Fix performance issue in misaligned strcpy.

diff --git a/ChangeLog b/ChangeLog
index 61f2fcd..f1c965e 100644 (file)
--- a/ChangeLog
+++ b/ChangeLog
@@ -1,3 +1,8 @@
+2014-08-07  Wilco Dijkstra  <wdijkstr@arm.com>
+
+       * sysdeps/arm/armv6/strcpy.S (strcpy):
+       Fix performance issue in misaligned cases.
+
 2014-08-05  Adhemerval Zanella  <azanella@linux.vnet.ibm.com>
 
        * sysdeps/unix/sysv/linux/powerpc/bits/ioctl-types.h (struct winsize):

diff --git a/sysdeps/arm/armv6/strcpy.S b/sysdeps/arm/armv6/strcpy.S
index 833a83c..67bd9d8 100644 (file)
--- a/sysdeps/arm/armv6/strcpy.S
+++ b/sysdeps/arm/armv6/strcpy.S
@@ -159,7 +159,7 @@ ENTRY (strcpy)
        @ Prologue to unaligned loop.  Seed shifted non-zero bytes.
        uqsub8  r4, r7, r2              @ Find EOS
        uqsub8  r5, r7, r3
-       mvns    r4, r4                  @ EOS in first word?
+       cmp     r4, #0                  @ EOS in first word?
        it      ne
        subne   r1, r1, #8
        bne     .Lbyte_loop
@@ -179,7 +179,7 @@ ENTRY (strcpy)
        @ Rotated unaligned copy loop.  The tail of the prologue is
        @ shared with the loop itself.
        .balign 8
-1:     mvns    r5, r5                  @ EOS in second word?
+1:     cmp     r5, #0                  @ EOS in second word?
        bne     4f
        @ Combine first and second words
        orr     r2, r2, r3, lsh_gt #(\unalign*8)
@@ -194,7 +194,7 @@ ENTRY (strcpy)
        sfi_pld r1, #128
        uqsub8  r5, r7, r3
        sfi_pld r0, #128
-       mvns    r4, r4                  @ EOS in first word?
+       cmp     r4, #0                  @ EOS in first word?
        bne     3f
        @ Combine the leftover and the first word
        orr     r6, r6, r2, lsh_gt #(\unalign*8)