database/postgres
1
0
Fork 0
mirror of https://github.com/postgres/postgres.git synced 2025-07-28 23:42:10 +03:00
Code Activity

Optimize pg_popcount() with AVX-512 instructions.

Browse Source 
Presently, pg_popcount() processes data in 32-bit or 64-bit chunks
when possible.  Newer hardware that supports AVX-512 instructions
can use 512-bit chunks, which provides a nice speedup, especially
for larger buffers.  This commit introduces the infrastructure
required to detect compiler and CPU support for the required
AVX-512 intrinsic functions, and it adds a new pg_popcount()
implementation that uses these functions.  If CPU support for this
optimized implementation is detected at runtime, a function pointer
is updated so that it is used by subsequent calls to pg_popcount().

Most of the existing in-tree calls to pg_popcount() should benefit
from these instructions, and calls with smaller buffers should at
least not regress compared to v16.  The new infrastructure
introduced by this commit can also be used to optimize
visibilitymap_count(), but that is left for a follow-up commit.

Co-authored-by: Paul Amonson, Ants Aasma
Reviewed-by: Matthias van de Meent, Tom Lane, Noah Misch, Akash Shankaran, Alvaro Herrera, Andres Freund, David Rowley
Discussion: https://postgr.es/m/BL1PR11MB5304097DF7EA81D04C33F3D1DCA6A%40BL1PR11MB5304.namprd11.prod.outlook.com
This commit is contained in:
Nathan Bossart
2024-04-06 21:56:23 -05:00
parent 158f581923
commit 792752af4e
15 changed files with 696 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

51
configure.ac
View File

@ -2052,6 +2052,17 @@ if test x"$pgac_cv__get_cpuid" = x"yes"; then
AC_DEFINE(HAVE__GET_CPUID, 1, [Define to 1 if you have __get_cpuid.])
fi
AC_CACHE_CHECK([for __get_cpuid_count], [pgac_cv__get_cpuid_count],
[AC_LINK_IFELSE([AC_LANG_PROGRAM([#include <cpuid.h>],
[[unsigned int exx[4] = {0, 0, 0, 0};
__get_cpuid_count(7, 0, &exx[0], &exx[1], &exx[2], &exx[3]);
]])],
[pgac_cv__get_cpuid_count="yes"],
[pgac_cv__get_cpuid_count="no"])])
if test x"$pgac_cv__get_cpuid_count" = x"yes"; then
AC_DEFINE(HAVE__GET_CPUID_COUNT, 1, [Define to 1 if you have __get_cpuid_count.])
fi
AC_CACHE_CHECK([for __cpuid], [pgac_cv__cpuid],
[AC_LINK_IFELSE([AC_LANG_PROGRAM([#include <intrin.h>],
[[unsigned int exx[4] = {0, 0, 0, 0};
@ -2063,6 +2074,46 @@ if test x"$pgac_cv__cpuid" = x"yes"; then
AC_DEFINE(HAVE__CPUID, 1, [Define to 1 if you have __cpuid.])
fi
AC_CACHE_CHECK([for __cpuidex], [pgac_cv__cpuidex],
[AC_LINK_IFELSE([AC_LANG_PROGRAM([#include <intrin.h>],
[[unsigned int exx[4] = {0, 0, 0, 0};
__get_cpuidex(exx[0], 7, 0);
]])],
[pgac_cv__cpuidex="yes"],
[pgac_cv__cpuidex="no"])])
if test x"$pgac_cv__cpuidex" = x"yes"; then
AC_DEFINE(HAVE__CPUIDEX, 1, [Define to 1 if you have __cpuidex.])
fi
# Check for XSAVE intrinsics
#
CFLAGS_XSAVE=""
PGAC_XSAVE_INTRINSICS([])
if test x"$pgac_xsave_intrinsics" != x"yes"; then
PGAC_XSAVE_INTRINSICS([-mxsave])
fi
if test x"$pgac_xsave_intrinsics" = x"yes"; then
AC_DEFINE(HAVE_XSAVE_INTRINSICS, 1, [Define to 1 if you have XSAVE intrinsics.])
fi
AC_SUBST(CFLAGS_XSAVE)
# Check for AVX-512 popcount intrinsics
#
CFLAGS_POPCNT=""
PG_POPCNT_OBJS=""
if test x"$host_cpu" = x"x86_64"; then
PGAC_AVX512_POPCNT_INTRINSICS([])
if test x"$pgac_avx512_popcnt_intrinsics" != x"yes"; then
PGAC_AVX512_POPCNT_INTRINSICS([-mavx512vpopcntdq -mavx512bw])
fi
if test x"$pgac_avx512_popcnt_intrinsics" = x"yes"; then
PG_POPCNT_OBJS="pg_popcount_avx512.o pg_popcount_avx512_choose.o"
AC_DEFINE(USE_AVX512_POPCNT_WITH_RUNTIME_CHECK, 1, [Define to 1 to use AVX-512 popcount instructions with a runtime check.])
fi
fi
AC_SUBST(CFLAGS_POPCNT)
AC_SUBST(PG_POPCNT_OBJS)
# Check for Intel SSE 4.2 intrinsics to do CRC calculations.
#
# First check if the _mm_crc32_u8 and _mm_crc32_u64 intrinsics can be used