Remove uses of popcount builtins.

This commit replaces the implementations of pg_popcount{32,64} with
branchless ones in plain C.  While these new implementations do not
make use of more sophisticated population count instructions
available on some CPUs, testing indicates they perform well,
especially now that they are inlined.  Newer versions of popular
compilers will automatically replace these with special
instructions if possible, anyway.  A follow-up commit will replace
various loops over these functions with calls to pg_popcount(),
leaving us little reason to worry about micro-optimizing them
further.

Since this commit removes the only uses of the popcount builtins,
we can also remove the corresponding configuration checks.

Suggested-by: John Naylor <johncnaylorls@gmail.com>
Reviewed-by: John Naylor <johncnaylorls@gmail.com>
Discussion: https://postgr.es/m/CANWCAZY7R%2Biy%2Br9YM_sySNydHzNqUirx1xk0tB3ej5HO62GdgQ%40mail.gmail.com

diff --git a/configure b/configure
index 7e6d9cb21396ae482925f7a0a0645543fd740832..8f35310cd08755f20494f8a8a100e0855a5c49ed 100755 (executable)
--- a/configure
+++ b/configure
@@ -15939,44 +15939,6 @@ cat >>confdefs.h <<_ACEOF
 #define HAVE__BUILTIN_CTZ 1
 _ACEOF
 
-fi
-{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for __builtin_popcount" >&5
-$as_echo_n "checking for __builtin_popcount... " >&6; }
-if ${pgac_cv__builtin_popcount+:} false; then :
-  $as_echo_n "(cached) " >&6
-else
-  cat confdefs.h - <<_ACEOF >conftest.$ac_ext
-/* end confdefs.h.  */
-
-int
-call__builtin_popcount(unsigned int x)
-{
-    return __builtin_popcount(x);
-}
-int
-main ()
-{
-
-  ;
-  return 0;
-}
-_ACEOF
-if ac_fn_c_try_link "$LINENO"; then :
-  pgac_cv__builtin_popcount=yes
-else
-  pgac_cv__builtin_popcount=no
-fi
-rm -f core conftest.err conftest.$ac_objext \
-    conftest$ac_exeext conftest.$ac_ext
-fi
-{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $pgac_cv__builtin_popcount" >&5
-$as_echo "$pgac_cv__builtin_popcount" >&6; }
-if test x"${pgac_cv__builtin_popcount}" = xyes ; then
-
-cat >>confdefs.h <<_ACEOF
-#define HAVE__BUILTIN_POPCOUNT 1
-_ACEOF
-
 fi
 # __builtin_frame_address may draw a diagnostic for non-constant argument,
 # so it needs a different test function.

diff --git a/configure.ac b/configure.ac
index f77ced6ddea0479c46aab7af7e6dc3c30efb41ec..0bad016f01c8a0f7350bc9d0975f43b60c139972 100644 (file)
--- a/configure.ac
+++ b/configure.ac
@@ -1865,7 +1865,6 @@ PGAC_CHECK_BUILTIN_FUNC([__builtin_bswap64], [long int x])
 # We assume that we needn't test all widths of these explicitly:
 PGAC_CHECK_BUILTIN_FUNC([__builtin_clz], [unsigned int x])
 PGAC_CHECK_BUILTIN_FUNC([__builtin_ctz], [unsigned int x])
-PGAC_CHECK_BUILTIN_FUNC([__builtin_popcount], [unsigned int x])
 # __builtin_frame_address may draw a diagnostic for non-constant argument,
 # so it needs a different test function.
 PGAC_CHECK_BUILTIN_FUNC_PTR([__builtin_frame_address], [0])

diff --git a/meson.build b/meson.build
index ebfb85e93e5f5f4116bb4db7802c11853e7ea6cc..83d1f06b528679facde66b523aed3bff22a19790 100644 (file)
--- a/meson.build
+++ b/meson.build
@@ -2006,7 +2006,6 @@ builtins = [
   'ctz',
   'constant_p',
   'frame_address',
-  'popcount',
   'unreachable',
 ]
 

diff --git a/src/include/pg_config.h.in b/src/include/pg_config.h.in
index 3824a5571bb63c8db6c2192626812143f57a063b..af08c5a7eb81eefdd0440d32e23b332fd08e4331 100644 (file)
--- a/src/include/pg_config.h.in
+++ b/src/include/pg_config.h.in
@@ -526,9 +526,6 @@
 /* Define to 1 if your compiler understands __builtin_$op_overflow. */
 #undef HAVE__BUILTIN_OP_OVERFLOW
 
-/* Define to 1 if your compiler understands __builtin_popcount. */
-#undef HAVE__BUILTIN_POPCOUNT
-
 /* Define to 1 if your compiler understands __builtin_types_compatible_p. */
 #undef HAVE__BUILTIN_TYPES_COMPATIBLE_P
 

diff --git a/src/include/port/pg_bitutils.h b/src/include/port/pg_bitutils.h
index 789663edd93040dedbab8a73341437a4b727d13d..0bca559caaa1ef03af777353588db569f5e7c75a 100644 (file)
--- a/src/include/port/pg_bitutils.h
+++ b/src/include/port/pg_bitutils.h
@@ -297,51 +297,41 @@ extern uint64 pg_popcount_masked_optimized(const char *buf, int bytes, bits8 mas
 /*
  * pg_popcount32
  *             Return the number of 1 bits set in word
+ *
+ * Adapted from
+ * https://graphics.stanford.edu/~seander/bithacks.html#CountBitsSetParallel.
+ *
+ * Note that newer versions of popular compilers will automatically replace
+ * this with a special popcount instruction if possible, so we don't bother
+ * using builtin functions or intrinsics.
  */
 static inline int
 pg_popcount32(uint32 word)
 {
-#ifdef HAVE__BUILTIN_POPCOUNT
-       return __builtin_popcount(word);
-#else                                                  /* !HAVE__BUILTIN_POPCOUNT */
-       int                     result = 0;
-
-       while (word != 0)
-       {
-               result += pg_number_of_ones[word & 255];
-               word >>= 8;
-       }
-
-       return result;
-#endif                                                 /* HAVE__BUILTIN_POPCOUNT */
+       word -= (word >> 1) & 0x55555555;
+       word = (word & 0x33333333) + ((word >> 2) & 0x33333333);
+       return (((word + (word >> 4)) & 0xf0f0f0f) * 0x1010101) >> 24;
 }
 
 /*
  * pg_popcount64
  *             Return the number of 1 bits set in word
+ *
+ * Adapted from
+ * https://graphics.stanford.edu/~seander/bithacks.html#CountBitsSetParallel.
+ *
+ * Note that newer versions of popular compilers will automatically replace
+ * this with a special popcount instruction if possible, so we don't bother
+ * using builtin functions or intrinsics.
  */
 static inline int
 pg_popcount64(uint64 word)
 {
-#ifdef HAVE__BUILTIN_POPCOUNT
-#if SIZEOF_LONG == 8
-       return __builtin_popcountl(word);
-#elif SIZEOF_LONG_LONG == 8
-       return __builtin_popcountll(word);
-#else
-#error "cannot find integer of the same size as uint64_t"
-#endif
-#else                                                  /* !HAVE__BUILTIN_POPCOUNT */
-       int                     result = 0;
-
-       while (word != 0)
-       {
-               result += pg_number_of_ones[word & 255];
-               word >>= 8;
-       }
-
-       return result;
-#endif                                                 /* HAVE__BUILTIN_POPCOUNT */
+       word -= (word >> 1) & UINT64CONST(0x5555555555555555);
+       word = (word & UINT64CONST(0x3333333333333333)) +
+               ((word >> 2) & UINT64CONST(0x3333333333333333));
+       word = (word + (word >> 4)) & UINT64CONST(0xf0f0f0f0f0f0f0f);
+       return (word * UINT64CONST(0x101010101010101)) >> 56;
 }
 
 /*

diff --git a/src/port/pg_popcount_aarch64.c b/src/port/pg_popcount_aarch64.c
index f474ef45510aa5b056a3bd4f6a795638b838849d..b0f10ae07a4e346860deef3a55debb793d83cdc2 100644 (file)
--- a/src/port/pg_popcount_aarch64.c
+++ b/src/port/pg_popcount_aarch64.c
@@ -298,11 +298,6 @@ pg_popcount_masked_optimized(const char *buf, int bytes, bits8 mask)
 static inline int
 pg_popcount64_neon(uint64 word)
 {
-       /*
-        * For some compilers, __builtin_popcountl() already emits Neon
-        * instructions.  The line below should compile to the same code on those
-        * systems.
-        */
        return vaddv_u8(vcnt_u8(vld1_u8((const uint8 *) &word)));
 }