mirror of
https://github.com/postgres/postgres.git
synced 2026-01-26 09:41:40 +03:00
25dc485074
This commit does the following:
* Removes TRY_POPCNT_X86_64. We now assume that the required CPUID
intrinsics are available when HAVE_X86_64_POPCNTQ is defined, as we
have done since v16 for meson builds when
USE_SSE42_CRC32C_WITH_RUNTIME_CHECK is defined and since v17 when
USE_AVX512_POPCNT_WITH_RUNTIME_CHECK is defined.
* Moves the MSVC check for HAVE_X86_64_POPCNTQ to configure-time.
This way, we set it for all relevant platforms in one place.
* Moves the #defines for USE_SSE2 and USE_NEON to c.h so that they
can be used elsewhere without including simd.h. Consequently, we
can remove the POPCNT_AARCH64 macro.
* Moves the #includes for pg_bitutils.h to below the system headers
in pg_popcount_{aarch64,x86}.c, since we no longer depend on macros
from pg_bitutils.h to decide which system headers to use.
Reviewed-by: John Naylor <johncnaylorls@gmail.com>
Discussion: https://postgr.es/m/aWf_InS1VrbeXAfP%40nathan
286 lines
7.6 KiB
C
286 lines
7.6 KiB
C
/*-------------------------------------------------------------------------
|
|
*
|
|
* pg_bitutils.c
|
|
* Miscellaneous functions for bit-wise operations.
|
|
*
|
|
* Copyright (c) 2019-2026, PostgreSQL Global Development Group
|
|
*
|
|
* IDENTIFICATION
|
|
* src/port/pg_bitutils.c
|
|
*
|
|
*-------------------------------------------------------------------------
|
|
*/
|
|
#include "c.h"
|
|
|
|
#include "port/pg_bitutils.h"
|
|
|
|
|
|
/*
|
|
* Array giving the position of the left-most set bit for each possible
|
|
* byte value. We count the right-most position as the 0th bit, and the
|
|
* left-most the 7th bit. The 0th entry of the array should not be used.
|
|
*
|
|
* Note: this is not used by the functions in pg_bitutils.h when
|
|
* HAVE__BUILTIN_CLZ is defined, but we provide it anyway, so that
|
|
* extensions possibly compiled with a different compiler can use it.
|
|
*/
|
|
const uint8 pg_leftmost_one_pos[256] = {
|
|
0, 0, 1, 1, 2, 2, 2, 2, 3, 3, 3, 3, 3, 3, 3, 3,
|
|
4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4,
|
|
5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5,
|
|
5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5,
|
|
6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6,
|
|
6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6,
|
|
6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6,
|
|
6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6,
|
|
7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7,
|
|
7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7,
|
|
7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7,
|
|
7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7,
|
|
7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7,
|
|
7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7,
|
|
7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7,
|
|
7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7
|
|
};
|
|
|
|
/*
|
|
* Array giving the position of the right-most set bit for each possible
|
|
* byte value. We count the right-most position as the 0th bit, and the
|
|
* left-most the 7th bit. The 0th entry of the array should not be used.
|
|
*
|
|
* Note: this is not used by the functions in pg_bitutils.h when
|
|
* HAVE__BUILTIN_CTZ is defined, but we provide it anyway, so that
|
|
* extensions possibly compiled with a different compiler can use it.
|
|
*/
|
|
const uint8 pg_rightmost_one_pos[256] = {
|
|
0, 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,
|
|
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
|
|
};
|
|
|
|
/*
|
|
* Array giving the number of 1-bits in each possible byte value.
|
|
*
|
|
* Note: we export this for use by functions in which explicit use
|
|
* of the popcount functions seems unlikely to be a win.
|
|
*/
|
|
const uint8 pg_number_of_ones[256] = {
|
|
0, 1, 1, 2, 1, 2, 2, 3, 1, 2, 2, 3, 2, 3, 3, 4,
|
|
1, 2, 2, 3, 2, 3, 3, 4, 2, 3, 3, 4, 3, 4, 4, 5,
|
|
1, 2, 2, 3, 2, 3, 3, 4, 2, 3, 3, 4, 3, 4, 4, 5,
|
|
2, 3, 3, 4, 3, 4, 4, 5, 3, 4, 4, 5, 4, 5, 5, 6,
|
|
1, 2, 2, 3, 2, 3, 3, 4, 2, 3, 3, 4, 3, 4, 4, 5,
|
|
2, 3, 3, 4, 3, 4, 4, 5, 3, 4, 4, 5, 4, 5, 5, 6,
|
|
2, 3, 3, 4, 3, 4, 4, 5, 3, 4, 4, 5, 4, 5, 5, 6,
|
|
3, 4, 4, 5, 4, 5, 5, 6, 4, 5, 5, 6, 5, 6, 6, 7,
|
|
1, 2, 2, 3, 2, 3, 3, 4, 2, 3, 3, 4, 3, 4, 4, 5,
|
|
2, 3, 3, 4, 3, 4, 4, 5, 3, 4, 4, 5, 4, 5, 5, 6,
|
|
2, 3, 3, 4, 3, 4, 4, 5, 3, 4, 4, 5, 4, 5, 5, 6,
|
|
3, 4, 4, 5, 4, 5, 5, 6, 4, 5, 5, 6, 5, 6, 6, 7,
|
|
2, 3, 3, 4, 3, 4, 4, 5, 3, 4, 4, 5, 4, 5, 5, 6,
|
|
3, 4, 4, 5, 4, 5, 5, 6, 4, 5, 5, 6, 5, 6, 6, 7,
|
|
3, 4, 4, 5, 4, 5, 5, 6, 4, 5, 5, 6, 5, 6, 6, 7,
|
|
4, 5, 5, 6, 5, 6, 6, 7, 5, 6, 6, 7, 6, 7, 7, 8
|
|
};
|
|
|
|
/*
|
|
* pg_popcount32_portable
|
|
* Return the number of 1 bits set in word
|
|
*/
|
|
int
|
|
pg_popcount32_portable(uint32 word)
|
|
{
|
|
#ifdef HAVE__BUILTIN_POPCOUNT
|
|
return __builtin_popcount(word);
|
|
#else /* !HAVE__BUILTIN_POPCOUNT */
|
|
int result = 0;
|
|
|
|
while (word != 0)
|
|
{
|
|
result += pg_number_of_ones[word & 255];
|
|
word >>= 8;
|
|
}
|
|
|
|
return result;
|
|
#endif /* HAVE__BUILTIN_POPCOUNT */
|
|
}
|
|
|
|
/*
|
|
* pg_popcount64_portable
|
|
* Return the number of 1 bits set in word
|
|
*/
|
|
int
|
|
pg_popcount64_portable(uint64 word)
|
|
{
|
|
#ifdef HAVE__BUILTIN_POPCOUNT
|
|
#if SIZEOF_LONG == 8
|
|
return __builtin_popcountl(word);
|
|
#elif SIZEOF_LONG_LONG == 8
|
|
return __builtin_popcountll(word);
|
|
#else
|
|
#error "cannot find integer of the same size as uint64_t"
|
|
#endif
|
|
#else /* !HAVE__BUILTIN_POPCOUNT */
|
|
int result = 0;
|
|
|
|
while (word != 0)
|
|
{
|
|
result += pg_number_of_ones[word & 255];
|
|
word >>= 8;
|
|
}
|
|
|
|
return result;
|
|
#endif /* HAVE__BUILTIN_POPCOUNT */
|
|
}
|
|
|
|
/*
|
|
* pg_popcount_portable
|
|
* Returns the number of 1-bits in buf
|
|
*/
|
|
uint64
|
|
pg_popcount_portable(const char *buf, int bytes)
|
|
{
|
|
uint64 popcnt = 0;
|
|
|
|
#if SIZEOF_VOID_P >= 8
|
|
/* Process in 64-bit chunks if the buffer is aligned. */
|
|
if (buf == (const char *) TYPEALIGN(8, buf))
|
|
{
|
|
const uint64 *words = (const uint64 *) buf;
|
|
|
|
while (bytes >= 8)
|
|
{
|
|
popcnt += pg_popcount64_portable(*words++);
|
|
bytes -= 8;
|
|
}
|
|
|
|
buf = (const char *) words;
|
|
}
|
|
#else
|
|
/* Process in 32-bit chunks if the buffer is aligned. */
|
|
if (buf == (const char *) TYPEALIGN(4, buf))
|
|
{
|
|
const uint32 *words = (const uint32 *) buf;
|
|
|
|
while (bytes >= 4)
|
|
{
|
|
popcnt += pg_popcount32_portable(*words++);
|
|
bytes -= 4;
|
|
}
|
|
|
|
buf = (const char *) words;
|
|
}
|
|
#endif
|
|
|
|
/* Process any remaining bytes */
|
|
while (bytes--)
|
|
popcnt += pg_number_of_ones[(unsigned char) *buf++];
|
|
|
|
return popcnt;
|
|
}
|
|
|
|
/*
|
|
* pg_popcount_masked_portable
|
|
* Returns the number of 1-bits in buf after applying the mask to each byte
|
|
*/
|
|
uint64
|
|
pg_popcount_masked_portable(const char *buf, int bytes, bits8 mask)
|
|
{
|
|
uint64 popcnt = 0;
|
|
|
|
#if SIZEOF_VOID_P >= 8
|
|
/* Process in 64-bit chunks if the buffer is aligned */
|
|
uint64 maskv = ~UINT64CONST(0) / 0xFF * mask;
|
|
|
|
if (buf == (const char *) TYPEALIGN(8, buf))
|
|
{
|
|
const uint64 *words = (const uint64 *) buf;
|
|
|
|
while (bytes >= 8)
|
|
{
|
|
popcnt += pg_popcount64_portable(*words++ & maskv);
|
|
bytes -= 8;
|
|
}
|
|
|
|
buf = (const char *) words;
|
|
}
|
|
#else
|
|
/* Process in 32-bit chunks if the buffer is aligned. */
|
|
uint32 maskv = ~((uint32) 0) / 0xFF * mask;
|
|
|
|
if (buf == (const char *) TYPEALIGN(4, buf))
|
|
{
|
|
const uint32 *words = (const uint32 *) buf;
|
|
|
|
while (bytes >= 4)
|
|
{
|
|
popcnt += pg_popcount32_portable(*words++ & maskv);
|
|
bytes -= 4;
|
|
}
|
|
|
|
buf = (const char *) words;
|
|
}
|
|
#endif
|
|
|
|
/* Process any remaining bytes */
|
|
while (bytes--)
|
|
popcnt += pg_number_of_ones[(unsigned char) *buf++ & mask];
|
|
|
|
return popcnt;
|
|
}
|
|
|
|
#if !defined(HAVE_X86_64_POPCNTQ) && !defined(USE_NEON)
|
|
|
|
/*
|
|
* When special CPU instructions are not available, there's no point in using
|
|
* function pointers to vary the implementation. We instead just make these
|
|
* actual external functions. The compiler should be able to inline the
|
|
* portable versions here.
|
|
*/
|
|
int
|
|
pg_popcount32(uint32 word)
|
|
{
|
|
return pg_popcount32_portable(word);
|
|
}
|
|
|
|
int
|
|
pg_popcount64(uint64 word)
|
|
{
|
|
return pg_popcount64_portable(word);
|
|
}
|
|
|
|
/*
|
|
* pg_popcount_optimized
|
|
* Returns the number of 1-bits in buf
|
|
*/
|
|
uint64
|
|
pg_popcount_optimized(const char *buf, int bytes)
|
|
{
|
|
return pg_popcount_portable(buf, bytes);
|
|
}
|
|
|
|
/*
|
|
* pg_popcount_masked_optimized
|
|
* Returns the number of 1-bits in buf after applying the mask to each byte
|
|
*/
|
|
uint64
|
|
pg_popcount_masked_optimized(const char *buf, int bytes, bits8 mask)
|
|
{
|
|
return pg_popcount_masked_portable(buf, bytes, mask);
|
|
}
|
|
|
|
#endif /* ! HAVE_X86_64_POPCNTQ && ! USE_NEON */
|