agora inbox for [email protected]  

help / color / mirror / Atom feed

[PATCH v16 05/10] pg_ls_tmpdir to show directories and "isdir" argument..
16+ messages / 2 participants
[nested] [flat]

* [PATCH v16 05/10] pg_ls_tmpdir to show directories and "isdir" argument..
@ 2020-03-09 03:57 Justin Pryzby <[email protected]>
  0 siblings, 0 replies; 16+ messages in thread

From: Justin Pryzby @ 2020-03-09 03:57 UTC (permalink / raw)

similar to pg_stat_file().

It's worth breaking the function's return type, since core postgres creates
"shared filesets" underneath the temp dirs, and it's unreasonable to not show
them here, and the alternative query to show them is unreasaonbly complicated.

See following commit which also adds these columns to the other pg_ls_*
functions.  Although I don't think it matters that they're easily UNIONed, it'd
still make great sense if they returned the same columns.

Need catversion bump
---
 doc/src/sgml/func.sgml                       | 22 +++++++++++---------
 src/backend/utils/adt/genfile.c              |  4 ++--
 src/include/catalog/pg_proc.dat              |  8 +++----
 src/test/regress/expected/misc_functions.out |  4 ++--
 src/test/regress/output/tablespace.source    |  4 ++--
 5 files changed, 22 insertions(+), 20 deletions(-)

diff --git a/doc/src/sgml/func.sgml b/doc/src/sgml/func.sgml
index 9d617f95b9..891b990859 100644
--- a/doc/src/sgml/func.sgml
+++ b/doc/src/sgml/func.sgml
@@ -25351,12 +25351,12 @@ postgres=# SELECT * FROM pg_walfile_name_offset(pg_stop_backup());
        </entry>
        <entry><type>setof record</type></entry>
        <entry>
-        List the name, size, and last modification time of files in the
-        temporary directory for <parameter>tablespace</parameter>.  If
-        <parameter>tablespace</parameter> is not provided, the
-        <literal>pg_default</literal> tablespace is used.  Access is granted
-        to members of the <literal>pg_monitor</literal> role and may be
-        granted to other non-superuser roles.
+        For the temporary directory within <parameter>tablespace</parameter>,
+        list each file's name, size, last modification time, and a boolean
+        indicating if it is a directory.  If <parameter>tablespace</parameter>
+        is not provided, the <literal>pg_default</literal> tablespace is used.
+        Access is granted to members of the <literal>pg_monitor</literal> role
+        and may be granted to other non-superuser roles.
        </entry>
       </row>
       <row>
@@ -25459,14 +25459,16 @@ postgres=# SELECT * FROM pg_walfile_name_offset(pg_stop_backup());
     <primary>pg_ls_tmpdir</primary>
    </indexterm>
    <para>
-    <function>pg_ls_tmpdir</function> returns the name, size, and last modified
-    time (mtime) of each file in the temporary file directory for the specified
-    <parameter>tablespace</parameter>.  If <parameter>tablespace</parameter> is
+    <function>pg_ls_tmpdir</function> lists each file in the temporary file
+    directory for the specified <parameter>tablespace</parameter>, along with
+    its size, last modified time (mtime) and a boolean indicating if the file is a
+    directory.  Directories are used for temporary files shared by parallel
+    processes.  If <parameter>tablespace</parameter> is
     not provided, the <literal>pg_default</literal> tablespace is used.  By
     default only superusers and members of the <literal>pg_monitor</literal>
     role can use this function.  Access may be granted to others using
     <command>GRANT</command>.
-    Filenames beginning with a dot, directories, and other special files are not shown.
+    Filenames beginning with a dot and special file types are not shown.
    </para>
 
    <indexterm>
diff --git a/src/backend/utils/adt/genfile.c b/src/backend/utils/adt/genfile.c
index 4824a55480..023f1ad605 100644
--- a/src/backend/utils/adt/genfile.c
+++ b/src/backend/utils/adt/genfile.c
@@ -481,7 +481,7 @@ pg_ls_dir_1arg(PG_FUNCTION_ARGS)
 }
 
 /*
- * Generic function to return a directory listing of files.
+ * Generic function to return a directory listing of files (and optionally dirs).
  *
  * If the directory isn't there, silently return an empty set if missing_ok.
  * Other unreadable-directory cases throw an error.
@@ -670,7 +670,7 @@ pg_ls_tmpdir(FunctionCallInfo fcinfo, Oid tblspc)
 
 	TempTablespacePath(path, tblspc);
 	return pg_ls_dir_files(fcinfo, path,
-			LS_DIR_HISTORIC | LS_DIR_MISSING_OK);
+			LS_DIR_SKIP_HIDDEN | LS_DIR_SKIP_SPECIAL | LS_DIR_ISDIR | LS_DIR_METADATA | LS_DIR_MISSING_OK);
 }
 
 /*
diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat
index 9f46cba5ed..dc3b497587 100644
--- a/src/include/catalog/pg_proc.dat
+++ b/src/include/catalog/pg_proc.dat
@@ -10896,13 +10896,13 @@
 { oid => '5029', descr => 'list files in the pgsql_tmp directory',
   proname => 'pg_ls_tmpdir', procost => '10', prorows => '20', proretset => 't',
   provolatile => 'v', prorettype => 'record', proargtypes => '',
-  proallargtypes => '{text,int8,timestamptz}', proargmodes => '{o,o,o}',
-  proargnames => '{name,size,modification}', prosrc => 'pg_ls_tmpdir_noargs' },
+  proallargtypes => '{text,int8,timestamptz,bool}', proargmodes => '{o,o,o,o}',
+  proargnames => '{name,size,modification,isdir}', prosrc => 'pg_ls_tmpdir_noargs' },
 { oid => '5030', descr => 'list files in the pgsql_tmp directory',
   proname => 'pg_ls_tmpdir', procost => '10', prorows => '20', proretset => 't',
   provolatile => 'v', prorettype => 'record', proargtypes => 'oid',
-  proallargtypes => '{oid,text,int8,timestamptz}', proargmodes => '{i,o,o,o}',
-  proargnames => '{tablespace,name,size,modification}',
+  proallargtypes => '{oid,text,int8,timestamptz,bool}', proargmodes => '{i,o,o,o,o}',
+  proargnames => '{tablespace,name,size,modification,isdir}',
   prosrc => 'pg_ls_tmpdir_1arg' },
 { oid => '5032', descr => 'list directory with metadata',
   proname => 'pg_ls_dir_metadata', procost => '10', prorows => '20', proretset => 't',
diff --git a/src/test/regress/expected/misc_functions.out b/src/test/regress/expected/misc_functions.out
index 7930909f02..38493de732 100644
--- a/src/test/regress/expected/misc_functions.out
+++ b/src/test/regress/expected/misc_functions.out
@@ -222,8 +222,8 @@ ERROR:  could not open directory "does not exist": No such file or directory
 -- This tests the missing_ok parameter, which causes pg_ls_tmpdir to succeed even if the tmpdir doesn't exist yet
 -- The name='' condition is never true, so the function runs to completion but returns zero rows.
 select * from pg_ls_tmpdir() where name='Does not exist';
- name | size | modification 
-------+------+--------------
+ name | size | modification | isdir 
+------+------+--------------+-------
 (0 rows)
 
 select name, isdir from pg_ls_dir_metadata('.') where name='.';
diff --git a/src/test/regress/output/tablespace.source b/src/test/regress/output/tablespace.source
index a42714bf40..1c88e914e3 100644
--- a/src/test/regress/output/tablespace.source
+++ b/src/test/regress/output/tablespace.source
@@ -17,8 +17,8 @@ CREATE TABLESPACE regress_tblspace LOCATION '@testtablespace@';
 -- The name='' condition is never true, so the function runs to completion but returns zero rows.
 -- The query is written to ERROR if the tablespace doesn't exist, rather than silently failing to call pg_ls_tmpdir()
 SELECT c.* FROM (SELECT oid FROM pg_tablespace b WHERE b.spcname='regress_tblspace' UNION SELECT 0 ORDER BY 1 DESC LIMIT 1) AS b , pg_ls_tmpdir(oid) AS c WHERE c.name='Does not exist';
- name | size | modification 
-------+------+--------------
+ name | size | modification | isdir 
+------+------+--------------+-------
 (0 rows)
 
 -- try setting and resetting some properties for the new tablespace
-- 
2.17.0


--2FkSFaIQeDFoAt0B
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
 filename="v16-0006-pg_ls_-dir-to-show-directories-and-isdir-column.patch"



^ permalink  raw  reply  [nested|flat] 16+ messages in thread

* [PATCH v21 2/3] AVX512 popcount support
@ 2024-03-27 21:39 Nathan Bossart <[email protected]>
  0 siblings, 0 replies; 16+ messages in thread

From: Nathan Bossart @ 2024-03-27 21:39 UTC (permalink / raw)

---
 config/c-compiler.m4                 |  58 ++++++
 configure                            | 252 +++++++++++++++++++++++++++
 configure.ac                         |  51 ++++++
 meson.build                          |  87 +++++++++
 src/Makefile.global.in               |   5 +
 src/include/pg_config.h.in           |  12 ++
 src/include/port/pg_bitutils.h       |  15 ++
 src/makefiles/meson.build            |   4 +-
 src/port/Makefile                    |  11 ++
 src/port/meson.build                 |   6 +-
 src/port/pg_bitutils.c               |  29 ++-
 src/port/pg_popcount_avx512.c        |  49 ++++++
 src/port/pg_popcount_avx512_choose.c |  71 ++++++++
 src/test/regress/expected/bit.out    |  24 +++
 src/test/regress/sql/bit.sql         |   4 +
 15 files changed, 673 insertions(+), 5 deletions(-)
 create mode 100644 src/port/pg_popcount_avx512.c
 create mode 100644 src/port/pg_popcount_avx512_choose.c

diff --git a/config/c-compiler.m4 b/config/c-compiler.m4
index 3268a780bb..5fb60775ca 100644
--- a/config/c-compiler.m4
+++ b/config/c-compiler.m4
@@ -694,3 +694,61 @@ if test x"$Ac_cachevar" = x"yes"; then
 fi
 undefine([Ac_cachevar])dnl
 ])# PGAC_LOONGARCH_CRC32C_INTRINSICS
+
+# PGAC_XSAVE_INTRINSICS
+# ---------------------
+# Check if the compiler supports the XSAVE instructions using the _xgetbv
+# intrinsic function.
+#
+# An optional compiler flag can be passed as argument (e.g., -mxsave).  If the
+# intrinsic is supported, sets pgac_xsave_intrinsics and CFLAGS_XSAVE.
+AC_DEFUN([PGAC_XSAVE_INTRINSICS],
+[define([Ac_cachevar], [AS_TR_SH([pgac_cv_xsave_intrinsics_$1])])dnl
+AC_CACHE_CHECK([for _xgetbv with CFLAGS=$1], [Ac_cachevar],
+[pgac_save_CFLAGS=$CFLAGS
+CFLAGS="$pgac_save_CFLAGS $1"
+AC_LINK_IFELSE([AC_LANG_PROGRAM([#include <immintrin.h>],
+  [return _xgetbv(0) & 0xe0;])],
+  [Ac_cachevar=yes],
+  [Ac_cachevar=no])
+CFLAGS="$pgac_save_CFLAGS"])
+if test x"$Ac_cachevar" = x"yes"; then
+  CFLAGS_XSAVE="$1"
+  pgac_xsave_intrinsics=yes
+fi
+undefine([Ac_cachevar])dnl
+])# PGAC_XSAVE_INTRINSICS
+
+# PGAC_AVX512_POPCNT_INTRINSICS
+# -----------------------------
+# Check if the compiler supports the AVX512 POPCNT instructions using the
+# _mm512_setzero_si512, _mm512_loadu_si512, _mm512_popcnt_epi64,
+# _mm512_add_epi64, and _mm512_reduce_add_epi64 intrinsic functions.
+#
+# An optional compiler flag can be passed as argument
+# (e.g., -mavx512vpopcntdq).  If the intrinsics are supported, sets
+# pgac_avx512_popcnt_intrinsics and CFLAGS_POPCNT.
+AC_DEFUN([PGAC_AVX512_POPCNT_INTRINSICS],
+[define([Ac_cachevar], [AS_TR_SH([pgac_cv_avx512_popcnt_intrinsics_$1])])dnl
+AC_CACHE_CHECK([for _mm512_popcnt_epi64 with CFLAGS=$1], [Ac_cachevar],
+[pgac_save_CFLAGS=$CFLAGS
+CFLAGS="$pgac_save_CFLAGS $1"
+AC_LINK_IFELSE([AC_LANG_PROGRAM([#include <immintrin.h>],
+  [const char buf@<:@sizeof(__m512i)@:>@;
+   PG_INT64_TYPE popcnt = 0;
+   __m512i accum = _mm512_setzero_si512();
+   const __m512i val = _mm512_loadu_si512((const __m512i *) buf);
+   const __m512i cnt = _mm512_popcnt_epi64(val);
+   accum = _mm512_add_epi64(accum, cnt);
+   popcnt = _mm512_reduce_add_epi64(accum);
+   /* return computed value, to prevent the above being optimized away */
+   return popcnt == 0;])],
+  [Ac_cachevar=yes],
+  [Ac_cachevar=no])
+CFLAGS="$pgac_save_CFLAGS"])
+if test x"$Ac_cachevar" = x"yes"; then
+  CFLAGS_POPCNT="$1"
+  pgac_avx512_popcnt_intrinsics=yes
+fi
+undefine([Ac_cachevar])dnl
+])# PGAC_AVX512_POPCNT_INTRINSICS
diff --git a/configure b/configure
index 36feeafbb2..b48ed7f271 100755
--- a/configure
+++ b/configure
@@ -647,6 +647,9 @@ MSGFMT_FLAGS
 MSGFMT
 PG_CRC32C_OBJS
 CFLAGS_CRC
+PG_POPCNT_OBJS
+CFLAGS_POPCNT
+CFLAGS_XSAVE
 LIBOBJS
 OPENSSL
 ZSTD
@@ -17404,6 +17407,40 @@ $as_echo "#define HAVE__GET_CPUID 1" >>confdefs.h
 
 fi
 
+{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for __get_cpuid_count" >&5
+$as_echo_n "checking for __get_cpuid_count... " >&6; }
+if ${pgac_cv__get_cpuid_count+:} 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_count(7, 0, &exx[0], &exx[1], &exx[2], &exx[3]);
+
+  ;
+  return 0;
+}
+_ACEOF
+if ac_fn_c_try_link "$LINENO"; then :
+  pgac_cv__get_cpuid_count="yes"
+else
+  pgac_cv__get_cpuid_count="no"
+fi
+rm -f core conftest.err conftest.$ac_objext \
+    conftest$ac_exeext conftest.$ac_ext
+fi
+{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $pgac_cv__get_cpuid_count" >&5
+$as_echo "$pgac_cv__get_cpuid_count" >&6; }
+if test x"$pgac_cv__get_cpuid_count" = x"yes"; then
+
+$as_echo "#define HAVE__GET_CPUID_COUNT 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 :
@@ -17438,6 +17475,221 @@ $as_echo "#define HAVE__CPUID 1" >>confdefs.h
 
 fi
 
+{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for __cpuidex" >&5
+$as_echo_n "checking for __cpuidex... " >&6; }
+if ${pgac_cv__cpuidex+:} 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_cpuidex(exx[0], 7, 0);
+
+  ;
+  return 0;
+}
+_ACEOF
+if ac_fn_c_try_link "$LINENO"; then :
+  pgac_cv__cpuidex="yes"
+else
+  pgac_cv__cpuidex="no"
+fi
+rm -f core conftest.err conftest.$ac_objext \
+    conftest$ac_exeext conftest.$ac_ext
+fi
+{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $pgac_cv__cpuidex" >&5
+$as_echo "$pgac_cv__cpuidex" >&6; }
+if test x"$pgac_cv__cpuidex" = x"yes"; then
+
+$as_echo "#define HAVE__CPUIDEX 1" >>confdefs.h
+
+fi
+
+# Check for XSAVE intrinsics
+#
+CFLAGS_XSAVE=""
+{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for _xgetbv with CFLAGS=" >&5
+$as_echo_n "checking for _xgetbv with CFLAGS=... " >&6; }
+if ${pgac_cv_xsave_intrinsics_+:} false; then :
+  $as_echo_n "(cached) " >&6
+else
+  pgac_save_CFLAGS=$CFLAGS
+CFLAGS="$pgac_save_CFLAGS "
+cat confdefs.h - <<_ACEOF >conftest.$ac_ext
+/* end confdefs.h.  */
+#include <immintrin.h>
+int
+main ()
+{
+return _xgetbv(0) & 0xe0;
+  ;
+  return 0;
+}
+_ACEOF
+if ac_fn_c_try_link "$LINENO"; then :
+  pgac_cv_xsave_intrinsics_=yes
+else
+  pgac_cv_xsave_intrinsics_=no
+fi
+rm -f core conftest.err conftest.$ac_objext \
+    conftest$ac_exeext conftest.$ac_ext
+CFLAGS="$pgac_save_CFLAGS"
+fi
+{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $pgac_cv_xsave_intrinsics_" >&5
+$as_echo "$pgac_cv_xsave_intrinsics_" >&6; }
+if test x"$pgac_cv_xsave_intrinsics_" = x"yes"; then
+  CFLAGS_XSAVE=""
+  pgac_xsave_intrinsics=yes
+fi
+
+if test x"$pgac_xsave_intrinsics" != x"yes"; then
+  { $as_echo "$as_me:${as_lineno-$LINENO}: checking for _xgetbv with CFLAGS=-mxsave" >&5
+$as_echo_n "checking for _xgetbv with CFLAGS=-mxsave... " >&6; }
+if ${pgac_cv_xsave_intrinsics__mxsave+:} false; then :
+  $as_echo_n "(cached) " >&6
+else
+  pgac_save_CFLAGS=$CFLAGS
+CFLAGS="$pgac_save_CFLAGS -mxsave"
+cat confdefs.h - <<_ACEOF >conftest.$ac_ext
+/* end confdefs.h.  */
+#include <immintrin.h>
+int
+main ()
+{
+return _xgetbv(0) & 0xe0;
+  ;
+  return 0;
+}
+_ACEOF
+if ac_fn_c_try_link "$LINENO"; then :
+  pgac_cv_xsave_intrinsics__mxsave=yes
+else
+  pgac_cv_xsave_intrinsics__mxsave=no
+fi
+rm -f core conftest.err conftest.$ac_objext \
+    conftest$ac_exeext conftest.$ac_ext
+CFLAGS="$pgac_save_CFLAGS"
+fi
+{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $pgac_cv_xsave_intrinsics__mxsave" >&5
+$as_echo "$pgac_cv_xsave_intrinsics__mxsave" >&6; }
+if test x"$pgac_cv_xsave_intrinsics__mxsave" = x"yes"; then
+  CFLAGS_XSAVE="-mxsave"
+  pgac_xsave_intrinsics=yes
+fi
+
+fi
+if test x"$pgac_xsave_intrinsics" = x"yes"; then
+
+$as_echo "#define HAVE_XSAVE_INTRINSICS 1" >>confdefs.h
+
+fi
+
+
+# Check for AVX512 popcount intrinsics
+#
+CFLAGS_POPCNT=""
+PG_POPCNT_OBJS=""
+if test x"$host_cpu" = x"x86_64"; then
+  { $as_echo "$as_me:${as_lineno-$LINENO}: checking for _mm512_popcnt_epi64 with CFLAGS=" >&5
+$as_echo_n "checking for _mm512_popcnt_epi64 with CFLAGS=... " >&6; }
+if ${pgac_cv_avx512_popcnt_intrinsics_+:} false; then :
+  $as_echo_n "(cached) " >&6
+else
+  pgac_save_CFLAGS=$CFLAGS
+CFLAGS="$pgac_save_CFLAGS "
+cat confdefs.h - <<_ACEOF >conftest.$ac_ext
+/* end confdefs.h.  */
+#include <immintrin.h>
+int
+main ()
+{
+const char buf[sizeof(__m512i)];
+   PG_INT64_TYPE popcnt = 0;
+   __m512i accum = _mm512_setzero_si512();
+   const __m512i val = _mm512_loadu_si512((const __m512i *) buf);
+   const __m512i cnt = _mm512_popcnt_epi64(val);
+   accum = _mm512_add_epi64(accum, cnt);
+   popcnt = _mm512_reduce_add_epi64(accum);
+   /* return computed value, to prevent the above being optimized away */
+   return popcnt == 0;
+  ;
+  return 0;
+}
+_ACEOF
+if ac_fn_c_try_link "$LINENO"; then :
+  pgac_cv_avx512_popcnt_intrinsics_=yes
+else
+  pgac_cv_avx512_popcnt_intrinsics_=no
+fi
+rm -f core conftest.err conftest.$ac_objext \
+    conftest$ac_exeext conftest.$ac_ext
+CFLAGS="$pgac_save_CFLAGS"
+fi
+{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $pgac_cv_avx512_popcnt_intrinsics_" >&5
+$as_echo "$pgac_cv_avx512_popcnt_intrinsics_" >&6; }
+if test x"$pgac_cv_avx512_popcnt_intrinsics_" = x"yes"; then
+  CFLAGS_POPCNT=""
+  pgac_avx512_popcnt_intrinsics=yes
+fi
+
+  if test x"$pgac_avx512_popcnt_intrinsics" != x"yes"; then
+    { $as_echo "$as_me:${as_lineno-$LINENO}: checking for _mm512_popcnt_epi64 with CFLAGS=-mavx512vpopcntdq" >&5
+$as_echo_n "checking for _mm512_popcnt_epi64 with CFLAGS=-mavx512vpopcntdq... " >&6; }
+if ${pgac_cv_avx512_popcnt_intrinsics__mavx512vpopcntdq+:} false; then :
+  $as_echo_n "(cached) " >&6
+else
+  pgac_save_CFLAGS=$CFLAGS
+CFLAGS="$pgac_save_CFLAGS -mavx512vpopcntdq"
+cat confdefs.h - <<_ACEOF >conftest.$ac_ext
+/* end confdefs.h.  */
+#include <immintrin.h>
+int
+main ()
+{
+const char buf[sizeof(__m512i)];
+   PG_INT64_TYPE popcnt = 0;
+   __m512i accum = _mm512_setzero_si512();
+   const __m512i val = _mm512_loadu_si512((const __m512i *) buf);
+   const __m512i cnt = _mm512_popcnt_epi64(val);
+   accum = _mm512_add_epi64(accum, cnt);
+   popcnt = _mm512_reduce_add_epi64(accum);
+   /* return computed value, to prevent the above being optimized away */
+   return popcnt == 0;
+  ;
+  return 0;
+}
+_ACEOF
+if ac_fn_c_try_link "$LINENO"; then :
+  pgac_cv_avx512_popcnt_intrinsics__mavx512vpopcntdq=yes
+else
+  pgac_cv_avx512_popcnt_intrinsics__mavx512vpopcntdq=no
+fi
+rm -f core conftest.err conftest.$ac_objext \
+    conftest$ac_exeext conftest.$ac_ext
+CFLAGS="$pgac_save_CFLAGS"
+fi
+{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $pgac_cv_avx512_popcnt_intrinsics__mavx512vpopcntdq" >&5
+$as_echo "$pgac_cv_avx512_popcnt_intrinsics__mavx512vpopcntdq" >&6; }
+if test x"$pgac_cv_avx512_popcnt_intrinsics__mavx512vpopcntdq" = x"yes"; then
+  CFLAGS_POPCNT="-mavx512vpopcntdq"
+  pgac_avx512_popcnt_intrinsics=yes
+fi
+
+  fi
+  if test x"$pgac_avx512_popcnt_intrinsics" = x"yes"; then
+    PG_POPCNT_OBJS="pg_popcount_avx512.o pg_popcount_avx512_choose.o"
+
+$as_echo "#define USE_AVX512_POPCNT_WITH_RUNTIME_CHECK 1" >>confdefs.h
+
+  fi
+fi
+
+
+
 # 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
diff --git a/configure.ac b/configure.ac
index 57f734879e..2bbd81dfb8 100644
--- a/configure.ac
+++ b/configure.ac
@@ -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"$pgac_xsave_intrinsics" = x"yes"; then
+  AC_DEFINE(HAVE_XSAVE_INTRINSICS, 1, [Define to 1 if you have XSAVE intrinsics.])
+fi
+AC_SUBST(CFLAGS_XSAVE)
+
+# Check for AVX512 popcount intrinsics
+#
+CFLAGS_POPCNT=""
+PG_POPCNT_OBJS=""
+if test x"$host_cpu" = x"x86_64"; then
+  PGAC_AVX512_POPCNT_INTRINSICS([])
+  if test x"$pgac_avx512_popcnt_intrinsics" != x"yes"; then
+    PGAC_AVX512_POPCNT_INTRINSICS([-mavx512vpopcntdq])
+  fi
+  if test x"$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 AVX512 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
diff --git a/meson.build b/meson.build
index 18b5be842e..96be29c22b 100644
--- a/meson.build
+++ b/meson.build
@@ -1783,6 +1783,30 @@ elif cc.links('''
 endif
 
 
+# Check for __get_cpuid_count() and __cpuidex() in a similar fashion.
+if cc.links('''
+    #include <cpuid.h>
+    int main(int arg, char **argv)
+    {
+        unsigned int exx[4] = {0, 0, 0, 0};
+        __get_cpuid_count(7, 0, &exx[0], &exx[1], &exx[2], &exx[3]);
+    }
+    ''', name: '__get_cpuid_count',
+    args: test_c_args)
+  cdata.set('HAVE__GET_CPUID_COUNT', 1)
+elif cc.links('''
+    #include <intrin.h>
+    int main(int arg, char **argv)
+    {
+        unsigned int exx[4] = {0, 0, 0, 0};
+        __cpuidex(exx, 7, 0);
+    }
+    ''', name: '__cpuidex',
+    args: test_c_args)
+  cdata.set('HAVE__CPUIDEX', 1)
+endif
+
+
 # Defend against clang being used on x86-32 without SSE2 enabled.  As current
 # versions of clang do not understand -fexcess-precision=standard, the use of
 # x87 floating point operations leads to problems like isinf possibly returning
@@ -1996,6 +2020,69 @@ int main(void)
 endif
 
 
+###############################################################
+# Check for the availability of XSAVE intrinsics.
+###############################################################
+
+cflags_xsave = []
+if host_cpu == 'x86' or host_cpu == 'x86_64'
+
+  prog = '''
+#include <immintrin.h>
+
+int main(void)
+{
+    return _xgetbv(0) & 0xe0;
+}
+'''
+
+  if cc.links(prog, name: 'XSAVE intrinsics without -mxsave',
+        args: test_c_args)
+    cdata.set('HAVE_XSAVE_INTRINSICS', 1)
+  elif cc.links(prog, name: 'XSAVE intrinsics with -mxsave',
+        args: test_c_args + ['-mxsave'])
+    cdata.set('HAVE_XSAVE_INTRINSICS', 1)
+    cflags_xsave += '-mxsave'
+  endif
+
+endif
+
+
+###############################################################
+# Check for the availability of AVX512 popcount intrinsics.
+###############################################################
+
+cflags_popcnt = []
+if host_cpu == 'x86_64'
+
+  prog = '''
+#include <immintrin.h>
+
+int main(void)
+{
+    const char buf[sizeof(__m512i)];
+    INT64 popcnt = 0;
+    __m512i accum = _mm512_setzero_si512();
+    const __m512i val = _mm512_loadu_si512((const __m512i *) buf);
+    const __m512i cnt = _mm512_popcnt_epi64(val);
+    accum = _mm512_add_epi64(accum, cnt);
+    popcnt = _mm512_reduce_add_epi64(accum);
+    /* return computed value, to prevent the above being optimized away */
+    return popcnt == 0;
+}
+'''
+
+  if cc.links(prog, name: 'AVX512 popcount without -mavx512vpopcntdq',
+        args: test_c_args + ['-DINT64=@0@'.format(cdata.get('PG_INT64_TYPE'))])
+    cdata.set('USE_AVX512_POPCNT_WITH_RUNTIME_CHECK', 1)
+  elif cc.links(prog, name: 'AVX512 popcount with -mavx512vpopcntdq',
+        args: test_c_args + ['-DINT64=@0@'.format(cdata.get('PG_INT64_TYPE'))] + ['-mavx512vpopcntdq'])
+    cdata.set('USE_AVX512_POPCNT_WITH_RUNTIME_CHECK', 1)
+    cflags_popcnt += '-mavx512vpopcntdq'
+  endif
+
+endif
+
 
 ###############################################################
 # Select CRC-32C implementation.
diff --git a/src/Makefile.global.in b/src/Makefile.global.in
index 8b3f8c24e0..36d880d225 100644
--- a/src/Makefile.global.in
+++ b/src/Makefile.global.in
@@ -262,7 +262,9 @@ CFLAGS_SL_MODULE = @CFLAGS_SL_MODULE@
 CXXFLAGS_SL_MODULE = @CXXFLAGS_SL_MODULE@
 CFLAGS_UNROLL_LOOPS = @CFLAGS_UNROLL_LOOPS@
 CFLAGS_VECTORIZE = @CFLAGS_VECTORIZE@
+CFLAGS_POPCNT = @CFLAGS_POPCNT@
 CFLAGS_CRC = @CFLAGS_CRC@
+CFLAGS_XSAVE = @CFLAGS_XSAVE@
 PERMIT_DECLARATION_AFTER_STATEMENT = @PERMIT_DECLARATION_AFTER_STATEMENT@
 CXXFLAGS = @CXXFLAGS@
 
@@ -758,6 +760,9 @@ LIBOBJS = @LIBOBJS@
 # files needed for the chosen CRC-32C implementation
 PG_CRC32C_OBJS = @PG_CRC32C_OBJS@
 
+# files needed for the chosen popcount implementation
+PG_POPCNT_OBJS = @PG_POPCNT_OBJS@
+
 LIBS := -lpgcommon -lpgport $(LIBS)
 
 # to make ws2_32.lib the last library
diff --git a/src/include/pg_config.h.in b/src/include/pg_config.h.in
index 591e1ca3df..de067e6182 100644
--- a/src/include/pg_config.h.in
+++ b/src/include/pg_config.h.in
@@ -513,6 +513,9 @@
 /* Define to 1 if the assembler supports X86_64's POPCNTQ instruction. */
 #undef HAVE_X86_64_POPCNTQ
 
+/* Define to 1 if you have XSAVE intrinsics. */
+#undef HAVE_XSAVE_INTRINSICS
+
 /* Define to 1 if the system has the type `_Bool'. */
 #undef HAVE__BOOL
 
@@ -555,9 +558,15 @@
 /* Define to 1 if you have __cpuid. */
 #undef HAVE__CPUID
 
+/* Define to 1 if you have __cpuidex. */
+#undef HAVE__CPUIDEX
+
 /* Define to 1 if you have __get_cpuid. */
 #undef HAVE__GET_CPUID
 
+/* Define to 1 if you have __get_cpuid_count. */
+#undef HAVE__GET_CPUID_COUNT
+
 /* Define to 1 if your compiler understands _Static_assert. */
 #undef HAVE__STATIC_ASSERT
 
@@ -680,6 +689,9 @@
 /* Define to 1 to build with assertion checks. (--enable-cassert) */
 #undef USE_ASSERT_CHECKING
 
+/* Define to 1 to use AVX512 popcount instructions with a runtime check. */
+#undef USE_AVX512_POPCNT_WITH_RUNTIME_CHECK
+
 /* Define to 1 to build with Bonjour support. (--with-bonjour) */
 #undef USE_BONJOUR
 
diff --git a/src/include/port/pg_bitutils.h b/src/include/port/pg_bitutils.h
index 1f487a4bc3..e4e96952b7 100644
--- a/src/include/port/pg_bitutils.h
+++ b/src/include/port/pg_bitutils.h
@@ -304,6 +304,21 @@ extern PGDLLIMPORT int (*pg_popcount32) (uint32 word);
 extern PGDLLIMPORT int (*pg_popcount64) (uint64 word);
 extern PGDLLIMPORT uint64 (*pg_popcount_optimized) (const char *buf, int bytes);
 
+/* Export pg_popcount_fast() for use in the AVX512 implementation. */
+extern uint64 pg_popcount_fast(const char *buf, int bytes);
+
+/*
+ * We can also try to use the AVX512 popcount instruction on some systems.
+ * The implementation of that is located in its own file because it may
+ * require special compiler flags that we don't want to apply to any other
+ * files.  Note that we only build this when TRY_POPCNT_FAST is set so that we
+ * can fall back to pg_popcount_fast() as needed.
+ */
+#ifdef USE_AVX512_POPCNT_WITH_RUNTIME_CHECK
+extern bool pg_popcount_avx512_available(void);
+extern uint64 pg_popcount_avx512(const char *buf, int bytes);
+#endif
+
 #else
 /* Use a portable implementation -- no need for a function pointer. */
 extern int	pg_popcount32(uint32 word);
diff --git a/src/makefiles/meson.build b/src/makefiles/meson.build
index b0f4178b3d..5618050b30 100644
--- a/src/makefiles/meson.build
+++ b/src/makefiles/meson.build
@@ -100,8 +100,10 @@ pgxs_kv = {
     ' '.join(cflags_no_decl_after_statement),
 
   'CFLAGS_CRC': ' '.join(cflags_crc),
+  'CFLAGS_POPCNT': ' '.join(cflags_popcnt),
   'CFLAGS_UNROLL_LOOPS': ' '.join(unroll_loops_cflags),
   'CFLAGS_VECTORIZE': ' '.join(vectorize_cflags),
+  'CFLAGS_XSAVE': ' '.join(cflags_xsave),
 
   'LDFLAGS': var_ldflags,
   'LDFLAGS_EX': var_ldflags_ex,
@@ -177,7 +179,7 @@ pgxs_empty = [
   'WANTED_LANGUAGES',
 
   # Not needed because we don't build the server / PLs with the generated makefile
-  'LIBOBJS', 'PG_CRC32C_OBJS', 'TAS',
+  'LIBOBJS', 'PG_CRC32C_OBJS', 'PG_POPCNT_OBJS', 'TAS',
   'DTRACEFLAGS', # only server has dtrace probes
 
   'perl_archlibexp', 'perl_embed_ccflags', 'perl_embed_ldflags', 'perl_includespec', 'perl_privlibexp',
diff --git a/src/port/Makefile b/src/port/Makefile
index dcc8737e68..db7c02117b 100644
--- a/src/port/Makefile
+++ b/src/port/Makefile
@@ -38,6 +38,7 @@ LIBS += $(PTHREAD_LIBS)
 OBJS = \
 	$(LIBOBJS) \
 	$(PG_CRC32C_OBJS) \
+	$(PG_POPCNT_OBJS) \
 	bsearch_arg.o \
 	chklocale.o \
 	inet_net_ntop.o \
@@ -92,6 +93,16 @@ pg_crc32c_armv8.o: CFLAGS+=$(CFLAGS_CRC)
 pg_crc32c_armv8_shlib.o: CFLAGS+=$(CFLAGS_CRC)
 pg_crc32c_armv8_srv.o: CFLAGS+=$(CFLAGS_CRC)
 
+# all versions of pg_popcount_avx512_choose.o need CFLAGS_XSAVE
+pg_popcount_avx512_choose.o: CFLAGS+=$(CFLAGS_XSAVE)
+pg_popcount_avx512_choose_shlib.o: CFLAGS+=$(CFLAGS_XSAVE)
+pg_popcount_avx512_choose_srv.o: CFLAGS+=$(CFLAGS_XSAVE)
+
+# all versions of pg_popcount_avx512.o need CFLAGS_POPCNT
+pg_popcount_avx512.o: CFLAGS+=$(CFLAGS_POPCNT)
+pg_popcount_avx512_shlib.o: CFLAGS+=$(CFLAGS_POPCNT)
+pg_popcount_avx512_srv.o: CFLAGS+=$(CFLAGS_POPCNT)
+
 #
 # Shared library versions of object files
 #
diff --git a/src/port/meson.build b/src/port/meson.build
index 92b593e6ef..fd9ee199d1 100644
--- a/src/port/meson.build
+++ b/src/port/meson.build
@@ -84,6 +84,8 @@ replace_funcs_pos = [
   ['pg_crc32c_sse42', 'USE_SSE42_CRC32C_WITH_RUNTIME_CHECK', 'crc'],
   ['pg_crc32c_sse42_choose', 'USE_SSE42_CRC32C_WITH_RUNTIME_CHECK'],
   ['pg_crc32c_sb8', 'USE_SSE42_CRC32C_WITH_RUNTIME_CHECK'],
+  ['pg_popcount_avx512', 'USE_AVX512_POPCNT_WITH_RUNTIME_CHECK', 'popcnt'],
+  ['pg_popcount_avx512_choose', 'USE_AVX512_POPCNT_WITH_RUNTIME_CHECK', 'xsave'],
 
   # arm / aarch64
   ['pg_crc32c_armv8', 'USE_ARMV8_CRC32C'],
@@ -98,8 +100,8 @@ replace_funcs_pos = [
   ['pg_crc32c_sb8', 'USE_SLICING_BY_8_CRC32C'],
 ]
 
-pgport_cflags = {'crc': cflags_crc}
-pgport_sources_cflags = {'crc': []}
+pgport_cflags = {'crc': cflags_crc, 'popcnt': cflags_popcnt, 'xsave': cflags_xsave}
+pgport_sources_cflags = {'crc': [], 'popcnt': [], 'xsave': []}
 
 foreach f : replace_funcs_neg
   func = f.get(0)
diff --git a/src/port/pg_bitutils.c b/src/port/pg_bitutils.c
index 4720f8e419..b02721b7e5 100644
--- a/src/port/pg_bitutils.c
+++ b/src/port/pg_bitutils.c
@@ -114,7 +114,10 @@ static int	pg_popcount64_choose(uint64 word);
 static uint64 pg_popcount_choose(const char *buf, int bytes);
 static inline int pg_popcount32_fast(uint32 word);
 static inline int pg_popcount64_fast(uint64 word);
-static uint64 pg_popcount_fast(const char *buf, int bytes);
+
+#ifdef USE_AVX512_POPCNT_WITH_RUNTIME_CHECK
+static uint64 pg_popcount_fast_or_avx512(const char *buf, int bytes);
+#endif
 
 int			(*pg_popcount32) (uint32 word) = pg_popcount32_choose;
 int			(*pg_popcount64) (uint64 word) = pg_popcount64_choose;
@@ -156,6 +159,10 @@ choose_popcount_functions(void)
 		pg_popcount32 = pg_popcount32_fast;
 		pg_popcount64 = pg_popcount64_fast;
 		pg_popcount_optimized = pg_popcount_fast;
+#ifdef USE_AVX512_POPCNT_WITH_RUNTIME_CHECK
+		if (pg_popcount_avx512_available())
+			pg_popcount_optimized = pg_popcount_fast_or_avx512;
+#endif
 	}
 	else
 	{
@@ -224,7 +231,7 @@ __asm__ __volatile__(" popcntq %1,%0\n":"=q"(res):"rm"(word):"cc");
  * pg_popcount_fast
  *		Returns the number of 1-bits in buf
  */
-static uint64
+uint64
 pg_popcount_fast(const char *buf, int bytes)
 {
 	uint64		popcnt = 0;
@@ -266,6 +273,24 @@ pg_popcount_fast(const char *buf, int bytes)
 	return popcnt;
 }
 
+/*
+ * This is a wrapper function for pg_popcount_avx512() that uses
+ * pg_popcount_fast() when there aren't enough bytes to fit in an AVX-512
+ * register.  The compiler should be able to inline pg_popcount_fast() so that
+ * we only take on additional function call overhead when it's likely to be a
+ * better option.
+ */
+#ifdef USE_AVX512_POPCNT_WITH_RUNTIME_CHECK
+static uint64
+pg_popcount_fast_or_avx512(const char *buf, int bytes)
+{
+	if (bytes < 64)
+		return pg_popcount_fast(buf, bytes);
+	else
+		return pg_popcount_avx512(buf, bytes);
+}
+#endif							/* USE_AVX512_POPCNT_WITH_RUNTIME_CHECK */
+
 #endif							/* TRY_POPCNT_FAST */
 
 
diff --git a/src/port/pg_popcount_avx512.c b/src/port/pg_popcount_avx512.c
new file mode 100644
index 0000000000..f86558d1ee
--- /dev/null
+++ b/src/port/pg_popcount_avx512.c
@@ -0,0 +1,49 @@
+/*-------------------------------------------------------------------------
+ *
+ * pg_popcount_avx512.c
+ *	  Holds the pg_popcount() implementation that uses AVX512 instructions.
+ *
+ * Copyright (c) 2024, PostgreSQL Global Development Group
+ *
+ * IDENTIFICATION
+ *	  src/port/pg_popcount_avx512.c
+ *
+ *-------------------------------------------------------------------------
+ */
+#include "c.h"
+
+#include <immintrin.h>
+
+#include "port/pg_bitutils.h"
+
+/*
+ * It's probably unlikely that TRY_POPCNT_FAST won't be set if we are able to
+ * use AVX512 intrinsics, but we check it anyway to be sure.  We rely on
+ * pg_popcount_fast() as our fallback implementation in pg_popcount_avx512().
+ */
+#ifdef TRY_POPCNT_FAST
+
+/*
+ * pg_popcount_avx512
+ *		Returns the number of 1-bits in buf
+ */
+uint64
+pg_popcount_avx512(const char *buf, int bytes)
+{
+	uint64		popcnt;
+	__m512i		accum = _mm512_setzero_si512();
+
+	for (; bytes >= sizeof(__m512i); bytes -= sizeof(__m512i))
+	{
+		const		__m512i val = _mm512_loadu_si512((const __m512i *) buf);
+		const		__m512i cnt = _mm512_popcnt_epi64(val);
+
+		accum = _mm512_add_epi64(accum, cnt);
+		buf += sizeof(__m512i);
+	}
+
+	popcnt = _mm512_reduce_add_epi64(accum);
+	return popcnt + pg_popcount_fast(buf, bytes);
+}
+
+#endif							/* TRY_POPCNT_FAST */
diff --git a/src/port/pg_popcount_avx512_choose.c b/src/port/pg_popcount_avx512_choose.c
new file mode 100644
index 0000000000..9e81cd33ad
--- /dev/null
+++ b/src/port/pg_popcount_avx512_choose.c
@@ -0,0 +1,71 @@
+/*-------------------------------------------------------------------------
+ *
+ * pg_popcount_avx512_choose.c
+ *    Test whether we can use AVX512 POPCNT instructions.
+ *
+ * Copyright (c) 2024, PostgreSQL Global Development Group
+ *
+ * IDENTIFICATION
+ *    src/port/pg_popcount_avx512_choose.c
+ *
+ *-------------------------------------------------------------------------
+ */
+#include "c.h"
+
+#if defined(HAVE__GET_CPUID) || defined(HAVE__GET_CPUID_COUNT)
+#include <cpuid.h>
+#endif
+
+#ifdef HAVE_XSAVE_INTRINSICS
+#include <immintrin.h>
+#endif
+
+#if defined(HAVE__CPUID) || defined(HAVE__CPUIDEX)
+#include <intrin.h>
+#endif
+
+#include "port/pg_bitutils.h"
+
+/*
+ * It's probably unlikely that TRY_POPCNT_FAST won't be set if we are able to
+ * use AVX512 intrinsics, but we check it anyway to be sure.  We rely on
+ * pg_popcount_fast() as our fallback implementation in pg_popcount_avx512().
+ */
+#ifdef TRY_POPCNT_FAST
+
+/*
+ * Returns true if the CPU supports AVX512 POPCNT.
+ */
+bool
+pg_popcount_avx512_available(void)
+{
+	unsigned int exx[4] = {0, 0, 0, 0};
+
+	/* does CPUID say there's support for AVX512 POPCNT? */
+#if defined(HAVE__GET_CPUID_COUNT)
+	__get_cpuid_count(7, 0, &exx[0], &exx[1], &exx[2], &exx[3]);
+#elif defined(HAVE__CPUIDEX)
+	__cpuidex(exx, 7, 0);
+#endif
+	if ((exx[2] & (1 << 14)) == 0)	/* avx512vpopcntdq */
+		return false;
+
+	/* does CPUID say there's support for XGETBV? */
+	memset(exx, 0, sizeof(exx));
+#if defined(HAVE__GET_CPUID)
+	__get_cpuid(1, &exx[0], &exx[1], &exx[2], &exx[3]);
+#elif defined(HAVE__CPUID)
+	__cpuid(exx, 1);
+#endif
+	if ((exx[2] & (1 << 26)) == 0)	/* xsave */
+		return false;
+
+	/* does XGETBV say the ZMM registers are enabled? */
+#ifdef HAVE_XSAVE_INTRINSICS
+	return (_xgetbv(0) & 0xe0) != 0;
+#else
+	return false;
+#endif
+}
+
+#endif							/* TRY_POPCNT_FAST */
diff --git a/src/test/regress/expected/bit.out b/src/test/regress/expected/bit.out
index e17cbf42ca..6a436288bb 100644
--- a/src/test/regress/expected/bit.out
+++ b/src/test/regress/expected/bit.out
@@ -740,6 +740,30 @@ SELECT bit_count(B'1111111111'::bit(10));
         10
 (1 row)
 
+SELECT bit_count(repeat('0', 100)::bit(100));
+ bit_count 
+-----------
+         0
+(1 row)
+
+SELECT bit_count(repeat('1', 100)::bit(100));
+ bit_count 
+-----------
+       100
+(1 row)
+
+SELECT bit_count(repeat('01', 500)::bit(1000));
+ bit_count 
+-----------
+       500
+(1 row)
+
+SELECT bit_count(repeat('10101', 200)::bit(1000));
+ bit_count 
+-----------
+       600
+(1 row)
+
 -- This table is intentionally left around to exercise pg_dump/pg_upgrade
 CREATE TABLE bit_defaults(
   b1 bit(4) DEFAULT '1001',
diff --git a/src/test/regress/sql/bit.sql b/src/test/regress/sql/bit.sql
index 34230b99fb..8ba6facd03 100644
--- a/src/test/regress/sql/bit.sql
+++ b/src/test/regress/sql/bit.sql
@@ -223,6 +223,10 @@ SELECT overlay(B'0101011100' placing '001' from 20);
 -- bit_count
 SELECT bit_count(B'0101011100'::bit(10));
 SELECT bit_count(B'1111111111'::bit(10));
+SELECT bit_count(repeat('0', 100)::bit(100));
+SELECT bit_count(repeat('1', 100)::bit(100));
+SELECT bit_count(repeat('01', 500)::bit(1000));
+SELECT bit_count(repeat('10101', 200)::bit(1000));
 
 -- This table is intentionally left around to exercise pg_dump/pg_upgrade
 CREATE TABLE bit_defaults(
-- 
2.25.1


--lrZ03NoBR/3+SXJZ
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v21-0003-optimize-visibilitymap_count-with-AVX512.patch"



^ permalink  raw  reply  [nested|flat] 16+ messages in thread

* [PATCH v22 2/3] AVX512 popcount support
@ 2024-03-27 21:39 Nathan Bossart <[email protected]>
  0 siblings, 0 replies; 16+ messages in thread

From: Nathan Bossart @ 2024-03-27 21:39 UTC (permalink / raw)

---
 config/c-compiler.m4                 |  58 ++++++
 configure                            | 252 +++++++++++++++++++++++++++
 configure.ac                         |  51 ++++++
 meson.build                          |  87 +++++++++
 src/Makefile.global.in               |   5 +
 src/include/pg_config.h.in           |  12 ++
 src/include/port/pg_bitutils.h       |  15 ++
 src/makefiles/meson.build            |   4 +-
 src/port/Makefile                    |  11 ++
 src/port/meson.build                 |   6 +-
 src/port/pg_bitutils.c               |  29 ++-
 src/port/pg_popcount_avx512.c        |  49 ++++++
 src/port/pg_popcount_avx512_choose.c |  71 ++++++++
 src/test/regress/expected/bit.out    |  24 +++
 src/test/regress/sql/bit.sql         |   4 +
 15 files changed, 673 insertions(+), 5 deletions(-)
 create mode 100644 src/port/pg_popcount_avx512.c
 create mode 100644 src/port/pg_popcount_avx512_choose.c

diff --git a/config/c-compiler.m4 b/config/c-compiler.m4
index 3268a780bb..5fb60775ca 100644
--- a/config/c-compiler.m4
+++ b/config/c-compiler.m4
@@ -694,3 +694,61 @@ if test x"$Ac_cachevar" = x"yes"; then
 fi
 undefine([Ac_cachevar])dnl
 ])# PGAC_LOONGARCH_CRC32C_INTRINSICS
+
+# PGAC_XSAVE_INTRINSICS
+# ---------------------
+# Check if the compiler supports the XSAVE instructions using the _xgetbv
+# intrinsic function.
+#
+# An optional compiler flag can be passed as argument (e.g., -mxsave).  If the
+# intrinsic is supported, sets pgac_xsave_intrinsics and CFLAGS_XSAVE.
+AC_DEFUN([PGAC_XSAVE_INTRINSICS],
+[define([Ac_cachevar], [AS_TR_SH([pgac_cv_xsave_intrinsics_$1])])dnl
+AC_CACHE_CHECK([for _xgetbv with CFLAGS=$1], [Ac_cachevar],
+[pgac_save_CFLAGS=$CFLAGS
+CFLAGS="$pgac_save_CFLAGS $1"
+AC_LINK_IFELSE([AC_LANG_PROGRAM([#include <immintrin.h>],
+  [return _xgetbv(0) & 0xe0;])],
+  [Ac_cachevar=yes],
+  [Ac_cachevar=no])
+CFLAGS="$pgac_save_CFLAGS"])
+if test x"$Ac_cachevar" = x"yes"; then
+  CFLAGS_XSAVE="$1"
+  pgac_xsave_intrinsics=yes
+fi
+undefine([Ac_cachevar])dnl
+])# PGAC_XSAVE_INTRINSICS
+
+# PGAC_AVX512_POPCNT_INTRINSICS
+# -----------------------------
+# Check if the compiler supports the AVX512 POPCNT instructions using the
+# _mm512_setzero_si512, _mm512_loadu_si512, _mm512_popcnt_epi64,
+# _mm512_add_epi64, and _mm512_reduce_add_epi64 intrinsic functions.
+#
+# An optional compiler flag can be passed as argument
+# (e.g., -mavx512vpopcntdq).  If the intrinsics are supported, sets
+# pgac_avx512_popcnt_intrinsics and CFLAGS_POPCNT.
+AC_DEFUN([PGAC_AVX512_POPCNT_INTRINSICS],
+[define([Ac_cachevar], [AS_TR_SH([pgac_cv_avx512_popcnt_intrinsics_$1])])dnl
+AC_CACHE_CHECK([for _mm512_popcnt_epi64 with CFLAGS=$1], [Ac_cachevar],
+[pgac_save_CFLAGS=$CFLAGS
+CFLAGS="$pgac_save_CFLAGS $1"
+AC_LINK_IFELSE([AC_LANG_PROGRAM([#include <immintrin.h>],
+  [const char buf@<:@sizeof(__m512i)@:>@;
+   PG_INT64_TYPE popcnt = 0;
+   __m512i accum = _mm512_setzero_si512();
+   const __m512i val = _mm512_loadu_si512((const __m512i *) buf);
+   const __m512i cnt = _mm512_popcnt_epi64(val);
+   accum = _mm512_add_epi64(accum, cnt);
+   popcnt = _mm512_reduce_add_epi64(accum);
+   /* return computed value, to prevent the above being optimized away */
+   return popcnt == 0;])],
+  [Ac_cachevar=yes],
+  [Ac_cachevar=no])
+CFLAGS="$pgac_save_CFLAGS"])
+if test x"$Ac_cachevar" = x"yes"; then
+  CFLAGS_POPCNT="$1"
+  pgac_avx512_popcnt_intrinsics=yes
+fi
+undefine([Ac_cachevar])dnl
+])# PGAC_AVX512_POPCNT_INTRINSICS
diff --git a/configure b/configure
index 36feeafbb2..b48ed7f271 100755
--- a/configure
+++ b/configure
@@ -647,6 +647,9 @@ MSGFMT_FLAGS
 MSGFMT
 PG_CRC32C_OBJS
 CFLAGS_CRC
+PG_POPCNT_OBJS
+CFLAGS_POPCNT
+CFLAGS_XSAVE
 LIBOBJS
 OPENSSL
 ZSTD
@@ -17404,6 +17407,40 @@ $as_echo "#define HAVE__GET_CPUID 1" >>confdefs.h
 
 fi
 
+{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for __get_cpuid_count" >&5
+$as_echo_n "checking for __get_cpuid_count... " >&6; }
+if ${pgac_cv__get_cpuid_count+:} 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_count(7, 0, &exx[0], &exx[1], &exx[2], &exx[3]);
+
+  ;
+  return 0;
+}
+_ACEOF
+if ac_fn_c_try_link "$LINENO"; then :
+  pgac_cv__get_cpuid_count="yes"
+else
+  pgac_cv__get_cpuid_count="no"
+fi
+rm -f core conftest.err conftest.$ac_objext \
+    conftest$ac_exeext conftest.$ac_ext
+fi
+{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $pgac_cv__get_cpuid_count" >&5
+$as_echo "$pgac_cv__get_cpuid_count" >&6; }
+if test x"$pgac_cv__get_cpuid_count" = x"yes"; then
+
+$as_echo "#define HAVE__GET_CPUID_COUNT 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 :
@@ -17438,6 +17475,221 @@ $as_echo "#define HAVE__CPUID 1" >>confdefs.h
 
 fi
 
+{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for __cpuidex" >&5
+$as_echo_n "checking for __cpuidex... " >&6; }
+if ${pgac_cv__cpuidex+:} 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_cpuidex(exx[0], 7, 0);
+
+  ;
+  return 0;
+}
+_ACEOF
+if ac_fn_c_try_link "$LINENO"; then :
+  pgac_cv__cpuidex="yes"
+else
+  pgac_cv__cpuidex="no"
+fi
+rm -f core conftest.err conftest.$ac_objext \
+    conftest$ac_exeext conftest.$ac_ext
+fi
+{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $pgac_cv__cpuidex" >&5
+$as_echo "$pgac_cv__cpuidex" >&6; }
+if test x"$pgac_cv__cpuidex" = x"yes"; then
+
+$as_echo "#define HAVE__CPUIDEX 1" >>confdefs.h
+
+fi
+
+# Check for XSAVE intrinsics
+#
+CFLAGS_XSAVE=""
+{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for _xgetbv with CFLAGS=" >&5
+$as_echo_n "checking for _xgetbv with CFLAGS=... " >&6; }
+if ${pgac_cv_xsave_intrinsics_+:} false; then :
+  $as_echo_n "(cached) " >&6
+else
+  pgac_save_CFLAGS=$CFLAGS
+CFLAGS="$pgac_save_CFLAGS "
+cat confdefs.h - <<_ACEOF >conftest.$ac_ext
+/* end confdefs.h.  */
+#include <immintrin.h>
+int
+main ()
+{
+return _xgetbv(0) & 0xe0;
+  ;
+  return 0;
+}
+_ACEOF
+if ac_fn_c_try_link "$LINENO"; then :
+  pgac_cv_xsave_intrinsics_=yes
+else
+  pgac_cv_xsave_intrinsics_=no
+fi
+rm -f core conftest.err conftest.$ac_objext \
+    conftest$ac_exeext conftest.$ac_ext
+CFLAGS="$pgac_save_CFLAGS"
+fi
+{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $pgac_cv_xsave_intrinsics_" >&5
+$as_echo "$pgac_cv_xsave_intrinsics_" >&6; }
+if test x"$pgac_cv_xsave_intrinsics_" = x"yes"; then
+  CFLAGS_XSAVE=""
+  pgac_xsave_intrinsics=yes
+fi
+
+if test x"$pgac_xsave_intrinsics" != x"yes"; then
+  { $as_echo "$as_me:${as_lineno-$LINENO}: checking for _xgetbv with CFLAGS=-mxsave" >&5
+$as_echo_n "checking for _xgetbv with CFLAGS=-mxsave... " >&6; }
+if ${pgac_cv_xsave_intrinsics__mxsave+:} false; then :
+  $as_echo_n "(cached) " >&6
+else
+  pgac_save_CFLAGS=$CFLAGS
+CFLAGS="$pgac_save_CFLAGS -mxsave"
+cat confdefs.h - <<_ACEOF >conftest.$ac_ext
+/* end confdefs.h.  */
+#include <immintrin.h>
+int
+main ()
+{
+return _xgetbv(0) & 0xe0;
+  ;
+  return 0;
+}
+_ACEOF
+if ac_fn_c_try_link "$LINENO"; then :
+  pgac_cv_xsave_intrinsics__mxsave=yes
+else
+  pgac_cv_xsave_intrinsics__mxsave=no
+fi
+rm -f core conftest.err conftest.$ac_objext \
+    conftest$ac_exeext conftest.$ac_ext
+CFLAGS="$pgac_save_CFLAGS"
+fi
+{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $pgac_cv_xsave_intrinsics__mxsave" >&5
+$as_echo "$pgac_cv_xsave_intrinsics__mxsave" >&6; }
+if test x"$pgac_cv_xsave_intrinsics__mxsave" = x"yes"; then
+  CFLAGS_XSAVE="-mxsave"
+  pgac_xsave_intrinsics=yes
+fi
+
+fi
+if test x"$pgac_xsave_intrinsics" = x"yes"; then
+
+$as_echo "#define HAVE_XSAVE_INTRINSICS 1" >>confdefs.h
+
+fi
+
+
+# Check for AVX512 popcount intrinsics
+#
+CFLAGS_POPCNT=""
+PG_POPCNT_OBJS=""
+if test x"$host_cpu" = x"x86_64"; then
+  { $as_echo "$as_me:${as_lineno-$LINENO}: checking for _mm512_popcnt_epi64 with CFLAGS=" >&5
+$as_echo_n "checking for _mm512_popcnt_epi64 with CFLAGS=... " >&6; }
+if ${pgac_cv_avx512_popcnt_intrinsics_+:} false; then :
+  $as_echo_n "(cached) " >&6
+else
+  pgac_save_CFLAGS=$CFLAGS
+CFLAGS="$pgac_save_CFLAGS "
+cat confdefs.h - <<_ACEOF >conftest.$ac_ext
+/* end confdefs.h.  */
+#include <immintrin.h>
+int
+main ()
+{
+const char buf[sizeof(__m512i)];
+   PG_INT64_TYPE popcnt = 0;
+   __m512i accum = _mm512_setzero_si512();
+   const __m512i val = _mm512_loadu_si512((const __m512i *) buf);
+   const __m512i cnt = _mm512_popcnt_epi64(val);
+   accum = _mm512_add_epi64(accum, cnt);
+   popcnt = _mm512_reduce_add_epi64(accum);
+   /* return computed value, to prevent the above being optimized away */
+   return popcnt == 0;
+  ;
+  return 0;
+}
+_ACEOF
+if ac_fn_c_try_link "$LINENO"; then :
+  pgac_cv_avx512_popcnt_intrinsics_=yes
+else
+  pgac_cv_avx512_popcnt_intrinsics_=no
+fi
+rm -f core conftest.err conftest.$ac_objext \
+    conftest$ac_exeext conftest.$ac_ext
+CFLAGS="$pgac_save_CFLAGS"
+fi
+{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $pgac_cv_avx512_popcnt_intrinsics_" >&5
+$as_echo "$pgac_cv_avx512_popcnt_intrinsics_" >&6; }
+if test x"$pgac_cv_avx512_popcnt_intrinsics_" = x"yes"; then
+  CFLAGS_POPCNT=""
+  pgac_avx512_popcnt_intrinsics=yes
+fi
+
+  if test x"$pgac_avx512_popcnt_intrinsics" != x"yes"; then
+    { $as_echo "$as_me:${as_lineno-$LINENO}: checking for _mm512_popcnt_epi64 with CFLAGS=-mavx512vpopcntdq" >&5
+$as_echo_n "checking for _mm512_popcnt_epi64 with CFLAGS=-mavx512vpopcntdq... " >&6; }
+if ${pgac_cv_avx512_popcnt_intrinsics__mavx512vpopcntdq+:} false; then :
+  $as_echo_n "(cached) " >&6
+else
+  pgac_save_CFLAGS=$CFLAGS
+CFLAGS="$pgac_save_CFLAGS -mavx512vpopcntdq"
+cat confdefs.h - <<_ACEOF >conftest.$ac_ext
+/* end confdefs.h.  */
+#include <immintrin.h>
+int
+main ()
+{
+const char buf[sizeof(__m512i)];
+   PG_INT64_TYPE popcnt = 0;
+   __m512i accum = _mm512_setzero_si512();
+   const __m512i val = _mm512_loadu_si512((const __m512i *) buf);
+   const __m512i cnt = _mm512_popcnt_epi64(val);
+   accum = _mm512_add_epi64(accum, cnt);
+   popcnt = _mm512_reduce_add_epi64(accum);
+   /* return computed value, to prevent the above being optimized away */
+   return popcnt == 0;
+  ;
+  return 0;
+}
+_ACEOF
+if ac_fn_c_try_link "$LINENO"; then :
+  pgac_cv_avx512_popcnt_intrinsics__mavx512vpopcntdq=yes
+else
+  pgac_cv_avx512_popcnt_intrinsics__mavx512vpopcntdq=no
+fi
+rm -f core conftest.err conftest.$ac_objext \
+    conftest$ac_exeext conftest.$ac_ext
+CFLAGS="$pgac_save_CFLAGS"
+fi
+{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $pgac_cv_avx512_popcnt_intrinsics__mavx512vpopcntdq" >&5
+$as_echo "$pgac_cv_avx512_popcnt_intrinsics__mavx512vpopcntdq" >&6; }
+if test x"$pgac_cv_avx512_popcnt_intrinsics__mavx512vpopcntdq" = x"yes"; then
+  CFLAGS_POPCNT="-mavx512vpopcntdq"
+  pgac_avx512_popcnt_intrinsics=yes
+fi
+
+  fi
+  if test x"$pgac_avx512_popcnt_intrinsics" = x"yes"; then
+    PG_POPCNT_OBJS="pg_popcount_avx512.o pg_popcount_avx512_choose.o"
+
+$as_echo "#define USE_AVX512_POPCNT_WITH_RUNTIME_CHECK 1" >>confdefs.h
+
+  fi
+fi
+
+
+
 # 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
diff --git a/configure.ac b/configure.ac
index 57f734879e..2bbd81dfb8 100644
--- a/configure.ac
+++ b/configure.ac
@@ -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"$pgac_xsave_intrinsics" = x"yes"; then
+  AC_DEFINE(HAVE_XSAVE_INTRINSICS, 1, [Define to 1 if you have XSAVE intrinsics.])
+fi
+AC_SUBST(CFLAGS_XSAVE)
+
+# Check for AVX512 popcount intrinsics
+#
+CFLAGS_POPCNT=""
+PG_POPCNT_OBJS=""
+if test x"$host_cpu" = x"x86_64"; then
+  PGAC_AVX512_POPCNT_INTRINSICS([])
+  if test x"$pgac_avx512_popcnt_intrinsics" != x"yes"; then
+    PGAC_AVX512_POPCNT_INTRINSICS([-mavx512vpopcntdq])
+  fi
+  if test x"$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 AVX512 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
diff --git a/meson.build b/meson.build
index 18b5be842e..96be29c22b 100644
--- a/meson.build
+++ b/meson.build
@@ -1783,6 +1783,30 @@ elif cc.links('''
 endif
 
 
+# Check for __get_cpuid_count() and __cpuidex() in a similar fashion.
+if cc.links('''
+    #include <cpuid.h>
+    int main(int arg, char **argv)
+    {
+        unsigned int exx[4] = {0, 0, 0, 0};
+        __get_cpuid_count(7, 0, &exx[0], &exx[1], &exx[2], &exx[3]);
+    }
+    ''', name: '__get_cpuid_count',
+    args: test_c_args)
+  cdata.set('HAVE__GET_CPUID_COUNT', 1)
+elif cc.links('''
+    #include <intrin.h>
+    int main(int arg, char **argv)
+    {
+        unsigned int exx[4] = {0, 0, 0, 0};
+        __cpuidex(exx, 7, 0);
+    }
+    ''', name: '__cpuidex',
+    args: test_c_args)
+  cdata.set('HAVE__CPUIDEX', 1)
+endif
+
+
 # Defend against clang being used on x86-32 without SSE2 enabled.  As current
 # versions of clang do not understand -fexcess-precision=standard, the use of
 # x87 floating point operations leads to problems like isinf possibly returning
@@ -1996,6 +2020,69 @@ int main(void)
 endif
 
 
+###############################################################
+# Check for the availability of XSAVE intrinsics.
+###############################################################
+
+cflags_xsave = []
+if host_cpu == 'x86' or host_cpu == 'x86_64'
+
+  prog = '''
+#include <immintrin.h>
+
+int main(void)
+{
+    return _xgetbv(0) & 0xe0;
+}
+'''
+
+  if cc.links(prog, name: 'XSAVE intrinsics without -mxsave',
+        args: test_c_args)
+    cdata.set('HAVE_XSAVE_INTRINSICS', 1)
+  elif cc.links(prog, name: 'XSAVE intrinsics with -mxsave',
+        args: test_c_args + ['-mxsave'])
+    cdata.set('HAVE_XSAVE_INTRINSICS', 1)
+    cflags_xsave += '-mxsave'
+  endif
+
+endif
+
+
+###############################################################
+# Check for the availability of AVX512 popcount intrinsics.
+###############################################################
+
+cflags_popcnt = []
+if host_cpu == 'x86_64'
+
+  prog = '''
+#include <immintrin.h>
+
+int main(void)
+{
+    const char buf[sizeof(__m512i)];
+    INT64 popcnt = 0;
+    __m512i accum = _mm512_setzero_si512();
+    const __m512i val = _mm512_loadu_si512((const __m512i *) buf);
+    const __m512i cnt = _mm512_popcnt_epi64(val);
+    accum = _mm512_add_epi64(accum, cnt);
+    popcnt = _mm512_reduce_add_epi64(accum);
+    /* return computed value, to prevent the above being optimized away */
+    return popcnt == 0;
+}
+'''
+
+  if cc.links(prog, name: 'AVX512 popcount without -mavx512vpopcntdq',
+        args: test_c_args + ['-DINT64=@0@'.format(cdata.get('PG_INT64_TYPE'))])
+    cdata.set('USE_AVX512_POPCNT_WITH_RUNTIME_CHECK', 1)
+  elif cc.links(prog, name: 'AVX512 popcount with -mavx512vpopcntdq',
+        args: test_c_args + ['-DINT64=@0@'.format(cdata.get('PG_INT64_TYPE'))] + ['-mavx512vpopcntdq'])
+    cdata.set('USE_AVX512_POPCNT_WITH_RUNTIME_CHECK', 1)
+    cflags_popcnt += '-mavx512vpopcntdq'
+  endif
+
+endif
+
 
 ###############################################################
 # Select CRC-32C implementation.
diff --git a/src/Makefile.global.in b/src/Makefile.global.in
index 8b3f8c24e0..36d880d225 100644
--- a/src/Makefile.global.in
+++ b/src/Makefile.global.in
@@ -262,7 +262,9 @@ CFLAGS_SL_MODULE = @CFLAGS_SL_MODULE@
 CXXFLAGS_SL_MODULE = @CXXFLAGS_SL_MODULE@
 CFLAGS_UNROLL_LOOPS = @CFLAGS_UNROLL_LOOPS@
 CFLAGS_VECTORIZE = @CFLAGS_VECTORIZE@
+CFLAGS_POPCNT = @CFLAGS_POPCNT@
 CFLAGS_CRC = @CFLAGS_CRC@
+CFLAGS_XSAVE = @CFLAGS_XSAVE@
 PERMIT_DECLARATION_AFTER_STATEMENT = @PERMIT_DECLARATION_AFTER_STATEMENT@
 CXXFLAGS = @CXXFLAGS@
 
@@ -758,6 +760,9 @@ LIBOBJS = @LIBOBJS@
 # files needed for the chosen CRC-32C implementation
 PG_CRC32C_OBJS = @PG_CRC32C_OBJS@
 
+# files needed for the chosen popcount implementation
+PG_POPCNT_OBJS = @PG_POPCNT_OBJS@
+
 LIBS := -lpgcommon -lpgport $(LIBS)
 
 # to make ws2_32.lib the last library
diff --git a/src/include/pg_config.h.in b/src/include/pg_config.h.in
index 591e1ca3df..de067e6182 100644
--- a/src/include/pg_config.h.in
+++ b/src/include/pg_config.h.in
@@ -513,6 +513,9 @@
 /* Define to 1 if the assembler supports X86_64's POPCNTQ instruction. */
 #undef HAVE_X86_64_POPCNTQ
 
+/* Define to 1 if you have XSAVE intrinsics. */
+#undef HAVE_XSAVE_INTRINSICS
+
 /* Define to 1 if the system has the type `_Bool'. */
 #undef HAVE__BOOL
 
@@ -555,9 +558,15 @@
 /* Define to 1 if you have __cpuid. */
 #undef HAVE__CPUID
 
+/* Define to 1 if you have __cpuidex. */
+#undef HAVE__CPUIDEX
+
 /* Define to 1 if you have __get_cpuid. */
 #undef HAVE__GET_CPUID
 
+/* Define to 1 if you have __get_cpuid_count. */
+#undef HAVE__GET_CPUID_COUNT
+
 /* Define to 1 if your compiler understands _Static_assert. */
 #undef HAVE__STATIC_ASSERT
 
@@ -680,6 +689,9 @@
 /* Define to 1 to build with assertion checks. (--enable-cassert) */
 #undef USE_ASSERT_CHECKING
 
+/* Define to 1 to use AVX512 popcount instructions with a runtime check. */
+#undef USE_AVX512_POPCNT_WITH_RUNTIME_CHECK
+
 /* Define to 1 to build with Bonjour support. (--with-bonjour) */
 #undef USE_BONJOUR
 
diff --git a/src/include/port/pg_bitutils.h b/src/include/port/pg_bitutils.h
index 1f487a4bc3..e4e96952b7 100644
--- a/src/include/port/pg_bitutils.h
+++ b/src/include/port/pg_bitutils.h
@@ -304,6 +304,21 @@ extern PGDLLIMPORT int (*pg_popcount32) (uint32 word);
 extern PGDLLIMPORT int (*pg_popcount64) (uint64 word);
 extern PGDLLIMPORT uint64 (*pg_popcount_optimized) (const char *buf, int bytes);
 
+/* Export pg_popcount_fast() for use in the AVX512 implementation. */
+extern uint64 pg_popcount_fast(const char *buf, int bytes);
+
+/*
+ * We can also try to use the AVX512 popcount instruction on some systems.
+ * The implementation of that is located in its own file because it may
+ * require special compiler flags that we don't want to apply to any other
+ * files.  Note that we only build this when TRY_POPCNT_FAST is set so that we
+ * can fall back to pg_popcount_fast() as needed.
+ */
+#ifdef USE_AVX512_POPCNT_WITH_RUNTIME_CHECK
+extern bool pg_popcount_avx512_available(void);
+extern uint64 pg_popcount_avx512(const char *buf, int bytes);
+#endif
+
 #else
 /* Use a portable implementation -- no need for a function pointer. */
 extern int	pg_popcount32(uint32 word);
diff --git a/src/makefiles/meson.build b/src/makefiles/meson.build
index b0f4178b3d..5618050b30 100644
--- a/src/makefiles/meson.build
+++ b/src/makefiles/meson.build
@@ -100,8 +100,10 @@ pgxs_kv = {
     ' '.join(cflags_no_decl_after_statement),
 
   'CFLAGS_CRC': ' '.join(cflags_crc),
+  'CFLAGS_POPCNT': ' '.join(cflags_popcnt),
   'CFLAGS_UNROLL_LOOPS': ' '.join(unroll_loops_cflags),
   'CFLAGS_VECTORIZE': ' '.join(vectorize_cflags),
+  'CFLAGS_XSAVE': ' '.join(cflags_xsave),
 
   'LDFLAGS': var_ldflags,
   'LDFLAGS_EX': var_ldflags_ex,
@@ -177,7 +179,7 @@ pgxs_empty = [
   'WANTED_LANGUAGES',
 
   # Not needed because we don't build the server / PLs with the generated makefile
-  'LIBOBJS', 'PG_CRC32C_OBJS', 'TAS',
+  'LIBOBJS', 'PG_CRC32C_OBJS', 'PG_POPCNT_OBJS', 'TAS',
   'DTRACEFLAGS', # only server has dtrace probes
 
   'perl_archlibexp', 'perl_embed_ccflags', 'perl_embed_ldflags', 'perl_includespec', 'perl_privlibexp',
diff --git a/src/port/Makefile b/src/port/Makefile
index dcc8737e68..db7c02117b 100644
--- a/src/port/Makefile
+++ b/src/port/Makefile
@@ -38,6 +38,7 @@ LIBS += $(PTHREAD_LIBS)
 OBJS = \
 	$(LIBOBJS) \
 	$(PG_CRC32C_OBJS) \
+	$(PG_POPCNT_OBJS) \
 	bsearch_arg.o \
 	chklocale.o \
 	inet_net_ntop.o \
@@ -92,6 +93,16 @@ pg_crc32c_armv8.o: CFLAGS+=$(CFLAGS_CRC)
 pg_crc32c_armv8_shlib.o: CFLAGS+=$(CFLAGS_CRC)
 pg_crc32c_armv8_srv.o: CFLAGS+=$(CFLAGS_CRC)
 
+# all versions of pg_popcount_avx512_choose.o need CFLAGS_XSAVE
+pg_popcount_avx512_choose.o: CFLAGS+=$(CFLAGS_XSAVE)
+pg_popcount_avx512_choose_shlib.o: CFLAGS+=$(CFLAGS_XSAVE)
+pg_popcount_avx512_choose_srv.o: CFLAGS+=$(CFLAGS_XSAVE)
+
+# all versions of pg_popcount_avx512.o need CFLAGS_POPCNT
+pg_popcount_avx512.o: CFLAGS+=$(CFLAGS_POPCNT)
+pg_popcount_avx512_shlib.o: CFLAGS+=$(CFLAGS_POPCNT)
+pg_popcount_avx512_srv.o: CFLAGS+=$(CFLAGS_POPCNT)
+
 #
 # Shared library versions of object files
 #
diff --git a/src/port/meson.build b/src/port/meson.build
index 92b593e6ef..fd9ee199d1 100644
--- a/src/port/meson.build
+++ b/src/port/meson.build
@@ -84,6 +84,8 @@ replace_funcs_pos = [
   ['pg_crc32c_sse42', 'USE_SSE42_CRC32C_WITH_RUNTIME_CHECK', 'crc'],
   ['pg_crc32c_sse42_choose', 'USE_SSE42_CRC32C_WITH_RUNTIME_CHECK'],
   ['pg_crc32c_sb8', 'USE_SSE42_CRC32C_WITH_RUNTIME_CHECK'],
+  ['pg_popcount_avx512', 'USE_AVX512_POPCNT_WITH_RUNTIME_CHECK', 'popcnt'],
+  ['pg_popcount_avx512_choose', 'USE_AVX512_POPCNT_WITH_RUNTIME_CHECK', 'xsave'],
 
   # arm / aarch64
   ['pg_crc32c_armv8', 'USE_ARMV8_CRC32C'],
@@ -98,8 +100,8 @@ replace_funcs_pos = [
   ['pg_crc32c_sb8', 'USE_SLICING_BY_8_CRC32C'],
 ]
 
-pgport_cflags = {'crc': cflags_crc}
-pgport_sources_cflags = {'crc': []}
+pgport_cflags = {'crc': cflags_crc, 'popcnt': cflags_popcnt, 'xsave': cflags_xsave}
+pgport_sources_cflags = {'crc': [], 'popcnt': [], 'xsave': []}
 
 foreach f : replace_funcs_neg
   func = f.get(0)
diff --git a/src/port/pg_bitutils.c b/src/port/pg_bitutils.c
index 6271acea60..2fa16b54b8 100644
--- a/src/port/pg_bitutils.c
+++ b/src/port/pg_bitutils.c
@@ -114,7 +114,10 @@ static int	pg_popcount64_choose(uint64 word);
 static uint64 pg_popcount_choose(const char *buf, int bytes);
 static inline int pg_popcount32_fast(uint32 word);
 static inline int pg_popcount64_fast(uint64 word);
-static uint64 pg_popcount_fast(const char *buf, int bytes);
+
+#ifdef USE_AVX512_POPCNT_WITH_RUNTIME_CHECK
+static uint64 pg_popcount_fast_or_avx512(const char *buf, int bytes);
+#endif
 
 int			(*pg_popcount32) (uint32 word) = pg_popcount32_choose;
 int			(*pg_popcount64) (uint64 word) = pg_popcount64_choose;
@@ -156,6 +159,10 @@ choose_popcount_functions(void)
 		pg_popcount32 = pg_popcount32_fast;
 		pg_popcount64 = pg_popcount64_fast;
 		pg_popcount_optimized = pg_popcount_fast;
+#ifdef USE_AVX512_POPCNT_WITH_RUNTIME_CHECK
+		if (pg_popcount_avx512_available())
+			pg_popcount_optimized = pg_popcount_fast_or_avx512;
+#endif
 	}
 	else
 	{
@@ -224,7 +231,7 @@ __asm__ __volatile__(" popcntq %1,%0\n":"=q"(res):"rm"(word):"cc");
  * pg_popcount_fast
  *		Returns the number of 1-bits in buf
  */
-static uint64
+uint64
 pg_popcount_fast(const char *buf, int bytes)
 {
 	uint64		popcnt = 0;
@@ -266,6 +273,24 @@ pg_popcount_fast(const char *buf, int bytes)
 	return popcnt;
 }
 
+/*
+ * This is a wrapper function for pg_popcount_avx512() that uses
+ * pg_popcount_fast() when there aren't enough bytes to fit in an AVX-512
+ * register.  The compiler should be able to inline pg_popcount_fast() so that
+ * we only take on additional function call overhead when it's likely to be a
+ * better option.
+ */
+#ifdef USE_AVX512_POPCNT_WITH_RUNTIME_CHECK
+static uint64
+pg_popcount_fast_or_avx512(const char *buf, int bytes)
+{
+	if (bytes < 64)
+		return pg_popcount_fast(buf, bytes);
+	else
+		return pg_popcount_avx512(buf, bytes);
+}
+#endif							/* USE_AVX512_POPCNT_WITH_RUNTIME_CHECK */
+
 #endif							/* TRY_POPCNT_FAST */
 
 
diff --git a/src/port/pg_popcount_avx512.c b/src/port/pg_popcount_avx512.c
new file mode 100644
index 0000000000..f86558d1ee
--- /dev/null
+++ b/src/port/pg_popcount_avx512.c
@@ -0,0 +1,49 @@
+/*-------------------------------------------------------------------------
+ *
+ * pg_popcount_avx512.c
+ *	  Holds the pg_popcount() implementation that uses AVX512 instructions.
+ *
+ * Copyright (c) 2024, PostgreSQL Global Development Group
+ *
+ * IDENTIFICATION
+ *	  src/port/pg_popcount_avx512.c
+ *
+ *-------------------------------------------------------------------------
+ */
+#include "c.h"
+
+#include <immintrin.h>
+
+#include "port/pg_bitutils.h"
+
+/*
+ * It's probably unlikely that TRY_POPCNT_FAST won't be set if we are able to
+ * use AVX512 intrinsics, but we check it anyway to be sure.  We rely on
+ * pg_popcount_fast() as our fallback implementation in pg_popcount_avx512().
+ */
+#ifdef TRY_POPCNT_FAST
+
+/*
+ * pg_popcount_avx512
+ *		Returns the number of 1-bits in buf
+ */
+uint64
+pg_popcount_avx512(const char *buf, int bytes)
+{
+	uint64		popcnt;
+	__m512i		accum = _mm512_setzero_si512();
+
+	for (; bytes >= sizeof(__m512i); bytes -= sizeof(__m512i))
+	{
+		const		__m512i val = _mm512_loadu_si512((const __m512i *) buf);
+		const		__m512i cnt = _mm512_popcnt_epi64(val);
+
+		accum = _mm512_add_epi64(accum, cnt);
+		buf += sizeof(__m512i);
+	}
+
+	popcnt = _mm512_reduce_add_epi64(accum);
+	return popcnt + pg_popcount_fast(buf, bytes);
+}
+
+#endif							/* TRY_POPCNT_FAST */
diff --git a/src/port/pg_popcount_avx512_choose.c b/src/port/pg_popcount_avx512_choose.c
new file mode 100644
index 0000000000..9e81cd33ad
--- /dev/null
+++ b/src/port/pg_popcount_avx512_choose.c
@@ -0,0 +1,71 @@
+/*-------------------------------------------------------------------------
+ *
+ * pg_popcount_avx512_choose.c
+ *    Test whether we can use AVX512 POPCNT instructions.
+ *
+ * Copyright (c) 2024, PostgreSQL Global Development Group
+ *
+ * IDENTIFICATION
+ *    src/port/pg_popcount_avx512_choose.c
+ *
+ *-------------------------------------------------------------------------
+ */
+#include "c.h"
+
+#if defined(HAVE__GET_CPUID) || defined(HAVE__GET_CPUID_COUNT)
+#include <cpuid.h>
+#endif
+
+#ifdef HAVE_XSAVE_INTRINSICS
+#include <immintrin.h>
+#endif
+
+#if defined(HAVE__CPUID) || defined(HAVE__CPUIDEX)
+#include <intrin.h>
+#endif
+
+#include "port/pg_bitutils.h"
+
+/*
+ * It's probably unlikely that TRY_POPCNT_FAST won't be set if we are able to
+ * use AVX512 intrinsics, but we check it anyway to be sure.  We rely on
+ * pg_popcount_fast() as our fallback implementation in pg_popcount_avx512().
+ */
+#ifdef TRY_POPCNT_FAST
+
+/*
+ * Returns true if the CPU supports AVX512 POPCNT.
+ */
+bool
+pg_popcount_avx512_available(void)
+{
+	unsigned int exx[4] = {0, 0, 0, 0};
+
+	/* does CPUID say there's support for AVX512 POPCNT? */
+#if defined(HAVE__GET_CPUID_COUNT)
+	__get_cpuid_count(7, 0, &exx[0], &exx[1], &exx[2], &exx[3]);
+#elif defined(HAVE__CPUIDEX)
+	__cpuidex(exx, 7, 0);
+#endif
+	if ((exx[2] & (1 << 14)) == 0)	/* avx512vpopcntdq */
+		return false;
+
+	/* does CPUID say there's support for XGETBV? */
+	memset(exx, 0, sizeof(exx));
+#if defined(HAVE__GET_CPUID)
+	__get_cpuid(1, &exx[0], &exx[1], &exx[2], &exx[3]);
+#elif defined(HAVE__CPUID)
+	__cpuid(exx, 1);
+#endif
+	if ((exx[2] & (1 << 26)) == 0)	/* xsave */
+		return false;
+
+	/* does XGETBV say the ZMM registers are enabled? */
+#ifdef HAVE_XSAVE_INTRINSICS
+	return (_xgetbv(0) & 0xe0) != 0;
+#else
+	return false;
+#endif
+}
+
+#endif							/* TRY_POPCNT_FAST */
diff --git a/src/test/regress/expected/bit.out b/src/test/regress/expected/bit.out
index e17cbf42ca..6a436288bb 100644
--- a/src/test/regress/expected/bit.out
+++ b/src/test/regress/expected/bit.out
@@ -740,6 +740,30 @@ SELECT bit_count(B'1111111111'::bit(10));
         10
 (1 row)
 
+SELECT bit_count(repeat('0', 100)::bit(100));
+ bit_count 
+-----------
+         0
+(1 row)
+
+SELECT bit_count(repeat('1', 100)::bit(100));
+ bit_count 
+-----------
+       100
+(1 row)
+
+SELECT bit_count(repeat('01', 500)::bit(1000));
+ bit_count 
+-----------
+       500
+(1 row)
+
+SELECT bit_count(repeat('10101', 200)::bit(1000));
+ bit_count 
+-----------
+       600
+(1 row)
+
 -- This table is intentionally left around to exercise pg_dump/pg_upgrade
 CREATE TABLE bit_defaults(
   b1 bit(4) DEFAULT '1001',
diff --git a/src/test/regress/sql/bit.sql b/src/test/regress/sql/bit.sql
index 34230b99fb..8ba6facd03 100644
--- a/src/test/regress/sql/bit.sql
+++ b/src/test/regress/sql/bit.sql
@@ -223,6 +223,10 @@ SELECT overlay(B'0101011100' placing '001' from 20);
 -- bit_count
 SELECT bit_count(B'0101011100'::bit(10));
 SELECT bit_count(B'1111111111'::bit(10));
+SELECT bit_count(repeat('0', 100)::bit(100));
+SELECT bit_count(repeat('1', 100)::bit(100));
+SELECT bit_count(repeat('01', 500)::bit(1000));
+SELECT bit_count(repeat('10101', 200)::bit(1000));
 
 -- This table is intentionally left around to exercise pg_dump/pg_upgrade
 CREATE TABLE bit_defaults(
-- 
2.25.1


--MGYHOYXEY6WxJCY8
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v22-0003-optimize-visibilitymap_count-with-AVX512.patch"



^ permalink  raw  reply  [nested|flat] 16+ messages in thread

* [PATCH v18 1/1] AVX512 popcount support
@ 2024-03-27 21:39 Nathan Bossart <[email protected]>
  0 siblings, 0 replies; 16+ messages in thread

From: Nathan Bossart @ 2024-03-27 21:39 UTC (permalink / raw)

---
 config/c-compiler.m4                 |  58 ++++++
 configure                            | 252 +++++++++++++++++++++++++++
 configure.ac                         |  51 ++++++
 meson.build                          |  87 +++++++++
 src/Makefile.global.in               |   5 +
 src/include/pg_config.h.in           |  12 ++
 src/include/port/pg_bitutils.h       |  15 ++
 src/makefiles/meson.build            |   4 +-
 src/port/Makefile                    |  11 ++
 src/port/meson.build                 |   6 +-
 src/port/pg_bitutils.c               |  56 +++---
 src/port/pg_popcount_avx512.c        |  49 ++++++
 src/port/pg_popcount_avx512_choose.c |  71 ++++++++
 src/test/regress/expected/bit.out    |  24 +++
 src/test/regress/sql/bit.sql         |   4 +
 15 files changed, 666 insertions(+), 39 deletions(-)
 create mode 100644 src/port/pg_popcount_avx512.c
 create mode 100644 src/port/pg_popcount_avx512_choose.c

diff --git a/config/c-compiler.m4 b/config/c-compiler.m4
index 3268a780bb..5fb60775ca 100644
--- a/config/c-compiler.m4
+++ b/config/c-compiler.m4
@@ -694,3 +694,61 @@ if test x"$Ac_cachevar" = x"yes"; then
 fi
 undefine([Ac_cachevar])dnl
 ])# PGAC_LOONGARCH_CRC32C_INTRINSICS
+
+# PGAC_XSAVE_INTRINSICS
+# ---------------------
+# Check if the compiler supports the XSAVE instructions using the _xgetbv
+# intrinsic function.
+#
+# An optional compiler flag can be passed as argument (e.g., -mxsave).  If the
+# intrinsic is supported, sets pgac_xsave_intrinsics and CFLAGS_XSAVE.
+AC_DEFUN([PGAC_XSAVE_INTRINSICS],
+[define([Ac_cachevar], [AS_TR_SH([pgac_cv_xsave_intrinsics_$1])])dnl
+AC_CACHE_CHECK([for _xgetbv with CFLAGS=$1], [Ac_cachevar],
+[pgac_save_CFLAGS=$CFLAGS
+CFLAGS="$pgac_save_CFLAGS $1"
+AC_LINK_IFELSE([AC_LANG_PROGRAM([#include <immintrin.h>],
+  [return _xgetbv(0) & 0xe0;])],
+  [Ac_cachevar=yes],
+  [Ac_cachevar=no])
+CFLAGS="$pgac_save_CFLAGS"])
+if test x"$Ac_cachevar" = x"yes"; then
+  CFLAGS_XSAVE="$1"
+  pgac_xsave_intrinsics=yes
+fi
+undefine([Ac_cachevar])dnl
+])# PGAC_XSAVE_INTRINSICS
+
+# PGAC_AVX512_POPCNT_INTRINSICS
+# -----------------------------
+# Check if the compiler supports the AVX512 POPCNT instructions using the
+# _mm512_setzero_si512, _mm512_loadu_si512, _mm512_popcnt_epi64,
+# _mm512_add_epi64, and _mm512_reduce_add_epi64 intrinsic functions.
+#
+# An optional compiler flag can be passed as argument
+# (e.g., -mavx512vpopcntdq).  If the intrinsics are supported, sets
+# pgac_avx512_popcnt_intrinsics and CFLAGS_POPCNT.
+AC_DEFUN([PGAC_AVX512_POPCNT_INTRINSICS],
+[define([Ac_cachevar], [AS_TR_SH([pgac_cv_avx512_popcnt_intrinsics_$1])])dnl
+AC_CACHE_CHECK([for _mm512_popcnt_epi64 with CFLAGS=$1], [Ac_cachevar],
+[pgac_save_CFLAGS=$CFLAGS
+CFLAGS="$pgac_save_CFLAGS $1"
+AC_LINK_IFELSE([AC_LANG_PROGRAM([#include <immintrin.h>],
+  [const char buf@<:@sizeof(__m512i)@:>@;
+   PG_INT64_TYPE popcnt = 0;
+   __m512i accum = _mm512_setzero_si512();
+   const __m512i val = _mm512_loadu_si512((const __m512i *) buf);
+   const __m512i cnt = _mm512_popcnt_epi64(val);
+   accum = _mm512_add_epi64(accum, cnt);
+   popcnt = _mm512_reduce_add_epi64(accum);
+   /* return computed value, to prevent the above being optimized away */
+   return popcnt == 0;])],
+  [Ac_cachevar=yes],
+  [Ac_cachevar=no])
+CFLAGS="$pgac_save_CFLAGS"])
+if test x"$Ac_cachevar" = x"yes"; then
+  CFLAGS_POPCNT="$1"
+  pgac_avx512_popcnt_intrinsics=yes
+fi
+undefine([Ac_cachevar])dnl
+])# PGAC_AVX512_POPCNT_INTRINSICS
diff --git a/configure b/configure
index 36feeafbb2..b48ed7f271 100755
--- a/configure
+++ b/configure
@@ -647,6 +647,9 @@ MSGFMT_FLAGS
 MSGFMT
 PG_CRC32C_OBJS
 CFLAGS_CRC
+PG_POPCNT_OBJS
+CFLAGS_POPCNT
+CFLAGS_XSAVE
 LIBOBJS
 OPENSSL
 ZSTD
@@ -17404,6 +17407,40 @@ $as_echo "#define HAVE__GET_CPUID 1" >>confdefs.h
 
 fi
 
+{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for __get_cpuid_count" >&5
+$as_echo_n "checking for __get_cpuid_count... " >&6; }
+if ${pgac_cv__get_cpuid_count+:} 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_count(7, 0, &exx[0], &exx[1], &exx[2], &exx[3]);
+
+  ;
+  return 0;
+}
+_ACEOF
+if ac_fn_c_try_link "$LINENO"; then :
+  pgac_cv__get_cpuid_count="yes"
+else
+  pgac_cv__get_cpuid_count="no"
+fi
+rm -f core conftest.err conftest.$ac_objext \
+    conftest$ac_exeext conftest.$ac_ext
+fi
+{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $pgac_cv__get_cpuid_count" >&5
+$as_echo "$pgac_cv__get_cpuid_count" >&6; }
+if test x"$pgac_cv__get_cpuid_count" = x"yes"; then
+
+$as_echo "#define HAVE__GET_CPUID_COUNT 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 :
@@ -17438,6 +17475,221 @@ $as_echo "#define HAVE__CPUID 1" >>confdefs.h
 
 fi
 
+{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for __cpuidex" >&5
+$as_echo_n "checking for __cpuidex... " >&6; }
+if ${pgac_cv__cpuidex+:} 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_cpuidex(exx[0], 7, 0);
+
+  ;
+  return 0;
+}
+_ACEOF
+if ac_fn_c_try_link "$LINENO"; then :
+  pgac_cv__cpuidex="yes"
+else
+  pgac_cv__cpuidex="no"
+fi
+rm -f core conftest.err conftest.$ac_objext \
+    conftest$ac_exeext conftest.$ac_ext
+fi
+{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $pgac_cv__cpuidex" >&5
+$as_echo "$pgac_cv__cpuidex" >&6; }
+if test x"$pgac_cv__cpuidex" = x"yes"; then
+
+$as_echo "#define HAVE__CPUIDEX 1" >>confdefs.h
+
+fi
+
+# Check for XSAVE intrinsics
+#
+CFLAGS_XSAVE=""
+{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for _xgetbv with CFLAGS=" >&5
+$as_echo_n "checking for _xgetbv with CFLAGS=... " >&6; }
+if ${pgac_cv_xsave_intrinsics_+:} false; then :
+  $as_echo_n "(cached) " >&6
+else
+  pgac_save_CFLAGS=$CFLAGS
+CFLAGS="$pgac_save_CFLAGS "
+cat confdefs.h - <<_ACEOF >conftest.$ac_ext
+/* end confdefs.h.  */
+#include <immintrin.h>
+int
+main ()
+{
+return _xgetbv(0) & 0xe0;
+  ;
+  return 0;
+}
+_ACEOF
+if ac_fn_c_try_link "$LINENO"; then :
+  pgac_cv_xsave_intrinsics_=yes
+else
+  pgac_cv_xsave_intrinsics_=no
+fi
+rm -f core conftest.err conftest.$ac_objext \
+    conftest$ac_exeext conftest.$ac_ext
+CFLAGS="$pgac_save_CFLAGS"
+fi
+{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $pgac_cv_xsave_intrinsics_" >&5
+$as_echo "$pgac_cv_xsave_intrinsics_" >&6; }
+if test x"$pgac_cv_xsave_intrinsics_" = x"yes"; then
+  CFLAGS_XSAVE=""
+  pgac_xsave_intrinsics=yes
+fi
+
+if test x"$pgac_xsave_intrinsics" != x"yes"; then
+  { $as_echo "$as_me:${as_lineno-$LINENO}: checking for _xgetbv with CFLAGS=-mxsave" >&5
+$as_echo_n "checking for _xgetbv with CFLAGS=-mxsave... " >&6; }
+if ${pgac_cv_xsave_intrinsics__mxsave+:} false; then :
+  $as_echo_n "(cached) " >&6
+else
+  pgac_save_CFLAGS=$CFLAGS
+CFLAGS="$pgac_save_CFLAGS -mxsave"
+cat confdefs.h - <<_ACEOF >conftest.$ac_ext
+/* end confdefs.h.  */
+#include <immintrin.h>
+int
+main ()
+{
+return _xgetbv(0) & 0xe0;
+  ;
+  return 0;
+}
+_ACEOF
+if ac_fn_c_try_link "$LINENO"; then :
+  pgac_cv_xsave_intrinsics__mxsave=yes
+else
+  pgac_cv_xsave_intrinsics__mxsave=no
+fi
+rm -f core conftest.err conftest.$ac_objext \
+    conftest$ac_exeext conftest.$ac_ext
+CFLAGS="$pgac_save_CFLAGS"
+fi
+{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $pgac_cv_xsave_intrinsics__mxsave" >&5
+$as_echo "$pgac_cv_xsave_intrinsics__mxsave" >&6; }
+if test x"$pgac_cv_xsave_intrinsics__mxsave" = x"yes"; then
+  CFLAGS_XSAVE="-mxsave"
+  pgac_xsave_intrinsics=yes
+fi
+
+fi
+if test x"$pgac_xsave_intrinsics" = x"yes"; then
+
+$as_echo "#define HAVE_XSAVE_INTRINSICS 1" >>confdefs.h
+
+fi
+
+
+# Check for AVX512 popcount intrinsics
+#
+CFLAGS_POPCNT=""
+PG_POPCNT_OBJS=""
+if test x"$host_cpu" = x"x86_64"; then
+  { $as_echo "$as_me:${as_lineno-$LINENO}: checking for _mm512_popcnt_epi64 with CFLAGS=" >&5
+$as_echo_n "checking for _mm512_popcnt_epi64 with CFLAGS=... " >&6; }
+if ${pgac_cv_avx512_popcnt_intrinsics_+:} false; then :
+  $as_echo_n "(cached) " >&6
+else
+  pgac_save_CFLAGS=$CFLAGS
+CFLAGS="$pgac_save_CFLAGS "
+cat confdefs.h - <<_ACEOF >conftest.$ac_ext
+/* end confdefs.h.  */
+#include <immintrin.h>
+int
+main ()
+{
+const char buf[sizeof(__m512i)];
+   PG_INT64_TYPE popcnt = 0;
+   __m512i accum = _mm512_setzero_si512();
+   const __m512i val = _mm512_loadu_si512((const __m512i *) buf);
+   const __m512i cnt = _mm512_popcnt_epi64(val);
+   accum = _mm512_add_epi64(accum, cnt);
+   popcnt = _mm512_reduce_add_epi64(accum);
+   /* return computed value, to prevent the above being optimized away */
+   return popcnt == 0;
+  ;
+  return 0;
+}
+_ACEOF
+if ac_fn_c_try_link "$LINENO"; then :
+  pgac_cv_avx512_popcnt_intrinsics_=yes
+else
+  pgac_cv_avx512_popcnt_intrinsics_=no
+fi
+rm -f core conftest.err conftest.$ac_objext \
+    conftest$ac_exeext conftest.$ac_ext
+CFLAGS="$pgac_save_CFLAGS"
+fi
+{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $pgac_cv_avx512_popcnt_intrinsics_" >&5
+$as_echo "$pgac_cv_avx512_popcnt_intrinsics_" >&6; }
+if test x"$pgac_cv_avx512_popcnt_intrinsics_" = x"yes"; then
+  CFLAGS_POPCNT=""
+  pgac_avx512_popcnt_intrinsics=yes
+fi
+
+  if test x"$pgac_avx512_popcnt_intrinsics" != x"yes"; then
+    { $as_echo "$as_me:${as_lineno-$LINENO}: checking for _mm512_popcnt_epi64 with CFLAGS=-mavx512vpopcntdq" >&5
+$as_echo_n "checking for _mm512_popcnt_epi64 with CFLAGS=-mavx512vpopcntdq... " >&6; }
+if ${pgac_cv_avx512_popcnt_intrinsics__mavx512vpopcntdq+:} false; then :
+  $as_echo_n "(cached) " >&6
+else
+  pgac_save_CFLAGS=$CFLAGS
+CFLAGS="$pgac_save_CFLAGS -mavx512vpopcntdq"
+cat confdefs.h - <<_ACEOF >conftest.$ac_ext
+/* end confdefs.h.  */
+#include <immintrin.h>
+int
+main ()
+{
+const char buf[sizeof(__m512i)];
+   PG_INT64_TYPE popcnt = 0;
+   __m512i accum = _mm512_setzero_si512();
+   const __m512i val = _mm512_loadu_si512((const __m512i *) buf);
+   const __m512i cnt = _mm512_popcnt_epi64(val);
+   accum = _mm512_add_epi64(accum, cnt);
+   popcnt = _mm512_reduce_add_epi64(accum);
+   /* return computed value, to prevent the above being optimized away */
+   return popcnt == 0;
+  ;
+  return 0;
+}
+_ACEOF
+if ac_fn_c_try_link "$LINENO"; then :
+  pgac_cv_avx512_popcnt_intrinsics__mavx512vpopcntdq=yes
+else
+  pgac_cv_avx512_popcnt_intrinsics__mavx512vpopcntdq=no
+fi
+rm -f core conftest.err conftest.$ac_objext \
+    conftest$ac_exeext conftest.$ac_ext
+CFLAGS="$pgac_save_CFLAGS"
+fi
+{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $pgac_cv_avx512_popcnt_intrinsics__mavx512vpopcntdq" >&5
+$as_echo "$pgac_cv_avx512_popcnt_intrinsics__mavx512vpopcntdq" >&6; }
+if test x"$pgac_cv_avx512_popcnt_intrinsics__mavx512vpopcntdq" = x"yes"; then
+  CFLAGS_POPCNT="-mavx512vpopcntdq"
+  pgac_avx512_popcnt_intrinsics=yes
+fi
+
+  fi
+  if test x"$pgac_avx512_popcnt_intrinsics" = x"yes"; then
+    PG_POPCNT_OBJS="pg_popcount_avx512.o pg_popcount_avx512_choose.o"
+
+$as_echo "#define USE_AVX512_POPCNT_WITH_RUNTIME_CHECK 1" >>confdefs.h
+
+  fi
+fi
+
+
+
 # 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
diff --git a/configure.ac b/configure.ac
index 57f734879e..2bbd81dfb8 100644
--- a/configure.ac
+++ b/configure.ac
@@ -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"$pgac_xsave_intrinsics" = x"yes"; then
+  AC_DEFINE(HAVE_XSAVE_INTRINSICS, 1, [Define to 1 if you have XSAVE intrinsics.])
+fi
+AC_SUBST(CFLAGS_XSAVE)
+
+# Check for AVX512 popcount intrinsics
+#
+CFLAGS_POPCNT=""
+PG_POPCNT_OBJS=""
+if test x"$host_cpu" = x"x86_64"; then
+  PGAC_AVX512_POPCNT_INTRINSICS([])
+  if test x"$pgac_avx512_popcnt_intrinsics" != x"yes"; then
+    PGAC_AVX512_POPCNT_INTRINSICS([-mavx512vpopcntdq])
+  fi
+  if test x"$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 AVX512 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
diff --git a/meson.build b/meson.build
index 18b5be842e..96be29c22b 100644
--- a/meson.build
+++ b/meson.build
@@ -1783,6 +1783,30 @@ elif cc.links('''
 endif
 
 
+# Check for __get_cpuid_count() and __cpuidex() in a similar fashion.
+if cc.links('''
+    #include <cpuid.h>
+    int main(int arg, char **argv)
+    {
+        unsigned int exx[4] = {0, 0, 0, 0};
+        __get_cpuid_count(7, 0, &exx[0], &exx[1], &exx[2], &exx[3]);
+    }
+    ''', name: '__get_cpuid_count',
+    args: test_c_args)
+  cdata.set('HAVE__GET_CPUID_COUNT', 1)
+elif cc.links('''
+    #include <intrin.h>
+    int main(int arg, char **argv)
+    {
+        unsigned int exx[4] = {0, 0, 0, 0};
+        __cpuidex(exx, 7, 0);
+    }
+    ''', name: '__cpuidex',
+    args: test_c_args)
+  cdata.set('HAVE__CPUIDEX', 1)
+endif
+
+
 # Defend against clang being used on x86-32 without SSE2 enabled.  As current
 # versions of clang do not understand -fexcess-precision=standard, the use of
 # x87 floating point operations leads to problems like isinf possibly returning
@@ -1996,6 +2020,69 @@ int main(void)
 endif
 
 
+###############################################################
+# Check for the availability of XSAVE intrinsics.
+###############################################################
+
+cflags_xsave = []
+if host_cpu == 'x86' or host_cpu == 'x86_64'
+
+  prog = '''
+#include <immintrin.h>
+
+int main(void)
+{
+    return _xgetbv(0) & 0xe0;
+}
+'''
+
+  if cc.links(prog, name: 'XSAVE intrinsics without -mxsave',
+        args: test_c_args)
+    cdata.set('HAVE_XSAVE_INTRINSICS', 1)
+  elif cc.links(prog, name: 'XSAVE intrinsics with -mxsave',
+        args: test_c_args + ['-mxsave'])
+    cdata.set('HAVE_XSAVE_INTRINSICS', 1)
+    cflags_xsave += '-mxsave'
+  endif
+
+endif
+
+
+###############################################################
+# Check for the availability of AVX512 popcount intrinsics.
+###############################################################
+
+cflags_popcnt = []
+if host_cpu == 'x86_64'
+
+  prog = '''
+#include <immintrin.h>
+
+int main(void)
+{
+    const char buf[sizeof(__m512i)];
+    INT64 popcnt = 0;
+    __m512i accum = _mm512_setzero_si512();
+    const __m512i val = _mm512_loadu_si512((const __m512i *) buf);
+    const __m512i cnt = _mm512_popcnt_epi64(val);
+    accum = _mm512_add_epi64(accum, cnt);
+    popcnt = _mm512_reduce_add_epi64(accum);
+    /* return computed value, to prevent the above being optimized away */
+    return popcnt == 0;
+}
+'''
+
+  if cc.links(prog, name: 'AVX512 popcount without -mavx512vpopcntdq',
+        args: test_c_args + ['-DINT64=@0@'.format(cdata.get('PG_INT64_TYPE'))])
+    cdata.set('USE_AVX512_POPCNT_WITH_RUNTIME_CHECK', 1)
+  elif cc.links(prog, name: 'AVX512 popcount with -mavx512vpopcntdq',
+        args: test_c_args + ['-DINT64=@0@'.format(cdata.get('PG_INT64_TYPE'))] + ['-mavx512vpopcntdq'])
+    cdata.set('USE_AVX512_POPCNT_WITH_RUNTIME_CHECK', 1)
+    cflags_popcnt += '-mavx512vpopcntdq'
+  endif
+
+endif
+
 
 ###############################################################
 # Select CRC-32C implementation.
diff --git a/src/Makefile.global.in b/src/Makefile.global.in
index 8b3f8c24e0..36d880d225 100644
--- a/src/Makefile.global.in
+++ b/src/Makefile.global.in
@@ -262,7 +262,9 @@ CFLAGS_SL_MODULE = @CFLAGS_SL_MODULE@
 CXXFLAGS_SL_MODULE = @CXXFLAGS_SL_MODULE@
 CFLAGS_UNROLL_LOOPS = @CFLAGS_UNROLL_LOOPS@
 CFLAGS_VECTORIZE = @CFLAGS_VECTORIZE@
+CFLAGS_POPCNT = @CFLAGS_POPCNT@
 CFLAGS_CRC = @CFLAGS_CRC@
+CFLAGS_XSAVE = @CFLAGS_XSAVE@
 PERMIT_DECLARATION_AFTER_STATEMENT = @PERMIT_DECLARATION_AFTER_STATEMENT@
 CXXFLAGS = @CXXFLAGS@
 
@@ -758,6 +760,9 @@ LIBOBJS = @LIBOBJS@
 # files needed for the chosen CRC-32C implementation
 PG_CRC32C_OBJS = @PG_CRC32C_OBJS@
 
+# files needed for the chosen popcount implementation
+PG_POPCNT_OBJS = @PG_POPCNT_OBJS@
+
 LIBS := -lpgcommon -lpgport $(LIBS)
 
 # to make ws2_32.lib the last library
diff --git a/src/include/pg_config.h.in b/src/include/pg_config.h.in
index 591e1ca3df..de067e6182 100644
--- a/src/include/pg_config.h.in
+++ b/src/include/pg_config.h.in
@@ -513,6 +513,9 @@
 /* Define to 1 if the assembler supports X86_64's POPCNTQ instruction. */
 #undef HAVE_X86_64_POPCNTQ
 
+/* Define to 1 if you have XSAVE intrinsics. */
+#undef HAVE_XSAVE_INTRINSICS
+
 /* Define to 1 if the system has the type `_Bool'. */
 #undef HAVE__BOOL
 
@@ -555,9 +558,15 @@
 /* Define to 1 if you have __cpuid. */
 #undef HAVE__CPUID
 
+/* Define to 1 if you have __cpuidex. */
+#undef HAVE__CPUIDEX
+
 /* Define to 1 if you have __get_cpuid. */
 #undef HAVE__GET_CPUID
 
+/* Define to 1 if you have __get_cpuid_count. */
+#undef HAVE__GET_CPUID_COUNT
+
 /* Define to 1 if your compiler understands _Static_assert. */
 #undef HAVE__STATIC_ASSERT
 
@@ -680,6 +689,9 @@
 /* Define to 1 to build with assertion checks. (--enable-cassert) */
 #undef USE_ASSERT_CHECKING
 
+/* Define to 1 to use AVX512 popcount instructions with a runtime check. */
+#undef USE_AVX512_POPCNT_WITH_RUNTIME_CHECK
+
 /* Define to 1 to build with Bonjour support. (--with-bonjour) */
 #undef USE_BONJOUR
 
diff --git a/src/include/port/pg_bitutils.h b/src/include/port/pg_bitutils.h
index 53e5239717..1a92c56bcd 100644
--- a/src/include/port/pg_bitutils.h
+++ b/src/include/port/pg_bitutils.h
@@ -304,6 +304,21 @@ extern PGDLLIMPORT int (*pg_popcount32) (uint32 word);
 extern PGDLLIMPORT int (*pg_popcount64) (uint64 word);
 extern PGDLLIMPORT uint64 (*pg_popcount) (const char *buf, int bytes);
 
+/* Export pg_popcount_fast() for use in the AVX512 implementation. */
+extern uint64 pg_popcount_fast(const char *buf, int bytes);
+
+/*
+ * We can also try to use the AVX512 popcount instruction on some systems.
+ * The implementation of that is located in its own file because it may
+ * require special compiler flags that we don't want to apply to any other
+ * files.  Note that we only build this when TRY_POPCNT_FAST is set so that we
+ * can fall back to pg_popcount_fast() as needed.
+ */
+#ifdef USE_AVX512_POPCNT_WITH_RUNTIME_CHECK
+extern bool pg_popcount_avx512_available(void);
+extern uint64 pg_popcount_avx512(const char *buf, int bytes);
+#endif
+
 #else
 /* Use a portable implementation -- no need for a function pointer. */
 extern int	pg_popcount32(uint32 word);
diff --git a/src/makefiles/meson.build b/src/makefiles/meson.build
index b0f4178b3d..5618050b30 100644
--- a/src/makefiles/meson.build
+++ b/src/makefiles/meson.build
@@ -100,8 +100,10 @@ pgxs_kv = {
     ' '.join(cflags_no_decl_after_statement),
 
   'CFLAGS_CRC': ' '.join(cflags_crc),
+  'CFLAGS_POPCNT': ' '.join(cflags_popcnt),
   'CFLAGS_UNROLL_LOOPS': ' '.join(unroll_loops_cflags),
   'CFLAGS_VECTORIZE': ' '.join(vectorize_cflags),
+  'CFLAGS_XSAVE': ' '.join(cflags_xsave),
 
   'LDFLAGS': var_ldflags,
   'LDFLAGS_EX': var_ldflags_ex,
@@ -177,7 +179,7 @@ pgxs_empty = [
   'WANTED_LANGUAGES',
 
   # Not needed because we don't build the server / PLs with the generated makefile
-  'LIBOBJS', 'PG_CRC32C_OBJS', 'TAS',
+  'LIBOBJS', 'PG_CRC32C_OBJS', 'PG_POPCNT_OBJS', 'TAS',
   'DTRACEFLAGS', # only server has dtrace probes
 
   'perl_archlibexp', 'perl_embed_ccflags', 'perl_embed_ldflags', 'perl_includespec', 'perl_privlibexp',
diff --git a/src/port/Makefile b/src/port/Makefile
index dcc8737e68..db7c02117b 100644
--- a/src/port/Makefile
+++ b/src/port/Makefile
@@ -38,6 +38,7 @@ LIBS += $(PTHREAD_LIBS)
 OBJS = \
 	$(LIBOBJS) \
 	$(PG_CRC32C_OBJS) \
+	$(PG_POPCNT_OBJS) \
 	bsearch_arg.o \
 	chklocale.o \
 	inet_net_ntop.o \
@@ -92,6 +93,16 @@ pg_crc32c_armv8.o: CFLAGS+=$(CFLAGS_CRC)
 pg_crc32c_armv8_shlib.o: CFLAGS+=$(CFLAGS_CRC)
 pg_crc32c_armv8_srv.o: CFLAGS+=$(CFLAGS_CRC)
 
+# all versions of pg_popcount_avx512_choose.o need CFLAGS_XSAVE
+pg_popcount_avx512_choose.o: CFLAGS+=$(CFLAGS_XSAVE)
+pg_popcount_avx512_choose_shlib.o: CFLAGS+=$(CFLAGS_XSAVE)
+pg_popcount_avx512_choose_srv.o: CFLAGS+=$(CFLAGS_XSAVE)
+
+# all versions of pg_popcount_avx512.o need CFLAGS_POPCNT
+pg_popcount_avx512.o: CFLAGS+=$(CFLAGS_POPCNT)
+pg_popcount_avx512_shlib.o: CFLAGS+=$(CFLAGS_POPCNT)
+pg_popcount_avx512_srv.o: CFLAGS+=$(CFLAGS_POPCNT)
+
 #
 # Shared library versions of object files
 #
diff --git a/src/port/meson.build b/src/port/meson.build
index 92b593e6ef..fd9ee199d1 100644
--- a/src/port/meson.build
+++ b/src/port/meson.build
@@ -84,6 +84,8 @@ replace_funcs_pos = [
   ['pg_crc32c_sse42', 'USE_SSE42_CRC32C_WITH_RUNTIME_CHECK', 'crc'],
   ['pg_crc32c_sse42_choose', 'USE_SSE42_CRC32C_WITH_RUNTIME_CHECK'],
   ['pg_crc32c_sb8', 'USE_SSE42_CRC32C_WITH_RUNTIME_CHECK'],
+  ['pg_popcount_avx512', 'USE_AVX512_POPCNT_WITH_RUNTIME_CHECK', 'popcnt'],
+  ['pg_popcount_avx512_choose', 'USE_AVX512_POPCNT_WITH_RUNTIME_CHECK', 'xsave'],
 
   # arm / aarch64
   ['pg_crc32c_armv8', 'USE_ARMV8_CRC32C'],
@@ -98,8 +100,8 @@ replace_funcs_pos = [
   ['pg_crc32c_sb8', 'USE_SLICING_BY_8_CRC32C'],
 ]
 
-pgport_cflags = {'crc': cflags_crc}
-pgport_sources_cflags = {'crc': []}
+pgport_cflags = {'crc': cflags_crc, 'popcnt': cflags_popcnt, 'xsave': cflags_xsave}
+pgport_sources_cflags = {'crc': [], 'popcnt': [], 'xsave': []}
 
 foreach f : replace_funcs_neg
   func = f.get(0)
diff --git a/src/port/pg_bitutils.c b/src/port/pg_bitutils.c
index 1197696e97..c08d3c056f 100644
--- a/src/port/pg_bitutils.c
+++ b/src/port/pg_bitutils.c
@@ -114,7 +114,6 @@ static int	pg_popcount64_choose(uint64 word);
 static uint64 pg_popcount_choose(const char *buf, int bytes);
 static inline int pg_popcount32_fast(uint32 word);
 static inline int pg_popcount64_fast(uint64 word);
-static uint64 pg_popcount_fast(const char *buf, int bytes);
 
 int			(*pg_popcount32) (uint32 word) = pg_popcount32_choose;
 int			(*pg_popcount64) (uint64 word) = pg_popcount64_choose;
@@ -142,20 +141,18 @@ pg_popcount_available(void)
 	return (exx[2] & (1 << 23)) != 0;	/* POPCNT */
 }
 
-/*
- * These functions get called on the first call to pg_popcount32 etc.
- * They detect whether we can use the asm implementations, and replace
- * the function pointers so that subsequent calls are routed directly to
- * the chosen implementation.
- */
-static int
-pg_popcount32_choose(uint32 word)
+static inline void
+choose_popcount_functions(void)
 {
 	if (pg_popcount_available())
 	{
 		pg_popcount32 = pg_popcount32_fast;
 		pg_popcount64 = pg_popcount64_fast;
 		pg_popcount = pg_popcount_fast;
+#ifdef USE_AVX512_POPCNT_WITH_RUNTIME_CHECK
+		if (pg_popcount_avx512_available())
+			pg_popcount = pg_popcount_avx512;
+#endif
 	}
 	else
 	{
@@ -163,45 +160,32 @@ pg_popcount32_choose(uint32 word)
 		pg_popcount64 = pg_popcount64_slow;
 		pg_popcount = pg_popcount_slow;
 	}
+}
 
+/*
+ * These functions get called on the first call to pg_popcount32 etc.
+ * They detect whether we can use the asm implementations, and replace
+ * the function pointers so that subsequent calls are routed directly to
+ * the chosen implementation.
+ */
+static int
+pg_popcount32_choose(uint32 word)
+{
+	choose_popcount_functions();
 	return pg_popcount32(word);
 }
 
 static int
 pg_popcount64_choose(uint64 word)
 {
-	if (pg_popcount_available())
-	{
-		pg_popcount32 = pg_popcount32_fast;
-		pg_popcount64 = pg_popcount64_fast;
-		pg_popcount = pg_popcount_fast;
-	}
-	else
-	{
-		pg_popcount32 = pg_popcount32_slow;
-		pg_popcount64 = pg_popcount64_slow;
-		pg_popcount = pg_popcount_slow;
-	}
-
+	choose_popcount_functions();
 	return pg_popcount64(word);
 }
 
 static uint64
 pg_popcount_choose(const char *buf, int bytes)
 {
-	if (pg_popcount_available())
-	{
-		pg_popcount32 = pg_popcount32_fast;
-		pg_popcount64 = pg_popcount64_fast;
-		pg_popcount = pg_popcount_fast;
-	}
-	else
-	{
-		pg_popcount32 = pg_popcount32_slow;
-		pg_popcount64 = pg_popcount64_slow;
-		pg_popcount = pg_popcount_slow;
-	}
-
+	choose_popcount_functions();
 	return pg_popcount(buf, bytes);
 }
 
@@ -243,7 +227,7 @@ __asm__ __volatile__(" popcntq %1,%0\n":"=q"(res):"rm"(word):"cc");
  * pg_popcount_fast
  *		Returns the number of 1-bits in buf
  */
-static uint64
+uint64
 pg_popcount_fast(const char *buf, int bytes)
 {
 	uint64		popcnt = 0;
diff --git a/src/port/pg_popcount_avx512.c b/src/port/pg_popcount_avx512.c
new file mode 100644
index 0000000000..f86558d1ee
--- /dev/null
+++ b/src/port/pg_popcount_avx512.c
@@ -0,0 +1,49 @@
+/*-------------------------------------------------------------------------
+ *
+ * pg_popcount_avx512.c
+ *	  Holds the pg_popcount() implementation that uses AVX512 instructions.
+ *
+ * Copyright (c) 2024, PostgreSQL Global Development Group
+ *
+ * IDENTIFICATION
+ *	  src/port/pg_popcount_avx512.c
+ *
+ *-------------------------------------------------------------------------
+ */
+#include "c.h"
+
+#include <immintrin.h>
+
+#include "port/pg_bitutils.h"
+
+/*
+ * It's probably unlikely that TRY_POPCNT_FAST won't be set if we are able to
+ * use AVX512 intrinsics, but we check it anyway to be sure.  We rely on
+ * pg_popcount_fast() as our fallback implementation in pg_popcount_avx512().
+ */
+#ifdef TRY_POPCNT_FAST
+
+/*
+ * pg_popcount_avx512
+ *		Returns the number of 1-bits in buf
+ */
+uint64
+pg_popcount_avx512(const char *buf, int bytes)
+{
+	uint64		popcnt;
+	__m512i		accum = _mm512_setzero_si512();
+
+	for (; bytes >= sizeof(__m512i); bytes -= sizeof(__m512i))
+	{
+		const		__m512i val = _mm512_loadu_si512((const __m512i *) buf);
+		const		__m512i cnt = _mm512_popcnt_epi64(val);
+
+		accum = _mm512_add_epi64(accum, cnt);
+		buf += sizeof(__m512i);
+	}
+
+	popcnt = _mm512_reduce_add_epi64(accum);
+	return popcnt + pg_popcount_fast(buf, bytes);
+}
+
+#endif							/* TRY_POPCNT_FAST */
diff --git a/src/port/pg_popcount_avx512_choose.c b/src/port/pg_popcount_avx512_choose.c
new file mode 100644
index 0000000000..9e81cd33ad
--- /dev/null
+++ b/src/port/pg_popcount_avx512_choose.c
@@ -0,0 +1,71 @@
+/*-------------------------------------------------------------------------
+ *
+ * pg_popcount_avx512_choose.c
+ *    Test whether we can use AVX512 POPCNT instructions.
+ *
+ * Copyright (c) 2024, PostgreSQL Global Development Group
+ *
+ * IDENTIFICATION
+ *    src/port/pg_popcount_avx512_choose.c
+ *
+ *-------------------------------------------------------------------------
+ */
+#include "c.h"
+
+#if defined(HAVE__GET_CPUID) || defined(HAVE__GET_CPUID_COUNT)
+#include <cpuid.h>
+#endif
+
+#ifdef HAVE_XSAVE_INTRINSICS
+#include <immintrin.h>
+#endif
+
+#if defined(HAVE__CPUID) || defined(HAVE__CPUIDEX)
+#include <intrin.h>
+#endif
+
+#include "port/pg_bitutils.h"
+
+/*
+ * It's probably unlikely that TRY_POPCNT_FAST won't be set if we are able to
+ * use AVX512 intrinsics, but we check it anyway to be sure.  We rely on
+ * pg_popcount_fast() as our fallback implementation in pg_popcount_avx512().
+ */
+#ifdef TRY_POPCNT_FAST
+
+/*
+ * Returns true if the CPU supports AVX512 POPCNT.
+ */
+bool
+pg_popcount_avx512_available(void)
+{
+	unsigned int exx[4] = {0, 0, 0, 0};
+
+	/* does CPUID say there's support for AVX512 POPCNT? */
+#if defined(HAVE__GET_CPUID_COUNT)
+	__get_cpuid_count(7, 0, &exx[0], &exx[1], &exx[2], &exx[3]);
+#elif defined(HAVE__CPUIDEX)
+	__cpuidex(exx, 7, 0);
+#endif
+	if ((exx[2] & (1 << 14)) == 0)	/* avx512vpopcntdq */
+		return false;
+
+	/* does CPUID say there's support for XGETBV? */
+	memset(exx, 0, sizeof(exx));
+#if defined(HAVE__GET_CPUID)
+	__get_cpuid(1, &exx[0], &exx[1], &exx[2], &exx[3]);
+#elif defined(HAVE__CPUID)
+	__cpuid(exx, 1);
+#endif
+	if ((exx[2] & (1 << 26)) == 0)	/* xsave */
+		return false;
+
+	/* does XGETBV say the ZMM registers are enabled? */
+#ifdef HAVE_XSAVE_INTRINSICS
+	return (_xgetbv(0) & 0xe0) != 0;
+#else
+	return false;
+#endif
+}
+
+#endif							/* TRY_POPCNT_FAST */
diff --git a/src/test/regress/expected/bit.out b/src/test/regress/expected/bit.out
index e17cbf42ca..6a436288bb 100644
--- a/src/test/regress/expected/bit.out
+++ b/src/test/regress/expected/bit.out
@@ -740,6 +740,30 @@ SELECT bit_count(B'1111111111'::bit(10));
         10
 (1 row)
 
+SELECT bit_count(repeat('0', 100)::bit(100));
+ bit_count 
+-----------
+         0
+(1 row)
+
+SELECT bit_count(repeat('1', 100)::bit(100));
+ bit_count 
+-----------
+       100
+(1 row)
+
+SELECT bit_count(repeat('01', 500)::bit(1000));
+ bit_count 
+-----------
+       500
+(1 row)
+
+SELECT bit_count(repeat('10101', 200)::bit(1000));
+ bit_count 
+-----------
+       600
+(1 row)
+
 -- This table is intentionally left around to exercise pg_dump/pg_upgrade
 CREATE TABLE bit_defaults(
   b1 bit(4) DEFAULT '1001',
diff --git a/src/test/regress/sql/bit.sql b/src/test/regress/sql/bit.sql
index 34230b99fb..8ba6facd03 100644
--- a/src/test/regress/sql/bit.sql
+++ b/src/test/regress/sql/bit.sql
@@ -223,6 +223,10 @@ SELECT overlay(B'0101011100' placing '001' from 20);
 -- bit_count
 SELECT bit_count(B'0101011100'::bit(10));
 SELECT bit_count(B'1111111111'::bit(10));
+SELECT bit_count(repeat('0', 100)::bit(100));
+SELECT bit_count(repeat('1', 100)::bit(100));
+SELECT bit_count(repeat('01', 500)::bit(1000));
+SELECT bit_count(repeat('10101', 200)::bit(1000));
 
 -- This table is intentionally left around to exercise pg_dump/pg_upgrade
 CREATE TABLE bit_defaults(
-- 
2.25.1


--azLHFNyN32YCQGCU--





^ permalink  raw  reply  [nested|flat] 16+ messages in thread

* [PATCH v19 3/4] AVX512 popcount support
@ 2024-03-27 21:39 Nathan Bossart <[email protected]>
  0 siblings, 0 replies; 16+ messages in thread

From: Nathan Bossart @ 2024-03-27 21:39 UTC (permalink / raw)

---
 config/c-compiler.m4                 |  58 ++++++
 configure                            | 252 +++++++++++++++++++++++++++
 configure.ac                         |  51 ++++++
 meson.build                          |  87 +++++++++
 src/Makefile.global.in               |   5 +
 src/include/pg_config.h.in           |  12 ++
 src/include/port/pg_bitutils.h       |  15 ++
 src/makefiles/meson.build            |   4 +-
 src/port/Makefile                    |  11 ++
 src/port/meson.build                 |   6 +-
 src/port/pg_bitutils.c               |   7 +-
 src/port/pg_popcount_avx512.c        |  49 ++++++
 src/port/pg_popcount_avx512_choose.c |  71 ++++++++
 src/test/regress/expected/bit.out    |  24 +++
 src/test/regress/sql/bit.sql         |   4 +
 15 files changed, 651 insertions(+), 5 deletions(-)
 create mode 100644 src/port/pg_popcount_avx512.c
 create mode 100644 src/port/pg_popcount_avx512_choose.c

diff --git a/config/c-compiler.m4 b/config/c-compiler.m4
index 3268a780bb..5fb60775ca 100644
--- a/config/c-compiler.m4
+++ b/config/c-compiler.m4
@@ -694,3 +694,61 @@ if test x"$Ac_cachevar" = x"yes"; then
 fi
 undefine([Ac_cachevar])dnl
 ])# PGAC_LOONGARCH_CRC32C_INTRINSICS
+
+# PGAC_XSAVE_INTRINSICS
+# ---------------------
+# Check if the compiler supports the XSAVE instructions using the _xgetbv
+# intrinsic function.
+#
+# An optional compiler flag can be passed as argument (e.g., -mxsave).  If the
+# intrinsic is supported, sets pgac_xsave_intrinsics and CFLAGS_XSAVE.
+AC_DEFUN([PGAC_XSAVE_INTRINSICS],
+[define([Ac_cachevar], [AS_TR_SH([pgac_cv_xsave_intrinsics_$1])])dnl
+AC_CACHE_CHECK([for _xgetbv with CFLAGS=$1], [Ac_cachevar],
+[pgac_save_CFLAGS=$CFLAGS
+CFLAGS="$pgac_save_CFLAGS $1"
+AC_LINK_IFELSE([AC_LANG_PROGRAM([#include <immintrin.h>],
+  [return _xgetbv(0) & 0xe0;])],
+  [Ac_cachevar=yes],
+  [Ac_cachevar=no])
+CFLAGS="$pgac_save_CFLAGS"])
+if test x"$Ac_cachevar" = x"yes"; then
+  CFLAGS_XSAVE="$1"
+  pgac_xsave_intrinsics=yes
+fi
+undefine([Ac_cachevar])dnl
+])# PGAC_XSAVE_INTRINSICS
+
+# PGAC_AVX512_POPCNT_INTRINSICS
+# -----------------------------
+# Check if the compiler supports the AVX512 POPCNT instructions using the
+# _mm512_setzero_si512, _mm512_loadu_si512, _mm512_popcnt_epi64,
+# _mm512_add_epi64, and _mm512_reduce_add_epi64 intrinsic functions.
+#
+# An optional compiler flag can be passed as argument
+# (e.g., -mavx512vpopcntdq).  If the intrinsics are supported, sets
+# pgac_avx512_popcnt_intrinsics and CFLAGS_POPCNT.
+AC_DEFUN([PGAC_AVX512_POPCNT_INTRINSICS],
+[define([Ac_cachevar], [AS_TR_SH([pgac_cv_avx512_popcnt_intrinsics_$1])])dnl
+AC_CACHE_CHECK([for _mm512_popcnt_epi64 with CFLAGS=$1], [Ac_cachevar],
+[pgac_save_CFLAGS=$CFLAGS
+CFLAGS="$pgac_save_CFLAGS $1"
+AC_LINK_IFELSE([AC_LANG_PROGRAM([#include <immintrin.h>],
+  [const char buf@<:@sizeof(__m512i)@:>@;
+   PG_INT64_TYPE popcnt = 0;
+   __m512i accum = _mm512_setzero_si512();
+   const __m512i val = _mm512_loadu_si512((const __m512i *) buf);
+   const __m512i cnt = _mm512_popcnt_epi64(val);
+   accum = _mm512_add_epi64(accum, cnt);
+   popcnt = _mm512_reduce_add_epi64(accum);
+   /* return computed value, to prevent the above being optimized away */
+   return popcnt == 0;])],
+  [Ac_cachevar=yes],
+  [Ac_cachevar=no])
+CFLAGS="$pgac_save_CFLAGS"])
+if test x"$Ac_cachevar" = x"yes"; then
+  CFLAGS_POPCNT="$1"
+  pgac_avx512_popcnt_intrinsics=yes
+fi
+undefine([Ac_cachevar])dnl
+])# PGAC_AVX512_POPCNT_INTRINSICS
diff --git a/configure b/configure
index 36feeafbb2..b48ed7f271 100755
--- a/configure
+++ b/configure
@@ -647,6 +647,9 @@ MSGFMT_FLAGS
 MSGFMT
 PG_CRC32C_OBJS
 CFLAGS_CRC
+PG_POPCNT_OBJS
+CFLAGS_POPCNT
+CFLAGS_XSAVE
 LIBOBJS
 OPENSSL
 ZSTD
@@ -17404,6 +17407,40 @@ $as_echo "#define HAVE__GET_CPUID 1" >>confdefs.h
 
 fi
 
+{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for __get_cpuid_count" >&5
+$as_echo_n "checking for __get_cpuid_count... " >&6; }
+if ${pgac_cv__get_cpuid_count+:} 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_count(7, 0, &exx[0], &exx[1], &exx[2], &exx[3]);
+
+  ;
+  return 0;
+}
+_ACEOF
+if ac_fn_c_try_link "$LINENO"; then :
+  pgac_cv__get_cpuid_count="yes"
+else
+  pgac_cv__get_cpuid_count="no"
+fi
+rm -f core conftest.err conftest.$ac_objext \
+    conftest$ac_exeext conftest.$ac_ext
+fi
+{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $pgac_cv__get_cpuid_count" >&5
+$as_echo "$pgac_cv__get_cpuid_count" >&6; }
+if test x"$pgac_cv__get_cpuid_count" = x"yes"; then
+
+$as_echo "#define HAVE__GET_CPUID_COUNT 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 :
@@ -17438,6 +17475,221 @@ $as_echo "#define HAVE__CPUID 1" >>confdefs.h
 
 fi
 
+{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for __cpuidex" >&5
+$as_echo_n "checking for __cpuidex... " >&6; }
+if ${pgac_cv__cpuidex+:} 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_cpuidex(exx[0], 7, 0);
+
+  ;
+  return 0;
+}
+_ACEOF
+if ac_fn_c_try_link "$LINENO"; then :
+  pgac_cv__cpuidex="yes"
+else
+  pgac_cv__cpuidex="no"
+fi
+rm -f core conftest.err conftest.$ac_objext \
+    conftest$ac_exeext conftest.$ac_ext
+fi
+{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $pgac_cv__cpuidex" >&5
+$as_echo "$pgac_cv__cpuidex" >&6; }
+if test x"$pgac_cv__cpuidex" = x"yes"; then
+
+$as_echo "#define HAVE__CPUIDEX 1" >>confdefs.h
+
+fi
+
+# Check for XSAVE intrinsics
+#
+CFLAGS_XSAVE=""
+{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for _xgetbv with CFLAGS=" >&5
+$as_echo_n "checking for _xgetbv with CFLAGS=... " >&6; }
+if ${pgac_cv_xsave_intrinsics_+:} false; then :
+  $as_echo_n "(cached) " >&6
+else
+  pgac_save_CFLAGS=$CFLAGS
+CFLAGS="$pgac_save_CFLAGS "
+cat confdefs.h - <<_ACEOF >conftest.$ac_ext
+/* end confdefs.h.  */
+#include <immintrin.h>
+int
+main ()
+{
+return _xgetbv(0) & 0xe0;
+  ;
+  return 0;
+}
+_ACEOF
+if ac_fn_c_try_link "$LINENO"; then :
+  pgac_cv_xsave_intrinsics_=yes
+else
+  pgac_cv_xsave_intrinsics_=no
+fi
+rm -f core conftest.err conftest.$ac_objext \
+    conftest$ac_exeext conftest.$ac_ext
+CFLAGS="$pgac_save_CFLAGS"
+fi
+{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $pgac_cv_xsave_intrinsics_" >&5
+$as_echo "$pgac_cv_xsave_intrinsics_" >&6; }
+if test x"$pgac_cv_xsave_intrinsics_" = x"yes"; then
+  CFLAGS_XSAVE=""
+  pgac_xsave_intrinsics=yes
+fi
+
+if test x"$pgac_xsave_intrinsics" != x"yes"; then
+  { $as_echo "$as_me:${as_lineno-$LINENO}: checking for _xgetbv with CFLAGS=-mxsave" >&5
+$as_echo_n "checking for _xgetbv with CFLAGS=-mxsave... " >&6; }
+if ${pgac_cv_xsave_intrinsics__mxsave+:} false; then :
+  $as_echo_n "(cached) " >&6
+else
+  pgac_save_CFLAGS=$CFLAGS
+CFLAGS="$pgac_save_CFLAGS -mxsave"
+cat confdefs.h - <<_ACEOF >conftest.$ac_ext
+/* end confdefs.h.  */
+#include <immintrin.h>
+int
+main ()
+{
+return _xgetbv(0) & 0xe0;
+  ;
+  return 0;
+}
+_ACEOF
+if ac_fn_c_try_link "$LINENO"; then :
+  pgac_cv_xsave_intrinsics__mxsave=yes
+else
+  pgac_cv_xsave_intrinsics__mxsave=no
+fi
+rm -f core conftest.err conftest.$ac_objext \
+    conftest$ac_exeext conftest.$ac_ext
+CFLAGS="$pgac_save_CFLAGS"
+fi
+{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $pgac_cv_xsave_intrinsics__mxsave" >&5
+$as_echo "$pgac_cv_xsave_intrinsics__mxsave" >&6; }
+if test x"$pgac_cv_xsave_intrinsics__mxsave" = x"yes"; then
+  CFLAGS_XSAVE="-mxsave"
+  pgac_xsave_intrinsics=yes
+fi
+
+fi
+if test x"$pgac_xsave_intrinsics" = x"yes"; then
+
+$as_echo "#define HAVE_XSAVE_INTRINSICS 1" >>confdefs.h
+
+fi
+
+
+# Check for AVX512 popcount intrinsics
+#
+CFLAGS_POPCNT=""
+PG_POPCNT_OBJS=""
+if test x"$host_cpu" = x"x86_64"; then
+  { $as_echo "$as_me:${as_lineno-$LINENO}: checking for _mm512_popcnt_epi64 with CFLAGS=" >&5
+$as_echo_n "checking for _mm512_popcnt_epi64 with CFLAGS=... " >&6; }
+if ${pgac_cv_avx512_popcnt_intrinsics_+:} false; then :
+  $as_echo_n "(cached) " >&6
+else
+  pgac_save_CFLAGS=$CFLAGS
+CFLAGS="$pgac_save_CFLAGS "
+cat confdefs.h - <<_ACEOF >conftest.$ac_ext
+/* end confdefs.h.  */
+#include <immintrin.h>
+int
+main ()
+{
+const char buf[sizeof(__m512i)];
+   PG_INT64_TYPE popcnt = 0;
+   __m512i accum = _mm512_setzero_si512();
+   const __m512i val = _mm512_loadu_si512((const __m512i *) buf);
+   const __m512i cnt = _mm512_popcnt_epi64(val);
+   accum = _mm512_add_epi64(accum, cnt);
+   popcnt = _mm512_reduce_add_epi64(accum);
+   /* return computed value, to prevent the above being optimized away */
+   return popcnt == 0;
+  ;
+  return 0;
+}
+_ACEOF
+if ac_fn_c_try_link "$LINENO"; then :
+  pgac_cv_avx512_popcnt_intrinsics_=yes
+else
+  pgac_cv_avx512_popcnt_intrinsics_=no
+fi
+rm -f core conftest.err conftest.$ac_objext \
+    conftest$ac_exeext conftest.$ac_ext
+CFLAGS="$pgac_save_CFLAGS"
+fi
+{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $pgac_cv_avx512_popcnt_intrinsics_" >&5
+$as_echo "$pgac_cv_avx512_popcnt_intrinsics_" >&6; }
+if test x"$pgac_cv_avx512_popcnt_intrinsics_" = x"yes"; then
+  CFLAGS_POPCNT=""
+  pgac_avx512_popcnt_intrinsics=yes
+fi
+
+  if test x"$pgac_avx512_popcnt_intrinsics" != x"yes"; then
+    { $as_echo "$as_me:${as_lineno-$LINENO}: checking for _mm512_popcnt_epi64 with CFLAGS=-mavx512vpopcntdq" >&5
+$as_echo_n "checking for _mm512_popcnt_epi64 with CFLAGS=-mavx512vpopcntdq... " >&6; }
+if ${pgac_cv_avx512_popcnt_intrinsics__mavx512vpopcntdq+:} false; then :
+  $as_echo_n "(cached) " >&6
+else
+  pgac_save_CFLAGS=$CFLAGS
+CFLAGS="$pgac_save_CFLAGS -mavx512vpopcntdq"
+cat confdefs.h - <<_ACEOF >conftest.$ac_ext
+/* end confdefs.h.  */
+#include <immintrin.h>
+int
+main ()
+{
+const char buf[sizeof(__m512i)];
+   PG_INT64_TYPE popcnt = 0;
+   __m512i accum = _mm512_setzero_si512();
+   const __m512i val = _mm512_loadu_si512((const __m512i *) buf);
+   const __m512i cnt = _mm512_popcnt_epi64(val);
+   accum = _mm512_add_epi64(accum, cnt);
+   popcnt = _mm512_reduce_add_epi64(accum);
+   /* return computed value, to prevent the above being optimized away */
+   return popcnt == 0;
+  ;
+  return 0;
+}
+_ACEOF
+if ac_fn_c_try_link "$LINENO"; then :
+  pgac_cv_avx512_popcnt_intrinsics__mavx512vpopcntdq=yes
+else
+  pgac_cv_avx512_popcnt_intrinsics__mavx512vpopcntdq=no
+fi
+rm -f core conftest.err conftest.$ac_objext \
+    conftest$ac_exeext conftest.$ac_ext
+CFLAGS="$pgac_save_CFLAGS"
+fi
+{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $pgac_cv_avx512_popcnt_intrinsics__mavx512vpopcntdq" >&5
+$as_echo "$pgac_cv_avx512_popcnt_intrinsics__mavx512vpopcntdq" >&6; }
+if test x"$pgac_cv_avx512_popcnt_intrinsics__mavx512vpopcntdq" = x"yes"; then
+  CFLAGS_POPCNT="-mavx512vpopcntdq"
+  pgac_avx512_popcnt_intrinsics=yes
+fi
+
+  fi
+  if test x"$pgac_avx512_popcnt_intrinsics" = x"yes"; then
+    PG_POPCNT_OBJS="pg_popcount_avx512.o pg_popcount_avx512_choose.o"
+
+$as_echo "#define USE_AVX512_POPCNT_WITH_RUNTIME_CHECK 1" >>confdefs.h
+
+  fi
+fi
+
+
+
 # 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
diff --git a/configure.ac b/configure.ac
index 57f734879e..2bbd81dfb8 100644
--- a/configure.ac
+++ b/configure.ac
@@ -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"$pgac_xsave_intrinsics" = x"yes"; then
+  AC_DEFINE(HAVE_XSAVE_INTRINSICS, 1, [Define to 1 if you have XSAVE intrinsics.])
+fi
+AC_SUBST(CFLAGS_XSAVE)
+
+# Check for AVX512 popcount intrinsics
+#
+CFLAGS_POPCNT=""
+PG_POPCNT_OBJS=""
+if test x"$host_cpu" = x"x86_64"; then
+  PGAC_AVX512_POPCNT_INTRINSICS([])
+  if test x"$pgac_avx512_popcnt_intrinsics" != x"yes"; then
+    PGAC_AVX512_POPCNT_INTRINSICS([-mavx512vpopcntdq])
+  fi
+  if test x"$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 AVX512 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
diff --git a/meson.build b/meson.build
index 18b5be842e..96be29c22b 100644
--- a/meson.build
+++ b/meson.build
@@ -1783,6 +1783,30 @@ elif cc.links('''
 endif
 
 
+# Check for __get_cpuid_count() and __cpuidex() in a similar fashion.
+if cc.links('''
+    #include <cpuid.h>
+    int main(int arg, char **argv)
+    {
+        unsigned int exx[4] = {0, 0, 0, 0};
+        __get_cpuid_count(7, 0, &exx[0], &exx[1], &exx[2], &exx[3]);
+    }
+    ''', name: '__get_cpuid_count',
+    args: test_c_args)
+  cdata.set('HAVE__GET_CPUID_COUNT', 1)
+elif cc.links('''
+    #include <intrin.h>
+    int main(int arg, char **argv)
+    {
+        unsigned int exx[4] = {0, 0, 0, 0};
+        __cpuidex(exx, 7, 0);
+    }
+    ''', name: '__cpuidex',
+    args: test_c_args)
+  cdata.set('HAVE__CPUIDEX', 1)
+endif
+
+
 # Defend against clang being used on x86-32 without SSE2 enabled.  As current
 # versions of clang do not understand -fexcess-precision=standard, the use of
 # x87 floating point operations leads to problems like isinf possibly returning
@@ -1996,6 +2020,69 @@ int main(void)
 endif
 
 
+###############################################################
+# Check for the availability of XSAVE intrinsics.
+###############################################################
+
+cflags_xsave = []
+if host_cpu == 'x86' or host_cpu == 'x86_64'
+
+  prog = '''
+#include <immintrin.h>
+
+int main(void)
+{
+    return _xgetbv(0) & 0xe0;
+}
+'''
+
+  if cc.links(prog, name: 'XSAVE intrinsics without -mxsave',
+        args: test_c_args)
+    cdata.set('HAVE_XSAVE_INTRINSICS', 1)
+  elif cc.links(prog, name: 'XSAVE intrinsics with -mxsave',
+        args: test_c_args + ['-mxsave'])
+    cdata.set('HAVE_XSAVE_INTRINSICS', 1)
+    cflags_xsave += '-mxsave'
+  endif
+
+endif
+
+
+###############################################################
+# Check for the availability of AVX512 popcount intrinsics.
+###############################################################
+
+cflags_popcnt = []
+if host_cpu == 'x86_64'
+
+  prog = '''
+#include <immintrin.h>
+
+int main(void)
+{
+    const char buf[sizeof(__m512i)];
+    INT64 popcnt = 0;
+    __m512i accum = _mm512_setzero_si512();
+    const __m512i val = _mm512_loadu_si512((const __m512i *) buf);
+    const __m512i cnt = _mm512_popcnt_epi64(val);
+    accum = _mm512_add_epi64(accum, cnt);
+    popcnt = _mm512_reduce_add_epi64(accum);
+    /* return computed value, to prevent the above being optimized away */
+    return popcnt == 0;
+}
+'''
+
+  if cc.links(prog, name: 'AVX512 popcount without -mavx512vpopcntdq',
+        args: test_c_args + ['-DINT64=@0@'.format(cdata.get('PG_INT64_TYPE'))])
+    cdata.set('USE_AVX512_POPCNT_WITH_RUNTIME_CHECK', 1)
+  elif cc.links(prog, name: 'AVX512 popcount with -mavx512vpopcntdq',
+        args: test_c_args + ['-DINT64=@0@'.format(cdata.get('PG_INT64_TYPE'))] + ['-mavx512vpopcntdq'])
+    cdata.set('USE_AVX512_POPCNT_WITH_RUNTIME_CHECK', 1)
+    cflags_popcnt += '-mavx512vpopcntdq'
+  endif
+
+endif
+
 
 ###############################################################
 # Select CRC-32C implementation.
diff --git a/src/Makefile.global.in b/src/Makefile.global.in
index 8b3f8c24e0..36d880d225 100644
--- a/src/Makefile.global.in
+++ b/src/Makefile.global.in
@@ -262,7 +262,9 @@ CFLAGS_SL_MODULE = @CFLAGS_SL_MODULE@
 CXXFLAGS_SL_MODULE = @CXXFLAGS_SL_MODULE@
 CFLAGS_UNROLL_LOOPS = @CFLAGS_UNROLL_LOOPS@
 CFLAGS_VECTORIZE = @CFLAGS_VECTORIZE@
+CFLAGS_POPCNT = @CFLAGS_POPCNT@
 CFLAGS_CRC = @CFLAGS_CRC@
+CFLAGS_XSAVE = @CFLAGS_XSAVE@
 PERMIT_DECLARATION_AFTER_STATEMENT = @PERMIT_DECLARATION_AFTER_STATEMENT@
 CXXFLAGS = @CXXFLAGS@
 
@@ -758,6 +760,9 @@ LIBOBJS = @LIBOBJS@
 # files needed for the chosen CRC-32C implementation
 PG_CRC32C_OBJS = @PG_CRC32C_OBJS@
 
+# files needed for the chosen popcount implementation
+PG_POPCNT_OBJS = @PG_POPCNT_OBJS@
+
 LIBS := -lpgcommon -lpgport $(LIBS)
 
 # to make ws2_32.lib the last library
diff --git a/src/include/pg_config.h.in b/src/include/pg_config.h.in
index 591e1ca3df..de067e6182 100644
--- a/src/include/pg_config.h.in
+++ b/src/include/pg_config.h.in
@@ -513,6 +513,9 @@
 /* Define to 1 if the assembler supports X86_64's POPCNTQ instruction. */
 #undef HAVE_X86_64_POPCNTQ
 
+/* Define to 1 if you have XSAVE intrinsics. */
+#undef HAVE_XSAVE_INTRINSICS
+
 /* Define to 1 if the system has the type `_Bool'. */
 #undef HAVE__BOOL
 
@@ -555,9 +558,15 @@
 /* Define to 1 if you have __cpuid. */
 #undef HAVE__CPUID
 
+/* Define to 1 if you have __cpuidex. */
+#undef HAVE__CPUIDEX
+
 /* Define to 1 if you have __get_cpuid. */
 #undef HAVE__GET_CPUID
 
+/* Define to 1 if you have __get_cpuid_count. */
+#undef HAVE__GET_CPUID_COUNT
+
 /* Define to 1 if your compiler understands _Static_assert. */
 #undef HAVE__STATIC_ASSERT
 
@@ -680,6 +689,9 @@
 /* Define to 1 to build with assertion checks. (--enable-cassert) */
 #undef USE_ASSERT_CHECKING
 
+/* Define to 1 to use AVX512 popcount instructions with a runtime check. */
+#undef USE_AVX512_POPCNT_WITH_RUNTIME_CHECK
+
 /* Define to 1 to build with Bonjour support. (--with-bonjour) */
 #undef USE_BONJOUR
 
diff --git a/src/include/port/pg_bitutils.h b/src/include/port/pg_bitutils.h
index 53e5239717..1a92c56bcd 100644
--- a/src/include/port/pg_bitutils.h
+++ b/src/include/port/pg_bitutils.h
@@ -304,6 +304,21 @@ extern PGDLLIMPORT int (*pg_popcount32) (uint32 word);
 extern PGDLLIMPORT int (*pg_popcount64) (uint64 word);
 extern PGDLLIMPORT uint64 (*pg_popcount) (const char *buf, int bytes);
 
+/* Export pg_popcount_fast() for use in the AVX512 implementation. */
+extern uint64 pg_popcount_fast(const char *buf, int bytes);
+
+/*
+ * We can also try to use the AVX512 popcount instruction on some systems.
+ * The implementation of that is located in its own file because it may
+ * require special compiler flags that we don't want to apply to any other
+ * files.  Note that we only build this when TRY_POPCNT_FAST is set so that we
+ * can fall back to pg_popcount_fast() as needed.
+ */
+#ifdef USE_AVX512_POPCNT_WITH_RUNTIME_CHECK
+extern bool pg_popcount_avx512_available(void);
+extern uint64 pg_popcount_avx512(const char *buf, int bytes);
+#endif
+
 #else
 /* Use a portable implementation -- no need for a function pointer. */
 extern int	pg_popcount32(uint32 word);
diff --git a/src/makefiles/meson.build b/src/makefiles/meson.build
index b0f4178b3d..5618050b30 100644
--- a/src/makefiles/meson.build
+++ b/src/makefiles/meson.build
@@ -100,8 +100,10 @@ pgxs_kv = {
     ' '.join(cflags_no_decl_after_statement),
 
   'CFLAGS_CRC': ' '.join(cflags_crc),
+  'CFLAGS_POPCNT': ' '.join(cflags_popcnt),
   'CFLAGS_UNROLL_LOOPS': ' '.join(unroll_loops_cflags),
   'CFLAGS_VECTORIZE': ' '.join(vectorize_cflags),
+  'CFLAGS_XSAVE': ' '.join(cflags_xsave),
 
   'LDFLAGS': var_ldflags,
   'LDFLAGS_EX': var_ldflags_ex,
@@ -177,7 +179,7 @@ pgxs_empty = [
   'WANTED_LANGUAGES',
 
   # Not needed because we don't build the server / PLs with the generated makefile
-  'LIBOBJS', 'PG_CRC32C_OBJS', 'TAS',
+  'LIBOBJS', 'PG_CRC32C_OBJS', 'PG_POPCNT_OBJS', 'TAS',
   'DTRACEFLAGS', # only server has dtrace probes
 
   'perl_archlibexp', 'perl_embed_ccflags', 'perl_embed_ldflags', 'perl_includespec', 'perl_privlibexp',
diff --git a/src/port/Makefile b/src/port/Makefile
index dcc8737e68..db7c02117b 100644
--- a/src/port/Makefile
+++ b/src/port/Makefile
@@ -38,6 +38,7 @@ LIBS += $(PTHREAD_LIBS)
 OBJS = \
 	$(LIBOBJS) \
 	$(PG_CRC32C_OBJS) \
+	$(PG_POPCNT_OBJS) \
 	bsearch_arg.o \
 	chklocale.o \
 	inet_net_ntop.o \
@@ -92,6 +93,16 @@ pg_crc32c_armv8.o: CFLAGS+=$(CFLAGS_CRC)
 pg_crc32c_armv8_shlib.o: CFLAGS+=$(CFLAGS_CRC)
 pg_crc32c_armv8_srv.o: CFLAGS+=$(CFLAGS_CRC)
 
+# all versions of pg_popcount_avx512_choose.o need CFLAGS_XSAVE
+pg_popcount_avx512_choose.o: CFLAGS+=$(CFLAGS_XSAVE)
+pg_popcount_avx512_choose_shlib.o: CFLAGS+=$(CFLAGS_XSAVE)
+pg_popcount_avx512_choose_srv.o: CFLAGS+=$(CFLAGS_XSAVE)
+
+# all versions of pg_popcount_avx512.o need CFLAGS_POPCNT
+pg_popcount_avx512.o: CFLAGS+=$(CFLAGS_POPCNT)
+pg_popcount_avx512_shlib.o: CFLAGS+=$(CFLAGS_POPCNT)
+pg_popcount_avx512_srv.o: CFLAGS+=$(CFLAGS_POPCNT)
+
 #
 # Shared library versions of object files
 #
diff --git a/src/port/meson.build b/src/port/meson.build
index 92b593e6ef..fd9ee199d1 100644
--- a/src/port/meson.build
+++ b/src/port/meson.build
@@ -84,6 +84,8 @@ replace_funcs_pos = [
   ['pg_crc32c_sse42', 'USE_SSE42_CRC32C_WITH_RUNTIME_CHECK', 'crc'],
   ['pg_crc32c_sse42_choose', 'USE_SSE42_CRC32C_WITH_RUNTIME_CHECK'],
   ['pg_crc32c_sb8', 'USE_SSE42_CRC32C_WITH_RUNTIME_CHECK'],
+  ['pg_popcount_avx512', 'USE_AVX512_POPCNT_WITH_RUNTIME_CHECK', 'popcnt'],
+  ['pg_popcount_avx512_choose', 'USE_AVX512_POPCNT_WITH_RUNTIME_CHECK', 'xsave'],
 
   # arm / aarch64
   ['pg_crc32c_armv8', 'USE_ARMV8_CRC32C'],
@@ -98,8 +100,8 @@ replace_funcs_pos = [
   ['pg_crc32c_sb8', 'USE_SLICING_BY_8_CRC32C'],
 ]
 
-pgport_cflags = {'crc': cflags_crc}
-pgport_sources_cflags = {'crc': []}
+pgport_cflags = {'crc': cflags_crc, 'popcnt': cflags_popcnt, 'xsave': cflags_xsave}
+pgport_sources_cflags = {'crc': [], 'popcnt': [], 'xsave': []}
 
 foreach f : replace_funcs_neg
   func = f.get(0)
diff --git a/src/port/pg_bitutils.c b/src/port/pg_bitutils.c
index 28312f3dd9..177509518f 100644
--- a/src/port/pg_bitutils.c
+++ b/src/port/pg_bitutils.c
@@ -114,7 +114,6 @@ static int	pg_popcount64_choose(uint64 word);
 static uint64 pg_popcount_choose(const char *buf, int bytes);
 static inline int pg_popcount32_fast(uint32 word);
 static inline int pg_popcount64_fast(uint64 word);
-static uint64 pg_popcount_fast(const char *buf, int bytes);
 
 int			(*pg_popcount32) (uint32 word) = pg_popcount32_choose;
 int			(*pg_popcount64) (uint64 word) = pg_popcount64_choose;
@@ -156,6 +155,10 @@ choose_popcount_functions(void)
 		pg_popcount32 = pg_popcount32_fast;
 		pg_popcount64 = pg_popcount64_fast;
 		pg_popcount = pg_popcount_fast;
+#ifdef USE_AVX512_POPCNT_WITH_RUNTIME_CHECK
+		if (pg_popcount_avx512_available())
+			pg_popcount = pg_popcount_avx512;
+#endif
 	}
 	else
 	{
@@ -224,7 +227,7 @@ __asm__ __volatile__(" popcntq %1,%0\n":"=q"(res):"rm"(word):"cc");
  * pg_popcount_fast
  *		Returns the number of 1-bits in buf
  */
-static uint64
+uint64
 pg_popcount_fast(const char *buf, int bytes)
 {
 	uint64		popcnt = 0;
diff --git a/src/port/pg_popcount_avx512.c b/src/port/pg_popcount_avx512.c
new file mode 100644
index 0000000000..f86558d1ee
--- /dev/null
+++ b/src/port/pg_popcount_avx512.c
@@ -0,0 +1,49 @@
+/*-------------------------------------------------------------------------
+ *
+ * pg_popcount_avx512.c
+ *	  Holds the pg_popcount() implementation that uses AVX512 instructions.
+ *
+ * Copyright (c) 2024, PostgreSQL Global Development Group
+ *
+ * IDENTIFICATION
+ *	  src/port/pg_popcount_avx512.c
+ *
+ *-------------------------------------------------------------------------
+ */
+#include "c.h"
+
+#include <immintrin.h>
+
+#include "port/pg_bitutils.h"
+
+/*
+ * It's probably unlikely that TRY_POPCNT_FAST won't be set if we are able to
+ * use AVX512 intrinsics, but we check it anyway to be sure.  We rely on
+ * pg_popcount_fast() as our fallback implementation in pg_popcount_avx512().
+ */
+#ifdef TRY_POPCNT_FAST
+
+/*
+ * pg_popcount_avx512
+ *		Returns the number of 1-bits in buf
+ */
+uint64
+pg_popcount_avx512(const char *buf, int bytes)
+{
+	uint64		popcnt;
+	__m512i		accum = _mm512_setzero_si512();
+
+	for (; bytes >= sizeof(__m512i); bytes -= sizeof(__m512i))
+	{
+		const		__m512i val = _mm512_loadu_si512((const __m512i *) buf);
+		const		__m512i cnt = _mm512_popcnt_epi64(val);
+
+		accum = _mm512_add_epi64(accum, cnt);
+		buf += sizeof(__m512i);
+	}
+
+	popcnt = _mm512_reduce_add_epi64(accum);
+	return popcnt + pg_popcount_fast(buf, bytes);
+}
+
+#endif							/* TRY_POPCNT_FAST */
diff --git a/src/port/pg_popcount_avx512_choose.c b/src/port/pg_popcount_avx512_choose.c
new file mode 100644
index 0000000000..9e81cd33ad
--- /dev/null
+++ b/src/port/pg_popcount_avx512_choose.c
@@ -0,0 +1,71 @@
+/*-------------------------------------------------------------------------
+ *
+ * pg_popcount_avx512_choose.c
+ *    Test whether we can use AVX512 POPCNT instructions.
+ *
+ * Copyright (c) 2024, PostgreSQL Global Development Group
+ *
+ * IDENTIFICATION
+ *    src/port/pg_popcount_avx512_choose.c
+ *
+ *-------------------------------------------------------------------------
+ */
+#include "c.h"
+
+#if defined(HAVE__GET_CPUID) || defined(HAVE__GET_CPUID_COUNT)
+#include <cpuid.h>
+#endif
+
+#ifdef HAVE_XSAVE_INTRINSICS
+#include <immintrin.h>
+#endif
+
+#if defined(HAVE__CPUID) || defined(HAVE__CPUIDEX)
+#include <intrin.h>
+#endif
+
+#include "port/pg_bitutils.h"
+
+/*
+ * It's probably unlikely that TRY_POPCNT_FAST won't be set if we are able to
+ * use AVX512 intrinsics, but we check it anyway to be sure.  We rely on
+ * pg_popcount_fast() as our fallback implementation in pg_popcount_avx512().
+ */
+#ifdef TRY_POPCNT_FAST
+
+/*
+ * Returns true if the CPU supports AVX512 POPCNT.
+ */
+bool
+pg_popcount_avx512_available(void)
+{
+	unsigned int exx[4] = {0, 0, 0, 0};
+
+	/* does CPUID say there's support for AVX512 POPCNT? */
+#if defined(HAVE__GET_CPUID_COUNT)
+	__get_cpuid_count(7, 0, &exx[0], &exx[1], &exx[2], &exx[3]);
+#elif defined(HAVE__CPUIDEX)
+	__cpuidex(exx, 7, 0);
+#endif
+	if ((exx[2] & (1 << 14)) == 0)	/* avx512vpopcntdq */
+		return false;
+
+	/* does CPUID say there's support for XGETBV? */
+	memset(exx, 0, sizeof(exx));
+#if defined(HAVE__GET_CPUID)
+	__get_cpuid(1, &exx[0], &exx[1], &exx[2], &exx[3]);
+#elif defined(HAVE__CPUID)
+	__cpuid(exx, 1);
+#endif
+	if ((exx[2] & (1 << 26)) == 0)	/* xsave */
+		return false;
+
+	/* does XGETBV say the ZMM registers are enabled? */
+#ifdef HAVE_XSAVE_INTRINSICS
+	return (_xgetbv(0) & 0xe0) != 0;
+#else
+	return false;
+#endif
+}
+
+#endif							/* TRY_POPCNT_FAST */
diff --git a/src/test/regress/expected/bit.out b/src/test/regress/expected/bit.out
index e17cbf42ca..6a436288bb 100644
--- a/src/test/regress/expected/bit.out
+++ b/src/test/regress/expected/bit.out
@@ -740,6 +740,30 @@ SELECT bit_count(B'1111111111'::bit(10));
         10
 (1 row)
 
+SELECT bit_count(repeat('0', 100)::bit(100));
+ bit_count 
+-----------
+         0
+(1 row)
+
+SELECT bit_count(repeat('1', 100)::bit(100));
+ bit_count 
+-----------
+       100
+(1 row)
+
+SELECT bit_count(repeat('01', 500)::bit(1000));
+ bit_count 
+-----------
+       500
+(1 row)
+
+SELECT bit_count(repeat('10101', 200)::bit(1000));
+ bit_count 
+-----------
+       600
+(1 row)
+
 -- This table is intentionally left around to exercise pg_dump/pg_upgrade
 CREATE TABLE bit_defaults(
   b1 bit(4) DEFAULT '1001',
diff --git a/src/test/regress/sql/bit.sql b/src/test/regress/sql/bit.sql
index 34230b99fb..8ba6facd03 100644
--- a/src/test/regress/sql/bit.sql
+++ b/src/test/regress/sql/bit.sql
@@ -223,6 +223,10 @@ SELECT overlay(B'0101011100' placing '001' from 20);
 -- bit_count
 SELECT bit_count(B'0101011100'::bit(10));
 SELECT bit_count(B'1111111111'::bit(10));
+SELECT bit_count(repeat('0', 100)::bit(100));
+SELECT bit_count(repeat('1', 100)::bit(100));
+SELECT bit_count(repeat('01', 500)::bit(1000));
+SELECT bit_count(repeat('10101', 200)::bit(1000));
 
 -- This table is intentionally left around to exercise pg_dump/pg_upgrade
 CREATE TABLE bit_defaults(
-- 
2.25.1


--bg08WKrSYDhXBjb5
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v19-0004-optimize-visibilitymap_count-with-AVX512.patch"



^ permalink  raw  reply  [nested|flat] 16+ messages in thread

* [PATCH v20 1/2] AVX512 popcount support
@ 2024-03-27 21:39 Nathan Bossart <[email protected]>
  0 siblings, 0 replies; 16+ messages in thread

From: Nathan Bossart @ 2024-03-27 21:39 UTC (permalink / raw)

---
 config/c-compiler.m4                 |  58 ++++++
 configure                            | 252 +++++++++++++++++++++++++++
 configure.ac                         |  51 ++++++
 meson.build                          |  87 +++++++++
 src/Makefile.global.in               |   5 +
 src/include/pg_config.h.in           |  12 ++
 src/include/port/pg_bitutils.h       |  15 ++
 src/makefiles/meson.build            |   4 +-
 src/port/Makefile                    |  11 ++
 src/port/meson.build                 |   6 +-
 src/port/pg_bitutils.c               |   7 +-
 src/port/pg_popcount_avx512.c        |  49 ++++++
 src/port/pg_popcount_avx512_choose.c |  71 ++++++++
 src/test/regress/expected/bit.out    |  24 +++
 src/test/regress/sql/bit.sql         |   4 +
 15 files changed, 651 insertions(+), 5 deletions(-)
 create mode 100644 src/port/pg_popcount_avx512.c
 create mode 100644 src/port/pg_popcount_avx512_choose.c

diff --git a/config/c-compiler.m4 b/config/c-compiler.m4
index 3268a780bb..5fb60775ca 100644
--- a/config/c-compiler.m4
+++ b/config/c-compiler.m4
@@ -694,3 +694,61 @@ if test x"$Ac_cachevar" = x"yes"; then
 fi
 undefine([Ac_cachevar])dnl
 ])# PGAC_LOONGARCH_CRC32C_INTRINSICS
+
+# PGAC_XSAVE_INTRINSICS
+# ---------------------
+# Check if the compiler supports the XSAVE instructions using the _xgetbv
+# intrinsic function.
+#
+# An optional compiler flag can be passed as argument (e.g., -mxsave).  If the
+# intrinsic is supported, sets pgac_xsave_intrinsics and CFLAGS_XSAVE.
+AC_DEFUN([PGAC_XSAVE_INTRINSICS],
+[define([Ac_cachevar], [AS_TR_SH([pgac_cv_xsave_intrinsics_$1])])dnl
+AC_CACHE_CHECK([for _xgetbv with CFLAGS=$1], [Ac_cachevar],
+[pgac_save_CFLAGS=$CFLAGS
+CFLAGS="$pgac_save_CFLAGS $1"
+AC_LINK_IFELSE([AC_LANG_PROGRAM([#include <immintrin.h>],
+  [return _xgetbv(0) & 0xe0;])],
+  [Ac_cachevar=yes],
+  [Ac_cachevar=no])
+CFLAGS="$pgac_save_CFLAGS"])
+if test x"$Ac_cachevar" = x"yes"; then
+  CFLAGS_XSAVE="$1"
+  pgac_xsave_intrinsics=yes
+fi
+undefine([Ac_cachevar])dnl
+])# PGAC_XSAVE_INTRINSICS
+
+# PGAC_AVX512_POPCNT_INTRINSICS
+# -----------------------------
+# Check if the compiler supports the AVX512 POPCNT instructions using the
+# _mm512_setzero_si512, _mm512_loadu_si512, _mm512_popcnt_epi64,
+# _mm512_add_epi64, and _mm512_reduce_add_epi64 intrinsic functions.
+#
+# An optional compiler flag can be passed as argument
+# (e.g., -mavx512vpopcntdq).  If the intrinsics are supported, sets
+# pgac_avx512_popcnt_intrinsics and CFLAGS_POPCNT.
+AC_DEFUN([PGAC_AVX512_POPCNT_INTRINSICS],
+[define([Ac_cachevar], [AS_TR_SH([pgac_cv_avx512_popcnt_intrinsics_$1])])dnl
+AC_CACHE_CHECK([for _mm512_popcnt_epi64 with CFLAGS=$1], [Ac_cachevar],
+[pgac_save_CFLAGS=$CFLAGS
+CFLAGS="$pgac_save_CFLAGS $1"
+AC_LINK_IFELSE([AC_LANG_PROGRAM([#include <immintrin.h>],
+  [const char buf@<:@sizeof(__m512i)@:>@;
+   PG_INT64_TYPE popcnt = 0;
+   __m512i accum = _mm512_setzero_si512();
+   const __m512i val = _mm512_loadu_si512((const __m512i *) buf);
+   const __m512i cnt = _mm512_popcnt_epi64(val);
+   accum = _mm512_add_epi64(accum, cnt);
+   popcnt = _mm512_reduce_add_epi64(accum);
+   /* return computed value, to prevent the above being optimized away */
+   return popcnt == 0;])],
+  [Ac_cachevar=yes],
+  [Ac_cachevar=no])
+CFLAGS="$pgac_save_CFLAGS"])
+if test x"$Ac_cachevar" = x"yes"; then
+  CFLAGS_POPCNT="$1"
+  pgac_avx512_popcnt_intrinsics=yes
+fi
+undefine([Ac_cachevar])dnl
+])# PGAC_AVX512_POPCNT_INTRINSICS
diff --git a/configure b/configure
index 36feeafbb2..b48ed7f271 100755
--- a/configure
+++ b/configure
@@ -647,6 +647,9 @@ MSGFMT_FLAGS
 MSGFMT
 PG_CRC32C_OBJS
 CFLAGS_CRC
+PG_POPCNT_OBJS
+CFLAGS_POPCNT
+CFLAGS_XSAVE
 LIBOBJS
 OPENSSL
 ZSTD
@@ -17404,6 +17407,40 @@ $as_echo "#define HAVE__GET_CPUID 1" >>confdefs.h
 
 fi
 
+{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for __get_cpuid_count" >&5
+$as_echo_n "checking for __get_cpuid_count... " >&6; }
+if ${pgac_cv__get_cpuid_count+:} 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_count(7, 0, &exx[0], &exx[1], &exx[2], &exx[3]);
+
+  ;
+  return 0;
+}
+_ACEOF
+if ac_fn_c_try_link "$LINENO"; then :
+  pgac_cv__get_cpuid_count="yes"
+else
+  pgac_cv__get_cpuid_count="no"
+fi
+rm -f core conftest.err conftest.$ac_objext \
+    conftest$ac_exeext conftest.$ac_ext
+fi
+{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $pgac_cv__get_cpuid_count" >&5
+$as_echo "$pgac_cv__get_cpuid_count" >&6; }
+if test x"$pgac_cv__get_cpuid_count" = x"yes"; then
+
+$as_echo "#define HAVE__GET_CPUID_COUNT 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 :
@@ -17438,6 +17475,221 @@ $as_echo "#define HAVE__CPUID 1" >>confdefs.h
 
 fi
 
+{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for __cpuidex" >&5
+$as_echo_n "checking for __cpuidex... " >&6; }
+if ${pgac_cv__cpuidex+:} 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_cpuidex(exx[0], 7, 0);
+
+  ;
+  return 0;
+}
+_ACEOF
+if ac_fn_c_try_link "$LINENO"; then :
+  pgac_cv__cpuidex="yes"
+else
+  pgac_cv__cpuidex="no"
+fi
+rm -f core conftest.err conftest.$ac_objext \
+    conftest$ac_exeext conftest.$ac_ext
+fi
+{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $pgac_cv__cpuidex" >&5
+$as_echo "$pgac_cv__cpuidex" >&6; }
+if test x"$pgac_cv__cpuidex" = x"yes"; then
+
+$as_echo "#define HAVE__CPUIDEX 1" >>confdefs.h
+
+fi
+
+# Check for XSAVE intrinsics
+#
+CFLAGS_XSAVE=""
+{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for _xgetbv with CFLAGS=" >&5
+$as_echo_n "checking for _xgetbv with CFLAGS=... " >&6; }
+if ${pgac_cv_xsave_intrinsics_+:} false; then :
+  $as_echo_n "(cached) " >&6
+else
+  pgac_save_CFLAGS=$CFLAGS
+CFLAGS="$pgac_save_CFLAGS "
+cat confdefs.h - <<_ACEOF >conftest.$ac_ext
+/* end confdefs.h.  */
+#include <immintrin.h>
+int
+main ()
+{
+return _xgetbv(0) & 0xe0;
+  ;
+  return 0;
+}
+_ACEOF
+if ac_fn_c_try_link "$LINENO"; then :
+  pgac_cv_xsave_intrinsics_=yes
+else
+  pgac_cv_xsave_intrinsics_=no
+fi
+rm -f core conftest.err conftest.$ac_objext \
+    conftest$ac_exeext conftest.$ac_ext
+CFLAGS="$pgac_save_CFLAGS"
+fi
+{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $pgac_cv_xsave_intrinsics_" >&5
+$as_echo "$pgac_cv_xsave_intrinsics_" >&6; }
+if test x"$pgac_cv_xsave_intrinsics_" = x"yes"; then
+  CFLAGS_XSAVE=""
+  pgac_xsave_intrinsics=yes
+fi
+
+if test x"$pgac_xsave_intrinsics" != x"yes"; then
+  { $as_echo "$as_me:${as_lineno-$LINENO}: checking for _xgetbv with CFLAGS=-mxsave" >&5
+$as_echo_n "checking for _xgetbv with CFLAGS=-mxsave... " >&6; }
+if ${pgac_cv_xsave_intrinsics__mxsave+:} false; then :
+  $as_echo_n "(cached) " >&6
+else
+  pgac_save_CFLAGS=$CFLAGS
+CFLAGS="$pgac_save_CFLAGS -mxsave"
+cat confdefs.h - <<_ACEOF >conftest.$ac_ext
+/* end confdefs.h.  */
+#include <immintrin.h>
+int
+main ()
+{
+return _xgetbv(0) & 0xe0;
+  ;
+  return 0;
+}
+_ACEOF
+if ac_fn_c_try_link "$LINENO"; then :
+  pgac_cv_xsave_intrinsics__mxsave=yes
+else
+  pgac_cv_xsave_intrinsics__mxsave=no
+fi
+rm -f core conftest.err conftest.$ac_objext \
+    conftest$ac_exeext conftest.$ac_ext
+CFLAGS="$pgac_save_CFLAGS"
+fi
+{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $pgac_cv_xsave_intrinsics__mxsave" >&5
+$as_echo "$pgac_cv_xsave_intrinsics__mxsave" >&6; }
+if test x"$pgac_cv_xsave_intrinsics__mxsave" = x"yes"; then
+  CFLAGS_XSAVE="-mxsave"
+  pgac_xsave_intrinsics=yes
+fi
+
+fi
+if test x"$pgac_xsave_intrinsics" = x"yes"; then
+
+$as_echo "#define HAVE_XSAVE_INTRINSICS 1" >>confdefs.h
+
+fi
+
+
+# Check for AVX512 popcount intrinsics
+#
+CFLAGS_POPCNT=""
+PG_POPCNT_OBJS=""
+if test x"$host_cpu" = x"x86_64"; then
+  { $as_echo "$as_me:${as_lineno-$LINENO}: checking for _mm512_popcnt_epi64 with CFLAGS=" >&5
+$as_echo_n "checking for _mm512_popcnt_epi64 with CFLAGS=... " >&6; }
+if ${pgac_cv_avx512_popcnt_intrinsics_+:} false; then :
+  $as_echo_n "(cached) " >&6
+else
+  pgac_save_CFLAGS=$CFLAGS
+CFLAGS="$pgac_save_CFLAGS "
+cat confdefs.h - <<_ACEOF >conftest.$ac_ext
+/* end confdefs.h.  */
+#include <immintrin.h>
+int
+main ()
+{
+const char buf[sizeof(__m512i)];
+   PG_INT64_TYPE popcnt = 0;
+   __m512i accum = _mm512_setzero_si512();
+   const __m512i val = _mm512_loadu_si512((const __m512i *) buf);
+   const __m512i cnt = _mm512_popcnt_epi64(val);
+   accum = _mm512_add_epi64(accum, cnt);
+   popcnt = _mm512_reduce_add_epi64(accum);
+   /* return computed value, to prevent the above being optimized away */
+   return popcnt == 0;
+  ;
+  return 0;
+}
+_ACEOF
+if ac_fn_c_try_link "$LINENO"; then :
+  pgac_cv_avx512_popcnt_intrinsics_=yes
+else
+  pgac_cv_avx512_popcnt_intrinsics_=no
+fi
+rm -f core conftest.err conftest.$ac_objext \
+    conftest$ac_exeext conftest.$ac_ext
+CFLAGS="$pgac_save_CFLAGS"
+fi
+{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $pgac_cv_avx512_popcnt_intrinsics_" >&5
+$as_echo "$pgac_cv_avx512_popcnt_intrinsics_" >&6; }
+if test x"$pgac_cv_avx512_popcnt_intrinsics_" = x"yes"; then
+  CFLAGS_POPCNT=""
+  pgac_avx512_popcnt_intrinsics=yes
+fi
+
+  if test x"$pgac_avx512_popcnt_intrinsics" != x"yes"; then
+    { $as_echo "$as_me:${as_lineno-$LINENO}: checking for _mm512_popcnt_epi64 with CFLAGS=-mavx512vpopcntdq" >&5
+$as_echo_n "checking for _mm512_popcnt_epi64 with CFLAGS=-mavx512vpopcntdq... " >&6; }
+if ${pgac_cv_avx512_popcnt_intrinsics__mavx512vpopcntdq+:} false; then :
+  $as_echo_n "(cached) " >&6
+else
+  pgac_save_CFLAGS=$CFLAGS
+CFLAGS="$pgac_save_CFLAGS -mavx512vpopcntdq"
+cat confdefs.h - <<_ACEOF >conftest.$ac_ext
+/* end confdefs.h.  */
+#include <immintrin.h>
+int
+main ()
+{
+const char buf[sizeof(__m512i)];
+   PG_INT64_TYPE popcnt = 0;
+   __m512i accum = _mm512_setzero_si512();
+   const __m512i val = _mm512_loadu_si512((const __m512i *) buf);
+   const __m512i cnt = _mm512_popcnt_epi64(val);
+   accum = _mm512_add_epi64(accum, cnt);
+   popcnt = _mm512_reduce_add_epi64(accum);
+   /* return computed value, to prevent the above being optimized away */
+   return popcnt == 0;
+  ;
+  return 0;
+}
+_ACEOF
+if ac_fn_c_try_link "$LINENO"; then :
+  pgac_cv_avx512_popcnt_intrinsics__mavx512vpopcntdq=yes
+else
+  pgac_cv_avx512_popcnt_intrinsics__mavx512vpopcntdq=no
+fi
+rm -f core conftest.err conftest.$ac_objext \
+    conftest$ac_exeext conftest.$ac_ext
+CFLAGS="$pgac_save_CFLAGS"
+fi
+{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $pgac_cv_avx512_popcnt_intrinsics__mavx512vpopcntdq" >&5
+$as_echo "$pgac_cv_avx512_popcnt_intrinsics__mavx512vpopcntdq" >&6; }
+if test x"$pgac_cv_avx512_popcnt_intrinsics__mavx512vpopcntdq" = x"yes"; then
+  CFLAGS_POPCNT="-mavx512vpopcntdq"
+  pgac_avx512_popcnt_intrinsics=yes
+fi
+
+  fi
+  if test x"$pgac_avx512_popcnt_intrinsics" = x"yes"; then
+    PG_POPCNT_OBJS="pg_popcount_avx512.o pg_popcount_avx512_choose.o"
+
+$as_echo "#define USE_AVX512_POPCNT_WITH_RUNTIME_CHECK 1" >>confdefs.h
+
+  fi
+fi
+
+
+
 # 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
diff --git a/configure.ac b/configure.ac
index 57f734879e..2bbd81dfb8 100644
--- a/configure.ac
+++ b/configure.ac
@@ -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"$pgac_xsave_intrinsics" = x"yes"; then
+  AC_DEFINE(HAVE_XSAVE_INTRINSICS, 1, [Define to 1 if you have XSAVE intrinsics.])
+fi
+AC_SUBST(CFLAGS_XSAVE)
+
+# Check for AVX512 popcount intrinsics
+#
+CFLAGS_POPCNT=""
+PG_POPCNT_OBJS=""
+if test x"$host_cpu" = x"x86_64"; then
+  PGAC_AVX512_POPCNT_INTRINSICS([])
+  if test x"$pgac_avx512_popcnt_intrinsics" != x"yes"; then
+    PGAC_AVX512_POPCNT_INTRINSICS([-mavx512vpopcntdq])
+  fi
+  if test x"$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 AVX512 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
diff --git a/meson.build b/meson.build
index 18b5be842e..96be29c22b 100644
--- a/meson.build
+++ b/meson.build
@@ -1783,6 +1783,30 @@ elif cc.links('''
 endif
 
 
+# Check for __get_cpuid_count() and __cpuidex() in a similar fashion.
+if cc.links('''
+    #include <cpuid.h>
+    int main(int arg, char **argv)
+    {
+        unsigned int exx[4] = {0, 0, 0, 0};
+        __get_cpuid_count(7, 0, &exx[0], &exx[1], &exx[2], &exx[3]);
+    }
+    ''', name: '__get_cpuid_count',
+    args: test_c_args)
+  cdata.set('HAVE__GET_CPUID_COUNT', 1)
+elif cc.links('''
+    #include <intrin.h>
+    int main(int arg, char **argv)
+    {
+        unsigned int exx[4] = {0, 0, 0, 0};
+        __cpuidex(exx, 7, 0);
+    }
+    ''', name: '__cpuidex',
+    args: test_c_args)
+  cdata.set('HAVE__CPUIDEX', 1)
+endif
+
+
 # Defend against clang being used on x86-32 without SSE2 enabled.  As current
 # versions of clang do not understand -fexcess-precision=standard, the use of
 # x87 floating point operations leads to problems like isinf possibly returning
@@ -1996,6 +2020,69 @@ int main(void)
 endif
 
 
+###############################################################
+# Check for the availability of XSAVE intrinsics.
+###############################################################
+
+cflags_xsave = []
+if host_cpu == 'x86' or host_cpu == 'x86_64'
+
+  prog = '''
+#include <immintrin.h>
+
+int main(void)
+{
+    return _xgetbv(0) & 0xe0;
+}
+'''
+
+  if cc.links(prog, name: 'XSAVE intrinsics without -mxsave',
+        args: test_c_args)
+    cdata.set('HAVE_XSAVE_INTRINSICS', 1)
+  elif cc.links(prog, name: 'XSAVE intrinsics with -mxsave',
+        args: test_c_args + ['-mxsave'])
+    cdata.set('HAVE_XSAVE_INTRINSICS', 1)
+    cflags_xsave += '-mxsave'
+  endif
+
+endif
+
+
+###############################################################
+# Check for the availability of AVX512 popcount intrinsics.
+###############################################################
+
+cflags_popcnt = []
+if host_cpu == 'x86_64'
+
+  prog = '''
+#include <immintrin.h>
+
+int main(void)
+{
+    const char buf[sizeof(__m512i)];
+    INT64 popcnt = 0;
+    __m512i accum = _mm512_setzero_si512();
+    const __m512i val = _mm512_loadu_si512((const __m512i *) buf);
+    const __m512i cnt = _mm512_popcnt_epi64(val);
+    accum = _mm512_add_epi64(accum, cnt);
+    popcnt = _mm512_reduce_add_epi64(accum);
+    /* return computed value, to prevent the above being optimized away */
+    return popcnt == 0;
+}
+'''
+
+  if cc.links(prog, name: 'AVX512 popcount without -mavx512vpopcntdq',
+        args: test_c_args + ['-DINT64=@0@'.format(cdata.get('PG_INT64_TYPE'))])
+    cdata.set('USE_AVX512_POPCNT_WITH_RUNTIME_CHECK', 1)
+  elif cc.links(prog, name: 'AVX512 popcount with -mavx512vpopcntdq',
+        args: test_c_args + ['-DINT64=@0@'.format(cdata.get('PG_INT64_TYPE'))] + ['-mavx512vpopcntdq'])
+    cdata.set('USE_AVX512_POPCNT_WITH_RUNTIME_CHECK', 1)
+    cflags_popcnt += '-mavx512vpopcntdq'
+  endif
+
+endif
+
 
 ###############################################################
 # Select CRC-32C implementation.
diff --git a/src/Makefile.global.in b/src/Makefile.global.in
index 8b3f8c24e0..36d880d225 100644
--- a/src/Makefile.global.in
+++ b/src/Makefile.global.in
@@ -262,7 +262,9 @@ CFLAGS_SL_MODULE = @CFLAGS_SL_MODULE@
 CXXFLAGS_SL_MODULE = @CXXFLAGS_SL_MODULE@
 CFLAGS_UNROLL_LOOPS = @CFLAGS_UNROLL_LOOPS@
 CFLAGS_VECTORIZE = @CFLAGS_VECTORIZE@
+CFLAGS_POPCNT = @CFLAGS_POPCNT@
 CFLAGS_CRC = @CFLAGS_CRC@
+CFLAGS_XSAVE = @CFLAGS_XSAVE@
 PERMIT_DECLARATION_AFTER_STATEMENT = @PERMIT_DECLARATION_AFTER_STATEMENT@
 CXXFLAGS = @CXXFLAGS@
 
@@ -758,6 +760,9 @@ LIBOBJS = @LIBOBJS@
 # files needed for the chosen CRC-32C implementation
 PG_CRC32C_OBJS = @PG_CRC32C_OBJS@
 
+# files needed for the chosen popcount implementation
+PG_POPCNT_OBJS = @PG_POPCNT_OBJS@
+
 LIBS := -lpgcommon -lpgport $(LIBS)
 
 # to make ws2_32.lib the last library
diff --git a/src/include/pg_config.h.in b/src/include/pg_config.h.in
index 591e1ca3df..de067e6182 100644
--- a/src/include/pg_config.h.in
+++ b/src/include/pg_config.h.in
@@ -513,6 +513,9 @@
 /* Define to 1 if the assembler supports X86_64's POPCNTQ instruction. */
 #undef HAVE_X86_64_POPCNTQ
 
+/* Define to 1 if you have XSAVE intrinsics. */
+#undef HAVE_XSAVE_INTRINSICS
+
 /* Define to 1 if the system has the type `_Bool'. */
 #undef HAVE__BOOL
 
@@ -555,9 +558,15 @@
 /* Define to 1 if you have __cpuid. */
 #undef HAVE__CPUID
 
+/* Define to 1 if you have __cpuidex. */
+#undef HAVE__CPUIDEX
+
 /* Define to 1 if you have __get_cpuid. */
 #undef HAVE__GET_CPUID
 
+/* Define to 1 if you have __get_cpuid_count. */
+#undef HAVE__GET_CPUID_COUNT
+
 /* Define to 1 if your compiler understands _Static_assert. */
 #undef HAVE__STATIC_ASSERT
 
@@ -680,6 +689,9 @@
 /* Define to 1 to build with assertion checks. (--enable-cassert) */
 #undef USE_ASSERT_CHECKING
 
+/* Define to 1 to use AVX512 popcount instructions with a runtime check. */
+#undef USE_AVX512_POPCNT_WITH_RUNTIME_CHECK
+
 /* Define to 1 to build with Bonjour support. (--with-bonjour) */
 #undef USE_BONJOUR
 
diff --git a/src/include/port/pg_bitutils.h b/src/include/port/pg_bitutils.h
index 53e5239717..1a92c56bcd 100644
--- a/src/include/port/pg_bitutils.h
+++ b/src/include/port/pg_bitutils.h
@@ -304,6 +304,21 @@ extern PGDLLIMPORT int (*pg_popcount32) (uint32 word);
 extern PGDLLIMPORT int (*pg_popcount64) (uint64 word);
 extern PGDLLIMPORT uint64 (*pg_popcount) (const char *buf, int bytes);
 
+/* Export pg_popcount_fast() for use in the AVX512 implementation. */
+extern uint64 pg_popcount_fast(const char *buf, int bytes);
+
+/*
+ * We can also try to use the AVX512 popcount instruction on some systems.
+ * The implementation of that is located in its own file because it may
+ * require special compiler flags that we don't want to apply to any other
+ * files.  Note that we only build this when TRY_POPCNT_FAST is set so that we
+ * can fall back to pg_popcount_fast() as needed.
+ */
+#ifdef USE_AVX512_POPCNT_WITH_RUNTIME_CHECK
+extern bool pg_popcount_avx512_available(void);
+extern uint64 pg_popcount_avx512(const char *buf, int bytes);
+#endif
+
 #else
 /* Use a portable implementation -- no need for a function pointer. */
 extern int	pg_popcount32(uint32 word);
diff --git a/src/makefiles/meson.build b/src/makefiles/meson.build
index b0f4178b3d..5618050b30 100644
--- a/src/makefiles/meson.build
+++ b/src/makefiles/meson.build
@@ -100,8 +100,10 @@ pgxs_kv = {
     ' '.join(cflags_no_decl_after_statement),
 
   'CFLAGS_CRC': ' '.join(cflags_crc),
+  'CFLAGS_POPCNT': ' '.join(cflags_popcnt),
   'CFLAGS_UNROLL_LOOPS': ' '.join(unroll_loops_cflags),
   'CFLAGS_VECTORIZE': ' '.join(vectorize_cflags),
+  'CFLAGS_XSAVE': ' '.join(cflags_xsave),
 
   'LDFLAGS': var_ldflags,
   'LDFLAGS_EX': var_ldflags_ex,
@@ -177,7 +179,7 @@ pgxs_empty = [
   'WANTED_LANGUAGES',
 
   # Not needed because we don't build the server / PLs with the generated makefile
-  'LIBOBJS', 'PG_CRC32C_OBJS', 'TAS',
+  'LIBOBJS', 'PG_CRC32C_OBJS', 'PG_POPCNT_OBJS', 'TAS',
   'DTRACEFLAGS', # only server has dtrace probes
 
   'perl_archlibexp', 'perl_embed_ccflags', 'perl_embed_ldflags', 'perl_includespec', 'perl_privlibexp',
diff --git a/src/port/Makefile b/src/port/Makefile
index dcc8737e68..db7c02117b 100644
--- a/src/port/Makefile
+++ b/src/port/Makefile
@@ -38,6 +38,7 @@ LIBS += $(PTHREAD_LIBS)
 OBJS = \
 	$(LIBOBJS) \
 	$(PG_CRC32C_OBJS) \
+	$(PG_POPCNT_OBJS) \
 	bsearch_arg.o \
 	chklocale.o \
 	inet_net_ntop.o \
@@ -92,6 +93,16 @@ pg_crc32c_armv8.o: CFLAGS+=$(CFLAGS_CRC)
 pg_crc32c_armv8_shlib.o: CFLAGS+=$(CFLAGS_CRC)
 pg_crc32c_armv8_srv.o: CFLAGS+=$(CFLAGS_CRC)
 
+# all versions of pg_popcount_avx512_choose.o need CFLAGS_XSAVE
+pg_popcount_avx512_choose.o: CFLAGS+=$(CFLAGS_XSAVE)
+pg_popcount_avx512_choose_shlib.o: CFLAGS+=$(CFLAGS_XSAVE)
+pg_popcount_avx512_choose_srv.o: CFLAGS+=$(CFLAGS_XSAVE)
+
+# all versions of pg_popcount_avx512.o need CFLAGS_POPCNT
+pg_popcount_avx512.o: CFLAGS+=$(CFLAGS_POPCNT)
+pg_popcount_avx512_shlib.o: CFLAGS+=$(CFLAGS_POPCNT)
+pg_popcount_avx512_srv.o: CFLAGS+=$(CFLAGS_POPCNT)
+
 #
 # Shared library versions of object files
 #
diff --git a/src/port/meson.build b/src/port/meson.build
index 92b593e6ef..fd9ee199d1 100644
--- a/src/port/meson.build
+++ b/src/port/meson.build
@@ -84,6 +84,8 @@ replace_funcs_pos = [
   ['pg_crc32c_sse42', 'USE_SSE42_CRC32C_WITH_RUNTIME_CHECK', 'crc'],
   ['pg_crc32c_sse42_choose', 'USE_SSE42_CRC32C_WITH_RUNTIME_CHECK'],
   ['pg_crc32c_sb8', 'USE_SSE42_CRC32C_WITH_RUNTIME_CHECK'],
+  ['pg_popcount_avx512', 'USE_AVX512_POPCNT_WITH_RUNTIME_CHECK', 'popcnt'],
+  ['pg_popcount_avx512_choose', 'USE_AVX512_POPCNT_WITH_RUNTIME_CHECK', 'xsave'],
 
   # arm / aarch64
   ['pg_crc32c_armv8', 'USE_ARMV8_CRC32C'],
@@ -98,8 +100,8 @@ replace_funcs_pos = [
   ['pg_crc32c_sb8', 'USE_SLICING_BY_8_CRC32C'],
 ]
 
-pgport_cflags = {'crc': cflags_crc}
-pgport_sources_cflags = {'crc': []}
+pgport_cflags = {'crc': cflags_crc, 'popcnt': cflags_popcnt, 'xsave': cflags_xsave}
+pgport_sources_cflags = {'crc': [], 'popcnt': [], 'xsave': []}
 
 foreach f : replace_funcs_neg
   func = f.get(0)
diff --git a/src/port/pg_bitutils.c b/src/port/pg_bitutils.c
index 28312f3dd9..177509518f 100644
--- a/src/port/pg_bitutils.c
+++ b/src/port/pg_bitutils.c
@@ -114,7 +114,6 @@ static int	pg_popcount64_choose(uint64 word);
 static uint64 pg_popcount_choose(const char *buf, int bytes);
 static inline int pg_popcount32_fast(uint32 word);
 static inline int pg_popcount64_fast(uint64 word);
-static uint64 pg_popcount_fast(const char *buf, int bytes);
 
 int			(*pg_popcount32) (uint32 word) = pg_popcount32_choose;
 int			(*pg_popcount64) (uint64 word) = pg_popcount64_choose;
@@ -156,6 +155,10 @@ choose_popcount_functions(void)
 		pg_popcount32 = pg_popcount32_fast;
 		pg_popcount64 = pg_popcount64_fast;
 		pg_popcount = pg_popcount_fast;
+#ifdef USE_AVX512_POPCNT_WITH_RUNTIME_CHECK
+		if (pg_popcount_avx512_available())
+			pg_popcount = pg_popcount_avx512;
+#endif
 	}
 	else
 	{
@@ -224,7 +227,7 @@ __asm__ __volatile__(" popcntq %1,%0\n":"=q"(res):"rm"(word):"cc");
  * pg_popcount_fast
  *		Returns the number of 1-bits in buf
  */
-static uint64
+uint64
 pg_popcount_fast(const char *buf, int bytes)
 {
 	uint64		popcnt = 0;
diff --git a/src/port/pg_popcount_avx512.c b/src/port/pg_popcount_avx512.c
new file mode 100644
index 0000000000..f86558d1ee
--- /dev/null
+++ b/src/port/pg_popcount_avx512.c
@@ -0,0 +1,49 @@
+/*-------------------------------------------------------------------------
+ *
+ * pg_popcount_avx512.c
+ *	  Holds the pg_popcount() implementation that uses AVX512 instructions.
+ *
+ * Copyright (c) 2024, PostgreSQL Global Development Group
+ *
+ * IDENTIFICATION
+ *	  src/port/pg_popcount_avx512.c
+ *
+ *-------------------------------------------------------------------------
+ */
+#include "c.h"
+
+#include <immintrin.h>
+
+#include "port/pg_bitutils.h"
+
+/*
+ * It's probably unlikely that TRY_POPCNT_FAST won't be set if we are able to
+ * use AVX512 intrinsics, but we check it anyway to be sure.  We rely on
+ * pg_popcount_fast() as our fallback implementation in pg_popcount_avx512().
+ */
+#ifdef TRY_POPCNT_FAST
+
+/*
+ * pg_popcount_avx512
+ *		Returns the number of 1-bits in buf
+ */
+uint64
+pg_popcount_avx512(const char *buf, int bytes)
+{
+	uint64		popcnt;
+	__m512i		accum = _mm512_setzero_si512();
+
+	for (; bytes >= sizeof(__m512i); bytes -= sizeof(__m512i))
+	{
+		const		__m512i val = _mm512_loadu_si512((const __m512i *) buf);
+		const		__m512i cnt = _mm512_popcnt_epi64(val);
+
+		accum = _mm512_add_epi64(accum, cnt);
+		buf += sizeof(__m512i);
+	}
+
+	popcnt = _mm512_reduce_add_epi64(accum);
+	return popcnt + pg_popcount_fast(buf, bytes);
+}
+
+#endif							/* TRY_POPCNT_FAST */
diff --git a/src/port/pg_popcount_avx512_choose.c b/src/port/pg_popcount_avx512_choose.c
new file mode 100644
index 0000000000..9e81cd33ad
--- /dev/null
+++ b/src/port/pg_popcount_avx512_choose.c
@@ -0,0 +1,71 @@
+/*-------------------------------------------------------------------------
+ *
+ * pg_popcount_avx512_choose.c
+ *    Test whether we can use AVX512 POPCNT instructions.
+ *
+ * Copyright (c) 2024, PostgreSQL Global Development Group
+ *
+ * IDENTIFICATION
+ *    src/port/pg_popcount_avx512_choose.c
+ *
+ *-------------------------------------------------------------------------
+ */
+#include "c.h"
+
+#if defined(HAVE__GET_CPUID) || defined(HAVE__GET_CPUID_COUNT)
+#include <cpuid.h>
+#endif
+
+#ifdef HAVE_XSAVE_INTRINSICS
+#include <immintrin.h>
+#endif
+
+#if defined(HAVE__CPUID) || defined(HAVE__CPUIDEX)
+#include <intrin.h>
+#endif
+
+#include "port/pg_bitutils.h"
+
+/*
+ * It's probably unlikely that TRY_POPCNT_FAST won't be set if we are able to
+ * use AVX512 intrinsics, but we check it anyway to be sure.  We rely on
+ * pg_popcount_fast() as our fallback implementation in pg_popcount_avx512().
+ */
+#ifdef TRY_POPCNT_FAST
+
+/*
+ * Returns true if the CPU supports AVX512 POPCNT.
+ */
+bool
+pg_popcount_avx512_available(void)
+{
+	unsigned int exx[4] = {0, 0, 0, 0};
+
+	/* does CPUID say there's support for AVX512 POPCNT? */
+#if defined(HAVE__GET_CPUID_COUNT)
+	__get_cpuid_count(7, 0, &exx[0], &exx[1], &exx[2], &exx[3]);
+#elif defined(HAVE__CPUIDEX)
+	__cpuidex(exx, 7, 0);
+#endif
+	if ((exx[2] & (1 << 14)) == 0)	/* avx512vpopcntdq */
+		return false;
+
+	/* does CPUID say there's support for XGETBV? */
+	memset(exx, 0, sizeof(exx));
+#if defined(HAVE__GET_CPUID)
+	__get_cpuid(1, &exx[0], &exx[1], &exx[2], &exx[3]);
+#elif defined(HAVE__CPUID)
+	__cpuid(exx, 1);
+#endif
+	if ((exx[2] & (1 << 26)) == 0)	/* xsave */
+		return false;
+
+	/* does XGETBV say the ZMM registers are enabled? */
+#ifdef HAVE_XSAVE_INTRINSICS
+	return (_xgetbv(0) & 0xe0) != 0;
+#else
+	return false;
+#endif
+}
+
+#endif							/* TRY_POPCNT_FAST */
diff --git a/src/test/regress/expected/bit.out b/src/test/regress/expected/bit.out
index e17cbf42ca..6a436288bb 100644
--- a/src/test/regress/expected/bit.out
+++ b/src/test/regress/expected/bit.out
@@ -740,6 +740,30 @@ SELECT bit_count(B'1111111111'::bit(10));
         10
 (1 row)
 
+SELECT bit_count(repeat('0', 100)::bit(100));
+ bit_count 
+-----------
+         0
+(1 row)
+
+SELECT bit_count(repeat('1', 100)::bit(100));
+ bit_count 
+-----------
+       100
+(1 row)
+
+SELECT bit_count(repeat('01', 500)::bit(1000));
+ bit_count 
+-----------
+       500
+(1 row)
+
+SELECT bit_count(repeat('10101', 200)::bit(1000));
+ bit_count 
+-----------
+       600
+(1 row)
+
 -- This table is intentionally left around to exercise pg_dump/pg_upgrade
 CREATE TABLE bit_defaults(
   b1 bit(4) DEFAULT '1001',
diff --git a/src/test/regress/sql/bit.sql b/src/test/regress/sql/bit.sql
index 34230b99fb..8ba6facd03 100644
--- a/src/test/regress/sql/bit.sql
+++ b/src/test/regress/sql/bit.sql
@@ -223,6 +223,10 @@ SELECT overlay(B'0101011100' placing '001' from 20);
 -- bit_count
 SELECT bit_count(B'0101011100'::bit(10));
 SELECT bit_count(B'1111111111'::bit(10));
+SELECT bit_count(repeat('0', 100)::bit(100));
+SELECT bit_count(repeat('1', 100)::bit(100));
+SELECT bit_count(repeat('01', 500)::bit(1000));
+SELECT bit_count(repeat('10101', 200)::bit(1000));
 
 -- This table is intentionally left around to exercise pg_dump/pg_upgrade
 CREATE TABLE bit_defaults(
-- 
2.25.1


--CE+1k2dSO48ffgeK
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v20-0002-optimize-visibilitymap_count-with-AVX512.patch"



^ permalink  raw  reply  [nested|flat] 16+ messages in thread

* [PATCH v13 1/1] AVX512 popcount support
@ 2024-03-27 21:39 Nathan Bossart <[email protected]>
  0 siblings, 0 replies; 16+ messages in thread

From: Nathan Bossart @ 2024-03-27 21:39 UTC (permalink / raw)

---
 src/include/port/pg_bitutils.h | 16 +++++++
 src/port/Makefile              |  1 +
 src/port/meson.build           |  1 +
 src/port/pg_bitutils.c         | 53 ++++++++------------
 src/port/pg_popcount_avx512.c  | 88 ++++++++++++++++++++++++++++++++++
 5 files changed, 125 insertions(+), 34 deletions(-)
 create mode 100644 src/port/pg_popcount_avx512.c

diff --git a/src/include/port/pg_bitutils.h b/src/include/port/pg_bitutils.h
index 53e5239717..4b1e4d92b4 100644
--- a/src/include/port/pg_bitutils.h
+++ b/src/include/port/pg_bitutils.h
@@ -298,6 +298,22 @@ pg_ceil_log2_64(uint64 num)
 #endif
 #endif
 
+/*
+ * We can also try to use the AVX512 popcount instruction on some systems.
+ * The implementation of that is located in its own file because it may
+ * require special compiler flags that we don't want to apply to any other
+ * files.
+ */
+#if defined(TRY_POPCNT_FAST) && \
+	defined(HAVE__IMMINTRIN) && \
+	defined(HAVE__AVX512_POPCNT)
+#if defined(HAVE__GET_CPUID_COUNT) || defined(HAVE__CPUIDEX)
+#define TRY_POPCNT_AVX512 1
+extern bool pg_popcount_avx512_available(void);
+extern uint64 pg_popcount_avx512(const char *buf, int bytes);
+#endif
+#endif
+
 #ifdef TRY_POPCNT_FAST
 /* Attempt to use the POPCNT instruction, but perform a runtime check first */
 extern PGDLLIMPORT int (*pg_popcount32) (uint32 word);
diff --git a/src/port/Makefile b/src/port/Makefile
index dcc8737e68..eb1e56fe41 100644
--- a/src/port/Makefile
+++ b/src/port/Makefile
@@ -44,6 +44,7 @@ OBJS = \
 	noblock.o \
 	path.o \
 	pg_bitutils.o \
+	pg_popcount_avx512.o \
 	pg_strong_random.o \
 	pgcheckdir.o \
 	pgmkdirp.o \
diff --git a/src/port/meson.build b/src/port/meson.build
index 92b593e6ef..c77bbd3168 100644
--- a/src/port/meson.build
+++ b/src/port/meson.build
@@ -7,6 +7,7 @@ pgport_sources = [
   'noblock.c',
   'path.c',
   'pg_bitutils.c',
+  'pg_popcount_avx512.c',
   'pg_strong_random.c',
   'pgcheckdir.c',
   'pgmkdirp.c',
diff --git a/src/port/pg_bitutils.c b/src/port/pg_bitutils.c
index 1197696e97..2f9a6690e0 100644
--- a/src/port/pg_bitutils.c
+++ b/src/port/pg_bitutils.c
@@ -142,20 +142,18 @@ pg_popcount_available(void)
 	return (exx[2] & (1 << 23)) != 0;	/* POPCNT */
 }
 
-/*
- * These functions get called on the first call to pg_popcount32 etc.
- * They detect whether we can use the asm implementations, and replace
- * the function pointers so that subsequent calls are routed directly to
- * the chosen implementation.
- */
-static int
-pg_popcount32_choose(uint32 word)
+static inline void
+choose_popcount_functions(void)
 {
 	if (pg_popcount_available())
 	{
 		pg_popcount32 = pg_popcount32_fast;
 		pg_popcount64 = pg_popcount64_fast;
 		pg_popcount = pg_popcount_fast;
+#ifdef TRY_POPCNT_AVX512
+		if (pg_popcount_avx512_available())
+			pg_popcount = pg_popcount_avx512;
+#endif
 	}
 	else
 	{
@@ -163,45 +161,32 @@ pg_popcount32_choose(uint32 word)
 		pg_popcount64 = pg_popcount64_slow;
 		pg_popcount = pg_popcount_slow;
 	}
+}
 
+/*
+ * These functions get called on the first call to pg_popcount32 etc.
+ * They detect whether we can use the asm implementations, and replace
+ * the function pointers so that subsequent calls are routed directly to
+ * the chosen implementation.
+ */
+static int
+pg_popcount32_choose(uint32 word)
+{
+	choose_popcount_functions();
 	return pg_popcount32(word);
 }
 
 static int
 pg_popcount64_choose(uint64 word)
 {
-	if (pg_popcount_available())
-	{
-		pg_popcount32 = pg_popcount32_fast;
-		pg_popcount64 = pg_popcount64_fast;
-		pg_popcount = pg_popcount_fast;
-	}
-	else
-	{
-		pg_popcount32 = pg_popcount32_slow;
-		pg_popcount64 = pg_popcount64_slow;
-		pg_popcount = pg_popcount_slow;
-	}
-
+	choose_popcount_functions();
 	return pg_popcount64(word);
 }
 
 static uint64
 pg_popcount_choose(const char *buf, int bytes)
 {
-	if (pg_popcount_available())
-	{
-		pg_popcount32 = pg_popcount32_fast;
-		pg_popcount64 = pg_popcount64_fast;
-		pg_popcount = pg_popcount_fast;
-	}
-	else
-	{
-		pg_popcount32 = pg_popcount32_slow;
-		pg_popcount64 = pg_popcount64_slow;
-		pg_popcount = pg_popcount_slow;
-	}
-
+	choose_popcount_functions();
 	return pg_popcount(buf, bytes);
 }
 
diff --git a/src/port/pg_popcount_avx512.c b/src/port/pg_popcount_avx512.c
new file mode 100644
index 0000000000..7c595a4b33
--- /dev/null
+++ b/src/port/pg_popcount_avx512.c
@@ -0,0 +1,88 @@
+/*-------------------------------------------------------------------------
+ *
+ * pg_popcount_avx512.c
+ *	  Holds the pg_popcount() implementation that uses AVX512 instructions.
+ *
+ * Copyright (c) 2019-2024, PostgreSQL Global Development Group
+ *
+ * IDENTIFICATION
+ *	  src/port/pg_popcount_avx512.c
+ *
+ *-------------------------------------------------------------------------
+ */
+#include "c.h"
+
+#include "port/pg_bitutils.h"
+
+/*
+ * XXX: Someday we should figure out how to determine whether this file needs
+ * to comiled at configure-time instead of relying on macros that are
+ * determined at compile-time.
+ */
+#ifdef TRY_POPCOUNT_AVX512
+
+/*
+ * Return true if CPUID indicates that the AVX512 POPCNT instruction is
+ * available.
+ */
+bool
+pg_popcount_avx512_available(void)
+{
+	unsigned int exx[4] = {0, 0, 0, 0};
+
+#if defined(HAVE__GET_CPUID_COUNT)
+	__get_cpuid_count(7, 0, &exx[0], &exx[1], &exx[2], &exx[3]);
+#elif defined(HAVE__CPUIDEX)
+	__cpuidex(exx, 7, 0);
+#else
+#error cpuid instruction not available
+#endif
+
+	if ((exx[1] & (1 << 16)) != 0 &&
+		(exx[2] & (1 << 14)) != 0)
+	{
+		/*
+		 * We also need to check that the OS has enabled support for the ZMM
+		 * registers.
+		 */
+#ifdef _MSC_VER
+		return (_xgetbv(0) & 0xe0) != 0;
+#else
+		uint64		xcr = 0;
+		uint32		high;
+		uint32		low;
+
+__asm__ __volatile__(" xgetbv\n":"=a"(low), "=d"(high):"c"(xcr));
+		return (low & 0xe0) != 0;
+#endif
+	}
+
+	return false;
+}
+
+/*
+ * pg_popcount_avx512
+ *		Returns the number of 1-bits in buf
+ */
+uint64
+pg_popcount_avx512(const char *buf, int bytes)
+{
+	uint64		popcnt;
+	__m512i		accum = _mm512_setzero_si512();
+
+	for (; bytes >= sizeof(__m512i); bytes -= sizeof(__m512i))
+	{
+		const		__m512i val = _mm512_loadu_si512((const __m512i *) buf);
+		const		__m512i cnt = _mm512_popcnt_epi64(val);
+
+		accum = _mm512_add_epi64(accum, cnt);
+
+		buf += sizeof(__m512i);
+	}
+
+	popcnt = _mm512_reduce_add_epi64(accum);
+
+	return popcnt + pg_popcount_fast(buf, bytes);
+}
+
+#endif							/* TRY_POPCOUNT_AVX512 */
-- 
2.25.1


--AhhlLboLdkugWU4S--





^ permalink  raw  reply  [nested|flat] 16+ messages in thread

* [PATCH v17 1/1] AVX512 popcount support
@ 2024-03-27 21:39 Nathan Bossart <[email protected]>
  0 siblings, 0 replies; 16+ messages in thread

From: Nathan Bossart @ 2024-03-27 21:39 UTC (permalink / raw)

---
 config/c-compiler.m4                 |  58 ++++++
 configure                            | 252 +++++++++++++++++++++++++++
 configure.ac                         |  51 ++++++
 meson.build                          |  87 +++++++++
 src/Makefile.global.in               |   5 +
 src/include/pg_config.h.in           |  12 ++
 src/include/port/pg_bitutils.h       |  15 ++
 src/makefiles/meson.build            |   4 +-
 src/port/Makefile                    |  11 ++
 src/port/meson.build                 |   6 +-
 src/port/pg_bitutils.c               |  56 +++---
 src/port/pg_popcount_avx512.c        |  49 ++++++
 src/port/pg_popcount_avx512_choose.c |  71 ++++++++
 13 files changed, 638 insertions(+), 39 deletions(-)
 create mode 100644 src/port/pg_popcount_avx512.c
 create mode 100644 src/port/pg_popcount_avx512_choose.c

diff --git a/config/c-compiler.m4 b/config/c-compiler.m4
index 3268a780bb..5fb60775ca 100644
--- a/config/c-compiler.m4
+++ b/config/c-compiler.m4
@@ -694,3 +694,61 @@ if test x"$Ac_cachevar" = x"yes"; then
 fi
 undefine([Ac_cachevar])dnl
 ])# PGAC_LOONGARCH_CRC32C_INTRINSICS
+
+# PGAC_XSAVE_INTRINSICS
+# ---------------------
+# Check if the compiler supports the XSAVE instructions using the _xgetbv
+# intrinsic function.
+#
+# An optional compiler flag can be passed as argument (e.g., -mxsave).  If the
+# intrinsic is supported, sets pgac_xsave_intrinsics and CFLAGS_XSAVE.
+AC_DEFUN([PGAC_XSAVE_INTRINSICS],
+[define([Ac_cachevar], [AS_TR_SH([pgac_cv_xsave_intrinsics_$1])])dnl
+AC_CACHE_CHECK([for _xgetbv with CFLAGS=$1], [Ac_cachevar],
+[pgac_save_CFLAGS=$CFLAGS
+CFLAGS="$pgac_save_CFLAGS $1"
+AC_LINK_IFELSE([AC_LANG_PROGRAM([#include <immintrin.h>],
+  [return _xgetbv(0) & 0xe0;])],
+  [Ac_cachevar=yes],
+  [Ac_cachevar=no])
+CFLAGS="$pgac_save_CFLAGS"])
+if test x"$Ac_cachevar" = x"yes"; then
+  CFLAGS_XSAVE="$1"
+  pgac_xsave_intrinsics=yes
+fi
+undefine([Ac_cachevar])dnl
+])# PGAC_XSAVE_INTRINSICS
+
+# PGAC_AVX512_POPCNT_INTRINSICS
+# -----------------------------
+# Check if the compiler supports the AVX512 POPCNT instructions using the
+# _mm512_setzero_si512, _mm512_loadu_si512, _mm512_popcnt_epi64,
+# _mm512_add_epi64, and _mm512_reduce_add_epi64 intrinsic functions.
+#
+# An optional compiler flag can be passed as argument
+# (e.g., -mavx512vpopcntdq).  If the intrinsics are supported, sets
+# pgac_avx512_popcnt_intrinsics and CFLAGS_POPCNT.
+AC_DEFUN([PGAC_AVX512_POPCNT_INTRINSICS],
+[define([Ac_cachevar], [AS_TR_SH([pgac_cv_avx512_popcnt_intrinsics_$1])])dnl
+AC_CACHE_CHECK([for _mm512_popcnt_epi64 with CFLAGS=$1], [Ac_cachevar],
+[pgac_save_CFLAGS=$CFLAGS
+CFLAGS="$pgac_save_CFLAGS $1"
+AC_LINK_IFELSE([AC_LANG_PROGRAM([#include <immintrin.h>],
+  [const char buf@<:@sizeof(__m512i)@:>@;
+   PG_INT64_TYPE popcnt = 0;
+   __m512i accum = _mm512_setzero_si512();
+   const __m512i val = _mm512_loadu_si512((const __m512i *) buf);
+   const __m512i cnt = _mm512_popcnt_epi64(val);
+   accum = _mm512_add_epi64(accum, cnt);
+   popcnt = _mm512_reduce_add_epi64(accum);
+   /* return computed value, to prevent the above being optimized away */
+   return popcnt == 0;])],
+  [Ac_cachevar=yes],
+  [Ac_cachevar=no])
+CFLAGS="$pgac_save_CFLAGS"])
+if test x"$Ac_cachevar" = x"yes"; then
+  CFLAGS_POPCNT="$1"
+  pgac_avx512_popcnt_intrinsics=yes
+fi
+undefine([Ac_cachevar])dnl
+])# PGAC_AVX512_POPCNT_INTRINSICS
diff --git a/configure b/configure
index 36feeafbb2..b48ed7f271 100755
--- a/configure
+++ b/configure
@@ -647,6 +647,9 @@ MSGFMT_FLAGS
 MSGFMT
 PG_CRC32C_OBJS
 CFLAGS_CRC
+PG_POPCNT_OBJS
+CFLAGS_POPCNT
+CFLAGS_XSAVE
 LIBOBJS
 OPENSSL
 ZSTD
@@ -17404,6 +17407,40 @@ $as_echo "#define HAVE__GET_CPUID 1" >>confdefs.h
 
 fi
 
+{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for __get_cpuid_count" >&5
+$as_echo_n "checking for __get_cpuid_count... " >&6; }
+if ${pgac_cv__get_cpuid_count+:} 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_count(7, 0, &exx[0], &exx[1], &exx[2], &exx[3]);
+
+  ;
+  return 0;
+}
+_ACEOF
+if ac_fn_c_try_link "$LINENO"; then :
+  pgac_cv__get_cpuid_count="yes"
+else
+  pgac_cv__get_cpuid_count="no"
+fi
+rm -f core conftest.err conftest.$ac_objext \
+    conftest$ac_exeext conftest.$ac_ext
+fi
+{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $pgac_cv__get_cpuid_count" >&5
+$as_echo "$pgac_cv__get_cpuid_count" >&6; }
+if test x"$pgac_cv__get_cpuid_count" = x"yes"; then
+
+$as_echo "#define HAVE__GET_CPUID_COUNT 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 :
@@ -17438,6 +17475,221 @@ $as_echo "#define HAVE__CPUID 1" >>confdefs.h
 
 fi
 
+{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for __cpuidex" >&5
+$as_echo_n "checking for __cpuidex... " >&6; }
+if ${pgac_cv__cpuidex+:} 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_cpuidex(exx[0], 7, 0);
+
+  ;
+  return 0;
+}
+_ACEOF
+if ac_fn_c_try_link "$LINENO"; then :
+  pgac_cv__cpuidex="yes"
+else
+  pgac_cv__cpuidex="no"
+fi
+rm -f core conftest.err conftest.$ac_objext \
+    conftest$ac_exeext conftest.$ac_ext
+fi
+{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $pgac_cv__cpuidex" >&5
+$as_echo "$pgac_cv__cpuidex" >&6; }
+if test x"$pgac_cv__cpuidex" = x"yes"; then
+
+$as_echo "#define HAVE__CPUIDEX 1" >>confdefs.h
+
+fi
+
+# Check for XSAVE intrinsics
+#
+CFLAGS_XSAVE=""
+{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for _xgetbv with CFLAGS=" >&5
+$as_echo_n "checking for _xgetbv with CFLAGS=... " >&6; }
+if ${pgac_cv_xsave_intrinsics_+:} false; then :
+  $as_echo_n "(cached) " >&6
+else
+  pgac_save_CFLAGS=$CFLAGS
+CFLAGS="$pgac_save_CFLAGS "
+cat confdefs.h - <<_ACEOF >conftest.$ac_ext
+/* end confdefs.h.  */
+#include <immintrin.h>
+int
+main ()
+{
+return _xgetbv(0) & 0xe0;
+  ;
+  return 0;
+}
+_ACEOF
+if ac_fn_c_try_link "$LINENO"; then :
+  pgac_cv_xsave_intrinsics_=yes
+else
+  pgac_cv_xsave_intrinsics_=no
+fi
+rm -f core conftest.err conftest.$ac_objext \
+    conftest$ac_exeext conftest.$ac_ext
+CFLAGS="$pgac_save_CFLAGS"
+fi
+{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $pgac_cv_xsave_intrinsics_" >&5
+$as_echo "$pgac_cv_xsave_intrinsics_" >&6; }
+if test x"$pgac_cv_xsave_intrinsics_" = x"yes"; then
+  CFLAGS_XSAVE=""
+  pgac_xsave_intrinsics=yes
+fi
+
+if test x"$pgac_xsave_intrinsics" != x"yes"; then
+  { $as_echo "$as_me:${as_lineno-$LINENO}: checking for _xgetbv with CFLAGS=-mxsave" >&5
+$as_echo_n "checking for _xgetbv with CFLAGS=-mxsave... " >&6; }
+if ${pgac_cv_xsave_intrinsics__mxsave+:} false; then :
+  $as_echo_n "(cached) " >&6
+else
+  pgac_save_CFLAGS=$CFLAGS
+CFLAGS="$pgac_save_CFLAGS -mxsave"
+cat confdefs.h - <<_ACEOF >conftest.$ac_ext
+/* end confdefs.h.  */
+#include <immintrin.h>
+int
+main ()
+{
+return _xgetbv(0) & 0xe0;
+  ;
+  return 0;
+}
+_ACEOF
+if ac_fn_c_try_link "$LINENO"; then :
+  pgac_cv_xsave_intrinsics__mxsave=yes
+else
+  pgac_cv_xsave_intrinsics__mxsave=no
+fi
+rm -f core conftest.err conftest.$ac_objext \
+    conftest$ac_exeext conftest.$ac_ext
+CFLAGS="$pgac_save_CFLAGS"
+fi
+{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $pgac_cv_xsave_intrinsics__mxsave" >&5
+$as_echo "$pgac_cv_xsave_intrinsics__mxsave" >&6; }
+if test x"$pgac_cv_xsave_intrinsics__mxsave" = x"yes"; then
+  CFLAGS_XSAVE="-mxsave"
+  pgac_xsave_intrinsics=yes
+fi
+
+fi
+if test x"$pgac_xsave_intrinsics" = x"yes"; then
+
+$as_echo "#define HAVE_XSAVE_INTRINSICS 1" >>confdefs.h
+
+fi
+
+
+# Check for AVX512 popcount intrinsics
+#
+CFLAGS_POPCNT=""
+PG_POPCNT_OBJS=""
+if test x"$host_cpu" = x"x86_64"; then
+  { $as_echo "$as_me:${as_lineno-$LINENO}: checking for _mm512_popcnt_epi64 with CFLAGS=" >&5
+$as_echo_n "checking for _mm512_popcnt_epi64 with CFLAGS=... " >&6; }
+if ${pgac_cv_avx512_popcnt_intrinsics_+:} false; then :
+  $as_echo_n "(cached) " >&6
+else
+  pgac_save_CFLAGS=$CFLAGS
+CFLAGS="$pgac_save_CFLAGS "
+cat confdefs.h - <<_ACEOF >conftest.$ac_ext
+/* end confdefs.h.  */
+#include <immintrin.h>
+int
+main ()
+{
+const char buf[sizeof(__m512i)];
+   PG_INT64_TYPE popcnt = 0;
+   __m512i accum = _mm512_setzero_si512();
+   const __m512i val = _mm512_loadu_si512((const __m512i *) buf);
+   const __m512i cnt = _mm512_popcnt_epi64(val);
+   accum = _mm512_add_epi64(accum, cnt);
+   popcnt = _mm512_reduce_add_epi64(accum);
+   /* return computed value, to prevent the above being optimized away */
+   return popcnt == 0;
+  ;
+  return 0;
+}
+_ACEOF
+if ac_fn_c_try_link "$LINENO"; then :
+  pgac_cv_avx512_popcnt_intrinsics_=yes
+else
+  pgac_cv_avx512_popcnt_intrinsics_=no
+fi
+rm -f core conftest.err conftest.$ac_objext \
+    conftest$ac_exeext conftest.$ac_ext
+CFLAGS="$pgac_save_CFLAGS"
+fi
+{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $pgac_cv_avx512_popcnt_intrinsics_" >&5
+$as_echo "$pgac_cv_avx512_popcnt_intrinsics_" >&6; }
+if test x"$pgac_cv_avx512_popcnt_intrinsics_" = x"yes"; then
+  CFLAGS_POPCNT=""
+  pgac_avx512_popcnt_intrinsics=yes
+fi
+
+  if test x"$pgac_avx512_popcnt_intrinsics" != x"yes"; then
+    { $as_echo "$as_me:${as_lineno-$LINENO}: checking for _mm512_popcnt_epi64 with CFLAGS=-mavx512vpopcntdq" >&5
+$as_echo_n "checking for _mm512_popcnt_epi64 with CFLAGS=-mavx512vpopcntdq... " >&6; }
+if ${pgac_cv_avx512_popcnt_intrinsics__mavx512vpopcntdq+:} false; then :
+  $as_echo_n "(cached) " >&6
+else
+  pgac_save_CFLAGS=$CFLAGS
+CFLAGS="$pgac_save_CFLAGS -mavx512vpopcntdq"
+cat confdefs.h - <<_ACEOF >conftest.$ac_ext
+/* end confdefs.h.  */
+#include <immintrin.h>
+int
+main ()
+{
+const char buf[sizeof(__m512i)];
+   PG_INT64_TYPE popcnt = 0;
+   __m512i accum = _mm512_setzero_si512();
+   const __m512i val = _mm512_loadu_si512((const __m512i *) buf);
+   const __m512i cnt = _mm512_popcnt_epi64(val);
+   accum = _mm512_add_epi64(accum, cnt);
+   popcnt = _mm512_reduce_add_epi64(accum);
+   /* return computed value, to prevent the above being optimized away */
+   return popcnt == 0;
+  ;
+  return 0;
+}
+_ACEOF
+if ac_fn_c_try_link "$LINENO"; then :
+  pgac_cv_avx512_popcnt_intrinsics__mavx512vpopcntdq=yes
+else
+  pgac_cv_avx512_popcnt_intrinsics__mavx512vpopcntdq=no
+fi
+rm -f core conftest.err conftest.$ac_objext \
+    conftest$ac_exeext conftest.$ac_ext
+CFLAGS="$pgac_save_CFLAGS"
+fi
+{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $pgac_cv_avx512_popcnt_intrinsics__mavx512vpopcntdq" >&5
+$as_echo "$pgac_cv_avx512_popcnt_intrinsics__mavx512vpopcntdq" >&6; }
+if test x"$pgac_cv_avx512_popcnt_intrinsics__mavx512vpopcntdq" = x"yes"; then
+  CFLAGS_POPCNT="-mavx512vpopcntdq"
+  pgac_avx512_popcnt_intrinsics=yes
+fi
+
+  fi
+  if test x"$pgac_avx512_popcnt_intrinsics" = x"yes"; then
+    PG_POPCNT_OBJS="pg_popcount_avx512.o pg_popcount_avx512_choose.o"
+
+$as_echo "#define USE_AVX512_POPCNT_WITH_RUNTIME_CHECK 1" >>confdefs.h
+
+  fi
+fi
+
+
+
 # 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
diff --git a/configure.ac b/configure.ac
index 57f734879e..2bbd81dfb8 100644
--- a/configure.ac
+++ b/configure.ac
@@ -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"$pgac_xsave_intrinsics" = x"yes"; then
+  AC_DEFINE(HAVE_XSAVE_INTRINSICS, 1, [Define to 1 if you have XSAVE intrinsics.])
+fi
+AC_SUBST(CFLAGS_XSAVE)
+
+# Check for AVX512 popcount intrinsics
+#
+CFLAGS_POPCNT=""
+PG_POPCNT_OBJS=""
+if test x"$host_cpu" = x"x86_64"; then
+  PGAC_AVX512_POPCNT_INTRINSICS([])
+  if test x"$pgac_avx512_popcnt_intrinsics" != x"yes"; then
+    PGAC_AVX512_POPCNT_INTRINSICS([-mavx512vpopcntdq])
+  fi
+  if test x"$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 AVX512 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
diff --git a/meson.build b/meson.build
index 18b5be842e..96be29c22b 100644
--- a/meson.build
+++ b/meson.build
@@ -1783,6 +1783,30 @@ elif cc.links('''
 endif
 
 
+# Check for __get_cpuid_count() and __cpuidex() in a similar fashion.
+if cc.links('''
+    #include <cpuid.h>
+    int main(int arg, char **argv)
+    {
+        unsigned int exx[4] = {0, 0, 0, 0};
+        __get_cpuid_count(7, 0, &exx[0], &exx[1], &exx[2], &exx[3]);
+    }
+    ''', name: '__get_cpuid_count',
+    args: test_c_args)
+  cdata.set('HAVE__GET_CPUID_COUNT', 1)
+elif cc.links('''
+    #include <intrin.h>
+    int main(int arg, char **argv)
+    {
+        unsigned int exx[4] = {0, 0, 0, 0};
+        __cpuidex(exx, 7, 0);
+    }
+    ''', name: '__cpuidex',
+    args: test_c_args)
+  cdata.set('HAVE__CPUIDEX', 1)
+endif
+
+
 # Defend against clang being used on x86-32 without SSE2 enabled.  As current
 # versions of clang do not understand -fexcess-precision=standard, the use of
 # x87 floating point operations leads to problems like isinf possibly returning
@@ -1996,6 +2020,69 @@ int main(void)
 endif
 
 
+###############################################################
+# Check for the availability of XSAVE intrinsics.
+###############################################################
+
+cflags_xsave = []
+if host_cpu == 'x86' or host_cpu == 'x86_64'
+
+  prog = '''
+#include <immintrin.h>
+
+int main(void)
+{
+    return _xgetbv(0) & 0xe0;
+}
+'''
+
+  if cc.links(prog, name: 'XSAVE intrinsics without -mxsave',
+        args: test_c_args)
+    cdata.set('HAVE_XSAVE_INTRINSICS', 1)
+  elif cc.links(prog, name: 'XSAVE intrinsics with -mxsave',
+        args: test_c_args + ['-mxsave'])
+    cdata.set('HAVE_XSAVE_INTRINSICS', 1)
+    cflags_xsave += '-mxsave'
+  endif
+
+endif
+
+
+###############################################################
+# Check for the availability of AVX512 popcount intrinsics.
+###############################################################
+
+cflags_popcnt = []
+if host_cpu == 'x86_64'
+
+  prog = '''
+#include <immintrin.h>
+
+int main(void)
+{
+    const char buf[sizeof(__m512i)];
+    INT64 popcnt = 0;
+    __m512i accum = _mm512_setzero_si512();
+    const __m512i val = _mm512_loadu_si512((const __m512i *) buf);
+    const __m512i cnt = _mm512_popcnt_epi64(val);
+    accum = _mm512_add_epi64(accum, cnt);
+    popcnt = _mm512_reduce_add_epi64(accum);
+    /* return computed value, to prevent the above being optimized away */
+    return popcnt == 0;
+}
+'''
+
+  if cc.links(prog, name: 'AVX512 popcount without -mavx512vpopcntdq',
+        args: test_c_args + ['-DINT64=@0@'.format(cdata.get('PG_INT64_TYPE'))])
+    cdata.set('USE_AVX512_POPCNT_WITH_RUNTIME_CHECK', 1)
+  elif cc.links(prog, name: 'AVX512 popcount with -mavx512vpopcntdq',
+        args: test_c_args + ['-DINT64=@0@'.format(cdata.get('PG_INT64_TYPE'))] + ['-mavx512vpopcntdq'])
+    cdata.set('USE_AVX512_POPCNT_WITH_RUNTIME_CHECK', 1)
+    cflags_popcnt += '-mavx512vpopcntdq'
+  endif
+
+endif
+
 
 ###############################################################
 # Select CRC-32C implementation.
diff --git a/src/Makefile.global.in b/src/Makefile.global.in
index 8b3f8c24e0..36d880d225 100644
--- a/src/Makefile.global.in
+++ b/src/Makefile.global.in
@@ -262,7 +262,9 @@ CFLAGS_SL_MODULE = @CFLAGS_SL_MODULE@
 CXXFLAGS_SL_MODULE = @CXXFLAGS_SL_MODULE@
 CFLAGS_UNROLL_LOOPS = @CFLAGS_UNROLL_LOOPS@
 CFLAGS_VECTORIZE = @CFLAGS_VECTORIZE@
+CFLAGS_POPCNT = @CFLAGS_POPCNT@
 CFLAGS_CRC = @CFLAGS_CRC@
+CFLAGS_XSAVE = @CFLAGS_XSAVE@
 PERMIT_DECLARATION_AFTER_STATEMENT = @PERMIT_DECLARATION_AFTER_STATEMENT@
 CXXFLAGS = @CXXFLAGS@
 
@@ -758,6 +760,9 @@ LIBOBJS = @LIBOBJS@
 # files needed for the chosen CRC-32C implementation
 PG_CRC32C_OBJS = @PG_CRC32C_OBJS@
 
+# files needed for the chosen popcount implementation
+PG_POPCNT_OBJS = @PG_POPCNT_OBJS@
+
 LIBS := -lpgcommon -lpgport $(LIBS)
 
 # to make ws2_32.lib the last library
diff --git a/src/include/pg_config.h.in b/src/include/pg_config.h.in
index 591e1ca3df..de067e6182 100644
--- a/src/include/pg_config.h.in
+++ b/src/include/pg_config.h.in
@@ -513,6 +513,9 @@
 /* Define to 1 if the assembler supports X86_64's POPCNTQ instruction. */
 #undef HAVE_X86_64_POPCNTQ
 
+/* Define to 1 if you have XSAVE intrinsics. */
+#undef HAVE_XSAVE_INTRINSICS
+
 /* Define to 1 if the system has the type `_Bool'. */
 #undef HAVE__BOOL
 
@@ -555,9 +558,15 @@
 /* Define to 1 if you have __cpuid. */
 #undef HAVE__CPUID
 
+/* Define to 1 if you have __cpuidex. */
+#undef HAVE__CPUIDEX
+
 /* Define to 1 if you have __get_cpuid. */
 #undef HAVE__GET_CPUID
 
+/* Define to 1 if you have __get_cpuid_count. */
+#undef HAVE__GET_CPUID_COUNT
+
 /* Define to 1 if your compiler understands _Static_assert. */
 #undef HAVE__STATIC_ASSERT
 
@@ -680,6 +689,9 @@
 /* Define to 1 to build with assertion checks. (--enable-cassert) */
 #undef USE_ASSERT_CHECKING
 
+/* Define to 1 to use AVX512 popcount instructions with a runtime check. */
+#undef USE_AVX512_POPCNT_WITH_RUNTIME_CHECK
+
 /* Define to 1 to build with Bonjour support. (--with-bonjour) */
 #undef USE_BONJOUR
 
diff --git a/src/include/port/pg_bitutils.h b/src/include/port/pg_bitutils.h
index 53e5239717..1a92c56bcd 100644
--- a/src/include/port/pg_bitutils.h
+++ b/src/include/port/pg_bitutils.h
@@ -304,6 +304,21 @@ extern PGDLLIMPORT int (*pg_popcount32) (uint32 word);
 extern PGDLLIMPORT int (*pg_popcount64) (uint64 word);
 extern PGDLLIMPORT uint64 (*pg_popcount) (const char *buf, int bytes);
 
+/* Export pg_popcount_fast() for use in the AVX512 implementation. */
+extern uint64 pg_popcount_fast(const char *buf, int bytes);
+
+/*
+ * We can also try to use the AVX512 popcount instruction on some systems.
+ * The implementation of that is located in its own file because it may
+ * require special compiler flags that we don't want to apply to any other
+ * files.  Note that we only build this when TRY_POPCNT_FAST is set so that we
+ * can fall back to pg_popcount_fast() as needed.
+ */
+#ifdef USE_AVX512_POPCNT_WITH_RUNTIME_CHECK
+extern bool pg_popcount_avx512_available(void);
+extern uint64 pg_popcount_avx512(const char *buf, int bytes);
+#endif
+
 #else
 /* Use a portable implementation -- no need for a function pointer. */
 extern int	pg_popcount32(uint32 word);
diff --git a/src/makefiles/meson.build b/src/makefiles/meson.build
index b0f4178b3d..5618050b30 100644
--- a/src/makefiles/meson.build
+++ b/src/makefiles/meson.build
@@ -100,8 +100,10 @@ pgxs_kv = {
     ' '.join(cflags_no_decl_after_statement),
 
   'CFLAGS_CRC': ' '.join(cflags_crc),
+  'CFLAGS_POPCNT': ' '.join(cflags_popcnt),
   'CFLAGS_UNROLL_LOOPS': ' '.join(unroll_loops_cflags),
   'CFLAGS_VECTORIZE': ' '.join(vectorize_cflags),
+  'CFLAGS_XSAVE': ' '.join(cflags_xsave),
 
   'LDFLAGS': var_ldflags,
   'LDFLAGS_EX': var_ldflags_ex,
@@ -177,7 +179,7 @@ pgxs_empty = [
   'WANTED_LANGUAGES',
 
   # Not needed because we don't build the server / PLs with the generated makefile
-  'LIBOBJS', 'PG_CRC32C_OBJS', 'TAS',
+  'LIBOBJS', 'PG_CRC32C_OBJS', 'PG_POPCNT_OBJS', 'TAS',
   'DTRACEFLAGS', # only server has dtrace probes
 
   'perl_archlibexp', 'perl_embed_ccflags', 'perl_embed_ldflags', 'perl_includespec', 'perl_privlibexp',
diff --git a/src/port/Makefile b/src/port/Makefile
index dcc8737e68..db7c02117b 100644
--- a/src/port/Makefile
+++ b/src/port/Makefile
@@ -38,6 +38,7 @@ LIBS += $(PTHREAD_LIBS)
 OBJS = \
 	$(LIBOBJS) \
 	$(PG_CRC32C_OBJS) \
+	$(PG_POPCNT_OBJS) \
 	bsearch_arg.o \
 	chklocale.o \
 	inet_net_ntop.o \
@@ -92,6 +93,16 @@ pg_crc32c_armv8.o: CFLAGS+=$(CFLAGS_CRC)
 pg_crc32c_armv8_shlib.o: CFLAGS+=$(CFLAGS_CRC)
 pg_crc32c_armv8_srv.o: CFLAGS+=$(CFLAGS_CRC)
 
+# all versions of pg_popcount_avx512_choose.o need CFLAGS_XSAVE
+pg_popcount_avx512_choose.o: CFLAGS+=$(CFLAGS_XSAVE)
+pg_popcount_avx512_choose_shlib.o: CFLAGS+=$(CFLAGS_XSAVE)
+pg_popcount_avx512_choose_srv.o: CFLAGS+=$(CFLAGS_XSAVE)
+
+# all versions of pg_popcount_avx512.o need CFLAGS_POPCNT
+pg_popcount_avx512.o: CFLAGS+=$(CFLAGS_POPCNT)
+pg_popcount_avx512_shlib.o: CFLAGS+=$(CFLAGS_POPCNT)
+pg_popcount_avx512_srv.o: CFLAGS+=$(CFLAGS_POPCNT)
+
 #
 # Shared library versions of object files
 #
diff --git a/src/port/meson.build b/src/port/meson.build
index 92b593e6ef..fd9ee199d1 100644
--- a/src/port/meson.build
+++ b/src/port/meson.build
@@ -84,6 +84,8 @@ replace_funcs_pos = [
   ['pg_crc32c_sse42', 'USE_SSE42_CRC32C_WITH_RUNTIME_CHECK', 'crc'],
   ['pg_crc32c_sse42_choose', 'USE_SSE42_CRC32C_WITH_RUNTIME_CHECK'],
   ['pg_crc32c_sb8', 'USE_SSE42_CRC32C_WITH_RUNTIME_CHECK'],
+  ['pg_popcount_avx512', 'USE_AVX512_POPCNT_WITH_RUNTIME_CHECK', 'popcnt'],
+  ['pg_popcount_avx512_choose', 'USE_AVX512_POPCNT_WITH_RUNTIME_CHECK', 'xsave'],
 
   # arm / aarch64
   ['pg_crc32c_armv8', 'USE_ARMV8_CRC32C'],
@@ -98,8 +100,8 @@ replace_funcs_pos = [
   ['pg_crc32c_sb8', 'USE_SLICING_BY_8_CRC32C'],
 ]
 
-pgport_cflags = {'crc': cflags_crc}
-pgport_sources_cflags = {'crc': []}
+pgport_cflags = {'crc': cflags_crc, 'popcnt': cflags_popcnt, 'xsave': cflags_xsave}
+pgport_sources_cflags = {'crc': [], 'popcnt': [], 'xsave': []}
 
 foreach f : replace_funcs_neg
   func = f.get(0)
diff --git a/src/port/pg_bitutils.c b/src/port/pg_bitutils.c
index 1197696e97..c08d3c056f 100644
--- a/src/port/pg_bitutils.c
+++ b/src/port/pg_bitutils.c
@@ -114,7 +114,6 @@ static int	pg_popcount64_choose(uint64 word);
 static uint64 pg_popcount_choose(const char *buf, int bytes);
 static inline int pg_popcount32_fast(uint32 word);
 static inline int pg_popcount64_fast(uint64 word);
-static uint64 pg_popcount_fast(const char *buf, int bytes);
 
 int			(*pg_popcount32) (uint32 word) = pg_popcount32_choose;
 int			(*pg_popcount64) (uint64 word) = pg_popcount64_choose;
@@ -142,20 +141,18 @@ pg_popcount_available(void)
 	return (exx[2] & (1 << 23)) != 0;	/* POPCNT */
 }
 
-/*
- * These functions get called on the first call to pg_popcount32 etc.
- * They detect whether we can use the asm implementations, and replace
- * the function pointers so that subsequent calls are routed directly to
- * the chosen implementation.
- */
-static int
-pg_popcount32_choose(uint32 word)
+static inline void
+choose_popcount_functions(void)
 {
 	if (pg_popcount_available())
 	{
 		pg_popcount32 = pg_popcount32_fast;
 		pg_popcount64 = pg_popcount64_fast;
 		pg_popcount = pg_popcount_fast;
+#ifdef USE_AVX512_POPCNT_WITH_RUNTIME_CHECK
+		if (pg_popcount_avx512_available())
+			pg_popcount = pg_popcount_avx512;
+#endif
 	}
 	else
 	{
@@ -163,45 +160,32 @@ pg_popcount32_choose(uint32 word)
 		pg_popcount64 = pg_popcount64_slow;
 		pg_popcount = pg_popcount_slow;
 	}
+}
 
+/*
+ * These functions get called on the first call to pg_popcount32 etc.
+ * They detect whether we can use the asm implementations, and replace
+ * the function pointers so that subsequent calls are routed directly to
+ * the chosen implementation.
+ */
+static int
+pg_popcount32_choose(uint32 word)
+{
+	choose_popcount_functions();
 	return pg_popcount32(word);
 }
 
 static int
 pg_popcount64_choose(uint64 word)
 {
-	if (pg_popcount_available())
-	{
-		pg_popcount32 = pg_popcount32_fast;
-		pg_popcount64 = pg_popcount64_fast;
-		pg_popcount = pg_popcount_fast;
-	}
-	else
-	{
-		pg_popcount32 = pg_popcount32_slow;
-		pg_popcount64 = pg_popcount64_slow;
-		pg_popcount = pg_popcount_slow;
-	}
-
+	choose_popcount_functions();
 	return pg_popcount64(word);
 }
 
 static uint64
 pg_popcount_choose(const char *buf, int bytes)
 {
-	if (pg_popcount_available())
-	{
-		pg_popcount32 = pg_popcount32_fast;
-		pg_popcount64 = pg_popcount64_fast;
-		pg_popcount = pg_popcount_fast;
-	}
-	else
-	{
-		pg_popcount32 = pg_popcount32_slow;
-		pg_popcount64 = pg_popcount64_slow;
-		pg_popcount = pg_popcount_slow;
-	}
-
+	choose_popcount_functions();
 	return pg_popcount(buf, bytes);
 }
 
@@ -243,7 +227,7 @@ __asm__ __volatile__(" popcntq %1,%0\n":"=q"(res):"rm"(word):"cc");
  * pg_popcount_fast
  *		Returns the number of 1-bits in buf
  */
-static uint64
+uint64
 pg_popcount_fast(const char *buf, int bytes)
 {
 	uint64		popcnt = 0;
diff --git a/src/port/pg_popcount_avx512.c b/src/port/pg_popcount_avx512.c
new file mode 100644
index 0000000000..f86558d1ee
--- /dev/null
+++ b/src/port/pg_popcount_avx512.c
@@ -0,0 +1,49 @@
+/*-------------------------------------------------------------------------
+ *
+ * pg_popcount_avx512.c
+ *	  Holds the pg_popcount() implementation that uses AVX512 instructions.
+ *
+ * Copyright (c) 2024, PostgreSQL Global Development Group
+ *
+ * IDENTIFICATION
+ *	  src/port/pg_popcount_avx512.c
+ *
+ *-------------------------------------------------------------------------
+ */
+#include "c.h"
+
+#include <immintrin.h>
+
+#include "port/pg_bitutils.h"
+
+/*
+ * It's probably unlikely that TRY_POPCNT_FAST won't be set if we are able to
+ * use AVX512 intrinsics, but we check it anyway to be sure.  We rely on
+ * pg_popcount_fast() as our fallback implementation in pg_popcount_avx512().
+ */
+#ifdef TRY_POPCNT_FAST
+
+/*
+ * pg_popcount_avx512
+ *		Returns the number of 1-bits in buf
+ */
+uint64
+pg_popcount_avx512(const char *buf, int bytes)
+{
+	uint64		popcnt;
+	__m512i		accum = _mm512_setzero_si512();
+
+	for (; bytes >= sizeof(__m512i); bytes -= sizeof(__m512i))
+	{
+		const		__m512i val = _mm512_loadu_si512((const __m512i *) buf);
+		const		__m512i cnt = _mm512_popcnt_epi64(val);
+
+		accum = _mm512_add_epi64(accum, cnt);
+		buf += sizeof(__m512i);
+	}
+
+	popcnt = _mm512_reduce_add_epi64(accum);
+	return popcnt + pg_popcount_fast(buf, bytes);
+}
+
+#endif							/* TRY_POPCNT_FAST */
diff --git a/src/port/pg_popcount_avx512_choose.c b/src/port/pg_popcount_avx512_choose.c
new file mode 100644
index 0000000000..9e81cd33ad
--- /dev/null
+++ b/src/port/pg_popcount_avx512_choose.c
@@ -0,0 +1,71 @@
+/*-------------------------------------------------------------------------
+ *
+ * pg_popcount_avx512_choose.c
+ *    Test whether we can use AVX512 POPCNT instructions.
+ *
+ * Copyright (c) 2024, PostgreSQL Global Development Group
+ *
+ * IDENTIFICATION
+ *    src/port/pg_popcount_avx512_choose.c
+ *
+ *-------------------------------------------------------------------------
+ */
+#include "c.h"
+
+#if defined(HAVE__GET_CPUID) || defined(HAVE__GET_CPUID_COUNT)
+#include <cpuid.h>
+#endif
+
+#ifdef HAVE_XSAVE_INTRINSICS
+#include <immintrin.h>
+#endif
+
+#if defined(HAVE__CPUID) || defined(HAVE__CPUIDEX)
+#include <intrin.h>
+#endif
+
+#include "port/pg_bitutils.h"
+
+/*
+ * It's probably unlikely that TRY_POPCNT_FAST won't be set if we are able to
+ * use AVX512 intrinsics, but we check it anyway to be sure.  We rely on
+ * pg_popcount_fast() as our fallback implementation in pg_popcount_avx512().
+ */
+#ifdef TRY_POPCNT_FAST
+
+/*
+ * Returns true if the CPU supports AVX512 POPCNT.
+ */
+bool
+pg_popcount_avx512_available(void)
+{
+	unsigned int exx[4] = {0, 0, 0, 0};
+
+	/* does CPUID say there's support for AVX512 POPCNT? */
+#if defined(HAVE__GET_CPUID_COUNT)
+	__get_cpuid_count(7, 0, &exx[0], &exx[1], &exx[2], &exx[3]);
+#elif defined(HAVE__CPUIDEX)
+	__cpuidex(exx, 7, 0);
+#endif
+	if ((exx[2] & (1 << 14)) == 0)	/* avx512vpopcntdq */
+		return false;
+
+	/* does CPUID say there's support for XGETBV? */
+	memset(exx, 0, sizeof(exx));
+#if defined(HAVE__GET_CPUID)
+	__get_cpuid(1, &exx[0], &exx[1], &exx[2], &exx[3]);
+#elif defined(HAVE__CPUID)
+	__cpuid(exx, 1);
+#endif
+	if ((exx[2] & (1 << 26)) == 0)	/* xsave */
+		return false;
+
+	/* does XGETBV say the ZMM registers are enabled? */
+#ifdef HAVE_XSAVE_INTRINSICS
+	return (_xgetbv(0) & 0xe0) != 0;
+#else
+	return false;
+#endif
+}
+
+#endif							/* TRY_POPCNT_FAST */
-- 
2.25.1


--1yeeQ81UyVL57Vl7--





^ permalink  raw  reply  [nested|flat] 16+ messages in thread

* [PATCH v24 1/2] AVX512 popcount support
@ 2024-03-27 21:39 Nathan Bossart <[email protected]>
  0 siblings, 0 replies; 16+ messages in thread

From: Nathan Bossart @ 2024-03-27 21:39 UTC (permalink / raw)

---
 config/c-compiler.m4                 |  58 ++++++
 configure                            | 252 +++++++++++++++++++++++++++
 configure.ac                         |  51 ++++++
 meson.build                          |  87 +++++++++
 src/Makefile.global.in               |   5 +
 src/include/pg_config.h.in           |  12 ++
 src/include/port/pg_bitutils.h       |  15 ++
 src/makefiles/meson.build            |   4 +-
 src/port/Makefile                    |  11 ++
 src/port/meson.build                 |   6 +-
 src/port/pg_bitutils.c               |  29 ++-
 src/port/pg_popcount_avx512.c        |  49 ++++++
 src/port/pg_popcount_avx512_choose.c |  71 ++++++++
 src/test/regress/expected/bit.out    |  24 +++
 src/test/regress/sql/bit.sql         |   4 +
 15 files changed, 673 insertions(+), 5 deletions(-)
 create mode 100644 src/port/pg_popcount_avx512.c
 create mode 100644 src/port/pg_popcount_avx512_choose.c

diff --git a/config/c-compiler.m4 b/config/c-compiler.m4
index 3268a780bb..5fb60775ca 100644
--- a/config/c-compiler.m4
+++ b/config/c-compiler.m4
@@ -694,3 +694,61 @@ if test x"$Ac_cachevar" = x"yes"; then
 fi
 undefine([Ac_cachevar])dnl
 ])# PGAC_LOONGARCH_CRC32C_INTRINSICS
+
+# PGAC_XSAVE_INTRINSICS
+# ---------------------
+# Check if the compiler supports the XSAVE instructions using the _xgetbv
+# intrinsic function.
+#
+# An optional compiler flag can be passed as argument (e.g., -mxsave).  If the
+# intrinsic is supported, sets pgac_xsave_intrinsics and CFLAGS_XSAVE.
+AC_DEFUN([PGAC_XSAVE_INTRINSICS],
+[define([Ac_cachevar], [AS_TR_SH([pgac_cv_xsave_intrinsics_$1])])dnl
+AC_CACHE_CHECK([for _xgetbv with CFLAGS=$1], [Ac_cachevar],
+[pgac_save_CFLAGS=$CFLAGS
+CFLAGS="$pgac_save_CFLAGS $1"
+AC_LINK_IFELSE([AC_LANG_PROGRAM([#include <immintrin.h>],
+  [return _xgetbv(0) & 0xe0;])],
+  [Ac_cachevar=yes],
+  [Ac_cachevar=no])
+CFLAGS="$pgac_save_CFLAGS"])
+if test x"$Ac_cachevar" = x"yes"; then
+  CFLAGS_XSAVE="$1"
+  pgac_xsave_intrinsics=yes
+fi
+undefine([Ac_cachevar])dnl
+])# PGAC_XSAVE_INTRINSICS
+
+# PGAC_AVX512_POPCNT_INTRINSICS
+# -----------------------------
+# Check if the compiler supports the AVX512 POPCNT instructions using the
+# _mm512_setzero_si512, _mm512_loadu_si512, _mm512_popcnt_epi64,
+# _mm512_add_epi64, and _mm512_reduce_add_epi64 intrinsic functions.
+#
+# An optional compiler flag can be passed as argument
+# (e.g., -mavx512vpopcntdq).  If the intrinsics are supported, sets
+# pgac_avx512_popcnt_intrinsics and CFLAGS_POPCNT.
+AC_DEFUN([PGAC_AVX512_POPCNT_INTRINSICS],
+[define([Ac_cachevar], [AS_TR_SH([pgac_cv_avx512_popcnt_intrinsics_$1])])dnl
+AC_CACHE_CHECK([for _mm512_popcnt_epi64 with CFLAGS=$1], [Ac_cachevar],
+[pgac_save_CFLAGS=$CFLAGS
+CFLAGS="$pgac_save_CFLAGS $1"
+AC_LINK_IFELSE([AC_LANG_PROGRAM([#include <immintrin.h>],
+  [const char buf@<:@sizeof(__m512i)@:>@;
+   PG_INT64_TYPE popcnt = 0;
+   __m512i accum = _mm512_setzero_si512();
+   const __m512i val = _mm512_loadu_si512((const __m512i *) buf);
+   const __m512i cnt = _mm512_popcnt_epi64(val);
+   accum = _mm512_add_epi64(accum, cnt);
+   popcnt = _mm512_reduce_add_epi64(accum);
+   /* return computed value, to prevent the above being optimized away */
+   return popcnt == 0;])],
+  [Ac_cachevar=yes],
+  [Ac_cachevar=no])
+CFLAGS="$pgac_save_CFLAGS"])
+if test x"$Ac_cachevar" = x"yes"; then
+  CFLAGS_POPCNT="$1"
+  pgac_avx512_popcnt_intrinsics=yes
+fi
+undefine([Ac_cachevar])dnl
+])# PGAC_AVX512_POPCNT_INTRINSICS
diff --git a/configure b/configure
index 36feeafbb2..b48ed7f271 100755
--- a/configure
+++ b/configure
@@ -647,6 +647,9 @@ MSGFMT_FLAGS
 MSGFMT
 PG_CRC32C_OBJS
 CFLAGS_CRC
+PG_POPCNT_OBJS
+CFLAGS_POPCNT
+CFLAGS_XSAVE
 LIBOBJS
 OPENSSL
 ZSTD
@@ -17404,6 +17407,40 @@ $as_echo "#define HAVE__GET_CPUID 1" >>confdefs.h
 
 fi
 
+{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for __get_cpuid_count" >&5
+$as_echo_n "checking for __get_cpuid_count... " >&6; }
+if ${pgac_cv__get_cpuid_count+:} 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_count(7, 0, &exx[0], &exx[1], &exx[2], &exx[3]);
+
+  ;
+  return 0;
+}
+_ACEOF
+if ac_fn_c_try_link "$LINENO"; then :
+  pgac_cv__get_cpuid_count="yes"
+else
+  pgac_cv__get_cpuid_count="no"
+fi
+rm -f core conftest.err conftest.$ac_objext \
+    conftest$ac_exeext conftest.$ac_ext
+fi
+{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $pgac_cv__get_cpuid_count" >&5
+$as_echo "$pgac_cv__get_cpuid_count" >&6; }
+if test x"$pgac_cv__get_cpuid_count" = x"yes"; then
+
+$as_echo "#define HAVE__GET_CPUID_COUNT 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 :
@@ -17438,6 +17475,221 @@ $as_echo "#define HAVE__CPUID 1" >>confdefs.h
 
 fi
 
+{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for __cpuidex" >&5
+$as_echo_n "checking for __cpuidex... " >&6; }
+if ${pgac_cv__cpuidex+:} 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_cpuidex(exx[0], 7, 0);
+
+  ;
+  return 0;
+}
+_ACEOF
+if ac_fn_c_try_link "$LINENO"; then :
+  pgac_cv__cpuidex="yes"
+else
+  pgac_cv__cpuidex="no"
+fi
+rm -f core conftest.err conftest.$ac_objext \
+    conftest$ac_exeext conftest.$ac_ext
+fi
+{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $pgac_cv__cpuidex" >&5
+$as_echo "$pgac_cv__cpuidex" >&6; }
+if test x"$pgac_cv__cpuidex" = x"yes"; then
+
+$as_echo "#define HAVE__CPUIDEX 1" >>confdefs.h
+
+fi
+
+# Check for XSAVE intrinsics
+#
+CFLAGS_XSAVE=""
+{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for _xgetbv with CFLAGS=" >&5
+$as_echo_n "checking for _xgetbv with CFLAGS=... " >&6; }
+if ${pgac_cv_xsave_intrinsics_+:} false; then :
+  $as_echo_n "(cached) " >&6
+else
+  pgac_save_CFLAGS=$CFLAGS
+CFLAGS="$pgac_save_CFLAGS "
+cat confdefs.h - <<_ACEOF >conftest.$ac_ext
+/* end confdefs.h.  */
+#include <immintrin.h>
+int
+main ()
+{
+return _xgetbv(0) & 0xe0;
+  ;
+  return 0;
+}
+_ACEOF
+if ac_fn_c_try_link "$LINENO"; then :
+  pgac_cv_xsave_intrinsics_=yes
+else
+  pgac_cv_xsave_intrinsics_=no
+fi
+rm -f core conftest.err conftest.$ac_objext \
+    conftest$ac_exeext conftest.$ac_ext
+CFLAGS="$pgac_save_CFLAGS"
+fi
+{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $pgac_cv_xsave_intrinsics_" >&5
+$as_echo "$pgac_cv_xsave_intrinsics_" >&6; }
+if test x"$pgac_cv_xsave_intrinsics_" = x"yes"; then
+  CFLAGS_XSAVE=""
+  pgac_xsave_intrinsics=yes
+fi
+
+if test x"$pgac_xsave_intrinsics" != x"yes"; then
+  { $as_echo "$as_me:${as_lineno-$LINENO}: checking for _xgetbv with CFLAGS=-mxsave" >&5
+$as_echo_n "checking for _xgetbv with CFLAGS=-mxsave... " >&6; }
+if ${pgac_cv_xsave_intrinsics__mxsave+:} false; then :
+  $as_echo_n "(cached) " >&6
+else
+  pgac_save_CFLAGS=$CFLAGS
+CFLAGS="$pgac_save_CFLAGS -mxsave"
+cat confdefs.h - <<_ACEOF >conftest.$ac_ext
+/* end confdefs.h.  */
+#include <immintrin.h>
+int
+main ()
+{
+return _xgetbv(0) & 0xe0;
+  ;
+  return 0;
+}
+_ACEOF
+if ac_fn_c_try_link "$LINENO"; then :
+  pgac_cv_xsave_intrinsics__mxsave=yes
+else
+  pgac_cv_xsave_intrinsics__mxsave=no
+fi
+rm -f core conftest.err conftest.$ac_objext \
+    conftest$ac_exeext conftest.$ac_ext
+CFLAGS="$pgac_save_CFLAGS"
+fi
+{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $pgac_cv_xsave_intrinsics__mxsave" >&5
+$as_echo "$pgac_cv_xsave_intrinsics__mxsave" >&6; }
+if test x"$pgac_cv_xsave_intrinsics__mxsave" = x"yes"; then
+  CFLAGS_XSAVE="-mxsave"
+  pgac_xsave_intrinsics=yes
+fi
+
+fi
+if test x"$pgac_xsave_intrinsics" = x"yes"; then
+
+$as_echo "#define HAVE_XSAVE_INTRINSICS 1" >>confdefs.h
+
+fi
+
+
+# Check for AVX512 popcount intrinsics
+#
+CFLAGS_POPCNT=""
+PG_POPCNT_OBJS=""
+if test x"$host_cpu" = x"x86_64"; then
+  { $as_echo "$as_me:${as_lineno-$LINENO}: checking for _mm512_popcnt_epi64 with CFLAGS=" >&5
+$as_echo_n "checking for _mm512_popcnt_epi64 with CFLAGS=... " >&6; }
+if ${pgac_cv_avx512_popcnt_intrinsics_+:} false; then :
+  $as_echo_n "(cached) " >&6
+else
+  pgac_save_CFLAGS=$CFLAGS
+CFLAGS="$pgac_save_CFLAGS "
+cat confdefs.h - <<_ACEOF >conftest.$ac_ext
+/* end confdefs.h.  */
+#include <immintrin.h>
+int
+main ()
+{
+const char buf[sizeof(__m512i)];
+   PG_INT64_TYPE popcnt = 0;
+   __m512i accum = _mm512_setzero_si512();
+   const __m512i val = _mm512_loadu_si512((const __m512i *) buf);
+   const __m512i cnt = _mm512_popcnt_epi64(val);
+   accum = _mm512_add_epi64(accum, cnt);
+   popcnt = _mm512_reduce_add_epi64(accum);
+   /* return computed value, to prevent the above being optimized away */
+   return popcnt == 0;
+  ;
+  return 0;
+}
+_ACEOF
+if ac_fn_c_try_link "$LINENO"; then :
+  pgac_cv_avx512_popcnt_intrinsics_=yes
+else
+  pgac_cv_avx512_popcnt_intrinsics_=no
+fi
+rm -f core conftest.err conftest.$ac_objext \
+    conftest$ac_exeext conftest.$ac_ext
+CFLAGS="$pgac_save_CFLAGS"
+fi
+{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $pgac_cv_avx512_popcnt_intrinsics_" >&5
+$as_echo "$pgac_cv_avx512_popcnt_intrinsics_" >&6; }
+if test x"$pgac_cv_avx512_popcnt_intrinsics_" = x"yes"; then
+  CFLAGS_POPCNT=""
+  pgac_avx512_popcnt_intrinsics=yes
+fi
+
+  if test x"$pgac_avx512_popcnt_intrinsics" != x"yes"; then
+    { $as_echo "$as_me:${as_lineno-$LINENO}: checking for _mm512_popcnt_epi64 with CFLAGS=-mavx512vpopcntdq" >&5
+$as_echo_n "checking for _mm512_popcnt_epi64 with CFLAGS=-mavx512vpopcntdq... " >&6; }
+if ${pgac_cv_avx512_popcnt_intrinsics__mavx512vpopcntdq+:} false; then :
+  $as_echo_n "(cached) " >&6
+else
+  pgac_save_CFLAGS=$CFLAGS
+CFLAGS="$pgac_save_CFLAGS -mavx512vpopcntdq"
+cat confdefs.h - <<_ACEOF >conftest.$ac_ext
+/* end confdefs.h.  */
+#include <immintrin.h>
+int
+main ()
+{
+const char buf[sizeof(__m512i)];
+   PG_INT64_TYPE popcnt = 0;
+   __m512i accum = _mm512_setzero_si512();
+   const __m512i val = _mm512_loadu_si512((const __m512i *) buf);
+   const __m512i cnt = _mm512_popcnt_epi64(val);
+   accum = _mm512_add_epi64(accum, cnt);
+   popcnt = _mm512_reduce_add_epi64(accum);
+   /* return computed value, to prevent the above being optimized away */
+   return popcnt == 0;
+  ;
+  return 0;
+}
+_ACEOF
+if ac_fn_c_try_link "$LINENO"; then :
+  pgac_cv_avx512_popcnt_intrinsics__mavx512vpopcntdq=yes
+else
+  pgac_cv_avx512_popcnt_intrinsics__mavx512vpopcntdq=no
+fi
+rm -f core conftest.err conftest.$ac_objext \
+    conftest$ac_exeext conftest.$ac_ext
+CFLAGS="$pgac_save_CFLAGS"
+fi
+{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $pgac_cv_avx512_popcnt_intrinsics__mavx512vpopcntdq" >&5
+$as_echo "$pgac_cv_avx512_popcnt_intrinsics__mavx512vpopcntdq" >&6; }
+if test x"$pgac_cv_avx512_popcnt_intrinsics__mavx512vpopcntdq" = x"yes"; then
+  CFLAGS_POPCNT="-mavx512vpopcntdq"
+  pgac_avx512_popcnt_intrinsics=yes
+fi
+
+  fi
+  if test x"$pgac_avx512_popcnt_intrinsics" = x"yes"; then
+    PG_POPCNT_OBJS="pg_popcount_avx512.o pg_popcount_avx512_choose.o"
+
+$as_echo "#define USE_AVX512_POPCNT_WITH_RUNTIME_CHECK 1" >>confdefs.h
+
+  fi
+fi
+
+
+
 # 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
diff --git a/configure.ac b/configure.ac
index 57f734879e..2bbd81dfb8 100644
--- a/configure.ac
+++ b/configure.ac
@@ -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"$pgac_xsave_intrinsics" = x"yes"; then
+  AC_DEFINE(HAVE_XSAVE_INTRINSICS, 1, [Define to 1 if you have XSAVE intrinsics.])
+fi
+AC_SUBST(CFLAGS_XSAVE)
+
+# Check for AVX512 popcount intrinsics
+#
+CFLAGS_POPCNT=""
+PG_POPCNT_OBJS=""
+if test x"$host_cpu" = x"x86_64"; then
+  PGAC_AVX512_POPCNT_INTRINSICS([])
+  if test x"$pgac_avx512_popcnt_intrinsics" != x"yes"; then
+    PGAC_AVX512_POPCNT_INTRINSICS([-mavx512vpopcntdq])
+  fi
+  if test x"$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 AVX512 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
diff --git a/meson.build b/meson.build
index 18b5be842e..96be29c22b 100644
--- a/meson.build
+++ b/meson.build
@@ -1783,6 +1783,30 @@ elif cc.links('''
 endif
 
 
+# Check for __get_cpuid_count() and __cpuidex() in a similar fashion.
+if cc.links('''
+    #include <cpuid.h>
+    int main(int arg, char **argv)
+    {
+        unsigned int exx[4] = {0, 0, 0, 0};
+        __get_cpuid_count(7, 0, &exx[0], &exx[1], &exx[2], &exx[3]);
+    }
+    ''', name: '__get_cpuid_count',
+    args: test_c_args)
+  cdata.set('HAVE__GET_CPUID_COUNT', 1)
+elif cc.links('''
+    #include <intrin.h>
+    int main(int arg, char **argv)
+    {
+        unsigned int exx[4] = {0, 0, 0, 0};
+        __cpuidex(exx, 7, 0);
+    }
+    ''', name: '__cpuidex',
+    args: test_c_args)
+  cdata.set('HAVE__CPUIDEX', 1)
+endif
+
+
 # Defend against clang being used on x86-32 without SSE2 enabled.  As current
 # versions of clang do not understand -fexcess-precision=standard, the use of
 # x87 floating point operations leads to problems like isinf possibly returning
@@ -1996,6 +2020,69 @@ int main(void)
 endif
 
 
+###############################################################
+# Check for the availability of XSAVE intrinsics.
+###############################################################
+
+cflags_xsave = []
+if host_cpu == 'x86' or host_cpu == 'x86_64'
+
+  prog = '''
+#include <immintrin.h>
+
+int main(void)
+{
+    return _xgetbv(0) & 0xe0;
+}
+'''
+
+  if cc.links(prog, name: 'XSAVE intrinsics without -mxsave',
+        args: test_c_args)
+    cdata.set('HAVE_XSAVE_INTRINSICS', 1)
+  elif cc.links(prog, name: 'XSAVE intrinsics with -mxsave',
+        args: test_c_args + ['-mxsave'])
+    cdata.set('HAVE_XSAVE_INTRINSICS', 1)
+    cflags_xsave += '-mxsave'
+  endif
+
+endif
+
+
+###############################################################
+# Check for the availability of AVX512 popcount intrinsics.
+###############################################################
+
+cflags_popcnt = []
+if host_cpu == 'x86_64'
+
+  prog = '''
+#include <immintrin.h>
+
+int main(void)
+{
+    const char buf[sizeof(__m512i)];
+    INT64 popcnt = 0;
+    __m512i accum = _mm512_setzero_si512();
+    const __m512i val = _mm512_loadu_si512((const __m512i *) buf);
+    const __m512i cnt = _mm512_popcnt_epi64(val);
+    accum = _mm512_add_epi64(accum, cnt);
+    popcnt = _mm512_reduce_add_epi64(accum);
+    /* return computed value, to prevent the above being optimized away */
+    return popcnt == 0;
+}
+'''
+
+  if cc.links(prog, name: 'AVX512 popcount without -mavx512vpopcntdq',
+        args: test_c_args + ['-DINT64=@0@'.format(cdata.get('PG_INT64_TYPE'))])
+    cdata.set('USE_AVX512_POPCNT_WITH_RUNTIME_CHECK', 1)
+  elif cc.links(prog, name: 'AVX512 popcount with -mavx512vpopcntdq',
+        args: test_c_args + ['-DINT64=@0@'.format(cdata.get('PG_INT64_TYPE'))] + ['-mavx512vpopcntdq'])
+    cdata.set('USE_AVX512_POPCNT_WITH_RUNTIME_CHECK', 1)
+    cflags_popcnt += '-mavx512vpopcntdq'
+  endif
+
+endif
+
 
 ###############################################################
 # Select CRC-32C implementation.
diff --git a/src/Makefile.global.in b/src/Makefile.global.in
index 8b3f8c24e0..36d880d225 100644
--- a/src/Makefile.global.in
+++ b/src/Makefile.global.in
@@ -262,7 +262,9 @@ CFLAGS_SL_MODULE = @CFLAGS_SL_MODULE@
 CXXFLAGS_SL_MODULE = @CXXFLAGS_SL_MODULE@
 CFLAGS_UNROLL_LOOPS = @CFLAGS_UNROLL_LOOPS@
 CFLAGS_VECTORIZE = @CFLAGS_VECTORIZE@
+CFLAGS_POPCNT = @CFLAGS_POPCNT@
 CFLAGS_CRC = @CFLAGS_CRC@
+CFLAGS_XSAVE = @CFLAGS_XSAVE@
 PERMIT_DECLARATION_AFTER_STATEMENT = @PERMIT_DECLARATION_AFTER_STATEMENT@
 CXXFLAGS = @CXXFLAGS@
 
@@ -758,6 +760,9 @@ LIBOBJS = @LIBOBJS@
 # files needed for the chosen CRC-32C implementation
 PG_CRC32C_OBJS = @PG_CRC32C_OBJS@
 
+# files needed for the chosen popcount implementation
+PG_POPCNT_OBJS = @PG_POPCNT_OBJS@
+
 LIBS := -lpgcommon -lpgport $(LIBS)
 
 # to make ws2_32.lib the last library
diff --git a/src/include/pg_config.h.in b/src/include/pg_config.h.in
index 591e1ca3df..de067e6182 100644
--- a/src/include/pg_config.h.in
+++ b/src/include/pg_config.h.in
@@ -513,6 +513,9 @@
 /* Define to 1 if the assembler supports X86_64's POPCNTQ instruction. */
 #undef HAVE_X86_64_POPCNTQ
 
+/* Define to 1 if you have XSAVE intrinsics. */
+#undef HAVE_XSAVE_INTRINSICS
+
 /* Define to 1 if the system has the type `_Bool'. */
 #undef HAVE__BOOL
 
@@ -555,9 +558,15 @@
 /* Define to 1 if you have __cpuid. */
 #undef HAVE__CPUID
 
+/* Define to 1 if you have __cpuidex. */
+#undef HAVE__CPUIDEX
+
 /* Define to 1 if you have __get_cpuid. */
 #undef HAVE__GET_CPUID
 
+/* Define to 1 if you have __get_cpuid_count. */
+#undef HAVE__GET_CPUID_COUNT
+
 /* Define to 1 if your compiler understands _Static_assert. */
 #undef HAVE__STATIC_ASSERT
 
@@ -680,6 +689,9 @@
 /* Define to 1 to build with assertion checks. (--enable-cassert) */
 #undef USE_ASSERT_CHECKING
 
+/* Define to 1 to use AVX512 popcount instructions with a runtime check. */
+#undef USE_AVX512_POPCNT_WITH_RUNTIME_CHECK
+
 /* Define to 1 to build with Bonjour support. (--with-bonjour) */
 #undef USE_BONJOUR
 
diff --git a/src/include/port/pg_bitutils.h b/src/include/port/pg_bitutils.h
index de480da71e..2b35021bc6 100644
--- a/src/include/port/pg_bitutils.h
+++ b/src/include/port/pg_bitutils.h
@@ -304,6 +304,21 @@ extern PGDLLIMPORT int (*pg_popcount32) (uint32 word);
 extern PGDLLIMPORT int (*pg_popcount64) (uint64 word);
 extern PGDLLIMPORT uint64 (*pg_popcount_optimized) (const char *buf, int bytes);
 
+/* Export pg_popcount_fast() for use in the AVX512 implementation. */
+extern uint64 pg_popcount_fast(const char *buf, int bytes);
+
+/*
+ * We can also try to use the AVX512 popcount instruction on some systems.
+ * The implementation of that is located in its own file because it may
+ * require special compiler flags that we don't want to apply to any other
+ * files.  Note that we only build this when TRY_POPCNT_FAST is set so that we
+ * can fall back to pg_popcount_fast() as needed.
+ */
+#ifdef USE_AVX512_POPCNT_WITH_RUNTIME_CHECK
+extern bool pg_popcount_avx512_available(void);
+extern uint64 pg_popcount_avx512(const char *buf, int bytes);
+#endif
+
 #else
 /* Use a portable implementation -- no need for a function pointer. */
 extern int	pg_popcount32(uint32 word);
diff --git a/src/makefiles/meson.build b/src/makefiles/meson.build
index b0f4178b3d..5618050b30 100644
--- a/src/makefiles/meson.build
+++ b/src/makefiles/meson.build
@@ -100,8 +100,10 @@ pgxs_kv = {
     ' '.join(cflags_no_decl_after_statement),
 
   'CFLAGS_CRC': ' '.join(cflags_crc),
+  'CFLAGS_POPCNT': ' '.join(cflags_popcnt),
   'CFLAGS_UNROLL_LOOPS': ' '.join(unroll_loops_cflags),
   'CFLAGS_VECTORIZE': ' '.join(vectorize_cflags),
+  'CFLAGS_XSAVE': ' '.join(cflags_xsave),
 
   'LDFLAGS': var_ldflags,
   'LDFLAGS_EX': var_ldflags_ex,
@@ -177,7 +179,7 @@ pgxs_empty = [
   'WANTED_LANGUAGES',
 
   # Not needed because we don't build the server / PLs with the generated makefile
-  'LIBOBJS', 'PG_CRC32C_OBJS', 'TAS',
+  'LIBOBJS', 'PG_CRC32C_OBJS', 'PG_POPCNT_OBJS', 'TAS',
   'DTRACEFLAGS', # only server has dtrace probes
 
   'perl_archlibexp', 'perl_embed_ccflags', 'perl_embed_ldflags', 'perl_includespec', 'perl_privlibexp',
diff --git a/src/port/Makefile b/src/port/Makefile
index dcc8737e68..db7c02117b 100644
--- a/src/port/Makefile
+++ b/src/port/Makefile
@@ -38,6 +38,7 @@ LIBS += $(PTHREAD_LIBS)
 OBJS = \
 	$(LIBOBJS) \
 	$(PG_CRC32C_OBJS) \
+	$(PG_POPCNT_OBJS) \
 	bsearch_arg.o \
 	chklocale.o \
 	inet_net_ntop.o \
@@ -92,6 +93,16 @@ pg_crc32c_armv8.o: CFLAGS+=$(CFLAGS_CRC)
 pg_crc32c_armv8_shlib.o: CFLAGS+=$(CFLAGS_CRC)
 pg_crc32c_armv8_srv.o: CFLAGS+=$(CFLAGS_CRC)
 
+# all versions of pg_popcount_avx512_choose.o need CFLAGS_XSAVE
+pg_popcount_avx512_choose.o: CFLAGS+=$(CFLAGS_XSAVE)
+pg_popcount_avx512_choose_shlib.o: CFLAGS+=$(CFLAGS_XSAVE)
+pg_popcount_avx512_choose_srv.o: CFLAGS+=$(CFLAGS_XSAVE)
+
+# all versions of pg_popcount_avx512.o need CFLAGS_POPCNT
+pg_popcount_avx512.o: CFLAGS+=$(CFLAGS_POPCNT)
+pg_popcount_avx512_shlib.o: CFLAGS+=$(CFLAGS_POPCNT)
+pg_popcount_avx512_srv.o: CFLAGS+=$(CFLAGS_POPCNT)
+
 #
 # Shared library versions of object files
 #
diff --git a/src/port/meson.build b/src/port/meson.build
index 92b593e6ef..fd9ee199d1 100644
--- a/src/port/meson.build
+++ b/src/port/meson.build
@@ -84,6 +84,8 @@ replace_funcs_pos = [
   ['pg_crc32c_sse42', 'USE_SSE42_CRC32C_WITH_RUNTIME_CHECK', 'crc'],
   ['pg_crc32c_sse42_choose', 'USE_SSE42_CRC32C_WITH_RUNTIME_CHECK'],
   ['pg_crc32c_sb8', 'USE_SSE42_CRC32C_WITH_RUNTIME_CHECK'],
+  ['pg_popcount_avx512', 'USE_AVX512_POPCNT_WITH_RUNTIME_CHECK', 'popcnt'],
+  ['pg_popcount_avx512_choose', 'USE_AVX512_POPCNT_WITH_RUNTIME_CHECK', 'xsave'],
 
   # arm / aarch64
   ['pg_crc32c_armv8', 'USE_ARMV8_CRC32C'],
@@ -98,8 +100,8 @@ replace_funcs_pos = [
   ['pg_crc32c_sb8', 'USE_SLICING_BY_8_CRC32C'],
 ]
 
-pgport_cflags = {'crc': cflags_crc}
-pgport_sources_cflags = {'crc': []}
+pgport_cflags = {'crc': cflags_crc, 'popcnt': cflags_popcnt, 'xsave': cflags_xsave}
+pgport_sources_cflags = {'crc': [], 'popcnt': [], 'xsave': []}
 
 foreach f : replace_funcs_neg
   func = f.get(0)
diff --git a/src/port/pg_bitutils.c b/src/port/pg_bitutils.c
index 6271acea60..2fa16b54b8 100644
--- a/src/port/pg_bitutils.c
+++ b/src/port/pg_bitutils.c
@@ -114,7 +114,10 @@ static int	pg_popcount64_choose(uint64 word);
 static uint64 pg_popcount_choose(const char *buf, int bytes);
 static inline int pg_popcount32_fast(uint32 word);
 static inline int pg_popcount64_fast(uint64 word);
-static uint64 pg_popcount_fast(const char *buf, int bytes);
+
+#ifdef USE_AVX512_POPCNT_WITH_RUNTIME_CHECK
+static uint64 pg_popcount_fast_or_avx512(const char *buf, int bytes);
+#endif
 
 int			(*pg_popcount32) (uint32 word) = pg_popcount32_choose;
 int			(*pg_popcount64) (uint64 word) = pg_popcount64_choose;
@@ -156,6 +159,10 @@ choose_popcount_functions(void)
 		pg_popcount32 = pg_popcount32_fast;
 		pg_popcount64 = pg_popcount64_fast;
 		pg_popcount_optimized = pg_popcount_fast;
+#ifdef USE_AVX512_POPCNT_WITH_RUNTIME_CHECK
+		if (pg_popcount_avx512_available())
+			pg_popcount_optimized = pg_popcount_fast_or_avx512;
+#endif
 	}
 	else
 	{
@@ -224,7 +231,7 @@ __asm__ __volatile__(" popcntq %1,%0\n":"=q"(res):"rm"(word):"cc");
  * pg_popcount_fast
  *		Returns the number of 1-bits in buf
  */
-static uint64
+uint64
 pg_popcount_fast(const char *buf, int bytes)
 {
 	uint64		popcnt = 0;
@@ -266,6 +273,24 @@ pg_popcount_fast(const char *buf, int bytes)
 	return popcnt;
 }
 
+/*
+ * This is a wrapper function for pg_popcount_avx512() that uses
+ * pg_popcount_fast() when there aren't enough bytes to fit in an AVX-512
+ * register.  The compiler should be able to inline pg_popcount_fast() so that
+ * we only take on additional function call overhead when it's likely to be a
+ * better option.
+ */
+#ifdef USE_AVX512_POPCNT_WITH_RUNTIME_CHECK
+static uint64
+pg_popcount_fast_or_avx512(const char *buf, int bytes)
+{
+	if (bytes < 64)
+		return pg_popcount_fast(buf, bytes);
+	else
+		return pg_popcount_avx512(buf, bytes);
+}
+#endif							/* USE_AVX512_POPCNT_WITH_RUNTIME_CHECK */
+
 #endif							/* TRY_POPCNT_FAST */
 
 
diff --git a/src/port/pg_popcount_avx512.c b/src/port/pg_popcount_avx512.c
new file mode 100644
index 0000000000..f86558d1ee
--- /dev/null
+++ b/src/port/pg_popcount_avx512.c
@@ -0,0 +1,49 @@
+/*-------------------------------------------------------------------------
+ *
+ * pg_popcount_avx512.c
+ *	  Holds the pg_popcount() implementation that uses AVX512 instructions.
+ *
+ * Copyright (c) 2024, PostgreSQL Global Development Group
+ *
+ * IDENTIFICATION
+ *	  src/port/pg_popcount_avx512.c
+ *
+ *-------------------------------------------------------------------------
+ */
+#include "c.h"
+
+#include <immintrin.h>
+
+#include "port/pg_bitutils.h"
+
+/*
+ * It's probably unlikely that TRY_POPCNT_FAST won't be set if we are able to
+ * use AVX512 intrinsics, but we check it anyway to be sure.  We rely on
+ * pg_popcount_fast() as our fallback implementation in pg_popcount_avx512().
+ */
+#ifdef TRY_POPCNT_FAST
+
+/*
+ * pg_popcount_avx512
+ *		Returns the number of 1-bits in buf
+ */
+uint64
+pg_popcount_avx512(const char *buf, int bytes)
+{
+	uint64		popcnt;
+	__m512i		accum = _mm512_setzero_si512();
+
+	for (; bytes >= sizeof(__m512i); bytes -= sizeof(__m512i))
+	{
+		const		__m512i val = _mm512_loadu_si512((const __m512i *) buf);
+		const		__m512i cnt = _mm512_popcnt_epi64(val);
+
+		accum = _mm512_add_epi64(accum, cnt);
+		buf += sizeof(__m512i);
+	}
+
+	popcnt = _mm512_reduce_add_epi64(accum);
+	return popcnt + pg_popcount_fast(buf, bytes);
+}
+
+#endif							/* TRY_POPCNT_FAST */
diff --git a/src/port/pg_popcount_avx512_choose.c b/src/port/pg_popcount_avx512_choose.c
new file mode 100644
index 0000000000..9e81cd33ad
--- /dev/null
+++ b/src/port/pg_popcount_avx512_choose.c
@@ -0,0 +1,71 @@
+/*-------------------------------------------------------------------------
+ *
+ * pg_popcount_avx512_choose.c
+ *    Test whether we can use AVX512 POPCNT instructions.
+ *
+ * Copyright (c) 2024, PostgreSQL Global Development Group
+ *
+ * IDENTIFICATION
+ *    src/port/pg_popcount_avx512_choose.c
+ *
+ *-------------------------------------------------------------------------
+ */
+#include "c.h"
+
+#if defined(HAVE__GET_CPUID) || defined(HAVE__GET_CPUID_COUNT)
+#include <cpuid.h>
+#endif
+
+#ifdef HAVE_XSAVE_INTRINSICS
+#include <immintrin.h>
+#endif
+
+#if defined(HAVE__CPUID) || defined(HAVE__CPUIDEX)
+#include <intrin.h>
+#endif
+
+#include "port/pg_bitutils.h"
+
+/*
+ * It's probably unlikely that TRY_POPCNT_FAST won't be set if we are able to
+ * use AVX512 intrinsics, but we check it anyway to be sure.  We rely on
+ * pg_popcount_fast() as our fallback implementation in pg_popcount_avx512().
+ */
+#ifdef TRY_POPCNT_FAST
+
+/*
+ * Returns true if the CPU supports AVX512 POPCNT.
+ */
+bool
+pg_popcount_avx512_available(void)
+{
+	unsigned int exx[4] = {0, 0, 0, 0};
+
+	/* does CPUID say there's support for AVX512 POPCNT? */
+#if defined(HAVE__GET_CPUID_COUNT)
+	__get_cpuid_count(7, 0, &exx[0], &exx[1], &exx[2], &exx[3]);
+#elif defined(HAVE__CPUIDEX)
+	__cpuidex(exx, 7, 0);
+#endif
+	if ((exx[2] & (1 << 14)) == 0)	/* avx512vpopcntdq */
+		return false;
+
+	/* does CPUID say there's support for XGETBV? */
+	memset(exx, 0, sizeof(exx));
+#if defined(HAVE__GET_CPUID)
+	__get_cpuid(1, &exx[0], &exx[1], &exx[2], &exx[3]);
+#elif defined(HAVE__CPUID)
+	__cpuid(exx, 1);
+#endif
+	if ((exx[2] & (1 << 26)) == 0)	/* xsave */
+		return false;
+
+	/* does XGETBV say the ZMM registers are enabled? */
+#ifdef HAVE_XSAVE_INTRINSICS
+	return (_xgetbv(0) & 0xe0) != 0;
+#else
+	return false;
+#endif
+}
+
+#endif							/* TRY_POPCNT_FAST */
diff --git a/src/test/regress/expected/bit.out b/src/test/regress/expected/bit.out
index e17cbf42ca..6a436288bb 100644
--- a/src/test/regress/expected/bit.out
+++ b/src/test/regress/expected/bit.out
@@ -740,6 +740,30 @@ SELECT bit_count(B'1111111111'::bit(10));
         10
 (1 row)
 
+SELECT bit_count(repeat('0', 100)::bit(100));
+ bit_count 
+-----------
+         0
+(1 row)
+
+SELECT bit_count(repeat('1', 100)::bit(100));
+ bit_count 
+-----------
+       100
+(1 row)
+
+SELECT bit_count(repeat('01', 500)::bit(1000));
+ bit_count 
+-----------
+       500
+(1 row)
+
+SELECT bit_count(repeat('10101', 200)::bit(1000));
+ bit_count 
+-----------
+       600
+(1 row)
+
 -- This table is intentionally left around to exercise pg_dump/pg_upgrade
 CREATE TABLE bit_defaults(
   b1 bit(4) DEFAULT '1001',
diff --git a/src/test/regress/sql/bit.sql b/src/test/regress/sql/bit.sql
index 34230b99fb..8ba6facd03 100644
--- a/src/test/regress/sql/bit.sql
+++ b/src/test/regress/sql/bit.sql
@@ -223,6 +223,10 @@ SELECT overlay(B'0101011100' placing '001' from 20);
 -- bit_count
 SELECT bit_count(B'0101011100'::bit(10));
 SELECT bit_count(B'1111111111'::bit(10));
+SELECT bit_count(repeat('0', 100)::bit(100));
+SELECT bit_count(repeat('1', 100)::bit(100));
+SELECT bit_count(repeat('01', 500)::bit(1000));
+SELECT bit_count(repeat('10101', 200)::bit(1000));
 
 -- This table is intentionally left around to exercise pg_dump/pg_upgrade
 CREATE TABLE bit_defaults(
-- 
2.25.1


--EeQfGwPcQSOJBaQU
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v24-0002-optimize-visibilitymap_count-with-AVX512.patch"



^ permalink  raw  reply  [nested|flat] 16+ messages in thread

* [PATCH v16 1/1] AVX512 popcount support
@ 2024-03-27 21:39 Nathan Bossart <[email protected]>
  0 siblings, 0 replies; 16+ messages in thread

From: Nathan Bossart @ 2024-03-27 21:39 UTC (permalink / raw)

---
 config/c-compiler.m4                 |  34 +++++++++
 configure                            | 100 +++++++++++++++++++++++++++
 configure.ac                         |  14 ++++
 meson.build                          |  35 ++++++++++
 src/Makefile.global.in               |   4 ++
 src/include/pg_config.h.in           |   3 +
 src/include/port/pg_bitutils.h       |  17 +++++
 src/makefiles/meson.build            |   3 +-
 src/port/Makefile                    |   6 ++
 src/port/meson.build                 |   6 +-
 src/port/pg_bitutils.c               |  56 ++++++---------
 src/port/pg_popcount_avx512.c        |  40 +++++++++++
 src/port/pg_popcount_avx512_choose.c |  61 ++++++++++++++++
 13 files changed, 340 insertions(+), 39 deletions(-)
 create mode 100644 src/port/pg_popcount_avx512.c
 create mode 100644 src/port/pg_popcount_avx512_choose.c

diff --git a/config/c-compiler.m4 b/config/c-compiler.m4
index 3268a780bb..7d13368b23 100644
--- a/config/c-compiler.m4
+++ b/config/c-compiler.m4
@@ -694,3 +694,37 @@ if test x"$Ac_cachevar" = x"yes"; then
 fi
 undefine([Ac_cachevar])dnl
 ])# PGAC_LOONGARCH_CRC32C_INTRINSICS
+
+# PGAC_AVX512_POPCNT_INTRINSICS
+# -----------------------------
+# Check if the compiler supports the AVX512 POPCNT instructions using the
+# _mm512_setzero_si512, _mm512_loadu_si512, _mm512_popcnt_epi64,
+# _mm512_add_epi64, and _mm512_reduce_add_epi64 intrinsic functions.
+#
+# An optional compiler flag can be passed as argument
+# (e.g., -mavx512vpopcntdq).  If the intrinsics are supported, sets
+# pgac_avx512_popcnt_intrinsics and CFLAGS_POPCNT.
+AC_DEFUN([PGAC_AVX512_POPCNT_INTRINSICS],
+[define([Ac_cachevar], [AS_TR_SH([pgac_cv_avx512_popcnt_intrinsics_$1])])dnl
+AC_CACHE_CHECK([for _mm512_popcnt_epi64 with CFLAGS=$1], [Ac_cachevar],
+[pgac_save_CFLAGS=$CFLAGS
+CFLAGS="$pgac_save_CFLAGS $1"
+AC_LINK_IFELSE([AC_LANG_PROGRAM([#include <immintrin.h>],
+  [const char buf@<:@sizeof(__m512i)@:>@;
+   PG_INT64_TYPE popcnt = 0;
+   __m512i accum = _mm512_setzero_si512();
+   const __m512i val = _mm512_loadu_si512((const __m512i *) buf);
+   const __m512i cnt = _mm512_popcnt_epi64(val);
+   accum = _mm512_add_epi64(accum, cnt);
+   popcnt = _mm512_reduce_add_epi64(accum);
+   /* return computed value, to prevent the above being optimized away */
+   return popcnt == 0;])],
+  [Ac_cachevar=yes],
+  [Ac_cachevar=no])
+CFLAGS="$pgac_save_CFLAGS"])
+if test x"$Ac_cachevar" = x"yes"; then
+  CFLAGS_POPCNT="$1"
+  pgac_avx512_popcnt_intrinsics=yes
+fi
+undefine([Ac_cachevar])dnl
+])# PGAC_AVX512_POPCNT_INTRINSICS
diff --git a/configure b/configure
index 36feeafbb2..86c471f4ec 100755
--- a/configure
+++ b/configure
@@ -647,6 +647,8 @@ MSGFMT_FLAGS
 MSGFMT
 PG_CRC32C_OBJS
 CFLAGS_CRC
+CFLAGS_POPCNT
+PG_POPCNT_OBJS
 LIBOBJS
 OPENSSL
 ZSTD
@@ -17438,6 +17440,104 @@ $as_echo "#define HAVE__CPUID 1" >>confdefs.h
 
 fi
 
+# Check for AVX512 popcount intrinsics
+#
+PG_POPCNT_OBJS=""
+{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for _mm512_popcnt_epi64 with CFLAGS=" >&5
+$as_echo_n "checking for _mm512_popcnt_epi64 with CFLAGS=... " >&6; }
+if ${pgac_cv_avx512_popcnt_intrinsics_+:} false; then :
+  $as_echo_n "(cached) " >&6
+else
+  pgac_save_CFLAGS=$CFLAGS
+CFLAGS="$pgac_save_CFLAGS "
+cat confdefs.h - <<_ACEOF >conftest.$ac_ext
+/* end confdefs.h.  */
+#include <immintrin.h>
+int
+main ()
+{
+const char buf[sizeof(__m512i)];
+   PG_INT64_TYPE popcnt = 0;
+   __m512i accum = _mm512_setzero_si512();
+   const __m512i val = _mm512_loadu_si512((const __m512i *) buf);
+   const __m512i cnt = _mm512_popcnt_epi64(val);
+   accum = _mm512_add_epi64(accum, cnt);
+   popcnt = _mm512_reduce_add_epi64(accum);
+   /* return computed value, to prevent the above being optimized away */
+   return popcnt == 0;
+  ;
+  return 0;
+}
+_ACEOF
+if ac_fn_c_try_link "$LINENO"; then :
+  pgac_cv_avx512_popcnt_intrinsics_=yes
+else
+  pgac_cv_avx512_popcnt_intrinsics_=no
+fi
+rm -f core conftest.err conftest.$ac_objext \
+    conftest$ac_exeext conftest.$ac_ext
+CFLAGS="$pgac_save_CFLAGS"
+fi
+{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $pgac_cv_avx512_popcnt_intrinsics_" >&5
+$as_echo "$pgac_cv_avx512_popcnt_intrinsics_" >&6; }
+if test x"$pgac_cv_avx512_popcnt_intrinsics_" = x"yes"; then
+  CFLAGS_POPCNT=""
+  pgac_avx512_popcnt_intrinsics=yes
+fi
+
+if test x"$pgac_avx512_popcnt_intrinsics" != x"yes"; then
+  { $as_echo "$as_me:${as_lineno-$LINENO}: checking for _mm512_popcnt_epi64 with CFLAGS=-mavx512vpopcntdq" >&5
+$as_echo_n "checking for _mm512_popcnt_epi64 with CFLAGS=-mavx512vpopcntdq... " >&6; }
+if ${pgac_cv_avx512_popcnt_intrinsics__mavx512vpopcntdq+:} false; then :
+  $as_echo_n "(cached) " >&6
+else
+  pgac_save_CFLAGS=$CFLAGS
+CFLAGS="$pgac_save_CFLAGS -mavx512vpopcntdq"
+cat confdefs.h - <<_ACEOF >conftest.$ac_ext
+/* end confdefs.h.  */
+#include <immintrin.h>
+int
+main ()
+{
+const char buf[sizeof(__m512i)];
+   PG_INT64_TYPE popcnt = 0;
+   __m512i accum = _mm512_setzero_si512();
+   const __m512i val = _mm512_loadu_si512((const __m512i *) buf);
+   const __m512i cnt = _mm512_popcnt_epi64(val);
+   accum = _mm512_add_epi64(accum, cnt);
+   popcnt = _mm512_reduce_add_epi64(accum);
+   /* return computed value, to prevent the above being optimized away */
+   return popcnt == 0;
+  ;
+  return 0;
+}
+_ACEOF
+if ac_fn_c_try_link "$LINENO"; then :
+  pgac_cv_avx512_popcnt_intrinsics__mavx512vpopcntdq=yes
+else
+  pgac_cv_avx512_popcnt_intrinsics__mavx512vpopcntdq=no
+fi
+rm -f core conftest.err conftest.$ac_objext \
+    conftest$ac_exeext conftest.$ac_ext
+CFLAGS="$pgac_save_CFLAGS"
+fi
+{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $pgac_cv_avx512_popcnt_intrinsics__mavx512vpopcntdq" >&5
+$as_echo "$pgac_cv_avx512_popcnt_intrinsics__mavx512vpopcntdq" >&6; }
+if test x"$pgac_cv_avx512_popcnt_intrinsics__mavx512vpopcntdq" = x"yes"; then
+  CFLAGS_POPCNT="-mavx512vpopcntdq"
+  pgac_avx512_popcnt_intrinsics=yes
+fi
+
+fi
+if test x"$pgac_avx512_popcnt_intrinsics" = x"yes"; then
+  PG_POPCNT_OBJS="pg_popcount_avx512.o pg_popcount_avx512_choose.o"
+
+$as_echo "#define USE_AVX512_POPCNT_WITH_RUNTIME_CHECK 1" >>confdefs.h
+
+fi
+
+
+
 # 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
diff --git a/configure.ac b/configure.ac
index 57f734879e..b1aebb8583 100644
--- a/configure.ac
+++ b/configure.ac
@@ -2063,6 +2063,20 @@ if test x"$pgac_cv__cpuid" = x"yes"; then
   AC_DEFINE(HAVE__CPUID, 1, [Define to 1 if you have __cpuid.])
 fi
 
+# Check for AVX512 popcount intrinsics
+#
+PG_POPCNT_OBJS=""
+PGAC_AVX512_POPCNT_INTRINSICS([])
+if test x"$pgac_avx512_popcnt_intrinsics" != x"yes"; then
+  PGAC_AVX512_POPCNT_INTRINSICS([-mavx512vpopcntdq])
+fi
+if test x"$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 AVX512 popcount instructions with a runtime check.])
+fi
+AC_SUBST(PG_POPCNT_OBJS)
+AC_SUBST(CFLAGS_POPCNT)
+
 # 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
diff --git a/meson.build b/meson.build
index 18b5be842e..fbd2aa3dbd 100644
--- a/meson.build
+++ b/meson.build
@@ -1996,6 +1996,41 @@ int main(void)
 endif
 
 
+###############################################################
+# Check for the availability of AVX512 popcount intrinsics.
+###############################################################
+
+cflags_popcnt = []
+if host_cpu == 'x86' or host_cpu == 'x86_64'
+
+  prog = '''
+#include <immintrin.h>
+
+int main(void)
+{
+    const char buf[sizeof(__m512i)];
+    INT64 popcnt = 0;
+    __m512i accum = _mm512_setzero_si512();
+    const __m512i val = _mm512_loadu_si512((const __m512i *) buf);
+    const __m512i cnt = _mm512_popcnt_epi64(val);
+    accum = _mm512_add_epi64(accum, cnt);
+    popcnt = _mm512_reduce_add_epi64(accum);
+    /* return computed value, to prevent the above being optimized away */
+    return popcnt == 0;
+}
+'''
+
+  if cc.links(prog, name: 'AVX512 popcount without -mavx512vpopcntdq',
+        args: test_c_args + ['-DINT64=@0@'.format(cdata.get('PG_INT64_TYPE'))])
+    cdata.set('USE_AVX512_POPCNT_WITH_RUNTIME_CHECK', 1)
+  elif cc.links(prog, name: 'AVX512 popcount with -mavx512vpopcntdq',
+        args: test_c_args + ['-DINT64=@0@'.format(cdata.get('PG_INT64_TYPE'))] + ['-mavx512vpopcntdq'])
+    cdata.set('USE_AVX512_POPCNT_WITH_RUNTIME_CHECK', 1)
+    cflags_popcnt += '-mavx512vpopcntdq'
+  endif
+
+endif
+
 
 ###############################################################
 # Select CRC-32C implementation.
diff --git a/src/Makefile.global.in b/src/Makefile.global.in
index 8b3f8c24e0..dec467b7dd 100644
--- a/src/Makefile.global.in
+++ b/src/Makefile.global.in
@@ -262,6 +262,7 @@ CFLAGS_SL_MODULE = @CFLAGS_SL_MODULE@
 CXXFLAGS_SL_MODULE = @CXXFLAGS_SL_MODULE@
 CFLAGS_UNROLL_LOOPS = @CFLAGS_UNROLL_LOOPS@
 CFLAGS_VECTORIZE = @CFLAGS_VECTORIZE@
+CFLAGS_POPCNT = @CFLAGS_POPCNT@
 CFLAGS_CRC = @CFLAGS_CRC@
 PERMIT_DECLARATION_AFTER_STATEMENT = @PERMIT_DECLARATION_AFTER_STATEMENT@
 CXXFLAGS = @CXXFLAGS@
@@ -758,6 +759,9 @@ LIBOBJS = @LIBOBJS@
 # files needed for the chosen CRC-32C implementation
 PG_CRC32C_OBJS = @PG_CRC32C_OBJS@
 
+# files needed for the chosen popcount implementation
+PG_POPCNT_OBJS = @PG_POPCNT_OBJS@
+
 LIBS := -lpgcommon -lpgport $(LIBS)
 
 # to make ws2_32.lib the last library
diff --git a/src/include/pg_config.h.in b/src/include/pg_config.h.in
index 591e1ca3df..c271c06b74 100644
--- a/src/include/pg_config.h.in
+++ b/src/include/pg_config.h.in
@@ -680,6 +680,9 @@
 /* Define to 1 to build with assertion checks. (--enable-cassert) */
 #undef USE_ASSERT_CHECKING
 
+/* Define to 1 to use AVX512 popcount instructions with a runtime check. */
+#undef USE_AVX512_POPCNT_WITH_RUNTIME_CHECK
+
 /* Define to 1 to build with Bonjour support. (--with-bonjour) */
 #undef USE_BONJOUR
 
diff --git a/src/include/port/pg_bitutils.h b/src/include/port/pg_bitutils.h
index 53e5239717..fc8d34ad25 100644
--- a/src/include/port/pg_bitutils.h
+++ b/src/include/port/pg_bitutils.h
@@ -298,12 +298,29 @@ pg_ceil_log2_64(uint64 num)
 #endif
 #endif
 
+/*
+ * We can also try to use the AVX512 popcount instruction on some systems.
+ * The implementation of that is located in its own file because it may
+ * require special compiler flags that we don't want to apply to any other
+ * files.
+ *
+ * NB: We assume that the availability of AVX512 intrinsics implies
+ * TRY_POPCNT_FAST.
+ */
+#ifdef USE_AVX512_POPCNT_WITH_RUNTIME_CHECK
+extern bool pg_popcount_avx512_available(void);
+extern uint64 pg_popcount_avx512(const char *buf, int bytes);
+#endif
+
 #ifdef TRY_POPCNT_FAST
 /* Attempt to use the POPCNT instruction, but perform a runtime check first */
 extern PGDLLIMPORT int (*pg_popcount32) (uint32 word);
 extern PGDLLIMPORT int (*pg_popcount64) (uint64 word);
 extern PGDLLIMPORT uint64 (*pg_popcount) (const char *buf, int bytes);
 
+/* Export pg_popcount_fast() for use in the AVX512 implementation. */
+extern uint64 pg_popcount_fast(const char *buf, int bytes);
+
 #else
 /* Use a portable implementation -- no need for a function pointer. */
 extern int	pg_popcount32(uint32 word);
diff --git a/src/makefiles/meson.build b/src/makefiles/meson.build
index b0f4178b3d..5a592ddaee 100644
--- a/src/makefiles/meson.build
+++ b/src/makefiles/meson.build
@@ -99,6 +99,7 @@ pgxs_kv = {
   'PERMIT_DECLARATION_AFTER_STATEMENT':
     ' '.join(cflags_no_decl_after_statement),
 
+  'CFLAGS_POPCNT': ' '.join(cflags_popcnt),
   'CFLAGS_CRC': ' '.join(cflags_crc),
   'CFLAGS_UNROLL_LOOPS': ' '.join(unroll_loops_cflags),
   'CFLAGS_VECTORIZE': ' '.join(vectorize_cflags),
@@ -177,7 +178,7 @@ pgxs_empty = [
   'WANTED_LANGUAGES',
 
   # Not needed because we don't build the server / PLs with the generated makefile
-  'LIBOBJS', 'PG_CRC32C_OBJS', 'TAS',
+  'LIBOBJS', 'PG_CRC32C_OBJS', 'PG_POPCNT_OBJS', 'TAS',
   'DTRACEFLAGS', # only server has dtrace probes
 
   'perl_archlibexp', 'perl_embed_ccflags', 'perl_embed_ldflags', 'perl_includespec', 'perl_privlibexp',
diff --git a/src/port/Makefile b/src/port/Makefile
index dcc8737e68..7e154ac379 100644
--- a/src/port/Makefile
+++ b/src/port/Makefile
@@ -38,6 +38,7 @@ LIBS += $(PTHREAD_LIBS)
 OBJS = \
 	$(LIBOBJS) \
 	$(PG_CRC32C_OBJS) \
+	$(PG_POPCNT_OBJS) \
 	bsearch_arg.o \
 	chklocale.o \
 	inet_net_ntop.o \
@@ -92,6 +93,11 @@ pg_crc32c_armv8.o: CFLAGS+=$(CFLAGS_CRC)
 pg_crc32c_armv8_shlib.o: CFLAGS+=$(CFLAGS_CRC)
 pg_crc32c_armv8_srv.o: CFLAGS+=$(CFLAGS_CRC)
 
+# all versions of pg_popcount_avx512.o need CFLAGS_POPCNT
+pg_popcount_avx512.o: CFLAGS+=$(CFLAGS_POPCNT)
+pg_popcount_avx512_shlib.o: CFLAGS+=$(CFLAGS_POPCNT)
+pg_popcount_avx512_srv.o: CFLAGS+=$(CFLAGS_POPCNT)
+
 #
 # Shared library versions of object files
 #
diff --git a/src/port/meson.build b/src/port/meson.build
index 92b593e6ef..7b93233428 100644
--- a/src/port/meson.build
+++ b/src/port/meson.build
@@ -84,6 +84,8 @@ replace_funcs_pos = [
   ['pg_crc32c_sse42', 'USE_SSE42_CRC32C_WITH_RUNTIME_CHECK', 'crc'],
   ['pg_crc32c_sse42_choose', 'USE_SSE42_CRC32C_WITH_RUNTIME_CHECK'],
   ['pg_crc32c_sb8', 'USE_SSE42_CRC32C_WITH_RUNTIME_CHECK'],
+  ['pg_popcount_avx512', 'USE_AVX512_POPCNT_WITH_RUNTIME_CHECK', 'popcnt'],
+  ['pg_popcount_avx512_choose', 'USE_AVX512_POPCNT_WITH_RUNTIME_CHECK'],
 
   # arm / aarch64
   ['pg_crc32c_armv8', 'USE_ARMV8_CRC32C'],
@@ -98,8 +100,8 @@ replace_funcs_pos = [
   ['pg_crc32c_sb8', 'USE_SLICING_BY_8_CRC32C'],
 ]
 
-pgport_cflags = {'crc': cflags_crc}
-pgport_sources_cflags = {'crc': []}
+pgport_cflags = {'crc': cflags_crc, 'popcnt': cflags_popcnt}
+pgport_sources_cflags = {'crc': [], 'popcnt': []}
 
 foreach f : replace_funcs_neg
   func = f.get(0)
diff --git a/src/port/pg_bitutils.c b/src/port/pg_bitutils.c
index 1197696e97..ada3e777f7 100644
--- a/src/port/pg_bitutils.c
+++ b/src/port/pg_bitutils.c
@@ -114,7 +114,6 @@ static int	pg_popcount64_choose(uint64 word);
 static uint64 pg_popcount_choose(const char *buf, int bytes);
 static inline int pg_popcount32_fast(uint32 word);
 static inline int pg_popcount64_fast(uint64 word);
-static uint64 pg_popcount_fast(const char *buf, int bytes);
 
 int			(*pg_popcount32) (uint32 word) = pg_popcount32_choose;
 int			(*pg_popcount64) (uint64 word) = pg_popcount64_choose;
@@ -142,20 +141,18 @@ pg_popcount_available(void)
 	return (exx[2] & (1 << 23)) != 0;	/* POPCNT */
 }
 
-/*
- * These functions get called on the first call to pg_popcount32 etc.
- * They detect whether we can use the asm implementations, and replace
- * the function pointers so that subsequent calls are routed directly to
- * the chosen implementation.
- */
-static int
-pg_popcount32_choose(uint32 word)
+static inline void
+choose_popcount_functions(void)
 {
 	if (pg_popcount_available())
 	{
 		pg_popcount32 = pg_popcount32_fast;
 		pg_popcount64 = pg_popcount64_fast;
 		pg_popcount = pg_popcount_fast;
+#ifdef USE_AVX512_POPCOUNT_WITH_RUNTIME_CHECK
+		if (pg_popcount_avx512_available())
+			pg_popcount = pg_popcount_avx512;
+#endif
 	}
 	else
 	{
@@ -163,45 +160,32 @@ pg_popcount32_choose(uint32 word)
 		pg_popcount64 = pg_popcount64_slow;
 		pg_popcount = pg_popcount_slow;
 	}
+}
 
+/*
+ * These functions get called on the first call to pg_popcount32 etc.
+ * They detect whether we can use the asm implementations, and replace
+ * the function pointers so that subsequent calls are routed directly to
+ * the chosen implementation.
+ */
+static int
+pg_popcount32_choose(uint32 word)
+{
+	choose_popcount_functions();
 	return pg_popcount32(word);
 }
 
 static int
 pg_popcount64_choose(uint64 word)
 {
-	if (pg_popcount_available())
-	{
-		pg_popcount32 = pg_popcount32_fast;
-		pg_popcount64 = pg_popcount64_fast;
-		pg_popcount = pg_popcount_fast;
-	}
-	else
-	{
-		pg_popcount32 = pg_popcount32_slow;
-		pg_popcount64 = pg_popcount64_slow;
-		pg_popcount = pg_popcount_slow;
-	}
-
+	choose_popcount_functions();
 	return pg_popcount64(word);
 }
 
 static uint64
 pg_popcount_choose(const char *buf, int bytes)
 {
-	if (pg_popcount_available())
-	{
-		pg_popcount32 = pg_popcount32_fast;
-		pg_popcount64 = pg_popcount64_fast;
-		pg_popcount = pg_popcount_fast;
-	}
-	else
-	{
-		pg_popcount32 = pg_popcount32_slow;
-		pg_popcount64 = pg_popcount64_slow;
-		pg_popcount = pg_popcount_slow;
-	}
-
+	choose_popcount_functions();
 	return pg_popcount(buf, bytes);
 }
 
@@ -243,7 +227,7 @@ __asm__ __volatile__(" popcntq %1,%0\n":"=q"(res):"rm"(word):"cc");
  * pg_popcount_fast
  *		Returns the number of 1-bits in buf
  */
-static uint64
+uint64
 pg_popcount_fast(const char *buf, int bytes)
 {
 	uint64		popcnt = 0;
diff --git a/src/port/pg_popcount_avx512.c b/src/port/pg_popcount_avx512.c
new file mode 100644
index 0000000000..c39db13f85
--- /dev/null
+++ b/src/port/pg_popcount_avx512.c
@@ -0,0 +1,40 @@
+/*-------------------------------------------------------------------------
+ *
+ * pg_popcount_avx512.c
+ *	  Holds the pg_popcount() implementation that uses AVX512 instructions.
+ *
+ * Copyright (c) 2019-2024, PostgreSQL Global Development Group
+ *
+ * IDENTIFICATION
+ *	  src/port/pg_popcount_avx512.c
+ *
+ *-------------------------------------------------------------------------
+ */
+#include "c.h"
+
+#include <immintrin.h>
+
+#include "port/pg_bitutils.h"
+
+/*
+ * pg_popcount_avx512
+ *		Returns the number of 1-bits in buf
+ */
+uint64
+pg_popcount_avx512(const char *buf, int bytes)
+{
+	uint64		popcnt;
+	__m512i		accum = _mm512_setzero_si512();
+
+	for (; bytes >= sizeof(__m512i); bytes -= sizeof(__m512i))
+	{
+		const		__m512i val = _mm512_loadu_si512((const __m512i *) buf);
+		const		__m512i cnt = _mm512_popcnt_epi64(val);
+
+		accum = _mm512_add_epi64(accum, cnt);
+		buf += sizeof(__m512i);
+	}
+
+	popcnt = _mm512_reduce_add_epi64(accum);
+	return popcnt + pg_popcount_fast(buf, bytes);
+}
diff --git a/src/port/pg_popcount_avx512_choose.c b/src/port/pg_popcount_avx512_choose.c
new file mode 100644
index 0000000000..62ebc515ce
--- /dev/null
+++ b/src/port/pg_popcount_avx512_choose.c
@@ -0,0 +1,61 @@
+/*-------------------------------------------------------------------------
+ *
+ * pg_popcount_avx512_choose.c
+ *    Test whether we can use AVX512 POPCNT instructions.
+ *
+ * Copyright (c) 2019-2024, PostgreSQL Global Development Group
+ *
+ * IDENTIFICATION
+ *    src/port/pg_popcount_avx512_choose.c
+ *
+ *-------------------------------------------------------------------------
+ */
+#include "c.h"
+
+#ifdef HAVE__GET_CPUID
+#include <cpuid.h>
+#endif
+
+#ifdef HAVE__CPUID
+#include <intrin.h>
+#endif
+
+#include "port/pg_bitutils.h"
+
+/*
+ * Return true if CPUID indicates that the AVX512 POPCNT instruction is
+ * available.
+ *
+ * NB: We assume the availability of AVX512 intrinsics implies availability of
+ * the required CPUID and XGETBV intrinsics.
+ */
+bool
+pg_popcount_avx512_available(void)
+{
+	unsigned int exx[4] = {0, 0, 0, 0};
+
+#if defined(HAVE__GET_CPUID)
+	__get_cpuid_count(7, 0, &exx[0], &exx[1], &exx[2], &exx[3]);
+#elif defined(HAVE__CPUID)
+	__cpuidex(exx, 7, 0);
+#else
+#error cpuid instruction not available
+#endif
+
+	if ((exx[2] & (1 << 14)) != 0)	/* avx512vpopcntdq */
+	{
+		/* Check that the OS has enabled support for the ZMM registers. */
+#ifdef _MSC_VER
+		return (_xgetbv(0) & 0xe0) != 0;
+#else
+		uint64		xcr = 0;
+		uint32		high;
+		uint32		low;
+
+__asm__ __volatile__(" xgetbv\n":"=a"(low), "=d"(high):"c"(xcr));
+		return (low & 0xe0) != 0;
+#endif
+	}
+
+	return false;
+}
-- 
2.25.1


--XsQoSWH+UP9D9v3l--





^ permalink  raw  reply  [nested|flat] 16+ messages in thread

* [PATCH v14 1/1] AVX512 popcount support
@ 2024-03-27 21:39 Nathan Bossart <[email protected]>
  0 siblings, 0 replies; 16+ messages in thread

From: Nathan Bossart @ 2024-03-27 21:39 UTC (permalink / raw)

---
 config/c-compiler.m4           |  34 +++++++
 configure                      | 165 +++++++++++++++++++++++++++++++++
 configure.ac                   |  34 +++++++
 meson.build                    |  59 ++++++++++++
 src/Makefile.global.in         |   1 +
 src/include/pg_config.h.in     |   9 ++
 src/include/port/pg_bitutils.h |  20 ++++
 src/makefiles/meson.build      |   1 +
 src/port/Makefile              |   6 ++
 src/port/meson.build           |   6 +-
 src/port/pg_bitutils.c         |  56 ++++-------
 src/port/pg_popcount_avx512.c  |  98 ++++++++++++++++++++
 12 files changed, 451 insertions(+), 38 deletions(-)
 create mode 100644 src/port/pg_popcount_avx512.c

diff --git a/config/c-compiler.m4 b/config/c-compiler.m4
index 3268a780bb..f881e7ec28 100644
--- a/config/c-compiler.m4
+++ b/config/c-compiler.m4
@@ -694,3 +694,37 @@ if test x"$Ac_cachevar" = x"yes"; then
 fi
 undefine([Ac_cachevar])dnl
 ])# PGAC_LOONGARCH_CRC32C_INTRINSICS
+
+# PGAC_AVX512_POPCNT_INTRINSICS
+# -----------------------------
+# Check if the compiler supports the AVX512 POPCNT instructions using the
+# _mm512_setzero_si512, _mm512_loadu_si512, _mm512_popcnt_epi64,
+# _mm512_add_epi64, and _mm512_reduce_add_epi64 intrinsic functions.
+#
+# An optional compiler flag can be passed as argument
+# (e.g., -mavx512vpopcntdq).  If the intrinsics are supported, sets
+# pgac_avx512_popcnt_intrinsics and CFLAGS_AVX512_POPCNT.
+AC_DEFUN([PGAC_AVX512_POPCNT_INTRINSICS],
+[define([Ac_cachevar], [AS_TR_SH([pgac_cv_avx512_popcnt_intrinsics_$1])])dnl
+AC_CACHE_CHECK([for _mm512_popcnt_epi64 with CFLAGS=$1], [Ac_cachevar],
+[pgac_save_CFLAGS=$CFLAGS
+CFLAGS="$pgac_save_CFLAGS $1"
+AC_LINK_IFELSE([AC_LANG_PROGRAM([#include <immintrin.h>],
+  [const char buf@<:@sizeof(__m512i)@:>@;
+   PG_INT64_TYPE popcnt = 0;
+   __m512i accum = _mm512_setzero_si512();
+   const __m512i val = _mm512_loadu_si512((const __m512i *) buf);
+   const __m512i cnt = _mm512_popcnt_epi64(val);
+   accum = _mm512_add_epi64(accum, cnt);
+   popcnt = _mm512_reduce_add_epi64(accum);
+   /* return computed value, to prevent the above being optimized away */
+   return popcnt == 0;])],
+  [Ac_cachevar=yes],
+  [Ac_cachevar=no])
+CFLAGS="$pgac_save_CFLAGS"])
+if test x"$Ac_cachevar" = x"yes"; then
+  CFLAGS_AVX512_POPCNT="$1"
+  pgac_avx512_popcnt_intrinsics=yes
+fi
+undefine([Ac_cachevar])dnl
+])# PGAC_AVX512_POPCNT_INTRINSICS
diff --git a/configure b/configure
index 36feeafbb2..189264b86e 100755
--- a/configure
+++ b/configure
@@ -647,6 +647,7 @@ MSGFMT_FLAGS
 MSGFMT
 PG_CRC32C_OBJS
 CFLAGS_CRC
+CFLAGS_AVX512_POPCNT
 LIBOBJS
 OPENSSL
 ZSTD
@@ -17404,6 +17405,41 @@ $as_echo "#define HAVE__GET_CPUID 1" >>confdefs.h
 
 fi
 
+# Check for x86 cpuid_count instruction
+{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for __get_cpuid_count" >&5
+$as_echo_n "checking for __get_cpuid_count... " >&6; }
+if ${pgac_cv__get_cpuid_count+:} 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_count(7, 0, &exx[0], &exx[1], &exx[2], &exx[3]);
+
+  ;
+  return 0;
+}
+_ACEOF
+if ac_fn_c_try_link "$LINENO"; then :
+  pgac_cv__get_cpuid_count="yes"
+else
+  pgac_cv__get_cpuid_count="no"
+fi
+rm -f core conftest.err conftest.$ac_objext \
+    conftest$ac_exeext conftest.$ac_ext
+fi
+{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $pgac_cv__get_cpuid_count" >&5
+$as_echo "$pgac_cv__get_cpuid_count" >&6; }
+if test x"$pgac_cv__get_cpuid_count" = x"yes"; then
+
+$as_echo "#define HAVE__GET_CPUID_COUNT 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 :
@@ -17438,6 +17474,135 @@ $as_echo "#define HAVE__CPUID 1" >>confdefs.h
 
 fi
 
+{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for __cpuidex" >&5
+$as_echo_n "checking for __cpuidex... " >&6; }
+if ${pgac_cv__cpuidex+:} 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_cpuidex(exx[0], 7, 0);
+
+  ;
+  return 0;
+}
+_ACEOF
+if ac_fn_c_try_link "$LINENO"; then :
+  pgac_cv__cpuidex="yes"
+else
+  pgac_cv__cpuidex="no"
+fi
+rm -f core conftest.err conftest.$ac_objext \
+    conftest$ac_exeext conftest.$ac_ext
+fi
+{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $pgac_cv__cpuidex" >&5
+$as_echo "$pgac_cv__cpuidex" >&6; }
+if test x"$pgac_cv__cpuidex" = x"yes"; then
+
+$as_echo "#define HAVE__CPUIDEX 1" >>confdefs.h
+
+fi
+
+# Check for AVX512 popcount intrinsics
+#
+{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for _mm512_popcnt_epi64 with CFLAGS=" >&5
+$as_echo_n "checking for _mm512_popcnt_epi64 with CFLAGS=... " >&6; }
+if ${pgac_cv_avx512_popcnt_intrinsics_+:} false; then :
+  $as_echo_n "(cached) " >&6
+else
+  pgac_save_CFLAGS=$CFLAGS
+CFLAGS="$pgac_save_CFLAGS "
+cat confdefs.h - <<_ACEOF >conftest.$ac_ext
+/* end confdefs.h.  */
+#include <immintrin.h>
+int
+main ()
+{
+const char buf[sizeof(__m512i)];
+   PG_INT64_TYPE popcnt = 0;
+   __m512i accum = _mm512_setzero_si512();
+   const __m512i val = _mm512_loadu_si512((const __m512i *) buf);
+   const __m512i cnt = _mm512_popcnt_epi64(val);
+   accum = _mm512_add_epi64(accum, cnt);
+   popcnt = _mm512_reduce_add_epi64(accum);
+   /* return computed value, to prevent the above being optimized away */
+   return popcnt == 0;
+  ;
+  return 0;
+}
+_ACEOF
+if ac_fn_c_try_link "$LINENO"; then :
+  pgac_cv_avx512_popcnt_intrinsics_=yes
+else
+  pgac_cv_avx512_popcnt_intrinsics_=no
+fi
+rm -f core conftest.err conftest.$ac_objext \
+    conftest$ac_exeext conftest.$ac_ext
+CFLAGS="$pgac_save_CFLAGS"
+fi
+{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $pgac_cv_avx512_popcnt_intrinsics_" >&5
+$as_echo "$pgac_cv_avx512_popcnt_intrinsics_" >&6; }
+if test x"$pgac_cv_avx512_popcnt_intrinsics_" = x"yes"; then
+  CFLAGS_AVX512_POPCNT=""
+  pgac_avx512_popcnt_intrinsics=yes
+fi
+
+if test x"$pgac_avx512_popcnt_intrinsics" != x"yes"; then
+  { $as_echo "$as_me:${as_lineno-$LINENO}: checking for _mm512_popcnt_epi64 with CFLAGS=-mavx512vpopcntdq" >&5
+$as_echo_n "checking for _mm512_popcnt_epi64 with CFLAGS=-mavx512vpopcntdq... " >&6; }
+if ${pgac_cv_avx512_popcnt_intrinsics__mavx512vpopcntdq+:} false; then :
+  $as_echo_n "(cached) " >&6
+else
+  pgac_save_CFLAGS=$CFLAGS
+CFLAGS="$pgac_save_CFLAGS -mavx512vpopcntdq"
+cat confdefs.h - <<_ACEOF >conftest.$ac_ext
+/* end confdefs.h.  */
+#include <immintrin.h>
+int
+main ()
+{
+const char buf[sizeof(__m512i)];
+   PG_INT64_TYPE popcnt = 0;
+   __m512i accum = _mm512_setzero_si512();
+   const __m512i val = _mm512_loadu_si512((const __m512i *) buf);
+   const __m512i cnt = _mm512_popcnt_epi64(val);
+   accum = _mm512_add_epi64(accum, cnt);
+   popcnt = _mm512_reduce_add_epi64(accum);
+   /* return computed value, to prevent the above being optimized away */
+   return popcnt == 0;
+  ;
+  return 0;
+}
+_ACEOF
+if ac_fn_c_try_link "$LINENO"; then :
+  pgac_cv_avx512_popcnt_intrinsics__mavx512vpopcntdq=yes
+else
+  pgac_cv_avx512_popcnt_intrinsics__mavx512vpopcntdq=no
+fi
+rm -f core conftest.err conftest.$ac_objext \
+    conftest$ac_exeext conftest.$ac_ext
+CFLAGS="$pgac_save_CFLAGS"
+fi
+{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $pgac_cv_avx512_popcnt_intrinsics__mavx512vpopcntdq" >&5
+$as_echo "$pgac_cv_avx512_popcnt_intrinsics__mavx512vpopcntdq" >&6; }
+if test x"$pgac_cv_avx512_popcnt_intrinsics__mavx512vpopcntdq" = x"yes"; then
+  CFLAGS_AVX512_POPCNT="-mavx512vpopcntdq"
+  pgac_avx512_popcnt_intrinsics=yes
+fi
+
+fi
+if test x"$pgac_avx512_popcnt_intrinsics" = x"yes"; then
+
+$as_echo "#define USE_AVX512_POPCNT_WITH_RUNTIME_CHECK 1" >>confdefs.h
+
+fi
+
+
 # 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
diff --git a/configure.ac b/configure.ac
index 57f734879e..ced39c9055 100644
--- a/configure.ac
+++ b/configure.ac
@@ -2052,6 +2052,18 @@ 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
 
+# Check for x86 cpuid_count instruction
+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"$pgac_cv__get_cpuid_count" = x"yes"; then
+  AC_DEFINE(HAVE__GET_CPUID_COUNT, 1, [Define to 1 if you have __get_cpuid_count.])
+fi
+
 AC_CACHE_CHECK([for __cpuid], [pgac_cv__cpuid],
 [AC_LINK_IFELSE([AC_LANG_PROGRAM([#include <intrin.h>],
   [[unsigned int exx[4] = {0, 0, 0, 0};
@@ -2063,6 +2075,28 @@ if test x"$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"$pgac_cv__cpuidex" = x"yes"; then
+  AC_DEFINE(HAVE__CPUIDEX, 1, [Define to 1 if you have __cpuidex.])
+fi
+
+# Check for AVX512 popcount intrinsics
+#
+PGAC_AVX512_POPCNT_INTRINSICS([])
+if test x"$pgac_avx512_popcnt_intrinsics" != x"yes"; then
+  PGAC_AVX512_POPCNT_INTRINSICS([-mavx512vpopcntdq])
+fi
+if test x"$pgac_avx512_popcnt_intrinsics" = x"yes"; then
+  AC_DEFINE(USE_AVX512_POPCNT_WITH_RUNTIME_CHECK, 1, [Define to 1 to use AVX512 popcount instructions with a runtime check.])
+fi
+AC_SUBST(CFLAGS_AVX512_POPCNT)
+
 # 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
diff --git a/meson.build b/meson.build
index 18b5be842e..2399b90d6e 100644
--- a/meson.build
+++ b/meson.build
@@ -1783,6 +1783,30 @@ elif cc.links('''
 endif
 
 
+# Check for __get_cpuid_count() and __cpuidex() in a similar fashion.
+if cc.links('''
+    #include <cpuid.h>
+    int main(int arg, char **argv)
+    {
+        unsigned int exx[4] = {0, 0, 0, 0};
+        __get_cpuid_count(7, &exx[0], &exx[1], &exx[2], &exx[3]);
+    }
+    ''', name: '__get_cpuid_count',
+    args: test_c_args)
+  cdata.set('HAVE__GET_CPUID_COUNT', 1)
+elif cc.links('''
+    #include <intrin.h>
+    int main(int arg, char **argv)
+    {
+        unsigned int exx[4] = {0, 0, 0, 0};
+        __cpuidex(exx, 7, 0);
+    }
+    ''', name: '__cpuidex',
+    args: test_c_args)
+  cdata.set('HAVE__CPUIDEX', 1)
+endif
+
+
 # Defend against clang being used on x86-32 without SSE2 enabled.  As current
 # versions of clang do not understand -fexcess-precision=standard, the use of
 # x87 floating point operations leads to problems like isinf possibly returning
@@ -1996,6 +2020,41 @@ int main(void)
 endif
 
 
+###############################################################
+# Check for the availability of AVX512 popcount intrinsics.
+###############################################################
+
+cflags_avx512_popcnt = []
+if host_cpu == 'x86' or host_cpu == 'x86_64'
+
+  prog = '''
+#include <immintrin.h>
+
+int main(void)
+{
+    const char buf[sizeof(__m512i)];
+    INT64 popcnt = 0;
+    __m512i accum = _mm512_setzero_si512();
+    const __m512i val = _mm512_loadu_si512((const __m512i *) buf);
+    const __m512i cnt = _mm512_popcnt_epi64(val);
+    accum = _mm512_add_epi64(accum, cnt);
+    popcnt = _mm512_reduce_add_epi64(accum);
+    /* return computed value, to prevent the above being optimized away */
+    return popcnt == 0;
+}
+'''
+
+  if cc.links(prog, name: 'AVX512 popcount without -mavx512vpopcntdq',
+        args: test_c_args + ['-DINT64=@0@'.format(cdata.get('PG_INT64_TYPE'))])
+    cdata.set('USE_AVX512_POPCNT_WITH_RUNTIME_CHECK', 1)
+  elif cc.links(prog, name: 'AVX512 popcount with -mavx512vpopcntdq',
+        args: test_c_args + ['-DINT64=@0@'.format(cdata.get('PG_INT64_TYPE'))] + ['-mavx512vpopcntdq'])
+    cdata.set('USE_AVX512_POPCNT_WITH_RUNTIME_CHECK', 1)
+    cflags_avx512_popcnt += '-mavx512vpopcntdq'
+  endif
+
+endif
+
 
 ###############################################################
 # Select CRC-32C implementation.
diff --git a/src/Makefile.global.in b/src/Makefile.global.in
index 8b3f8c24e0..a6c0c4a692 100644
--- a/src/Makefile.global.in
+++ b/src/Makefile.global.in
@@ -262,6 +262,7 @@ CFLAGS_SL_MODULE = @CFLAGS_SL_MODULE@
 CXXFLAGS_SL_MODULE = @CXXFLAGS_SL_MODULE@
 CFLAGS_UNROLL_LOOPS = @CFLAGS_UNROLL_LOOPS@
 CFLAGS_VECTORIZE = @CFLAGS_VECTORIZE@
+CFLAGS_AVX512_POPCNT = @CFLAGS_AVX512_POPCNT@
 CFLAGS_CRC = @CFLAGS_CRC@
 PERMIT_DECLARATION_AFTER_STATEMENT = @PERMIT_DECLARATION_AFTER_STATEMENT@
 CXXFLAGS = @CXXFLAGS@
diff --git a/src/include/pg_config.h.in b/src/include/pg_config.h.in
index 591e1ca3df..133d8ba071 100644
--- a/src/include/pg_config.h.in
+++ b/src/include/pg_config.h.in
@@ -555,9 +555,15 @@
 /* Define to 1 if you have __cpuid. */
 #undef HAVE__CPUID
 
+/* Define to 1 if you have __cpuidex. */
+#undef HAVE__CPUIDEX
+
 /* Define to 1 if you have __get_cpuid. */
 #undef HAVE__GET_CPUID
 
+/* Define to 1 if you have __get_cpuid_count. */
+#undef HAVE__GET_CPUID_COUNT
+
 /* Define to 1 if your compiler understands _Static_assert. */
 #undef HAVE__STATIC_ASSERT
 
@@ -680,6 +686,9 @@
 /* Define to 1 to build with assertion checks. (--enable-cassert) */
 #undef USE_ASSERT_CHECKING
 
+/* Define to 1 to use AVX512 popcount instructions with a runtime check. */
+#undef USE_AVX512_POPCNT_WITH_RUNTIME_CHECK
+
 /* Define to 1 to build with Bonjour support. (--with-bonjour) */
 #undef USE_BONJOUR
 
diff --git a/src/include/port/pg_bitutils.h b/src/include/port/pg_bitutils.h
index 53e5239717..c69a85e08e 100644
--- a/src/include/port/pg_bitutils.h
+++ b/src/include/port/pg_bitutils.h
@@ -298,12 +298,32 @@ pg_ceil_log2_64(uint64 num)
 #endif
 #endif
 
+/*
+ * We can also try to use the AVX512 popcount instruction on some systems.
+ * The implementation of that is located in its own file because it may
+ * require special compiler flags that we don't want to apply to any other
+ * files.
+ *
+ * NB: We assume that there's no hope of AVX512 popcount support if the "fast"
+ * implementations aren't available.
+ */
+#if defined(TRY_POPCNT_FAST) && defined(USE_AVX512_POPCNT_WITH_RUNTIME_CHECK)
+#if defined(HAVE__GET_CPUID_COUNT) || defined(HAVE__CPUIDEX)
+#define TRY_POPCNT_AVX512 1
+extern bool pg_popcount_avx512_available(void);
+extern uint64 pg_popcount_avx512(const char *buf, int bytes);
+#endif
+#endif
+
 #ifdef TRY_POPCNT_FAST
 /* Attempt to use the POPCNT instruction, but perform a runtime check first */
 extern PGDLLIMPORT int (*pg_popcount32) (uint32 word);
 extern PGDLLIMPORT int (*pg_popcount64) (uint64 word);
 extern PGDLLIMPORT uint64 (*pg_popcount) (const char *buf, int bytes);
 
+/* Export pg_popcount_fast() for use in the AVX512 implementation. */
+extern uint64 pg_popcount_fast(const char *buf, int bytes);
+
 #else
 /* Use a portable implementation -- no need for a function pointer. */
 extern int	pg_popcount32(uint32 word);
diff --git a/src/makefiles/meson.build b/src/makefiles/meson.build
index b0f4178b3d..c2345cc95f 100644
--- a/src/makefiles/meson.build
+++ b/src/makefiles/meson.build
@@ -99,6 +99,7 @@ pgxs_kv = {
   'PERMIT_DECLARATION_AFTER_STATEMENT':
     ' '.join(cflags_no_decl_after_statement),
 
+  'CFLAGS_AVX512_POPCNT': ' '.join(cflags_avx512_popcnt),
   'CFLAGS_CRC': ' '.join(cflags_crc),
   'CFLAGS_UNROLL_LOOPS': ' '.join(unroll_loops_cflags),
   'CFLAGS_VECTORIZE': ' '.join(vectorize_cflags),
diff --git a/src/port/Makefile b/src/port/Makefile
index dcc8737e68..fd2c59aec6 100644
--- a/src/port/Makefile
+++ b/src/port/Makefile
@@ -44,6 +44,7 @@ OBJS = \
 	noblock.o \
 	path.o \
 	pg_bitutils.o \
+	pg_popcount_avx512.o \
 	pg_strong_random.o \
 	pgcheckdir.o \
 	pgmkdirp.o \
@@ -92,6 +93,11 @@ pg_crc32c_armv8.o: CFLAGS+=$(CFLAGS_CRC)
 pg_crc32c_armv8_shlib.o: CFLAGS+=$(CFLAGS_CRC)
 pg_crc32c_armv8_srv.o: CFLAGS+=$(CFLAGS_CRC)
 
+# all versions of pg_popcount_avx512.o need CFLAGS_AVX512_POPCNT
+pg_popcount_avx512.o: CFLAGS+=$(CFLAGS_AVX512_POPCNT)
+pg_popcount_avx512_shlib.o: CFLAGS+=$(CFLAGS_AVX512_POPCNT)
+pg_popcount_avx512_srv.o: CFLAGS+=$(CFLAGS_AVX512_POPCNT)
+
 #
 # Shared library versions of object files
 #
diff --git a/src/port/meson.build b/src/port/meson.build
index 92b593e6ef..4e69fe8e91 100644
--- a/src/port/meson.build
+++ b/src/port/meson.build
@@ -7,6 +7,7 @@ pgport_sources = [
   'noblock.c',
   'path.c',
   'pg_bitutils.c',
+  'pg_popcount_avx512.c',
   'pg_strong_random.c',
   'pgcheckdir.c',
   'pgmkdirp.c',
@@ -84,6 +85,7 @@ replace_funcs_pos = [
   ['pg_crc32c_sse42', 'USE_SSE42_CRC32C_WITH_RUNTIME_CHECK', 'crc'],
   ['pg_crc32c_sse42_choose', 'USE_SSE42_CRC32C_WITH_RUNTIME_CHECK'],
   ['pg_crc32c_sb8', 'USE_SSE42_CRC32C_WITH_RUNTIME_CHECK'],
+  ['pg_popcount_avx512', 'USE_AVX512_POPCNT_WITH_RUNTIME_CHECK', 'avx512_popcnt'],
 
   # arm / aarch64
   ['pg_crc32c_armv8', 'USE_ARMV8_CRC32C'],
@@ -98,8 +100,8 @@ replace_funcs_pos = [
   ['pg_crc32c_sb8', 'USE_SLICING_BY_8_CRC32C'],
 ]
 
-pgport_cflags = {'crc': cflags_crc}
-pgport_sources_cflags = {'crc': []}
+pgport_cflags = {'crc': cflags_crc, 'avx512_popcnt': cflags_avx512_popcnt}
+pgport_sources_cflags = {'crc': [], 'avx512_popcnt': []}
 
 foreach f : replace_funcs_neg
   func = f.get(0)
diff --git a/src/port/pg_bitutils.c b/src/port/pg_bitutils.c
index 1197696e97..61cd049553 100644
--- a/src/port/pg_bitutils.c
+++ b/src/port/pg_bitutils.c
@@ -114,7 +114,6 @@ static int	pg_popcount64_choose(uint64 word);
 static uint64 pg_popcount_choose(const char *buf, int bytes);
 static inline int pg_popcount32_fast(uint32 word);
 static inline int pg_popcount64_fast(uint64 word);
-static uint64 pg_popcount_fast(const char *buf, int bytes);
 
 int			(*pg_popcount32) (uint32 word) = pg_popcount32_choose;
 int			(*pg_popcount64) (uint64 word) = pg_popcount64_choose;
@@ -142,20 +141,18 @@ pg_popcount_available(void)
 	return (exx[2] & (1 << 23)) != 0;	/* POPCNT */
 }
 
-/*
- * These functions get called on the first call to pg_popcount32 etc.
- * They detect whether we can use the asm implementations, and replace
- * the function pointers so that subsequent calls are routed directly to
- * the chosen implementation.
- */
-static int
-pg_popcount32_choose(uint32 word)
+static inline void
+choose_popcount_functions(void)
 {
 	if (pg_popcount_available())
 	{
 		pg_popcount32 = pg_popcount32_fast;
 		pg_popcount64 = pg_popcount64_fast;
 		pg_popcount = pg_popcount_fast;
+#ifdef TRY_POPCNT_AVX512
+		if (pg_popcount_avx512_available())
+			pg_popcount = pg_popcount_avx512;
+#endif
 	}
 	else
 	{
@@ -163,45 +160,32 @@ pg_popcount32_choose(uint32 word)
 		pg_popcount64 = pg_popcount64_slow;
 		pg_popcount = pg_popcount_slow;
 	}
+}
 
+/*
+ * These functions get called on the first call to pg_popcount32 etc.
+ * They detect whether we can use the asm implementations, and replace
+ * the function pointers so that subsequent calls are routed directly to
+ * the chosen implementation.
+ */
+static int
+pg_popcount32_choose(uint32 word)
+{
+	choose_popcount_functions();
 	return pg_popcount32(word);
 }
 
 static int
 pg_popcount64_choose(uint64 word)
 {
-	if (pg_popcount_available())
-	{
-		pg_popcount32 = pg_popcount32_fast;
-		pg_popcount64 = pg_popcount64_fast;
-		pg_popcount = pg_popcount_fast;
-	}
-	else
-	{
-		pg_popcount32 = pg_popcount32_slow;
-		pg_popcount64 = pg_popcount64_slow;
-		pg_popcount = pg_popcount_slow;
-	}
-
+	choose_popcount_functions();
 	return pg_popcount64(word);
 }
 
 static uint64
 pg_popcount_choose(const char *buf, int bytes)
 {
-	if (pg_popcount_available())
-	{
-		pg_popcount32 = pg_popcount32_fast;
-		pg_popcount64 = pg_popcount64_fast;
-		pg_popcount = pg_popcount_fast;
-	}
-	else
-	{
-		pg_popcount32 = pg_popcount32_slow;
-		pg_popcount64 = pg_popcount64_slow;
-		pg_popcount = pg_popcount_slow;
-	}
-
+	choose_popcount_functions();
 	return pg_popcount(buf, bytes);
 }
 
@@ -243,7 +227,7 @@ __asm__ __volatile__(" popcntq %1,%0\n":"=q"(res):"rm"(word):"cc");
  * pg_popcount_fast
  *		Returns the number of 1-bits in buf
  */
-static uint64
+uint64
 pg_popcount_fast(const char *buf, int bytes)
 {
 	uint64		popcnt = 0;
diff --git a/src/port/pg_popcount_avx512.c b/src/port/pg_popcount_avx512.c
new file mode 100644
index 0000000000..66ca92c029
--- /dev/null
+++ b/src/port/pg_popcount_avx512.c
@@ -0,0 +1,98 @@
+/*-------------------------------------------------------------------------
+ *
+ * pg_popcount_avx512.c
+ *	  Holds the pg_popcount() implementation that uses AVX512 instructions.
+ *
+ * Copyright (c) 2019-2024, PostgreSQL Global Development Group
+ *
+ * IDENTIFICATION
+ *	  src/port/pg_popcount_avx512.c
+ *
+ *-------------------------------------------------------------------------
+ */
+#include "c.h"
+
+#ifdef HAVE__GET_CPUID_COUNT
+#include <cpuid.h>
+#endif
+
+#ifdef USE_AVX512_POPCNT_WITH_RUNTIME_CHECK
+#include <immintrin.h>
+#endif
+
+#ifdef HAVE__CPUIDEX
+#include <intrin.h>
+#endif
+
+#include "port/pg_bitutils.h"
+
+/*
+ * XXX: Someday we should figure out how to determine whether this file needs
+ * to compiled at configure-time instead of relying on macros that are
+ * determined at compile-time.
+ */
+#ifdef TRY_POPCNT_AVX512
+
+/*
+ * Return true if CPUID indicates that the AVX512 POPCNT instruction is
+ * available.
+ */
+bool
+pg_popcount_avx512_available(void)
+{
+	unsigned int exx[4] = {0, 0, 0, 0};
+
+#if defined(HAVE__GET_CPUID_COUNT)
+	__get_cpuid_count(7, 0, &exx[0], &exx[1], &exx[2], &exx[3]);
+#elif defined(HAVE__CPUIDEX)
+	__cpuidex(exx, 7, 0);
+#else
+#error cpuid instruction not available
+#endif
+
+	if ((exx[1] & (1 << 16)) != 0 &&	/* avx512f */
+		(exx[2] & (1 << 14)) != 0)	/* avx512vpopcntdq */
+	{
+		/*
+		 * We also need to check that the OS has enabled support for the ZMM
+		 * registers.
+		 */
+#ifdef _MSC_VER
+		return (_xgetbv(0) & 0xe0) != 0;
+#else
+		uint64		xcr = 0;
+		uint32		high;
+		uint32		low;
+
+__asm__ __volatile__(" xgetbv\n":"=a"(low), "=d"(high):"c"(xcr));
+		return (low & 0xe0) != 0;
+#endif
+	}
+
+	return false;
+}
+
+/*
+ * pg_popcount_avx512
+ *		Returns the number of 1-bits in buf
+ */
+uint64
+pg_popcount_avx512(const char *buf, int bytes)
+{
+	uint64		popcnt;
+	__m512i		accum = _mm512_setzero_si512();
+
+	for (; bytes >= sizeof(__m512i); bytes -= sizeof(__m512i))
+	{
+		const		__m512i val = _mm512_loadu_si512((const __m512i *) buf);
+		const		__m512i cnt = _mm512_popcnt_epi64(val);
+
+		accum = _mm512_add_epi64(accum, cnt);
+		buf += sizeof(__m512i);
+	}
+
+	popcnt = _mm512_reduce_add_epi64(accum);
+	return popcnt + pg_popcount_fast(buf, bytes);
+}
+
+#endif							/* TRY_POPCNT_AVX512 */
-- 
2.25.1


--WIyZ46R2i8wDzkSu--





^ permalink  raw  reply  [nested|flat] 16+ messages in thread

* [PATCH v27 1/2] AVX512 popcount support
@ 2024-03-27 21:39 Nathan Bossart <[email protected]>
  0 siblings, 0 replies; 16+ messages in thread

From: Nathan Bossart @ 2024-03-27 21:39 UTC (permalink / raw)

---
 config/c-compiler.m4                 |  58 ++++++
 configure                            | 252 +++++++++++++++++++++++++++
 configure.ac                         |  51 ++++++
 meson.build                          |  87 +++++++++
 src/Makefile.global.in               |   5 +
 src/include/pg_config.h.in           |  12 ++
 src/include/port/pg_bitutils.h       |  11 ++
 src/makefiles/meson.build            |   4 +-
 src/port/Makefile                    |  11 ++
 src/port/meson.build                 |   6 +-
 src/port/pg_bitutils.c               |   5 +
 src/port/pg_popcount_avx512.c        |  82 +++++++++
 src/port/pg_popcount_avx512_choose.c |  81 +++++++++
 src/test/regress/expected/bit.out    |  24 +++
 src/test/regress/sql/bit.sql         |   4 +
 15 files changed, 690 insertions(+), 3 deletions(-)
 create mode 100644 src/port/pg_popcount_avx512.c
 create mode 100644 src/port/pg_popcount_avx512_choose.c

diff --git a/config/c-compiler.m4 b/config/c-compiler.m4
index 3268a780bb..892b3c9580 100644
--- a/config/c-compiler.m4
+++ b/config/c-compiler.m4
@@ -694,3 +694,61 @@ if test x"$Ac_cachevar" = x"yes"; then
 fi
 undefine([Ac_cachevar])dnl
 ])# PGAC_LOONGARCH_CRC32C_INTRINSICS
+
+# PGAC_XSAVE_INTRINSICS
+# ---------------------
+# Check if the compiler supports the XSAVE instructions using the _xgetbv
+# intrinsic function.
+#
+# An optional compiler flag can be passed as argument (e.g., -mxsave).  If the
+# intrinsic is supported, sets pgac_xsave_intrinsics and CFLAGS_XSAVE.
+AC_DEFUN([PGAC_XSAVE_INTRINSICS],
+[define([Ac_cachevar], [AS_TR_SH([pgac_cv_xsave_intrinsics_$1])])dnl
+AC_CACHE_CHECK([for _xgetbv with CFLAGS=$1], [Ac_cachevar],
+[pgac_save_CFLAGS=$CFLAGS
+CFLAGS="$pgac_save_CFLAGS $1"
+AC_LINK_IFELSE([AC_LANG_PROGRAM([#include <immintrin.h>],
+  [return _xgetbv(0) & 0xe0;])],
+  [Ac_cachevar=yes],
+  [Ac_cachevar=no])
+CFLAGS="$pgac_save_CFLAGS"])
+if test x"$Ac_cachevar" = x"yes"; then
+  CFLAGS_XSAVE="$1"
+  pgac_xsave_intrinsics=yes
+fi
+undefine([Ac_cachevar])dnl
+])# PGAC_XSAVE_INTRINSICS
+
+# PGAC_AVX512_POPCNT_INTRINSICS
+# -----------------------------
+# Check if the compiler supports the AVX512 POPCNT instructions using the
+# _mm512_setzero_si512, _mm512_maskz_loadu_epi8, _mm512_popcnt_epi64,
+# _mm512_add_epi64, and _mm512_reduce_add_epi64 intrinsic functions.
+#
+# Optional compiler flags can be passed as argument (e.g., -mavx512vpopcntdq
+# -mavx512bw).  If the intrinsics are supported, sets
+# pgac_avx512_popcnt_intrinsics and CFLAGS_POPCNT.
+AC_DEFUN([PGAC_AVX512_POPCNT_INTRINSICS],
+[define([Ac_cachevar], [AS_TR_SH([pgac_cv_avx512_popcnt_intrinsics_$1])])dnl
+AC_CACHE_CHECK([for _mm512_popcnt_epi64 with CFLAGS=$1], [Ac_cachevar],
+[pgac_save_CFLAGS=$CFLAGS
+CFLAGS="$pgac_save_CFLAGS $1"
+AC_LINK_IFELSE([AC_LANG_PROGRAM([#include <immintrin.h>],
+  [const char buf@<:@sizeof(__m512i)@:>@;
+   PG_INT64_TYPE popcnt = 0;
+   __m512i accum = _mm512_setzero_si512();
+   const __m512i val = _mm512_maskz_loadu_epi8((__mmask64) 0xf0f0f0f0f0f0f0f0, (const __m512i *) buf);
+   const __m512i cnt = _mm512_popcnt_epi64(val);
+   accum = _mm512_add_epi64(accum, cnt);
+   popcnt = _mm512_reduce_add_epi64(accum);
+   /* return computed value, to prevent the above being optimized away */
+   return popcnt == 0;])],
+  [Ac_cachevar=yes],
+  [Ac_cachevar=no])
+CFLAGS="$pgac_save_CFLAGS"])
+if test x"$Ac_cachevar" = x"yes"; then
+  CFLAGS_POPCNT="$1"
+  pgac_avx512_popcnt_intrinsics=yes
+fi
+undefine([Ac_cachevar])dnl
+])# PGAC_AVX512_POPCNT_INTRINSICS
diff --git a/configure b/configure
index 36feeafbb2..72d20d3945 100755
--- a/configure
+++ b/configure
@@ -647,6 +647,9 @@ MSGFMT_FLAGS
 MSGFMT
 PG_CRC32C_OBJS
 CFLAGS_CRC
+PG_POPCNT_OBJS
+CFLAGS_POPCNT
+CFLAGS_XSAVE
 LIBOBJS
 OPENSSL
 ZSTD
@@ -17404,6 +17407,40 @@ $as_echo "#define HAVE__GET_CPUID 1" >>confdefs.h
 
 fi
 
+{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for __get_cpuid_count" >&5
+$as_echo_n "checking for __get_cpuid_count... " >&6; }
+if ${pgac_cv__get_cpuid_count+:} 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_count(7, 0, &exx[0], &exx[1], &exx[2], &exx[3]);
+
+  ;
+  return 0;
+}
+_ACEOF
+if ac_fn_c_try_link "$LINENO"; then :
+  pgac_cv__get_cpuid_count="yes"
+else
+  pgac_cv__get_cpuid_count="no"
+fi
+rm -f core conftest.err conftest.$ac_objext \
+    conftest$ac_exeext conftest.$ac_ext
+fi
+{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $pgac_cv__get_cpuid_count" >&5
+$as_echo "$pgac_cv__get_cpuid_count" >&6; }
+if test x"$pgac_cv__get_cpuid_count" = x"yes"; then
+
+$as_echo "#define HAVE__GET_CPUID_COUNT 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 :
@@ -17438,6 +17475,221 @@ $as_echo "#define HAVE__CPUID 1" >>confdefs.h
 
 fi
 
+{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for __cpuidex" >&5
+$as_echo_n "checking for __cpuidex... " >&6; }
+if ${pgac_cv__cpuidex+:} 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_cpuidex(exx[0], 7, 0);
+
+  ;
+  return 0;
+}
+_ACEOF
+if ac_fn_c_try_link "$LINENO"; then :
+  pgac_cv__cpuidex="yes"
+else
+  pgac_cv__cpuidex="no"
+fi
+rm -f core conftest.err conftest.$ac_objext \
+    conftest$ac_exeext conftest.$ac_ext
+fi
+{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $pgac_cv__cpuidex" >&5
+$as_echo "$pgac_cv__cpuidex" >&6; }
+if test x"$pgac_cv__cpuidex" = x"yes"; then
+
+$as_echo "#define HAVE__CPUIDEX 1" >>confdefs.h
+
+fi
+
+# Check for XSAVE intrinsics
+#
+CFLAGS_XSAVE=""
+{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for _xgetbv with CFLAGS=" >&5
+$as_echo_n "checking for _xgetbv with CFLAGS=... " >&6; }
+if ${pgac_cv_xsave_intrinsics_+:} false; then :
+  $as_echo_n "(cached) " >&6
+else
+  pgac_save_CFLAGS=$CFLAGS
+CFLAGS="$pgac_save_CFLAGS "
+cat confdefs.h - <<_ACEOF >conftest.$ac_ext
+/* end confdefs.h.  */
+#include <immintrin.h>
+int
+main ()
+{
+return _xgetbv(0) & 0xe0;
+  ;
+  return 0;
+}
+_ACEOF
+if ac_fn_c_try_link "$LINENO"; then :
+  pgac_cv_xsave_intrinsics_=yes
+else
+  pgac_cv_xsave_intrinsics_=no
+fi
+rm -f core conftest.err conftest.$ac_objext \
+    conftest$ac_exeext conftest.$ac_ext
+CFLAGS="$pgac_save_CFLAGS"
+fi
+{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $pgac_cv_xsave_intrinsics_" >&5
+$as_echo "$pgac_cv_xsave_intrinsics_" >&6; }
+if test x"$pgac_cv_xsave_intrinsics_" = x"yes"; then
+  CFLAGS_XSAVE=""
+  pgac_xsave_intrinsics=yes
+fi
+
+if test x"$pgac_xsave_intrinsics" != x"yes"; then
+  { $as_echo "$as_me:${as_lineno-$LINENO}: checking for _xgetbv with CFLAGS=-mxsave" >&5
+$as_echo_n "checking for _xgetbv with CFLAGS=-mxsave... " >&6; }
+if ${pgac_cv_xsave_intrinsics__mxsave+:} false; then :
+  $as_echo_n "(cached) " >&6
+else
+  pgac_save_CFLAGS=$CFLAGS
+CFLAGS="$pgac_save_CFLAGS -mxsave"
+cat confdefs.h - <<_ACEOF >conftest.$ac_ext
+/* end confdefs.h.  */
+#include <immintrin.h>
+int
+main ()
+{
+return _xgetbv(0) & 0xe0;
+  ;
+  return 0;
+}
+_ACEOF
+if ac_fn_c_try_link "$LINENO"; then :
+  pgac_cv_xsave_intrinsics__mxsave=yes
+else
+  pgac_cv_xsave_intrinsics__mxsave=no
+fi
+rm -f core conftest.err conftest.$ac_objext \
+    conftest$ac_exeext conftest.$ac_ext
+CFLAGS="$pgac_save_CFLAGS"
+fi
+{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $pgac_cv_xsave_intrinsics__mxsave" >&5
+$as_echo "$pgac_cv_xsave_intrinsics__mxsave" >&6; }
+if test x"$pgac_cv_xsave_intrinsics__mxsave" = x"yes"; then
+  CFLAGS_XSAVE="-mxsave"
+  pgac_xsave_intrinsics=yes
+fi
+
+fi
+if test x"$pgac_xsave_intrinsics" = x"yes"; then
+
+$as_echo "#define HAVE_XSAVE_INTRINSICS 1" >>confdefs.h
+
+fi
+
+
+# Check for AVX512 popcount intrinsics
+#
+CFLAGS_POPCNT=""
+PG_POPCNT_OBJS=""
+if test x"$host_cpu" = x"x86_64"; then
+  { $as_echo "$as_me:${as_lineno-$LINENO}: checking for _mm512_popcnt_epi64 with CFLAGS=" >&5
+$as_echo_n "checking for _mm512_popcnt_epi64 with CFLAGS=... " >&6; }
+if ${pgac_cv_avx512_popcnt_intrinsics_+:} false; then :
+  $as_echo_n "(cached) " >&6
+else
+  pgac_save_CFLAGS=$CFLAGS
+CFLAGS="$pgac_save_CFLAGS "
+cat confdefs.h - <<_ACEOF >conftest.$ac_ext
+/* end confdefs.h.  */
+#include <immintrin.h>
+int
+main ()
+{
+const char buf[sizeof(__m512i)];
+   PG_INT64_TYPE popcnt = 0;
+   __m512i accum = _mm512_setzero_si512();
+   const __m512i val = _mm512_maskz_loadu_epi8((__mmask64) 0xf0f0f0f0f0f0f0f0, (const __m512i *) buf);
+   const __m512i cnt = _mm512_popcnt_epi64(val);
+   accum = _mm512_add_epi64(accum, cnt);
+   popcnt = _mm512_reduce_add_epi64(accum);
+   /* return computed value, to prevent the above being optimized away */
+   return popcnt == 0;
+  ;
+  return 0;
+}
+_ACEOF
+if ac_fn_c_try_link "$LINENO"; then :
+  pgac_cv_avx512_popcnt_intrinsics_=yes
+else
+  pgac_cv_avx512_popcnt_intrinsics_=no
+fi
+rm -f core conftest.err conftest.$ac_objext \
+    conftest$ac_exeext conftest.$ac_ext
+CFLAGS="$pgac_save_CFLAGS"
+fi
+{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $pgac_cv_avx512_popcnt_intrinsics_" >&5
+$as_echo "$pgac_cv_avx512_popcnt_intrinsics_" >&6; }
+if test x"$pgac_cv_avx512_popcnt_intrinsics_" = x"yes"; then
+  CFLAGS_POPCNT=""
+  pgac_avx512_popcnt_intrinsics=yes
+fi
+
+  if test x"$pgac_avx512_popcnt_intrinsics" != x"yes"; then
+    { $as_echo "$as_me:${as_lineno-$LINENO}: checking for _mm512_popcnt_epi64 with CFLAGS=-mavx512vpopcntdq -mavx512bw" >&5
+$as_echo_n "checking for _mm512_popcnt_epi64 with CFLAGS=-mavx512vpopcntdq -mavx512bw... " >&6; }
+if ${pgac_cv_avx512_popcnt_intrinsics__mavx512vpopcntdq__mavx512bw+:} false; then :
+  $as_echo_n "(cached) " >&6
+else
+  pgac_save_CFLAGS=$CFLAGS
+CFLAGS="$pgac_save_CFLAGS -mavx512vpopcntdq -mavx512bw"
+cat confdefs.h - <<_ACEOF >conftest.$ac_ext
+/* end confdefs.h.  */
+#include <immintrin.h>
+int
+main ()
+{
+const char buf[sizeof(__m512i)];
+   PG_INT64_TYPE popcnt = 0;
+   __m512i accum = _mm512_setzero_si512();
+   const __m512i val = _mm512_maskz_loadu_epi8((__mmask64) 0xf0f0f0f0f0f0f0f0, (const __m512i *) buf);
+   const __m512i cnt = _mm512_popcnt_epi64(val);
+   accum = _mm512_add_epi64(accum, cnt);
+   popcnt = _mm512_reduce_add_epi64(accum);
+   /* return computed value, to prevent the above being optimized away */
+   return popcnt == 0;
+  ;
+  return 0;
+}
+_ACEOF
+if ac_fn_c_try_link "$LINENO"; then :
+  pgac_cv_avx512_popcnt_intrinsics__mavx512vpopcntdq__mavx512bw=yes
+else
+  pgac_cv_avx512_popcnt_intrinsics__mavx512vpopcntdq__mavx512bw=no
+fi
+rm -f core conftest.err conftest.$ac_objext \
+    conftest$ac_exeext conftest.$ac_ext
+CFLAGS="$pgac_save_CFLAGS"
+fi
+{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $pgac_cv_avx512_popcnt_intrinsics__mavx512vpopcntdq__mavx512bw" >&5
+$as_echo "$pgac_cv_avx512_popcnt_intrinsics__mavx512vpopcntdq__mavx512bw" >&6; }
+if test x"$pgac_cv_avx512_popcnt_intrinsics__mavx512vpopcntdq__mavx512bw" = x"yes"; then
+  CFLAGS_POPCNT="-mavx512vpopcntdq -mavx512bw"
+  pgac_avx512_popcnt_intrinsics=yes
+fi
+
+  fi
+  if test x"$pgac_avx512_popcnt_intrinsics" = x"yes"; then
+    PG_POPCNT_OBJS="pg_popcount_avx512.o pg_popcount_avx512_choose.o"
+
+$as_echo "#define USE_AVX512_POPCNT_WITH_RUNTIME_CHECK 1" >>confdefs.h
+
+  fi
+fi
+
+
+
 # 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
diff --git a/configure.ac b/configure.ac
index 57f734879e..f35ce78a3c 100644
--- a/configure.ac
+++ b/configure.ac
@@ -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"$pgac_xsave_intrinsics" = x"yes"; then
+  AC_DEFINE(HAVE_XSAVE_INTRINSICS, 1, [Define to 1 if you have XSAVE intrinsics.])
+fi
+AC_SUBST(CFLAGS_XSAVE)
+
+# Check for AVX512 popcount intrinsics
+#
+CFLAGS_POPCNT=""
+PG_POPCNT_OBJS=""
+if test x"$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 AVX512 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
diff --git a/meson.build b/meson.build
index 87437960bc..498e39cd3a 100644
--- a/meson.build
+++ b/meson.build
@@ -1783,6 +1783,30 @@ elif cc.links('''
 endif
 
 
+# Check for __get_cpuid_count() and __cpuidex() in a similar fashion.
+if cc.links('''
+    #include <cpuid.h>
+    int main(int arg, char **argv)
+    {
+        unsigned int exx[4] = {0, 0, 0, 0};
+        __get_cpuid_count(7, 0, &exx[0], &exx[1], &exx[2], &exx[3]);
+    }
+    ''', name: '__get_cpuid_count',
+    args: test_c_args)
+  cdata.set('HAVE__GET_CPUID_COUNT', 1)
+elif cc.links('''
+    #include <intrin.h>
+    int main(int arg, char **argv)
+    {
+        unsigned int exx[4] = {0, 0, 0, 0};
+        __cpuidex(exx, 7, 0);
+    }
+    ''', name: '__cpuidex',
+    args: test_c_args)
+  cdata.set('HAVE__CPUIDEX', 1)
+endif
+
+
 # Defend against clang being used on x86-32 without SSE2 enabled.  As current
 # versions of clang do not understand -fexcess-precision=standard, the use of
 # x87 floating point operations leads to problems like isinf possibly returning
@@ -1996,6 +2020,69 @@ int main(void)
 endif
 
 
+###############################################################
+# Check for the availability of XSAVE intrinsics.
+###############################################################
+
+cflags_xsave = []
+if host_cpu == 'x86' or host_cpu == 'x86_64'
+
+  prog = '''
+#include <immintrin.h>
+
+int main(void)
+{
+    return _xgetbv(0) & 0xe0;
+}
+'''
+
+  if cc.links(prog, name: 'XSAVE intrinsics without -mxsave',
+        args: test_c_args)
+    cdata.set('HAVE_XSAVE_INTRINSICS', 1)
+  elif cc.links(prog, name: 'XSAVE intrinsics with -mxsave',
+        args: test_c_args + ['-mxsave'])
+    cdata.set('HAVE_XSAVE_INTRINSICS', 1)
+    cflags_xsave += '-mxsave'
+  endif
+
+endif
+
+
+###############################################################
+# Check for the availability of AVX512 popcount intrinsics.
+###############################################################
+
+cflags_popcnt = []
+if host_cpu == 'x86_64'
+
+  prog = '''
+#include <immintrin.h>
+
+int main(void)
+{
+    const char buf[sizeof(__m512i)];
+    INT64 popcnt = 0;
+    __m512i accum = _mm512_setzero_si512();
+    const __m512i val = _mm512_maskz_loadu_epi8((__mmask64) 0xf0f0f0f0f0f0f0f0, (const __m512i *) buf);
+    const __m512i cnt = _mm512_popcnt_epi64(val);
+    accum = _mm512_add_epi64(accum, cnt);
+    popcnt = _mm512_reduce_add_epi64(accum);
+    /* return computed value, to prevent the above being optimized away */
+    return popcnt == 0;
+}
+'''
+
+  if cc.links(prog, name: 'AVX512 popcount without -mavx512vpopcntdq -mavx512bw',
+        args: test_c_args + ['-DINT64=@0@'.format(cdata.get('PG_INT64_TYPE'))])
+    cdata.set('USE_AVX512_POPCNT_WITH_RUNTIME_CHECK', 1)
+  elif cc.links(prog, name: 'AVX512 popcount with -mavx512vpopcntdq -mavx512bw',
+        args: test_c_args + ['-DINT64=@0@'.format(cdata.get('PG_INT64_TYPE'))] + ['-mavx512vpopcntdq'] + ['-mavx512bw'])
+    cdata.set('USE_AVX512_POPCNT_WITH_RUNTIME_CHECK', 1)
+    cflags_popcnt += ['-mavx512vpopcntdq'] + ['-mavx512bw']
+  endif
+
+endif
+
 
 ###############################################################
 # Select CRC-32C implementation.
diff --git a/src/Makefile.global.in b/src/Makefile.global.in
index 8b3f8c24e0..36d880d225 100644
--- a/src/Makefile.global.in
+++ b/src/Makefile.global.in
@@ -262,7 +262,9 @@ CFLAGS_SL_MODULE = @CFLAGS_SL_MODULE@
 CXXFLAGS_SL_MODULE = @CXXFLAGS_SL_MODULE@
 CFLAGS_UNROLL_LOOPS = @CFLAGS_UNROLL_LOOPS@
 CFLAGS_VECTORIZE = @CFLAGS_VECTORIZE@
+CFLAGS_POPCNT = @CFLAGS_POPCNT@
 CFLAGS_CRC = @CFLAGS_CRC@
+CFLAGS_XSAVE = @CFLAGS_XSAVE@
 PERMIT_DECLARATION_AFTER_STATEMENT = @PERMIT_DECLARATION_AFTER_STATEMENT@
 CXXFLAGS = @CXXFLAGS@
 
@@ -758,6 +760,9 @@ LIBOBJS = @LIBOBJS@
 # files needed for the chosen CRC-32C implementation
 PG_CRC32C_OBJS = @PG_CRC32C_OBJS@
 
+# files needed for the chosen popcount implementation
+PG_POPCNT_OBJS = @PG_POPCNT_OBJS@
+
 LIBS := -lpgcommon -lpgport $(LIBS)
 
 # to make ws2_32.lib the last library
diff --git a/src/include/pg_config.h.in b/src/include/pg_config.h.in
index 591e1ca3df..de067e6182 100644
--- a/src/include/pg_config.h.in
+++ b/src/include/pg_config.h.in
@@ -513,6 +513,9 @@
 /* Define to 1 if the assembler supports X86_64's POPCNTQ instruction. */
 #undef HAVE_X86_64_POPCNTQ
 
+/* Define to 1 if you have XSAVE intrinsics. */
+#undef HAVE_XSAVE_INTRINSICS
+
 /* Define to 1 if the system has the type `_Bool'. */
 #undef HAVE__BOOL
 
@@ -555,9 +558,15 @@
 /* Define to 1 if you have __cpuid. */
 #undef HAVE__CPUID
 
+/* Define to 1 if you have __cpuidex. */
+#undef HAVE__CPUIDEX
+
 /* Define to 1 if you have __get_cpuid. */
 #undef HAVE__GET_CPUID
 
+/* Define to 1 if you have __get_cpuid_count. */
+#undef HAVE__GET_CPUID_COUNT
+
 /* Define to 1 if your compiler understands _Static_assert. */
 #undef HAVE__STATIC_ASSERT
 
@@ -680,6 +689,9 @@
 /* Define to 1 to build with assertion checks. (--enable-cassert) */
 #undef USE_ASSERT_CHECKING
 
+/* Define to 1 to use AVX512 popcount instructions with a runtime check. */
+#undef USE_AVX512_POPCNT_WITH_RUNTIME_CHECK
+
 /* Define to 1 to build with Bonjour support. (--with-bonjour) */
 #undef USE_BONJOUR
 
diff --git a/src/include/port/pg_bitutils.h b/src/include/port/pg_bitutils.h
index de480da71e..1512be1e4a 100644
--- a/src/include/port/pg_bitutils.h
+++ b/src/include/port/pg_bitutils.h
@@ -304,6 +304,17 @@ extern PGDLLIMPORT int (*pg_popcount32) (uint32 word);
 extern PGDLLIMPORT int (*pg_popcount64) (uint64 word);
 extern PGDLLIMPORT uint64 (*pg_popcount_optimized) (const char *buf, int bytes);
 
+/*
+ * We can also try to use the AVX512 popcount instruction on some systems.
+ * The implementation of that is located in its own file because it may
+ * require special compiler flags that we don't want to apply to any other
+ * files.
+ */
+#ifdef USE_AVX512_POPCNT_WITH_RUNTIME_CHECK
+extern bool pg_popcount_avx512_available(void);
+extern uint64 pg_popcount_avx512(const char *buf, int bytes);
+#endif
+
 #else
 /* Use a portable implementation -- no need for a function pointer. */
 extern int	pg_popcount32(uint32 word);
diff --git a/src/makefiles/meson.build b/src/makefiles/meson.build
index b0f4178b3d..5618050b30 100644
--- a/src/makefiles/meson.build
+++ b/src/makefiles/meson.build
@@ -100,8 +100,10 @@ pgxs_kv = {
     ' '.join(cflags_no_decl_after_statement),
 
   'CFLAGS_CRC': ' '.join(cflags_crc),
+  'CFLAGS_POPCNT': ' '.join(cflags_popcnt),
   'CFLAGS_UNROLL_LOOPS': ' '.join(unroll_loops_cflags),
   'CFLAGS_VECTORIZE': ' '.join(vectorize_cflags),
+  'CFLAGS_XSAVE': ' '.join(cflags_xsave),
 
   'LDFLAGS': var_ldflags,
   'LDFLAGS_EX': var_ldflags_ex,
@@ -177,7 +179,7 @@ pgxs_empty = [
   'WANTED_LANGUAGES',
 
   # Not needed because we don't build the server / PLs with the generated makefile
-  'LIBOBJS', 'PG_CRC32C_OBJS', 'TAS',
+  'LIBOBJS', 'PG_CRC32C_OBJS', 'PG_POPCNT_OBJS', 'TAS',
   'DTRACEFLAGS', # only server has dtrace probes
 
   'perl_archlibexp', 'perl_embed_ccflags', 'perl_embed_ldflags', 'perl_includespec', 'perl_privlibexp',
diff --git a/src/port/Makefile b/src/port/Makefile
index dcc8737e68..db7c02117b 100644
--- a/src/port/Makefile
+++ b/src/port/Makefile
@@ -38,6 +38,7 @@ LIBS += $(PTHREAD_LIBS)
 OBJS = \
 	$(LIBOBJS) \
 	$(PG_CRC32C_OBJS) \
+	$(PG_POPCNT_OBJS) \
 	bsearch_arg.o \
 	chklocale.o \
 	inet_net_ntop.o \
@@ -92,6 +93,16 @@ pg_crc32c_armv8.o: CFLAGS+=$(CFLAGS_CRC)
 pg_crc32c_armv8_shlib.o: CFLAGS+=$(CFLAGS_CRC)
 pg_crc32c_armv8_srv.o: CFLAGS+=$(CFLAGS_CRC)
 
+# all versions of pg_popcount_avx512_choose.o need CFLAGS_XSAVE
+pg_popcount_avx512_choose.o: CFLAGS+=$(CFLAGS_XSAVE)
+pg_popcount_avx512_choose_shlib.o: CFLAGS+=$(CFLAGS_XSAVE)
+pg_popcount_avx512_choose_srv.o: CFLAGS+=$(CFLAGS_XSAVE)
+
+# all versions of pg_popcount_avx512.o need CFLAGS_POPCNT
+pg_popcount_avx512.o: CFLAGS+=$(CFLAGS_POPCNT)
+pg_popcount_avx512_shlib.o: CFLAGS+=$(CFLAGS_POPCNT)
+pg_popcount_avx512_srv.o: CFLAGS+=$(CFLAGS_POPCNT)
+
 #
 # Shared library versions of object files
 #
diff --git a/src/port/meson.build b/src/port/meson.build
index 92b593e6ef..fd9ee199d1 100644
--- a/src/port/meson.build
+++ b/src/port/meson.build
@@ -84,6 +84,8 @@ replace_funcs_pos = [
   ['pg_crc32c_sse42', 'USE_SSE42_CRC32C_WITH_RUNTIME_CHECK', 'crc'],
   ['pg_crc32c_sse42_choose', 'USE_SSE42_CRC32C_WITH_RUNTIME_CHECK'],
   ['pg_crc32c_sb8', 'USE_SSE42_CRC32C_WITH_RUNTIME_CHECK'],
+  ['pg_popcount_avx512', 'USE_AVX512_POPCNT_WITH_RUNTIME_CHECK', 'popcnt'],
+  ['pg_popcount_avx512_choose', 'USE_AVX512_POPCNT_WITH_RUNTIME_CHECK', 'xsave'],
 
   # arm / aarch64
   ['pg_crc32c_armv8', 'USE_ARMV8_CRC32C'],
@@ -98,8 +100,8 @@ replace_funcs_pos = [
   ['pg_crc32c_sb8', 'USE_SLICING_BY_8_CRC32C'],
 ]
 
-pgport_cflags = {'crc': cflags_crc}
-pgport_sources_cflags = {'crc': []}
+pgport_cflags = {'crc': cflags_crc, 'popcnt': cflags_popcnt, 'xsave': cflags_xsave}
+pgport_sources_cflags = {'crc': [], 'popcnt': [], 'xsave': []}
 
 foreach f : replace_funcs_neg
   func = f.get(0)
diff --git a/src/port/pg_bitutils.c b/src/port/pg_bitutils.c
index 6271acea60..411be90f73 100644
--- a/src/port/pg_bitutils.c
+++ b/src/port/pg_bitutils.c
@@ -163,6 +163,11 @@ choose_popcount_functions(void)
 		pg_popcount64 = pg_popcount64_slow;
 		pg_popcount_optimized = pg_popcount_slow;
 	}
+
+#ifdef USE_AVX512_POPCNT_WITH_RUNTIME_CHECK
+	if (pg_popcount_avx512_available())
+		pg_popcount_optimized = pg_popcount_avx512;
+#endif
 }
 
 static int
diff --git a/src/port/pg_popcount_avx512.c b/src/port/pg_popcount_avx512.c
new file mode 100644
index 0000000000..03a5bfb137
--- /dev/null
+++ b/src/port/pg_popcount_avx512.c
@@ -0,0 +1,82 @@
+/*-------------------------------------------------------------------------
+ *
+ * pg_popcount_avx512.c
+ *	  Holds the pg_popcount() implementation that uses AVX512 instructions.
+ *
+ * Copyright (c) 2024, PostgreSQL Global Development Group
+ *
+ * IDENTIFICATION
+ *	  src/port/pg_popcount_avx512.c
+ *
+ *-------------------------------------------------------------------------
+ */
+#include "c.h"
+
+#include <immintrin.h>
+
+#include "port/pg_bitutils.h"
+
+/*
+ * It's probably unlikely that TRY_POPCNT_FAST won't be set if we are able to
+ * use AVX512 intrinsics, but we check it anyway to be sure.  We piggy-back on
+ * the function pointers that are only used when TRY_POPCNT_FAST is set.
+ */
+#ifdef TRY_POPCNT_FAST
+
+/*
+ * pg_popcount_avx512
+ *		Returns the number of 1-bits in buf
+ */
+uint64
+pg_popcount_avx512(const char *buf, int bytes)
+{
+	__m512i		val,
+				cnt;
+	__m512i		accum = _mm512_setzero_si512();
+	const char *final;
+	int			tail_idx;
+	__mmask64	mask = ~UINT64CONST(0);
+
+	/*
+	 * Align buffer down to avoid double load overhead from unaligned access.
+	 * Calculate a mask to ignore preceding bytes.  Find start offset of final
+	 * iteration and number of valid bytes making sure that final iteration is
+	 * not empty.
+	 */
+	mask <<= ((uintptr_t) buf) % sizeof(__m512i);
+	tail_idx = (((uintptr_t) buf + bytes - 1) % sizeof(__m512i)) + 1;
+	final = (const char *) TYPEALIGN_DOWN(sizeof(__m512i), buf + bytes - 1);
+	buf = (const char *) TYPEALIGN_DOWN(sizeof(__m512i), buf);
+
+	/*
+	 * Iterate through all but the final iteration.  Starting from second
+	 * iteration, the start index mask is ignored.
+	 */
+	if (buf < final)
+	{
+		val = _mm512_maskz_loadu_epi8(mask, (const __m512i *) buf);
+		cnt = _mm512_popcnt_epi64(val);
+		accum = _mm512_add_epi64(accum, cnt);
+
+		buf += sizeof(__m512i);
+		mask = ~UINT64CONST(0);
+
+		for (; buf < final; buf += sizeof(__m512i))
+		{
+			val = _mm512_load_si512((const __m512i *) buf);
+			cnt = _mm512_popcnt_epi64(val);
+			accum = _mm512_add_epi64(accum, cnt);
+		}
+	}
+
+	/* Final iteration needs to ignore bytes that are not within the length */
+	mask &= (~UINT64CONST(0) >> (sizeof(__m512i) - tail_idx));
+
+	val = _mm512_maskz_loadu_epi8(mask, (const __m512i *) buf);
+	cnt = _mm512_popcnt_epi64(val);
+	accum = _mm512_add_epi64(accum, cnt);
+
+	return _mm512_reduce_add_epi64(accum);
+}
+
+#endif							/* TRY_POPCNT_FAST */
diff --git a/src/port/pg_popcount_avx512_choose.c b/src/port/pg_popcount_avx512_choose.c
new file mode 100644
index 0000000000..4b0f1dc546
--- /dev/null
+++ b/src/port/pg_popcount_avx512_choose.c
@@ -0,0 +1,81 @@
+/*-------------------------------------------------------------------------
+ *
+ * pg_popcount_avx512_choose.c
+ *    Test whether we can use AVX512 POPCNT instructions.
+ *
+ * Copyright (c) 2024, PostgreSQL Global Development Group
+ *
+ * IDENTIFICATION
+ *    src/port/pg_popcount_avx512_choose.c
+ *
+ *-------------------------------------------------------------------------
+ */
+#include "c.h"
+
+#if defined(HAVE__GET_CPUID) || defined(HAVE__GET_CPUID_COUNT)
+#include <cpuid.h>
+#endif
+
+#ifdef HAVE_XSAVE_INTRINSICS
+#include <immintrin.h>
+#endif
+
+#if defined(HAVE__CPUID) || defined(HAVE__CPUIDEX)
+#include <intrin.h>
+#endif
+
+#include "port/pg_bitutils.h"
+
+/*
+ * It's probably unlikely that TRY_POPCNT_FAST won't be set if we are able to
+ * use AVX512 intrinsics, but we check it anyway to be sure.  We piggy-back on
+ * the function pointers that are only used when TRY_POPCNT_FAST is set.
+ */
+#ifdef TRY_POPCNT_FAST
+
+/*
+ * Returns true if the CPU supports AVX512 POPCNT.
+ */
+bool
+pg_popcount_avx512_available(void)
+{
+	unsigned int exx[4] = {0, 0, 0, 0};
+
+	/* does CPUID say there's support for AVX512 POPCNT? */
+#if defined(HAVE__GET_CPUID_COUNT)
+	__get_cpuid_count(7, 0, &exx[0], &exx[1], &exx[2], &exx[3]);
+#elif defined(HAVE__CPUIDEX)
+	__cpuidex(exx, 7, 0);
+#endif
+	if ((exx[2] & (1 << 14)) == 0)	/* avx512-vpopcntdq */
+		return false;
+
+	/* does CPUID say there's support for AVX512-BW? */
+	memset(exx, 0, sizeof(exx));
+#if defined(HAVE__GET_CPUID_COUNT)
+	__get_cpuid_count(7, 0, &exx[0], &exx[1], &exx[2], &exx[3]);
+#elif defined(HAVE__CPUIDEX)
+	__cpuidex(exx, 7, 0);
+#endif
+	if ((exx[1] & (1 << 30)) == 0)	/* avx512-bw */
+		return false;
+
+	/* does CPUID say there's support for XGETBV? */
+	memset(exx, 0, sizeof(exx));
+#if defined(HAVE__GET_CPUID)
+	__get_cpuid(1, &exx[0], &exx[1], &exx[2], &exx[3]);
+#elif defined(HAVE__CPUID)
+	__cpuid(exx, 1);
+#endif
+	if ((exx[2] & (1 << 26)) == 0)	/* xsave */
+		return false;
+
+	/* does XGETBV say the ZMM registers are enabled? */
+#ifdef HAVE_XSAVE_INTRINSICS
+	return (_xgetbv(0) & 0xe0) != 0;
+#else
+	return false;
+#endif
+}
+
+#endif							/* TRY_POPCNT_FAST */
diff --git a/src/test/regress/expected/bit.out b/src/test/regress/expected/bit.out
index e17cbf42ca..6a436288bb 100644
--- a/src/test/regress/expected/bit.out
+++ b/src/test/regress/expected/bit.out
@@ -740,6 +740,30 @@ SELECT bit_count(B'1111111111'::bit(10));
         10
 (1 row)
 
+SELECT bit_count(repeat('0', 100)::bit(100));
+ bit_count 
+-----------
+         0
+(1 row)
+
+SELECT bit_count(repeat('1', 100)::bit(100));
+ bit_count 
+-----------
+       100
+(1 row)
+
+SELECT bit_count(repeat('01', 500)::bit(1000));
+ bit_count 
+-----------
+       500
+(1 row)
+
+SELECT bit_count(repeat('10101', 200)::bit(1000));
+ bit_count 
+-----------
+       600
+(1 row)
+
 -- This table is intentionally left around to exercise pg_dump/pg_upgrade
 CREATE TABLE bit_defaults(
   b1 bit(4) DEFAULT '1001',
diff --git a/src/test/regress/sql/bit.sql b/src/test/regress/sql/bit.sql
index 34230b99fb..8ba6facd03 100644
--- a/src/test/regress/sql/bit.sql
+++ b/src/test/regress/sql/bit.sql
@@ -223,6 +223,10 @@ SELECT overlay(B'0101011100' placing '001' from 20);
 -- bit_count
 SELECT bit_count(B'0101011100'::bit(10));
 SELECT bit_count(B'1111111111'::bit(10));
+SELECT bit_count(repeat('0', 100)::bit(100));
+SELECT bit_count(repeat('1', 100)::bit(100));
+SELECT bit_count(repeat('01', 500)::bit(1000));
+SELECT bit_count(repeat('10101', 200)::bit(1000));
 
 -- This table is intentionally left around to exercise pg_dump/pg_upgrade
 CREATE TABLE bit_defaults(
-- 
2.25.1


--5vNYLRcllDrimb99
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v27-0002-optimize-visibilitymap_count-with-AVX512.patch"



^ permalink  raw  reply  [nested|flat] 16+ messages in thread

* [PATCH v26 1/2] AVX512 popcount support
@ 2024-03-27 21:39 Nathan Bossart <[email protected]>
  0 siblings, 0 replies; 16+ messages in thread

From: Nathan Bossart @ 2024-03-27 21:39 UTC (permalink / raw)

---
 config/c-compiler.m4                 |  58 ++++++
 configure                            | 252 +++++++++++++++++++++++++++
 configure.ac                         |  51 ++++++
 meson.build                          |  87 +++++++++
 src/Makefile.global.in               |   5 +
 src/include/pg_config.h.in           |  12 ++
 src/include/port/pg_bitutils.h       |  11 ++
 src/makefiles/meson.build            |   4 +-
 src/port/Makefile                    |  11 ++
 src/port/meson.build                 |   6 +-
 src/port/pg_bitutils.c               |   5 +
 src/port/pg_popcount_avx512.c        |  74 ++++++++
 src/port/pg_popcount_avx512_choose.c |  81 +++++++++
 src/test/regress/expected/bit.out    |  24 +++
 src/test/regress/sql/bit.sql         |   4 +
 15 files changed, 682 insertions(+), 3 deletions(-)
 create mode 100644 src/port/pg_popcount_avx512.c
 create mode 100644 src/port/pg_popcount_avx512_choose.c

diff --git a/config/c-compiler.m4 b/config/c-compiler.m4
index 3268a780bb..892b3c9580 100644
--- a/config/c-compiler.m4
+++ b/config/c-compiler.m4
@@ -694,3 +694,61 @@ if test x"$Ac_cachevar" = x"yes"; then
 fi
 undefine([Ac_cachevar])dnl
 ])# PGAC_LOONGARCH_CRC32C_INTRINSICS
+
+# PGAC_XSAVE_INTRINSICS
+# ---------------------
+# Check if the compiler supports the XSAVE instructions using the _xgetbv
+# intrinsic function.
+#
+# An optional compiler flag can be passed as argument (e.g., -mxsave).  If the
+# intrinsic is supported, sets pgac_xsave_intrinsics and CFLAGS_XSAVE.
+AC_DEFUN([PGAC_XSAVE_INTRINSICS],
+[define([Ac_cachevar], [AS_TR_SH([pgac_cv_xsave_intrinsics_$1])])dnl
+AC_CACHE_CHECK([for _xgetbv with CFLAGS=$1], [Ac_cachevar],
+[pgac_save_CFLAGS=$CFLAGS
+CFLAGS="$pgac_save_CFLAGS $1"
+AC_LINK_IFELSE([AC_LANG_PROGRAM([#include <immintrin.h>],
+  [return _xgetbv(0) & 0xe0;])],
+  [Ac_cachevar=yes],
+  [Ac_cachevar=no])
+CFLAGS="$pgac_save_CFLAGS"])
+if test x"$Ac_cachevar" = x"yes"; then
+  CFLAGS_XSAVE="$1"
+  pgac_xsave_intrinsics=yes
+fi
+undefine([Ac_cachevar])dnl
+])# PGAC_XSAVE_INTRINSICS
+
+# PGAC_AVX512_POPCNT_INTRINSICS
+# -----------------------------
+# Check if the compiler supports the AVX512 POPCNT instructions using the
+# _mm512_setzero_si512, _mm512_maskz_loadu_epi8, _mm512_popcnt_epi64,
+# _mm512_add_epi64, and _mm512_reduce_add_epi64 intrinsic functions.
+#
+# Optional compiler flags can be passed as argument (e.g., -mavx512vpopcntdq
+# -mavx512bw).  If the intrinsics are supported, sets
+# pgac_avx512_popcnt_intrinsics and CFLAGS_POPCNT.
+AC_DEFUN([PGAC_AVX512_POPCNT_INTRINSICS],
+[define([Ac_cachevar], [AS_TR_SH([pgac_cv_avx512_popcnt_intrinsics_$1])])dnl
+AC_CACHE_CHECK([for _mm512_popcnt_epi64 with CFLAGS=$1], [Ac_cachevar],
+[pgac_save_CFLAGS=$CFLAGS
+CFLAGS="$pgac_save_CFLAGS $1"
+AC_LINK_IFELSE([AC_LANG_PROGRAM([#include <immintrin.h>],
+  [const char buf@<:@sizeof(__m512i)@:>@;
+   PG_INT64_TYPE popcnt = 0;
+   __m512i accum = _mm512_setzero_si512();
+   const __m512i val = _mm512_maskz_loadu_epi8((__mmask64) 0xf0f0f0f0f0f0f0f0, (const __m512i *) buf);
+   const __m512i cnt = _mm512_popcnt_epi64(val);
+   accum = _mm512_add_epi64(accum, cnt);
+   popcnt = _mm512_reduce_add_epi64(accum);
+   /* return computed value, to prevent the above being optimized away */
+   return popcnt == 0;])],
+  [Ac_cachevar=yes],
+  [Ac_cachevar=no])
+CFLAGS="$pgac_save_CFLAGS"])
+if test x"$Ac_cachevar" = x"yes"; then
+  CFLAGS_POPCNT="$1"
+  pgac_avx512_popcnt_intrinsics=yes
+fi
+undefine([Ac_cachevar])dnl
+])# PGAC_AVX512_POPCNT_INTRINSICS
diff --git a/configure b/configure
index 36feeafbb2..72d20d3945 100755
--- a/configure
+++ b/configure
@@ -647,6 +647,9 @@ MSGFMT_FLAGS
 MSGFMT
 PG_CRC32C_OBJS
 CFLAGS_CRC
+PG_POPCNT_OBJS
+CFLAGS_POPCNT
+CFLAGS_XSAVE
 LIBOBJS
 OPENSSL
 ZSTD
@@ -17404,6 +17407,40 @@ $as_echo "#define HAVE__GET_CPUID 1" >>confdefs.h
 
 fi
 
+{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for __get_cpuid_count" >&5
+$as_echo_n "checking for __get_cpuid_count... " >&6; }
+if ${pgac_cv__get_cpuid_count+:} 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_count(7, 0, &exx[0], &exx[1], &exx[2], &exx[3]);
+
+  ;
+  return 0;
+}
+_ACEOF
+if ac_fn_c_try_link "$LINENO"; then :
+  pgac_cv__get_cpuid_count="yes"
+else
+  pgac_cv__get_cpuid_count="no"
+fi
+rm -f core conftest.err conftest.$ac_objext \
+    conftest$ac_exeext conftest.$ac_ext
+fi
+{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $pgac_cv__get_cpuid_count" >&5
+$as_echo "$pgac_cv__get_cpuid_count" >&6; }
+if test x"$pgac_cv__get_cpuid_count" = x"yes"; then
+
+$as_echo "#define HAVE__GET_CPUID_COUNT 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 :
@@ -17438,6 +17475,221 @@ $as_echo "#define HAVE__CPUID 1" >>confdefs.h
 
 fi
 
+{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for __cpuidex" >&5
+$as_echo_n "checking for __cpuidex... " >&6; }
+if ${pgac_cv__cpuidex+:} 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_cpuidex(exx[0], 7, 0);
+
+  ;
+  return 0;
+}
+_ACEOF
+if ac_fn_c_try_link "$LINENO"; then :
+  pgac_cv__cpuidex="yes"
+else
+  pgac_cv__cpuidex="no"
+fi
+rm -f core conftest.err conftest.$ac_objext \
+    conftest$ac_exeext conftest.$ac_ext
+fi
+{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $pgac_cv__cpuidex" >&5
+$as_echo "$pgac_cv__cpuidex" >&6; }
+if test x"$pgac_cv__cpuidex" = x"yes"; then
+
+$as_echo "#define HAVE__CPUIDEX 1" >>confdefs.h
+
+fi
+
+# Check for XSAVE intrinsics
+#
+CFLAGS_XSAVE=""
+{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for _xgetbv with CFLAGS=" >&5
+$as_echo_n "checking for _xgetbv with CFLAGS=... " >&6; }
+if ${pgac_cv_xsave_intrinsics_+:} false; then :
+  $as_echo_n "(cached) " >&6
+else
+  pgac_save_CFLAGS=$CFLAGS
+CFLAGS="$pgac_save_CFLAGS "
+cat confdefs.h - <<_ACEOF >conftest.$ac_ext
+/* end confdefs.h.  */
+#include <immintrin.h>
+int
+main ()
+{
+return _xgetbv(0) & 0xe0;
+  ;
+  return 0;
+}
+_ACEOF
+if ac_fn_c_try_link "$LINENO"; then :
+  pgac_cv_xsave_intrinsics_=yes
+else
+  pgac_cv_xsave_intrinsics_=no
+fi
+rm -f core conftest.err conftest.$ac_objext \
+    conftest$ac_exeext conftest.$ac_ext
+CFLAGS="$pgac_save_CFLAGS"
+fi
+{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $pgac_cv_xsave_intrinsics_" >&5
+$as_echo "$pgac_cv_xsave_intrinsics_" >&6; }
+if test x"$pgac_cv_xsave_intrinsics_" = x"yes"; then
+  CFLAGS_XSAVE=""
+  pgac_xsave_intrinsics=yes
+fi
+
+if test x"$pgac_xsave_intrinsics" != x"yes"; then
+  { $as_echo "$as_me:${as_lineno-$LINENO}: checking for _xgetbv with CFLAGS=-mxsave" >&5
+$as_echo_n "checking for _xgetbv with CFLAGS=-mxsave... " >&6; }
+if ${pgac_cv_xsave_intrinsics__mxsave+:} false; then :
+  $as_echo_n "(cached) " >&6
+else
+  pgac_save_CFLAGS=$CFLAGS
+CFLAGS="$pgac_save_CFLAGS -mxsave"
+cat confdefs.h - <<_ACEOF >conftest.$ac_ext
+/* end confdefs.h.  */
+#include <immintrin.h>
+int
+main ()
+{
+return _xgetbv(0) & 0xe0;
+  ;
+  return 0;
+}
+_ACEOF
+if ac_fn_c_try_link "$LINENO"; then :
+  pgac_cv_xsave_intrinsics__mxsave=yes
+else
+  pgac_cv_xsave_intrinsics__mxsave=no
+fi
+rm -f core conftest.err conftest.$ac_objext \
+    conftest$ac_exeext conftest.$ac_ext
+CFLAGS="$pgac_save_CFLAGS"
+fi
+{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $pgac_cv_xsave_intrinsics__mxsave" >&5
+$as_echo "$pgac_cv_xsave_intrinsics__mxsave" >&6; }
+if test x"$pgac_cv_xsave_intrinsics__mxsave" = x"yes"; then
+  CFLAGS_XSAVE="-mxsave"
+  pgac_xsave_intrinsics=yes
+fi
+
+fi
+if test x"$pgac_xsave_intrinsics" = x"yes"; then
+
+$as_echo "#define HAVE_XSAVE_INTRINSICS 1" >>confdefs.h
+
+fi
+
+
+# Check for AVX512 popcount intrinsics
+#
+CFLAGS_POPCNT=""
+PG_POPCNT_OBJS=""
+if test x"$host_cpu" = x"x86_64"; then
+  { $as_echo "$as_me:${as_lineno-$LINENO}: checking for _mm512_popcnt_epi64 with CFLAGS=" >&5
+$as_echo_n "checking for _mm512_popcnt_epi64 with CFLAGS=... " >&6; }
+if ${pgac_cv_avx512_popcnt_intrinsics_+:} false; then :
+  $as_echo_n "(cached) " >&6
+else
+  pgac_save_CFLAGS=$CFLAGS
+CFLAGS="$pgac_save_CFLAGS "
+cat confdefs.h - <<_ACEOF >conftest.$ac_ext
+/* end confdefs.h.  */
+#include <immintrin.h>
+int
+main ()
+{
+const char buf[sizeof(__m512i)];
+   PG_INT64_TYPE popcnt = 0;
+   __m512i accum = _mm512_setzero_si512();
+   const __m512i val = _mm512_maskz_loadu_epi8((__mmask64) 0xf0f0f0f0f0f0f0f0, (const __m512i *) buf);
+   const __m512i cnt = _mm512_popcnt_epi64(val);
+   accum = _mm512_add_epi64(accum, cnt);
+   popcnt = _mm512_reduce_add_epi64(accum);
+   /* return computed value, to prevent the above being optimized away */
+   return popcnt == 0;
+  ;
+  return 0;
+}
+_ACEOF
+if ac_fn_c_try_link "$LINENO"; then :
+  pgac_cv_avx512_popcnt_intrinsics_=yes
+else
+  pgac_cv_avx512_popcnt_intrinsics_=no
+fi
+rm -f core conftest.err conftest.$ac_objext \
+    conftest$ac_exeext conftest.$ac_ext
+CFLAGS="$pgac_save_CFLAGS"
+fi
+{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $pgac_cv_avx512_popcnt_intrinsics_" >&5
+$as_echo "$pgac_cv_avx512_popcnt_intrinsics_" >&6; }
+if test x"$pgac_cv_avx512_popcnt_intrinsics_" = x"yes"; then
+  CFLAGS_POPCNT=""
+  pgac_avx512_popcnt_intrinsics=yes
+fi
+
+  if test x"$pgac_avx512_popcnt_intrinsics" != x"yes"; then
+    { $as_echo "$as_me:${as_lineno-$LINENO}: checking for _mm512_popcnt_epi64 with CFLAGS=-mavx512vpopcntdq -mavx512bw" >&5
+$as_echo_n "checking for _mm512_popcnt_epi64 with CFLAGS=-mavx512vpopcntdq -mavx512bw... " >&6; }
+if ${pgac_cv_avx512_popcnt_intrinsics__mavx512vpopcntdq__mavx512bw+:} false; then :
+  $as_echo_n "(cached) " >&6
+else
+  pgac_save_CFLAGS=$CFLAGS
+CFLAGS="$pgac_save_CFLAGS -mavx512vpopcntdq -mavx512bw"
+cat confdefs.h - <<_ACEOF >conftest.$ac_ext
+/* end confdefs.h.  */
+#include <immintrin.h>
+int
+main ()
+{
+const char buf[sizeof(__m512i)];
+   PG_INT64_TYPE popcnt = 0;
+   __m512i accum = _mm512_setzero_si512();
+   const __m512i val = _mm512_maskz_loadu_epi8((__mmask64) 0xf0f0f0f0f0f0f0f0, (const __m512i *) buf);
+   const __m512i cnt = _mm512_popcnt_epi64(val);
+   accum = _mm512_add_epi64(accum, cnt);
+   popcnt = _mm512_reduce_add_epi64(accum);
+   /* return computed value, to prevent the above being optimized away */
+   return popcnt == 0;
+  ;
+  return 0;
+}
+_ACEOF
+if ac_fn_c_try_link "$LINENO"; then :
+  pgac_cv_avx512_popcnt_intrinsics__mavx512vpopcntdq__mavx512bw=yes
+else
+  pgac_cv_avx512_popcnt_intrinsics__mavx512vpopcntdq__mavx512bw=no
+fi
+rm -f core conftest.err conftest.$ac_objext \
+    conftest$ac_exeext conftest.$ac_ext
+CFLAGS="$pgac_save_CFLAGS"
+fi
+{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $pgac_cv_avx512_popcnt_intrinsics__mavx512vpopcntdq__mavx512bw" >&5
+$as_echo "$pgac_cv_avx512_popcnt_intrinsics__mavx512vpopcntdq__mavx512bw" >&6; }
+if test x"$pgac_cv_avx512_popcnt_intrinsics__mavx512vpopcntdq__mavx512bw" = x"yes"; then
+  CFLAGS_POPCNT="-mavx512vpopcntdq -mavx512bw"
+  pgac_avx512_popcnt_intrinsics=yes
+fi
+
+  fi
+  if test x"$pgac_avx512_popcnt_intrinsics" = x"yes"; then
+    PG_POPCNT_OBJS="pg_popcount_avx512.o pg_popcount_avx512_choose.o"
+
+$as_echo "#define USE_AVX512_POPCNT_WITH_RUNTIME_CHECK 1" >>confdefs.h
+
+  fi
+fi
+
+
+
 # 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
diff --git a/configure.ac b/configure.ac
index 57f734879e..f35ce78a3c 100644
--- a/configure.ac
+++ b/configure.ac
@@ -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"$pgac_xsave_intrinsics" = x"yes"; then
+  AC_DEFINE(HAVE_XSAVE_INTRINSICS, 1, [Define to 1 if you have XSAVE intrinsics.])
+fi
+AC_SUBST(CFLAGS_XSAVE)
+
+# Check for AVX512 popcount intrinsics
+#
+CFLAGS_POPCNT=""
+PG_POPCNT_OBJS=""
+if test x"$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 AVX512 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
diff --git a/meson.build b/meson.build
index 87437960bc..498e39cd3a 100644
--- a/meson.build
+++ b/meson.build
@@ -1783,6 +1783,30 @@ elif cc.links('''
 endif
 
 
+# Check for __get_cpuid_count() and __cpuidex() in a similar fashion.
+if cc.links('''
+    #include <cpuid.h>
+    int main(int arg, char **argv)
+    {
+        unsigned int exx[4] = {0, 0, 0, 0};
+        __get_cpuid_count(7, 0, &exx[0], &exx[1], &exx[2], &exx[3]);
+    }
+    ''', name: '__get_cpuid_count',
+    args: test_c_args)
+  cdata.set('HAVE__GET_CPUID_COUNT', 1)
+elif cc.links('''
+    #include <intrin.h>
+    int main(int arg, char **argv)
+    {
+        unsigned int exx[4] = {0, 0, 0, 0};
+        __cpuidex(exx, 7, 0);
+    }
+    ''', name: '__cpuidex',
+    args: test_c_args)
+  cdata.set('HAVE__CPUIDEX', 1)
+endif
+
+
 # Defend against clang being used on x86-32 without SSE2 enabled.  As current
 # versions of clang do not understand -fexcess-precision=standard, the use of
 # x87 floating point operations leads to problems like isinf possibly returning
@@ -1996,6 +2020,69 @@ int main(void)
 endif
 
 
+###############################################################
+# Check for the availability of XSAVE intrinsics.
+###############################################################
+
+cflags_xsave = []
+if host_cpu == 'x86' or host_cpu == 'x86_64'
+
+  prog = '''
+#include <immintrin.h>
+
+int main(void)
+{
+    return _xgetbv(0) & 0xe0;
+}
+'''
+
+  if cc.links(prog, name: 'XSAVE intrinsics without -mxsave',
+        args: test_c_args)
+    cdata.set('HAVE_XSAVE_INTRINSICS', 1)
+  elif cc.links(prog, name: 'XSAVE intrinsics with -mxsave',
+        args: test_c_args + ['-mxsave'])
+    cdata.set('HAVE_XSAVE_INTRINSICS', 1)
+    cflags_xsave += '-mxsave'
+  endif
+
+endif
+
+
+###############################################################
+# Check for the availability of AVX512 popcount intrinsics.
+###############################################################
+
+cflags_popcnt = []
+if host_cpu == 'x86_64'
+
+  prog = '''
+#include <immintrin.h>
+
+int main(void)
+{
+    const char buf[sizeof(__m512i)];
+    INT64 popcnt = 0;
+    __m512i accum = _mm512_setzero_si512();
+    const __m512i val = _mm512_maskz_loadu_epi8((__mmask64) 0xf0f0f0f0f0f0f0f0, (const __m512i *) buf);
+    const __m512i cnt = _mm512_popcnt_epi64(val);
+    accum = _mm512_add_epi64(accum, cnt);
+    popcnt = _mm512_reduce_add_epi64(accum);
+    /* return computed value, to prevent the above being optimized away */
+    return popcnt == 0;
+}
+'''
+
+  if cc.links(prog, name: 'AVX512 popcount without -mavx512vpopcntdq -mavx512bw',
+        args: test_c_args + ['-DINT64=@0@'.format(cdata.get('PG_INT64_TYPE'))])
+    cdata.set('USE_AVX512_POPCNT_WITH_RUNTIME_CHECK', 1)
+  elif cc.links(prog, name: 'AVX512 popcount with -mavx512vpopcntdq -mavx512bw',
+        args: test_c_args + ['-DINT64=@0@'.format(cdata.get('PG_INT64_TYPE'))] + ['-mavx512vpopcntdq'] + ['-mavx512bw'])
+    cdata.set('USE_AVX512_POPCNT_WITH_RUNTIME_CHECK', 1)
+    cflags_popcnt += ['-mavx512vpopcntdq'] + ['-mavx512bw']
+  endif
+
+endif
+
 
 ###############################################################
 # Select CRC-32C implementation.
diff --git a/src/Makefile.global.in b/src/Makefile.global.in
index 8b3f8c24e0..36d880d225 100644
--- a/src/Makefile.global.in
+++ b/src/Makefile.global.in
@@ -262,7 +262,9 @@ CFLAGS_SL_MODULE = @CFLAGS_SL_MODULE@
 CXXFLAGS_SL_MODULE = @CXXFLAGS_SL_MODULE@
 CFLAGS_UNROLL_LOOPS = @CFLAGS_UNROLL_LOOPS@
 CFLAGS_VECTORIZE = @CFLAGS_VECTORIZE@
+CFLAGS_POPCNT = @CFLAGS_POPCNT@
 CFLAGS_CRC = @CFLAGS_CRC@
+CFLAGS_XSAVE = @CFLAGS_XSAVE@
 PERMIT_DECLARATION_AFTER_STATEMENT = @PERMIT_DECLARATION_AFTER_STATEMENT@
 CXXFLAGS = @CXXFLAGS@
 
@@ -758,6 +760,9 @@ LIBOBJS = @LIBOBJS@
 # files needed for the chosen CRC-32C implementation
 PG_CRC32C_OBJS = @PG_CRC32C_OBJS@
 
+# files needed for the chosen popcount implementation
+PG_POPCNT_OBJS = @PG_POPCNT_OBJS@
+
 LIBS := -lpgcommon -lpgport $(LIBS)
 
 # to make ws2_32.lib the last library
diff --git a/src/include/pg_config.h.in b/src/include/pg_config.h.in
index 591e1ca3df..de067e6182 100644
--- a/src/include/pg_config.h.in
+++ b/src/include/pg_config.h.in
@@ -513,6 +513,9 @@
 /* Define to 1 if the assembler supports X86_64's POPCNTQ instruction. */
 #undef HAVE_X86_64_POPCNTQ
 
+/* Define to 1 if you have XSAVE intrinsics. */
+#undef HAVE_XSAVE_INTRINSICS
+
 /* Define to 1 if the system has the type `_Bool'. */
 #undef HAVE__BOOL
 
@@ -555,9 +558,15 @@
 /* Define to 1 if you have __cpuid. */
 #undef HAVE__CPUID
 
+/* Define to 1 if you have __cpuidex. */
+#undef HAVE__CPUIDEX
+
 /* Define to 1 if you have __get_cpuid. */
 #undef HAVE__GET_CPUID
 
+/* Define to 1 if you have __get_cpuid_count. */
+#undef HAVE__GET_CPUID_COUNT
+
 /* Define to 1 if your compiler understands _Static_assert. */
 #undef HAVE__STATIC_ASSERT
 
@@ -680,6 +689,9 @@
 /* Define to 1 to build with assertion checks. (--enable-cassert) */
 #undef USE_ASSERT_CHECKING
 
+/* Define to 1 to use AVX512 popcount instructions with a runtime check. */
+#undef USE_AVX512_POPCNT_WITH_RUNTIME_CHECK
+
 /* Define to 1 to build with Bonjour support. (--with-bonjour) */
 #undef USE_BONJOUR
 
diff --git a/src/include/port/pg_bitutils.h b/src/include/port/pg_bitutils.h
index de480da71e..1512be1e4a 100644
--- a/src/include/port/pg_bitutils.h
+++ b/src/include/port/pg_bitutils.h
@@ -304,6 +304,17 @@ extern PGDLLIMPORT int (*pg_popcount32) (uint32 word);
 extern PGDLLIMPORT int (*pg_popcount64) (uint64 word);
 extern PGDLLIMPORT uint64 (*pg_popcount_optimized) (const char *buf, int bytes);
 
+/*
+ * We can also try to use the AVX512 popcount instruction on some systems.
+ * The implementation of that is located in its own file because it may
+ * require special compiler flags that we don't want to apply to any other
+ * files.
+ */
+#ifdef USE_AVX512_POPCNT_WITH_RUNTIME_CHECK
+extern bool pg_popcount_avx512_available(void);
+extern uint64 pg_popcount_avx512(const char *buf, int bytes);
+#endif
+
 #else
 /* Use a portable implementation -- no need for a function pointer. */
 extern int	pg_popcount32(uint32 word);
diff --git a/src/makefiles/meson.build b/src/makefiles/meson.build
index b0f4178b3d..5618050b30 100644
--- a/src/makefiles/meson.build
+++ b/src/makefiles/meson.build
@@ -100,8 +100,10 @@ pgxs_kv = {
     ' '.join(cflags_no_decl_after_statement),
 
   'CFLAGS_CRC': ' '.join(cflags_crc),
+  'CFLAGS_POPCNT': ' '.join(cflags_popcnt),
   'CFLAGS_UNROLL_LOOPS': ' '.join(unroll_loops_cflags),
   'CFLAGS_VECTORIZE': ' '.join(vectorize_cflags),
+  'CFLAGS_XSAVE': ' '.join(cflags_xsave),
 
   'LDFLAGS': var_ldflags,
   'LDFLAGS_EX': var_ldflags_ex,
@@ -177,7 +179,7 @@ pgxs_empty = [
   'WANTED_LANGUAGES',
 
   # Not needed because we don't build the server / PLs with the generated makefile
-  'LIBOBJS', 'PG_CRC32C_OBJS', 'TAS',
+  'LIBOBJS', 'PG_CRC32C_OBJS', 'PG_POPCNT_OBJS', 'TAS',
   'DTRACEFLAGS', # only server has dtrace probes
 
   'perl_archlibexp', 'perl_embed_ccflags', 'perl_embed_ldflags', 'perl_includespec', 'perl_privlibexp',
diff --git a/src/port/Makefile b/src/port/Makefile
index dcc8737e68..db7c02117b 100644
--- a/src/port/Makefile
+++ b/src/port/Makefile
@@ -38,6 +38,7 @@ LIBS += $(PTHREAD_LIBS)
 OBJS = \
 	$(LIBOBJS) \
 	$(PG_CRC32C_OBJS) \
+	$(PG_POPCNT_OBJS) \
 	bsearch_arg.o \
 	chklocale.o \
 	inet_net_ntop.o \
@@ -92,6 +93,16 @@ pg_crc32c_armv8.o: CFLAGS+=$(CFLAGS_CRC)
 pg_crc32c_armv8_shlib.o: CFLAGS+=$(CFLAGS_CRC)
 pg_crc32c_armv8_srv.o: CFLAGS+=$(CFLAGS_CRC)
 
+# all versions of pg_popcount_avx512_choose.o need CFLAGS_XSAVE
+pg_popcount_avx512_choose.o: CFLAGS+=$(CFLAGS_XSAVE)
+pg_popcount_avx512_choose_shlib.o: CFLAGS+=$(CFLAGS_XSAVE)
+pg_popcount_avx512_choose_srv.o: CFLAGS+=$(CFLAGS_XSAVE)
+
+# all versions of pg_popcount_avx512.o need CFLAGS_POPCNT
+pg_popcount_avx512.o: CFLAGS+=$(CFLAGS_POPCNT)
+pg_popcount_avx512_shlib.o: CFLAGS+=$(CFLAGS_POPCNT)
+pg_popcount_avx512_srv.o: CFLAGS+=$(CFLAGS_POPCNT)
+
 #
 # Shared library versions of object files
 #
diff --git a/src/port/meson.build b/src/port/meson.build
index 92b593e6ef..fd9ee199d1 100644
--- a/src/port/meson.build
+++ b/src/port/meson.build
@@ -84,6 +84,8 @@ replace_funcs_pos = [
   ['pg_crc32c_sse42', 'USE_SSE42_CRC32C_WITH_RUNTIME_CHECK', 'crc'],
   ['pg_crc32c_sse42_choose', 'USE_SSE42_CRC32C_WITH_RUNTIME_CHECK'],
   ['pg_crc32c_sb8', 'USE_SSE42_CRC32C_WITH_RUNTIME_CHECK'],
+  ['pg_popcount_avx512', 'USE_AVX512_POPCNT_WITH_RUNTIME_CHECK', 'popcnt'],
+  ['pg_popcount_avx512_choose', 'USE_AVX512_POPCNT_WITH_RUNTIME_CHECK', 'xsave'],
 
   # arm / aarch64
   ['pg_crc32c_armv8', 'USE_ARMV8_CRC32C'],
@@ -98,8 +100,8 @@ replace_funcs_pos = [
   ['pg_crc32c_sb8', 'USE_SLICING_BY_8_CRC32C'],
 ]
 
-pgport_cflags = {'crc': cflags_crc}
-pgport_sources_cflags = {'crc': []}
+pgport_cflags = {'crc': cflags_crc, 'popcnt': cflags_popcnt, 'xsave': cflags_xsave}
+pgport_sources_cflags = {'crc': [], 'popcnt': [], 'xsave': []}
 
 foreach f : replace_funcs_neg
   func = f.get(0)
diff --git a/src/port/pg_bitutils.c b/src/port/pg_bitutils.c
index 6271acea60..411be90f73 100644
--- a/src/port/pg_bitutils.c
+++ b/src/port/pg_bitutils.c
@@ -163,6 +163,11 @@ choose_popcount_functions(void)
 		pg_popcount64 = pg_popcount64_slow;
 		pg_popcount_optimized = pg_popcount_slow;
 	}
+
+#ifdef USE_AVX512_POPCNT_WITH_RUNTIME_CHECK
+	if (pg_popcount_avx512_available())
+		pg_popcount_optimized = pg_popcount_avx512;
+#endif
 }
 
 static int
diff --git a/src/port/pg_popcount_avx512.c b/src/port/pg_popcount_avx512.c
new file mode 100644
index 0000000000..7c33c544e1
--- /dev/null
+++ b/src/port/pg_popcount_avx512.c
@@ -0,0 +1,74 @@
+/*-------------------------------------------------------------------------
+ *
+ * pg_popcount_avx512.c
+ *	  Holds the pg_popcount() implementation that uses AVX512 instructions.
+ *
+ * Copyright (c) 2024, PostgreSQL Global Development Group
+ *
+ * IDENTIFICATION
+ *	  src/port/pg_popcount_avx512.c
+ *
+ *-------------------------------------------------------------------------
+ */
+#include "c.h"
+
+#include <immintrin.h>
+
+#include "port/pg_bitutils.h"
+
+/*
+ * It's probably unlikely that TRY_POPCNT_FAST won't be set if we are able to
+ * use AVX512 intrinsics, but we check it anyway to be sure.  We piggy-back on
+ * the function pointers that are only used when TRY_POPCNT_FAST is set.
+ */
+#ifdef TRY_POPCNT_FAST
+
+/*
+ * pg_popcount_avx512
+ *		Returns the number of 1-bits in buf
+ */
+uint64
+pg_popcount_avx512(const char *buf, int bytes)
+{
+	__m512i		val,
+				cnt;
+	__m512i		accum = _mm512_setzero_si512();
+	const char *final;
+	int			tail_idx;
+	__mmask64	mask = ~UINT64CONST(0);
+
+	/*
+	 * Align buffer down to avoid double load overhead from unaligned access.
+	 * Calculate a mask to ignore preceding bytes.  Find start offset of final
+	 * iteration and number of valid bytes making sure that final iteration is
+	 * not empty.
+	 */
+	mask <<= ((uintptr_t) buf) % sizeof(__m512i);
+	tail_idx = (((uintptr_t) buf + bytes - 1) % sizeof(__m512i)) + 1;
+	final = (const char *) TYPEALIGN_DOWN(sizeof(__m512i), buf + bytes - 1);
+	buf = (const char *) TYPEALIGN_DOWN(sizeof(__m512i), buf);
+
+	/*
+	 * Iterate through all but the final iteration.  Starting from second
+	 * iteration, the start index mask is ignored.
+	 */
+	for (; buf < final; buf += sizeof(__m512i))
+	{
+		val = _mm512_maskz_loadu_epi8(mask, (const __m512i *) buf);
+		cnt = _mm512_popcnt_epi64(val);
+		accum = _mm512_add_epi64(accum, cnt);
+
+		mask = ~UINT64CONST(0);
+	}
+
+	/* Final iteration needs to ignore bytes that are not within the length */
+	mask &= (~UINT64CONST(0) >> (sizeof(__m512i) - tail_idx));
+
+	val = _mm512_maskz_loadu_epi8(mask, (const __m512i *) buf);
+	cnt = _mm512_popcnt_epi64(val);
+	accum = _mm512_add_epi64(accum, cnt);
+
+	return _mm512_reduce_add_epi64(accum);
+}
+
+#endif							/* TRY_POPCNT_FAST */
diff --git a/src/port/pg_popcount_avx512_choose.c b/src/port/pg_popcount_avx512_choose.c
new file mode 100644
index 0000000000..4b0f1dc546
--- /dev/null
+++ b/src/port/pg_popcount_avx512_choose.c
@@ -0,0 +1,81 @@
+/*-------------------------------------------------------------------------
+ *
+ * pg_popcount_avx512_choose.c
+ *    Test whether we can use AVX512 POPCNT instructions.
+ *
+ * Copyright (c) 2024, PostgreSQL Global Development Group
+ *
+ * IDENTIFICATION
+ *    src/port/pg_popcount_avx512_choose.c
+ *
+ *-------------------------------------------------------------------------
+ */
+#include "c.h"
+
+#if defined(HAVE__GET_CPUID) || defined(HAVE__GET_CPUID_COUNT)
+#include <cpuid.h>
+#endif
+
+#ifdef HAVE_XSAVE_INTRINSICS
+#include <immintrin.h>
+#endif
+
+#if defined(HAVE__CPUID) || defined(HAVE__CPUIDEX)
+#include <intrin.h>
+#endif
+
+#include "port/pg_bitutils.h"
+
+/*
+ * It's probably unlikely that TRY_POPCNT_FAST won't be set if we are able to
+ * use AVX512 intrinsics, but we check it anyway to be sure.  We piggy-back on
+ * the function pointers that are only used when TRY_POPCNT_FAST is set.
+ */
+#ifdef TRY_POPCNT_FAST
+
+/*
+ * Returns true if the CPU supports AVX512 POPCNT.
+ */
+bool
+pg_popcount_avx512_available(void)
+{
+	unsigned int exx[4] = {0, 0, 0, 0};
+
+	/* does CPUID say there's support for AVX512 POPCNT? */
+#if defined(HAVE__GET_CPUID_COUNT)
+	__get_cpuid_count(7, 0, &exx[0], &exx[1], &exx[2], &exx[3]);
+#elif defined(HAVE__CPUIDEX)
+	__cpuidex(exx, 7, 0);
+#endif
+	if ((exx[2] & (1 << 14)) == 0)	/* avx512-vpopcntdq */
+		return false;
+
+	/* does CPUID say there's support for AVX512-BW? */
+	memset(exx, 0, sizeof(exx));
+#if defined(HAVE__GET_CPUID_COUNT)
+	__get_cpuid_count(7, 0, &exx[0], &exx[1], &exx[2], &exx[3]);
+#elif defined(HAVE__CPUIDEX)
+	__cpuidex(exx, 7, 0);
+#endif
+	if ((exx[1] & (1 << 30)) == 0)	/* avx512-bw */
+		return false;
+
+	/* does CPUID say there's support for XGETBV? */
+	memset(exx, 0, sizeof(exx));
+#if defined(HAVE__GET_CPUID)
+	__get_cpuid(1, &exx[0], &exx[1], &exx[2], &exx[3]);
+#elif defined(HAVE__CPUID)
+	__cpuid(exx, 1);
+#endif
+	if ((exx[2] & (1 << 26)) == 0)	/* xsave */
+		return false;
+
+	/* does XGETBV say the ZMM registers are enabled? */
+#ifdef HAVE_XSAVE_INTRINSICS
+	return (_xgetbv(0) & 0xe0) != 0;
+#else
+	return false;
+#endif
+}
+
+#endif							/* TRY_POPCNT_FAST */
diff --git a/src/test/regress/expected/bit.out b/src/test/regress/expected/bit.out
index e17cbf42ca..6a436288bb 100644
--- a/src/test/regress/expected/bit.out
+++ b/src/test/regress/expected/bit.out
@@ -740,6 +740,30 @@ SELECT bit_count(B'1111111111'::bit(10));
         10
 (1 row)
 
+SELECT bit_count(repeat('0', 100)::bit(100));
+ bit_count 
+-----------
+         0
+(1 row)
+
+SELECT bit_count(repeat('1', 100)::bit(100));
+ bit_count 
+-----------
+       100
+(1 row)
+
+SELECT bit_count(repeat('01', 500)::bit(1000));
+ bit_count 
+-----------
+       500
+(1 row)
+
+SELECT bit_count(repeat('10101', 200)::bit(1000));
+ bit_count 
+-----------
+       600
+(1 row)
+
 -- This table is intentionally left around to exercise pg_dump/pg_upgrade
 CREATE TABLE bit_defaults(
   b1 bit(4) DEFAULT '1001',
diff --git a/src/test/regress/sql/bit.sql b/src/test/regress/sql/bit.sql
index 34230b99fb..8ba6facd03 100644
--- a/src/test/regress/sql/bit.sql
+++ b/src/test/regress/sql/bit.sql
@@ -223,6 +223,10 @@ SELECT overlay(B'0101011100' placing '001' from 20);
 -- bit_count
 SELECT bit_count(B'0101011100'::bit(10));
 SELECT bit_count(B'1111111111'::bit(10));
+SELECT bit_count(repeat('0', 100)::bit(100));
+SELECT bit_count(repeat('1', 100)::bit(100));
+SELECT bit_count(repeat('01', 500)::bit(1000));
+SELECT bit_count(repeat('10101', 200)::bit(1000));
 
 -- This table is intentionally left around to exercise pg_dump/pg_upgrade
 CREATE TABLE bit_defaults(
-- 
2.25.1


--W/nzBZO5zC0uMSeA
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v26-0002-optimize-visibilitymap_count-with-AVX512.patch"



^ permalink  raw  reply  [nested|flat] 16+ messages in thread