Make use of compiler builtins and/or assembly for CLZ, CTZ, POPCNT.

Test for the compiler builtins __builtin_clz, __builtin_ctz, and
__builtin_popcount, and make use of these in preference to
handwritten C code if they're available.  Create src/port
infrastructure for "leftmost one", "rightmost one", and "popcount"
so as to centralize these decisions.

On x86_64, __builtin_popcount generally won't make use of the POPCNT
opcode because that's not universally supported yet.  Provide code
that checks CPUID and then calls POPCNT via asm() if available.
This requires indirecting through a function pointer, which is
an annoying amount of overhead for a one-instruction operation,
but it's probably not worth working harder than this for our
current use-cases.

I'm not sure we've found all the existing places that could profit
from this new infrastructure; but we at least touched all the
ones that used copied-and-pasted versions of the bitmapset.c code,
and got rid of multiple copies of the associated constant arrays.

While at it, replace c-compiler.m4's one-per-builtin-function
macros with a single one that can handle all the cases we need
to worry about so far.  Also, because I'm paranoid, make those
checks into AC_LINK checks rather than just AC_COMPILE; the
former coding failed to verify that libgcc has support for the
builtin, in cases where it's not inline code.

David Rowley, Thomas Munro, Alvaro Herrera, Tom Lane

Discussion: https://postgr.es/m/CAKJS1f9WTAGG1tPeJnD18hiQW5gAk59fQ6WK-vfdAKEHyRg2RA@mail.gmail.com

1 files changed, 4 insertions, 27 deletions

diff --git a/src/backend/utils/adt/tsgistidx.c b/src/backend/utils/adt/tsgistidx.c
index a1987936467..4f256260fd1 100644
--- a/src/backend/utils/adt/tsgistidx.c
+++ b/src/backend/utils/adt/tsgistidx.c
@@ -16,6 +16,7 @@
 
 #include "access/gist.h"
 #include "access/tuptoaster.h"
+#include "port/pg_bitutils.h"
 #include "tsearch/ts_utils.h"
 #include "utils/builtins.h"
 #include "utils/pg_crc.h"
@@ -70,26 +71,6 @@ typedef struct
 #define GETARR(x)	( (int32*)( (char*)(x)+GTHDRSIZE ) )
 #define ARRNELEM(x) ( ( VARSIZE(x) - GTHDRSIZE )/sizeof(int32) )
 
-/* Number of one-bits in an unsigned byte */
-static const uint8 number_of_ones[256] = {
-	0, 1, 1, 2, 1, 2, 2, 3, 1, 2, 2, 3, 2, 3, 3, 4,
-	1, 2, 2, 3, 2, 3, 3, 4, 2, 3, 3, 4, 3, 4, 4, 5,
-	1, 2, 2, 3, 2, 3, 3, 4, 2, 3, 3, 4, 3, 4, 4, 5,
-	2, 3, 3, 4, 3, 4, 4, 5, 3, 4, 4, 5, 4, 5, 5, 6,
-	1, 2, 2, 3, 2, 3, 3, 4, 2, 3, 3, 4, 3, 4, 4, 5,
-	2, 3, 3, 4, 3, 4, 4, 5, 3, 4, 4, 5, 4, 5, 5, 6,
-	2, 3, 3, 4, 3, 4, 4, 5, 3, 4, 4, 5, 4, 5, 5, 6,
-	3, 4, 4, 5, 4, 5, 5, 6, 4, 5, 5, 6, 5, 6, 6, 7,
-	1, 2, 2, 3, 2, 3, 3, 4, 2, 3, 3, 4, 3, 4, 4, 5,
-	2, 3, 3, 4, 3, 4, 4, 5, 3, 4, 4, 5, 4, 5, 5, 6,
-	2, 3, 3, 4, 3, 4, 4, 5, 3, 4, 4, 5, 4, 5, 5, 6,
-	3, 4, 4, 5, 4, 5, 5, 6, 4, 5, 5, 6, 5, 6, 6, 7,
-	2, 3, 3, 4, 3, 4, 4, 5, 3, 4, 4, 5, 4, 5, 5, 6,
-	3, 4, 4, 5, 4, 5, 5, 6, 4, 5, 5, 6, 5, 6, 6, 7,
-	3, 4, 4, 5, 4, 5, 5, 6, 4, 5, 5, 6, 5, 6, 6, 7,
-	4, 5, 5, 6, 5, 6, 6, 7, 5, 6, 6, 7, 6, 7, 7, 8
-};
-
 static int32 sizebitvec(BITVECP sign);
 
 Datum
@@ -503,12 +484,7 @@ gtsvector_same(PG_FUNCTION_ARGS)
 static int32
 sizebitvec(BITVECP sign)
 {
-	int32		size = 0,
-				i;
-
-	LOOPBYTE
-		size += number_of_ones[(unsigned char) sign[i]];
-	return size;
+	return pg_popcount(sign, SIGLEN);
 }
 
 static int
@@ -521,7 +497,8 @@ hemdistsign(BITVECP a, BITVECP b)
 	LOOPBYTE
 	{
 		diff = (unsigned char) (a[i] ^ b[i]);
-		dist += number_of_ones[diff];
+		/* Using the popcount functions here isn't likely to win */
+		dist += pg_number_of_ones[diff];
 	}
 	return dist;
 }