From e72897402df0b93978d9471979e6d5c62d278b2a Mon Sep 17 00:00:00 2001 From: aqrit Date: Tue, 11 Aug 2020 21:14:09 -0400 Subject: [PATCH] rejigger bit counting intrinsics Fix lz4/lz4#867 Optimize software fallback routines. Delete some faulty (and dead?) MSVC big endian code. --- lib/lz4.c | 91 ++++++++++++++++++++++++++++--------------------------- 1 file changed, 46 insertions(+), 45 deletions(-) diff --git a/lib/lz4.c b/lib/lz4.c index 1cd7322..5d0a2d2 100644 --- a/lib/lz4.c +++ b/lib/lz4.c @@ -487,75 +487,76 @@ LZ4_memcpy_using_offset(BYTE* dstPtr, const BYTE* srcPtr, BYTE* dstEnd, const si **************************************/ static unsigned LZ4_NbCommonBytes (reg_t val) { + assert(val != 0); if (LZ4_isLittleEndian()) { - if (sizeof(val)==8) { -# if defined(_MSC_VER) && defined(_WIN64) && !defined(LZ4_FORCE_SW_BITCOUNT) + if (sizeof(val) == 8) { +# if defined(_MSC_VER) && (_MSC_VER >= 1800) && defined(_M_AMD64) && !defined(LZ4_FORCE_SW_BITCOUNT) + /* x64 CPUS without BMI support interpret `TZCNT` as `REP BSF` */ + return (unsigned)_tzcnt_u64(val) >> 3; +# elif defined(_MSC_VER) && defined(_WIN64) && !defined(LZ4_FORCE_SW_BITCOUNT) unsigned long r = 0; - _BitScanForward64( &r, (U64)val ); - return (int)(r>>3); -# elif (defined(__clang__) || (defined(__GNUC__) && (__GNUC__>=3))) && !defined(LZ4_FORCE_SW_BITCOUNT) + _BitScanForward64(&r, (U64)val); + return (unsigned)r >> 3; +# elif (defined(__clang__) || (defined(__GNUC__) && ((__GNUC__ > 3) || \ + ((__GNUC__ == 3) && (__GNUC_MINOR__ >= 4))))) && \ + !defined(LZ4_FORCE_SW_BITCOUNT) return (unsigned)__builtin_ctzll((U64)val) >> 3; # else - static const int DeBruijnBytePos[64] = { 0, 0, 0, 0, 0, 1, 1, 2, - 0, 3, 1, 3, 1, 4, 2, 7, - 0, 2, 3, 6, 1, 5, 3, 5, - 1, 3, 4, 4, 2, 5, 6, 7, - 7, 0, 1, 2, 3, 3, 4, 6, - 2, 6, 5, 5, 3, 4, 5, 6, - 7, 1, 2, 4, 6, 4, 4, 5, - 7, 2, 6, 5, 7, 6, 7, 7 }; - return DeBruijnBytePos[((U64)((val & -(long long)val) * 0x0218A392CDABBD3FULL)) >> 58]; + const U64 m = 0x0101010101010101ULL; + val ^= val - 1; + return (unsigned)(((U64)((val & (m - 1)) * m)) >> 56); # endif } else /* 32 bits */ { # if defined(_MSC_VER) && !defined(LZ4_FORCE_SW_BITCOUNT) unsigned long r; - _BitScanForward( &r, (U32)val ); - return (int)(r>>3); -# elif (defined(__clang__) || (defined(__GNUC__) && (__GNUC__>=3))) && !defined(LZ4_FORCE_SW_BITCOUNT) + _BitScanForward(&r, (U32)val); + return (unsigned)r >> 3; +# elif (defined(__clang__) || (defined(__GNUC__) && ((__GNUC__ > 3) || \ + ((__GNUC__ == 3) && (__GNUC_MINOR__ >= 4))))) && \ + !defined(LZ4_FORCE_SW_BITCOUNT) return (unsigned)__builtin_ctz((U32)val) >> 3; # else - static const int DeBruijnBytePos[32] = { 0, 0, 3, 0, 3, 1, 3, 0, - 3, 2, 2, 1, 3, 2, 0, 1, - 3, 3, 1, 2, 2, 2, 2, 0, - 3, 1, 2, 0, 1, 0, 1, 1 }; - return DeBruijnBytePos[((U32)((val & -(S32)val) * 0x077CB531U)) >> 27]; + const U32 m = 0x01010101; + return (unsigned)((((val - 1) ^ val) & (m - 1)) * m) >> 24; # endif } } else /* Big Endian CPU */ { - if (sizeof(val)==8) { /* 64-bits */ -# if defined(_MSC_VER) && defined(_WIN64) && !defined(LZ4_FORCE_SW_BITCOUNT) - unsigned long r = 0; - _BitScanReverse64( &r, val ); - return (unsigned)(r>>3); -# elif (defined(__clang__) || (defined(__GNUC__) && (__GNUC__>=3))) && !defined(LZ4_FORCE_SW_BITCOUNT) + if (sizeof(val)==8) { +# if (defined(__clang__) || (defined(__GNUC__) && ((__GNUC__ > 3) || \ + ((__GNUC__ == 3) && (__GNUC_MINOR__ >= 4))))) && \ + !defined(LZ4_FORCE_SW_BITCOUNT) return (unsigned)__builtin_clzll((U64)val) >> 3; # else - static const U32 by32 = sizeof(val)*4; /* 32 on 64 bits (goal), 16 on 32 bits. - Just to avoid some static analyzer complaining about shift by 32 on 32-bits target. - Note that this code path is never triggered in 32-bits mode. */ - unsigned r; - if (!(val>>by32)) { r=4; } else { r=0; val>>=by32; } - if (!(val>>16)) { r+=2; val>>=8; } else { val>>=24; } - r += (!val); - return r; + static const unsigned char ctz7_tab[128] = { + 7, 0, 1, 0, 2, 0, 1, 0, 3, 0, 1, 0, 2, 0, 1, 0, + 4, 0, 1, 0, 2, 0, 1, 0, 3, 0, 1, 0, 2, 0, 1, 0, + 5, 0, 1, 0, 2, 0, 1, 0, 3, 0, 1, 0, 2, 0, 1, 0, + 4, 0, 1, 0, 2, 0, 1, 0, 3, 0, 1, 0, 2, 0, 1, 0, + 6, 0, 1, 0, 2, 0, 1, 0, 3, 0, 1, 0, 2, 0, 1, 0, + 4, 0, 1, 0, 2, 0, 1, 0, 3, 0, 1, 0, 2, 0, 1, 0, + 5, 0, 1, 0, 2, 0, 1, 0, 3, 0, 1, 0, 2, 0, 1, 0, + 4, 0, 1, 0, 2, 0, 1, 0, 3, 0, 1, 0, 2, 0, 1, 0, + }; + const U64 mask = 0x0101010101010101ULL; + val = (((val >> 8) - mask) | val) & mask; + return ctz7_tab[((U64)(val * 0x0080402010080402ULL)) >> 57]; # endif } else /* 32 bits */ { -# if defined(_MSC_VER) && !defined(LZ4_FORCE_SW_BITCOUNT) - unsigned long r = 0; - _BitScanReverse( &r, (unsigned long)val ); - return (unsigned)(r>>3); -# elif (defined(__clang__) || (defined(__GNUC__) && (__GNUC__>=3))) && !defined(LZ4_FORCE_SW_BITCOUNT) +# if (defined(__clang__) || (defined(__GNUC__) && ((__GNUC__ > 3) || \ + ((__GNUC__ == 3) && (__GNUC_MINOR__ >= 4))))) && \ + !defined(LZ4_FORCE_SW_BITCOUNT) return (unsigned)__builtin_clz((U32)val) >> 3; # else - unsigned r; - if (!(val>>16)) { r=2; val>>=8; } else { r=0; val>>=24; } - r += (!val); - return r; + val >>= 8; + val = ((((val + 0x00FFFF00) | 0x00FFFFFF) + val) | + (val + 0x00FF0000)) >> 24; + return (unsigned)val ^ 3; # endif } } } + #define STEPSIZE sizeof(reg_t) LZ4_FORCE_INLINE unsigned LZ4_count(const BYTE* pIn, const BYTE* pMatch, const BYTE* pInLimit)