database/postgres
1
0
Fork 0
mirror of https://github.com/postgres/postgres.git synced 2025-07-27 12:41:57 +03:00
Code Activity

Use Intel SSE 4.2 CRC instructions where available.

Browse Source 
Modern x86 and x86-64 processors with SSE 4.2 support have special
instructions, crc32b and crc32q, for calculating CRC-32C. They greatly
speed up CRC calculation.

Whether the instructions can be used or not depends on the compiler and the
target architecture. If generation of SSE 4.2 instructions is allowed for
the target (-msse4.2 flag on gcc and clang), use them. If they are not
allowed by default, but the compiler supports the -msse4.2 flag to enable
them, compile just the CRC-32C function with -msse4.2 flag, and check at
runtime whether the processor we're running on supports it. If it doesn't,
fall back to the slicing-by-8 algorithm. (With the common defaults on
current operating systems, the runtime-check variant is what you get in
practice.)

Abhijit Menon-Sen, heavily modified by me, reviewed by Andres Freund.
This commit is contained in:
Heikki Linnakangas
2015-04-14 17:05:03 +03:00
parent 4f700bcd20
commit 3dc2d62d04
11 changed files with 534 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

212
configure vendored
View File

@ -650,6 +650,8 @@ MSGMERGE
MSGFMT_FLAGS
MSGFMT
HAVE_POSIX_SIGNALS
PG_CRC32C_OBJS
CFLAGS_SSE42
LDAP_LIBS_BE
LDAP_LIBS_FE
PTHREAD_CFLAGS
@ -14095,6 +14097,216 @@ $as_echo "#define HAVE_GCC__ATOMIC_INT64_CAS 1" >>confdefs.h
fi
# Check for x86 cpuid instruction
{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for __get_cpuid" >&5
$as_echo_n "checking for __get_cpuid... " >&6; }
if ${pgac_cv__get_cpuid+:} false; then :
$as_echo_n "(cached) " >&6
else
cat confdefs.h - <<_ACEOF >conftest.$ac_ext
/* end confdefs.h. */
#include <cpuid.h>
int
main ()
{
unsigned int exx[4] = {0, 0, 0, 0};
__get_cpuid(1, &exx[0], &exx[1], &exx[2], &exx[3]);
;
return 0;
}
_ACEOF
if ac_fn_c_try_link "$LINENO"; then :
pgac_cv__get_cpuid="yes"
else
pgac_cv__get_cpuid="no"
fi
rm -f core conftest.err conftest.$ac_objext \
conftest$ac_exeext conftest.$ac_ext
fi
{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $pgac_cv__get_cpuid" >&5
$as_echo "$pgac_cv__get_cpuid" >&6; }
if test x"$pgac_cv__get_cpuid" = x"yes"; then
$as_echo "#define HAVE__GET_CPUID 1" >>confdefs.h
fi
{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for __cpuid" >&5
$as_echo_n "checking for __cpuid... " >&6; }
if ${pgac_cv__cpuid+:} false; then :
$as_echo_n "(cached) " >&6
else
cat confdefs.h - <<_ACEOF >conftest.$ac_ext
/* end confdefs.h. */
#include <intrin.h>
int
main ()
{
unsigned int exx[4] = {0, 0, 0, 0};
__get_cpuid(exx[0], 1);
;
return 0;
}
_ACEOF
if ac_fn_c_try_link "$LINENO"; then :
pgac_cv__cpuid="yes"
else
pgac_cv__cpuid="no"
fi
rm -f core conftest.err conftest.$ac_objext \
conftest$ac_exeext conftest.$ac_ext
fi
{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $pgac_cv__cpuid" >&5
$as_echo "$pgac_cv__cpuid" >&6; }
if test x"$pgac_cv__cpuid" = x"yes"; then
$as_echo "#define HAVE__CPUID 1" >>confdefs.h
fi
# Check for Intel SSE 4.2 intrinsics to do CRC calculations.
#
# First check if the _mm_crc32_u8 and _mmcrc32_u64 intrinsics can be used
# with the default compiler flags. If not, check if adding the -msse4.2
# flag helps. CFLAGS_SSE42 is set to -msse4.2 if that's required.
{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for _mm_crc32_u8 and _mm_crc32_u64 with CFLAGS=" >&5
$as_echo_n "checking for _mm_crc32_u8 and _mm_crc32_u64 with CFLAGS=... " >&6; }
if ${pgac_cv_sse42_crc32_intrinsics_+:} false; then :
$as_echo_n "(cached) " >&6
else
pgac_save_CFLAGS=$CFLAGS
CFLAGS="$pgac_save_CFLAGS "
ac_save_c_werror_flag=$ac_c_werror_flag
ac_c_werror_flag=yes
cat confdefs.h - <<_ACEOF >conftest.$ac_ext
/* end confdefs.h. */
#include <nmmintrin.h>
int
main ()
{
unsigned int crc = 0;
crc = _mm_crc32_u8(crc, 0);
crc = (unsigned int) _mm_crc32_u64(crc, 0);
;
return 0;
}
_ACEOF
if ac_fn_c_try_link "$LINENO"; then :
pgac_cv_sse42_crc32_intrinsics_=yes
else
pgac_cv_sse42_crc32_intrinsics_=no
fi
rm -f core conftest.err conftest.$ac_objext \
conftest$ac_exeext conftest.$ac_ext
ac_c_werror_flag=$ac_save_c_werror_flag
CFLAGS="$pgac_save_CFLAGS"
fi
{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $pgac_cv_sse42_crc32_intrinsics_" >&5
$as_echo "$pgac_cv_sse42_crc32_intrinsics_" >&6; }
if test x"$pgac_cv_sse42_crc32_intrinsics_" = x"yes"; then
CFLAGS_SSE42=""
pgac_sse42_crc32_intrinsics=yes
fi
if test x"$pgac_sse42_crc32_intrinsics" != x"yes"; then
{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for _mm_crc32_u8 and _mm_crc32_u64 with CFLAGS=-msse4.2" >&5
$as_echo_n "checking for _mm_crc32_u8 and _mm_crc32_u64 with CFLAGS=-msse4.2... " >&6; }
if ${pgac_cv_sse42_crc32_intrinsics__msse4_2+:} false; then :
$as_echo_n "(cached) " >&6
else
pgac_save_CFLAGS=$CFLAGS
CFLAGS="$pgac_save_CFLAGS -msse4.2"
ac_save_c_werror_flag=$ac_c_werror_flag
ac_c_werror_flag=yes
cat confdefs.h - <<_ACEOF >conftest.$ac_ext
/* end confdefs.h. */
#include <nmmintrin.h>
int
main ()
{
unsigned int crc = 0;
crc = _mm_crc32_u8(crc, 0);
crc = (unsigned int) _mm_crc32_u64(crc, 0);
;
return 0;
}
_ACEOF
if ac_fn_c_try_link "$LINENO"; then :
pgac_cv_sse42_crc32_intrinsics__msse4_2=yes
else
pgac_cv_sse42_crc32_intrinsics__msse4_2=no
fi
rm -f core conftest.err conftest.$ac_objext \
conftest$ac_exeext conftest.$ac_ext
ac_c_werror_flag=$ac_save_c_werror_flag
CFLAGS="$pgac_save_CFLAGS"
fi
{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $pgac_cv_sse42_crc32_intrinsics__msse4_2" >&5
$as_echo "$pgac_cv_sse42_crc32_intrinsics__msse4_2" >&6; }
if test x"$pgac_cv_sse42_crc32_intrinsics__msse4_2" = x"yes"; then
CFLAGS_SSE42="-msse4.2"
pgac_sse42_crc32_intrinsics=yes
fi
fi
# Select CRC-32C implementation.
#
# If the SSE 4.2 intrinsics are available without extra CFLAGS, then use them
# always. If they require extra CFLAGS, compile both implementations and
# select which one to use at runtime, depending on whether SSE 4.2 is
# supported by the processor we're running on.
#
# You can override this logic by setting the appropriate USE_*_CRC32 flag to 1
# in the template or configure command line.
if test x"$USE_SSE42_CRC32C" = x"" && test x"$USE_SSE42_CRC32C_WITH_RUNTIME_CHECK" = x"" && test x"$USE_SLICING_BY_8_CRC32C" = x""; then
if test x"$pgac_sse42_crc32_intrinsics" = x"yes" && test x"$CFLAGS_SSE42" = x"" ; then
USE_SSE42_CRC32C=1
else
# the CPUID instruction is needed for the runtime check.
if test x"$pgac_sse42_crc32_intrinsics" = x"yes" && (test x"$pgac_cv__get_cpuid" = x"yes" || test x"$pgac_cv__cpuid" = x"yes"); then
USE_SSE42_CRC32C_WITH_RUNTIME_CHECK=1
else
USE_SLICING_BY_8_CRC32C=1
fi
fi
fi
# Set PG_CRC32C_OBJS appropriately depending on the selected implementation.
{ $as_echo "$as_me:${as_lineno-$LINENO}: checking which CRC-32C implementation to use" >&5
$as_echo_n "checking which CRC-32C implementation to use... " >&6; }
if test x"$USE_SSE42_CRC32C" = x"1"; then
$as_echo "#define USE_SSE42_CRC32C 1" >>confdefs.h
PG_CRC32C_OBJS="pg_crc32c_sse42.o"
{ $as_echo "$as_me:${as_lineno-$LINENO}: result: SSE 4.2" >&5
$as_echo "SSE 4.2" >&6; }
else
if test x"$USE_SSE42_CRC32C_WITH_RUNTIME_CHECK" = x"1"; then
$as_echo "#define USE_SSE42_CRC32C_WITH_RUNTIME_CHECK 1" >>confdefs.h
PG_CRC32C_OBJS="pg_crc32c_sse42.o pg_crc32c_sb8.o pg_crc32c_choose.o"
{ $as_echo "$as_me:${as_lineno-$LINENO}: result: SSE 4.2 with runtime check" >&5
$as_echo "SSE 4.2 with runtime check" >&6; }
else
$as_echo "#define USE_SLICING_BY_8_CRC32C 1" >>confdefs.h
PG_CRC32C_OBJS="pg_crc32c_sb8.o"
{ $as_echo "$as_me:${as_lineno-$LINENO}: result: slicing-by-8" >&5
$as_echo "slicing-by-8" >&6; }
fi
fi
# Check that POSIX signals are available if thread safety is enabled.
if test "$PORTNAME" != "win32"
then
{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for POSIX signal interface" >&5