Micro-optimize AllocSetFreeIndex() by reference to pg_bitutils code.

Use __builtin_clz() where available.  Where it isn't, we can still win
a little by using the pg_leftmost_one_pos[] lookup table instead of
having a private table.

Also drop the initial right shift by ALLOC_MINBITS in favor of
subtracting ALLOC_MINBITS from the leftmost-one-pos result.  This
is a win because the compiler can fold that adjustment into other
constants it'd have to add anyway, making the shift-removal free.

Also, we can explain this coding as an unrolled form of
pg_leftmost_one_pos32(), even though that's a bit ahistorical
since it long predates pg_bitutils.h.

John Naylor, with some cosmetic adjustments by me

Discussion: https://postgr.es/m/CACPNZCuNUGMxjK7WTn_=WZnRbfASDdBxmjsVf2+m9MdmeNw_sg@mail.gmail.com

Author: tglsfdc

src/backend/utils/mmgr/aset.c

@@ -46,6 +46,7 @@
 
 #include "postgres.h"
 
+#include "port/pg_bitutils.h"
 #include "utils/memdebug.h"
 #include "utils/memutils.h"
 
@@ -297,18 +298,6 @@ static const MemoryContextMethods AllocSetMethods = {
 #endif
 };
 
-/*
- * Table for AllocSetFreeIndex
- */
-#define LT16(n) n, n, n, n, n, n, n, n, n, n, n, n, n, n, n, n
-
-static const unsigned char LogTable256[256] =
-{
-	0, 1, 2, 2, 3, 3, 3, 3, 4, 4, 4, 4, 4, 4, 4, 4,
-	LT16(5), LT16(6), LT16(6), LT16(7), LT16(7), LT16(7), LT16(7),
-	LT16(8), LT16(8), LT16(8), LT16(8), LT16(8), LT16(8), LT16(8), LT16(8)
-};
-
 /* ----------
  * Debug macros
  * ----------
@@ -337,24 +326,41 @@ static inline int
 AllocSetFreeIndex(Size size)
 {
 	int			idx;
-	unsigned int t,
-				tsize;
 
 	if (size > (1 << ALLOC_MINBITS))
 	{
-		tsize = (size - 1) >> ALLOC_MINBITS;
-
-		/*
-		 * At this point we need to obtain log2(tsize)+1, ie, the number of
-		 * not-all-zero bits at the right.  We used to do this with a
-		 * shift-and-count loop, but this function is enough of a hotspot to
-		 * justify micro-optimization effort.  The best approach seems to be
-		 * to use a lookup table.  Note that this code assumes that
-		 * ALLOCSET_NUM_FREELISTS <= 17, since we only cope with two bytes of
-		 * the tsize value.
+		/*----------
+		 * At this point we must compute ceil(log2(size >> ALLOC_MINBITS)).
+		 * This is the same as
+		 *		pg_leftmost_one_pos32((size - 1) >> ALLOC_MINBITS) + 1
+		 * or equivalently
+		 *		pg_leftmost_one_pos32(size - 1) - ALLOC_MINBITS + 1
+		 *
+		 * However, rather than just calling that function, we duplicate the
+		 * logic here, allowing an additional optimization.  It's reasonable
+		 * to assume that ALLOC_CHUNK_LIMIT fits in 16 bits, so we can unroll
+		 * the byte-at-a-time loop in pg_leftmost_one_pos32 and just handle
+		 * the last two bytes.
+		 *
+		 * Yes, this function is enough of a hot-spot to make it worth this
+		 * much trouble.
+		 *----------
 		 */
+#ifdef HAVE__BUILTIN_CLZ
+		idx = 31 - __builtin_clz((uint32) size - 1) - ALLOC_MINBITS + 1;
+#else
+		uint32		t,
+					tsize;
+
+		/* Statically assert that we only have a 16-bit input value. */
+		StaticAssertStmt(ALLOC_CHUNK_LIMIT < (1 << 16),
+						 "ALLOC_CHUNK_LIMIT must be less than 64kB");
+
+		tsize = size - 1;
 		t = tsize >> 8;
-		idx = t ? LogTable256[t] + 8 : LogTable256[tsize];
+		idx = t ? pg_leftmost_one_pos[t] + 8 : pg_leftmost_one_pos[tsize];
+		idx -= ALLOC_MINBITS - 1;
+#endif
 
 		Assert(idx < ALLOCSET_NUM_FREELISTS);
 	}