linux_dsm_epyc7002/arch/arc/lib/strlen.S
Vineet Gupta 5210d1e688 ARC: String library
Hand optimised asm code for ARC700 pipeline.
Originally written/optimized by Joern Rennecke

Signed-off-by: Vineet Gupta <vgupta@synopsys.com>
Cc: Joern Rennecke <joern.rennecke@embecosm.com>
2013-02-11 20:00:35 +05:30

84 lines
1.4 KiB
ArmAsm

/*
* Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
* published by the Free Software Foundation.
*/
#include <asm/linkage.h>
ARC_ENTRY strlen
or r3,r0,7
ld r2,[r3,-7]
ld.a r6,[r3,-3]
mov r4,0x01010101
; uses long immediate
#ifdef __LITTLE_ENDIAN__
asl_s r1,r0,3
btst_s r0,2
asl r7,r4,r1
ror r5,r4
sub r1,r2,r7
bic_s r1,r1,r2
mov.eq r7,r4
sub r12,r6,r7
bic r12,r12,r6
or.eq r12,r12,r1
and r12,r12,r5
brne r12,0,.Learly_end
#else /* BIG ENDIAN */
ror r5,r4
btst_s r0,2
mov_s r1,31
sub3 r7,r1,r0
sub r1,r2,r4
bic_s r1,r1,r2
bmsk r1,r1,r7
sub r12,r6,r4
bic r12,r12,r6
bmsk.ne r12,r12,r7
or.eq r12,r12,r1
and r12,r12,r5
brne r12,0,.Learly_end
#endif /* ENDIAN */
.Loop:
ld_s r2,[r3,4]
ld.a r6,[r3,8]
; stall for load result
sub r1,r2,r4
bic_s r1,r1,r2
sub r12,r6,r4
bic r12,r12,r6
or r12,r12,r1
and r12,r12,r5
breq r12,0,.Loop
.Lend:
and.f r1,r1,r5
sub.ne r3,r3,4
mov.eq r1,r12
#ifdef __LITTLE_ENDIAN__
sub_s r2,r1,1
bic_s r2,r2,r1
norm r1,r2
sub_s r0,r0,3
lsr_s r1,r1,3
sub r0,r3,r0
j_s.d [blink]
sub r0,r0,r1
#else /* BIG ENDIAN */
lsr_s r1,r1,7
mov.eq r2,r6
bic_s r1,r1,r2
norm r1,r1
sub r0,r3,r0
lsr_s r1,r1,3
j_s.d [blink]
add r0,r0,r1
#endif /* ENDIAN */
.Learly_end:
b.d .Lend
sub_s.ne r1,r1,r1
ARC_EXIT strlen