Here's a v17 of the patch.  This one has configure checks for everything
(i.e., CPUID, XGETBV, and the AVX512 intrinsics) as well as the relevant
runtime checks (i.e., we call CPUID to check for XGETBV and AVX512 POPCNT
availability, and we call XGETBV to ensure the ZMM registers are enabled).
I restricted the AVX512 configure checks to x86_64 since we know we won't
have TRY_POPCNT_FAST on 32-bit, and we rely on pg_popcount_fast() as our
fallback implementation in the AVX512 version.  Finally, I removed the
inline assembly in favor of using the _xgetbv() intrinsic on all systems.
It looks like that's available on gcc, clang, and msvc, although it
sometimes requires -mxsave, so that's applied to
pg_popcount_avx512_choose.o as needed.  I doubt this will lead to SIGILLs,
but it's admittedly a little shaky.

-- 
Nathan Bossart
Amazon Web Services: https://aws.amazon.com
>From a26b209927cc6b266b33f74fd734772eff87bff9 Mon Sep 17 00:00:00 2001
From: Nathan Bossart <nat...@postgresql.org>
Date: Wed, 27 Mar 2024 16:39:24 -0500
Subject: [PATCH v17 1/1] AVX512 popcount support

---
 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

Reply via email to