[PATCH] aarch64: Improve strncmp for mutually misaligned inputs

[Wilco Dijkstra]

Hi,

Why not use lsr limit_wd, limit, 3? We have 3-operand shifts on AArch64!

--- a/sysdeps/aarch64/strncmp.S
+++ b/sysdeps/aarch64/strncmp.S
@@ -208,13 +208,15 @@ L(done):
        /* Align the SRC1 to a dword by doing a bytewise compare and then do
           the dword loop.  */
 L(try_misaligned_words):
-       mov     limit_wd, limit, lsr #3
+       mov     limit_wd, limit
+       lsr     limit_wd, limit_wd, #3
        cbz     count, L(do_misaligned)
 
        neg     count, count
        and     count, count, #7
        sub     limit, limit, count
-       mov     limit_wd, limit, lsr #3
+       mov     limit_wd, limit
+       lsr     limit_wd, limit_wd, #3

Also it seems to me it would be far easier to subtract 8 from limit in the main loop.
This means we don't ever need limit_wd, and avoids having to do this later:

        /* We found a difference or a NULL before the limit was reached.  */
        and     limit, limit, #7
        cbz     limit, L(not_limit)

Wilco