v1-verify-utf8-sse-ascii.patch

diff --git a/src/common/wchar.c b/src/common/wchar.c
index 6e7d731e02..12b3a5e1a2 100644
--- a/src/common/wchar.c
+++ b/src/common/wchar.c
@@ -13,6 +13,10 @@
 #include "c.h"
 
 #include "mb/pg_wchar.h"
+#include "port/pg_bitutils.h"
+
+/* FIXME -- should go in src/include/port */
+#include <emmintrin.h>
 
 
 /*
@@ -1762,6 +1766,80 @@ pg_utf8_verifystr(const unsigned char *s, int len)
 {
 	const unsigned char *start = s;
 
+#ifdef __x86_64__
+
+
+	const __m128i	zero = _mm_setzero_si128();
+	__m128i			chunk,
+					cmp;
+
+	const int		chunk_size = sizeof(__m128i);
+	int				zero_mask,
+					highbit_mask,
+					ascii_count,
+					remainder;
+
+	while (len >= chunk_size)
+	{
+		/* load next chunk */
+		chunk = _mm_loadu_si128((const __m128i *) s);
+
+		/* first detect any zero bytes */
+		cmp = _mm_cmpeq_epi8(chunk, zero);
+		zero_mask = _mm_movemask_epi8(cmp);
+
+		/* if there is a zero byte, let the slow path encounter it */
+		if (zero_mask)
+			break;
+
+		/* now check for non-ascii bytes */
+		highbit_mask = _mm_movemask_epi8(chunk);
+
+		if (!highbit_mask)
+		{
+			/* all ascii, so advance to the next chunk */
+			s += chunk_size;
+			len -= chunk_size;
+			continue;
+		}
+
+		/*
+		 * if not all ascii, maybe there is a solid block of ascii
+		 * at the beginning of the chunk. if so, skip it
+		 */
+		ascii_count = pg_rightmost_one_pos32(highbit_mask);
+
+		s += ascii_count;
+		len -= ascii_count;
+		remainder = chunk_size - ascii_count;
+
+		/* found non-ascii, so handle the remainder in the normal way */
+		while (remainder > 0)
+		{
+			int			l;
+
+			/*
+			 * fast path for ASCII-subset characters
+			 * we already know they're non-zero
+			 */
+			if (!IS_HIGHBIT_SET(*s))
+				l = 1;
+			else
+			{
+				l = pg_utf8_verifychar(s, len);
+				if (l == -1)
+					goto finish;
+			}
+			s += l;
+			len -= l;
+			remainder -= l;
+
+		}
+	}
+
+#endif							/* __x86_64__ */
+
+	/* handle last few bytes */
 	while (len > 0)
 	{
 		int			l;
@@ -1770,19 +1848,20 @@ pg_utf8_verifystr(const unsigned char *s, int len)
 		if (!IS_HIGHBIT_SET(*s))
 		{
 			if (*s == '\0')
-				break;
+				goto finish;
 			l = 1;
 		}
 		else
 		{
 			l = pg_utf8_verifychar(s, len);
 			if (l == -1)
-				break;
+				goto finish;
 		}
 		s += l;
 		len -= l;
 	}
 
+finish:
 	return s - start;
 }