIC unsigned ZSTD_countLeadingZeros32_fallback(U32 val) {
 MEM_STATIC unsigned ZSTD_countLeadingZeros32(U32 val)
 {
     assert(val != 0);
-#   if defined(_MSC_VER)
-#       if STATIC_BMI2 == 1
-            return (unsigned)_lzcnt_u32(val);
-#       else
-            if (val != 0) {
-                unsigned long r;
-                _BitScanReverse(&r, val);
-                return (unsigned)(31 - r);
-            } else {
-                /* Should not reach this code path */
-                __assume(0);
-            }
-#       endif
-#   elif defined(__GNUC__) && (__GNUC__ >= 4)
-        return (unsigned)__builtin_clz(val);
-#   else
-        return ZSTD_countLeadingZeros32_fallback(val);
-#   endif
+#if defined(_MSC_VER)
+#  if STATIC_BMI2
+    return (unsigned)_lzcnt_u32(val);
+#  else
+    if (val != 0) {
+        unsigned long r;
+        _BitScanReverse(&r, val);
+        return (unsigned)(31 - r);
+    } else {
+        __assume(0); /* Should not reach this code path */
+    }
+#  endif
+#elif defined(__GNUC__) && (__GNUC__ >= 4)
+    return (unsigned)__builtin_clz(val);
+#elif defined(__ICCARM__)
+    return (unsigned)__builtin_clz(val);
+#else
+    return ZSTD_countLeadingZeros32_fallback(val);
+#endif
 }
 
 MEM_STATIC unsigned ZSTD_countTrailingZeros64(U64 val)
 {
     assert(val != 0);
-#   if defined(_MSC_VER) && defined(_WIN64)
-#       if STATIC_BMI2 == 1
-            return (unsigned)_tzcnt_u64(val);
-#       else
-            if (val != 0) {
-                unsigned long r;
-                _BitScanForward64(&r, val);
-                return (unsigned)r;
-            } else {
-                /* Should not reach this code path */
-                __assume(0);
-            }
-#       endif
-#   elif defined(__GNUC__) && (__GNUC__ >= 4) && defined(__LP64__)
-        return (unsigned)__builtin_ctzll(val);
-#   else
-        {
-            U32 mostSignificantWord = (U32)(val >> 32);
-            U32 leastSignificantWord = (U32)val;
-            if (leastSignificantWord == 0) {
-                return 32 + ZSTD_countTrailingZeros32(mostSignificantWord);
-            } else {
-                return ZSTD_countTrailingZeros32(leastSignificantWord);
-            }
+#if defined(_MSC_VER) && defined(_WIN64)
+#  if STATIC_BMI2
+    return (unsigned)_tzcnt_u64(val);
+#  else
+    if (val != 0) {
+        unsigned long r;
+        _BitScanForward64(&r, val);
+        return (unsigned)r;
+    } else {
+        __assume(0); /* Should not reach this code path */
+    }
+#  endif
+#elif defined(__GNUC__) && (__GNUC__ >= 4) && defined(__LP64__)
+    return (unsigned)__builtin_ctzll(val);
+#elif defined(__ICCARM__)
+    return (unsigned)__builtin_ctzll(val);
+#else
+    {
+        U32 mostSignificantWord = (U32)(val >> 32);
+        U32 leastSignificantWord = (U32)val;
+        if (leastSignificantWord == 0) {
+            return 32 + ZSTD_countTrailingZeros32(mostSignificantWord);
+        } else {
+            return ZSTD_countTrailingZeros32(leastSignificantWord);
         }
-#   endif
+    }
+#endif
 }
 
 MEM_STATIC unsigned ZSTD_countLeadingZeros64(U64 val)
 {
     assert(val != 0);
-#   if defined(_MSC_VER) && defined(_WIN64)
-#       if STATIC_BMI2 == 1
-            return (unsigned)_lzcnt_u64(val);
-#       else
-            if (val != 0) {
-                unsigned long r;
-                _BitScanReverse64(&r, val);
-                return (unsigned)(63 - r);
-            } else {
-                /* Should not reach this code path */
-                __assume(0);
-            }
-#       endif
-#   elif defined(__GNUC__) && (__GNUC__ >= 4)
-        return (unsigned)(__builtin_clzll(val));
-#   else
-        {
-            U32 mostSignificantWord = (U32)(val >> 32);
-            U32 leastSignificantWord = (U32)val;
-            if (mostSignificantWord == 0) {
-                return 32 + ZSTD_countLeadingZeros32(leastSignificantWord);
-            } else {
-                return ZSTD_countLeadingZeros32(mostSignificantWord);
-            }
+#if defined(_MSC_VER) && defined(_WIN64)
+#  if STATIC_BMI2
+    return (unsigned)_lzcnt_u64(val);
+#  else
+    if (val != 0) {
+        unsigned long r;
+        _BitScanReverse64(&r, val);
+        return (unsigned)(63 - r);
+    } else {
+        __assume(0); /* Should not reach this code path */
+    }
+#  endif
+#elif defined(__GNUC__) && (__GNUC__ >= 4)
+    return (unsigned)(__builtin_clzll(val));
+#elif defined(__ICCARM__)
+    return (unsigned)(__builtin_clzll(val));
+#else
+    {
+        U32 mostSignificantWord = (U32)(val >> 32);
+        U32 leastSignificantWord = (U32)val;
+        if (mostSignificantWord == 0) {
+            return 32 + ZSTD_countLeadingZeros32(leastSignificantWord);
+        } else {
+            return ZSTD_countLeadingZeros32(mostSignificantWord);
         }
-#   endif
+    }
+#endif
 }
 
 MEM_STATIC unsigned ZSTD_NbCommonBytes(size_t val)

data/ext/multi_compress/vendor/zstd/lib/common/bitstream.h

@@ -14,9 +14,6 @@
 #ifndef BITSTREAM_H_MODULE
 #define BITSTREAM_H_MODULE
 
-#if defined (__cplusplus)
-extern "C" {
-#endif
 /*
 *  This API consists of small unitary functions, which must be inlined for best performance.
 *  Since link-time-optimization is not available for all compilers,
@@ -32,7 +29,6 @@ extern "C" {
 #include "error_private.h"  /* error codes and messages */
 #include "bits.h"           /* ZSTD_highbit32 */
 
-
 /*=========================================
 *  Target specific
 =========================================*/
@@ -52,12 +48,13 @@ extern "C" {
 /*-******************************************
 *  bitStream encoding API (write forward)
 ********************************************/
+typedef size_t BitContainerType;
 /* bitStream can mix input from multiple sources.
  * A critical property of these streams is that they encode and decode in **reverse** direction.
  * So the first bit sequence you add will be the last to be read, like a LIFO stack.
  */
 typedef struct {
-    size_t bitContainer;
+    BitContainerType bitContainer;
     unsigned bitPos;
     char*  startPtr;
     char*  ptr;
@@ -65,7 +62,7 @@ typedef struct {
 } BIT_CStream_t;
 
 MEM_STATIC size_t BIT_initCStream(BIT_CStream_t* bitC, void* dstBuffer, size_t dstCapacity);
-MEM_STATIC void   BIT_addBits(BIT_CStream_t* bitC, size_t value, unsigned nbBits);
+MEM_STATIC void   BIT_addBits(BIT_CStream_t* bitC, BitContainerType value, unsigned nbBits);
 MEM_STATIC void   BIT_flushBits(BIT_CStream_t* bitC);
 MEM_STATIC size_t BIT_closeCStream(BIT_CStream_t* bitC);
 
@@ -74,7 +71,7 @@ MEM_STATIC size_t BIT_closeCStream(BIT_CStream_t* bitC);
 *  `dstCapacity` must be >= sizeof(bitD->bitContainer), otherwise @return will be an error code.
 *
 *  bits are first added to a local register.
-*  Local register is size_t, hence 64-bits on 64-bits systems, or 32-bits on 32-bits systems.
+*  Local register is BitContainerType, 64-bits on 64-bits systems, or 32-bits on 32-bits systems.
 *  Writing data into memory is an explicit operation, performed by the flushBits function.
 *  Hence keep track how many bits are potentially stored into local register to avoid register overflow.
 *  After a flushBits, a maximum of 7 bits might still be stored into local register.
@@ -90,7 +87,6 @@ MEM_STATIC size_t BIT_closeCStream(BIT_CStream_t* bitC);
 /*-********************************************
 *  bitStream decoding API (read backward)
 **********************************************/
-typedef size_t BitContainerType;
 typedef struct {
     BitContainerType bitContainer;
     unsigned bitsConsumed;
@@ -106,7 +102,7 @@ typedef enum { BIT_DStream_unfinished = 0,  /* fully refilled */
     } BIT_DStream_status;  /* result of BIT_reloadDStream() */
 
 MEM_STATIC size_t   BIT_initDStream(BIT_DStream_t* bitD, const void* srcBuffer, size_t srcSize);
-MEM_STATIC size_t   BIT_readBits(BIT_DStream_t* bitD, unsigned nbBits);
+MEM_STATIC BitContainerType BIT_readBits(BIT_DStream_t* bitD, unsigned nbBits);
 MEM_STATIC BIT_DStream_status BIT_reloadDStream(BIT_DStream_t* bitD);
 MEM_STATIC unsigned BIT_endOfDStream(const BIT_DStream_t* bitD);
 
@@ -125,7 +121,7 @@ MEM_STATIC unsigned BIT_endOfDStream(const BIT_DStream_t* bitD);
 /*-****************************************
 *  unsafe API
 ******************************************/
-MEM_STATIC void BIT_addBitsFast(BIT_CStream_t* bitC, size_t value, unsigned nbBits);
+MEM_STATIC void BIT_addBitsFast(BIT_CStream_t* bitC, BitContainerType value, unsigned nbBits);
 /* faster, but works only if value is "clean", meaning all high bits above nbBits are 0 */
 
 MEM_STATIC void BIT_flushBitsFast(BIT_CStream_t* bitC);
@@ -163,10 +159,15 @@ MEM_STATIC size_t BIT_initCStream(BIT_CStream_t* bitC,
     return 0;
 }
 
-FORCE_INLINE_TEMPLATE size_t BIT_getLowerBits(size_t bitContainer, U32 const nbBits)
+FORCE_INLINE_TEMPLATE BitContainerType BIT_getLowerBits(BitContainerType bitContainer, U32 const nbBits)
 {
-#if defined(STATIC_BMI2) && STATIC_BMI2 == 1 && !defined(ZSTD_NO_INTRINSICS)
-    return  _bzhi_u64(bitContainer, nbBits);
+#if STATIC_BMI2 && !defined(ZSTD_NO_INTRINSICS)
+#  if (defined(__x86_64__) || defined(_M_X64)) && !defined(__ILP32__)
+    return _bzhi_u64(bitContainer, nbBits);
+#  else
+    DEBUG_STATIC_ASSERT(sizeof(bitContainer) == sizeof(U32));
+    return _bzhi_u32(bitContainer, nbBits);
+#  endif
 #else
     assert(nbBits < BIT_MASK_SIZE);
     return bitContainer & BIT_mask[nbBits];
@@ -177,7 +178,7 @@ FORCE_INLINE_TEMPLATE size_t BIT_getLowerBits(size_t bitContainer, U32 const nbB
  *  can add up to 31 bits into `bitC`.
  *  Note : does not check for register overflow ! */
 MEM_STATIC void BIT_addBits(BIT_CStream_t* bitC,
-                            size_t value, unsigned nbBits)
+                            BitContainerType value, unsigned nbBits)
 {
     DEBUG_STATIC_ASSERT(BIT_MASK_SIZE == 32);
     assert(nbBits < BIT_MASK_SIZE);
@@ -190,7 +191,7 @@ MEM_STATIC void BIT_addBits(BIT_CStream_t* bitC,
  *  works only if `value` is _clean_,
  *  meaning all high bits above nbBits are 0 */
 MEM_STATIC void BIT_addBitsFast(BIT_CStream_t* bitC,
-                                size_t value, unsigned nbBits)
+                                BitContainerType value, unsigned nbBits)
 {
     assert((value>>nbBits) == 0);
     assert(nbBits + bitC->bitPos < sizeof(bitC->bitContainer) * 8);
@@ -237,7 +238,7 @@ MEM_STATIC size_t BIT_closeCStream(BIT_CStream_t* bitC)
     BIT_addBitsFast(bitC, 1, 1);   /* endMark */
     BIT_flushBits(bitC);
     if (bitC->ptr >= bitC->endPtr) return 0; /* overflow detected */
-    return (bitC->ptr - bitC->startPtr) + (bitC->bitPos > 0);
+    return (size_t)(bitC->ptr - bitC->startPtr) + (bitC->bitPos > 0);
 }
 
 
@@ -298,12 +299,12 @@ MEM_STATIC size_t BIT_initDStream(BIT_DStream_t* bitD, const void* srcBuffer, si
     return srcSize;
 }
 
-FORCE_INLINE_TEMPLATE size_t BIT_getUpperBits(BitContainerType bitContainer, U32 const start)
+FORCE_INLINE_TEMPLATE BitContainerType BIT_getUpperBits(BitContainerType bitContainer, U32 const start)
 {
     return bitContainer >> start;
 }
 
-FORCE_INLINE_TEMPLATE size_t BIT_getMiddleBits(BitContainerType bitContainer, U32 const start, U32 const nbBits)
+FORCE_INLINE_TEMPLATE BitContainerType BIT_getMiddleBits(BitContainerType bitContainer, U32 const start, U32 const nbBits)
 {
     U32 const regMask = sizeof(bitContainer)*8 - 1;
     /* if start > regMask, bitstream is corrupted, and result is undefined */
@@ -313,7 +314,7 @@ FORCE_INLINE_TEMPLATE size_t BIT_getMiddleBits(BitContainerType bitContainer, U3
      * such cpus old (pre-Haswell, 2013) and their performance is not of that
      * importance.
      */
-#if defined(__x86_64__) || defined(_M_X86)
+#if defined(__x86_64__) || defined(_M_X64)
     return (bitContainer >> (start & regMask)) & ((((U64)1) << nbBits) - 1);
 #else
     return (bitContainer >> (start & regMask)) & BIT_mask[nbBits];
@@ -326,7 +327,7 @@ FORCE_INLINE_TEMPLATE size_t BIT_getMiddleBits(BitContainerType bitContainer, U3
  *  On 32-bits, maxNbBits==24.
  *  On 64-bits, maxNbBits==56.
  * @return : value extracted */
-FORCE_INLINE_TEMPLATE size_t BIT_lookBits(const BIT_DStream_t*  bitD, U32 nbBits)
+FORCE_INLINE_TEMPLATE BitContainerType BIT_lookBits(const BIT_DStream_t*  bitD, U32 nbBits)
 {
     /* arbitrate between double-shift and shift+mask */
 #if 1
@@ -342,7 +343,7 @@ FORCE_INLINE_TEMPLATE size_t BIT_lookBits(const BIT_DStream_t*  bitD, U32 nbBits
 
 /*! BIT_lookBitsFast() :
  *  unsafe version; only works if nbBits >= 1 */
-MEM_STATIC size_t BIT_lookBitsFast(const BIT_DStream_t* bitD, U32 nbBits)
+MEM_STATIC BitContainerType BIT_lookBitsFast(const BIT_DStream_t* bitD, U32 nbBits)
 {
     U32 const regMask = sizeof(bitD->bitContainer)*8 - 1;
     assert(nbBits >= 1);
@@ -358,18 +359,18 @@ FORCE_INLINE_TEMPLATE void BIT_skipBits(BIT_DStream_t* bitD, U32 nbBits)
  *  Read (consume) next n bits from local register and update.
  *  Pay attention to not read more than nbBits contained into local register.
  * @return : extracted value. */
-FORCE_INLINE_TEMPLATE size_t BIT_readBits(BIT_DStream_t* bitD, unsigned nbBits)
+FORCE_INLINE_TEMPLATE BitContainerType BIT_readBits(BIT_DStream_t* bitD, unsigned nbBits)
 {
-    size_t const value = BIT_lookBits(bitD, nbBits);
+    BitContainerType const value = BIT_lookBits(bitD, nbBits);
     BIT_skipBits(bitD, nbBits);
     return value;
 }
 
 /*! BIT_readBitsFast() :
  *  unsafe version; only works if nbBits >= 1 */
-MEM_STATIC size_t BIT_readBitsFast(BIT_DStream_t* bitD, unsigned nbBits)
+MEM_STATIC BitContainerType BIT_readBitsFast(BIT_DStream_t* bitD, unsigned nbBits)
 {
-    size_t const value = BIT_lookBitsFast(bitD, nbBits);
+    BitContainerType const value = BIT_lookBitsFast(bitD, nbBits);
     assert(nbBits >= 1);
     BIT_skipBits(bitD, nbBits);
     return value;
@@ -450,8 +451,4 @@ MEM_STATIC unsigned BIT_endOfDStream(const BIT_DStream_t* DStream)
     return ((DStream->ptr == DStream->start) && (DStream->bitsConsumed == sizeof(DStream->bitContainer)*8));
 }
 
-#if defined (__cplusplus)
-}
-#endif
-
 #endif /* BITSTREAM_H_MODULE */