in cdk/extra/lz4/lib/lz4.c [558:654]
static unsigned LZ4_NbCommonBytes (reg_t val)
{
assert(val != 0);
if (LZ4_isLittleEndian()) {
if (sizeof(val) == 8) {
# if defined(_MSC_VER) && (_MSC_VER >= 1800) && (defined(_M_AMD64) && !defined(_M_ARM64EC)) && !defined(LZ4_FORCE_SW_BITCOUNT)
/*-*************************************************************************************************
* ARM64EC is a Microsoft-designed ARM64 ABI compatible with AMD64 applications on ARM64 Windows 11.
* The ARM64EC ABI does not support AVX/AVX2/AVX512 instructions, nor their relevant intrinsics
* including _tzcnt_u64. Therefore, we need to neuter the _tzcnt_u64 code path for ARM64EC.
****************************************************************************************************/
# if defined(__clang__) && (__clang_major__ < 10)
/* Avoid undefined clang-cl intrinsics issue.
* See https://github.com/lz4/lz4/pull/1017 for details. */
return (unsigned)__builtin_ia32_tzcnt_u64(val) >> 3;
# else
/* x64 CPUS without BMI support interpret `TZCNT` as `REP BSF` */
return (unsigned)_tzcnt_u64(val) >> 3;
# endif
# elif defined(_MSC_VER) && defined(_WIN64) && !defined(LZ4_FORCE_SW_BITCOUNT)
unsigned long r = 0;
_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
const U64 m = 0x0101010101010101ULL;
val ^= val - 1;
return (unsigned)(((U64)((val & (m - 1)) * m)) >> 56);
# endif
} else /* 32 bits */ {
# if defined(_MSC_VER) && (_MSC_VER >= 1400) && !defined(LZ4_FORCE_SW_BITCOUNT)
unsigned long r;
_BitScanForward(&r, (U32)val);
return (unsigned)r >> 3;
# elif (defined(__clang__) || (defined(__GNUC__) && ((__GNUC__ > 3) || \
((__GNUC__ == 3) && (__GNUC_MINOR__ >= 4))))) && \
!defined(__TINYC__) && !defined(LZ4_FORCE_SW_BITCOUNT)
return (unsigned)__builtin_ctz((U32)val) >> 3;
# else
const U32 m = 0x01010101;
return (unsigned)((((val - 1) ^ val) & (m - 1)) * m) >> 24;
# endif
}
} else /* Big Endian CPU */ {
if (sizeof(val)==8) {
# if (defined(__clang__) || (defined(__GNUC__) && ((__GNUC__ > 3) || \
((__GNUC__ == 3) && (__GNUC_MINOR__ >= 4))))) && \
!defined(__TINYC__) && !defined(LZ4_FORCE_SW_BITCOUNT)
return (unsigned)__builtin_clzll((U64)val) >> 3;
# else
#if 1
/* this method is probably faster,
* but adds a 128 bytes lookup table */
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,
};
U64 const mask = 0x0101010101010101ULL;
U64 const t = (((val >> 8) - mask) | val) & mask;
return ctz7_tab[(t * 0x0080402010080402ULL) >> 57];
#else
/* this method doesn't consume memory space like the previous one,
* but it contains several branches,
* that may end up slowing execution */
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;
#endif
# endif
} else /* 32 bits */ {
# 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
val >>= 8;
val = ((((val + 0x00FFFF00) | 0x00FFFFFF) + val) |
(val + 0x00FF0000)) >> 24;
return (unsigned)val ^ 3;
# endif
}
}
}