v8-0002-Feat-Add-AVX-512-POPCNT-support-initial-checkin.patch

From 67a887d8fe8be389c709fdc87b196cd2ad5d2bf7 Mon Sep 17 00:00:00 2001
From: Paul Amonson <paul.d.amonson@intel.com>
Date: Wed, 13 Mar 2024 12:49:57 -0700
Subject: [PATCH 2/2] [Feat] Add AVX-512 POPCNT support initial checkin.

Signed-off-by: Paul Amonson <paul.d.amonson@intel.com>
---
 config/c-compiler.m4              |  37 ++++++
 configure                         | 205 ++++++++++++++++++++++++++++++
 configure.ac                      |  44 +++++++
 meson.build                       |  72 +++++++++++
 src/Makefile.global.in            |   1 +
 src/include/pg_config.h.in        |  12 ++
 src/include/port/pg_bitutils.h    |  10 +-
 src/makefiles/meson.build         |   1 +
 src/port/Makefile                 |   5 +
 src/port/meson.build              |   6 +-
 src/port/pg_bitutils.c            |   9 +-
 src/port/pg_popcnt_choose.c       |  67 +++++++++-
 src/port/pg_popcnt_x86_64_accel.c |  36 +++++-
 13 files changed, 494 insertions(+), 11 deletions(-)

diff --git a/config/c-compiler.m4 b/config/c-compiler.m4
index 3268a780bb..54f7415e5a 100644
--- a/config/c-compiler.m4
+++ b/config/c-compiler.m4
@@ -694,3 +694,40 @@ 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 x86_64 AVX512 POPCNT instructions using
+# intrinsics used in CPUID features AVX512F and AVX512VPOPCNTDQ.
+#
+# Optional compiler flags can be passed as argument (e.g. -mavx512vpopcntdq).
+# If the intrinsics are supported then pgac_avx512_popcnt_intrinsics and
+# CFLAGS_AVX512_POPCNT are set.
+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 $1"
+AC_LINK_IFELSE([AC_LANG_PROGRAM([#include <immintrin.h>
+#include <stdint.h>
+#include <stdlib.h>
+#include <string.h>],
+  [const uint64_t *buf = malloc((size_t)64);
+   uint64_t popcnt = 0;
+   __m512i accumulator = _mm512_setzero_si512();
+   const __m512i v = _mm512_loadu_si512((const __m512i *)buf);
+   const __m512i p = _mm512_popcnt_epi64(v);
+   memset(buf, 0, 64);
+   accumulator = _mm512_add_epi64(accumulator, p);
+   popcnt = _mm512_reduce_add_epi64(accumulator);
+   /* return computed value, to prevent the above being optimized away */
+   return popcnt == 0;])],
+  [Ac_cachevar=yes],
+  [Ac_cachevar=no])
+CFLAGS="$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
\ No newline at end of file
diff --git a/configure b/configure
index 36feeafbb2..0fbfc7c78f 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 +17474,175 @@ $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
+
+{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for __immintrin" >&5
+$as_echo_n "checking for __immintrin... " >&6; }
+if ${pgac_cv__immintrin+:} false; then :
+  $as_echo_n "(cached) " >&6
+else
+  cat confdefs.h - <<_ACEOF >conftest.$ac_ext
+/* end confdefs.h.  */
+#include <immintrin.h>
+int
+main ()
+{
+/* Don't exclude code so added return. */
+    return 1701;
+
+  ;
+  return 0;
+}
+_ACEOF
+if ac_fn_c_try_link "$LINENO"; then :
+  pgac_cv__immintrin="yes"
+else
+  pgac_cv__immintrin="no"
+fi
+rm -f core conftest.err conftest.$ac_objext \
+    conftest$ac_exeext conftest.$ac_ext
+fi
+{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $pgac_cv__immintrin" >&5
+$as_echo "$pgac_cv__immintrin" >&6; }
+if test x"$pgac_cv__immintrin" = x"yes"; then
+
+$as_echo "#define HAVE__IMMINTRIN 1" >>confdefs.h
+
+fi
+
+# Check for Intel AVX512 intrinsics to do POPCNT calculations.
+#
+{ $as_echo "$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>
+#include <stdint.h>
+#include <stdlib.h>
+#include <string.h>
+int
+main ()
+{
+const uint64_t *buf = malloc((size_t)64);
+   uint64_t popcnt = 0;
+   __m512i accumulator = _mm512_setzero_si512();
+   const __m512i v = _mm512_loadu_si512((const __m512i *)buf);
+   const __m512i p = _mm512_popcnt_epi64(v);
+   memset(buf, 0, 64);
+   accumulator = _mm512_add_epi64(accumulator, p);
+   popcnt = _mm512_reduce_add_epi64(accumulator);
+   /* 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>
+#include <stdint.h>
+#include <stdlib.h>
+#include <string.h>
+int
+main ()
+{
+const uint64_t *buf = malloc((size_t)64);
+   uint64_t popcnt = 0;
+   __m512i accumulator = _mm512_setzero_si512();
+   const __m512i v = _mm512_loadu_si512((const __m512i *)buf);
+   const __m512i p = _mm512_popcnt_epi64(v);
+   memset(buf, 0, 64);
+   accumulator = _mm512_add_epi64(accumulator, p);
+   popcnt = _mm512_reduce_add_epi64(accumulator);
+   /* 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
+
+
+$as_echo "#define HAVE__AVX512_POPCNT 1" >>confdefs.h
+
+fi
+
+
 # Check for Intel SSE 4.2 intrinsics to do CRC calculations.
 #
 # First check if the _mm_crc32_u8 and _mm_crc32_u64 intrinsics can be used
diff --git a/configure.ac b/configure.ac
index 57f734879e..3c741d457d 100644
--- a/configure.ac
+++ b/configure.ac
@@ -2052,6 +2052,18 @@ if test x"$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"$pgac_cv__get_cpuid_count" = x"yes"; then
+  AC_DEFINE(HAVE__GET_CPUID_COUNT, 1, [Define to 1 if you have __get_cpuid.])
+fi
+
 AC_CACHE_CHECK([for __cpuid], [pgac_cv__cpuid],
 [AC_LINK_IFELSE([AC_LANG_PROGRAM([#include <intrin.h>],
   [[unsigned int exx[4] = {0, 0, 0, 0};
@@ -2063,6 +2075,38 @@ if test x"$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"$pgac_cv__cpuidex" = x"yes"; then
+  AC_DEFINE(HAVE__CPUIDEX, 1, [Define to 1 if you have __cpuidex.])
+fi
+
+AC_CACHE_CHECK([for __immintrin], [pgac_cv__immintrin],
+[AC_LINK_IFELSE([AC_LANG_PROGRAM([#include <immintrin.h>],
+  [[/* Don't exclude code so added return. */
+    return 1701;
+  ]])],
+  [pgac_cv__immintrin="yes"],
+  [pgac_cv__immintrin="no"])])
+if test x"$pgac_cv__immintrin" = x"yes"; then
+  AC_DEFINE(HAVE__IMMINTRIN, 1, [Define to 1 if you have immintrin.])
+fi
+
+# Check for Intel AVX512 intrinsics to do POPCNT calculations.
+#
+PGAC_AVX512_POPCNT_INTRINSICS([])
+if test x"$pgac_avx512_popcnt_intrinsics" != x"yes"; then
+  PGAC_AVX512_POPCNT_INTRINSICS([-mavx512vpopcntdq])
+  AC_DEFINE(HAVE__AVX512_POPCNT, 1, [Define to 1 if you have cpu
+                                     support for AVX512 POPCNT.])
+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 85788f9dd8..39480b4251 100644
--- a/meson.build
+++ b/meson.build
@@ -1773,6 +1773,37 @@ elif cc.links('''
 endif
 
 
+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
+
+
+# Check for header immintrin.h
+if cc.has_header('immintrin.h',
+    include_directories: postgres_inc, args: test_c_args)
+  cdata.set('HAVE__IMMINTRIN', 1,
+            description: 'Define to 1 if you have the immintrin.h header file.')
+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
@@ -2147,6 +2178,47 @@ elif host_cpu == 'ppc' or host_cpu == 'ppc64'
 endif
 
 
+###############################################################
+# AVX 512 POPCNT Intrinsic check
+###############################################################
+have_avx512_popcnt = false
+cflags_avx512_popcnt = []
+if host_cpu == 'x86_64'
+  test_flags = ['-mavx512vpopcntdq']
+  if host_system == 'windows'
+    test_flags = ['/arch:AVX512']
+  endif
+  prog = '''
+      #include <immintrin.h>
+      #include <stdint.h>
+      #include <stdlib.h>
+      #include <string.h>
+      void main(void)
+      {
+        const uint64_t *buf = malloc((size_t)64);
+        uint64_t popcnt = 0;
+        __m512i accumulator = _mm512_setzero_si512();
+        const __m512i v = _mm512_loadu_si512((const __m512i *)buf);
+        const __m512i p = _mm512_popcnt_epi64(v);
+        memset(buf, 0, 64);
+        accumulator = _mm512_add_epi64(accumulator, p);
+        popcnt = _mm512_reduce_add_epi64(accumulator);
+        /* return computed value, to prevent the above being optimized away */
+        return popcnt == 0;
+      }'''
+  if cc.links(prog, name: '_mm512_* methods with -mavx512vpopcntdq flag.',
+              args: test_c_args + test_flags)
+    have_avx512_popcnt = true
+    cdata.set('USE_AVX512_POPCNT_WITH_RUNTIME_CHECK', 1)
+    cdata.set('HAVE__AVX512_POPCNT', 1)
+    cflags_avx512_popcnt = test_flags
+  else
+    have_avx512_popcnt = false
+    cdata.set('USE_AVX512_POPCNT_WITH_RUNTIME_CHECK', 1)
+    cflags_avx512_popcnt = []
+  endif # compile/link test
+endif # host_cpu check
+
 
 ###############################################################
 # Library / OS tests
diff --git a/src/Makefile.global.in b/src/Makefile.global.in
index 8b3f8c24e0..089f49b7f3 100644
--- a/src/Makefile.global.in
+++ b/src/Makefile.global.in
@@ -263,6 +263,7 @@ CXXFLAGS_SL_MODULE = @CXXFLAGS_SL_MODULE@
 CFLAGS_UNROLL_LOOPS = @CFLAGS_UNROLL_LOOPS@
 CFLAGS_VECTORIZE = @CFLAGS_VECTORIZE@
 CFLAGS_CRC = @CFLAGS_CRC@
+CFLAGS_AVX512_POPCNT = @CFLAGS_AVX512_POPCNT@
 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..e4d56dee79 100644
--- a/src/include/pg_config.h.in
+++ b/src/include/pg_config.h.in
@@ -555,6 +555,18 @@
 /* Define to 1 if you have __cpuid. */
 #undef HAVE__CPUID
 
+/* Define to 1 if you have __get_cpuid_count. */
+#undef HAVE__GET_CPUID_COUNT
+
+/* Define to 1 if you have __get_cpuidex. */
+#undef HAVE__GET_CPUIDEX
+
+/* Define to 1 if you have  immintrin. */
+#undef HAVE__IMMINTRIN
+
+/* Define to 1 if you have AVX512. */
+#undef HAVE__AVX512_POPCNT
+
 /* Define to 1 if you have __get_cpuid. */
 #undef HAVE__GET_CPUID
 
diff --git a/src/include/port/pg_bitutils.h b/src/include/port/pg_bitutils.h
index 46bf4f0103..cc42ce49c9 100644
--- a/src/include/port/pg_bitutils.h
+++ b/src/include/port/pg_bitutils.h
@@ -300,19 +300,19 @@ pg_ceil_log2_64(uint64 num)
 
 #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 int	(*pg_popcount32) (uint32 word);
+extern PGDLLIMPORT int	(*pg_popcount64) (uint64 word);
+extern PGDLLIMPORT uint64 (*pg_popcount) (const char *buf, int bytes);
 #else
 /* Use a portable implementation -- no need for a function pointer. */
 extern int	pg_popcount32(uint32 word);
 extern int	pg_popcount64(uint64 word);
 
-#endif							/* TRY_POPCNT_FAST */
-
 /* Count the number of one-bits in a byte array */
 extern uint64 pg_popcount(const char *buf, int bytes);
 
+#endif							/* TRY_POPCNT_FAST */
+
 /*
  * Rotate the bits of "word" to the right/left by n bits.
  */
diff --git a/src/makefiles/meson.build b/src/makefiles/meson.build
index b0f4178b3d..ee3647282e 100644
--- a/src/makefiles/meson.build
+++ b/src/makefiles/meson.build
@@ -100,6 +100,7 @@ pgxs_kv = {
     ' '.join(cflags_no_decl_after_statement),
 
   'CFLAGS_CRC': ' '.join(cflags_crc),
+  'CFLAGS_AVX512_POPCNT': ' '.join(cflags_avx512_popcnt),
   'CFLAGS_UNROLL_LOOPS': ' '.join(unroll_loops_cflags),
   'CFLAGS_VECTORIZE': ' '.join(vectorize_cflags),
 
diff --git a/src/port/Makefile b/src/port/Makefile
index 12c56b0ba7..0b76926301 100644
--- a/src/port/Makefile
+++ b/src/port/Makefile
@@ -89,6 +89,11 @@ pg_crc32c_sse42.o: CFLAGS+=$(CFLAGS_CRC)
 pg_crc32c_sse42_shlib.o: CFLAGS+=$(CFLAGS_CRC)
 pg_crc32c_sse42_srv.o: CFLAGS+=$(CFLAGS_CRC)
 
+# Newer Intel processors can use AVX-512 POPCNT Capabilities (01/30/2024)
+pg_popcnt_x86_64_accel.o: CFLAGS+=$(CFLAGS_AVX512_POPCNT)
+pg_popcnt_x86_64_accel_shlib.o: CFLAGS+=$(CFLAGS_AVX512_POPCNT)
+pg_popcnt_x86_64_accel_srv.o: CFLAGS+=$(CFLAGS_AVX512_POPCNT)
+
 # all versions of pg_crc32c_armv8.o need CFLAGS_CRC
 pg_crc32c_armv8.o: CFLAGS+=$(CFLAGS_CRC)
 pg_crc32c_armv8_shlib.o: CFLAGS+=$(CFLAGS_CRC)
diff --git a/src/port/meson.build b/src/port/meson.build
index ed8828c739..d7930672cb 100644
--- a/src/port/meson.build
+++ b/src/port/meson.build
@@ -8,7 +8,6 @@ pgport_sources = [
   'path.c',
   'pg_bitutils.c',
   'pg_popcnt_choose.c',
-  'pg_popcnt_x86_64_accel.c',
   'pg_strong_random.c',
   'pgcheckdir.c',
   'pgmkdirp.c',
@@ -86,6 +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_popcnt_x86_64_accel', 'USE_AVX512_POPCNT_WITH_RUNTIME_CHECK', 'avx512'],
 
   # arm / aarch64
   ['pg_crc32c_armv8', 'USE_ARMV8_CRC32C'],
@@ -100,8 +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': cflags_avx512_popcnt}
+pgport_sources_cflags = {'crc': [], 'avx512': []}
 
 foreach f : replace_funcs_neg
   func = f.get(0)
diff --git a/src/port/pg_bitutils.c b/src/port/pg_bitutils.c
index d8b045d0a4..22c51c1679 100644
--- a/src/port/pg_bitutils.c
+++ b/src/port/pg_bitutils.c
@@ -98,6 +98,7 @@ const uint8 pg_number_of_ones[256] = {
 
 int	pg_popcount32_slow(uint32 word);
 int	pg_popcount64_slow(uint64 word);
+uint64 pg_popcount_slow(const char *buf, int bytes);
 
 /*
  * pg_popcount32_slow
@@ -170,6 +171,12 @@ pg_popcount64(uint64 word)
 	return pg_popcount64_slow(word);
 }
 
+uint64
+pg_popcount(const char *buf, int bytes)
+{
+	return pg_popcount_slow(buf, bytes);
+}
+
 #endif							/* !TRY_POPCNT_FAST */
 
 /*
@@ -177,7 +184,7 @@ pg_popcount64(uint64 word)
  *		Returns the number of 1-bits in buf
  */
 uint64
-pg_popcount(const char *buf, int bytes)
+pg_popcount_slow(const char *buf, int bytes)
 {
 	uint64		popcnt = 0;
 
diff --git a/src/port/pg_popcnt_choose.c b/src/port/pg_popcnt_choose.c
index 89fcf2609c..ac1344415d 100644
--- a/src/port/pg_popcnt_choose.c
+++ b/src/port/pg_popcnt_choose.c
@@ -26,18 +26,23 @@
 /* In pg_bitutils.c file */
 int	pg_popcount32_slow(uint32 word);
 int	pg_popcount64_slow(uint64 word);
+uint64 pg_popcount_slow(const char *buf, int bytes);
 
 #ifdef TRY_POPCNT_FAST
 static bool pg_popcount_available(void);
+static bool pg_popcount512_available(void);
 static int	pg_popcount32_choose(uint32 word);
 static int	pg_popcount64_choose(uint64 word);
+static uint64	pg_popcount_choose(const char *buf, int bytes);
 
 /* In pg_popcnt_*_accel source file. */
 int	pg_popcount32_fast(uint32 word);
 int	pg_popcount64_fast(uint64 word);
+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;
+uint64      (*pg_popcount) (const char *buf, int bytes) = pg_popcount_choose;
 #endif							/* TRY_POPCNT_FAST */
 
 #ifdef TRY_POPCNT_FAST
@@ -61,6 +66,52 @@ pg_popcount_available(void)
 	return (exx[2] & (1 << 23)) != 0;	/* POPCNT */
 }
 
+/*
+ * Return true if CPUID indicates that the AVX512_POPCNT instruction is
+ * available. This is similar to the method above; see
+ * https://en.wikipedia.org/wiki/CPUID#EAX=7,_ECX=0:_Extended_Features
+ *
+ * Finally, we make sure the xgetbv result is consistent with the CPUID
+ * results.
+ */
+static bool
+pg_popcount512_available(void)
+{
+	unsigned int exx[4] = {0, 0, 0, 0};
+
+	/* Check for AVX512VPOPCNTDQ and AVX512F */
+#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] & (0x00004000)) != 0 && (exx[1] & (0x00010000)) != 0)
+	{
+        /*
+         * CPUID succeeded, does the current running OS support the
+         * ZMM registers which are required for AVX512? This check is
+         * required to make sure an old OS on a new CPU is correctly
+         * checked or a VM hypervisor is not excluding AVX512 ZMM
+         * support in the VM; see "5.1.9 Detection of AVX Instructions"
+         * https://www.intel.com/content/www/us/en/content-details/671488/intel-64-and-ia-32-architectures-optimization-reference-manual-volume-1.html
+         */
+        uint64 xcr = 0;
+#ifdef _MSC_VER
+        uint64 highlow = _xgetbv(xcr);
+
+        return (highlow & 0xE0) != 0;
+#else
+        uint32 high;
+        uint32 low;
+
+        __asm__ __volatile__("xgetbv\t\n" : "=a"(low), "=d"(high) : "c"(xcr));
+        return (low & 0xE0) != 0;
+#endif
+    } /* POPCNT 512 */
+    return false;
+}
+
 /*
  * These functions get called on the first call to pg_popcount32 etc.
  * They detect whether we can use the asm implementations, and replace
@@ -69,15 +120,23 @@ pg_popcount_available(void)
  */
 static void setup_function_pointers()
 {
-	if (pg_popcount_available())
+	if (pg_popcount512_available())
 	{
 		pg_popcount32 = pg_popcount32_fast;
 		pg_popcount64 = pg_popcount64_fast;
+		pg_popcount = pg_popcount_fast;
+	}
+	else if (pg_popcount_available())
+	{
+		pg_popcount32 = pg_popcount32_fast;
+		pg_popcount64 = pg_popcount64_fast;
+		pg_popcount = pg_popcount_slow;
 	}
 	else
 	{
 		pg_popcount32 = pg_popcount32_slow;
 		pg_popcount64 = pg_popcount64_slow;
+		pg_popcount = pg_popcount_slow;
 	}
 }
 
@@ -94,4 +153,10 @@ pg_popcount64_choose(uint64 word)
 	setup_function_pointers();
 	return pg_popcount64(word);
 }
+
+static uint64
+pg_popcount_choose(const char* buf, int bytes) {
+	setup_function_pointers();
+	return pg_popcount(buf, bytes);
+}
 #endif							/* TRY_POPCNT_FAST */
diff --git a/src/port/pg_popcnt_x86_64_accel.c b/src/port/pg_popcnt_x86_64_accel.c
index 2e9b2ee774..ecc07afd37 100644
--- a/src/port/pg_popcnt_x86_64_accel.c
+++ b/src/port/pg_popcnt_x86_64_accel.c
@@ -14,8 +14,14 @@
 
 #include "port/pg_bitutils.h"
 
+#if defined(HAVE__IMMINTRIN)
+#include <immintrin.h>
+#endif
+
 int pg_popcount32_fast(uint32 word);
 int pg_popcount64_fast(uint64 word);
+uint64 pg_popcount_fast(const char *buf, int bytes);
+uint64 pg_popcount_slow(const char *buf, int bytes);
 
 #ifdef TRY_POPCNT_FAST
 /*
@@ -52,4 +58,32 @@ __asm__ __volatile__(" popcntq %1,%0\n":"=q"(res):"rm"(word):"cc");
 #endif
 }
 
-#endif							/* TRY_POPCNT_FAST */
+/*
+ * Use AVX-512 Intrinsics for supported Intel CPUs or fall back the the software
+ * loop in pg_bunutils.c and use the best 32 or 64 bit fast methods. If no fast
+ * methods are used this will fall back to __builtin_* or pure software.
+ */
+uint64
+pg_popcount_fast(const char *buf, int bytes)
+{
+    uint64 popcnt = 0;
+ #if defined(HAVE__IMMINTRIN) && HAVE__AVX512_POPCNT == 1
+   __m512i accumulator = _mm512_setzero_si512();
+
+    while (bytes >= 64)
+    {
+        const __m512i v = _mm512_loadu_si512((const __m512i *)buf);
+        const __m512i p = _mm512_popcnt_epi64(v);
+
+        accumulator = _mm512_add_epi64(accumulator, p);
+        bytes -= 64;
+        buf += 64;
+    }
+
+    popcnt = _mm512_reduce_add_epi64(accumulator);
+#endif 				/* defined(HAVE__IMMINTRIN) && HAVE__AVX512_POPCNT == 1 */
+
+    /* Process any remaining bytes */
+    return popcnt + pg_popcount_slow(buf, bytes);
+}
+#endif                              /* TRY_POPCNT_FAST */
-- 
2.34.1