Use __attribute__((target(...))) for AVX-512 support.

Presently, we check for compiler support for the required
intrinsics both with and without extra compiler flags (e.g.,
-mxsave), and then depending on the results of those checks, we
pick which files to compile with which flags.  This is tedious and
complicated, and it results in unsustainable coding patterns such
as separate files for each portion of code may need to be built
with different compiler flags.

This commit introduces support for __attribute__((target(...))) and
uses it for the AVX-512 code.  This simplifies both the
configure-time checks and the build scripts, and it allows us to
place the functions that use the intrinsics in files that we
otherwise do not want to build with special CPU instructions.  We
are careful to avoid using __attribute__((target(...))) on
compilers that do not understand it, but we still perform the
configure-time checks in case the compiler allows using the
intrinsics without it (e.g., MSVC).

A similar change could likely be made for some of the CRC-32C code,
but that is left as a future exercise.

Suggested-by: Andres Freund
Reviewed-by: Raghuveer Devulapalli, Andres Freund
Discussion: https://postgr.es/m/20240731205254.vfpap7uxwmebqeaf%40awork3.anarazel.de

1 files changed, 41 insertions, 126 deletions

diff --git a/configure b/configure
index 6e256b417b9..3a7332f8349 100755
--- a/configure
+++ b/configure
@@ -647,9 +647,6 @@ MSGFMT_FLAGS
 MSGFMT
 PG_CRC32C_OBJS
 CFLAGS_CRC
-PG_POPCNT_OBJS
-CFLAGS_POPCNT
-CFLAGS_XSAVE
 LIBOBJS
 OPENSSL
 ZSTD
@@ -17272,185 +17269,103 @@ 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 :
+{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for _xgetbv" >&5
+$as_echo_n "checking for _xgetbv... " >&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
+  cat confdefs.h - <<_ACEOF >conftest.$ac_ext
 /* end confdefs.h.  */
 #include <immintrin.h>
+    #if defined(__has_attribute) && __has_attribute (target)
+    __attribute__((target("xsave")))
+    #endif
+    static int xsave_test(void)
+    {
+      return _xgetbv(0) & 0xe0;
+    }
 int
 main ()
 {
-return _xgetbv(0) & 0xe0;
+return xsave_test();
   ;
   return 0;
 }
 _ACEOF
 if ac_fn_c_try_link "$LINENO"; then :
-  pgac_cv_xsave_intrinsics__mxsave=yes
+  pgac_cv_xsave_intrinsics=yes
 else
-  pgac_cv_xsave_intrinsics__mxsave=no
+  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: $pgac_cv_xsave_intrinsics__mxsave" >&5
-$as_echo "$pgac_cv_xsave_intrinsics__mxsave" >&6; }
-if test x"$pgac_cv_xsave_intrinsics__mxsave" = x"yes"; then
-  CFLAGS_XSAVE="-mxsave"
+{ $as_echo "$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
   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 AVX-512 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 :
+  { $as_echo "$as_me:${as_lineno-$LINENO}: checking for _mm512_popcnt_epi64" >&5
+$as_echo_n "checking for _mm512_popcnt_epi64... " >&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
+  cat confdefs.h - <<_ACEOF >conftest.$ac_ext
 /* end confdefs.h.  */
 #include <immintrin.h>
+    #if defined(__has_attribute) && __has_attribute (target)
+    __attribute__((target("avx512vpopcntdq","avx512bw")))
+    #endif
+    static int popcount_test(void)
+    {
+      const char buf[sizeof(__m512i)];
+      PG_INT64_TYPE popcnt = 0;
+      __m512i accum = _mm512_setzero_si512();
+      const __m512i val = _mm512_maskz_loadu_epi8((__mmask64) 0xf0f0f0f0f0f0f0f0, (const __m512i *) buf);
+      const __m512i cnt = _mm512_popcnt_epi64(val);
+      accum = _mm512_add_epi64(accum, cnt);
+      popcnt = _mm512_reduce_add_epi64(accum);
+      return (int) popcnt;
+    }
 int
 main ()
 {
-const char buf[sizeof(__m512i)];
-   PG_INT64_TYPE popcnt = 0;
-   __m512i accum = _mm512_setzero_si512();
-   const __m512i val = _mm512_maskz_loadu_epi8((__mmask64) 0xf0f0f0f0f0f0f0f0, (const __m512i *) buf);
-   const __m512i cnt = _mm512_popcnt_epi64(val);
-   accum = _mm512_add_epi64(accum, cnt);
-   popcnt = _mm512_reduce_add_epi64(accum);
-   /* return computed value, to prevent the above being optimized away */
-   return popcnt == 0;
+return popcount_test();
   ;
   return 0;
 }
 _ACEOF
 if ac_fn_c_try_link "$LINENO"; then :
-  pgac_cv_avx512_popcnt_intrinsics__mavx512vpopcntdq__mavx512bw=yes
+  pgac_cv_avx512_popcnt_intrinsics=yes
 else
-  pgac_cv_avx512_popcnt_intrinsics__mavx512vpopcntdq__mavx512bw=no
+  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: $pgac_cv_avx512_popcnt_intrinsics__mavx512vpopcntdq__mavx512bw" >&5
-$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"
+{ $as_echo "$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
   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