From 3b71dbc2310b338f5dd1d8e842d835fc615d849d Mon Sep 17 00:00:00 2001
From: James Bonfield <jkb@sanger.ac.uk>
Date: Tue, 24 Sep 2024 17:06:48 +0100
Subject: [PATCH] Replace home-brew string end searching with memchr.

With long aux tags the trival while loop can be suprisingly slow.

"while (s < end && *s) ++s;" isn't well vectorised or turned into
word-by-word processing by neither gcc nor clang, but these tricks are
used by the system memchr implementation.

An alternative could be this (used in my WIP VCF parser), which is
more optimised for relatively short strings.  Included here just for
potential future reference on systems with noddy memchr
implementations.

    #define haszero(x) (((x)-0x0101010101010101UL)&~(x)&0x8080808080808080UL)
    static inline char *memchr8(char *s, char sym, size_t len) {
        const uint64_t sym8 = sym * 0x0101010101010101UL;
        uint64_t *s8 = (uint64_t *)s;
        uint64_t *s8_end = (uint64_t *)(s+(len&~7));

        while (s8 < s8_end && !haszero(*s8 ^ sym8))
            s8++;

        // Precise identification
        char *s_end = s + len;
        s = (char *)s8;
        while (s < s_end && *s != sym) {
            s++;
        }

        return s < s_end ? s : NULL;
    }
---
 sam.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/sam.c b/sam.c
index 7e58da6e7..a96a6120d 100644
--- a/sam.c
+++ b/sam.c
@@ -4856,9 +4856,9 @@ static inline uint8_t *skip_aux(uint8_t *s, uint8_t *end)
     switch (size) {
     case 'Z':
     case 'H':
-        while (s < end && *s) ++s;
-        return s < end ? s + 1 : end;
-    case 'B':
+        s = memchr(s, 0, end-s);
+        return s ? s+1 : end;
+     case 'B':
         if (end - s < 5) return NULL;
         size = aux_type2size(*s); ++s;
         n = le_to_u32(s);